src/basic/gunicode.c

   1 /* gunicode.c - Unicode manipulation functions
   2  *
   3  *  Copyright (C) 1999, 2000 Tom Tromey
   4  *  Copyright © 2000, 2005 Red Hat, Inc.
   5  */
   6
   7 #include "gunicode.h"
   8
   9 #define unichar uint32_t
  10
  11 /**
  12  * g_utf8_prev_char:
  13  * @p: a pointer to a position within a UTF-8 encoded string
  14  *
  15  * Finds the previous UTF-8 character in the string before @p.
  16  *
  17  * @p does not have to be at the beginning of a UTF-8 character. No check
  18  * is made to see if the character found is actually valid other than
  19  * it starts with an appropriate byte. If @p might be the first
  20  * character of the string, you must use g_utf8_find_prev_char() instead.
  21  *
  22  * Return value: a pointer to the found character.
  23  **/
  24 char *
  25 utf8_prev_char (const char *p)
  26 {
  27   for (;;)
  28     {
  29       p--;
  30       if ((*p & 0xc0) != 0x80)
  31         return (char *)p;
  32     }
  33 }
  34
  35 struct Interval
  36 {
  37   unichar start, end;
  38 };
  39
  40 static int
  41 interval_compare (const void *key, const void *elt)
  42 {
  43   unichar c = (unichar) (long) (key);
  44   struct Interval *interval = (struct Interval *)elt;
  45
  46   if (c < interval->start)
  47     return -1;
  48   if (c > interval->end)
  49     return +1;
  50
  51   return 0;
  52 }
  53
  54 /*
  55  * NOTE:
  56  *
  57  * The tables for g_unichar_iswide() and g_unichar_iswide_cjk() are
  58  * generated from the Unicode Character Database's file
  59  * extracted/DerivedEastAsianWidth.txt using the gen-iswide-table.py
  60  * in this way:
  61  *
  62  *   ./gen-iswide-table.py < path/to/ucd/extracted/DerivedEastAsianWidth.txt | fmt
  63  *
  64  * Last update for Unicode 6.0.
  65  */
  66
  67 /**
  68  * g_unichar_iswide:
  69  * @c: a Unicode character
  70  *
  71  * Determines if a character is typically rendered in a double-width
  72  * cell.
  73  *
  74  * Return value: %TRUE if the character is wide
  75  **/
  76 bool
  77 unichar_iswide (unichar c)
  78 {
  79   /* See NOTE earlier for how to update this table. */
  80   static const struct Interval wide[] = {
  81     {0x1100, 0x115F}, {0x2329, 0x232A}, {0x2E80, 0x2E99}, {0x2E9B, 0x2EF3},
  82     {0x2F00, 0x2FD5}, {0x2FF0, 0x2FFB}, {0x3000, 0x303E}, {0x3041, 0x3096},
  83     {0x3099, 0x30FF}, {0x3105, 0x312D}, {0x3131, 0x318E}, {0x3190, 0x31BA},
  84     {0x31C0, 0x31E3}, {0x31F0, 0x321E}, {0x3220, 0x3247}, {0x3250, 0x32FE},
  85     {0x3300, 0x4DBF}, {0x4E00, 0xA48C}, {0xA490, 0xA4C6}, {0xA960, 0xA97C},
  86     {0xAC00, 0xD7A3}, {0xF900, 0xFAFF}, {0xFE10, 0xFE19}, {0xFE30, 0xFE52},
  87     {0xFE54, 0xFE66}, {0xFE68, 0xFE6B}, {0xFF01, 0xFF60}, {0xFFE0, 0xFFE6},
  88     {0x1B000, 0x1B001}, {0x1F200, 0x1F202}, {0x1F210, 0x1F23A},
  89     {0x1F240, 0x1F248}, {0x1F250, 0x1F251},
  90     {0x1F300, 0x1F567}, /* Miscellaneous Symbols and Pictographs */
  91     {0x20000, 0x2FFFD}, {0x30000, 0x3FFFD},
  92   };
  93
  94   if (bsearch ((void *)(uintptr_t)c, wide, (sizeof (wide) / sizeof ((wide)[0])), sizeof wide[0],
  95                interval_compare))
  96     return true;
  97
  98   return false;
  99 }
 100
 101 const char utf8_skip_data[256] = {
 102   1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
 103   1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
 104   1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
 105   1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
 106   1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
 107   1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,
 108   2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,2,
 109   3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,3,4,4,4,4,4,4,4,4,5,5,5,5,6,6,1,1
 110 };