From 54732448eb933607bdcb11a457756741dc4e0b44 Mon Sep 17 00:00:00 2001 From: Hans Hagen Date: Mon, 30 Dec 2019 20:42:59 +0100 Subject: 2019-12-30 19:16:00 --- .../sources/general/manuals/bidi/bidi-contents.tex | 9 + .../sources/general/manuals/bidi/bidi-fonts.tex | 99 + .../general/manuals/bidi/bidi-introduction.tex | 53 + .../sources/general/manuals/bidi/bidi-lua.tex | 38 + .../sources/general/manuals/bidi/bidi-mixed.tex | 178 ++ .../general/manuals/bidi/bidi-numbering.tex | 19 + .../sources/general/manuals/bidi/bidi-style.tex | 123 + .../general/manuals/bidi/bidi-titlepage.tex | 33 + .../sources/general/manuals/bidi/bidi-vertical.tex | 18 + doc/context/sources/general/manuals/bidi/bidi.tex | 518 +--- .../manuals/luametatex/luametatex-callbacks.tex | 820 +++++++ .../manuals/luametatex/luametatex-differences.tex | 209 ++ .../manuals/luametatex/luametatex-enhancements.tex | 1781 ++++++++++++++ .../manuals/luametatex/luametatex-fonts.tex | 596 +++++ .../manuals/luametatex/luametatex-libraries.tex | 573 +++++ .../general/manuals/luametatex/luametatex-lua.tex | 224 ++ .../general/manuals/luametatex/luametatex-math.tex | 1585 ++++++++++++ .../manuals/luametatex/luametatex-metapost.tex | 479 ++++ .../luametatex/luametatex-modifications.tex | 440 ++++ .../manuals/luametatex/luametatex-nodes.tex | 2527 ++++++++++++++++++++ .../general/manuals/luametatex/luametatex-pdf.tex | 565 +++++ .../manuals/luametatex/luametatex-preamble.tex | 166 ++ .../manuals/luametatex/luametatex-primitives.tex | 392 +++ .../manuals/luametatex/luametatex-registers.tex | 47 + .../manuals/luametatex/luametatex-statistics.tex | 17 + .../general/manuals/luametatex/luametatex-tex.tex | 2477 +++++++++++++++++++ 26 files changed, 13488 insertions(+), 498 deletions(-) create mode 100644 doc/context/sources/general/manuals/bidi/bidi-contents.tex create mode 100644 doc/context/sources/general/manuals/bidi/bidi-fonts.tex create mode 100644 doc/context/sources/general/manuals/bidi/bidi-introduction.tex create mode 100644 doc/context/sources/general/manuals/bidi/bidi-lua.tex create mode 100644 doc/context/sources/general/manuals/bidi/bidi-mixed.tex create mode 100644 doc/context/sources/general/manuals/bidi/bidi-numbering.tex create mode 100644 doc/context/sources/general/manuals/bidi/bidi-style.tex create mode 100644 doc/context/sources/general/manuals/bidi/bidi-titlepage.tex create mode 100644 doc/context/sources/general/manuals/bidi/bidi-vertical.tex create mode 100644 doc/context/sources/general/manuals/luametatex/luametatex-callbacks.tex create mode 100644 doc/context/sources/general/manuals/luametatex/luametatex-differences.tex create mode 100644 doc/context/sources/general/manuals/luametatex/luametatex-enhancements.tex create mode 100644 doc/context/sources/general/manuals/luametatex/luametatex-fonts.tex create mode 100644 doc/context/sources/general/manuals/luametatex/luametatex-libraries.tex create mode 100644 doc/context/sources/general/manuals/luametatex/luametatex-lua.tex create mode 100644 doc/context/sources/general/manuals/luametatex/luametatex-math.tex create mode 100644 doc/context/sources/general/manuals/luametatex/luametatex-metapost.tex create mode 100644 doc/context/sources/general/manuals/luametatex/luametatex-modifications.tex create mode 100644 doc/context/sources/general/manuals/luametatex/luametatex-nodes.tex create mode 100644 doc/context/sources/general/manuals/luametatex/luametatex-pdf.tex create mode 100644 doc/context/sources/general/manuals/luametatex/luametatex-preamble.tex create mode 100644 doc/context/sources/general/manuals/luametatex/luametatex-primitives.tex create mode 100644 doc/context/sources/general/manuals/luametatex/luametatex-registers.tex create mode 100644 doc/context/sources/general/manuals/luametatex/luametatex-statistics.tex create mode 100644 doc/context/sources/general/manuals/luametatex/luametatex-tex.tex (limited to 'doc/context/sources/general') diff --git a/doc/context/sources/general/manuals/bidi/bidi-contents.tex b/doc/context/sources/general/manuals/bidi/bidi-contents.tex new file mode 100644 index 000000000..21c318dff --- /dev/null +++ b/doc/context/sources/general/manuals/bidi/bidi-contents.tex @@ -0,0 +1,9 @@ +% language=us + +\startcomponent bidi-contents + + \starttitle[title=Table of contents] + \placelist[chapter] + \stoptitle + +\stopcomponent diff --git a/doc/context/sources/general/manuals/bidi/bidi-fonts.tex b/doc/context/sources/general/manuals/bidi/bidi-fonts.tex new file mode 100644 index 000000000..bfedd8f47 --- /dev/null +++ b/doc/context/sources/general/manuals/bidi/bidi-fonts.tex @@ -0,0 +1,99 @@ +% language=us + +\startcomponent bidi-fonts + +\environment bidi-style + +\startchapter[title={Setting up fonts}] + +So let's see how Arabic and Hebrew come out: + +\startbuffer +The sentence \quotation {I have no clue what this means.} is translated (by +Google Translate) into \quotation {\ar \righttoleft ليس لدي أي فكرة عما يعنيه هذا.} +which is then translated back to \quotation {I have no idea what this means.} so +maybe arabic has no clue what a clue is. The suggested Arabic pronunciation is +\quotation {lays laday 'ayu fikrat eamaa yaenih hadha}. Hebrew also likes ideas +more: \quotation {\he \righttoleft אין לי מושג מה זה אומר}. +\stopbuffer + +\typebuffer + +\getbuffer + +According to Idris Hamid the Arabic should actually be this: \quotation {\ar +لَيْسَ لَدَيَّ أَيُّ فِكْرَةٍ عَمَّا يَعْنِيهِ هٰذَا} and the transliteration \quotation {Laysa +ladayya ayyu fikratin ʿammā yaʿnihi hādhā}. + +The \CONTEXT\ (or any \TEX) ecosystem deals with languages and fonts. Languages +(that relate to scripts) have specific characteristics, like running from right +to left, and fonts provide a repertoire of glyphs and features. There is no real +(standard) relationship between these. In for instance browsers, there are +automatic fallback systems for missing characters in a font: another font is +taken. These fallbacks are often not easy to tweak. + +In this document we use Dejavu and although that font has Arabic shapes in its +monospace variant, the serifs come without them (at least when I write this +down). Before we actually define the bodyfont we hook in some fallbacks. The +typescript for Dejavu has lines like this: + +\starttyping +\definefontsynonym + [SerifBoldItalic] + [name:dejavuserifbolditalic] + [features=default, + fallbacks=SerifBoldItalic] +\stoptyping + +This permits us to do this: + +\typebuffer[preamble-fonts] + +In addition we set up the languages: + +\typebuffer[preamble-languages] + +The following example demonstrates what the effects of these commands are: + +\startbuffer +{لَيْسَ لَدَيَّ أَيُّ فِكْرَةٍ عَمَّا يَعْنِيهِ هٰذَا.} +{אין לי מושג מה זה אומר.} +{\righttoleft لَيْسَ لَدَيَّ أَيُّ فِكْرَةٍ عَمَّا يَعْنِيهِ هٰذَا.} +{\righttoleft אין לי מושג מה זה אומר.} +{\ar \righttoleft لَيْسَ لَدَيَّ أَيُّ فِكْرَةٍ عَمَّا يَعْنِيهِ هٰذَا.} +{\he \righttoleft אין לי מושג מה זה אומר.} +{\ar لَيْسَ لَدَيَّ أَيُّ فِكْرَةٍ عَمَّا يَعْنِيهِ هٰذَا.} +{\he אין לי מושג מה זה אומר.} +\stopbuffer + +\typebuffer + +\startlines +\getbuffer +\stoplines + +In principle you can also rely on automatic direction changes, for instance +by using the following command: + +\starttyping +\setupdirections + [bidi=global, + method=three] +\stoptyping + +But that doesn't do a font switch for you, nor does it do any of the other +language related settings. It really helps if you properly tag your +document content, as in: + +\starttyping +{\ar لَيْسَ لَدَيَّ أَيُّ فِكْرَةٍ عَمَّا يَعْنِيهِ هٰذَا.} +{\he אין לי מושג מה זה אומר.} +\stoptyping + +One reason to set the \type {font} parameter for a language is that it will +activate the right features in a font. Instead of falling back on some default, +we can be very specific in what we want to enable. + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/bidi/bidi-introduction.tex b/doc/context/sources/general/manuals/bidi/bidi-introduction.tex new file mode 100644 index 000000000..5ea0f9879 --- /dev/null +++ b/doc/context/sources/general/manuals/bidi/bidi-introduction.tex @@ -0,0 +1,53 @@ +% language=us + +\startcomponent bidi-introduction + +\environment bidi-style + +\startchapter[title=Introduction] + +With \CONTEXT\ you can typeset in two directions: from left to right and from +right to left. In fact you can also combine these two directions, like this: + +\startbuffer +There are many {\righttoleft \maincolor \it scripts in use} and some run into the +other direction. However, there is {\righttoleft \maincolor \it no fixed relation +{\lefttoright \black \it between the} direction of the script} and cars being +driven left or right of the road. +\stopbuffer + +\typebuffer + +\getbuffer + +Even someone not familiar with right to left typesetting can see what happens +here, or not? In fact Luigi Scarso pointed out that the \type {fixed} reversed +into {\righttoleft \type {fixed}} but not in the example where {\bf fixed} +becomes {\righttoleft \bf fixed}. This signals an important property of the way +the text gets processed: you input something, at some points font features get +applied (like ligatures) and in the end the resulting glyph stream is reversed. +By that time the combination of {\bf f}+{\bf i} has become {\bf fi}! So, be +prepared for surprises. + +This manual is written by a left to right user so don't expect a manual on +semitic typesetting. Also don't expect a (yet) complete manual. I'll add whatever +comes to mind. This is not a manual about Hebrew or Arabic, if only because I +can't read any of those scripts (languages). I leave that to others to cover. + +This is work in progress and might always be! So expect errors and typos. As with +anything related to typesetting the truth about how it should be done and what +looks best is not absolute. So, the most we can offer is flexibility and the way +\CONTEXT\ is setup permits that. + +Of course this is not possible without input. When we moved to \CONTEXT\ \LMTX, +the bidi thread was picked up by Mohammad Hossein Bateni, Idris Samawi Hamid, +Wolfgang Schuster and myself. So, expect more! + +\startlines +Hans Hagen +Hasselt, NL +\stoplines + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/bidi/bidi-lua.tex b/doc/context/sources/general/manuals/bidi/bidi-lua.tex new file mode 100644 index 000000000..beb93b604 --- /dev/null +++ b/doc/context/sources/general/manuals/bidi/bidi-lua.tex @@ -0,0 +1,38 @@ +% language=us + +\startcomponent bidi-lua + +\environment bidi-style + +\startchapter[title={The \LUA\ interface}] + +We assume that you run \CONTEXT\ \MKIV\ in combination with \LUATEX. Direction +support in this engine has been improved over time. Originally the \OMEGA\ +(\ALEPH) direction model was used but in the meantime it has been stripped to the +basics, and what used to be so called whatsits (extension nodes) are now first +class nodes. Of the many directions only four are kept in \LUATEX\ and they are +indicated by three letters: + +\starttabulate[|l|l|l|] +\NC 0 \NC \type {TLT} \NC left to right \NC \NR +\NC 1 \NC \type {TRT} \NC right to left \NC \NR +\NC 2 \NC \type {LTL} \NC not used in context (obsolete) \NC \NR +\NC 3 \NC \type {RTT} \NC not used in context (obsolete) \NC \NR +\stoptabulate + +In \LUAMETATEX, and therefore \CONTEXT\ \LMTX\ we only have the first two. +Therefore in \LMTX\ you normally don't have to worry about checking for them at +the \LUA\ end because they are irrelevant for calculations (the vertical ones +swapped the horizontal and vertical progression). Also, when really needed, we +use the \type {direction} keys with numerical indicators, so zero for \type {l2r} +and one for \type {r2l}. These values are used for local par nodes as well as +direction nodes. In addition a direction node has a subtype: + +\starttabulate[|l|l|l|] +\NC 0 \NC \type {normal} \NC comparable to \type {+} \NC \NR +\NC 1 \NC \type {cancel} \NC comparable to \type {-} \NC \NR +\stoptabulate + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/bidi/bidi-mixed.tex b/doc/context/sources/general/manuals/bidi/bidi-mixed.tex new file mode 100644 index 000000000..851d6d8b4 --- /dev/null +++ b/doc/context/sources/general/manuals/bidi/bidi-mixed.tex @@ -0,0 +1,178 @@ +% language=us + +\startcomponent bidi-mixed + +\environment bidi-style + +\startchapter[title=A mixed layout] + +The typesetting engine normally works from left to right and top to bottom. Going +from right to left actually involved two decisions: + +\startitemize[packed] +\startitem the direction of the display elements, the paragraphs \stopitem +\startitem the direction of the inline text, the lines \stopitem +\stopitemize + +The first one is kept track of in a state variable. Every paragraph starts with +a node that carries, among other information, that state. This node is added +automatically and does not interfere with the typesetting. The inline direction +is more intrusive as it is marked by nodes that indicate the beginning and end +of a reversed strip. This mechanism is rather reliable and normally works out +well. Take this: + +\startbuffer +left {\righttoleft right} left +left{ \righttoleft right} left +left {\righttoleft right }left +left{ \righttoleft right }left +\stopbuffer + +\typebuffer + +You can see that we need to be careful with spaces as they can end up inside or +outside a substream and by swapping next to each other: + +\startlines +\getbuffer +\stoplines + +We can wrap the lines in boxes as in: + +\startbuffer +\hbox{left\space{\bf\righttoleft right}\space left} +\hbox{left{\bf\space \righttoleft right}\space left} +\hbox{left\space{\bf\righttoleft right\space}left} +\hbox{left{\bf\space\righttoleft right\space}left} +\stopbuffer + +\typebuffer + +\definecolor[ShineThrough][s=0,a=1,t=.2] + +When visualize the spaces we get this: + +\startlines\ShineThrough +\showmakeup[space,hbox]\getbuffer +\stoplines + +The space of a normal and bold font in the same family normally is the same but +let's mix with a larger size: + +\startbuffer +\hbox{left {\bfa\righttoleft right} left} +\hbox{left{\bfa\space \righttoleft right} left} +\hbox{left {\bfa\righttoleft right }left} +\hbox{left{\bfa\space\righttoleft right }left} +\stopbuffer + +\typebuffer + +Now we get the following. As you can see, it really matters where we put the +braces. + +\startlines +\ShineThrough\showmakeup[space,hbox]\getbuffer +\stoplines + +Once you are accustomed to tagging and \TEX\ you will probably not fall into +these traps. In \in {figure} [fig:spaces] we show a large version. + +\startplacefigure[location=top,title={Watch your spaces!},reference=fig:spaces] + \scale + [width=\hsize] + {\vbox{\ShineThrough\showmakeup[space,hbox]\getbuffer}} +\stopplacefigure + +The \type {\righttoleft} command actually has two meanings. This can best be seen +from an example. + +\startbuffer +\righttoleft \bf How will this come out? +\stopbuffer + +\typebuffer + +\start \getbuffer \par \stop + +\startbuffer +And \righttoleft \bf how will this come out? +\stopbuffer + +\typebuffer + +\start \getbuffer \par \stop + +When we start a paragraph (or in \TEX\ speak: when we are still in vertical mode) +the paragraph direction as well as the inline direction is set. Otherwise only +the inline direction is set. There are low level \TEX\ commands (primitives) to +set the direction but you can best {\em not} use these because we need to do a +bit more than that. + +There are quite some low level commands related to changing directions. Some deal +with the layout, some with boxes. We might provide more in the future. + +\starttabulate[|l|p|] +\FL +\NC \type {\lefttoright} \NC l2r dir node or paragraph property \NC \NR +\NC \type {\righttoleft} \NC r2l dir node or paragraph property \NC \NR +\NC \type {\checkedlefttoright} \NC l2r dir node or paragraph property (unless already set) \NC \NR +\NC \type {\checkedrighttoleft} \NC r2l dir node or paragraph property (unless already set) \NC \NR +\ML +\NC \type {\synchronizeinlinedirection} \NC pickup a (possibly) reset state \NC \NR +\NC \type {\synchronizelayoutdirection} \NC pickup a (possibly) reset state \NC \NR +\NC \type {\synchronizedisplaydirection} \NC pickup a (possibly) reset state \NC \NR +\ML +\NC \type {\righttolefthbox} \NC r2l \type {\hbox} \NC \NR +\NC \type {\lefttorighthbox} \NC l2r \type {\hbox} \NC \NR +\NC \type {\righttoleftvbox} \NC r2l \type {\vbox} \NC \NR +\NC \type {\lefttorightvbox} \NC l2r \type {\vbox} \NC \NR +\NC \type {\righttoleftvtop} \NC r2l \type {\vtop} \NC \NR +\NC \type {\lefttorightvtop} \NC l2r \type {\vtop} \NC \NR +\ML +\NC \type {\leftorrighthbox} \NC l2r or r2l \type {\hbox} \NC \NR +\NC \type {\leftorrightvbox} \NC l2r or r2l \type {\vbox} \NC \NR +\NC \type {\leftorrightvtop} \NC l2r or r2l \type {\vtop} \NC \NR +\ML +\NC \type {\autodirhbox} \NC l2r or r2l \type {\hbox} (a bit more clever) \NC \NR +\NC \type {\autodirvbox} \NC l2r or r2l \type {\vbox} (a bit more clever) \NC \NR +\NC \type {\autodirvtop} \NC l2r or r2l \type {\vtop} (a bit more clever) \NC \NR +\ML +\NC \type {\bidilre} \NC character \type {U+202A}, enforce l2r state \NC \NR +\NC \type {\bidirle} \NC character \type {U+202B}, enforce r2l state \NC \NR +\NC \type {\bidipop} \NC character \type {U+202C}, return to last state \NC \NR +\NC \type {\bidilro} \NC character \type {U+202D}, override l2r state \NC \NR +\NC \type {\bidirlo} \NC character \type {U+202E}, override r2l state \NC \NR +\NC \type {\lefttorightmark} \type {\lrm} \NC character \type {U+200E}, l2r indicator \NC \NR +\NC \type {\righttoleftmark} \type {\rlm} \NC character \type {U+200F}, r2l indicator \NC \NR +\ML +\NC \type {\dirlre} \NC switch to l2r mode using \type {\bidilre} or \lefttoright \NC \NR +\NC \type {\dirrle} \NC switch to r2l mode using \type {\bidirle} or \righttoleft \NC \NR +\NC \type {\dirlro} \NC enforce l2r mode using \type {\bidilro} or \lefttoright \NC \NR +\NC \type {\dirrlo} \NC enforce r2l mode using \type {\bidirlo} or \righttoleft \NC \NR +\ML +\NC \type {\naturalhbox} \NC a normal l2r \type {hbox} \NC \NR +\NC \type {\naturalvbox} \NC a normal l2r \type {vbox} \NC \NR +\NC \type {\naturalvtop} \NC a normal l2r \type {vtop} \NC \NR +\NC \type {\naturalhpack} \NC a normal l2r \type {hpack} \NC \NR +\NC \type {\naturalvpack} \NC a normal l2r \type {vpack} \NC \NR +\LL +\stoptabulate + +When we talk about layout, we mean the overall layout, concerning the document as +a whole. We can have a dominantly l2r, dominantly r2l or mixed setup. In a next +chapter we will give more details on the dominant setup. Here we stick to +mentioning that the document flow direction is set with + +\starttyping +\setupalign[r2l] % or r2l +\stoptyping + +When a command to setup an environment has a \type {align} parameter, the same +keywords can be uses as part of the specification. \footnote {We haven't tested +all situations and possible interferences. Just report anomalies to the mailing +list.} + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/bidi/bidi-numbering.tex b/doc/context/sources/general/manuals/bidi/bidi-numbering.tex new file mode 100644 index 000000000..c328d6a1a --- /dev/null +++ b/doc/context/sources/general/manuals/bidi/bidi-numbering.tex @@ -0,0 +1,19 @@ +% language=us + +\startcomponent bidi-numbering + +\environment bidi-style + +\startchapter[title={Numbering and positioning}] + +todo: columns (direction key), numbers (conversionsets), margins (begin/end), etc + +% \defineconversionset [\s!default] [] [numbers] +% \defineconversionset [\v!number] [] [numbers] +% \defineconversionset [\v!pagenumber] [] [numbers] +% \defineconversionset [\v!appendix:\s!default] [Romannumerals,Characters] [numbers] +% \defineconversionset [\v!formula] [numbers,characters] % no \v! ? + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/bidi/bidi-style.tex b/doc/context/sources/general/manuals/bidi/bidi-style.tex new file mode 100644 index 000000000..1ce4e3b79 --- /dev/null +++ b/doc/context/sources/general/manuals/bidi/bidi-style.tex @@ -0,0 +1,123 @@ +\startenvironment bidi-style + +\usemodule[abr-04] + +\dontcomplain + +\startbuffer[preamble-fonts] +\definefontfallback + [Serif] [scheherazaderegular*arabic] + [arabic] [force=yes,rscale=1.5] +\definefontfallback + [SerifBold] [scheherazadebold*arabic] + [arabic] [force=yes,rscale=1.5] +\definefontfallback + [SerifItalic] [scheherazaderegular*arabic] + [arabic] [force=yes,rscale=1.5] +\definefontfallback + [SerifBoldItalic] [scheherazadebold*arabic] + [arabic] [force=yes,rscale=1.5] + +\definefontfallback + [Serif] [sileot*hebrew] + [hebrew] [force=yes] +\definefontfallback + [SerifBold] [sileot*hebrew] + [hebrew] [force=yes] +\definefontfallback + [SerifItalic] [sileot*hebrew] + [hebrew] [force=yes] +\definefontfallback + [SerifBoldItalic] [sileot*hebrew] + [hebrew] [force=yes] + +\definefontfallback + [Mono] [almfixed*none] + [arabic] [force=yes] + +\definefontfallback + [Mono] [sileot*none] + [hebrew] [force=yes,factor=1] % factor forces a monospace + +\setupbodyfont + [dejavu,10pt] +\stopbuffer + +\startbuffer[preamble-languages] +\setuplanguage[ar][font=arabic,bidi=right] +\setuplanguage[he][font=hebrew,bidi=right] +\stopbuffer + +\getbuffer[preamble-fonts] +\getbuffer[preamble-languages] + +\setuplayout + [backspace=15mm, + topspace=15mm, + footer=0pt, + width=middle, + height=middle] + +% \setuptyping +% [color=middleblue] +% +% \setuptype +% [color=middleblue] + +\usemodule[scite] + +\setuptyping + [option=TEX] + +\setuptype + [option=TEX] + +\definecolor + [maincolor] + [middleblue] + +\setupwhitespace + [big] + +\setuphead + [color=darkyellow] + +\setuphead + [chapter] + [style=\bfc] + +\setuphead + [section] + [style=\bfb] + +\setuphead + [subsection] + [style=\bfa] + +%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% + +\startluacode + local report = logs.reporter("directions","check") + local line = 0 + function nodes.tracers.checkdirections(head) + line = line + 1 + report("line: %i",line) + for n in nodes.traverse_id(nodes.nodecodes.dir,head) do + report(" %s (%i,%i)",n.dir,n.subtype,n.direction) + end + return head, false + end + + nodes.tasks.appendaction("contributers","after","nodes.tracers.checkdirections") + nodes.tasks.disableaction("contributers","nodes.tracers.checkdirections") +\stopluacode + +\installtextracker + {directions.check} + {\ctxlua{nodes.tasks.enableaction("contributers","nodes.tracers.checkdirections")}} + {\ctxlua{nodes.tasks.disableaction("contributers","nodes.tracers.checkdirections")}} + +% \enabletrackers[directions.check] +% \disabletrackers[directions.check] + +\stopenvironment diff --git a/doc/context/sources/general/manuals/bidi/bidi-titlepage.tex b/doc/context/sources/general/manuals/bidi/bidi-titlepage.tex new file mode 100644 index 000000000..a80851aea --- /dev/null +++ b/doc/context/sources/general/manuals/bidi/bidi-titlepage.tex @@ -0,0 +1,33 @@ +\startcomponent bidi-titlepage + +\environment bidi-style + +\startMPpage + + picture p, q, r, s ; + + p := textext("l2r") xsized .9PaperWidth ; + q := textext("r2l") xsized .9PaperWidth ; + r := textext("a few tips") xsized .9PaperWidth ; + s := textext("\bf\ss hans\quad\space\quad hagen") xsized .5bbheight(p); + + p := p shifted - llcorner p ; + q := q shifted - llcorner q ; + r := r shifted - llcorner r ; + s := s shifted - llcorner s ; + + fill Page withcolor "darkyellow" ; + + p := p shifted (.05PaperWidth,ypart .5[ulcorner Page, urcorner Page]-1.1bbheight(p)) ; + q := q shifted (.05PaperWidth,ypart .5[ulcorner Page, urcorner Page]-1.1bbheight(p)-1.15bbheight(q)) ; + r := r shifted (.05PaperWidth,ypart .5[llcorner Page, lrcorner Page]+0.3bbheight(r)) ; + s := s shifted (.66PaperWidth,ypart .5[llcorner Page, lrcorner Page]+1.5bbheight(s)) ; + + draw p withcolor "lightgray" ; + draw q withcolor "lightgray" ; + draw r withcolor "middleblue" ; + draw s withcolor "lightgray" ; + +\stopMPpage + +\stopcomponent diff --git a/doc/context/sources/general/manuals/bidi/bidi-vertical.tex b/doc/context/sources/general/manuals/bidi/bidi-vertical.tex new file mode 100644 index 000000000..824d7a033 --- /dev/null +++ b/doc/context/sources/general/manuals/bidi/bidi-vertical.tex @@ -0,0 +1,18 @@ +% language=us + +\startcomponent bidi-vertical + +\environment bidi-style + +\startchapter[title={Going vertical}] + +Normally the term bidi is reserved for horizontal direction swapping but there is +no reason to limit our view to that. So, here I will spend some words on how we +can deal with vertical directions. + +{\em I will move some (not yet public) explanation from elsewhere to here in due +time.} + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/bidi/bidi.tex b/doc/context/sources/general/manuals/bidi/bidi.tex index fb3705a37..c6fedacdf 100644 --- a/doc/context/sources/general/manuals/bidi/bidi.tex +++ b/doc/context/sources/general/manuals/bidi/bidi.tex @@ -1,506 +1,28 @@ -% language=uk +% Because we cross a threshold in the amount of content the sources +% have been split into components. This is typical a manual that +% grows. Feel free to send suggestions and improvements. -% \showglyphs +\environment bidi-style -\usemodule[abr-04] +\startdocument -\dontcomplain + \component bidi-titlepage -\startbuffer[preamble-fonts] -\definefontfallback - [Serif] [scheherazaderegular*arabic] - [arabic] [force=yes,rscale=1.5] -\definefontfallback - [SerifBold] [scheherazadebold*arabic] - [arabic] [force=yes,rscale=1.5] -\definefontfallback - [SerifItalic] [scheherazaderegular*arabic] - [arabic] [force=yes,rscale=1.5] -\definefontfallback - [SerifBoldItalic] [scheherazadebold*arabic] - [arabic] [force=yes,rscale=1.5] + \startfrontmatter + \component bidi-contents + \component bidi-introduction + \stopfrontmatter -\definefontfallback - [Serif] [sileot*hebrew] - [hebrew] [force=yes] -\definefontfallback - [SerifBold] [sileot*hebrew] - [hebrew] [force=yes] -\definefontfallback - [SerifItalic] [sileot*hebrew] - [hebrew] [force=yes] -\definefontfallback - [SerifBoldItalic] [sileot*hebrew] - [hebrew] [force=yes] + \startbodymatter + \component bidi-fonts + \component bidi-mixed + \component bidi-numbering -\definefontfallback - [Mono] [almfixed*none] - [arabic] [force=yes] + % work in progress / dev: + \component bidi-tables -\definefontfallback - [Mono] [sileot*none] - [hebrew] [force=yes,factor=1] % factor forces a monospace + \component bidi-lua + \component bidi-vertical + \stopbodymatter -\setupbodyfont - [dejavu,10pt] -\stopbuffer - -\startbuffer[preamble-languages] -\setuplanguage[ar][font=arabic,bidi=right] -\setuplanguage[he][font=hebrew,bidi=right] -\stopbuffer - -\getbuffer[preamble-fonts] -\getbuffer[preamble-languages] - -\setuplayout - [backspace=15mm, - topspace=15mm, - footer=0pt, - width=middle, - height=middle] - -\setuptyping - [color=middleblue] - -\setuptype - [color=middleblue] - -\definecolor - [maincolor] - [middleblue] - -\setupwhitespace - [big] - -\setuphead - [color=darkyellow] - -\setuphead - [chapter] - [style=\bfc] - -\setuphead - [section] - [style=\bfb] - -\setuphead - [subsection] - [style=\bfa] - -%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% - -\startluacode - local report = logs.reporter("directions","check") - local line = 0 - function nodes.tracers.checkdirections(head) - line = line + 1 - report("line: %i",line) - for n in nodes.traverse_id(nodes.nodecodes.dir,head) do - report(" %s (%i,%i)",n.dir,n.subtype,n.direction) - end - return head, false - end - - nodes.tasks.appendaction("contributers","after","nodes.tracers.checkdirections") - nodes.tasks.disableaction("contributers","nodes.tracers.checkdirections") -\stopluacode - -\installtextracker - {directions.check} - {\ctxlua{nodes.tasks.enableaction("contributers","nodes.tracers.checkdirections")}} - {\ctxlua{nodes.tasks.disableaction("contributers","nodes.tracers.checkdirections")}} - -% \enabletrackers[directions.check] -% \disabletrackers[directions.check] - -%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% - -\starttext - -\startMPpage - - picture p, q, r, s ; - - p := textext("l2r") xsized .9PaperWidth ; - q := textext("r2l") xsized .9PaperWidth ; - r := textext("a few tips") xsized .9PaperWidth ; - s := textext("\bf\ss hans\quad\space\quad hagen") xsized .5bbheight(p); - - p := p shifted - llcorner p ; - q := q shifted - llcorner q ; - r := r shifted - llcorner r ; - s := s shifted - llcorner s ; - - fill Page withcolor "darkyellow" ; - - p := p shifted (.05PaperWidth,ypart .5[ulcorner Page, urcorner Page]-1.1bbheight(p)) ; - q := q shifted (.05PaperWidth,ypart .5[ulcorner Page, urcorner Page]-1.1bbheight(p)-1.15bbheight(q)) ; - r := r shifted (.05PaperWidth,ypart .5[llcorner Page, lrcorner Page]+0.3bbheight(r)) ; - s := s shifted (.66PaperWidth,ypart .5[llcorner Page, lrcorner Page]+1.5bbheight(s)) ; - - draw p withcolor "lightgray" ; - draw q withcolor "lightgray" ; - draw r withcolor "middleblue" ; - draw s withcolor "lightgray" ; - -\stopMPpage - -\startchapter[title=Introduction] - -With \CONTEXT\ you can typeset in two directions: from left to right and from -right to left. In fact you can also combine these two directions, like this: - -\startbuffer -There are many {\righttoleft \maincolor \it scripts in use} and some run into the -other direction. However, there is {\righttoleft \maincolor \it no fixed relation -{\lefttoright \black \it between the} direction of the script} and cars being -driven left or right of the road. -\stopbuffer - -\typebuffer - -\getbuffer - -Even someone not familiar with right to left typesetting can see what happens -here, or not? In fact Luigi Scarso pointed out that the \type {fixed} reversed -into {\righttoleft \type {fixed}} but not in the example where {\bf fixed} -becomes {\righttoleft \bf fixed}. This signals an important property of the way -the text gets processed: you input something, at some points font features get -applied (like ligatures) and in the end the resulting glyph stream is reversed. -By that time the combination of {\bf f}+{\bf i} has become {\bf fi}! So, be -prepared for surprises. - -This manual is written by a left to right user so don't expect a manual on -semitic typesetting. Also don't expect a (yet) complete manual. I'll add whatever -comes to mind. This is not a manual about Hebrew or Arabic, if only because I -can't read any of those scripts (languages). I leave that to others to cover. - -{\em This is work in progress! So expect errors and typos.} - -\startlines -Hans Hagen -Hasselt, NL -\stoplines - -\stopchapter - -\startchapter[title={Setting up fonts}] - -So let's see how Arabic and Hebrew come out: - -\startbuffer -The sentence \quotation {I have no clue what this means.} is translated (by -Google Translate) into \quotation {\ar \righttoleft ليس لدي أي فكرة عما يعنيه هذا.} -which is then translated back to \quotation {I have no idea what this means.} so -maybe arabic has no clue what a clue is. The suggested Arabic pronunciation is -\quotation {lays laday 'ayu fikrat eamaa yaenih hadha}. Hebrew also likes ideas -more: \quotation {\he \righttoleft אין לי מושג מה זה אומר}. -\stopbuffer - -\typebuffer - -\getbuffer - -According to Idris Hamid the Arabic should actually be this: \quotation {\ar -لَيْسَ لَدَيَّ أَيُّ فِكْرَةٍ عَمَّا يَعْنِيهِ هٰذَا} and the transliteration \quotation {Laysa -ladayya ayyu fikratin ʿammā yaʿnihi hādhā}. - -The \CONTEXT\ (or any \TEX) ecosystem deals with languages and fonts. Languages -(that relate to scripts) have specific characteristics, like running from right -to left, and fonts provide a repertoire of glyphs and features. There is no real -(standard) relationship between these. In for instance browsers, there are -automatic fallback systems for missing characters in a font: another font is -taken. These fallbacks are often not easy to tweak. - -In this document we use Dejavu and although that font has Arabic shapes in its -monospace variant, the serifs come without them (at least when I write this -down). Before we actually define the bodyfont we hook in some fallbacks. The -typescript for Dejavu has lines like this: - -\starttyping -\definefontsynonym - [SerifBoldItalic] - [name:dejavuserifbolditalic] - [features=default, - fallbacks=SerifBoldItalic] -\stoptyping - -This permits us to do this: - -\typebuffer[preamble-fonts] - -In addition we set up the languages: - -\typebuffer[preamble-languages] - -The following example demonstrates what the effects of these commands are: - -\startbuffer -{لَيْسَ لَدَيَّ أَيُّ فِكْرَةٍ عَمَّا يَعْنِيهِ هٰذَا.} -{אין לי מושג מה זה אומר.} -{\righttoleft لَيْسَ لَدَيَّ أَيُّ فِكْرَةٍ عَمَّا يَعْنِيهِ هٰذَا.} -{\righttoleft אין לי מושג מה זה אומר.} -{\ar \righttoleft لَيْسَ لَدَيَّ أَيُّ فِكْرَةٍ عَمَّا يَعْنِيهِ هٰذَا.} -{\he \righttoleft אין לי מושג מה זה אומר.} -{\ar لَيْسَ لَدَيَّ أَيُّ فِكْرَةٍ عَمَّا يَعْنِيهِ هٰذَا.} -{\he אין לי מושג מה זה אומר.} -\stopbuffer - -\typebuffer - -\startlines -\getbuffer -\stoplines - -In principle you can also rely on automatic direction changes, for instance -by using the following command: - -\starttyping -\setupdirections - [bidi=global, - method=three] -\stoptyping - -But that doesn't do a font switch for you, nor does it do any of the other -language related settings. It really helps if you properly tag your -document content, as in: - -\starttyping -{\ar لَيْسَ لَدَيَّ أَيُّ فِكْرَةٍ عَمَّا يَعْنِيهِ هٰذَا.} -{\he אין לי מושג מה זה אומר.} -\stoptyping - -One reason to set the \type {font} parameter for a language is that it will -activate the right features in a font. Instead of falling back on some default, -we can be very specific in what we want to enable. - -\stopchapter - -\startchapter[title=A mixed layout] - -The typesetting engine normally works from left to right and top to bottom. Going -from right to left actually involved two decisions: - -\startitemize[packed] -\startitem the direction of the display elements, the paragraphs \stopitem -\startitem the direction of the inline text, the lines \stopitem -\stopitemize - -The first one is kept track of in a state variable. Every paragraph starts with -a node that carries, among other information, that state. This node is added -automatically and does not interfere with the typesetting. The inline direction -is more intrusive as it is marked by nodes that indicate the beginning and end -of a reversed strip. This mechanism is rather reliable and normally works out -well. Take this: - -\startbuffer -left {\righttoleft right} left -left{ \righttoleft right} left -left {\righttoleft right }left -left{ \righttoleft right }left -\stopbuffer - -\typebuffer - -You can see that we need to be careful with spaces as they can end up inside or -outside a substream and by swapping next to each other: - -\startlines -\getbuffer -\stoplines - -We can wrap the lines in boxes as in: - -\startbuffer -\hbox{left\space{\bf\righttoleft right}\space left} -\hbox{left{\bf\space \righttoleft right}\space left} -\hbox{left\space{\bf\righttoleft right\space}left} -\hbox{left{\bf\space\righttoleft right\space}left} -\stopbuffer - -\typebuffer - -\definecolor[ShineThrough][s=0,a=1,t=.2] - -When visualize the spaces we get this: - -\startlines\ShineThrough -\showmakeup[space,hbox]\getbuffer -\stoplines - -The space of a normal and bold font in the same family normally is the same but -let's mix with a larger size: - -\startbuffer -\hbox{left {\bfa\righttoleft right} left} -\hbox{left{\bfa\space \righttoleft right} left} -\hbox{left {\bfa\righttoleft right }left} -\hbox{left{\bfa\space\righttoleft right }left} -\stopbuffer - -\typebuffer - -Now we get the following. As you can see, it really matters where we put the -braces. - -\startlines -\ShineThrough\showmakeup[space,hbox]\getbuffer -\stoplines - -Once you are accustomed to tagging and \TEX\ you will probably not fall into -these traps. In \in {figure} [fig:spaces] we show a large version. - -\startplacefigure[location=top,title={Watch your spaces!},reference=fig:spaces] - \scale - [width=\hsize] - {\vbox{\ShineThrough\showmakeup[space,hbox]\getbuffer}} -\stopplacefigure - - -The \type {\righttoleft} command actually has two meanings. This can best be seen -from an example. - -\startbuffer -\righttoleft \bf How will this come out? -\stopbuffer - -\typebuffer - -\start \getbuffer \par \stop - -\startbuffer -And \righttoleft \bf how will this come out? -\stopbuffer - -\typebuffer - -\start \getbuffer \par \stop - -When we start a paragraph (or in \TEX\ speak: when we are still in vertical mode) -the paragraph direction as well as the inline direction is set. Otherwise only -the inline direction is set. There are low level \TEX\ commands (primitives) to -set the direction but you can best {\em not} use these because we need to do a -bit more than that. - -There are quite some low level commands related to changing directions. Some deal -with the layout, some with boxes. We might provide more in the future. - -\starttabulate[|l|p|] -\FL -\NC \type {\lefttoright} \NC l2r dir node or paragraph property \NC \NR -\NC \type {\righttoleft} \NC r2l dir node or paragraph property \NC \NR -\NC \type {\checkedlefttoright} \NC l2r dir node or paragraph property (unless already set) \NC \NR -\NC \type {\checkedrighttoleft} \NC r2l dir node or paragraph property (unless already set) \NC \NR -\ML -\NC \type {\synchronizeinlinedirection} \NC pickup a (possibly) reset state \NC \NR -\NC \type {\synchronizelayoutdirection} \NC pickup a (possibly) reset state \NC \NR -\NC \type {\synchronizedisplaydirection} \NC pickup a (possibly) reset state \NC \NR -\ML -\NC \type {\righttolefthbox} \NC r2l \type {\hbox} \NC \NR -\NC \type {\lefttorighthbox} \NC l2r \type {\hbox} \NC \NR -\NC \type {\righttoleftvbox} \NC r2l \type {\vbox} \NC \NR -\NC \type {\lefttorightvbox} \NC l2r \type {\vbox} \NC \NR -\NC \type {\righttoleftvtop} \NC r2l \type {\vtop} \NC \NR -\NC \type {\lefttorightvtop} \NC l2r \type {\vtop} \NC \NR -\ML -\NC \type {\leftorrighthbox} \NC l2r or r2l \type {\hbox} \NC \NR -\NC \type {\leftorrightvbox} \NC l2r or r2l \type {\vbox} \NC \NR -\NC \type {\leftorrightvtop} \NC l2r or r2l \type {\vtop} \NC \NR -\ML -\NC \type {\autodirhbox} \NC l2r or r2l \type {\hbox} (a bit more clever) \NC \NR -\NC \type {\autodirvbox} \NC l2r or r2l \type {\vbox} (a bit more clever) \NC \NR -\NC \type {\autodirvtop} \NC l2r or r2l \type {\vtop} (a bit more clever) \NC \NR -\ML -\NC \type {\bidilre} \NC character \type {U+202A}, enforce l2r state \NC \NR -\NC \type {\bidirle} \NC character \type {U+202B}, enforce r2l state \NC \NR -\NC \type {\bidipop} \NC character \type {U+202C}, return to last state \NC \NR -\NC \type {\bidilro} \NC character \type {U+202D}, override l2r state \NC \NR -\NC \type {\bidirlo} \NC character \type {U+202E}, override r2l state \NC \NR -\NC \type {\lefttorightmark} \type {\lrm} \NC character \type {U+200E}, l2r indicator \NC \NR -\NC \type {\righttoleftmark} \type {\rlm} \NC character \type {U+200F}, r2l indicator \NC \NR -\ML -\NC \type {\dirlre} \NC switch to l2r mode using \type {\bidilre} or \lefttoright \NC \NR -\NC \type {\dirrle} \NC switch to r2l mode using \type {\bidirle} or \righttoleft \NC \NR -\NC \type {\dirlro} \NC enforce l2r mode using \type {\bidilro} or \lefttoright \NC \NR -\NC \type {\dirrlo} \NC enforce r2l mode using \type {\bidirlo} or \righttoleft \NC \NR -\ML -\NC \type {\naturalhbox} \NC a normal l2r \type {hbox} \NC \NR -\NC \type {\naturalvbox} \NC a normal l2r \type {vbox} \NC \NR -\NC \type {\naturalvtop} \NC a normal l2r \type {vtop} \NC \NR -\NC \type {\naturalhpack} \NC a normal l2r \type {hpack} \NC \NR -\NC \type {\naturalvpack} \NC a normal l2r \type {vpack} \NC \NR -\LL -\stoptabulate - -When we talk about layout, we mean the overall layout, concerning the document as -a whole. We can have a dominantly l2r, dominantly r2l or mixed setup. In a next -chapter we will give more details on the dominant setup. Here we stick to -mentioning that the document flow direction is set with - -\starttyping -\setupalign[r2l] % or r2l -\stoptyping - -When a command to setup an environment has a \type {align} parameter, the same -keywords can be uses as part of the specification. \footnote {We haven't tested -all situations and possible interferences. Just report anomalies to the mailing -list.} - -\stopchapter - -\startchapter[title={Numbering and positioning}] - -todo: columns (direction key), numbers (conversionsets), margins (begin/end), etc - -\stopchapter - -\startchapter[title={The \LUA\ interface}] - -We assume that you run \CONTEXT\ \MKIV\ in combination with \LUATEX. Direction -support in this engine has been improved over time. Originally the \OMEGA\ -(\ALEPH) direction model was used but in the meantime it has been stripped to the -basics, and what used to be so called whatsits (extension nodes) are now first -class nodes. Of the many directions only four are kept in \LUATEX\ and they are -indicated by three letters: - -\starttabulate[|l|l|l|] -\NC 0 \NC \type {TLT} \NC left to right \NC \NR -\NC 1 \NC \type {TRT} \NC right to left \NC \NR -\NC 2 \NC \type {LTL} \NC not used in context (obsolete) \NC \NR -\NC 3 \NC \type {RTT} \NC not used in context (obsolete) \NC \NR -\stoptabulate - -In \LUAMETATEX, and therefore \CONTEXT\ \LMTX\ we only have the first two. -Therefore in \LMTX\ you normally don't have to worry about checking for them at -the \LUA\ end because they are irrelevant for calculations (the vertical ones -swapped the horizontal and vertical progression). Also, when really needed, we -use the \type {direction} keys with numerical indicators, so zero for \type {l2r} -and one for \type {r2l}. These values are used for local par nodes as well as -direction nodes. In addition a direction node has a subtype: - -\starttabulate[|l|l|l|] -\NC 0 \NC \type {normal} \NC comparable to \type {+} \NC \NR -\NC 1 \NC \type {cancel} \NC comparable to \type {-} \NC \NR -\stoptabulate - -\stopchapter - -\startchapter[title={Going vertical}] - -Normally the term bidi is reserved for horizontal direction swapping but there is -no reason to limit our view to that. So, here I will spend some words on how we -can deal with vertical directions. - -{\em I will move some (not yet public) explanation from elsewhere to here in due -time.} - -\stopchapter - -\stoptext - -% \defineconversionset [\s!default] [] [numbers] -% \defineconversionset [\v!number] [] [numbers] -% \defineconversionset [\v!pagenumber] [] [numbers] -% \defineconversionset [\v!appendix:\s!default] [Romannumerals,Characters] [numbers] -% \defineconversionset [\v!formula] [numbers,characters] % no \v! ? +\stopdocument diff --git a/doc/context/sources/general/manuals/luametatex/luametatex-callbacks.tex b/doc/context/sources/general/manuals/luametatex/luametatex-callbacks.tex new file mode 100644 index 000000000..e713d13c3 --- /dev/null +++ b/doc/context/sources/general/manuals/luametatex/luametatex-callbacks.tex @@ -0,0 +1,820 @@ +% language=uk + +\environment luametatex-style + +\startcomponent luametatex-callbacks + +\startchapter[reference=callbacks,title={\LUA\ callbacks}] + +\startsection[title={Registering callbacks}][library=callback] + +\topicindex{callbacks} + +\libindex{register} +\libindex{list} +\libindex{find} + +This library has functions that register, find and list callbacks. Callbacks are +\LUA\ functions that are called in well defined places. There are two kind of +callbacks: those that mix with existing functionality, and those that (when +enabled) replace functionality. In mosty cases the second category is expected to +behave similar to the built in functionality because in a next step specific +data is expected. For instance, you can replace the hyphenation routine. The +function gets a list that can be hyphenated (or not). The final list should be +valid and is (normally) used for constructing a paragraph. Another function can +replace the ligature builder and|/|or kerner. Doing something else is possible +but in the end might not give the user the expected outcome. + +The first thing you need to do is registering a callback: + +\startfunctioncall +id, error = + callback.register( callback_name, func) +id, error = + callback.register( callback_name, nil) +id, error = + callback.register( callback_name, false) +\stopfunctioncall + +Here the \syntax {callback_name} is a predefined callback name, see below. The +function returns the internal \type {id} of the callback or \type {nil}, if the +callback could not be registered. In the latter case, \type {error} contains an +error message, otherwise it is \type {nil}. + +\LUATEX\ internalizes the callback function in such a way that it does not matter +if you redefine a function accidentally. + +Callback assignments are always global. You can use the special value \type {nil} +instead of a function for clearing the callback. + +For some minor speed gain, you can assign the boolean \type {false} to the +non|-|file related callbacks, doing so will prevent \LUATEX\ from executing +whatever it would execute by default (when no callback function is registered at +all). Be warned: this may cause all sorts of grief unless you know \notabene +{exactly} what you are doing! + +\startfunctioncall + info = + callback.list() +\stopfunctioncall + +The keys in the table are the known callback names, the value is a boolean where +\type {true} means that the callback is currently set (active). + +\startfunctioncall + f = callback.find(callback_name) +\stopfunctioncall + +If the callback is not set, \type {find} returns \type {nil}. + +\stopsection + +\startsection[title={File related callbacks}][library=callback] + +The behaviour documented in this subsection is considered stable in the sense that +there will not be backward|-|incompatible changes any more. + +\subsection{\cbk {find_read_file}} + +Your callback function should have the following conventions: + +\startfunctioncall + actual_name = + function ( id_number, asked_name) +\stopfunctioncall + +Arguments: + +\startitemize + +\sym{id_number} + +This number is zero for the log or \prm {input} files. For \TEX's \prm {read} +or \prm {write} the number is incremented by one, so \type {\read0} becomes~1. + +\sym{asked_name} + +This is the user|-|supplied filename, as found by \prm {input}, \prm {openin} +or \prm {openout}. + +\stopitemize + +Return value: + +\startitemize + +\sym{actual_name} + +This is the filename used. For the very first file that is read in by \TEX, you +have to make sure you return an \type {actual_name} that has an extension and +that is suitable for use as \type {jobname}. If you don't, you will have to +manually fix the name of the log file and output file after \LUATEX\ is finished, +and an eventual format filename will become mangled. That is because these file +names depend on the jobname. + +You have to return \type {nil} if the file cannot be found. + +\stopitemize + +\subsection{\cbk {find_data_file}} + +\topicindex{callbacks+data files} + +Your callback function should have the following conventions: + +\startfunctioncall + actual_name = + function ( asked_name) +\stopfunctioncall + +Return \type {nil} if the file cannot be found. + +\subsection{\cbk {find_format_file}} + +\topicindex{callbacks+format file} + +Your callback function should have the following conventions: + +\startfunctioncall + actual_name = + function ( asked_name) +\stopfunctioncall + +The \type {asked_name} is a format file for reading (the format file for writing +is always opened in the current directory). + +\subsection{\cbk {open_read_file}} + +\topicindex{callbacks+opening files} + +Your callback function should have the following conventions: + +\startfunctioncall +
env = + function ( file_name) +\stopfunctioncall + +Argument: + +\startitemize + +\sym{file_name} + +The filename returned by a previous \cbk {find_read_file} or the return value of +\type {kpse.find_file()} if there was no such callback defined. + +\stopitemize + +Return value: + +\startitemize + +\sym{env} + +This is a table containing at least one required and one optional callback +function for this file. The required field is \type {reader} and the associated +function will be called once for each new line to be read, the optional one is +\type {close} that will be called once when \LUATEX\ is done with the file. + +\LUATEX\ never looks at the rest of the table, so you can use it to store your +private per|-|file data. Both the callback functions will receive the table as +their only argument. + +\stopitemize + +\subsubsection{\type {reader}} + +\topicindex{callbacks+reader} + +\LUATEX\ will run this function whenever it needs a new input line from the file. + +\startfunctioncall +function(
env) + return line +end +\stopfunctioncall + +Your function should return either a string or \type {nil}. The value \type {nil} +signals that the end of file has occurred, and will make \TEX\ call the optional +\type {close} function next. + +\subsubsection{\type {close}} + +\topicindex{callbacks+closing files} + +\LUATEX\ will run this optional function when it decides to close the file. + +\startfunctioncall +function(
env) +end +\stopfunctioncall + +Your function should not return any value. + +\stopsection + +\startsection[title={Data processing callbacks}][library=callback] + +\subsection{\cbk {process_jobname}} + +\topicindex{callbacks+jobname} + +This callback allows you to change the jobname given by \prm {jobname} in \TEX\ +and \type {tex.jobname} in Lua. It does not affect the internal job name or the +name of the output or log files. + +\startfunctioncall +function( jobname) + return adjusted_jobname +end +\stopfunctioncall + +The only argument is the actual job name; you should not use \type {tex.jobname} +inside this function or infinite recursion may occur. If you return \type {nil}, +\LUATEX\ will pretend your callback never happened. This callback does not +replace any internal code. + +\stopsection + +\startsection[title={Node list processing callbacks}][library=callback] + +The description of nodes and node lists is in~\in{chapter}[nodes]. + +\subsection{\cbk {contribute_filter}} + +\topicindex{callbacks+contributions} + +This callback is called when \LUATEX\ adds contents to list: + +\startfunctioncall +function( extrainfo) +end +\stopfunctioncall + +The string reports the group code. From this you can deduce from +what list you can give a treat. + +\starttabulate[|l|p|] +\DB value \BC explanation \NC \NR +\TB +\NC \type{pre_box} \NC interline material is being added \NC \NR +\NC \type{pre_adjust} \NC \prm {vadjust} material is being added \NC \NR +\NC \type{box} \NC a typeset box is being added (always called) \NC \NR +\NC \type{adjust} \NC \prm {vadjust} material is being added \NC \NR +\LL +\stoptabulate + +\subsection{\cbk {buildpage_filter}} + +\topicindex{callbacks+building pages} + +This callback is called whenever \LUATEX\ is ready to move stuff to the main +vertical list. You can use this callback to do specialized manipulation of the +page building stage like imposition or column balancing. + +\startfunctioncall +function( extrainfo) +end +\stopfunctioncall + +The string \type {extrainfo} gives some additional information about what \TEX's +state is with respect to the \quote {current page}. The possible values for the +\cbk {buildpage_filter} callback are: + +\starttabulate[|l|p|] +\DB value \BC explanation \NC \NR +\TB +\NC \type{alignment} \NC a (partial) alignment is being added \NC \NR +\NC \type{after_output} \NC an output routine has just finished \NC \NR +\NC \type{new_graf} \NC the beginning of a new paragraph \NC \NR +\NC \type{vmode_par} \NC \prm {par} was found in vertical mode \NC \NR +\NC \type{hmode_par} \NC \prm {par} was found in horizontal mode \NC \NR +\NC \type{insert} \NC an insert is added \NC \NR +\NC \type{penalty} \NC a penalty (in vertical mode) \NC \NR +\NC \type{before_display} \NC immediately before a display starts \NC \NR +\NC \type{after_display} \NC a display is finished \NC \NR +\NC \type{end} \NC \LUATEX\ is terminating (it's all over) \NC \NR +\LL +\stoptabulate + +\subsection{\cbk {build_page_insert}} + +\topicindex{callbacks+inserts} + +This callback is called when the pagebuilder adds an insert. There is not much +control over this mechanism but this callback permits some last minute +manipulations of the spacing before an insert, something that might be handy when +for instance multiple inserts (types) are appended in a row. + +\startfunctioncall +function( n, i) + return register +end +\stopfunctioncall + +with + +\starttabulate[|l|p|] +\DB value \BC explanation \NC \NR +\TB +\NC \type{n} \NC the insert class \NC \NR +\NC \type{i} \NC the order of the insert \NC \NR +\LL +\stoptabulate + +The return value is a number indicating the skip register to use for the +prepended spacing. This permits for instance a different top space (when \type +{i} equals one) and intermediate space (when \type {i} is larger than one). Of +course you can mess with the insert box but you need to make sure that \LUATEX\ +is happy afterwards. + +\subsection{\cbk {pre_linebreak_filter}} + +\topicindex{callbacks+linebreaks} + +This callback is called just before \LUATEX\ starts converting a list of nodes +into a stack of \prm {hbox}es, after the addition of \prm {parfillskip}. + +\startfunctioncall +function( head, groupcode) + return true | false | newhead +end +\stopfunctioncall + +The string called \type {groupcode} identifies the nodelist's context within +\TEX's processing. The range of possibilities is given in the table below, but +not all of those can actually appear in \cbk {pre_linebreak_filter}, some are +for the \cbk {hpack_filter} and \cbk {vpack_filter} callbacks that will be +explained in the next two paragraphs. + +\starttabulate[|l|p|] +\DB value \BC explanation \NC \NR +\TB +\NC \type{} \NC main vertical list \NC \NR +\NC \type{hbox} \NC \prm {hbox} in horizontal mode \NC \NR +\NC \type{adjusted_hbox} \NC \prm {hbox} in vertical mode \NC \NR +\NC \type{vbox} \NC \prm {vbox} \NC \NR +\NC \type{vtop} \NC \prm {vtop} \NC \NR +\NC \type{align} \NC \prm {halign} or \prm {valign} \NC \NR +\NC \type{disc} \NC discretionaries \NC \NR +\NC \type{insert} \NC packaging an insert \NC \NR +\NC \type{vcenter} \NC \prm {vcenter} \NC \NR +\NC \type{local_box} \NC \lpr {localleftbox} or \lpr {localrightbox} \NC \NR +\NC \type{split_off} \NC top of a \prm {vsplit} \NC \NR +\NC \type{split_keep} \NC remainder of a \prm {vsplit} \NC \NR +\NC \type{align_set} \NC alignment cell \NC \NR +\NC \type{fin_row} \NC alignment row \NC \NR +\LL +\stoptabulate + +As for all the callbacks that deal with nodes, the return value can be one of +three things: + +\startitemize +\startitem + boolean \type {true} signals successful processing +\stopitem +\startitem + \type {} signals that the \quote {head} node should be replaced by the + returned node +\stopitem +\startitem + boolean \type {false} signals that the \quote {head} node list should be + ignored and flushed from memory +\stopitem +\stopitemize + +This callback does not replace any internal code. + +\subsection{\cbk {linebreak_filter}} + +\topicindex{callbacks+linebreaks} + +This callback replaces \LUATEX's line breaking algorithm. + +\startfunctioncall +function( head, is_display) + return newhead +end +\stopfunctioncall + +The returned node is the head of the list that will be added to the main vertical +list, the boolean argument is true if this paragraph is interrupted by a +following math display. + +If you return something that is not a \type {}, \LUATEX\ will apply the +internal linebreak algorithm on the list that starts at \type {}. +Otherwise, the \type {} you return is supposed to be the head of a list of +nodes that are all allowed in vertical mode, and at least one of those has to +represent a hbox. Failure to do so will result in a fatal error. + +Setting this callback to \type {false} is possible, but dangerous, because it is +possible you will end up in an unfixable \quote {deadcycles loop}. + +\subsection{\type {append_to_vlist_filter}} + +\topicindex{callbacks+contributions} + +This callback is called whenever \LUATEX\ adds a box to a vertical list: + +\startfunctioncall +function( box, locationcode, , + mirrored) + return list, prevdepth +end +\stopfunctioncall + +It is ok to return nothing in which case you also need to flush the box or deal +with it yourself. The prevdepth is also optional. Locations are \type {box}, +\type {alignment}, \type {equation}, \type {equation_number} and \type +{post_linebreak}. + +\subsection{\cbk {post_linebreak_filter}} + +\topicindex{callbacks+linebreaks} + +This callback is called just after \LUATEX\ has converted a list of nodes into a +stack of \prm {hbox}es. + +\startfunctioncall +function( head, groupcode) + return true | false | newhead +end +\stopfunctioncall + +This callback does not replace any internal code. + +\subsection{\cbk {hpack_filter}} + +\topicindex{callbacks+packing} + +This callback is called when \TEX\ is ready to start boxing some horizontal mode +material. Math items and line boxes are ignored at the moment. + +\startfunctioncall +function( head, groupcode, size, + packtype [, direction] [, attributelist]) + return true | false | newhead +end +\stopfunctioncall + +The \type {packtype} is either \type {additional} or \type {exactly}. If \type +{additional}, then the \type {size} is a \type {\hbox spread ...} argument. If +\type {exactly}, then the \type {size} is a \type {\hbox to ...}. In both cases, +the number is in scaled points. + +The \type {direction} is either one of the three-letter direction specifier +strings, or \type {nil}. + +This callback does not replace any internal code. + +\subsection{\cbk {vpack_filter}} + +\topicindex{callbacks+packing} + +This callback is called when \TEX\ is ready to start boxing some vertical mode +material. Math displays are ignored at the moment. + +This function is very similar to the \cbk {hpack_filter}. Besides the fact +that it is called at different moments, there is an extra variable that matches +\TEX's \prm {maxdepth} setting. + +\startfunctioncall +function( head, groupcode, size, packtype, + maxdepth [, direction] [, attributelist])) + return true | false | newhead +end +\stopfunctioncall + +This callback does not replace any internal code. + +\subsection{\type {hpack_quality}} + +\topicindex{callbacks+packing} + +This callback can be used to intercept the overfull messages that can result from +packing a horizontal list (as happens in the par builder). The function takes a +few arguments: + +\startfunctioncall +function( incident, detail, head, first, + last) + return whatever +end +\stopfunctioncall + +The incident is one of \type {overfull}, \type {underfull}, \type {loose} or +\type {tight}. The detail is either the amount of overflow in case of \type +{overfull}, or the badness otherwise. The head is the list that is constructed +(when protrusion or expansion is enabled, this is an intermediate list). +Optionally you can return a node, for instance an overfull rule indicator. That +node will be appended to the list (just like \TEX's own rule would). + +\subsection{\type {vpack_quality}} + +\topicindex{callbacks+packing} + +This callback can be used to intercept the overfull messages that can result from +packing a vertical list (as happens in the page builder). The function takes a +few arguments: + +\startfunctioncall +function( incident, detail, head, first, + last) +end +\stopfunctioncall + +The incident is one of \type {overfull}, \type {underfull}, \type {loose} or +\type {tight}. The detail is either the amount of overflow in case of \type +{overfull}, or the badness otherwise. The head is the list that is constructed. + +\subsection{\cbk {process_rule}} + +\topicindex{callbacks+rules} + +This is an experimental callback. It can be used with rules of subtype~4 +(user). The callback gets three arguments: the node, the width and the +height. The callback can use \type {pdf.print} to write code to the \PDF\ +file but beware of not messing up the final result. No checking is done. + +\subsection{\type {pre_output_filter}} + +\topicindex{callbacks+output} + +This callback is called when \TEX\ is ready to start boxing the box 255 for \prm +{output}. + +\startfunctioncall +function( head, groupcode, size, packtype, + maxdepth [, direction]) + return true | false | newhead +end +\stopfunctioncall + +This callback does not replace any internal code. + +\subsection{\cbk {hyphenate}} + +\topicindex{callbacks+hyphenation} + +\startfunctioncall +function( head, tail) +end +\stopfunctioncall + +No return values. This callback has to insert discretionary nodes in the node +list it receives. + +Setting this callback to \type {false} will prevent the internal discretionary +insertion pass. + +\subsection{\cbk {ligaturing}} + +\topicindex{callbacks+ligature building} + +\startfunctioncall +function( head, tail) +end +\stopfunctioncall + +No return values. This callback has to apply ligaturing to the node list it +receives. + +You don't have to worry about return values because the \type {head} node that is +passed on to the callback is guaranteed not to be a glyph_node (if need be, a +temporary node will be prepended), and therefore it cannot be affected by the +mutations that take place. After the callback, the internal value of the \quote +{tail of the list} will be recalculated. + +The \type {next} of \type {head} is guaranteed to be non-nil. + +The \type {next} of \type {tail} is guaranteed to be nil, and therefore the +second callback argument can often be ignored. It is provided for orthogonality, +and because it can sometimes be handy when special processing has to take place. + +Setting this callback to \type {false} will prevent the internal ligature +creation pass. + +You must not ruin the node list. For instance, the head normally is a local par node, +and the tail a glue. Messing too much can push \LUATEX\ into panic mode. + +\subsection{\cbk {kerning}} + +\topicindex{callbacks+kerning} + +\startfunctioncall +function( head, tail) +end +\stopfunctioncall + +No return values. This callback has to apply kerning between the nodes in the +node list it receives. See \cbk {ligaturing} for calling conventions. + +Setting this callback to \type {false} will prevent the internal kern insertion +pass. + +You must not ruin the node list. For instance, the head normally is a local par node, +and the tail a glue. Messing too much can push \LUATEX\ into panic mode. + +\subsection{\type {insert_local_par}} + +Each paragraph starts with a local par node that keeps track of for instance +the direction. You can hook a callback into the creator: + +\startfunctioncall +function( local_par, location) +end +\stopfunctioncall + +There is no return value and you should make sure that the node stays valid +as otherwise \TEX\ can get confused. + +\subsection{\cbk {mlist_to_hlist}} + +\topicindex{callbacks+math} + +This callback replaces \LUATEX's math list to node list conversion algorithm. + +\startfunctioncall +function( head, display_type, need_penalties) + return newhead +end +\stopfunctioncall + +The returned node is the head of the list that will be added to the vertical or +horizontal list, the string argument is either \quote {text} or \quote {display} +depending on the current math mode, the boolean argument is \type {true} if +penalties have to be inserted in this list, \type {false} otherwise. + +Setting this callback to \type {false} is bad, it will almost certainly result in +an endless loop. + +\stopsection + +\startsection[title={Information reporting callbacks}][library=callback] + +\subsection{\cbk {pre_dump}} + +\topicindex{callbacks+dump} + +\startfunctioncall +function() +end +\stopfunctioncall + +This function is called just before dumping to a format file starts. It does not +replace any code and there are neither arguments nor return values. + +\subsection{\cbk {start_run}} + +\topicindex{callbacks+job run} + +\startfunctioncall +function() +end +\stopfunctioncall + +This callback replaces the code that prints \LUATEX's banner. Note that for +successful use, this callback has to be set in the \LUA\ initialization script, +otherwise it will be seen only after the run has already started. + +\subsection{\cbk {stop_run}} + +\topicindex{callbacks+job run} + +\startfunctioncall +function() +end +\stopfunctioncall + +This callback replaces the code that prints \LUATEX's statistics and \quote +{output written to} messages. The engine can still do housekeeping and therefore +you should not rely on this hook for postprocessing the \PDF\ or log file. + +\subsection{\cbk {show_error_hook}} + +\topicindex{callbacks+errors} + +\startfunctioncall +function() +end +\stopfunctioncall + +This callback is run from inside the \TEX\ error function, and the idea is to +allow you to do some extra reporting on top of what \TEX\ already does (none of +the normal actions are removed). You may find some of the values in the \type +{status} table useful. This callback does not replace any internal code. + +\subsection{\cbk {show_error_message}} + +\topicindex{callbacks+errors} + +\startfunctioncall +function() +end +\stopfunctioncall + +This callback replaces the code that prints the error message. The usual +interaction after the message is not affected. + +\subsection{\cbk {show_lua_error_hook}} + +\topicindex{callbacks+errors} + +\startfunctioncall +function() +end +\stopfunctioncall + +This callback replaces the code that prints the extra \LUA\ error message. + +\subsection{\cbk {start_file}} + +\topicindex{callbacks+files} + +\startfunctioncall +function(category,filename) +end +\stopfunctioncall + +This callback replaces the code that prints \LUATEX's when a file is opened like +\type {(filename} for regular files. The category is a number: + +\starttabulate[|c|l|] +\DB value \BC meaning \NC \NR +\TB +\NC 1 \NC a normal data file, like a \TEX\ source \NC \NR +\NC 2 \NC a font map coupling font names to resources \NC \NR +\NC 3 \NC an image file (\type {png}, \type {pdf}, etc) \NC \NR +\NC 4 \NC an embedded font subset \NC \NR +\NC 5 \NC a fully embedded font \NC \NR +\LL +\stoptabulate + +\subsection{\cbk {stop_file}} + +\topicindex{callbacks+files} + +\startfunctioncall +function(category) +end +\stopfunctioncall + +This callback replaces the code that prints \LUATEX's when a file is closed like +the \type {)} for regular files. + +\subsection{\cbk {wrapup_run}} + +\topicindex{callbacks+wrapping up} + +This callback is called after the \PDF\ and log files are closed. Use it at your own +risk. + +\stopsection + +\startsection[title={Font-related callbacks}][library=callback] + +\subsection{\cbk {define_font}} + +\topicindex{callbacks+fonts} + +\startfunctioncall +function( name, size) + return id +end +\stopfunctioncall + +The string \type {name} is the filename part of the font specification, as given +by the user. + +The number \type {size} is a bit special: + +\startitemize[packed] +\startitem + If it is positive, it specifies an \quote{at size} in scaled points. +\stopitem +\startitem + If it is negative, its absolute value represents a \quote {scaled} setting + relative to the design size of the font. +\stopitem +\stopitemize + +The font can be defined with \type {font.define} which returns a font identifier +that can be returned in the callback. So, contrary to \LUATEX, in \LUAMETATEX\ +we only accept a number. + +The internal structure of the \type {font} table that is passed to \type +{font.define} is explained in \in {chapter} [fonts]. That table is saved +internally, so you can put extra fields in the table for your later \LUA\ code to +use. In alternative, \type {retval} can be a previously defined fontid. This is +useful if a previous definition can be reused instead of creating a whole new +font structure. + +Setting this callback to \type {false} is pointless as it will prevent font +loading completely but will nevertheless generate errors. + +\stopsection + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/luametatex/luametatex-differences.tex b/doc/context/sources/general/manuals/luametatex/luametatex-differences.tex new file mode 100644 index 000000000..3e164c711 --- /dev/null +++ b/doc/context/sources/general/manuals/luametatex/luametatex-differences.tex @@ -0,0 +1,209 @@ +% language=uk + +\environment luametatex-style + +\startcomponent luametatex-differences + +\startchapter[reference=differences,title={Differences with \LUATEX}] + +As \LUAMETATEX\ is a leaner and meaner \LUATEX, this chapter will discuss +what is gone. We start with the primitives that were dropped. + +\starttabulate[|l|pl|] +\NC fonts \NC \type {\letterspacefont} + \type {\copyfont} + \type {\expandglyphsinfont} + \type {\ignoreligaturesinfont} + \type {\tagcode} + \NC \NR +\NC backend \NC \type {\dviextension} + \type {\dvivariable } + \type {\dvifeedback} + \type {\pdfextension} + \type {\pdfvariable } + \type {\pdffeedback} + \type {\dviextension} + \type {\draftmode} + \type {\outputmode} + \NC \NR +\NC dimensions \NC \type {\pageleftoffset} + \type {\pagerightoffset} + \type {\pagetopoffset} + \type {\pagebottomoffset} + \type {\pageheight} + \type {\pagewidth} + \NC \NR +\NC resources \NC \type {\saveboxresource} + \type {\useboxresource} + \type {\lastsavedboxresourceindex} + \type {\saveimageresource} + \type {\useimageresource} + \type {\lastsavedimageresourceindex} + \type {\lastsavedimageresourcepages} + \NC \NR +\NC positioning \NC \type {\savepos} + \type {\lastxpos} + \type {\lastypos} + \NC \NR +\NC directions \NC \type {\textdir} + \type {\linedir} + \type {\mathdir} + \type {\pardir} + \type {\pagedir} + \type {\bodydir} + \type {\pagedirection} + \type {\bodydirection} + \NC \NR +\NC randomizer \NC \type {\randomseed} + \type {\setrandomseed} + \type {\normaldeviate} + \type {\uniformdeviate} + \NC \NR +\NC utilities \NC \type {\synctex} + \NC \NR +\NC extensions \NC \type {\latelua} + \type {\lateluafunction} + \type {\immediate} + \type {\openout} + \type {\write} + \type {\closeout} + \NC \NR +\NC control \NC \type {\suppressfontnotfounderror} + \type {\suppresslongerror} + \type {\suppressprimitiveerror} + \type {\suppressmathparerror} + \type {\suppressifcsnameerror} + \type {\suppressoutererror} + \type {\mathoption} + \NC \NR +\NC whatever \NC \type {\primitive} + \type {\ifprimitive} + \NC \NR +\NC ignored \NC \type {\long} + \type {\outer} + \type {\mag} + \NC \NR +\stoptabulate + +The resources and positioning primitives are actually useful but can be defined +as macros that (via \LUA) inject nodes in the input that suit the macro package +and backend. The three||letter direction primitives are gone and the numeric +variants are now leading. There is no need for page and body related directions +and they don't work well in \LUATEX\ anyway. We only have two directions left. + +The primitive related extensions were not that useful and reliable so they have +been removed. There are some new variants that will be discussed later. The \type +{\outer} and \type {\long} prefixes are gone as they don't make much sense +nowadays and them becoming dummies opened the way to something new, again to be +discussed elsewhere. I don't think that (\CONTEXT) users will notice it. The +\type {\suppress..} features are now default. + +The \type {\shipout} primitive does no ship out but just erases the content of +the box, if that hasn't happened already in another way. + +The extension primitives relate to the backend (when not immediate) and can be +implemented as part of a backend design using generic whatsits. There is only one +type of whatsit now. In fact we're now closer to original \TEX\ with respect to +the extensions. + +The \type {img} library has been removed as it's rather bound to the backend. The +\type {slunicode} library is also gone. There are some helpers in the string +library that can be used instead and one can write additional \LUA\ code if +needed. There is no longer a \type {pdf} backend library. + +In the \type {node}, \type {tex} and \type {status} library we no longer have +helpers and variables that relate to the backend. The \LUAMETATEX\ engine is in +principle \DVI\ and \PDF\ unaware. There are only generic whatsit nodes that can +be used for some management related tasks. For instance you can use them to +implement user nodes. + +The \KPSE\ library is no longer built|-|in. Because there is no backend, quite +some file related callbacks could go away. The following file related callbacks +remained (till now): + +\starttyping +find_write_file find_data_file find_format_file +open_data_file read_data_file +\stoptyping + +Also callbacks related to errors stay: + +\starttyping +show_error_hook show_lua_error_hook, +show_error_message show_warning_message +\stoptyping + +The (job) management hooks are kept: + +\starttyping +process_jobname +start_run stop_run wrapup_run +pre_dump +start_file stop_file +\stoptyping + +Because we use a more generic whatsit model, there is a new callback: + +\starttyping +show_whatsit +\stoptyping + +Being the core of extensibility, the typesetting callbacks of course stayed. This +is what we ended up with: + +\starttyping +find_log_file, find_data_file, find_format_file, open_data_file, read_data_file, +process_jobname, start_run, stop_run, define_font, pre_output_filter, +buildpage_filter, hpack_filter, vpack_filter, hyphenate, ligaturing, kerning, +pre_linebreak_filter, linebreak_filter, post_linebreak_filter, +append_to_vlist_filter, mlist_to_hlist, pre_dump, start_file, stop_file, +handle_error_hook, show_error_hook, show_lua_error_hook, show_error_message, +show_warning_message, hpack_quality, vpack_quality, insert_local_par, +contribute_filter, build_page_insert, wrapup_run, new_graf, make_extensible, +show_whatsit, terminal_input, +\stoptyping + +As in \LUATEX\ font loading happens with the following callback. This time it +really needs to be set because there is no built|-|in font loader. + +\starttyping +define_font +\stoptyping + +There are all kind of subtle differences in the implementation, for instance we +no longer intercept \type {*} and \type {&} as these were already replaced long +ago in \TEX\ engines by command line options. Talking of options, only a few are +left. + +We took our time for reaching a stable state in \LUATEX. Among the reasons is the +fact that most was experimented with in \CONTEXT. It took many man|-|years to +decide what to keep and how to do things. Of course there are places when things +can be improved and it might happen in \LUAMETATEX. Contrary to what is sometimes +suggested, the \LUATEX|-|\CONTEXT\ \MKIV\ combination (assuming matched versions) +has been quite stable. It made no sense otherwise. Most \CONTEXT\ functionality +didn't change much at the user level. Of course there have been issues, as is +natural with everything new and beta, but we have a fast update cycle. + +The same is true for \LUAMETATEX\ and \CONTEXT\ \LMTX: it can be used for +production as usual and in practice \CONTEXT\ users tend to use the beta +releases, which proves this. Of course, of you use low level features that are +experimental you're on your own. Also, as with \LUATEX\ it might take many years +before a long term stable is defined. The good news is that, the source code +being part of the \CONTEXT\ distribution, there is always a properly working, +more of less long term stable, snapshot. + +The error reporting subsystem has been redone a little but is still fundamentally +the same. We don't really assume interactive usage but if someone uses it, it +might be noticed that it is not possible to backtrack or inject something. Of +course it is no big deal to implement all that in \LUA\ if needed. It removes a +system dependency and makes for a bit cleaner code. + +There are new primitives too as well as some extensions to existing primitive +functionality. These are described in following chapters but there might be +hidden treasures in the binary. If you locate them, don't automatically assume +them to stay, some might be part of experiments! + +\stopchapter + +\stopcomponent + diff --git a/doc/context/sources/general/manuals/luametatex/luametatex-enhancements.tex b/doc/context/sources/general/manuals/luametatex/luametatex-enhancements.tex new file mode 100644 index 000000000..34e717a72 --- /dev/null +++ b/doc/context/sources/general/manuals/luametatex/luametatex-enhancements.tex @@ -0,0 +1,1781 @@ +% language=uk + +\environment luametatex-style + +\startcomponent luametatex-enhancements + +\startchapter[reference=enhancements,title={Basic \TEX\ enhancements}] + +\startsection[title={Introduction}] + +\startsubsection[title={Primitive behaviour}] + +From day one, \LUATEX\ has offered extra features compared to the superset of +\PDFTEX, which includes \ETEX, and \ALEPH. This has not been limited to the +possibility to execute \LUA\ code via \prm {directlua}, but \LUATEX\ also adds +functionality via new \TEX|-|side primitives or extensions to existing ones. The +same is true fir \LUAMETATEX. Some primitives have \type {luatex} in their name +and there will be no \type {luametatex} variants. This is because we consider +\LUAMETATEX\ to be \LUATEX 2\high{+}. + +Contrary to the \LUATEX\ engine \LUAMETATEX\ enables all its primitives. You can +clone (a selection of) primitives with a different prefix, like: + +\starttyping +\directlua { tex.enableprimitives('normal',tex.extraprimitives()) } +\stoptyping + +The \type {extraprimitives} function returns the whole list or a subset, +specified by one or more keywords \type {core}, \type {tex}, \type {etex} or +\type {luatex}. \footnote {At some point this function might be changed to return +the whole list always}. + +But be aware that the curly braces may not have the proper \prm {catcode} +assigned to them at this early time (giving a \quote {Missing number} error), so +it may be needed to put these assignments before the above line: + +\starttyping +\catcode `\{=1 +\catcode `\}=2 +\stoptyping + +More fine|-|grained primitives control is possible and you can look up the +details in \in {section} [luaprimitives]. For simplicity's sake, this manual +assumes that you have executed the \prm {directlua} command as given above. + +The startup behaviour documented above is considered stable in the sense that +there will not be backward|-|incompatible changes any more. We have promoted some +rather generic \PDFTEX\ primitives to core \LUATEX\ ones, and a few that we +inherited from \ALEPH\ (\OMEGA) are also promoted. Effectively this means that we +now only have the \type {tex}, \type {etex} and \type {luatex} sets left. + +\stopsubsection + +\startsubsection[title={Experiments}] + +There are a few extensions to the engine regarding the macro machinery. Some are +already well tested but others are (still) experimental. Although they are likely +to stay, their exact behaviour might evolve. Because \LUAMETATEX\ is also used +for experiments, this is not a problem. We can always decide to also add some of +what is discussed here to \LUATEX, but it will happen with a delay. + +There are all kind of small improvements that might find their way into stock +\LUATEX: a few more helpers, some cleanup of code, etc. We'll see. In any case, +if you play with these before they are declared stable, unexpected side effects +are what you have to accept. + +\stopsubsection + +\startsubsection[title={Version information}] + +\startsubsubsection[title={\lpr {luatexbanner}, \lpr {luatexversion} and \lpr {luatexrevision}}] + +\topicindex{version} +\topicindex{banner} + +There are three primitives to test the version of \LUATEX\ (and \LUAMETATEX): + +\unexpanded\def\VersionHack#1% otherwise different luatex and luajittex runs + {\ctxlua{% + local banner = "\luatexbanner" + local banner = string.match(banner,"(.+)\letterpercent(") or banner + context(string.gsub(banner ,"jit",""))% + }} + +\starttabulate[|l|l|pl|] +\DB primitive \BC value + \BC explanation \NC \NR +\TB +\NC \lpr {luatexbanner} \NC \VersionHack{\luatexbanner} + \NC the banner reported on the command line \NC \NR +\NC \lpr {luatexversion} \NC \the\luatexversion + \NC a combination of major and minor number \NC \NR +\NC \lpr {luatexrevision} \NC \luatexrevision + \NC the revision number, the current value is \NC \NR +\LL +\stoptabulate + +A version is defined as follows: + +\startitemize +\startitem + The major version is the integer result of \lpr {luatexversion} divided by + 100. The primitive is an \quote {internal variable}, so you may need to prefix + its use with \prm {the} depending on the context. +\stopitem +\startitem + The minor version is the two|-|digit result of \lpr {luatexversion} modulo 100. +\stopitem +\startitem + The revision is reported by \lpr {luatexrevision}. This primitive expands to + a positive integer. +\stopitem +\startitem + The full version number consists of the major version, minor version and + revision, separated by dots. +\stopitem +\stopitemize + +\stopsubsubsection + +The \LUAMETATEX\ version number starts at 2 in order to prevent a clash with +\LUATEX, and the version commands are the same. This is a way to indicate that +these projects are related. + +\startsubsubsection[title={\lpr {formatname}}] + +\topicindex{format} + +The \lpr {formatname} syntax is identical to \prm {jobname}. In \INITEX, the +expansion is empty. Otherwise, the expansion is the value that \prm {jobname} had +during the \INITEX\ run that dumped the currently loaded format. You can use this +token list to provide your own version info. + +\stopsubsubsection + +\stopsubsection + +\stopsection + +\startsection[title={\UNICODE\ text support}] + +\startsubsection[title={Extended ranges}] + +\topicindex{\UNICODE} + +Text input and output is now considered to be \UNICODE\ text, so input characters +can use the full range of \UNICODE\ ($2^{20}+2^{16}-1 = \hbox{0x10FFFF}$). Later +chapters will talk of characters and glyphs. Although these are not +interchangeable, they are closely related. During typesetting, a character is +always converted to a suitable graphic representation of that character in a +specific font. However, while processing a list of to|-|be|-|typeset nodes, its +contents may still be seen as a character. Inside the engine there is no clear +separation between the two concepts. Because the subtype of a glyph node can be +changed in \LUA\ it is up to the user. Subtypes larger than 255 indicate that +font processing has happened. + +A few primitives are affected by this, all in a similar fashion: each of them has +to accommodate for a larger range of acceptable numbers. For instance, \prm +{char} now accepts values between~0 and $1{,}114{,}111$. This should not be a +problem for well|-|behaved input files, but it could create incompatibilities for +input that would have generated an error when processed by older \TEX|-|based +engines. The affected commands with an altered initial (left of the equal sign) +or secondary (right of the equal sign) value are: \prm {char}, \prm {lccode}, +\prm {uccode}, \lpr {hjcode}, \prm {catcode}, \prm {sfcode}, \lpr {efcode}, \lpr +{lpcode}, \lpr {rpcode}, \prm {chardef}. + +As far as the core engine is concerned, all input and output to text files is +\UTF-8 encoded. Input files can be pre|-|processed using the \type {reader} +callback. This will be explained in \in {section} [iocallback]. Normalization of +the \UNICODE\ input is on purpose not built|-|in and can be handled by a macro +package during callback processing. We have made some practical choices and the +user has to live with those. + +Output in byte|-|sized chunks can be achieved by using characters just outside of +the valid \UNICODE\ range, starting at the value $1{,}114{,}112$ (0x110000). When +the time comes to print a character $c>=1{,}114{,}112$, \LUATEX\ will actually +print the single byte corresponding to $c$ minus 1{,}114{,}112. + +Contrary to other \TEX\ engines, the output to the terminal is as|-|is so there +is no escaping with \type {^^}. We operate in a \UTF\ universe. + +\stopsubsection + +\startsubsection[title={\lpr {Uchar}}] + +\topicindex{\UNICODE} + +The expandable command \lpr {Uchar} reads a number between~0 and $1{,}114{,}111$ +and expands to the associated \UNICODE\ character. + +\stopsubsection + +\startsubsection[title={Extended tables}] + +All traditional \TEX\ and \ETEX\ registers can be 16-bit numbers. The affected +commands are: + +\startfourcolumns +\startlines +\prm {count} +\prm {dimen} +\prm {skip} +\prm {muskip} +\prm {marks} +\prm {toks} +\prm {countdef} +\prm {dimendef} +\prm {skipdef} +\prm {muskipdef} +\prm {toksdef} +\prm {insert} +\prm {box} +\prm {unhbox} +\prm {unvbox} +\prm {copy} +\prm {unhcopy} +\prm {unvcopy} +\prm {wd} +\prm {ht} +\prm {dp} +\prm {setbox} +\prm {vsplit} +\stoplines +\stopfourcolumns + +Fonts are loaded via \LUA\ and a minimal amount of information is kept at the +\TEX\ end. Sharing resources is up to the loaders. The engine doesn't really care +about what a character (or glyph) number represents (an \UNICODE\ or index) as it +only is interested in dimensions. + +\stopsubsection + +\stopsection + +\startsection[title={Attributes}] + +\startsubsection[title={Nodes}] + +\topicindex {nodes} + +When \TEX\ reads input it will interpret the stream according to the properties +of the characters. Some signal a macro name and trigger expansion, others open +and close groups, trigger math mode, etc. What's left over becomes the typeset +text. Internally we get a linked list of nodes. Characters become \nod {glyph} +nodes that have for instance a \type {font} and \type {char} property and \typ +{\kern 10pt} becomes a \nod {kern} node with a \type {width} property. Spaces are +alien to \TEX\ as they are turned into \nod {glue} nodes. So, a simple paragraph +is mostly a mix of sequences of \nod {glyph} nodes (words) and \nod {glue} nodes +(spaces). A node can have a subtype to that it can be recognized as for instance +a space related glue. + +The sequences of characters at some point are extended with \nod {disc} nodes +that relate to hyphenation. After that font logic can be applied and we get a +list where some characters can be replaced, for instance multiple characters can +become one ligature, and font kerns can be injected. This is driven by the +font properties. + +Boxes (like \prm {hbox} and \prm {vbox}) become \nod {hlist} or \nod {vlist} +nodes with \type {width}, \type {height}, \type {depth} and \type {shift} +properties and a pointer \type {list} to its actual content. Boxes can be +constructed explicitly or can be the result of subprocesses. For instance, when +lines are broken into paragraphs, the lines are a linked list of \nod {hlist} +nodes, possibly with glue and penalties in between. + +Internally nodes have a number. This number is actually an index in the memory +used to store nodes. + +So, to summarize: all that you enter as content eventually becomes a node, often +as part of a (nested) list structure. They have a relative small memory footprint +and carry only the minimal amount of information needed. In traditional \TEX\ a +character node only held the font and slot number, in \LUATEX\ we also store some +language related information, the expansion factor, etc. Now that we have access +to these nodes from \LUA\ it makes sense to be able to carry more information +with an node and this is where attributes kick in. + +\stopsubsection + +\startsubsection[title={Attribute registers}] + +\topicindex {attributes} + +Attributes are a completely new concept in \LUATEX. Syntactically, they behave a +lot like counters: attributes obey \TEX's nesting stack and can be used after +\prm {the} etc.\ just like the normal \prm {count} registers. + +\startsyntax +\attribute <16-bit number> <32-bit number>!crlf +\attributedef <16-bit number> +\stopsyntax + +Conceptually, an attribute is either \quote {set} or \quote {unset}. Unset +attributes have a special negative value to indicate that they are unset, that +value is the lowest legal value: \type {-"7FFFFFFF} in hexadecimal, a.k.a. +$-2147483647$ in decimal. It follows that the value \type {-"7FFFFFFF} cannot be +used as a legal attribute value, but you {\it can\/} assign \type {-"7FFFFFFF} to +\quote {unset} an attribute. All attributes start out in this \quote {unset} +state in \INITEX. + +Attributes can be used as extra counter values, but their usefulness comes mostly +from the fact that the numbers and values of all \quote {set} attributes are +attached to all nodes created in their scope. These can then be queried from any +\LUA\ code that deals with node processing. Further information about how to use +attributes for node list processing from \LUA\ is given in~\in {chapter}[nodes]. + +Attributes are stored in a sorted (sparse) linked list that are shared when +possible. This permits efficient testing and updating. You can define many +thousands of attributes but normally such a large number makes no sense and is +also not that efficient because each node carries a (possibly shared) link to a +list of currently set attributes. But they are a convenient extension and one of +the first extensions we implemented in \LUATEX. + +In \LUAMETATEX\ we try to minimize the memory footprint and creation of these +attribute lists more aggressive sharing them. This feature is still somewhat +experimental. + +\stopsubsection + +\startsubsection[title={Box attributes}] + +\topicindex {attributes} +\topicindex {boxes} + +Nodes typically receive the list of attributes that is in effect when they are +created. This moment can be quite asynchronous. For example: in paragraph +building, the individual line boxes are created after the \prm {par} command has +been processed, so they will receive the list of attributes that is in effect +then, not the attributes that were in effect in, say, the first or third line of +the paragraph. + +Similar situations happen in \LUATEX\ regularly. A few of the more obvious +problematic cases are dealt with: the attributes for nodes that are created +during hyphenation, kerning and ligaturing borrow their attributes from their +surrounding glyphs, and it is possible to influence box attributes directly. + +When you assemble a box in a register, the attributes of the nodes contained in +the box are unchanged when such a box is placed, unboxed, or copied. In this +respect attributes act the same as characters that have been converted to +references to glyphs in fonts. For instance, when you use attributes to implement +color support, each node carries information about its eventual color. In that +case, unless you implement mechanisms that deal with it, applying a color to +already boxed material will have no effect. Keep in mind that this +incompatibility is mostly due to the fact that separate specials and literals are +a more unnatural approach to colors than attributes. + +It is possible to fine-tune the list of attributes that are applied to a \type +{hbox}, \type {vbox} or \type {vtop} by the use of the keyword \type {attr}. The +\type {attr} keyword(s) should come before a \type {to} or \type {spread}, if +that is also specified. An example is: + +\startbuffer[tex] +\attribute997=123 +\attribute998=456 +\setbox0=\hbox {Hello} +\setbox2=\hbox attr 999 = 789 attr 998 = -"7FFFFFFF{Hello} +\stopbuffer + +\startbuffer[lua] + for b=0,2,2 do + for a=997, 999 do + tex.sprint("box ", b, " : attr ",a," : ",tostring(tex.box[b] [a])) + tex.sprint("\\quad\\quad") + tex.sprint("list ",b, " : attr ",a," : ",tostring(tex.box[b].list[a])) + tex.sprint("\\par") + end + end +\stopbuffer + +\typebuffer[tex] + +Box 0 now has attributes 997 and 998 set while box 2 has attributes 997 and 999 +set while the nodes inside that box will all have attributes 997 and 998 set. +Assigning the maximum negative value causes an attribute to be ignored. + +To give you an idea of what this means at the \LUA\ end, take the following +code: + +\typebuffer[lua] + +Later we will see that you can access properties of a node. The boxes here are so +called \nod {hlist} nodes that have a field \type {list} that points to the +content. Because the attributes are a list themselves you can access them by +indexing the node (here we do that with \type {[a]}. Running this snippet gives: + +\start + \getbuffer[tex] + \startpacked \tt + \ctxluabuffer[lua] + \stoppacked +\stop + +Because some values are not set we need to apply the \type {tostring} function +here so that we get the word \type {nil}. + +\stopsubsection + +\stopsection + +\startsection[title={\LUA\ related primitives}] + +\startsubsection[title={\prm {directlua}}] + +In order to merge \LUA\ code with \TEX\ input, a few new primitives are needed. +The primitive \prm {directlua} is used to execute \LUA\ code immediately. The +syntax is + +\startsyntax +\directlua +\stopsyntax + +The \syntax {} is expanded fully, and then fed into the \LUA\ +interpreter. After reading and expansion has been applied to the \syntax +{}, the resulting token list is converted to a string as if it was +displayed using \type {\the\toks}. On the \LUA\ side, each \prm {directlua} block +is treated as a separate chunk. In such a chunk you can use the \type {local} +directive to keep your variables from interfering with those used by the macro +package. + +The conversion to and from a token list means that you normally can not use \LUA\ +line comments (starting with \type {--}) within the argument. As there typically +will be only one \quote {line} the first line comment will run on until the end +of the input. You will either need to use \TEX|-|style line comments (starting +with \%), or change the \TEX\ category codes locally. Another possibility is to +say: + +\starttyping +\begingroup +\endlinechar=10 +\directlua ... +\endgroup +\stoptyping + +Then \LUA\ line comments can be used, since \TEX\ does not replace line endings +with spaces. Of course such an approach depends on the macro package that you +use. + +The \prm {directlua} command is expandable. Since it passes \LUA\ code to the +\LUA\ interpreter its expansion from the \TEX\ viewpoint is usually empty. +However, there are some \LUA\ functions that produce material to be read by \TEX, +the so called print functions. The most simple use of these is \type +{tex.print( s)}. The characters of the string \type {s} will be placed on +the \TEX\ input buffer, that is, \quote {before \TEX's eyes} to be read by \TEX\ +immediately. For example: + +\startbuffer +\count10=20 +a\directlua{tex.print(tex.count[10]+5)}b +\stopbuffer + +\typebuffer + +expands to + +\getbuffer + +Here is another example: + +\startbuffer +$\pi = \directlua{tex.print(math.pi)}$ +\stopbuffer + +\typebuffer + +will result in + +\getbuffer + +Note that the expansion of \prm {directlua} is a sequence of characters, not of +tokens, contrary to all \TEX\ commands. So formally speaking its expansion is +null, but it places material on a pseudo-file to be immediately read by \TEX, as +\ETEX's \prm {scantokens}. For a description of print functions look at \in +{section} [sec:luaprint]. + +Because the \syntax {} is a chunk, the normal \LUA\ error handling +is triggered if there is a problem in the included code. The \LUA\ error messages +should be clear enough, but the contextual information is still pretty bad. +Often, you will only see the line number of the right brace at the end of the +code. + +While on the subject of errors: some of the things you can do inside \LUA\ code +can break up \LUAMETATEX\ pretty bad. If you are not careful while working with +the node list interface, you may even end up with assertion errors from within +the \TEX\ portion of the executable. + +\stopsubsection + +\startsubsection[title={\lpr {luaescapestring}}] + +\topicindex {escaping} + +This primitive converts a \TEX\ token sequence so that it can be safely used as +the contents of a \LUA\ string: embedded backslashes, double and single quotes, +and newlines and carriage returns are escaped. This is done by prepending an +extra token consisting of a backslash with category code~12, and for the line +endings, converting them to \type {n} and \type {r} respectively. The token +sequence is fully expanded. + +\startsyntax +\luaescapestring +\stopsyntax + +Most often, this command is not actually the best way to deal with the +differences between \TEX\ and \LUA. In very short bits of \LUA\ code it is often +not needed, and for longer stretches of \LUA\ code it is easier to keep the code +in a separate file and load it using \LUA's \type {dofile}: + +\starttyping +\directlua { dofile("mysetups.lua") } +\stoptyping + +\stopsubsection + +\startsubsection[title={\lpr {luafunction}, \lpr {luafunctioncall} and \lpr {luadef}}] + +The \prm {directlua} commands involves tokenization of its argument (after +picking up an optional name or number specification). The tokenlist is then +converted into a string and given to \LUA\ to turn into a function that is +called. The overhead is rather small but when you have millions of calls it can +have some impact. For this reason there is a variant call available: \lpr +{luafunction}. This command is used as follows: + +\starttyping +\directlua { + local t = lua.get_functions_table() + t[1] = function() tex.print("!") end + t[2] = function() tex.print("?") end +} + +\luafunction1 +\luafunction2 +\stoptyping + +Of course the functions can also be defined in a separate file. There is no limit +on the number of functions apart from normal \LUA\ limitations. Of course there +is the limitation of no arguments but that would involve parsing and thereby give +no gain. The function, when called in fact gets one argument, being the index, so +in the following example the number \type {8} gets typeset. + +\starttyping +\directlua { + local t = lua.get_functions_table() + t[8] = function(slot) tex.print(slot) end +} +\stoptyping + +The \lpr {luafunctioncall} primitive does the same but is unexpandable, for +instance in an \prm {edef}. In addition \LUATEX\ provides a definer: + +\starttyping + \luadef\MyFunctionA 1 + \global\luadef\MyFunctionB 2 +\protected\global\luadef\MyFunctionC 3 +\stoptyping + +You should really use these commands with care. Some references get stored in +tokens and assume that the function is available when that token expands. On the +other hand, as we have tested this functionality in relative complex situations +normal usage should not give problems. + +\stopsubsection + +\startsubsection[title={\lpr {luabytecode} and \lpr {luabytecodecall}}] + +Analogue to the function callers discussed in the previous section we have byte +code callers. Again the call variant is unexpandable. + +\starttyping +\directlua { + lua.bytecode[9998] = function(s) + tex.sprint(s*token.scan_int()) + end + lua.bytecode[5555] = function(s) + tex.sprint(s*token.scan_dimen()) + end +} +\stoptyping + +This works with: + +\starttyping +\luabytecode 9998 5 \luabytecode 5555 5sp +\luabytecodecall9998 5 \luabytecodecall5555 5sp +\stoptyping + +The variable \type {s} in the code is the number of the byte code register that +can be used for diagnostic purposes. The advantage of bytecode registers over +function calls is that they are stored in the format (but without upvalues). + +\stopsubsection + +\stopsection + +\startsection[title={Catcode tables}] + +\startsubsection[title={Catcodes}] + +\topicindex {catcodes} + +Catcode tables are a new feature that allows you to switch to a predefined +catcode regime in a single statement. You can have lots of different tables, but +if you need a dozen you might wonder what you're doing. . This subsystem is +backward compatible: if you never use the following commands, your document will +not notice any difference in behaviour compared to traditional \TEX. The contents +of each catcode table is independent from any other catcode table, and its +contents is stored and retrieved from the format file. + +\stopsubsection + +\startsubsection[title={\lpr {catcodetable}}] + +\startsyntax +\catcodetable <15-bit number> +\stopsyntax + +The primitive \lpr {catcodetable} switches to a different catcode table. Such a +table has to be previously created using one of the two primitives below, or it +has to be zero. Table zero is initialized by \INITEX. + +\stopsubsection + +\startsubsection[title={\lpr {initcatcodetable}}] + +\startsyntax +\initcatcodetable <15-bit number> +\stopsyntax + +The primitive \lpr {initcatcodetable} creates a new table with catcodes +identical to those defined by \INITEX. The new catcode table is allocated +globally: it will not go away after the current group has ended. If the supplied +number is identical to the currently active table, an error is raised. The +initial values are: + +\starttabulate[|c|c|l|l|] +\DB catcode \BC character \BC equivalent \BC category \NC \NR +\TB +\NC 0 \NC \tttf \letterbackslash \NC \NC \type {escape} \NC \NR +\NC 5 \NC \tttf \letterhat\letterhat M \NC return \NC \type {car_ret} \NC \NR +\NC 9 \NC \tttf \letterhat\letterhat @ \NC null \NC \type {ignore} \NC \NR +\NC 10 \NC \tttf \NC space \NC \type {spacer} \NC \NR +\NC 11 \NC {\tttf a} \endash\ {\tttf z} \NC \NC \type {letter} \NC \NR +\NC 11 \NC {\tttf A} \endash\ {\tttf Z} \NC \NC \type {letter} \NC \NR +\NC 12 \NC everything else \NC \NC \type {other} \NC \NR +\NC 14 \NC \tttf \letterpercent \NC \NC \type {comment} \NC \NR +\NC 15 \NC \tttf \letterhat\letterhat ? \NC delete \NC \type {invalid_char} \NC \NR +\LL +\stoptabulate + +\stopsubsection + +\startsubsection[title={\lpr {savecatcodetable}}] + +\startsyntax +\savecatcodetable <15-bit number> +\stopsyntax + +\lpr {savecatcodetable} copies the current set of catcodes to a new table with +the requested number. The definitions in this new table are all treated as if +they were made in the outermost level. + +The new table is allocated globally: it will not go away after the current group +has ended. If the supplied number is the currently active table, an error is +raised. + +\stopsubsection + +\stopsection + +\startsection[title={Tokens, commands and strings}] + +\startsubsection[title={\lpr {scantextokens}}] + +\topicindex {tokens+scanning} + +The syntax of \lpr {scantextokens} is identical to \prm {scantokens}. This +primitive is a slightly adapted version of \ETEX's \prm {scantokens}. The +differences are: + +\startitemize +\startitem + The last (and usually only) line does not have a \prm {endlinechar} + appended. +\stopitem +\startitem + \lpr {scantextokens} never raises an EOF error, and it does not execute + \prm {everyeof} tokens. +\stopitem +\startitem + There are no \quote {\unknown\ while end of file \unknown} error tests + executed. This allows the expansion to end on a different grouping level or + while a conditional is still incomplete. +\stopitem +\stopitemize + +\stopsubsection + +\startsubsection[title={\lpr {toksapp}, \lpr {tokspre}, \lpr {etoksapp}, \lpr {etokspre}, +\lpr {gtoksapp}, \lpr {gtokspre}, \lpr {xtoksapp}, \lpr {xtokspre}}] + +Instead of: + +\starttyping +\toks0\expandafter{\the\toks0 foo} +\stoptyping + +you can use: + +\starttyping +\etoksapp0{foo} +\stoptyping + +The \type {pre} variants prepend instead of append, and the \type {e} variants +expand the passed general text. The \type {g} and \type {x} variants are global. + +\stopsubsection + +\startsubsection[title={\prm {csstring}, \lpr {begincsname} and \lpr {lastnamedcs}}] + +These are somewhat special. The \prm {csstring} primitive is like +\prm {string} but it omits the leading escape character. This can be +somewhat more efficient than stripping it afterwards. + +The \lpr {begincsname} primitive is like \prm {csname} but doesn't create +a relaxed equivalent when there is no such name. It is equivalent to + +\starttyping +\ifcsname foo\endcsname + \csname foo\endcsname +\fi +\stoptyping + +The advantage is that it saves a lookup (don't expect much speedup) but more +important is that it avoids using the \prm {if} test. The \lpr {lastnamedcs} +is one that should be used with care. The above example could be written as: + +\starttyping +\ifcsname foo\endcsname + \lastnamedcs +\fi +\stoptyping + +This is slightly more efficient than constructing the string twice (deep down in +\LUATEX\ this also involves some \UTF8 juggling), but probably more relevant is +that it saves a few tokens and can make code a bit more readable. + +\stopsubsection + +\startsubsection[title={\lpr {clearmarks}}] + +\topicindex {marks} + +This primitive complements the \ETEX\ mark primitives and clears a mark class +completely, resetting all three connected mark texts to empty. It is an +immediate command. + +\startsyntax +\clearmarks <16-bit number> +\stopsyntax + +\stopsubsection + +\startsubsection[title={\lpr {alignmark} and \lpr {aligntab}}] + +The primitive \lpr {alignmark} duplicates the functionality of \type {#} inside +alignment preambles, while \lpr {aligntab} duplicates the functionality of \type +{&}. + +\stopsubsection + +\startsubsection[title={\lpr {letcharcode}}] + +This primitive can be used to assign a meaning to an active character, as in: + +\starttyping +\def\foo{bar} \letcharcode123=\foo +\stoptyping + +This can be a bit nicer than using the uppercase tricks (using the property of +\prm {uppercase} that it treats active characters special). + +\stopsubsection + +\startsubsection[title={\lpr {glet}}] + +This primitive is similar to: + +\starttyping +\protected\def\glet{\global\let} +\stoptyping + +but faster (only measurable with millions of calls) and probably more convenient +(after all we also have \type {\gdef}). + +\stopsubsection + +\startsubsection[title={\lpr {expanded}, \lpr {immediateassignment} and \lpr {immediateassigned}}] + +\topicindex {expansion} + +The \lpr {expanded} primitive takes a token list and expands it content which can +come in handy: it avoids a tricky mix of \prm {expandafter} and \prm {noexpand}. +You can compare it with what happens inside the body of an \prm {edef}. But this +kind of expansion it still doesn't expand some primitive operations. + +\startbuffer +\newcount\NumberOfCalls + +\def\TestMe{\advance\NumberOfCalls1 } + +\edef\Tested{\TestMe foo:\the\NumberOfCalls} +\edef\Tested{\TestMe foo:\the\NumberOfCalls} +\edef\Tested{\TestMe foo:\the\NumberOfCalls} + +\meaning\Tested +\stopbuffer + +\typebuffer + +The result is a macro that has the not expanded code in its body: + +\getbuffer + +Instead we can define \tex {TestMe} in a way that expands the assignment +immediately. You need of course to be aware of preventing look ahead interference +by using a space or \tex {relax} (often an expression works better as it doesn't +leave an \tex {relax}). + +\startbuffer +\def\TestMe{\immediateassignment\advance\NumberOfCalls1 } + +\edef\Tested{\TestMe foo:\the\NumberOfCalls} +\edef\Tested{\TestMe foo:\the\NumberOfCalls} +\edef\Tested{\TestMe foo:\the\NumberOfCalls} + +\meaning\Tested +\stopbuffer + +\typebuffer + +This time the counter gets updates and we don't see interference in the +resulting \tex {Tested} macro: + +\getbuffer + +Here is a somewhat silly example of expanded comparison: + +\startbuffer +\def\expandeddoifelse#1#2#3#4% + {\immediateassignment\edef\tempa{#1}% + \immediateassignment\edef\tempb{#2}% + \ifx\tempa\tempb + \immediateassignment\def\next{#3}% + \else + \immediateassignment\def\next{#4}% + \fi + \next} + +\edef\Tested + {(\expandeddoifelse{abc}{def}{yes}{nop}/% + \expandeddoifelse{abc}{abc}{yes}{nop})} + +\meaning\Tested +\stopbuffer + +\typebuffer + +It gives: + +\getbuffer + +A variant is: + +\starttyping +\def\expandeddoifelse#1#2#3#4% + {\immediateassigned{ + \edef\tempa{#1}% + \edef\tempb{#2}% + }% + \ifx\tempa\tempb + \immediateassignment\def\next{#3}% + \else + \immediateassignment\def\next{#4}% + \fi + \next} +\stoptyping + +The possible error messages are the same as using assignments in preambles of +alignments and after the \prm {accent} command. The supported assignments are the +so called prefixed commands (except box assignments). + +\stopsubsection + +\startsubsection[title={\lpr {ignorepars}}] + +This primitives is like \prm {ignorespaces} but also skips paragraph ending +commands (normally \prm {par} and empty lines). + +\stopsubsection + +\startsubsection[title={\lpr {futureexpand}, \lpr {futureexpandis}, \lpr {futureexpandisap}}] + +These commands are use as: + +\starttyping +\futureexpand\sometoken\whenfound\whennotfound +\stoptyping + +When there is no match and a space was gobbled a space will be put back. The +\type {is} variant doesn't do that while the \type {isap} even skips \type +{\pars}, These characters stand for \quote {ignorespaces} and \quote +{ignorespacesandpars}. + +\stopsubsection + +\startsubsection[title={\lpr {aftergrouped}}] + +There is a new experimental feature that can inject multiple tokens to after the group +ends. An example demonstrate its use: + +\startbuffer +{ + \aftergroup A \aftergroup B \aftergroup C +test 1 : } + +{ + \aftergrouped{What comes next 1} + \aftergrouped{What comes next 2} + \aftergrouped{What comes next 3} +test 2 : } + + +{ + \aftergroup A \aftergrouped{What comes next 1} + \aftergroup B \aftergrouped{What comes next 2} + \aftergroup C \aftergrouped{What comes next 3} +test 3 : } + +{ + \aftergrouped{What comes next 1} \aftergroup A + \aftergrouped{What comes next 2} \aftergroup B + \aftergrouped{What comes next 3} \aftergroup C +test 4 : } +\stopbuffer + +\typebuffer + +This gives: + +\startpacked\getbuffer\stoppacked + +\stopsubsection + +\stopsection + +\startsection[title=Conditions] + +\startsubsection[title={\lpr{ifabsnum} and \lpr {ifabsdim}}] + +There are two tests that we took from \PDFTEX: + +\startbuffer +\ifabsnum -10 = 10 + the same number +\fi +\ifabsdim -10pt = 10pt + the same dimension +\fi +\stopbuffer + +\typebuffer + +This gives + +\blank {\tt \getbuffer} \blank + +\stopsubsection + +\startsubsection[title={\lpr{ifcmpnum}, \lpr {ifcmpdim}, \lpr {ifnumval}, \lpr +{ifdimval}, \lpr {ifchknum} and \lpr {ifchkdim}}] + +\topicindex {conditions+numbers} +\topicindex {conditions+dimensions} +\topicindex {numbers} +\topicindex {dimensions} + +New are the ones that compare two numbers or dimensions: + +\startbuffer +\ifcmpnum 5 8 less \or equal \else more \fi +\ifcmpnum 5 5 less \or equal \else more \fi +\ifcmpnum 8 5 less \or equal \else more \fi +\stopbuffer + +\typebuffer \blank {\tt \getbuffer} \blank + +and + +\startbuffer +\ifcmpdim 5pt 8pt less \or equal \else more \fi +\ifcmpdim 5pt 5pt less \or equal \else more \fi +\ifcmpdim 8pt 5pt less \or equal \else more \fi +\stopbuffer + +\typebuffer \blank {\tt \getbuffer} \blank + +There are also some number and dimension tests. All four expose the \type {\else} +branch when there is an error, but two also report if the number is less, equal +or more than zero. + +\startbuffer +\ifnumval -123 \or < \or = \or > \or ! \else ? \fi +\ifnumval 0 \or < \or = \or > \or ! \else ? \fi +\ifnumval 123 \or < \or = \or > \or ! \else ? \fi +\ifnumval abc \or < \or = \or > \or ! \else ? \fi + +\ifdimval -123pt \or < \or = \or > \or ! \else ? \fi +\ifdimval 0pt \or < \or = \or > \or ! \else ? \fi +\ifdimval 123pt \or < \or = \or > \or ! \else ? \fi +\ifdimval abcpt \or < \or = \or > \or ! \else ? \fi +\stopbuffer + +\typebuffer \blank {\tt \getbuffer} \blank + +\startbuffer +\ifchknum -123 \or okay \else bad \fi +\ifchknum 0 \or okay \else bad \fi +\ifchknum 123 \or okay \else bad \fi +\ifchknum abc \or okay \else bad \fi + +\ifchkdim -123pt \or okay \else bad \fi +\ifchkdim 0pt \or okay \else bad \fi +\ifchkdim 123pt \or okay \else bad \fi +\ifchkdim abcpt \or okay \else bad \fi +\stopbuffer + +\typebuffer \blank {\tt \getbuffer} \blank + +\stopsubsection + +\startsubsection[title={\lpr {iftok} and \lpr {ifcstok}}] + +\topicindex {conditions+tokens} +\topicindex {tokens} + +Comparing tokens and macros can be done with \type {\ifx}. Two extra test are +provided in \LUAMETATEX: + +\startbuffer +\def\ABC{abc} \def\DEF{def} \def\PQR{abc} \newtoks\XYZ \XYZ {abc} + +\iftok{abc}{def}\relax (same) \else [different] \fi +\iftok{abc}{abc}\relax [same] \else (different) \fi +\iftok\XYZ {abc}\relax [same] \else (different) \fi + +\ifcstok\ABC \DEF\relax (same) \else [different] \fi +\ifcstok\ABC \PQR\relax [same] \else (different) \fi +\ifcstok{abc}\ABC\relax [same] \else (different) \fi +\stopbuffer + +\typebuffer \startpacked[blank] {\tt\nospacing\getbuffer} \stoppacked + +You can check if a macro is is defined as protected with \type {\ifprotected} +while frozen macros can be tested with \type {\iffrozen}. A provisional \type +{\ifusercmd} tests will check if a command is defined at the user level (and this +one might evolve). + +\stopsubsection + +\startsubsection[title={\lpr {ifcondition}}] + +\topicindex {conditions} + +This is a somewhat special one. When you write macros conditions need to be +properly balanced in order to let \TEX's fast branch skipping work well. This new +primitive is basically a no||op flagged as a condition so that the scanner can +recognize it as an if|-|test. However, when a real test takes place the work is +done by what follows, in the next example \tex {something}. + +\starttyping +\unexpanded\def\something#1#2% + {\edef\tempa{#1}% + \edef\tempb{#2} + \ifx\tempa\tempb} + +\ifcondition\something{a}{b}% + \ifcondition\something{a}{a}% + true 1 + \else + false 1 + \fi +\else + \ifcondition\something{a}{a}% + true 2 + \else + false 2 + \fi +\fi +\stoptyping + +If you are familiar with \METAPOST, this is a bit like \type {vardef} where the macro +has a return value. Here the return value is a test. + +Experiments with something \type {\ifdef} actually worked ok but were rejected +because in the end it gave no advantage so this generic one has to do. The \type +{\ifcondition} test is basically is a no|-|op except when branches are skipped. +However, when a test is expected, the scanner gobbles it and the next test result +is used. Here is an other example: + +\startbuffer +\def\mytest#1% + {\ifabsdim#1>0pt\else + \expandafter \unless + \fi + \iftrue} + +\ifcondition\mytest{10pt}\relax non-zero \else zero \fi +\ifcondition\mytest {0pt}\relax non-zero \else zero \fi +\stopbuffer + +\typebuffer \blank {\tt \getbuffer} \blank + +The last expansion in a macro like \type {\mytest} has to be a condition and here +we use \type {\unless} to negate the result. + +\stopsubsection + +\startsubsection[title={\lpr {orelse}}] + +Sometimes you have successive tests that, when laid out in the source lead to +deep trees. The \type {\ifcase} test is an exception. Experiments with \type +{\ifcasex} worked out fine but eventually were rejected because we have many +tests so it would add a lot. As \LUAMETATEX\ permitted more experiments, +eventually an alternative was cooked up, one that has some restrictions but is +relative lightweight. It goes like this: + +\starttyping +\ifnum\count0<10 + less +\orelse\ifnum\count0=10 + equal +\else + more +\fi +\stoptyping + +The \type {\orelse} has to be followed by one of the if test commands, except +\type {\ifcondition}, and there can be an \type {\unless} in front of such a +command. These restrictions make it possible to stay in the current condition +(read: at the same level). If you need something more complex, using \type +{\orelse} is probably unwise anyway. In case you wonder about performance, there +is a little more checking needed when skipping branches but that can be +neglected. There is some gain due to staying at the same level but that is only +measurable when you runs tens of millions of complex tests and in that case it is +very likely to drown in the real action. It's a convenience mechanism, in the +sense that it can make your code look a bit easier to follow. + +There is an nice side effect of this mechanism. When you define: + +\starttyping +\def\quitcondition{\orelse\iffalse} +\stoptyping + +you can do this: + +\starttyping +\ifnum\count0<10 + less +\orelse\ifnum\count0=10 + equal + \quitcondition + indeed +\else + more +\fi +\stoptyping + +Of course it is only useful at the right level, so you might end up with cases like + +\starttyping +\ifnum\count0<10 + less +\orelse\ifnum\count0=10 + equal + \ifnum\count2=30 + \expandafter\quitcondition + \fi + indeed +\else + more +\fi +\stoptyping + +\stopsubsection + +\startsubsection[title={\lpr {ifprotected}, \lpr {frozen}, \lpr {iffrozen} and \lpr {ifusercmd}}] + +These checkers deal with control sequences. You can check if a command is a +protected one, that is, defined with the \type {\protected} prefix. A command is +frozen when it has been defined with the \type {\frozen} prefix. Beware: only +macros can be frozen. A user command is a command that is not part of the +predefined set of commands. This is an experimental command. + +\stopsubsection + +\stopsection + +\startsection[title={Boxes, rules and leaders}] + +\startsubsection[title={\lpr {outputbox}}] + +\topicindex {output} + +This integer parameter allows you to alter the number of the box that will be +used to store the page sent to the output routine. Its default value is 255, and +the acceptable range is from 0 to 65535. + +\startsyntax +\outputbox = 12345 +\stopsyntax + +\stopsubsection + +\startsubsection[title={\prm {vpack}, \prm {hpack} and \prm {tpack}}] + +These three primitives are like \prm {vbox}, \prm {hbox} and \prm {vtop} +but don't apply the related callbacks. + +\stopsubsection + +\startsubsection[title={\prm {vsplit}}] + +\topicindex {splitting} + +The \prm {vsplit} primitive has to be followed by a specification of the required +height. As alternative for the \type {to} keyword you can use \type {upto} to get +a split of the given size but result has the natural dimensions then. + +\stopsubsection + +\startsubsection[title={Images and reused box objects},reference=sec:imagedandforms] + +In original \TEX\ image support is dealt with via specials. It's not a native +feature of the engine. All that \TEX\ cares about is dimensions, so in practice +that meant: using a box with known dimensions that wraps a special that instructs +the backend to include an image. The wrapping is needed because a special itself +is a whatsit and as such has no dimensions. + +In \PDFTEX\ a special whatsit for images was introduced and that one {\em has} +dimensions. As a consequence, in several places where the engine to deal with the +dimensions of nodes, it now has to check the details of whatsits. By inheriting +code from \PDFTEX, the \LUATEX\ engine also had that property. However, at some +point this approach was abandoned and a more natural trick was used: images (and +box resources) became a special kind of rules, and as rules already have +dimensions, the code could be simplified. + +When direction nodes and localpar nodes also became first class nodes, whatsits +again became just that: nodes representing whatever you want, but without +dimensions, and therefore they could again be ignored when dimensions mattered. +And, because images were disguised as rules, as mentioned ,their dimensions +automatically were taken into account. This seperation between front and backend +cleaned up the code base already quite a bit. + +In \LUAMETATEX\ we still have the image specific subtypes for rules, but the +engine never looks at subtypes of rules. That was up to the backend. This means +that image support is not present in \LUAMETATEX. When an image specification was +parsed the special properties, like the filename, or additional attributes, were +stored in the backend and all that \LUATEX\ does is registering a reference to an +image s specification in the rule node. But, having no backend means nothing is +stored, which in turn would make the image inclusion primitives kind of weird. + +Therefore you need to realize that contrary to \LUATEX, {\em in \LUAMETATEX\ +support for images and box reuse is not built in}! However, we can assume that +an implementation uses rules in a similar fashion as \LUATEX\ does. So, you can +still consider images and box reuse to be core concepts. Here we just mention the +primitives that \LUATEX\ provides. They are not available in the engine but can +of course be implemented in \LUA. + +\starttabulate[|l|p|] +\DB command \BC explanation \NC \NR +\TB +\NC \lpr {saveboxresource} \NC save the box as an object to be included later \NC \NR +\NC \lpr {saveimageresource} \NC save the image as an object to be included later \NC \NR +\NC \lpr {useboxresource} \NC include the saved box object here (by index) \NC \NR +\NC \lpr {useimageresource} \NC include the saved image object here (by index) \NC \NR +\NC \lpr {lastsavedboxresourceindex} \NC the index of the last saved box object \NC \NR +\NC \lpr {lastsavedimageresourceindex} \NC the index of the last saved image object \NC \NR +\NC \lpr {lastsavedimageresourcepages} \NC the number of pages in the last saved image object \NC \NR +\LL +\stoptabulate + +An implementation probably should accepts the usual optional dimension parameters +for \type {\use...resource} in the same format as for rules. With images, these +dimensions are then used instead of the ones given to \lpr {useimageresource} but +the original dimensions are not overwritten, so that a \lpr {useimageresource} +without dimensions still provides the image with dimensions defined by \lpr +{saveimageresource}. These optional parameters are not implemented for \lpr +{saveboxresource}. + +\starttyping +\useimageresource width 20mm height 10mm depth 5mm \lastsavedimageresourceindex +\useboxresource width 20mm height 10mm depth 5mm \lastsavedboxresourceindex +\stoptyping + +Examples or optional entries are \type {attr} and \type {resources} that accept a +token list, and the \type {type} key. When set to non|-|zero the \type {/Type} +entry is omitted. A value of 1 or 3 still writes a \type {/BBox}, while 2 or 3 +will write a \type {/Matrix}. But, as said: this is entirely up to the backend. +Generic macro packages (like \type {tikz}) can use these assumed primitives so +one can best provide them. It is probably, for historic reasons, the only more or +less standardized image inclusion interface one can expect to work in all macro +packages. + +\stopsubsection + +\startsubsection[title={\lpr {hpack}, \lpr {vpack} and \lpr {tpack}}] + +These three primitives are the equivalents of \type {\hbox}, \type {\vbox} and +\type {\vtop} but they don't trigger the packaging related callbacks. Of course +one never know if content needs a treatment so using them should be done with +care. + +\stopsubsection + +\startsubsection[title={\lpr {nohrule} and \lpr {novrule}}] + +\topicindex {rules} + +Because introducing a new keyword can cause incompatibilities, two new primitives +were introduced: \lpr {nohrule} and \lpr {novrule}. These can be used to +reserve space. This is often more efficient than creating an empty box with fake +dimensions. + +\stopsubsection + +\startsubsection[title={\lpr {gleaders}},reference=sec:gleaders] + +\topicindex {leaders} + +This type of leaders is anchored to the origin of the box to be shipped out. So +they are like normal \prm {leaders} in that they align nicely, except that the +alignment is based on the {\it largest\/} enclosing box instead of the {\it +smallest\/}. The \type {g} stresses this global nature. + +\stopsubsection + +\stopsection + +\startsection[title={Languages}] + +\startsubsection[title={\lpr {hyphenationmin}}] + +\topicindex {languages} +\topicindex {hyphenation} + +This primitive can be used to set the minimal word length, so setting it to a value +of~$5$ means that only words of 6 characters and more will be hyphenated, of course +within the constraints of the \prm {lefthyphenmin} and \prm {righthyphenmin} +values (as stored in the glyph node). This primitive accepts a number and stores +the value with the language. + +\stopsubsection + +\startsubsection[title={\prm {boundary}, \prm {noboundary}, \prm {protrusionboundary} and \prm {wordboundary}}] + +The \prm {noboundary} command is used to inject a whatsit node but now injects a normal +node with type \nod {boundary} and subtype~0. In addition you can say: + +\starttyping +x\boundary 123\relax y +\stoptyping + +This has the same effect but the subtype is now~1 and the value~123 is stored. +The traditional ligature builder still sees this as a cancel boundary directive +but at the \LUA\ end you can implement different behaviour. The added benefit of +passing this value is a side effect of the generalization. The subtypes~2 and~3 +are used to control protrusion and word boundaries in hyphenation and have +related primitives. + +\stopsubsection + +\stopsection + +\startsection[title={Control and debugging}] + +\startsubsection[title={Tracing}] + +\topicindex {tracing} + +If \prm {tracingonline} is larger than~2, the node list display will also print +the node number of the nodes. + +\stopsubsection + +\startsubsection[title={\lpr {lastnodetype}, \lpr {lastnodesubtype}, \lpr +{currentiftype} and \lpr {internalcodesmode}.}] + +The \ETEX\ command \type {\lastnodetype} is limited to some nodes. When the +parameter \type {\internalcodesmode} is set to a non|-|zero value the normal +(internally used) numbers are reported. The same is true for \type +{\currentiftype}, as we have more conditionals and also use a different order. +The \type {\lastnodesubtype} is a bonus. + +\stopsubsection + +\stopsection + +\startsection[title={Files}] + +\startsubsection[title={File syntax}] + +\topicindex {files+names} + +\LUAMETATEX\ will accept a braced argument as a file name: + +\starttyping +\input {plain} +\openin 0 {plain} +\stoptyping + +This allows for embedded spaces, without the need for double quotes. Macro +expansion takes place inside the argument. + +The \lpr {tracingfonts} primitive that has been inherited from \PDFTEX\ has +been adapted to support variants in reporting the font. The reason for this +extension is that a csname not always makes sense. The zero case is the default. + +\starttabulate[|l|l|] +\DB value \BC reported \NC \NR +\TB +\NC \type{0} \NC \type{\foo xyz} \NC \NR +\NC \type{1} \NC \type{\foo (bar)} \NC \NR +\NC \type{2} \NC \type{ xyz} \NC \NR +\NC \type{3} \NC \type{ xyz} \NC \NR +\NC \type{4} \NC \type{} \NC \NR +\NC \type{5} \NC \type{} \NC \NR +\NC \type{6} \NC \type{ xyz} \NC \NR +\LL +\stoptabulate + +\stopsubsection + +\startsubsection[title={Writing to file}] + +\topicindex {files+writing} + +You can now open upto 127 files with \prm {openout}. When no file is open writes +will go to the console and log. The \type {write} related primitives have to be +implemented as part of a backend! As a consequence a system command is no longer +possible but one can use \type {os.execute} to do the same. + +\stopsubsection + +\stopsection + +\startsection[title={Math}] + +\topicindex {math} + +We will cover math extensions in its own chapter because not only the font +subsystem and spacing model have been enhanced (thereby introducing many new +primitives) but also because some more control has been added to existing +functionality. Much of this relates to the different approaches of traditional +\TEX\ fonts and \OPENTYPE\ math. + +\stopsection + +\startsection[title={Fonts}] + +\topicindex {fonts} + +Like math, we will cover fonts extensions in its own chapter. Here we stick to +mentioning that loading fonts is different in \LUAMETATEX. As in \LUATEX\ we have +the extra primitives \type {\fontid} and \type {\setfontid}, \type {\noligs} and +\type {\nokerns}, and \type {\nospaces}. The other new primitives in \LUATEX\ +have been dropped. + +\stopsection + +\startsection[title=Directions] + +\topicindex {\OMEGA} +\topicindex {\ALEPH} +\topicindex {directions} + +\startsubsection[title={Two directions}] + +The directional model in \LUAMETATEX\ is a simplified version the the model used +in \LUATEX. In fact, not much is happening at all: we only register a change in +direction. + +\stopsubsection + +\startsubsection[title={How it works}] + +The approach is that we try to make node lists balanced but also try to avoid +some side effects. What happens is quite intuitive if we forget about spaces +(turned into glue) but even there what happens makes sense if you look at it in +detail. However that logic makes in|-|group switching kind of useless when no +proper nested grouping is used: switching from right to left several times +nested, results in spacing ending up after each other due to nested mirroring. Of +course a sane macro package will manage this for the user but here we are +discussing the low level injection of directional information. + +This is what happens: + +\starttyping +\textdirection 1 nur {\textdirection 0 run \textdirection 1 NUR} nur +\stoptyping + +This becomes stepwise: + +\startnarrower +\starttyping +injected: [push 1]nur {[push 0]run [push 1]NUR} nur +balanced: [push 1]nur {[push 0]run [pop 0][push 1]NUR[pop 1]} nur[pop 0] +result : run {RUNrun } run +\stoptyping +\stopnarrower + +And this: + +\starttyping +\textdirection 1 nur {nur \textdirection 0 run \textdirection 1 NUR} nur +\stoptyping + +becomes: + +\startnarrower +\starttyping +injected: [+TRT]nur {nur [+TLT]run [+TRT]NUR} nur +balanced: [+TRT]nur {nur [+TLT]run [-TLT][+TRT]NUR[-TRT]} nur[-TRT] +result : run {run RUNrun } run +\stoptyping +\stopnarrower + +Now, in the following examples watch where we put the braces: + +\startbuffer +\textdirection 1 nur {{\textdirection 0 run} {\textdirection 1 NUR}} nur +\stopbuffer + +\typebuffer + +This becomes: + +\startnarrower +\getbuffer +\stopnarrower + +Compare this to: + +\startbuffer +\textdirection 1 nur {{\textdirection 0 run }{\textdirection 1 NUR}} nur +\stopbuffer + +\typebuffer + +Which renders as: + +\startnarrower +\getbuffer +\stopnarrower + +So how do we deal with the next? + +\startbuffer +\def\ltr{\textdirection 0\relax} +\def\rtl{\textdirection 1\relax} + +run {\rtl nur {\ltr run \rtl NUR \ltr run \rtl NUR} nur} +run {\ltr run {\rtl nur \ltr RUN \rtl nur \ltr RUN} run} +\stopbuffer + +\typebuffer + +It gets typeset as: + +\startnarrower +\startlines +\getbuffer +\stoplines +\stopnarrower + +We could define the two helpers to look back, pick up a skip, remove it and +inject it after the dir node. But that way we loose the subtype information that +for some applications can be handy to be kept as|-|is. This is why we now have a +variant of \lpr {textdirection} which injects the balanced node before the skip. +Instead of the previous definition we can use: + +\startbuffer[def] +\def\ltr{\linedirection 0\relax} +\def\rtl{\linedirection 1\relax} +\stopbuffer + +\typebuffer[def] + +and this time: + +\startbuffer[txt] +run {\rtl nur {\ltr run \rtl NUR \ltr run \rtl NUR} nur} +run {\ltr run {\rtl nur \ltr RUN \rtl nur \ltr RUN} run} +\stopbuffer + +\typebuffer[txt] + +comes out as a properly spaced: + +\startnarrower +\startlines +\getbuffer[def,txt] +\stoplines +\stopnarrower + +Anything more complex that this, like combination of skips and penalties, or +kerns, should be handled in the input or macro package because there is no way we +can predict the expected behaviour. In fact, the \lpr {linedir} is just a +convenience extra which could also have been implemented using node list parsing. + +\stopsubsection + +\startsubsection[title={Controlling glue with \lpr {breakafterdirmode}}] + +Glue after a dir node is ignored in the linebreak decision but you can bypass that +by setting \lpr {breakafterdirmode} to~\type {1}. The following table shows the +difference. Watch your spaces. + +\def\ShowSome#1{% + \BC \type{#1} + \NC \breakafterdirmode\zerocount\hsize\zeropoint#1 + \NC + \NC \breakafterdirmode\plusone\hsize\zeropoint#1 + \NC + \NC \NR +} + +\starttabulate[|l|Tp(1pt)|w(5em)|Tp(1pt)|w(5em)|] + \DB + \BC \type{0} + \NC + \BC \type{1} + \NC + \NC \NR + \TB + \ShowSome{pre {\textdirection 0 xxx} post} + \ShowSome{pre {\textdirection 0 xxx }post} + \ShowSome{pre{ \textdirection 0 xxx} post} + \ShowSome{pre{ \textdirection 0 xxx }post} + \ShowSome{pre { \textdirection 0 xxx } post} + \ShowSome{pre {\textdirection 0\relax\space xxx} post} + \LL +\stoptabulate + +\stopsubsection + +\startsubsection[title={Controling parshapes with \lpr {shapemode}}] + +Another adaptation to the \ALEPH\ directional model is control over shapes driven +by \prm {hangindent} and \prm {parshape}. This is controlled by a new parameter +\lpr {shapemode}: + +\starttabulate[|c|l|l|] +\DB value \BC \prm {hangindent} \BC \prm {parshape} \NC \NR +\TB +\BC \type{0} \NC normal \NC normal \NC \NR +\BC \type{1} \NC mirrored \NC normal \NC \NR +\BC \type{2} \NC normal \NC mirrored \NC \NR +\BC \type{3} \NC mirrored \NC mirrored \NC \NR +\LL +\stoptabulate + +The value is reset to zero (like \prm {hangindent} and \prm {parshape}) +after the paragraph is done with. You can use negative values to prevent +this. In \in {figure} [fig:shapemode] a few examples are given. + +\startplacefigure[reference=fig:shapemode,title={The effect of \type {shapemode}.}] + \startcombination[2*3] + {\ruledvbox \bgroup \setuptolerance[verytolerant] + \hsize .45\textwidth \switchtobodyfont[6pt] + \pardirection 0 \textdirection 0 + \hangindent 40pt \hangafter -3 + \leftskip10pt \input tufte \par + \egroup} {TLT: hangindent} + {\ruledvbox \bgroup \setuptolerance[verytolerant] + \hsize .45\textwidth \switchtobodyfont[6pt] + \pardirection 0 \textdirection 0 + \parshape 4 0pt .8\hsize 10pt .8\hsize 20pt .8\hsize 0pt \hsize + \input tufte \par + \egroup} {TLT: parshape} + {\ruledvbox \bgroup \setuptolerance[verytolerant] + \hsize .45\textwidth \switchtobodyfont[6pt] + \pardirection 1 \textdirection 1 + \hangindent 40pt \hangafter -3 + \leftskip10pt \input tufte \par + \egroup} {TRT: hangindent mode 0} + {\ruledvbox \bgroup \setuptolerance[verytolerant] + \hsize .45\textwidth \switchtobodyfont[6pt] + \pardirection 1 \textdirection 1 + \parshape 4 0pt .8\hsize 10pt .8\hsize 20pt .8\hsize 0pt \hsize + \input tufte \par + \egroup} {TRT: parshape mode 0} + {\ruledvbox \bgroup \setuptolerance[verytolerant] + \hsize .45\textwidth \switchtobodyfont[6pt] + \shapemode=3 + \pardirection 1 \textdirection 1 + \hangindent 40pt \hangafter -3 + \leftskip10pt \input tufte \par + \egroup} {TRT: hangindent mode 1 & 3} + {\ruledvbox \bgroup \setuptolerance[verytolerant] + \hsize .45\textwidth \switchtobodyfont[6pt] + \shapemode=3 + \pardirection 1 \textdirection 1 + \parshape 4 0pt .8\hsize 10pt .8\hsize 20pt .8\hsize 0pt \hsize + \input tufte \par + \egroup} {TRT: parshape mode 2 & 3} + \stopcombination +\stopplacefigure + +We have \type {\pardirection}, \type {\textdirection}, \type {\mathdirection} and +\type {\linedirection} that is like \type {\textdirection} but with some +additional (inline) glue checking. + +\stopsubsection + +\startsubsection[title=Orientations] + +As mentioned, the difference with \LUATEX\ is that we only have numeric +directions and that there are only two: left|-|to|-|right (\type {0}) and +right|-|to|-|left (\type {1}). The direction of a box is set with \type +{direction}. + +In addition to that boxes can now have an \type {orientation} keyword followed by +optional \type {xoffset} and|/|or \type {yoffset} keywords. The offsets don't +have consequences for the dimensions. The alternatives \type {xmove} and \type +{ymove} on the contrary are reflected in the dimensions. Just play with them. The +offsets and moves only are accepted when there is also an orientation, so no time +is wasted on testing for these rarely used keywords. There are related primitives +\type {\box...} that set these properties. + +As these are experimental it will not be explained here (yet). They are covered +in the descriptions of the development of \LUAMETATEX: articles and|/|or +documents in the \CONTEXT\ distribution. For now it is enough to know that the +orientation can be up, down, left or right (rotated) and that it has some +anchoring variants. Combined with the offsets this permits macro writers to +provide solutions for top|-|down and bottom|-|up writing directions, something +that is rather macro package specific and used for scripts that need +manipulations anyway. The \quote {old} vertical directions were never okay and +therefore not used. + +There are a couple of properties in boxes that you can set and query but that +only really take effect when the backend supports them. When usage on \CONTEXT\ +shows that is't okay, they will become official, so we just mention them: \type +{\boxdirection}, \type {\boxattr}, \type {\boxorientation}, \type {\boxxoffset}, +\type {\boxyoffset}, \type {\boxxmove}, \type {\boxymove} and \type {\boxtotal}. + +\stopsubsection + +\stopsection + +\startsection[title=Expressions] + +The \type {*expr} parsers now accept \type {:} as operator for integer division +(the \type {/} operators does rounding. This can be used for division compatible +with \type {\divide}. I'm still wondering if adding a couple of bit operators +makes sense (for integers). + +\stopsection + +\startsection[title=Nodes] + +The \ETEX\ primitive \type {\lastnodetype} is not honest in reporting the +internal numbers as it uses its own values. But you can set \type +{\internalcodesmode} to a non|-|zero value to get the real id's instead. In +addition there is \type {\lastnodesubtype}. + +Another last one is \type {\lastnamedcs} which holds the last match but this one +should be used with care because one never knows if in the meantime something +else \quote {last} has been seen. + +\stopsection + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/luametatex/luametatex-fonts.tex b/doc/context/sources/general/manuals/luametatex/luametatex-fonts.tex new file mode 100644 index 000000000..077d9e51e --- /dev/null +++ b/doc/context/sources/general/manuals/luametatex/luametatex-fonts.tex @@ -0,0 +1,596 @@ +% language=uk + +\environment luametatex-style + +\startcomponent luametatex-fonts + +\startchapter[reference=fonts,title={Fonts}] + +\startsection[title={Introduction}] + +Only traditional font support is built in, anything more needs to be implemented +in \LUA. This is conform the \LUATEX\ philosophy. When you pass a font to the +frontend only the dimensions matter, as these are used in typesetting, and +optionally ligatures and kerns when you rely on the built|-|in font handler. For +math some extra data is needed, like information about extensibles and next in +size glyphs. You can of course put more information in your \LUA\ tables because +when such a table is passed to \TEX\ only that what is needed is filtered from +it. + +Because there is no built|-|in backend, virtual font information is not used. If +you want to be compatible you'd better make sure that your tables are okay, and +in that case you can best consult the \LUATEX\ manual. For instance, parameters +like \type {extend} are backend related and the standard \LUATEX\ backend sets +the standard here. + +\stopsection + +\startsection[title={Defining fonts}] + +All \TEX\ fonts are represented to \LUA\ code as tables, and internally as +\CCODE\ structures. All keys in the table below are saved in the internal font +structure if they are present in the table passed to \type {font.define}. When +the callback is set, which is needed for \type {\font} to work, its function +gets the name and size passed, and it has to return a valid font identifier (a +positive number). + +For the engine to work well, the following information has to be present at +the font level: + +\starttabulate[|l|l|pl|] +\DB key \BC value type \BC description \NC \NR +\TB +\NC \type {name} \NC string \NC metric (file) name \NC \NR +\NC \type {characters} \NC table \NC the defined glyphs of this font \NC \NR +\NC \type {designsize} \NC number \NC expected size (default: 655360 == 10pt) \NC \NR +\NC \type {fonts} \NC table \NC locally used fonts \NC \NR +\NC \type {hyphenchar} \NC number \NC default: \TEX's \prm {hyphenchar} \NC \NR +\NC \type {parameters} \NC hash \NC default: 7 parameters, all zero \NC \NR +\NC \type {size} \NC number \NC the required scaling (by default the same as designsize) \NC \NR +\NC \type {skewchar} \NC number \NC default: \TEX's \prm {skewchar} \NC \NR +\NC \type {stretch} \NC number \NC the \quote {stretch} \NC \NR +\NC \type {shrink} \NC number \NC the \quote {shrink} \NC \NR +\NC \type {step} \NC number \NC the \quote {step} \NC \NR +\NC \type {nomath} \NC boolean \NC this key allows a minor speedup for text fonts; if it + is present and true, then \LUATEX\ will not check the + character entries for math|-|specific keys \NC \NR +\NC \type {oldmath} \NC boolean \NC this key flags a font as representing an old school \TEX\ + math font and disables the \OPENTYPE\ code path \NC \NR +\LL +\stoptabulate + +The \type {parameters} is a hash with mixed key types. There are seven possible +string keys, as well as a number of integer indices (these start from 8 up). The +seven strings are actually used instead of the bottom seven indices, because that +gives a nicer user interface. + +The names and their internal remapping are: + +\starttabulate[|l|c|] +\DB name \BC remapping \NC \NR +\TB +\NC \type {slant} \NC 1 \NC \NR +\NC \type {space} \NC 2 \NC \NR +\NC \type {space_stretch} \NC 3 \NC \NR +\NC \type {space_shrink} \NC 4 \NC \NR +\NC \type {x_height} \NC 5 \NC \NR +\NC \type {quad} \NC 6 \NC \NR +\NC \type {extra_space} \NC 7 \NC \NR +\LL +\stoptabulate + +The \type {characters} table is a list of character hashes indexed by an integer +number. The number is the \quote {internal code} \TEX\ knows this character by. +For proper paragraph building and math rendering the following fields can be +present in en entry in the \type {characters} table. You can of course add all +kind of extra fields. The engine only uses those that it needs for typesetting +a paragraph or formula. + +Each character hash itself is a hash. For example, here is the character \quote +{f} (decimal 102) in the font \type {cmr10 at 10pt}. The numbers that represent +dimensions are in scaled points. + +\starttyping +[102] = { + ["width"] = 200250, + ["height"] = 455111, + ["depth"] = 0, + ["italic"] = 50973, + ["kerns"] = { + [63] = 50973, + [93] = 50973, + [39] = 50973, + [33] = 50973, + [41] = 50973 + }, + ["ligatures"] = { + [102] = { ["char"] = 11, ["type"] = 0 }, + [108] = { ["char"] = 13, ["type"] = 0 }, + [105] = { ["char"] = 12, ["type"] = 0 } + } +} +\stoptyping + +Providing ligatures and kerns this way permits \TEX\ to construct ligatures and +add inter|-|character kerning. However, normally you will use an \OPENTYPE\ font +in combination with \LUA\ code that does this. In \CONTEXT\ we have base mode +that uses the engine, and node mode that uses \LUA. A monospaced font normally +has no ligatures and kerns and is normally not processed at all. + +\starttabulate[|l|l|pl|] +\DB key \BC type \BC description \NC\NR +\TB +\NC \type {width} \NC number \NC width in sp (default 0) \NC\NR +\NC \type {height} \NC number \NC height in sp (default 0) \NC\NR +\NC \type {depth} \NC number \NC depth in sp (default 0) \NC\NR +\NC \type {italic} \NC number \NC italic correction in sp (default 0) \NC\NR +\NC \type {top_accent} \NC number \NC top accent alignment place in sp (default zero) \NC\NR +\NC \type {bot_accent} \NC number \NC bottom accent alignment place, in sp (default zero) \NC\NR +\NC \type {left_protruding} \NC number \NC left protruding factor (\lpr {lpcode}) \NC\NR +\NC \type {right_protruding} \NC number \NC right protruding factor (\lpr {rpcode}) \NC\NR +\NC \type {expansion_factor} \NC number \NC expansion factor (\lpr {efcode}) \NC\NR +\NC \type {next} \NC number \NC \quote {next larger} character index \NC\NR +\NC \type {extensible} \NC table \NC constituent parts of an extensible recipe \NC\NR +\NC \type {vert_variants} \NC table \NC constituent parts of a vertical variant set \NC \NR +\NC \type {horiz_variants} \NC table \NC constituent parts of a horizontal variant set \NC \NR +\NC \type {kerns} \NC table \NC kerning information \NC\NR +\NC \type {ligatures} \NC table \NC ligaturing information \NC\NR +\NC \type {mathkern} \NC table \NC math cut-in specifications \NC\NR +\LL +\stoptabulate + +Two very special string indexes can be used also: \type {left_boundary} is a +virtual character whose ligatures and kerns are used to handle word boundary +processing. \type {right_boundary} is similar but not actually used for anything +(yet). + +The values of \type {top_accent}, \type {bot_accent} and \type {mathkern} are +used only for math accent and superscript placement, see \at {page} [math] in +this manual for details. The values of \type {left_protruding} and \type +{right_protruding} are used only when \lpr {protrudechars} is non-zero. Whether +or not \type {expansion_factor} is used depends on the font's global expansion +settings, as well as on the value of \lpr {adjustspacing}. + +A math character can have a \type {next} field that points to a next larger +shape. However, the presence of \type {extensible} will overrule \type {next}, if +that is also present. The \type {extensible} field in turn can be overruled by +\type {vert_variants}, the \OPENTYPE\ version. The \type {extensible} table is +very simple: + +\starttabulate[|l|l|p|] +\DB key \BC type \BC description \NC\NR +\TB +\NC \type{top} \NC number \NC top character index \NC\NR +\NC \type{mid} \NC number \NC middle character index \NC\NR +\NC \type{bot} \NC number \NC bottom character index \NC\NR +\NC \type{rep} \NC number \NC repeatable character index \NC\NR +\LL +\stoptabulate + +The \type {horiz_variants} and \type {vert_variants} are arrays of components. +Each of those components is itself a hash of up to five keys: + +\starttabulate[|l|l|p|] +\DB key \BC type \BC explanation \NC \NR +\TB +\NC \type{glyph} \NC number \NC The character index. Note that this is an encoding number, not a name. \NC \NR +\NC \type{extender} \NC number \NC One (1) if this part is repeatable, zero (0) otherwise. \NC \NR +\NC \type{start} \NC number \NC The maximum overlap at the starting side (in scaled points). \NC \NR +\NC \type{end} \NC number \NC The maximum overlap at the ending side (in scaled points). \NC \NR +\NC \type{advance} \NC number \NC The total advance width of this item. It can be zero or missing, + then the natural size of the glyph for character \type {component} + is used. \NC \NR +\LL +\stoptabulate + +The \type {kerns} table is a hash indexed by character index (and \quote +{character index} is defined as either a non|-|negative integer or the string +value \type {right_boundary}), with the values of the kerning to be applied, in +scaled points. + +The \type {ligatures} table is a hash indexed by character index (and \quote +{character index} is defined as either a non|-|negative integer or the string +value \type {right_boundary}), with the values being yet another small hash, with +two fields: + +\starttabulate[|l|l|p|] +\DB key \BC type \BC description \NC \NR +\TB +\NC \type{type} \NC number \NC the type of this ligature command, default 0 \NC \NR +\NC \type{char} \NC number \NC the character index of the resultant ligature \NC \NR +\LL +\stoptabulate + +The \type {char} field in a ligature is required. The \type {type} field inside a +ligature is the numerical or string value of one of the eight possible ligature +types supported by \TEX. When \TEX\ inserts a new ligature, it puts the new glyph +in the middle of the left and right glyphs. The original left and right glyphs +can optionally be retained, and when at least one of them is kept, it is also +possible to move the new \quote {insertion point} forward one or two places. The +glyph that ends up to the right of the insertion point will become the next +\quote {left}. + +\starttabulate[|l|c|l|l|] +\DB textual (Knuth) \BC number \BC string \BC result \NC\NR +\TB +\NC \type{l + r =: n} \NC 0 \NC \type{=:} \NC \type{|n} \NC\NR +\NC \type{l + r =:| n} \NC 1 \NC \type{=:|} \NC \type{|nr} \NC\NR +\NC \type{l + r |=: n} \NC 2 \NC \type{|=:} \NC \type{|ln} \NC\NR +\NC \type{l + r |=:| n} \NC 3 \NC \type{|=:|} \NC \type{|lnr} \NC\NR +\NC \type{l + r =:|> n} \NC 5 \NC \type{=:|>} \NC \type{n|r} \NC\NR +\NC \type{l + r |=:> n} \NC 6 \NC \type{|=:>} \NC \type{l|n} \NC\NR +\NC \type{l + r |=:|> n} \NC 7 \NC \type{|=:|>} \NC \type{l|nr} \NC\NR +\NC \type{l + r |=:|>> n} \NC 11 \NC \type{|=:|>>} \NC \type{ln|r} \NC\NR +\LL +\stoptabulate + +The default value is~0, and can be left out. That signifies a \quote {normal} +ligature where the ligature replaces both original glyphs. In this table the~\type {|} +indicates the final insertion point. + +\stopsection + +\startsection[reference=virtualfonts,title={Virtual fonts}] + +% \topicindex {fonts+virtual} + +Virtual fonts have been introduced to overcome limitations of good old \TEX. They +were mostly use for providing a direct mapping from for instance accented +characters onto a glyph. The backend was responsible for turning a reference to a +character slot into a real glyph, possibly constructed from other glyphs. In our +case there is no backend so there is also no need to pass this information +through \TEX. But it can of course be part of the font information and because it is +a kind of standard, we describe it here. + +A character is virtual when it has a \type {commands} array as part of the data. +A virtual character can itself point to virtual characters but be careful with +nesting as you can create loops and overflow the stack (which often indicates an +error anyway). + +At the font level there can be a \type {fonts} an (indexed) \LUA\ table. The +values are one- or two|-|key hashes themselves, each entry indicating one of the +base fonts in a virtual font. In case your font is referring to itself in for +instance a virtual font, you can use the \type {slot} command with a zero font +reference, which indicates that the font itself is used. So, a table looks like +this: + +\starttyping +fonts = { + { name = "ptmr8a", size = 655360 }, + { name = "psyr", size = 600000 }, + { id = 38 } +} +\stoptyping + +The first referenced font (at index~1) in this virtual font is \type {ptrmr8a} +loaded at 10pt, and the second is \type {psyr} loaded at a little over 9pt. The +third one is a previously defined font that is known to \LUATEX\ as font id~38. +The array index numbers are used by the character command definitions that are +part of each character. + +The \type {commands} array is a hash where each item is another small array, +with the first entry representing a command and the extra items being the +parameters to that command. The allowed commands and their arguments are: + +\starttabulate[|l|l|l|p|] +\DB command \BC arguments \BC type \BC description \NC \NR +\TB +\NC \type{font} \NC 1 \NC number \NC select a new font from the local \type {fonts} table \NC \NR +\NC \type{char} \NC 1 \NC number \NC typeset this character number from the current font, + and move right by the character's width \NC \NR +\NC \type{node} \NC 1 \NC node \NC output this node (list), and move right + by the width of this list\NC \NR +\NC \type{slot} \NC 2 \NC 2 numbers \NC a shortcut for the combination of a font and char command\NC \NR +\NC \type{push} \NC 0 \NC \NC save current position\NC \NR +\NC \type{nop} \NC 0 \NC \NC do nothing \NC \NR +\NC \type{pop} \NC 0 \NC \NC pop position \NC \NR +\NC \type{rule} \NC 2 \NC 2 numbers \NC output a rule $ht*wd$, and move right. \NC \NR +\NC \type{down} \NC 1 \NC number \NC move down on the page \NC \NR +\NC \type{right} \NC 1 \NC number \NC move right on the page \NC \NR +\NC \type{special} \NC 1 \NC string \NC output a \prm {special} command \NC \NR +\NC \type{pdf} \NC 2 \NC 2 strings \NC output a \PDF\ literal, the first string is one of \type {origin}, + \type {page}, \type {text}, \type {font}, \type {direct} or \type {raw}; if you + have one string only \type {origin} is assumed \NC \NR +\NC \type{lua} \NC 1 \NC string, + function \NC execute a \LUA\ script when the glyph is embedded; in case of a + function it gets the font id and character code passed \NC \NR +\NC \type{image} \NC 1 \NC image \NC output an image (the argument can be either an \type {} variable or an \type {image_spec} table) \NC \NR +\NC \type{comment} \NC any \NC any \NC the arguments of this command are ignored \NC \NR +\LL +\stoptabulate + +When a font id is set to~0 then it will be replaced by the currently assigned +font id. This prevents the need for hackery with future id's. + +The \type {pdf} option also accepts a \type {mode} keyword in which case the +third argument sets the mode. That option will change the mode in an efficient +way (passing an empty string would result in an extra empty lines in the \PDF\ +file. This option only makes sense for virtual fonts. The \type {font} mode only +makes sense in virtual fonts. Modes are somewhat fuzzy and partially inherited +from \PDFTEX. + +\starttabulate[|l|p|] +\DB mode \BC description \NC \NR +\TB +\NC \type {origin} \NC enter page mode and set the position \NC \NR +\NC \type {page} \NC enter page mode \NC \NR +\NC \type {text} \NC enter text mode \NC \NR +\NC \type {font} \NC enter font mode (kind of text mode, only in virtual fonts) \NC \NR +\NC \type {always} \NC finish the current string and force a transform if needed \NC \NR +\NC \type {raw} \NC finish the current string \NC \NR +\LL +\stoptabulate + +You always need to check what \PDF\ code is generated because there can be all +kind of interferences with optimization in the backend and fonts are complicated +anyway. Here is a rather elaborate glyph commands example using such keys: + +\starttyping +... +commands = { + { "push" }, -- remember where we are + { "right", 5000 }, -- move right about 0.08pt + { "font", 3 }, -- select the fonts[3] entry + { "char", 97 }, -- place character 97 (ASCII 'a') + -- { "slot", 2, 97 }, -- an alternative for the previous two + { "pop" }, -- go all the way back + { "down", -200000 }, -- move upwards by about 3pt + { "special", "pdf: 1 0 0 rg" } -- switch to red color + -- { "pdf", "origin", "1 0 0 rg" } -- switch to red color (alternative) + { "rule", 500000, 20000 } -- draw a bar + { "special", "pdf: 0 g" } -- back to black + -- { "pdf", "origin", "0 g" } -- back to black (alternative) +} +... +\stoptyping + +The default value for \type {font} is always~1 at the start of the +\type {commands} array. Therefore, if the virtual font is essentially only a +re|-|encoding, then you do usually not have created an explicit \quote {font} +command in the array. + +Rules inside of \type {commands} arrays are built up using only two dimensions: +they do not have depth. For correct vertical placement, an extra \type {down} +command may be needed. + +Regardless of the amount of movement you create within the \type {commands}, the +output pointer will always move by exactly the width that was given in the \type +{width} key of the character hash. Any movements that take place inside the \type +{commands} array are ignored on the upper level. + +The special can have a \type {pdf:}, \type {pdf:origin:}, \type {pdf:page:}, +\type {pdf:direct:} or \type {pdf:raw:} prefix. When you have to concatenate +strings using the \type {pdf} command might be more efficient. + +The fields mentioned above can be found in external fonts. It is good to keep in +mind that we can extend this model, given that the backend knows what to do with +it. + +\stopsection + +\startsection[title={Additional \TEX\ commands}] + +\startsubsection[title={Font syntax}] + +\topicindex {fonts} + +\LUATEX\ will accept a braced argument as a font name: + +\starttyping +\font\myfont = {cmr10} +\stoptyping + +This allows for embedded spaces, without the need for double quotes. Macro +expansion takes place inside the argument. + +\stopsubsection + +\startsubsection[title={\lpr {fontid} and \lpr {setfontid}}] + +\startsyntax +\fontid\font +\stopsyntax + +This primitive expands into a number. It is not a register so there is no need to +prefix with \prm {number} (and using \prm {the} gives an error). The currently +used font id is \fontid\font. Here are some more: + +\starttabulate[|l|c|c|] +\DB style \BC command \BC font id \NC \NR +\TB +\NC normal \NC \type {\tf} \NC \tf \fontid\font \NC \NR +\NC bold \NC \type {\bf} \NC \bf \fontid\font \NC \NR +\NC italic \NC \type {\it} \NC \it \fontid\font \NC \NR +\NC bold italic \NC \type {\bi} \NC \bi \fontid\font \NC \NR +\LL +\stoptabulate + +These numbers depend on the macro package used because each one has its own way +of dealing with fonts. They can also differ per run, as they can depend on the +order of loading fonts. For instance, when in \CONTEXT\ virtual math \UNICODE\ +fonts are used, we can easily get over a hundred ids in use. Not all ids have to +be bound to a real font, after all it's just a number. + +The primitive \lpr {setfontid} can be used to enable a font with the given id, +which of course needs to be a valid one. + +\stopsubsection + +\startsubsection[title={\lpr {noligs} and \lpr {nokerns}}] + +\topicindex {ligatures+suppress} +\topicindex {kerns+suppress} + +These primitives prohibit ligature and kerning insertion at the time when the +initial node list is built by \LUATEX's main control loop. You can enable these +primitives when you want to do node list processing of \quote {characters}, where +\TEX's normal processing would get in the way. + +\startsyntax +\noligs !crlf +\nokerns +\stopsyntax + +These primitives can also be implemented by overloading the ligature building and +kerning functions, i.e.\ by assigning dummy functions to their associated +callbacks. Keep in mind that when you define a font (using \LUA) you can also +omit the kern and ligature tables, which has the same effect as the above. + +\stopsubsection + +\startsubsection[title={\type{\nospaces}}] + +\topicindex {spaces+suppress} + +This new primitive can be used to overrule the usual \prm {spaceskip} related +heuristics when a space character is seen in a text flow. The value~\type{1} +triggers no injection while \type{2} results in injection of a zero skip. In \in +{figure} [fig:nospaces] we see the results for four characters separated by a +space. + +\startplacefigure[reference=fig:nospaces,title={The \lpr {nospaces} options.}] +\startcombination[3*2] + {\ruledhbox to 5cm{\vtop{\hsize 10mm\nospaces=0\relax x x x x \par}\hss}} {\type {0 / hsize 10mm}} + {\ruledhbox to 5cm{\vtop{\hsize 10mm\nospaces=1\relax x x x x \par}\hss}} {\type {1 / hsize 10mm}} + {\ruledhbox to 5cm{\vtop{\hsize 10mm\nospaces=2\relax x x x x \par}\hss}} {\type {2 / hsize 10mm}} + {\ruledhbox to 5cm{\vtop{\hsize 1mm\nospaces=0\relax x x x x \par}\hss}} {\type {0 / hsize 1mm}} + {\ruledhbox to 5cm{\vtop{\hsize 1mm\nospaces=1\relax x x x x \par}\hss}} {\type {1 / hsize 1mm}} + {\ruledhbox to 5cm{\vtop{\hsize 1mm\nospaces=2\relax x x x x \par}\hss}} {\type {2 / hsize 1mm}} +\stopcombination +\stopplacefigure + +\stopsubsection + +\startsubsection[title={\type{\protrusionboundary}}] + +\topicindex {protrusion} +\topicindex {boundaries} + +The protrusion detection mechanism is enhanced a bit to enable a bit more complex +situations. When protrusion characters are identified some nodes are skipped: + +\startitemize[packed,columns,two] +\startitem zero glue \stopitem +\startitem penalties \stopitem +\startitem empty discretionaries \stopitem +\startitem normal zero kerns \stopitem +\startitem rules with zero dimensions \stopitem +\startitem math nodes with a surround of zero \stopitem +\startitem dir nodes \stopitem +\startitem empty horizontal lists \stopitem +\startitem local par nodes \stopitem +\startitem inserts, marks and adjusts \stopitem +\startitem boundaries \stopitem +\startitem whatsits \stopitem +\stopitemize + +Because this can not be enough, you can also use a protrusion boundary node to +make the next node being ignored. When the value is~1 or~3, the next node will be +ignored in the test when locating a left boundary condition. When the value is~2 +or~3, the previous node will be ignored when locating a right boundary condition +(the search goes from right to left). This permits protrusion combined with for +instance content moved into the margin: + +\starttyping +\protrusionboundary1\llap{!\quad}«Who needs protrusion?» +\stoptyping + +\stopsubsection + +\stopsection + +\startsection[title={The \LUA\ font library}][library=font] + +\startsubsection[title={Introduction}] + +The \LUA\ font library is reduced to a few commands. Contrary to \LUATEX\ there +is no loading of \TFM\ or \VF\ files. The explanation of the following commands +is in the \LUATEX\ manual. + +\starttabulate[|l|pl|] +\DB function \BC description \NC\NR +\TB +\NC \type {current} \NC returns the id of the currently active font \NC \NR +\NC \type {max} \NC returns the last assigned font identifier \NC \NR +\NC \type {setfont} \NC enables a font setfont (sets the current font id) \NC \NR +\NC \type {addcharacters} \NC adds characters to a font \NC \NR +\NC \type {define} \NC defined a font \NC \NR +\NC \type {id} \NC returns the id that relates to a command name \NC \NR +\LL +\stoptabulate + +For practical reasons the management of font identifiers is still done by \TEX\ +but it can become an experiment to delegate that to \LUA\ as well. + +\stopsubsection + +\startsubsection[title={Defining a font with \type {define}, \type {addcharacters} and \type +{setfont}}] + +\topicindex {fonts+define} +\topicindex {fonts+extend} + +Normally you will use a callback to define a font but there's also a \LUA\ +function that does the job. + +\startfunctioncall +id = font.define(
f) +\stopfunctioncall + +Within reasonable bounds you can extend a font after it has been defined. Because +some properties are best left unchanged this is limited to adding characters. + +\startfunctioncall +font.addcharacters(,
f) +\stopfunctioncall + +The table passed can have the fields \type {characters} which is a (sub)table +like the one used in define, and for virtual fonts a \type {fonts} table can be +added. The characters defined in the \type {characters} table are added (when not +yet present) or replace an existing entry. Keep in mind that replacing can have +side effects because a character already can have been used. Instead of posing +restrictions we expect the user to be careful. The \type {setfont} helper is +a more drastic replacer and only works when a font has not been used yet. + +\stopsubsection + +\startsubsection[title={Font ids: \type {id}, \type {max} and \type {current}}] + +\topicindex {fonts+id} +\topicindex {fonts+current} + +\startfunctioncall + i = font.id( csname) +\stopfunctioncall + +This returns the font id associated with \type {csname}, or $-1$ if \type +{csname} is not defined. + +\startfunctioncall + i = font.max() +\stopfunctioncall + +This is the largest used index so far. The currently active font id can be +queried or set with: + +\startfunctioncall + i = font.current() +font.current( i) +\stopfunctioncall + +\stopsubsection + +% \startsubsection[title={Glyph data: \lpr {glyphdata}] +% +% This primitive can be used to set an additional glyph property. Of course it's very +% macro package dependant what is done with that. Consider it an experiment (we had +% some room left in the glyphs data structure). It's basically an single attribute. +% +% \stopsubsection + +\stopsection + +\stopchapter + +\stopcomponent + diff --git a/doc/context/sources/general/manuals/luametatex/luametatex-libraries.tex b/doc/context/sources/general/manuals/luametatex/luametatex-libraries.tex new file mode 100644 index 000000000..d8210ac48 --- /dev/null +++ b/doc/context/sources/general/manuals/luametatex/luametatex-libraries.tex @@ -0,0 +1,573 @@ +% language=uk + +\environment luametatex-style + +\startcomponent luametatex-libraries + +\startchapter[reference=libraries,title={Extra libraries}] + +\startsection[title=Introduction] + +The libraries can be grouped in categories like fonts, languages, \TEX, +\METAPOST, \PDF, etc. There are however also some that are more general puspose +and these are discussed here. + +\stopsection + +\startsection[title=File and string readers: \type {fio} and type {sio}] + +This library provides a set of functions for reading numbers from a file and +in addition to the regular \type {io} library functions. The following +work on normal \LUA\ file handles. + +\starttabulate[|Tw(12em)|T|T|] +\DB name \BC arguments \BC results \NC \NR +\TB +\NC readcardinal1 \NC (f) \NC a 1 byte unsigned integer \NC \NR +\NC readcardinal2 \NC (f) \NC a 2 byte unsigned integer \NC \NR +\NC readcardinal3 \NC (f) \NC a 3 byte unsigned integer \NC \NR +\NC readcardinal4 \NC (f) \NC a 4 byte unsigned integer \NC \NR +\NC readcardinaltable \NC (f,n,b) \NC \type {n} cardinals of \type {b} bytes \NC \NR +\NC readinteger1 \NC (f) \NC a 1 byte signed integer \NC \NR +\NC readinteger2 \NC (f) \NC a 2 byte signed integer \NC \NR +\NC readinteger3 \NC (f) \NC a 3 byte signed integer \NC \NR +\NC readinteger4 \NC (f) \NC a 4 byte signed integer \NC \NR +\NC readintegertable \NC (f,n,b) \NC \type {n} integers of \type {b} bytes \NC \NR +\NC readfixed2 \NC (f) \NC a 2 byte float (used in font files) \NC \NR +\NC readfixed4 \NC (f) \NC a 4 byte float (used in font files) \NC \NR +\NC read2dot14 \NC (f) \NC a 2 byte float (used in font files) \NC \NR +\NC setposition \NC (f,p) \NC goto position \type {p} \NC \NR +\NC getposition \NC (f) \NC get the current position \NC \NR +\NC skipposition \NC (f,n) \NC skip \type {n} positions \NC \NR +\NC readbytes \NC (f,n) \NC \type {n} bytes \NC \NR +\NC readbytetable \NC (f,n) \NC \type {n} bytes\NC \NR +\LL +\stoptabulate + +When relevant there are also variants that end with \type {le} that do it the +little endian way. + +A similar set of function as in the \type {fio} library is available in the \type +{sio} library: \libidx {sio} {readcardinal1}, \libidx {sio} {readcardinal2}, +\libidx {sio} {readcardinal3}, \libidx {sio} {readcardinal4}, \libidx {sio} +{readcardinaltable}, \libidx {sio} {readinteger1}, \libidx {sio} {readinteger2}, +\libidx {sio} {readinteger3}, \libidx {sio} {readinteger4}, \libidx {sio} +{readintegertable}, \libidx {sio} {readfixed2}, \libidx {sio} {readfixed4}, +\libidx {sio} {read2dot14}, \libidx {sio} {setposition}, \libidx {sio} +{getposition}, \libidx {sio} {skipposition}, \libidx {sio} {readbytes} and +\libidx {sio} {readbytetable}. Here the first argument is a string instead of a +file handle. + +\stopsection + +\startsection[title=\type{md5}] + +\starttabulate[|Tw(12em)|T|T|] +\DB name \BC arguments \BC results \NC \NR +\TB +\NC sum \NC \NC \NC \NR +\NC hex \NC \NC \NC \NR +\NC HEX \NC \NC \NC \NR +\LL +\stoptabulate + +\stopsection + +\startsection[title=\type{sha2}] + +\starttabulate[|Tw(12em)|T|T|] +\DB name \BC arguments \BC results \NC \NR +\TB +\NC digest256 \NC \NC \NC \NR +\NC digest384 \NC \NC \NC \NR +\NC digest512 \NC \NC \NC \NR +\LL +\stoptabulate + +\stopsection + +% \startsection[title=\type{flate}] +% +% \starttabulate[|Tw(12em)|T|T|] +% \DB name \BC arguments \BC results \NC \NR +% \TB +% \NC flate_compress \NC \NC \NC \NR +% \NC flate_decompress \NC \NC \NC \NR +% \NC zip_compress \NC \NC \NC \NR +% \NC zip_decompress \NC \NC \NC \NR +% \NC gz_compress \NC \NC \NC \NR +% \NC gz_decompress \NC \NC \NC \NR +% \NC update_adler32 \NC \NC \NC \NR +% \NC update_crc32 \NC \NC \NC \NR +% \LL +% \stoptabulate +% +% \stopsection + +\startsection[title=\type{xzip}] + +\starttabulate[|Tw(12em)|T|T|] +\DB name \BC arguments \BC results \NC \NR +\TB +\NC compress \NC \NC \NC \NR +\NC decompress \NC \NC \NC \NR +\NC adler32 \NC \NC \NC \NR +\NC crc32 \NC \NC \NC \NR +\LL +\stoptabulate + +\stopsection + +\startsection[title=\type{xmath}] + +This library just opens up standard \CCODE\ math library and the main reason for +it being there is that it permits advanced graphics in \METAPOST\ (via the \LUA\ +interface). There are three constant values: + +\starttabulate[|Tw(12em)|T|T|] +\DB name \BC arguments \BC results \NC \NR +\TB +\NC inf \NC \emdash \NC \cldcontext{xmath.inf} \NC \NR +\NC nan \NC \emdash \NC \cldcontext{xmath.nan} \NC \NR +\NC pi \NC \emdash \NC \cldcontext{xmath.pi} \NC \NR +\LL +\stoptabulate + +and a lot of functions: + +\starttabulate[|Tw(12em)|T|T|] +\DB name \BC arguments \BC results \NC \NR +\TB +\NC acos \NC (a) \NC \NC \NR +\NC acosh \NC (a) \NC \NC \NR +\NC asin \NC (a) \NC \NC \NR +\NC asinh \NC (a) \NC \NC \NR +\NC atan \NC (a[,b]) \NC \NC \NR +\NC atan2 \NC (a[,b]) \NC \NC \NR +\NC atanh \NC (a) \NC \NC \NR +\NC cbrt \NC (a) \NC \NC \NR +\NC ceil \NC (a) \NC \NC \NR +\NC copysign \NC (a,b) \NC \NC \NR +\NC cos \NC (a) \NC \NC \NR +\NC cosh \NC (a) \NC \NC \NR +\NC deg \NC (a) \NC \NC \NR +\NC erf \NC (a) \NC \NC \NR +\NC erfc \NC (a) \NC \NC \NR +\NC exp \NC (a) \NC \NC \NR +\NC exp2 \NC (a) \NC \NC \NR +\NC expm1 \NC (a) \NC \NC \NR +\NC fabs \NC (a) \NC \NC \NR +\NC fdim \NC (a,b) \NC \NC \NR +\NC floor \NC (a) \NC \NC \NR +\NC fma \NC (a,b,c) \NC \NC \NR +\NC fmax \NC (...) \NC \NC \NR +\NC fmin \NC (...) \NC \NC \NR +\NC fmod \NC (a,b) \NC \NC \NR +\NC frexp \NC (a,b) \NC \NC \NR +\NC gamma \NC (a) \NC \NC \NR +\NC hypot \NC (a,b) \NC \NC \NR +\NC isfinite \NC (a) \NC \NC \NR +\NC isinf \NC (a) \NC \NC \NR +\NC isnan \NC (a) \NC \NC \NR +\NC isnormal \NC (a) \NC \NC \NR +\NC j0 \NC (a) \NC \NC \NR +\NC j1 \NC (a) \NC \NC \NR +\NC jn \NC (a,b) \NC \NC \NR +\NC ldexp \NC (a,b) \NC \NC \NR +\NC lgamma \NC (a) \NC \NC \NR +\NC l0 \NC (a) \NC \NC \NR +\NC l1 \NC (a) \NC \NC \NR +\NC ln \NC (a,b) \NC \NC \NR +\NC log \NC (a[,b]) \NC \NC \NR +\NC log10 \NC (a) \NC \NC \NR +\NC log1p \NC (a) \NC \NC \NR +\NC log2 \NC (a) \NC \NC \NR +\NC logb \NC (a) \NC \NC \NR +\NC modf \NC (a,b) \NC \NC \NR +\NC nearbyint \NC (a) \NC \NC \NR +\NC nextafter \NC (a,b) \NC \NC \NR +\NC pow \NC (a,b) \NC \NC \NR +\NC rad \NC (a) \NC \NC \NR +\NC remainder \NC (a,b) \NC \NC \NR +\NC remquo \NC (a,b) \NC \NC \NR +\NC round \NC (a) \NC \NC \NR +\NC scalbn \NC (a,b) \NC \NC \NR +\NC sin \NC (a) \NC \NC \NR +\NC sinh \NC (a) \NC \NC \NR +\NC sqrt \NC (a) \NC \NC \NR +\NC tan \NC (a) \NC \NC \NR +\NC tanh \NC (a) \NC \NC \NR +\NC tgamma \NC (a) \NC \NC \NR +\NC trunc \NC (a) \NC \NC \NR +\NC y0 \NC (a) \NC \NC \NR +\NC y1 \NC (a) \NC \NC \NR +\NC yn \NC (a) \NC \NC \NR +\LL +\stoptabulate + +\stopsection + +\startsection[title=\type{xcomplex}] + +\LUAMETATEX\ also provides a complex library \type {xcomplex}. The complex +number is a userdatum: + +\starttabulate[|Tw(12em)|T|T|] +\DB name \BC arguments \BC results \NC \NR +\TB +\NC new \NC (r,i) \NC a complex userdata type \NC \NR +\NC tostring \NC (z) \NC a string representation \NC \NR +\NC topair \NC (z) \NC two numbers \NC \NR +\LL +\stoptabulate + +There is a bunch of functions that take a complex number: + +\starttabulate[|Tw(12em)|T|T|] +\DB name \BC arguments \BC results \NC \NR +\TB +\NC abs \NC (a) \NC \NC \NR +\NC arg \NC (a) \NC \NC \NR +\NC imag \NC (a) \NC \NC \NR +\NC real \NC (a) \NC \NC \NR +\NC onj \NC (a) \NC \NC \NR +\NC proj \NC (a) \NC \NC \NR +\NC exp" \NC (a) \NC \NC \NR +\NC log \NC (a) \NC \NC \NR +\NC sqrt \NC (a) \NC \NC \NR +\NC pow \NC (a,b) \NC \NC \NR +\NC sin \NC (a) \NC \NC \NR +\NC cos \NC (a) \NC \NC \NR +\NC tan \NC (a) \NC \NC \NR +\NC asin \NC (a) \NC \NC \NR +\NC acos \NC (a) \NC \NC \NR +\NC atan \NC (a) \NC \NC \NR +\NC sinh \NC (a) \NC \NC \NR +\NC cosh \NC (a) \NC \NC \NR +\NC tanh \NC (a) \NC \NC \NR +\NC asinh \NC (a) \NC \NC \NR +\NC acosh \NC (a) \NC \NC \NR +\NC atanh \NC (a) \NC \NC \NR +\LL +\stoptabulate + +These are accompanied by \type {libcerf} functions: + +\starttabulate[|Tw(12em)|T|T|] +\DB name \BC arguments \BC results \NC \NR +\TB +\NC erf \NC (a) \NC The complex error function erf(z) \NC \NR +\NC erfc \NC (a) \NC The complex complementary error function erfc(z) = 1 - erf(z) \NC \NR +\NC erfcx \NC (a) \NC The underflow-compensating function erfcx(z) = exp(z^2) erfc(z) \NC \NR +\NC erfi \NC (a) \NC The imaginary error function erfi(z) = -i erf(iz) \NC \NR +\NC dawson \NC (a) \NC Dawson's integral D(z) = sqrt(pi)/2 * exp(-z^2) * erfi(z) \NC \NR +\NC voigt \NC (a,b,c) \NC The convolution of a Gaussian and a Lorentzian \NC \NR +\NC voigt_hwhm \NC (a,b) \NC The half width at half maximum of the Voigt profile \NC \NR +\LL +\stoptabulate + +\stopsection + +\startsection[title=\type{lfs}] + +The original \type {lfs} module has been adapted a bit to our needs but for +practical reasons we kept the namespace. This module will probably evolve a bit +over time. + +\starttabulate[|Tw(12em)|T|Tp|] +\DB name \BC arguments \BC results \NC \NR +\TB +\NC attributes \NC (name) \NC \NC \NR +\NC chdir \NC (name) \NC \NC \NR +\NC currentdir \NC () \NC \NC \NR +\NC dir \NC (name) \NC \type {name}, \type {mode}, \type {size} and \type {mtime} \NC \NR +\NC mkdir \NC (name) \NC \NC \NR +\NC rmdir \NC (name) \NC \NC \NR +\NC touch \NC (name) \NC \NC \NR +\NC link \NC (name) \NC \NC \NR +\NC symlinkattributes \NC (name) \NC \NC \NR +\NC isdir \NC (name) \NC \NC \NR +\NC isfile \NC (name) \NC \NC \NR +\NC iswriteabledir \NC (name) \NC \NC \NR +\NC iswriteablefile \NC (name) \NC \NC \NR +\NC isreadabledir \NC (name) \NC \NC \NR +\NC isreadablefile \NC (name) \NC \NC \NR +\LL +\stoptabulate + +The \type {dir} function is a traverser which in addition to the name returns +some more properties. Keep in mind that the traverser loops over a directory and +that it doesn't run well when used nested. This is a side effect of the operating +system. It is also the reason why we return some properties because querying them +via \type {attributes} would interfere badly. + +The following attributes are returned by \type {attributes}: + +\starttabulate[|Tw(12em)|T|] +\DB name \BC value \NC \NR +\TB +\NC mode \NC \NC \NR +\NC size \NC \NC \NR +\NC modification \NC \NC \NR +\NC access \NC \NC \NR +\NC change \NC \NC \NR +\NC permissions \NC \NC \NR +\NC nlink \NC \NC \NR +\LL +\stoptabulate + +\stopsection + +\startsection[title=\type{pngdecode}] + +This module is experimental and used in image inclusion. It is not some general +purpose module and is supposed to be used in a very controlled way. The +interfaces might evolve. + +\starttabulate[|Tw(12em)|T|T|] +\DB name \BC arguments \BC results \NC \NR +\TB +\NC applyfilter \NC (str,nx,ny,slice) \NC string \NC \NR +\NC splitmask \NC (str,nx,ny,bpp,bytes) \NC string \NC \NR +\NC interlace \NC (str,nx,ny,slice,pass) \NC string \NC \NR +\NC expand \NC (str,nx,ny,parts,xline,factor) \NC string \NC \NR +\LL +\stoptabulate + +\stopsection + +\startsection[title=\type{basexx}] + +Some more experimental helpers: + +\starttabulate[|Tw(12em)|T|T|] +\DB name \BC arguments \BC results \NC \NR +\TB +\NC encode16 \NC (str[,newline]) \NC string \NC \NR +\NC decode16 \NC (str) \NC string \NC \NR +\NC encode64 \NC (str[,newline]) \NC string \NC \NR +\NC decode64 \NC (str) \NC string \NC \NR +\NC encode85 \NC (str[,newline]) \NC string \NC \NR +\NC decode85 \NC (str) \NC string \NC \NR +\NC encodeRL \NC (str) \NC string \NC \NR +\NC decodeRL \NC (str) \NC string \NC \NR +\NC encodeLZW \NC (str[,defaults]) \NC string \NC \NR +\NC decodeLZW \NC (str[,defaults]) \NC string \NC \NR +\LL +\stoptabulate + +\stopsection + +\startsection[title={Multibyte \type {string} functions}] + +The \type {string} library has a few extra functions, for example \libidx +{string} {explode}. This function takes upto two arguments: \type +{string.explode(s[,m])} and returns an array containing the string argument \type +{s} split into sub-strings based on the value of the string argument \type {m}. +The second argument is a string that is either empty (this splits the string into +characters), a single character (this splits on each occurrence of that +character, possibly introducing empty strings), or a single character followed by +the plus sign \type {+} (this special version does not create empty sub-strings). +The default value for \type {m} is \quote {\type { +}} (multiple spaces). Note: +\type {m} is not hidden by surrounding braces as it would be if this function was +written in \TEX\ macros. + +The \type {string} library also has six extra iterators that return strings +piecemeal: \libidx {string} {utfvalues}, \libidx {string} {utfcharacters}, +\libidx {string} {characters}, \libidx {string} {characterpairs}, \libidx +{string} {bytes} and \libidx {string} {bytepairs}. + +\startitemize +\startitem + \type {string.utfvalues(s)}: an integer value in the \UNICODE\ range +\stopitem +\startitem + \type {string.utfcharacters(s)}: a string with a single \UTF-8 token in it +\stopitem +\startitem + \type {string.cWharacters(s)}: a string containing one byte +\stopitem +\startitem + \type {string.characterpairs(s)}: two strings each containing one byte or an + empty second string if the string length was odd +\stopitem +\startitem + \type {string.bytes(s)}: a single byte value +\stopitem +\startitem + \type {string.bytepairs(s)}: two byte values or nil instead of a number as + its second return value if the string length was odd +\stopitem +\stopitemize + +The \type {string.characterpairs()} and \type {string.bytepairs()} iterators +are useful especially in the conversion of \UTF16 encoded data into \UTF8. + +There is also a two|-|argument form of \type {string.dump()}. The second argument +is a boolean which, if true, strips the symbols from the dumped data. This +matches an extension made in \type {luajit}. This is typically a function that +gets adapted as \LUA\ itself progresses. + +The \type {string} library functions \type {len}, \type {lower}, \type {sub} +etc.\ are not \UNICODE|-|aware. For strings in the \UTF8 encoding, i.e., strings +containing characters above code point 127, the corresponding functions from the +\type {slnunicode} library can be used, e.g., \type {unicode.utf8.len}, \type +{unicode.utf8.lower} etc.\ The exceptions are \type {unicode.utf8.find}, that +always returns byte positions in a string, and \type {unicode.utf8.match} and +\type {unicode.utf8.gmatch}. While the latter two functions in general {\it +are} \UNICODE|-|aware, they fall|-|back to non|-|\UNICODE|-|aware behavior when +using the empty capture \type {()} but other captures work as expected. For the +interpretation of character classes in \type {unicode.utf8} functions refer to +the library sources at \hyphenatedurl {http://luaforge.net/projects/sln}. + +Version 5.3 of \LUA\ provides some native \UTF8 support but we have added a few +similar helpers too: \libidx {string} {utfvalue}, \libidx {string} {utfcharacter} +and \libidx {string} {utflength}. + +\startitemize +\startitem + \type {string.utfvalue(s)}: returns the codepoints of the characters in the + given string +\stopitem +\startitem + \type {string.utfcharacter(c,...)}: returns a string with the characters of + the given code points +\stopitem +\startitem + \type {string.utflength(s)}: returns the length of the given string +\stopitem +\stopitemize + +These three functions are relative fast and don't do much checking. They can be +used as building blocks for other helpers. + +\stopsection + +\startsection[title={Extra \type {os} library functions}] + +The \type {os} library has a few extra functions and variables: \libidx {os} +{selfdir}, \libidx {os} {selfarg}, \libidx {os} {setenv}, \libidx {os} {env}, \libidx {os} +{gettimeofday}, \libidx {os} {type}, \libidx {os} {name} and \libidx {os} +{uname}, that we will discuss here. There are also some time related helpers in +the \type {lua} namespace. + +\startitemize + +% selfbin +% selfpath +% selfdir +% selfbase +% selfname +% selfcore + +\startitem + \type {os.selfdir} is a variable that holds the directory path of the + actual executable. For example: \type {\directlua {tex.sprint(os.selfdir)}}. +\stopitem + +\startitem + \type {os.selfarg} is a table with the command line arguments. +\stopitem + +\startitem + \type {os.setenv(key,value)} sets a variable in the environment. Passing + \type {nil} instead of a value string will remove the variable. +\stopitem + +\startitem + \type {os.env} is a hash table containing a dump of the variables and + values in the process environment at the start of the run. It is writeable, + but the actual environment is \notabene {not} updated automatically. +\stopitem + +\startitem + \type {os.gettimeofday} returns the current \quote {\UNIX\ time}, but as a + float. Keep in mind that there might be platforms where this function is + available. +\stopitem + +\startitem + \type {os.type} is a string that gives a global indication of the class of + operating system. The possible values are currently \type {windows}, \type + {unix}, and \type {msdos} (you are unlikely to find this value \quote {in the + wild}). +\stopitem + +\startitem + \type {os.name} is a string that gives a more precise indication of the + operating system. These possible values are not yet fixed, and for \type + {os.type} values \type {windows} and \type {msdos}, the \type {os.name} + values are simply \type {windows} and \type {msdos} + + The list for the type \type {unix} is more precise: \type {linux}, \type + {freebsd}, \type {kfreebsd}, \type {cygwin}, \type {openbsd}, \type + {solaris}, \type {sunos} (pre-solaris), \type {hpux}, \type {irix}, \type + {macosx}, \type {gnu} (hurd), \type {bsd} (unknown, but \BSD|-|like), \type + {sysv}, \type {generic} (unknown). But \unknown\ we only provide \LUAMETATEX\ + binaries for the mainstream variants. + + Officially we only support mainstream systems: \MSWINDOWS, \LINUX, \FREEBSD\ + and \OSX. Of course one can build \LUAMETATEX\ for other systems, in which + case on has to check the above. +\stopitem + +\startitem + \type {os.uname} returns a table with specific operating system + information acquired at runtime. The keys in the returned table are all + string values, and their names are: \type {sysname}, \type {machine}, \type + {release}, \type {version}, and \type {nodename}. +\stopitem + +\stopitemize + +\stopsection + +\startsection[title={The \type {lua} library functions}] + +The \type {lua} library provide some general helpers. + +\startitemize + +\startitem + The \type {newtable} and \type {newindex} functions can be used to create + tables with space reserved beforehand for the given amount of entries. +\stopitem + +\startitem + The \type {getstacktop} function returns a number that can be used for + diagnostic purposes. +\stopitem + +\startitem + The functions \type {getruntime}, \type {getcurrenttime}, \type + {getpreciseticks} and \type {getpreciseseconds} return what their name + suggests. +\stopitem + +\startitem + On \MSWINDOWS\ the \type {getcodepage} function returns two numbers, one + for the command handler and one for the graphical user interface. +\stopitem + +\startitem + The name of the startup file is reported by \type {getstartupfile}. +\stopitem + +\startitem + The \LUA\ version is reported by \type {getversion}. +\stopitem + +\startitem + The \type {lua.openfile} function can be used instead of \type {io.open}. On + \MSWINDOWS\ it will convert the filename to a so called wide one which means + that filenames in \UTF8 encoding will work ok. On the other hand, names given + in the codepage won't. +\stopitem + +\stopitemize + +\stopsection + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/luametatex/luametatex-lua.tex b/doc/context/sources/general/manuals/luametatex/luametatex-lua.tex new file mode 100644 index 000000000..50db9593b --- /dev/null +++ b/doc/context/sources/general/manuals/luametatex/luametatex-lua.tex @@ -0,0 +1,224 @@ +% language=uk + +\environment luametatex-style + +\startcomponent luametatex-lua + +\startchapter[reference=lua,title={Using \LUAMETATEX}] + +\startsection[title={Initialization},reference=init] + +\startsubsection[title={\LUAMETATEX\ as a \LUA\ interpreter}] + +\topicindex {initialization} +\topicindex {\LUA+interpreter} + +Although \LUAMETATEX\ is primarily meant as a \TEX\ engine, it can also serve as +a stand alone \LUA\ interpreter. There are two ways to make \LUAMETATEX\ behave +like a standalone \LUA\ interpreter: + +\startitemize[packed] +\startitem + if a \type {--luaonly} option is given on the commandline, or +\stopitem +\startitem + if the only non|-|option argument (file) on the commandline has the extension + \type {lua} or \type {luc}. +\stopitem +\stopitemize + +In this mode, it will set \LUA's \type {arg[0]} to the found script name, pushing +preceding options in negative values and the rest of the command line in the +positive values, just like the \LUA\ interpreter does. + +\LUAMETATEX\ will exit immediately after executing the specified \LUA\ script and is, +in effect, a somewhat bulky stand alone \LUA\ interpreter with a bunch of extra +preloaded libraries. + +When no argument is given, \LUAMETATEX\ will look for a \LUA\ file with the same +name as the binary and run that one when present. This makes it possible to use +the engine as a stub. For instance, in \CONTEXT\ a symlink from \type {mtxrun} to +type {luametatex} will run the \type {mtxrun.lua} script when present in the same +path as the binary itself + +\stopsubsection + +\startsubsection[title={Other commandline processing}] + +\topicindex {command line} + +When the \LUAMETATEX\ executable starts, it looks for the \type {--lua} command line +option. If there is no \type {--lua} option, the command line is interpreted in a +similar fashion as the other \TEX\ engines. All options are accepted but only some +have are understood by \LUAMETATEX\ itself: + +\starttabulate[|l|p|] +\DB commandline argument \BC explanation \NC \NR +\TB +\NC \type{--credits} \NC display credits and exit \NC \NR +\NC \type{--fmt=FORMAT} \NC load the format file \type {FORMAT} \NC\NR +\NC \type{--help} \NC display help and exit \NC\NR +\NC \type{--ini} \NC be \type {iniluatex}, for dumping formats \NC\NR +\NC \type{--jobname=STRING} \NC set the job name to \type {STRING} \NC \NR +\NC \type{--lua=FILE} \NC load and execute a \LUA\ initialization script \NC\NR +\NC \type{--version} \NC display version and exit \NC \NR +\LL +\stoptabulate + +There are less options than with \LUATEX, because one has to deal with them in +\LUA\ anyway. There are no options to enter a safer mode or control executing +programs. This can easily be achieved with a startup \LUA\ script. + +The value to use for \prm {jobname} is decided as follows: + +\startitemize +\startitem + If \type {--jobname} is given on the command line, its argument will be the + value for \prm {jobname}, without any changes. The argument will not be + used for actual input so it need not exist. The \type {--jobname} switch only + controls the \prm {jobname} setting. +\stopitem +\startitem + Otherwise, \prm {jobname} will be the name of the first file that is read + from the file system, with any path components and the last extension (the + part following the last \type {.}) stripped off. +\stopitem +\startitem + There is an exception to the previous point: if the command line goes into + interactive mode (by starting with a command) and there are no files input + via \prm {everyjob} either, then the \prm {jobname} is set to \type + {texput} as a last resort. +\stopitem +\stopitemize + +Next the initialization script is loaded and executed. From within the script, +the entire command line is available in the \LUA\ table \type {arg}, beginning +with \type {arg[0]}, containing the name of the executable. As consequence +warnings about unrecognized options are suppressed. + +Command line processing happens very early on. So early, in fact, that none of +\TEX's initializations have taken place yet. The \LUA\ libraries that don't deal +with \TEX\ are initialized early. + +\LUAMETATEX\ allows some of the command line options to be overridden by reading +values from the \type {texconfig} table at the end of script execution (see the +description of the \type {texconfig} table later on in this document for more +details on which ones exactly). + +So let's summarize this. The handling of when is called jobname is a bit complex. +There can be explicit names set on the command line but when not set they can be +taken from the \type {texconfig} table. + +\starttabulate[|l|T|T|T|] +\NC startup filename \NC --lua \NC a \LUA\ file \NC \NC \NR +\NC startup jobname \NC --jobname \NC a \TEX\ tex \NC texconfig.jobname \NC \NR +\NC startup dumpname \NC --fmt \NC a format file \NC texconfig.formatname \NC \NR +\stoptabulate + +These names are initialized according to \type {--luaonly} or the first filename +seen in the list of options. Special treatment of \type {&} and \type {*} as well +as interactive startup is gone. + +When we are in \TEX\ mode at some point the engine needs a filename, for instance +for opening a log file. At that moment the set jobname becomes the internal one +and when it has not been set which internalized to jobname but when not set +becomes \type {texput}. When you see a \type {texput.log} file someplace on your +system it normally indicates a bad run. + +When running on \MSWINDOWS\ the command line, filenames, environment variable +access etc.\ internally uses the current code page but to the user is exposed as +\UTF8. Normally users won't notice this. + +% fileio_state .jobname : a tex string (set when a (log) file is opened) +% engine_state .startup_jobname : handles by option parser +% environment_state.input_name : temporary interceptor + +\stopsubsection + +\stopsection + +\startsection[title={\LUA\ behaviour}] + +\startsubsection[title={The \LUA\ version}] + +\topicindex {\LUA+libraries} +\topicindex {\LUA+extensions} + +We currently use \LUA\ 5.4 and will follow developments of the language but +normally with some delay. Therefore the user needs to keep an eye on (subtle) +differences in successive versions of the language. Here is an example of one +aspect. + +\LUA s \type {tostring} function (and \type {string.format} may return values in +scientific notation, thereby confusing the \TEX\ end of things when it is used as +the right|-|hand side of an assignment to a \prm {dimen} or \prm {count}. The +output of these serializers also depend on the \LUA\ version, so in \LUA\ 5.3 you +can get different output than from 5.2. It is best not to depend the automatic +cast from string to number and vise versa as this can change in future versions. + +\stopsubsection + +\startsubsection[title={Locales}] + +\index {locales} + +In stock \LUA, many things depend on the current locale. In \LUAMETATEX, we can't +do that, because it makes documents unportable. While \LUAMETATEX\ is running if +forces the following locale settings: + +\starttyping +LC_CTYPE=C +LC_COLLATE=C +LC_NUMERIC=C +\stoptyping + +There is no way to change that as it would interfere badly with the often +language specific conversions needed at the \TEX\ end. + +\stopsubsection + +\stopsection + +\startsection[title={\LUA\ modules}] + +\topicindex {\LUA+libraries} +\topicindex {\LUA+modules} + +Of course the regular \LUA\ modules are present. In addition we provide the \type +{lpeg} library by Roberto Ierusalimschy, This library is not \UNICODE|-|aware, +but interprets strings on a byte|-|per|-|byte basis. This mainly means that \type +{lpeg.S} cannot be used with \UTF8 characters encoded in more than two bytes, and +thus \type {lpeg.S} will look for one of those two bytes when matching, not the +combination of the two. The same is true for \type {lpeg.R}, although the latter +will display an error message if used with multibyte characters. Therefore \type +{lpeg.R('aä')} results in the message \type {bad argument #1 to 'R' (range must +have two characters)}, since to \type {lpeg}, \type {ä} is two 'characters' +(bytes), so \type {aä} totals three. In practice this is no real issue and with +some care you can deal with \UNICODE\ just fine. + +There are some more libraries present. These are discussed on a later chapter. +For instance we embed \type {luasocket} but contrary to \LUATEX\ don't embed the +related \LUA\ code. An adapted version of \type {luafilesystem} is also included. +There is a more extensive math library and there are libraries that deal with +encryption and compression. + +\stopsection + +\startsection[title={Testing}] + +\topicindex {testing} + +For development reasons you can influence the used startup date and time. By +setting the \type {start_time} variable in the \type {texconfig} table; as with +other variables we use the internal name there. When Universal Time is needed, +set the entry \type {use_utc_time} in the \type {texconfig} table. + +In \CONTEXT\ we provide the command line argument \type {--nodates} that does +a bit more than disabling dates; it avoids time dependent information in the +output file for instance. + +\stopsection + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/luametatex/luametatex-math.tex b/doc/context/sources/general/manuals/luametatex/luametatex-math.tex new file mode 100644 index 000000000..111a6cf03 --- /dev/null +++ b/doc/context/sources/general/manuals/luametatex/luametatex-math.tex @@ -0,0 +1,1585 @@ +% language=uk + +\environment luametatex-style + +\startcomponent luametatex-math + +\startchapter[reference=math,title={Math}] + +\startsection[title={Traditional alongside \OPENTYPE}] + +\topicindex {math} + +At this point there is no difference between \LUAMETATEX\ and \LUATEX\ with +respect to math. The handling of mathematics in \LUATEX\ differs quite a bit from +how \TEX82 (and therefore \PDFTEX) handles math. First, \LUATEX\ adds primitives +and extends some others so that \UNICODE\ input can be used easily. Second, all +of \TEX82's internal special values (for example for operator spacing) have been +made accessible and changeable via control sequences. Third, there are extensions +that make it easier to use \OPENTYPE\ math fonts. And finally, there are some +extensions that have been proposed or considered in the past that are now added +to the engine. + +\stopsection + +\startsection[title={Unicode math characters}] + +\topicindex {math+\UNICODE} +\topicindex {\UNICODE+math} + +Character handling is now extended up to the full \UNICODE\ range (the \type {\U} +prefix), which is compatible with \XETEX. + +The math primitives from \TEX\ are kept as they are, except for the ones that +convert from input to math commands: \type {mathcode}, and \type {delcode}. These +two now allow for a 21-bit character argument on the left hand side of the equals +sign. + +Some of the new \LUATEX\ primitives read more than one separate value. This is +shown in the tables below by a plus sign. + +The input for such primitives would look like this: + +\starttyping +\def\overbrace{\Umathaccent 0 1 "23DE } +\stoptyping + +The altered \TEX82 primitives are: + +\starttabulate[|l|l|r|c|l|r|] +\DB primitive \BC min \BC max \BC \kern 2em \BC min \BC max \NC \NR +\TB +\NC \prm {mathcode} \NC 0 \NC 10FFFF \NC = \NC 0 \NC 8000 \NC \NR +\NC \prm {delcode} \NC 0 \NC 10FFFF \NC = \NC 0 \NC FFFFFF \NC \NR +\LL +\stoptabulate + +The unaltered ones are: + +\starttabulate[|l|l|r|] +\DB primitive \BC min \BC max \NC \NR +\TB +\NC \prm {mathchardef} \NC 0 \NC 8000 \NC \NR +\NC \prm {mathchar} \NC 0 \NC 7FFF \NC \NR +\NC \prm {mathaccent} \NC 0 \NC 7FFF \NC \NR +\NC \prm {delimiter} \NC 0 \NC 7FFFFFF \NC \NR +\NC \prm {radical} \NC 0 \NC 7FFFFFF \NC \NR +\LL +\stoptabulate + +For practical reasons \prm {mathchardef} will silently accept values larger +that \type {0x8000} and interpret it as \lpr {Umathcharnumdef}. This is needed +to satisfy older macro packages. + +The following new primitives are compatible with \XETEX: + +% somewhat fuzzy: + +\starttabulate[|l|l|r|c|l|r|] +\DB primitive \BC min \BC max \BC \kern 2em \BC min \BC max \NC \NR +\TB +\NC \lpr {Umathchardef} \NC 0+0+0 \NC 7+FF+10FFFF \NC \NC \NC \NC \NR +\NC \lpr {Umathcharnumdef}\rlap{\high{5}} \NC -80000000 \NC 7FFFFFFF \NC \NC \NC \NC \NR +\NC \lpr {Umathcode} \NC 0 \NC 10FFFF \NC = \NC 0+0+0 \NC 7+FF+10FFFF \NC \NR +\NC \lpr {Udelcode} \NC 0 \NC 10FFFF \NC = \NC 0+0 \NC FF+10FFFF \NC \NR +\NC \lpr {Umathchar} \NC 0+0+0 \NC 7+FF+10FFFF \NC \NC \NC \NC \NR +\NC \lpr {Umathaccent} \NC 0+0+0 \NC 7+FF+10FFFF \NC \NC \NC \NC \NR +\NC \lpr {Udelimiter} \NC 0+0+0 \NC 7+FF+10FFFF \NC \NC \NC \NC \NR +\NC \lpr {Uradical} \NC 0+0 \NC FF+10FFFF \NC \NC \NC \NC \NR +\NC \lpr {Umathcharnum} \NC -80000000 \NC 7FFFFFFF \NC \NC \NC \NC \NR +\NC \lpr {Umathcodenum} \NC 0 \NC 10FFFF \NC = \NC -80000000 \NC 7FFFFFFF \NC \NR +\NC \lpr {Udelcodenum} \NC 0 \NC 10FFFF \NC = \NC -80000000 \NC 7FFFFFFF \NC \NR +\LL +\stoptabulate + +Specifications typically look like: + +\starttyping +\Umathchardef\xx="1"0"456 +\Umathcode 123="1"0"789 +\stoptyping + +The new primitives that deal with delimiter|-|style objects do not set up a +\quote {large family}. Selecting a suitable size for display purposes is expected +to be dealt with by the font via the \lpr {Umathoperatorsize} parameter. + +For some of these primitives, all information is packed into a single signed +integer. For the first two (\lpr {Umathcharnum} and \lpr {Umathcodenum}), the +lowest 21 bits are the character code, the 3 bits above that represent the math +class, and the family data is kept in the topmost bits. This means that the values +for math families 128--255 are actually negative. For \lpr {Udelcodenum} there +is no math class. The math family information is stored in the bits directly on +top of the character code. Using these three commands is not as natural as using +the two- and three|-|value commands, so unless you know exactly what you are +doing and absolutely require the speedup resulting from the faster input +scanning, it is better to use the verbose commands instead. + +The \lpr {Umathaccent} command accepts optional keywords to control various +details regarding math accents. See \in {section} [mathacc] below for details. + +There are more new primitives and all of these will be explained in following +sections: + +\starttabulate[|l|l|] +\DB primitive \BC value range (in hex) \NC \NR +\TB +\NC \lpr {Uroot} \NC 0 + 0--FF + 10FFFF \NC \NR +\NC \lpr {Uoverdelimiter} \NC 0 + 0--FF + 10FFFF \NC \NR +\NC \lpr {Uunderdelimiter} \NC 0 + 0--FF + 10FFFF \NC \NR +\NC \lpr {Udelimiterover} \NC 0 + 0--FF + 10FFFF \NC \NR +\NC \lpr {Udelimiterunder} \NC 0 + 0--FF + 10FFFF \NC \NR +\LL +\stoptabulate + +\stopsection + +\startsection[title={Math styles}] + +\subsection{\lpr {mathstyle}} + +\topicindex {math+styles} + +It is possible to discover the math style that will be used for a formula in an +expandable fashion (while the math list is still being read). To make this +possible, \LUATEX\ adds the new primitive: \lpr {mathstyle}. This is a \quote +{convert command} like e.g. \prm {romannumeral}: its value can only be read, +not set. + +The returned value is between 0 and 7 (in math mode), or $-1$ (all other modes). +For easy testing, the eight math style commands have been altered so that they can +be used as numeric values, so you can write code like this: + +\starttyping +\ifnum\mathstyle=\textstyle + \message{normal text style} +\else \ifnum\mathstyle=\crampedtextstyle + \message{cramped text style} +\fi \fi +\stoptyping + +Sometimes you won't get what you expect so a bit of explanation might help to +understand what happens. When math is parsed and expanded it gets turned into a +linked list. In a second pass the formula will be build. This has to do with the +fact that in order to determine the automatically chosen sizes (in for instance +fractions) following content can influence preceding sizes. A side effect of this +is for instance that one cannot change the definition of a font family (and +thereby reusing numbers) because the number that got used is stored and used in +the second pass (so changing \type {\fam 12} mid|-|formula spoils over to +preceding use of that family). + +The style switching primitives like \prm {textstyle} are turned into nodes so the +styles set there are frozen. The \prm {mathchoice} primitive results in four +lists being constructed of which one is used in the second pass. The fact that +some automatic styles are not yet known also means that the \lpr {mathstyle} +primitive expands to the current style which can of course be different from the +one really used. It's a snapshot of the first pass state. As a consequence in the +following example you get a style number (first pass) typeset that can actually +differ from the used style (second pass). In the case of a math choice used +ungrouped, the chosen style is used after the choice too, unless you group. + +\startbuffer[1] + [a:\mathstyle]\quad + \bgroup + \mathchoice + {\bf \scriptstyle (x:d :\mathstyle)} + {\bf \scriptscriptstyle (x:t :\mathstyle)} + {\bf \scriptscriptstyle (x:s :\mathstyle)} + {\bf \scriptscriptstyle (x:ss:\mathstyle)} + \egroup + \quad[b:\mathstyle]\quad + \mathchoice + {\bf \scriptstyle (y:d :\mathstyle)} + {\bf \scriptscriptstyle (y:t :\mathstyle)} + {\bf \scriptscriptstyle (y:s :\mathstyle)} + {\bf \scriptscriptstyle (y:ss:\mathstyle)} + \quad[c:\mathstyle]\quad + \bgroup + \mathchoice + {\bf \scriptstyle (z:d :\mathstyle)} + {\bf \scriptscriptstyle (z:t :\mathstyle)} + {\bf \scriptscriptstyle (z:s :\mathstyle)} + {\bf \scriptscriptstyle (z:ss:\mathstyle)} + \egroup + \quad[d:\mathstyle] +\stopbuffer + +\startbuffer[2] + [a:\mathstyle]\quad + \begingroup + \mathchoice + {\bf \scriptstyle (x:d :\mathstyle)} + {\bf \scriptscriptstyle (x:t :\mathstyle)} + {\bf \scriptscriptstyle (x:s :\mathstyle)} + {\bf \scriptscriptstyle (x:ss:\mathstyle)} + \endgroup + \quad[b:\mathstyle]\quad + \mathchoice + {\bf \scriptstyle (y:d :\mathstyle)} + {\bf \scriptscriptstyle (y:t :\mathstyle)} + {\bf \scriptscriptstyle (y:s :\mathstyle)} + {\bf \scriptscriptstyle (y:ss:\mathstyle)} + \quad[c:\mathstyle]\quad + \begingroup + \mathchoice + {\bf \scriptstyle (z:d :\mathstyle)} + {\bf \scriptscriptstyle (z:t :\mathstyle)} + {\bf \scriptscriptstyle (z:s :\mathstyle)} + {\bf \scriptscriptstyle (z:ss:\mathstyle)} + \endgroup + \quad[d:\mathstyle] +\stopbuffer + +\typebuffer[1] + +% \typebuffer[2] + +This gives: + +\blank $\displaystyle \getbuffer[1]$ \blank +\blank $\textstyle \getbuffer[1]$ \blank + +Using \prm {begingroup} \unknown\ \prm {endgroup} instead gives: + +\blank $\displaystyle \getbuffer[2]$ \blank +\blank $\textstyle \getbuffer[2]$ \blank + +This might look wrong but it's just a side effect of \lpr {mathstyle} expanding +to the current (first pass) style and the number being injected in the list that +gets converted in the second pass. It all makes sense and it illustrates the +importance of grouping. In fact, the math choice style being effective afterwards +has advantages. It would be hard to get it otherwise. + +\subsection{\lpr {Ustack}} + +\topicindex {math+stacks} + +There are a few math commands in \TEX\ where the style that will be used is not +known straight from the start. These commands (\prm {over}, \prm {atop}, +\prm {overwithdelims}, \prm {atopwithdelims}) would therefore normally return +wrong values for \lpr {mathstyle}. To fix this, \LUATEX\ introduces a special +prefix command: \lpr {Ustack}: + +\starttyping +$\Ustack {a \over b}$ +\stoptyping + +The \lpr {Ustack} command will scan the next brace and start a new math group +with the correct (numerator) math style. + +\subsection{The new \type {\cramped...style} commands} + +\topicindex {math+styles} +\topicindex {math+spacing} +\topicindex {math+cramped} + +\LUATEX\ has four new primitives to set the cramped math styles directly: + +\starttyping +\crampeddisplaystyle +\crampedtextstyle +\crampedscriptstyle +\crampedscriptscriptstyle +\stoptyping + +These additional commands are not all that valuable on their own, but they come +in handy as arguments to the math parameter settings that will be added shortly. + +In Eijkhouts \quotation {\TEX\ by Topic} the rules for handling styles in scripts +are described as follows: + +\startitemize +\startitem + In any style superscripts and subscripts are taken from the next smaller style. + Exception: in display style they are in script style. +\stopitem +\startitem + Subscripts are always in the cramped variant of the style; superscripts are only + cramped if the original style was cramped. +\stopitem +\startitem + In an \type {..\over..} formula in any style the numerator and denominator are + taken from the next smaller style. +\stopitem +\startitem + The denominator is always in cramped style; the numerator is only in cramped + style if the original style was cramped. +\stopitem +\startitem + Formulas under a \type {\sqrt} or \prm {overline} are in cramped style. +\stopitem +\stopitemize + +In \LUATEX\ one can set the styles in more detail which means that you sometimes +have to set both normal and cramped styles to get the effect you want. (Even) if +we force styles in the script using \prm {scriptstyle} and \lpr +{crampedscriptstyle} we get this: + +\startbuffer[demo] +\starttabulate +\DB style \BC example \NC \NR +\TB +\NC default \NC $b_{x=xx}^{x=xx}$ \NC \NR +\NC script \NC $b_{\scriptstyle x=xx}^{\scriptstyle x=xx}$ \NC \NR +\NC crampedscript \NC $b_{\crampedscriptstyle x=xx}^{\crampedscriptstyle x=xx}$ \NC \NR +\LL +\stoptabulate +\stopbuffer + +\getbuffer[demo] + +Now we set the following parameters + +\startbuffer[setup] +\Umathordrelspacing\scriptstyle=30mu +\Umathordordspacing\scriptstyle=30mu +\stopbuffer + +\typebuffer[setup] + +This gives a different result: + +\start\getbuffer[setup,demo]\stop + +But, as this is not what is expected (visually) we should say: + +\startbuffer[setup] +\Umathordrelspacing\scriptstyle=30mu +\Umathordordspacing\scriptstyle=30mu +\Umathordrelspacing\crampedscriptstyle=30mu +\Umathordordspacing\crampedscriptstyle=30mu +\stopbuffer + +\typebuffer[setup] + +Now we get: + +\start\getbuffer[setup,demo]\stop + +\stopsection + +\startsection[title={Math parameter settings}] + +\subsection {Many new \lpr {Umath*} primitives} + +\topicindex {math+parameters} + +In \LUATEX, the font dimension parameters that \TEX\ used in math typesetting are +now accessible via primitive commands. In fact, refactoring of the math engine +has resulted in many more parameters than were not accessible before. + +\starttabulate +\DB primitive name \BC description \NC \NR +\TB +\NC \lpr {Umathquad} \NC the width of 18 mu's \NC \NR +\NC \lpr {Umathaxis} \NC height of the vertical center axis of + the math formula above the baseline \NC \NR +\NC \lpr {Umathoperatorsize} \NC minimum size of large operators in display mode \NC \NR +\NC \lpr {Umathoverbarkern} \NC vertical clearance above the rule \NC \NR +\NC \lpr {Umathoverbarrule} \NC the width of the rule \NC \NR +\NC \lpr {Umathoverbarvgap} \NC vertical clearance below the rule \NC \NR +\NC \lpr {Umathunderbarkern} \NC vertical clearance below the rule \NC \NR +\NC \lpr {Umathunderbarrule} \NC the width of the rule \NC \NR +\NC \lpr {Umathunderbarvgap} \NC vertical clearance above the rule \NC \NR +\NC \lpr {Umathradicalkern} \NC vertical clearance above the rule \NC \NR +\NC \lpr {Umathradicalrule} \NC the width of the rule \NC \NR +\NC \lpr {Umathradicalvgap} \NC vertical clearance below the rule \NC \NR +\NC \lpr {Umathradicaldegreebefore}\NC the forward kern that takes place before placement of + the radical degree \NC \NR +\NC \lpr {Umathradicaldegreeafter} \NC the backward kern that takes place after placement of + the radical degree \NC \NR +\NC \lpr {Umathradicaldegreeraise} \NC this is the percentage of the total height and depth of + the radical sign that the degree is raised by; it is + expressed in \type {percents}, so 60\% is expressed as the + integer $60$ \NC \NR +\NC \lpr {Umathstackvgap} \NC vertical clearance between the two + elements in a \prm {atop} stack \NC \NR +\NC \lpr {Umathstacknumup} \NC numerator shift upward in \prm {atop} stack \NC \NR +\NC \lpr {Umathstackdenomdown} \NC denominator shift downward in \prm {atop} stack \NC \NR +\NC \lpr {Umathfractionrule} \NC the width of the rule in a \prm {over} \NC \NR +\NC \lpr {Umathfractionnumvgap} \NC vertical clearance between the numerator and the rule \NC \NR +\NC \lpr {Umathfractionnumup} \NC numerator shift upward in \prm {over} \NC \NR +\NC \lpr {Umathfractiondenomvgap} \NC vertical clearance between the denominator and the rule \NC \NR +\NC \lpr {Umathfractiondenomdown} \NC denominator shift downward in \prm {over} \NC \NR +\NC \lpr {Umathfractiondelsize} \NC minimum delimiter size for \type {\...withdelims} \NC \NR +\NC \lpr {Umathlimitabovevgap} \NC vertical clearance for limits above operators \NC \NR +\NC \lpr {Umathlimitabovebgap} \NC vertical baseline clearance for limits above operators \NC \NR +\NC \lpr {Umathlimitabovekern} \NC space reserved at the top of the limit \NC \NR +\NC \lpr {Umathlimitbelowvgap} \NC vertical clearance for limits below operators \NC \NR +\NC \lpr {Umathlimitbelowbgap} \NC vertical baseline clearance for limits below operators \NC \NR +\NC \lpr {Umathlimitbelowkern} \NC space reserved at the bottom of the limit \NC \NR +\NC \lpr {Umathoverdelimitervgap} \NC vertical clearance for limits above delimiters \NC \NR +\NC \lpr {Umathoverdelimiterbgap} \NC vertical baseline clearance for limits above delimiters \NC \NR +\NC \lpr {Umathunderdelimitervgap} \NC vertical clearance for limits below delimiters \NC \NR +\NC \lpr {Umathunderdelimiterbgap} \NC vertical baseline clearance for limits below delimiters \NC \NR +\NC \lpr {Umathsubshiftdrop} \NC subscript drop for boxes and subformulas \NC \NR +\NC \lpr {Umathsubshiftdown} \NC subscript drop for characters \NC \NR +\NC \lpr {Umathsupshiftdrop} \NC superscript drop (raise, actually) for boxes and subformulas \NC \NR +\NC \lpr {Umathsupshiftup} \NC superscript raise for characters \NC \NR +\NC \lpr {Umathsubsupshiftdown} \NC subscript drop in the presence of a superscript \NC \NR +\NC \lpr {Umathsubtopmax} \NC the top of standalone subscripts cannot be higher than this + above the baseline \NC \NR +\NC \lpr {Umathsupbottommin} \NC the bottom of standalone superscripts cannot be less than + this above the baseline \NC \NR +\NC \lpr {Umathsupsubbottommax} \NC the bottom of the superscript of a combined super- and subscript + be at least as high as this above the baseline \NC \NR +\NC \lpr {Umathsubsupvgap} \NC vertical clearance between super- and subscript \NC \NR +\NC \lpr {Umathspaceafterscript} \NC additional space added after a super- or subscript \NC \NR +\NC \lpr {Umathconnectoroverlapmin}\NC minimum overlap between parts in an extensible recipe \NC \NR +\LL +\stoptabulate + +Each of the parameters in this section can be set by a command like this: + +\starttyping +\Umathquad\displaystyle=1em +\stoptyping + +they obey grouping, and you can use \type {\the\Umathquad\displaystyle} if +needed. + +\subsection{Font|-|based math parameters} + +\topicindex {math+parameters} + +While it is nice to have these math parameters available for tweaking, it would +be tedious to have to set each of them by hand. For this reason, \LUATEX\ +initializes a bunch of these parameters whenever you assign a font identifier to +a math family based on either the traditional math font dimensions in the font +(for assignments to math family~2 and~3 using \TFM|-|based fonts like \type +{cmsy} and \type {cmex}), or based on the named values in a potential \type +{MathConstants} table when the font is loaded via Lua. If there is a \type +{MathConstants} table, this takes precedence over font dimensions, and in that +case no attention is paid to which family is being assigned to: the \type +{MathConstants} tables in the last assigned family sets all parameters. + +In the table below, the one|-|letter style abbreviations and symbolic tfm font +dimension names match those used in the \TeX book. Assignments to \prm +{textfont} set the values for the cramped and uncramped display and text styles, +\prm {scriptfont} sets the script styles, and \prm {scriptscriptfont} sets the +scriptscript styles, so we have eight parameters for three font sizes. In the +\TFM\ case, assignments only happen in family~2 and family~3 (and of course only +for the parameters for which there are font dimensions). + +Besides the parameters below, \LUATEX\ also looks at the \quote {space} font +dimension parameter. For math fonts, this should be set to zero. + +\def\MathLine#1#2#3#4#5% + {\TB + \NC \llap{\high{\tx #2\enspace}}\ttbf \string #1 \NC \tt #5 \NC \NR + \NC \tx #3 \NC \tt #4 \NC \NR} + +\starttabulate[|l|l|] +\DB variable / style \BC tfm / opentype \NC \NR +\MathLine{\Umathaxis} {} {} {AxisHeight} {axis_height} +\MathLine{\Umathoperatorsize} {6} {D, D'} {DisplayOperatorMinHeight} {\emdash} +\MathLine{\Umathfractiondelsize} {9} {D, D'} {FractionDelimiterDisplayStyleSize} {delim1} +\MathLine{\Umathfractiondelsize} {9} {T, T', S, S', SS, SS'}{FractionDelimiterSize} {delim2} +\MathLine{\Umathfractiondenomdown} {} {D, D'} {FractionDenominatorDisplayStyleShiftDown}{denom1} +\MathLine{\Umathfractiondenomdown} {} {T, T', S, S', SS, SS'}{FractionDenominatorShiftDown} {denom2} +\MathLine{\Umathfractiondenomvgap} {} {D, D'} {FractionDenominatorDisplayStyleGapMin} {3*default_rule_thickness} +\MathLine{\Umathfractiondenomvgap} {} {T, T', S, S', SS, SS'}{FractionDenominatorGapMin} {default_rule_thickness} +\MathLine{\Umathfractionnumup} {} {D, D'} {FractionNumeratorDisplayStyleShiftUp} {num1} +\MathLine{\Umathfractionnumup} {} {T, T', S, S', SS, SS'}{FractionNumeratorShiftUp} {num2} +\MathLine{\Umathfractionnumvgap} {} {D, D'} {FractionNumeratorDisplayStyleGapMin} {3*default_rule_thickness} +\MathLine{\Umathfractionnumvgap} {} {T, T', S, S', SS, SS'}{FractionNumeratorGapMin} {default_rule_thickness} +\MathLine{\Umathfractionrule} {} {} {FractionRuleThickness} {default_rule_thickness} +\MathLine{\Umathskewedfractionhgap} {} {} {SkewedFractionHorizontalGap} {math_quad/2} +\MathLine{\Umathskewedfractionvgap} {} {} {SkewedFractionVerticalGap} {math_x_height} +\MathLine{\Umathlimitabovebgap} {} {} {UpperLimitBaselineRiseMin} {big_op_spacing3} +\MathLine{\Umathlimitabovekern} {1} {} {0} {big_op_spacing5} +\MathLine{\Umathlimitabovevgap} {} {} {UpperLimitGapMin} {big_op_spacing1} +\MathLine{\Umathlimitbelowbgap} {} {} {LowerLimitBaselineDropMin} {big_op_spacing4} +\MathLine{\Umathlimitbelowkern} {1} {} {0} {big_op_spacing5} +\MathLine{\Umathlimitbelowvgap} {} {} {LowerLimitGapMin} {big_op_spacing2} +\MathLine{\Umathoverdelimitervgap} {} {} {StretchStackGapBelowMin} {big_op_spacing1} +\MathLine{\Umathoverdelimiterbgap} {} {} {StretchStackTopShiftUp} {big_op_spacing3} +\MathLine{\Umathunderdelimitervgap} {} {} {StretchStackGapAboveMin} {big_op_spacing2} +\MathLine{\Umathunderdelimiterbgap} {} {} {StretchStackBottomShiftDown} {big_op_spacing4} +\MathLine{\Umathoverbarkern} {} {} {OverbarExtraAscender} {default_rule_thickness} +\MathLine{\Umathoverbarrule} {} {} {OverbarRuleThickness} {default_rule_thickness} +\MathLine{\Umathoverbarvgap} {} {} {OverbarVerticalGap} {3*default_rule_thickness} +\MathLine{\Umathquad} {1} {} {} {math_quad} +\MathLine{\Umathradicalkern} {} {} {RadicalExtraAscender} {default_rule_thickness} +\MathLine{\Umathradicalrule} {2} {} {RadicalRuleThickness} {} +\MathLine{\Umathradicalvgap} {3} {D, D'} {RadicalDisplayStyleVerticalGap} {default_rule_thickness+abs(math_x_height)/4} +\MathLine{\Umathradicalvgap} {3} {T, T', S, S', SS, SS'}{RadicalVerticalGap} {default_rule_thickness+abs(default_rule_thickness)/4} +\MathLine{\Umathradicaldegreebefore}{2} {} {RadicalKernBeforeDegree} {} +\MathLine{\Umathradicaldegreeafter} {2} {} {RadicalKernAfterDegree} {} +\MathLine{\Umathradicaldegreeraise} {2,7}{} {RadicalDegreeBottomRaisePercent} {} +\MathLine{\Umathspaceafterscript} {4} {} {SpaceAfterScript} {script_space} +\MathLine{\Umathstackdenomdown} {} {D, D'} {StackBottomDisplayStyleShiftDown} {denom1} +\MathLine{\Umathstackdenomdown} {} {T, T', S, S', SS, SS'}{StackBottomShiftDown} {denom2} +\MathLine{\Umathstacknumup} {} {D, D'} {StackTopDisplayStyleShiftUp} {num1} +\MathLine{\Umathstacknumup} {} {T, T', S, S', SS, SS'}{StackTopShiftUp} {num3} +\MathLine{\Umathstackvgap} {} {D, D'} {StackDisplayStyleGapMin} {7*default_rule_thickness} +\MathLine{\Umathstackvgap} {} {T, T', S, S', SS, SS'}{StackGapMin} {3*default_rule_thickness} +\MathLine{\Umathsubshiftdown} {} {} {SubscriptShiftDown} {sub1} +\MathLine{\Umathsubshiftdrop} {} {} {SubscriptBaselineDropMin} {sub_drop} +\MathLine{\Umathsubsupshiftdown} {8} {} {SubscriptShiftDownWithSuperscript} {\emdash} +\MathLine{\Umathsubtopmax} {} {} {SubscriptTopMax} {abs(math_x_height*4)/5} +\MathLine{\Umathsubsupvgap} {} {} {SubSuperscriptGapMin} {4*default_rule_thickness} +\MathLine{\Umathsupbottommin} {} {} {SuperscriptBottomMin} {abs(math_x_height/4)} +\MathLine{\Umathsupshiftdrop} {} {} {SuperscriptBaselineDropMax} {sup_drop} +\MathLine{\Umathsupshiftup} {} {D} {SuperscriptShiftUp} {sup1} +\MathLine{\Umathsupshiftup} {} {T, S, SS,} {SuperscriptShiftUp} {sup2} +\MathLine{\Umathsupshiftup} {} {D', T', S', SS'} {SuperscriptShiftUpCramped} {sup3} +\MathLine{\Umathsupsubbottommax} {} {} {SuperscriptBottomMaxWithSubscript} {abs(math_x_height*4)/5} +\MathLine{\Umathunderbarkern} {} {} {UnderbarExtraDescender} {default_rule_thickness} +\MathLine{\Umathunderbarrule} {} {} {UnderbarRuleThickness} {default_rule_thickness} +\MathLine{\Umathunderbarvgap} {} {} {UnderbarVerticalGap} {3*default_rule_thickness} +\MathLine{\Umathconnectoroverlapmin}{5} {} {MinConnectorOverlap} {0} +\LL +\stoptabulate + +Note 1: \OPENTYPE\ fonts set \lpr {Umathlimitabovekern} and \lpr +{Umathlimitbelowkern} to zero and set \lpr {Umathquad} to the font size of the +used font, because these are not supported in the \type {MATH} table, + +Note 2: Traditional \TFM\ fonts do not set \lpr {Umathradicalrule} because +\TEX82\ uses the height of the radical instead. When this parameter is indeed not +set when \LUATEX\ has to typeset a radical, a backward compatibility mode will +kick in that assumes that an oldstyle \TEX\ font is used. Also, they do not set +\lpr {Umathradicaldegreebefore}, \lpr {Umathradicaldegreeafter}, and \lpr +{Umathradicaldegreeraise}. These are then automatically initialized to +$5/18$quad, $-10/18$quad, and 60. + +Note 3: If \TFM\ fonts are used, then the \lpr {Umathradicalvgap} is not set +until the first time \LUATEX\ has to typeset a formula because this needs +parameters from both family~2 and family~3. This provides a partial backward +compatibility with \TEX82, but that compatibility is only partial: once the \lpr +{Umathradicalvgap} is set, it will not be recalculated any more. + +Note 4: When \TFM\ fonts are used a similar situation arises with respect to \lpr +{Umathspaceafterscript}: it is not set until the first time \LUATEX\ has to +typeset a formula. This provides some backward compatibility with \TEX82. But +once the \lpr {Umathspaceafterscript} is set, \prm {scriptspace} will never be +looked at again. + +Note 5: Traditional \TFM\ fonts set \lpr {Umathconnectoroverlapmin} to zero +because \TEX82\ always stacks extensibles without any overlap. + +Note 6: The \lpr {Umathoperatorsize} is only used in \prm {displaystyle}, and is +only set in \OPENTYPE\ fonts. In \TFM\ font mode, it is artificially set to one +scaled point more than the initial attempt's size, so that always the \quote +{first next} will be tried, just like in \TEX82. + +Note 7: The \lpr {Umathradicaldegreeraise} is a special case because it is the +only parameter that is expressed in a percentage instead of a number of scaled +points. + +Note 8: \type {SubscriptShiftDownWithSuperscript} does not actually exist in the +\quote {standard} \OPENTYPE\ math font Cambria, but it is useful enough to be +added. + +Note 9: \type {FractionDelimiterDisplayStyleSize} and \type +{FractionDelimiterSize} do not actually exist in the \quote {standard} \OPENTYPE\ +math font Cambria, but were useful enough to be added. + +\stopsection + +\startsection[title={Math spacing}] + +\subsection{Setting inline surrounding space with \lpr {mathsurround[skip]}} + +\topicindex {math+spacing} + +Inline math is surrounded by (optional) \prm {mathsurround} spacing but that is a fixed +dimension. There is now an additional parameter \lpr {mathsurroundskip}. When set to a +non|-|zero value (or zero with some stretch or shrink) this parameter will replace +\prm {mathsurround}. By using an additional parameter instead of changing the nature +of \prm {mathsurround}, we can remain compatible. In the meantime a bit more +control has been added via \lpr {mathsurroundmode}. This directive can take 6 values +with zero being the default behaviour. + +\start + +\def\OneLiner#1#2% + {\NC \type{#1} + \NC \dontleavehmode\inframed[align=normal,offset=0pt,frame=off]{\mathsurroundmode#1\relax\hsize 100pt x$x$x} + \NC \dontleavehmode\inframed[align=normal,offset=0pt,frame=off]{\mathsurroundmode#1\relax\hsize 100pt x $x$ x} + \NC #2 + \NC \NR} + +\startbuffer +\mathsurround 10pt +\mathsurroundskip20pt +\stopbuffer + +\typebuffer \getbuffer + +\starttabulate[|c|c|c|pl|] +\DB mode \BC x\$x\$x \BC x \$x\$ x \BC effect \NC \NR +\TB +\OneLiner{0}{obey \prm {mathsurround} when \lpr {mathsurroundskip} is 0pt} +\OneLiner{1}{only add skip to the left} +\OneLiner{2}{only add skip to the right} +\OneLiner{3}{add skip to the left and right} +\OneLiner{4}{ignore the skip setting, obey \prm {mathsurround}} +\OneLiner{5}{disable all spacing around math} +\OneLiner{6}{only apply \lpr {mathsurroundskip} when also spacing} +\OneLiner{7}{only apply \lpr {mathsurroundskip} when no spacing} +\LL +\stoptabulate + +\stop + +Method six omits the surround glue when there is (x)spacing glue present while +method seven does the opposite, the glue is only applied when there is (x)space +glue present too. Anything more fancy, like checking the begining or end of a +paragraph (or edges of a box) would not be robust anyway. If you want that you +can write a callback that runs over a list and analyzes a paragraph. Actually, in +that case you could also inject glue (or set the properties of a math node) +explicitly. So, these modes are in practice mostly useful for special purposes +and experiments (they originate in a tracker item). Keep in mind that this glue +is part of the math node and not always treated as normal glue: it travels with +the begin and end math nodes. Also, method 6 and 7 will zero the skip related +fields in a node when applicable in the first occasion that checks them +(linebreaking or packaging). + +\subsection{Pairwise spacing and \lpr {Umath...spacing} commands} + +\topicindex {math+spacing} + +Besides the parameters mentioned in the previous sections, there are also 64 new +primitives to control the math spacing table (as explained in Chapter~18 of the +\TEX book). The primitive names are a simple matter of combining two math atom +types, but for completeness' sake, here is the whole list: + +\starttwocolumns +\startlines +\lpr {Umathordordspacing} +\lpr {Umathordopspacing} +\lpr {Umathordbinspacing} +\lpr {Umathordrelspacing} +\lpr {Umathordopenspacing} +\lpr {Umathordclosespacing} +\lpr {Umathordpunctspacing} +\lpr {Umathordinnerspacing} +\lpr {Umathopordspacing} +\lpr {Umathopopspacing} +\lpr {Umathopbinspacing} +\lpr {Umathoprelspacing} +\lpr {Umathopopenspacing} +\lpr {Umathopclosespacing} +\lpr {Umathoppunctspacing} +\lpr {Umathopinnerspacing} +\lpr {Umathbinordspacing} +\lpr {Umathbinopspacing} +\lpr {Umathbinbinspacing} +\lpr {Umathbinrelspacing} +\lpr {Umathbinopenspacing} +\lpr {Umathbinclosespacing} +\lpr {Umathbinpunctspacing} +\lpr {Umathbininnerspacing} +\lpr {Umathrelordspacing} +\lpr {Umathrelopspacing} +\lpr {Umathrelbinspacing} +\lpr {Umathrelrelspacing} +\lpr {Umathrelopenspacing} +\lpr {Umathrelclosespacing} +\lpr {Umathrelpunctspacing} +\lpr {Umathrelinnerspacing} +\lpr {Umathopenordspacing} +\lpr {Umathopenopspacing} +\lpr {Umathopenbinspacing} +\lpr {Umathopenrelspacing} +\lpr {Umathopenopenspacing} +\lpr {Umathopenclosespacing} +\lpr {Umathopenpunctspacing} +\lpr {Umathopeninnerspacing} +\lpr {Umathcloseordspacing} +\lpr {Umathcloseopspacing} +\lpr {Umathclosebinspacing} +\lpr {Umathcloserelspacing} +\lpr {Umathcloseopenspacing} +\lpr {Umathcloseclosespacing} +\lpr {Umathclosepunctspacing} +\lpr {Umathcloseinnerspacing} +\lpr {Umathpunctordspacing} +\lpr {Umathpunctopspacing} +\lpr {Umathpunctbinspacing} +\lpr {Umathpunctrelspacing} +\lpr {Umathpunctopenspacing} +\lpr {Umathpunctclosespacing} +\lpr {Umathpunctpunctspacing} +\lpr {Umathpunctinnerspacing} +\lpr {Umathinnerordspacing} +\lpr {Umathinneropspacing} +\lpr {Umathinnerbinspacing} +\lpr {Umathinnerrelspacing} +\lpr {Umathinneropenspacing} +\lpr {Umathinnerclosespacing} +\lpr {Umathinnerpunctspacing} +\lpr {Umathinnerinnerspacing} +\stoplines +\stoptwocolumns + +These parameters are of type \prm {muskip}, so setting a parameter can be done +like this: + +\starttyping +\Umathopordspacing\displaystyle=4mu plus 2mu +\stoptyping + +They are all initialized by \type {initex} to the values mentioned in the table +in Chapter~18 of the \TEX book. + +Note 1: for ease of use as well as for backward compatibility, \prm {thinmuskip}, +\prm {medmuskip} and \prm {thickmuskip} are treated specially. In their case a +pointer to the corresponding internal parameter is saved, not the actual \prm +{muskip} value. This means that any later changes to one of these three +parameters will be taken into account. + +Note 2: Careful readers will realise that there are also primitives for the items +marked \type {*} in the \TEX book. These will not actually be used as those +combinations of atoms cannot actually happen, but it seemed better not to break +orthogonality. They are initialized to zero. + +\subsection{Local settings} + +Math is processed in two passes. The first pass is needed to intercept for +instance \type {\over}, one of the few \TEX\ commands that actually has a +preceding argument. There are often lots of curly braces used in math and these +can result in a nested run of the math sub engine. However, you need to be aware +of the fact that some properties are kind of global to a formula and the last +setting (for instance a family switch) wins. This also means that a change (or +again, the last one) in math parameters affects the whole formula. In +\LUAMETATEX\ we have changed this model a bit. One can argue that this introduces +an incompatibility but it's hard to imagine a reason for setting the parameters +at the end of a formula run and assume that they also influence what goes in +front. + +\startbuffer +$ + x \Usubscript {-} + \frozen\Umathsubshiftdown\textstyle 0pt x \Usubscript {0} + {\frozen\Umathsubshiftdown\textstyle 5pt x \Usubscript {5}} + x \Usubscript {0} + {\frozen\Umathsubshiftdown\textstyle 15pt x \Usubscript {15}} + x \Usubscript {0} + {\frozen\Umathsubshiftdown\textstyle 20pt x \Usubscript {20}} + x \Usubscript {0} + \frozen\Umathsubshiftdown\textstyle 10pt x \Usubscript {10} + x \Usubscript {0} +$ +\stopbuffer + +\typebuffer + +The \type {\frozen} prefix does the magic: it injects information in the +math list about the set parameter. + +In \LUATEX\ 1.10 the last setting, the \type {10pt} drop wins, but in +\LUAMETATEX\ you will see each local setting taking effect. The implementation +uses a new node type, parameters nodes, so you you might encounter these in an +unprocessed math list. The result looks as follows: + +\blank \getbuffer \blank + + + +\subsection{Skips around display math and \lpr {mathdisplayskipmode}} + +\topicindex {math+spacing} + +The injection of \prm {abovedisplayskip} and \prm {belowdisplayskip} is not +symmetrical. An above one is always inserted, also when zero, but the below is +only inserted when larger than zero. Especially the latter makes it sometimes hard +to fully control spacing. Therefore \LUATEX\ comes with a new directive: \lpr +{mathdisplayskipmode}. The following values apply: + +\starttabulate[|c|l|] +\DB value \BC meaning \NC \NR +\TB +\NC 0 \NC normal \TEX\ behaviour \NC \NR +\NC 1 \NC always (same as 0) \NC \NR +\NC 2 \NC only when not zero \NC \NR +\NC 3 \NC never, not even when not zero \NC \NR +\LL +\stoptabulate + +\subsection {Nolimit correction with \lpr {mathnolimitsmode}} + +\topicindex {math+limits} + +There are two extra math parameters \lpr {Umathnolimitsupfactor} and \lpr +{Umathnolimitsubfactor} that were added to provide some control over how limits +are spaced (for example the position of super and subscripts after integral +operators). They relate to an extra parameter \lpr {mathnolimitsmode}. The half +corrections are what happens when scripts are placed above and below. The +problem with italic corrections is that officially that correction italic is used +for above|/|below placement while advanced kerns are used for placement at the +right end. The question is: how often is this implemented, and if so, do the +kerns assume correction too. Anyway, with this parameter one can control it. + +\starttabulate[|l|ck1|ck1|ck1|ck1|ck1|ck1|] + \NC + \NC \mathnolimitsmode0 $\displaystyle\int\nolimits^0_1$ + \NC \mathnolimitsmode1 $\displaystyle\int\nolimits^0_1$ + \NC \mathnolimitsmode2 $\displaystyle\int\nolimits^0_1$ + \NC \mathnolimitsmode3 $\displaystyle\int\nolimits^0_1$ + \NC \mathnolimitsmode4 $\displaystyle\int\nolimits^0_1$ + \NC \mathnolimitsmode8000 $\displaystyle\int\nolimits^0_1$ + \NC \NR + \TB + \BC mode + \NC \tttf 0 + \NC \tttf 1 + \NC \tttf 2 + \NC \tttf 3 + \NC \tttf 4 + \NC \tttf 8000 + \NC \NR + \BC superscript + \NC 0 + \NC font + \NC 0 + \NC 0 + \NC +ic/2 + \NC 0 + \NC \NR + \BC subscript + \NC -ic + \NC font + \NC 0 + \NC -ic/2 + \NC -ic/2 + \NC 8000ic/1000 + \NC \NR +\stoptabulate + +When the mode is set to one, the math parameters are used. This way a macro +package writer can decide what looks best. Given the current state of fonts in +\CONTEXT\ we currently use mode 1 with factor 0 for the superscript and 750 for +the subscripts. Positive values are used for both parameters but the subscript +shifts to the left. A \lpr {mathnolimitsmode} larger that 15 is considered to +be a factor for the subscript correction. This feature can be handy when +experimenting. + +\subsection {Controlling math italic mess with \lpr {mathitalicsmode}} + +\topicindex {math+italics} + +The \lpr {mathitalicsmode} parameter can be set to~1 to force italic correction +before noads that represent some more complex structure (read: everything +that is not an ord, bin, rel, open, close, punct or inner). We show a Cambria +example. + +\starttexdefinition Whatever #1 + \NC \type{\mathitalicsmode = #1} + \NC \mathitalicsmode#1\ruledhbox{$\left|T^1\right|$} + \NC \mathitalicsmode#1\ruledhbox{$\left|T\right|$} + \NC \mathitalicsmode#1\ruledhbox{$T+1$} + \NC \mathitalicsmode#1\ruledhbox{$T{1\over2}$} + \NC \mathitalicsmode#1\ruledhbox{$T\sqrt{1}$} + \NC \NR +\stoptexdefinition + +\start + \switchtobodyfont[cambria] + \starttabulate[|c|c|c|c|c|c|] + \Whatever{0}% + \Whatever{1}% + \stoptabulate +\stop + +This kind of parameters relate to the fact that italic correction in \OPENTYPE\ +math is bound to fuzzy rules. So, control is the solution. + +\subsection {Influencing script kerning with \lpr {mathscriptboxmode}} + +\topicindex {math+kerning} +\topicindex {math+scripts} + +If you want to typeset text in math macro packages often provide something \type +{\text} which obeys the script sizes. As the definition can be anything there is +a good chance that the kerning doesn't come out well when used in a script. Given +that the first glyph ends up in a \prm {hbox} we have some control over this. +And, as a bonus we also added control over the normal sublist kerning. The \lpr +{mathscriptboxmode} parameter defaults to~1. + +\starttabulate[|c|l|] +\DB value \BC meaning \NC \NR +\TB +\NC \type {0} \NC forget about kerning \NC \NR +\NC \type {1} \NC kern math sub lists with a valid glyph \NC \NR +\NC \type {2} \NC also kern math sub boxes that have a valid glyph \NC \NR +\NC \type {2} \NC only kern math sub boxes with a boundary node present\NC \NR +\LL +\stoptabulate + +Here we show some examples. Of course this doesn't solve all our problems, if +only because some fonts have characters with bounding boxes that compensate for +italics, while other fonts can lack kerns. + +\startbuffer[1] + $T_{\tf fluff}$ +\stopbuffer + +\startbuffer[2] + $T_{\text{fluff}}$ +\stopbuffer + +\startbuffer[3] + $T_{\text{\boundary1 fluff}}$ +\stopbuffer + +\unexpanded\def\Show#1#2#3% + {\doifelsenothing{#3} + {\small\tx\typeinlinebuffer[#1]} + {\doifelse{#3}{-} + {\small\bf\tt mode #2} + {\switchtobodyfont[#3]\showfontkerns\showglyphs\mathscriptboxmode#2\relax\inlinebuffer[#1]}}} + +\starttabulate[|lBT|c|c|c|c|c|] + \NC \NC \Show{1}{0}{} \NC\Show{1}{1}{} \NC \Show{2}{1}{} \NC \Show{2}{2}{} \NC \Show{3}{3}{} \NC \NR + \NC \NC \Show{1}{0}{-} \NC\Show{1}{1}{-} \NC \Show{2}{1}{-} \NC \Show{2}{2}{-} \NC \Show{3}{3}{-} \NC \NR + \NC modern \NC \Show{1}{0}{modern} \NC\Show{1}{1}{modern} \NC \Show{2}{1}{modern} \NC \Show{2}{2}{modern} \NC \Show{3}{3}{modern} \NC \NR + \NC lucidaot \NC \Show{1}{0}{lucidaot} \NC\Show{1}{1}{lucidaot} \NC \Show{2}{1}{lucidaot} \NC \Show{2}{2}{lucidaot} \NC \Show{3}{3}{lucidaot} \NC \NR + \NC pagella \NC \Show{1}{0}{pagella} \NC\Show{1}{1}{pagella} \NC \Show{2}{1}{pagella} \NC \Show{2}{2}{pagella} \NC \Show{3}{3}{pagella} \NC \NR + \NC cambria \NC \Show{1}{0}{cambria} \NC\Show{1}{1}{cambria} \NC \Show{2}{1}{cambria} \NC \Show{2}{2}{cambria} \NC \Show{3}{3}{cambria} \NC \NR + \NC dejavu \NC \Show{1}{0}{dejavu} \NC\Show{1}{1}{dejavu} \NC \Show{2}{1}{dejavu} \NC \Show{2}{2}{dejavu} \NC \Show{3}{3}{dejavu} \NC \NR +\stoptabulate + +Kerning between a character subscript is controlled by \lpr {mathscriptcharmode} +which also defaults to~1. + +Here is another example. Internally we tag kerns as italic kerns or font kerns +where font kerns result from the staircase kern tables. In 2018 fonts like Latin +Modern and Pagella rely on cheats with the boundingbox, Cambria uses staircase +kerns and Lucida a mixture. Depending on how fonts evolve we might add some more +control over what one can turn on and off. + +\def\MathSample#1#2#3% + {\NC + #1 \NC + #2 \NC + \showglyphdata \switchtobodyfont[#2,17.3pt]$#3T_{f}$ \NC + \showglyphdata \switchtobodyfont[#2,17.3pt]$#3\gamma_{e}$ \NC + \showglyphdata \switchtobodyfont[#2,17.3pt]$#3\gamma_{ee}$ \NC + \showglyphdata \switchtobodyfont[#2,17.3pt]$#3T_{\tf fluff}$ \NC + \NR} + +\starttabulate[|Tl|Tl|l|l|l|l|] + \FL + \MathSample{normal}{modern} {\mr} + \MathSample{} {pagella} {\mr} + \MathSample{} {cambria} {\mr} + \MathSample{} {lucidaot}{\mr} + \ML + \MathSample{bold} {modern} {\mb} + \MathSample{} {pagella} {\mb} + \MathSample{} {cambria} {\mb} + \MathSample{} {lucidaot}{\mb} + \LL +\stoptabulate + +\subsection{Forcing fixed scripts with \lpr {mathscriptsmode}} + +We have three parameters that are used for this fixed anchoring: + +\starttabulate[|c|l|] +\DB parameter \BC register \NC \NR +\NC $d$ \NC \lpr {Umathsubshiftdown} \NC \NR +\NC $u$ \NC \lpr {Umathsupshiftup} \NC \NR +\NC $s$ \NC \lpr {Umathsubsupshiftdown} \NC \NR +\LL +\stoptabulate + +When we set \lpr {mathscriptsmode} to a value other than zero these are used +for calculating fixed positions. This is something that is needed for instance +for chemistry. You can manipulate the mentioned variables to achieve different +effects. + +\def\SampleMath#1% + {$\mathscriptsmode#1\mathupright CH_2 + CH^+_2 + CH^2_2$} + +\starttabulate[|c|c|c|p|] +\DB mode \BC down \BC up \BC example \NC \NR +\TB +\NC 0 \NC dynamic \NC dynamic \NC \SampleMath{0} \NC \NR +\NC 1 \NC $d$ \NC $u$ \NC \SampleMath{1} \NC \NR +\NC 2 \NC $s$ \NC $u$ \NC \SampleMath{2} \NC \NR +\NC 3 \NC $s$ \NC $u + s - d$ \NC \SampleMath{3} \NC \NR +\NC 4 \NC $d + (s-d)/2$ \NC $u + (s-d)/2$ \NC \SampleMath{4} \NC \NR +\NC 5 \NC $d$ \NC $u + s - d$ \NC \SampleMath{5} \NC \NR +\LL +\stoptabulate + +The value of this parameter obeys grouping but applies to the whole current +formula. + +% if needed we can put the value in stylenodes but maybe more should go there + +\subsection{Penalties: \lpr {mathpenaltiesmode}} + +\topicindex {math+penalties} + +Only in inline math penalties will be added in a math list. You can force +penalties (also in display math) by setting: + +\starttyping +\mathpenaltiesmode = 1 +\stoptyping + +This primnitive is not really needed in \LUATEX\ because you can use the callback +\cbk {mlist_to_hlist} to force penalties by just calling the regular routine +with forced penalties. However, as part of opening up and control this primitive +makes sense. As a bonus we also provide two extra penalties: + +\starttyping +\prebinoppenalty = -100 % example value +\prerelpenalty = 900 % example value +\stoptyping + +They default to inifinite which signals that they don't need to be inserted. When +set they are injected before a binop or rel noad. This is an experimental feature. + +\subsection{Equation spacing: \lpr {matheqnogapstep}} + +By default \TEX\ will add one quad between the equation and the number. This is +hard coded. A new primitive can control this: + +\startsyntax +\matheqnogapstep = 1000 +\stopsyntax + +Because a math quad from the math text font is used instead of a dimension, we +use a step to control the size. A value of zero will suppress the gap. The step +is divided by 1000 which is the usual way to mimmick floating point factors in +\TEX. + +\stopsection + +\startsection[title={Math constructs}] + +\subsection {Unscaled fences and \lpr{mathdelimitersmode}} + +\topicindex {math+fences} + +The \lpr {mathdelimitersmode} primitive is experimental and deals with the +following (potential) problems. Three bits can be set. The first bit prevents an +unwanted shift when the fence symbol is not scaled (a cambria side effect). The +second bit forces italic correction between a preceding character ordinal and the +fenced subformula, while the third bit turns that subformula into an ordinary so +that the same spacing applies as with unfenced variants. Here we show Cambria +(with \lpr {mathitalicsmode} enabled). + +\starttexdefinition Whatever #1 + \NC \type{\mathdelimitersmode = #1} + \NC \mathitalicsmode1\mathdelimitersmode#1\ruledhbox{\showglyphs\showfontkerns\showfontitalics$f(x)$} + \NC \mathitalicsmode1\mathdelimitersmode#1\ruledhbox{\showglyphs\showfontkerns\showfontitalics$f\left(x\right)$} + \NC \NR +\stoptexdefinition + +\start + \switchtobodyfont[cambria] + \starttabulate[|l|l|l|] + \Whatever{0}\Whatever{1}\Whatever{2}\Whatever{3}% + \Whatever{4}\Whatever{5}\Whatever{6}\Whatever{7}% + \stoptabulate +\stop + +So, when set to 7 fenced subformulas with unscaled delimiters come out the same +as unfenced ones. This can be handy for cases where one is forced to use \prm +{left} and \prm {right} always because of unpredictable content. As said, it's an +experimental feature (which somehow fits in the exceptional way fences are dealt +with in the engine). The full list of flags is given in the next table: + +\starttabulate[|c|l|] +\DB value \BC meaning \NC \NR +\TB +\NC \type{"01} \NC don't apply the usual shift \NC \NR +\NC \type{"02} \NC apply italic correction when possible \NC \NR +\NC \type{"04} \NC force an ordinary subformula \NC \NR +\NC \type{"08} \NC no shift when a base character \NC \NR +\NC \type{"10} \NC only shift when an extensible \NC \NR +\LL +\stoptabulate + +The effect can depend on the font (and for Cambria one can use for instance \type {"16}). + +\subsection[mathacc]{Accent handling with \lpr {Umathaccent}} + +\topicindex {math+accents} + +\LUATEX\ supports both top accents and bottom accents in math mode, and math +accents stretch automatically (if this is supported by the font the accent comes +from, of course). Bottom and combined accents as well as fixed-width math accents +are controlled by optional keywords following \lpr {Umathaccent}. + +The keyword \type {bottom} after \lpr {Umathaccent} signals that a bottom accent +is needed, and the keyword \type {both} signals that both a top and a bottom +accent are needed (in this case two accents need to be specified, of course). + +Then the set of three integers defining the accent is read. This set of integers +can be prefixed by the \type {fixed} keyword to indicate that a non-stretching +variant is requested (in case of both accents, this step is repeated). + +A simple example: + +\starttyping +\Umathaccent both fixed 0 0 "20D7 fixed 0 0 "20D7 {example} +\stoptyping + +If a math top accent has to be placed and the accentee is a character and has a +non-zero \type {top_accent} value, then this value will be used to place the +accent instead of the \prm {skewchar} kern used by \TEX82. + +The \type {top_accent} value represents a vertical line somewhere in the +accentee. The accent will be shifted horizontally such that its own \type +{top_accent} line coincides with the one from the accentee. If the \type +{top_accent} value of the accent is zero, then half the width of the accent +followed by its italic correction is used instead. + +The vertical placement of a top accent depends on the \type {x_height} of the +font of the accentee (as explained in the \TEX book), but if a value turns out +to be zero and the font had a \type {MathConstants} table, then \type +{AccentBaseHeight} is used instead. + +The vertical placement of a bottom accent is straight below the accentee, no +correction takes place. + +Possible locations are \type {top}, \type {bottom}, \type {both} and \type +{center}. When no location is given \type {top} is assumed. An additional +parameter \nod {fraction} can be specified followed by a number; a value of for +instance 1200 means that the criterium is 1.2 times the width of the nucleus. The +fraction only applies to the stepwise selected shapes and is mostly meant for the +\type {overlay} location. It also works for the other locations but then it +concerns the width. + +\subsection{Building radicals with \lpr {Uradical} and \lpr {Uroot}} + +\topicindex {math+radicals} + +The new primitive \lpr {Uroot} allows the construction of a radical noad +including a degree field. Its syntax is an extension of \lpr {Uradical}: + +\starttyping +\Uradical +\Uroot +\stoptyping + +The placement of the degree is controlled by the math parameters \lpr +{Umathradicaldegreebefore}, \lpr {Umathradicaldegreeafter}, and \lpr +{Umathradicaldegreeraise}. The degree will be typeset in \prm +{scriptscriptstyle}. + +\subsection{Super- and subscripts} + +The character fields in a \LUA|-|loaded \OPENTYPE\ math font can have a \quote +{mathkern} table. The format of this table is the same as the \quote {mathkern} +table that is returned by the \type {fontloader} library, except that all height +and kern values have to be specified in actual scaled points. + +When a super- or subscript has to be placed next to a math item, \LUATEX\ checks +whether the super- or subscript and the nucleus are both simple character items. +If they are, and if the fonts of both character items are \OPENTYPE\ fonts (as +opposed to legacy \TEX\ fonts), then \LUATEX\ will use the \OPENTYPE\ math +algorithm for deciding on the horizontal placement of the super- or subscript. + +This works as follows: + +\startitemize + \startitem + The vertical position of the script is calculated. + \stopitem + \startitem + The default horizontal position is flat next to the base character. + \stopitem + \startitem + For superscripts, the italic correction of the base character is added. + \stopitem + \startitem + For a superscript, two vertical values are calculated: the bottom of the + script (after shifting up), and the top of the base. For a subscript, the two + values are the top of the (shifted down) script, and the bottom of the base. + \stopitem + \startitem + For each of these two locations: + \startitemize + \startitem + find the math kern value at this height for the base (for a subscript + placement, this is the bottom_right corner, for a superscript + placement the top_right corner) + \stopitem + \startitem + find the math kern value at this height for the script (for a + subscript placement, this is the top_left corner, for a superscript + placement the bottom_left corner) + \stopitem + \startitem + add the found values together to get a preliminary result. + \stopitem + \stopitemize + \stopitem + \startitem + The horizontal kern to be applied is the smallest of the two results from + previous step. + \stopitem +\stopitemize + +The math kern value at a specific height is the kern value that is specified by the +next higher height and kern pair, or the highest one in the character (if there is no +value high enough in the character), or simply zero (if the character has no math kern +pairs at all). + +\subsection{Scripts on extensibles: \lpr {Uunderdelimiter}, \lpr {Uoverdelimiter}, +\lpr {Udelimiterover}, \lpr {Udelimiterunder} and \lpr {Uhextensible}} + +\topicindex {math+scripts} +\topicindex {math+delimiters} +\topicindex {math+extensibles} + +The primitives \lpr {Uunderdelimiter} and \lpr {Uoverdelimiter} allow the +placement of a subscript or superscript on an automatically extensible item and +\lpr {Udelimiterunder} and \lpr {Udelimiterover} allow the placement of an +automatically extensible item as a subscript or superscript on a nucleus. The +input: + +% these produce radical noads .. in fact the code base has the numbers wrong for +% quite a while, so no one seems to use this + +\startbuffer +$\Uoverdelimiter 0 "2194 {\hbox{\strut overdelimiter}}$ +$\Uunderdelimiter 0 "2194 {\hbox{\strut underdelimiter}}$ +$\Udelimiterover 0 "2194 {\hbox{\strut delimiterover}}$ +$\Udelimiterunder 0 "2194 {\hbox{\strut delimiterunder}}$ +\stopbuffer + +\typebuffer will render this: + +\blank \startnarrower \getbuffer \stopnarrower \blank + +The vertical placements are controlled by \lpr {Umathunderdelimiterbgap}, \lpr +{Umathunderdelimitervgap}, \lpr {Umathoverdelimiterbgap}, and \lpr +{Umathoverdelimitervgap} in a similar way as limit placements on large operators. +The superscript in \lpr {Uoverdelimiter} is typeset in a suitable scripted style, +the subscript in \lpr {Uunderdelimiter} is cramped as well. + +These primitives accepts an option \type {width} specification. When used the +also optional keywords \type {left}, \type {middle} and \type {right} will +determine what happens when a requested size can't be met (which can happen when +we step to successive larger variants). + +An extra primitive \lpr {Uhextensible} is available that can be used like this: + +\startbuffer +$\Uhextensible width 10cm 0 "2194$ +\stopbuffer + +\typebuffer This will render this: + +\blank \startnarrower \getbuffer \stopnarrower \blank + +Here you can also pass options, like: + +\startbuffer +$\Uhextensible width 1pt middle 0 "2194$ +\stopbuffer + +\typebuffer This gives: + +\blank \startnarrower \getbuffer \stopnarrower \blank + +\LUATEX\ internally uses a structure that supports \OPENTYPE\ \quote +{MathVariants} as well as \TFM\ \quote {extensible recipes}. In most cases where +font metrics are involved we have a different code path for traditional fonts end +\OPENTYPE\ fonts. + +\subsection{Fractions and the new \lpr {Uskewed} and \lpr {Uskewedwithdelims}} + +\topicindex {math+fractions} + +The \prm {abovewithdelims} command accepts a keyword \type {exact}. When issued +the extra space relative to the rule thickness is not added. One can of course +use the \type {\Umathfraction..gap} commands to influence the spacing. Also the +rule is still positioned around the math axis. + +\starttyping +$$ { {a} \abovewithdelims() exact 4pt {b} }$$ +\stoptyping + +The math parameter table contains some parameters that specify a horizontal and +vertical gap for skewed fractions. Of course some guessing is needed in order to +implement something that uses them. And so we now provide a primitive similar to the +other fraction related ones but with a few options so that one can influence the +rendering. Of course a user can also mess around a bit with the parameters +\lpr {Umathskewedfractionhgap} and \lpr {Umathskewedfractionvgap}. + +The syntax used here is: + +\starttyping +{ {1} \Uskewed / {2} } +{ {1} \Uskewedwithdelims / () {2} } +\stoptyping + +where the options can be \type {noaxis} and \type {exact}. By default we add half +the axis to the shifts and by default we zero the width of the middle character. +For Latin Modern the result looks as follows: + +\def\ShowA#1#2#3{$x + { {#1} \Uskewed / #3 {#2} } + x$} +\def\ShowB#1#2#3{$x + { {#1} \Uskewedwithdelims / () #3 {#2} } + x$} + +\start + \switchtobodyfont[modern] + \starttabulate[||||||] + \NC \NC + \ShowA{a}{b}{} \NC + \ShowA{1}{2}{} \NC + \ShowB{a}{b}{} \NC + \ShowB{1}{2}{} \NC + \NR + \NC \type{exact} \NC + \ShowA{a}{b}{exact} \NC + \ShowA{1}{2}{exact} \NC + \ShowB{a}{b}{exact} \NC + \ShowB{1}{2}{exact} \NC + \NR + \NC \type{noaxis} \NC + \ShowA{a}{b}{noaxis} \NC + \ShowA{1}{2}{noaxis} \NC + \ShowB{a}{b}{noaxis} \NC + \ShowB{1}{2}{noaxis} \NC + \NR + \NC \type{exact noaxis} \NC + \ShowA{a}{b}{exact noaxis} \NC + \ShowA{1}{2}{exact noaxis} \NC + \ShowB{a}{b}{exact noaxis} \NC + \ShowB{1}{2}{exact noaxis} \NC + \NR + \stoptabulate +\stop + +\subsection {Delimiters: \type{\Uleft}, \prm {Umiddle} and \prm {Uright}} + +\topicindex {math+delimiters} + +Normally you will force delimiters to certain sizes by putting an empty box or +rule next to it. The resulting delimiter will either be a character from the +stepwise size range or an extensible. The latter can be quite differently +positioned than the characters as it depends on the fit as well as the fact if +the used characters in the font have depth or height. Commands like (plain \TEX +s) \type {\big} need use this feature. In \LUATEX\ we provide a bit more control +by three variants that support optional parameters \type {height}, \type {depth} +and \type {axis}. The following example uses this: + +\startbuffer +\Uleft height 30pt depth 10pt \Udelimiter "0 "0 "000028 +\quad x\quad +\Umiddle height 40pt depth 15pt \Udelimiter "0 "0 "002016 +\quad x\quad +\Uright height 30pt depth 10pt \Udelimiter "0 "0 "000029 +\quad \quad \quad +\Uleft height 30pt depth 10pt axis \Udelimiter "0 "0 "000028 +\quad x\quad +\Umiddle height 40pt depth 15pt axis \Udelimiter "0 "0 "002016 +\quad x\quad +\Uright height 30pt depth 10pt axis \Udelimiter "0 "0 "000029 +\stopbuffer + +\typebuffer + +\startlinecorrection +\ruledhbox{\mathematics{\getbuffer}} +\stoplinecorrection + +The keyword \type {exact} can be used as directive that the real dimensions +should be applied when the criteria can't be met which can happen when we're +still stepping through the successively larger variants. When no dimensions are +given the \type {noaxis} command can be used to prevent shifting over the axis. + +You can influence the final class with the keyword \type {class} which will +influence the spacing. The numbers are the same as for character classes. + +\subsection {Accents: \type{\mathlimitsmode}} + +\topicindex {math+accents} + +When you use \type {\limits} or \type {\nolimits} without scripts spacing might +get messed up. This can be prevented by setting \type {\mathlimitsmode} to a +non|-|zero value. + +\stopsection + +\startsection[title={Extracting values}] + +\subsection{Codes and using \lpr {Umathcode}, \lpr {Umathcharclass}, \lpr +{Umathcharfam} and \lpr {Umathcharslot}} + +\topicindex {math+codes} + +You can extract the components of a math character. Say that we have defined: + +\starttyping +\Umathcode 1 2 3 4 +\stoptyping + +then + +\starttyping +[\Umathcharclass1] [\Umathcharfam1] [\Umathcharslot1] +\stoptyping + +will return: + +\starttyping +[2] [3] [4] +\stoptyping + +These commands are provides as convenience. Before they come available you could +do the following: + +\starttyping +\def\Umathcharclass{\directlua{tex.print(tex.getmathcode(token.scan_int())[1])}} +\def\Umathcharfam {\directlua{tex.print(tex.getmathcode(token.scan_int())[2])}} +\def\Umathcharslot {\directlua{tex.print(tex.getmathcode(token.scan_int())[3])}} +\stoptyping + +\subsection {Last lines and \lpr{predisplaygapfactor}} + +\topicindex {math+last line} + +There is a new primitive to control the overshoot in the calculation of the +previous line in mid|-|paragraph display math. The default value is 2 times +the em width of the current font: + +\starttyping +\predisplaygapfactor=2000 +\stoptyping + +If you want to have the length of the last line independent of math i.e.\ you don't +want to revert to a hack where you insert a fake display math formula in order to +get the length of the last line, the following will often work too: + +\starttyping +\def\lastlinelength{\dimexpr + \directlua {tex.sprint ( + (nodes.dimensions(node.tail(tex.lists.page_head).list)) + )}sp +\relax} +\stoptyping + +\stopsection + +\startsection[title={Math mode}] + +\subsection {Verbose versions of single|-|character math commands like \lpr {Usuperscript} +and \lpr {Usubscript}} + +\topicindex {math+styles} + +\LUATEX\ defines six new primitives that have the same function as +\type {^}, \type {_}, \type {$}, and \type {$$}: + +\starttabulate[|l|l|] +\DB primitive \BC explanation \NC \NR +\TB +\NC \lpr {Usuperscript} \NC duplicates the functionality of \type {^} \NC \NR +\NC \lpr {Usubscript} \NC duplicates the functionality of \type {_} \NC \NR +\NC \lpr {Ustartmath} \NC duplicates the functionality of \type {$}, % $ + when used in non-math mode. \NC \NR +\NC \lpr {Ustopmath} \NC duplicates the functionality of \type {$}, % $ + when used in inline math mode. \NC \NR +\NC \lpr {Ustartdisplaymath} \NC duplicates the functionality of \type {$$}, % $$ + when used in non-math mode. \NC \NR +\NC \lpr {Ustopdisplaymath} \NC duplicates the functionality of \type {$$}, % $$ + when used in display math mode. \NC \NR +\LL +\stoptabulate + +The \lpr {Ustopmath} and \lpr {Ustopdisplaymath} primitives check if the current +math mode is the correct one (inline vs.\ displayed), but you can freely intermix +the four mathon|/|mathoff commands with explicit dollar sign(s). + +\subsection{Script commands \lpr {Unosuperscript} and \lpr {Unosubscript}} + +\topicindex {math+styles} +\topicindex {math+scripts} + +These two commands result in super- and subscripts but with the current style (at the +time of rendering). So, + +\startbuffer[script] +$ + x\Usuperscript {1}\Usubscript {2} = + x\Unosuperscript{1}\Unosubscript{2} = + x\Usuperscript {1}\Unosubscript{2} = + x\Unosuperscript{1}\Usubscript {2} +$ +\stopbuffer + +\typebuffer + +results in \inlinebuffer[script]. + +\subsection{Allowed math commands in non|-|math modes} + +\topicindex {math+text} +\topicindex {text+math} + +The commands \prm {mathchar}, and \lpr {Umathchar} and control sequences that are +the result of \prm {mathchardef} or \lpr {Umathchardef} are also acceptable in +the horizontal and vertical modes. In those cases, the \prm {textfont} from the +requested math family is used. + +\stopsection + +\startsection[title={Goodies}] + +\subsection {Flattening: \lpr {mathflattenmode}} + +\topicindex {math+flattening} + +The \TEX\ math engine collapses \type {ord} noads without sub- and superscripts +and a character as nucleus. and which has the side effect that in \OPENTYPE\ mode +italic corrections are applied (given that they are enabled). + +\startbuffer[sample] +\switchtobodyfont[modern] +$V \mathbin{\mathbin{v}} V$\par +$V \mathord{\mathord{v}} V$\par +\stopbuffer + +\typebuffer[sample] + +This renders as: + +\blank \start \mathflattenmode\plusone \getbuffer[sample] \stop \blank + +When we set \lpr {mathflattenmode} to 31 we get: + +\blank \start \mathflattenmode\numexpr1+2+4+8+16\relax \getbuffer[sample] \stop \blank + +When you see no difference, then the font probably has the proper character +dimensions and no italic correction is needed. For Latin Modern (at least till +2018) there was a visual difference. In that respect this parameter is not always +needed unless of course you want efficient math lists anyway. + +You can influence flattening by adding the appropriate number to the value of the +mode parameter. The default value is~1. + +\starttabulate[|Tc|c|] +\DB mode \BC class \NC \NR +\TB +\NC 1 \NC ord \NC \NR +\NC 2 \NC bin \NC \NR +\NC 4 \NC rel \NC \NR +\NC 8 \NC punct \NC \NR +\NC 16 \NC inner \NC \NR +\LL +\stoptabulate + +\subsection {Less Tracing} + +\topicindex {math+tracing} + +Because there are quite some math related parameters and values, it is possible +to limit tracing. Only when \type {tracingassigns} and|/|or \type +{tracingrestores} are set to~2 or more they will be traced. + +\stopsection + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/luametatex/luametatex-metapost.tex b/doc/context/sources/general/manuals/luametatex/luametatex-metapost.tex new file mode 100644 index 000000000..3f0d0a945 --- /dev/null +++ b/doc/context/sources/general/manuals/luametatex/luametatex-metapost.tex @@ -0,0 +1,479 @@ +% language=uk + +% lua.newtable + +\environment luametatex-style + +\startcomponent luametatex-metapost + +\startchapter[reference=metapost,title={The \METAPOST\ library \type {mplib}}] + +\startsection[title={Process management}][library=mplib] + +\topicindex {\METAPOST} +\topicindex {\METAPOST+mplib} +\topicindex {images+mplib} +\topicindex {images+\METAPOST} + +\libindex{version} + +The \METAPOST\ library interface registers itself in the table \type {mplib}. It +is based on \MPLIB\ version \ctxlua {context(mplib.version())}. + +\subsection{\type {new}} + +\libindex{new} + +To create a new \METAPOST\ instance, call + +\startfunctioncall + mp = mplib.new({...}) +\stopfunctioncall + +This creates the \type {mp} instance object. The argument hash can have a number +of different fields, as follows: + +\starttabulate[|l|l|pl|pl|] +\DB name \BC type \BC description \BC default \NC \NR +\TB +\NC \type{error_line} \NC number \NC error line width \NC 79 \NC \NR +\NC \type{print_line} \NC number \NC line length in ps output \NC 100 \NC \NR +\NC \type{random_seed} \NC number \NC the initial random seed \NC variable \NC \NR +\NC \type{math_mode} \NC string \NC the number system to use: + \type {scaled}, + \type {double} or + % \type {binary} or + \type {decimal} \NC \type {scaled} \NC \NR +\NC \type{interaction} \NC string \NC the interaction mode: + \type {batch}, + \type {nonstop}, + \type {scroll} or + \type {errorstop} \NC \type {errorstop} \NC \NR +\NC \type{job_name} \NC string \NC a compatibility value \NC \type {mpout} \NC \NR +\NC \type{find_file} \NC function \NC a function to find files \NC only local files \NC \NR +\NC \type{utf8} \NC boolean \NC permit characters in the + range 128 upto 255 to be + part of names \NC \type {false} \NC \NR +\LL +\stoptabulate + +The binary mode is no longer available in the \LUATEX\ version of \MPLIB. It +offers no real advantage and brings a ton of extra libraries with platform +specific properties that we can now avoid. We might introduce a high resolution +scaled variant at some point but only when it pays of performance wise. + +The \type {find_file} function should be of this form: + +\starttyping + found = finder ( name, mode, type) +\stoptyping + +with: + +\starttabulate[|l|p|] +\DB name \BC the requested file \NC \NR +\TB +\NC \type{mode} \NC the file mode: \type {r} or \type {w} \NC \NR +\NC \type{type} \NC the kind of file, one of: \type {mp}, \type {tfm}, \type {map}, + \type {pfb}, \type {enc} \NC \NR +\LL +\stoptabulate + +Return either the full path name of the found file, or \type {nil} if the file +cannot be found. + +Note that the new version of \MPLIB\ no longer uses binary mem files, so the way +to preload a set of macros is simply to start off with an \type {input} command +in the first \type {execute} call. + +When you are processing a snippet of text starting with \type {btex} and +ending with either \type {etex} or \type {verbatimtex}, the \METAPOST\ +\type {texscriptmode} parameter controls how spaces and newlines get honoured. +The default value is~1. Possible values are: + +\starttabulate[|l|p|] +\DB name \BC meaning \NC \NR +\TB +\NC \type {0} \NC no newlines \NC \NR +\NC \type {1} \NC newlines in \type {verbatimtex} \NC \NR +\NC \type {2} \NC newlines in \type {verbatimtex} and \type {etex} \NC \NR +\NC \type {3} \NC no leading and trailing strip in \type {verbatimtex} \NC \NR +\NC \type {4} \NC no leading and trailing strip in \type {verbatimtex} and \type {btex} \NC \NR +\LL +\stoptabulate + +That way the \LUA\ handler (assigned to \type {make_text}) can do what it likes. +An \type {etex} has to be followed by a space or \type {;} or be at the end of a +line and preceded by a space or at the beginning of a line. + +\subsection{\type {statistics}} + +\libindex{statistics} + +You can request statistics with: + +\startfunctioncall +
stats = mp:statistics() +\stopfunctioncall + +This function returns the vital statistics for an \MPLIB\ instance. There are +four fields, giving the maximum number of used items in each of four allocated +object classes: + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{main_memory} \NC number \NC memory size \NC \NR +\NC \type{hash_size} \NC number \NC hash size\NC \NR +\NC \type{param_size} \NC number \NC simultaneous macro parameters\NC \NR +\NC \type{max_in_open} \NC number \NC input file nesting levels\NC \NR +\LL +\stoptabulate + +Note that in the new version of \MPLIB, this is informational only. The objects +are all allocated dynamically, so there is no chance of running out of space +unless the available system memory is exhausted. + +\subsection{\type {execute}} + +\libindex{execute} + +You can ask the \METAPOST\ interpreter to run a chunk of code by calling + +\startfunctioncall +
rettable = execute(mp,"metapost code") +\stopfunctioncall + +for various bits of \METAPOST\ language input. Be sure to check the \type +{rettable.status} (see below) because when a fatal \METAPOST\ error occurs the +\MPLIB\ instance will become unusable thereafter. + +Generally speaking, it is best to keep your chunks small, but beware that all +chunks have to obey proper syntax, like each of them is a small file. For +instance, you cannot split a single statement over multiple chunks. + +In contrast with the normal stand alone \type {mpost} command, there is +\notabene {no} implied \quote{input} at the start of the first chunk. + +\subsection{\type {finish}} + +\libindex{finish} + +\startfunctioncall +
rettable = finish(mp) +\stopfunctioncall + +If for some reason you want to stop using an \MPLIB\ instance while processing is +not yet actually done, you can call \type {finish}. Eventually, used memory +will be freed and open files will be closed by the \LUA\ garbage collector, but +an explicit \type {finish} is the only way to capture the final part of the +output streams. + +\stopsection + +\startsection[title={The end result}] + +\libindex {fields} + +The return value of \type {execute} and \type {finish} is a table with a +few possible keys (only \type {status} is always guaranteed to be present). + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{log} \NC string \NC output to the \quote {log} stream \NC \NR +\NC \type{term} \NC string \NC output to the \quote {term} stream \NC \NR +\NC \type{error} \NC string \NC output to the \quote {error} stream + (only used for \quote {out of memory}) \NC \NR +\NC \type{status} \NC number \NC the return value: + \type {0} = good, + \type {1} = warning, + \type {2} = errors, + \type {3} = fatal error \NC \NR +\NC \type{fig} \NC table \NC an array of generated figures (if any) \NC \NR +\LL +\stoptabulate + +When \type {status} equals~3, you should stop using this \MPLIB\ instance +immediately, it is no longer capable of processing input. + +If it is present, each of the entries in the \type {fig} array is a userdata +representing a figure object, and each of those has a number of object methods +you can call: + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{boundingbox} \NC function \NC returns the bounding box, as an array of 4 + values \NC \NR +\NC \type{postscript} \NC function \NC returns a string that is the ps output of the + \type {fig}. this function accepts two optional + integer arguments for specifying the values of + \type {prologues} (first argument) and \type + {procset} (second argument) \NC \NR +\NC \type{svg} \NC function \NC returns a string that is the svg output of the + \type {fig}. This function accepts an optional + integer argument for specifying the value of + \type {prologues} \NC \NR +\NC \type{objects} \NC function \NC returns the actual array of graphic objects in + this \type {fig} \NC \NR +\NC \type{copy_objects} \NC function \NC returns a deep copy of the array of graphic + objects in this \type {fig} \NC \NR +\NC \type{filename} \NC function \NC the filename this \type {fig}'s \POSTSCRIPT\ + output would have written to in stand alone + mode \NC \NR +\NC \type{width} \NC function \NC the \type {fontcharwd} value \NC \NR +\NC \type{height} \NC function \NC the \type {fontcharht} value \NC \NR +\NC \type{depth} \NC function \NC the \type {fontchardp} value \NC \NR +\NC \type{italcorr} \NC function \NC the \type {fontcharit} value \NC \NR +\NC \type{charcode} \NC function \NC the (rounded) \type {charcode} value \NC \NR +\LL +\stoptabulate + +Note: you can call \type {fig:objects()} only once for any one \type {fig} +object! + +When the boundingbox represents a \quote {negated rectangle}, i.e.\ when the +first set of coordinates is larger than the second set, the picture is empty. + +Graphical objects come in various types that each has a different list of +accessible values. The types are: \type {fill}, \type {outline}, \type {text}, +\type {start_clip}, \type {stop_clip}, \type {start_bounds}, \type {stop_bounds}, +\type {special}. + +There is a helper function (\type {mplib.fields(obj)}) to get the list of +accessible values for a particular object, but you can just as easily use the +tables given below. + +All graphical objects have a field \type {type} that gives the object type as a +string value; it is not explicit mentioned in the following tables. In the +following, \type {number}s are \POSTSCRIPT\ points represented as a floating +point number, unless stated otherwise. Field values that are of type \type +{table} are explained in the next section. + +\subsection{fill} + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{path} \NC table \NC the list of knots \NC \NR +\NC \type{htap} \NC table \NC the list of knots for the reversed trajectory \NC \NR +\NC \type{pen} \NC table \NC knots of the pen \NC \NR +\NC \type{color} \NC table \NC the object's color \NC \NR +\NC \type{linejoin} \NC number \NC line join style (bare number)\NC \NR +\NC \type{miterlimit} \NC number \NC miterlimit\NC \NR +\NC \type{prescript} \NC string \NC the prescript text \NC \NR +\NC \type{postscript} \NC string \NC the postscript text \NC \NR +\LL +\stoptabulate + +The entries \type {htap} and \type {pen} are optional. + +\subsection{outline} + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{path} \NC table \NC the list of knots \NC \NR +\NC \type{pen} \NC table \NC knots of the pen \NC \NR +\NC \type{color} \NC table \NC the object's color \NC \NR +\NC \type{linejoin} \NC number \NC line join style (bare number) \NC \NR +\NC \type{miterlimit} \NC number \NC miterlimit \NC \NR +\NC \type{linecap} \NC number \NC line cap style (bare number) \NC \NR +\NC \type{dash} \NC table \NC representation of a dash list \NC \NR +\NC \type{prescript} \NC string \NC the prescript text \NC \NR +\NC \type{postscript} \NC string \NC the postscript text \NC \NR +\LL +\stoptabulate + +The entry \type {dash} is optional. + +\subsection{text} + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{text} \NC string \NC the text \NC \NR +\NC \type{font} \NC string \NC font tfm name \NC \NR +\NC \type{dsize} \NC number \NC font size \NC \NR +\NC \type{color} \NC table \NC the object's color \NC \NR +\NC \type{width} \NC number \NC \NC \NR +\NC \type{height} \NC number \NC \NC \NR +\NC \type{depth} \NC number \NC \NC \NR +\NC \type{transform} \NC table \NC a text transformation \NC \NR +\NC \type{prescript} \NC string \NC the prescript text \NC \NR +\NC \type{postscript} \NC string \NC the postscript text \NC \NR +\LL +\stoptabulate + +\subsection{special} + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{prescript} \NC string \NC special text \NC \NR +\LL +\stoptabulate + +\subsection{start_bounds, start_clip} + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{path} \NC table \NC the list of knots \NC \NR +\LL +\stoptabulate + +\subsubsection{stop_bounds, stop_clip} + +Here are no fields available. + +\stopsection + +\startsection[title={Subsidiary table formats}] + +\subsection{Paths and pens} + +Paths and pens (that are really just a special type of paths as far as \MPLIB\ is +concerned) are represented by an array where each entry is a table that +represents a knot. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{left_type} \NC string \NC when present: endpoint, but usually absent \NC \NR +\NC \type{right_type} \NC string \NC like \type {left_type} \NC \NR +\NC \type{x_coord} \NC number \NC X coordinate of this knot \NC \NR +\NC \type{y_coord} \NC number \NC Y coordinate of this knot \NC \NR +\NC \type{left_x} \NC number \NC X coordinate of the precontrol point of this knot \NC \NR +\NC \type{left_y} \NC number \NC Y coordinate of the precontrol point of this knot \NC \NR +\NC \type{right_x} \NC number \NC X coordinate of the postcontrol point of this knot \NC \NR +\NC \type{right_y} \NC number \NC Y coordinate of the postcontrol point of this knot \NC \NR +\LL +\stoptabulate + +There is one special case: pens that are (possibly transformed) ellipses have an +extra string-valued key \type {type} with value \type {elliptical} besides the +array part containing the knot list. + +\subsection{Colors} + +A color is an integer array with 0, 1, 3 or 4 values: + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{0} \NC marking only \NC no values \NC \NR +\NC \type{1} \NC greyscale \NC one value in the range $(0,1)$, \quote {black} is $0$ \NC \NR +\NC \type{3} \NC \RGB \NC three values in the range $(0,1)$, \quote {black} is $0,0,0$ \NC \NR +\NC \type{4} \NC \CMYK \NC four values in the range $(0,1)$, \quote {black} is $0,0,0,1$ \NC \NR +\LL +\stoptabulate + +If the color model of the internal object was \type {uninitialized}, then it was +initialized to the values representing \quote {black} in the colorspace \type +{defaultcolormodel} that was in effect at the time of the \type {shipout}. + +\subsection{Transforms} + +Each transform is a six|-|item array. + +\starttabulate[|l|l|p|] +\DB index \BC type \BC explanation \NC \NR +\TB +\NC \type{1} \NC number \NC represents x \NC \NR +\NC \type{2} \NC number \NC represents y \NC \NR +\NC \type{3} \NC number \NC represents xx \NC \NR +\NC \type{4} \NC number \NC represents yx \NC \NR +\NC \type{5} \NC number \NC represents xy \NC \NR +\NC \type{6} \NC number \NC represents yy \NC \NR +\LL +\stoptabulate + +Note that the translation (index 1 and 2) comes first. This differs from the +ordering in \POSTSCRIPT, where the translation comes last. + +\subsection{Dashes} + +Each \type {dash} is two-item hash, using the same model as \POSTSCRIPT\ for the +representation of the dashlist. \type {dashes} is an array of \quote {on} and +\quote {off}, values, and \type {offset} is the phase of the pattern. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{dashes} \NC hash \NC an array of on-off numbers \NC \NR +\NC \type{offset} \NC number \NC the starting offset value \NC \NR +\LL +\stoptabulate + +\subsection{Pens and \type {pen_info}} + +\libindex{pen_info} + +There is helper function (\type {pen_info(obj)}) that returns a table containing +a bunch of vital characteristics of the used pen (all values are floats): + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{width} \NC number \NC width of the pen \NC \NR +\NC \type{sx} \NC number \NC $x$ scale \NC \NR +\NC \type{rx} \NC number \NC $xy$ multiplier \NC \NR +\NC \type{ry} \NC number \NC $yx$ multiplier \NC \NR +\NC \type{sy} \NC number \NC $y$ scale \NC \NR +\NC \type{tx} \NC number \NC $x$ offset \NC \NR +\NC \type{ty} \NC number \NC $y$ offset \NC \NR +\LL +\stoptabulate + +\stopsection + +\startsection[title=Acessors] + +\subsection[title={Character size information}] + +\libindex{char_width} +\libindex{char_height} +\libindex{char_depth} + +These functions find the size of a glyph in a defined font. The \type {fontname} +is the same name as the argument to \type {infont}; the \type {char} is a glyph +id in the range 0 to 255; the returned \type {w} is in AFM units. + + +\startfunctioncall + w = char_width(mp, fontname, char) + h = char_height(mp, fontname, char) + d = char_depth(mp, fontname, char) +\stopfunctioncall + +These are rather useless and might become obsolete. + +\subsection{\type {get_[boolean|numeric|string|path]}} + +\libindex{get_boolean} +\libindex{get_numeric} +\libindex{get_path} +\libindex{get_string} + +When a script call brings you from the \METAPOST\ run (temporarily) back to +\LUA\ you can access variables, but only if they are known (so for instance +anonymous capsules like loop variables are not accessible). + +\startfunctioncall + w = get_boolean(mp, name) + n = get_numeric(mp, name) + s = get_string (mp, name) +
p = get_path (mp, name) +\stopfunctioncall + +The path is returned a a table with subtables that have six numbers: the +coordinates of the point, pre- and postcontrol. A \type {cycle} fields indicates +if a path is cyclic. + +\stopsection + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/luametatex/luametatex-modifications.tex b/doc/context/sources/general/manuals/luametatex/luametatex-modifications.tex new file mode 100644 index 000000000..dca6c3781 --- /dev/null +++ b/doc/context/sources/general/manuals/luametatex/luametatex-modifications.tex @@ -0,0 +1,440 @@ +% language=uk + +\environment luametatex-style + +\startcomponent luametatex-modifications + +\startchapter[reference=modifications,title={The original engines}] + +\startsection[title=The merged engines] + +\startsubsection[title=The rationale] + +\topicindex {engines} +\topicindex {history} + +The first version of \LUATEX, made by Hartmut after we discussed the possibility +of an extension language, only had a few extra primitives and it was largely the +same as \PDFTEX. It was presented to the public in 2005. As part of the Oriental +\TEX\ project, Taco merged substantial parts of \ALEPH\ into the code and some +more primitives were added. Then we started more fundamental experiments. After +many years, when the engine had become more stable, the decision was made to +clean up the rather hybrid nature of the program. This means that some primitives +were promoted to core primitives, often with a different name, and that others +were removed. This also made it possible to start cleaning up the code base. In +\in {chapter} [enhancements] we discussed some new primitives, here we will cover +most of the adapted ones. + +During more than a decade stepwise new functionality was added and after 10 years +the more of less stable version 1.0 was presented. But we continued and after +some 15 years the \LUAMETATEX\ follow up entered its first testing stage. But +before details about the engine are discussed in successive chapters, we first +summarize where we started from. Keep in mind that in \LUAMETATEX\ we have a bit +less than in \LUATEX, so this section differs from the one in the \LUATEX\ +manual. + +Besides the expected changes caused by new functionality, there are a number of +not|-|so|-|expected changes. These are sometimes a side|-|effect of a new +(conflicting) feature, or, more often than not, a change necessary to clean up +the internal interfaces. These will also be mentioned. + +\stopsubsection + +\startsubsection[title=Changes from \TEX\ 3.1415926] + +\topicindex {\TEX} + +Of course it all starts with traditional \TEX. Even if we started with \PDFTEX, +most still comes from original Knuthian \TEX. But we divert a bit. + +\startitemize + +\startitem + The current code base is written in \CCODE, not \PASCAL. The original \CWEB\ + documentation is kept when possible and not wrapped in tagged comments. As a + consequence instead of one large file plus change files, we now have multiple + files organized in categories like \type {tex}, \type {luaf}, \type + {languages}, \type {fonts}, \type {libraries}, etc. There are some artifacts + of the conversion to \CCODE, but these got (and get) removed stepwise. The + documentation, which is actually comes from the mix of engines (via so called + change files) is kept as much as possible. Of course we want to stay as close + as possible to the original so that the documentation of the fundamentals + behind \TEX\ by Don Knuth still applies. However, because we use \CCODE, some + documentation is a bit off. Also, most global variables are now collected in + structures, but the original names were kept. There are lots of so called + macros too. +\stopitem + +\startitem + See \in {chapter} [languages] for many small changes related to paragraph + building, language handling and hyphenation. The most important change is + that adding a brace group in the middle of a word (like in \type {of{}fice}) + does not prevent ligature creation. Also, the hyphenation, ligature building + and kerning has been split so that we can hook in alternative or extra code + wherever we like. There are various options to control discretionary + injection and related penalties are now integrated in these nodes. Language + information is now bound to glyphs. The number of languages in \LUAMETATEX\ + is smaller than in \LUATEX. +\stopitem + +\startitem + There is no pool file, all strings are embedded during compilation. This also + removed some memory constraints. We kept token and node memory management + because it is convenient and efficient but parts were reimplemented in order + to remove some constraints. Token memory management is largely the same. +\stopitem + +\startitem + The specifier \type {plus 1 fillll} does not generate an error. The extra + \quote {l} is simply typeset. +\stopitem + +\startitem + The upper limit to \prm {endlinechar} and \prm {newlinechar} is 127. +\stopitem + +\startitem + Because the backend is not built|-|in, the magnification (\prm {mag}) + primitive is not doing nothing. A \type {shipout} just discards the content + of the given box. The write related primitives have to be implemented in the + used macro package using \LUA. None of the \PDFTEX\ derived primitives is + present. +\stopitem + +\startitem + There is more control over some (formerly hard|-|coded) math properties. In fact, + there is a whole extra bit of math related code because we need to deal with + \OPENTYPE\ fonts. +\stopitem + +\startitem + The \type {\outer} and \type {\long} prefixed are silently ignored. It is + permitted to use \type {\par} in math. +\stopitem + +\startitem + Because there is no font loader, a \LUA\ variant is free to either support or + not the \OMEGA\ \type {ofm} file format. As there are hardly any such fonts + it probably makes no sense. +\stopitem + +\startitem + The lack of a backend means that some primitives related to it are not + implemented. This is no big deal because it is possible to use the scanner + library to implement them as needed, which depends on the macro package and + backend. +\stopitem + +\startitem + When detailed logging is enabled more detail is output with respect to what + nodes are involved. This is a side effect of the core nodes having more + detailed subtype information. The benefit of more detail wins from any wish + to be byte compatible in the logging. One can always write additional logging + in \LUA. +\stopitem + +\stopitemize + +\stopsubsection + +\startsubsection[title=Changes from \ETEX\ 2.2] + +\topicindex {\ETEX} + +Being the de|-|facto standard extension of course we provide the \ETEX\ +features, but with a few small adaptations. + +\startitemize + +\startitem + The \ETEX\ functionality is always present and enabled so the prepended + asterisk or \type {-etex} switch for \INITEX\ is not needed. +\stopitem + +\startitem + The \TEXXET\ extension is not present, so the primitives \type + {\TeXXeTstate}, \type {\beginR}, \type {\beginL}, \type {\endR} and \type + {\endL} are missing. Instead we used the \OMEGA|/|\ALEPH\ approach to + directionality as starting point, albeit it has been changed quite a bit, + so that we're probably not that far from \TEXXET. +\stopitem + +\startitem + Some of the tracing information that is output by \ETEX's \prm + {tracingassigns} and \prm {tracingrestores} is not there. Also keep in mind + that tracing doesn't involve what \LUA\ does. +\stopitem + +\startitem + Register management in \LUAMETATEX\ uses the \OMEGA|/|\ALEPH\ model, so the + maximum value is 65535 and the implementation uses a flat array instead of + the mixed flat & sparse model from \ETEX. +\stopitem + +\startitem + Because we don't use change files on top of original \TEX, the integration of + \ETEX\ functionality is bit more natural, code wise. +\stopitem + +\stopitemize + +\stopsubsection + +\startsubsection[title=Changes from \PDFTEX\ 1.40] + +\topicindex {\PDFTEX} + +Because we want to produce \PDF\ the most natural starting point was the popular +\PDFTEX\ program. We inherit the stable features, dropped most of the +experimental code and promoted some functionality to core \LUATEX\ functionality +which in turn triggered renaming primitives. However, as the backend was dropped, +not that much from \PDFTEX\ is present any more. Basically all we now inherit +from \PDFTEX\ is expansion and protrusion but even that has been adapted. So +don't expect \LUAMETATEX\ to be compatible. + +\startitemize + +\startitem + The experimental primitives \lpr {ifabsnum} and \lpr {ifabsdim} have been + promoted to core primitives. +\stopitem + +\startitem + The primitives \lpr {ifincsname}, \lpr {expanded} and \lpr {quitvmode} + have become core primitives. +\stopitem + +\startitem + As the hz (expansion) and protrusion mechanism are part of the core the + related primitives \lpr {lpcode}, \lpr {rpcode}, \lpr {efcode}, \lpr + {leftmarginkern}, \lpr {rightmarginkern} are promoted to core primitives. The + two commands \lpr {protrudechars} and \lpr {adjustspacing} control these + processes. +\stopitem + +\startitem + In \LUAMETATEX\ three extra primitives can be used to overload the font + specific settings: \lpr {adjustspacingstep} (max: 100), \lpr + {adjustspacingstretch} (max: 1000) and \lpr {adjustspacingshrink} (max: 500). +\stopitem + +\startitem + The hz optimization code has been partially redone so that we no longer need + to create extra font instances. The front- and backend have been decoupled + and the glyph and kern nodes carry the used values. In \LUATEX\ that made a + more efficient generation of \PDF\ code possible. It also resulted in much + cleaner code. The backend code is gone, but of course the information is + still carried around. +\stopitem + +\startitem + When \lpr {adjustspacing} has value~2, hz optimization will be applied to + glyphs and kerns. When the value is~3, only glyphs will be treated. A value + smaller than~2 disables this feature. With value of~1, font expansion is + applied after \TEX's normal paragraph breaking routines have broken the + paragraph into lines. In this case, line breaks are identical to standard + \TEX\ behavior (as with \PDFTEX). But \unknown\ this is a left|-|over from + the early days of \PDFTEX\ when this feature was part of a research topic. At + some point level~1 might be dropped from \LUAMETATEX. +\stopitem + +\startitem + When \lpr {protrudechars} has a value larger than zero characters at the edge + of a line can be made to hang out. A value of~2 will take the protrusion into + account when breaking a paragraph into lines. A value of~3 will try to deal + with right|-|to|-|left rendering; this is a still experimental feature. +\stopitem + +\startitem + The pixel multiplier dimension \lpr {pxdimen} has be inherited as core + primitive. +\stopitem + +\startitem + The primitive \lpr {tracingfonts} is now a core primitive but doesn't relate + to the backend. +\stopitem + +\stopitemize + +\stopsubsection + +\startsubsection[title=Changes from \ALEPH\ RC4] + +\topicindex {\ALEPH} + +In \LUATEX\ we took the 32 bit aspects and much of the directional mechanisms and +merged it into the \PDFTEX\ code base as starting point for further development. +Then we simplified directionality, fixed it and opened it up. In \LUAMETATEX\ not +that much of the later is left. We only have two horizontal directions. Instead +of vertical directions we introduce an orientation model bound to boxes. + +The already reduced|-|to|-|four set of directions now only has two members: +left|-|to|-|right and right|-|to|-|left. They don't do much as it is the backend +that has to deal with them. When paragraphs are constructed a change in +horizontal direction is irrelevant for calculating the dimensions. So, basically +most that we do is registering state and passing that on till the backend can do +something with it. + +Here is a summary of inherited functionality: + +\startitemize + +\startitem + The \type {^^} notation has been extended: after \type {^^^^} four + hexadecimal characters are expected and after \type {^^^^^^} six hexadecimal + characters have to be given. The original \TEX\ interpretation is still valid + for the \type {^^} case but the four and six variants do no backtracking, + i.e.\ when they are not followed by the right number of hexadecimal digits + they issue an error message. Because \type {^^^} is a normal \TEX\ case, we + don't support the odd number of \type {^^^^^} either. +\stopitem + +\startitem + Glues {\it immediately after} direction change commands are not legal + breakpoints. There is a bit more sanity testing for the direction state. +\stopitem + +\startitem + The placement of math formula numbers is direction aware and adapts + accordingly. Boxes carry directional information but rules don't. +\stopitem + +\startitem + There are no direction related primitives for page and body directions. The + paragraph, text and math directions are specified using primitives that + take a number. +\stopitem + +\stopitemize + +\stopsubsection + +\startsubsection[title=Changes from standard \WEBC] + +\topicindex {\WEBC} + +The \LUAMETATEX\ codebase is not dependent on the \WEBC\ framework. The +interaction with the file system and \TDS\ is up to \LUA. There still might be +traces but eventually the code base should be lean and mean. The \METAPOST\ +library is coded in \CWEB\ and in order to be independent from related tools, +conversion to \CCODE\ is done with a \LUA\ script ran by, surprise, \LUAMETATEX. + +\stopsubsection + +\stopsection + +\startsection[title=Implementation notes] + +\startsubsection[title=Memory allocation] + +\topicindex {memory} + +The single internal memory heap that traditional \TEX\ used for tokens and nodes +is split into two separate arrays. Each of these will grow dynamically when +needed. Internally a token or node is an index into these arrays. This permits +for an efficient implementation and is also responsible for the performance of +the core. The original documentation in \TEX\ The Program mostly applies! + +\stopsubsection + +\startsubsection[title=Sparse arrays] + +The \prm {mathcode}, \prm {delcode}, \prm {catcode}, \prm {sfcode}, \prm {lccode} +and \prm {uccode} (and the new \lpr {hjcode}) tables are now sparse arrays that +are implemented in~\CCODE. They are no longer part of the \TEX\ \quote +{equivalence table} and because each had 1.1 million entries with a few memory +words each, this makes a major difference in memory usage. Performance is not +really hurt by this. + +The \prm {catcode}, \prm {sfcode}, \prm {lccode}, \prm {uccode} and \lpr {hjcode} +assignments don't show up when using the \ETEX\ tracing routines \prm +{tracingassigns} and \prm {tracingrestores} but we don't see that as a real +limitation. It also saves a lot of clutter. + +A side|-|effect of the current implementation is that \prm {global} is now more +expensive in terms of processing than non|-|global assignments but not many users +will notice that. + +The glyph ids within a font are also managed by means of a sparse array as glyph +ids can go up to index $2^{21}-1$ but these are never accessed directly so again +users will not notice this. + +\stopsubsection + +\startsubsection[title=Simple single|-|character csnames] + +\topicindex {csnames} + +Single|-|character commands are no longer treated specially in the internals, +they are stored in the hash just like the multiletter csnames. + +The code that displays control sequences explicitly checks if the length is one +when it has to decide whether or not to add a trailing space. + +Active characters are internally implemented as a special type of multi|-|letter +control sequences that uses a prefix that is otherwise impossible to obtain. + +\stopsubsection + +\startsubsection[title=Binary file reading] + +\topicindex {files+binary} + +All of the internal code is changed in such a way that if one of the \type +{read_xxx_file} callbacks is not set, then the file is read by a \CCODE\ function +using basically the same convention as the callback: a single read into a buffer +big enough to hold the entire file contents. While this uses more memory than the +previous code (that mostly used \type {getc} calls), it can be quite a bit faster +(depending on your \IO\ subsystem). So far we never had issues with this approach. + +\stopsubsection + +\startsubsection[title=Tabs and spaces] + +\topicindex {space} +\topicindex {newline} + +We conform to the way other \TEX\ engines handle trailing tabs and spaces. For +decades trailing tabs and spaces (before a newline) were removed from the input +but this behaviour was changed in September 2017 to only handle spaces. We are +aware that this can introduce compatibility issues in existing workflows but +because we don't want too many differences with upstream \TEXLIVE\ we just follow +up on that patch (which is a functional one and not really a fix). It is up to +macro packages maintainers to deal with possible compatibility issues and in +\LUAMETATEX\ they can do so via the callbacks that deal with reading from files. + +The previous behaviour was a known side effect and (as that kind of input +normally comes from generated sources) it was normally dealt with by adding a +comment token to the line in case the spaces and|/|or tabs were intentional and +to be kept. We are aware of the fact that this contradicts some of our other +choices but consistency with other engines. We still stick to our view that at +the log level we can (and might be) more incompatible. We already expose some +more details anyway. + +\stopsubsection + +\startsubsection[title=Logging] + +The information that goes into the log file can be different from \LUATEX, and +might even differ a bit more in the future. The main reason is that inside the +engine we have more granularity, which for instance means that we output subtype +related information when nodes are printed. Of course we could have offered a +compatibility mode but it serves no purpose. Over time there have been many +subtle changes to control logs in the \TEX\ ecosystems so another one is +bearable. + +In a similar fashion, there is a bit different behaviour when \TEX\ expects +input, which in turn is a side effect of removing the interception of \type {*} +and \type {&} which made for cleaner code (quite a bit had accumulated as side +effect of continuous adaptations in the \TEX\ ecosystems). There was already code +that was never executed, simply as side effect of the way \LUATEX\ initializes +itself (one needs to enable classes of primitives for instance). + +\stopsubsection + +\stopsection + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/luametatex/luametatex-nodes.tex b/doc/context/sources/general/manuals/luametatex/luametatex-nodes.tex new file mode 100644 index 000000000..1d408ba6c --- /dev/null +++ b/doc/context/sources/general/manuals/luametatex/luametatex-nodes.tex @@ -0,0 +1,2527 @@ +% language=uk + +\environment luametatex-style + +\startcomponent luametatex-nodes + +\startchapter[reference=nodes,title={Nodes}] + +\startsection[title={\LUA\ node representation}][library=node] + +\topicindex {nodes} + +\libindex {fields} +\libindex {subtypes} +\libindex {values} + +\TEX's nodes are represented in \LUA\ as userdata objects with a variable set of +fields or by a numeric identifier when requested. When you print a node userdata +object you will see these numbers. In the following syntax tables, such as the +type of such a userdata object is represented as \syntax {}. + +\blank +\dontleavehmode {\bf The return values of \type {node.types()} are:} \showtypes +\blank + +In \ETEX\ the \prm {lastnodetype} primitive has been introduced. With this +primitive the valid range of numbers is still $[-1,15]$ and glyph nodes (formerly +known as char nodes) have number~0. That way macro packages can use the same +symbolic names as in traditional \ETEX. But you need to keep in mind that these +\ETEX\ node numbers are different from the real internal ones. When you set \prm +{internalcodesmode} to a non|-|zero value, the internal codes will be used in +the \ETEX\ introspection commands \prm {lastnodetype} and \prm {currentiftype}. + +You can ask for a list of fields with \type {node.fields} and for valid subtypes +with \type {node.subtypes}. The \type {node.values} function reports some used +values. Valid arguments are \type {glue}, \type {style} and \type {math}. Keep in +mind that the setters normally expect a number, but this helper gives you a list +of what numbers matter. For practical reason the \type {pagestate} values are +also reported with this helper, but they are backend specific. + +\def\ShowValues#1{ + \blank + \dontleavehmode + {\bf The return values of \type {node.values("#1"} are:} + \showvalues{#1} + \blank +} + +\ShowValues{glue} \ShowValues{style} \ShowValues{math} \ShowValues{pagestate} + +\stopsection + +\startsection[title={Main text nodes}] + +\topicindex {nodes+text} + +These are the nodes that comprise actual typesetting commands. A few fields are +present in all nodes regardless of their type, these are: + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{next} \NC node \NC the next node in a list, or nil \NC \NR +\NC \type{id} \NC number \NC the node's type (\type {id}) number \NC \NR +\NC \type{subtype} \NC number \NC the node \type {subtype} identifier \NC \NR +\LL +\stoptabulate + +The \type {subtype} is sometimes just a dummy entry because not all nodes +actually use the \type {subtype}, but this way you can be sure that all nodes +accept it as a valid field name, and that is often handy in node list traversal. +In the following tables \type {next} and \type {id} are not explicitly mentioned. + +Besides these three fields, almost all nodes also have an \type {attr} field, and +there is a also a field called \type {prev}. That last field is always present, +but only initialized on explicit request: when the function \type {node.slide} +is called, it will set up the \type {prev} fields to be a backwards pointer in +the argument node list. By now most of \TEX's node processing makes sure that the +\type {prev} nodes are valid but there can be exceptions, especially when the +internal magic uses a leading \nod {temp} nodes to temporarily store a state. + +The \LUAMETATEX\ engine provides a lot of freedom and it is up to the user to +make sure that the node lists remain sane. There are some safeguards but there +can be cases where the engine just quits out of frustration. And, of course you +can make the engine crash. + +\startsubsection[title={\nod {hlist} and \nod {vlist} nodes}] + +\topicindex {nodes+lists} +\topicindex {lists} + +These lists share fields and subtypes although some subtypes can only occur in +horizontal lists while others are unique for vertical lists. The possible +fields are \showfields {hlist}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC \showsubtypes{list} \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{width} \NC number \NC the width of the box \NC \NR +\NC \type{height} \NC number \NC the height of the box \NC \NR +\NC \type{depth} \NC number \NC the depth of the box \NC \NR +\NC \type{direction} \NC number \NC the direction of this box, see~\in [dirnodes] \NC \NR +\NC \type{shift} \NC number \NC a displacement perpendicular to the character + (hlist) or line (vlist) progression direction \NC \NR +\NC \type{glue_order} \NC number \NC a number in the range $[0,4]$, indicating the + glue order \NC \NR +\NC \type{glue_set} \NC number \NC the calculated glue ratio \NC \NR +\NC \type{glue_sign} \NC number \NC 0 = \type {normal}, 1 = \type {stretching}, 2 = + \type {shrinking} \NC \NR +\NC \type{list} \NC node \NC the first node of the body of this list \NC \NR +\LL +\stoptabulate + +The \type {orientation}, \type {woffset}, \type {hoffset}, \type {doffset}, +\type {xoffset} and \type {yoffset} fields are special. They can be used to make +the backend rotate and shift boxes which can be handy in for instance vertical +typesetting. Because they relate to (and depend on the) the backend they are not +discussed here (yet). + +A warning: never assign a node list to the \type {list} field unless you are sure +its internal link structure is correct, otherwise an error may result. + +Note: the field name \type {head} and \type {list} are both valid. Sometimes it +makes more sense to refer to a list by \type {head}, sometimes \type {list} makes +more sense. + +\stopsubsection + +\startsubsection[title={\nod {rule} nodes}] + +\topicindex {nodes+rules} +\topicindex {rules} + +Contrary to traditional \TEX, \LUATEX\ has more \prm {rule} subtypes because we +also use rules to store reuseable objects and images. User nodes are invisible +and can be intercepted by a callback. The supported fields are \showfields {rule}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC \showsubtypes {rule} \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{width} \NC number \NC the width of the rule where the special value + $-1073741824$ is used for \quote {running} glue dimensions \NC \NR +\NC \type{height} \NC number \NC the height of the rule (can be negative) \NC \NR +\NC \type{depth} \NC number \NC the depth of the rule (can be negative) \NC \NR +\NC \type{left} \NC number \NC shift at the left end (also subtracted from width) \NC \NR +\NC \type{right} \NC number \NC (subtracted from width) \NC \NR +\NC \type{dir} \NC string \NC the direction of this rule, see~\in[dirnodes] \NC \NR +\NC \type{index} \NC number \NC an optional index that can be referred to \NC \NR +\NC \type{transform} \NC number \NC an private variable (also used to specify outline width) \NC \NR +\LL +\stoptabulate + +The \type {left} and type {right} keys are somewhat special (and experimental). +When rules are auto adapting to the surrounding box width you can enforce a shift +to the right by setting \type {left}. The value is also subtracted from the width +which can be a value set by the engine itself and is not entirely under user +control. The \type {right} is also subtracted from the width. It all happens in +the backend so these are not affecting the calculations in the frontend (actually +the auto settings also happen in the backend). For a vertical rule \type {left} +affects the height and \type {right} affects the depth. There is no matching +interface at the \TEX\ end (although we can have more keywords for rules it would +complicate matters and introduce a speed penalty.) However, you can just +construct a rule node with \LUA\ and write it to the \TEX\ input. The \type +{outline} subtype is just a convenient variant and the \type {transform} field +specifies the width of the outline. + +The \type {xoffset} and \type {yoffset} fields are special. They can be used to +shift rules. Because they relate to (and depend on the) the backend they are not +discussed here (yet). + +\stopsubsection + +\startsubsection[title={\nod {ins} nodes}] + +\topicindex {nodes+insertions} +\topicindex {insertions} + +This node relates to the \prm {insert} primitive and support the fields: \showfields{ins}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC the insertion class \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{cost} \NC number \NC the penalty associated with this insert \NC \NR +\NC \type{height} \NC number \NC height of the insert \NC \NR +\NC \type{depth} \NC number \NC depth of the insert \NC \NR +\NC \type{list} \NC node \NC the first node of the body of this insert \NC \NR +\LL +\stoptabulate + +There is a set of extra fields that concern the associated glue: \type {width}, +\type {stretch}, \type {stretch_order}, \type {shrink} and \type {shrink_order}. +These are all numbers. + +A warning: never assign a node list to the \type {head} field unless you are sure +its internal link structure is correct, otherwise an error may result. You can use +\type {list} instead (often in functions you want to use local variable with similar +names and both names are equally sensible). + +\stopsubsection + +\startsubsection[title={\nod {mark} nodes}] + +\topicindex {nodes+marks} +\topicindex {marks} + +This one relates to the \prm {mark} primitive and only has a few fields: +\showfields {mark}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC unused \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{class} \NC number \NC the mark class \NC \NR +\NC \type{mark} \NC table \NC a table representing a token list \NC \NR +\LL +\stoptabulate + +\stopsubsection + +\startsubsection[title={\nod {adjust} nodes}] + +\topicindex {nodes+adjust} +\topicindex {adjust} + +This node comes from \prm {vadjust} primitive and has fields: \showfields {adjust}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC \showsubtypes{adjust} \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{list} \NC node \NC adjusted material \NC \NR +\LL +\stoptabulate + +A warning: never assign a node list to the \type {head} field unless you are sure +its internal link structure is correct, otherwise an error may be the result. + +\stopsubsection + +\startsubsection[title={\nod {disc} nodes}] + +\topicindex {nodes+discretionaries} +\topicindex {discretionaries} + +The \prm {discretionary} and \prm {-}, the \type {-} character but also the +hyphenation mechanism produces these nodes. The available fields are: \showfields +{disc}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC \showsubtypes{disc} \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{pre} \NC node \NC pointer to the pre|-|break text \NC \NR +\NC \type{post} \NC node \NC pointer to the post|-|break text \NC \NR +\NC \type{replace} \NC node \NC pointer to the no|-|break text \NC \NR +\NC \type{penalty} \NC number \NC the penalty associated with the break, normally + \prm {hyphenpenalty} or \prm {exhyphenpenalty} \NC \NR +\LL +\stoptabulate + +The subtype numbers~4 and~5 belong to the \quote {of-f-ice} explanation given +elsewhere. These disc nodes are kind of special as at some point they also keep +information about breakpoints and nested ligatures. + +The \type {pre}, \type {post} and \type {replace} fields at the \LUA\ end are in +fact indirectly accessed and have a \type {prev} pointer that is not \type {nil}. +This means that when you mess around with the head of these (three) lists, you +also need to reassign them because that will restore the proper \type {prev} +pointer, so: + +\starttyping +pre = d.pre +-- change the list starting with pre +d.pre = pre +\stoptyping + +Otherwise you can end up with an invalid internal perception of reality and +\LUAMETATEX\ might even decide to crash on you. It also means that running forward +over for instance \type {pre} is ok but backward you need to stop at \type {pre}. +And you definitely must not mess with the node that \type {prev} points to, if +only because it is not really a node but part of the disc data structure (so +freeing it again might crash \LUAMETATEX). + +\stopsubsection + +\startsubsection[title={\nod {math} nodes}] + +\topicindex {nodes+math} +\topicindex {math+nodes} + +Math nodes represent the boundaries of a math formula, normally wrapped into +\type {$} signs. The following fields are available: \showfields {math}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC \showsubtypes{math} \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{surround} \NC number \NC width of the \prm {mathsurround} kern \NC \NR +\NC \type{width} \NC number \NC the horizontal or vertical displacement \NC \NR +\NC \type{stretch} \NC number \NC extra (positive) displacement or stretch amount \NC \NR +\NC \type{stretch_order} \NC number \NC factor applied to stretch amount \NC \NR +\NC \type{shrink} \NC number \NC extra (negative) displacement or shrink amount\NC \NR +\NC \type{shrink_order} \NC number \NC factor applied to shrink amount \NC \NR +\LL +\stoptabulate + +The glue fields only kick in when the \type {surround} fields is zero. + +\stopsubsection + +\startsubsection[title={\nod {glue} nodes}] + +\topicindex {nodes+glue} +\topicindex {glue} + +Skips are about the only type of data objects in traditional \TEX\ that are not a +simple value. They are inserted when \TEX\ sees a space in the text flow but also +by \prm {hskip} and \prm {vskip}. The structure that represents the glue +components of a skip internally is called a \nod {glue_spec}. In \LUAMETATEX\ we +don't use the spec itself but just its values. A glue node has the fields: +\showfields {glue}. + +\starttabulate[|l|l|pA{flushleft,tolerant}|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC \showsubtypes{glue} \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{leader} \NC node \NC pointer to a box or rule for leaders \NC \NR +\NC \type{width} \NC number \NC the horizontal or vertical displacement \NC \NR +\NC \type{stretch} \NC number \NC extra (positive) displacement or stretch amount \NC \NR +\NC \type{stretch_order} \NC number \NC factor applied to stretch amount \NC \NR +\NC \type{shrink} \NC number \NC extra (negative) displacement or shrink amount\NC \NR +\NC \type{shrink_order} \NC number \NC factor applied to shrink amount \NC \NR +\LL +\stoptabulate + +Note that we use the key \type {width} in both horizontal and vertical glue. This +suits the \TEX\ internals well so we decided to stick to that naming. + +The effective width of some glue subtypes depends on the stretch or shrink needed +to make the encapsulating box fit its dimensions. For instance, in a paragraph +lines normally have glue representing spaces and these stretch or shrink to make +the content fit in the available space. The \type {effective_glue} function that +takes a glue node and a parent (hlist or vlist) returns the effective width of +that glue item. When you pass \type {true} as third argument the value will be +rounded. + +\stopsubsection + +\startsubsection[title={\nod {glue_spec} nodes}] + +\topicindex {nodes+glue} +\topicindex {gluespec} + +Internally \LUAMETATEX\ (like its ancestors) also uses nodes to store data that +is not seen in node lists. For instance the state of expression scanning (\type +{\dimexpr} etc.) and conditionals (\type {\ifcase} etc.) is also kept in lists of +nodes. A glue, which has five components, is stored in a node as well, so, where +most registers store just a number, a skip register (of internal quantity) uses a +pointer to a glue spec node. It has similar fields as glue nodes: \showfields +{glue_spec}, which is not surprising because in the past (and other engines than +\LUATEX) a glue node also has its values stored in a glue spec. This has some +advantages because often the values are the same, so for instance spacing related +skips were not resolved immediately but pointed to the current value of a space +related internal register (like \type {\spaceskip}). But, in \LUATEX\ we do +resolve these quantities immediately and we put the current values in the glue +nodes. + +\starttabulate[|l|l|pA{flushleft,tolerant}|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{width} \NC number \NC the horizontal or vertical displacement \NC \NR +\NC \type{stretch} \NC number \NC extra (positive) displacement or stretch amount \NC \NR +\NC \type{stretch_order} \NC number \NC factor applied to stretch amount \NC \NR +\NC \type{shrink} \NC number \NC extra (negative) displacement or shrink amount\NC \NR +\NC \type{shrink_order} \NC number \NC factor applied to shrink amount \NC \NR +\LL +\stoptabulate + +You will only find these nodes in a few places, for instance when you query an +internal quantity. In principle we could do without them as we have interfaces +that use the five numbers instead. For compatibility reasons we keep glue spec +nodes exposed but this might change in the future. + +\stopsubsection + +\startsubsection[title={\nod {kern} nodes}] + +\topicindex {nodes+kerns} +\topicindex {kerns} + +The \prm {kern} command creates such nodes but for instance the font and math +machinery can also add them. There are not that many fields: \showfields {kern}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC \showsubtypes{kern} \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{kern} \NC number \NC fixed horizontal or vertical advance \NC \NR +\NC \type{expansion_factor} \NC number \NC multiplier related to hz for font kerns \NC \NR +\LL +\stoptabulate + +\stopsubsection + +\startsubsection[title={\nod {penalty} nodes}] + +\topicindex {nodes+penalty} +\topicindex {penalty} + +The \prm {penalty} command is one that generates these nodes. It is one of the +type of nodes often found in vertical lists. It has the fields: \showfields +{penalty}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC \showsubtypes{penalty} \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{penalty} \NC number \NC the penalty value \NC \NR +\LL +\stoptabulate + +The subtypes are just informative and \TEX\ itself doesn't use them. When you +run into an \type {linebreakpenalty} you need to keep in mind that it's a +accumulation of \type {club}, \type{widow} and other relevant penalties. + +\stopsubsection + +\startsubsection[title={\nod {glyph} nodes},reference=glyphnodes] + +\topicindex {nodes+glyph} +\topicindex {glyphs} + +These are probably the mostly used nodes and although you can push them in the +current list with for instance \prm {char} \TEX\ will normally do it for you when +it considers some input to be text. Glyph nodes are relatively large and have many +fields: \showfields {glyph}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC bit field \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{char} \NC number \NC the character index in the font \NC \NR +\NC \type{font} \NC number \NC the font identifier \NC \NR +\NC \type{lang} \NC number \NC the language identifier \NC \NR +\NC \type{left} \NC number \NC the frozen \type {\lefthyphenmnin} value \NC \NR +\NC \type{right} \NC number \NC the frozen \type {\righthyphenmnin} value \NC \NR +\NC \type{uchyph} \NC boolean \NC the frozen \prm {uchyph} value \NC \NR +\NC \type{components} \NC node \NC pointer to ligature components \NC \NR +\NC \type{xoffset} \NC number \NC a virtual displacement in horizontal direction \NC \NR +\NC \type{yoffset} \NC number \NC a virtual displacement in vertical direction \NC \NR +\NC \type{width} \NC number \NC the (original) width of the character \NC \NR +\NC \type{height} \NC number \NC the (original) height of the character\NC \NR +\NC \type{depth} \NC number \NC the (original) depth of the character\NC \NR +\NC \type{expansion_factor} \NC number \NC the to be applied expansion_factor \NC \NR +\NC \type{data} \NC number \NC a general purpose field for users (we had room for it) \NC \NR +\LL +\stoptabulate + +The \type {width}, \type {height} and \type {depth} values are read|-|only. The +\type {expansion_factor} is assigned in the par builder and used in the backend. + +A warning: never assign a node list to the components field unless you are sure +its internal link structure is correct, otherwise an error may be result. Valid +bits for the \type {subtype} field are: + +\starttabulate[|c|l|] +\DB bit \BC meaning \NC \NR +\TB +\NC 0 \NC character \NC \NR +\NC 1 \NC ligature \NC \NR +\NC 2 \NC ghost \NC \NR +\NC 3 \NC left \NC \NR +\NC 4 \NC right \NC \NR +\LL +\stoptabulate + +The \type {expansion_factor} has been introduced as part of the separation +between font- and backend. It is the result of extensive experiments with a more +efficient implementation of expansion. Early versions of \LUATEX\ already +replaced multiple instances of fonts in the backend by scaling but contrary to +\PDFTEX\ in \LUATEX\ we now also got rid of font copies in the frontend and +replaced them by expansion factors that travel with glyph nodes. Apart from a +cleaner approach this is also a step towards a better separation between front- +and backend. + +The \type {is_char} function checks if a node is a glyph node with a subtype still +less than 256. This function can be used to determine if applying font logic to a +glyph node makes sense. The value \type {nil} gets returned when the node is not +a glyph, a character number is returned if the node is still tagged as character +and \type {false} gets returned otherwise. When nil is returned, the id is also +returned. The \type {is_glyph} variant doesn't check for a subtype being less +than 256, so it returns either the character value or nil plus the id. These +helpers are not always faster than separate calls but they sometimes permit +making more readable tests. The \type {uses_font} helpers takes a node +and font id and returns true when a glyph or disc node references that font. + +\stopsubsection + +\startsubsection[title={\nod {boundary} nodes}] + +\topicindex {nodes+boundary} +\topicindex {boundary} + +This node relates to the \prm {noboundary}, \prm {boundary}, \prm +{protrusionboundary} and \prm {wordboundary} primitives. These are small +nodes: \showfields {boundary} are the only fields. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC \showsubtypes{boundary} \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{value} \NC number \NC values 0--255 are reserved \NC \NR +\LL +\stoptabulate + +\stopsubsection + +\startsubsection[title={\nod {local_par} nodes}] + +\topicindex {nodes+paragraphs} +\topicindex {paragraphs} + +This node is inserted at the start of a paragraph. You should not mess +too much with this one. Valid fields are: \showfields {local_par}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{pen_inter} \NC number \NC local interline penalty (from \lpr {localinterlinepenalty}) \NC \NR +\NC \type{pen_broken} \NC number \NC local broken penalty (from \lpr {localbrokenpenalty}) \NC \NR +\NC \type{dir} \NC string \NC the direction of this par. see~\in [dirnodes] \NC \NR +\NC \type{box_left} \NC node \NC the \lpr {localleftbox} \NC \NR +\NC \type{box_left_width} \NC number \NC width of the \lpr {localleftbox} \NC \NR +\NC \type{box_right} \NC node \NC the \lpr {localrightbox} \NC \NR +\NC \type{box_right_width} \NC number \NC width of the \lpr {localrightbox} \NC \NR +\LL +\stoptabulate + +A warning: never assign a node list to the \type {box_left} or \type {box_right} +field unless you are sure its internal link structure is correct, otherwise an +error may result. + +\stopsubsection + +\startsubsection[title={\nod {dir} nodes},reference=dirnodes] + +\topicindex {nodes+direction} +\topicindex {directions} + +Direction nodes mark parts of the running text that need a change of direction +and the \prm {textdir} command generates them. Again this is a small node, we +just have \showfields {dir}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC \showsubtypes{dir} \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{dir} \NC string \NC the direction (\type {0} = l2r, \type {1} = r2l) \NC \NR +\NC \type{level} \NC number \NC nesting level of this direction \NC \NR +\LL +\stoptabulate + +There are only two directions: left|-|to|-|right (\type {0}) and +right|-|to|-|left (\type {1}). This is different from \LUATEX\ that has four +directions. + +\stopsubsection + +\startsubsection[title={\nod {marginkern} nodes}] + +\topicindex {nodes+paragraphs} +\topicindex {paragraphs} +\topicindex {protrusion} + +Margin kerns result from protrusion and have: \showfields {margin_kern}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC \showsubtypes{marginkern} \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{width} \NC number \NC the advance of the kern \NC \NR +\NC \type{glyph} \NC node \NC the glyph to be used \NC \NR +\LL +\stoptabulate + +\stopsubsection + +\startsubsection[title={Whatsits}] + +A whatsit node is a real simple one and it only has a subtype. It is even less +than a user node (which it actually could be) and uses hardly any memory. What +you do with it it entirely up to you: it's is real minimalistic. You can assign a +subtype and it has attributes. It is all up to the user how they are handled. + +\stopsubsection + +\startsubsection[title={Math noads}] + +\topicindex {nodes+math} +\topicindex {math+nodes} + +\startsubsubsection[title=The concept] + +These are the so||called \quote {noad}s and the nodes that are specifically +associated with math processing. When you enter a formula, \TEX\ creates a node +list with regular nodes and noads. Then it hands over the list the math +processing engine. The result of that is a nodelist without noads. Most of the +noads contain subnodes so that the list of possible fields is actually quite +small. Math formulas are both a linked list and a tree. For instance in $e = +mc^2$ there is a linked list \type {e = m c} but the \type {c} has a superscript +branch that itself can be a list with branches. + +First, there are the objects (the \TEX book calls them \quote {atoms}) that are +associated with the simple math objects: ord, op, bin, rel, open, close, punct, +inner, over, under, vcenter. These all have the same fields, and they are combined +into a single node type with separate subtypes for differentiation: \showfields +{noad}. + +Many object fields in math mode are either simple characters in a specific family +or math lists or node lists: \type {math_char}, \type {math_text_char}, {sub_box} +and \type {sub_mlist} and \type {delim}. These are endpoints and therefore the +\type {next} and \type {prev} fields of these these subnodes are unused. + +Some of the more elaborate noads have an option field. The values in this bitset +are common: + +\starttabulate[|l|r|] +\DB meaning \BC bits \NC \NR +\TB +\NC set \NC \type{0x08} \NC \NR +\NC internal \NC \type{0x00} + \type{0x08} \NC \NR +\NC internal \NC \type{0x01} + \type{0x08} \NC \NR +\NC axis \NC \type{0x02} + \type{0x08} \NC \NR +\NC no axis \NC \type{0x04} + \type{0x08} \NC \NR +\NC exact \NC \type{0x10} + \type{0x08} \NC \NR +\NC left \NC \type{0x11} + \type{0x08} \NC \NR +\NC middle \NC \type{0x12} + \type{0x08} \NC \NR +\NC right \NC \type{0x14} + \type{0x08} \NC \NR +\NC no subscript \NC \type{0x21} + \type{0x08} \NC \NR +\NC no superscript \NC \type{0x22} + \type{0x08} \NC \NR +\NC no script \NC \type{0x23} + \type{0x08} \NC \NR +\LL +\stoptabulate + +\stopsubsubsection + +\startsubsubsection[title={\nod {math_char} and \nod {math_text_char} subnodes}] + +These are the most common ones, as they represent characters, and they both have +the same fields: \showfields {math_char}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{char} \NC number \NC the character index \NC \NR +\NC \type{fam} \NC number \NC the family number \NC \NR +\LL +\stoptabulate + +The \nod {math_char} is the simplest subnode field, it contains the character and +family for a single glyph object. The family eventually resolves on a reference +to a font. The \nod {math_text_char} is a special case that you will not normally +encounter, it arises temporarily during math list conversion (its sole function +is to suppress a following italic correction). + +\stopsubsubsection + +\startsubsubsection[title={\nod {sub_box} and \nod {sub_mlist} subnodes}] + +These two subnode types are used for subsidiary list items. For \nod {sub_box}, +the \type {list} points to a \quote {normal} vbox or hbox. For \nod {sub_mlist}, +the \type {list} points to a math list that is yet to be converted. Their fields +are: \showfields {sub_box}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{list} \NC node \NC list of nodes \NC \NR +\LL +\stoptabulate + +A warning: never assign a node list to the \type {list} field unless you are sure +its internal link structure is correct, otherwise an error is triggered. + +\stopsubsubsection + +\startsubsubsection[title={\nod {delim} subnodes}] + +There is a fifth subnode type that is used exclusively for delimiter fields. As +before, the \type {next} and \type {prev} fields are unused, but we do have: +\showfields {delim}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{small_char} \NC number \NC character index of base character \NC \NR +\NC \type{small_fam} \NC number \NC family number of base character \NC \NR +\NC \type{large_char} \NC number \NC character index of next larger character \NC \NR +\NC \type{large_fam} \NC number \NC family number of next larger character \NC \NR +\LL +\stoptabulate + +The fields \type {large_char} and \type {large_fam} can be zero, in that case the +font that is set for the \type {small_fam} is expected to provide the large +version as an extension to the \type {small_char}. + +\stopsubsubsection + +\startsubsubsection[title={simple \nod {noad} nodes}] + +In these noads, the \type {nucleus}, \type {sub} and \type {sup} fields can +branch of. Its fields are: \showfields {noad}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC \showsubtypes{noad} \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{nucleus} \NC kernel node \NC base \NC \NR +\NC \type{sub} \NC kernel node \NC subscript \NC \NR +\NC \type{sup} \NC kernel node \NC superscript \NC \NR +\NC \type{options} \NC number \NC bitset of rendering options \NC \NR +\LL +\stoptabulate + +\stopsubsubsection + +\startsubsubsection[title={\nod {accent} nodes}] + +Accent nodes deal with stuff on top or below a math constructs. They support: +\showfields {accent}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC \showsubtypes{accent} \NC \NR +\NC \type{nucleus} \NC kernel node \NC base \NC \NR +\NC \type{sub} \NC kernel node \NC subscript \NC \NR +\NC \type{sup} \NC kernel node \NC superscript \NC \NR +\NC \type{accent} \NC kernel node \NC top accent \NC \NR +\NC \type{bot_accent} \NC kernel node \NC bottom accent \NC \NR +\NC \type{fraction} \NC number \NC larger step criterium (divided by 1000) \NC \NR +\LL +\stoptabulate + +\stopsubsubsection + +\startsubsubsection[title={\nod {style} nodes}] + +These nodes are signals to switch to another math style. They are quite simple: +\showfields {style}. Currently the subtype is actually used to store the style +but don't rely on that for the future. Fields are: \showfields {style}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{style} \NC string \NC contains the style \NC \NR +\LL +\stoptabulate + +Valid styles are: \showvalues{style}. + +\stopsubsubsection + +\startsubsubsection[title={\nod {parameter} nodes}] + +These nodes are used to (locally) set math parameters: \showfields {parameter}. +Fields are: \showfields {parameter}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{style} \NC string \NC contains the style \NC \NR +\NC \type{name} \NC string \NC defines the parameter \NC \NR +\NC \type{value} \NC number \NC holds the value, in case of a muglue multiple \NC \NR +\LL +\stoptabulate + +\stopsubsubsection + +\startsubsubsection[title={\nod {choice} nodes}] + +Of its fields \showfields {choice} most are lists. Warning: never assign a node +list unless you are sure its internal link structure is correct, otherwise an +error can occur. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{display} \NC node \NC list of display size alternatives \NC \NR +\NC \type{text} \NC node \NC list of text size alternatives \NC \NR +\NC \type{script} \NC node \NC list of scriptsize alternatives \NC \NR +\NC \type{scriptscript} \NC node \NC list of scriptscriptsize alternatives \NC \NR +\LL +\stoptabulate + +\stopsubsubsection + +\startsubsubsection[title={\nod {radical} nodes}] + +Radical nodes are the most complex as they deal with scripts as well as +constructed large symbols. Many fields: \showfields {radical}. Warning: never +assign a node list to the \type {nucleus}, \type {sub}, \type {sup}, \type +{left}, or \type {degree} field unless you are sure its internal link structure +is correct, otherwise an error can be triggered. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC \showsubtypes{radical} \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{nucleus} \NC kernel node \NC base \NC \NR +\NC \type{sub} \NC kernel node \NC subscript \NC \NR +\NC \type{sup} \NC kernel node \NC superscript \NC \NR +\NC \type{left} \NC delimiter node \NC \NC \NR +\NC \type{degree} \NC kernel node \NC only set by \lpr {Uroot} \NC \NR +\NC \type{width} \NC number \NC required width \NC \NR +\NC \type{options} \NC number \NC bitset of rendering options \NC \NR +\LL +\stoptabulate + +\stopsubsubsection + +\startsubsubsection[title={\nod {fraction} nodes}] + +Fraction nodes are also used for delimited cases, hence the \type {left} and +\type {right} fields among: \showfields {fraction}. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{width} \NC number \NC (optional) width of the fraction \NC \NR +\NC \type{num} \NC kernel node \NC numerator \NC \NR +\NC \type{denom} \NC kernel node \NC denominator \NC \NR +\NC \type{left} \NC delimiter node \NC left side symbol \NC \NR +\NC \type{right} \NC delimiter node \NC right side symbol \NC \NR +\NC \type{middle} \NC delimiter node \NC middle symbol \NC \NR +\NC \type{options} \NC number \NC bitset of rendering options \NC \NR +\LL +\stoptabulate + +Warning: never assign a node list to the \type {num}, or \type {denom} field +unless you are sure its internal link structure is correct, otherwise an error +can result. + +\stopsubsubsection + +\startsubsubsection[title={\nod {fence} nodes}] + +Fence nodes come in pairs but either one can be a dummy (this period driven empty +fence). Fields are: \showfields {fence}. Some of these fields are used by the +renderer and might get adapted in the process. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{subtype} \NC number \NC \showsubtypes{fence} \NC \NR +\NC \type{attr} \NC node \NC list of attributes \NC \NR +\NC \type{delim} \NC delimiter node \NC delimiter specification \NC \NR +\NC \type{italic} \NC number \NC italic correction \NC \NR +\NC \type{height} \NC number \NC required height \NC \NR +\NC \type{depth} \NC number \NC required depth \NC \NR +\NC \type{options} \NC number \NC bitset of rendering options \NC \NR +\NC \type{class} \NC number \NC spacing related class \NC \NR +\LL +\stoptabulate + +\stopsubsubsection + +\stopsubsection + +\stopsection + +\startsection[title={The \type {node} library}][library=node] + +\startsubsection[title={Introduction}] + +The \type {node} library provides methods that facilitate dealing with (lists of) +nodes and their values. They allow you to create, alter, copy, delete, and insert +node, the core objects within the typesetter. Nodes are represented in \LUA\ as +userdata. The various parts within a node can be accessed using named fields. + +Each node has at least the three fields \type {next}, \type {id}, and \type +{subtype}. The other available fields depend on the \type {id}. + +\startitemize[intro] + +\startitem + The \type {next} field returns the userdata object for the next node in a + linked list of nodes, or \type {nil}, if there is no next node. +\stopitem + +\startitem + The \type {id} indicates \TEX's \quote{node type}. The field \type {id} has a + numeric value for efficiency reasons, but some of the library functions also + accept a string value instead of \type {id}. +\stopitem + +\startitem + The \type {subtype} is another number. It often gives further information + about a node of a particular \type {id}. +\stopitem + +\stopitemize + +% Support for \nod {unset} (alignment) nodes is partial: they can be queried and +% modified from \LUA\ code, but not created. + +Nodes can be compared to each other, but: you are actually comparing indices into +the node memory. This means that equality tests can only be trusted under very +limited conditions. It will not work correctly in any situation where one of the +two nodes has been freed and|/|or reallocated: in that case, there will be false +positives. The general approach to a node related callback is as follows: + +\startitemize + +\startitem + Assume that the node list that you get is okay and properly double linked. + If for some reason the links are not right, you can apply \type {node.slide} + to the list. +\stopitem + +\startitem + When you insert a node, make sure you use a previously removed one, a new one + or a copy. Don't simply inject the same node twice. +\stopitem + +\startitem + When you remove a node, make sure that when this is permanent, you also free + the node or list. When you free a node its components are checked and when + they are nodes themselves they are also freed. +\stopitem + +\startitem + Although you can fool the system, normally you will trigger an error when you + try to copy a nonexisting node, or free an already freed node. There is some + overhead involved in this checking but the current compromise is acceptable. +\stopitem + +\startitem + When you're done, pass back (if needed) the result. It's your responsibility + to make sure that the list is properly linked (you can play safe and again + apply \type {node.slide}. In principle you can put nodes in a list that are + not acceptable in the following up actions. Some nodes get ignored, others + will trigger an error, and sometimes the engine will just crash. +\stopitem + +\stopitemize + +So, from the above it will be clear then memory management of nodes has to be +done explicitly by the user. Nodes are not \quote {seen} by the \LUA\ garbage +collector, so you have to call the node freeing functions yourself when you are +no longer in need of a node (list). Nodes form linked lists without reference +counting, so you have to be careful that when control returns back to \LUATEX\ +itself, you have not deleted nodes that are still referenced from a \type {next} +pointer elsewhere, and that you did not create nodes that are referenced more +than once. Normally the setters and getters handle this for you. + +A good example are discretionary nodes that themselves have three sublists. +Internally they use special pointers, but the user never sees them because when +you query them or set fields, this property is hidden and taken care of. You just +see a list. But, when you mess with these sub lists it is your responsibility +that it only contains nodes that are permitted in a discretionary. + +There are statistics available with regards to the allocated node memory, which +can be handy for tracing. Normally the amount of used nodes is not that large. +Typesetting a page can involve thousands of them but most are freed when the page +has been shipped out. Compared to other programs, node memory usage is not that +excessive. So, if for some reason your application leaks nodes, if at the end of +your run you lost as few hundred it's not a real problem. In fact, if you created +boxes and made copies but not flushed them for good reason, your run will for +sure end with used nodes and the statistics will mention that. The same is true +for attributes and skips (glue spec nodes): keeping the current state involves +using nodes. + +\stopsubsection + +\startsubsection[title={Housekeeping}] + +\startsubsubsection[title={\type {types}}] + +\libindex {types} + +This function returns an array that maps node id numbers to node type strings, +providing an overview of the possible top|-|level \type {id} types. + +\startfunctioncall +
t = node.types() +\stopfunctioncall + +when we issue this command, we get a table. The currently visible types are +\inlineluavalue { node.types() } where the numbers are the internal identifiers. +Only those nodes are reported that make sense to users so there can be gaps in +the range of numbers. + +\stopsubsubsection + +\startsubsubsection[title={\type {id} and \type {type}}] + +\libindex{id} +\libindex{type} + +This converts a single type name to its internal numeric representation. + +\startfunctioncall + id = node.id( type) +\stopfunctioncall + +The \type {node.id("glyph")} command returns the number \inlineluavalue { node.id +("glyph") } and \type {node.id("hlist")} returns \inlineluavalue { node.id +("hlist") } where the number don't relate to importance or some ordering; they +just appear in the order that is handy for the engine. Commands like this are +rather optimized so performance should be ok but you can of course always store +the id in a \LUA\ number. + +The reverse operation is: \type {node.type} If the argument is a number, then the +next function converts an internal numeric representation to an external string +representation. Otherwise, it will return the string \type {node} if the object +represents a node, and \type {nil} otherwise. + +\startfunctioncall + type = node.type( n) +\stopfunctioncall + +The \type {node.type(4)} command returns the string \inlineluavalue { node.type +(4) } and \type {node.id(99)} returns \inlineluavalue { node.id (99) } because +there is no node with that id. + +\stopsubsubsection + +\startsubsubsection[title={\type {fields} and \type {has_field}}] + +\libindex {fields} +\libindex {has_field} + +This function returns an indexed table with valid field names for a particular type of +node. + +\startfunctioncall +
t = node.fields( id) +\stopfunctioncall + +The function accepts a string or number, so \typ {node.fields ("glyph")} returns +\inlineluavalue { node.fields ("glyph") } and \typ {node.fields (12)} gives +\inlineluavalue { node.fields (12) }. + +The \type {has_field} function returns a boolean that is only true if \type {n} +is actually a node, and it has the field. + +\startfunctioncall + t = node.has_field( n, field) +\stopfunctioncall + +This function probably is not that useful but some nodes don't have a \type +{subtype}, \type {attr} or \type {prev} field and this is a way to test for that. + +\stopsubsubsection + +\startsubsubsection[title={\type {is_node}}] + +\topicindex {nodes+functions} + +\libindex {is_node} + +\startfunctioncall + t = node.is_node( item) +\stopfunctioncall + +This function returns a number (the internal index of the node) if the argument +is a userdata object of type \type {} and false when no node is passed. + +\stopsubsubsection + +\startsubsubsection[title={\type {new}}] + +\libindex{new} + +The \type {new} function creates a new node. All its fields are initialized to +either zero or \type {nil} except for \type {id} and \type {subtype}. Instead of +numbers you can also use strings (names). If you pass a second argument the +subtype will be set too. + +\startfunctioncall + n = node.new( id) + n = node.new( id, subtype) +\stopfunctioncall + +As already has been mentioned, you are responsible for making sure that nodes +created this way are used only once, and are freed when you don't pass them +back somehow. + +\stopsubsubsection + +\startsubsubsection[title={\type {free}, \type {flush_node} and \type {flush_list}}] + +\libindex{free} +\libindex{flush_node} +\libindex{flush_list} + +The next one frees node \type {n} from \TEX's memory. Be careful: no checks are +done on whether this node is still pointed to from a register or some \type +{next} field: it is up to you to make sure that the internal data structures +remain correct. Fields that point to nodes or lists are flushed too. So, when +you used their content for something else you need to set them to nil first. + +\startfunctioncall + next = node.free( n) +flush_node( n) +\stopfunctioncall + +The \type {free} function returns the next field of the freed node, while the +\type {flush_node} alternative returns nothing. + +A list starting with node \type {n} can be flushed from \TEX's memory too. Be +careful: no checks are done on whether any of these nodes is still pointed to +from a register or some \type {next} field: it is up to you to make sure that the +internal data structures remain correct. + +\startfunctioncall +node.flush_list( n) +\stopfunctioncall + +When you free for instance a discretionary node, \type {flush_list} is applied to +the \type {pre}, \type {post}, \type {replace} so you don't need to do that +yourself. Assigning them \type {nil} won't free those lists! + +\stopsubsubsection + +\startsubsubsection[title={\type {copy} and \type {copy_list}}] + +\libindex{copy} +\libindex{copy_list} + +This creates a deep copy of node \type {n}, including all nested lists as in the case +of a hlist or vlist node. Only the \type {next} field is not copied. + +\startfunctioncall + m = node.copy( n) +\stopfunctioncall + +A deep copy of the node list that starts at \type {n} can be created too. If +\type {m} is also given, the copy stops just before node \type {m}. + +\startfunctioncall + m = node.copy_list( n) + m = node.copy_list( n, m) +\stopfunctioncall + +Note that you cannot copy attribute lists this way. However, there is normally no +need to copy attribute lists as when you do assignments to the \type {attr} field +or make changes to specific attributes, the needed copying and freeing takes +place automatically. When you change a value of an attribute {\em in} a list, it will +affect all the nodes that share that list. + +\stopsubsubsection + +\startsubsubsection[title={\type {write}}] + +\libindex {write} + +\startfunctioncall +node.write( n) +\stopfunctioncall + +This function that will append a node list to \TEX's \quote {current list}. The +node list is not deep|-|copied! There is no error checking either! You mignt need +to enforce horizontal mode in order for this to work as expected. + +\stopsubsubsection + +\stopsubsection + +\startsubsection[title={Manipulating lists}] + +\startsubsubsection[title={\type {slide}}] + +\libindex {slide} + +This helper makes sure that the node lists is double linked and returns the found +tail node. + +\startfunctioncall + tail = node.slide( n) +\stopfunctioncall + +After some callbacks automatic sliding takes place. This feature can be turned +off with \type {node.fix_node_lists(false)} but you better make sure then that +you don't mess up lists. In most cases \TEX\ itself only uses \type {next} +pointers but your other callbacks might expect proper \type {prev} pointers too. +Future versions of \LUATEX\ can add more checking but this will not influence +usage. + +\stopsubsubsection + +\startsubsubsection[title={\type {tail}}] + +\libindex {tail} + +\startfunctioncall + m = node.tail( n) +\stopfunctioncall + +Returns the last node of the node list that starts at \type {n}. + +\stopsubsubsection + +\startsubsubsection[title={\type {length} and \type {count}}] + +\libindex {length} +\libindex {count} + +\startfunctioncall + i = node.length( n) + i = node.length( n, m) +\stopfunctioncall + +Returns the number of nodes contained in the node list that starts at \type {n}. +If \type {m} is also supplied it stops at \type {m} instead of at the end of the +list. The node \type {m} is not counted. + +\startfunctioncall + i = node.count( id, n) + i = node.count( id, n, m) +\stopfunctioncall + +Returns the number of nodes contained in the node list that starts at \type {n} +that have a matching \type {id} field. If \type {m} is also supplied, counting +stops at \type {m} instead of at the end of the list. The node \type {m} is not +counted. This function also accept string \type {id}'s. + +\stopsubsubsection + +\startsubsubsection[title={\type {remove}}] + +\libindex {remove} + +\startfunctioncall + head, current, removed = + node.remove( head, current) + head, current = + node.remove( head, current, true) +\stopfunctioncall + +This function removes the node \type {current} from the list following \type +{head}. It is your responsibility to make sure it is really part of that list. +The return values are the new \type {head} and \type {current} nodes. The +returned \type {current} is the node following the \type {current} in the calling +argument, and is only passed back as a convenience (or \type {nil}, if there is +no such node). The returned \type {head} is more important, because if the +function is called with \type {current} equal to \type {head}, it will be +changed. When the third argument is passed, the node is freed. + +\stopsubsubsection + +\startsubsubsection[title={\type {insert_before}}] + +\libindex {insert_before} + +\startfunctioncall + head, new = node.insert_before( head, current, new) +\stopfunctioncall + +This function inserts the node \type {new} before \type {current} into the list +following \type {head}. It is your responsibility to make sure that \type +{current} is really part of that list. The return values are the (potentially +mutated) \type {head} and the node \type {new}, set up to be part of the list +(with correct \type {next} field). If \type {head} is initially \type {nil}, it +will become \type {new}. + +\stopsubsubsection + +\startsubsubsection[title={\type {insert_after}}] + +\libindex {insert_after} + +\startfunctioncall + head, new = node.insert_after( head, current, new) +\stopfunctioncall + +This function inserts the node \type {new} after \type {current} into the list +following \type {head}. It is your responsibility to make sure that \type +{current} is really part of that list. The return values are the \type {head} and +the node \type {new}, set up to be part of the list (with correct \type {next} +field). If \type {head} is initially \type {nil}, it will become \type {new}. + +\stopsubsubsection + +\startsubsubsection[title={\type {last_node}}] + +\libindex {last_node} + +\startfunctioncall + n = node.last_node() +\stopfunctioncall + +This function pops the last node from \TEX's \quote{current list}. It returns +that node, or \type {nil} if the current list is empty. + +\stopsubsubsection + +\startsubsubsection[title={\type {traverse}}] + +\libindex {traverse} + +\startfunctioncall + t, id, subtype = node.traverse( n) +\stopfunctioncall + +This is a \LUA\ iterator that loops over the node list that starts at \type {n}. +Typically code looks like this: + +\starttyping +for n in node.traverse(head) do + ... +end +\stoptyping + +is functionally equivalent to: + +\starttyping +do + local n + local function f (head,var) + local t + if var == nil then + t = head + else + t = var.next + end + return t + end + while true do + n = f (head, n) + if n == nil then break end + ... + end +end +\stoptyping + +It should be clear from the definition of the function \type {f} that even though +it is possible to add or remove nodes from the node list while traversing, you +have to take great care to make sure all the \type {next} (and \type {prev}) +pointers remain valid. + +If the above is unclear to you, see the section \quote {For Statement} in the +\LUA\ Reference Manual. + +\stopsubsubsection + +\startsubsubsection[title={\type {traverse_id}}] + +\libindex {traverse_id} + +\startfunctioncall + t, subtype = node.traverse_id( id, n) +\stopfunctioncall + +This is an iterator that loops over all the nodes in the list that starts at +\type {n} that have a matching \type {id} field. + +See the previous section for details. The change is in the local function \type +{f}, which now does an extra while loop checking against the upvalue \type {id}: + +\starttyping + local function f(head,var) + local t + if var == nil then + t = head + else + t = var.next + end + while not t.id == id do + t = t.next + end + return t + end +\stoptyping + +\stopsubsubsection + +\startsubsubsection[title={\type {traverse_char} and \type {traverse_glyph}}] + +\libindex {traverse_char} +\libindex {traverse_glyph} + +The \type{traverse_char} iterator loops over the \nod {glyph} nodes in a list. +Only nodes with a subtype less than 256 are seen. + +\startfunctioncall + n, font, char = node.traverse_char( n) +\stopfunctioncall + +The \type{traverse_glyph} iterator loops over a list and returns the list and +filters all glyphs: + +\startfunctioncall + n, font, char = node.traverse_glyph( n) +\stopfunctioncall + +\stopsubsubsection + +\startsubsubsection[title={\type {traverse_list}}] + +\libindex {traverse_list} + +This iterator loops over the \nod {hlist} and \nod {vlist} nodes in a list. + +\startfunctioncall + n, id, subtype, list = node.traverse_list( n) +\stopfunctioncall + +The four return values can save some time compared to fetching these fields but +in practice you seldom need them all. So consider it a (side effect of +experimental) convenience. + +\stopsubsubsection + +\startsubsubsection[title={\type {find_node}}] + +\libindex {find_node} + +This helper returns the location of the first match at or after node \type {n}: + +\startfunctioncall + n = node.traverse_list( n, subtype) + n, subtype = node.traverse_list( n) +\stopfunctioncall + +\stopsubsubsection + + +\stopsubsection + +\startsubsection[title={Glue handling}][library=node] + +\startsubsubsection[title={\type {setglue}}] + +\libindex {setglue} + +You can set the properties of a glue in one go. If you pass no values, the glue +will become a zero glue. + +\startfunctioncall +node.setglue( n) +node.setglue( n,width,stretch,shrink,stretch_order,shrink_order) +\stopfunctioncall + +When you pass values, only arguments that are numbers are assigned so + +\starttyping +node.setglue(n,655360,false,65536) +\stoptyping + +will only adapt the width and shrink. + +When a list node is passed, you set the glue, order and sign instead. + +\stopsubsubsection + +\startsubsubsection[title={\type {getglue}}] + +\libindex {getglue} + +The next call will return 5 values or nothing when no glue is passed. + +\startfunctioncall + width, stretch, shrink, stretch_order, + shrink_order = node.getglue( n) +\stopfunctioncall + +When the second argument is false, only the width is returned (this is consistent +with \type {tex.get}). + +When a list node is passed, you get back the glue that is set, the order of that +glue and the sign. + +\stopsubsubsection + +\startsubsubsection[title={\type {is_zero_glue}}] + +\libindex {is_zero_glue} + +This function returns \type {true} when the width, stretch and shrink properties +are zero. + +\startfunctioncall + isglue = node.is_zero_glue( n) +\stopfunctioncall + +\stopsubsubsection + +\stopsubsection + +\startsubsection[title={Attribute handling}][library=node] + +\startsubsubsection[title={Attributes}] + +\topicindex {attributes} + +Assignments to attributes registers result in assigning lists with set attributes +to nodes and the implementation is non|-|trivial because the value that is +attached to a node is essentially a (sorted) sparse array of key|-|value pairs. +It is generally easiest to deal with attribute lists and attributes by using the +dedicated functions in the \type {node} library. + +\stopsubsubsection + +\startsubsubsection[title={\nod {attribute_list} nodes}] + +\topicindex {nodes+attributes} + +An \type {attribute_list} item is used as a head pointer for a list of attribute +items. It has only one user|-|visible field: + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{next} \NC node \NC pointer to the first attribute \NC \NR +\LL +\stoptabulate + +\stopsubsubsection + +\startsubsubsection[title={\nod {attr} nodes}] + +A normal node's attribute field will point to an item of type \nod +{attribute_list}, and the \type {next} field in that item will point to the first +defined \quote {attribute} item, whose \type {next} will point to the second +\quote {attribute} item, etc. + +\starttabulate[|l|l|p|] +\DB field \BC type \BC explanation \NC \NR +\TB +\NC \type{next} \NC node \NC pointer to the next attribute \NC \NR +\NC \type{number} \NC number \NC the attribute type id \NC \NR +\NC \type{value} \NC number \NC the attribute value \NC \NR +\LL +\stoptabulate + +As mentioned it's better to use the official helpers rather than edit these +fields directly. For instance the \type {prev} field is used for other purposes +and there is no double linked list. + +\stopsubsubsection + +\startsubsubsection[title={\type {current_attr}}] + +\libindex{current_attr} + +This returns the currently active list of attributes, if there is one. + +\startfunctioncall + m = node.current_attr() +\stopfunctioncall + +The intended usage of \type {current_attr} is as follows: + +\starttyping +local x1 = node.new("glyph") +x1.attr = node.current_attr() +local x2 = node.new("glyph") +x2.attr = node.current_attr() +\stoptyping + +or: + +\starttyping +local x1 = node.new("glyph") +local x2 = node.new("glyph") +local ca = node.current_attr() +x1.attr = ca +x2.attr = ca +\stoptyping + +The attribute lists are ref counted and the assignment takes care of incrementing +the refcount. You cannot expect the value \type {ca} to be valid any more when +you assign attributes (using \type {tex.setattribute}) or when control has been +passed back to \TEX. + +\stopsubsubsection + +\startsubsubsection[title={\type {has_attribute}}] + +\libindex {has_attribute} + +\startfunctioncall + v = node.has_attribute( n, id) + v = node.has_attribute( n, id, val) +\stopfunctioncall + +Tests if a node has the attribute with number \type {id} set. If \type {val} is +also supplied, also tests if the value matches \type {val}. It returns the value, +or, if no match is found, \type {nil}. + +\stopsubsubsection + +\startsubsubsection[title={\type {get_attribute}}] + +\libindex {get_attribute} + +\startfunctioncall + v = node.get_attribute( n, id) +\stopfunctioncall + +Tests if a node has an attribute with number \type {id} set. It returns the +value, or, if no match is found, \type {nil}. If no \type {id} is given then the +zero attributes is assumed. + +\stopsubsubsection + +\startsubsubsection[title={\type {find_attribute}}] + +\libindex {find_attribute} + +\startfunctioncall + v, n = node.find_attribute( n, id) +\stopfunctioncall + +Finds the first node that has attribute with number \type {id} set. It returns +the value and the node if there is a match and otherwise nothing. + +\stopsubsubsection + +\startsubsubsection[title={\type {set_attribute}}] + +\libindex {set_attribute} + +\startfunctioncall +node.set_attribute( n, id, val) +\stopfunctioncall + +Sets the attribute with number \type {id} to the value \type {val}. Duplicate +assignments are ignored. + +\stopsubsubsection + +\startsubsubsection[title={\type {unset_attribute}}] + +\libindex {unset_attribute} + +\startfunctioncall + v = + node.unset_attribute( n, id) + v = + node.unset_attribute( n, id, val) +\stopfunctioncall + +Unsets the attribute with number \type {id}. If \type {val} is also supplied, it +will only perform this operation if the value matches \type {val}. Missing +attributes or attribute|-|value pairs are ignored. + +If the attribute was actually deleted, returns its old value. Otherwise, returns +\type {nil}. + +\stopsubsubsection + +\stopsubsection + +\startsubsection[title={Glyph handling}][library=node] + +\startsubsubsection[title={\type {first_glyph}}] + +\libindex {first_glyph} + +\startfunctioncall + n = node.first_glyph( n) + n = node.first_glyph( n, m) +\stopfunctioncall + +Returns the first node in the list starting at \type {n} that is a glyph node +with a subtype indicating it is a glyph, or \type {nil}. If \type {m} is given, +processing stops at (but including) that node, otherwise processing stops at the +end of the list. + +\stopsubsubsection + +\startsubsubsection[title={\type {is_char} and \type {is_glyph}}] + +\libindex {is_char} +\libindex {is_glyph} + +The subtype of a glyph node signals if the glyph is already turned into a character reference +or not. + +\startfunctioncall + b = node.is_char( n) + b = node.is_glyph( n) +\stopfunctioncall + +\stopsubsubsection + +\startsubsubsection[title={\type {has_glyph}}] + +\libindex {has_glyph} + +This function returns the first glyph or disc node in the given list: + +\startfunctioncall + n = node.has_glyph( n) +\stopfunctioncall + +\stopsubsubsection + +\startsubsubsection[title={\type {ligaturing}}] + +\libindex {ligaturing} + +\startfunctioncall + h, t, success = node.ligaturing( n) + h, t, success = node.ligaturing( n, m) +\stopfunctioncall + +Apply \TEX-style ligaturing to the specified nodelist. The tail node \type {m} is +optional. The two returned nodes \type {h} and \type {t} are the new head and +tail (both \type {n} and \type {m} can change into a new ligature). + +\stopsubsubsection + +\startsubsubsection[title={\type {kerning}}] + +\libindex {kerning} + +\startfunctioncall + h, t, success = node.kerning( n) + h, t, success = node.kerning( n, m) +\stopfunctioncall + +Apply \TEX|-|style kerning to the specified node list. The tail node \type {m} is +optional. The two returned nodes \type {h} and \type {t} are the head and tail +(either one of these can be an inserted kern node, because special kernings with +word boundaries are possible). + +\stopsubsubsection + +\startsubsubsection[title={\type {unprotect_glyph[s]}}] + +\libindex {unprotect_glyphs} +\libindex {unprotect_glyph} + +\startfunctioncall +node.unprotect_glyph( n) +node.unprotect_glyphs( n,[ n]) +\stopfunctioncall + +Subtracts 256 from all glyph node subtypes. This and the next function are +helpers to convert from \type {characters} to \type {glyphs} during node +processing. The second argument is optional and indicates the end of a range. + +\stopsubsubsection + +\startsubsubsection[title={\type {protect_glyph[s]}}] + +\libindex {protect_glyphs} +\libindex {protect_glyph} + +\startfunctioncall +node.protect_glyph( n) +node.protect_glyphs( n,[ n]) +\stopfunctioncall + +Adds 256 to all glyph node subtypes in the node list starting at \type {n}, +except that if the value is 1, it adds only 255. The special handling of 1 means +that \type {characters} will become \type {glyphs} after subtraction of 256. A +single character can be marked by the singular call. The second argument is +optional and indicates the end of a range. + +\stopsubsubsection + +\startsubsubsection[title={\type {protrusion_skippable}}] + +\libindex {protrusion_skippable} + +\startfunctioncall + skippable = node.protrusion_skippable( n) +\stopfunctioncall + +Returns \type {true} if, for the purpose of line boundary discovery when +character protrusion is active, this node can be skipped. + +\stopsubsubsection + +\startsubsubsection[title={\type {check_discretionary}, \type {check_discretionaries}}] + +\libindex{check_discretionary} +\libindex{check_discretionaries} + +When you fool around with disc nodes you need to be aware of the fact that they +have a special internal data structure. As long as you reassign the fields when +you have extended the lists it's ok because then the tail pointers get updated, +but when you add to list without reassigning you might end up in trouble when +the linebreak routine kicks in. You can call this function to check the list for +issues with disc nodes. + +\startfunctioncall +node.check_discretionary( n) +node.check_discretionaries( head) +\stopfunctioncall + +The plural variant runs over all disc nodes in a list, the singular variant +checks one node only (it also checks if the node is a disc node). + +\stopsubsubsection + +\startsubsubsection[title={\type {flatten_discretionaries}}] + +\libindex {flatten_discretionaries} + +This function will remove the discretionaries in the list and inject the replace +field when set. + +\startfunctioncall + head, count = node.flatten_discretionaries( n) +\stopfunctioncall + +\stopsubsubsection + +\stopsubsection + +\startsubsection[title={Packaging}][library=node] + +\startsubsubsection[title={\type {hpack}}] + +\libindex {hpack} + +This function creates a new hlist by packaging the list that begins at node \type +{n} into a horizontal box. With only a single argument, this box is created using +the natural width of its components. In the three argument form, \type {info} +must be either \type {additional} or \type {exactly}, and \type {w} is the +additional (\type {\hbox spread}) or exact (\type {\hbox to}) width to be used. +The second return value is the badness of the generated box. + +\startfunctioncall + h, b = + node.hpack( n) + h, b = + node.hpack( n, w, info) + h, b = + node.hpack( n, w, info, dir) +\stopfunctioncall + +Caveat: there can be unexpected side|-|effects to this function, like updating +some of the \prm {marks} and \type {\inserts}. Also note that the content of +\type {h} is the original node list \type {n}: if you call \type {node.free(h)} +you will also free the node list itself, unless you explicitly set the \type +{list} field to \type {nil} beforehand. And in a similar way, calling \type +{node.free(n)} will invalidate \type {h} as well! + +\stopsubsubsection + +\startsubsubsection[title={\type {vpack}}] + +\libindex {vpack} + +This function creates a new vlist by packaging the list that begins at node \type +{n} into a vertical box. With only a single argument, this box is created using +the natural height of its components. In the three argument form, \type {info} +must be either \type {additional} or \type {exactly}, and \type {w} is the +additional (\type {\vbox spread}) or exact (\type {\vbox to}) height to be used. + +\startfunctioncall + h, b = + node.vpack( n) + h, b = + node.vpack( n, w, info) + h, b = + node.vpack( n, w, info, dir) +\stopfunctioncall + +The second return value is the badness of the generated box. See the description +of \type {hpack} for a few memory allocation caveats. + +\stopsubsubsection + +\startsubsubsection[title={\type {prepend_prevdepth}}] + +\libindex {prepend_prevdepth} + +This function is somewhat special in the sense that it is an experimental helper +that adds the interlinespace to a line keeping the baselineskip and lineskip into +account. + +\startfunctioncall + n, delta = + node.prepend_prevdepth( n, prevdepth) +\stopfunctioncall + +\stopsubsubsection + +\startsubsubsection[title={\type {dimensions}, \type {rangedimensions}, \type {naturalwidth}}] + +\libindex{dimensions} +\libindex{rangedimensions} + +\startfunctioncall + w, h, d = + node.dimensions( n) + w, h, d = + node.dimensions( n, t) +\stopfunctioncall + +This function calculates the natural in|-|line dimensions of the node list starting +at node \type {n} and terminating just before node \type {t} (or the end of the +list, if there is no second argument). The return values are scaled points. An +alternative format that starts with glue parameters as the first three arguments +is also possible: + +\startfunctioncall + w, h, d = + node.dimensions( glue_set, glue_sign, glue_order, + n) + w, h, d = + node.dimensions( glue_set, glue_sign, glue_order, + n, t) +\stopfunctioncall + +This calling method takes glue settings into account and is especially useful for +finding the actual width of a sublist of nodes that are already boxed, for +example in code like this, which prints the width of the space in between the +\type {a} and \type {b} as it would be if \type {\box0} was used as-is: + +\starttyping +\setbox0 = \hbox to 20pt {a b} + +\directlua{print (node.dimensions( + tex.box[0].glue_set, + tex.box[0].glue_sign, + tex.box[0].glue_order, + tex.box[0].head.next, + node.tail(tex.box[0].head) +)) } +\stoptyping + +You need to keep in mind that this is one of the few places in \TEX\ where floats +are used, which means that you can get small differences in rounding when you +compare the width reported by \type {hpack} with \type {dimensions}. + +The second alternative saves a few lookups and can be more convenient in some +cases: + +\startfunctioncall + w, h, d = + node.rangedimensions( parent, first) + w, h, d = + node.rangedimensions( parent, first, last) +\stopfunctioncall + +A simple and somewhat more efficient variant is this: + +\startfunctioncall + w = + node.naturalwidth( start, stop) +\stopfunctioncall + +\stopsubsubsection + +\stopsubsection + +\startsubsection[title={Math}][library=node] + +\startsubsubsection[title={\type {mlist_to_hlist}}] + +\libindex {mlist_to_hlist} + +\startfunctioncall + h = + node.mlist_to_hlist( n, display_type, penalties) +\stopfunctioncall + +This runs the internal mlist to hlist conversion, converting the math list in +\type {n} into the horizontal list \type {h}. The interface is exactly the same +as for the callback \cbk {mlist_to_hlist}. + +\stopsubsubsection + +\startsubsubsection[title={\type {end_of_math}}] + +\libindex {end_of_math} + +\startfunctioncall + t = node.end_of_math( start) +\stopfunctioncall + +Looks for and returns the next \type {math_node} following the \type {start}. If +the given node is a math end node this helper returns that node, else it follows +the list and returns the next math endnote. If no such node is found nil is +returned. + +\stopsubsubsection + +\stopsubsection + +\stopsection + +\startsection[title={Two access models}][library=node] + +\topicindex{nodes+direct} +\topicindex{direct nodes} + +\libindex {todirect} +\libindex {tonode} +\libindex {tostring} + +Deep down in \TEX\ a node has a number which is a numeric entry in a memory +table. In fact, this model, where \TEX\ manages memory is real fast and one of +the reasons why plugging in callbacks that operate on nodes is quite fast too. +Each node gets a number that is in fact an index in the memory table and that +number often is reported when you print node related information. You go from +userdata nodes and there numeric references and back with: + +\startfunctioncall + d = node.todirect( n)) + n = node.tonode( d)) +\stopfunctioncall + +The userdata model is rather robust as it is a virtual interface with some +additional checking while the more direct access which uses the node numbers +directly. However, even with userdata you can get into troubles when you free +nodes that are no longer allocated or mess up lists. if you apply \type +{tostring} to a node you see its internal (direct) number and id. + +The first model provides key based access while the second always accesses fields +via functions: + +\starttyping +nodeobject.char +getfield(nodenumber,"char") +\stoptyping + +If you use the direct model, even if you know that you deal with numbers, you +should not depend on that property but treat it as an abstraction just like +traditional nodes. In fact, the fact that we use a simple basic datatype has the +penalty that less checking can be done, but less checking is also the reason why +it's somewhat faster. An important aspect is that one cannot mix both methods, +but you can cast both models. So, multiplying a node number makes no sense. + +So our advice is: use the indexed (table) approach when possible and investigate +the direct one when speed might be a real issue. For that reason \LUATEX\ also +provide the \type {get*} and \type {set*} functions in the top level node +namespace. There is a limited set of getters. When implementing this direct +approach the regular index by key variant was also optimized, so direct access +only makes sense when nodes are accessed millions of times (which happens in some +font processing for instance). + +We're talking mostly of getters because setters are less important. Documents +have not that many content related nodes and setting many thousands of properties +is hardly a burden contrary to millions of consultations. + +Normally you will access nodes like this: + +\starttyping +local next = current.next +if next then + -- do something +end +\stoptyping + +Here \type {next} is not a real field, but a virtual one. Accessing it results in +a metatable method being called. In practice it boils down to looking up the node +type and based on the node type checking for the field name. In a worst case you +have a node type that sits at the end of the lookup list and a field that is last +in the lookup chain. However, in successive versions of \LUATEX\ these lookups +have been optimized and the most frequently accessed nodes and fields have a +higher priority. + +Because in practice the \type {next} accessor results in a function call, there +is some overhead involved. The next code does the same and performs a tiny bit +faster (but not that much because it is still a function call but one that knows +what to look up). + +\starttyping +local next = node.next(current) +if next then + -- do something +end +\stoptyping + +In the direct namespace there are more helpers and most of them are accompanied +by setters. The getters and setters are clever enough to see what node is meant. +We don't deal with whatsit nodes: their fields are always accessed by name. It +doesn't make sense to add getters for all fields, we just identifier the most +likely candidates. In complex documents, many node and fields types never get +seen, or seen only a few times, but for instance glyphs are candidates for such +optimization. The \type {node.direct} interface has some more helpers. \footnote +{We can define the helpers in the node namespace with \type {getfield} which is +about as efficient, so at some point we might provide that as module.} + +The \type {setdisc} helper takes three (optional) arguments plus an optional +fourth indicating the subtype. Its \type {getdisc} takes an optional boolean; +when its value is \type {true} the tail nodes will also be returned. The \type +{setfont} helper takes an optional second argument, it being the character. The +directmode setter \type {setlink} takes a list of nodes and will link them, +thereby ignoring \type {nil} entries. The first valid node is returned (beware: +for good reason it assumes single nodes). For rarely used fields no helpers are +provided and there are a few that probably are used seldom too but were added for +consistency. You can of course always define additional accessors using \type +{getfield} and \type {setfield} with little overhead. When the second argument of +\type {setattributelist} is \type {true} the current attribute list is assumed. + +In \CONTEXT\ some of the not performance|-|critical userdata variants are +emulated in \LUA\ and not in the engine, so we retain downward compatibility. + +\def\yes{$+$} \def\nop{$-$} + +\def\supported#1#2#3#4% + {\NC \type{#1} + \NC \ifx#2\yes\lix{node} {#1}\fi #2 + \NC \ifx#3\yes\lix{node.direct}{#1}\fi #3 \NC + \NC #4 \NC + \NR} + +\starttabulate[|l|c|c|] +\DB function \BC node \BC direct \NC emulated \NC \NR +\TB +\supported {check_discretionaries} \nop \yes \yes +\supported {check_discretionary} \nop \yes \yes +\supported {copy} \yes \yes \relax +\supported {copy_list} \yes \yes \relax +%supported {copy_only} \nop \yes \relax +\supported {count} \nop \yes \yes +\supported {current_attr} \yes \yes \relax +\supported {dimensions} \nop \yes \yes +\supported {effective_glue} \nop \yes \yes +\supported {end_of_math} \nop \yes \yes +\supported {find_attribute} \nop \yes \yes +%supported {find_attribute_range} \nop \yes \relax +%supported {find_node} \nop \yes \relax +\supported {first_glyph} \nop \yes \yes +\supported {flatten_discretionaries} \nop \yes \yes +%supported {flush_components} \nop \yes \relax +\supported {flush_list} \yes \yes \relax +\supported {flush_node} \yes \yes \relax +\supported {free} \yes \yes \relax +\supported {get_attribute} \yes \yes \relax +\supported {get_properties_table} \yes \yes \relax +\supported {get_synctex_fields} \nop \yes \relax +\supported {getattributelist} \nop \yes \relax +\supported {getboth} \nop \yes \relax +\supported {getbox} \nop \yes \relax +\supported {getchar} \nop \yes \relax +\supported {getcomponents} \nop \yes \relax +\supported {getdata} \nop \yes \relax +\supported {getdepth} \nop \yes \relax +\supported {getdirection} \nop \yes \relax +\supported {getdisc} \nop \yes \relax +\supported {getexpansion} \nop \yes \relax +\supported {getfam} \nop \yes \relax +\supported {getfield} \yes \yes \relax +\supported {getfont} \nop \yes \relax +\supported {getglue} \nop \yes \yes +%supported {getglyphdata} \nop \yes \relax % experiment +\supported {getheight} \nop \yes \relax +\supported {getid} \nop \yes \relax +\supported {getkern} \nop \yes \relax +\supported {getlang} \nop \yes \relax +\supported {getleader} \nop \yes \relax +\supported {getlist} \nop \yes \relax +\supported {getnext} \nop \yes \relax +\supported {getnormalizedline} \nop \yes \relax +\supported {getnucleus} \nop \yes \relax +\supported {getoffsets} \nop \yes \relax +\supported {getorientation} \nop \yes \relax +\supported {getpenalty} \nop \yes \relax +\supported {getpost} \nop \yes \relax +\supported {getpre} \nop \yes \relax +\supported {getprev} \nop \yes \relax +\supported {getproperty} \yes \yes \relax +\supported {getreplace} \nop \yes \relax +\supported {getshift} \nop \yes \relax +\supported {getsub} \nop \yes \relax +\supported {getsubtype} \nop \yes \relax +\supported {getsup} \nop \yes \relax +\supported {getwhd} \nop \yes \relax +\supported {getwidth} \nop \yes \relax +\supported {has_attribute} \yes \yes \relax +\supported {has_dimensions} \nop \yes \relax +\supported {has_field} \yes \yes \relax +\supported {has_glyph} \nop \yes \yes +\supported {hpack} \nop \yes \yes +%supported {ignore_math_skip} \nop \yes \relax +\supported {insert_after} \yes \yes \relax +\supported {insert_before} \yes \yes \relax +\supported {is_char} \nop \yes \relax +\supported {is_direct} \nop \yes \relax +\supported {is_glyph} \nop \yes \relax +\supported {is_node} \yes \yes \relax +\supported {is_valid} \nop \yes \relax +\supported {is_zero_glue} \nop \yes \yes +\supported {kerning} \nop \yes \yes +\supported {last_node} \nop \yes \yes +\supported {length} \nop \yes \yes +\supported {ligaturing} \nop \yes \yes +\supported {make_extensible} \nop \yes \yes +\supported {mlist_to_hlist} \nop \yes \yes +\supported {naturalwidth} \nop \yes \yes +\supported {new} \yes \yes \relax +\supported {prepend_prevdepth} \nop \yes \yes +\supported {protect_glyphs} \nop \yes \yes +\supported {protect_glyph} \nop \yes \yes +\supported {protrusion_skippable} \nop \yes \yes +\supported {rangedimensions} \nop \yes \yes +\supported {remove} \yes \yes \relax +\supported {set_attribute} \yes \yes \relax +\supported {set_synctex_fields} \nop \yes \relax +\supported {setattributelist} \nop \yes \relax +\supported {setboth} \nop \yes \relax +\supported {setbox} \nop \yes \relax +\supported {setchar} \nop \yes \relax +\supported {setcomponents} \nop \yes \relax +\supported {setdata} \nop \yes \relax +\supported {setdepth} \nop \yes \relax +\supported {setdirection} \nop \yes \relax +\supported {setdisc} \nop \yes \relax +\supported {setexpansion} \nop \yes \relax +\supported {setfam} \nop \yes \relax +\supported {setfield} \yes \yes \relax +\supported {setfont} \nop \yes \relax +\supported {setglue} \yes \yes \relax +%supported {setglyphdata} \nop \yes \relax % experiment +\supported {setheight} \nop \yes \relax +\supported {setkern} \nop \yes \relax +\supported {setlang} \nop \yes \relax +\supported {setleader} \nop \yes \relax +\supported {setlink} \nop \yes \relax +\supported {setlist} \nop \yes \relax +\supported {setnext} \nop \yes \relax +\supported {setnucleus} \nop \yes \relax +\supported {setoffsets} \nop \yes \relax +\supported {setorientation} \nop \yes \relax +\supported {setpenalty} \nop \yes \relax +\supported {setprev} \nop \yes \relax +\supported {setproperty} \yes \yes \relax +\supported {setshift} \nop \yes \relax +\supported {setsplit} \nop \yes \relax +\supported {setsub} \nop \yes \relax +\supported {setsubtype} \nop \yes \relax +\supported {setsup} \nop \yes \relax +\supported {setwhd} \nop \yes \relax +\supported {setwidth} \nop \yes \relax +\supported {slide} \nop \yes \yes +\supported {start_of_par} \nop \yes \relax +\supported {subtype} \nop \nop \relax +\supported {tail} \yes \yes \relax +\supported {todirect} \nop \yes \relax +\supported {tonode} \nop \yes \relax +\supported {tostring} \yes \nop \relax +\supported {traverse} \yes \yes \relax +\supported {traverse_char} \yes \yes \relax +\supported {traverse_glyph} \yes \yes \relax +\supported {traverse_id} \yes \yes \relax +\supported {traverse_list} \yes \yes \relax +\supported {type} \yes \nop \relax +\supported {unprotect_glyphs} \nop \yes \yes +\supported {unprotect_glyph} \nop \yes \yes +\supported {unset_attribute} \yes \yes \relax +\supported {usedlist} \nop \yes \yes +\supported {uses_font} \nop \yes \yes +\supported {vpack} \nop \yes \yes +\supported {write} \yes \yes \relax +\LL +\stoptabulate + +The \type {node.next} and \type {node.prev} functions will stay but for +consistency there are variants called \type {getnext} and \type {getprev}. We had +to use \type {get} because \type {node.id} and \type {node.subtype} are already +taken for providing meta information about nodes. Note: The getters do only basic +checking for valid keys. You should just stick to the keys mentioned in the +sections that describe node properties. + +Some of the getters and setters handle multiple node types, given that the field +is relevant. In that case, some field names are considered similar (like \type +{kern} and \type {width}, or \type {data} and \type {value}. In retrospect we +could have normalized field names better but we decided to stick to the original +(internal) names as much as possible. After all, at the \LUA\ end one can easily +create synonyms. + +Some nodes have indirect references. For instance a math character refers to a +family instead of a font. In that case we provide a virtual font field as +accessor. So, \type {getfont} and \type {.font} can be used on them. The same is +true for the \type {width}, \type {height} and \type {depth} of glue nodes. These +actually access the spec node properties, and here we can set as well as get the +values. + +In some places \LUATEX\ can do a bit of extra checking for valid node lists and +you can enable that with: + +\startfunctioncall +node.fix_node_lists( b) +\stopfunctioncall + +You can set and query the \SYNCTEX\ fields, a file number aka tag and a line +number, for a glue, kern, hlist, vlist, rule and math nodes as well as glyph +nodes (although this last one is not used in native \SYNCTEX). + +\startfunctioncall +node.set_synctex_fields( f, l) + f, l = + node.get_synctex_fields( n) +\stopfunctioncall + +Of course you need to know what you're doing as no checking on sane values takes +place. Also, the synctex interpreter used in editors is rather peculiar and has +some assumptions (heuristics). + +\stopsection + +\startsection[title={Normalization}][library=node] + +As an experiment the lines resulting from paragraph construction can be normalized. +There are several modes, that can be set and queried with: + +\startfunctioncall +node.direct.setnormalize( n) + n = node.direct.getnormalize() +\stopfunctioncall + +The state of a line (a hlist) can be queried with: + +\startfunctioncall + leftskip, rightskip, + lefthangskip, righthangskip, + head, tail, + parindent, parfillskip = node.direct.getnormalized() +\stopfunctioncall + +The modes accumulate, so mode \type {4} includes \type {1} upto \type {3}: + +\starttabulate[|l|p|] +\DB value \BC explanation \NC \NR +\TB +\NC \type{1} \NC left and right skips and directions \NC \NR +\NC \type{2} \NC indentation and parfill skip \NC \NR +\NC \type{3} \NC hanging indentation and par shapes \NC \NR +\NC \type{4} \NC idem but before left and right skips \NC \NR +\NC \type{5} \NC inject compensation for overflow \NC \NR +\LL +\stoptabulate + +This is experimental code and might take a while to become frozen. + +\stopsection + +\startsection[title={Properties}][library=node] + +\topicindex {nodes+properties} +\topicindex {properties} + +\libindex{flush_properties_table} +\libindex{get_properties_table} +\libindex{set_properties_mode} + +Attributes are a convenient way to relate extra information to a node. You can +assign them at the \TEX\ end as well as at the \LUA\ end and and consult them at +the \LUA\ end. One big advantage is that they obey grouping. They are linked +lists and normally checking for them is pretty efficient, even if you use a lot +of them. A macro package has to provide some way to manage these attributes at the +\TEX\ end because otherwise clashes in their usage can occur. + +Each node also can have a properties table and you can assign values to this +table using the \type {setproperty} function and get properties using the \type +{getproperty} function. Managing properties is way more demanding than managing +attributes. + +Take the following example: + +\starttyping +\directlua { + local n = node.new("glyph") + + node.setproperty(n,"foo") + print(node.getproperty(n)) + + node.setproperty(n,"bar") + print(node.getproperty(n)) + + node.free(n) +} +\stoptyping + +This will print \type {foo} and \type {bar} which in itself is not that useful +when multiple mechanisms want to use this feature. A variant is: + +\starttyping +\directlua { + local n = node.new("glyph") + + node.setproperty(n,{ one = "foo", two = "bar" }) + print(node.getproperty(n).one) + print(node.getproperty(n).two) + + node.free(n) +} +\stoptyping + +This time we store two properties with the node. It really makes sense to have a +table as property because that way we can store more. But in order for that to +work well you need to do it this way: + +\starttyping +\directlua { + local n = node.new("glyph") + + local t = node.getproperty(n) + + if not t then + t = { } + node.setproperty(n,t) + end + t.one = "foo" + t.two = "bar" + + print(node.getproperty(n).one) + print(node.getproperty(n).two) + + node.free(n) +} +\stoptyping + +Here our own properties will not overwrite other users properties unless of +course they use the same keys. So, eventually you will end up with something: + +\starttyping +\directlua { + local n = node.new("glyph") + + local t = node.getproperty(n) + + if not t then + t = { } + node.setproperty(n,t) + end + t.myself = { one = "foo", two = "bar" } + + print(node.getproperty(n).myself.one) + print(node.getproperty(n).myself.two) + + node.free(n) +} +\stoptyping + +This assumes that only you use \type {myself} as subtable. The possibilities are +endless but care is needed. For instance, the generic font handler that ships +with \CONTEXT\ uses the \type {injections} subtable and you should not mess with +that one! + +There are a few helper functions that you normally should not touch as user: \typ +{flush_properties_table} will wipe the table (normally a bad idea), \typ +{get_properties_table} and will give the table that stores properties (using +direct entries) and you can best not mess too much with that one either because +\LUATEX\ itself will make sure that entries related to nodes will get wiped when +nodes get freed, so that the \LUA\ garbage collector can do its job. In fact, the +main reason why we have this mechanism is that it saves the user (or macro +package) some work. One can easily write a property mechanism in \LUA\ where +after a shipout properties gets cleaned up but it's not entirely trivial to make +sure that with each freed node also its properties get freed, due to the fact +that there can be nodes left over for a next page. And having a callback bound to +the node deallocator would add way to much overhead. + +When we copy a node list that has a table as property, there are several +possibilities: we do the same as a new node, we copy the entry to the table in +properties (a reference), we do a deep copy of a table in the properties, we +create a new table and give it the original one as a metatable. After some +experiments (that also included timing) with these scenarios we decided that a +deep copy made no sense, nor did nilling. In the end both the shallow copy and +the metatable variant were both ok, although the second one is slower. The most +important aspect to keep in mind is that references to other nodes in properties +no longer can be valid for that copy. We could use two tables (one unique and one +shared) or metatables but that only complicates matters. + +When defining a new node, we could already allocate a table but it is rather easy +to do that at the lua end e.g.\ using a metatable \type {__index} method. That +way it is under macro package control. When deleting a node, we could keep the +slot (e.g. setting it to false) but it could make memory consumption raise +unneeded when we have temporary large node lists and after that only small lists. +Both are not done. + +So in the end this is what happens now: when a node is copied, and it has a table +as property, the new node will share that table. If the second argument of \typ +{set_properties_mode} is \type {true} then a metatable approach is chosen: the +copy gets its own table with the original table as metatable. If you use the +generic font loader the mode is enabled that way. + +A few more xperiments were done. For instance: copy attributes to the properties +so that we have fast access at the \LUA\ end. In the end the overhead is not +compensated by speed and convenience, in fact, attributes are not that slow when +it comes to accessing them. So this was rejected. + +Another experiment concerned a bitset in the node but again the gain compared to +attributes was neglectable and given the small amount of available bits it also +demands a pretty strong agreement over what bit represents what, and this is +unlikely to succeed in the \TEX\ community. It doesn't pay off. + +Just in case one wonders why properties make sense: it is not so much speed that +we gain, but more convenience: storing all kind of (temporary) data in attributes +is no fun and this mechanism makes sure that properties are cleaned up when a +node is freed. Also, the advantage of a more or less global properties table is +that we stay at the \LUA\ end. An alternative is to store a reference in the node +itself but that is complicated by the fact that the register has some limitations +(no numeric keys) and we also don't want to mess with it too much. + +\stopsection + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/luametatex/luametatex-pdf.tex b/doc/context/sources/general/manuals/luametatex/luametatex-pdf.tex new file mode 100644 index 000000000..3e2150053 --- /dev/null +++ b/doc/context/sources/general/manuals/luametatex/luametatex-pdf.tex @@ -0,0 +1,565 @@ +% language=uk + +% lua.newtable + +\environment luametatex-style + +\startcomponent luametatex-pdf + +\startchapter[reference=pdf,title={The \PDF\ related libraries}] + +\startsection[title={The \type {pdfe} library}][library=pdfe] + +\startsubsection[title={Introduction}] + +\topicindex{\PDF+objects} + +\topicindex{\PDF+analyze} +\topicindex{\PDF+\type{pdfe}} + +The \type {pdfe} library replaces the \type {epdf} library and provides an +interface to \PDF\ files. It uses the same code as is used for \PDF\ image +inclusion. The \type {pplib} library by Paweł Jackowski replaces the \type +{poppler} (derived from \type {xpdf}) library. + +A \PDF\ file is basically a tree of objects and one descends into the tree via +dictionaries (key/value) and arrays (index/value). There are a few topmost +dictionaries that start at root that are accessed more directly. + +Although everything in \PDF\ is basically an object we only wrap a few in so +called userdata \LUA\ objects. + +\starttabulate[|l|l|] +\DB type \BC mapping \NC \NR +\TB +\BC \PDF \BC \LUA \NC \NR +\NC null \NC nil \NC \NR +\NC boolean \NC boolean \NC \NR +\NC integer \NC integer \NC \NR +\NC float \NC number \NC \NR +\NC name \NC string \NC \NR +\NC string \NC string \NC \NR +\NC array \NC array userdatum \NC \NR +\NC dictionary \NC dictionary userdatum \NC \NR +\NC stream \NC stream userdatum (with related dictionary) \NC \NR +\NC reference \NC reference userdatum \NC \NR +\LL +\stoptabulate + +The regular getters return these \LUA\ data types but one can also get more +detailed information. + +\stopsubsection + +\startsubsection[title={\type {open}, \type {openfile}, \type {new}, \type {getstatus}, \type {close}, \type {unencrypt}}] + +\libindex {open} +\libindex {new} +\libindex {new} +\libindex {getstatus} +\libindex {close} +\libindex {unencrypt} + +A document is loaded from a file (by name or handle) or string: + +\starttyping + = pdfe.open(filename) + = pdfe.openfile(filehandle) + = pdfe.new(somestring,somelength) +\stoptyping + +Such a document is closed with: + +\starttyping +pdfe.close() +\stoptyping + +You can check if a document opened well by: + +\starttyping +pdfe.getstatus() +\stoptyping + +The returned codes are: + +\starttabulate[|c|l|] +\DB value \BC explanation \NC \NR +\TB +\NC \type {-2} \NC the document failed to open \NC \NR +\NC \type {-1} \NC the document is (still) protected \NC \NR +\NC \type {0} \NC the document is not encrypted \NC \NR +\NC \type {2} \NC the document has been unencrypted \NC \NR +\LL +\stoptabulate + +An encrypted document can be unencrypted by the next command where instead of +either password you can give \type {nil}: + +\starttyping +pdfe.unencrypt(,userpassword,ownerpassword) +\stoptyping + +\stopsubsection + +\startsubsection[title={\type {getsize}, \type {getversion}, \type {getnofobjects}, \type {getnofpages}}] + +\libindex {getsize} +\libindex {getversion} +\libindex {getnofobjects} +\libindex {getnofpages} + +A successfully opened document can provide some information: + +\starttyping +bytes = getsize() +major, minor = getversion() +n = getnofobjects() +n = getnofpages() +bytes, waste = getnofpages() +\stoptyping + +\stopsubsection + +\startsubsection[title={\type {get[catalog|trailer|info]}}] + +\libindex {getcatalog} +\libindex {gettrailer} +\libindex {getinfo} + +For accessing the document structure you start with the so called catalog, a +dictionary: + +\starttyping + = pdfe.getcatalog() +\stoptyping + +The other two root dictionaries are accessed with: + +\starttyping + = pdfe.gettrailer() + = pdfe.getinfo() +\stoptyping + +\stopsubsection + +\startsubsection[title={\type {getpage}, \type {getbox}}] + +\libindex {getpage} +\libindex {getbox} + +A specific page can conveniently be reached with the next command, which +returns a dictionary. The first argument is to be a page dictionary. + +\starttyping + = pdfe.getpage(,pagenumber) +\stoptyping + +Another convenience command gives you the (bounding) box of a (normally page) +which can be inherited from the document itself. An example of a valid box name +is \type {MediaBox}. + +\starttyping +pages = pdfe.getbox(,boxname) +\stoptyping + +\stopsubsection + +\startsubsection[title={\type {get[string|integer|number|boolean|name]}}] + +\libindex {getstring} +\libindex {getinteger} +\libindex {getnumber} +\libindex {getboolean} +\libindex {getname} + +Common values in dictionaries and arrays are strings, integers, floats, booleans +and names (which are also strings) and these are also normal \LUA\ objects: + +\starttyping +s = getstring (,index|key) +i = getinteger(,index|key) +n = getnumber (,index|key) +b = getboolean(,index|key) +n = getname (,index|key) +\stoptyping + +\stopsubsection + +\startsubsection[title={\type {get[from][dictionary|array|stream]}}] + +\libindex {getdictionary} \libindex {getfromdictionary} +\libindex {getarray} \libindex {getfromarray} +\libindex {getstream} \libindex {getfromstream} + +Normally you will use an index in an array and key in a dictionary but dictionaries +also accept an index. The size of an array or dictionary is available with the +usual \type {#} operator. + +\starttyping + = getdictionary(,index|key) + = getarray (,index|key) +, + = getstream (,index|key) +\stoptyping + +These commands return dictionaries, arrays and streams, which are dictionaries +with a blob of data attached. + +Before we come to an alternative access mode, we mention that the objects provide +access in a different way too, for instance this is valid: + +\starttyping +print(pdfe.open("foo.pdf").Catalog.Type) +\stoptyping + +At the topmost level there are \type {Catalog}, \type {Info}, \type {Trailer} +and \type {Pages}, so this is also okay: + +\starttyping +print(pdfe.open("foo.pdf").Pages[1]) +\stoptyping + +\stopsubsection + +\startsubsection[title={\type {[open|close|readfrom|whole|]stream}}] + +\libindex {openstream} +\libindex {closestream} +\libindex {readfromstream} +\libindex {readfromwholestream} + +Streams are sort of special. When your index or key hits a stream you get back a +stream object and dictionary object. The dictionary you can access in the usual +way and for the stream there are the following methods: + +\starttyping +okay = openstream(,[decode]) + closestream() +str, n = readfromstream() +str, n = readwholestream(,[decode]) +\stoptyping + +You either read in chunks, or you ask for the whole. When reading in chunks, you +need to open and close the stream yourself. The \type {n} value indicates the +length read. The \type {decode} parameter controls if the stream data gets +uncompressed. + +As with dictionaries, you can access fields in a stream dictionary in the usual +\LUA\ way too. You get the content when you \quote {call} the stream. You can +pass a boolean that indicates if the stream has to be decompressed. + +% pdfe.objectcodes = objectcodes +% pdfe.stringcodes = stringcodes +% pdfe.encryptioncodes = encryptioncodes + +\stopsubsection + +\startsubsection[title={\type {getfrom[dictionary|array]}}] + +\libindex {getfromdictionary} +\libindex {getfromarray} + +In addition to the interface described before, there is also a bit lower level +interface available. + +\starttyping +key, type, value, detail = getfromdictionary(,index) +type, value, detail = getfromarray(,index) +\stoptyping + +\starttabulate[|c|l|l|l|] +\DB type \BC meaning \BC value \BC detail \NC \NR +\NC \type {0} \NC none \NC nil \NC \NC \NR +\NC \type {1} \NC null \NC nil \NC \NC \NR +\NC \type {2} \NC boolean \NC boolean \NC \NC \NR +\NC \type {3} \NC integer \NC integer \NC \NC \NR +\NC \type {4} \NC number \NC float \NC \NC \NR +\NC \type {5} \NC name \NC string \NC \NC \NR +\NC \type {6} \NC string \NC string \NC hex \NC \NR +\NC \type {7} \NC array \NC arrayobject \NC size \NC \NR +\NC \type {8} \NC dictionary \NC dictionaryobject \NC size \NC \NR +\NC \type {9} \NC stream \NC streamobject \NC dictionary size \NC \NR +\NC \type {10} \NC reference \NC integer \NC \NC \NR +\LL +\stoptabulate + +A \type {hex} string is (in the \PDF\ file) surrounded by \type {<>} while plain +strings are bounded by \type {<>}. + +\stopsubsection + +\startsubsection[title={\type {[dictionary|array]totable}}] + +\libindex {dictionarytotable} +\libindex {arraytotable} + +All entries in a dictionary or table can be fetched with the following commands +where the return values are a hashed or indexed table. + +\starttyping +hash = dictionarytotable() +list = arraytotable() +\stoptyping + +You can get a list of pages with: + +\starttyping +{ { , size, objnum }, ... } = pagestotable() +\stoptyping + +\stopsubsection + +\startsubsection[title={\type {getfromreference}}] + +\libindex {getfromreference} + +Because you can have unresolved references, a reference object can be resolved +with: + +\starttyping +type, , detail = getfromreference() +\stoptyping + +So, as second value you get back a new \type {pdfe} userdata object that you can +query. + +\stopsubsection + +\stopsection + +\startsection[title={Memory streams}][library=pdfe] + +\topicindex{\PDF+memory streams} + +\libindex {new} + +The \type {pdfe.new} that takes three arguments: + +\starttabulate +\DB value \BC explanation \NC \NR +\TB +\NC \type {stream} \NC this is a (in low level \LUA\ speak) light userdata + object, i.e.\ a pointer to a sequence of bytes \NC \NR +\NC \type {length} \NC this is the length of the stream in bytes (the stream can + have embedded zeros) \NC \NR +\NC \type {name} \NC optional, this is a unique identifier that is used for + hashing the stream, so that multiple doesn't use more + memory \NC \NR +\LL +\stoptabulate + +The third argument is optional. When it is not given the function will return an +\type {pdfe} document object as with a regular file, otherwise it will return a +filename that can be used elsewhere (e.g.\ in the image library) to reference the +stream as pseudo file. + +Instead of a light userdata stream (which is actually fragile but handy when you +come from a library) you can also pass a \LUA\ string, in which case the given +length is (at most) the string length. + +The function returns an \type {pdfe} object and a string. The string can be used in +the \type {img} library instead of a filename. You need to prevent garbage +collection of the object when you use it as image (for instance by storing it +somewhere). + +Both the memory stream and it's use in the image library is experimental and can +change. In case you wonder where this can be used: when you use the swiglib +library for \type {graphicmagick}, it can return such a userdata object. This +permits conversion in memory and passing the result directly to the backend. This +might save some runtime in one|-|pass workflows. This feature is currently not +meant for production and we might come up with a better implementation. + +\stopsection + +\startsection[title={The \type {pdfscanner} library}][library=pdfscanner] + +This library is not available in \LUAMETATEX. + +\stopsection + +% \startsection[title={The \type {pdfscanner} library}][library=pdfscanner] +% +% \topicindex{\PDF+scanner} +% +% \libindex {scan} +% +% The \type {pdfscanner} library allows interpretation of \PDF\ content streams and +% \type {/ToUnicode} (cmap) streams. You can get those streams from the \type +% {pdfe} library, as explained in an earlier section. There is only a single +% top|-|level function in this library: +% +% \startfunctioncall +% pdfscanner.scan (,
operatortable,
info) +% pdfscanner.scan (,
operatortable,
info) +% pdfscanner.scan (,
operatortable,
info) +% \stopfunctioncall +% +% The first argument should be a \LUA\ string or a stream or array onject coming +% from the \type {pdfe} library. The second argument, \type {operatortable}, should +% be a \LUA\ table where the keys are \PDF\ operator name strings and the values +% are \LUA\ functions (defined by you) that are used to process those operators. +% The functions are called whenever the scanner finds one of these \PDF\ operators +% in the content stream(s). The functions are called with two arguments: the \type +% {scanner} object itself, and the \type {info} table that was passed are the third +% argument to \type {pdfscanner.scan}. +% +% Internally, \type {pdfscanner.scan} loops over the \PDF\ operators in the +% stream(s), collecting operands on an internal stack until it finds a \PDF\ +% operator. If that \PDF\ operator's name exists in \type {operatortable}, then the +% associated function is executed. After the function has run (or when there is no +% function to execute) the internal operand stack is cleared in preparation for the +% next operator, and processing continues. +% +% The \type {scanner} argument to the processing functions is needed because it +% offers various methods to get the actual operands from the internal operand +% stack. +% +% A simple example of processing a \PDF's document stream could look like this: +% +% \starttyping +% local operatortable = { } +% +% operatortable.Do = function(scanner,info) +% local resources = info.resources +% if resources then +% local val = scanner:pop() +% local name = val[2] +% local xobject = resources.XObject +% print(info.space .. "Uses XObject " .. name) +% local resources = xobject.Resources +% if resources then +% local newinfo = { +% space = info.space .. " ", +% resources = resources, +% } +% pdfscanner.scan(entry, operatortable, newinfo) +% end +% end +% end +% +% local function Analyze(filename) +% local doc = pdfe.open(filename) +% if doc then +% local pages = doc.Pages +% for i=1,#pages do +% local page = pages[i] +% local info = { +% space = " " , +% resources = page.Resources, +% } +% print("Page " .. i) +% -- pdfscanner.scan(page.Contents,operatortable,info) +% pdfscanner.scan(page.Contents(),operatortable,info) +% end +% end +% end +% +% Analyze("foo.pdf") +% \stoptyping +% +% This example iterates over all the actual content in the \PDF, and prints out the +% found \type {XObject} names. While the code demonstrates quite some of the \type +% {pdfe} functions, let's focus on the type \type {pdfscanner} specific code +% instead. +% +% From the bottom up, the following line runs the scanner with the \PDF\ page's +% top|-|level content given in the first argument. +% +% The third argument, \type {info}, contains two entries: \type {space} is used to +% indent the printed output, and \type {resources} is needed so that embedded \type +% {XForms} can find their own content. +% +% The second argument, \type {operatortable} defines a processing function for a +% single \PDF\ operator, \type {Do}. +% +% The function \type {Do} prints the name of the current \type {XObject}, and then +% starts a new scanner for that object's content stream, under the condition that +% the \type {XObject} is in fact a \type {/Form}. That nested scanner is called +% with new \type {info} argument with an updated \type {space} value so that the +% indentation of the output nicely nests, and with a new \type {resources} field +% to help the next iteration down to properly process any other, embedded \type +% {XObject}s. +% +% Of course, this is not a very useful example in practice, but for the purpose of +% demonstrating \type {pdfscanner}, it is just long enough. It makes use of only +% one \type {scanner} method: \type {scanner:pop()}. That function pops the top +% operand of the internal stack, and returns a \LUA\ table where the object at index +% one is a string representing the type of the operand, and object two is its +% value. +% +% The list of possible operand types and associated \LUA\ value types is: +% +% \starttabulate[|l|l|] +% \DB types \BC type \NC \NR +% \TB +% \NC \type{integer} \NC \NC \NR +% \NC \type{real} \NC \NC \NR +% \NC \type{boolean} \NC \NC \NR +% \NC \type{name} \NC \NC \NR +% \NC \type{operator} \NC \NC \NR +% \NC \type{string} \NC \NC \NR +% \NC \type{array} \NC
\NC \NR +% \NC \type{dict} \NC
\NC \NR +% \LL +% \stoptabulate +% +% In case of \type {integer} or \type {real}, the value is always a \LUA\ (floating +% point) number. In case of \type {name}, the leading slash is always stripped. +% +% In case of \type {string}, please bear in mind that \PDF\ actually supports +% different types of strings (with different encodings) in different parts of the +% \PDF\ document, so you may need to reencode some of the results; \type {pdfscanner} +% always outputs the byte stream without reencoding anything. \type {pdfscanner} +% does not differentiate between literal strings and hexadecimal strings (the +% hexadecimal values are decoded), and it treats the stream data for inline images +% as a string that is the single operand for \type {EI}. +% +% In case of \type {array}, the table content is a list of \type {pop} return +% values and in case of \type {dict}, the table keys are \PDF\ name strings and the +% values are \type {pop} return values. +% +% \libindex{pop} +% \libindex{popnumber} +% \libindex{popname} +% \libindex{popstring} +% \libindex{poparray} +% \libindex{popdictionary} +% \libindex{popboolean} +% \libindex{done} +% +% There are a few more methods defined that you can ask \type {scanner}: +% +% \starttabulate[|l|p|] +% \DB method \BC explanation \NC \NR +% \TB +% \NC \type{pop} \NC see above \NC \NR +% \NC \type{popnumber} \NC return only the value of a \type {real} or \type {integer} \NC \NR +% \NC \type{popname} \NC return only the value of a \type {name} \NC \NR +% \NC \type{popstring} \NC return only the value of a \type {string} \NC \NR +% \NC \type{poparray} \NC return only the value of a \type {array} \NC \NR +% \NC \type{popdictionary} \NC return only the value of a \type {dict} \NC \NR +% \NC \type{popboolean} \NC return only the value of a \type {boolean} \NC \NR +% \NC \type{done} \NC abort further processing of this \type {scan()} call \NC \NR +% \LL +% \stoptabulate +% +% The \type {pop*} are convenience functions, and come in handy when you know the +% type of the operands beforehand (which you usually do, in \PDF). For example, the +% \type {Do} function could have used \type {local name = scanner:popname()} +% instead, because the single operand to the \type {Do} operator is always a \PDF\ +% name object. +% +% The \type {done} function allows you to abort processing of a stream once you +% have learned everything you want to learn. This comes in handy while parsing +% \type {/ToUnicode}, because there usually is trailing garbage that you are not +% interested in. Without \type {done}, processing only ends at the end of the +% stream, possibly wasting \CPU\ cycles. +% +% {\em We keep the older names \type {popNumber}, \type {popName}, \type +% {popString}, \type {popArray}, \type {popDict} and \type {popBool} around.} +% +% \stopsection + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/luametatex/luametatex-preamble.tex b/doc/context/sources/general/manuals/luametatex/luametatex-preamble.tex new file mode 100644 index 000000000..8f1400c9f --- /dev/null +++ b/doc/context/sources/general/manuals/luametatex/luametatex-preamble.tex @@ -0,0 +1,166 @@ +% language=uk + +\environment luametatex-style + +\startcomponent luametatex-preamble + +\startchapter[reference=preamble,title={The internals}] + +\topicindex{nodes} +\topicindex{boxes} +\topicindex{\LUA} + +This is a reference manual, not a tutorial. This means that we discuss changes +relative to traditional \TEX\ and also present new functionality. As a +consequence we will refer to concepts that we assume to be known or that might be +explained later. Because the \LUATEX\ and \LUAMETATEX\ engines open up \TEX\ +there's suddenly quite some more to explain, especially about the way a (to be) +typeset stream moves through the machinery. However, discussing all that in +detail makes not much sense, because deep knowledge is only relevant for those +who write code not possible with regular \TEX\ and who are already familiar with +these internals (or willing to spend time on figuring it out). + +So, the average user doesn't need to know much about what is in this manual. For +instance fonts and languages are normally dealt with in the macro package that +you use. Messing around with node lists is also often not really needed at the +user level. If you do mess around, you'd better know what you're dealing with. +Reading \quotation {The \TEX\ Book} by Donald Knuth is a good investment of time +then also because it's good to know where it all started. A more summarizing +overview is given by \quotation {\TEX\ by Topic} by Victor Eijkhout. You might +want to peek in \quotation {The \ETEX\ manual} too. + +But \unknown\ if you're here because of \LUA, then all you need to know is that +you can call it from within a run. If you want to learn the language, just read +the well written \LUA\ book. The macro package that you use probably will provide +a few wrapper mechanisms but the basic \lpr {directlua} command that does the job +is: + +\starttyping +\directlua{tex.print("Hi there")} +\stoptyping + +You can put code between curly braces but if it's a lot you can also put it in a +file and load that file with the usual \LUA\ commands. If you don't know what +this means, you definitely need to have a look at the \LUA\ book first. + +If you still decide to read on, then it's good to know what nodes are, so we do a +quick introduction here. If you input this text: + +\starttyping +Hi There +\stoptyping + +eventually we will get a linked lists of nodes, which in \ASCII\ art looks like: + +\starttyping +H <=> i <=> [glue] <=> T <=> h <=> e <=> r <=> e +\stoptyping + +When we have a paragraph, we actually get something: + +\starttyping +[localpar] <=> H <=> i <=> [glue] <=> T <=> h <=> e <=> r <=> e <=> [glue] +\stoptyping + +Each character becomes a so called glyph node, a record with properties like the +current font, the character code and the current language. Spaces become glue +nodes. There are many node types that we will discuss later. Each node points +back to a previous node or next node, given that these exist. Sometimes +multiple characters are represented by one glyphs, so one can also get: + +\starttyping +[localpar] <=> H <=> i <=> [glue] <=> Th <=> e <=> r <=> e <=> [glue] +\stoptyping + +And maybe some characters get positioned relative to each other, so we might +see: + +\starttyping +[localpar] <=> H <=> [kern] <=> i <=> [glue] <=> Th <=> e <=> r <=> e <=> [glue] +\stoptyping + +It's also good to know beforehand that \TEX\ is basically centered around +creating paragraphs and pages. The par builder takes a list and breaks it into +lines. At some point horizontal blobs are wrapped into vertical ones. Lines are +so called boxes and can be separated by glue, penalties and more. The page +builder accumulates lines and when feasible triggers an output routine that will +take the list so far. Constructing the actual page is not part of \TEX\ but done +using primitives that permit manipulation of boxes. The result is handled back to +\TEX\ and flushed to a (often \PDF) file. + +The \LUATEX\ engine provides hooks for \LUA\ code at nearly every reasonable +point in the process: collecting content, hyphenating, applying font features, +breaking into lines, etc. This means that you can overload \TEX's natural +behaviour, which still is the benchmark. When we refer to \quote {callbacks} we +means these hooks. The \TEX\ engine itself is pretty well optimized but when you +kick in much \LUA\ code, you will notices that performance drops. Don't blame and +bother the authors with performance issues. In \CONTEXT\ over 50\% of the time +can be spent in \LUA, but so far we didn't get many complaints about efficiency. + +Where plain \TEX\ is basically a basic framework for writing a specific style, +macro packages like \CONTEXT\ and \LATEX\ provide the user a whole lot of +additional tools to make documents look good. They hide the dirty details of font +management, language demands, turning structure into typeset results, wrapping +pages, including images, and so on. You should be aware of the fact that when you +hook in your own code to manipulate lists, this can interfere with the macro +package that you use. Each successive step expects a certain result and if you +mess around to much, the engine eventually might bark and quit. It can even +crash, because testing everywhere for what users can do wrong is no real option. + +When you read about nodes in the following chapters it's good to keep in mind +their commands that relate to then. Here are a few: + +\starttabulate[|l|l|p|] +\DB command \BC node \BC explanation \NC \NR +\TB +\NC \prm {hbox} \NC \nod {hlist} \NC horizontal box \NC \NR +\NC \prm {vbox} \NC \nod {vlist} \NC vertical box with the baseline at the bottom \NC \NR +\NC \prm {vtop} \NC \nod {vlist} \NC vertical box with the baseline at the top \NC \NR +\NC \prm {hskip} \NC \nod {glue} \NC horizontal skip with optional stretch and shrink \NC \NR +\NC \prm {vskip} \NC \nod {glue} \NC vertical skip with optional stretch and shrink \NC \NR +\NC \prm {kern} \NC \nod {kern} \NC horizontal or vertical fixed skip \NC \NR +\NC \prm {discretionary} \NC \nod {disc} \NC hyphenation point (pre, post, replace) \NC \NR +\NC \prm {char} \NC \nod {glyph} \NC a character \NC \NR +\NC \prm {hrule} \NC \nod {rule} \NC a horizontal rule \NC \NR +\NC \prm {vrule} \NC \nod {rule} \NC a vertical rule \NC \NR +\NC \prm {textdirection} \NC \nod {dir} \NC a change in text direction \NC \NR +\LL +\stoptabulate + +Text (interspersed with macros) comes from an input medium. This can be a file, +token list, macro body cq.\ arguments, \ some internal quantity (like a number), +\LUA, etc. Macros get expanded. In the process \TEX\ can enter a group. Inside +the group, changes to registers get saved on a stack, and restored after leaving +the group. When conditionals are encountered, another kind of nesting happens, +and again there is a stack involved. Tokens, expansion, stacks, input levels are +all terms used in the next chapters. Don't worry, they loose their magic once you +use \TEX\ a lot. You have access to most of the internals and when not, at least +it is possible to query some state we're in or level we're at. + +When we talk about packing it can mean two things. When \TEX\ has consumed some +tokens that represent text the next can happen. When the text is put into a so +called \type {\hbox} it (normally) first gets hyphenated, next ligatures are +build, and finally kerns are added. Each of that stages can be overloaded using +\LUA\ code. When these three stages are finished, the dimension of the content is +calculated and the box gets its width, height and depth. What happens with the +box depends on what macros do with it. + +The other thing that can happen is that the text starts a new paragraph. In that +case some (directional) information is put in front, indentation is prepended and +some skip appended at the end. Again the three stages are applied but this time, +afterwards, the long line is broken into lines and the result is either added to +the content of a box or to the main vertical list (the running text so to say). +This is called par building. At some point \TEX\ decides that enough is enough +and it will trigger the page builder. So, building is another concept we will +encounter. Another example of a builder is the one that turns an intermediate +math list into something typeset. + +Wrapping something in a box is called packing. Adding something to a list is +described in terms of contributing. The more complicated processes are wrapped +into builders. For now this should be enough to enable you to understand the next +chapters. The text is not as enlightening and entertaining as Don Knuths books, +sorry. + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/luametatex/luametatex-primitives.tex b/doc/context/sources/general/manuals/luametatex/luametatex-primitives.tex new file mode 100644 index 000000000..5c4724100 --- /dev/null +++ b/doc/context/sources/general/manuals/luametatex/luametatex-primitives.tex @@ -0,0 +1,392 @@ +% language=uk + +\environment luametatex-style + +\startcomponent luametatex-primitives + +\startchapter[reference=primitives,title={Primitives aka commands}] + +\startsection[title=Introduction] + +The starting point of \LUATEX\ is \PDFTEX, which itself contains regular \TEX\ +and \ETEX. Because directional support was needed we also took some code from +\ALEPH\ (\OMEGA). In a later stage the backend specific commands were isolated in +its own namespace which resulted in a cleaner code base where the backend code no +longer was interwoven with the normal frontend primitives. We also promoted some +generic constructs (like box resources and directions) to core functionality. + +Some of the \PDFTEX\ support primitives have been around from the start but when +\LUA\ integration became better and when a token scanner library was added, not +all of those made sense as primitives. In previous chapters we already mentioned +what is gone from the core. Deep down some more has changes but not all is +reflected at the primitive level. Because there is still a considerable amount of +new primitives, a summary is given below. + +\stopsection + +\startsection[title=Languages] + +\starttabulate[|||p|] +\NC \type {automatichyphenmode} \NC integer \NC \NC \NR +\NC \type {automatichyphenpenalty} \NC integer \NC \NC \NR +\NC \type {hyphenpenaltymode} \NC integer \NC \NC \NR +\NC \type {compoundhyphenmode} \NC integer \NC \NC \NR +\NC \type {exceptionpenalty} \NC integer \NC \NC \NR +\NC \type {explicithyphenpenalty} \NC integer \NC \NC \NR +\NC \type {hyphenationbounds} \NC integer \NC \NC \NR +\NC \type {hjcode} \NC charactercode \NC \NC \NR +\NC \type {hyphenationmin} \NC charactercode \NC \NC \NR +\NC \type {postexhyphenchar} \NC charactercode \NC \NC \NR +\NC \type {posthyphenchar} \NC charactercode \NC \NC \NR +\NC \type {preexhyphenchar} \NC charactercode \NC \NC \NR +\NC \type {prehyphenchar} \NC charactercode \NC \NC \NR +\stoptabulate + +\stopsection + +\startsection[title=Fonts] + +\starttabulate[|||p|] +\NC \type {tracingfonts} \NC integer \NC \NC \NR +\NC \type {suppressfontnotfounderror} \NC integer \NC \NC \NR +\NC \type {setfontid} \NC integer \NC \NC \NR +\NC \type {fontid} \NC font \NC \NC \NR +\NC \type {efcode} \NC font charactercode \NC \NC \NR +\NC \type {lpcode} \NC font charactercode \NC \NC \NR +\NC \type {rpcode} \NC font charactercode \NC \NC \NR +\stoptabulate + +\stopsection + +\startsection[title=Math] + +\starttabulate[|||p|] +\NC \type {matholdmode} \NC integer \NC \NC \NR +\NC \type {mathstyle} \NC integer \NC \NC \NR +\NC \type {matheqnogapstep} \NC integer \NC \NC \NR +\NC \type {Uskewed} \NC \NC \NC \NR +\NC \type {Uskewedwithdelims} \NC \NC \NC \NR +\NC \type {Ustartdisplaymath} \NC \NC \NC \NR +\NC \type {Ustartmath} \NC \NC \NC \NR +\NC \type {Ustopdisplaymath} \NC \NC \NC \NR +\NC \type {Ustopmath} \NC \NC \NC \NR +\NC \type {crampeddisplaystyle} \NC \NC \NC \NR +\NC \type {crampedtextstyle} \NC \NC \NC \NR +\NC \type {crampedscriptstyle} \NC \NC \NC \NR +\NC \type {crampedscriptscriptstyle} \NC \NC \NC \NR +\NC \type {Umathchardef} \NC \NC \NC \NR +\NC \type {Umathcharnumdef} \NC \NC \NC \NR +\NC \type {mathdisplayskipmode} \NC integer \NC \NC \NR +\NC \type {mathscriptsmode} \NC integer \NC \NC \NR +\NC \type {mathnolimitsmode} \NC integer \NC \NC \NR +\NC \type {mathitalicsmode} \NC integer \NC \NC \NR +\NC \type {mathrulesmode} \NC integer \NC \NC \NR +\NC \type {mathrulesfam} \NC integer \NC \NC \NR +\NC \type {mathdelimitersmode} \NC integer \NC \NC \NR +\NC \type {mathflattenmode} \NC integer \NC \NC \NR +\NC \type {mathpenaltiesmode} \NC integer \NC \NC \NR +\NC \type {mathrulethicknessmode} \NC integer \NC \NC \NR +\NC \type {mathscriptboxmode} \NC integer \NC \NC \NR +\NC \type {mathscriptcharmode} \NC integer \NC \NC \NR +\NC \type {mathsurroundmode} \NC integer \NC \NC \NR +\NC \type {nokerns} \NC integer \NC \NC \NR +\NC \type {noligs} \NC integer \NC \NC \NR +\NC \type {prebinoppenalty} \NC integer \NC \NC \NR +\NC \type {predisplaygapfactor} \NC integer \NC \NC \NR +\NC \type {prerelpenalty} \NC integer \NC \NC \NR +\NC \type {Usuperscript} \NC command \NC \NC \NR +\NC \type {Usubscript} \NC command \NC \NC \NR +\NC \type {Unosuperscript} \NC command \NC \NC \NR +\NC \type {Unosubscript} \NC command \NC \NC \NR +\NC \type {Umathcode} \NC \NC \NC \NR +\NC \type {Umathcodenum} \NC \NC \NC \NR +\NC \type {Udelcode} \NC \NC \NC \NR +\NC \type {Udelcodenum} \NC \NC \NC \NR +\NC \type {Umathaxis} \NC family dimension \NC \NC \NR +\NC \type {Umathbinbinspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathbinclosespacing} \NC family dimension \NC \NC \NR +\NC \type {Umathbininnerspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathbinopenspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathbinopspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathbinordspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathbinpunctspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathbinrelspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathclosebinspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathcloseclosespacing} \NC family dimension \NC \NC \NR +\NC \type {Umathcloseinnerspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathcloseopenspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathcloseopspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathcloseordspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathclosepunctspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathcloserelspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathconnectoroverlapmin} \NC family dimension \NC \NC \NR +\NC \type {Umathfractiondelsize} \NC family dimension \NC \NC \NR +\NC \type {Umathfractiondenomdown} \NC family dimension \NC \NC \NR +\NC \type {Umathfractiondenomvgap} \NC family dimension \NC \NC \NR +\NC \type {Umathfractionnumup} \NC family dimension \NC \NC \NR +\NC \type {Umathfractionnumvgap} \NC family dimension \NC \NC \NR +\NC \type {Umathfractionrule} \NC family dimension \NC \NC \NR +\NC \type {Umathinnerbinspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathinnerclosespacing} \NC family dimension \NC \NC \NR +\NC \type {Umathinnerinnerspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathinneropenspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathinneropspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathinnerordspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathinnerpunctspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathinnerrelspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathlimitabovebgap} \NC family dimension \NC \NC \NR +\NC \type {Umathlimitabovekern} \NC family dimension \NC \NC \NR +\NC \type {Umathlimitabovevgap} \NC family dimension \NC \NC \NR +\NC \type {Umathlimitbelowbgap} \NC family dimension \NC \NC \NR +\NC \type {Umathlimitbelowkern} \NC family dimension \NC \NC \NR +\NC \type {Umathlimitbelowvgap} \NC family dimension \NC \NC \NR +\NC \type {Umathnolimitsubfactor} \NC family dimension \NC \NC \NR +\NC \type {Umathnolimitsupfactor} \NC family dimension \NC \NC \NR +\NC \type {Umathopbinspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathopclosespacing} \NC family dimension \NC \NC \NR +\NC \type {Umathopenbinspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathopenclosespacing} \NC family dimension \NC \NC \NR +\NC \type {Umathopeninnerspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathopenopenspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathopenopspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathopenordspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathopenpunctspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathopenrelspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathoperatorsize} \NC family dimension \NC \NC \NR +\NC \type {Umathopinnerspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathopopenspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathopopspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathopordspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathoppunctspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathoprelspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathordbinspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathordclosespacing} \NC family dimension \NC \NC \NR +\NC \type {Umathordinnerspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathordopenspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathordopspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathordordspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathordpunctspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathordrelspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathoverbarkern} \NC family dimension \NC \NC \NR +\NC \type {Umathoverbarrule} \NC family dimension \NC \NC \NR +\NC \type {Umathoverbarvgap} \NC family dimension \NC \NC \NR +\NC \type {Umathoverdelimiterbgap} \NC family dimension \NC \NC \NR +\NC \type {Umathoverdelimitervgap} \NC family dimension \NC \NC \NR +\NC \type {Umathpunctbinspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathpunctclosespacing} \NC family dimension \NC \NC \NR +\NC \type {Umathpunctinnerspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathpunctopenspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathpunctopspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathpunctordspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathpunctpunctspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathpunctrelspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathquad} \NC family dimension \NC \NC \NR +\NC \type {Umathradicaldegreeafter} \NC family dimension \NC \NC \NR +\NC \type {Umathradicaldegreebefore} \NC family dimension \NC \NC \NR +\NC \type {Umathradicaldegreeraise} \NC family dimension \NC \NC \NR +\NC \type {Umathradicalkern} \NC family dimension \NC \NC \NR +\NC \type {Umathradicalrule} \NC family dimension \NC \NC \NR +\NC \type {Umathradicalvgap} \NC family dimension \NC \NC \NR +\NC \type {Umathrelbinspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathrelclosespacing} \NC family dimension \NC \NC \NR +\NC \type {Umathrelinnerspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathrelopenspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathrelopspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathrelordspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathrelpunctspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathrelrelspacing} \NC family dimension \NC \NC \NR +\NC \type {Umathskewedfractionhgap} \NC family dimension \NC \NC \NR +\NC \type {Umathskewedfractionvgap} \NC family dimension \NC \NC \NR +\NC \type {Umathspaceafterscript} \NC family dimension \NC \NC \NR +\NC \type {Umathstackdenomdown} \NC family dimension \NC \NC \NR +\NC \type {Umathstacknumup} \NC family dimension \NC \NC \NR +\NC \type {Umathstackvgap} \NC family dimension \NC \NC \NR +\NC \type {Umathsubshiftdown} \NC family dimension \NC \NC \NR +\NC \type {Umathsubshiftdrop} \NC family dimension \NC \NC \NR +\NC \type {Umathsubsupshiftdown} \NC family dimension \NC \NC \NR +\NC \type {Umathsubsupvgap} \NC family dimension \NC \NC \NR +\NC \type {Umathsubtopmax} \NC family dimension \NC \NC \NR +\NC \type {Umathsupbottommin} \NC family dimension \NC \NC \NR +\NC \type {Umathsupshiftdrop} \NC family dimension \NC \NC \NR +\NC \type {Umathsupshiftup} \NC family dimension \NC \NC \NR +\NC \type {Umathsupsubbottommax} \NC family dimension \NC \NC \NR +\NC \type {Umathunderbarkern} \NC family dimension \NC \NC \NR +\NC \type {Umathunderbarrule} \NC family dimension \NC \NC \NR +\NC \type {Umathunderbarvgap} \NC family dimension \NC \NC \NR +\NC \type {Umathunderdelimiterbgap} \NC family dimension \NC \NC \NR +\NC \type {Umathunderdelimitervgap} \NC family dimension \NC \NC \NR +\NC \type {Udelimiter} \NC \NC \NC \NR +\NC \type {Umathaccent} \NC \NC \NC \NR +\NC \type {Umathchar} \NC \NC \NC \NR +\NC \type {Umathcharnum} \NC \NC \NC \NR +\NC \type {Ustack} \NC \NC \NC \NR +\NC \type {Uradical} \NC \NC \NC \NR +\NC \type {Uroot} \NC \NC \NC \NR +\NC \type {Uunderdelimiter} \NC \NC \NC \NR +\NC \type {Uoverdelimiter} \NC \NC \NC \NR +\NC \type {Udelimiterunder} \NC \NC \NC \NR +\NC \type {Udelimiterover} \NC \NC \NC \NR +\NC \type {Uhextensible} \NC \NC \NC \NR +\NC \type {Uchar} \NC \NC \NC \NR +\NC \type {Umathcharclass} \NC \NC \NC \NR +\NC \type {Umathcharfam} \NC \NC \NC \NR +\NC \type {Umathcharslot} \NC \NC \NC \NR +\NC \type {Uleft} \NC \NC \NC \NR +\NC \type {Umiddle} \NC \NC \NC \NR +\NC \type {Uright} \NC \NC \NC \NR +\NC \type {Uvextensible} \NC \NC \NC \NR +\stoptabulate + +\stopsection + +\startsection[title=Boxes and directions] + +\starttabulate[|||p|] +\NC \type {pardirection} \NC direction \NC \NC \NR +\NC \type {textdirection} \NC direction \NC \NC \NR +\NC \type {mathdirection} \NC direction \NC \NC \NR +\NC \type {linedirection} \NC direction \NC \NC \NR +\NC \type {breakafterdirmode} \NC integer \NC \NC \NR +\NC \type {shapemode} \NC integer \NC \NC \NR +\NC \type {fixupboxesmode} \NC integer \NC \NC \NR +\NC \type {boxdirection} \NC box direction \NC \NC \NR +\NC \type {boxorientation} \NC box orientation \NC rotation over 90, 180, 270 degrees \NC \NR +\NC \type {boxxoffset} \NC box xoffset \NC leaves dimensions untounched \NC \NR +\NC \type {boxyoffset} \NC box yoffset \NC leaves dimensions untounched \NC \NR +\NC \type {boxxmove} \NC box xmove \NC offsets that reflect on dimensions \NC \NR +\NC \type {boxymove} \NC box ymove \NC offsets that reflect on dimensions \NC \NR +\NC \type {boxtotal} \NC box ht+dp \NC height plus depth (and when assigned halfs) \NC \NR +\NC \type {boxattr} \NC box attr value \NC (sets) a specific attribute to a value \NC \NR +\stoptabulate + +\stopsection + +\startsection[title=Scanning] + +\starttabulate[|||p|] +\NC \type {aftergrouped} \NC text \NC like aftergroup but for given list \NC \NR +\NC \type {alignmark} \NC \NC equivalent to hash token \NC \NR +\NC \type {aligntab} \NC \NC equivalent to tab token \NC \NR +\NC \type {begincsname} \NC command \NC variant of \type {\csname} that ignores undefined commands \NC \NR +\NC \type {catcodetable} \NC integer \NC switch to catcode table \NC \NR +\NC \type {csstring} \NC command \NC the command without preceding escape character \NC \NR +\NC \type {endlocalcontrol} \NC command \NC switches back to the main control loop \NC \NR +\NC \type {etoksapp} \NC tokenregister text \NC append expanded text to given tokenregister \NC \NR +\NC \type {etokspre} \NC tokenregister text \NC prepend expanded text to given tokenregister \NC \NR +\NC \type {expanded} \NC text \NC expands the given text \NC \NR +\NC \type {frozen} \NN prefix \NC \NC \NR +\NC \type {futureexpand} \NN token command command \NC expands second ot third token depending on first match \NC \NR +\NC \type {futureexpandis} \NN token command command \NC as \type {futureexpand} but also skips pars \NC \NR +\NC \type {futureexpandisap} \NN token command command \NC same as idem but doesn't push back skipped spaces \NC \NR +\NC \type {gtoksapp} \NC tokenregister text \NC globally append text to given tokenregister \NC \NR +\NC \type {gtokspre} \NC tokenregister text \NC globally prepend text to given tokenregister \NC \NR +\NC \type {ifabsdim} \NC dimension <=> dimension \NC test the absolute value of the given dimension \NC \NR +\NC \type {ifabsnum} \NC integer <=> integer \NC test the absolute value of the given integer \NC \NR +\NC \type {ifcondition} \NC command \NC assume the next token is a test (so skip as if) \NC \NR +\NC \type {ifdimen} \NC possibly a dimension \NC acts like an \type {\ifcase} with 1 for valid and 2 for invalid \NC \NR +\NC \type {ifincsname} \NC command \NC check if we're inside a csname expansion \NC \NR +\NC \type {ifnumval} \NC \NC \NC \NR +\NC \type {ifdimval} \NC \NC \NC \NR +\NC \type {ifchknum} \NC \NC \NC \NR +\NC \type {ifchkdim} \NC \NC \NC \NR +\NC \type {ifcmpnum} \NC \NC \NC \NR +\NC \type {ifcmpdim} \NC \NC \NC \NR +\NC \type {ifusercmd} \NC command \NC \NC \NR +\NC \type {ifprotected} \NC command \NC \NC \NR +\NC \type {iffrozen} \NC command \NC \NC \NR +\NC \type {iftok} \NC \NC \NC \NR +\NC \type {ifcstok} \NC \NC \NC \NR +\NC \type {internalcodesmode} \NC integer \NC \NC \NR +%NC \type {ifprimitive} \NC command \NC check if the given command is a primitive \NC \NR +\NC \type {immediateassigned} \NC command \NC (todo) expand the following assignment now\NC \NR +\NC \type {immediateassignment} \NC command \NC (todo) expand the following assignment now\NC \NR +\NC \type {initcatcodetable} \NC integer \NC initialize catcode table \NC \NR +\NC \type {lastnamedcs} \NC command \NC last found command of \type {\ifcsname} construction \NC \NR +\NC \type {nospaces} \NC integer \NC don't inject spaces \NC \NR +%NC \type {primitive} \NC command \NC expands the next primitive equivalent \NC \NR +\NC \type {orelse} \NC condition \NC \NC \NR +\NC \type {pxdimen} \NC dimension \NC multiplier for the \type {px} unit \NC \NR +\NC \type {savecatcodetable} \NC integer \NC save catcode table \NC \NR +\NC \type {scantextokens} \NC text \NC \type {\scantokens} without file side effects \NC \NR +\NC \type {suppressifcsnameerror} \NC integer \NC recover from issues in csname testing \NC \NR +\NC \type {suppresslongerror} \NC integer \NC make \type {\long} a nop \NC \NR +\NC \type {suppressmathparerror} \NC integer \NC accepts \type {\par} and empty lines in math \NC \NR +\NC \type {suppressoutererror} \NC integer \NC make \type {\outer} a nop \NC \NR +\NC \type {suppressprimitiveerror} \NC integer \NC don't report an invalid \type {\primitive} \NC \NR +\NC \type {toksapp} \NC tokenregister text \NC append text to given tokenregister \NC \NR +\NC \type {tokspre} \NC tokenregister text \NC prepend text to given tokenregister \NC \NR +\NC \type {xtoksapp} \NC tokenregister text \NC globally append expanded text to given tokenregister \NC \NR +\NC \type {xtokspre} \NC tokenregister text \NC globally prepend expanded text to given tokenregister \NC \NR +\stoptabulate + +\stopsection + +\startsection[title=Typesetting] + +\starttabulate[|||p|] +\NC \type {protrudechars} \NC integer \NC \NC \NR +\NC \type {localbrokenpenalty} \NC integer \NC \NC \NR +\NC \type {localinterlinepenalty} \NC integer \NC \NC \NR +\NC \type {adjustspacing} \NC integer \NC \NC \NR +\NC \type {boundary} \NC command \NC \NC \NR +\NC \type {noboundary} \NC command \NC \NC \NR +\NC \type {protrusionboundary} \NC command \NC \NC \NR +\NC \type {wordboundary} \NC command \NC \NC \NR +\NC \type {leftghost} \NC charactercode \NC \NC \NR +\NC \type {rightghost} \NC charactercode \NC \NC \NR +\NC \type {nohrule} \NC command \NC \NC \NR +\NC \type {novrule} \NC command \NC \NC \NR +\NC \type {insertht} \NC number \NC \NC \NR +\NC \type {quitvmode} \NC command \NC \NC \NR +\NC \type {leftmarginkern} \NC dimension \NC \NC \NR +\NC \type {rightmarginkern} \NC dimension \NC \NC \NR +\NC \type {localleftbox} \NC box \NC \NC \NR +\NC \type {localrightbox} \NC box \NC \NC \NR +\NC \type {gleaders} \NC command \NC \NC \NR +\stoptabulate + +\stopsection + +\startsection[title=\LUA] + +\starttabulate[|||p|] +\NC \type {luacopyinputnodes} \NC integer \NC \NC \NR +\NC \type {luadef} \NC \NC \NC \NR +\NC \type {luabytecodecall} \NC \NC \NC \NR +\NC \type {luafunctioncall} \NC \NC \NC \NR +\NC \type {latelua} \NC \NC \NC \NR +\NC \type {lateluafunction} \NC \NC \NC \NR +\NC \type {luabytecode} \NC \NC \NC \NR +\NC \type {luaescapestring} \NC \NC \NC \NR +\NC \type {luafunction} \NC \NC \NC \NR +\stoptabulate + +\stopsection + +\startsection[title=Management] + +\starttabulate[|||p|] +\NC \type {outputbox} \NC integer \NC \NC \NR +\NC \type {clearmarks} \NC \NC \NC \NR +\NC \type {attribute} \NC \NC \NC \NR +\NC \type {glet} \NC \NC \NC \NR +\NC \type {letcharcode} \NC \NC \NC \NR +\NC \type {attributedef} \NC \NC \NC \NR +\stoptabulate + +\stopsection + +\startsection[title=Miscellaneous] + +\starttabulate[|||p|] +\NC \type {luatexversion} \NC \NC \NC \NR +\NC \type {formatname} \NC \NC \NC \NR +\NC \type {luatexbanner} \NC \NC \NC \NR +\NC \type {luatexrevision} \NC \NC \NC \NR +\stoptabulate + +\stopsection + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/luametatex/luametatex-registers.tex b/doc/context/sources/general/manuals/luametatex/luametatex-registers.tex new file mode 100644 index 000000000..f230a4500 --- /dev/null +++ b/doc/context/sources/general/manuals/luametatex/luametatex-registers.tex @@ -0,0 +1,47 @@ +\environment luametatex-style + +\startcomponent luametatex-registers + +\startchapter[title=Topics] + + \placeregister[topicindex] + +\stopchapter + +\startchapter[title=Primitives] + + This register contains the primitives that are mentioned in the manual. There + are of course many more primitives. The \LUATEX\ primitives are typeset in + bold. The primitives from \PDFTEX\ are not supported that way but mentioned + anyway. + + \placeregister[primitiveindex][indicator=no] + +\stopchapter + +\startchapter[title=Callbacks] + + \placeregister[callbackindex] + +\stopchapter + +\startchapter[title=Nodes] + + This register contains the nodes that are known to \LUATEX. The primary nodes + are in bold, whatsits that are determined by their subtype are normal. The + names prefixed by \type {pdf_} are backend specific. + + \placeregister[nodeindex] + +\stopchapter + +\startchapter[title=Libraries] + + This register contains the functions available in libraries. Not all functions + are documented, for instance because they can be experimental or obsolete. + + \placeregister[libraryindex] + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/luametatex/luametatex-statistics.tex b/doc/context/sources/general/manuals/luametatex/luametatex-statistics.tex new file mode 100644 index 000000000..d779a0899 --- /dev/null +++ b/doc/context/sources/general/manuals/luametatex/luametatex-statistics.tex @@ -0,0 +1,17 @@ +% language=uk + +\environment luametatex-style + +\startcomponent luametatex-statistics + +\startchapter[title={Statistics}] + + \topicindex{fonts+used} + + The following fonts are used in this document: + + \showfontusage + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/luametatex/luametatex-tex.tex b/doc/context/sources/general/manuals/luametatex/luametatex-tex.tex new file mode 100644 index 000000000..4e5a4f584 --- /dev/null +++ b/doc/context/sources/general/manuals/luametatex/luametatex-tex.tex @@ -0,0 +1,2477 @@ +% language=uk + +\environment luametatex-style + +\startcomponent luametatex-tex + +\startchapter[reference=tex,title={The \TEX\ related libraries}] + +\startsection[title={The \type {lua} library}][library=lua] + +\startsubsection[title={Version information}] + +\topicindex{libraries+\type{lua}} +\topicindex{version} +\topicindex{startupfile} + +\libindex{version} +\libindex{startupfile} + +This library contains two read|-|only items: + +\starttyping + v = lua.version + s = lua.startupfile +\stoptyping + +This returns the \LUA\ version identifier string. The value is currently +\directlua {tex.print(lua.version)}. + +\stopsubsection + +\startsubsection[title={Table allocators}] + +\topicindex{tables} + +\libindex{newtable} +\libindex{newindex} + +Sometimes performance (and memory usage) can benefit a little from +it preallocating a table with \type {newtable}: + +\starttyping +
t = lua.newtable(100,5000) +\stoptyping + +This preallocates 100 hash entries and 5000 index entries. The \type +{newindex} function create an indexed table with preset values: + +\starttyping +
t = lua.newindex(2500,true) +\stoptyping + +\stopsubsection + +\startsubsection[title={Bytecode registers}] + +\topicindex{bytecodes} +\topicindex{registers+bytecodes} + +\libindex{bytecode} +\libindex{setbytecode} +\libindex{getbytecode} + +\LUA\ registers can be used to store \LUA\ code chunks. The accepted values for +assignments are functions and \type {nil}. Likewise, the retrieved value is +either a function or \type {nil}. + +\starttyping +lua.bytecode[ n] = f +lua.bytecode[ n]() +\stoptyping + +The contents of the \type {lua.bytecode} array is stored inside the format file +as actual \LUA\ bytecode, so it can also be used to preload \LUA\ code. The +function must not contain any upvalues. The associated function calls are: + +\startfunctioncall + f = lua.getbytecode( n) +lua.setbytecode( n, f) +\stopfunctioncall + +Note: Since a \LUA\ file loaded using \type {loadfile(filename)} is essentially +an anonymous function, a complete file can be stored in a bytecode register like +this: + +\startfunctioncall +lua.bytecode[n] = loadfile(filename) +\stopfunctioncall + +Now all definitions (functions, variables) contained in the file can be +created by executing this bytecode register: + +\startfunctioncall +lua.bytecode[n]() +\stopfunctioncall + +Note that the path of the file is stored in the \LUA\ bytecode to be used in +stack backtraces and therefore dumped into the format file if the above code is +used in \INITEX. If it contains private information, i.e. the user name, this +information is then contained in the format file as well. This should be kept in +mind when preloading files into a bytecode register in \INITEX. + +\stopsubsection + +\startsubsection[title={Chunk name registers}] + +\libindex{name} +\libindex{setluaname} +\libindex{getluaname} + +There is an array of 65536 (0--65535) potential chunk names for use with the +\prm {directlua} and \lpr {latelua} primitives. + +\startfunctioncall +lua.name[ n] = s + s = lua.name[ n] +\stopfunctioncall + +If you want to unset a \LUA\ name, you can assign \type {nil} to it. The function +accessors are: + +\startfunctioncall +lua.setluaname( s, n]) + s = lua.getluaname( n) +\stopfunctioncall + +\stopsubsection + +\startsubsection[title={Introspection}] + +\libindex{getstacktop} +\libindex{getruntime} +\libindex{getcurrenttime} +\libindex{getpreciseticks} +\libindex{getpreciseseconds} + +The \type {getstacktop} function return a number indicating how full the \LUA\ +stack is. This function only makes sense as breakpoint when checking some +mechanism going haywire. + +There are four time related helpers. The \type {getruntime} function returns the +time passed since startup. The \type {getcurrenttime} does what its name says. +Just play with them to see how it pays off. The \type {getpreciseticks} returns a +number that can be used later, after a similar call, to get a difference. The +\type {getpreciseseconds} function gets such a tick (delta) as argument and +returns the number of seconds. Ticks can differ per operating system, but one +always creates a reference first and then deltas to this reference. + +\stopsubsection + +\stopsection + +\startsection[title={The \type {status} library}][library=status] + +\topicindex{libraries+\type{status}} + +\libindex{list} +\libindex{resetmessages} +\libindex{setexitcode} + +This contains a number of run|-|time configuration items that you may find useful +in message reporting, as well as an iterator function that gets all of the names +and values as a table. + +\startfunctioncall +
info = status.list() +\stopfunctioncall + +The keys in the table are the known items, the value is the current value. Almost +all of the values in \type {status} are fetched through a metatable at run|-|time +whenever they are accessed, so you cannot use \type {pairs} on \type {status}, +but you {\it can\/} use \type {pairs} on \type {info}, of course. If you do not +need the full list, you can also ask for a single item by using its name as an +index into \type {status}. The current list is: + +\starttabulate[|l|p|] +\DB key \BC explanation \NC \NR +\TB +\NC \type{banner} \NC terminal display banner \NC \NR +\NC \type{best_page_break} \NC the current best break (a node) \NC \NR +\NC \type{buf_size} \NC current allocated size of the line buffer \NC \NR +\NC \type{callbacks} \NC total number of executed callbacks so far \NC \NR +\NC \type{cs_count} \NC number of control sequences \NC \NR +\NC \type{dest_names_size} \NC \PDF\ destination table size \NC \NR +\NC \type{dvi_gone} \NC written \DVI\ bytes \NC \NR +\NC \type{dvi_ptr} \NC not yet written \DVI\ bytes \NC \NR +\NC \type{dyn_used} \NC token (multi|-|word) memory in use \NC \NR +\NC \type{filename} \NC name of the current input file \NC \NR +\NC \type{fix_mem_end} \NC maximum number of used tokens \NC \NR +\NC \type{fix_mem_min} \NC minimum number of allocated words for tokens \NC \NR +\NC \type{fix_mem_max} \NC maximum number of allocated words for tokens \NC \NR +\NC \type{font_ptr} \NC number of active fonts \NC \NR +\NC \type{hash_extra} \NC extra allowed hash \NC \NR +\NC \type{hash_size} \NC size of hash \NC \NR +\NC \type{indirect_callbacks} \NC number of those that were themselves a result of other callbacks (e.g. file readers) \NC \NR +\NC \type{ini_version} \NC \type {true} if this is an \INITEX\ run \NC \NR +\NC \type{init_pool_ptr} \NC \INITEX\ string pool index \NC \NR +\NC \type{init_str_ptr} \NC number of \INITEX\ strings \NC \NR +\NC \type{input_ptr} \NC the level of input we're at \NC \NR +\NC \type{inputid} \NC numeric id of the current input \NC \NR +\NC \type{largest_used_mark} \NC max referenced marks class \NC \NR +\NC \type{lasterrorcontext} \NC last error context string (with newlines) \NC \NR +\NC \type{lasterrorstring} \NC last \TEX\ error string \NC \NR +\NC \type{lastluaerrorstring} \NC last \LUA\ error string \NC \NR +\NC \type{lastwarningstring} \NC last warning tag, normally an indication of in what part\NC \NR +\NC \type{lastwarningtag} \NC last warning string\NC \NR +\NC \type{linenumber} \NC location in the current input file \NC \NR +\NC \type{log_name} \NC name of the log file \NC \NR +\NC \type{luabytecode_bytes} \NC number of bytes in \LUA\ bytecode registers \NC \NR +\NC \type{luabytecodes} \NC number of active \LUA\ bytecode registers \NC \NR +\NC \type{luastate_bytes} \NC number of bytes in use by \LUA\ interpreters \NC \NR +\NC \type{luatex_engine} \NC the \LUATEX\ engine identifier \NC \NR +\NC \type{luatex_hashchars} \NC length to which \LUA\ hashes strings ($2^n$) \NC \NR +\NC \type{luatex_hashtype} \NC the hash method used (in \LUAJITTEX) \NC \NR +\NC \type{luatex_version} \NC the \LUATEX\ version number \NC \NR +\NC \type{luatex_revision} \NC the \LUATEX\ revision string \NC \NR +\NC \type{max_buf_stack} \NC max used buffer position \NC \NR +\NC \type{max_in_stack} \NC max used input stack entries \NC \NR +\NC \type{max_nest_stack} \NC max used nesting stack entries \NC \NR +\NC \type{max_param_stack} \NC max used parameter stack entries \NC \NR +\NC \type{max_save_stack} \NC max used save stack entries \NC \NR +\NC \type{max_strings} \NC maximum allowed strings \NC \NR +\NC \type{nest_size} \NC nesting stack size \NC \NR +\NC \type{node_mem_usage} \NC a string giving insight into currently used nodes \NC \NR +\NC \type{obj_ptr} \NC max \PDF\ object pointer \NC \NR +\NC \type{obj_tab_size} \NC \PDF\ object table size \NC \NR +\NC \type{output_active} \NC \type {true} if the \prm {output} routine is active \NC \NR +\NC \type{output_file_name} \NC name of the \PDF\ or \DVI\ file \NC \NR +\NC \type{param_size} \NC parameter stack size \NC \NR +\NC \type{pdf_dest_names_ptr} \NC max \PDF\ destination pointer \NC \NR +\NC \type{pdf_gone} \NC written \PDF\ bytes \NC \NR +\NC \type{pdf_mem_ptr} \NC max \PDF\ memory used \NC \NR +\NC \type{pdf_mem_size} \NC \PDF\ memory size \NC \NR +\NC \type{pdf_os_cntr} \NC max \PDF\ object stream pointer \NC \NR +\NC \type{pdf_os_objidx} \NC \PDF\ object stream index \NC \NR +\NC \type{pdf_ptr} \NC not yet written \PDF\ bytes \NC \NR +\NC \type{pool_ptr} \NC string pool index \NC \NR +\NC \type{pool_size} \NC current size allocated for string characters \NC \NR +\NC \type{save_size} \NC save stack size \NC \NR +\NC \type{shell_escape} \NC \type {0} means disabled, \type {1} means anything is permitted, and \type {2} is restricted \NC \NR +\NC \type{safer_option} \NC \type {1} means safer is enforced \NC \NR +\NC \type{kpse_used} \NC \type {1} means that kpse is used \NC \NR +\NC \type{stack_size} \NC input stack size \NC \NR +\NC \type{str_ptr} \NC number of strings \NC \NR +\NC \type{total_pages} \NC number of written pages \NC \NR +\NC \type{var_mem_max} \NC number of allocated words for nodes \NC \NR +\NC \type{var_used} \NC variable (one|-|word) memory in use \NC \NR +\NC \type{lc_collate} \NC the value of \type {LC_COLLATE} at startup time (becomes \type {C} at startup) \NC \NR +\NC \type{lc_ctype} \NC the value of \type {LC_CTYPE} at startup time (becomes \type {C} at startup) \NC \NR +%NC \type{lc_monetary} \NC the value of \type {LC_MONETARY} at startup time \NC \NR +\NC \type{lc_numeric} \NC the value of \type {LC_NUMERIC} at startup time \NC \NR +%NC \type{lc_time} \NC the value of \type {LC_TIME} at startup time (becomes \type {C} at startup) \NC \NR +\LL +\stoptabulate + +The error and warning messages can be wiped with the \type {resetmessages} +function. A return value can be set with \type {setexitcode}. + +\stopsection + +\startsection[title={The \type {tex} library}][library=tex] + +\startsubsection[title={Introduction}] + +\topicindex{libraries+\type{tex}} + +The \type {tex} table contains a large list of virtual internal \TEX\ +parameters that are partially writable. + +The designation \quote {virtual} means that these items are not properly defined +in \LUA, but are only front\-ends that are handled by a metatable that operates +on the actual \TEX\ values. As a result, most of the \LUA\ table operators (like +\type {pairs} and \type {#}) do not work on such items. + +At the moment, it is possible to access almost every parameter that you can use +after \prm {the}, is a single tokens or is sort of special in \TEX. This excludes +parameters that need extra arguments, like \type {\the\scriptfont}. The subset +comprising simple integer and dimension registers are writable as well as +readable (like \prm {tracingcommands} and \prm {parindent}). + +\stopsubsection + +\startsubsection[title={Internal parameter values, \type {set} and \type {get}}] + +\topicindex{parameters+internal} + +\libindex{set} \libindex{get} + +For all the parameters in this section, it is possible to access them directly +using their names as index in the \type {tex} table, or by using one of the +functions \type {tex.get} and \type {tex.set}. + +The exact parameters and return values differ depending on the actual parameter, +and so does whether \type {tex.set} has any effect. For the parameters that {\em +can} be set, it is possible to use \type {global} as the first argument to \type +{tex.set}; this makes the assignment global instead of local. + +\startfunctioncall +tex.set (["global",] n, ...) +... = tex.get ( n) +\stopfunctioncall + +Glue is kind of special because there are five values involved. The return value +is a \nod {glue_spec} node but when you pass \type {false} as last argument to +\type {tex.get} you get the width of the glue and when you pass \type {true} you +get all five values. Otherwise you get a node which is a copy of the internal +value so you are responsible for its freeing at the \LUA\ end. When you set a +glue quantity you can either pass a \nod {glue_spec} or upto five numbers. If +you pass \type {true} to \type {get} you get 5 values returned for a glue and +when you pass \type {false} you only get the width returned. + +\subsubsection{Integer parameters} + +The integer parameters accept and return \LUA\ numbers. These are read|-|write: + +\starttwocolumns +\starttyping +tex.adjdemerits +tex.binoppenalty +tex.brokenpenalty +tex.catcodetable +tex.clubpenalty +tex.day +tex.defaulthyphenchar +tex.defaultskewchar +tex.delimiterfactor +tex.displaywidowpenalty +tex.doublehyphendemerits +tex.endlinechar +tex.errorcontextlines +tex.escapechar +tex.exhyphenpenalty +tex.fam +tex.finalhyphendemerits +tex.floatingpenalty +tex.globaldefs +tex.hangafter +tex.hbadness +tex.holdinginserts +tex.hyphenpenalty +tex.interlinepenalty +tex.language +tex.lastlinefit +tex.lefthyphenmin +tex.linepenalty +tex.localbrokenpenalty +tex.localinterlinepenalty +tex.looseness +tex.mag +tex.maxdeadcycles +tex.month +tex.newlinechar +tex.outputpenalty +tex.pausing +tex.postdisplaypenalty +tex.predisplaydirection +tex.predisplaypenalty +tex.pretolerance +tex.relpenalty +tex.righthyphenmin +tex.savinghyphcodes +tex.savingvdiscards +tex.showboxbreadth +tex.showboxdepth +tex.time +tex.tolerance +tex.tracingassigns +tex.tracingcommands +tex.tracinggroups +tex.tracingifs +tex.tracinglostchars +tex.tracingmacros +tex.tracingnesting +tex.tracingonline +tex.tracingoutput +tex.tracingpages +tex.tracingparagraphs +tex.tracingrestores +tex.tracingscantokens +tex.tracingstats +tex.uchyph +tex.vbadness +tex.widowpenalty +tex.year +\stoptyping +\stoptwocolumns + +These are read|-|only: + +\startthreecolumns +\starttyping +tex.deadcycles +tex.insertpenalties +tex.parshape +tex.prevgraf +tex.spacefactor +\stoptyping +\stopthreecolumns + +\subsubsection{Dimension parameters} + +The dimension parameters accept \LUA\ numbers (signifying scaled points) or +strings (with included dimension). The result is always a number in scaled +points. These are read|-|write: + +\startthreecolumns +\starttyping +tex.boxmaxdepth +tex.delimitershortfall +tex.displayindent +tex.displaywidth +tex.emergencystretch +tex.hangindent +tex.hfuzz +tex.hoffset +tex.hsize +tex.lineskiplimit +tex.mathsurround +tex.maxdepth +tex.nulldelimiterspace +tex.overfullrule +tex.pagebottomoffset +tex.pageheight +tex.pageleftoffset +tex.pagerightoffset +tex.pagetopoffset +tex.pagewidth +tex.parindent +tex.predisplaysize +tex.scriptspace +tex.splitmaxdepth +tex.vfuzz +tex.voffset +tex.vsize +tex.prevdepth +tex.prevgraf +tex.spacefactor +\stoptyping +\stopthreecolumns + +These are read|-|only: + +\startthreecolumns +\starttyping +tex.pagedepth +tex.pagefilllstretch +tex.pagefillstretch +tex.pagefilstretch +tex.pagegoal +tex.pageshrink +tex.pagestretch +tex.pagetotal +\stoptyping +\stopthreecolumns + +Beware: as with all \LUA\ tables you can add values to them. So, the following is +valid: + +\starttyping +tex.foo = 123 +\stoptyping + +When you access a \TEX\ parameter a look up takes place. For read||only variables +that means that you will get something back, but when you set them you create a +new entry in the table thereby making the original invisible. + +There are a few special cases that we make an exception for: \type {prevdepth}, +\type {prevgraf} and \type {spacefactor}. These normally are accessed via the +\type {tex.nest} table: + +\starttyping +tex.nest[tex.nest.ptr].prevdepth = p +tex.nest[tex.nest.ptr].spacefactor = s +\stoptyping + +However, the following also works: + +\starttyping +tex.prevdepth = p +tex.spacefactor = s +\stoptyping + +Keep in mind that when you mess with node lists directly at the \LUA\ end you +might need to update the top of the nesting stack's \type {prevdepth} explicitly +as there is no way \LUATEX\ can guess your intentions. By using the accessor in +the \type {tex} tables, you get and set the values at the top of the nesting +stack. + +\subsubsection{Direction parameters} + +The direction states can be queried and set with: + +\startthreecolumns +\starttyping +tex.gettextdir() +tex.getlinedir() +tex.getmathdir() +tex.getpardir() +tex.settextdir() +tex.setlinedir() +tex.setmathdir() +tex.setpardir() +\stoptyping +\stopthreecolumns + +and also with: + +\startthreecolumns +\starttyping +tex.textdirection +tex.linedirection +tex.mathdirection +tex.pardirection +\stoptyping +\stopthreecolumns + + +\subsubsection{Glue parameters} + +The glue parameters accept and return a userdata object that represents a \nod {glue_spec} node. + +\startthreecolumns +\starttyping +tex.abovedisplayshortskip +tex.abovedisplayskip +tex.baselineskip +tex.belowdisplayshortskip +tex.belowdisplayskip +tex.leftskip +tex.lineskip +tex.parfillskip +tex.parskip +tex.rightskip +tex.spaceskip +tex.splittopskip +tex.tabskip +tex.topskip +tex.xspaceskip +\stoptyping +\stopthreecolumns + +\subsubsection{Muglue parameters} + +All muglue parameters are to be used read|-|only and return a \LUA\ string. + +\startthreecolumns +\starttyping +tex.medmuskip +tex.thickmuskip +tex.thinmuskip +\stoptyping +\stopthreecolumns + +\subsubsection{Tokenlist parameters} + +The tokenlist parameters accept and return \LUA\ strings. \LUA\ strings are +converted to and from token lists using \prm {the} \prm {toks} style expansion: +all category codes are either space (10) or other (12). It follows that assigning +to some of these, like \quote {tex.output}, is actually useless, but it feels bad +to make exceptions in view of a coming extension that will accept full|-|blown +token strings. + +\startthreecolumns +\starttyping +tex.errhelp +tex.everycr +tex.everydisplay +tex.everyeof +tex.everyhbox +tex.everyjob +tex.everymath +tex.everypar +tex.everyvbox +tex.output +\stoptyping +\stopthreecolumns + +\stopsubsection + +\startsubsection[title={Convert commands}] + +\topicindex{convert commands} + +All \quote {convert} commands are read|-|only and return a \LUA\ string. The +supported commands at this moment are: + +\starttwocolumns +\starttyping +tex.eTeXVersion +tex.eTeXrevision +tex.formatname +tex.jobname +tex.luatexbanner +tex.luatexrevision +tex.fontname(number) +tex.uniformdeviate(number) +tex.number(number) +tex.romannumeral(number) +tex.fontidentifier(number) +\stoptyping +\stoptwocolumns + +If you are wondering why this list looks haphazard; these are all the cases of +the \quote {convert} internal command that do not require an argument, as well as +the ones that require only a simple numeric value. The special (\LUA|-|only) case +of \type {tex.fontidentifier} returns the \type {csname} string that matches a +font id number (if there is one). + +\stopsubsection + +\startsubsection[title={Last item commands}] + +\topicindex{last items} + +All \quote {last item} commands are read|-|only and return a number. The +supported commands at this moment are: + +\startthreecolumns +\starttyping +tex.lastpenalty +tex.lastkern +tex.lastskip +tex.lastnodetype +tex.inputlineno +tex.lastxpos +tex.lastypos +tex.randomseed +tex.luatexversion +tex.eTeXminorversion +tex.eTeXversion +tex.currentgrouplevel +tex.currentgrouptype +tex.currentiflevel +tex.currentiftype +tex.currentifbranch +\stoptyping +\stopthreecolumns + +\stopsubsection + +\startsubsection[title={Accessing registers: \type {set*}, \type {get*} and \type {is*}}] + +\topicindex{attributes} +\topicindex{registers} + +\libindex{attribute} \libindex{setattribute} \libindex{getattribute} \libindex{isattribute} +\libindex{count} \libindex{setcount} \libindex{getcount} \libindex{iscount} +\libindex{dimen} \libindex{setdimen} \libindex{getdimen} \libindex{isdimen} +\libindex{skip} \libindex{setskip} \libindex{getskip} \libindex{isskip} +\libindex{muskip} \libindex{setmuskip} \libindex{getmuskip} \libindex{ismuskip} +\libindex{glue} \libindex{setglue} \libindex{getglue} \libindex{isglue} +\libindex{muglue} \libindex{setmuglue} \libindex{getmuglue} \libindex{ismuglue} +\libindex{toks} \libindex{settoks} \libindex{gettoks} \libindex{istoks} +\libindex{box} \libindex{setbox} \libindex{getbox} \libindex{isbox} + +\libindex{scantoks} + +\TEX's attributes (\lpr {attribute}), counters (\prm {count}), dimensions (\prm +{dimen}), skips (\prm {skip}, \prm {muskip}) and token (\prm {toks}) registers +can be accessed and written to using two times five virtual sub|-|tables of the +\type {tex} table: + +\startthreecolumns +\starttyping +tex.attribute +tex.count +tex.dimen +tex.skip +tex.glue +tex.muskip +tex.muglue +tex.toks +\stoptyping +\stopthreecolumns + +It is possible to use the names of relevant \lpr {attributedef}, \prm {countdef}, +\prm {dimendef}, \prm {skipdef}, or \prm {toksdef} control sequences as indices +to these tables: + +\starttyping +tex.count.scratchcounter = 0 +enormous = tex.dimen['maxdimen'] +\stoptyping + +In this case, \LUATEX\ looks up the value for you on the fly. You have to use a +valid \prm {countdef} (or \lpr {attributedef}, or \prm {dimendef}, or \prm +{skipdef}, or \prm {toksdef}), anything else will generate an error (the intent +is to eventually also allow \type {} and even macros that expand +into a number). + +\startitemize + + \startitem + The count registers accept and return \LUA\ numbers. + \stopitem + + \startitem + The dimension registers accept \LUA\ numbers (in scaled points) or + strings (with an included absolute dimension; \type {em} and \type {ex} + and \type {px} are forbidden). The result is always a number in scaled + points. + \stopitem + + \startitem + The token registers accept and return \LUA\ strings. \LUA\ strings are + converted to and from token lists using \prm {the} \prm {toks} style + expansion: all category codes are either space (10) or other (12). + \stopitem + + \startitem + The skip registers accept and return \nod {glue_spec} userdata node + objects (see the description of the node interface elsewhere in this + manual). + \stopitem + + \startitem + The glue registers are just skip registers but instead of userdata + are verbose. + \stopitem + + \startitem + Like the counts, the attribute registers accept and return \LUA\ numbers. + \stopitem + +\stopitemize + +As an alternative to array addressing, there are also accessor functions defined +for all cases, for example, here is the set of possibilities for \prm {skip} +registers: + +\startfunctioncall +tex.setskip (["global",] n, s) +tex.setskip (["global",] s, s) + s = tex.getskip ( n) + s = tex.getskip ( s) +\stopfunctioncall + +We have similar setters for \type {count}, \type {dimen}, \type {muskip}, and +\type {toks}. Counters and dimen are represented by numbers, skips and muskips by +nodes, and toks by strings. + +Again the glue variants are not using the \nod {glue-spec} userdata nodes. The +\type {setglue} function accepts upto 5 arguments: width, stretch, shrink, +stretch order and shrink order and the \type {getglue} function reports them, +unless the second argument is \type {false} in which care only the width is +returned. + +Here is an example usign a threesome: + +\startfunctioncall +local d = tex.getdimen("foo") +if tex.isdimen("bar") then + tex.setdimen("bar",d) +end +\stopfunctioncall + +There are six extra skip (glue) related helpers: + +\startfunctioncall +tex.setglue (["global"], n, + width, stretch, shrink, stretch_order, shrink_order) +tex.setglue (["global"], s, + width, stretch, shrink, stretch_order, shrink_order) +width, stretch, shrink, stretch_order, shrink_order = + tex.getglue ( n) +width, stretch, shrink, stretch_order, shrink_order = + tex.getglue ( s) +\stopfunctioncall + +The other two are \type {tex.setmuglue} and \type {tex.getmuglue}. + +There are such helpers for \type {dimen}, \type {count}, \type {skip}, \type +{muskip}, \type {box} and \type {attribute} registers but the glue ones +are special because they have to deal with more properties. + +As with the general \type {get} and \type {set} function discussed before, for +the skip registers \type {getskip} returns a node and \type {getglue} returns +numbers, while \type {setskip} accepts a node and \type {setglue} expects upto 5 +numbers. Again, when you pass \type {false} as second argument to \type {getglue} +you only get the width returned. The same is true for the \type {mu} variants +\type {getmuskip}, \type {setmuskip}, \type {getmuskip} and\type {setmuskip}. + +For tokens registers we have an alternative where a catcode table is specified: + +\startfunctioncall +tex.scantoks(0,3,"$e=mc^2$") +tex.scantoks("global",0,3,"$\int\limits^1_2$") +\stopfunctioncall + +In the function-based interface, it is possible to define values globally by +using the string \type {global} as the first function argument. + +\stopsubsection + +\startsubsection[title={Character code registers: \type {[get|set]*code[s]}}] + +\topicindex{characters+codes} + +\libindex{lccode} \libindex{setlccode} \libindex{getlccode} +\libindex{uccode} \libindex{setuccode} \libindex{getuccode} +\libindex{sfcode} \libindex{setsfcode} \libindex{getsfcode} +\libindex{catcode} \libindex{setcatcode} \libindex{getcatcode} +\libindex{mathcode} \libindex{setmathcode} \libindex{getmathcode} +\libindex{delcode} \libindex{setdelcode} \libindex{getdelcode} + +\libindex{setdelcodes} \libindex{getdelcodes} +\libindex{setmathcodes} \libindex{getmathcodes} + +\TEX's character code tables (\prm {lccode}, \prm {uccode}, \prm {sfcode}, \prm +{catcode}, \prm {mathcode}, \prm {delcode}) can be accessed and written to using +six virtual subtables of the \type {tex} table + +\startthreecolumns +\starttyping +tex.lccode +tex.uccode +tex.sfcode +tex.catcode +tex.mathcode +tex.delcode +\stoptyping +\stopthreecolumns + +The function call interfaces are roughly as above, but there are a few twists. +\type {sfcode}s are the simple ones: + +\startfunctioncall +tex.setsfcode (["global",] n, s) + s = tex.getsfcode ( n) +\stopfunctioncall + +The function call interface for \type {lccode} and \type {uccode} additionally +allows you to set the associated sibling at the same time: + +\startfunctioncall +tex.setlccode (["global"], n, lc) +tex.setlccode (["global"], n, lc, uc) + lc = tex.getlccode ( n) +tex.setuccode (["global"], n, uc) +tex.setuccode (["global"], n, uc, lc) + uc = tex.getuccode ( n) +\stopfunctioncall + +The function call interface for \type {catcode} also allows you to specify a +category table to use on assignment or on query (default in both cases is the +current one): + +\startfunctioncall +tex.setcatcode (["global"], n, c) +tex.setcatcode (["global"], cattable, n, c) + lc = tex.getcatcode ( n) + lc = tex.getcatcode ( cattable, n) +\stopfunctioncall + +The interfaces for \type {delcode} and \type {mathcode} use small array tables to +set and retrieve values: + +\startfunctioncall +tex.setmathcode (["global"], n,
mval ) +
mval = tex.getmathcode ( n) +tex.setdelcode (["global"], n,
dval ) +
dval = tex.getdelcode ( n) +\stopfunctioncall + +Where the table for \type {mathcode} is an array of 3 numbers, like this: + +\starttyping +{ + class, + family, + character +} +\stoptyping + +And the table for \type {delcode} is an array with 4 numbers, like this: + +\starttyping +{ + small_fam, + small_char, + large_fam, + large_char +} +\stoptyping + +You can also avoid the table: + +\startfunctioncall +tex.setmathcode (["global"], n, class, + family, character) +class, family, char = + tex.getmathcodes ( n) +tex.setdelcode (["global"], n, smallfam, + smallchar, largefam, largechar) +smallfam, smallchar, largefam, largechar = + tex.getdelcodes ( n) +\stopfunctioncall + +Normally, the third and fourth values in a delimiter code assignment will be zero +according to \lpr {Udelcode} usage, but the returned table can have values there +(if the delimiter code was set using \prm {delcode}, for example). Unset \type +{delcode}'s can be recognized because \type {dval[1]} is $-1$. + +\stopsubsection + +\startsubsection[title={Box registers: \type {[get|set]box}}] + +\topicindex{registers} +\topicindex{boxes} + +\libindex{box} +\libindex{setbox} \libindex{getbox} + +It is possible to set and query actual boxes, coming for instance from \prm +{hbox}, \prm {vbox} or \prm {vtop}, using the node interface as defined in the +\type {node} library: + +\starttyping +tex.box +\stoptyping + +for array access, or + +\starttyping +tex.setbox(["global",] n, s) +tex.setbox(["global",] cs, s) + n = tex.getbox( n) + n = tex.getbox( cs) +\stoptyping + +for function|-|based access. In the function-based interface, it is possible to +define values globally by using the string \type {global} as the first function +argument. + +Be warned that an assignment like + +\starttyping +tex.box[0] = tex.box[2] +\stoptyping + +does not copy the node list, it just duplicates a node pointer. If \type {\box2} +will be cleared by \TEX\ commands later on, the contents of \type {\box0} becomes +invalid as well. To prevent this from happening, always use \type +{node.copy_list} unless you are assigning to a temporary variable: + +\starttyping +tex.box[0] = node.copy_list(tex.box[2]) +\stoptyping + +\stopsubsection + +\startsubsection[title={\type {triggerbuildpage}}] + +\topicindex{pages} + +\libindex{triggerbuildpage} + +You should not expect to much from the \type {triggerbuildpage} helpers because +often \TEX\ doesn't do much if it thinks nothing has to be done, but it might be +useful for some applications. It just does as it says it calls the internal +function that build a page, given that there is something to build. + +\stopsubsection + +\startsubsection[title={\type {splitbox}}] + +\topicindex{boxes+split} + +\libindex{splitbox} + +You can split a box: + +\starttyping +local vlist = tex.splitbox(n,height,mode) +\stoptyping + +The remainder is kept in the original box and a packaged vlist is returned. This +operation is comparable to the \prm {vsplit} operation. The mode can be \type +{additional} or \type {exactly} and concerns the split off box. + +\stopsubsection + +\startsubsection[title={Accessing math parameters: \type {[get|set]math}}] + +\topicindex{math+parameters} +\topicindex{parameters+math} + +\libindex{setmath} +\libindex{getmath} + +It is possible to set and query the internal math parameters using: + +\startfunctioncall +tex.setmath(["global",] n, t, n) + n = tex.getmath( n, t) +\stopfunctioncall + +As before an optional first parameter \type {global} indicates a global +assignment. + +The first string is the parameter name minus the leading \quote {Umath}, and the +second string is the style name minus the trailing \quote {style}. Just to be +complete, the values for the math parameter name are: + +\starttyping +quad axis operatorsize +overbarkern overbarrule overbarvgap +underbarkern underbarrule underbarvgap +radicalkern radicalrule radicalvgap +radicaldegreebefore radicaldegreeafter radicaldegreeraise +stackvgap stacknumup stackdenomdown +fractionrule fractionnumvgap fractionnumup +fractiondenomvgap fractiondenomdown fractiondelsize +limitabovevgap limitabovebgap limitabovekern +limitbelowvgap limitbelowbgap limitbelowkern +underdelimitervgap underdelimiterbgap +overdelimitervgap overdelimiterbgap +subshiftdrop supshiftdrop subshiftdown +subsupshiftdown subtopmax supshiftup +supbottommin supsubbottommax subsupvgap +spaceafterscript connectoroverlapmin +ordordspacing ordopspacing ordbinspacing ordrelspacing +ordopenspacing ordclosespacing ordpunctspacing ordinnerspacing +opordspacing opopspacing opbinspacing oprelspacing +opopenspacing opclosespacing oppunctspacing opinnerspacing +binordspacing binopspacing binbinspacing binrelspacing +binopenspacing binclosespacing binpunctspacing bininnerspacing +relordspacing relopspacing relbinspacing relrelspacing +relopenspacing relclosespacing relpunctspacing relinnerspacing +openordspacing openopspacing openbinspacing openrelspacing +openopenspacing openclosespacing openpunctspacing openinnerspacing +closeordspacing closeopspacing closebinspacing closerelspacing +closeopenspacing closeclosespacing closepunctspacing closeinnerspacing +punctordspacing punctopspacing punctbinspacing punctrelspacing +punctopenspacing punctclosespacing punctpunctspacing punctinnerspacing +innerordspacing inneropspacing innerbinspacing innerrelspacing +inneropenspacing innerclosespacing innerpunctspacing innerinnerspacing +\stoptyping + +The values for the style parameter are: + +\starttyping +display crampeddisplay +text crampedtext +script crampedscript +scriptscript crampedscriptscript +\stoptyping + +The value is either a number (representing a dimension or number) or a glue spec +node representing a muskip for \type {ordordspacing} and similar spacing +parameters. + +\stopsubsection + +\startsubsection[title={Special list heads: \type {[get|set]list}}] + +\topicindex{lists} + +\libindex{lists} +\libindex{setlist} +\libindex{getlist} + +The virtual table \type {tex.lists} contains the set of internal registers that +keep track of building page lists. + +\starttabulate[|l|p|] +\DB field \BC explanation \NC \NR +\TB +\NC \type{page_ins_head} \NC circular list of pending insertions \NC \NR +\NC \type{contrib_head} \NC the recent contributions \NC \NR +\NC \type{page_head} \NC the current page content \NC \NR +%NC \type{temp_head} \NC \NC \NR +\NC \type{hold_head} \NC used for held-over items for next page \NC \NR +\NC \type{adjust_head} \NC head of the current \prm {vadjust} list \NC \NR +\NC \type{pre_adjust_head} \NC head of the current \type {\vadjust pre} list \NC \NR +%NC \type{align_head} \NC \NC \NR +\NC \type{page_discards_head} \NC head of the discarded items of a page break \NC \NR +\NC \type{split_discards_head} \NC head of the discarded items in a vsplit \NC \NR +\LL +\stoptabulate + +The getter and setter functions are \type {getlist} and \type {setlist}. You have +to be careful with what you set as \TEX\ can have expectations with regards to +how a list is constructed or in what state it is. + +\stopsubsection + +\startsubsection[title={Semantic nest levels: \type {getnest} and \type {ptr}}] + +\topicindex{nesting} + +\libindex{nest} +\libindex{ptr} +%libindex{setnest} % only a message +\libindex{getnest} + +The virtual table \type {nest} contains the currently active semantic nesting +state. It has two main parts: a zero-based array of userdata for the semantic +nest itself, and the numerical value \type {ptr}, which gives the highest +available index. Neither the array items in \type {nest[]} nor \type {ptr} can be +assigned to (as this would confuse the typesetting engine beyond repair), but you +can assign to the individual values inside the array items, e.g.\ \type +{tex.nest[tex.nest.ptr].prevdepth}. + +\type {tex.nest[tex.nest.ptr]} is the current nest state, \type {nest[0]} the +outermost (main vertical list) level. The getter function is \type {getnest}. You +can pass a number (which gives you a list), nothing or \type {top}, which returns +the topmost list, or the string \type {ptr} which gives you the index of the +topmost list. + +The known fields are: + +\starttabulate[|l|l|l|p|] +\DB key \BC type \BC modes \BC explanation \NC \NR +\TB +\NC \type{mode} \NC number \NC all \NC the meaning of these numbers depends on the engine + and sometimes even the version; you can use \typ + {tex.getmodevalues()} to get the mapping: positive + values signal vertical, horizontal and math mode, + while negative values indicate inner and inline + variants \NC \NR +\NC \type{modeline} \NC number \NC all \NC source input line where this mode was entered in, + negative inside the output routine \NC \NR +\NC \type{head} \NC node \NC all \NC the head of the current list \NC \NR +\NC \type{tail} \NC node \NC all \NC the tail of the current list \NC \NR +\NC \type{prevgraf} \NC number \NC vmode \NC number of lines in the previous paragraph \NC \NR +\NC \type{prevdepth} \NC number \NC vmode \NC depth of the previous paragraph \NC \NR +\NC \type{spacefactor} \NC number \NC hmode \NC the current space factor \NC \NR +\NC \type{dirs} \NC node \NC hmode \NC used for temporary storage by the line break algorithm\NC \NR +\NC \type{noad} \NC node \NC mmode \NC used for temporary storage of a pending fraction numerator, + for \prm {over} etc. \NC \NR +\NC \type{delimptr} \NC node \NC mmode \NC used for temporary storage of the previous math delimiter, + for \prm {middle} \NC \NR +\NC \type{mathdir} \NC boolean \NC mmode \NC true when during math processing the \lpr {mathdir} is not + the same as the surrounding \lpr {textdir} \NC \NR +\NC \type{mathstyle} \NC number \NC mmode \NC the current \lpr {mathstyle} \NC \NR +\LL +\stoptabulate + +\stopsubsection + +\startsubsection[reference=sec:luaprint,title={Print functions}] + +\topicindex{printing} + +The \type {tex} table also contains the three print functions that are the major +interface from \LUA\ scripting to \TEX. The arguments to these three functions +are all stored in an in|-|memory virtual file that is fed to the \TEX\ scanner as +the result of the expansion of \prm {directlua}. + +The total amount of returnable text from a \prm {directlua} command is only +limited by available system \RAM. However, each separate printed string has to +fit completely in \TEX's input buffer. The result of using these functions from +inside callbacks is undefined at the moment. + +\subsubsection{\type {print}} + +\libindex{print} + +\startfunctioncall +tex.print( s, ...) +tex.print( n, s, ...) +tex.print(
t) +tex.print( n,
t) +\stopfunctioncall + +Each string argument is treated by \TEX\ as a separate input line. If there is a +table argument instead of a list of strings, this has to be a consecutive array +of strings to print (the first non-string value will stop the printing process). + +The optional parameter can be used to print the strings using the catcode regime +defined by \lpr {catcodetable}~\type {n}. If \type {n} is $-1$, the currently +active catcode regime is used. If \type {n} is $-2$, the resulting catcodes are +the result of \prm {the} \prm {toks}: all category codes are 12 (other) except for +the space character, that has category code 10 (space). Otherwise, if \type {n} +is not a valid catcode table, then it is ignored, and the currently active +catcode regime is used instead. + +The very last string of the very last \type {tex.print} command in a \prm +{directlua} will not have the \prm {endlinechar} appended, all others do. + +\subsubsection{\type {sprint}} + +\libindex{sprint} + +\startfunctioncall +tex.sprint( s, ...) +tex.sprint( n, s, ...) +tex.sprint(
t) +tex.sprint( n,
t) +\stopfunctioncall + +Each string argument is treated by \TEX\ as a special kind of input line that +makes it suitable for use as a partial line input mechanism: + +\startitemize[packed] +\startitem + \TEX\ does not switch to the \quote {new line} state, so that leading spaces + are not ignored. +\stopitem +\startitem + No \prm {endlinechar} is inserted. +\stopitem +\startitem + Trailing spaces are not removed. Note that this does not prevent \TEX\ itself + from eating spaces as result of interpreting the line. For example, in + + \starttyping + before\directlua{tex.sprint("\\relax")tex.sprint(" inbetween")}after + \stoptyping + + the space before \type {in between} will be gobbled as a result of the \quote + {normal} scanning of \prm {relax}. +\stopitem +\stopitemize + +If there is a table argument instead of a list of strings, this has to be a +consecutive array of strings to print (the first non-string value will stop the +printing process). + +The optional argument sets the catcode regime, as with \type {tex.print}. This +influences the string arguments (or numbers turned into strings). + +Although this needs to be used with care, you can also pass token or node +userdata objects. These get injected into the stream. Tokens had best be valid +tokens, while nodes need to be around when they get injected. Therefore it is +important to realize the following: + +\startitemize +\startitem + When you inject a token, you need to pass a valid token userdata object. This + object will be collected by \LUA\ when it no longer is referenced. When it gets + printed to \TEX\ the token itself gets copied so there is no interference with the + \LUA\ garbage collection. You manage the object yourself. Because tokens are + actually just numbers, there is no real extra overhead at the \TEX\ end. +\stopitem +\startitem + When you inject a node, you need to pass a valid node userdata object. The + node related to the object will not be collected by \LUA\ when it no longer + is referenced. It lives on at the \TEX\ end in its own memory space. When it + gets printed to \TEX\ the node reference is used assuming that node stays + around. There is no \LUA\ garbage collection involved. Again, you manage the + object yourself. The node itself is freed when \TEX\ is done with it. +\stopitem +\stopitemize + +If you consider the last remark you might realize that we have a problem when a +printed mix of strings, tokens and nodes is reused. Inside \TEX\ the sequence +becomes a linked list of input buffers. So, \type {"123"} or \type {"\foo{123}"} +gets read and parsed on the fly, while \typ {} already is +tokenized and effectively is a token list now. A \typ {} is also +tokenized into a token list but it has a reference to a real node. Normally this +goes fine. But now assume that you store the whole lot in a macro: in that case +the tokenized node can be flushed many times. But, after the first such flush the +node is used and its memory freed. You can prevent this by using copies which is +controlled by setting \lpr {luacopyinputnodes} to a non|-|zero value. This is one +of these fuzzy areas you have to live with if you really mess with these low +level issues. + +\subsubsection{\type {tprint}} + +\libindex{tprint} + +\startfunctioncall +tex.tprint({ n, s, ...}, {...}) +\stopfunctioncall + +This function is basically a shortcut for repeated calls to \type +{tex.sprint( n, s, ...)}, once for each of the supplied argument +tables. + +\subsubsection{\type {cprint}} + +\libindex{cprint} + +This function takes a number indicating the to be used catcode, plus either a +table of strings or an argument list of strings that will be pushed into the +input stream. + +\startfunctioncall +tex.cprint( 1," 1: $&{\\foo}") tex.print("\\par") -- a lot of \bgroup s +tex.cprint( 2," 2: $&{\\foo}") tex.print("\\par") -- matching \egroup s +tex.cprint( 9," 9: $&{\\foo}") tex.print("\\par") -- all get ignored +tex.cprint(10,"10: $&{\\foo}") tex.print("\\par") -- all become spaces +tex.cprint(11,"11: $&{\\foo}") tex.print("\\par") -- letters +tex.cprint(12,"12: $&{\\foo}") tex.print("\\par") -- other characters +tex.cprint(14,"12: $&{\\foo}") tex.print("\\par") -- comment triggers +\stopfunctioncall + +% \subsubsection{\type {write}, \type {twrite}, \type {nwrite}} +\subsubsection{\type {write}} + +\libindex{write} +% \libindex{twrite} +% \libindex{nwrite} + +\startfunctioncall +tex.write( s, ...) +tex.write(
t) +\stopfunctioncall + +Each string argument is treated by \TEX\ as a special kind of input line that +makes it suitable for use as a quick way to dump information: + +\startitemize +\item All catcodes on that line are either \quote{space} (for '~') or \quote + {character} (for all others). +\item There is no \prm {endlinechar} appended. +\stopitemize + +If there is a table argument instead of a list of strings, this has to be a +consecutive array of strings to print (the first non-string value will stop the +printing process). + +% The functions \type {twrite} and \type {nwrite} can be used to write a token or +% node back to \TEX\, possibly intermixed with regular strings that will be +% tokenized. You have to make sure that you pass the right data because sometimes +% \TEX\ has expectations that need to be met. + +\stopsubsection + +\startsubsection[title={Helper functions}] + +\subsubsection{\type {round}} + +\topicindex {helpers} + +\libindex{round} + +\startfunctioncall + n = tex.round( o) +\stopfunctioncall + +Rounds \LUA\ number \type {o}, and returns a number that is in the range of a +valid \TEX\ register value. If the number starts out of range, it generates a +\quote {number too big} error as well. + +\subsubsection{\type {scale}} + +\libindex{scale} + +\startfunctioncall + n = tex.scale( o, delta) +
n = tex.scale(table o, delta) +\stopfunctioncall + +Multiplies the \LUA\ numbers \type {o} and \nod {delta}, and returns a rounded +number that is in the range of a valid \TEX\ register value. In the table +version, it creates a copy of the table with all numeric top||level values scaled +in that manner. If the multiplied number(s) are of range, it generates +\quote{number too big} error(s) as well. + +Note: the precision of the output of this function will depend on your computer's +architecture and operating system, so use with care! An interface to \LUATEX's +internal, 100\% portable scale function will be added at a later date. + +\subsubsection{\type {number} and \type {romannumeral}} + +\libindex{number} +\libindex{romannumeral} + +These are the companions to the primitives \prm {number} and \prm +{romannumeral}. They can be used like: + +\startfunctioncall +tex.print(tex.romannumeral(123)) +\stopfunctioncall + +\subsubsection{\type {fontidentifier} and \type {fontname}} + +\libindex{fontidentifier} +\libindex{fontname} + +The first one returns the name only, the second one reports the size too. + +\startfunctioncall +tex.print(tex.fontname(tex.fontname)) +tex.print(tex.fontname(tex.fontidentidier)) +\stopfunctioncall + +\subsubsection{\type {sp}} + +\libindex{sp} + +\startfunctioncall + n = tex.sp( o) + n = tex.sp( s) +\stopfunctioncall + +Converts the number \type {o} or a string \type {s} that represents an explicit +dimension into an integer number of scaled points. + +For parsing the string, the same scanning and conversion rules are used that +\LUATEX\ would use if it was scanning a dimension specifier in its \TEX|-|like +input language (this includes generating errors for bad values), expect for the +following: + +\startitemize[n] +\startitem + only explicit values are allowed, control sequences are not handled +\stopitem +\startitem + infinite dimension units (\type {fil...}) are forbidden +\stopitem +\startitem + \type {mu} units do not generate an error (but may not be useful either) +\stopitem +\stopitemize + +\subsubsection{\type {tex.getlinenumber} and \type {tex.setlinenumber}} + +\libindex{getlinenumber} +\libindex{setlinenumber} + +You can mess with the current line number: + +\startfunctioncall +local n = tex.getlinenumber() +tex.setlinenumber(n+10) +\stopfunctioncall + +which can be shortcut to: + +\startfunctioncall +tex.setlinenumber(10,true) +\stopfunctioncall + +This might be handy when you have a callback that read numbers from a file and +combines them in one line (in which case an error message probably has to refer +to the original line). Interference with \TEX's internal handling of numbers is +of course possible. + +\subsubsection{\type {error}, \type {show_context} and \type {gethelptext}} + +\topicindex{errors} + +\libindex{error} +\libindex{show_context} +\libindex{gethelptext} + +\startfunctioncall +tex.error( s) +tex.error( s,
help) + s = tex.gethelptext() +\stopfunctioncall + +This creates an error somewhat like the combination of \prm {errhelp} and \prm +{errmessage} would. During this error, deletions are disabled. + +The array part of the \type {help} table has to contain strings, one for each +line of error help. + +In case of an error the \type {show_context} function will show the current +context where we're at (in the expansion). + +\subsubsection{\type {getfamilyoffont}} + +\libindex {getfamilyoffont} + +When you pass a proper family identifier the next helper will return the font +currently associated with it. + +\startfunctioncall + id = font.getfamilyoffont( fam) +\stopfunctioncall + +\subsubsection{\type {[set|get]interaction}} + +\libindex{setinteraction} +\libindex{getinteraction} + +The engine can in one of four modes: + +\starttabulate[|lT|l|pl|] +\DB value \NC mode \BC meaning \NC \NR +\TB +\NC 0 \NC batch \NC omits all stops and omits terminal output \NC \NR +\NC 1 \NC nonstop \NC omits all stops \NC \NR +\NC 2 \NC scroll \NC omits error stops \NC \NR +\NC 3 \NC errorstop \NC stops at every opportunity to interact \NC \NR +\LL +\stoptabulate + +The mode can be queried and set with: + +\startfunctioncall + i = tex.getinteraction() +tex.setinteraction( i) +\stopfunctioncall + +\subsubsection{\type {runtoks} and \type {quittoks}} + +Because of the fact that \TEX\ is in a complex dance of expanding, dealing with +fonts, typesetting paragraphs, messing around with boxes, building pages, and so +on, you cannot easily run a nested \TEX\ run (read nested main loop). However, +there is an option to force a local run with \type {runtoks}. The content of the +given token list register gets expanded locally after which we return to where we +triggered this expansion, at the \LUA\ end. Instead a function can get passed +that does some work. You have to make sure that at the end \TEX\ is in a sane +state and this is not always trivial. A more complex mechanism would complicate +\TEX\ itself (and probably also harm performance) so this simple local expansion +loop has to do. + +\startfunctioncall +tex.runtoks() +tex.runtoks() +tex.runtoks() +tex.runtoks() +\stopfunctioncall + +When the \prm {tracingnesting} parameter is set to a value larger than~2 some +information is reported about the state of the local loop. The return value indicates +an error: + +\starttabulate[|lT|pl|] +\DB value \NC meaning \NC \NR +\TB +\NC 0 \NC no error \NC \NR +\NC 1 \NC bad register number \NC \NR +\NC 2 \NC unknown macro or register name \NC \NR +\NC 3 \NC macro is unsuitable for runtoks (has arguments) \NC \NR +\LL +\stoptabulate + +This function has two optional arguments in case a token register is passed: + +\startfunctioncall +tex.runtoks(,force,grouped) +\stopfunctioncall + +Inside for instance an \type {\edef} the \type {runtoks} function behaves (at +least tries to) like it were an \type {\the}. This prevents unwanted side +effects: normally in such an definition tokens remain tokens and (for instance) +characters don't become nodes. With the second argument you can force the local +main loop, no matter what. The third argument adds a level of grouping. + +You can quit the local loop with \type {\endlocalcontrol} or from the \LUA\ end +with \type {tex.quittoks}. In that case you end one level up! Of course in the +end that can mean that you arrive at the main level in which case an extra end +will trigger a redundancy warning (not an abort!). + +\subsubsection{\type {forcehmode}} + +\libindex{forcehmode} + +An example of a (possible error triggering) complication is that \TEX\ expects to +be in some state, say horizontal mode, and you have to make sure it is when you +start feeding back something from \LUA\ into \TEX. Normally a user will not run +into issues but when you start writing tokens or nodes or have a nested run there +can be situations that you need to run \type {forcehmode}. There is no recipe for +this and intercepting possible cases would weaken \LUATEX's flexibility. + +\subsubsection{\type {hashtokens}} + +\libindex{hashtokens} + +\topicindex{hash} + +\startfunctioncall +for i,v in pairs (tex.hashtokens()) do ... end +\stopfunctioncall + +Returns a list of names. This can be useful for debugging, but note that this +also reports control sequences that may be unreachable at this moment due to +local redefinitions: it is strictly a dump of the hash table. You can use \type +{token.create} to inspect properties, for instance when the \type {command} key +in a created table equals \type {123}, you have the \type {cmdname} value \type +{undefined_cs}. + +\subsubsection{\type {definefont}} + +\topicindex{fonts+defining} + +\libindex{definefont} + +\startfunctioncall +tex.definefont( csname, fontid) +tex.definefont( global, csname, fontid) +\stopfunctioncall + +Associates \type {csname} with the internal font number \type {fontid}. The +definition is global if (and only if) \type {global} is specified and true (the +setting of \type {globaldefs} is not taken into account). + +\stopsubsection + +\startsubsection[reference=luaprimitives,title={Functions for dealing with primitives}] + +\subsubsection{\type {enableprimitives}} + +\libindex{enableprimitives} + +\topicindex{initialization} +\topicindex{primitives} + +\startfunctioncall +tex.enableprimitives( prefix,
primitive names) +\stopfunctioncall + +This function accepts a prefix string and an array of primitive names. For each +combination of \quote {prefix} and \quote {name}, the \type +{tex.enableprimitives} first verifies that \quote {name} is an actual primitive +(it must be returned by one of the \type {tex.extraprimitives} calls explained +below, or part of \TEX82, or \prm {directlua}). If it is not, \type +{tex.enableprimitives} does nothing and skips to the next pair. + +But if it is, then it will construct a csname variable by concatenating the +\quote {prefix} and \quote {name}, unless the \quote {prefix} is already the +actual prefix of \quote {name}. In the latter case, it will discard the \quote +{prefix}, and just use \quote {name}. + +Then it will check for the existence of the constructed csname. If the csname is +currently undefined (note: that is not the same as \prm {relax}), it will +globally define the csname to have the meaning: run code belonging to the +primitive \quote {name}. If for some reason the csname is already defined, it +does nothing and tries the next pair. + +An example: + +\starttyping +tex.enableprimitives('LuaTeX', {'formatname'}) +\stoptyping + +will define \type {\LuaTeXformatname} with the same intrinsic meaning as the +documented primitive \lpr {formatname}, provided that the control sequences \type +{\LuaTeXformatname} is currently undefined. + +When \LUATEX\ is run with \type {--ini} only the \TEX82 primitives and \prm +{directlua} are available, so no extra primitives {\bf at all}. + +If you want to have all the new functionality available using their default +names, as it is now, you will have to add + +\starttyping +\ifx\directlua\undefined \else + \directlua {tex.enableprimitives('',tex.extraprimitives ())} +\fi +\stoptyping + +near the beginning of your format generation file. Or you can choose different +prefixes for different subsets, as you see fit. + +Calling some form of \type {tex.enableprimitives} is highly important though, +because if you do not, you will end up with a \TEX82-lookalike that can run \LUA\ +code but not do much else. The defined csnames are (of course) saved in the +format and will be available at runtime. + +\subsubsection{\type {extraprimitives}} + +\libindex{extraprimitives} + +\startfunctioncall +
t = tex.extraprimitives( s, ...) +\stopfunctioncall + +This function returns a list of the primitives that originate from the engine(s) +given by the requested string value(s). The possible values and their (current) +return values are given in the following table. In addition the somewhat special +primitives \quote{\tex{ }}, \quote{\tex {/}} and \quote{\type {-}} are defined. + +\startluacode +function document.showprimitives(tag) + for k, v in table.sortedpairs(tex.extraprimitives(tag)) do + if v ~= ' ' and v ~= "/" and v ~= "-" then + context.type(v) + context.space() + end + end +end +\stopluacode + +\starttabulate[|l|pl|] +\DB name \BC values \NC \NR +\TB +\NC tex \NC \ctxlua{document.showprimitives('tex') } \NC \NR +\NC core \NC \ctxlua{document.showprimitives('core') } \NC \NR +\NC etex \NC \ctxlua{document.showprimitives('etex') } \NC \NR +\NC luatex \NC \ctxlua{document.showprimitives('luatex') } \NC \NR +\LL +\stoptabulate + +Note that \type {luatex} does not contain \type {directlua}, as that is +considered to be a core primitive, along with all the \TEX82 primitives, so it is +part of the list that is returned from \type {'core'}. + +Running \type {tex.extraprimitives} will give you the complete list of +primitives \type {-ini} startup. It is exactly equivalent to \type +{tex.extraprimitives("etex","luatex")}. + +\subsubsection{\type {primitives}} + +\libindex{primitives} + +\startfunctioncall +
t = tex.primitives() +\stopfunctioncall + +This function returns a list of all primitives that \LUATEX\ knows about. + +\stopsubsection + +\startsubsection[title={Core functionality interfaces}] + +\subsubsection{\type {badness}} + +\libindex{badness} + +\startfunctioncall + b = tex.badness( t, s) +\stopfunctioncall + +This helper function is useful during linebreak calculations. \type {t} and \type +{s} are scaled values; the function returns the badness for when total \type {t} +is supposed to be made from amounts that sum to \type {s}. The returned number is +a reasonable approximation of \mathematics {100(t/s)^3}; + +\subsubsection{\type {tex.resetparagraph}} + +\topicindex {paragraphs+reset} + +\libindex{resetparagraph} + +This function resets the parameters that \TEX\ normally resets when a new paragraph +is seen. + +\subsubsection{\type {linebreak}} + +\topicindex {linebreaks} + +\libindex{linebreak} + +\startfunctioncall +local nodelist,
info = + tex.linebreak( listhead,
parameters) +\stopfunctioncall + +The understood parameters are as follows: + +\starttabulate[|l|l|p|] +\DB name \BC type \BC explanation \NC \NR +\TB +\NC \type{pardir} \NC string \NC \NC \NR +\NC \type{pretolerance} \NC number \NC \NC \NR +\NC \type{tracingparagraphs} \NC number \NC \NC \NR +\NC \type{tolerance} \NC number \NC \NC \NR +\NC \type{looseness} \NC number \NC \NC \NR +\NC \type{hyphenpenalty} \NC number \NC \NC \NR +\NC \type{exhyphenpenalty} \NC number \NC \NC \NR +\NC \type{pdfadjustspacing} \NC number \NC \NC \NR +\NC \type{adjdemerits} \NC number \NC \NC \NR +\NC \type{pdfprotrudechars} \NC number \NC \NC \NR +\NC \type{linepenalty} \NC number \NC \NC \NR +\NC \type{lastlinefit} \NC number \NC \NC \NR +\NC \type{doublehyphendemerits} \NC number \NC \NC \NR +\NC \type{finalhyphendemerits} \NC number \NC \NC \NR +\NC \type{hangafter} \NC number \NC \NC \NR +\NC \type{interlinepenalty} \NC number or table \NC if a table, then it is an array like \prm {interlinepenalties} \NC \NR +\NC \type{clubpenalty} \NC number or table \NC if a table, then it is an array like \prm {clubpenalties} \NC \NR +\NC \type{widowpenalty} \NC number or table \NC if a table, then it is an array like \prm {widowpenalties} \NC \NR +\NC \type{brokenpenalty} \NC number \NC \NC \NR +\NC \type{emergencystretch} \NC number \NC in scaled points \NC \NR +\NC \type{hangindent} \NC number \NC in scaled points \NC \NR +\NC \type{hsize} \NC number \NC in scaled points \NC \NR +\NC \type{leftskip} \NC glue_spec node \NC \NC \NR +\NC \type{rightskip} \NC glue_spec node \NC \NC \NR +\NC \type{parshape} \NC table \NC \NC \NR +\LL +\stoptabulate + +Note that there is no interface for \prm {displaywidowpenalties}, you have to +pass the right choice for \type {widowpenalties} yourself. + +It is your own job to make sure that \type {listhead} is a proper paragraph list: +this function does not add any nodes to it. To be exact, if you want to replace +the core line breaking, you may have to do the following (when you are not +actually working in the \cbk {pre_linebreak_filter} or \cbk {linebreak_filter} +callbacks, or when the original list starting at listhead was generated in +horizontal mode): + +\startitemize +\startitem + add an \quote {indent box} and perhaps a \nod {local_par} node at the start + (only if you need them) +\stopitem +\startitem + replace any found final glue by an infinite penalty (or add such a penalty, + if the last node is not a glue) +\stopitem +\startitem + add a glue node for the \prm {parfillskip} after that penalty node +\stopitem +\startitem + make sure all the \type {prev} pointers are OK +\stopitem +\stopitemize + +The result is a node list, it still needs to be vpacked if you want to assign it +to a \prm {vbox}. The returned \type {info} table contains four values that are +all numbers: + +\starttabulate[|l|p|] +\DB name \BC explanation \NC \NR +\TB +\NC prevdepth \NC depth of the last line in the broken paragraph \NC \NR +\NC prevgraf \NC number of lines in the broken paragraph \NC \NR +\NC looseness \NC the actual looseness value in the broken paragraph \NC \NR +\NC demerits \NC the total demerits of the chosen solution \NC \NR +\LL +\stoptabulate + +Note there are a few things you cannot interface using this function: You cannot +influence font expansion other than via \type {pdfadjustspacing}, because the +settings for that take place elsewhere. The same is true for hbadness and hfuzz +etc. All these are in the \type {hpack} routine, and that fetches its own +variables via globals. + +\subsubsection{\type {shipout}} + +\topicindex {shipout} + +\libindex{shipout} + +\startfunctioncall +tex.shipout( n) +\stopfunctioncall + +Ships out box number \type {n} to the output file, and clears the box register. + +\subsubsection{\type {getpagestate}} + +\topicindex {pages} + +\libindex{getpagestate} + +This helper reports the current page state: \type {empty}, \type {box_there} or +\type {inserts_only} as integer value. + +\subsubsection{\type {getlocallevel}} + +\topicindex {nesting} + +\libindex{getlocallevel} + +This integer reports the current level of the local loop. It's only useful for +debugging and the (relative state) numbers can change with the implementation. + +\stopsubsection + +\startsubsection[title={Randomizers}] + +\libindex{lua_math_random} +\libindex{lua_math_randomseed} +\libindex{init_rand} +\libindex{normal_rand} +\libindex{uniform_rand} +\libindex{uniformdeviate} + +For practical reasons \LUATEX\ has its own random number generator. The original +\LUA\ random function is available as \typ {tex.lua_math_random}. You can +initialize with a new seed with \type {init_rand} (\typ {lua_math_randomseed} is +equivalent to this one. + +There are three generators: \type {normal_rand} (no argument is used), \type +{uniform_rand} (takes a number that will get rounded before being used) and \type +{uniformdeviate} which behaves like the primitive and expects a scaled integer, so + +\startfunctioncall +tex.print(tex.uniformdeviate(65536)/65536) +\stopfunctioncall + +will give a random number between zero and one. + +\stopsubsection + +\startsubsection[reference=synctex,title={Functions related to synctex}] + +\topicindex {synctex} + +\libindex{set_synctex_mode} \libindex{get_synctex_mode} +\libindex{set_synctex_no_files} +\libindex{set_synctex_tag} \libindex{get_synctex_tag} \libindex{force_synctex_tag} +\libindex{set_synctex_line} \libindex{get_synctex_line} \libindex{force_synctex_line} + +The next helpers only make sense when you implement your own synctex logic. Keep in +mind that the library used in editors assumes a certain logic and is geared for +plain and \LATEX, so after a decade users expect a certain behaviour. + +\starttabulate[|l|p|] +\DB name \BC explanation \NC \NR +\TB +\NC \type{set_synctex_mode} \NC \type {0} is the default and used normal synctex + logic, \type {1} uses the values set by the next + helpers while \type {2} also sets these for glyph + nodes; \type{3} sets glyphs and glue and \type {4} + sets only glyphs \NC \NR +\NC \type{set_synctex_tag} \NC set the current tag (file) value (obeys save stack) \NC \NR +\NC \type{set_synctex_line} \NC set the current line value (obeys save stack) \NC \NR +\NC \type{set_synctex_no_files} \NC disable synctex file logging \NC \NR +\NC \type{get_synctex_mode} \NC returns the current mode (for values see above) \NC \NR +\NC \type{get_synctex_tag} \NC get the currently set value of tag (file) \NC \NR +\NC \type{get_synctex_line} \NC get the currently set value of line \NC \NR +\NC \type{force_synctex_tag} \NC overload the tag (file) value (\type {0} resets) \NC \NR +\NC \type{force_synctex_line} \NC overload the line value (\type {0} resets) \NC \NR +\LL +\stoptabulate + +The last one is somewhat special. Due to the way files are registered in \SYNCTEX\ we need +to explicitly disable that feature if we provide our own alternative if we want to avoid +that overhead. Passing a value of 1 disables registering. + +\stopsubsection + +\stopsection + +\startsection[title={The \type {texconfig} table},reference=texconfig][library=texconfig] + +\topicindex{libraries+\type{texconfig}} + +\topicindex {configuration} + +This is a table that is created empty. A startup \LUA\ script could fill this +table with a number of settings that are read out by the executable after loading +and executing the startup file. + +\starttabulate[|l|l|l|] +\DB key \BC type \BC default \NC \NR +\TB +\NC \type{max_strings} \NC number \NC 100000 \NC \NR +\NC \type{strings_free} \NC number \NC 100 \NC \NR +\NC \type{nest_size} \NC number \NC 50 \NC \NR +\NC \type{max_in_open} \NC number \NC 100 \NC \NR +\NC \type{param_size} \NC number \NC 60 \NC \NR +\NC \type{save_size} \NC number \NC 5000 \NC \NR +\NC \type{stack_size} \NC number \NC 500 \NC \NR +\NC \type{expand_depth} \NC number \NC 1000 \NC \NR +\NC \type{function_size} \NC number \NC 0 \NC \NR +\NC \type{error_line} \NC number \NC 79 \NC \NR +\NC \type{half_error_line} \NC number \NC 50 \NC \NR +\NC \type{hash_extra} \NC number \NC 0 \NC \NR +\NC \type{formatname} \NC string \NC \NC \NR +\NC \type{jobname} \NC string \NC \NC \NR +\LL +\stoptabulate + +If no format name or jobname is given on the command line, the related keys will +be tested first instead of simply quitting. + +\stopsection + +\startsection[title={The \type {texio} library}][library=texio] + +\topicindex{libraries+\type{texio}} +\topicindex{\IO} + +This library takes care of the low|-|level I/O interface: writing to the log file +and|/|or console. + +\startsubsection[title={\type {write}}] + +\libindex{write} + +\startfunctioncall +texio.write( target, s, ...) +texio.write( s, ...) +\stopfunctioncall + +Without the \type {target} argument, writes all given strings to the same +location(s) \TEX\ writes messages to at this moment. If \prm {batchmode} is in +effect, it writes only to the log, otherwise it writes to the log and the +terminal. The optional \type {target} can be one of three possibilities: \type +{term}, \type {log} or \type {term and log}. + +Note: If several strings are given, and if the first of these strings is or might +be one of the targets above, the \type {target} must be specified explicitly to +prevent \LUA\ from interpreting the first string as the target. + +\stopsubsection + +\startsubsection[title={\type {write_nl}}] + +\libindex{write_nl} + +\startfunctioncall +texio.write_nl( target, s, ...) +texio.write_nl( s, ...) +\stopfunctioncall + +This function behaves like \type {texio.write}, but make sure that the given +strings will appear at the beginning of a new line. You can pass a single empty +string if you only want to move to the next line. + +\stopsubsection + +\startsubsection[title={\type {setescape}}] + +\libindex{setescape} + +You can disable \type {^^} escaping of control characters by passing a value of +zero. + +\stopsubsection + +\startsubsection[title={\type {closeinput}}] + +\libindex{closeinput} + +This function that should be used with care. It acts as \prm {endinput} but at +the \LUA\ end. You can use it to (sort of) force a jump back to \TEX. Normally a +\LUA\ will just collect prints and at the end bump an input level and flush these +prints. This function can help you stay at the current level but you need to know +what you're doing (or more precise: what \TEX\ is doing with input). + +\stopsubsection + +\stopsection + +\startsection[title={The \type {token} library}][library=token] + +\startsubsection[title={The scanner}] + +\topicindex{libraries+\type{token}} +\topicindex{tokens} + +\libindex{scan_keyword} +\libindex{scan_keywordcs} +\libindex{scan_int} +\libindex{scan_real} +\libindex{scan_float} +\libindex{scan_dimen} +\libindex{scan_glue} +\libindex{scan_toks} +\libindex{scan_code} +\libindex{scan_string} +\libindex{scan_argument} +\libindex{scan_word} +\libindex{scan_csname} +\libindex{scan_list} + +The token library provides means to intercept the input and deal with it at the +\LUA\ level. The library provides a basic scanner infrastructure that can be used +to write macros that accept a wide range of arguments. This interface is on +purpose kept general and as performance is quite ok. One can build additional +parsers without too much overhead. It's up to macro package writers to see how +they can benefit from this as the main principle behind \LUATEX\ is to provide a +minimal set of tools and no solutions. The scanner functions are probably the +most intriguing. + +\starttabulate[|l|l|p|] +\DB function \BC argument \BC result \NC \NR +\TB +\NC \type{scan_keyword} \NC string \NC returns true if the given keyword is gobbled; as with + the regular \TEX\ keyword scanner this is case insensitive + (and \ASCII\ based) \NC \NR +\NC \type{scan_keywordcs} \NC string \NC returns true if the given keyword is gobbled; this variant + is case sensitive and also suitable for \UTF8 \NC \NR +\NC \type{scan_int} \NC \NC returns an integer \NC \NR +\NC \type{scan_real} \NC \NC returns a number from e.g.\ \type {1}, \type {1.1}, \type {.1} with optional collapsed signs \NC \NR +\NC \type{scan_float} \NC \NC returns a number from e.g.\ \type {1}, \type {1.1}, \type {.1}, \type {1.1E10}, , \type {.1e-10} with optional collapsed signs \NC \NR +\NC \type{scan_dimen} \NC infinity, mu-units \NC returns a number representing a dimension and or two numbers being the filler and order \NC \NR +\NC \type{scan_glue} \NC mu-units \NC returns a glue spec node \NC \NR +\NC \type{scan_toks} \NC definer, expand \NC returns a table of tokens tokens \NC \NR +\NC \type{scan_code} \NC bitset \NC returns a character if its category is in the given bitset (representing catcodes) \NC \NR +\NC \type{scan_string} \NC \NC returns a string given between \type {{}}, as \type {\macro} or as sequence of characters with catcode 11 or 12 \NC \NR +\NC \type{scan_argument} \NC \NC this one is simular to \type {scanstring} but also accepts a \type {\cs} + (which then get expanded) \NC \NR +\NC \type{scan_word} \NC \NC returns a sequence of characters with catcode 11 or 12 as string \NC \NR +\NC \type{scan_csname} \NC \NC returns \type {foo} after scanning \type {\foo} \NC \NR +\NC \type{scan_list} \NC \NC picks up a box specification and returns a \type {[h|v]list} node \NC \NR +\LL +\stoptabulate + +The scanners can be considered stable apart from the one scanning for a token. +The \type {scan_code} function takes an optional number, the \type {keyword} +function a normal \LUA\ string. The \type {infinity} boolean signals that we also +permit \type {fill} as dimension and the \type {mu-units} flags the scanner that +we expect math units. When scanning tokens we can indicate that we are defining a +macro, in which case the result will also provide information about what +arguments are expected and in the result this is separated from the meaning by a +separator token. The \type {expand} flag determines if the list will be expanded. + +The string scanner scans for something between curly braces and expands on the +way, or when it sees a control sequence it will return its meaning. Otherwise it +will scan characters with catcode \type {letter} or \type {other}. So, given the +following definition: + +\startbuffer +\def\bar{bar} +\def\foo{foo-\bar} +\stopbuffer + +\typebuffer \getbuffer + +we get: + +\starttabulate[|l|Tl|l|] +\DB name \BC result \NC \NR +\TB +\NC \type {\directlua{token.scan_string()}{foo}} \NC \directlua{context("{\\red\\type {"..token.scan_string().."}}")} {foo} \NC full expansion \NC \NR +\NC \type {\directlua{token.scan_string()}foo} \NC \directlua{context("{\\red\\type {"..token.scan_string().."}}")} foo \NC letters and others \NC \NR +\NC \type {\directlua{token.scan_string()}\foo} \NC \directlua{context("{\\red\\type {"..token.scan_string().."}}")}\foo \NC meaning \NC \NR +\LL +\stoptabulate + +The \type {\foo} case only gives the meaning, but one can pass an already +expanded definition (\prm {edef}'d). In the case of the braced variant one can of +course use the \prm {detokenize} and \prm {unexpanded} primitives since there we +do expand. + +The \type {scan_word} scanner can be used to implement for instance a number scanner: + +\starttyping +function token.scan_number(base) + return tonumber(token.scan_word(),base) +end +\stoptyping + +This scanner accepts any valid \LUA\ number so it is a way to pick up floats +in the input. + +You can use the \LUA\ interface as follows: + +\starttyping +\directlua { + function mymacro(n) + ... + end +} + +\def\mymacro#1{% + \directlua { + mymacro(\number\dimexpr#1) + }% +} + +\mymacro{12pt} +\mymacro{\dimen0} +\stoptyping + +You can also do this: + +\starttyping +\directlua { + function mymacro() + local d = token.scan_dimen() + ... + end +} + +\def\mymacro{% + \directlua { + mymacro() + }% +} + +\mymacro 12pt +\mymacro \dimen0 +\stoptyping + +It is quite clear from looking at the code what the first method needs as +argument(s). For the second method you need to look at the \LUA\ code to see what +gets picked up. Instead of passing from \TEX\ to \LUA\ we let \LUA\ fetch from +the input stream. + +In the first case the input is tokenized and then turned into a string, then it +is passed to \LUA\ where it gets interpreted. In the second case only a function +call gets interpreted but then the input is picked up by explicitly calling the +scanner functions. These return proper \LUA\ variables so no further conversion +has to be done. This is more efficient but in practice (given what \TEX\ has to +do) this effect should not be overestimated. For numbers and dimensions it saves +a bit but for passing strings conversion to and from tokens has to be done anyway +(although we can probably speed up the process in later versions if needed). + +\stopsubsection + +\startsubsection[title= {Picking up one token}] + +\libindex {get_next} +\libindex {scan_token} +\libindex {expand} + +The scanners look for a sequence. When you want to pick up one token from the +input you use \type {get_next}. This creates a token with the (low level) +properties as discussed next. This token is just the next one. If you want to +enforce expansion first you can use \type {scan_token}. Internally tokens are +characterized by a number that packs a lot of information. In order to access +the bits of information a token is wrapped in a userdata object. + +The \type {expand} function will trigger expansion of the next token in the +input. This can be quite unpredictable but when you call it you probably know +enough about \TEX\ not to be too worried about that. It basically is a call to +the internal expand related function. + +\stopsubsection + +\startsubsection[title={Creating tokens}] + +\libindex{create} +\libindex{new} + +\libindex{is_defined} +\libindex{is_token} +\libindex{biggest_char} + +\libindex{commands} +\libindex{command_id} + +\libindex{get_command} +\libindex{get_cmdname} +\libindex{get_csname} +\libindex{get_id} +\libindex{get_active} +\libindex{get_expandable} +\libindex{get_protected} +\libindex{get_mode} +\libindex{get_index} +\libindex{get_tok} + +\libindex{get_next} + +The creator function can be used as follows: + +\starttyping +local t = token.create("relax") +\stoptyping + +This gives back a token object that has the properties of the \prm {relax} +primitive. The possible properties of tokens are: + +\starttabulate[|l|p|] +\DB name \BC explanation \NC \NR +\TB +\NC \type {command} \NC a number representing the internal command number \NC \NR +\NC \type {cmdname} \NC the type of the command (for instance the catcode in case of a + character or the classifier that determines the internal + treatment \NC \NR +\NC \type {csname} \NC the associated control sequence (if applicable) \NC \NR +\NC \type {id} \NC the unique id of the token \NC \NR +\NC \type {tok} \NC the full token number as stored in \TEX \NC \NR +\NC \type {active} \NC a boolean indicating the active state of the token \NC \NR +\NC \type {expandable} \NC a boolean indicating if the token (macro) is expandable \NC \NR +\NC \type {protected} \NC a boolean indicating if the token (macro) is protected \NC \NR +\NC \type {mode} \NC a number either representing a character or another entity \NC \NR +\NC \type {index} \NC a number running from 0x0000 upto 0xFFFF indicating a \TEX\ register index \NC \NR +\LL +\stoptabulate + +Alternatively you can use a getter \type {get_} to access a property +of a token. + +The numbers that represent a catcode are the same as in \TEX\ itself, so using +this information assumes that you know a bit about \TEX's internals. The other +numbers and names are used consistently but are not frozen. So, when you use them +for comparing you can best query a known primitive or character first to see the +values. + +You can ask for a list of commands: + +\starttyping +local t = token.commands() +\stoptyping + +The id of a token class can be queried as follows: + +\starttyping +local id = token.command_id("math_shift") +\stoptyping + +If you really know what you're doing you can create character tokens by not +passing a string but a number: + +\starttyping +local letter_x = token.create(string.byte("x")) +local other_x = token.create(string.byte("x"),12) +\stoptyping + +Passing weird numbers can give side effects so don't expect too much help with +that. As said, you need to know what you're doing. The best way to explore the +way these internals work is to just look at how primitives or macros or \prm +{chardef}'d commands are tokenized. Just create a known one and inspect its +fields. A variant that ignores the current catcode table is: + +\starttyping +local whatever = token.new(123,12) +\stoptyping + +You can test if a control sequence is defined with \type {is_defined}, which +accepts a string and returns a boolean: + +\starttyping +local okay = token.is_defined("foo") +\stoptyping + +The largest character possible is returned by \type {biggest_char}, just in case you +need to know that boundary condition. + +\stopsubsection + +\startsubsection[title={Macros}] + +\topicindex {macros} + +\libindex{set_macro} +\libindex{get_macro} +\libindex{get_meaning} +\libindex{set_char} +\libindex{set_lua} +\libindex{get_functions_table} + +The \type {set_macro} function can get upto 4 arguments: + +\starttyping +set_macro("csname","content") +set_macro("csname","content","global") +set_macro("csname") +\stoptyping + +You can pass a catcodetable identifier as first argument: + +\starttyping +set_macro(catcodetable,"csname","content") +set_macro(catcodetable,"csname","content","global") +set_macro(catcodetable,"csname") +\stoptyping + +The results are like: + +\starttyping + \def\csname{content} +\gdef\csname{content} + \def\csname{} +\stoptyping + +The \type {get_macro} function can be used to get the content of a macro while +the \type {get_meaning} function gives the meaning including the argument +specification (as usual in \TEX\ separated by \type {->}). + +The \type {set_char} function can be used to do a \prm {chardef} at the +\LUA\ end, where invalid assignments are silently ignored: + +\starttyping +set_char("csname",number) +set_char("csname",number,"global") +\stoptyping + +A special one is the following: + +\starttyping +set_lua("mycode",id) +set_lua("mycode",id,"global","protected") +\stoptyping + +This creates a token that refers to a \LUA\ function with an entry in the table +that you can access with \type {lua.get_functions_table}. It is the companion +to \lpr {luadef}. When the first (and only) argument is true the size will preset +to the value of \type {texconfig.function_size}. + +\stopsubsection + +\startsubsection[title={Pushing back}] + +\libindex{get_next} +\libindex{put_next} + +There is a (for now) experimental putter: + +\starttyping +local t1 = token.get_next() +local t2 = token.get_next() +local t3 = token.get_next() +local t4 = token.get_next() +-- watch out, we flush in sequence +token.put_next { t1, t2 } +-- but this one gets pushed in front +token.put_next ( t3, t4 ) +\stoptyping + +When we scan \type {wxyz!} we get \type {yzwx!} back. The argument is either a table +with tokens or a list of tokens. The \type {token.expand} function will trigger +expansion but what happens really depends on what you're doing where. + +\stopsubsection + +\startsubsection[title={Nota bene}] + +When scanning for the next token you need to keep in mind that we're not scanning +like \TEX\ does: expanding, changing modes and doing things as it goes. When we +scan with \LUA\ we just pick up tokens. Say that we have: + +\starttyping +\bar +\stoptyping + +but \type {\bar} is undefined. Normally \TEX\ will then issue an error message. +However, when we have: + +\starttyping +\def\foo{\bar} +\stoptyping + +We get no error, unless we expand \type {\foo} while \type {\bar} is still +undefined. What happens is that as soon as \TEX\ sees an undefined macro it will +create a hash entry and when later it gets defined that entry will be reused. So, +\type {\bar} really exists but can be in an undefined state. + +\startbuffer[demo] +bar : \directlua{tex.print(token.scan_csname())}\bar +foo : \directlua{tex.print(token.scan_csname())}\foo +myfirstbar : \directlua{tex.print(token.scan_csname())}\myfirstbar +\stopbuffer + +\startlines +\getbuffer[demo] +\stoplines + +This was entered as: + +\typebuffer[demo] + +The reason that you see \type {bar} reported and not \type {myfirstbar} is that +\type {\bar} was already used in a previous paragraph. + +If we now say: + +\startbuffer +\def\foo{} +\stopbuffer + +\typebuffer \getbuffer + +we get: + +\startlines +\getbuffer[demo] +\stoplines + +And if we say + +\startbuffer +\def\foo{\bar} +\stopbuffer + +\typebuffer \getbuffer + +we get: + +\startlines +\getbuffer[demo] +\stoplines + +When scanning from \LUA\ we are not in a mode that defines (undefined) macros at +all. There we just get the real primitive undefined macro token. + +\startbuffer +\directlua{local t = token.get_next() tex.print(t.id.." "..t.tok)}\myfirstbar +\directlua{local t = token.get_next() tex.print(t.id.." "..t.tok)}\mysecondbar +\directlua{local t = token.get_next() tex.print(t.id.." "..t.tok)}\mythirdbar +\stopbuffer + +\startlines +\getbuffer +\stoplines + +This was generated with: + +\typebuffer + +So, we do get a unique token because after all we need some kind of \LUA\ object +that can be used and garbage collected, but it is basically the same one, +representing an undefined control sequence. + +\stopsubsection + +\stopsection + +\stopchapter + +\stopcomponent -- cgit v1.2.3