X-Git-Url: http://review.tizen.org/git/?a=blobdiff_plain;f=glib%2Fguniprop.c;h=420d58ac9ba922a977718d2eeac7faa3283d7bd6;hb=147c398cd05d71fb172d3788b9dc576c67141811;hp=8a28513edc1615e4653a3bec2eb7256f2c509097;hpb=5e3c122e6c1fb35ed1a2cb0b76e62a519251fb33;p=platform%2Fupstream%2Fglib2.0.git diff --git a/glib/guniprop.c b/glib/guniprop.c index 8a28513..420d58a 100644 --- a/glib/guniprop.c +++ b/glib/guniprop.c @@ -26,12 +26,18 @@ #include #include -#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] \ @@ -82,7 +88,7 @@ #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), \ @@ -434,6 +440,20 @@ interval_compare (const void *key, const void *elt) 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 @@ -446,19 +466,18 @@ interval_compare (const void *key, const void *elt) gboolean g_unichar_iswide (gunichar c) { - /* sorted list of intervals of East_Asian_Width = W and F characters - * from Unicode 5.1.0. produced by mungling output of: - * grep ';[FW]\>' EastAsianWidth.txt */ + /* See NOTE earlier for how to update this table. */ static const struct Interval wide[] = { - {0x1100, 0x1159}, {0x115F, 0x115F}, {0x2329, 0x232A}, {0x2E80, 0x2E99}, - {0x2E9B, 0x2EF3}, {0x2F00, 0x2FD5}, {0x2FF0, 0x2FFB}, {0x3000, 0x303E}, - {0x3041, 0x3096}, {0x3099, 0x30FF}, {0x3105, 0x312D}, {0x3131, 0x318E}, - {0x3190, 0x31B7}, {0x31C0, 0x31E3}, {0x31F0, 0x321E}, {0x3220, 0x3243}, - {0x3250, 0x32FE}, {0x3300, 0x4DB5}, {0x4E00, 0x9FC3}, {0xA000, 0xA48C}, - {0xA490, 0xA4C6}, {0xAC00, 0xD7A3}, {0xF900, 0xFA2D}, {0xFA30, 0xFA6A}, - {0xFA70, 0xFAD9}, {0xFE10, 0xFE19}, {0xFE30, 0xFE52}, {0xFE54, 0xFE66}, - {0xFE68, 0xFE6B}, {0xFF01, 0xFF60}, {0xFFE0, 0xFFE6}, {0x20000, 0x2FFFD}, - {0x30000, 0x3FFFD} + {0x1100, 0x115F}, {0x11A3, 0x11A7}, {0x11FA, 0x11FF}, {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}, {0xD7B0, 0xD7C6}, + {0xD7CB, 0xD7FB}, {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], @@ -491,9 +510,7 @@ g_unichar_iswide (gunichar c) gboolean g_unichar_iswide_cjk (gunichar c) { - /* sorted list of intervals of East_Asian_Width = A and F characters - * from Unicode 5.1.0. produced by mungling output of: - * grep ';[A]\>' EastAsianWidth.txt */ + /* 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}, @@ -517,24 +534,28 @@ g_unichar_iswide_cjk (gunichar c) {0x2103, 0x2103}, {0x2105, 0x2105}, {0x2109, 0x2109}, {0x2113, 0x2113}, {0x2116, 0x2116}, {0x2121, 0x2122}, {0x2126, 0x2126}, {0x212B, 0x212B}, {0x2153, 0x2154}, {0x215B, 0x215E}, {0x2160, 0x216B}, {0x2170, 0x2179}, - {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}, {0x273D, 0x273D}, - {0x2776, 0x277F}, {0xE000, 0xF8FF}, {0xFE00, 0xFE0F}, {0xFFFD, 0xFFFD}, - {0xE0100, 0xE01EF}, {0xF0000, 0xFFFFD}, {0x100000, 0x10FFFD} + {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)) @@ -582,7 +603,7 @@ g_unichar_toupper (gunichar c) 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; @@ -834,15 +855,14 @@ real_toupper (const gchar *str, * 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); @@ -853,7 +873,7 @@ real_toupper (const gchar *str, last_was_i = FALSE; } } - + if (locale_type == LOCALE_TURKIC && c == 'i') { /* i => LATIN CAPITAL LETTER I WITH DOT ABOVE */ @@ -1277,7 +1297,7 @@ g_unichar_get_script_bsearch (gunichar ch) * @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. * @@ -1298,5 +1318,193 @@ g_unichar_get_script (gunichar ch) } -#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 */ + +#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 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 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; +}