summaryrefslogtreecommitdiff
path: root/Master/texmf-dist/source/latex/base/utf8ienc.dtx
diff options
context:
space:
mode:
authorKarl Berry <karl@freefriends.org>2009-09-28 15:31:27 +0000
committerKarl Berry <karl@freefriends.org>2009-09-28 15:31:27 +0000
commite5fabe7a228278dc1eaeb1f8740c21724639a9da (patch)
treeecd1aff89e7ef9d0b22eaaad5a0219f1d753581c /Master/texmf-dist/source/latex/base/utf8ienc.dtx
parentb57ff57a6c2fec7c7c89f59ea8a75eae8cc252a9 (diff)
latex (latex core) update via latex-tds (25sep09)
git-svn-id: svn://tug.org/texlive/trunk@15515 c570f23f-e606-0410-a88d-b1316a301751
Diffstat (limited to 'Master/texmf-dist/source/latex/base/utf8ienc.dtx')
-rw-r--r--Master/texmf-dist/source/latex/base/utf8ienc.dtx142
1 files changed, 128 insertions, 14 deletions
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 @@
%</driver>
% \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 @@
%<all,ly1,utf8>\DeclareUnicodeCharacter{02DC}{\textasciitilde}
%<all,ts1>\DeclareUnicodeCharacter{02D8}{\textasciibreve}
%<all,ts1>\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}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0400}{\@tabacckludge`\CYRE}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0401}{\CYRYO}
%<all,x2,t2a,ot2>\DeclareUnicodeCharacter{0402}{\CYRDJE}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0403}{\@tabacckludge`\CYRG}
%<all,x2,t2a,ot2,lcy>\DeclareUnicodeCharacter{0404}{\CYRIE}
%<all,x2,t2c,t2b,t2a,ot2>\DeclareUnicodeCharacter{0405}{\CYRDZE}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0406}{\CYRII}
@@ -882,6 +894,8 @@
%<all,x2,t2b,t2a,ot2>\DeclareUnicodeCharacter{0409}{\CYRLJE}
%<all,x2,t2b,t2a,ot2>\DeclareUnicodeCharacter{040A}{\CYRNJE}
%<all,x2,t2a,ot2>\DeclareUnicodeCharacter{040B}{\CYRTSHE}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{040C}{\@tabacckludge`\CYRK}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{040D}{\@tabacckludge`\CYRI}
%<all,x2,t2b,t2a,lcy>\DeclareUnicodeCharacter{040E}{\CYRUSHRT}
%<all,x2,t2c,t2a,ot2>\DeclareUnicodeCharacter{040F}{\CYRDZHE}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0410}{\CYRA}
@@ -948,8 +962,10 @@
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{044D}{\cyrerev}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{044E}{\cyryu}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{044F}{\cyrya}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0450}{\@tabacckludge`\cyre}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0451}{\cyryo}
%<all,x2,t2a,ot2>\DeclareUnicodeCharacter{0452}{\cyrdje}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0453}{\@tabacckludge`\cyrg}
%<all,x2,t2a,ot2,lcy>\DeclareUnicodeCharacter{0454}{\cyrie}
%<all,x2,t2c,t2b,t2a,ot2>\DeclareUnicodeCharacter{0455}{\cyrdze}
%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{0456}{\cyrii}
@@ -958,16 +974,47 @@
%<all,x2,t2b,t2a,ot2>\DeclareUnicodeCharacter{0459}{\cyrlje}
%<all,x2,t2b,t2a,ot2>\DeclareUnicodeCharacter{045A}{\cyrnje}
%<all,x2,t2a,ot2>\DeclareUnicodeCharacter{045B}{\cyrtshe}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{045C}{\@tabacckludge`\cyrk}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{045D}{\@tabacckludge`\cyri}
%<all,x2,t2b,t2a,lcy>\DeclareUnicodeCharacter{045E}{\cyrushrt}
%<all,x2,t2c,t2a,ot2>\DeclareUnicodeCharacter{045F}{\cyrdzhe}
%<all,x2,ot2>\DeclareUnicodeCharacter{0462}{\CYRYAT}
%<all,x2,ot2>\DeclareUnicodeCharacter{0463}{\cyryat}
%<all,x2>\DeclareUnicodeCharacter{046A}{\CYRBYUS}
%<all,x2>\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}
%<all,ot2>\DeclareUnicodeCharacter{0472}{\CYRFITA}
%<all,ot2>\DeclareUnicodeCharacter{0473}{\cyrfita}
+% \end{macrocode}
+%
+% \begin{macrocode}
%<all,x2,ot2>\DeclareUnicodeCharacter{0474}{\CYRIZH}
%<all,x2,ot2>\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}
+%<all,x2>\DeclareUnicodeCharacter{0476}{\C\CYRIZH}
+%<all,x2>\DeclareUnicodeCharacter{0477}{\C\cyrizh}
+% \end{macrocode}
+%
+% \begin{macrocode}
%<all,t2c>\DeclareUnicodeCharacter{048C}{\CYRSEMISFTSN}
%<all,t2c>\DeclareUnicodeCharacter{048D}{\cyrsemisftsn}
%<all,t2c>\DeclareUnicodeCharacter{048E}{\CYRRTICK}
@@ -988,8 +1035,8 @@
%<all,x2,t2a>\DeclareUnicodeCharacter{049D}{\cyrkvcrs}
%<all,x2,t2c>\DeclareUnicodeCharacter{049E}{\CYRKHCRS}
%<all,x2,t2c>\DeclareUnicodeCharacter{049F}{\cyrkhcrs}
-%<all,x2>\DeclareUnicodeCharacter{04A0}{\CYRKBEAK}
-%<all,x2>\DeclareUnicodeCharacter{04A1}{\cyrkbeak}
+%<all,x2,t2a>\DeclareUnicodeCharacter{04A0}{\CYRKBEAK}
+%<all,x2,t2a>\DeclareUnicodeCharacter{04A1}{\cyrkbeak}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04A2}{\CYRNDSC}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04A3}{\cyrndsc}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{04A4}{\CYRNG}
@@ -1000,8 +1047,8 @@
%<all,x2,t2c>\DeclareUnicodeCharacter{04A9}{\cyrabhha}
%<all,x2,t2a>\DeclareUnicodeCharacter{04AA}{\CYRSDSC}
%<all,x2,t2a>\DeclareUnicodeCharacter{04AB}{\cyrsdsc}
-%<all,x2,t2c,t2a>\DeclareUnicodeCharacter{04AC}{\CYRTDSC}
-%<all,x2,t2c,t2a>\DeclareUnicodeCharacter{04AD}{\cyrtdsc}
+%<all,x2,t2c>\DeclareUnicodeCharacter{04AC}{\CYRTDSC}
+%<all,x2,t2c>\DeclareUnicodeCharacter{04AD}{\cyrtdsc}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{04AE}{\CYRY}
%<all,x2,t2b,t2a>\DeclareUnicodeCharacter{04AF}{\cyry}
%<all,x2,t2a>\DeclareUnicodeCharacter{04B0}{\CYRYHCRS}
@@ -1020,25 +1067,92 @@
%<all,x2,t2c>\DeclareUnicodeCharacter{04BD}{\cyrabhch}
%<all,x2,t2c>\DeclareUnicodeCharacter{04BE}{\CYRABHCHDSC}
%<all,x2,t2c>\DeclareUnicodeCharacter{04BF}{\cyrabhchdsc}
-%<all,x2,t2c,t2b,t2a,ot2,lcy>\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}
+%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04C0}{\CYRpalochka}
+% \end{macrocode}
+%
+% \begin{macrocode}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04C1}{\U\CYRZH}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04C2}{\U\cyrzh}
%<all,x2,t2b>\DeclareUnicodeCharacter{04C3}{\CYRKHK}
%<all,x2,t2b>\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}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04C5}{\CYRLDSC}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04C6}{\cyrldsc}
+% \end{macrocode}
+%
+% \begin{macrocode}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04C7}{\CYRNHK}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04C8}{\cyrnhk}
%<all,x2,t2b>\DeclareUnicodeCharacter{04CB}{\CYRCHLDSC}
%<all,x2,t2b>\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}
%<all,x2,t2c>\DeclareUnicodeCharacter{04CD}{\CYRMDSC}
%<all,x2,t2c>\DeclareUnicodeCharacter{04CE}{\cyrmdsc}
+% \end{macrocode}
+%
+% \begin{macrocode}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D0}{\U\CYRA}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D1}{\U\cyra}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D2}{\"\CYRA}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D3}{\"\cyra}
%<all,x2,t2a>\DeclareUnicodeCharacter{04D4}{\CYRAE}
%<all,x2,t2a>\DeclareUnicodeCharacter{04D5}{\cyrae}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D6}{\U\CYRE}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04D7}{\U\cyre}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04D8}{\CYRSCHWA}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04D9}{\cyrschwa}
+%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04DA}{\"\CYRSCHWA}
+%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04DB}{\"\cyrschwa}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04DC}{\"\CYRZH}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04DD}{\"\cyrzh}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04DE}{\"\CYRZ}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04DF}{\"\cyrz}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04E0}{\CYRABHDZE}
%<all,x2,t2c,t2b>\DeclareUnicodeCharacter{04E1}{\cyrabhdze}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E2}{\=\CYRI}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E3}{\=\cyri}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E4}{\"\CYRI}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E5}{\"\cyri}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E6}{\"\CYRO}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04E7}{\"\cyro}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04E8}{\CYROTLD}
%<all,x2,t2c,t2b,t2a>\DeclareUnicodeCharacter{04E9}{\cyrotld}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04EC}{\"\CYREREV}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04ED}{\"\cyrerev}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04EE}{\=\CYRU}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04EF}{\=\cyru}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F0}{\"\CYRU}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F1}{\"\cyru}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F2}{\H\CYRU}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F3}{\H\cyru}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F4}{\"\CYRCH}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F5}{\"\cyrch}
+%<all,x2,t2b>\DeclareUnicodeCharacter{04F6}{\CYRGDSC}
+%<all,x2,t2b>\DeclareUnicodeCharacter{04F7}{\cyrgdsc}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F8}{\"\CYRERY}
+%<all,x2,t2c,t2b,t2a,ot2,lcy>\DeclareUnicodeCharacter{04F9}{\"\cyrery}
+%<all,t2b>\DeclareUnicodeCharacter{04FA}{\CYRGDSCHCRS}
+%<all,t2b>\DeclareUnicodeCharacter{04FB}{\cyrgdschcrs}
+%<all,x2,t2b>\DeclareUnicodeCharacter{04FC}{\CYRHHK}
+%<all,x2,t2b>\DeclareUnicodeCharacter{04FD}{\cyrhhk}
+%<all,t2b>\DeclareUnicodeCharacter{04FE}{\CYRHHCRS}
+%<all,t2b>\DeclareUnicodeCharacter{04FF}{\cyrhhcrs}
%<all,ts1>\DeclareUnicodeCharacter{0E3F}{\textbaht}
%<all,x2,t2c,t2b,t2a,t1,utf8>\DeclareUnicodeCharacter{200C}{\textcompwordmark}
%<all,x2,t2c,t2b,t2a,t1,ot2,ot1,ly1,lcy>\DeclareUnicodeCharacter{2013}{\textendash}