From e5fabe7a228278dc1eaeb1f8740c21724639a9da Mon Sep 17 00:00:00 2001 From: Karl Berry Date: Mon, 28 Sep 2009 15:31:27 +0000 Subject: latex (latex core) update via latex-tds (25sep09) git-svn-id: svn://tug.org/texlive/trunk@15515 c570f23f-e606-0410-a88d-b1316a301751 --- Master/texmf-dist/source/latex/base/utf8ienc.dtx | 142 ++++++++++++++++++++--- 1 file changed, 128 insertions(+), 14 deletions(-) (limited to 'Master/texmf-dist/source/latex/base/utf8ienc.dtx') diff --git a/Master/texmf-dist/source/latex/base/utf8ienc.dtx b/Master/texmf-dist/source/latex/base/utf8ienc.dtx index 5b9fe574c4a..a35b9416ef7 100644 --- a/Master/texmf-dist/source/latex/base/utf8ienc.dtx +++ b/Master/texmf-dist/source/latex/base/utf8ienc.dtx @@ -1,6 +1,6 @@ % \iffalse meta-comment % -% Copyright 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 +% Copyright 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 % The LaTeX3 Project and any individual authors listed elsewhere % in this file. % @@ -45,7 +45,7 @@ % % \fi % -% \CheckSum{1090} +% \CheckSum{1232} % % \newpage % @@ -217,7 +217,7 @@ %<+ts1> \ProvidesFile{ts1enc.dfu} %<+x2> \ProvidesFile{x2enc.dfu} %<+all> \ProvidesFile{utf8enc.dfu} - [2006/03/30 v1.1i UTF-8 support for inputenc] + [2008/04/05 v1.1m UTF-8 support for inputenc] % \end{macrocode} % % \begin{macrocode} @@ -589,12 +589,15 @@ \wlog{Now handling font encoding #1 ...}% \lowercase{% \InputIfFileExists{#1enc.dfu}}% - {\wlog{... processing UTF-8 mapping file for font encoding - #1}% + {\wlog{... processing UTF-8 mapping file for font % + encoding #1}% % \end{macrocode} -% From this point on we ignore spaces again, i.e., while we are -% reading the \texttt{.dfu} file. The |\endgroup| below will -% restore it again. +% \changes{v1.1m}{2008/04/05}{Ensure we don't lose spaces in the log} +% The previous line is written to the log with the newline char being +% ignored (thus not producing a space). Therefore either everything has to +% be on a single input line or some specical care must be taken. From this +% point on we ignore spaces again, i.e., while we are reading the +% \texttt{.dfu} file. The |\endgroup| below will restore it again. % \changes{v1.1d}{2004/05/08}{Explicitly set catcode of space} % \changes{v1.1g}{2005/09/27}{We lost the ``false'' case} % \begin{macrocode} @@ -624,7 +627,8 @@ \wlog{Now handling font encoding #1 ...}% \lowercase{% \InputIfFileExists{#1enc.dfu}}% - {\wlog{... processing UTF-8 mapping file for font encoding #1}}% + {\wlog{... processing UTF-8 mapping file for font % + encoding #1}}% {\wlog{... no UTF-8 mapping file for font encoding #1}}% \endgroup \else @@ -872,8 +876,16 @@ %\DeclareUnicodeCharacter{02DC}{\textasciitilde} %\DeclareUnicodeCharacter{02D8}{\textasciibreve} %\DeclareUnicodeCharacter{02DD}{\textacutedbl} +% \end{macrocode} +% The Cyrillic code points have been recently checked (2007) and extended +% and corrected by Matthias Noe (\verb=a9931078@unet.univie.ac.at=) --- thanks. +% \changes{v1.1j}{2007/11/09}{Added a few new unicode decls in cyrillic (pr/3988)} +% \changes{v1.1k}{2007/11/11}{Added and further unicode decls in cyrillic} +% \begin{macrocode} +%\DeclareUnicodeCharacter{0400}{\@tabacckludge`\CYRE} %\DeclareUnicodeCharacter{0401}{\CYRYO} %\DeclareUnicodeCharacter{0402}{\CYRDJE} +%\DeclareUnicodeCharacter{0403}{\@tabacckludge`\CYRG} %\DeclareUnicodeCharacter{0404}{\CYRIE} %\DeclareUnicodeCharacter{0405}{\CYRDZE} %\DeclareUnicodeCharacter{0406}{\CYRII} @@ -882,6 +894,8 @@ %\DeclareUnicodeCharacter{0409}{\CYRLJE} %\DeclareUnicodeCharacter{040A}{\CYRNJE} %\DeclareUnicodeCharacter{040B}{\CYRTSHE} +%\DeclareUnicodeCharacter{040C}{\@tabacckludge`\CYRK} +%\DeclareUnicodeCharacter{040D}{\@tabacckludge`\CYRI} %\DeclareUnicodeCharacter{040E}{\CYRUSHRT} %\DeclareUnicodeCharacter{040F}{\CYRDZHE} %\DeclareUnicodeCharacter{0410}{\CYRA} @@ -948,8 +962,10 @@ %\DeclareUnicodeCharacter{044D}{\cyrerev} %\DeclareUnicodeCharacter{044E}{\cyryu} %\DeclareUnicodeCharacter{044F}{\cyrya} +%\DeclareUnicodeCharacter{0450}{\@tabacckludge`\cyre} %\DeclareUnicodeCharacter{0451}{\cyryo} %\DeclareUnicodeCharacter{0452}{\cyrdje} +%\DeclareUnicodeCharacter{0453}{\@tabacckludge`\cyrg} %\DeclareUnicodeCharacter{0454}{\cyrie} %\DeclareUnicodeCharacter{0455}{\cyrdze} %\DeclareUnicodeCharacter{0456}{\cyrii} @@ -958,16 +974,47 @@ %\DeclareUnicodeCharacter{0459}{\cyrlje} %\DeclareUnicodeCharacter{045A}{\cyrnje} %\DeclareUnicodeCharacter{045B}{\cyrtshe} +%\DeclareUnicodeCharacter{045C}{\@tabacckludge`\cyrk} +%\DeclareUnicodeCharacter{045D}{\@tabacckludge`\cyri} %\DeclareUnicodeCharacter{045E}{\cyrushrt} %\DeclareUnicodeCharacter{045F}{\cyrdzhe} %\DeclareUnicodeCharacter{0462}{\CYRYAT} %\DeclareUnicodeCharacter{0463}{\cyryat} %\DeclareUnicodeCharacter{046A}{\CYRBYUS} %\DeclareUnicodeCharacter{046B}{\cyrbyus} +% \end{macrocode} +% The next two declarations are questionable, the encoding definition +% should probably contain |\CYROTLD| and |\cyrotld|. Or alternatively, if +% the characters in the X2 encodings are really meant to represent the +% historical characters in Ux0472 and Ux0473 (they look like them) then +% they would need to change instead. +% +% However, their looks are probably a font designers decision and the next +% two mappings are wrong or rather the names in OT2 should change for +% consistancy. +% +% On the other hand the names |\CYROTLD| are somewhat questionabled as the +% Unicode standard only describes ``Cyrillic barred O'' while |TLD| refers +% to a tilde (which is more less what the ``Cyrillic FITA looks according +% to the Unicode book). +% \begin{macrocode} %\DeclareUnicodeCharacter{0472}{\CYRFITA} %\DeclareUnicodeCharacter{0473}{\cyrfita} +% \end{macrocode} +% +% \begin{macrocode} %\DeclareUnicodeCharacter{0474}{\CYRIZH} %\DeclareUnicodeCharacter{0475}{\cyrizh} +% \end{macrocode} +% While the double grave accent seems to exist in X2, T2A, T2B and T2C +% encoding, the letter izhitsa exists only in X2 and OT2. Therefore, +% izhitsa with double grave seems to be possible only using X2. +% \begin{macrocode} +%\DeclareUnicodeCharacter{0476}{\C\CYRIZH} +%\DeclareUnicodeCharacter{0477}{\C\cyrizh} +% \end{macrocode} +% +% \begin{macrocode} %\DeclareUnicodeCharacter{048C}{\CYRSEMISFTSN} %\DeclareUnicodeCharacter{048D}{\cyrsemisftsn} %\DeclareUnicodeCharacter{048E}{\CYRRTICK} @@ -988,8 +1035,8 @@ %\DeclareUnicodeCharacter{049D}{\cyrkvcrs} %\DeclareUnicodeCharacter{049E}{\CYRKHCRS} %\DeclareUnicodeCharacter{049F}{\cyrkhcrs} -%\DeclareUnicodeCharacter{04A0}{\CYRKBEAK} -%\DeclareUnicodeCharacter{04A1}{\cyrkbeak} +%\DeclareUnicodeCharacter{04A0}{\CYRKBEAK} +%\DeclareUnicodeCharacter{04A1}{\cyrkbeak} %\DeclareUnicodeCharacter{04A2}{\CYRNDSC} %\DeclareUnicodeCharacter{04A3}{\cyrndsc} %\DeclareUnicodeCharacter{04A4}{\CYRNG} @@ -1000,8 +1047,8 @@ %\DeclareUnicodeCharacter{04A9}{\cyrabhha} %\DeclareUnicodeCharacter{04AA}{\CYRSDSC} %\DeclareUnicodeCharacter{04AB}{\cyrsdsc} -%\DeclareUnicodeCharacter{04AC}{\CYRTDSC} -%\DeclareUnicodeCharacter{04AD}{\cyrtdsc} +%\DeclareUnicodeCharacter{04AC}{\CYRTDSC} +%\DeclareUnicodeCharacter{04AD}{\cyrtdsc} %\DeclareUnicodeCharacter{04AE}{\CYRY} %\DeclareUnicodeCharacter{04AF}{\cyry} %\DeclareUnicodeCharacter{04B0}{\CYRYHCRS} @@ -1020,25 +1067,92 @@ %\DeclareUnicodeCharacter{04BD}{\cyrabhch} %\DeclareUnicodeCharacter{04BE}{\CYRABHCHDSC} %\DeclareUnicodeCharacter{04BF}{\cyrabhchdsc} -%\DeclareUnicodeCharacter{04C0}{\CYRpalochka} +% \end{macrocode} +% The character |\CYRpalochka| is not defined by OT2 and LCY. However it is +% looking identical to |\CYRII| and the Unicode standard explicitly refers +% to that (and to Latin I). So perhaps those encodings could get an alias? +% On the other hand, why are there two distinct slots in the T2 encodings +% even though they are so pressed for space? Perhaps they don't always look +% alike. +% \begin{macrocode} +%\DeclareUnicodeCharacter{04C0}{\CYRpalochka} +% \end{macrocode} +% +% \begin{macrocode} +%\DeclareUnicodeCharacter{04C1}{\U\CYRZH} +%\DeclareUnicodeCharacter{04C2}{\U\cyrzh} %\DeclareUnicodeCharacter{04C3}{\CYRKHK} %\DeclareUnicodeCharacter{04C4}{\cyrkhk} +% \end{macrocode} +% According to the Unicode standard Ux04C5 should be an L with ``tail'' not +% with descender (which also exists as Ux04A2) but it looks as if the char +% names do not make this distinction). Should they? +% \begin{macrocode} %\DeclareUnicodeCharacter{04C5}{\CYRLDSC} %\DeclareUnicodeCharacter{04C6}{\cyrldsc} +% \end{macrocode} +% +% \begin{macrocode} %\DeclareUnicodeCharacter{04C7}{\CYRNHK} %\DeclareUnicodeCharacter{04C8}{\cyrnhk} %\DeclareUnicodeCharacter{04CB}{\CYRCHLDSC} %\DeclareUnicodeCharacter{04CC}{\cyrchldsc} +% \end{macrocode} +% According to the Unicode standard Ux04CD should be an M with ``tail'' not +% with descender. However this time there is no M with descender in the +% Unicode standard. +% \begin{macrocode} %\DeclareUnicodeCharacter{04CD}{\CYRMDSC} %\DeclareUnicodeCharacter{04CE}{\cyrmdsc} +% \end{macrocode} +% +% \begin{macrocode} +%\DeclareUnicodeCharacter{04D0}{\U\CYRA} +%\DeclareUnicodeCharacter{04D1}{\U\cyra} +%\DeclareUnicodeCharacter{04D2}{\"\CYRA} +%\DeclareUnicodeCharacter{04D3}{\"\cyra} %\DeclareUnicodeCharacter{04D4}{\CYRAE} %\DeclareUnicodeCharacter{04D5}{\cyrae} +%\DeclareUnicodeCharacter{04D6}{\U\CYRE} +%\DeclareUnicodeCharacter{04D7}{\U\cyre} %\DeclareUnicodeCharacter{04D8}{\CYRSCHWA} %\DeclareUnicodeCharacter{04D9}{\cyrschwa} +%\DeclareUnicodeCharacter{04DA}{\"\CYRSCHWA} +%\DeclareUnicodeCharacter{04DB}{\"\cyrschwa} +%\DeclareUnicodeCharacter{04DC}{\"\CYRZH} +%\DeclareUnicodeCharacter{04DD}{\"\cyrzh} +%\DeclareUnicodeCharacter{04DE}{\"\CYRZ} +%\DeclareUnicodeCharacter{04DF}{\"\cyrz} %\DeclareUnicodeCharacter{04E0}{\CYRABHDZE} %\DeclareUnicodeCharacter{04E1}{\cyrabhdze} +%\DeclareUnicodeCharacter{04E2}{\=\CYRI} +%\DeclareUnicodeCharacter{04E3}{\=\cyri} +%\DeclareUnicodeCharacter{04E4}{\"\CYRI} +%\DeclareUnicodeCharacter{04E5}{\"\cyri} +%\DeclareUnicodeCharacter{04E6}{\"\CYRO} +%\DeclareUnicodeCharacter{04E7}{\"\cyro} %\DeclareUnicodeCharacter{04E8}{\CYROTLD} %\DeclareUnicodeCharacter{04E9}{\cyrotld} +%\DeclareUnicodeCharacter{04EC}{\"\CYREREV} +%\DeclareUnicodeCharacter{04ED}{\"\cyrerev} +%\DeclareUnicodeCharacter{04EE}{\=\CYRU} +%\DeclareUnicodeCharacter{04EF}{\=\cyru} +%\DeclareUnicodeCharacter{04F0}{\"\CYRU} +%\DeclareUnicodeCharacter{04F1}{\"\cyru} +%\DeclareUnicodeCharacter{04F2}{\H\CYRU} +%\DeclareUnicodeCharacter{04F3}{\H\cyru} +%\DeclareUnicodeCharacter{04F4}{\"\CYRCH} +%\DeclareUnicodeCharacter{04F5}{\"\cyrch} +%\DeclareUnicodeCharacter{04F6}{\CYRGDSC} +%\DeclareUnicodeCharacter{04F7}{\cyrgdsc} +%\DeclareUnicodeCharacter{04F8}{\"\CYRERY} +%\DeclareUnicodeCharacter{04F9}{\"\cyrery} +%\DeclareUnicodeCharacter{04FA}{\CYRGDSCHCRS} +%\DeclareUnicodeCharacter{04FB}{\cyrgdschcrs} +%\DeclareUnicodeCharacter{04FC}{\CYRHHK} +%\DeclareUnicodeCharacter{04FD}{\cyrhhk} +%\DeclareUnicodeCharacter{04FE}{\CYRHHCRS} +%\DeclareUnicodeCharacter{04FF}{\cyrhhcrs} %\DeclareUnicodeCharacter{0E3F}{\textbaht} %\DeclareUnicodeCharacter{200C}{\textcompwordmark} %\DeclareUnicodeCharacter{2013}{\textendash} -- cgit v1.2.3