![[tokkee]](http://tokkee.org/images/avatar.png){kind=avatar}
diff --git a/src/dom/ucd.cpp b/src/dom/ucd.cpp
index 862c6de2882c9fb19908755fdc3d579389ce5680..3747334d2b0861f682993c12dbfe47714520e02d 100644 (file)
--- a/src/dom/ucd.cpp
+++ b/src/dom/ucd.cpp
/*
- * Generated by UcdReader at:Tue May 06 16:19:25 CDT 2008
+ * Generated by UcdReader at:Mon Jun 30 13:52:41 GMT-06:00 2008
* block table size:2 (4 bytes)
* plane table size:6 (64 bytes)
*
*
* This table reflects information gleaned from the Unicode Character
- * Database, version 5.1.0. All codepoints are included.
+ * Database. All codepoints are included.
*
* You might notice that this table is larger than some other implementations.
* This is because we included the entire UCD set of codepoints, rather than
+/**
+ * Look for comments in ucd.h
+ */
+#include "ucd.h"
+
+
+static UcdBlockData ucd_blocks[] =
+{
+ { 0x000000, 0x00007f, "Basic Latin" },
+ { 0x000080, 0x0000ff, "Latin-1 Supplement" },
+ { 0x000100, 0x00017f, "Latin Extended-A" },
+ { 0x000180, 0x00024f, "Latin Extended-B" },
+ { 0x000250, 0x0002af, "IPA Extensions" },
+ { 0x0002b0, 0x0002ff, "Spacing Modifier Letters" },
+ { 0x000300, 0x00036f, "Combining Diacritical Marks" },
+ { 0x000370, 0x0003ff, "Greek and Coptic" },
+ { 0x000400, 0x0004ff, "Cyrillic" },
+ { 0x000500, 0x00052f, "Cyrillic Supplement" },
+ { 0x000530, 0x00058f, "Armenian" },
+ { 0x000590, 0x0005ff, "Hebrew" },
+ { 0x000600, 0x0006ff, "Arabic" },
+ { 0x000700, 0x00074f, "Syriac" },
+ { 0x000750, 0x00077f, "Arabic Supplement" },
+ { 0x000780, 0x0007bf, "Thaana" },
+ { 0x0007c0, 0x0007ff, "NKo" },
+ { 0x000900, 0x00097f, "Devanagari" },
+ { 0x000980, 0x0009ff, "Bengali" },
+ { 0x000a00, 0x000a7f, "Gurmukhi" },
+ { 0x000a80, 0x000aff, "Gujarati" },
+ { 0x000b00, 0x000b7f, "Oriya" },
+ { 0x000b80, 0x000bff, "Tamil" },
+ { 0x000c00, 0x000c7f, "Telugu" },
+ { 0x000c80, 0x000cff, "Kannada" },
+ { 0x000d00, 0x000d7f, "Malayalam" },
+ { 0x000d80, 0x000dff, "Sinhala" },
+ { 0x000e00, 0x000e7f, "Thai" },
+ { 0x000e80, 0x000eff, "Lao" },
+ { 0x000f00, 0x000fff, "Tibetan" },
+ { 0x001000, 0x00109f, "Myanmar" },
+ { 0x0010a0, 0x0010ff, "Georgian" },
+ { 0x001100, 0x0011ff, "Hangul Jamo" },
+ { 0x001200, 0x00137f, "Ethiopic" },
+ { 0x001380, 0x00139f, "Ethiopic Supplement" },
+ { 0x0013a0, 0x0013ff, "Cherokee" },
+ { 0x001400, 0x00167f, "Unified Canadian Aboriginal Syllabics" },
+ { 0x001680, 0x00169f, "Ogham" },
+ { 0x0016a0, 0x0016ff, "Runic" },
+ { 0x001700, 0x00171f, "Tagalog" },
+ { 0x001720, 0x00173f, "Hanunoo" },
+ { 0x001740, 0x00175f, "Buhid" },
+ { 0x001760, 0x00177f, "Tagbanwa" },
+ { 0x001780, 0x0017ff, "Khmer" },
+ { 0x001800, 0x0018af, "Mongolian" },
+ { 0x001900, 0x00194f, "Limbu" },
+ { 0x001950, 0x00197f, "Tai Le" },
+ { 0x001980, 0x0019df, "New Tai Lue" },
+ { 0x0019e0, 0x0019ff, "Khmer Symbols" },
+ { 0x001a00, 0x001a1f, "Buginese" },
+ { 0x001b00, 0x001b7f, "Balinese" },
+ { 0x001b80, 0x001bbf, "Sundanese" },
+ { 0x001c00, 0x001c4f, "Lepcha" },
+ { 0x001c50, 0x001c7f, "Ol Chiki" },
+ { 0x001d00, 0x001d7f, "Phonetic Extensions" },
+ { 0x001d80, 0x001dbf, "Phonetic Extensions Supplement" },
+ { 0x001dc0, 0x001dff, "Combining Diacritical Marks Supplement" },
+ { 0x001e00, 0x001eff, "Latin Extended Additional" },
+ { 0x001f00, 0x001fff, "Greek Extended" },
+ { 0x002000, 0x00206f, "General Punctuation" },
+ { 0x002070, 0x00209f, "Superscripts and Subscripts" },
+ { 0x0020a0, 0x0020cf, "Currency Symbols" },
+ { 0x0020d0, 0x0020ff, "Combining Diacritical Marks for Symbols" },
+ { 0x002100, 0x00214f, "Letterlike Symbols" },
+ { 0x002150, 0x00218f, "Number Forms" },
+ { 0x002190, 0x0021ff, "Arrows" },
+ { 0x002200, 0x0022ff, "Mathematical Operators" },
+ { 0x002300, 0x0023ff, "Miscellaneous Technical" },
+ { 0x002400, 0x00243f, "Control Pictures" },
+ { 0x002440, 0x00245f, "Optical Character Recognition" },
+ { 0x002460, 0x0024ff, "Enclosed Alphanumerics" },
+ { 0x002500, 0x00257f, "Box Drawing" },
+ { 0x002580, 0x00259f, "Block Elements" },
+ { 0x0025a0, 0x0025ff, "Geometric Shapes" },
+ { 0x002600, 0x0026ff, "Miscellaneous Symbols" },
+ { 0x002700, 0x0027bf, "Dingbats" },
+ { 0x0027c0, 0x0027ef, "Miscellaneous Mathematical Symbols-A" },
+ { 0x0027f0, 0x0027ff, "Supplemental Arrows-A" },
+ { 0x002800, 0x0028ff, "Braille Patterns" },
+ { 0x002900, 0x00297f, "Supplemental Arrows-B" },
+ { 0x002980, 0x0029ff, "Miscellaneous Mathematical Symbols-B" },
+ { 0x002a00, 0x002aff, "Supplemental Mathematical Operators" },
+ { 0x002b00, 0x002bff, "Miscellaneous Symbols and Arrows" },
+ { 0x002c00, 0x002c5f, "Glagolitic" },
+ { 0x002c60, 0x002c7f, "Latin Extended-C" },
+ { 0x002c80, 0x002cff, "Coptic" },
+ { 0x002d00, 0x002d2f, "Georgian Supplement" },
+ { 0x002d30, 0x002d7f, "Tifinagh" },
+ { 0x002d80, 0x002ddf, "Ethiopic Extended" },
+ { 0x002de0, 0x002dff, "Cyrillic Extended-A" },
+ { 0x002e00, 0x002e7f, "Supplemental Punctuation" },
+ { 0x002e80, 0x002eff, "CJK Radicals Supplement" },
+ { 0x002f00, 0x002fdf, "Kangxi Radicals" },
+ { 0x002ff0, 0x002fff, "Ideographic Description Characters" },
+ { 0x003000, 0x00303f, "CJK Symbols and Punctuation" },
+ { 0x003040, 0x00309f, "Hiragana" },
+ { 0x0030a0, 0x0030ff, "Katakana" },
+ { 0x003100, 0x00312f, "Bopomofo" },
+ { 0x003130, 0x00318f, "Hangul Compatibility Jamo" },
+ { 0x003190, 0x00319f, "Kanbun" },
+ { 0x0031a0, 0x0031bf, "Bopomofo Extended" },
+ { 0x0031c0, 0x0031ef, "CJK Strokes" },
+ { 0x0031f0, 0x0031ff, "Katakana Phonetic Extensions" },
+ { 0x003200, 0x0032ff, "Enclosed CJK Letters and Months" },
+ { 0x003300, 0x0033ff, "CJK Compatibility" },
+ { 0x003400, 0x004dbf, "CJK Unified Ideographs Extension A" },
+ { 0x004dc0, 0x004dff, "Yijing Hexagram Symbols" },
+ { 0x004e00, 0x009fff, "CJK Unified Ideographs" },
+ { 0x00a000, 0x00a48f, "Yi Syllables" },
+ { 0x00a490, 0x00a4cf, "Yi Radicals" },
+ { 0x00a500, 0x00a63f, "Vai" },
+ { 0x00a640, 0x00a69f, "Cyrillic Extended-B" },
+ { 0x00a700, 0x00a71f, "Modifier Tone Letters" },
+ { 0x00a720, 0x00a7ff, "Latin Extended-D" },
+ { 0x00a800, 0x00a82f, "Syloti Nagri" },
+ { 0x00a840, 0x00a87f, "Phags-pa" },
+ { 0x00a880, 0x00a8df, "Saurashtra" },
+ { 0x00a900, 0x00a92f, "Kayah Li" },
+ { 0x00a930, 0x00a95f, "Rejang" },
+ { 0x00aa00, 0x00aa5f, "Cham" },
+ { 0x00ac00, 0x00d7af, "Hangul Syllables" },
+ { 0x00d800, 0x00db7f, "High Surrogates" },
+ { 0x00db80, 0x00dbff, "High Private Use Surrogates" },
+ { 0x00dc00, 0x00dfff, "Low Surrogates" },
+ { 0x00e000, 0x00f8ff, "Private Use Area" },
+ { 0x00f900, 0x00faff, "CJK Compatibility Ideographs" },
+ { 0x00fb00, 0x00fb4f, "Alphabetic Presentation Forms" },
+ { 0x00fb50, 0x00fdff, "Arabic Presentation Forms-A" },
+ { 0x00fe00, 0x00fe0f, "Variation Selectors" },
+ { 0x00fe10, 0x00fe1f, "Vertical Forms" },
+ { 0x00fe20, 0x00fe2f, "Combining Half Marks" },
+ { 0x00fe30, 0x00fe4f, "CJK Compatibility Forms" },
+ { 0x00fe50, 0x00fe6f, "Small Form Variants" },
+ { 0x00fe70, 0x00feff, "Arabic Presentation Forms-B" },
+ { 0x00ff00, 0x00ffef, "Halfwidth and Fullwidth Forms" },
+ { 0x00fff0, 0x00ffff, "Specials" },
+ { 0x010000, 0x01007f, "Linear B Syllabary" },
+ { 0x010080, 0x0100ff, "Linear B Ideograms" },
+ { 0x010100, 0x01013f, "Aegean Numbers" },
+ { 0x010140, 0x01018f, "Ancient Greek Numbers" },
+ { 0x010190, 0x0101cf, "Ancient Symbols" },
+ { 0x0101d0, 0x0101ff, "Phaistos Disc" },
+ { 0x010280, 0x01029f, "Lycian" },
+ { 0x0102a0, 0x0102df, "Carian" },
+ { 0x010300, 0x01032f, "Old Italic" },
+ { 0x010330, 0x01034f, "Gothic" },
+ { 0x010380, 0x01039f, "Ugaritic" },
+ { 0x0103a0, 0x0103df, "Old Persian" },
+ { 0x010400, 0x01044f, "Deseret" },
+ { 0x010450, 0x01047f, "Shavian" },
+ { 0x010480, 0x0104af, "Osmanya" },
+ { 0x010800, 0x01083f, "Cypriot Syllabary" },
+ { 0x010900, 0x01091f, "Phoenician" },
+ { 0x010920, 0x01093f, "Lydian" },
+ { 0x010a00, 0x010a5f, "Kharoshthi" },
+ { 0x012000, 0x0123ff, "Cuneiform" },
+ { 0x012400, 0x01247f, "Cuneiform Numbers and Punctuation" },
+ { 0x01d000, 0x01d0ff, "Byzantine Musical Symbols" },
+ { 0x01d100, 0x01d1ff, "Musical Symbols" },
+ { 0x01d200, 0x01d24f, "Ancient Greek Musical Notation" },
+ { 0x01d300, 0x01d35f, "Tai Xuan Jing Symbols" },
+ { 0x01d360, 0x01d37f, "Counting Rod Numerals" },
+ { 0x01d400, 0x01d7ff, "Mathematical Alphanumeric Symbols" },
+ { 0x01f000, 0x01f02f, "Mahjong Tiles" },
+ { 0x01f030, 0x01f09f, "Domino Tiles" },
+ { 0x020000, 0x02a6df, "CJK Unified Ideographs Extension B" },
+ { 0x02f800, 0x02fa1f, "CJK Compatibility Ideographs Supplement" },
+ { 0x0e0000, 0x0e007f, "Tags" },
+ { 0x0e0100, 0x0e01ef, "Variation Selectors Supplement" },
+ { 0x0f0000, 0x0fffff, "Supplementary Private Use Area-A" },
+ { 0x100000, 0x10ffff, "Supplementary Private Use Area-B" },
+ { 0x000000, 0x10FFFF, (char*)0 } /* No_Block */
+};
+
+
/**
* Plane table has 4352 entries
*/
0x00067001, 0x00057002, 0x00007002, 0x00007005, /* 268 */
0x00067001, 0x00057002, 0x00007002, 0x07217002, /* 272 */
0x00007005, 0x00007005, 0x00007005, 0x00007005, /* 276 */
- 0x000a7001, 0x0007f003, 0x00097002, 0x000a7001, /* 280 */
- 0x0007f003, 0x00097002, 0x000a7001, 0x0007f003, /* 284 */
- 0x00097002, 0x00067001, 0x00057002, 0x00067001, /* 288 */
+ 0x000af001, 0x0007f003, 0x0009f002, 0x000af001, /* 280 */
+ 0x0007f003, 0x0009f002, 0x000af001, 0x0007f003, /* 284 */
+ 0x0009f002, 0x00067001, 0x00057002, 0x00067001, /* 288 */
0x00057002, 0x013d7002, 0x00067001, 0x00057002, /* 292 */
- 0x07fd7002, 0x000a7001, 0x0007f003, 0x00097002, /* 296 */
+ 0x07fd7002, 0x000af001, 0x0007f003, 0x0009f002, /* 296 */
0x00067001, 0x00057002, 0x067e7001, 0x07227001, /* 300 */
0x05fa7001, 0x00007002, 0x00067001, 0x00057002, /* 304 */
0x00007002, 0x00007002, 0x00007002, 0x00007002, /* 308 */
#define UNI_CODE(ch) (prop[block[plane[(ch>>8)&8191]+((ch>>2)&63)]+(ch&3)])
+/**
+ * Get type part of code
+
+ */
+#define UNI_CODE_TO_TYPE(ch) (ch & 0x1f)
+
/**
* Fetch the category type
*/
-#define UNI_TYPE(ch) (UNI_CODE(ch) & 0x1f)
+#define UNI_TYPE(ch) (UNI_CODE_TO_TYPE(UNI_CODE(ch)))
/**
* Fetch the digit offset
-/**
- * Look for comments in ucd.h
- */
-#include "ucd.h"
int uni_is_letter(int ch)
{
- int c = UNI_CODE(ch);
+ int c = UNI_TYPE(ch);
return (c>=UNI_UPPERCASE_LETTER && c<=UNI_OTHER_LETTER);
}
int uni_is_letter_or_digit(int ch)
{
- int c = UNI_CODE(ch);
+ int c = UNI_TYPE(ch);
return ((c>=UNI_UPPERCASE_LETTER && c<=UNI_OTHER_LETTER)
|| c==UNI_DECIMAL_DIGIT_NUMBER);
}
int uni_is_space(int ch)
{
- int c = UNI_CODE(ch);
+ int c = UNI_TYPE(ch);
return (c==UNI_SPACE_SEPARATOR || c==UNI_LINE_SEPARATOR
- || c==UNI_PARAGRAPH_SEPARATOR);
+ || c==UNI_PARAGRAPH_SEPARATOR || (ch>= 0x09 && ch <= 0x0d));
}
int uni_to_lower(int ch)
{
int c = UNI_CODE(ch);
- if (c == UNI_LOWERCASE_LETTER)
+ if (UNI_CODE_TO_TYPE(c) == UNI_LOWERCASE_LETTER)
return ch;
ch -= (c>>18) & 0x1ff;
return ch;
int uni_to_upper(int ch)
{
int c = UNI_CODE(ch);
- if (c == UNI_UPPERCASE_LETTER)
+ if (UNI_CODE_TO_TYPE(c) == UNI_UPPERCASE_LETTER)
return ch;
ch += (c>>18) & 0x1ff;
return ch;
int uni_to_title(int ch)
{
int c = UNI_CODE(ch);
- if (c == UNI_TITLECASE_LETTER)
+ if (UNI_CODE_TO_TYPE(c) == UNI_TITLECASE_LETTER)
return ch;
ch += (c>>18) & 0x1ff;
return ch;
}
+int uni_block(int ch)
+{
+ int ret;
+ UcdBlockData *entry;
+ for (entry = ucd_blocks, ret=0 ; entry->name ; entry++, ret++)
+ if (ch >= entry->low && ch <= entry->high)
+ return ret;
+ return UCD_BLOCK_NO_BLOCK;
+}
+
+UcdBlockData *uni_block_data(int blockNr)
+{
+ if (blockNr >= 0 && blockNr < UCD_BLOCK_NO_BLOCK)
+ return &(ucd_blocks[blockNr]);
+ else
+ return (UcdBlockData *)0;
+}
+