-/* This file is part of
- * ======================================================
- *
- * LyX, The Document Processor
- *
- * Copyright 1995 Matthias Ettrich
- * Copyright 1995-2001 The LyX Team.
+/**
+ * \file encoding.C
+ * This file is part of LyX, the document processor.
+ * Licence details can be found in the file COPYING.
*
- * ====================================================== */
+ * \author Lars Gullik Bjønnes
+ * \author Jean-Marc Lasgouttes
+ * \author Dekel Tsur
+ *
+ * Full author contact details are available in file CREDITS.
+ */
#include <config.h>
-#ifdef __GNUG__
-#pragma implementation
-#endif
-
#include "encoding.h"
-#include "debug.h"
-using std::endl;
+#include "debug.h"
+#include "LaTeXFeatures.h"
+#include "lyxlex.h"
+#include "lyxrc.h"
-Encodings encodings;
+#include "support/filename.h"
+#include "support/lstrings.h"
+#include "support/unicode.h"
-namespace {
+#include <sstream>
-Uchar tab_iso8859_1[256] = {
- 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
- 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
- 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f,
- 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f,
- 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x4a, 0x4b, 0x4c, 0x4d, 0x4e, 0x4f,
- 0x50, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5a, 0x5b, 0x5c, 0x5d, 0x5e, 0x5f,
- 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d, 0x6e, 0x6f,
- 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f,
- 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f,
- 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, 0x9a, 0x9b, 0x9c, 0x9d, 0x9e, 0x9f,
- 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, 0xa8, 0xa9, 0xaa, 0xab, 0xac, 0xad, 0xae, 0xaf,
- 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, 0xb8, 0xb9, 0xba, 0xbb, 0xbc, 0xbd, 0xbe, 0xbf,
- 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7, 0xc8, 0xc9, 0xca, 0xcb, 0xcc, 0xcd, 0xce, 0xcf,
- 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf,
- 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef,
- 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff
-};
-#ifdef USE_UNICODE_FOR_SYMBOLS
-Uchar tab_symbol[256] = {
- 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07, 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f,
- 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f,
+namespace lyx {
- 0x0020, 0x0021, 0x2200, 0x0023, 0x2203, 0x0025, 0x0026, 0x220b,
- 0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f,
+using support::FileName;
- 0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f,
+#ifndef CXX_GLOBAL_CSTD
+using std::strtol;
+#endif
-// 0x2245, 0x0391, 0x0392, 0x03a7, 0x0394, 0x0395, 0x03a6, 0x0393,
-// 0x0397, 0x0399, 0x03d1, 0x039a, 0x039b, 0x039c, 0x039d, 0x039f,
+using std::endl;
+using std::string;
-// 0x03a0, 0x0398, 0x03a1, 0x03a3, 0x03a4, 0x03a5, 0x03c2, 0x03a9,
-// 0x039e, 0x03a8, 0x0396, 0x005b, 0x2234, 0x005d, 0x22a5, 0xffff,
- 0x2245, 0x0041, 0x0042, 0x0058, 0x0394, 0x0045, 0x03c2, 0x03a9,
- 0x0048, 0x0049, 0x03d1, 0x004b, 0x039b, 0x004d, 0x004e, 0x004f,
- 0x03a0, 0x0398, 0x0050, 0x03a3, 0x0054, 0x0059, 0x03c2, 0x03a9,
- 0x039e, 0x03a8, 0x005a, 0x005b, 0x2234, 0x005d, 0x22a5, 0xffff,
+Encodings encodings;
- 0xffff, 0x03b1, 0x03b2, 0x03c7, 0x03b4, 0x03b5, 0x03d5, 0x03b3,
- 0x03b7, 0x03b9, 0x03c6, 0x03ba, 0x03bb, 0x03bc, 0x03bd, 0x03bf,
+namespace {
- 0x03c0, 0x03b8, 0x03c1, 0x03c3, 0x03c4, 0x03c5, 0x03d6, 0x03c9,
- 0x03be, 0x03c8, 0x03b6, 0x007b, 0x007c, 0x007d, 0x007e, 0xffff,
+char_type arabic_table[50][4] = {
+ {0xfe80, 0xfe80, 0xfe80, 0xfe80}, // 0x0621 = hamza
+ {0xfe81, 0xfe82, 0xfe81, 0xfe82}, // 0x0622 = ligature madda on alef
+ {0xfe83, 0xfe84, 0xfe83, 0xfe84}, // 0x0623 = ligature hamza on alef
+ {0xfe85, 0xfe86, 0xfe85, 0xfe86}, // 0x0624 = ligature hamza on waw
+ {0xfe87, 0xfe88, 0xfe87, 0xfe88}, // 0x0625 = ligature hamza under alef
+ {0xfe89, 0xfe8a, 0xfe8b, 0xfe8c}, // 0x0626 = ligature hamza on ya
+ {0xfe8d, 0xfe8e, 0xfe8d, 0xfe8e}, // 0x0627 = alef
+ {0xfe8f, 0xfe90, 0xfe91, 0xfe92}, // 0x0628 = baa
+ {0xfe93, 0xfe94, 0xfe93, 0xfe94}, // 0x0629 = taa marbuta
+ {0xfe95, 0xfe96, 0xfe97, 0xfe98}, // 0x062a = taa
+ {0xfe99, 0xfe9a, 0xfe9b, 0xfe9c}, // 0x062b = thaa
+ {0xfe9d, 0xfe9e, 0xfe9f, 0xfea0}, // 0x062c = jeem
+ {0xfea1, 0xfea2, 0xfea3, 0xfea4}, // 0x062d = haa
+ {0xfea5, 0xfea6, 0xfea7, 0xfea8}, // 0x062e = khaa
+ {0xfea9, 0xfeaa, 0xfea9, 0xfeaa}, // 0x062f = dal
+
+ {0xfeab, 0xfeac, 0xfeab, 0xfeac}, // 0x0630 = thal
+ {0xfead, 0xfeae, 0xfead, 0xfeae}, // 0x0631 = ra
+ {0xfeaf, 0xfeb0, 0xfeaf, 0xfeb0}, // 0x0632 = zain
+ {0xfeb1, 0xfeb2, 0xfeb3, 0xfeb4}, // 0x0633 = seen
+ {0xfeb5, 0xfeb6, 0xfeb7, 0xfeb8}, // 0x0634 = sheen
+ {0xfeb9, 0xfeba, 0xfebb, 0xfebc}, // 0x0635 = sad
+ {0xfebd, 0xfebe, 0xfebf, 0xfec0}, // 0x0636 = dad
+ {0xfec1, 0xfec2, 0xfec3, 0xfec4}, // 0x0637 = tah
+ {0xfec5, 0xfec6, 0xfec7, 0xfec8}, // 0x0638 = zah
+ {0xfec9, 0xfeca, 0xfecb, 0xfecc}, // 0x0639 = ain
+ {0xfecd, 0xfece, 0xfecf, 0xfed0}, // 0x063a = ghain
+ {0, 0, 0, 0}, // 0x063b
+ {0, 0, 0, 0}, // 0x063c
+ {0, 0, 0, 0}, // 0x063d
+ {0, 0, 0, 0}, // 0x063e
+ {0, 0, 0, 0}, // 0x063f
+
+ {0, 0, 0, 0}, // 0x0640
+ {0xfed1, 0xfed2, 0xfed3, 0xfed4}, // 0x0641 = fa
+ {0xfed5, 0xfed6, 0xfed7, 0xfed8}, // 0x0642 = qaf
+ {0xfed9, 0xfeda, 0xfedb, 0xfedc}, // 0x0643 = kaf
+ {0xfedd, 0xfede, 0xfedf, 0xfee0}, // 0x0644 = lam
+ {0xfee1, 0xfee2, 0xfee3, 0xfee4}, // 0x0645 = meem
+ {0xfee5, 0xfee6, 0xfee7, 0xfee8}, // 0x0646 = noon
+ {0xfee9, 0xfeea, 0xfeeb, 0xfeec}, // 0x0647 = ha
+ {0xfeed, 0xfeee, 0xfeed, 0xfeee}, // 0x0648 = waw
+ {0xfeef, 0xfef0, 0xfeef, 0xfef0}, // 0x0649 = alef maksura
+ {0xfef1, 0xfef2, 0xfef3, 0xfef4}, // 0x064a = ya
+ {0x065b, 0x065b, 0x065b, 0x065b}, // 0x064b = fathatan
+ {0x065c, 0x065c, 0x065c, 0x065c}, // 0x064c = dammatan
+ {0x064d, 0x064d, 0x064d, 0x064d}, // 0x064d = kasratan
+ {0x064e, 0x064e, 0x064e, 0x064e}, // 0x064e = fatha
+ {0x064f, 0x064f, 0x064f, 0x064f}, // 0x064f = damma
+
+ {0x0650, 0x0650, 0x0650, 0x0650}, // 0x0650 = kasra
+ {0x0651, 0x0651, 0x0651, 0x0651}, // 0x0651 = shadda
+ {0x0652, 0x0652, 0x0652, 0x0652}, // 0x0652 = sukun
+};
- 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff,
- 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff,
- 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff,
- 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff,
-
- 0xffff, 0x03d2, 0x2032, 0x2264, 0x2215, 0x221e, 0xffff, 0x2663,
- 0x2666, 0x2665, 0x2660, 0x2194, 0x2190, 0x2191, 0x2192, 0x2193,
+char_type const arabic_start = 0x0621;
+char_type const arabic_end = 0x0652;
+
+
+/// Information about a single UCS4 character
+struct CharInfo {
+ /// LaTeX command for this character
+ docstring command;
+ /// Needed LaTeX preamble (or feature)
+ string preamble;
+ /// Is this a combining character?
+ bool combining;
+ /// Is \c preamble a feature known by LaTeXFeatures, or a raw LaTeX
+ /// command?
+ bool feature;
+ /// Always force the LaTeX command, even if the encoding contains
+ /// this character?
+ bool force;
+};
- 0x00b0, 0x00b1, 0x2033, 0x2265, 0x00d7, 0x221d, 0x2202, 0x2022,
- 0x00f7, 0x2260, 0x2261, 0x2248, 0x22ef, 0xffff, 0xffff, 0x21b5,
- 0x2135, 0x2111, 0x211c, 0x2118, 0x2297, 0x2295, 0x2205, 0x2229,
- 0x222a, 0x2283, 0x2287, 0x2284, 0x2282, 0x2286, 0x2208, 0x2209,
+typedef std::map<char_type, CharInfo> CharInfoMap;
+CharInfoMap unicodesymbols;
- 0x2220, 0x2207, 0x00ae, 0x00a9, 0x2122, 0x220f, 0x221a, 0x22c5,
- 0x00ac, 0x2227, 0x2228, 0x21d4, 0x21d0, 0x21d1, 0x21d2, 0x21d3,
+} // namespace anon
- 0x2662, 0x2329, 0x00ae, 0x00a9, 0x2122, 0x2211, 0xffff, 0xffff,
- 0xffff, 0x2308, 0xffff, 0x230a, 0xffff, 0xffff, 0xffff, 0xffff,
- 0xffff, 0x232a, 0x222b, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff,
- 0xffff, 0x2309, 0xffff, 0x230b, 0xffff, 0xffff, 0xffff, 0xffff
-};
-#endif
+Encoding::Encoding(string const & n, string const & l, string const & i)
+ : Name_(n), LatexName_(l), iconvName_(i)
+{
+ 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();
+ for (unsigned short j = 0; j < 256; ++j) {
+ char const c = j;
+ std::vector<char_type> const ucs4 = eightbit_to_ucs4(&c, 1, i);
+ if (ucs4.size() == 1) {
+ char_type const c = ucs4[0];
+ 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_);
+ }
+ }
+}
-unsigned char arabic_table2[63][4] = {
- {0x41, 0x41, 0x41, 0x41}, // 0xc1 = hamza
- {0x42, 0xa1, 0x42, 0x42}, // 0xc2 = ligature madda on alef
- {0x43, 0xa2, 0x43, 0x43}, // 0xc3 = ligature hamza on alef
- {0x44, 0xa3, 0x44, 0x44}, // 0xc4 = ligature hamza on waw
- {0x45, 0xa4, 0x45, 0x45}, // 0xc5 = ligature hamza under alef
- {0xf9, 0xf9, 0xf8, 0xa0}, // 0xc6 = ligature hamza on ya
- {0x47, 0xa5, 0xa5, 0xa5}, // 0xc7 = alef
- {0x48, 0xae, 0xac, 0xad}, // 0xc8 = baa
- {0x49, 0xb1, 0xaf, 0xb0}, // 0xc9 = taa marbuta
- {0x4a, 0xb4, 0xb2, 0xb3}, // 0xca = taa
- {0x4b, 0xb7, 0xb5, 0xb6}, // 0xcb = thaa
- {0x4c, 0xba, 0xb8, 0xb9}, // 0xcc = jeem
- {0x4d, 0xbd, 0xbb, 0xbc}, // 0xcd = haa
- {0x4e, 0xc0, 0xbe, 0xbf}, // 0xce = khaa
- {0x4f, 0xa6, 0xa6, 0xa6}, // 0xcf = dal
-
- {0x50, 0xa7, 0xa7, 0xa7}, // 0xd0 = thal
- {0x51, 0xa8, 0xa8, 0xa8}, // 0xd1 = ra
- {0x52, 0xa9, 0xa9, 0xa9}, // 0xd2 = zain
- {0x53, 0xc3, 0xc1, 0xc2}, // 0xd3 = seen
- {0x54, 0xc6, 0xc4, 0xc5}, // 0xd4 = sheen
- {0x55, 0xc9, 0xc7, 0xc8}, // 0xd5 = sad
- {0x56, 0xcc, 0xca, 0xcb}, // 0xd6 = dad
- {0x57, 0xcf, 0xcd, 0xce}, // 0xd7 = tah
- {0x58, 0xd2, 0xd0, 0xd1}, // 0xd8 = zah
- {0x59, 0xd5, 0xd3, 0xd4}, // 0xd9 = ain
- {0x5a, 0xd8, 0xd6, 0xd7}, // 0xda = ghain
- {0,0,0,0}, // 0xdb
- {0,0,0,0}, // 0xdc
- {0,0,0,0}, // 0xdd
- {0,0,0,0}, // 0xde
- {0,0,0,0}, // 0xdf
-
- {0,0,0,0}, // 0xe0
- {0x61, 0xdb, 0xd9, 0xda}, // 0xe1 = fa
- {0x62, 0xde, 0xdc, 0xdd}, // 0xe2 = qaf
- {0x63, 0xe1, 0xdf, 0xe0}, // 0xe3 = kaf
- {0x64, 0xe4, 0xe2, 0xe3}, // 0xe4 = lam
- {0x65, 0xe7, 0xe5, 0xe6}, // 0xe5 = meem
- {0x66, 0xea, 0xe8, 0xe9}, // 0xe6 = noon
- {0x67, 0xed, 0xeb, 0xec}, // 0xe7 = ha
- {0x68, 0xaa, 0xaa, 0xaa}, // 0xe8 = waw
- {0x69, 0xab, 0xab, 0xab}, // 0xe9 = alef maksura
- {0x6a, 0xf0, 0xee, 0xef}, // 0xea = ya
- {0x6b, 0x6b, 0x6b, 0x6b}, // 0xeb = fathatan
- {0x6c, 0x6c, 0x6c, 0x6c}, // 0xec = dammatan
- {0x6d, 0x6d, 0x6d, 0x6d}, // 0xed = kasratan
- {0x6e, 0x6e, 0x6e, 0x6e}, // 0xee = fatha
- {0x6f, 0x6f, 0x6f, 0x6f}, // 0xef = damma
-
- {0x70, 0x70, 0x70, 0x70}, // 0xf0 = kasra
- {0x71, 0x71, 0x71, 0x71}, // 0xf1 = shadda
- {0x72, 0x72, 0x72, 0x72}, // 0xf2 = sukun
- {0,0,0,0}, // 0xf3
- {0,0,0,0}, // 0xf4
- {0,0,0,0}, // 0xf5
- {0,0,0,0}, // 0xf6
- {0,0,0,0}, // 0xf7
- {0,0,0,0}, // 0xf8
- {0,0,0,0}, // 0xf9
- {0,0,0,0}, // 0xfa
- {0,0,0,0}, // 0xfb
- {0,0,0,0}, // 0xfc
- {0,0,0,0}, // 0xfd
- {0,0,0,0}, // 0xfe
- {0,0,0,0}, // 0xff
-};
+docstring const Encoding::latexChar(char_type c) const
+{
+ if (c < start_encodable_)
+ return docstring(1, c);
+ if (encodable_.find(c) == encodable_.end()) {
+ // c cannot be encoded in this encoding
+ CharInfoMap::const_iterator const it = unicodesymbols.find(c);
+ if (it == unicodesymbols.end())
+ lyxerr << "Could not find LaTeX command for character 0x"
+ << std::hex << c << std::dec
+ << ".\nLaTeX export will fail."
+ << endl;
+ else
+ return it->second.command;
+ }
+ return docstring(1, c);
+}
-unsigned char arabic_table[63][2] = {
- {0xc1, 0xc1}, // 0xc1 = hamza
- {0xc2, 0xc2}, // 0xc2 = ligature madda on alef
- {0xc3, 0xc3}, // 0xc3 = ligature hamza on alef
- {0xc4, 0xc4}, // 0xc4 = ligature hamza on waw
- {0xc5, 0xc5}, // 0xc5 = ligature hamza under alef
- {0xc6, 0xc0}, // 0xc6 = ligature hamza on ya
- {0xc7, 0xc7}, // 0xc7 = alef
- {0xc8, 0xeb}, // 0xc8 = baa
- {0xc9, 0xc9}, // 0xc9 = taa marbuta
- {0xca, 0xec}, // 0xca = taa
- {0xcb, 0xed}, // 0xcb = thaa
- {0xcc, 0xee}, // 0xcc = jeem
- {0xcd, 0xef}, // 0xcd = haa
- {0xce, 0xf0}, // 0xce = khaa
- {0xcf, 0xcf}, // 0xcf = dal
-
- {0xd0, 0xd0}, // 0xd0 = thal
- {0xd1, 0xd1}, // 0xd1 = ra
- {0xd2, 0xd2}, // 0xd2 = zain
- {0xd3, 0xf1}, // 0xd3 = seen
- {0xd4, 0xf2}, // 0xd4 = sheen
- {0xd5, 0xf3}, // 0xd5 = sad
- {0xd6, 0xf4}, // 0xd6 = dad
- {0xd7, 0xd7}, // 0xd7 = tah
- {0xd8, 0xd8}, // 0xd8 = zah
- {0xd9, 0xf5}, // 0xd9 = ain
- {0xda, 0xf6}, // 0xda = ghain
- {0,0}, // 0xdb
- {0,0}, // 0xdc
- {0,0}, // 0xdd
- {0,0}, // 0xde
- {0,0}, // 0xdf
-
- {0,0}, // 0xe0
- {0xe1, 0xf7}, // 0xe1 = fa
- {0xe2, 0xf8}, // 0xe2 = qaf
- {0xe3, 0xf9}, // 0xe3 = kaf
- {0xe4, 0xfa}, // 0xe4 = lam
- {0xe5, 0xfb}, // 0xe5 = meem
- {0xe6, 0xfc}, // 0xe6 = noon
- {0xe7, 0xfd}, // 0xe7 = ha
- {0xe8, 0xe8}, // 0xe8 = waw
- {0xe9, 0xe9}, // 0xe9 = alef maksura
- {0xea, 0xfe}, // 0xea = ya
- {0xa8, 0xa8}, // 0xeb = fathatan
- {0xa9, 0xa9}, // 0xec = dammatan
- {0xaa, 0xaa}, // 0xed = kasratan
- {0xab, 0xab}, // 0xee = fatha
- {0xac, 0xac}, // 0xef = damma
-
- {0xad, 0xad}, // 0xf0 = kasra
- {0xae, 0xae}, // 0xf1 = shadda
- {0xaf, 0xaf}, // 0xf2 = sukun
- {0,0}, // 0xf3
- {0,0}, // 0xf4
- {0,0}, // 0xf5
- {0,0}, // 0xf6
- {0,0}, // 0xf7
- {0,0}, // 0xf8
- {0,0}, // 0xf9
- {0,0}, // 0xfa
- {0,0}, // 0xfb
- {0,0}, // 0xfc
- {0,0}, // 0xfd
- {0,0}, // 0xfe
- {0,0} // 0xff
-};
+void Encoding::validate(char_type c, LaTeXFeatures & features) const
+{
+ // 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.
+ CharInfoMap::const_iterator const it = unicodesymbols.find(c);
+ if (it != unicodesymbols.end() && !it->second.preamble.empty()) {
+ if (it->second.feature)
+ features.require(it->second.preamble);
+ else
+ features.addPreambleSnippet(it->second.preamble);
+ }
+}
-unsigned char const arabic_start = 0xc1;
+bool Encodings::isComposeChar_hebrew(char_type c)
+{
+ return c <= 0x05c2 && c >= 0x05b0 &&
+ c != 0x05be && c != 0x05c0;
+}
-} // namespace anon
+// Special Arabic letters are ones that do not get connected from left
+// they are hamza, alef_madda, alef_hamza, waw_hamza, alef_hamza_under,
+// alef, tah_marbota, dal, thal, rah, zai, wow, alef_maksoura
-bool Encodings::IsComposeChar_hebrew(unsigned char c)
+bool Encodings::is_arabic_special(char_type c)
{
- return c <= 0xd2 && c >= 0xc0 &&
- c != 0xce && c != 0xd0;
+ return (c >= 0x0621 && c <= 0x0625) ||
+ c == 0x0627 || c == 0x0629 ||
+ c == 0x062f || c == 0x0648 ||
+ (c >= 0x0630 && c <= 0x0632) ||
+ c == 0x0649;
}
-bool Encodings::IsComposeChar_arabic(unsigned char c)
+bool Encodings::isComposeChar_arabic(char_type c)
{
- return c >= 0xeb && c <= 0xf2;
+ return c >= 0x064b && c <= 0x0652;
}
-bool Encodings::is_arabic(unsigned char c)
+bool Encodings::is_arabic(char_type c)
{
- return c >= arabic_start && arabic_table[c-arabic_start][0];
+ return c >= arabic_start && c <= arabic_end &&
+ arabic_table[c-arabic_start][0];
}
-unsigned char Encodings::TransformChar(unsigned char c,
+char_type Encodings::transformChar(char_type c,
Encodings::Letter_Form form)
{
if (!is_arabic(c))
return c;
- if (lyxrc.font_norm == "iso10646-1")
- return arabic_table2[c-arabic_start][form];
- else
- return arabic_table[c-arabic_start][form >> 1];
+ return arabic_table[c-arabic_start][form];
}
-Encoding const * Encodings::getEncoding(string const & encoding) const
+bool Encodings::isCombiningChar(char_type c)
{
- EncodingList::const_iterator it = encodinglist.find(encoding);
+ CharInfoMap::const_iterator const it = unicodesymbols.find(c);
+ if (it != unicodesymbols.end())
+ return it->second.combining;
+ return false;
+}
+
+
+Encoding const * Encodings::getFromLyXName(string const & name) const
+{
+ EncodingList::const_iterator it = encodinglist.find(name);
if (it != encodinglist.end())
- return &(*it).second;
+ return &it->second;
else
return 0;
}
+
+Encoding const * Encodings::getFromLaTeXName(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.latexName() == name)
+ return &it->second;
+ return 0;
+}
+
+
Encodings::Encodings()
{
- encodinglist["iso8859-1"] = Encoding("iso8859-1", "latin1", tab_iso8859_1);
- symbol_encoding_ =
-#ifdef USE_UNICODE_FOR_SYMBOLS
- Encoding("symbol", "", tab_symbol);
-#else
- Encoding("symbol", "", tab_iso8859_1);
-#endif
}
-void Encodings::read(string const & filename)
+
+void Encodings::read(FileName const & encfile, FileName const & symbolsfile)
{
+ // We must read the symbolsfile first, because the Encoding
+ // constructor depends on it.
+ LyXLex symbolslex(0, 0);
+ symbolslex.setFile(symbolsfile);
+ while (symbolslex.isOK()) {
+ char_type symbol;
+ CharInfo info;
+ string flags;
+
+ if (symbolslex.next(true)) {
+ std::istringstream is(symbolslex.getString());
+ // reading symbol directly does not work if
+ // char_type == std::wchar_t.
+ boost::uint32_t tmp;
+ if(!(is >> std::hex >> tmp))
+ break;
+ symbol = tmp;
+ } else
+ break;
+ if (symbolslex.next(true))
+ info.command = symbolslex.getDocString();
+ else
+ break;
+ if (symbolslex.next(true))
+ info.preamble = symbolslex.getString();
+ else
+ break;
+ if (symbolslex.next(true))
+ flags = symbolslex.getString();
+ else
+ break;
+
+ info.combining = false;
+ info.feature = false;
+ info.force = false;
+ while (!flags.empty()) {
+ string flag;
+ flags = support::split(flags, flag, ',');
+ if (flag == "combining")
+ info.combining = true;
+ else if (flag == "force")
+ info.force = true;
+ else
+ lyxerr << "Ignoring unknown flag `" << flag
+ << "' for symbol `0x"
+ << std::hex << symbol << std::dec
+ << "'." << endl;
+ }
+
+ if (!info.preamble.empty())
+ info.feature = info.preamble[0] != '\\';
+
+ LYXERR(Debug::INFO)
+ << "Read unicode symbol " << symbol << " '"
+ << to_utf8(info.command) << "' '" << info.preamble
+ << "' " << info.combining << ' ' << info.feature
+ << endl;
+ unicodesymbols[symbol] = info;
+ }
+
+ // Now read the encodings
enum Encodingtags {
et_encoding = 1,
et_end,
};
LyXLex lex(encodingtags, et_last - 1);
- lex.setFile(filename);
- while (lex.IsOK()) {
+ lex.setFile(encfile);
+ while (lex.isOK()) {
switch (lex.lex()) {
case et_encoding:
{
lex.next();
- string name = lex.GetString();
+ string const name = lex.getString();
lex.next();
- string latexname = lex.GetString();
- lyxerr[Debug::INIT] << "Reading encoding " << name << endl;
- Uchar table[256];
- for (unsigned int i = 0; i < 256; ++i) {
- lex.next();
- string tmp = lex.GetString();
- table[i] = ::strtol(tmp.c_str(), 0 , 16);
- }
- encodinglist[name] = Encoding(name, latexname, table);
+ string const latexname = lex.getString();
+ lex.next();
+ string const iconvname = lex.getString();
+ LYXERR(Debug::INFO) << "Reading encoding " << name << endl;
+ encodinglist[name] = Encoding(name, latexname, iconvname);
if (lex.lex() != et_end)
lex.printError("Encodings::read: "
"missing end");
}
}
}
+
+
+} // namespace lyx