Re: XeTeX encoding problem

[Masamichi HOSODA]

> Thank you for your comments.
> I've updated the patch.
> 
> I want the following.
>   UTF-8 auxiliary file.
>   Handling Unicode filename (image files and include files).
>   Handling Unicode PDF bookmark strings.
> 
> For this purpose, I used the method that changes catcode.
> The patch that is attached to this mail
> uses different method for this purpose.
> It uses re-defining replacing macros.

I've improved native Unicode replacing patch.

My previous patch could not handle @U command.
This patch can handle it.
In addition, I've added some comments and fixed some macro names.

How about this?

--- texinfo.tex.org     2016-01-21 23:04:22.405562200 +0900
+++ texinfo.tex 2016-01-21 23:10:48.289263700 +0900
@@ -9433,42 +9433,18 @@
   \global\righthyphenmin = #3\relax
 }
 
-% Get input by bytes instead of by UTF-8 codepoints for XeTeX and LuaTeX, 
-% otherwise the encoding support is completely broken.
-\ifx\XeTeXrevision\thisisundefined
-\else
-\XeTeXdefaultencoding "bytes"  % For subsequent files to be read
-\XeTeXinputencoding "bytes"  % Effective in texinfo.tex only
-% Unfortunately, there seems to be no corresponding XeTeX command for
-% output encoding.  This is a problem for auxiliary index and TOC files.
-% The only solution would be perhaps to write out @U{...} sequences in
-% place of UTF-8 characters.
-\fi
+% XeTeX and LuaTeX can handle native Unicode.
+%
+\newif\iftxinativeunicodecapable
 
-\ifx\luatexversion\thisisundefined
+\ifx\XeTeXrevision\thisisundefined
+  \ifx\luatexversion\thisisundefined
+    \txinativeunicodecapablefalse
+  \else
+    \txinativeunicodecapabletrue
+  \fi
 \else
-\directlua{
-local utf8_char, byte, gsub = unicode.utf8.char, string.byte, string.gsub
-local function convert_char (char)
-  return utf8_char(byte(char))
-end
-
-local function convert_line (line)
-  return gsub(line, ".", convert_char)
-end
-
-callback.register("process_input_buffer", convert_line)
-
-local function convert_line_out (line)
-  local line_out = ""
-  for c in string.utfvalues(line) do
-     line_out = line_out .. string.char(c)
-  end
-  return line_out
-end
-
-callback.register("process_output_buffer", convert_line_out)
-}
+  \txinativeunicodecapabletrue
 \fi
 
 
@@ -9496,13 +9472,6 @@
 %
 \def\documentencoding{\parseargusing\filenamecatcodes\documentencodingzzz}
 \def\documentencodingzzz#1{%
-  % Get input by bytes instead of by UTF-8 codepoints for XeTeX,
-  % otherwise the encoding support is completely broken.
-  % This settings is for the document root file.
-  \ifx\XeTeXrevision\thisisundefined
-  \else
-    \XeTeXinputencoding "bytes"
-  \fi
   %
   % Encoding being declared for the document.
   \def\declaredencoding{\csname #1.enc\endcsname}%
@@ -9531,10 +9500,16 @@
      \latninechardefs
   %
   \else \ifx \declaredencoding \utfeight
-     \setnonasciicharscatcode\active
-     % since we already invoked \utfeightchardefs at the top level
-     % (below), do not re-invoke it, then our check for duplicated
-     % definitions triggers.  Making non-ascii chars active is enough.
+     \iftxinativeunicodecapable
+       % For native Unicode (XeTeX and LuaTeX)
+       \nativeunicodechardefs
+     \else
+       % For UTF-8 byte sequence (pdfTeX)
+       \setnonasciicharscatcode\active
+       % since we already invoked \utfeightchardefs at the top level
+       % (below), do not re-invoke it, then our check for duplicated
+       % definitions triggers.  Making non-ascii chars active is enough.
+     \fi
   %
   \else
     \message{Ignoring unknown document encoding: #1.}%
@@ -9849,13 +9824,26 @@
 % @U{xxxx} to produce U+xxxx, if we support it.
 \def\U#1{%
   \expandafter\ifx\csname uni:#1\endcsname \relax
-    \errhelp = \EMsimple       
-    \errmessage{Unicode character U+#1 not supported, sorry}%
+    \iftxinativeunicodecapable
+      % Any Unicode characters can be used by native Unicode.
+      % However, if the font does not have the glyph, the letter will miss.
+      \begingroup
+        \uccode`\.="#1\relax
+       \uppercase{.}
+      \endgroup
+    \else
+      \errhelp = \EMsimple     
+      \errmessage{Unicode character U+#1 not supported, sorry}%
+    \fi
   \else
     \csname uni:#1\endcsname
   \fi
 }
 
+% For UTF-8 byte sequence (pdfTeX)
+% Definition macro to replace the Unicode character
+% Definition macro that is used by @U command
+%
 \begingroup
   \catcode`\"=12
   \catcode`\<=12
@@ -9864,7 +9852,7 @@
   \catcode`\;=12
   \catcode`\!=12
   \catcode`\~=13
-  \gdef\DeclareUnicodeCharacter#1#2{%
+  \gdef\DeclareUnicodeCharacterUTFviii#1#2{%
     \countUTFz = "#1\relax
     %\wlog{\space\space defining Unicode char U+#1 (decimal \the\countUTFz)}%
     \begingroup
@@ -9922,6 +9910,37 @@
     \uppercase{\gdef\UTFviiiTmp{#2#3#4}}}
 \endgroup
 
+% For native Unicode (XeTeX and LuaTeX)
+% Definition macro to replace the Unicode character
+%
+\def\DeclareUnicodeCharacterNative#1#2{%
+  \catcode"#1=\active
+  \begingroup
+    \uccode`\~="#1\relax
+    \uppercase{\gdef~}{#2}%
+  \endgroup}
+
+% For native Unicode (XeTeX and LuaTeX)
+% Definition macro not to replace (through) the Unicode character
+%
+\def\DeclareUnicodeCharacterNativeThru#1#2{%
+  \catcode"#1=\active
+  \begingroup
+    \uccode`\.="#1\relax
+    \uppercase{\endgroup \def\UTFNativeTmp{.}}%
+  \begingroup
+    \uccode`\~="#1\relax
+    \uppercase{\endgroup \edef~}{\UTFNativeTmp}%
+}
+
+% For native Unicode (XeTeX and LuaTeX)
+% Definition macro that is used by @U command
+%
+\def\DeclareUnicodeCharacterNativeAtU#1#2{%
+  \def\UTFAtUTmp{#2}
+  \expandafter\globallet\csname uni:#1\endcsname \UTFAtUTmp
+}
+
 % https://en.wikipedia.org/wiki/Plane_(Unicode)#Basic_M
 % U+0000..U+007F = https://en.wikipedia.org/wiki/Basic_Latin_(Unicode_block)
 % U+0080..U+00FF = 
https://en.wikipedia.org/wiki/Latin-1_Supplement_(Unicode_block)
@@ -9936,7 +9955,7 @@
 % We won't be doing that here in this simple file.  But we can try to at
 % least make most of the characters not bomb out.
 %
-\def\utfeightchardefs{%
+\def\unicodechardefs{%
   \DeclareUnicodeCharacter{00A0}{\tie}
   \DeclareUnicodeCharacter{00A1}{\exclamdown}
   \DeclareUnicodeCharacter{00A2}{{\tcfont \char162}}% 0242=cent
@@ -10606,14 +10625,48 @@
 
   \global\mathchardef\checkmark="1370 % actually the square root sign
   \DeclareUnicodeCharacter{2713}{\ensuremath\checkmark}
-}% end of \utfeightchardefs
+}% end of \unicodechardefs
+
+% UTF-8 byte sequence (pdfTeX) definitions (replacing and @U command)
+% It makes the setting that replace UTF-8 byte sequence.
+\def\utfeightchardefs{
+  \let\DeclareUnicodeCharacter\DeclareUnicodeCharacterUTFviii
+  \unicodechardefs
+}
+
+% Native Unicode (XeTeX and LuaTeX) character replacing definitions
+% It makes the setting that replace the Unicode characters.
+\def\nativeunicodechardefs{
+  \iftxinativeunicodecapable
+    \let\DeclareUnicodeCharacter\DeclareUnicodeCharacterNative
+    \unicodechardefs
+  \fi
+}
+
+% Native Unicode (XeTeX and LuaTeX) character ``through'' definitions
+% It makes the setting that does not replace the Unicode characters.
+\def\nativeunicodechardefsthru{
+  \iftxinativeunicodecapable
+    \let\DeclareUnicodeCharacter\DeclareUnicodeCharacterNativeThru
+    \unicodechardefs
+  \fi
+}
+
+% Native Unicode (XeTeX and LuaTeX) @U command definitions
+\def\nativeunicodechardefsatu{
+  \iftxinativeunicodecapable
+    \let\DeclareUnicodeCharacter\DeclareUnicodeCharacterNativeAtU
+    \unicodechardefs
+  \fi
+}
 
 % US-ASCII character definitions.
 \def\asciichardefs{% nothing need be done
    \relax
 }
 
-% Latin1 (ISO-8859-1) character definitions.
+% Non-ASCII bytes ``through'' definitions.
+% It makes the setting that does not replace the non-ASCII byte.
 \def\nonasciistringdefs{%
   \setnonasciicharscatcode\active
   \def\defstringchar##1{\def##1{\string##1}}%
@@ -10659,9 +10712,23 @@
   \defstringchar^^fc\defstringchar^^fd\defstringchar^^fe\defstringchar^^ff%
 }
 
+% Character ``through'' definitions.
+% It makes the setting that does not replace the characters.
+\def\throughcharactersdefs{%
+  \iftxinativeunicodecapable
+    \nativeunicodechardefsthru
+  \else
+    \nonasciistringdefs
+  \fi
+}
+
 
 % define all the unicode characters we know about, for the sake of @U.
-\utfeightchardefs
+\iftxinativeunicodecapable
+  \nativeunicodechardefsatu
+\else
+  \utfeightchardefs
+\fi
 
 
 % Make non-ASCII characters printable again for compatibility with
@@ -11010,7 +11077,7 @@
 %
 address@hidden = @active
  @address@hidden
-   @nonasciistringdefs
+   @throughcharactersdefs
    @address@hidden
    @let"address@hidden
    @address@hidden %$ font-lock fix

\input texinfo.tex

@documentencoding UTF-8

@contents

@chapter für

für

@U{00FC}: U+00FC supported by XeTeX, LuaTeX and pdfTeX

@U{0132}: U+0132 supported by XeTeX, LuaTeX and pdfTeX

@U{0041}: U+0041 supported by XeTeX and LuaTeX only

@bye

\input texinfo.tex

@documentencoding US-ASCII

@contents

@chapter address@hidden

address@hidden

@U{00FC}: U+00FC supported by XeTeX, LuaTeX and pdfTeX

@U{0132}: U+0132 supported by XeTeX, LuaTeX and pdfTeX

@U{0041}: U+0041 supported by XeTeX and LuaTeX only

@bye