On Thu, Oct 11, 2007 at 11:31:30PM +0200, Enrico Forestieri wrote:
> On Thu, Oct 11, 2007 at 09:55:01AM +0200, Abdelrazak Younes wrote:
>
> > >> I'd prefer:
> > >> if (Encodings::isGreekChar(next))
> > >> + break;
>
> Thanks for the suggestion. I also updated the patch in order to have
> a sane behaviour with change tracking.
While trying to extend the patch to cyrillic, I realized that the
code could be reused, so here is a patch also covering cyrillic
chars. This skeleton could also be used for other languages.
Note that one can still mark the text with the proper language
and then it works exactly as before. I also attach here the .lyx file
I used for testing.
> If there are no objections I will commit it.
As it seems there are none, I am going to commit the patch.
--
Enrico
Index: src/Paragraph.cpp
===================================================================
--- src/Paragraph.cpp (revision 20930)
+++ src/Paragraph.cpp (working copy)
@@ -66,8 +66,10 @@ using std::ostream;
namespace lyx {
using support::contains;
+using support::prefixIs;
using support::suffixIs;
using support::rsplit;
+using support::rtrim;
/////////////////////////////////////////////////////////////////////
@@ -187,6 +189,11 @@ public:
unsigned int & column,
Font const & font,
Layout const & style);
+ /// Output consecutive known unicode chars, belonging to the same
+ /// language as specified by \p preamble, to \p os starting from \p c.
+ /// \return the number of characters written.
+ int knownLangChars(odocstream & os, value_type c, string & preamble,
+ Change &, Encoding const &, pos_type &);
///
void simpleTeXSpecialChars(Buffer const &, BufferParams const &,
odocstream &,
@@ -627,6 +634,61 @@ bool Paragraph::Pimpl::simpleTeXBlanks(E
}
+int Paragraph::Pimpl::knownLangChars(odocstream & os,
+ value_type c,
+ string & preamble,
+ Change & runningChange,
+ Encoding const & encoding,
+ pos_type & i)
+{
+ // The latex command is "\textLANG{<spec>}" and we have to retain
+ // "\textLANG{<spec>" for the first char but only "<spec>" for all
+ // subsequent chars (this also works when we are passed untranslated
+ // unicode).
+ docstring const latex1 = rtrim(encoding.latexChar(c), "}");
+ int length = latex1.length();
+ os << latex1;
+ while (i < size() - 1) {
+ char_type next = getChar(i + 1);
+ if (!Encodings::isKnownLangChar(next, preamble) ||
+ runningChange != lookupChange(i + 1))
+ break;
+ Font prev_font;
+ bool found = false;
+ FontList::const_iterator cit = fontlist.begin();
+ FontList::const_iterator end = fontlist.end();
+ for (; cit != end; ++cit) {
+ if (cit->pos() >= i && !found) {
+ prev_font = cit->font();
+ found = true;
+ }
+ if (cit->pos() >= i + 1)
+ break;
+ }
+ if (found && cit != end && prev_font != cit->font())
+ break;
+ docstring const latex = rtrim(encoding.latexChar(next), "}");
+ docstring::size_type const j =
+ latex.find_first_of(from_ascii("{"));
+ if (j == docstring::npos) {
+ os << latex;
+ length += latex.length();
+ } else {
+ os << latex.substr(j + 1);
+ length += latex.substr(j + 1).length();
+ }
+ ++i;
+ }
+ // When the proper language is set, we are passed the straight unicode,
+ // so we should not try to close the \textLANG command.
+ if (prefixIs(latex1, from_ascii("\\" + preamble))) {
+ os << '}';
+ ++length;
+ }
+ return length;
+}
+
+
bool Paragraph::Pimpl::isTextAt(string const & str, pos_type pos) const
{
pos_type const len = str.length();
@@ -952,6 +1014,14 @@ void Paragraph::Pimpl::simpleTeXSpecialC
break;
}
}
+ string preamble;
+ if (Encodings::isKnownLangChar(c, preamble)) {
+ column +=
+ knownLangChars(os, c, preamble,
+ running_change,
+ encoding, i) - 1;
+ break;
+ }
docstring const latex = encoding.latexChar(c);
if (latex.length() > 1 &&
latex[latex.length() - 1] != '}') {
Index: src/LaTeXFeatures.cpp
===================================================================
--- src/LaTeXFeatures.cpp (revision 20930)
+++ src/LaTeXFeatures.cpp (working copy)
@@ -186,6 +186,20 @@ static string const changetracking_none_
"\\newcommand{\\lyxadded}[3]{#3}\n"
"\\newcommand{\\lyxdeleted}[3]{}\n";
+static string const textgreek_def =
+ "\\DeclareRobustCommand{\\greektext}{%\n"
+ " \\fontencoding{LGR}\\selectfont\n"
+ " \\def\\encodingdefault{LGR}}\n"
+ "\\DeclareRobustCommand{\\textgreek}[1]{\\leavevmode{\\greektext #1}}\n"
+ "\\DeclareFontEncoding{LGR}{}{}\n";
+
+static string const textcyr_def =
+ "\\DeclareRobustCommand{\\cyrtext}{%\n"
+ " \\fontencoding{T2A}\\selectfont\n"
+ " \\def\\encodingdefault{T2A}}\n"
+ "\\DeclareRobustCommand{\\textcyr}[1]{\\leavevmode{\\cyrtext #1}}\n"
+ "\\DeclareFontEncoding{T2A}{}{}\n";
+
/////////////////////////////////////////////////////////////////////
//
@@ -618,6 +632,12 @@ string const LaTeXFeatures::getMacros()
if (mustProvide("lyxarrow"))
macros << lyxarrow_def << '\n';
+ if (mustProvide("textgreek"))
+ macros << textgreek_def << '\n';
+
+ if (mustProvide("textcyr"))
+ macros << textcyr_def << '\n';
+
// quotes.
if (mustProvide("quotesinglbase"))
macros << quotesinglbase_def << '\n';
Index: src/Encoding.cpp
===================================================================
--- src/Encoding.cpp (revision 20930)
+++ src/Encoding.cpp (working copy)
@@ -401,6 +401,23 @@ bool Encodings::isCombiningChar(char_typ
}
+bool Encodings::isKnownLangChar(char_type c, string & preamble)
+{
+ CharInfoMap::const_iterator const it = unicodesymbols.find(c);
+ if (it != unicodesymbols.end()) {
+ if (it->second.preamble != "textgreek" &&
+ it->second.preamble != "textcyr")
+ return false;
+ if (preamble.empty()) {
+ preamble = it->second.preamble;
+ return true;
+ }
+ return it->second.preamble == preamble;
+ }
+ return false;
+}
+
+
Encoding const * Encodings::getFromLyXName(string const & name) const
{
EncodingList::const_iterator it = encodinglist.find(name);
Index: src/Encoding.h
===================================================================
--- src/Encoding.h (revision 20930)
+++ src/Encoding.h (working copy)
@@ -143,6 +143,15 @@ public:
/// Is this a combining char?
static bool isCombiningChar(char_type c);
/**
+ * Is this a known char from some language?
+ * If \p preamble is empty and code point \p c is known to belong
+ * to a supported language, true is returned and \p preamble is set
+ * to the corresponding entry in the unicodesymbols file.
+ * If \p preamble is not empty, a check is made whether code point
+ * \p c is a known character matching the preamble entry.
+ */
+ static bool isKnownLangChar(char_type c, std::string & preamble);
+ /**
* Add the preamble snippet needed for the output of \p c to
* \p features.
* This does not depend on the used encoding, since the inputenc
Index: lib/unicodesymbols
===================================================================
--- lib/unicodesymbols (revision 20930)
+++ lib/unicodesymbols (working copy)
@@ -684,7 +684,120 @@
#0x036d "" "" "combining" # COMBINING LATIN SMALL
LETTER T
#0x036e "" "" "combining" # COMBINING LATIN SMALL
LETTER V
#0x036f "" "" "combining" # COMBINING LATIN SMALL
LETTER X
+0x0391 "\\textgreek{A}" "textgreek" "" # GREEK CAPITAL LETTER ALPHA
+0x0392 "\\textgreek{B}" "textgreek" "" # GREEK CAPITAL LETTER BETA
+0x0393 "\\textgreek{G}" "textgreek" "" # GREEK CAPITAL LETTER GAMMA
+0x0394 "\\textgreek{D}" "textgreek" "" # GREEK CAPITAL LETTER DELTA
+0x0395 "\\textgreek{E}" "textgreek" "" # GREEK CAPITAL LETTER EPSILON
+0x0396 "\\textgreek{Z}" "textgreek" "" # GREEK CAPITAL LETTER ZETA
+0x0397 "\\textgreek{H}" "textgreek" "" # GREEK CAPITAL LETTER ETA
+0x0398 "\\textgreek{J}" "textgreek" "" # GREEK CAPITAL LETTER THETA
+0x0399 "\\textgreek{I}" "textgreek" "" # GREEK CAPITAL LETTER IOTA
+0x039a "\\textgreek{K}" "textgreek" "" # GREEK CAPITAL LETTER KAPPA
+0x039b "\\textgreek{L}" "textgreek" "" # GREEK CAPITAL LETTER LAMDA
+0x039c "\\textgreek{M}" "textgreek" "" # GREEK CAPITAL LETTER MU
+0x039d "\\textgreek{N}" "textgreek" "" # GREEK CAPITAL LETTER NU
+0x039e "\\textgreek{X}" "textgreek" "" # GREEK CAPITAL LETTER XI
+0x039f "\\textgreek{O}" "textgreek" "" # GREEK CAPITAL LETTER OMICRON
+0x03a0 "\\textgreek{P}" "textgreek" "" # GREEK CAPITAL LETTER PI
+0x03a1 "\\textgreek{R}" "textgreek" "" # GREEK CAPITAL LETTER RHO
+0x03a3 "\\textgreek{S}" "textgreek" "" # GREEK CAPITAL LETTER SIGMA
+0x03a4 "\\textgreek{T}" "textgreek" "" # GREEK CAPITAL LETTER TAU
+0x03a5 "\\textgreek{U}" "textgreek" "" # GREEK CAPITAL LETTER UPSILON
+0x03a6 "\\textgreek{F}" "textgreek" "" # GREEK CAPITAL LETTER PHI
+0x03a7 "\\textgreek{Q}" "textgreek" "" # GREEK CAPITAL LETTER CHI
+0x03a8 "\\textgreek{Y}" "textgreek" "" # GREEK CAPITAL LETTER PSI
+0x03a9 "\\textgreek{W}" "textgreek" "" # GREEK CAPITAL LETTER OMEGA
+0x03b1 "\\textgreek{a}" "textgreek" "" # GREEK SMALL LETTER ALPHA
+0x03b2 "\\textgreek{b}" "textgreek" "" # GREEK SMALL LETTER BETA
+0x03b3 "\\textgreek{g}" "textgreek" "" # GREEK SMALL LETTER GAMMA
+0x03b4 "\\textgreek{d}" "textgreek" "" # GREEK SMALL LETTER DELTA
+0x03b5 "\\textgreek{e}" "textgreek" "" # GREEK SMALL LETTER EPSILON
+0x03b6 "\\textgreek{z}" "textgreek" "" # GREEK SMALL LETTER ZETA
+0x03b7 "\\textgreek{h}" "textgreek" "" # GREEK SMALL LETTER ETA
+0x03b8 "\\textgreek{j}" "textgreek" "" # GREEK SMALL LETTER THETA
+0x03b9 "\\textgreek{i}" "textgreek" "" # GREEK SMALL LETTER IOTA
+0x03ba "\\textgreek{k}" "textgreek" "" # GREEK SMALL LETTER KAPPA
+0x03bb "\\textgreek{l}" "textgreek" "" # GREEK SMALL LETTER LAMDA
+0x03bc "\\textgreek{m}" "textgreek" "" # GREEK SMALL LETTER MU
+0x03bd "\\textgreek{n}" "textgreek" "" # GREEK SMALL LETTER NU
+0x03be "\\textgreek{x}" "textgreek" "" # GREEK SMALL LETTER XI
+0x03bf "\\textgreek{o}" "textgreek" "" # GREEK SMALL LETTER OMICRON
+0x03c0 "\\textgreek{p}" "textgreek" "" # GREEK SMALL LETTER PI
+0x03c1 "\\textgreek{r}" "textgreek" "" # GREEK SMALL LETTER RHO
+0x03c2 "\\textgreek{c}" "textgreek" "" # GREEK SMALL LETTER FINAL
SIGMA
+0x03c3 "\\textgreek{s}" "textgreek" "" # GREEK SMALL LETTER SIGMA
+0x03c4 "\\textgreek{t}" "textgreek" "" # GREEK SMALL LETTER TAU
+0x03c5 "\\textgreek{u}" "textgreek" "" # GREEK SMALL LETTER UPSILON
+0x03c6 "\\textgreek{f}" "textgreek" "" # GREEK SMALL LETTER PHI
+0x03c7 "\\textgreek{q}" "textgreek" "" # GREEK SMALL LETTER CHI
+0x03c8 "\\textgreek{y}" "textgreek" "" # GREEK SMALL LETTER PSI
+0x03c9 "\\textgreek{w}" "textgreek" "" # GREEK SMALL LETTER OMEGA
0x0e3f "\\textbaht" "textcomp" "" # THAI CURRENCY SYMBOL BAHT
+0x0410 "\\textcyr{\\char192}" "textcyr" "" # CYRILLIC CAPITAL LETTER A
+0x0411 "\\textcyr{\\char193}" "textcyr" "" # CYRILLIC CAPITAL LETTER BE
+0x0412 "\\textcyr{\\char194}" "textcyr" "" # CYRILLIC CAPITAL LETTER VE
+0x0413 "\\textcyr{\\char195}" "textcyr" "" # CYRILLIC CAPITAL LETTER GHE
+0x0414 "\\textcyr{\\char196}" "textcyr" "" # CYRILLIC CAPITAL LETTER DE
+0x0415 "\\textcyr{\\char197}" "textcyr" "" # CYRILLIC CAPITAL LETTER IE
+0x0416 "\\textcyr{\\char198}" "textcyr" "" # CYRILLIC CAPITAL LETTER ZHE
+0x0417 "\\textcyr{\\char199}" "textcyr" "" # CYRILLIC CAPITAL LETTER ZE
+0x0418 "\\textcyr{\\char200}" "textcyr" "" # CYRILLIC CAPITAL LETTER I
+0x0419 "\\textcyr{\\char201}" "textcyr" "" # CYRILLIC CAPITAL LETTER SHORT
I
+0x041a "\\textcyr{\\char202}" "textcyr" "" # CYRILLIC CAPITAL LETTER KA
+0x041b "\\textcyr{\\char203}" "textcyr" "" # CYRILLIC CAPITAL LETTER EL
+0x041c "\\textcyr{\\char204}" "textcyr" "" # CYRILLIC CAPITAL LETTER EM
+0x041d "\\textcyr{\\char205}" "textcyr" "" # CYRILLIC CAPITAL LETTER EN
+0x041e "\\textcyr{\\char206}" "textcyr" "" # CYRILLIC CAPITAL LETTER O
+0x041f "\\textcyr{\\char207}" "textcyr" "" # CYRILLIC CAPITAL LETTER PE
+0x0420 "\\textcyr{\\char208}" "textcyr" "" # CYRILLIC CAPITAL LETTER ER
+0x0421 "\\textcyr{\\char209}" "textcyr" "" # CYRILLIC CAPITAL LETTER ES
+0x0422 "\\textcyr{\\char210}" "textcyr" "" # CYRILLIC CAPITAL LETTER TE
+0x0423 "\\textcyr{\\char211}" "textcyr" "" # CYRILLIC CAPITAL LETTER U
+0x0424 "\\textcyr{\\char212}" "textcyr" "" # CYRILLIC CAPITAL LETTER EF
+0x0425 "\\textcyr{\\char213}" "textcyr" "" # CYRILLIC CAPITAL LETTER HA
+0x0426 "\\textcyr{\\char214}" "textcyr" "" # CYRILLIC CAPITAL LETTER TSE
+0x0427 "\\textcyr{\\char215}" "textcyr" "" # CYRILLIC CAPITAL LETTER CHE
+0x0428 "\\textcyr{\\char216}" "textcyr" "" # CYRILLIC CAPITAL LETTER SHA
+0x0429 "\\textcyr{\\char217}" "textcyr" "" # CYRILLIC CAPITAL LETTER SHCHA
+0x042a "\\textcyr{\\char218}" "textcyr" "" # CYRILLIC CAPITAL LETTER HARD
SIGN
+0x042b "\\textcyr{\\char219}" "textcyr" "" # CYRILLIC CAPITAL LETTER YERU
+0x042c "\\textcyr{\\char220}" "textcyr" "" # CYRILLIC CAPITAL LETTER SOFT
SIGN
+0x042d "\\textcyr{\\char221}" "textcyr" "" # CYRILLIC CAPITAL LETTER E
+0x042e "\\textcyr{\\char222}" "textcyr" "" # CYRILLIC CAPITAL LETTER YU
+0x042f "\\textcyr{\\char223}" "textcyr" "" # CYRILLIC CAPITAL LETTER YA
+0x0430 "\\textcyr{\\char224}" "textcyr" "" # CYRILLIC SMALL LETTER A
+0x0431 "\\textcyr{\\char225}" "textcyr" "" # CYRILLIC SMALL LETTER BE
+0x0432 "\\textcyr{\\char226}" "textcyr" "" # CYRILLIC SMALL LETTER VE
+0x0433 "\\textcyr{\\char227}" "textcyr" "" # CYRILLIC SMALL LETTER GHE
+0x0434 "\\textcyr{\\char228}" "textcyr" "" # CYRILLIC SMALL LETTER DE
+0x0435 "\\textcyr{\\char229}" "textcyr" "" # CYRILLIC SMALL LETTER IE
+0x0436 "\\textcyr{\\char230}" "textcyr" "" # CYRILLIC SMALL LETTER ZHE
+0x0437 "\\textcyr{\\char231}" "textcyr" "" # CYRILLIC SMALL LETTER ZE
+0x0438 "\\textcyr{\\char232}" "textcyr" "" # CYRILLIC SMALL LETTER I
+0x0439 "\\textcyr{\\char233}" "textcyr" "" # CYRILLIC SMALL LETTER SHORT I
+0x043a "\\textcyr{\\char234}" "textcyr" "" # CYRILLIC SMALL LETTER KA
+0x043b "\\textcyr{\\char235}" "textcyr" "" # CYRILLIC SMALL LETTER EL
+0x043c "\\textcyr{\\char236}" "textcyr" "" # CYRILLIC SMALL LETTER EM
+0x043d "\\textcyr{\\char237}" "textcyr" "" # CYRILLIC SMALL LETTER EN
+0x043e "\\textcyr{\\char238}" "textcyr" "" # CYRILLIC SMALL LETTER O
+0x043f "\\textcyr{\\char239}" "textcyr" "" # CYRILLIC SMALL LETTER PE
+0x0440 "\\textcyr{\\char240}" "textcyr" "" # CYRILLIC SMALL LETTER ER
+0x0441 "\\textcyr{\\char241}" "textcyr" "" # CYRILLIC SMALL LETTER ES
+0x0442 "\\textcyr{\\char242}" "textcyr" "" # CYRILLIC SMALL LETTER TE
+0x0443 "\\textcyr{\\char243}" "textcyr" "" # CYRILLIC SMALL LETTER U
+0x0444 "\\textcyr{\\char244}" "textcyr" "" # CYRILLIC SMALL LETTER EF
+0x0445 "\\textcyr{\\char245}" "textcyr" "" # CYRILLIC SMALL LETTER HA
+0x0446 "\\textcyr{\\char246}" "textcyr" "" # CYRILLIC SMALL LETTER TSE
+0x0447 "\\textcyr{\\char247}" "textcyr" "" # CYRILLIC SMALL LETTER CHE
+0x0448 "\\textcyr{\\char248}" "textcyr" "" # CYRILLIC SMALL LETTER SHA
+0x0449 "\\textcyr{\\char249}" "textcyr" "" # CYRILLIC SMALL LETTER SHCHA
+0x044a "\\textcyr{\\char250}" "textcyr" "" # CYRILLIC SMALL LETTER HARD
SIGN
+0x044b "\\textcyr{\\char251}" "textcyr" "" # CYRILLIC SMALL LETTER YERU
+0x044c "\\textcyr{\\char252}" "textcyr" "" # CYRILLIC SMALL LETTER SOFT
SIGN
+0x044d "\\textcyr{\\char253}" "textcyr" "" # CYRILLIC SMALL LETTER E
+0x044e "\\textcyr{\\char254}" "textcyr" "" # CYRILLIC SMALL LETTER YU
+0x044f "\\textcyr{\\char255}" "textcyr" "" # CYRILLIC SMALL LETTER YA
0x1e00 "\\textsubring{A}" "tipa" "" # LATIN CAPITAL LETTER A WITH RING
BELOW
0x1e01 "\\textsubring{a}" "tipa" "" # LATIN SMALL LETTER A WITH RING
BELOW
0x1e02 "\\.{B}" "" "" # LATIN CAPITAL LETTER B WITH DOT ABOVE
#LyX 1.6.0svn created this file. For more info see http://www.lyx.org/
\lyxformat 293
\begin_document
\begin_header
\textclass article
\language english
\inputencoding auto
\font_roman default
\font_sans default
\font_typewriter default
\font_default_family default
\font_sc false
\font_osf false
\font_sf_scale 100
\font_tt_scale 100
\graphics default
\paperfontsize default
\spacing single
\use_hyperref false
\papersize default
\use_geometry false
\use_amsmath 1
\use_esint 1
\cite_engine basic
\use_bibtopic false
\paperorientation portrait
\secnumdepth 3
\tocdepth 3
\paragraph_separation indent
\defskip medskip
\quotes_language english
\papercolumns 1
\papersides 1
\paperpagestyle default
\tracking_changes false
\output_changes false
\author ""
\author ""
\end_header
\begin_manifest
\end_manifest
\begin_body
\begin_layout Standard
\lang greek
ÎÎÎÎÎÎÎÎÎÎÎÎÎÎÎΠΡΣΤΥΦΧΨΩ
\end_layout
\begin_layout Standard
ÎÎÎÎÎÎÎÎÎÎÎÎÎÎÎΠΡΣΤΥΦΧΨΩ
\end_layout
\begin_layout Standard
\lang greek
αβγδεζηθικλμνξοÏÏÏÏÏÏ
ÏÏÏÏ
\end_layout
\begin_layout Standard
αβγδεζηθικλμνξοÏÏÏÏÏÏ
ÏÏÏÏ
\end_layout
\begin_layout Standard
\lang russian
ÐÐÐÐÐÐÐÐÐÐÐÐÐÐÐÐРСТУФХЦЧШЩЪЫЬÐЮЯ
\end_layout
\begin_layout Standard
ÐÐÐÐÐÐÐÐÐÐÐÐÐÐÐÐРСТУФХЦЧШЩЪЫЬÐЮЯ
\end_layout
\begin_layout Standard
\lang russian
абвгдежзийклмнопÑÑÑÑÑÑ
ÑÑÑÑÑÑÑÑÑÑ
\end_layout
\begin_layout Standard
абвгдежзийклмнопÑÑÑÑÑÑ
ÑÑÑÑÑÑÑÑÑÑ
\end_layout
\end_body
\end_document
