X-Git-Url: https://git.lyx.org/gitweb/?a=blobdiff_plain;f=src%2Ftex2lyx%2Ftext.cpp;h=62d5e8df9ebfaf80c6d3458a94bf37d5ffdba6af;hb=fe5a4c8c81ef2e5dca844732c7f24545b5edaca9;hp=2f59222ed7deeeaa7725ceb9d737fb31236f1a62;hpb=1a6c599917355743a868c20a0b62b5f4c47c8294;p=lyx.git diff --git a/src/tex2lyx/text.cpp b/src/tex2lyx/text.cpp index 2f59222ed7..62d5e8df9e 100644 --- a/src/tex2lyx/text.cpp +++ b/src/tex2lyx/text.cpp @@ -117,6 +117,30 @@ char const * const known_ref_commands[] = { "ref", "pageref", "vref", char const * const known_coded_ref_commands[] = { "ref", "pageref", "vref", "vpageref", "formatted", "eqref", 0 }; +/** + * supported CJK encodings + * SJIS anf Bg5 cannot be supported as this is not + * supported by iconv + * JIS does not work with LyX's encoding conversion + */ +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 +485,9 @@ 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; @@ -1186,8 +1212,7 @@ void parse_unknown_environment(Parser & p, string const & name, ostream & os, void parse_environment(Parser & p, ostream & os, bool outer, - string & last_env, bool & title_layout_found, - Context & parent_context) + string & last_env, Context & parent_context) { Layout const * newlayout; InsetLayout const * newinsetlayout = 0; @@ -1211,6 +1236,23 @@ void parse_environment(Parser & p, ostream & os, bool outer, } } + else if (is_known(name, preamble.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 = preamble.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"; @@ -1380,6 +1422,55 @@ 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.getEncoding(); + string const encoding = p.getArg('{', '}'); + // SJIS and Bg5 cammopt be handled by iconv + // JIS does not work with LyX's encoding conversion + if (encoding != "Bg5" && encoding != "JIS" && encoding != "SJIS") + 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. JIS can contain + // normally invalid characters + string const s = p.plainEnvironment("CJK"); + 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; + } + 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.setEncoding(encoding_old); + p.skip_spaces(); + } + else if (name == "lyxgreyedout") { eat_whitespace(p, os, parent_context, false); parent_context.check_layout(os); @@ -1554,10 +1645,12 @@ void parse_environment(Parser & p, ostream & os, bool outer, context.check_end_deeper(os); parent_context.new_paragraph(os); p.skip_spaces(); - if (!title_layout_found) - title_layout_found = newlayout->intitle; + 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); } @@ -1971,10 +2064,46 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, bool const use_natbib = preamble.isPackageUsed("natbib"); bool const use_jurabib = preamble.isPackageUsed("jurabib"); string last_env; - bool title_layout_found = false; 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 the language manually in the document settings.\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 @@ -2298,7 +2427,7 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, else if (t.cs() == "begin") parse_environment(p, os, outer, last_env, - title_layout_found, context); + context); else if (t.cs() == "end") { if (flags & FLAG_END) { @@ -2469,10 +2598,14 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, // Must catch empty dates before findLayout is called below else if (t.cs() == "date") { + eat_whitespace(p, os, context, false); + p.pushPosition(); string const date = p.verbatim_item(); - if (date.empty()) + p.popPosition(); + if (date.empty()) { preamble.suppressDate(true); - else { + p.verbatim_item(); + } else { preamble.suppressDate(false); if (context.new_layout_allowed && (newlayout = findLayout(context.textclass, @@ -2480,16 +2613,18 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, // write the layout output_command_layout(os, p, outer, context, newlayout); - p.skip_spaces(); - if (!title_layout_found) - title_layout_found = newlayout->intitle; + parse_text_snippet(p, os, FLAG_ITEM, outer, context); + 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, "\\date{" + date + '}', - context); + handle_ert(os, + "\\date{" + p.verbatim_item() + '}', + context); } } @@ -2502,10 +2637,10 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, p.get_token(); output_command_layout(os, p, outer, context, newlayout); p.skip_spaces(); - if (!title_layout_found) - title_layout_found = newlayout->intitle; + 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); } @@ -2515,10 +2650,10 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, // write the layout output_command_layout(os, p, outer, context, newlayout); p.skip_spaces(); - if (!title_layout_found) - title_layout_found = newlayout->intitle; + 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); } @@ -2808,18 +2943,20 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, } else if (t.cs() == "makeindex" || t.cs() == "maketitle") { - if (title_layout_found) { + if (preamble.titleLayoutFound()) { // swallow this skip_spaces_braces(p); } else handle_ert(os, t.asInput(), context); } - else if (t.cs() == "tableofcontents") { + else if (t.cs() == "tableofcontents" || t.cs() == "lstlistoflistings") { context.check_layout(os); - begin_command_inset(os, "toc", "tableofcontents"); + begin_command_inset(os, "toc", t.cs()); end_inset(os); skip_spaces_braces(p); + if (t.cs() == "lstlistoflistings") + preamble.registerAutomaticallyLoadedPackage("listings"); } else if (t.cs() == "listoffigures") { @@ -3391,7 +3528,6 @@ 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"; } @@ -3402,6 +3538,36 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, context, "\\lang", context.font.language, lang); } + + else if (prefixIs(t.cs(), "text") + && is_known(t.cs().substr(4), preamble.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(','); + string::size_type k = langopts.find('=', pos_var); + if (pos_var != string::npos && i == string::npos) { + string variant; + variant = langopts.substr(k + 1, langopts.length() - k - 2); + lang = preamble.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 { + lang = preamble.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 @@ -3516,7 +3682,7 @@ 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 @@ -3745,14 +3911,21 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, arg += p.getFullOpt(); eat_whitespace(p, os, context, false); handle_ert(os, arg + '{', context); - eat_whitespace(p, os, context, false); parse_text(p, os, FLAG_ITEM, outer, context); handle_ert(os, "}", context); } else { string special = p.getFullOpt(); special += p.getOpt(); - parse_outer_box(p, os, FLAG_ITEM, outer, - context, t.cs(), special); + // LyX does not yet support \framebox without any option + if (!special.empty()) + parse_outer_box(p, os, FLAG_ITEM, outer, + context, t.cs(), special); + else { + eat_whitespace(p, os, context, false); + handle_ert(os, "\\framebox{", context); + parse_text(p, os, FLAG_ITEM, outer, context); + handle_ert(os, "}", context); + } } } @@ -3766,7 +3939,6 @@ void parse_text(Parser & p, ostream & os, unsigned flags, bool outer, arg += p.getFullOpt(); eat_whitespace(p, os, context, false); handle_ert(os, arg + '{', context); - eat_whitespace(p, os, context, false); parse_text(p, os, FLAG_ITEM, outer, context); handle_ert(os, "}", context); } else @@ -4123,7 +4295,7 @@ 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;