From 33e29b1ba0661b0f58605749528362a0e12eae52 Mon Sep 17 00:00:00 2001 From: Context Git Mirror Bot Date: Wed, 24 Feb 2016 12:15:08 +0100 Subject: 2016-02-24 11:22:00 --- .../manuals/languages/languages-appendix.tex | 48 ++ .../general/manuals/languages/languages-back.tex | 14 + .../general/manuals/languages/languages-basics.tex | 348 +++++++++ .../manuals/languages/languages-contents.tex | 13 + .../general/manuals/languages/languages-cover.tex | 133 ++++ .../manuals/languages/languages-environment.tex | 347 +++++++++ .../manuals/languages/languages-goodies.tex | 138 ++++ .../manuals/languages/languages-hyphenation.tex | 810 +++++++++++++++++++++ .../manuals/languages/languages-introduction.tex | 69 ++ .../general/manuals/languages/languages-labels.tex | 141 ++++ .../general/manuals/languages/languages-mkiv.tex | 38 + .../manuals/languages/languages-numbering.tex | 295 ++++++++ .../manuals/languages/languages-sorting.tex | 235 ++++++ 13 files changed, 2629 insertions(+) create mode 100644 doc/context/sources/general/manuals/languages/languages-appendix.tex create mode 100644 doc/context/sources/general/manuals/languages/languages-back.tex create mode 100644 doc/context/sources/general/manuals/languages/languages-basics.tex create mode 100644 doc/context/sources/general/manuals/languages/languages-contents.tex create mode 100644 doc/context/sources/general/manuals/languages/languages-cover.tex create mode 100644 doc/context/sources/general/manuals/languages/languages-environment.tex create mode 100644 doc/context/sources/general/manuals/languages/languages-goodies.tex create mode 100644 doc/context/sources/general/manuals/languages/languages-hyphenation.tex create mode 100644 doc/context/sources/general/manuals/languages/languages-introduction.tex create mode 100644 doc/context/sources/general/manuals/languages/languages-labels.tex create mode 100644 doc/context/sources/general/manuals/languages/languages-mkiv.tex create mode 100644 doc/context/sources/general/manuals/languages/languages-numbering.tex create mode 100644 doc/context/sources/general/manuals/languages/languages-sorting.tex (limited to 'doc/context/sources/general/manuals/languages') diff --git a/doc/context/sources/general/manuals/languages/languages-appendix.tex b/doc/context/sources/general/manuals/languages/languages-appendix.tex new file mode 100644 index 000000000..d8f33e44a --- /dev/null +++ b/doc/context/sources/general/manuals/languages/languages-appendix.tex @@ -0,0 +1,48 @@ +% language=uk + +\startcomponent languages-appendix + +\environment languages-environment + +\startchapter[title=Appendix][color=darkgray] + +\startsection[title=The language files] + + Todo. + +\stopsection + +\startsection[title=The \type {mtx-patterns} script] + + Todo. + +\stopsection + +\startsection[title=Installed sorters] + +\startbuffer +\usemodule[s-languages-sorting] + +\showinstalledsorting +\stopbuffer + +\typebuffer \blank[2*line] \getbuffer + +\stopsection + +\startsection[title=Verbose counters] + +\startbuffer +\usemodule[s-languages-counters] + +\showverbosecounters[language={en,es}] +\stopbuffer + +\typebuffer \blank[2*line] \getbuffer + +\stopsection + +\stopchapter + +\stopcomponent + diff --git a/doc/context/sources/general/manuals/languages/languages-back.tex b/doc/context/sources/general/manuals/languages/languages-back.tex new file mode 100644 index 000000000..aadcc3aa4 --- /dev/null +++ b/doc/context/sources/general/manuals/languages/languages-back.tex @@ -0,0 +1,14 @@ +% \doifmodeelse {simple} { +% +% \page +% \page[empty,left] +% +% \startMPpage +% DrawCoverPage("back") ; +% \stopMPpage +% +% } { +% +% % not needed as it's part of the cover page +% +% } diff --git a/doc/context/sources/general/manuals/languages/languages-basics.tex b/doc/context/sources/general/manuals/languages/languages-basics.tex new file mode 100644 index 000000000..39ce840f3 --- /dev/null +++ b/doc/context/sources/general/manuals/languages/languages-basics.tex @@ -0,0 +1,348 @@ +% language=uk + +\environment languages-environment + +\startcomponent languages-basics + +\startchapter[title=Some basics][color=darkyellow] + +\startsection[title={Introduction}] + +In this chapter we will see how we can toggle between languages. A first +introduction to patterns will be given. Some details of how to control the +hyphenation with specific patterns will be given in a later chapter. + +\stopsection + +\startsection[title={Available languages}] + +When you use the English version of \CONTEXT\ you will default to US English as +main language. This means that hyphenation will be US specific, which by the way +is different from the rules in GB. All labels that are generated by the system +are also in English. Languages can often be accessed by names like \type +{english} or \type {dutch} although it is quite common to use the short tags like +\type {en} and \type {nl}. Because we want to be as compatible as possible with +\MKII, there are quite some synonyms. The following table lists the languages that +for which support is built|-|in.\footnote {More languages can be defined. It is +up to users to provide the information.} + +\startbuffer +\usemodule[languages-system] + +\loadinstalledlanguages +\showinstalledlanguages +\stopbuffer + +\getbuffer + +\noindentation You can call up such a table with the following commands: + +\typebuffer + +\noindentation Instead you can run \type {context --global languages-system.mkiv}. + +As you can see, many languages have hyphenation patterns but for Japanese, +Korean, Chinese as well as Arabic languages they make no sense. The patterns are +loaded on demand. The number is the internal number that is used in the engine; a +user never has to use that number. Numbers $<1$ are used to disable hyphenation. +The file tag is used to locate and load a specification. Such files have names +like type {lang-nl.lua}. + +Some languages share the same hyphenation patterns but can have demands that +differ, like labels or quotes. The characters shown in the table are those found +in the pattern files. The number of patterns differs a lot between languages. +This relates to the systematic behind them. Some languages use word stems, others +base their hyphenation on syllables. Some language have inflections which adds to +the complexity while others can combine words in ways that demand special care +for word boundaries. Of course a low or high number can signal a low quality as +well, but most pattern collections are assembled over many years and updated when +for instance spelling rules change. I think that we can safely say that most patterns +are quite stable and of good quality. + +\stopsection + +\startsection[title=Switching] + +The document language is set with + +\starttyping +\mainlanguage[en] +\stoptyping + +but when you want to apply the proper hyphenation rules to an embedded language +you can use: + +\starttyping +\language[en] +\stoptyping + +or just: + +\starttyping +\en +\stoptyping + +The main language determines what labels show up, how numbering happens, in what +way dates get formatted, etc. Normally the \typ {\mainlanguage} command comes +before the \typ {\starttext} command. + +\stopsection + +\startsection[title=Hyphenation] + +In \LUATEX\ each character that gets typeset not only carries a font id and character +code, but also a language number. You can switch language whenever you want and +the change will be carried with the characters. Switching within a word doesn't make +sense but it is permitted: + +\starttabulate[|||T|] +\NC 1 \NC \type{\de incrediblykompliziert} \NC \hyphenatedword{\de incrediblykompliziert} \NC \NR +\NC 2 \NC \type{\en incrediblykompliziert} \NC \hyphenatedword{\en incrediblykompliziert} \NC \NR +\NC 3 \NC \type{\en incredibly\de kompliziert} \NC \hyphenatedword{\en incredibly\de kompliziert} \NC \NR +\NC 4 \NC \type{\en incredibly\de\-kompliziert} \NC \hyphenatedword{\en incredibly\de\-kompliziert} \NC \NR +\NC 5 \NC \type{\en incredibly\de-kompliziert} \NC \hyphenatedword{\en incredibly\de-kompliziert} \NC \NR +\stoptabulate + +In the line 4 we have a \type {\-} between the two words, and in the last +line just a \type {-}. If you look closely you will notice that the snippets +can be quite small. If we typeset a word with a 1mm text width we get this: + +\blank \noindentation \start \en \hsize 1mm incredibly \par \stop \blank + +If you are familiar with the details of hyphenation, you know that the number of +characters at the end and beginning of a word is controlled by the two variables +\typ {\lefthyphenmin} and \typ {\righthyphenmin}. However, these only influence +the hyphenation process. What bits and pieces eventually end up on a line is +determined by the par builder and there the \type {\hsize} matters. In practice +you will not run into these situations, unless you have extreme long words and a +narrow column. + +Hyphenation normally is limited to regular characters that make up the alphabet of +a language. It is insensitive for capitalization as the following text shows: + +\blank + +\startnarrower \noindentation +\hyphenatedword {This time the musical distraction while developing code came +from watching youtube performances of Cory Henry (also known from Snarky Puppy, +a conglomerate of excellent players). Just search the web for his name with \quote +{Stevie Wonder and Michael Jackson Tribute}. There is no keyboard he can't play. +Another interesting keyboard player is Sun Rai (a short name for Rai +Thistlethwayte, just google for \quote {The Beatles, Come Together, Live Piano +Acoustic with Loop Pedal}, or do a combined search with \quote {Matt +Chamberlain}. Okay, and talking of keyboards, let's not forget Vika Yermolyeva +(vkgoeswild) as she's one of a kind too on the web. And then there is Jacob +Collier, in one word: incredible (or hyphenated the Dutch way {\nl incredible}, +let me repeat that in French {\fr incredible}).} \footnote {Get me right, there +are of course many more fantastic musicians.} +\stopnarrower + +\blank + +\noindentation Of course, names are often short and don't need to be hyphenated +(or the left and right settings prohibit it). Another complication with names is +that they can come from another language so we either need to switch language +temporarily or we need to add an exception (more about that later). + +\stopsection + +\startsection[title=Primitives] + +In traditional \TEX\ the language is not a property of a character but is +triggered by a signal in the (so called) list. Think of: + +\starttyping +this is nederlands mixed with english +\stoptyping + +This number is set by the primitive \typ {\language}. Language triggers are +injected into the list depending on the value of this number. There is also a \typ +{\setlanguage} primitive that can inject triggers without setting the \typ +{\language} number. Because in \LUATEX\ the state is kept with the character +you don't need to worry about the subtle differences here. + +In \CONTEXT\ the \typ {\language} and \typ {\setlanguage} commands are overloaded +by a more advanced switch macro. You cannot assume that they work as explained in +general manuals about \TEX. Currently you can still assign a number but that +might change. Just consider the language to be an abstraction and don't mess with +this number. Both commands not only change the current language but also do +specific initializations when needed. + +What characters get involved in hyhenation is historically determines by the so +called \type {\lccode} values. Each character can have such a value which maps +an uppercase to a lowercase character. This concept has been extended in \ETEX\ +where it binds to a pattern set (language). However, in \CONTEXT\ the user never +has to worry about such details. + +% The \type {\patterns} primitive is +% The \type {\hyphenation} primitive is + +In traditional hyphenation there will not be hyphenated if the sum of \typ +{\lefthyphenmin} and \typ {\righthyphenmin} exceeds 62. This limitation is not +present in the to be presented \LUA\ variant of this routine as there is no +good reason for this limitation other than implementation constraints. + +\stopsection + +\startsection[title=Control] + +We already mentioned \typ {\lefthyphenmin} and \typ {\righthyphenmin}. These +two variables control the area in a word that is subjected to hyphenation. +Setting these values is a matter of taste but making them too small can result in +bad hyphenation when the patterns are made with the assumptions that certain +minima are used. Using a \typ {\lefthyphenmin} of 2 while the patterns are made +with a value of 3 in mind is a bad idea. + +\startlinecorrection[blank] +\startluacode +context.bTABLE { option = "stretch", align= "middle" } + context.bTR() + context.bTD { ny = 2, align = "middle,lohi", style = "monobold" } + context.verbatim("\\lefthyphenmin") + context.eTD() + context.bTD { nx = 5, style = "monobold" } + context.verbatim("\\righthyphenmin") + context.eTD() + context.eTR() + context.bTR() + for right=1,5 do + context.bTD() + context.mono(right) + context.eTD() + end + context.eTR() + for left=1,5 do + context.bTR() + context.bTD() + context.mono(left) + context.eTD() + for right=1,5 do + context.bTD() + context("\\lefthyphenmin %s \\righthyphenmin %s \\hyphenatedword{interesting}",left,right) + context.eTD() + end + context.eTR() + end +context.eTABLE() +\stopluacode +\stoplinecorrection + +When \TEX\ breaks a paragraph into lines it will try do so without hyphenation. +When that fails (read: when the badness becomes too high) a next effort will take +hyphenation into account. \footnote {Because in \LUATEX\ we always hyphenate +there is no real gain in trying not to hyphenate. Because in traditional \TEX\ +hyphenation happens on the fly a pass without hyphenating makes more sense.} When +the badness is still too high, an optional emergency pass can be made but only +when the tolerances are set to permit this. In \CONTEXT\ you can try these +settings when you get too many over- or underfull boxes reported on the console. + +\starttyping +\setupalign[tolerant] +\setupalign[verytolerant] +\setupalign[verytolerant,stretch] +\stoptyping + +Personally I tend to use the last setting, especially in automated flows. After +all, \TEX\ will not apply stretch unless it's really needed. + +The two \typ {\*hyphenmin} parameters can be set any time and the current value +is stored with each character. They can also be set with the language which we +will see later. + +When \TEX\ hyphenates words it has to decide where a word starts and ends. In +traditional \TEX\ the words starts normally at a character that falls within the +scope of the hyphenator. It ends at when a box (hlist or vlist) is seen, but also +at a rule, discretionary, accent (forget about this in \CONTEXT) or math. An +example will be given in the chapter that discussed the \LUA\ alternative. + +\stopsection + +\startsection[title=Installing] + + todo + +\stopsection + +\startsection[title=Modes] + +Languages are one of the mechanisms where you can access the current state. There are +for instance two (official) macros that contain the current (main) language: + +\startbuffer +\starttabulate[||Tc|] +\HL +\NC \bf macro \NC \bf value \NC \NR +\HL +\NC \type {\currentmainlanguage} \NC \currentmainlanguage \NC \NR +\NC \type {\currentlanguage} \NC \currentlanguage \NC \NR +\HL +\stoptabulate +\stopbuffer + +\getbuffer + +When we have set \type {\language[nl]} we get this: + +\start \nl \getbuffer \stop + +If you write a style that needs to adapt to a language you can use modes. There +are several ways to do this: + +\startbuffer +\language[nl] + +\startmode[**en] + \color[darkred]{main english} +\stopmode + +\startmode[*en] + \color[darkred]{local english} +\stopmode + +\startmode[**nl] + \color[darkblue]{main dutch} +\stopmode + +\startmode[*nl] + \color[darkblue]{local dutch} +\stopmode + +\startmodeset + [*en] {\color[darkgreen]{english set}} + [*nl] {\color[darkgreen]{dutch set}} +\stopmodeset +\stopbuffer + +\typebuffer + +\noindentation This typesets: + +\blank \start \setupindenting[no] \getbuffer \stop \blank + +When you use setups you can use the following trick: + +\startbuffer +\language[nl] + +\startsetups language:en + \color[darkorange]{something english} +\stopsetups + +\startsetups language:nl + \color[darkorange]{something dutch} +\stopsetups + +\setups[language:\currentlanguage] +\stopbuffer + +\typebuffer + +\noindentation As expected we get: + +\blank \start \setupindenting[no] \getbuffer \stop \blank + +\stopsection + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/languages/languages-contents.tex b/doc/context/sources/general/manuals/languages/languages-contents.tex new file mode 100644 index 000000000..10fadb56b --- /dev/null +++ b/doc/context/sources/general/manuals/languages/languages-contents.tex @@ -0,0 +1,13 @@ +% language=uk + +\startcomponent languages-contents + +\environment languages-environment + +\starttitle[title=Contents][color=darkgray] + +\placelist[chapter][criterium=text] + +\stoptitle + +\stopcomponent diff --git a/doc/context/sources/general/manuals/languages/languages-cover.tex b/doc/context/sources/general/manuals/languages/languages-cover.tex new file mode 100644 index 000000000..75a033b5f --- /dev/null +++ b/doc/context/sources/general/manuals/languages/languages-cover.tex @@ -0,0 +1,133 @@ +% language=uk + +\startcomponent languages-cover + +\environment languages-environment + +\startbuffer[abstract] + +This book explains how we support languages (and +scripts) in \CONTEXT\ \MKIV\ and \LUATEX. Some of +the mechanisms discussed are generic and not +\CONTEXT\ specific. We discuss the way languages are +dealt with in the engine, hyphenation, standard +features and additional goodies. Tracing and the +extensibility of code are also discussed. + +\stopbuffer + +\startsetups document:abstract + \framed [ + foregroundstyle=bold, + foregroundcolor=white, + width=7.5cm, + align={normal,tolerant}, + frame=off, + strut=no, + ] { + \getbuffer[abstract] + } +\stopsetups + +\startMPextensions + + def DrawCoverPage (expr what) = + + begingroup ; + + save SpineWidth ; numeric SpineWidth ; SpineWidth := 8mm ; + save PaperBleed ; numeric PaperBleed ; PaperBleed := 2mm ; % todo + + StartCover ; + + save width, size, anchor ; + + numeric width, size ; pair anchor, offset ; + + color ColorVariant[] ; + + % ColorVariant[1] := \MPcolor{darkred} ; + % ColorVariant[2] := \MPcolor{darkgreen} ; + % ColorVariant[3] := \MPcolor{darkblue} ; + % ColorVariant[4] := \MPcolor{darkyellow} ; + + ColorVariant[1] := \MPcolor{darkmagenta} ; + ColorVariant[2] := \MPcolor{darkorange} ; + ColorVariant[3] := \MPcolor{darkyellow} ; + ColorVariant[4] := \MPcolor{darkcyan} ; + + fill CoverPage enlarged PaperBleed withcolor \MPcolor{darkgray} ; + + fill Spine bottomenlarged -.5CoverHeight withcolor ColorVariant[3] ; + fill Spine topenlarged -.5CoverHeight withcolor ColorVariant[2] ; + + width := FrontPageWidth ; + height := FrontPageHeight ; + size := 4 * width / 3 ; + offset := (-1cm,1cm) ; + anchor := .5[lrcorner CoverPage,urcorner CoverPage] ; + + fill anchored.llft(lltriangle scaled size, urcorner FrontPage) withcolor ColorVariant[1] ; + fill anchored.urt (urtriangle scaled size, llcorner FrontPage) withcolor ColorVariant[2] ; + fill anchored.lrt (lrtriangle scaled size, ulcorner FrontPage) withcolor ColorVariant[3] ; + fill anchored.ulft(ultriangle scaled size, lrcorner FrontPage) withcolor ColorVariant[4] ; + + fill anchored.lrt (lrtriangle scaled size, ulcorner BackPage) withcolor ColorVariant[1] ; + fill anchored.llft(lltriangle scaled size, urcorner BackPage) withcolor ColorVariant[3] ; + fill anchored.ulft(ultriangle scaled size, lrcorner BackPage) withcolor ColorVariant[2] ; + fill anchored.urt (urtriangle scaled size, llcorner BackPage) withcolor ColorVariant[4] ; + + draw thetextext.llft(textext("\bf Languages in \ConTeXt\hskip-.1em") rotated 45 ysized .350height, anchor shifted (6*offset+offset)) withcolor white ; + draw thetextext.llft(textext("\bf explaining luatex and mkiv") rotated 45 ysized .275height, anchor shifted (5*offset+offset)) withcolor white ; + draw thetextext.llft(textext("\bf Hans Hagen") rotated 45 ysized .200height, anchor shifted (2*offset+offset)) withcolor white ; + draw thetextext.llft(textext("\bf PRAGMA ADE") rotated 45 ysized .200height, anchor shifted (1*offset+offset)) withcolor white ; + + % for the moment + + draw thetextext.top(textext("\bf work in progress") xsized 4cm, lrcorner Page shifted (-3cm,1cm)) withcolor white ; + + % till here + + width := BackPageWidth ; + + draw thetextext(textext("\bf\setups[document:abstract]") xsized .65width rotated 45 , center BackPage) withcolor white ; + + anchor := .5[ulcorner Spine,urcorner Spine] shifted (0,-1cm); + + draw thetextext.bot(textext("\bf Languages in \ConTeXt\hskip-.1em") rotated 90 xsized .8SpineWidth, anchor) withcolor white ; + + anchor := .5[llcorner Spine,lrcorner Spine] shifted (0,1cm); + + draw thetextext.top(textext("\bf Hans Hagen") rotated 90 xsized .8SpineWidth, anchor) withcolor white ; + + StopCover ; + + if what = "front" : + clip currentpicture to FrontPage ; + elseif what = "back" : + clip currentpicture to BackPage ; + else : + drawboundary CoverPage ; + fi ; + + endgroup ; + + enddef ; + +\stopMPextensions + +\doifmodeelse {simple} { + + \startMPpage + DrawCoverPage("front") ; + \stopMPpage + +} { + + \startMPpage + DrawCoverPage("cover") ; + \stopMPpage + +} + +\stopcomponent diff --git a/doc/context/sources/general/manuals/languages/languages-environment.tex b/doc/context/sources/general/manuals/languages/languages-environment.tex new file mode 100644 index 000000000..ff529a8d1 --- /dev/null +++ b/doc/context/sources/general/manuals/languages/languages-environment.tex @@ -0,0 +1,347 @@ +\startenvironment languages-environment + +\usemodule[visual] +\usemodule[simulate] + +\dontcomplain + +\definepapersize + [book] + [width=18cm, + height=24cm] + +\setuppapersize + [book] + +\startmode[oversized] + + \setuppapersize + [book] + [oversized] + + \setuplayout + [marking=on] + +\stopmode + +\setuplayout + [location=middle, + topspace=1.5cm, + bottomspace=2cm, + backspace=2cm, + cutspace=2cm, + header=0cm, + footer=0cm, + margindistance=.25cm, + margin=1.25cm, + width=middle, + height=middle] + +\setuplayout + [style=\ss] + +\usetypescript + [dejavu-condensed] + +\setupbodyfont + [ipaex,9pt] + +\setupbodyfont + [dejavu,9pt] + +\definetyping + [narrowtyping] + [typing] + [bodyfont=dejavu-condensed] + +% This is way too ugly for a manual: +% +% \setuptyping +% [indentnext=no] +% +% \setupindenting +% [medium,yes] + +\setupwhitespace + [big] + +\defineoverlay + [page] + [\useMPgraphic{page}] + +\setupbackgrounds + [page] + [background=page] + +\setuphead + [chapter,section,subsection] + [color=\namedstructureuservariable{chapter}{color}] + +\setuphead + [chapter] + [style=\bfc] + +\setuphead + [section] + [style=\bfb] + +\setuphead + [subsection] + [style=\bf, + before=\blank, + after=\blank] + +\startsetups document:chapter:inside + \definecolor[maincolor][1.0(\namedheadparameter{chapter}{color})] % this expands the color + \definecolor[halfcolor][0.5(maincolor,white)] +\stopsetups + +\setuphead + [chapter] + [insidesection=\setup{document:chapter:inside}] + +\setuppagenumbering + [alternative=doublesided, + location=] + +\setuplist + [aligntitle=yes] + +\setuplist + [chapter] + [pagenumber=no, + style=bold, + before={\blank\startcolor[\structurelistuservariable{color}]}, + after={\placelist[section]\stopcolor}] + +\setuplist + [chapter,section] + [width=3em] + +\startuseMPgraphic{page} + + StartPage ; + + linecap := butt ; + + if OnRightPage : + + path p ; p := ( + urcorner Page shifted (-2cm,0) -- + urcorner Page -- + urcorner Page shifted (0,-2cm) -- cycle + ) shifted (-2.5mm,-2.5mm) ; + + else : + + path p ; p := ( + ulcorner Page shifted (2cm,0) -- + ulcorner Page -- + ulcorner Page shifted (0,-2cm) -- cycle + ) shifted (2.5mm,-2.5mm) ; + + fi ; + + fill p + withpen pencircle scaled 1mm + % withcolor \MPcolor{\namedstructureuservariable{chapter}{color}} ; + withcolor \MPcolor{maincolor} ; + + draw thetextext("\bf\userpagenumber", + if OnRightPage : urcorner p shifted (-5mm,-5mm) else : ulcorner p shifted (5mm,-5mm) fi) + withcolor white ; + + if OnRightPage : + + path p ; p := ( + lrcorner Page shifted (-5cm,0) -- + lrcorner Page + ) shifted (-5mm,10mm) + + else : + + path p ; p := ( + llcorner Page shifted (5cm,0) -- + llcorner Page + ) shifted (5mm,10mm) ; + + fi ; + + draw p + withpen pencircle scaled 1mm + % withcolor \MPcolor{\namedstructureuservariable{chapter}{color}} ; + withcolor \MPcolor{maincolor} ; + + draw if OnRightPage : + thetextext.lft("\bf\getspecificstructuretitle{chapter}",lrcorner Page shifted (-5mm,5mm)) + else : + thetextext.rt ("\bf\getspecificstructuretitle{chapter}",llcorner Page shifted ( 5mm,5mm)) + fi withcolor \MPcolor{\namedstructureuservariable{chapter}{color}} ; + % fi withcolor \MPcolor{maincolor} ; + + StopPage ; +\stopuseMPgraphic + +\definecolor[orange] [r=1,g=.6,b=.1] + +\definecolor[middlegray] [s=.75] +\definecolor[darkgray] [s=.25] +\definecolor[darkred] [r=.5] +\definecolor[darkgreen] [g=.5] +\definecolor[darkblue] [b=.5] + +\definecolor[darkyellow] [.5(red,green)] +\definecolor[darkmagenta][.5(red,blue)] +\definecolor[darkcyan] [.5(green,blue)] + +\definecolor[darkorange] [.5(orange)] + +\definecolor [mix-1] [r=1,g=.75,b=.25] \definecolor [darkmix-1][.5(mix-1)] +\definecolor [mix-2] [r=1,g=.25,b=.75] \definecolor [darkmix-2][.5(mix-2)] +\definecolor [mix-3] [r=.75,g=1,b=.25] \definecolor [darkmix-3][.5(mix-3)] +\definecolor [mix-4] [r=.75,g=.25,b=1] \definecolor [darkmix-4][.5(mix-4)] +\definecolor [mix-5] [r=.25,g=1,b=.75] \definecolor [darkmix-5][.5(mix-5)] +\definecolor [mix-6] [r=.25,g=.75,b=1] \definecolor [darkmix-6][.5(mix-6)] + +% \blackrule[height=1cm,width=10cm,color=mix-1] \blackrule[height=1cm,width=10cm,color=darkmix-1] +% \blackrule[height=1cm,width=10cm,color=mix-2] \blackrule[height=1cm,width=10cm,color=darkmix-2] +% \blackrule[height=1cm,width=10cm,color=mix-3] \blackrule[height=1cm,width=10cm,color=darkmix-3] +% \blackrule[height=1cm,width=10cm,color=mix-4] \blackrule[height=1cm,width=10cm,color=darkmix-4] +% \blackrule[height=1cm,width=10cm,color=mix-5] \blackrule[height=1cm,width=10cm,color=darkmix-5] +% \blackrule[height=1cm,width=10cm,color=mix-6] \blackrule[height=1cm,width=10cm,color=darkmix-6] + +\definecolor[maincolor] [darkgray] + +% modules + +\usemodule + [abr-01] + +\setupsorting + [logo] + [style=] + +\usemodule [chart] +\usemodule [nodechart] + +% \usemodule [s] [fonts-tables] +% \usemodule [s] [fonts-missing] +% \usemodule [s] [fonts-vectors] +% \usemodule [s] [fonts-features] + +\usemodule [s] [languages-words] +\usemodule [s] [languages-hyphenation] +\usemodule [s] [languages-frequencies] +\usemodule [s] [languages-sorting] +\usemodule [s] [languages-counters] +\usemodule [s] [languages-system] + +\usemodule [s] [math-extensibles] + +\setupFLOWchart + [width=6em, + height=3em, + offset=-2em, % maybe default : todo: hoffset and voffset + dx=2em, + dy=2em] + +\setupFLOWlines + [color=maincolor] + +\setupFLOWshapes + [rulecolor=maincolor] + +% tables + +\setuptabulate + [rulethickness=.5mm, + rulecolor=maincolor] + +% special commands + +\startuniqueMPgraphic{reference}{color} + fill + .5[llcorner OverlayBox,ulcorner OverlayBox] -- + .5[ulcorner OverlayBox,urcorner OverlayBox] -- + .5[urcorner OverlayBox,lrcorner OverlayBox] -- + .5[lrcorner OverlayBox,llcorner OverlayBox] -- cycle + withcolor \MPvar{color} ; +\stopuniqueMPgraphic + +\startuniqueMPgraphic{reference}{color} + path p ; p := OverlayBox enlarged -1mm ; + filldraw + ulcorner p -- + urcorner p -- + lrcorner p -- + .5[lrcorner p,llcorner p] shifted (0,-1ExHeight) -- + llcorner p -- cycle + withpen pencircle scaled 1mm + withcolor \MPvar{color} ; + setbounds currentpicture to OverlayBox enlarged 1ExHeight ; +\stopuniqueMPgraphic + +\defineoverlay[reference][\uniqueMPgraphic{reference}{color=maincolor,}] + +\definecolor[maincolor][red] + +\definemargindata + [appendixdata] +% [inner] + [outer] + [stack=yes] + +\definemarginframed + [appendixdata] + [width=3.5em, + height=\lineheight, % we know what goes in there + align=middle, + offset=overlay, + foregroundcolor=white, + background=reference] + +% todo: +% +% \appendixdata[reference=bla]{} +% +% whole data + +% interaction + +\setupinteraction + [state=start, + click=no, + color=, + contrastcolor=, + style=] + +% extra fonts (shared among chapters) + +\definefontfeature[demo-onum][kern=yes,onum=yes] +%definefontfeature[demo-lnum][kern=yes,lnum=yes] +\definefontfeature[demo-tnum][kern=yes,tnum=yes] +\definefontfeature[demo-pnum][kern=yes,pnum=yes] +\definefontfeature[demo-zero][zero=yes] +\definefontfeature[demo-none][] + +\definefont[DemoOnumLM][file:lmroman10-regular*demo-onum at 42pt] +%definefont[DemoLnumLM][file:lmroman10-regular*demo-lnum at 42pt] +\definefont[DemoTnumLM][file:lmroman10-regular*demo-tnum at 42pt] +\definefont[DemoPnumLM][file:lmroman10-regular*demo-pnum at 42pt] + +\definefont[DemoZeroLM][file:lmroman10-regular*demo-zero at 42pt] +\definefont[DemoNoneLM][file:lmroman10-regular*demo-none at 42pt] + +\definefont[DemoZeroLT][file:lmtypewriter10-regular*demo-zero at 42pt] +\definefont[DemoNoneLT][file:lmtypewriter10-regular*demo-none at 42pt] + +\definestartstop + [notabene] + [before=\blank, + after=\blank, + style=\em] + +\setuphyphenation + [method=default] + +\stopenvironment diff --git a/doc/context/sources/general/manuals/languages/languages-goodies.tex b/doc/context/sources/general/manuals/languages/languages-goodies.tex new file mode 100644 index 000000000..fbbfafc34 --- /dev/null +++ b/doc/context/sources/general/manuals/languages/languages-goodies.tex @@ -0,0 +1,138 @@ +% language=uk + +\environment languages-environment + +\startcomponent languages-goodies + +\startchapter[title=Goodies][color=darkorange] + +\startsection[title=Introduction] + +There are some features that will only be used in rare cases. They were often +implemented as experiment but found useful enough to keep around. + +\stopsection + +\startsection[title=Spell checking] + +There are some means to check the spelling of words in your document but get it +right: \CONTEXT\ is not a spell|-|checker. These features were added in order to +be able to do some quick checking of documents written by multiple authors. There +are currently three options and we only show a simple examples. + +First you need to load word lists. These are either text files with just words +separated by spacing. + +\starttyping[color=maincolor] +foobar foo-bar foo=bar foo{}{}{}bar foo{}{}{bar} +\stoptyping + +All these words become \type {foobar} which means that one can use words with +discretionary specifications. A text list is loaded with: + +\startbuffer +\loadspellchecklist[en][t:/manuals/lua/words-en.txt] +\stopbuffer + +\typebuffer \getbuffer + +Instead you can load a \LUA\ file with words. Here we use the same structure that +we use for the spell checker provided for \SCITE: + +\starttyping[color=maincolor] +return { + max = 9, + min = 6, + n = 2, + words = { + ["barfoo"] = "Barfoo" + ["foobarred"] = "foobarred", + } +} +\stoptyping + +We use the same load command (you can also load bytecode files with suffix \type +{luc} this way): + +\startbuffer +\loadspellchecklist[nl][t:/scite/data/context/lexers/data/spell-nl.lua] +\stopbuffer + +\typebuffer \getbuffer + +Usage boils down to enabling the checker. If needed we can add more methods. The +first method colors the known and unknown colors. Words shorter then the +threshold of 4 will be skipped. + +\startbuffer +\setupspellchecking[state=start,method=1] +\en Is this written right or is this wromg?\par % m -> n error +\nl Is dit goed geschreven of niet?\par +\setupspellchecking[state=stop] +\stopbuffer + +\typebuffer \startpacked \getbuffer \stoppacked + +You can change the colors: + +\starttyping +\definecolor[word:yes] [g=.75] +\definecolor[word:no] [r=.75] +\stoptyping + +The second method doesn't show anything but produces a file \type +{jobname.words}) with used words. The \type {found} value of \type {list} is used +as key in the produced table. + +\startbuffer +\setupspellchecking[state=start,method=2,list=found] +\en Is this written right or is this wrong?\par +\nl Is dit goed geschreven of niet?\par +\setupspellchecking[state=stop] +\stopbuffer + +\typebuffer \startpacked \getbuffer \stoppacked + +The produced table is: + +\typefile{\jobname.words} + +The result can be traced with a module: + +\startbuffer +\usemodule[s-languages-words] + +\showwords +\stopbuffer + +\typebuffer + +This shows up as: + +\getbuffer + +The third mechanism colors languages differently. We only defined a few colors: + +\starttyping +\definecolor[word:en] [b=.75] +\definecolor[word:de] [r=.75] +\definecolor[word:nl] [g=.75] +\definecolor[word:unknown][r=.75,g=.75] +\stoptyping + +but you can of course define a color for your favourite language in a similar way. + +\startbuffer +\setupspellchecking[state=start,method=3] +\en Is this written right or is this wrong?\par +\nl Is dit goed geschreven of niet?\par +\setupspellchecking[state=stop] +\stopbuffer + +\typebuffer \startpacked \getbuffer \stoppacked + +\stopsection + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/languages/languages-hyphenation.tex b/doc/context/sources/general/manuals/languages/languages-hyphenation.tex new file mode 100644 index 000000000..48e6eb385 --- /dev/null +++ b/doc/context/sources/general/manuals/languages/languages-hyphenation.tex @@ -0,0 +1,810 @@ +% language=uk + +\environment languages-environment + +\startcomponent languages-hyphenation + +\startchapter[title=Hyphenation][color=darkmagenta] + +\startsection[title=How it works] + +Proper hyphenation is one of the strong points of \TEX. Hyphenation in \TEX\ is +done using so called hyphenation patterns. Making these patterns is an art +and most users (including me) happily use whatever is available. Patterns can be +created automatically using \type {patgen} but often manual tweaking is needed +too. A pattern looks as follows: + +\starttyping +pat1tern +\stoptyping + +This means as much as: you can split the word \type {pattern} in two pieces, with +a hyphen between the two \type {t}'s. Actually it will also split the word \type +{patterns} because the hyphenation mechanism looks at substrings. When no number +between characters in a pattern is given, a zero is assumed. This means as much +as {\em undefined}. An even number inhibits hyphenation, an odd number permits +it. The larger the number (weight), the more influence it has. A more restricted +pattern is: + +\starttyping +.pat1tern. +\stoptyping + +Here the periods set the word boundaries. The pattern dictionary for us +english has smaller patterns and the next trace shows how these are applied. + +\starthyphenation[traditional] +\showhyphenationtrace[en][pattern] +\stophyphenation + +The effective hyphenation of a word is determined by several factors: + +\startitemize[packed] +\startitem the current language, each language can have different patterns \stopitem +\startitem the characters, as some characters might block hyphenation \stopitem +\startitem the settings of \type {\lefthyphenmin} and \type {\righthyphenmin} \stopitem +\stopitemize + +A place where a word can be hyphenated is called a discretionary. When \TEX\ +analyzes a stream, it will inject discretionary nodes into that stream. + +\starttyping +pat\discretionary{-}{}{}tern. +\stoptyping + +In traditional \TEX\ hyphenation, ligature building and kerning are tightly +interwoven which is quite effective. However, there was also a strong +relationship between the current font and hyphenation. This is a side effect of +traditional \TEX\ having at most 256 characters in a font and the fact that the +used character is fact a reference to a slot in a font. There a character in the +input initially ends up as a character node and eventually becomes a glyph node. +For instance two characters \type {fi} can become a ligature glyph representing +this combination. + +In \LUATEX\ the hyphenation, ligature building and kerning stages are separated +and can be overloaded. In \CONTEXT\ all three can be replaced by code written in +\LUA. Because normally hyphenation happens before font logic is applied, there is +no relationship with font encoding. I wrote the first \LUA\ version of the +hyohenator on a rainy weekend and the result was not that bad so it was presented +at the 2014 \CONTEXT\ meeting. After some polishing I decided to add this routine +to the standard \MKIV\ repertoire which then involved some proper interfacing. + +You can enable the \LUA\ variant with the following command: + +\starttyping +\setuphyphenation[method=traditional] +\stoptyping + +We call this method \type {traditional} because in principle we can have +many more methods and this one is (supposed to be) mostly compatible to the +built-in method. This is a global setting. You can switch back with: + +\starttyping +\setuphyphenation[method=default] +\stoptyping + +In the next sections we will see how we can provide alternatives within the +traditional method. These alternatives can be set local and therefore can operate +over a limited range of characters. + +One complication in interfacing is that \TEX\ has grouping (which permits local +settings) and we want to limit some of the above functionality using groups. At +the same time hyphenation is a paragraph related action so we need to enable the +hyphenation related code at a global level (or at least make sure that it gets +exercised by forcing a \type {\par}). That means that the alternative +hyphenator has to be quite compatible so that we could just enable it for a whole +document. This can have an impact on performance but in practice that can be +neglected. In \LUATEX\ the \LUA\ variant is 4~times slower than the built-in one, +in \LUAJITTEX\ it's 3~times slower. But the good news is that the amount of time +spent in the hyphenator is relatively small compared to other manipulations and +macro expansion. The additional time needed for loading and preparing the +patterns into a more \LUA\ specific format can be neglected. + +You can check how words get hyphenated using the patterns management script: + +\starttyping +>mtxrun --script patterns --hyphenate language + +hyphenator | +hyphenator | . l a n g u a g e . . l a n g u a g e . +hyphenator | 0a2n0 0 0 2 0 0 0 0 0 0 +hyphenator | 2a0n0g0 0 2 2 0 0 0 0 0 0 +hyphenator | 0n1g0u0 0 2 2 1 0 0 0 0 0 +hyphenator | 0g0u4a0 0 2 2 1 0 4 0 0 0 +hyphenator | 2g0e0.0 0 2 2 1 0 4 2 0 0 +hyphenator | .0l2a2n1g0u4a2g0e0. . l a n-g u a g e . +hyphenator | +mtx-patterns | us 3 3 : language : lan-guage +\stoptyping + +\stopsection + +\startsection[title=The last words] + +Mid 2014 we had to upgrade a style for a \PDF\ assembly service: chapters from +(technical) school books are combined into arbitrary new books. There are some +nasty aspects with this flow: for instance, all section numbers in a chapter are +replaced by new numbers and this also involves figure and table prefixes. +It boils down to splitting up books, analyzing the typeset content and +preparing it for replacements. The structure is described in \XML\ files so that +we can generate tables of contents. The reason for not generating from \XML\ +sources is that the publisher doesn't have a \XML\ workflow and that books +already were available. Also, books from several series are combined and even +within a series structure (and rendering) differs. + +What has this to do with hyphenation? Writing a style for such a flow always +results in a more complex one that estimated and as usual it's in the details. +The original style was written in \MKII\ and used some box juggling to achieve +reasonable results but in \MKIV\ we can do better. + +Each chapter has a title and books get titles and subtitles as well. The titles +are typeset each time a new book is composed. This happens within some layout +constraints. Think of constraints like these: + +\startitemize[packed] +\startitem the title goes on top of a shape that doesn't permit much overflow \stopitem +\startitem there can be very long words (not uncommon in Dutch or German) \stopitem +\startitem a short word or hyphenated part should not end up on the last line \stopitem +\startitem the left and right hyphenation minima are at least four \stopitem +\stopitemize + +The last requirement is a compromise because in most cases publishers seem to +want ragged right not hyphenated rendering (at least in Dutch schoolbooks). The +arguments for this are quite weak and probably originate in fear of bad rendering +given past experiences. It's this kind of situations that drive the development +of the more obscure features that ship with \CONTEXT\ and a (partial) solution +for this specific case will be given later. + +If you look at thousands of titles and turn these into (small) paragraphs \TEX\ +does a pretty good job. It's the few exceptions that we need to catch. The next +examples demonstrate such an extreme case. + +\startbuffer[example] +\dorecurse{5} { % dejavu + \startlinecorrection[blank] + \bTABLE + \bTR + \bTD[align=middle,width=2em,foregroundstyle=bold] + #1 + \eTD + \bTD[align={verytolerant,flushleft},width=15em,offset=1ex] + \hsize \dimexpr11\emwidth-#1\dimexpr.5\emwidth\relax + \dontcomplain + \lefthyphenmin=4\righthyphenmin=4 + \blackrule[color=darkyellow,width=\hsize,height=-3pt,depth=5pt]\par + \begstrut\getbuffer[long]\endstrut\par + \eTD + \bTD[align={verytolerant,flushleft},width=15em,offset=1ex] + \sethyphenationfeatures[demo] + \hsize \dimexpr11\emwidth-#1\dimexpr.5\emwidth\relax + \dontcomplain + \blackrule[color=darkyellow,width=\hsize,height=-3pt,depth=5pt]\par + \begstrut\getbuffer[long]\endstrut\par + \eTD + \eTR + \eTABLE + \stoplinecorrection +} +\stopbuffer + +\definehyphenationfeatures + [demo] + [rightwords=1, + lefthyphenmin=4, + righthyphenmin=4] + +\startbuffer[long] +a verylongword and then anevenlongerword +\stopbuffer + +\starthyphenation[traditional] + \enabletrackers[hyphenator.visualize] + \getbuffer[example]\par + \disabletrackers[hyphenator.visualize] +\stophyphenation + +Of course in practice there need to be some reasonable width and when we pose +these limits the longest possible word should fit into the allocated space. In +these examples the rule shows the width. In the right columns we see a red +colored word and that one will not get hyphenated. + +\stopsection + +\startsection[title=Explicit hyphens] + +Another special case that we needed to handle were (compound) words with explicit +hyphens. Because often data comes from \XML\ files we can not really control the +typesetting as in a \TEX\ document where the author sees what gets done. So here +we need a way to turn these hyphens into proper hyphenation directives and at the +same time permit the words to be hyphenated. + +\definehyphenationfeatures + [demo] + [hyphens=yes, + lefthyphenmin=4, + righthyphenmin=4] + +\startbuffer[long] +a very-long-word and then an-even-longer-word +\stopbuffer + +\starthyphenation[traditional] + \enabletrackers[hyphenator.visualize] + \getbuffer[example]\par + \disabletrackers[hyphenator.visualize] +\stophyphenation + +\stopsection + +\startsection[title=Extended patterns] + +As with more opened up mechanisms, in \MKIV\ we can extend functionality. As an +example I have implemented the extensions discussed in the article by László +Németh in the Proceedings of Euro\TEX\ 2006: {\em Hyphenation in OpenOffice.org} +(TUGboat, Volume 27, 2006). The syntax for these extension is somewhat ugly and +involves optional offsets and ranges. \footnote {I'm not sure if there were ever +patterns released that used this syntax.} + +\startbuffer +\registerhyphenationpattern[nl][e1ë/e=e] +\registerhyphenationpattern[nl][a9atje./a=t,1,3] +\registerhyphenationpattern[en][eigh1tee/t=t,5,1] +\registerhyphenationpattern[de][c1k/k=k] +\registerhyphenationpattern[de][schif1f/ff=f,5,2] +\stopbuffer + +\typebuffer \getbuffer + +These patterns result in the following hyphenations: + +\starthyphenation[traditional] + \switchtobodyfont[big] + \starttabulate[|||] + \NC reëel \NC \language[nl]\hyphenatedcoloredword{reëel} \NC \NR + \NC omaatje \NC \language[nl]\hyphenatedcoloredword{omaatje} \NC \NR + \NC eighteen \NC \language[en]\hyphenatedcoloredword{eighteen} \NC \NR + \NC Zucker \NC \language[de]\hyphenatedcoloredword{Zucker} \NC \NR + \NC Schiffahrt \NC \language[de]\hyphenatedcoloredword{Schiffahrt} \NC \NR + \stoptabulate +\stophyphenation + +In a specification, the \type {.} indicates a word boundary and numbers indicate +the weight of a breakpoint. The optional extended specification comes after the +\type {/}. The values separated by a \type {=} are the pre and post sequences: +these end up at the end of the current line and beginning of the next one. The +optional numbers are the start position and length. These default to~1 and~2, so +in the first example they identify \type {eë} (the weights don't count). + +There is a pitfall here. When the language already has patterns that for +instance prohibit a hyphen between \type {e} and type {ë}, like \type{e2ë}, we +need to make sure that we give our new one a higher priority, which is why we +used a \type{e9ë}. + +This feature is somewhat experimental and can be improved. Here is a more \LUA-ish +way of setting such patterns: + +\starttyping +local registerpattern = + languages.hyphenators.traditional.registerpattern + +registerpattern("nl","e1ë", { + start = 1, + length = 2, + before = "e", + after = "e", +} ) + +registerpattern("nl","a9atje./a=t,1,3") +\stoptyping + +Just adding extra patterns to an existing set without much testing is not wise. For +instance we could add these to the dutch dictionary: + +\starttyping +\registerhyphenationpattern[nl][e3ë/e=e] +\registerhyphenationpattern[nl][o3ë/o=e] +\registerhyphenationpattern[nl][e3ï/e=i] +\registerhyphenationpattern[nl][i3ë/i=e] +\registerhyphenationpattern[nl][a5atje./a=t,1,3] +\registerhyphenationpattern[nl][toma8at5je] +\stoptyping + +That would work oke well for words like + +\starttyping +coëfficiënt +geïntroduceerd +copiëren +omaatje +tomaatje +\stoptyping + +However, the last word only goes right because we explicitly added a pattern +for it. One reason is that the existing patterns already contain rules to +prevent weird hyphenations. The same is true for the accented characters. So, +consider these examples and coordinate additional patterns with other users +so that errors can be identified. + +\stopsection + +\startsection[title=Exceptions] + +We have a variant on the \TEX\ primitive \type {\hyphenation}, the official way +to register a specific way to hyphenate a word. + +\startbuffer +\registerhyphenationexception[aaaaa-bbbbb] +aaaaabbbbb \par +\stopbuffer + +\typebuffer + +\noindentation This code is self explaining and results in: + +\blank + +\starthyphenation[traditional] +\setupindenting[no]\hsize 1mm \lefthyphenmin 1 \righthyphenmin 1 \getbuffer +\stophyphenation + +\noindentation There can be multiple hyphens and even multiple words in such a +specification: + +\startbuffer +\registerhyphenationexception[aaaaa-bbbbb cc-ccc-ddd-dd] +aaaaabbbbb \par +cccccddddd \par +\stopbuffer + +\typebuffer + +\noindentation We get: + +\blank + +\starthyphenation[traditional] +\setupindenting[no]\hsize 1mm \lefthyphenmin 1 \righthyphenmin 1 \getbuffer +\stophyphenation + + +\stopsection + +\startsection[title=Boundaries] + +A box, rule, math or discretionary will end a word and prohibit hyphenation +of that word. Take this example: + +\startbuffer[demo] +whatever \par +whatever\hbox{!} \par +\vl whatever\vl \par +whatever$x$ \par +whatever-whatever \par +\stopbuffer + +\typebuffer[demo] + +These lines will hyphenate differently and in traditional \TEX\ you need to +insert penalties and|/|or glue to get around it. In the \LUA\ variant we can +enable that limitation. + +\startbuffer +\definehyphenationfeatures + [strict] + [rightedge=tex] +\stopbuffer + +\typebuffer \getbuffer + +Here we show the three variants: traditional \TEX\ and \LUA\ with and without +strict settings. + +\starttabulate[|p|p|p|] +\HL +\NC \ttbf \hbox to 11em{default\hss} +\NC \ttbf \hbox to 11em{traditional\hss} +\NC \ttbf \hbox to 11em{traditional strict\hss} +\NC \NR +\HL +\NC \starthyphenation[default] \hsize1mm \getbuffer[demo] \stophyphenation +\NC \starthyphenation[traditional] \hsize1mm \getbuffer[demo] \stophyphenation +\NC \starthyphenation[traditional] \sethyphenationfeatures[strict] + \hsize1mm \getbuffer[demo] \stophyphenation +\NC \NR +\HL +\stoptabulate + +By default \CONTEXT\ is configured to hyphenate words that start with an +uppercase character. This behaviour is controlled in \TEX\ by the \typ {\uchyph} +variable. A positive value will enable this and a negative one disables it. + +\starttabulate[|p|p|p|p|] +\HL +\NC \ttbf \hbox to 8em{default 0\hss} +\NC \ttbf \hbox to 8em{default 1\hss} +\NC \ttbf \hbox to 8em{traditional 0\hss} +\NC \ttbf \hbox to 8em{traditional 1\hss} +\NC \NR +\HL +\NC \starthyphenation[default] \hsize1mm \uchyph\zerocount TEXified \dontcomplain \stophyphenation +\NC \starthyphenation[traditional] \hsize1mm \uchyph\zerocount TEXified \dontcomplain \stophyphenation +\NC \starthyphenation[default] \hsize1mm \uchyph\plusone TEXified \dontcomplain \stophyphenation +\NC \starthyphenation[traditional] \hsize1mm \uchyph\plusone TEXified \dontcomplain \stophyphenation +\NC \NR +\HL +\stoptabulate + +The \LUA\ variants behaves the same as the built-in implementation (that of course +remains the reference). + +\stopsection + +\startsection[title=Plug-ins] + +The default hyphenator is similar to the built-in one, with a couple of +extensions as mentioned. However, you can plug in your own code, given that it +does return a proper hyphenation result. One reason for providing this plug is +that there are users who want to play with hyphenators based on a different +logic. In \CONTEXT\ we already have some methods to deal with languages that +(for instance) have no spaces but split on words or syllabes. A more tight +integration with the hyphenator can have advantages so I will explore these +options when there is demand. + +A result table indicates where we can break a word. If we have a four character +word and can break after the second character, the result looks like this: + +\starttyping +result = { false, true, false, false } +\stoptyping + +Instead of \type {true} we can also have a table that has entries like the +extensions discussed in a previous section. Let's give an example of a +plug-in. + +\startbuffer +\startluacode + local subset = { + a = true, + e = true, + i = true, + o = true, + u = true, + y = true, + } + + languages.hyphenators.traditional.installmethod("test", + function(dictionary,word,n) + local t = { } + for i=1,#word do + local w = word[i] + if subset[w] then + t[i] = { + before = "<" .. w, + after = w .. ">", + left = false, + right = false, + } + else + t[i] = false + end + end + return t + end + ) +\stopluacode +\stopbuffer + +\typebuffer \getbuffer + +Here we hyphenate on vowels and surround them by angle brackets when +split over lines. This alternative is installed as follows: + +\startbuffer +\definehyphenationfeatures + [demo] + [alternative=test] +\stopbuffer + +\typebuffer \getbuffer + +We can now use it as follows: + +\starttyping +\setuphyphenation[method=traditional] +\sethyphenationfeatures[demo] +\stoptyping + +When applied to one the tufte example we get: + +\startbuffer[demo] +\starthyphenation[traditional] + \setuptolerance[tolerant] + \sethyphenationfeatures[demo] + \noindentation % \dontleavehmode + \input tufte\relax +\stophyphenation +\stopbuffer + +\blank \startnarrower \getbuffer[demo] \stopnarrower \blank + +A more realistic (but not perfect) example is the following: + +\startbuffer +\startluacode + local packslashes = false + + local specials = { + ["!"] = "before", ["?"] = "before", + ['"'] = "before", ["'"] = "before", + ["/"] = "before", ["\\"] = "before", + ["#"] = "before", + ["$"] = "before", + ["%"] = "before", + ["&"] = "before", + ["*"] = "before", + ["+"] = "before", ["-"] = "before", + [","] = "before", ["."] = "before", + [":"] = "before", [";"] = "before", + ["<"] = "before", [">"] = "before", + ["="] = "before", + ["@"] = "before", + ["("] = "before", + ["["] = "before", + ["{"] = "before", + ["^"] = "before", ["_"] = "before", + ["`"] = "before", + ["|"] = "before", + ["~"] = "before", + -- + [")"] = "after", + ["]"] = "after", + ["}"] = "after", + } + + languages.hyphenators.traditional.installmethod("url", + function(dictionary,word,n) + local t = { } + local p = nil + for i=1,#word do + local w = word[i] + local s = specials[w] + if s == "after" then + s = { + start = 1, + length = 1, + after = w, + left = false, + right = false, + } + specials[w] = s + elseif s == "before" then + s = { + start = 1, + length = 1, + before = w, + left = false, + right = false, + } + specials[w] = s + end + if not s then + s = false + elseif w == p and w == "/" then + t[i-1] = false + end + t[i] = s + if packslashes then + p = w + end + end + return t + end + ) +\stopluacode +\stopbuffer + +\typebuffer \getbuffer + +Again we define a plug: + +\startbuffer +\definehyphenationfeatures + [url] + [characters=all, + alternative=url] +\stopbuffer + +\typebuffer \getbuffer + +So, we only break a line after symbols. + +\startlinecorrection[blank] + \starthyphenation[traditional] + \tt + \sethyphenationfeatures[url] + \scale[width=\hsize]{\hyphenatedcoloredword{http://www.pragma-ade.nl}} + \stophyphenation +\stoplinecorrection + +\noindentation A quick test can look as follows: + +\startbuffer +\starthyphenation[traditional] + \sethyphenationfeatures[url] + \tt + \dontcomplain + \hsize 1mm + http://www.pragma-ade.nl +\stophyphenation +\stopbuffer + +\typebuffer + +Or: + +\getbuffer + +\stopsection + +\startsection[title=Blocking ligatures] + +Yet another predefined feature is the ability to block a ligature. In +traditional \TEX\ this can be done by putting a \type {{}} between +the characters, although that effect can get lost when the text is +manipulated. The natural way to do this in a \UNICODE\ environment +is to use the special characters \type {zwj} and \type {zwnj}. + +We use the following example lines: + +\startbuffer[sample] +supereffective \blank +superef\zwnj fective +\stopbuffer + +\typebuffer[sample] + +\noindentation and define two featuresets: + +\startbuffer +\definehyphenationfeatures + [demo-1] + [characters=\zwnj\zwj, + joiners=yes] + +\definehyphenationfeatures + [demo-2] + [joiners=no] +\stopbuffer + +\typebuffer \getbuffer + +\noindentation We limit the width to 1mm and get: + +\startlinecorrection[blank] +\bTABLE[option=stretch,offset=.5ex] + \bTR + \bTD \tx + \type{method=default} + \eTD + \bTD \tx + \type{method=traditional} + \eTD + \bTD \tx + \type{method=traditional}\par + \type{featureset=demo-1} + \eTD + \bTD \tx + \type{method=traditional}\par + \type{featureset=demo-2} + \eTD + \eTR + \bTR + \bTD + \hsize 1mm \dontcomplain + \starthyphenation[default] + \getbuffer[sample] + \stophyphenation + \eTD + \bTD + \hsize 1mm \dontcomplain + \starthyphenation[traditional] + \getbuffer[sample] + \stophyphenation + \eTD + \bTD + \hsize 1mm \dontcomplain + \starthyphenation[traditional] + \sethyphenationfeatures[demo-1] + \getbuffer[sample] + \stophyphenation + \eTD + \bTD + \hsize 1mm \dontcomplain + \starthyphenation[traditional] + \sethyphenationfeatures[demo-2] + \getbuffer[sample] + \stophyphenation + \eTD + \eTR +\eTABLE +\stoplinecorrection + +\stopsection + +\startsection[title=Special characters] + +The \type {characters} example can be used (to some extend) to do the +same as the breakpoints mechanism (compounds). + +\startbuffer +\definehyphenationfeatures + [demo-3] + [characters={()[]}] +\stopbuffer + +\typebuffer \blank \getbuffer \blank + +\startbuffer[demo] +\starthyphenation[traditional] + \sethyphenationfeatures[demo-3] + \dontcomplain + \hsize 1mm \noindentation + we use (super)special(ized) patterns +\stophyphenation +\stopbuffer + +\typebuffer[demo] \blank \getbuffer[demo] \blank + +We can make this more clever by adding patterns: + +\startbuffer +\registerhyphenationpattern[en][)9] +\registerhyphenationpattern[en][9(] +\stopbuffer + +\typebuffer \blank \getbuffer \blank + +\noindentation This gives: + +\blank \getbuffer[demo] \blank + +\noindentation A detailed trace shows that these patterns get applied: + +\starthyphenation[traditional] + \ttx + \showhyphenationtrace[en][(super)special(ized)] +\stophyphenation + +\unregisterhyphenationpattern[en][)9] +\unregisterhyphenationpattern[en][9(] + +\noindentation The somewhat weird hyphens at the edges will in practice not show +up because there is always one regular character there. + +\stopsection + +\startsection[title=Tracing] + +Among the tracing options (low level trackers) there is one for pattern developers: + +\startbuffer +\usemodule[s-languages-hyphenation] + +\startcomparepatterns[de,nl,en,fr] + \input zapf \quad (\showcomparepatternslegend) +\stopcomparepatterns +\stopbuffer + +\typebuffer + +The different hyphenation points are shown with colored bars. Some valid points +might not be shown because the font engine can collapse successive +discretionaries. + +\getbuffer + +\stopsection + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/languages/languages-introduction.tex b/doc/context/sources/general/manuals/languages/languages-introduction.tex new file mode 100644 index 000000000..25bbb1a90 --- /dev/null +++ b/doc/context/sources/general/manuals/languages/languages-introduction.tex @@ -0,0 +1,69 @@ +% language=uk + +\startcomponent languages-introduction + +\environment languages-environment + +\startchapter[title=Introduction][color=darkgray] + +This document describes an important property of the \TEX\ typesetting system and +\CONTEXT\ in particular: the ability to deal with different languages at the same +time. With languages we refer to natural languages. So, we're not going to +discuss the \TEX\ language itself, not \METAPOST, nor \LUA. + +The original application of \TEX\ was English that uses the Latin script. The +fonts that came with \TEX\ were suitable for that usage. When lines became too +long they could be hyphenated using so called hyphenation patterns. Due to the +implementation for many years there was a close relationship between fonts and +hyphenation. Although at some point many more languages and scripts were +supported, it was only when the \UNICODE\ aware variants showed up that +hyphenation and fonts were decoupled. This makes it much more easier to mix +languages that use different scripts. Although Greek, Cyrillic, Arabic, Chinese, +Japanese, Korean and other languages have been supported for a while using +(sometimes dirty) tricks, we now have cleaner implementations. + +We can hyphenate words in all languages (and scripts) that have a need for it, +that is, split it at the end of a line and add a symbol before and|/|or after the +break. The way words are broken into parts is called hyphenation and so called +patterns are used to achieve that goal. The way these patterns are constructed +and applied was part of the research related to \TEX\ development. The method +used is also applied in other programs and is probably one of the few popular +ways to deal with hyphenation. There have been ideas about extensions that cover +the demands of certain languages but so far nothing better has shown up. In the +end \TEX\ does a pretty decent job and more advanced tricks don't necessarily +lead to better results. + +Hyphenation is driven by a language number and that's about it. This means that +one cannot claim that \TEX\ in its raw form supports languages, other than that +it can hyphenate and use fonts that provide the glyphs. It's upto a macro package +to wrap this into a mechanism that provides the user an interface. So, when we +speak about language support, hyphenation is only one aspect. Labels, like the +\type {figure} in {\em figure~1.2} need to adapt to the main document language. +When dates are shown they can be language specific. Scientific units and math +function names can also be subjected to translation. Registers and other lists +have to be sorted according to specific rules. Spacing dan differ per language. + +In this manual we will cover some of functionality in \CONTEXT\ \MKIV\ that +relates to languages (and scripts). This manual is a compliment to other manuals, +articles and documentation. Here we mostly focus on the language aspects. Some of +the content (or maybe most) might looks alien and complex to you. This is because +one purpose of this manual is to provide a place to wrap up some aspects of +\CONTEXT. If you're not interested in that, just stick to the more general +manuals that also cover language aspects. + +\startnotabene + This document is still under construction. The functionality discussed here + will stay and more might show up. Of course there are errors, and they're all + mine. The text is not checked for spelling errors. Feel free to let me know + what should get added. +\stopnotabene + +\startlines +Hans Hagen +PRAGMA ADE, Hasselt NL +2013 \emdash\ 2016 +\stoplines + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/languages/languages-labels.tex b/doc/context/sources/general/manuals/languages/languages-labels.tex new file mode 100644 index 000000000..3d1c00c04 --- /dev/null +++ b/doc/context/sources/general/manuals/languages/languages-labels.tex @@ -0,0 +1,141 @@ +% language=uk + +\environment languages-environment + +\startcomponent languages-labels + +\startchapter[title=Labels][color=darkcyan] + +\startsection[title=Introduction] + +When we started using \TEX, I naturally started with plain \TEX. But it didn't +take long before we tried \LATEX. Because our documents were in Dutch one of the +first fights with this package was to get rid of the english labels. Because +rather soon we decided to cook up an alternative package, a decent label +mechanism was one of the first things to show up. And as soon as multiple +language typesetting gets into view, such a mechanism becomes one of those +language dependent features. In this chapter the basics will be covered. + +\stopsection + +\startsection[title=Defining labels] + +Before we define a label we need to define a label class. You probably seldom +need that but this is how it's done: + +\startbuffer +\definelabelclass [mylabel] +\stopbuffer + +\typebuffer \getbuffer + +There are some classes predefined: + +\starttabulate[|lB|l|] + \NC head \NC (complete) titles like \headtext {chapter} and \headtext {figure} \NC \NR + \NC label \NC in||text labels like \labeltext {chapter} and \labeltext {figure} \NC \NR + \NC mathlabel \NC function names like \mathlabeltext{sin} and \mathlabeltext{cos} \NC \NR + \NC taglabel \NC labels used for tagging purposed in the backend \NC \NR + \NC btxlabel \NC labels used in typesetting bibliographic items \NC \NR +\stoptabulate + +The physical units mechanism also uses labels: unit, operator, prefix and suffix. +All these labels are defined per language with a fall back on english. + +Given that we have defined class \type {mylabel}, a label itself is set like +this: + +\startbuffer +\setupmylabeltext + [en] + [first={},{ \NC word \NC \NR +\LL +\stoptabulate + +\stopsection + +% \startsection[title=Counters] +% +% \stopsection + +\stopchapter + +\stopcomponent diff --git a/doc/context/sources/general/manuals/languages/languages-sorting.tex b/doc/context/sources/general/manuals/languages/languages-sorting.tex new file mode 100644 index 000000000..abf7b292c --- /dev/null +++ b/doc/context/sources/general/manuals/languages/languages-sorting.tex @@ -0,0 +1,235 @@ +% language=uk + +\environment languages-environment + +\startcomponent languages-sorting + +\startchapter[title=Sorting][color=darkblue] + +\startsection[title=Introduction] + +Sorting is complex, not so much for English, Dutch, German, etc. only texts but +there are languages and scripts that are more demanding. There are several +complications: + +\startitemize + + \startitem + There can be characters that have accents, like à, á, â, ã, ä + \unknown\ that have a base shape a and in an index these often end up + close to each other. The order can differ per language. + \stopitem + + \startitem + There are upper and lowercase words and there can be different + expectations to them being mixed or separated. + \stopitem + \startitem + Some scripts have characters that are combinations, like Æ, and + one might want to see them as one character or two, in which the + second one obeys the sorting order. The shape can dominate here. + \stopitem + \startitem + Some scripts, like Japanese, are a combination of several scripts + and sorting then depends on normalization. + \stopitem + \startitem + When there are many glyphs, like in Chinese, the order can depend + on the complexity of the glyph and when we're lucky that order is + reflected in the numeric character order. + \stopitem +\stopitemize + +Often the rules are somewhat strict and one can doubt of the same rules would +have been imposed if computers had been developed earlier. Given discussions one +can doubt if the rules are really consistent or just there because someone (or a +group) with influence set the standard (not so much different from grammar). So, +if we deal with sorting, we do that in such a way that users can (to some extend) +influence the outcome. After all, one important aspect of typesetting and +organizing content is that the users gets the feeling of control and a diversion +from a standard can be part of that. The reader will often not notice these +details. In the next sections we will explore the way sorting is done in +\CONTEXT. The method evolved over a few decades. In \MKII\ sorting happened +between runs and it was just part of the processing of a document that users +never really saw in action. Sorting just happened and few users will have noticed +that we moved from a \MODULA\ program to a \PERL\ script and ended up with a +\RUBY\ script. In fact, there is a \LUA\ replacement but it never got tested well +because we moved in to \MKIV. There all happens inside the engine using \LUA. +Some principles stayed the same but we are more flexible now. + +\stopsection + +\startsection[title=How it works] + +How does sorting work out? Take these words: + +\startlines +abracadabra +abräcàdábra +àbracádabrä +ábracadàbra +äbrácadabrà +\stoplines + +As long as they end up in an order where the reader can find it, we're okay. +After all we're pretty good in pattern recognition. + +There are probably many ways to implement a sorter but the one we uses is more or +less a follow up on the one we had for over a decade and was the result of an +evolution based on user demand. It boils down to cleaning up the string in such a +way that it can be split into meaningful characters. One can argue that we should +use some kd of standardized sorting method but the problem is that we always have +to deal with for instance embedded tex commands and mixed content, for instance +numbers. And users using the same language can have different opinions about the +rules too. + +A word (or sequence of words) is split into characters. Because there can be +\TEX\ commands in there some cleanup happens beforehand. After that we create +several lists with numbers that will be compared when sorting two entries. + +\startluacode + +-- local ignoredoffset = sorters.constants.ignoredoffset +-- local replacementoffset = sorters.constants.replacementoffset +-- local digitsoffset = sorters.constants.digitsoffset +-- local digitsmaximum = sorters.constants.digitsmaximum + +local context = context + +local utfchar = utf.char +local utfyte = utf.byte +local concat = table.concat +local gsub = string.gsub +local formatters = string.formatters + +local f_char = formatters["%s"] +local f_byte = formatters["x%02X"] + +local meaning = { + ch = "raw character", + mm = "minus mapping", + zm = "zero mapping", + pm = "plus mapping", + mc = "lowercase - 1", + zc = "lowercase", + pc = "lowercase + 1", + uc = "unicode", +} + +local function show(s,key,bodyfont) + local c = s[key] + local t = { } + for i=1,#c do + local ci = c[i] + if type(ci) == "string" then + t[i] = f_char(ci) + else + t[i] = f_byte(ci) + end + end + t = concat(t,"~") + context.NC() context.maincolor() context(key) + context.NC() context.maincolor() context(meaning[key]) + context.NC() if bodyfont then context.switchtobodyfont{bodyfont} end context(t) + context.NC() context.NR() +end + +function document.ShowSortSplit(str,language,bodyfont) + sorters.setlanguage(language or "en") + local s = sorters.splitters.utf(str) + context.starttabulate{ "|Tl|Tlj2|Tp|" } + context.FL() + context.NC() + context.NC() context.maincolor() context(language) + context.NC() if bodyfont then context.switchtobodyfont{bodyfont} end context.maincolor() context(str) + context.NC() context.NR() + context.ML() + show(s,"ch",bodyfont) + show(s,"uc") + show(s,"zc") + show(s,"mc") + show(s,"pc") + show(s,"zm") + show(s,"mm") + show(s,"pm") + context.LL() + context.stoptabulate() +end + +\stopluacode + +We can best demonstrate this with a few examples. As usual an English language +example is trivial. + +\ctxlua{document.ShowSortSplit("abracadabra","en")} + +When we add an uppercase character we get a slightly different outcome: + +\ctxlua{document.ShowSortSplit("Abracadabra","en")} + +Some characters will be split, like \type {æ}: + +\ctxlua{document.ShowSortSplit("æsop","en")} + +It gets more complex when langiage specific demands kick in. Compare an English, German +and Austrian split: + +\ctxlua{document.ShowSortSplit("Abräcàdábra","en")} +\ctxlua{document.ShowSortSplit("Abräcàdábra","de")} +\ctxlua{document.ShowSortSplit("Abräcàdábra","de-at")} + +The way a character gets replaced, like \type {ä} into \type {ae}, is defined in +\type {sort-lan.lua} using \LUA\ tables. We will not explain all the obscure +details here; most of the work is already done, so users are not bothered by +these definitions. And new ones can often be made by copying and adapting an +existing one. + +The sorting itself is specified by a sequence: + +\starttabulate[|TlCT{maincolor}|Tl|] +\NC default \NC zc,pc,zm,pm,uc \NC \NR +\NC before \NC mm,mc,uc \NC \NR +\NC after \NC pm,mc,uc \NC \NR +\NC first \NC pc,mm,uc \NC \NR +\NC last \NC mc,mm,uc \NC \NR +\stoptabulate + +The raw character is what we get after the (language specific) replacement has +been applied and the unicodes are used when comparing. Lowercasing is done using +the \UNICODE\ lowercase code, but one can define language specific ones too. The +plus and minus variants can be used to force lowercase before or after uppercase. +The mapping is based on an alphabet specification so this can differ per language +and again we also provide plus and minus values that depend on case. When a +character has no case we use shapes instead. For instance, the shape of \type +{à} is \type {a}. Digits are treated special and currently get an offset so that +they end up last in the sort order. + +\defineregister[jindex] + +\startbuffer +ぱあ \jindex{ぱあ} +ぱー \jindex{ぱー} +ぱぁ \jindex{ぱぁ} +\stopbuffer + +{\switchtobodyfont[ipaex]\startlines\typebuffer\stoplines} + +This three entry index\jindex{ぱあ}\jindex{ぱー}\jindex{ぱぁ} should be sorted in the order: +{\switchtobodyfont[ipaex]\ruledhbox{ぱー}\enspace\ruledhbox{ぱぁ}\enspace\ruledhbox{ぱあ}}. + +{\mainlanguage[jp]\switchtobodyfont[ipaex]\placeregister[jindex][language=jp,n=1,method=default]} +{\mainlanguage[jp]\switchtobodyfont[ipaex]\placeregister[jindex][language=jp,n=1,method=zm]} + +\ctxlua{document.ShowSortSplit("ぱあ","jp","ipaex")} +\ctxlua{document.ShowSortSplit("ぱー","jp","ipaex")} +\ctxlua{document.ShowSortSplit("ぱぁ","jp","ipaex")} + +{\em To be continued!} + +\stopsection + +% ぱー $\prec$ ぱぁ $\prec$ ぱあ + +\stopchapter + +\stopcomponent -- cgit v1.2.3