X-Git-Url: https://git.lyx.org/gitweb/?a=blobdiff_plain;f=src%2Ftex2lyx%2Ftext.cpp;h=50eee93a3d2291596ee63140d7afac665298232f;hb=8e7b5eebf0ef9742e5f6983d8f55f563c12a31ab;hp=3f65d43642b0fc361bbbf52d54a0bb498eb912a9;hpb=c1965123ed2a5390a1d719f4ba3f92c27376adff;p=lyx.git diff --git a/src/tex2lyx/text.cpp b/src/tex2lyx/text.cpp index 3f65d43642..50eee93a3d 100644 --- a/src/tex2lyx/text.cpp +++ b/src/tex2lyx/text.cpp @@ -117,6 +117,62 @@ char const * const known_ref_commands[] = { "ref", "pageref", "vref", char const * const known_coded_ref_commands[] = { "ref", "pageref", "vref", "vpageref", "formatted", "eqref", 0 }; +/** + * known polyglossia language names (including variants) + */ +const char * const polyglossia_languages[] = { +"albanian", "croatian", "hebrew", "norsk", "swedish", "amharic", "czech", "hindi", +"nynorsk", "syriac", "arabic", "danish", "icelandic", "occitan", "tamil", +"armenian", "divehi", "interlingua", "polish", "telugu", "asturian", "dutch", +"irish", "portuges", "thai", "bahasai", "english", "italian", "romanian", "turkish", +"bahasam", "esperanto", "lao", "russian", "turkmen", "basque", "estonian", "latin", +"samin", "ukrainian", "bengali", "farsi", "latvian", "sanskrit", "urdu", "brazil", +"brazilian", "finnish", "lithuanian", "scottish", "usorbian", "breton", "french", +"lsorbian", "serbian", "vietnamese", "bulgarian", "galician", "magyar", "slovak", +"welsh", "catalan", "german", "malayalam", "slovenian", "coptic", "greek", +"marathi", "spanish", +"american", "ancient", "australian", "british", "monotonic", "newzealand", +"polytonic", 0}; + +/** + * the same as polyglossia_languages with .lyx names + * please keep this in sync with polyglossia_languages line by line! + */ +const char * const coded_polyglossia_languages[] = { +"albanian", "croatian", "hebrew", "norsk", "swedish", "amharic", "czech", "hindi", +"nynorsk", "syriac", "arabic_arabi", "danish", "icelandic", "occitan", "tamil", +"armenian", "divehi", "interlingua", "polish", "telugu", "asturian", "dutch", +"irish", "portuges", "thai", "bahasa", "english", "italian", "romanian", "turkish", +"bahasam", "esperanto", "lao", "russian", "turkmen", "basque", "estonian", "latin", +"samin", "ukrainian", "bengali", "farsi", "latvian", "sanskrit", "urdu", "brazilian", +"brazilian", "finnish", "lithuanian", "scottish", "uppersorbian", "breton", "french", +"lowersorbian", "serbian", "vietnamese", "bulgarian", "galician", "magyar", "slovak", +"welsh", "catalan", "ngerman", "malayalam", "slovene", "coptic", "greek", +"marathi", "spanish", +"american", "ancientgreek", "australian", "british", "greek", "newzealand", +"polutonikogreek", 0}; + +/** + * supported CJK encodings + */ +const char * const supported_CJK_encodings[] = { +"EUC-JP", "KS", "GB", "UTF8", 0}; + +/** + * the same as supported_CJK_encodings with their corresponding LyX language name + * please keep this in sync with supported_CJK_encodings line by line! + */ +const char * const coded_supported_CJK_encodings[] = { +"japanese-cjk", "korean", "chinese-simplified", "chinese-traditional", 0}; + +string CJK2lyx(string const & encoding) +{ + char const * const * where = is_known(encoding, supported_CJK_encodings); + if (where) + return coded_supported_CJK_encodings[where - supported_CJK_encodings]; + return encoding; +} + /*! * natbib commands. * The starred forms are also known except for "citefullauthor", @@ -461,7 +517,9 @@ docstring convert_unicodesymbols(docstring s) set req; docstring parsed = encodings.fromLaTeXCommand(s, Encodings::TEXT_CMD, termination, rem, &req); - for (set::const_iterator it = req.begin(); it != req.end(); it++) + set::const_iterator it = req.begin(); + set::const_iterator en = req.end(); + for (; it != en; ++it) preamble.registerAutomaticallyLoadedPackage(*it); os << parsed; s = rem; @@ -1210,6 +1268,23 @@ void parse_environment(Parser & p, ostream & os, bool outer, } } + else if (is_known(name, polyglossia_languages)) { + // We must begin a new paragraph if not already done + if (! parent_context.atParagraphStart()) { + parent_context.check_end_layout(os); + parent_context.new_paragraph(os); + } + // save the language in the context so that it is + // handled by parse_text + parent_context.font.language = polyglossia2lyx(name); + parse_text(p, os, FLAG_END, outer, parent_context); + // Just in case the environment is empty + parent_context.extra_stuff.erase(); + // We must begin a new paragraph to reset the language + parent_context.new_paragraph(os); + p.skip_spaces(); + } + else if (unstarred_name == "tabular" || name == "longtable") { eat_whitespace(p, os, parent_context, false); string width = "0pt"; @@ -1379,6 +1454,57 @@ void parse_environment(Parser & p, ostream & os, bool outer, os << "\n\\begin_layout Standard\n"; } + else if (name == "CJK") { + // the scheme is \begin{CJK}{encoding}{mapping}{text} + // It is impossible to decide if a CJK environment was in its own paragraph or within + // a line. We therefore always assume a paragraph since the latter is a rare case. + eat_whitespace(p, os, parent_context, false); + parent_context.check_end_layout(os); + // store the encoding to be able to reset it + string const encoding_old = p.encoding_latex_; + string const encoding = p.getArg('{', '}'); + // SJIS and BIG5 don't work with LaTeX according to the comment in unicode.cpp + // JIS does not work with LyX's encoding conversion + if (encoding != "SJIS" && encoding != "BIG5" && encoding != "JIS") + p.setEncoding(encoding); + else + p.setEncoding("utf8"); + // LyX doesn't support the second argument so if + // this is used we need to output everything as ERT + string const mapping = p.getArg('{', '}'); + if ( (!mapping.empty() && mapping != " ") + || (!is_known(encoding, supported_CJK_encodings))) { + parent_context.check_layout(os); + handle_ert(os, "\\begin{" + name + "}{" + encoding + "}{" + mapping + "}", + parent_context); + // we must parse the content as verbatim because e.g. SJIS can contain + // normally invalid characters + string const s = p.plainEnvironment("CJK"); + string::const_iterator it2 = s.begin(); + for (string::const_iterator it = s.begin(), et = s.end(); it != et; ++it) { + if (*it == '\\') + handle_ert(os, "\\", parent_context); + else if (*it == '$') + handle_ert(os, "$", parent_context); + else + os << *it; + } + p.skip_spaces(); + handle_ert(os, "\\end{" + name + "}", + parent_context); + } else { + string const lang = CJK2lyx(encoding); + // store the language because we must reset it at the end + string const lang_old = parent_context.font.language; + parent_context.font.language = lang; + parse_text_in_inset(p, os, FLAG_END, outer, parent_context); + parent_context.font.language = lang_old; + parent_context.new_paragraph(os); + } + p.encoding_latex_ = encoding_old; + p.skip_spaces(); + } + else if (name == "lyxgreyedout") { eat_whitespace(p, os, parent_context, false); parent_context.check_layout(os); @@ -1556,7 +1682,9 @@ void parse_environment(Parser & p, ostream & os, bool outer, if (!preamble.titleLayoutFound()) preamble.titleLayoutFound(newlayout->intitle); set const & req = newlayout->requires(); - for (set::const_iterator it = req.begin(); it != req.end(); it++) + set::const_iterator it = req.begin(); + set::const_iterator en = req.end(); + for (; it != en; ++it) preamble.registerAutomaticallyLoadedPackage(*it); } @@ -1973,6 +2101,43 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, while (p.good()) { Token const & t = p.get_token(); + // it is impossible to determine the correct document language if CJK is used. + // Therefore write a note at the beginning of the document + if (have_CJK) { + context.check_layout(os); + begin_inset(os, "Note Note\n"); + os << "status open\n\\begin_layout Plain Layout\n" + << "\\series bold\n" + << "Important information:\n" + << "\\end_layout\n\n" + << "\\begin_layout Plain Layout\n" + << "This document contains text in Chinese, Japanese or Korean.\n" + << " It was therefore impossible for tex2lyx to set the correct document langue for your document." + << " Please set in the document settings by yourself!\n" + << "\\end_layout\n"; + end_inset(os); + have_CJK = false; + } + + // it is impossible to determine the correct encoding for non-CJK Japanese. + // Therefore write a note at the beginning of the document + if (is_nonCJKJapanese) { + context.check_layout(os); + begin_inset(os, "Note Note\n"); + os << "status open\n\\begin_layout Plain Layout\n" + << "\\series bold\n" + << "Important information:\n" + << "\\end_layout\n\n" + << "\\begin_layout Plain Layout\n" + << "This document is in Japanese (non-CJK).\n" + << " It was therefore impossible for tex2lyx to determine the correct encoding." + << " The encoding EUC-JP was assumed. If this is incorrect, please set the correct" + << " encoding in the document settings.\n" + << "\\end_layout\n"; + end_inset(os); + is_nonCJKJapanese = false; + } + #ifdef FILEDEBUG debugToken(cerr, t, flags); #endif @@ -2486,8 +2651,9 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, if (!preamble.titleLayoutFound()) preamble.titleLayoutFound(newlayout->intitle); set const & req = newlayout->requires(); - for (set::const_iterator it = req.begin(); - it != req.end(); it++) + set::const_iterator it = req.begin(); + set::const_iterator en = req.end(); + for (; it != en; ++it) preamble.registerAutomaticallyLoadedPackage(*it); } else handle_ert(os, @@ -2508,7 +2674,7 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, if (!preamble.titleLayoutFound()) preamble.titleLayoutFound(newlayout->intitle); set const & req = newlayout->requires(); - for (set::const_iterator it = req.begin(); it != req.end(); it++) + for (set::const_iterator it = req.begin(); it != req.end(); ++it) preamble.registerAutomaticallyLoadedPackage(*it); } @@ -2521,7 +2687,7 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, if (!preamble.titleLayoutFound()) preamble.titleLayoutFound(newlayout->intitle); set const & req = newlayout->requires(); - for (set::const_iterator it = req.begin(); it != req.end(); it++) + for (set::const_iterator it = req.begin(); it != req.end(); ++it) preamble.registerAutomaticallyLoadedPackage(*it); } @@ -3396,7 +3562,6 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, context.check_layout(os); // save the language for the case that a // \foreignlanguage is used - context.font.language = babel2lyx(p.verbatim_item()); os << "\n\\lang " << context.font.language << "\n"; } @@ -3407,6 +3572,38 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, context, "\\lang", context.font.language, lang); } + + else if (is_known(t.cs().substr(4, string::npos), polyglossia_languages)) { + // scheme is \textLANGUAGE{text} where LANGUAGE is in polyglossia_languages[] + string lang; + // We have to output the whole command if it has an option + // because LyX doesn't support this yet, see bug #8214, + // only if there is a single option specifying a variant, we can handle it. + if (p.hasOpt()) { + string langopts = p.getOpt(); + // check if the option contains a variant, if yes, extract it + string::size_type pos_var = langopts.find("variant"); + string::size_type i = langopts.find(','); + if (pos_var != string::npos){ + string variant; + if (i == string::npos) { + variant = langopts.substr(pos_var + 8, langopts.length() - pos_var - 9); + lang = polyglossia2lyx(variant); + parse_text_attributes(p, os, FLAG_ITEM, outer, + context, "\\lang", + context.font.language, lang); + } + else + handle_ert(os, t.asInput() + langopts, context); + } else + handle_ert(os, t.asInput() + langopts, context); + } else { + lang = polyglossia2lyx(t.cs().substr(4, string::npos)); + parse_text_attributes(p, os, FLAG_ITEM, outer, + context, "\\lang", + context.font.language, lang); + } + } else if (t.cs() == "inputencoding") { // nothing to write here @@ -3521,7 +3718,7 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, << ", result is " << to_utf8(s) << "+" << to_utf8(rem) << endl; os << to_utf8(s); - for (set::const_iterator it = req.begin(); it != req.end(); it++) + for (set::const_iterator it = req.begin(); it != req.end(); ++it) preamble.registerAutomaticallyLoadedPackage(*it); } else // we did not find a non-ert version @@ -4128,7 +4325,7 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, os << to_utf8(s); if (termination) skip_spaces_braces(p); - for (set::const_iterator it = req.begin(); it != req.end(); it++) + for (set::const_iterator it = req.begin(); it != req.end(); ++it) preamble.registerAutomaticallyLoadedPackage(*it); } //cerr << "#: " << t << " mode: " << mode << endl;