* Lesser General Public License for more details.
*
* You should have received a copy of the GNU Lesser General Public
- * License along with this library; if not, write to the
- * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
- * Boston, MA 02111-1307, USA.
+ * License along with this library; if not, see <http://www.gnu.org/licenses/>.
*/
#include "config.h"
+#include <stdlib.h>
#include <stddef.h>
#include <string.h>
#include <locale.h>
-#include "glib.h"
+#include "gmem.h"
+#include "gstring.h"
+#include "gtestutils.h"
+#include "gtypes.h"
+#include "gunicode.h"
#include "gunichartables.h"
+#include "gmirroringtable.h"
+#include "gscripttable.h"
#include "gunicodeprivate.h"
+#ifdef G_OS_WIN32
+#include "gwin32.h"
+#endif
#define ATTR_TABLE(Page) (((Page) <= G_UNICODE_LAST_PAGE_PART1) \
? attr_table_part1[Page] \
: G_UNICODE_UNASSIGNED))
-#define ISDIGIT(Type) ((Type) == G_UNICODE_DECIMAL_NUMBER \
- || (Type) == G_UNICODE_LETTER_NUMBER \
- || (Type) == G_UNICODE_OTHER_NUMBER)
+#define IS(Type, Class) (((guint)1 << (Type)) & (Class))
+#define OR(Type, Rest) (((guint)1 << (Type)) | (Rest))
-#define ISALPHA(Type) ((Type) == G_UNICODE_LOWERCASE_LETTER \
- || (Type) == G_UNICODE_UPPERCASE_LETTER \
- || (Type) == G_UNICODE_TITLECASE_LETTER \
- || (Type) == G_UNICODE_MODIFIER_LETTER \
- || (Type) == G_UNICODE_OTHER_LETTER)
-#define ISMARK(Type) ((Type) == G_UNICODE_NON_SPACING_MARK || \
- (Type) == G_UNICODE_COMBINING_MARK || \
- (Type) == G_UNICODE_ENCLOSING_MARK)
-
+
+#define ISALPHA(Type) IS ((Type), \
+ OR (G_UNICODE_LOWERCASE_LETTER, \
+ OR (G_UNICODE_UPPERCASE_LETTER, \
+ OR (G_UNICODE_TITLECASE_LETTER, \
+ OR (G_UNICODE_MODIFIER_LETTER, \
+ OR (G_UNICODE_OTHER_LETTER, 0))))))
+
+#define ISALDIGIT(Type) IS ((Type), \
+ OR (G_UNICODE_DECIMAL_NUMBER, \
+ OR (G_UNICODE_LETTER_NUMBER, \
+ OR (G_UNICODE_OTHER_NUMBER, \
+ OR (G_UNICODE_LOWERCASE_LETTER, \
+ OR (G_UNICODE_UPPERCASE_LETTER, \
+ OR (G_UNICODE_TITLECASE_LETTER, \
+ OR (G_UNICODE_MODIFIER_LETTER, \
+ OR (G_UNICODE_OTHER_LETTER, 0)))))))))
+
+#define ISMARK(Type) IS ((Type), \
+ OR (G_UNICODE_NON_SPACING_MARK, \
+ OR (G_UNICODE_SPACING_MARK, \
+ OR (G_UNICODE_ENCLOSING_MARK, 0))))
+
+#define ISZEROWIDTHTYPE(Type) IS ((Type), \
+ OR (G_UNICODE_NON_SPACING_MARK, \
+ OR (G_UNICODE_ENCLOSING_MARK, \
+ OR (G_UNICODE_FORMAT, 0))))
/**
* g_unichar_isalnum:
gboolean
g_unichar_isalnum (gunichar c)
{
- int t = TYPE (c);
- return ISDIGIT (t) || ISALPHA (t);
+ return ISALDIGIT (TYPE (c)) ? TRUE : FALSE;
}
/**
gboolean
g_unichar_isalpha (gunichar c)
{
- int t = TYPE (c);
- return ISALPHA (t);
+ return ISALPHA (TYPE (c)) ? TRUE : FALSE;
}
gboolean
g_unichar_isgraph (gunichar c)
{
- int t = TYPE (c);
- return (t != G_UNICODE_CONTROL
- && t != G_UNICODE_FORMAT
- && t != G_UNICODE_UNASSIGNED
- && t != G_UNICODE_PRIVATE_USE
- && t != G_UNICODE_SURROGATE
- && t != G_UNICODE_SPACE_SEPARATOR);
+ return !IS (TYPE(c),
+ OR (G_UNICODE_CONTROL,
+ OR (G_UNICODE_FORMAT,
+ OR (G_UNICODE_UNASSIGNED,
+ OR (G_UNICODE_SURROGATE,
+ OR (G_UNICODE_SPACE_SEPARATOR,
+ 0))))));
}
/**
gboolean
g_unichar_isprint (gunichar c)
{
- int t = TYPE (c);
- return (t != G_UNICODE_CONTROL
- && t != G_UNICODE_FORMAT
- && t != G_UNICODE_UNASSIGNED
- && t != G_UNICODE_PRIVATE_USE
- && t != G_UNICODE_SURROGATE);
+ return !IS (TYPE(c),
+ OR (G_UNICODE_CONTROL,
+ OR (G_UNICODE_FORMAT,
+ OR (G_UNICODE_UNASSIGNED,
+ OR (G_UNICODE_SURROGATE,
+ 0)))));
}
/**
gboolean
g_unichar_ispunct (gunichar c)
{
- int t = TYPE (c);
- return (t == G_UNICODE_CONNECT_PUNCTUATION || t == G_UNICODE_DASH_PUNCTUATION
- || t == G_UNICODE_CLOSE_PUNCTUATION || t == G_UNICODE_FINAL_PUNCTUATION
- || t == G_UNICODE_INITIAL_PUNCTUATION || t == G_UNICODE_OTHER_PUNCTUATION
- || t == G_UNICODE_OPEN_PUNCTUATION || t == G_UNICODE_CURRENCY_SYMBOL
- || t == G_UNICODE_MODIFIER_SYMBOL || t == G_UNICODE_MATH_SYMBOL
- || t == G_UNICODE_OTHER_SYMBOL);
+ return IS (TYPE(c),
+ OR (G_UNICODE_CONNECT_PUNCTUATION,
+ OR (G_UNICODE_DASH_PUNCTUATION,
+ OR (G_UNICODE_CLOSE_PUNCTUATION,
+ OR (G_UNICODE_FINAL_PUNCTUATION,
+ OR (G_UNICODE_INITIAL_PUNCTUATION,
+ OR (G_UNICODE_OTHER_PUNCTUATION,
+ OR (G_UNICODE_OPEN_PUNCTUATION,
+ OR (G_UNICODE_CURRENCY_SYMBOL,
+ OR (G_UNICODE_MODIFIER_SYMBOL,
+ OR (G_UNICODE_MATH_SYMBOL,
+ OR (G_UNICODE_OTHER_SYMBOL,
+ 0)))))))))))) ? TRUE : FALSE;
}
/**
* Pango or equivalent to get word breaking right, the algorithm
* is fairly complex.)
*
- * Return value: %TRUE if @c is a punctuation character
+ * Return value: %TRUE if @c is a space character
**/
gboolean
g_unichar_isspace (gunichar c)
default:
{
- int t = TYPE (c);
- return (t == G_UNICODE_SPACE_SEPARATOR || t == G_UNICODE_LINE_SEPARATOR
- || t == G_UNICODE_PARAGRAPH_SEPARATOR);
+ return IS (TYPE(c),
+ OR (G_UNICODE_SPACE_SEPARATOR,
+ OR (G_UNICODE_LINE_SEPARATOR,
+ OR (G_UNICODE_PARAGRAPH_SEPARATOR,
+ 0)))) ? TRUE : FALSE;
}
break;
}
}
/**
+ * g_unichar_ismark:
+ * @c: a Unicode character
+ *
+ * Determines whether a character is a mark (non-spacing mark,
+ * combining mark, or enclosing mark in Unicode speak).
+ * Given some UTF-8 text, obtain a character value
+ * with g_utf8_get_char().
+ *
+ * Note: in most cases where isalpha characters are allowed,
+ * ismark characters should be allowed to as they are essential
+ * for writing most European languages as well as many non-Latin
+ * scripts.
+ *
+ * Return value: %TRUE if @c is a mark character
+ *
+ * Since: 2.14
+ **/
+gboolean
+g_unichar_ismark (gunichar c)
+{
+ return ISMARK (TYPE (c));
+}
+
+/**
* g_unichar_isupper:
* @c: a Unicode character
*
unsigned int i;
for (i = 0; i < G_N_ELEMENTS (title_table); ++i)
if (title_table[i][0] == c)
- return 1;
- return 0;
+ return TRUE;
+ return FALSE;
}
/**
gboolean
g_unichar_isxdigit (gunichar c)
{
- int t = TYPE (c);
return ((c >= 'a' && c <= 'f')
|| (c >= 'A' && c <= 'F')
- || ISDIGIT (t));
+ || (TYPE (c) == G_UNICODE_DECIMAL_NUMBER));
}
/**
gboolean
g_unichar_isdefined (gunichar c)
{
- int t = TYPE (c);
- return t != G_UNICODE_UNASSIGNED;
+ return !IS (TYPE(c),
+ OR (G_UNICODE_UNASSIGNED,
+ OR (G_UNICODE_SURROGATE,
+ 0)));
+}
+
+/**
+ * g_unichar_iszerowidth:
+ * @c: a Unicode character
+ *
+ * Determines if a given character typically takes zero width when rendered.
+ * The return value is %TRUE for all non-spacing and enclosing marks
+ * (e.g., combining accents), format characters, zero-width
+ * space, but not U+00AD SOFT HYPHEN.
+ *
+ * A typical use of this function is with one of g_unichar_iswide() or
+ * g_unichar_iswide_cjk() to determine the number of cells a string occupies
+ * when displayed on a grid display (terminals). However, note that not all
+ * terminals support zero-width rendering of zero-width marks.
+ *
+ * Return value: %TRUE if the character has zero width
+ *
+ * Since: 2.14
+ **/
+gboolean
+g_unichar_iszerowidth (gunichar c)
+{
+ if (G_UNLIKELY (c == 0x00AD))
+ return FALSE;
+
+ if (G_UNLIKELY (ISZEROWIDTHTYPE (TYPE (c))))
+ return TRUE;
+
+ if (G_UNLIKELY ((c >= 0x1160 && c < 0x1200) ||
+ c == 0x200B))
+ return TRUE;
+
+ return FALSE;
+}
+
+struct Interval
+{
+ gunichar start, end;
+};
+
+static int
+interval_compare (const void *key, const void *elt)
+{
+ gunichar c = GPOINTER_TO_UINT (key);
+ struct Interval *interval = (struct Interval *)elt;
+
+ if (c < interval->start)
+ return -1;
+ if (c > interval->end)
+ return +1;
+
+ return 0;
}
+
+/*
+ * NOTE:
+ *
+ * The tables for g_unichar_iswide() and g_unichar_iswide_cjk() are
+ * generated from the Unicode Character Database's file
+ * extracted/DerivedEastAsianWidth.txt using the gen-iswide-table.py
+ * in this way:
+ *
+ * ./gen-iswide-table.py < path/to/ucd/extracted/DerivedEastAsianWidth.txt | fmt
+ *
+ * Last update for Unicode 6.0.
+ */
+
/**
* g_unichar_iswide:
* @c: a Unicode character
*
* Return value: %TRUE if the character is wide
**/
-/* This function stolen from Markus Kuhn <Markus.Kuhn@cl.cam.ac.uk>. */
gboolean
g_unichar_iswide (gunichar c)
{
- if (c < 0x1100)
- return FALSE;
+ /* See NOTE earlier for how to update this table. */
+ static const struct Interval wide[] = {
+ {0x1100, 0x115F}, {0x2329, 0x232A}, {0x2E80, 0x2E99}, {0x2E9B, 0x2EF3},
+ {0x2F00, 0x2FD5}, {0x2FF0, 0x2FFB}, {0x3000, 0x303E}, {0x3041, 0x3096},
+ {0x3099, 0x30FF}, {0x3105, 0x312D}, {0x3131, 0x318E}, {0x3190, 0x31BA},
+ {0x31C0, 0x31E3}, {0x31F0, 0x321E}, {0x3220, 0x3247}, {0x3250, 0x32FE},
+ {0x3300, 0x4DBF}, {0x4E00, 0xA48C}, {0xA490, 0xA4C6}, {0xA960, 0xA97C},
+ {0xAC00, 0xD7A3}, {0xF900, 0xFAFF}, {0xFE10, 0xFE19}, {0xFE30, 0xFE52},
+ {0xFE54, 0xFE66}, {0xFE68, 0xFE6B}, {0xFF01, 0xFF60}, {0xFFE0, 0xFFE6},
+ {0x1B000, 0x1B001}, {0x1F200, 0x1F202}, {0x1F210, 0x1F23A}, {0x1F240,
+ 0x1F248}, {0x1F250, 0x1F251}, {0x20000, 0x2FFFD}, {0x30000, 0x3FFFD}
+ };
+
+ if (bsearch (GUINT_TO_POINTER (c), wide, G_N_ELEMENTS (wide), sizeof wide[0],
+ interval_compare))
+ return TRUE;
+
+ return FALSE;
+}
+
+
+/**
+ * g_unichar_iswide_cjk:
+ * @c: a Unicode character
+ *
+ * Determines if a character is typically rendered in a double-width
+ * cell under legacy East Asian locales. If a character is wide according to
+ * g_unichar_iswide(), then it is also reported wide with this function, but
+ * the converse is not necessarily true. See the
+ * [Unicode Standard Annex #11](http://www.unicode.org/reports/tr11/)
+ * for details.
+ *
+ * If a character passes the g_unichar_iswide() test then it will also pass
+ * this test, but not the other way around. Note that some characters may
+ * pas both this test and g_unichar_iszerowidth().
+ *
+ * Return value: %TRUE if the character is wide in legacy East Asian locales
+ *
+ * Since: 2.12
+ */
+gboolean
+g_unichar_iswide_cjk (gunichar c)
+{
+ /* See NOTE earlier for how to update this table. */
+ static const struct Interval ambiguous[] = {
+ {0x00A1, 0x00A1}, {0x00A4, 0x00A4}, {0x00A7, 0x00A8}, {0x00AA, 0x00AA},
+ {0x00AD, 0x00AE}, {0x00B0, 0x00B4}, {0x00B6, 0x00BA}, {0x00BC, 0x00BF},
+ {0x00C6, 0x00C6}, {0x00D0, 0x00D0}, {0x00D7, 0x00D8}, {0x00DE, 0x00E1},
+ {0x00E6, 0x00E6}, {0x00E8, 0x00EA}, {0x00EC, 0x00ED}, {0x00F0, 0x00F0},
+ {0x00F2, 0x00F3}, {0x00F7, 0x00FA}, {0x00FC, 0x00FC}, {0x00FE, 0x00FE},
+ {0x0101, 0x0101}, {0x0111, 0x0111}, {0x0113, 0x0113}, {0x011B, 0x011B},
+ {0x0126, 0x0127}, {0x012B, 0x012B}, {0x0131, 0x0133}, {0x0138, 0x0138},
+ {0x013F, 0x0142}, {0x0144, 0x0144}, {0x0148, 0x014B}, {0x014D, 0x014D},
+ {0x0152, 0x0153}, {0x0166, 0x0167}, {0x016B, 0x016B}, {0x01CE, 0x01CE},
+ {0x01D0, 0x01D0}, {0x01D2, 0x01D2}, {0x01D4, 0x01D4}, {0x01D6, 0x01D6},
+ {0x01D8, 0x01D8}, {0x01DA, 0x01DA}, {0x01DC, 0x01DC}, {0x0251, 0x0251},
+ {0x0261, 0x0261}, {0x02C4, 0x02C4}, {0x02C7, 0x02C7}, {0x02C9, 0x02CB},
+ {0x02CD, 0x02CD}, {0x02D0, 0x02D0}, {0x02D8, 0x02DB}, {0x02DD, 0x02DD},
+ {0x02DF, 0x02DF}, {0x0300, 0x036F}, {0x0391, 0x03A1}, {0x03A3, 0x03A9},
+ {0x03B1, 0x03C1}, {0x03C3, 0x03C9}, {0x0401, 0x0401}, {0x0410, 0x044F},
+ {0x0451, 0x0451}, {0x2010, 0x2010}, {0x2013, 0x2016}, {0x2018, 0x2019},
+ {0x201C, 0x201D}, {0x2020, 0x2022}, {0x2024, 0x2027}, {0x2030, 0x2030},
+ {0x2032, 0x2033}, {0x2035, 0x2035}, {0x203B, 0x203B}, {0x203E, 0x203E},
+ {0x2074, 0x2074}, {0x207F, 0x207F}, {0x2081, 0x2084}, {0x20AC, 0x20AC},
+ {0x2103, 0x2103}, {0x2105, 0x2105}, {0x2109, 0x2109}, {0x2113, 0x2113},
+ {0x2116, 0x2116}, {0x2121, 0x2122}, {0x2126, 0x2126}, {0x212B, 0x212B},
+ {0x2153, 0x2154}, {0x215B, 0x215E}, {0x2160, 0x216B}, {0x2170, 0x2179},
+ {0x2189, 0x2189}, {0x2190, 0x2199}, {0x21B8, 0x21B9}, {0x21D2, 0x21D2},
+ {0x21D4, 0x21D4}, {0x21E7, 0x21E7}, {0x2200, 0x2200}, {0x2202, 0x2203},
+ {0x2207, 0x2208}, {0x220B, 0x220B}, {0x220F, 0x220F}, {0x2211, 0x2211},
+ {0x2215, 0x2215}, {0x221A, 0x221A}, {0x221D, 0x2220}, {0x2223, 0x2223},
+ {0x2225, 0x2225}, {0x2227, 0x222C}, {0x222E, 0x222E}, {0x2234, 0x2237},
+ {0x223C, 0x223D}, {0x2248, 0x2248}, {0x224C, 0x224C}, {0x2252, 0x2252},
+ {0x2260, 0x2261}, {0x2264, 0x2267}, {0x226A, 0x226B}, {0x226E, 0x226F},
+ {0x2282, 0x2283}, {0x2286, 0x2287}, {0x2295, 0x2295}, {0x2299, 0x2299},
+ {0x22A5, 0x22A5}, {0x22BF, 0x22BF}, {0x2312, 0x2312}, {0x2460, 0x24E9},
+ {0x24EB, 0x254B}, {0x2550, 0x2573}, {0x2580, 0x258F}, {0x2592, 0x2595},
+ {0x25A0, 0x25A1}, {0x25A3, 0x25A9}, {0x25B2, 0x25B3}, {0x25B6, 0x25B7},
+ {0x25BC, 0x25BD}, {0x25C0, 0x25C1}, {0x25C6, 0x25C8}, {0x25CB, 0x25CB},
+ {0x25CE, 0x25D1}, {0x25E2, 0x25E5}, {0x25EF, 0x25EF}, {0x2605, 0x2606},
+ {0x2609, 0x2609}, {0x260E, 0x260F}, {0x2614, 0x2615}, {0x261C, 0x261C},
+ {0x261E, 0x261E}, {0x2640, 0x2640}, {0x2642, 0x2642}, {0x2660, 0x2661},
+ {0x2663, 0x2665}, {0x2667, 0x266A}, {0x266C, 0x266D}, {0x266F, 0x266F},
+ {0x269E, 0x269F}, {0x26BE, 0x26BF}, {0x26C4, 0x26CD}, {0x26CF, 0x26E1},
+ {0x26E3, 0x26E3}, {0x26E8, 0x26FF}, {0x273D, 0x273D}, {0x2757, 0x2757},
+ {0x2776, 0x277F}, {0x2B55, 0x2B59}, {0x3248, 0x324F}, {0xE000, 0xF8FF},
+ {0xFE00, 0xFE0F}, {0xFFFD, 0xFFFD}, {0x1F100, 0x1F10A}, {0x1F110,
+ 0x1F12D}, {0x1F130, 0x1F169}, {0x1F170, 0x1F19A}, {0xE0100, 0xE01EF},
+ {0xF0000, 0xFFFFD}, {0x100000, 0x10FFFD}
+ };
+
+ if (g_unichar_iswide (c))
+ return TRUE;
+
+ if (bsearch (GUINT_TO_POINTER (c), ambiguous, G_N_ELEMENTS (ambiguous), sizeof ambiguous[0],
+ interval_compare))
+ return TRUE;
- return (c <= 0x115f /* Hangul Jamo init. consonants */
- || c == 0x2329 || c == 0x232a /* angle brackets */
- || (c >= 0x2e80 && c <= 0xa4cf && (c < 0x302a || c > 0x302f)
- && c != 0x303f && c != 0x3099 && c!= 0x309a) /* CJK ... Yi */
- || (c >= 0xac00 && c <= 0xd7a3) /* Hangul Syllables */
- || (c >= 0xf900 && c <= 0xfaff) /* CJK Compatibility Ideographs */
- || (c >= 0xfe30 && c <= 0xfe6f) /* CJK Compatibility Forms */
- || (c >= 0xff00 && c <= 0xff60) /* Fullwidth Forms */
- || (c >= 0xffe0 && c <= 0xffe6) /* Fullwidth Forms */
- || (c >= 0x20000 && c <= 0x2fffd) /* CJK extra stuff */
- || (c >= 0x30000 && c <= 0x3fffd));
+ return FALSE;
}
+
/**
* g_unichar_toupper:
* @c: a Unicode character
if (val >= 0x1000000)
{
const gchar *p = special_case_table + val - 0x1000000;
- return g_utf8_get_char (p);
+ val = g_utf8_get_char (p);
}
- else
- return val ? val : c;
+ /* Some lowercase letters, e.g., U+000AA, FEMININE ORDINAL INDICATOR,
+ * do not have an uppercase equivalent, in which case val will be
+ * zero.
+ */
+ return val ? val : c;
}
else if (t == G_UNICODE_TITLECASE_LETTER)
{
for (i = 0; i < G_N_ELEMENTS (title_table); ++i)
{
if (title_table[i][0] == c)
- return title_table[i][1];
+ return title_table[i][1] ? title_table[i][1] : c;
}
}
return c;
return g_utf8_get_char (p);
}
else
- return val ? val : c;
+ {
+ /* Not all uppercase letters are guaranteed to have a lowercase
+ * equivalent. If this is the case, val will be zero. */
+ return val ? val : c;
+ }
}
else if (t == G_UNICODE_TITLECASE_LETTER)
{
|| title_table[i][2] == c)
return title_table[i][0];
}
- return (TYPE (c) == G_UNICODE_LOWERCASE_LETTER
- ? ATTTABLE (c >> 8, c & 0xff)
- : c);
+
+ if (TYPE (c) == G_UNICODE_LOWERCASE_LETTER)
+ return g_unichar_toupper (c);
+
+ return c;
}
/**
static LocaleType
get_locale_type (void)
{
+#ifdef G_OS_WIN32
+ char *tem = g_win32_getlocale ();
+ char locale[2];
+
+ locale[0] = tem[0];
+ locale[1] = tem[1];
+ g_free (tem);
+#else
const char *locale = setlocale (LC_CTYPE, NULL);
+ if (locale == NULL)
+ return LOCALE_NORMAL;
+#endif
+
switch (locale[0])
{
case 'a':
while (*p)
{
gunichar c = g_utf8_get_char (p);
- int t = TYPE(c);
- if (ISMARK(t))
+ if (ISMARK (TYPE (c)))
{
if (!remove_dot || c != 0x307 /* COMBINING DOT ABOVE */)
len += g_unichar_to_utf8 (c, out_buffer ? out_buffer + len : NULL);
* which could simplify this considerably.
*/
gsize decomp_len, i;
- gunichar *decomp;
+ gunichar decomp[G_UNICHAR_MAX_DECOMPOSITION_LENGTH];
- decomp = g_unicode_canonical_decomposition (c, &decomp_len);
+ decomp_len = g_unichar_fully_decompose (c, FALSE, decomp, G_N_ELEMENTS (decomp));
for (i=0; i < decomp_len; i++)
{
if (decomp[i] != 0x307 /* COMBINING DOT ABOVE */)
len += g_unichar_to_utf8 (g_unichar_toupper (decomp[i]), out_buffer ? out_buffer + len : NULL);
}
- g_free (decomp);
len += output_marks (&p, out_buffer ? out_buffer + len : NULL, TRUE);
continue;
}
- if (!ISMARK(t))
+ if (!ISMARK (t))
last_was_i = FALSE;
}
}
-
+
if (locale_type == LOCALE_TURKIC && c == 'i')
{
/* i => LATIN CAPITAL LETTER I WITH DOT ABOVE */
/* And output as GREEK CAPITAL LETTER IOTA */
len += g_unichar_to_utf8 (0x399, out_buffer ? out_buffer + len : NULL);
}
- else if (t == G_UNICODE_LOWERCASE_LETTER || t == G_UNICODE_TITLECASE_LETTER)
+ else if (IS (t,
+ OR (G_UNICODE_LOWERCASE_LETTER,
+ OR (G_UNICODE_TITLECASE_LETTER,
+ 0))))
{
val = ATTTABLE (c >> 8, c & 0xff);
for (i = 0; i < G_N_ELEMENTS (title_table); ++i)
{
if (title_table[i][0] == c)
- val = title_table[i][1];
+ {
+ val = title_table[i][1];
+ break;
+ }
}
}
- len += g_unichar_to_utf8 (val, out_buffer ? out_buffer + len : NULL);
+ /* Some lowercase letters, e.g., U+000AA, FEMININE ORDINAL INDICATOR,
+ * do not have an uppercase equivalent, in which case val will be
+ * zero. */
+ len += g_unichar_to_utf8 (val ? val : c, out_buffer ? out_buffer + len : NULL);
}
}
else
while (*p)
{
- combining_class = _g_unichar_combining_class (g_utf8_get_char (p));
+ combining_class = g_unichar_combining_class (g_utf8_get_char (p));
if (combining_class == 230)
return TRUE;
else if (combining_class == 0)
* sigma, but I don't think that occurs in real text.
* The test here matches that in ICU.
*/
- if (ISALPHA(next_type)) /* Lu,Ll,Lt,Lm,Lo */
+ if (ISALPHA (next_type)) /* Lu,Ll,Lt,Lm,Lo */
val = 0x3c3; /* GREEK SMALL SIGMA */
else
val = 0x3c2; /* GREEK SMALL FINAL SIGMA */
len += g_unichar_to_utf8 (val, out_buffer ? out_buffer + len : NULL);
}
- else if (t == G_UNICODE_UPPERCASE_LETTER || t == G_UNICODE_TITLECASE_LETTER)
+ else if (IS (t,
+ OR (G_UNICODE_UPPERCASE_LETTER,
+ OR (G_UNICODE_TITLECASE_LETTER,
+ 0))))
{
val = ATTTABLE (c >> 8, c & 0xff);
for (i = 0; i < G_N_ELEMENTS (title_table); ++i)
{
if (title_table[i][0] == c)
- val = title_table[i][2];
+ {
+ val = title_table[i][2];
+ break;
+ }
}
}
- len += g_unichar_to_utf8 (val, out_buffer ? out_buffer + len : NULL);
+ /* Not all uppercase letters are guaranteed to have a lowercase
+ * equivalent. If this is the case, val will be zero. */
+ len += g_unichar_to_utf8 (val ? val : c, out_buffer ? out_buffer + len : NULL);
}
}
else
/**
* g_unichar_get_mirror_char:
- * @ch: a unicode character
+ * @ch: a Unicode character
* @mirrored_ch: location to store the mirrored character
*
* In Unicode, some characters are <firstterm>mirrored</firstterm>. This
*
* If @ch has the Unicode mirrored property and there is another unicode
* character that typically has a glyph that is the mirror image of @ch's
- * glyph, puts that character in the address pointed to by @mirrored_ch.
+ * glyph and @mirrored_ch is set, it puts that character in the address
+ * pointed to by @mirrored_ch. Otherwise the original character is put.
*
- * Return value: %TRUE if @ch has a mirrored character and @mirrored_ch is
- * filled in, %FALSE otherwise
+ * Return value: %TRUE if @ch has a mirrored character, %FALSE otherwise
*
* Since: 2.4
**/
-/* This code is adapted from FriBidi (http://fribidi.sourceforge.net/).
- * FriBidi is: Copyright (C) 1999,2000 Dov Grobgeld, and
- * Copyright (C) 2001,2002 Behdad Esfahbod.
- */
gboolean
g_unichar_get_mirror_char (gunichar ch,
gunichar *mirrored_ch)
{
- gint pos, step, size;
gboolean found;
+ gunichar mirrored;
- size = G_N_ELEMENTS (bidi_mirroring_table);
- pos = step = (size / 2) + 1;
+ mirrored = GLIB_GET_MIRRORING(ch);
- while (step > 1)
- {
- gunichar cmp_ch = bidi_mirroring_table[pos].ch;
- step = (step + 1) / 2;
+ found = ch != mirrored;
+ if (mirrored_ch)
+ *mirrored_ch = mirrored;
- if (cmp_ch < ch)
- {
- pos += step;
- if (pos > size - 1)
- pos = size - 1;
- }
- else if (cmp_ch > ch)
- {
- pos -= step;
- if (pos < 0)
- pos = 0;
- }
+ return found;
+
+}
+
+#define G_SCRIPT_TABLE_MIDPOINT (G_N_ELEMENTS (g_script_table) / 2)
+
+static inline GUnicodeScript
+g_unichar_get_script_bsearch (gunichar ch)
+{
+ int lower = 0;
+ int upper = G_N_ELEMENTS (g_script_table) - 1;
+ static int saved_mid = G_SCRIPT_TABLE_MIDPOINT;
+ int mid = saved_mid;
+
+
+ do
+ {
+ if (ch < g_script_table[mid].start)
+ upper = mid - 1;
+ else if (ch >= g_script_table[mid].start + g_script_table[mid].chars)
+ lower = mid + 1;
else
- break;
+ return g_script_table[saved_mid = mid].script;
+
+ mid = (lower + upper) / 2;
}
- found = bidi_mirroring_table[pos].ch == ch;
- if (mirrored_ch)
- *mirrored_ch = found ? bidi_mirroring_table[pos].mirrored_ch : ch;
+ while (lower <= upper);
- return found;
+ return G_UNICODE_SCRIPT_UNKNOWN;
+}
+
+/**
+ * g_unichar_get_script:
+ * @ch: a Unicode character
+ *
+ * Looks up the #GUnicodeScript for a particular character (as defined
+ * by Unicode Standard Annex \#24). No check is made for @ch being a
+ * valid Unicode character; if you pass in invalid character, the
+ * result is undefined.
+ *
+ * This function is equivalent to pango_script_for_unichar() and the
+ * two are interchangeable.
+ *
+ * Return value: the #GUnicodeScript for the character.
+ *
+ * Since: 2.14
+ */
+GUnicodeScript
+g_unichar_get_script (gunichar ch)
+{
+ if (ch < G_EASY_SCRIPTS_RANGE)
+ return g_script_easy_table[ch];
+ else
+ return g_unichar_get_script_bsearch (ch);
+}
+
+
+/* http://unicode.org/iso15924/ */
+static const guint32 iso15924_tags[] =
+{
+#define PACK(a,b,c,d) ((guint32)((((guint8)(a))<<24)|(((guint8)(b))<<16)|(((guint8)(c))<<8)|((guint8)(d))))
+
+ PACK ('Z','y','y','y'), /* G_UNICODE_SCRIPT_COMMON */
+ PACK ('Z','i','n','h'), /* G_UNICODE_SCRIPT_INHERITED */
+ PACK ('A','r','a','b'), /* G_UNICODE_SCRIPT_ARABIC */
+ PACK ('A','r','m','n'), /* G_UNICODE_SCRIPT_ARMENIAN */
+ PACK ('B','e','n','g'), /* G_UNICODE_SCRIPT_BENGALI */
+ PACK ('B','o','p','o'), /* G_UNICODE_SCRIPT_BOPOMOFO */
+ PACK ('C','h','e','r'), /* G_UNICODE_SCRIPT_CHEROKEE */
+ PACK ('C','o','p','t'), /* G_UNICODE_SCRIPT_COPTIC */
+ PACK ('C','y','r','l'), /* G_UNICODE_SCRIPT_CYRILLIC */
+ PACK ('D','s','r','t'), /* G_UNICODE_SCRIPT_DESERET */
+ PACK ('D','e','v','a'), /* G_UNICODE_SCRIPT_DEVANAGARI */
+ PACK ('E','t','h','i'), /* G_UNICODE_SCRIPT_ETHIOPIC */
+ PACK ('G','e','o','r'), /* G_UNICODE_SCRIPT_GEORGIAN */
+ PACK ('G','o','t','h'), /* G_UNICODE_SCRIPT_GOTHIC */
+ PACK ('G','r','e','k'), /* G_UNICODE_SCRIPT_GREEK */
+ PACK ('G','u','j','r'), /* G_UNICODE_SCRIPT_GUJARATI */
+ PACK ('G','u','r','u'), /* G_UNICODE_SCRIPT_GURMUKHI */
+ PACK ('H','a','n','i'), /* G_UNICODE_SCRIPT_HAN */
+ PACK ('H','a','n','g'), /* G_UNICODE_SCRIPT_HANGUL */
+ PACK ('H','e','b','r'), /* G_UNICODE_SCRIPT_HEBREW */
+ PACK ('H','i','r','a'), /* G_UNICODE_SCRIPT_HIRAGANA */
+ PACK ('K','n','d','a'), /* G_UNICODE_SCRIPT_KANNADA */
+ PACK ('K','a','n','a'), /* G_UNICODE_SCRIPT_KATAKANA */
+ PACK ('K','h','m','r'), /* G_UNICODE_SCRIPT_KHMER */
+ PACK ('L','a','o','o'), /* G_UNICODE_SCRIPT_LAO */
+ PACK ('L','a','t','n'), /* G_UNICODE_SCRIPT_LATIN */
+ PACK ('M','l','y','m'), /* G_UNICODE_SCRIPT_MALAYALAM */
+ PACK ('M','o','n','g'), /* G_UNICODE_SCRIPT_MONGOLIAN */
+ PACK ('M','y','m','r'), /* G_UNICODE_SCRIPT_MYANMAR */
+ PACK ('O','g','a','m'), /* G_UNICODE_SCRIPT_OGHAM */
+ PACK ('I','t','a','l'), /* G_UNICODE_SCRIPT_OLD_ITALIC */
+ PACK ('O','r','y','a'), /* G_UNICODE_SCRIPT_ORIYA */
+ PACK ('R','u','n','r'), /* G_UNICODE_SCRIPT_RUNIC */
+ PACK ('S','i','n','h'), /* G_UNICODE_SCRIPT_SINHALA */
+ PACK ('S','y','r','c'), /* G_UNICODE_SCRIPT_SYRIAC */
+ PACK ('T','a','m','l'), /* G_UNICODE_SCRIPT_TAMIL */
+ PACK ('T','e','l','u'), /* G_UNICODE_SCRIPT_TELUGU */
+ PACK ('T','h','a','a'), /* G_UNICODE_SCRIPT_THAANA */
+ PACK ('T','h','a','i'), /* G_UNICODE_SCRIPT_THAI */
+ PACK ('T','i','b','t'), /* G_UNICODE_SCRIPT_TIBETAN */
+ PACK ('C','a','n','s'), /* G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL */
+ PACK ('Y','i','i','i'), /* G_UNICODE_SCRIPT_YI */
+ PACK ('T','g','l','g'), /* G_UNICODE_SCRIPT_TAGALOG */
+ PACK ('H','a','n','o'), /* G_UNICODE_SCRIPT_HANUNOO */
+ PACK ('B','u','h','d'), /* G_UNICODE_SCRIPT_BUHID */
+ PACK ('T','a','g','b'), /* G_UNICODE_SCRIPT_TAGBANWA */
+
+ /* Unicode-4.0 additions */
+ PACK ('B','r','a','i'), /* G_UNICODE_SCRIPT_BRAILLE */
+ PACK ('C','p','r','t'), /* G_UNICODE_SCRIPT_CYPRIOT */
+ PACK ('L','i','m','b'), /* G_UNICODE_SCRIPT_LIMBU */
+ PACK ('O','s','m','a'), /* G_UNICODE_SCRIPT_OSMANYA */
+ PACK ('S','h','a','w'), /* G_UNICODE_SCRIPT_SHAVIAN */
+ PACK ('L','i','n','b'), /* G_UNICODE_SCRIPT_LINEAR_B */
+ PACK ('T','a','l','e'), /* G_UNICODE_SCRIPT_TAI_LE */
+ PACK ('U','g','a','r'), /* G_UNICODE_SCRIPT_UGARITIC */
+
+ /* Unicode-4.1 additions */
+ PACK ('T','a','l','u'), /* G_UNICODE_SCRIPT_NEW_TAI_LUE */
+ PACK ('B','u','g','i'), /* G_UNICODE_SCRIPT_BUGINESE */
+ PACK ('G','l','a','g'), /* G_UNICODE_SCRIPT_GLAGOLITIC */
+ PACK ('T','f','n','g'), /* G_UNICODE_SCRIPT_TIFINAGH */
+ PACK ('S','y','l','o'), /* G_UNICODE_SCRIPT_SYLOTI_NAGRI */
+ PACK ('X','p','e','o'), /* G_UNICODE_SCRIPT_OLD_PERSIAN */
+ PACK ('K','h','a','r'), /* G_UNICODE_SCRIPT_KHAROSHTHI */
+
+ /* Unicode-5.0 additions */
+ PACK ('Z','z','z','z'), /* G_UNICODE_SCRIPT_UNKNOWN */
+ PACK ('B','a','l','i'), /* G_UNICODE_SCRIPT_BALINESE */
+ PACK ('X','s','u','x'), /* G_UNICODE_SCRIPT_CUNEIFORM */
+ PACK ('P','h','n','x'), /* G_UNICODE_SCRIPT_PHOENICIAN */
+ PACK ('P','h','a','g'), /* G_UNICODE_SCRIPT_PHAGS_PA */
+ PACK ('N','k','o','o'), /* G_UNICODE_SCRIPT_NKO */
+
+ /* Unicode-5.1 additions */
+ PACK ('K','a','l','i'), /* G_UNICODE_SCRIPT_KAYAH_LI */
+ PACK ('L','e','p','c'), /* G_UNICODE_SCRIPT_LEPCHA */
+ PACK ('R','j','n','g'), /* G_UNICODE_SCRIPT_REJANG */
+ PACK ('S','u','n','d'), /* G_UNICODE_SCRIPT_SUNDANESE */
+ PACK ('S','a','u','r'), /* G_UNICODE_SCRIPT_SAURASHTRA */
+ PACK ('C','h','a','m'), /* G_UNICODE_SCRIPT_CHAM */
+ PACK ('O','l','c','k'), /* G_UNICODE_SCRIPT_OL_CHIKI */
+ PACK ('V','a','i','i'), /* G_UNICODE_SCRIPT_VAI */
+ PACK ('C','a','r','i'), /* G_UNICODE_SCRIPT_CARIAN */
+ PACK ('L','y','c','i'), /* G_UNICODE_SCRIPT_LYCIAN */
+ PACK ('L','y','d','i'), /* G_UNICODE_SCRIPT_LYDIAN */
+
+ /* Unicode-5.2 additions */
+ PACK ('A','v','s','t'), /* G_UNICODE_SCRIPT_AVESTAN */
+ PACK ('B','a','m','u'), /* G_UNICODE_SCRIPT_BAMUM */
+ PACK ('E','g','y','p'), /* G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS */
+ PACK ('A','r','m','i'), /* G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC */
+ PACK ('P','h','l','i'), /* G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI */
+ PACK ('P','r','t','i'), /* G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN */
+ PACK ('J','a','v','a'), /* G_UNICODE_SCRIPT_JAVANESE */
+ PACK ('K','t','h','i'), /* G_UNICODE_SCRIPT_KAITHI */
+ PACK ('L','i','s','u'), /* G_UNICODE_SCRIPT_LISU */
+ PACK ('M','t','e','i'), /* G_UNICODE_SCRIPT_MEETEI_MAYEK */
+ PACK ('S','a','r','b'), /* G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN */
+ PACK ('O','r','k','h'), /* G_UNICODE_SCRIPT_OLD_TURKIC */
+ PACK ('S','a','m','r'), /* G_UNICODE_SCRIPT_SAMARITAN */
+ PACK ('L','a','n','a'), /* G_UNICODE_SCRIPT_TAI_THAM */
+ PACK ('T','a','v','t'), /* G_UNICODE_SCRIPT_TAI_VIET */
+
+ /* Unicode-6.0 additions */
+ PACK ('B','a','t','k'), /* G_UNICODE_SCRIPT_BATAK */
+ PACK ('B','r','a','h'), /* G_UNICODE_SCRIPT_BRAHMI */
+ PACK ('M','a','n','d'), /* G_UNICODE_SCRIPT_MANDAIC */
+
+ /* Unicode-6.1 additions */
+ PACK ('C','a','k','m'), /* G_UNICODE_SCRIPT_CHAKMA */
+ PACK ('M','e','r','c'), /* G_UNICODE_SCRIPT_MEROITIC_CURSIVE */
+ PACK ('M','e','r','o'), /* G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS */
+ PACK ('P','l','r','d'), /* G_UNICODE_SCRIPT_MIAO */
+ PACK ('S','h','r','d'), /* G_UNICODE_SCRIPT_SHARADA */
+ PACK ('S','o','r','a'), /* G_UNICODE_SCRIPT_SORA_SOMPENG */
+ PACK ('T','a','k','r'), /* G_UNICODE_SCRIPT_TAKRI */
+
+#undef PACK
+};
+
+/**
+ * g_unicode_script_to_iso15924:
+ * @script: a Unicode script
+ *
+ * Looks up the ISO 15924 code for @script. ISO 15924 assigns four-letter
+ * codes to scripts. For example, the code for Arabic is 'Arab'. The
+ * four letter codes are encoded as a @guint32 by this function in a
+ * big-endian fashion. That is, the code returned for Arabic is
+ * 0x41726162 (0x41 is ASCII code for 'A', 0x72 is ASCII code for 'r', etc).
+ *
+ * See
+ * [Codes for the representation of names of scripts](http://unicode.org/iso15924/codelists.html)
+ * for details.
+ *
+ * Return value: the ISO 15924 code for @script, encoded as an integer,
+ * of zero if @script is %G_UNICODE_SCRIPT_INVALID_CODE or
+ * ISO 15924 code 'Zzzz' (script code for UNKNOWN) if @script is not understood.
+ *
+ * Since: 2.30
+ */
+guint32
+g_unicode_script_to_iso15924 (GUnicodeScript script)
+{
+ if (G_UNLIKELY (script == G_UNICODE_SCRIPT_INVALID_CODE))
+ return 0;
+
+ if (G_UNLIKELY (script < 0 || script >= (int) G_N_ELEMENTS (iso15924_tags)))
+ return 0x5A7A7A7A;
+
+ return iso15924_tags[script];
+}
+
+/**
+ * g_unicode_script_from_iso15924:
+ * @iso15924: a Unicode script
+ *
+ * Looks up the Unicode script for @iso15924. ISO 15924 assigns four-letter
+ * codes to scripts. For example, the code for Arabic is 'Arab'.
+ * This function accepts four letter codes encoded as a @guint32 in a
+ * big-endian fashion. That is, the code expected for Arabic is
+ * 0x41726162 (0x41 is ASCII code for 'A', 0x72 is ASCII code for 'r', etc).
+ *
+ * See
+ * [Codes for the representation of names of scripts](http://unicode.org/iso15924/codelists.html)
+ * for details.
+ *
+ * Return value: the Unicode script for @iso15924, or
+ * of %G_UNICODE_SCRIPT_INVALID_CODE if @iso15924 is zero and
+ * %G_UNICODE_SCRIPT_UNKNOWN if @iso15924 is unknown.
+ *
+ * Since: 2.30
+ */
+GUnicodeScript
+g_unicode_script_from_iso15924 (guint32 iso15924)
+{
+ unsigned int i;
+
+ if (!iso15924)
+ return G_UNICODE_SCRIPT_INVALID_CODE;
+
+ for (i = 0; i < G_N_ELEMENTS (iso15924_tags); i++)
+ if (iso15924_tags[i] == iso15924)
+ return (GUnicodeScript) i;
+ return G_UNICODE_SCRIPT_UNKNOWN;
}
projects / platform / upstream / glib.git / blobdiff