File Manager

003 File Manager

Current Path: /usr/src/contrib/subversion/subversion/libsvn_subr

usr / src / contrib / subversion / subversion / libsvn_subr /

📁 ..
📄 adler32.c(3.16 KB)
📄 atomic.c(7.23 KB)
📄 auth.c(32.4 KB)
📄 auth.h(6.1 KB)
📄 base64.c(19.18 KB)
📄 bit_array.c(6.26 KB)
📄 cache-inprocess.c(21.2 KB)
📄 cache-membuffer.c(116.43 KB)
📄 cache-memcache.c(17.35 KB)
📄 cache-null.c(4.35 KB)
📄 cache.c(10.22 KB)
📄 cache.h(4.03 KB)
📄 cache_config.c(6.01 KB)
📄 checksum.c(24.17 KB)
📄 checksum.h(2.32 KB)
📄 cmdline.c(58.99 KB)
📄 compat.c(5.28 KB)
📄 compress_lz4.c(4.51 KB)
📄 compress_zlib.c(6.85 KB)
📄 config.c(39.66 KB)
📄 config_auth.c(8.65 KB)
📄 config_file.c(70.25 KB)
📄 config_impl.h(6.15 KB)
📄 config_keys.inc(2.65 KB)
📄 config_win.c(9.61 KB)
📄 crypto.c(25.19 KB)
📄 crypto.h(5.43 KB)
📄 ctype.c(13.81 KB)
📄 date.c(12.86 KB)
📄 debug.c(3.77 KB)
📄 deprecated.c(64.3 KB)
📄 dirent_uri.c(80.17 KB)
📄 dirent_uri.h(1.43 KB)
📄 dso.c(3.74 KB)
📄 encode.c(2.69 KB)
📄 eol.c(2.79 KB)
📄 error.c(24.52 KB)
📄 errorcode.inc(4.27 KB)
📄 fnv1a.c(6.92 KB)
📄 fnv1a.h(3.04 KB)
📄 genctype.py(3.84 KB)
📄 gpg_agent.c(22.29 KB)
📄 hash.c(19.59 KB)
📄 internal_statements.h(1.87 KB)
📄 internal_statements.sql(1.58 KB)
📄 io.c(182.6 KB)
📄 iter.c(3.84 KB)
📄 libsvn_subr.pc.in(515 B)
📄 lock.c(1.69 KB)
📄 log.c(14 KB)
📁 lz4
📄 macos_keychain.c(9.7 KB)
📄 magic.c(5.25 KB)
📄 md5.c(1.8 KB)
📄 mergeinfo.c(89.24 KB)
📄 mutex.c(3.06 KB)
📄 nls.c(3.06 KB)
📄 object_pool.c(9.76 KB)
📄 opt.c(39.34 KB)
📄 opt.h(1.89 KB)
📄 packed_data.c(33.43 KB)
📄 path.c(35.99 KB)
📄 pool.c(4.35 KB)
📄 pools.h(1.45 KB)
📄 prefix_string.c(10.65 KB)
📄 prompt.c(28.82 KB)
📄 properties.c(13.59 KB)
📄 quoprint.c(8.96 KB)
📄 root_pools.c(3.15 KB)
📄 simple_providers.c(25.54 KB)
📄 skel.c(23.04 KB)
📄 sorts.c(15.9 KB)
📄 spillbuf.c(19.78 KB)
📄 sqlite.c(49.68 KB)
📄 sqlite3wrapper.c(3.16 KB)
📄 ssl_client_cert_providers.c(6.66 KB)
📄 ssl_client_cert_pw_providers.c(18.93 KB)
📄 ssl_server_trust_providers.c(7.77 KB)
📄 stream.c(65.69 KB)
📄 string.c(40.2 KB)
📄 subst.c(67.57 KB)
📄 sysinfo.c(43.67 KB)
📄 sysinfo.h(2.58 KB)
📄 target.c(11.58 KB)
📄 temp_serializer.c(14.02 KB)
📄 time.c(9.08 KB)
📄 token.c(2.58 KB)
📄 types.c(9.43 KB)
📄 user.c(2.66 KB)
📄 username_providers.c(9.2 KB)
📄 utf.c(40.38 KB)
📁 utf8proc
📄 utf8proc.c(20.71 KB)
📄 utf_validate.c(13.3 KB)
📄 utf_width.c(10.85 KB)
📄 validate.c(3.35 KB)
📄 version.c(9.89 KB)
📄 win32_crashrpt.c(25.06 KB)
📄 win32_crashrpt.h(1.35 KB)
📄 win32_crashrpt_dll.h(4 KB)
📄 win32_crypto.c(18.12 KB)
📄 win32_xlate.c(7.3 KB)
📄 win32_xlate.h(2.11 KB)
📄 x509.h(3.75 KB)
📄 x509info.c(9.53 KB)
📄 x509parse.c(35.77 KB)
📄 xml.c(20.01 KB)

Editing: utf_width.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 -- 2007-05-26 (Unicode 5.0)
 *
 * 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
 */

#include <apr_lib.h>

#include "svn_utf.h"
#include "private/svn_utf_private.h"

#include "svn_private_config.h"

struct interval {
  apr_uint32_t first;
  apr_uint32_t last;
};

/* auxiliary function for binary search in interval table */
static int
bisearch(apr_uint32_t ucs, const struct interval *table, apr_uint32_t max)
{
  apr_uint32_t min = 0;
  apr_uint32_t 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; /* this is safe because ucs >= table[0].first */
    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.
 *
 *    - SOFT HYPHEN (U+00AD) has a column width of 1.
 *
 *    - 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.
 */

static int
mk_wcwidth(apr_uint32_t ucs)
{
  /* sorted list of non-overlapping intervals of non-spacing characters */
  /* generated by "uniset +cat=Me +cat=Mn +cat=Cf -00AD +1160-11FF +200B c" */
  static const struct interval combining[] = {
    { 0x0300, 0x036F }, { 0x0483, 0x0486 }, { 0x0488, 0x0489 },
    { 0x0591, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 },
    { 0x05C4, 0x05C5 }, { 0x05C7, 0x05C7 }, { 0x0600, 0x0603 },
    { 0x0610, 0x0615 }, { 0x064B, 0x065E }, { 0x0670, 0x0670 },
    { 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED },
    { 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A },
    { 0x07A6, 0x07B0 }, { 0x07EB, 0x07F3 }, { 0x0901, 0x0902 },
    { 0x093C, 0x093C }, { 0x0941, 0x0948 }, { 0x094D, 0x094D },
    { 0x0951, 0x0954 }, { 0x0962, 0x0963 }, { 0x0981, 0x0981 },
    { 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD },
    { 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 }, { 0x0A3C, 0x0A3C },
    { 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D },
    { 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 }, { 0x0ABC, 0x0ABC },
    { 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 }, { 0x0ACD, 0x0ACD },
    { 0x0AE2, 0x0AE3 }, { 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 }, { 0x0CBC, 0x0CBC },
    { 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD },
    { 0x0CE2, 0x0CE3 }, { 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 }, { 0x135F, 0x135F },
    { 0x1712, 0x1714 }, { 0x1732, 0x1734 }, { 0x1752, 0x1753 },
    { 0x1772, 0x1773 }, { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD },
    { 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD },
    { 0x180B, 0x180D }, { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 },
    { 0x1927, 0x1928 }, { 0x1932, 0x1932 }, { 0x1939, 0x193B },
    { 0x1A17, 0x1A18 }, { 0x1B00, 0x1B03 }, { 0x1B34, 0x1B34 },
    { 0x1B36, 0x1B3A }, { 0x1B3C, 0x1B3C }, { 0x1B42, 0x1B42 },
    { 0x1B6B, 0x1B73 }, { 0x1DC0, 0x1DCA }, { 0x1DFE, 0x1DFF },
    { 0x200B, 0x200F }, { 0x202A, 0x202E }, { 0x2060, 0x2063 },
    { 0x206A, 0x206F }, { 0x20D0, 0x20EF }, { 0x302A, 0x302F },
    { 0x3099, 0x309A }, { 0xA806, 0xA806 }, { 0xA80B, 0xA80B },
    { 0xA825, 0xA826 }, { 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F },
    { 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB },
    { 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F },
    { 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, { 0x1D167, 0x1D169 },
    { 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B }, { 0x1D1AA, 0x1D1AD },
    { 0x1D242, 0x1D244 }, { 0xE0001, 0xE0001 }, { 0xE0020, 0xE007F },
    { 0xE0100, 0xE01EF }
  };

/* 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 >= 0xfe10 && ucs <= 0xfe19) || /* Vertical forms */
      (ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */
      (ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */
      (ucs >= 0xffe0 && ucs <= 0xffe6) ||
      (ucs >= 0x20000 && ucs <= 0x2fffd) ||
      (ucs >= 0x30000 && ucs <= 0x3fffd)));
}

int
svn_utf_cstring_utf8_width(const char *cstr)
{
  int width = 0;

if (*cstr == '\0')
    return 0;

/* Ensure the conversion below doesn't fail because of encoding errors. */
  if (!svn_utf__cstring_is_valid(cstr))
    return -1;

/* Convert the UTF-8 string to UTF-32 (UCS4) which is the format
   * mk_wcwidth() expects, and get the width of each character.
   * We don't need much error checking since the input is valid UTF-8. */
  while (*cstr)
    {
      apr_uint32_t ucs;
      int nbytes;
      int lead_mask;
      int w;
      int i;

if ((*cstr & 0x80) == 0)
        {
          nbytes = 1;
          lead_mask = 0x7f;
        }
      else if ((*cstr & 0xe0) == 0xc0)
        {
          nbytes = 2;
          lead_mask = 0x1f;
        }
      else if ((*cstr & 0xf0) == 0xe0)
        {
          nbytes = 3;
          lead_mask = 0x0f;
        }
      else if ((*cstr & 0xf8) == 0xf0)
        {
          nbytes = 4;
          lead_mask = 0x07;
        }
      else
        {
          /* RFC 3629 restricts UTF-8 to max 4 bytes per character. */
          return -1;
        }

/* Parse character data from leading byte. */
      ucs = (apr_uint32_t)(*cstr & lead_mask);

/* Parse character data from continuation bytes. */
      for (i = 1; i < nbytes; i++)
        {
          ucs <<= 6;
          ucs |= (cstr[i] & 0x3f);
        }

cstr += nbytes;

/* Determine the width of this character and add it to the total. */
      w = mk_wcwidth(ucs);
      if (w == -1)
        return -1;
      width += w;
    }

return width;
}

003 File Manager

Editing: utf_width.c

Upload File

Create Folder