Am Sonntag, 1. April 2007 11:20 schrieb Abdelrazak Younes:
> So Georg, what's next on this front?
Concerning the input method I don't have an overview. Concerning the LaTeX
export I did start to develop a patch (attached), but it is completely
broken currently. I'll continue to work (slowly) on this, but don't expect
anything before easter.
Georg
Index: src/LaTeXFeatures.C
===================================================================
--- src/LaTeXFeatures.C (Revision 17674)
+++ src/LaTeXFeatures.C (Arbeitskopie)
@@ -60,8 +60,9 @@ LaTeXFeatures::LaTeXFeatures(Buffer cons
bool LaTeXFeatures::useBabel() const
{
return lyxrc.language_use_babel ||
- bufferParams().language->lang() != lyxrc.default_language ||
- this->hasLanguages();
+ (bufferParams().language->lang() != lyxrc.default_language &&
+ !bufferParams().language->babel().empty()) ||
+ hasLanguages();
}
@@ -185,7 +186,8 @@ void LaTeXFeatures::useFloat(string cons
void LaTeXFeatures::useLanguage(Language const * lang)
{
- UsedLanguages_.insert(lang);
+ if (!lang->babel().empty())
+ UsedLanguages_.insert(lang);
}
@@ -205,26 +207,29 @@ string LaTeXFeatures::getLanguages() con
{
ostringstream languages;
- for (LanguageList::const_iterator cit =
- UsedLanguages_.begin();
+ LanguageList::const_iterator const begin = UsedLanguages_.begin();
+ for (LanguageList::const_iterator cit = begin;
cit != UsedLanguages_.end();
- ++cit)
- languages << (*cit)->babel() << ',';
+ ++cit) {
+ if (cit != begin)
+ languages << ',';
+ languages << (*cit)->babel();
+ }
return languages.str();
}
set<string> LaTeXFeatures::getEncodingSet(string const & doc_encoding) const
{
+ // This does only find encodings of languages supported by babel, but
+ // that does not matter since we don't have a language with an
+ // encoding supported by inputenc but without babel support.
set<string> encodings;
LanguageList::const_iterator it = UsedLanguages_.begin();
LanguageList::const_iterator end = UsedLanguages_.end();
for (; it != end; ++it)
- // thailatex does not use the inputenc package, but sets up
- // babel directly for tis620-0 encoding, therefore we must
- // not add tis620-0 to the encoding set.
if ((*it)->encoding()->latexName() != doc_encoding &&
- (*it)->encoding()->name() != "tis620-0")
+ (*it)->encoding()->package() == Encoding::inputenc)
encodings.insert((*it)->encoding()->latexName());
return encodings;
}
Index: src/encoding.h
===================================================================
--- src/encoding.h (Revision 17674)
+++ src/encoding.h (Arbeitskopie)
@@ -28,11 +28,19 @@ class LaTeXFeatures;
///
class Encoding {
public:
+ /// Which LaTeX package handles this encoding?
+ enum Package {
+ none,
+ inputenc,
+ CJK
+ };
///
Encoding() {}
///
Encoding(std::string const & n, std::string const & l,
- std::string const & i);
+ std::string const & i, bool f, Package p);
+ ///
+ void init() const;
///
std::string const & name() const { return Name_; }
///
@@ -51,6 +59,8 @@ public:
/// Add the preamble snippet needed for the output of latexChar(c)
/// to \p features.
void validate(char_type c, LaTeXFeatures & features) const;
+ /// Which LaTeX package handles this encoding?
+ Package package() const { return package_; }
private:
///
std::string Name_;
@@ -58,15 +68,27 @@ private:
std::string LatexName_;
///
std::string iconvName_;
+ /// Is this a fixed width encoding?
+ bool fixedwidth_;
///
typedef std::set<char_type> CharSet;
/// Set of UCS4 characters that we can encode (for singlebyte
/// encodings only)
- CharSet encodable_;
+ mutable CharSet encodable_;
/// All code points below this are encodable. This helps us to avoid
/// lokup of ASCII characters in encodable_ and gives about 1 sec
/// speedup on export of the Userguide.
- char_type start_encodable_;
+ mutable char_type start_encodable_;
+ /// Which LaTeX package handles this encoding?
+ Package package_;
+ /**
+ * If this is true the stored information about the encoding covers
+ * all encodable characters. We set this to false initially so that
+ * we only need to query iconv for the actually used encodings.
+ * This is needed especially for the multibyte encodings, if we
+ * complete all encoding info on startup it takes 2-3 minutes.
+ */
+ mutable bool complete_;
};
class Encodings {
@@ -94,6 +116,9 @@ public:
Encoding const * getFromLyXName(std::string const & name) const;
/// Get encoding from LaTeX name \p name
Encoding const * getFromLaTeXName(std::string const & name) const;
+ /// Get encoding from iconv name \p name
+ /// This is not unique!
+ Encoding const * getFromIconvName(std::string const & name) const;
///
const_iterator begin() const { return encodinglist.begin(); }
Index: src/paragraph_pimpl.C
===================================================================
--- src/paragraph_pimpl.C (Revision 17674)
+++ src/paragraph_pimpl.C (Arbeitskopie)
@@ -817,7 +817,7 @@ void Paragraph::Pimpl::validate(LaTeXFea
{
features.useLanguage(language);
lyxerr[Debug::LATEX] << "Found language "
- << language->babel() << endl;
+ << language->lang() << endl;
}
}
Index: src/LaTeXFeatures.h
===================================================================
--- src/LaTeXFeatures.h (Revision 17674)
+++ src/LaTeXFeatures.h (Arbeitskopie)
@@ -113,7 +113,7 @@ private:
static PackagesList packages_;
///
typedef std::set<Language const *> LanguageList;
- ///
+ /// used languages (only those that are supported by babel)
LanguageList UsedLanguages_;
///
typedef std::set<std::string> UsedFloats;
Index: src/buffer.C
===================================================================
--- src/buffer.C (Revision 17674)
+++ src/buffer.C (Arbeitskopie)
@@ -141,7 +141,7 @@ using std::string;
namespace {
-int const LYX_FORMAT = 263;
+int const LYX_FORMAT = 264;
} // namespace anon
@@ -976,7 +976,8 @@ void Buffer::writeLaTeXSource(odocstream
} // output_preamble
lyxerr[Debug::INFO] << "preamble finished, now the body." << endl;
- if (!lyxrc.language_auto_begin) {
+ if (!lyxrc.language_auto_begin &&
+ !params().language->babel().empty()) {
// FIXME UNICODE
os << from_utf8(subst(lyxrc.language_command_begin,
"$$lang",
@@ -985,6 +986,16 @@ void Buffer::writeLaTeXSource(odocstream
texrow().newline();
}
+ Encoding const & encoding = params().encoding();
+ if (encoding.package() == Encoding::CJK) {
+ // Open a CJK environment, since in contrast to the encodings
+ // handled by inputenc the document encoding is not set in
+ // the preamble if it is handled by CJK.sty.
+ os << "\\begin{CJK}{" << from_ascii(encoding.latexName())
+ << "}{}\n";
+ texrow().newline();
+ }
+
// if we are doing a real file with body, even if this is the
// child of some other buffer, let's cut the link here.
// This happens for example if only a child document is printed.
@@ -1005,7 +1016,16 @@ void Buffer::writeLaTeXSource(odocstream
os << endl;
texrow().newline();
- if (!lyxrc.language_auto_end) {
+ if (encoding.package() == Encoding::CJK) {
+ // Close the open CJK environment.
+ // latexParagraphs will have opened one even if the last text
+ // was not CJK.
+ os << "\\end{CJK}\n";
+ texrow().newline();
+ }
+
+ if (!lyxrc.language_auto_end &&
+ !params().language->babel().empty()) {
os << from_utf8(subst(lyxrc.language_command_end,
"$$lang",
params().language->babel()))
Index: src/bufferparams.C
===================================================================
--- src/bufferparams.C (Revision 17674)
+++ src/bufferparams.C (Arbeitskopie)
@@ -797,16 +797,15 @@ bool BufferParams::writeLaTeX(odocstream
clsoptions << "landscape,";
// language should be a parameter to \documentclass
- if (language->babel() == "hebrew"
- && default_language->babel() != "hebrew")
- // This seems necessary
- features.useLanguage(default_language);
-
ostringstream language_options;
bool const use_babel = features.useBabel();
if (use_babel) {
language_options << features.getLanguages();
- language_options << language->babel();
+ if (!language->babel().empty()) {
+ if (!language_options.str().empty())
+ language_options << ',';
+ language_options << language->babel();
+ }
if (lyxrc.language_global_options)
clsoptions << language_options.str() << ',';
}
@@ -849,16 +848,15 @@ bool BufferParams::writeLaTeX(odocstream
if (inputenc == "auto") {
string const doc_encoding =
language->encoding()->latexName();
+ Encoding::Package const package =
+ language->encoding()->package();
// Create a list with all the input encodings used
// in the document
std::set<string> encodings =
features.getEncodingSet(doc_encoding);
- // thailatex does not use the inputenc package, but sets up
- // babel directly for tis620-0 encoding, therefore we must
- // not request inputenc for tis620-0 encoding
- if (!encodings.empty() || doc_encoding != "tis620-0") {
+ if (!encodings.empty() || package == Encoding::inputenc) {
os << "\\usepackage[";
std::set<string>::const_iterator it = encodings.begin();
std::set<string>::const_iterator const end = encodings.end();
@@ -868,7 +866,7 @@ bool BufferParams::writeLaTeX(odocstream
}
for (; it != end; ++it)
os << ',' << from_ascii(*it);
- if (doc_encoding != "tis620-0") {
+ if (package == Encoding::inputenc) {
if (!encodings.empty())
os << ',';
os << from_ascii(doc_encoding);
@@ -876,11 +874,24 @@ bool BufferParams::writeLaTeX(odocstream
os << "]{inputenc}\n";
texrow.newline();
}
- } else if (inputenc != "default" && inputenc != "tis620-0" &&
- inputenc != "ascii") {
- os << "\\usepackage[" << from_ascii(inputenc)
- << "]{inputenc}\n";
- texrow.newline();
+ if (package == Encoding::CJK) {
+ os << "\\usepackage{CJK}\n";
+ texrow.newline();
+ }
+ } else if (inputenc != "default") {
+ switch (language->encoding()->package()) {
+ case Encoding::none:
+ break;
+ case Encoding::inputenc:
+ os << "\\usepackage[" << from_ascii(inputenc)
+ << "]{inputenc}\n";
+ texrow.newline();
+ break;
+ case Encoding::CJK:
+ os << "\\usepackage{CJK}\n";
+ texrow.newline();
+ break;
+ }
}
if (use_geometry || nonstandard_papersize) {
Index: src/lyxfont.C
===================================================================
--- src/lyxfont.C (Revision 17674)
+++ src/lyxfont.C (Arbeitskopie)
@@ -752,12 +752,15 @@ int LyXFont::latexWriteStartChanges(odoc
os << "\\L{";
count += 3;
}
- } else {
+ } else if (!language()->babel().empty()) {
string const tmp =
subst(lyxrc.language_command_local,
"$$lang", language()->babel());
os << from_ascii(tmp);
count += tmp.length();
+ } else {
+ os << '{';
+ count += 1;
}
}
Index: src/paragraph.C
===================================================================
--- src/paragraph.C (Revision 17674)
+++ src/paragraph.C (Arbeitskopie)
@@ -1075,12 +1075,15 @@ bool Paragraph::simpleTeXOnePar(Buffer c
}
// Switch file encoding if necessary
- int const count = switchEncoding(os, bparams,
- *(runparams.encoding),
- *(font.language()->encoding()));
- if (count > 0) {
- column += count;
- runparams.encoding = font.language()->encoding();
+ if (runparams.encoding->package() == Encoding::inputenc &&
+ font.language()->encoding()->package() == Encoding::inputenc) {
+ int const count = switchEncoding(os, bparams,
+ *(runparams.encoding),
+ *(font.language()->encoding()));
+ if (count > 0) {
+ column += count;
+ runparams.encoding = font.language()->encoding();
+ }
}
// Do we need to change font?
Index: src/encoding.C
===================================================================
--- src/encoding.C (Revision 17674)
+++ src/encoding.C (Arbeitskopie)
@@ -123,25 +123,42 @@ struct CharInfo {
typedef std::map<char_type, CharInfo> CharInfoMap;
CharInfoMap unicodesymbols;
+
+/// The highest code point in UCS4 encoding (1<<20 + 1<<16)
+char_type const max_ucs4 = 0x110000;
+
} // namespace anon
-Encoding::Encoding(string const & n, string const & l, string const & i)
- : Name_(n), LatexName_(l), iconvName_(i)
+Encoding::Encoding(string const & n, string const & l, string const & i,
+ bool f, Encoding::Package p)
+ : Name_(n), LatexName_(l), iconvName_(i), fixedwidth_(f), package_(p)
{
- if (n == "ascii")
+ if (n == "ascii") {
// ASCII can encode 128 code points and nothing else
start_encodable_ = 128;
- else if (i == "UTF-8")
- // UTF8 can encode all 1<<20 + 1<<16 UCS4 code points
- start_encodable_ = 0x110000;
- else {
- start_encodable_ = 0;
- // temporarily switch off lyxerr, since we will generate iconv errors
- lyxerr.disable();
+ complete_ = true;
+ } else if (i == "UTF-8") {
+ // UTF8 can encode all UCS4 code points
+ start_encodable_ = max_ucs4;
+ complete_ = true;
+ } else {
+ complete_ = false;
+ }
+}
+
+
+void Encoding::init() const
+{
+ start_encodable_ = 0;
+ // temporarily switch off lyxerr, since we will generate iconv errors
+ lyxerr.disable();
+ if (fixedwidth_) {
+ // We do not need to check all UCS4 code points, it is enough
+ // if we check all 256 code points of this encoding.
for (unsigned short j = 0; j < 256; ++j) {
char const c = j;
- std::vector<char_type> const ucs4 = eightbit_to_ucs4(&c, 1, i);
+ std::vector<char_type> const ucs4 = eightbit_to_ucs4(&c, 1, iconvName_);
if (ucs4.size() == 1) {
char_type const c = ucs4[0];
CharInfoMap::const_iterator const it = unicodesymbols.find(c);
@@ -149,19 +166,36 @@ Encoding::Encoding(string const & n, str
encodable_.insert(c);
}
}
- lyxerr.enable();
- CharSet::iterator it = encodable_.find(start_encodable_);
- while (it != encodable_.end()) {
- encodable_.erase(it);
- ++start_encodable_;
- it = encodable_.find(start_encodable_);
+ } else {
+ // We do not know how many code points this encoding has, and
+ // they do not have a direct representation as a single byte,
+ // therefore we need to check all UCS4 code points.
+ // This is expensive!
+ for (char_type c = 0; c < max_ucs4; ++c) {
+ std::vector<char> const eightbit = ucs4_to_eightbit(&c, 1, iconvName_);
+ if (!eightbit.empty()) {
+ CharInfoMap::const_iterator const it = unicodesymbols.find(c);
+ if (it == unicodesymbols.end() || !it->second.force)
+ encodable_.insert(c);
+ }
}
}
+ lyxerr.enable();
+ CharSet::iterator it = encodable_.find(start_encodable_);
+ while (it != encodable_.end()) {
+ encodable_.erase(it);
+ ++start_encodable_;
+ it = encodable_.find(start_encodable_);
+ }
+ complete_ = true;
}
docstring const Encoding::latexChar(char_type c) const
{
+ // validate() should have been called before
+ BOOST_ASSERT(complete_);
+
if (c < start_encodable_)
return docstring(1, c);
if (encodable_.find(c) == encodable_.end()) {
@@ -181,6 +215,8 @@ docstring const Encoding::latexChar(char
void Encoding::validate(char_type c, LaTeXFeatures & features) const
{
+ if (!complete_)
+ init();
// Add the preamble stuff even if c can be encoded in this encoding,
// since the inputenc package only maps the code point c to a command,
// it does not make this command available.
@@ -272,6 +308,21 @@ Encoding const * Encodings::getFromLaTeX
}
+Encoding const * Encodings::getFromIconvName(string const & name) const
+{
+ // We don't use std::find_if because it makes copies of the pairs in
+ // the map.
+ // This linear search is OK since we don't have many encodings.
+ // Users could even optimize it by putting the encodings they use
+ // most at the top of lib/encodings.
+ EncodingList::const_iterator const end = encodinglist.end();
+ for (EncodingList::const_iterator it = encodinglist.begin(); it != end; ++it)
+ if (it->second.iconvName() == name)
+ return &it->second;
+ return 0;
+}
+
+
Encodings::Encodings()
{
}
@@ -363,8 +414,32 @@ void Encodings::read(FileName const & en
string const latexname = lex.getString();
lex.next();
string const iconvname = lex.getString();
+ lex.next();
+ string const width = lex.getString();
+ bool fixedwidth;
+ if (width == "fixed")
+ fixedwidth = true;
+ else if (width == "variable")
+ fixedwidth = false;
+ else
+ lex.printError("Encodings::read: "
+ "Unknown width: `$$Token'");
+ lex.next();
+ string const p = lex.getString();
+ Encoding::Package package;
+ if (p == "none")
+ package = Encoding::none;
+ else if (p == "inputenc")
+ package = Encoding::inputenc;
+ else if (p == "CJK")
+ package = Encoding::CJK;
+ else
+ lex.printError("Encodings::read: "
+ "Unknown package: `$$Token'");
lyxerr[Debug::INFO] << "Reading encoding " << name << endl;
- encodinglist[name] = Encoding(name, latexname, iconvname);
+ encodinglist[name] = Encoding(name, latexname,
+ iconvname, fixedwidth,
+ package);
if (lex.lex() != et_end)
lex.printError("Encodings::read: "
"missing end");
Index: src/output_latex.C
===================================================================
--- src/output_latex.C (Revision 17674)
+++ src/output_latex.C (Arbeitskopie)
@@ -105,7 +105,8 @@ TeXEnvironment(Buffer const & buf,
if (par_language->babel() != prev_par_language->babel()) {
if (!lyxrc.language_command_end.empty() &&
- prev_par_language->babel() != doc_language->babel()) {
+ prev_par_language->babel() != doc_language->babel() &&
+ !prev_par_language->babel().empty()) {
os << from_ascii(subst(
lyxrc.language_command_end,
"$$lang",
@@ -115,7 +116,8 @@ TeXEnvironment(Buffer const & buf,
}
if (lyxrc.language_command_end.empty() ||
- par_language->babel() != doc_language->babel()) {
+ par_language->babel() != doc_language->babel() &&
+ !par_language->babel().empty()) {
os << from_ascii(subst(
lyxrc.language_command_begin,
"$$lang",
@@ -271,7 +273,8 @@ TeXOnePar(Buffer const & buf,
|| boost::prior(pit)->getDepth() < pit->getDepth())))
{
if (!lyxrc.language_command_end.empty() &&
- prev_par_language->babel() != doc_language->babel())
+ prev_par_language->babel() != doc_language->babel() &&
+ !prev_par_language->babel().empty())
{
os << from_ascii(subst(lyxrc.language_command_end,
"$$lang",
@@ -281,7 +284,8 @@ TeXOnePar(Buffer const & buf,
}
if (lyxrc.language_command_end.empty() ||
- par_language->babel() != doc_language->babel())
+ par_language->babel() != doc_language->babel() &&
+ !par_language->babel().empty())
{
os << from_ascii(subst(
lyxrc.language_command_begin,
@@ -430,17 +434,21 @@ TeXOnePar(Buffer const & buf,
os << '\n';
texrow.newline();
}
- if (lyxrc.language_command_end.empty())
- os << from_ascii(subst(
- lyxrc.language_command_begin,
- "$$lang",
- doc_language->babel()));
- else
+ if (lyxrc.language_command_end.empty()) {
+ if (!doc_language->babel().empty()) {
+ os << from_ascii(subst(
+ lyxrc.language_command_begin,
+ "$$lang",
+ doc_language->babel()));
+ pending_newline = true;
+ }
+ } else if (!par_language->babel().empty()) {
os << from_ascii(subst(
lyxrc.language_command_end,
"$$lang",
par_language->babel()));
- pending_newline = true;
+ pending_newline = true;
+ }
}
if (pending_newline) {
@@ -567,22 +575,43 @@ void latexParagraphs(Buffer const & buf,
int switchEncoding(odocstream & os, BufferParams const & bparams,
Encoding const & oldEnc, Encoding const & newEnc)
{
- // FIXME thailatex does not support the inputenc package, so we
- // ignore switches from/to tis620-0 encoding here. This does of
- // course only work as long as the non-thai text contains ASCII
- // only, but it is the best we can do.
+ // FIXME We ignore encoding switches from/to encodings that do
+ // neither support the inputenc package nor the CJK package here.
+ // This does of course only work in special cases (e.g. switch from
+ // tis620-0 to latin1, but the text in latin1 contains ASCII only,
+ // but it is the best we can do.
if ((bparams.inputenc == "auto" || bparams.inputenc == "default") &&
oldEnc.name() != newEnc.name() &&
- oldEnc.name() != "ascii" && newEnc.name() != "ascii" &&
- oldEnc.name() != "tis620-0" && newEnc.name() != "tis620-0") {
+ oldEnc.package() != Encoding::none &&
+ newEnc.package() != Encoding::none) {
lyxerr[Debug::LATEX] << "Changing LaTeX encoding from "
<< oldEnc.name() << " to "
<< newEnc.name() << endl;
os << setEncoding(newEnc.iconvName());
if (bparams.inputenc != "default") {
docstring const inputenc(from_ascii(newEnc.latexName()));
- os << "\\inputencoding{" << inputenc << '}';
- return 16 + inputenc.length();
+ switch (newEnc.package()) {
+ case Encoding::none:
+ break;
+ case Encoding::inputenc: {
+ int count = inputenc.length();
+ if (oldEnc.package() == Encoding::CJK) {
+ os << "\\end{CJK}";
+ count += 9;
+ }
+ os << "\\inputencoding{" << inputenc << '}';
+ return count + 16;
+ }
+ case Encoding::CJK: {
+ int count = inputenc.length();
+ if (oldEnc.package() == Encoding::CJK) {
+ os << "\\end{CJK}";
+ count += 9;
+ }
+ os << "\\begin{CJK}{" << inputenc << "}{}";
+ return count + 15;
+ }
+ }
}
}
return 0;
Index: lib/lyx2lyx/LyX.py
===================================================================
--- lib/lyx2lyx/LyX.py (Revision 17674)
+++ lib/lyx2lyx/LyX.py (Arbeitskopie)
@@ -74,7 +74,7 @@ format_relation = [("0_06", [200], ge
("1_2", [220], generate_minor_versions("1.2" , 4)),
("1_3", [221], generate_minor_versions("1.3" , 7)),
("1_4", range(222,246), generate_minor_versions("1.4" , 3)),
- ("1_5", range(246,264), generate_minor_versions("1.5" , 0))]
+ ("1_5", range(246,265), generate_minor_versions("1.5" , 0))]
def formats_list():
Index: lib/lyx2lyx/lyx_1_5.py
===================================================================
--- lib/lyx2lyx/lyx_1_5.py (Revision 17674)
+++ lib/lyx2lyx/lyx_1_5.py (Arbeitskopie)
@@ -1246,6 +1246,28 @@ def revert_language_name(document):
document.header[i] = "\\language %s" % document.language
+def revert_CJK(document):
+ " Set CJK encodings to default and languages chinese, japanese and korean to english. "
+ encodings = ["Bg5", "Bg5+", "GB", "GBt", "GBK", "JIS",
+ "KS", "SJIS", "UTF8", "EUC-TW", "EUC-JP"]
+ i = find_token(document.header, "\\inputencoding", 0)
+ if i == -1:
+ document.header.append("\\inputencoding auto")
+ else:
+ inputenc = get_value(document.header, "\\inputencoding", i)
+ if inputenc in encodings:
+ document.header[i] = "\\inputencoding default"
+ document.inputencoding = get_value(document.header, "\\inputencoding", 0)
+
+ if document.language == "chinese-simplified" or \
+ document.language == "chinese-traditional" or \
+ document.language == "japanese" or document.language == "korean":
+ document.language = "english"
+ i = find_token(document.header, "\\language", 0)
+ if i != -1:
+ document.header[i] = "\\language english"
+
+
##
# Conversion hub
#
@@ -1268,9 +1290,11 @@ convert = [[246, []],
[260, []],
[261, [convert_changes]],
[262, []],
- [263, [normalize_language_name]]]
+ [263, [normalize_language_name]],
+ [264, []]]
-revert = [[262, [revert_language_name]],
+revert = [[263, [revert_CJK]],
+ [262, [revert_language_name]],
[261, [revert_ascii]],
[260, []],
[259, [revert_utf8x]],
Index: lib/languages
===================================================================
--- lib/languages (Revision 17674)
+++ lib/languages (Arbeitskopie)
@@ -14,6 +14,8 @@ bulgarian bulgarian "Bulgarian"
canadian canadian "Canadian" false iso8859-15 en_CA ""
canadien canadien "French Canadian" false iso8859-15 fr_CA ""
catalan catalan "Catalan" false iso8859-15 ca_ES ""
+chinese-simplified "" "Chinese (simplified)" false euc-cn zh ""
+chinese-traditional "" "Chinese (traditional)" false utf8-cjk zh ""
croatian croatian "Croatian" false iso8859-2 hr_HR ""
czech czech "Czech" false iso8859-2 cs_CZ ""
danish danish "Danish" false iso8859-15 da_DK ""
@@ -35,7 +37,9 @@ hebrew hebrew "Hebrew" true cp125
#hungarian hungarian "Hungarian" false iso8859-2 "" ""
irish irish "Irish" false iso8859-15 ga_IE ""
italian italian "Italian" false iso8859-15 it_IT ""
+japanese "" "Japanese" false euc-jp ja ""
kazakh kazakh "Kazakh" false pt154 kk_KZ ""
+korean "" "Korean" false euc-kr ko ""
#lsorbian lsorbian "Lsorbian" false iso8859-2 "" ""
# no ISO listing for lsorbian (Garst)
lithuanian lithuanian "Lithuanian" false iso8859-13 lt_LT ""
Index: lib/encodings
===================================================================
--- lib/encodings (Revision 17674)
+++ lib/encodings (Arbeitskopie)
@@ -1,125 +1,181 @@
# FIXME: Have a look at the encodings known by the inputenc package and add
# missing ones. Caution: File format change!
-# Note that you can only add single byte encodings to this file without
-# changing some C++ code.
-# The only multibyte encoding that is currently supported is utf8, and this
-# support is hardcoded to the iconv name "UTF-8".
+# Note that you can only add singlebyte encodings to this file.
+# LyX does not support the output of multibyte encodings (e.g. utf16).
+# It does support singlebyte encodings with variable with (e.g. utf8).
+# These are marked with the "variable" keyword.
+# Fixed width encodings are marked with the "fixed" keyword.
-# Order of names: LyX name LaTeX name iconv name
+# Syntax: Encoding <LyX name> <LaTeX name> <iconv name> fixed|variable <package> End
-Encoding utf8 utf8 UTF-8
+# encodings used by inputenc.sty
+
+Encoding utf8 utf8 UTF-8 variable inputenc
End
# This one is used by many CJK packages. utf8 is supposed to be the successor,
# but does not have all features of utf8x yet.
-Encoding utf8x utf8x UTF-8
+Encoding utf8x utf8x UTF-8 variable inputenc
End
-Encoding iso8859-1 latin1 ISO-8859-1
+Encoding iso8859-1 latin1 ISO-8859-1 fixed inputenc
End
-Encoding iso8859-2 latin2 ISO-8859-2
+Encoding iso8859-2 latin2 ISO-8859-2 fixed inputenc
End
-Encoding iso8859-3 latin3 ISO-8859-3
+Encoding iso8859-3 latin3 ISO-8859-3 fixed inputenc
End
-Encoding iso8859-4 latin4 ISO-8859-4
+Encoding iso8859-4 latin4 ISO-8859-4 fixed inputenc
End
-Encoding iso8859-5 iso88595 ISO-8859-5
+Encoding iso8859-5 iso88595 ISO-8859-5 fixed inputenc
End
# Not standard, see http://tug.ctan.org/tex-archive/language/arabic/arabi/arabi/texmf/latex/arabi/
-Encoding iso8859-6 8859-6 ISO-8859-6
+Encoding iso8859-6 8859-6 ISO-8859-6 fixed inputenc
End
-Encoding iso8859-7 iso-8859-7 ISO-8859-7
+Encoding iso8859-7 iso-8859-7 ISO-8859-7 fixed inputenc
End
-Encoding iso8859-8 8859-8 ISO-8859-8
+Encoding iso8859-8 8859-8 ISO-8859-8 fixed inputenc
End
-Encoding iso8859-9 latin5 ISO-8859-9
+Encoding iso8859-9 latin5 ISO-8859-9 fixed inputenc
End
# Not standard, see http://www.vtex.lt/tex/littex/index.html
-Encoding iso8859-13 l7xenc ISO-8859-13
+Encoding iso8859-13 l7xenc ISO-8859-13 fixed inputenc
End
-Encoding iso8859-15 latin9 ISO-8859-15
+Encoding iso8859-15 latin9 ISO-8859-15 fixed inputenc
End
-Encoding iso8859-16 latin10 ISO-8859-16
+Encoding iso8859-16 latin10 ISO-8859-16 fixed inputenc
End
-Encoding cp437 cp437 CP437
+Encoding cp437 cp437 CP437 fixed inputenc
End
# cp437, but on position 225 is sz instead of beta
-Encoding cp437de cp437de CP437
+Encoding cp437de cp437de CP437 fixed inputenc
End
-Encoding cp850 cp850 CP850
+Encoding cp850 cp850 CP850 fixed inputenc
End
-Encoding cp852 cp852 CP852
+Encoding cp852 cp852 CP852 fixed inputenc
End
-Encoding cp855 cp855 CP855
+Encoding cp855 cp855 CP855 fixed inputenc
End
-Encoding cp858 cp858 CP858
+Encoding cp858 cp858 CP858 fixed inputenc
End
-Encoding cp862 cp862 CP862
+Encoding cp862 cp862 CP862 fixed inputenc
End
-Encoding cp865 cp865 CP865
+Encoding cp865 cp865 CP865 fixed inputenc
End
-Encoding cp866 cp866 CP866
+Encoding cp866 cp866 CP866 fixed inputenc
End
-Encoding cp1250 cp1250 CP1250
+Encoding cp1250 cp1250 CP1250 fixed inputenc
End
-Encoding cp1251 cp1251 CP1251
+Encoding cp1251 cp1251 CP1251 fixed inputenc
End
-Encoding cp1252 cp1252 CP1252
+Encoding cp1252 cp1252 CP1252 fixed inputenc
End
-Encoding cp1255 cp1255 CP1255
+Encoding cp1255 cp1255 CP1255 fixed inputenc
End
# Not standard, see http://tug.ctan.org/tex-archive/language/arabic/arabi/arabi/texmf/latex/arabi/
-Encoding cp1256 cp1256 CP1256
+Encoding cp1256 cp1256 CP1256 fixed inputenc
End
-Encoding cp1257 cp1257 CP1257
+Encoding cp1257 cp1257 CP1257 fixed inputenc
End
-Encoding koi8 koi8-r KOI8-R
+Encoding koi8 koi8-r KOI8-R fixed inputenc
End
-Encoding koi8-u koi8-u KOI8-U
+Encoding koi8-u koi8-u KOI8-U fixed inputenc
End
-# This one needs hardcoded support, since the inputenc package does not know
-# tis620-0, and thailatex sets up babel directly to use tis620-0, so the value
-# for inputenc is never output to .tex files (but needed for the hardcoded
-# tis620-0 support).
-Encoding tis620-0 tis620-0 TIS620-0
+Encoding pt154 pt154 PT154 fixed inputenc
End
-Encoding pt154 pt154 PT154
+Encoding pt254 pt254 PT254 fixed inputenc
End
-Encoding pt254 pt254 PT254
+
+# encodings used by CJK.sty
+
+# The following encodings that are supported by the CJK package are not
+# included here, because they are not widely used and lack proper iconv support:
+# Bg5+, GBt
+# See the NOTES file of libiconv for details.
+
+# The following encodings can't be handled directly, because the code points
+# of TeX control characters like {, } and \ can occur in the second byte:
+
+# For traditional chinese
+#Encoding big5 Bg5 BIG5 variable CJK
+#End
+
+# For japanese
+#Encoding shift-jis SJIS SJIS variable CJK
+#End
+
+# The following encodings need hardcoded support of the encodable unicode
+# range, but are known by iconv:
+
+# For simplified chinese
+Encoding euc-cn GB EUC-CN variable CJK
+End
+
+# For simplified chinese
+Encoding gbk GBK GBK variable CJK
End
+# For japanese
+Encoding jis JIS JIS variable CJK
+End
+
+# For korean
+Encoding euc-kr KS EUC-KR variable CJK
+End
+
+# The CJK package has yet another name for utf8...
+Encoding utf8-cjk UTF8 UTF-8 variable CJK
+End
+
+# For traditional chinese
+Encoding euc-tw EUC-TW EUC-TW variable CJK
+End
+
+# For japanese
+Encoding euc-jp EUC-JP EUC-JP variable CJK
+End
+
+
+# This one needs hardcoded support, since the inputenc package does not know
+# tis620-0, and thailatex sets up babel directly to use tis620-0, so the
+# LaTeX name is never output to .tex files (but needed for the hardcoded
+# tis620-0 support).
+Encoding tis620-0 tis620-0 TIS620-0 fixed none
+End
+
+
# Pure 7bit ASCII encoding (partially hardcoded in LyX)
-Encoding ascii ascii ascii
+Encoding ascii ascii ascii fixed none
End
+
