namespace {
-char_type arabic_table2[63][4] = {
- {0x41, 0x41, 0x41, 0x41}, // 0xc1 = hamza
- {0x42, 0xa1, 0x42, 0xa1}, // 0xc2 = ligature madda on alef
- {0x43, 0xa2, 0x43, 0xa2}, // 0xc3 = ligature hamza on alef
- {0x44, 0xa3, 0x44, 0xa3}, // 0xc4 = ligature hamza on waw
- {0x45, 0xa4, 0x45, 0xa4}, // 0xc5 = ligature hamza under alef
- {0x46, 0xf9, 0xf8, 0xa0}, // 0xc6 = ligature hamza on ya
- {0x47, 0xa5, 0x47, 0xa5}, // 0xc7 = alef
- {0x48, 0xae, 0xac, 0xad}, // 0xc8 = baa
- {0x49, 0xb1, 0x49, 0xb1}, // 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, 0x4f, 0xa6}, // 0xcf = dal
-
- {0x50, 0xa7, 0x50, 0xa7}, // 0xd0 = thal
- {0x51, 0xa8, 0x51, 0xa8}, // 0xd1 = ra
- {0x52, 0xa9, 0x52, 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, 0x68, 0xaa}, // 0xe8 = waw
- {0x69, 0xab, 0x69, 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
+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
};
-char_type 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
-};
-
-
-char_type const arabic_start = 0xc1;
+char_type const arabic_start = 0x0621;
+char_type const arabic_end = 0x0652;
/// Information about a single UCS4 character
Encoding::Encoding(string const & n, string const & l, string const & i)
: Name_(n), LatexName_(l), iconvName_(i)
{
- if (n == "utf8")
+ 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 {
CharInfoMap::const_iterator const it = unicodesymbols.find(c);
if (it == unicodesymbols.end())
lyxerr << "Could not find LaTeX command for character 0x"
- << std::hex << c << ".\nLaTeX export will fail."
+ << std::hex << c << std::dec
+ << ".\nLaTeX export will fail."
<< endl;
else
return it->second.command;
}
-void Encoding::validate(char_type c, LaTeXFeatures & features) const
+void Encodings::validate(char_type c, LaTeXFeatures & features)
{
- if (c < start_encodable_)
- return;
-
- if (encodable_.find(c) != encodable_.end())
- return;
-
- // c cannot be encoded in this encoding
CharInfoMap::const_iterator const it = unicodesymbols.find(c);
if (it != unicodesymbols.end() && !it->second.preamble.empty()) {
if (it->second.feature)
bool Encodings::isComposeChar_hebrew(char_type c)
{
- return c <= 0xd2 && c >= 0xc0 &&
- c != 0xce && c != 0xd0;
+ return c <= 0x05c2 && c >= 0x05b0 &&
+ c != 0x05be && c != 0x05c0;
}
bool Encodings::is_arabic_special(char_type c)
{
- return (c >= 0xc1 && c <= 0xc5) ||
- c == 0xc7 || c == 0xc9 ||
- c == 0xcf || c == 0xe8 ||
- (c >= 0xd0 && c <= 0xd2) ||
- c == 0xe9;
+ return (c >= 0x0621 && c <= 0x0625) ||
+ c == 0x0627 || c == 0x0629 ||
+ c == 0x062f || c == 0x0648 ||
+ (c >= 0x0630 && c <= 0x0632) ||
+ c == 0x0649;
}
+
bool Encodings::isComposeChar_arabic(char_type c)
{
- return c >= 0xeb && c <= 0xf2;
+ return c >= 0x064b && c <= 0x0652;
}
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];
}
if (!is_arabic(c))
return c;
- if (lyxrc.font_norm_type == LyXRC::ISO_10646_1)
- return arabic_table2[c-arabic_start][form];
- else
- return arabic_table[c-arabic_start][form >> 1];
+ return arabic_table[c-arabic_start][form];
}
break;
info.combining = false;
+ info.feature = false;
info.force = false;
while (!flags.empty()) {
string flag;
info.force = true;
else
lyxerr << "Ignoring unknown flag `" << flag
- << "' for symbol `0x" << std::hex
- << symbol << "'." << endl;
+ << "' for symbol `0x"
+ << std::hex << symbol << std::dec
+ << "'." << endl;
}
if (!info.preamble.empty())
info.feature = info.preamble[0] != '\\';
- lyxerr[Debug::INFO]
+ LYXERR(Debug::INFO)
<< "Read unicode symbol " << symbol << " '"
<< to_utf8(info.command) << "' '" << info.preamble
<< "' " << info.combining << ' ' << info.feature
string const latexname = lex.getString();
lex.next();
string const iconvname = lex.getString();
- lyxerr[Debug::INFO] << "Reading encoding " << name << endl;
+ LYXERR(Debug::INFO) << "Reading encoding " << name << endl;
encodinglist[name] = Encoding(name, latexname, iconvname);
if (lex.lex() != et_end)
lex.printError("Encodings::read: "
projects / lyx.git / blobdiff