*** Implement GUI names for encodings (part of bug 4971) ***

* lib/encodings:
	- add new column "GUI names"

* src/Encoding.{cpp,h}:
	- read in and handle GUI names

* src/frontends/qt4/GuiDocument.cpp:
	- display GUI names instead of LaTeX names

* po/lyx_pot.py:
* po/Rules-lyx:
* development/scons/SConstruct:
	- add encoding GUI names to the po files.

git-svn-id: svn://svn.lyx.org/lyx/lyx-devel/trunk@25558 a592a061-630c-0410-9148-cb99ea01b6c8

development/scons/SConstruct

@@ -1762,7 +1762,7 @@ if 'update_po' in BUILD_TARGETS:
         ['$TOP_SRCDIR/src/tex2lyx/%s' % x for x in src_tex2lyx_header_files + src_tex2lyx_files ]
     )
     Alias('update_po', POTFILES_in)
-    # build language_l10n.pot, ui_l10n.pot, layouts_l10n.pot, qt4_l10n.pot, external_l10n, formats_l10n
+    # build language_l10n.pot, encodings_10n.pot, ui_l10n.pot, layouts_l10n.pot, qt4_l10n.pot, external_l10n, formats_l10n
     # and combine them to lyx.po
     env['LYX_POT'] = 'python $TOP_SRCDIR/po/lyx_pot.py'
     lyx_po = env.Command('$BUILDDIR/po/lyx.po',
@@ -1775,6 +1775,8 @@ if 'update_po' in BUILD_TARGETS:
                 '$LYX_POT -b $TOP_SRCDIR -t layouts -o $TARGET $SOURCES'),
              env.Command('$BUILDDIR/po/languages_l10n.pot', '$TOP_SRCDIR/lib/languages',
                 '$LYX_POT -b $TOP_SRCDIR -t languages -o $TARGET $SOURCES'),
+             env.Command('$BUILDDIR/po/encodings_l10n.pot', '$TOP_SRCDIR/lib/encodings',
+                '$LYX_POT -b $TOP_SRCDIR -t encodings -o $TARGET $SOURCES'),
              env.Command('$BUILDDIR/po/ui_l10n.pot', 
                 ['$TOP_SRCDIR/lib/ui/%s' % x for x in lib_ui_files],
                 '$LYX_POT -b $TOP_SRCDIR -t ui -o $TARGET $SOURCES'),

lib/encodings

@@ -7,117 +7,117 @@
 # These are marked with the "variable" keyword.
 # Fixed width encodings are marked with the "fixed" keyword.
 
-# Syntax: Encoding <LyX name> <LaTeX name> <iconv name> fixed|variable <package> End
+# Syntax: Encoding <LyX name> <LaTeX name> <GUI name> <iconv name> fixed|variable <package> End
 
 # encodings used by inputenc.sty
 
-Encoding utf8 utf8 UTF-8 variable inputenc
+Encoding utf8 utf8 "Unicode (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 variable inputenc
+Encoding utf8x utf8x "Unicode (ucs-extended) (utf8x)" UTF-8 variable inputenc
 End
 
 # This encoding is used to typeset Armenian using the armTeX package
-Encoding armscii8 armscii8 ARMSCII-8 fixed inputenc
+Encoding armscii8 armscii8 "Armenian (ArmSCII8)" ARMSCII-8 fixed inputenc
 End
 
-Encoding iso8859-1 latin1 ISO-8859-1 fixed inputenc
+Encoding iso8859-1 latin1 "Western European (ISO 8859-1)" ISO-8859-1 fixed inputenc
 End
 
-Encoding iso8859-2 latin2 ISO-8859-2 fixed inputenc
+Encoding iso8859-2 latin2 "Central European (ISO 8859-2)" ISO-8859-2 fixed inputenc
 End
 
-Encoding iso8859-3 latin3 ISO-8859-3 fixed inputenc
+Encoding iso8859-3 latin3 "Middle European (ISO 8859-3)" ISO-8859-3 fixed inputenc
 End
 
-Encoding iso8859-4 latin4 ISO-8859-4 fixed inputenc
+Encoding iso8859-4 latin4 "Baltic (ISO 8859-4)" ISO-8859-4 fixed inputenc
 End
 
-Encoding iso8859-5 iso88595 ISO-8859-5 fixed inputenc
+Encoding iso8859-5 iso88595 "Cyrillic (ISO 8859-5)" 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 fixed inputenc
+Encoding iso8859-6 8859-6 "Arabic (ISO 8859-6)" ISO-8859-6 fixed inputenc
 End
 
-Encoding iso8859-7 iso-8859-7 ISO-8859-7 fixed inputenc
+Encoding iso8859-7 iso-8859-7 "Greek (ISO 8859-7)" ISO-8859-7 fixed inputenc
 End
 
-Encoding iso8859-8 8859-8 ISO-8859-8 fixed inputenc
+Encoding iso8859-8 8859-8 "Hebrew (ISO 8859-8)" ISO-8859-8 fixed inputenc
 End
 
-Encoding iso8859-9 latin5 ISO-8859-9 fixed inputenc
+Encoding iso8859-9 latin5 "Turkish (ISO 8859-9)" ISO-8859-9 fixed inputenc
 End
 
 # Not standard, see http://www.vtex.lt/tex/littex/index.html
-Encoding iso8859-13 l7xenc ISO-8859-13 fixed inputenc
+Encoding iso8859-13 l7xenc "Baltic (ISO 8859-13)" ISO-8859-13 fixed inputenc
 End
 
-Encoding iso8859-15 latin9 ISO-8859-15 fixed inputenc
+Encoding iso8859-15 latin9 "Western European (ISO 8859-15)" ISO-8859-15 fixed inputenc
 End
 
-Encoding iso8859-16 latin10 ISO-8859-16 fixed inputenc
+Encoding iso8859-16 latin10 "South-Eastern European (ISO 8859-16)" ISO-8859-16 fixed inputenc
 End
 
-Encoding cp437 cp437 CP437 fixed inputenc
+Encoding cp437 cp437 "DOS (CP 437)" CP437 fixed inputenc
 End
 
 # cp437, but on position 225 is sz instead of beta
-Encoding cp437de cp437de CP437 fixed inputenc
+Encoding cp437de cp437de "DOS-de (CP 437-de)" CP437 fixed inputenc
 End
 
-Encoding cp850 cp850 CP850 fixed inputenc
+Encoding cp850 cp850 "Western European (CP 850)" CP850 fixed inputenc
 End
 
-Encoding cp852 cp852 CP852 fixed inputenc
+Encoding cp852 cp852 "Central European (CP 852)" CP852 fixed inputenc
 End
 
-Encoding cp855 cp855 CP855 fixed inputenc
+Encoding cp855 cp855 "Cyrillic (CP 855)" CP855 fixed inputenc
 End
 
-Encoding cp858 cp858 CP858 fixed inputenc
+Encoding cp858 cp858 "Western European (CP 858)" CP858 fixed inputenc
 End
 
-Encoding cp862 cp862 CP862 fixed inputenc
+Encoding cp862 cp862 "Hebrew (CP 862)" CP862 fixed inputenc
 End
 
-Encoding cp865 cp865 CP865 fixed inputenc
+Encoding cp865 cp865 "Nordic languages (CP 865)" CP865 fixed inputenc
 End
 
-Encoding cp866 cp866 CP866 fixed inputenc
+Encoding cp866 cp866 "Cyrillic (CP 866)" CP866 fixed inputenc
 End
 
-Encoding cp1250 cp1250 CP1250 fixed inputenc
+Encoding cp1250 cp1250 "Central European (CP 1250)" CP1250 fixed inputenc
 End
 
-Encoding cp1251 cp1251 CP1251 fixed inputenc
+Encoding cp1251 cp1251 "Cyrillic (CP 1251)" CP1251 fixed inputenc
 End
 
-Encoding cp1252 cp1252 CP1252 fixed inputenc
+Encoding cp1252 cp1252 "Western European (CP 1252)" CP1252 fixed inputenc
 End
 
-Encoding cp1255 cp1255 CP1255 fixed inputenc
+Encoding cp1255 cp1255 "Hebrew (CP 1255)" CP1255 fixed inputenc
 End
 
 # Not standard, see http://tug.ctan.org/tex-archive/language/arabic/arabi/arabi/texmf/latex/arabi/
-Encoding cp1256 cp1256 CP1256 fixed inputenc
+Encoding cp1256 cp1256 "Arabic (CP 1256)" CP1256 fixed inputenc
 End
 
-Encoding cp1257 cp1257 CP1257 fixed inputenc
+Encoding cp1257 cp1257 "Baltic (CP 1257)" CP1257 fixed inputenc
 End
 
-Encoding koi8 koi8-r KOI8-R fixed inputenc
+Encoding koi8 koi8-r "Cyrillic (KOI8-R)" KOI8-R fixed inputenc
 End
 
-Encoding koi8-u koi8-u KOI8-U fixed inputenc
+Encoding koi8-u koi8-u "Cyrillic (KOI8-U)" KOI8-U fixed inputenc
 End
 
-Encoding pt154 pt154 PT154 fixed inputenc
+Encoding pt154 pt154 "Cyrillic (pt 154)" PT154 fixed inputenc
 End
 
-Encoding pt254 pt254 PT254 fixed inputenc
+Encoding pt254 pt254 "Cyrillic (pt 254)" PT254 fixed inputenc
 End
 
 # encodings used by CJK.sty
@@ -131,68 +131,68 @@ End
 # of TeX control characters like {, } and \ can occur in the second byte:
 
 # For traditional chinese
-#Encoding big5 Bg5 BIG5 variable CJK
+#Encoding big5 Bg5 "Chinese (traditional) (Big5)" BIG5 variable CJK
 #End
 
 # For japanese
-#Encoding shift-jis SJIS SJIS variable CJK
+#Encoding shift-jis SJIS "Japanese (CJK) (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
+Encoding euc-cn GB "Chinese (simplified) (EUC-CN)" EUC-CN variable CJK
 End
 
 # For simplified chinese
-Encoding gbk GBK GBK variable CJK
+Encoding gbk GBK "Chinese (simplified) (GBK)" GBK variable CJK
 End
 
 # For japanese
-Encoding jis JIS ISO-2022-JP variable CJK
+Encoding jis JIS "Japanese (CJK) (JIS)" ISO-2022-JP variable CJK
 End
 
 # For korean
-Encoding euc-kr KS EUC-KR variable CJK
+Encoding euc-kr KS "Korean (EUC-KR)" EUC-KR variable CJK
 End
 
 # The CJK package has yet another name for utf8...
-Encoding utf8-cjk UTF8 UTF-8 variable CJK
+Encoding utf8-cjk UTF8 "Unicode (CJK) (utf8)" UTF-8 variable CJK
 End
 
 # For traditional chinese
-Encoding euc-tw EUC-TW EUC-TW variable CJK
+Encoding euc-tw EUC-TW "Chinese (traditional) (EUC-TW)" EUC-TW variable CJK
 End
 
 # For japanese
-Encoding euc-jp EUC-JP EUC-JP variable CJK
+Encoding euc-jp EUC-JP "Japanese (CJK) (EUC-JP)" EUC-JP variable CJK
 End
 
 # encodings that do not use a package
 
 # Traditional Japanese TeX programs require neither CJK nor inputenc
 # package.
-Encoding euc-jp-plain EUC-JP-pLaTeX EUC-JP variable none
+Encoding euc-jp-plain EUC-JP-pLaTeX "Japanese (non-CJK) (EUC-JP)" EUC-JP variable none
 End
-Encoding jis-plain JIS-pLaTeX ISO-2022-JP variable none
+Encoding jis-plain JIS-pLaTeX "Japanese (non-CJK) (JIS)" ISO-2022-JP variable none
 End
-Encoding shift-jis-plain SJIS-pLaTeX CP932 variable none
+Encoding shift-jis-plain SJIS-pLaTeX "Japanese (non-CJK) (SJIS)" CP932 variable none
 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
+Encoding tis620-0 tis620-0 "Thai (TIS 620-0)" TIS620-0 fixed none
 End
 
 # A plain utf8 encoding that does not use the inputenc package.
 # Such an encoding is required for XeTeX.
-Encoding utf8-plain utf8-plain UTF-8 variable none
+Encoding utf8-plain utf8-plain "Unicode (XeTeX) (utf8)" UTF-8 variable none
 End
 
 # Pure 7bit ASCII encoding (partially hardcoded in LyX)
-Encoding ascii ascii ascii fixed none
+Encoding ascii ascii "ASCII" ascii fixed none
 End
 

po/Rules-lyx

@@ -16,7 +16,7 @@ ${srcdir}/POTFILES.in: $(POTFILE_IN_DEPS)
 	     sort | uniq ) > $@-t \
 	&& mv $@-t $@
 
-l10n_pots: qt4_l10n.pot layouts_l10n.pot languages_l10n.pot ui_l10n.pot external_l10n.pot formats_l10n.pot
+l10n_pots: qt4_l10n.pot layouts_l10n.pot languages_l10n.pot encodings_l10n.pot ui_l10n.pot external_l10n.pot formats_l10n.pot
 	cat $^ | \
 	msguniq -o $(DOMAIN).po && rm -f  $^
 
@@ -33,6 +33,9 @@ layouts_l10n.pot: $(top_srcdir)/lib/layouts/*.layout $(top_srcdir)/lib/layouts/*
 languages_l10n.pot: $(top_srcdir)/lib/languages
 	python $(srcdir)/lyx_pot.py -b $(top_srcdir) -o $@ -t languages ${top_srcdir}/lib/languages
 
+encodings_l10n.pot: $(top_srcdir)/lib/encodings
+	python $(srcdir)/lyx_pot.py -b $(top_srcdir) -o $@ -t encodings ${top_srcdir}/lib/encodings
+
 ui_l10n.pot: $(top_srcdir)/lib/ui/*.ui $(top_srcdir)/lib/ui/*.inc
 	LC_ALL=C ; export LC_ALL ; \
 	python $(srcdir)/lyx_pot.py -b $(top_srcdir) -o $@ -t ui ${top_srcdir}/lib/ui/*.ui ${top_srcdir}/lib/ui/*.inc

po/lyx_pot.py

@@ -282,6 +282,29 @@ def formats_l10n(input_files, output, base):
     output.close()
 
 
+def encodings_l10n(input_files, output, base):
+    '''Generate pot file from lib/encodings'''
+    output = open(output, 'w')
+    # assuming only one encodings file
+    #                 Encoding utf8      utf8    "Unicode (utf8)" UTF-8    variable inputenc
+    reg = re.compile('Encoding [\w-]+\s+[\w-]+\s+"([\w \-\(\)]+)"\s+[\w-]+\s+(fixed|variable)\s+\w+.*')
+    input = open(input_files[0])
+    for lineno, line in enumerate(input.readlines()):
+        if not line.startswith('Encoding'):
+            continue
+        if reg.match(line):
+            print >> output, '#: %s:%d\nmsgid "%s"\nmsgstr ""\n' % \
+                (relativePath(input_files[0], base), lineno+1, reg.match(line).groups()[0])
+        else:
+            print "Error: Unable to handle line:"
+            print line
+            # No need to abort if the parsing fails
+            # sys.exit(1)
+    input.close()
+    output.close()
+
+
+
 Usage = '''
 lyx_pot.py [-b|--base top_src_dir] [-o|--output output_file] [-h|--help] -t|--type input_type input_files
 
@@ -295,6 +318,7 @@ where
         layouts: lib/layouts/*
         qt4: qt4 ui files
         languages: file lib/languages
+        encodings: file lib/encodings
         external: external templates file
         formats: formats predefined in lib/configure.py
 '''
@@ -316,7 +340,7 @@ if __name__ == '__main__':
             base = value
         elif opt in ['-t', '--type']:
             input_type = value
-    if input_type not in ['ui', 'layouts', 'modules', 'qt4', 'languages', 'external', 'formats'] or output is None:
+    if input_type not in ['ui', 'layouts', 'modules', 'qt4', 'languages', 'encodings', 'external', 'formats'] or output is None:
         print 'Wrong input type or output filename.'
         sys.exit(1)
     if input_type == 'ui':
@@ -329,6 +353,8 @@ if __name__ == '__main__':
         external_l10n(args, output, base)
     elif input_type == 'formats':
         formats_l10n(args, output, base)
+    elif input_type == 'encodings':
+        encodings_l10n(args, output, base)
     else:
         languages_l10n(args, output, base)
 

src/Encoding.cpp

@@ -269,9 +269,9 @@ const char * EncodingException::what() const throw()
 }
 
 
-Encoding::Encoding(string const & n, string const & l, string const & i,
+Encoding::Encoding(string const & n, string const & l, string const & g,
-		   bool f, Encoding::Package p)
+		   string const & i, bool f, Encoding::Package p)
-	: name_(n), latexName_(l), iconvName_(i), fixedwidth_(f), package_(p)
+	: name_(n), latexName_(l), guiName_(g), iconvName_(i), fixedwidth_(f), package_(p)
 {
 	if (n == "ascii") {
 		// ASCII can encode 128 code points and nothing else
@@ -731,6 +731,8 @@ void Encodings::read(FileName const & encfile, FileName const & symbolsfile)
 			lex.next();
 			string const latexname = lex.getString();
 			lex.next();
+			string const guiname = lex.getString();
+			lex.next();
 			string const iconvname = lex.getString();
 			lex.next();
 			string const width = lex.getString();
@@ -756,7 +758,7 @@ void Encodings::read(FileName const & encfile, FileName const & symbolsfile)
 
 			LYXERR(Debug::INFO, "Reading encoding " << name);
 			encodinglist[name] = Encoding(name, latexname,
-				iconvname, fixedwidth, package);
+				guiname, iconvname, fixedwidth, package);
 
 			if (lex.lex() != et_end)
 				lex.printError("Missing end");

src/Encoding.h

@@ -51,7 +51,8 @@ public:
 	Encoding() {}
 	///
 	Encoding(std::string const & n, std::string const & l,
-		 std::string const & i, bool f, Package p);
+		 std::string const & g, std::string const & i,
+		 bool f, Package p);
 	///
 	void init() const;
 	///
@@ -59,6 +60,8 @@ public:
 	///
 	std::string const & latexName() const { return latexName_; }
 	///
+	std::string const & guiName() const { return guiName_; }
+	///
 	std::string const & iconvName() const { return iconvName_; }
 	/**
 	 * Convert \p c to something that LaTeX can understand.
@@ -79,6 +82,8 @@ private:
 	///
 	std::string latexName_;
 	///
+	std::string guiName_;
+	///
 	std::string iconvName_;
 	/// Is this a fixed width encoding?
 	bool fixedwidth_;

src/frontends/qt4/GuiDocument.cpp

@@ -796,12 +796,14 @@ GuiDocument::GuiDocument(GuiView & lv)
 	langModule->languageCO->setModel(language_model);
 
 	// Always put the default encoding in the first position.
-	// It is special because the displayed text is translated.
 	langModule->encodingCO->addItem(qt_("LaTeX default"));
+	QStringList encodinglist;
 	Encodings::const_iterator it = encodings.begin();
 	Encodings::const_iterator const end = encodings.end();
 	for (; it != end; ++it)
-		langModule->encodingCO->addItem(toqstr(it->latexName()));
+		encodinglist.append(qt_(it->guiName()));
+	encodinglist.sort();
+	langModule->encodingCO->addItems(encodinglist);
 
 	langModule->quoteStyleCO->addItem(qt_("``text''"));
 	langModule->quoteStyleCO->addItem(qt_("''text''"));
@@ -1481,9 +1483,25 @@ void GuiDocument::apply(BufferParams & params)
 		int i = langModule->encodingCO->currentIndex();
 		if (i == 0)
 			params.inputenc = "default";
-		else
+		else {
-			params.inputenc =
+			QString const enc_gui =
-				fromqstr(langModule->encodingCO->currentText());
+				langModule->encodingCO->currentText();
+			Encodings::const_iterator it = encodings.begin();
+			Encodings::const_iterator const end = encodings.end();
+			bool found = false;
+			for (; it != end; ++it) {
+				if (qt_(it->guiName()) == enc_gui) {
+					params.inputenc = it->latexName();
+					found = true;
+					break;
+				}
+			}
+			if (!found) {
+				// should not happen
+				lyxerr << "GuiDocument::apply: Unknown encoding! Resetting to default" << endl;
+				params.inputenc = "default";
+			}
+		}
 	}
 
 	InsetQuotes::QuoteLanguage lga = InsetQuotes::EnglishQuotes;
@@ -1796,8 +1814,17 @@ void GuiDocument::paramsToDialog(BufferParams const & params)
 		if (params.inputenc == "default") {
 			langModule->encodingCO->setCurrentIndex(0);
 		} else {
+			string enc_gui;
+			Encodings::const_iterator it = encodings.begin();
+			Encodings::const_iterator const end = encodings.end();
+			for (; it != end; ++it) {
+				if (it->latexName() == params.inputenc) {
+					enc_gui = it->guiName();
+					break;
+				}
+			}
 			int const i = langModule->encodingCO->findText(
-					toqstr(params.inputenc));
+					qt_(enc_gui));
 			if (i >= 0)
 				langModule->encodingCO->setCurrentIndex(i);
 			else