Logo Search packages:      
Sourcecode: katoob version File versions  Download package

fribidi_wcwidth.c

/*
 * This is an implementation of wcwidth() and wcswidth() (defined in
 * IEEE Std 1002.1-2001) for Unicode.
 *
 * http://www.opengroup.org/onlinepubs/007904975/functions/wcwidth.html
 * http://www.opengroup.org/onlinepubs/007904975/functions/wcswidth.html
 *
 * In fixed-width output devices, Latin characters all occupy a single
 * "cell" position of equal width, whereas ideographic CJK characters
 * occupy two such cells. Interoperability between terminal-line
 * applications and (teletype-style) character terminals using the
 * UTF-8 encoding requires agreement on which character should advance
 * the cursor by how many cell positions. No established formal
 * standards exist at present on which Unicode character shall occupy
 * how many cell positions on character terminals. These routines are
 * a first attempt of defining such behavior based on simple rules
 * applied to data provided by the Unicode Consortium.
 *
 * For some graphical characters, the Unicode standard explicitly
 * defines a character-cell width via the definition of the East Asian
 * FullWidth (F), Wide (W), Half-width (H), and Narrow (Na) classes.
 * In all these cases, there is no ambiguity about which width a
 * terminal shall use. For characters in the East Asian Ambiguous (A)
 * class, the width choice depends purely on a preference of backward
 * compatibility with either historic CJK or Western practice.
 * Choosing single-width for these characters is easy to justify as
 * the appropriate long-term solution, as the CJK practice of
 * displaying these characters as double-width comes from historic
 * implementation simplicity (8-bit encoded characters were displayed
 * single-width and 16-bit ones double-width, even for Greek,
 * Cyrillic, etc.) and not any typographic considerations.
 *
 * Much less clear is the choice of width for the Not East Asian
 * (Neutral) class. Existing practice does not dictate a width for any
 * of these characters. It would nevertheless make sense
 * typographically to allocate two character cells to characters such
 * as for instance EM SPACE or VOLUME INTEGRAL, which cannot be
 * represented adequately with a single-width glyph. The following
 * routines at present merely assign a single-cell width to all
 * neutral characters, in the interest of simplicity. This is not
 * entirely satisfactory and should be reconsidered before
 * establishing a formal standard in this area. At the moment, the
 * decision which Not East Asian (Neutral) characters should be
 * represented by double-width glyphs cannot yet be answered by
 * applying a simple rule from the Unicode database content. Setting
 * up a proper standard for the behavior of UTF-8 character terminals
 * will require a careful analysis not only of each Unicode character,
 * but also of each presentation form, something the author of these
 * routines has avoided to do so far.
 *
 * http://www.unicode.org/unicode/reports/tr11/
 *
 * Markus Kuhn -- 2002-05-08 (Unicode 3.2)
 *
 * Permission to use, copy, modify, and distribute this software
 * for any purpose and without fee is hereby granted. The author
 * disclaims all warranties with regard to this software.
 *
 * Latest version: http://www.cl.cam.ac.uk/~mgk25/ucs/wcwidth.c
 */

/* 
 * Adapted for Katoob Copyright (c) 2002, 2003 Arabeyes, Mohammed Sameer.
 */

#include <glib.h>
#include "fribidi.h"

#define mk_wcwidth      fribidi_wcwidth
#define mk_wcswidth     fribidi_wcswidth
#define size_t          FriBidiStrIndex

struct interval
{
  unsigned int first;
  unsigned int last;
};

/* auxiliary function for binary search in interval table */
static int
bisearch (gunichar ucs, const struct interval *table, int max)
{
  int min = 0;
  int mid;

  if (ucs < table[0].first || ucs > table[max].last)
    return 0;
  while (max >= min)
    {
      mid = (min + max) / 2;
      if (ucs > table[mid].last)
      min = mid + 1;
      else if (ucs < table[mid].first)
      max = mid - 1;
      else
      return 1;
    }

  return 0;
}


/* The following two functions define the column width of an ISO 10646
 * character as follows:
 *
 *    - The null character (U+0000) has a column width of 0.
 *
 *    - Other C0/C1 control characters and DEL will lead to a return
 *      value of -1.
 *
 *    - Non-spacing and enclosing combining characters (general
 *      category code Mn or Me in the Unicode database) have a
 *      column width of 0.
 *
 *    - Other format characters (general category code Cf in the Unicode
 *      database) and ZERO WIDTH SPACE (U+200B) have a column width of 0.
 *
 *    - Hangul Jamo medial vowels and final consonants (U+1160-U+11FF)
 *      have a column width of 0.
 *
 *    - Spacing characters in the East Asian Wide (W) or East Asian
 *      Full-width (F) category as defined in Unicode Technical
 *      Report #11 have a column width of 2.
 *
 *    - All remaining characters (including all printable
 *      ISO 8859-1 and WGL4 characters, Unicode control characters,
 *      etc.) have a column width of 1.
 *
 * This implementation assumes that wchar_t characters are encoded
 * in ISO 10646.
 */

int
mk_wcwidth (gunichar ucs)
{
  /* sorted list of non-overlapping intervals of non-spacing characters */
  /* generated with "uniset +cat=Me +cat=Mn +cat=Cf +1160-11FF +200B c" */
  static const struct interval combining[] = {
    {0x0300, 0x034F}, {0x0360, 0x036F}, {0x0483, 0x0486},
    {0x0488, 0x0489}, {0x0591, 0x05A1}, {0x05A3, 0x05B9},
    {0x05BB, 0x05BD}, {0x05BF, 0x05BF}, {0x05C1, 0x05C2},
    {0x05C4, 0x05C4}, {0x064B, 0x0655}, {0x0670, 0x0670},
    {0x06D6, 0x06E4}, {0x06E7, 0x06E8}, {0x06EA, 0x06ED},
    {0x070F, 0x070F}, {0x0711, 0x0711}, {0x0730, 0x074A},
    {0x07A6, 0x07B0}, {0x0901, 0x0902}, {0x093C, 0x093C},
    {0x0941, 0x0948}, {0x094D, 0x094D}, {0x0951, 0x0954},
    {0x0962, 0x0963}, {0x0981, 0x0981}, {0x09BC, 0x09BC},
    {0x09C1, 0x09C4}, {0x09CD, 0x09CD}, {0x09E2, 0x09E3},
    {0x0A02, 0x0A02}, {0x0A3C, 0x0A3C}, {0x0A41, 0x0A42},
    {0x0A47, 0x0A48}, {0x0A4B, 0x0A4D}, {0x0A70, 0x0A71},
    {0x0A81, 0x0A82}, {0x0ABC, 0x0ABC}, {0x0AC1, 0x0AC5},
    {0x0AC7, 0x0AC8}, {0x0ACD, 0x0ACD}, {0x0B01, 0x0B01},
    {0x0B3C, 0x0B3C}, {0x0B3F, 0x0B3F}, {0x0B41, 0x0B43},
    {0x0B4D, 0x0B4D}, {0x0B56, 0x0B56}, {0x0B82, 0x0B82},
    {0x0BC0, 0x0BC0}, {0x0BCD, 0x0BCD}, {0x0C3E, 0x0C40},
    {0x0C46, 0x0C48}, {0x0C4A, 0x0C4D}, {0x0C55, 0x0C56},
    {0x0CBF, 0x0CBF}, {0x0CC6, 0x0CC6}, {0x0CCC, 0x0CCD},
    {0x0D41, 0x0D43}, {0x0D4D, 0x0D4D}, {0x0DCA, 0x0DCA},
    {0x0DD2, 0x0DD4}, {0x0DD6, 0x0DD6}, {0x0E31, 0x0E31},
    {0x0E34, 0x0E3A}, {0x0E47, 0x0E4E}, {0x0EB1, 0x0EB1},
    {0x0EB4, 0x0EB9}, {0x0EBB, 0x0EBC}, {0x0EC8, 0x0ECD},
    {0x0F18, 0x0F19}, {0x0F35, 0x0F35}, {0x0F37, 0x0F37},
    {0x0F39, 0x0F39}, {0x0F71, 0x0F7E}, {0x0F80, 0x0F84},
    {0x0F86, 0x0F87}, {0x0F90, 0x0F97}, {0x0F99, 0x0FBC},
    {0x0FC6, 0x0FC6}, {0x102D, 0x1030}, {0x1032, 0x1032},
    {0x1036, 0x1037}, {0x1039, 0x1039}, {0x1058, 0x1059},
    {0x1160, 0x11FF}, {0x1712, 0x1714}, {0x1732, 0x1734},
    {0x1752, 0x1753}, {0x1772, 0x1773}, {0x17B7, 0x17BD},
    {0x17C6, 0x17C6}, {0x17C9, 0x17D3}, {0x180B, 0x180E},
    {0x18A9, 0x18A9}, {0x200B, 0x200F}, {0x202A, 0x202E},
    {0x2060, 0x2063}, {0x206A, 0x206F}, {0x20D0, 0x20EA},
    {0x302A, 0x302F}, {0x3099, 0x309A}, {0xFB1E, 0xFB1E},
    {0xFE00, 0xFE0F}, {0xFE20, 0xFE23}, {0xFEFF, 0xFEFF},
    {0xFFF9, 0xFFFB}, {0x1D167, 0x1D169}, {0x1D173, 0x1D182},
    {0x1D185, 0x1D18B}, {0x1D1AA, 0x1D1AD}, {0xE0001, 0xE0001},
    {0xE0020, 0xE007F}
  };

  /* test for 8-bit control characters */
  if (ucs == 0)
    return 0;
  if (ucs < 32 || (ucs >= 0x7f && ucs < 0xa0))
    return -1;

  /* binary search in table of non-spacing characters */
  if (bisearch (ucs, combining,
            sizeof (combining) / sizeof (struct interval) - 1))
    return 0;

  /* if we arrive here, ucs is not a combining or C0/C1 control character */

  return 1 + (ucs >= 0x1100 && (ucs <= 0x115f ||      /* Hangul Jamo init. consonants */
                        ucs == 0x2329 || ucs == 0x232a || (ucs >= 0x2e80 && ucs <= 0xa4cf && ucs != 0x303f) ||    /* CJK ... Yi */
                        (ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */
                        (ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */
                        (ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */
                        (ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */
                        (ucs >= 0xffe0 && ucs <= 0xffe6) ||
                        (ucs >= 0x20000 && ucs <= 0x2ffff)));
}


int
mk_wcswidth (const gunichar * pwcs, size_t n)
{
  int w, width = 0;

  for (; *pwcs && n-- > 0; pwcs++)
    if ((w = mk_wcwidth (*pwcs)) < 0)
      return -1;
    else
      width += w;

  return width;
}

Generated by  Doxygen 1.6.0   Back to index