* 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 <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"
-#include "galias.h"
+#ifdef G_OS_WIN32
+#include "gwin32.h"
+#endif
#define ATTR_TABLE(Page) (((Page) <= G_UNICODE_LAST_PAGE_PART1) \
? attr_table_part1[Page] \
#define ISMARK(Type) IS ((Type), \
OR (G_UNICODE_NON_SPACING_MARK, \
- OR (G_UNICODE_COMBINING_MARK, \
+ OR (G_UNICODE_SPACING_MARK, \
OR (G_UNICODE_ENCLOSING_MARK, 0))))
#define ISZEROWIDTHTYPE(Type) IS ((Type), \
* Given some UTF-8 text, obtain a character value
* with g_utf8_get_char().
*
- * Return value: %TRUE if @c is an alphanumeric character
+ * Returns: %TRUE if @c is an alphanumeric character
**/
gboolean
g_unichar_isalnum (gunichar c)
* Given some UTF-8 text, obtain a character value with
* g_utf8_get_char().
*
- * Return value: %TRUE if @c is an alphabetic character
+ * Returns: %TRUE if @c is an alphabetic character
**/
gboolean
g_unichar_isalpha (gunichar c)
* Given some UTF-8 text, obtain a character value with
* g_utf8_get_char().
*
- * Return value: %TRUE if @c is a control character
+ * Returns: %TRUE if @c is a control character
**/
gboolean
g_unichar_iscntrl (gunichar c)
* covers ASCII 0-9 and also digits in other languages/scripts. Given
* some UTF-8 text, obtain a character value with g_utf8_get_char().
*
- * Return value: %TRUE if @c is a digit
+ * Returns: %TRUE if @c is a digit
**/
gboolean
g_unichar_isdigit (gunichar c)
* spaces. Given some UTF-8 text, obtain a character value with
* g_utf8_get_char().
*
- * Return value: %TRUE if @c is printable unless it's a space
+ * Returns: %TRUE if @c is printable unless it's a space
**/
gboolean
g_unichar_isgraph (gunichar c)
OR (G_UNICODE_CONTROL,
OR (G_UNICODE_FORMAT,
OR (G_UNICODE_UNASSIGNED,
- OR (G_UNICODE_PRIVATE_USE,
OR (G_UNICODE_SURROGATE,
OR (G_UNICODE_SPACE_SEPARATOR,
- 0)))))));
+ 0))))));
}
/**
* Given some UTF-8 text, obtain a character value with
* g_utf8_get_char().
*
- * Return value: %TRUE if @c is a lowercase letter
+ * Returns: %TRUE if @c is a lowercase letter
**/
gboolean
g_unichar_islower (gunichar c)
* Given some UTF-8 text, obtain a character value with
* g_utf8_get_char().
*
- * Return value: %TRUE if @c is printable
+ * Returns: %TRUE if @c is printable
**/
gboolean
g_unichar_isprint (gunichar c)
OR (G_UNICODE_CONTROL,
OR (G_UNICODE_FORMAT,
OR (G_UNICODE_UNASSIGNED,
- OR (G_UNICODE_PRIVATE_USE,
OR (G_UNICODE_SURROGATE,
- 0))))));
+ 0)))));
}
/**
* Given some UTF-8 text, obtain a character value with
* g_utf8_get_char().
*
- * Return value: %TRUE if @c is a punctuation or symbol character
+ * Returns: %TRUE if @c is a punctuation or symbol character
**/
gboolean
g_unichar_ispunct (gunichar c)
* Pango or equivalent to get word breaking right, the algorithm
* is fairly complex.)
*
- * Return value: %TRUE if @c is a space character
+ * Returns: %TRUE if @c is a space character
**/
gboolean
g_unichar_isspace (gunichar c)
* for writing most European languages as well as many non-Latin
* scripts.
*
- * Return value: %TRUE if @c is a mark character
+ * Returns: %TRUE if @c is a mark character
*
* Since: 2.14
**/
*
* Determines if a character is uppercase.
*
- * Return value: %TRUE if @c is an uppercase character
+ * Returns: %TRUE if @c is an uppercase character
**/
gboolean
g_unichar_isupper (gunichar c)
* first letter is capitalized. The titlecase form of the DZ
* digraph is U+01F2 LATIN CAPITAL LETTTER D WITH SMALL LETTER Z.
*
- * Return value: %TRUE if the character is titlecase
+ * Returns: %TRUE if the character is titlecase
**/
gboolean
g_unichar_istitle (gunichar c)
*
* Determines if a character is a hexidecimal digit.
*
- * Return value: %TRUE if the character is a hexadecimal digit
+ * Returns: %TRUE if the character is a hexadecimal digit
**/
gboolean
g_unichar_isxdigit (gunichar c)
* Determines if a given character is assigned in the Unicode
* standard.
*
- * Return value: %TRUE if the character has an assigned value
+ * Returns: %TRUE if the character has an assigned value
**/
gboolean
g_unichar_isdefined (gunichar c)
{
- return TYPE (c) != G_UNICODE_UNASSIGNED;
+ return !IS (TYPE(c),
+ OR (G_UNICODE_UNASSIGNED,
+ OR (G_UNICODE_SURROGATE,
+ 0)));
}
/**
* 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
+ * Returns: %TRUE if the character has zero width
*
* Since: 2.14
**/
return FALSE;
}
-/**
- * g_unichar_iswide:
- * @c: a Unicode character
- *
- * Determines if a character is typically rendered in a double-width
- * cell.
- *
- * Return value: %TRUE if the character is wide
- **/
-gboolean
-g_unichar_iswide (gunichar c)
-{
- gunichar ucs = c;
-
- /* The following block is stolen from Markus Kuhn <Markus.Kuhn@cl.cam.ac.uk>'s
- * wcwidth implementation. */
- return
- (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)));
-}
-
-
-/* The following block is stolen from Markus Kuhn <Markus.Kuhn@cl.cam.ac.uk>'s
- * wcwidth implementation. */
-struct Interval
-{
- gunichar start, end;
-};
-
-/* The following block is stolen from Markus Kuhn <Markus.Kuhn@cl.cam.ac.uk>'s
- * wcwidth implementation. */
static int
interval_compare (const void *key, const void *elt)
{
}
/**
+ * g_unichar_iswide:
+ * @c: a Unicode character
+ *
+ * Determines if a character is typically rendered in a double-width
+ * cell.
+ *
+ * Returns: %TRUE if the character is wide
+ **/
+gboolean
+g_unichar_iswide (gunichar c)
+{
+ if (bsearch (GUINT_TO_POINTER (c),
+ g_unicode_width_table_wide,
+ G_N_ELEMENTS (g_unicode_width_table_wide),
+ sizeof g_unicode_width_table_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
- * <ulink url="http://www.unicode.org/reports/tr11/">Unicode Standard
- * Annex #11</ulink> for details.
+ * 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
+ * pass both this test and g_unichar_iszerowidth().
*
- * Return value: %TRUE if the character is wide in legacy East Asian locales
+ * Returns: %TRUE if the character is wide in legacy East Asian locales
*
* Since: 2.12
*/
gboolean
g_unichar_iswide_cjk (gunichar c)
{
- /* The following block is stolen from Markus Kuhn <Markus.Kuhn@cl.cam.ac.uk>'s
- * wcwidth implementation. */
- /* sorted list of non-overlapping intervals of East Asian Ambiguous
- * characters, generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */
- static const struct Interval ambiguous[] = {
- { 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 }
- };
-
if (g_unichar_iswide (c))
return TRUE;
- if (bsearch (GUINT_TO_POINTER (c), ambiguous, G_N_ELEMENTS (ambiguous), sizeof ambiguous[0],
+ if (bsearch (GUINT_TO_POINTER (c),
+ g_unicode_width_table_ambiguous,
+ G_N_ELEMENTS (g_unicode_width_table_ambiguous),
+ sizeof g_unicode_width_table_ambiguous[0],
interval_compare))
return TRUE;
*
* Converts a character to uppercase.
*
- * Return value: the result of converting @c to uppercase.
+ * Returns: the result of converting @c to uppercase.
* If @c is not an lowercase or titlecase character,
* or has no upper case equivalent @c is returned unchanged.
**/
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;
*
* Converts a character to lower case.
*
- * Return value: the result of converting @c to lower case.
+ * Returns: the result of converting @c to lower case.
* If @c is not an upperlower or titlecase character,
* or has no lowercase equivalent @c is returned unchanged.
**/
*
* Converts a character to the titlecase.
*
- * Return value: the result of converting @c to titlecase.
+ * Returns: the result of converting @c to titlecase.
* If @c is not an uppercase or lowercase character,
* @c is returned unchanged.
**/
* Determines the numeric value of a character as a decimal
* digit.
*
- * Return value: If @c is a decimal digit (according to
+ * Returns: If @c is a decimal digit (according to
* g_unichar_isdigit()), its numeric value. Otherwise, -1.
**/
int
* Determines the numeric value of a character as a hexidecimal
* digit.
*
- * Return value: If @c is a hex digit (according to
+ * Returns: If @c is a hex digit (according to
* g_unichar_isxdigit()), its numeric value. Otherwise, -1.
**/
int
*
* Classifies a Unicode character by type.
*
- * Return value: the type of the character.
+ * Returns: the type of the character.
**/
GUnicodeType
g_unichar_type (gunichar c)
g_free (tem);
#else
const char *locale = setlocale (LC_CTYPE, NULL);
+
+ if (locale == NULL)
+ return LOCALE_NORMAL;
#endif
switch (locale[0])
* 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);
last_was_i = FALSE;
}
}
-
+
if (locale_type == LOCALE_TURKIC && c == 'i')
{
/* i => LATIN CAPITAL LETTER I WITH DOT ABOVE */
* characters in the string increasing. (For instance, the
* German ess-zet will be changed to SS.)
*
- * Return value: a newly allocated string, with all characters
+ * Returns: a newly allocated string, with all characters
* converted to uppercase.
**/
gchar *
* on the current locale, and may result in the number of
* characters in the string changing.
*
- * Return value: a newly allocated string, with all characters
+ * Returns: a newly allocated string, with all characters
* converted to lowercase.
**/
gchar *
* takes case sensitivity into account. GLib does not currently
* provide such a function.
*
- * Return value: a newly allocated string, that is a
+ * Returns: a newly allocated string, that is a
* case independent form of @str.
**/
gchar *
* @ch: a Unicode character
* @mirrored_ch: location to store the mirrored character
*
- * In Unicode, some characters are <firstterm>mirrored</firstterm>. This
- * means that their images are mirrored horizontally in text that is laid
- * out from right to left. For instance, "(" would become its mirror image,
- * ")", in right-to-left text.
+ * In Unicode, some characters are "mirrored". This means that their
+ * images are mirrored horizontally in text that is laid out from right
+ * to left. For instance, "(" would become its mirror image, ")", in
+ * right-to-left text.
*
* 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 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, %FALSE otherwise
+ * Returns: %TRUE if @ch has a mirrored character, %FALSE otherwise
*
* Since: 2.4
**/
* @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
+ * 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.
+ * Returns: the #GUnicodeScript for the character.
*
* Since: 2.14
*/
}
-#define __G_UNIPROP_C__
-#include "galiasdef.c"
+/* 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 */
+
+ /* Unicode 7.0 additions */
+ PACK ('B','a','s','s'), /* G_UNICODE_SCRIPT_BASSA_VAH */
+ PACK ('A','g','h','b'), /* G_UNICODE_SCRIPT_CAUCASIAN_ALBANIAN */
+ PACK ('D','u','p','l'), /* G_UNICODE_SCRIPT_DUPLOYAN */
+ PACK ('E','l','b','a'), /* G_UNICODE_SCRIPT_ELBASAN */
+ PACK ('G','r','a','n'), /* G_UNICODE_SCRIPT_GRANTHA */
+ PACK ('K','h','o','j'), /* G_UNICODE_SCRIPT_KHOJKI*/
+ PACK ('S','i','n','d'), /* G_UNICODE_SCRIPT_KHUDAWADI */
+ PACK ('L','i','n','a'), /* G_UNICODE_SCRIPT_LINEAR_A */
+ PACK ('M','a','h','j'), /* G_UNICODE_SCRIPT_MAHAJANI */
+ PACK ('M','a','n','u'), /* G_UNICODE_SCRIPT_MANICHAEAN */
+ PACK ('M','e','n','d'), /* G_UNICODE_SCRIPT_MENDE_KIKAKUI */
+ PACK ('M','o','d','i'), /* G_UNICODE_SCRIPT_MODI */
+ PACK ('M','r','o','o'), /* G_UNICODE_SCRIPT_MRO */
+ PACK ('N','b','a','t'), /* G_UNICODE_SCRIPT_NABATAEAN */
+ PACK ('N','a','r','b'), /* G_UNICODE_SCRIPT_OLD_NORTH_ARABIAN */
+ PACK ('P','e','r','m'), /* G_UNICODE_SCRIPT_OLD_PERMIC */
+ PACK ('H','m','n','g'), /* G_UNICODE_SCRIPT_PAHAWH_HMONG */
+ PACK ('P','a','l','m'), /* G_UNICODE_SCRIPT_PALMYRENE */
+ PACK ('P','a','u','c'), /* G_UNICODE_SCRIPT_PAU_CIN_HAU */
+ PACK ('P','h','l','p'), /* G_UNICODE_SCRIPT_PSALTER_PAHLAVI */
+ PACK ('S','i','d','d'), /* G_UNICODE_SCRIPT_SIDDHAM */
+ PACK ('T','i','r','h'), /* G_UNICODE_SCRIPT_TIRHUTA */
+ PACK ('W','a','r','a'), /* G_UNICODE_SCRIPT_WARANG_CITI */
+
+#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.
+ *
+ * Returns: 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.
+ *
+ * Returns: 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