get builddir!=srcdir compiling working; allow successful make even without noweb...

[lyx.git] / src / encoding.C

diff --git a/src/encoding.C b/src/encoding.C
index c2a8bc53a9e6e9ce7f717f9b3876f436688a4428..f8350dd1db7edb613c4b42b8c1723f08444fe24f 100644 (file)
--- a/src/encoding.C
+++ b/src/encoding.C
@@ -10,8 +10,13 @@
 
 #include <config.h>
 
+#ifdef __GNUG__
+#pragma implementation
+#endif
+
 #include "encoding.h"
 
+static
 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,
@@ -31,6 +36,8 @@ Uchar tab_iso8859_1[256] = {
    0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff
 };
 
+
+static
 Uchar tab_iso8859_2[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,
@@ -56,6 +63,35 @@ Uchar tab_iso8859_2[256] = {
    0x0159, 0x016f, 0x00fa, 0x0171, 0x00fc, 0x00fd, 0x0163, 0x02d9
 };
 
+
+static
+Uchar tab_iso8859_3[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,
+   0x00a0, 0x0126, 0x02d8, 0x00a3, 0x00a4, 0xffff, 0x0124, 0x00a7,
+   0x00a8, 0x0130, 0x015e, 0x011e, 0x0134, 0x00ad, 0xffff, 0x017b,
+   0x00b0, 0x0127, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x0125, 0x00b7,
+   0x00b8, 0x0131, 0x015f, 0x011f, 0x0135, 0x00bd, 0xffff, 0x017c,
+   0x00c0, 0x00c1, 0x00c2, 0xffff, 0x00c4, 0x010a, 0x0108, 0x00c7,
+   0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf,
+   0xffff, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x0120, 0x00d6, 0x00d7,
+   0x011c, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x016c, 0x015c, 0x00df,
+   0x00e0, 0x00e1, 0x00e2, 0xffff, 0x00e4, 0x010b, 0x0109, 0x00e7,
+   0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef,
+   0xffff, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x0121, 0x00f6, 0x00f7,
+   0x011d, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x016d, 0x015d, 0x02d9,
+};
+
+
+static
 Uchar tab_iso8859_4[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,
@@ -81,6 +117,8 @@ Uchar tab_iso8859_4[256] = {
    0x00f8, 0x0173, 0x00fa, 0x00fb, 0x00fc, 0x0169, 0x016b, 0x02d9
 };
 
+
+static
 Uchar tab_iso8859_6_16[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,
@@ -112,6 +150,8 @@ Uchar tab_iso8859_6_16[256] = {
    0xfe8b, 0xfe8a, 0xfef6, 0xfefa, 0xfef8, 0xfefc, 0x00fe, 0x00ff
 };
 
+
+static
 Uchar tab_iso8859_7[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,
@@ -137,6 +177,35 @@ Uchar tab_iso8859_7[256] = {
    0x03c8, 0x03c9, 0x03ca, 0x03cb, 0x03cc, 0x03cd, 0x03ce, 0xffff
 };
 
+
+static
+Uchar tab_iso8859_9[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,
+   0x00a0, 0x00a1, 0x00a2, 0x00a3, 0x00a4, 0x00a5, 0x00a6, 0x00a7,
+   0x00a8, 0x00a9, 0x00aa, 0x00ab, 0x00ac, 0x00ad, 0x00ae, 0x00af,
+   0x00b0, 0x00b1, 0x00b2, 0x00b3, 0x00b4, 0x00b5, 0x00b6, 0x00b7,
+   0x00b8, 0x00b9, 0x00ba, 0x00bb, 0x00bc, 0x00bd, 0x00be, 0x00bf,
+   0x00c0, 0x00c1, 0x00c2, 0x00c3, 0x00c4, 0x00c5, 0x00c6, 0x00c7,
+   0x00c8, 0x00c9, 0x00ca, 0x00cb, 0x00cc, 0x00cd, 0x00ce, 0x00cf,
+   0x011e, 0x00d1, 0x00d2, 0x00d3, 0x00d4, 0x00d5, 0x00d6, 0x00d7,
+   0x00d8, 0x00d9, 0x00da, 0x00db, 0x00dc, 0x0130, 0x015e, 0x00df,
+   0x00e0, 0x00e1, 0x00e2, 0x00e3, 0x00e4, 0x00e5, 0x00e6, 0x00e7,
+   0x00e8, 0x00e9, 0x00ea, 0x00eb, 0x00ec, 0x00ed, 0x00ee, 0x00ef,
+   0x011f, 0x00f1, 0x00f2, 0x00f3, 0x00f4, 0x00f5, 0x00f6, 0x00f7,
+   0x00f8, 0x00f9, 0x00fa, 0x00fb, 0x00fc, 0x0131, 0x015f, 0x00ff,
+};
+
+
+static
 Uchar tab_cp1255[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,
@@ -162,6 +231,8 @@ Uchar tab_cp1255[256] = {
    0x05e8, 0x05e9, 0x05ea, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff
 };
 
+
+static
 Uchar tab_koi8[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,
@@ -189,6 +260,63 @@ Uchar tab_koi8[256] = {
    0x042c, 0x042b, 0x0417, 0x0428, 0x042d, 0x0429, 0x0427, 0x042a
 };
 
+
+#ifdef USE_UNICODE_FOR_SYMBOLS
+static
+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,
+
+   0x0020, 0x0021, 0x2200, 0x0023, 0x2203, 0x0025, 0x0026, 0x220b,
+   0x0028, 0x0029, 0x002a, 0x002b, 0x002c, 0x002d, 0x002e, 0x002f,
+
+   0x30, 0x31, 0x32, 0x33, 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f,
+
+//   0x2245, 0x0391, 0x0392, 0x03a7, 0x0394, 0x0395, 0x03a6, 0x0393,
+//   0x0397, 0x0399, 0x03d1, 0x039a, 0x039b, 0x039c, 0x039d, 0x039f,
+
+//   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,
+
+   0xffff, 0x03b1, 0x03b2, 0x03c7, 0x03b4, 0x03b5, 0x03d5, 0x03b3,
+   0x03b7, 0x03b9, 0x03c6, 0x03ba, 0x03bb, 0x03bc, 0x03bd, 0x03bf,
+
+   0x03c0, 0x03b8, 0x03c1, 0x03c3, 0x03c4, 0x03c5, 0x03d6, 0x03c9,
+   0x03be, 0x03c8, 0x03b6, 0x007b, 0x007c, 0x007d, 0x007e, 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,
+ 
+   0xffff, 0x03d2, 0x2032, 0x2264, 0x2215, 0x221e, 0xffff, 0x2663,
+   0x2666, 0x2665, 0x2660, 0x2194, 0x2190, 0x2191, 0x2192, 0x2193,
+
+   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,
+
+   0x2220, 0x2207, 0x00ae, 0x00a9, 0x2122, 0x220f, 0x221a, 0x22c5,
+   0x00ac, 0x2227, 0x2228, 0x21d4, 0x21d0, 0x21d1, 0x21d2, 0x21d3,
+
+   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
+
+
+static
 unsigned char arabic_table2[63][4] = {
        {0x41, 0x41, 0x41, 0x41}, // 0xc1 = hamza
        {0x42, 0xa1, 0x42, 0x42}, // 0xc2 = ligature madda on alef
@@ -258,6 +386,8 @@ unsigned char arabic_table2[63][4] = {
        {0,0,0,0}, // 0xff
 };
 
+
+static
 unsigned char arabic_table[63][2] = {
        {0xc1, 0xc1}, // 0xc1 = hamza
        {0xc2, 0xc2}, // 0xc2 = ligature madda on alef
@@ -303,7 +433,7 @@ unsigned char arabic_table[63][2] = {
        {0xe8, 0xe8},   // 0xe8 = waw
        {0xe9, 0xe9},   // 0xe9 = alef maksura
        {0xea, 0xfe},   // 0xea = ya
-       {0xeb, 0xa8},   // 0xeb = fathatan
+       {0xa8, 0xa8},   // 0xeb = fathatan
        {0xa9, 0xa9},   // 0xec = dammatan
        {0xaa, 0xaa},   // 0xed = kasratan
        {0xab, 0xab},   // 0xee = fatha
@@ -329,8 +459,53 @@ unsigned char arabic_table[63][2] = {
 
 Encoding iso8859_1("latin1",tab_iso8859_1);
 Encoding iso8859_2("latin2",tab_iso8859_2);
+Encoding iso8859_3("latin3",tab_iso8859_3);
 Encoding iso8859_4("latin4",tab_iso8859_4);
-Encoding iso8859_6("latin6",tab_iso8859_6_16);
-Encoding iso8859_7("latin7",tab_iso8859_7);
+Encoding iso8859_6("unknown",tab_iso8859_6_16);
+Encoding iso8859_7("iso-8859-7",tab_iso8859_7);
+Encoding iso8859_9("latin5",tab_iso8859_9);
 Encoding cp1255("cp1255",tab_cp1255);
 Encoding koi8("koi8-r",tab_koi8);
+
+
+#ifdef USE_UNICODE_FOR_SYMBOLS
+Encoding symbol_encoding("",tab_symbol);
+#else
+Encoding symbol_encoding("",tab_iso8859_1);
+#endif
+
+
+bool Encoding::IsComposeChar_hebrew(unsigned char c)
+{
+       return c <= 0xd2 && c >= 0xc0 &&
+               c != 0xce && c != 0xd0;
+}
+
+
+bool Encoding::IsComposeChar_arabic(unsigned char c)
+{
+       return c >= 0xeb && c <= 0xf2;
+}
+
+
+static
+unsigned char const arabic_start = 0xc1;
+
+
+bool Encoding::is_arabic(unsigned char c)
+{
+       return c >= arabic_start && arabic_table[c-arabic_start][0];
+}
+
+
+unsigned char Encoding::TransformChar(unsigned char c,
+                                     Encoding::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];
+}