3 * This file is part of LyX, the document processor.
4 * Licence details can be found in the file COPYING.
6 * \author Lars Gullik Bjønnes
7 * \author Jean-Marc Lasgouttes
10 * Full author contact details are available in file CREDITS.
21 #include "support/filename.h"
26 #ifndef CXX_GLOBAL_CSTD
38 char_type arabic_table2[63][4] = {
39 {0x41, 0x41, 0x41, 0x41}, // 0xc1 = hamza
40 {0x42, 0xa1, 0x42, 0xa1}, // 0xc2 = ligature madda on alef
41 {0x43, 0xa2, 0x43, 0xa2}, // 0xc3 = ligature hamza on alef
42 {0x44, 0xa3, 0x44, 0xa3}, // 0xc4 = ligature hamza on waw
43 {0x45, 0xa4, 0x45, 0xa4}, // 0xc5 = ligature hamza under alef
44 {0x46, 0xf9, 0xf8, 0xa0}, // 0xc6 = ligature hamza on ya
45 {0x47, 0xa5, 0x47, 0xa5}, // 0xc7 = alef
46 {0x48, 0xae, 0xac, 0xad}, // 0xc8 = baa
47 {0x49, 0xb1, 0x49, 0xb1}, // 0xc9 = taa marbuta
48 {0x4a, 0xb4, 0xb2, 0xb3}, // 0xca = taa
49 {0x4b, 0xb7, 0xb5, 0xb6}, // 0xcb = thaa
50 {0x4c, 0xba, 0xb8, 0xb9}, // 0xcc = jeem
51 {0x4d, 0xbd, 0xbb, 0xbc}, // 0xcd = haa
52 {0x4e, 0xc0, 0xbe, 0xbf}, // 0xce = khaa
53 {0x4f, 0xa6, 0x4f, 0xa6}, // 0xcf = dal
55 {0x50, 0xa7, 0x50, 0xa7}, // 0xd0 = thal
56 {0x51, 0xa8, 0x51, 0xa8}, // 0xd1 = ra
57 {0x52, 0xa9, 0x52, 0xa9}, // 0xd2 = zain
58 {0x53, 0xc3, 0xc1, 0xc2}, // 0xd3 = seen
59 {0x54, 0xc6, 0xc4, 0xc5}, // 0xd4 = sheen
60 {0x55, 0xc9, 0xc7, 0xc8}, // 0xd5 = sad
61 {0x56, 0xcc, 0xca, 0xcb}, // 0xd6 = dad
62 {0x57, 0xcf, 0xcd, 0xce}, // 0xd7 = tah
63 {0x58, 0xd2, 0xd0, 0xd1}, // 0xd8 = zah
64 {0x59, 0xd5, 0xd3, 0xd4}, // 0xd9 = ain
65 {0x5a, 0xd8, 0xd6, 0xd7}, // 0xda = ghain
73 {0x61, 0xdb, 0xd9, 0xda}, // 0xe1 = fa
74 {0x62, 0xde, 0xdc, 0xdd}, // 0xe2 = qaf
75 {0x63, 0xe1, 0xdf, 0xe0}, // 0xe3 = kaf
76 {0x64, 0xe4, 0xe2, 0xe3}, // 0xe4 = lam
77 {0x65, 0xe7, 0xe5, 0xe6}, // 0xe5 = meem
78 {0x66, 0xea, 0xe8, 0xe9}, // 0xe6 = noon
79 {0x67, 0xed, 0xeb, 0xec}, // 0xe7 = ha
80 {0x68, 0xaa, 0x68, 0xaa}, // 0xe8 = waw
81 {0x69, 0xab, 0x69, 0xab}, // 0xe9 = alef maksura
82 {0x6a, 0xf0, 0xee, 0xef}, // 0xea = ya
83 {0x6b, 0x6b, 0x6b, 0x6b}, // 0xeb = fathatan
84 {0x6c, 0x6c, 0x6c, 0x6c}, // 0xec = dammatan
85 {0x6d, 0x6d, 0x6d, 0x6d}, // 0xed = kasratan
86 {0x6e, 0x6e, 0x6e, 0x6e}, // 0xee = fatha
87 {0x6f, 0x6f, 0x6f, 0x6f}, // 0xef = damma
89 {0x70, 0x70, 0x70, 0x70}, // 0xf0 = kasra
90 {0x71, 0x71, 0x71, 0x71}, // 0xf1 = shadda
91 {0x72, 0x72, 0x72, 0x72}, // 0xf2 = sukun
108 char_type arabic_table[63][2] = {
109 {0xc1, 0xc1}, // 0xc1 = hamza
110 {0xc2, 0xc2}, // 0xc2 = ligature madda on alef
111 {0xc3, 0xc3}, // 0xc3 = ligature hamza on alef
112 {0xc4, 0xc4}, // 0xc4 = ligature hamza on waw
113 {0xc5, 0xc5}, // 0xc5 = ligature hamza under alef
114 {0xc6, 0xc0}, // 0xc6 = ligature hamza on ya
115 {0xc7, 0xc7}, // 0xc7 = alef
116 {0xc8, 0xeb}, // 0xc8 = baa
117 {0xc9, 0xc9}, // 0xc9 = taa marbuta
118 {0xca, 0xec}, // 0xca = taa
119 {0xcb, 0xed}, // 0xcb = thaa
120 {0xcc, 0xee}, // 0xcc = jeem
121 {0xcd, 0xef}, // 0xcd = haa
122 {0xce, 0xf0}, // 0xce = khaa
123 {0xcf, 0xcf}, // 0xcf = dal
125 {0xd0, 0xd0}, // 0xd0 = thal
126 {0xd1, 0xd1}, // 0xd1 = ra
127 {0xd2, 0xd2}, // 0xd2 = zain
128 {0xd3, 0xf1}, // 0xd3 = seen
129 {0xd4, 0xf2}, // 0xd4 = sheen
130 {0xd5, 0xf3}, // 0xd5 = sad
131 {0xd6, 0xf4}, // 0xd6 = dad
132 {0xd7, 0xd7}, // 0xd7 = tah
133 {0xd8, 0xd8}, // 0xd8 = zah
134 {0xd9, 0xf5}, // 0xd9 = ain
135 {0xda, 0xf6}, // 0xda = ghain
143 {0xe1, 0xf7}, // 0xe1 = fa
144 {0xe2, 0xf8}, // 0xe2 = qaf
145 {0xe3, 0xf9}, // 0xe3 = kaf
146 {0xe4, 0xfa}, // 0xe4 = lam
147 {0xe5, 0xfb}, // 0xe5 = meem
148 {0xe6, 0xfc}, // 0xe6 = noon
149 {0xe7, 0xfd}, // 0xe7 = ha
150 {0xe8, 0xe8}, // 0xe8 = waw
151 {0xe9, 0xe9}, // 0xe9 = alef maksura
152 {0xea, 0xfe}, // 0xea = ya
153 {0xa8, 0xa8}, // 0xeb = fathatan
154 {0xa9, 0xa9}, // 0xec = dammatan
155 {0xaa, 0xaa}, // 0xed = kasratan
156 {0xab, 0xab}, // 0xee = fatha
157 {0xac, 0xac}, // 0xef = damma
159 {0xad, 0xad}, // 0xf0 = kasra
160 {0xae, 0xae}, // 0xf1 = shadda
161 {0xaf, 0xaf}, // 0xf2 = sukun
178 char_type const arabic_start = 0xc1;
184 bool Encodings::isComposeChar_hebrew(char_type c)
186 return c <= 0xd2 && c >= 0xc0 &&
187 c != 0xce && c != 0xd0;
191 // Special Arabic letters are ones that do not get connected from left
192 // they are hamza, alef_madda, alef_hamza, waw_hamza, alef_hamza_under,
193 // alef, tah_marbota, dal, thal, rah, zai, wow, alef_maksoura
195 bool Encodings::is_arabic_special(char_type c)
197 return (c >= 0xc1 && c <= 0xc5) ||
198 c == 0xc7 || c == 0xc9 ||
199 c == 0xcf || c == 0xe8 ||
200 (c >= 0xd0 && c <= 0xd2) ||
204 bool Encodings::isComposeChar_arabic(char_type c)
206 return c >= 0xeb && c <= 0xf2;
210 bool Encodings::is_arabic(char_type c)
212 return c >= arabic_start && arabic_table[c-arabic_start][0];
216 char_type Encodings::transformChar(char_type c,
217 Encodings::Letter_Form form)
222 if (lyxrc.font_norm_type == LyXRC::ISO_10646_1)
223 return arabic_table2[c-arabic_start][form];
225 return arabic_table[c-arabic_start][form >> 1];
229 Encoding const * Encodings::getFromLyXName(string const & name) const
231 EncodingList::const_iterator it = encodinglist.find(name);
232 if (it != encodinglist.end())
241 class LaTeXNamesEqual : public std::unary_function<std::pair<std::string, Encoding>, bool> {
243 LaTeXNamesEqual(string const & LaTeXName)
244 : LaTeXName_(LaTeXName) {}
245 bool operator()(std::pair<std::string, Encoding> const & encoding) const
247 return encoding.second.latexName() == LaTeXName_;
256 Encoding const * Encodings::getFromLaTeXName(string const & name) const
258 EncodingList::const_iterator const it =
259 std::find_if(encodinglist.begin(), encodinglist.end(),
260 LaTeXNamesEqual(name));
261 if (it != encodinglist.end())
268 Encodings::Encodings()
272 void Encodings::read(support::FileName const & filename)
280 struct keyword_item encodingtags[et_last - 1] = {
281 { "encoding", et_encoding },
285 LyXLex lex(encodingtags, et_last - 1);
286 lex.setFile(filename);
292 string const name = lex.getString();
294 string const latexname = lex.getString();
296 string const iconvname = lex.getString();
297 lyxerr[Debug::INFO] << "Reading encoding " << name << endl;
298 encodinglist[name] = Encoding(name, latexname, iconvname);
299 if (lex.lex() != et_end)
300 lex.printError("Encodings::read: "
305 lex.printError("Encodings::read: Misplaced end");
307 case LyXLex::LEX_FEOF:
310 lex.printError("Encodings::read: "
311 "Unknown tag: `$$Token'");