beta 2012.05.30 11:26

16 files changed, 108 insertions, 25 deletions

diff --git a/scripts/context/lua/mtxrun.lua b/scripts/context/lua/mtxrun.lua
index 644c1d9b2..108f2a8a1 100644
--- a/scripts/context/lua/mtxrun.lua
+++ b/scripts/context/lua/mtxrun.lua
@@ -4087,8 +4087,10 @@ local one  = P(1)
 local two  = C(1) * C(1)
 local four = C(R(utfchar(0xD8),utfchar(0xFF))) * C(1) * C(1) * C(1)
 
+-- actually one of them is already utf ... sort of useless this one
+
 local pattern = P("\254\255") * Cs( (
-                    four   / function(a,b,c,d)
+                    four  / function(a,b,c,d)
                                 local ab = 0xFF * byte(a) + byte(b)
                                 local cd = 0xFF * byte(c) + byte(d)
                                 return utfchar((ab-0xD800)*0x400 + (cd-0xDC00) + 0x10000)
@@ -4099,7 +4101,7 @@ local pattern = P("\254\255") * Cs( (
                   + one
                 )^1 )
               + P("\255\254") * Cs( (
-                    four   / function(b,a,d,c)
+                    four  / function(b,a,d,c)
                                 local ab = 0xFF * byte(a) + byte(b)
                                 local cd = 0xFF * byte(c) + byte(d)
                                 return utfchar((ab-0xD800)*0x400 + (cd-0xDC00) + 0x10000)
@@ -4114,6 +4116,22 @@ function string.toutf(s)
     return lpegmatch(pattern,s) or s -- todo: utf32
 end
 
+local validatedutf = Cs (
+    (
+        patterns.utf8one
+      + patterns.utf8two
+      + patterns.utf8three
+      + patterns.utf8four
+      + P(1) / "�"
+    )^0
+)
+
+patterns.validatedutf = validatedutf
+
+function string.validutf(str)
+    return lpegmatch(validatedutf,str)
+end
+
 
 end -- of closure
 
diff --git a/scripts/context/stubs/mswin/mtxrun.lua b/scripts/context/stubs/mswin/mtxrun.lua
index 644c1d9b2..108f2a8a1 100644
--- a/scripts/context/stubs/mswin/mtxrun.lua
+++ b/scripts/context/stubs/mswin/mtxrun.lua
@@ -4087,8 +4087,10 @@ local one  = P(1)
 local two  = C(1) * C(1)
 local four = C(R(utfchar(0xD8),utfchar(0xFF))) * C(1) * C(1) * C(1)
 
+-- actually one of them is already utf ... sort of useless this one
+
 local pattern = P("\254\255") * Cs( (
-                    four   / function(a,b,c,d)
+                    four  / function(a,b,c,d)
                                 local ab = 0xFF * byte(a) + byte(b)
                                 local cd = 0xFF * byte(c) + byte(d)
                                 return utfchar((ab-0xD800)*0x400 + (cd-0xDC00) + 0x10000)
@@ -4099,7 +4101,7 @@ local pattern = P("\254\255") * Cs( (
                   + one
                 )^1 )
               + P("\255\254") * Cs( (
-                    four   / function(b,a,d,c)
+                    four  / function(b,a,d,c)
                                 local ab = 0xFF * byte(a) + byte(b)
                                 local cd = 0xFF * byte(c) + byte(d)
                                 return utfchar((ab-0xD800)*0x400 + (cd-0xDC00) + 0x10000)
@@ -4114,6 +4116,22 @@ function string.toutf(s)
     return lpegmatch(pattern,s) or s -- todo: utf32
 end
 
+local validatedutf = Cs (
+    (
+        patterns.utf8one
+      + patterns.utf8two
+      + patterns.utf8three
+      + patterns.utf8four
+      + P(1) / "�"
+    )^0
+)
+
+patterns.validatedutf = validatedutf
+
+function string.validutf(str)
+    return lpegmatch(validatedutf,str)
+end
+
 
 end -- of closure
 
diff --git a/scripts/context/stubs/unix/mtxrun b/scripts/context/stubs/unix/mtxrun
index 644c1d9b2..108f2a8a1 100755
--- a/scripts/context/stubs/unix/mtxrun
+++ b/scripts/context/stubs/unix/mtxrun
@@ -4087,8 +4087,10 @@ local one  = P(1)
 local two  = C(1) * C(1)
 local four = C(R(utfchar(0xD8),utfchar(0xFF))) * C(1) * C(1) * C(1)
 
+-- actually one of them is already utf ... sort of useless this one
+
 local pattern = P("\254\255") * Cs( (
-                    four   / function(a,b,c,d)
+                    four  / function(a,b,c,d)
                                 local ab = 0xFF * byte(a) + byte(b)
                                 local cd = 0xFF * byte(c) + byte(d)
                                 return utfchar((ab-0xD800)*0x400 + (cd-0xDC00) + 0x10000)
@@ -4099,7 +4101,7 @@ local pattern = P("\254\255") * Cs( (
                   + one
                 )^1 )
               + P("\255\254") * Cs( (
-                    four   / function(b,a,d,c)
+                    four  / function(b,a,d,c)
                                 local ab = 0xFF * byte(a) + byte(b)
                                 local cd = 0xFF * byte(c) + byte(d)
                                 return utfchar((ab-0xD800)*0x400 + (cd-0xDC00) + 0x10000)
@@ -4114,6 +4116,22 @@ function string.toutf(s)
     return lpegmatch(pattern,s) or s -- todo: utf32
 end
 
+local validatedutf = Cs (
+    (
+        patterns.utf8one
+      + patterns.utf8two
+      + patterns.utf8three
+      + patterns.utf8four
+      + P(1) / "�"
+    )^0
+)
+
+patterns.validatedutf = validatedutf
+
+function string.validutf(str)
+    return lpegmatch(validatedutf,str)
+end
+
 
 end -- of closure
 
diff --git a/tex/context/base/buff-imp-mp.lua b/tex/context/base/buff-imp-mp.lua
index f219df797..34e3459c6 100644
--- a/tex/context/base/buff-imp-mp.lua
+++ b/tex/context/base/buff-imp-mp.lua
@@ -13,6 +13,14 @@ if not modules then modules = { } end modules ['buff-imp-mp'] = {
 -- the rendering and have a different way of nesting. It is no coincidence
 -- that the coloring looks similar: both are derived from earlier lexing (in
 -- texedit, mkii and the c++ scite lexer).
+--
+-- In the meantime we have lpeg based lexers in scite! And, as all this
+-- lexing boils down to the same principles (associating symbolic rendering
+-- with ranges of characters) and as the scite lexers do nesting, it makes
+-- sense at some point to share code. However, keep in mind that the pretty
+-- printers are also supposed to support invalid code (for educational
+-- purposes). The scite lexers are more recent and there a different color
+-- scheme is used. So, we might move away from the traditional coloring.
 
 local P, S, V, patterns = lpeg.P, lpeg.S, lpeg.V, lpeg.patterns
 
diff --git a/tex/context/base/buff-imp-xml.lua b/tex/context/base/buff-imp-xml.lua
index baf290d4c..0c48ed3b0 100644
--- a/tex/context/base/buff-imp-xml.lua
+++ b/tex/context/base/buff-imp-xml.lua
@@ -99,11 +99,11 @@ local grammar = visualizers.newgrammar("default", { "visualizer",
       * makepattern(handler,"boundary",closeend),
     comment =
         makepattern(handler,"boundary",opencomment)
-      * (V("whitespace") + makepattern(handler,"comment",(1-closecomment)))^0 -- slow
+      * (V("whitespace") + makepattern(handler,"comment",(1-closecomment)^1))^0 -- slow
       * makepattern(handler,"boundary",closecomment),
     cdata =
         makepattern(handler,"boundary",opencdata)
-      * (V("whitespace") + makepattern(handler,"comment",(1-closecdata)))^0 -- slow
+      * (V("whitespace") + makepattern(handler,"comment",(1-closecdata)^1))^0 -- slow
       * makepattern(handler,"boundary",closecdata),
     instruction =
         makepattern(handler,"boundary",openinstruction)
diff --git a/tex/context/base/cont-new.mkii b/tex/context/base/cont-new.mkii
index 39bef537a..b4958762f 100644
--- a/tex/context/base/cont-new.mkii
+++ b/tex/context/base/cont-new.mkii
@@ -11,7 +11,7 @@
 %C therefore copyrighted by \PRAGMA. See mreadme.pdf for
 %C details.
 
-\newcontextversion{2012.05.29 18:43}
+\newcontextversion{2012.05.30 11:26}
 
 %D This file is loaded at runtime, thereby providing an
 %D excellent place for hacks, patches, extensions and new
diff --git a/tex/context/base/cont-new.mkiv b/tex/context/base/cont-new.mkiv
index 929174025..5a28f8e29 100644
--- a/tex/context/base/cont-new.mkiv
+++ b/tex/context/base/cont-new.mkiv
@@ -11,7 +11,7 @@
 %C therefore copyrighted by \PRAGMA. See mreadme.pdf for
 %C details.
 
-\newcontextversion{2012.05.29 18:43}
+\newcontextversion{2012.05.30 11:26}
 
 %D This file is loaded at runtime, thereby providing an
 %D excellent place for hacks, patches, extensions and new
diff --git a/tex/context/base/context-version.pdf b/tex/context/base/context-version.pdf
index aa5f54b0a..7b8733c88 100644
--- a/tex/context/base/context-version.pdf
+++ b/tex/context/base/context-version.pdf
diff --git a/tex/context/base/context-version.png b/tex/context/base/context-version.png
index c236521cb..bb280817c 100644
--- a/tex/context/base/context-version.png
+++ b/tex/context/base/context-version.png
diff --git a/tex/context/base/context.mkii b/tex/context/base/context.mkii
index 2cf8fd924..8cd02fd9e 100644
--- a/tex/context/base/context.mkii
+++ b/tex/context/base/context.mkii
@@ -20,7 +20,7 @@
 %D your styles an modules.
 
 \edef\contextformat {\jobname}
-\edef\contextversion{2012.05.29 18:43}
+\edef\contextversion{2012.05.30 11:26}
 
 %D For those who want to use this:
 
diff --git a/tex/context/base/context.mkiv b/tex/context/base/context.mkiv
index 426422c60..5044edae1 100644
--- a/tex/context/base/context.mkiv
+++ b/tex/context/base/context.mkiv
@@ -23,7 +23,7 @@
 %D up and the dependencies are more consistent.
 
 \edef\contextformat {\jobname}
-\edef\contextversion{2012.05.29 18:43}
+\edef\contextversion{2012.05.30 11:26}
 
 %D For those who want to use this:
 
diff --git a/tex/context/base/grph-trf.mkiv b/tex/context/base/grph-trf.mkiv
index a33e5606d..5984c8a06 100644
--- a/tex/context/base/grph-trf.mkiv
+++ b/tex/context/base/grph-trf.mkiv
@@ -38,6 +38,7 @@
 
 \newconditional\c_grph_scale_done
 \newconditional\c_grph_scale_scaling_done
+\newconditional\c_grph_scale_limit_factors \settrue\c_grph_scale_limit_factors
 
 \newdimen\d_grph_scale_wd
 \newdimen\d_grph_scale_ht
@@ -232,14 +233,14 @@
    % final values
    \global\d_grph_scale_used_x_size \zeropoint % see note * (core-fig)
    \global\d_grph_scale_used_y_size \zeropoint % see note * (core-fig)
-   \c_grph_scale_used_x_scale   \plusone        % see note * (core-fig)
-   \c_grph_scale_used_y_scale   \plusone        % see note * (core-fig)
+   \c_grph_scale_used_x_scale       \plusone   % see note * (core-fig)
+   \c_grph_scale_used_y_scale       \plusone   % see note * (core-fig)
    % preparations
    \setfalse\c_grph_scale_scaling_done
    \grph_scale_check_parameters
    % calculators
    % beware, they operate in sequence, and calculate missing dimensions / messy
-   %setscaleboxbynature % when? needed?
+   %grph_scale_by_nature % when? needed?
    \ifconditional\c_grph_scale_scaling_done\else\grph_scale_by_factor   \fi
    \ifconditional\c_grph_scale_scaling_done\else\grph_scale_by_scale    \fi
    \ifconditional\c_grph_scale_scaling_done\else\grph_scale_by_dimension\fi
@@ -321,13 +322,15 @@
 
 \def\grph_scale_by_factor_indeed
   {\settrue\c_grph_scale_scaling_done
-   \ifdim\d_grph_scale_used_x_size>\d_grph_scale_h_size
-     \global\d_grph_scale_used_y_size\zeropoint
-     \global\d_grph_scale_used_x_size\d_grph_scale_h_size
-   \else\ifdim\d_grph_scale_used_y_size>\d_grph_scale_v_size
-     \global\d_grph_scale_used_x_size\zeropoint
-     \global\d_grph_scale_used_y_size\d_grph_scale_v_size
-   \fi\fi
+   \ifconditional\c_grph_scale_limit_factors
+     \ifdim\d_grph_scale_used_x_size>\d_grph_scale_h_size
+       \global\d_grph_scale_used_y_size\zeropoint
+       \global\d_grph_scale_used_x_size\d_grph_scale_h_size
+     \else\ifdim\d_grph_scale_used_y_size>\d_grph_scale_v_size
+       \global\d_grph_scale_used_x_size\zeropoint
+       \global\d_grph_scale_used_y_size\d_grph_scale_v_size
+     \fi\fi
+   \fi
    \grph_scale_by_dimension}
 
 \def\grph_scale_by_scale
diff --git a/tex/context/base/l-unicode.lua b/tex/context/base/l-unicode.lua
index 246171aec..f4480e93c 100644
--- a/tex/context/base/l-unicode.lua
+++ b/tex/context/base/l-unicode.lua
@@ -437,8 +437,10 @@ local one  = P(1)
 local two  = C(1) * C(1)
 local four = C(R(utfchar(0xD8),utfchar(0xFF))) * C(1) * C(1) * C(1)
 
+-- actually one of them is already utf ... sort of useless this one
+
 local pattern = P("\254\255") * Cs( (
-                    four   / function(a,b,c,d)
+                    four  / function(a,b,c,d)
                                 local ab = 0xFF * byte(a) + byte(b)
                                 local cd = 0xFF * byte(c) + byte(d)
                                 return utfchar((ab-0xD800)*0x400 + (cd-0xDC00) + 0x10000)
@@ -449,7 +451,7 @@ local pattern = P("\254\255") * Cs( (
                   + one
                 )^1 )
               + P("\255\254") * Cs( (
-                    four   / function(b,a,d,c)
+                    four  / function(b,a,d,c)
                                 local ab = 0xFF * byte(a) + byte(b)
                                 local cd = 0xFF * byte(c) + byte(d)
                                 return utfchar((ab-0xD800)*0x400 + (cd-0xDC00) + 0x10000)
@@ -463,3 +465,19 @@ local pattern = P("\254\255") * Cs( (
 function string.toutf(s)
     return lpegmatch(pattern,s) or s -- todo: utf32
 end
+
+local validatedutf = Cs (
+    (
+        patterns.utf8one
+      + patterns.utf8two
+      + patterns.utf8three
+      + patterns.utf8four
+      + P(1) / "�"
+    )^0
+)
+
+patterns.validatedutf = validatedutf
+
+function string.validutf(str)
+    return lpegmatch(validatedutf,str)
+end
diff --git a/tex/context/base/status-files.pdf b/tex/context/base/status-files.pdf
index d9e0cb21f..8d2ac5857 100644
--- a/tex/context/base/status-files.pdf
+++ b/tex/context/base/status-files.pdf
diff --git a/tex/context/base/status-lua.pdf b/tex/context/base/status-lua.pdf
index 96f1ea93a..0d58d1b16 100644
--- a/tex/context/base/status-lua.pdf
+++ b/tex/context/base/status-lua.pdf
diff --git a/tex/generic/context/luatex/luatex-fonts-merged.lua b/tex/generic/context/luatex/luatex-fonts-merged.lua
index e1f4e9966..ea509c338 100644
--- a/tex/generic/context/luatex/luatex-fonts-merged.lua
+++ b/tex/generic/context/luatex/luatex-fonts-merged.lua
@@ -1,6 +1,6 @@
 -- merged file : luatex-fonts-merged.lua
 -- parent file : luatex-fonts.lua
--- merge date  : 05/29/12 18:43:34
+-- merge date  : 05/30/12 11:26:34
 
 do -- begin closure to overcome local limits and interference