glib/tests/unicode.c

   1 /* Unit tests for utilities
   2  * Copyright (C) 2010 Red Hat, Inc.
   3  * Copyright (C) 2011 Google, Inc.
   4  *
   5  * This work is provided "as is"; redistribution and modification
   6  * in whole or in part, in any medium, physical or electronic is
   7  * permitted without restriction.
   8  *
   9  * This work is distributed in the hope that it will be useful,
  10  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  11  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
  12  *
  13  * In no event shall the authors or contributors be liable for any
  14  * direct, indirect, incidental, special, exemplary, or consequential
  15  * damages (including, but not limited to, procurement of substitute
  16  * goods or services; loss of use, data, or profits; or business
  17  * interruption) however caused and on any theory of liability, whether
  18  * in contract, strict liability, or tort (including negligence or
  19  * otherwise) arising in any way out of the use of this software, even
  20  * if advised of the possibility of such damage.
  21  *
  22  * Author: Matthias Clasen, Behdad Esfahbod
  23  */
  24
  25 /* We are testing some deprecated APIs here */
  26 #define GLIB_DISABLE_DEPRECATION_WARNINGS
  27
  28 #include "glib.h"
  29
  30 static void
  31 test_unichar_validate (void)
  32 {
  33   g_assert (g_unichar_validate ('j'));
  34   g_assert (g_unichar_validate (8356));
  35   g_assert (g_unichar_validate (8356));
  36   g_assert (g_unichar_validate (0xfdd1));
  37   g_assert (g_unichar_validate (917760));
  38   g_assert (!g_unichar_validate (0x110000));
  39 }
  40
  41 static void
  42 test_unichar_character_type (void)
  43 {
  44   guint i;
  45   struct {
  46     GUnicodeType type;
  47     gunichar     c;
  48   } examples[] = {
  49     { G_UNICODE_CONTROL,              0x000D },
  50     { G_UNICODE_FORMAT,               0x200E },
  51      /* G_UNICODE_UNASSIGNED */
  52     { G_UNICODE_PRIVATE_USE,          0xE000 },
  53     { G_UNICODE_SURROGATE,            0xD800 },
  54     { G_UNICODE_LOWERCASE_LETTER,     0x0061 },
  55     { G_UNICODE_MODIFIER_LETTER,      0x02B0 },
  56     { G_UNICODE_OTHER_LETTER,         0x3400 },
  57     { G_UNICODE_TITLECASE_LETTER,     0x01C5 },
  58     { G_UNICODE_UPPERCASE_LETTER,     0xFF21 },
  59     { G_UNICODE_COMBINING_MARK,       0x0903 },
  60     { G_UNICODE_ENCLOSING_MARK,       0x20DD },
  61     { G_UNICODE_NON_SPACING_MARK,     0xA806 },
  62     { G_UNICODE_DECIMAL_NUMBER,       0xFF10 },
  63     { G_UNICODE_LETTER_NUMBER,        0x16EE },
  64     { G_UNICODE_OTHER_NUMBER,         0x17F0 },
  65     { G_UNICODE_CONNECT_PUNCTUATION,  0x005F },
  66     { G_UNICODE_DASH_PUNCTUATION,     0x058A },
  67     { G_UNICODE_CLOSE_PUNCTUATION,    0x0F3B },
  68     { G_UNICODE_FINAL_PUNCTUATION,    0x2019 },
  69     { G_UNICODE_INITIAL_PUNCTUATION,  0x2018 },
  70     { G_UNICODE_OTHER_PUNCTUATION,    0x2016 },
  71     { G_UNICODE_OPEN_PUNCTUATION,     0x0F3A },
  72     { G_UNICODE_CURRENCY_SYMBOL,      0x20A0 },
  73     { G_UNICODE_MODIFIER_SYMBOL,      0x309B },
  74     { G_UNICODE_MATH_SYMBOL,          0xFB29 },
  75     { G_UNICODE_OTHER_SYMBOL,         0x00A6 },
  76     { G_UNICODE_LINE_SEPARATOR,       0x2028 },
  77     { G_UNICODE_PARAGRAPH_SEPARATOR,  0x2029 },
  78     { G_UNICODE_SPACE_SEPARATOR,      0x202F },
  79   };
  80
  81   for (i = 0; i < G_N_ELEMENTS (examples); i++)
  82     {
  83       g_assert_cmpint (g_unichar_type (examples[i].c), ==, examples[i].type);
  84     }
  85 }
  86
  87 static void
  88 test_unichar_break_type (void)
  89 {
  90   guint i;
  91   struct {
  92     GUnicodeBreakType type;
  93     gunichar          c;
  94   } examples[] = {
  95     { G_UNICODE_BREAK_MANDATORY,           0x2028 },
  96     { G_UNICODE_BREAK_CARRIAGE_RETURN,     0x000D },
  97     { G_UNICODE_BREAK_LINE_FEED,           0x000A },
  98     { G_UNICODE_BREAK_COMBINING_MARK,      0x0300 },
  99     { G_UNICODE_BREAK_SURROGATE,           0xD800 },
 100     { G_UNICODE_BREAK_ZERO_WIDTH_SPACE,    0x200B },
 101     { G_UNICODE_BREAK_INSEPARABLE,         0x2024 },
 102     { G_UNICODE_BREAK_NON_BREAKING_GLUE,   0x00A0 },
 103     { G_UNICODE_BREAK_CONTINGENT,          0xFFFC },
 104     { G_UNICODE_BREAK_SPACE,               0x0020 },
 105     { G_UNICODE_BREAK_AFTER,               0x05BE },
 106     { G_UNICODE_BREAK_BEFORE,              0x02C8 },
 107     { G_UNICODE_BREAK_BEFORE_AND_AFTER,    0x2014 },
 108     { G_UNICODE_BREAK_HYPHEN,              0x002D },
 109     { G_UNICODE_BREAK_NON_STARTER,         0x17D6 },
 110     { G_UNICODE_BREAK_OPEN_PUNCTUATION,    0x0028 },
 111     { G_UNICODE_BREAK_CLOSE_PARANTHESIS,   0x0029 },
 112     { G_UNICODE_BREAK_CLOSE_PUNCTUATION,   0x007D },
 113     { G_UNICODE_BREAK_QUOTATION,           0x0022 },
 114     { G_UNICODE_BREAK_EXCLAMATION,         0x0021 },
 115     { G_UNICODE_BREAK_IDEOGRAPHIC,         0x2E80 },
 116     { G_UNICODE_BREAK_NUMERIC,             0x0030 },
 117     { G_UNICODE_BREAK_INFIX_SEPARATOR,     0x002C },
 118     { G_UNICODE_BREAK_SYMBOL,              0x002F },
 119     { G_UNICODE_BREAK_ALPHABETIC,          0x0023 },
 120     { G_UNICODE_BREAK_PREFIX,              0x0024 },
 121     { G_UNICODE_BREAK_POSTFIX,             0x0025 },
 122     { G_UNICODE_BREAK_COMPLEX_CONTEXT,     0x0E01 },
 123     { G_UNICODE_BREAK_AMBIGUOUS,           0x00F7 },
 124     { G_UNICODE_BREAK_UNKNOWN,             0xE000 },
 125     { G_UNICODE_BREAK_NEXT_LINE,           0x0085 },
 126     { G_UNICODE_BREAK_WORD_JOINER,         0x2060 },
 127     { G_UNICODE_BREAK_HANGUL_L_JAMO,       0x1100 },
 128     { G_UNICODE_BREAK_HANGUL_V_JAMO,       0x1160 },
 129     { G_UNICODE_BREAK_HANGUL_T_JAMO,       0x11A8 },
 130     { G_UNICODE_BREAK_HANGUL_LV_SYLLABLE,  0xAC00 },
 131     { G_UNICODE_BREAK_HANGUL_LVT_SYLLABLE, 0xAC01 },
 132     { G_UNICODE_BREAK_CONDITIONAL_JAPANESE_STARTER, 0x3041 },
 133     { G_UNICODE_BREAK_HEBREW_LETTER,                0x05D0 },
 134     { G_UNICODE_BREAK_REGIONAL_INDICATOR,           0x1F1F6 },
 135     { G_UNICODE_BREAK_EMOJI_BASE,          0x1F466 },
 136     { G_UNICODE_BREAK_EMOJI_MODIFIER,      0x1F3FB },
 137     { G_UNICODE_BREAK_ZERO_WIDTH_JOINER,   0x200D },
 138   };
 139
 140   for (i = 0; i < G_N_ELEMENTS (examples); i++)
 141     {
 142       g_assert_cmpint (g_unichar_break_type (examples[i].c), ==, examples[i].type);
 143     }
 144 }
 145
 146 static void
 147 test_unichar_script (void)
 148 {
 149   guint i;
 150   struct {
 151     GUnicodeScript script;
 152     gunichar          c;
 153   } examples[] = {
 154     { G_UNICODE_SCRIPT_COMMON,                  0x002A },
 155     { G_UNICODE_SCRIPT_INHERITED,               0x1CED },
 156     { G_UNICODE_SCRIPT_INHERITED,               0x0670 },
 157     { G_UNICODE_SCRIPT_ARABIC,                  0x060D },
 158     { G_UNICODE_SCRIPT_ARMENIAN,                0x0559 },
 159     { G_UNICODE_SCRIPT_BENGALI,                 0x09CD },
 160     { G_UNICODE_SCRIPT_BOPOMOFO,                0x31B6 },
 161     { G_UNICODE_SCRIPT_CHEROKEE,                0x13A2 },
 162     { G_UNICODE_SCRIPT_COPTIC,                  0x2CFD },
 163     { G_UNICODE_SCRIPT_CYRILLIC,                0x0482 },
 164     { G_UNICODE_SCRIPT_DESERET,                0x10401 },
 165     { G_UNICODE_SCRIPT_DEVANAGARI,              0x094D },
 166     { G_UNICODE_SCRIPT_ETHIOPIC,                0x1258 },
 167     { G_UNICODE_SCRIPT_GEORGIAN,                0x10FC },
 168     { G_UNICODE_SCRIPT_GOTHIC,                 0x10341 },
 169     { G_UNICODE_SCRIPT_GREEK,                   0x0375 },
 170     { G_UNICODE_SCRIPT_GUJARATI,                0x0A83 },
 171     { G_UNICODE_SCRIPT_GURMUKHI,                0x0A3C },
 172     { G_UNICODE_SCRIPT_HAN,                     0x3005 },
 173     { G_UNICODE_SCRIPT_HANGUL,                  0x1100 },
 174     { G_UNICODE_SCRIPT_HEBREW,                  0x05BF },
 175     { G_UNICODE_SCRIPT_HIRAGANA,                0x309F },
 176     { G_UNICODE_SCRIPT_KANNADA,                 0x0CBC },
 177     { G_UNICODE_SCRIPT_KATAKANA,                0x30FF },
 178     { G_UNICODE_SCRIPT_KHMER,                   0x17DD },
 179     { G_UNICODE_SCRIPT_LAO,                     0x0EDD },
 180     { G_UNICODE_SCRIPT_LATIN,                   0x0061 },
 181     { G_UNICODE_SCRIPT_MALAYALAM,               0x0D3D },
 182     { G_UNICODE_SCRIPT_MONGOLIAN,               0x1843 },
 183     { G_UNICODE_SCRIPT_MYANMAR,                 0x1031 },
 184     { G_UNICODE_SCRIPT_OGHAM,                   0x169C },
 185     { G_UNICODE_SCRIPT_OLD_ITALIC,             0x10322 },
 186     { G_UNICODE_SCRIPT_ORIYA,                   0x0B3C },
 187     { G_UNICODE_SCRIPT_RUNIC,                   0x16EF },
 188     { G_UNICODE_SCRIPT_SINHALA,                 0x0DBD },
 189     { G_UNICODE_SCRIPT_SYRIAC,                  0x0711 },
 190     { G_UNICODE_SCRIPT_TAMIL,                   0x0B82 },
 191     { G_UNICODE_SCRIPT_TELUGU,                  0x0C03 },
 192     { G_UNICODE_SCRIPT_THAANA,                  0x07B1 },
 193     { G_UNICODE_SCRIPT_THAI,                    0x0E31 },
 194     { G_UNICODE_SCRIPT_TIBETAN,                 0x0FD4 },
 195     { G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL,     0x1400 },
 196     { G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL,     0x1401 },
 197     { G_UNICODE_SCRIPT_YI,                      0xA015 },
 198     { G_UNICODE_SCRIPT_TAGALOG,                 0x1700 },
 199     { G_UNICODE_SCRIPT_HANUNOO,                 0x1720 },
 200     { G_UNICODE_SCRIPT_BUHID,                   0x1740 },
 201     { G_UNICODE_SCRIPT_TAGBANWA,                0x1760 },
 202     { G_UNICODE_SCRIPT_BRAILLE,                 0x2800 },
 203     { G_UNICODE_SCRIPT_CYPRIOT,                0x10808 },
 204     { G_UNICODE_SCRIPT_LIMBU,                   0x1932 },
 205     { G_UNICODE_SCRIPT_OSMANYA,                0x10480 },
 206     { G_UNICODE_SCRIPT_SHAVIAN,                0x10450 },
 207     { G_UNICODE_SCRIPT_LINEAR_B,               0x10000 },
 208     { G_UNICODE_SCRIPT_TAI_LE,                  0x1950 },
 209     { G_UNICODE_SCRIPT_UGARITIC,               0x1039F },
 210     { G_UNICODE_SCRIPT_NEW_TAI_LUE,             0x1980 },
 211     { G_UNICODE_SCRIPT_BUGINESE,                0x1A1F },
 212     { G_UNICODE_SCRIPT_GLAGOLITIC,              0x2C00 },
 213     { G_UNICODE_SCRIPT_TIFINAGH,                0x2D6F },
 214     { G_UNICODE_SCRIPT_SYLOTI_NAGRI,            0xA800 },
 215     { G_UNICODE_SCRIPT_OLD_PERSIAN,            0x103D0 },
 216     { G_UNICODE_SCRIPT_KHAROSHTHI,             0x10A3F },
 217     { G_UNICODE_SCRIPT_UNKNOWN,              0x1111111 },
 218     { G_UNICODE_SCRIPT_BALINESE,                0x1B04 },
 219     { G_UNICODE_SCRIPT_CUNEIFORM,              0x12000 },
 220     { G_UNICODE_SCRIPT_PHOENICIAN,             0x10900 },
 221     { G_UNICODE_SCRIPT_PHAGS_PA,                0xA840 },
 222     { G_UNICODE_SCRIPT_NKO,                     0x07C0 },
 223     { G_UNICODE_SCRIPT_KAYAH_LI,                0xA900 },
 224     { G_UNICODE_SCRIPT_LEPCHA,                  0x1C00 },
 225     { G_UNICODE_SCRIPT_REJANG,                  0xA930 },
 226     { G_UNICODE_SCRIPT_SUNDANESE,               0x1B80 },
 227     { G_UNICODE_SCRIPT_SAURASHTRA,              0xA880 },
 228     { G_UNICODE_SCRIPT_CHAM,                    0xAA00 },
 229     { G_UNICODE_SCRIPT_OL_CHIKI,                0x1C50 },
 230     { G_UNICODE_SCRIPT_VAI,                     0xA500 },
 231     { G_UNICODE_SCRIPT_CARIAN,                 0x102A0 },
 232     { G_UNICODE_SCRIPT_LYCIAN,                 0x10280 },
 233     { G_UNICODE_SCRIPT_LYDIAN,                 0x1093F },
 234     { G_UNICODE_SCRIPT_AVESTAN,                0x10B00 },
 235     { G_UNICODE_SCRIPT_BAMUM,                   0xA6A0 },
 236     { G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS,   0x13000 },
 237     { G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC,       0x10840 },
 238     { G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI,  0x10B60 },
 239     { G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN, 0x10B40 },
 240     { G_UNICODE_SCRIPT_JAVANESE,                0xA980 },
 241     { G_UNICODE_SCRIPT_KAITHI,                 0x11082 },
 242     { G_UNICODE_SCRIPT_LISU,                    0xA4D0 },
 243     { G_UNICODE_SCRIPT_MEETEI_MAYEK,            0xABE5 },
 244     { G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN,      0x10A60 },
 245     { G_UNICODE_SCRIPT_OLD_TURKIC,             0x10C00 },
 246     { G_UNICODE_SCRIPT_SAMARITAN,               0x0800 },
 247     { G_UNICODE_SCRIPT_TAI_THAM,                0x1A20 },
 248     { G_UNICODE_SCRIPT_TAI_VIET,                0xAA80 },
 249     { G_UNICODE_SCRIPT_BATAK,                   0x1BC0 },
 250     { G_UNICODE_SCRIPT_BRAHMI,                 0x11000 },
 251     { G_UNICODE_SCRIPT_MANDAIC,                 0x0840 },
 252     { G_UNICODE_SCRIPT_CHAKMA,                 0x11100 },
 253     { G_UNICODE_SCRIPT_MEROITIC_CURSIVE,       0x109A0 },
 254     { G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS,   0x10980 },
 255     { G_UNICODE_SCRIPT_MIAO,                   0x16F00 },
 256     { G_UNICODE_SCRIPT_SHARADA,                0x11180 },
 257     { G_UNICODE_SCRIPT_SORA_SOMPENG,           0x110D0 },
 258     { G_UNICODE_SCRIPT_TAKRI,                  0x11680 },
 259     { G_UNICODE_SCRIPT_BASSA_VAH,              0x16AD0 },
 260     { G_UNICODE_SCRIPT_CAUCASIAN_ALBANIAN,     0x10530 },
 261     { G_UNICODE_SCRIPT_DUPLOYAN,               0x1BC00 },
 262     { G_UNICODE_SCRIPT_ELBASAN,                0x10500 },
 263     { G_UNICODE_SCRIPT_GRANTHA,                0x11301 },
 264     { G_UNICODE_SCRIPT_KHOJKI,                 0x11200 },
 265     { G_UNICODE_SCRIPT_KHUDAWADI,              0x112B0 },
 266     { G_UNICODE_SCRIPT_LINEAR_A,               0x10600 },
 267     { G_UNICODE_SCRIPT_MAHAJANI,               0x11150 },
 268     { G_UNICODE_SCRIPT_MANICHAEAN,             0x10AC0 },
 269     { G_UNICODE_SCRIPT_MENDE_KIKAKUI,          0x1E800 },
 270     { G_UNICODE_SCRIPT_MODI,                   0x11600 },
 271     { G_UNICODE_SCRIPT_MRO,                    0x16A40 },
 272     { G_UNICODE_SCRIPT_NABATAEAN,              0x10880 },
 273     { G_UNICODE_SCRIPT_OLD_NORTH_ARABIAN,      0x10A80 },
 274     { G_UNICODE_SCRIPT_OLD_PERMIC,             0x10350 },
 275     { G_UNICODE_SCRIPT_PAHAWH_HMONG,           0x16B00 },
 276     { G_UNICODE_SCRIPT_PALMYRENE,              0x10860 },
 277     { G_UNICODE_SCRIPT_PAU_CIN_HAU,            0x11AC0 },
 278     { G_UNICODE_SCRIPT_PSALTER_PAHLAVI,        0x10B80 },
 279     { G_UNICODE_SCRIPT_SIDDHAM,                0x11580 },
 280     { G_UNICODE_SCRIPT_TIRHUTA,                0x11480 },
 281     { G_UNICODE_SCRIPT_WARANG_CITI,            0x118A0 },
 282     { G_UNICODE_SCRIPT_CHEROKEE,               0x0AB71 },
 283     { G_UNICODE_SCRIPT_HATRAN,                 0x108E0 },
 284     { G_UNICODE_SCRIPT_OLD_HUNGARIAN,          0x10C80 },
 285     { G_UNICODE_SCRIPT_MULTANI,                0x11280 },
 286     { G_UNICODE_SCRIPT_AHOM,                   0x11700 },
 287     { G_UNICODE_SCRIPT_CUNEIFORM,              0x12480 },
 288     { G_UNICODE_SCRIPT_ANATOLIAN_HIEROGLYPHS,  0x14400 },
 289     { G_UNICODE_SCRIPT_SIGNWRITING,            0x1D800 },
 290     { G_UNICODE_SCRIPT_ADLAM,                  0x1E900 },
 291     { G_UNICODE_SCRIPT_BHAIKSUKI,              0x11C00 },
 292     { G_UNICODE_SCRIPT_MARCHEN,                0x11C70 },
 293     { G_UNICODE_SCRIPT_NEWA,                   0x11400 },
 294     { G_UNICODE_SCRIPT_OSAGE,                  0x104B0 },
 295     { G_UNICODE_SCRIPT_TANGUT,                 0x16FE0 },
 296   };
 297   for (i = 0; i < G_N_ELEMENTS (examples); i++)
 298     g_assert_cmpint (g_unichar_get_script (examples[i].c), ==, examples[i].script);
 299 }
 300
 301 static void
 302 test_combining_class (void)
 303 {
 304   guint i;
 305   struct {
 306     gint class;
 307     gunichar          c;
 308   } examples[] = {
 309     {   0, 0x0020 },
 310     {   1, 0x0334 },
 311     {   7, 0x093C },
 312     {   8, 0x3099 },
 313     {   9, 0x094D },
 314     {  10, 0x05B0 },
 315     {  11, 0x05B1 },
 316     {  12, 0x05B2 },
 317     {  13, 0x05B3 },
 318     {  14, 0x05B4 },
 319     {  15, 0x05B5 },
 320     {  16, 0x05B6 },
 321     {  17, 0x05B7 },
 322     {  18, 0x05B8 },
 323     {  19, 0x05B9 },
 324     {  20, 0x05BB },
 325     {  21, 0x05BC },
 326     {  22, 0x05BD },
 327     {  23, 0x05BF },
 328     {  24, 0x05C1 },
 329     {  25, 0x05C2 },
 330     {  26, 0xFB1E },
 331     {  27, 0x064B },
 332     {  28, 0x064C },
 333     {  29, 0x064D },
 334     /* ... */
 335     { 228, 0x05AE },
 336     { 230, 0x0300 },
 337     { 232, 0x302C },
 338     { 233, 0x0362 },
 339     { 234, 0x0360 },
 340     { 234, 0x1DCD },
 341     { 240, 0x0345 }
 342   };
 343   for (i = 0; i < G_N_ELEMENTS (examples); i++)
 344     {
 345       g_assert_cmpint (g_unichar_combining_class (examples[i].c), ==, examples[i].class);
 346     }
 347 }
 348
 349 static void
 350 test_mirror (void)
 351 {
 352   gunichar mirror;
 353
 354   g_assert (g_unichar_get_mirror_char ('(', &mirror));
 355   g_assert_cmpint (mirror, ==, ')');
 356   g_assert (g_unichar_get_mirror_char (')', &mirror));
 357   g_assert_cmpint (mirror, ==, '(');
 358   g_assert (g_unichar_get_mirror_char ('{', &mirror));
 359   g_assert_cmpint (mirror, ==, '}');
 360   g_assert (g_unichar_get_mirror_char ('}', &mirror));
 361   g_assert_cmpint (mirror, ==, '{');
 362   g_assert (g_unichar_get_mirror_char (0x208D, &mirror));
 363   g_assert_cmpint (mirror, ==, 0x208E);
 364   g_assert (g_unichar_get_mirror_char (0x208E, &mirror));
 365   g_assert_cmpint (mirror, ==, 0x208D);
 366   g_assert (!g_unichar_get_mirror_char ('a', &mirror));
 367 }
 368
 369 static void
 370 test_mark (void)
 371 {
 372   g_assert (g_unichar_ismark (0x0903));
 373   g_assert (g_unichar_ismark (0x20DD));
 374   g_assert (g_unichar_ismark (0xA806));
 375   g_assert (!g_unichar_ismark ('a'));
 376 }
 377
 378 static void
 379 test_zerowidth (void)
 380 {
 381   g_assert (!g_unichar_iszerowidth (0x00AD));
 382   g_assert (!g_unichar_iszerowidth (0x00AD));
 383   g_assert (!g_unichar_iszerowidth (0x115F));
 384   g_assert (g_unichar_iszerowidth (0x1160));
 385   g_assert (g_unichar_iszerowidth (0x11AA));
 386   g_assert (g_unichar_iszerowidth (0x11FF));
 387   g_assert (!g_unichar_iszerowidth (0x1200));
 388   g_assert (g_unichar_iszerowidth (0x200B));
 389   g_assert (g_unichar_iszerowidth (0x591));
 390 }
 391
 392 static void
 393 test_title (void)
 394 {
 395   g_assert (g_unichar_istitle (0x01c5));
 396   g_assert (g_unichar_istitle (0x1f88));
 397   g_assert (g_unichar_istitle (0x1fcc));
 398   g_assert (!g_unichar_istitle ('a'));
 399   g_assert (!g_unichar_istitle ('A'));
 400
 401   g_assert_cmphex (g_unichar_totitle (0x01c6), ==, 0x01c5);
 402   g_assert_cmphex (g_unichar_totitle (0x01c4), ==, 0x01c5);
 403   g_assert_cmphex (g_unichar_totitle (0x01c5), ==, 0x01c5);
 404   g_assert_cmphex (g_unichar_totitle (0x1f80), ==, 0x1f88);
 405   g_assert_cmphex (g_unichar_totitle (0x1f88), ==, 0x1f88);
 406   g_assert_cmphex (g_unichar_totitle ('a'), ==, 'A');
 407   g_assert_cmphex (g_unichar_totitle ('A'), ==, 'A');
 408 }
 409
 410 static void
 411 test_cases (void)
 412 {
 413   g_assert_cmphex (g_unichar_toupper ('a'), ==, 'A');
 414   g_assert_cmphex (g_unichar_toupper ('A'), ==, 'A');
 415   g_assert_cmphex (g_unichar_toupper (0x01C5), ==, 0x01C4);
 416   g_assert_cmphex (g_unichar_toupper (0x01C6), ==, 0x01C4);
 417   g_assert_cmphex (g_unichar_tolower ('A'), ==, 'a');
 418   g_assert_cmphex (g_unichar_tolower ('a'), ==, 'a');
 419   g_assert_cmphex (g_unichar_tolower (0x01C4), ==, 0x01C6);
 420   g_assert_cmphex (g_unichar_tolower (0x01C5), ==, 0x01C6);
 421   g_assert_cmphex (g_unichar_tolower (0x1F8A), ==, 0x1F82);
 422   g_assert_cmphex (g_unichar_totitle (0x1F8A), ==, 0x1F8A);
 423   g_assert_cmphex (g_unichar_toupper (0x1F8A), ==, 0x1F8A);
 424   g_assert_cmphex (g_unichar_tolower (0x1FB2), ==, 0x1FB2);
 425   g_assert_cmphex (g_unichar_toupper (0x1FB2), ==, 0x1FB2);
 426 }
 427
 428 static void
 429 test_defined (void)
 430 {
 431   g_assert (g_unichar_isdefined (0x0903));
 432   g_assert (g_unichar_isdefined (0x20DD));
 433   g_assert (g_unichar_isdefined (0x20BA));
 434   g_assert (g_unichar_isdefined (0xA806));
 435   g_assert (g_unichar_isdefined ('a'));
 436   g_assert (!g_unichar_isdefined (0x10C49));
 437   g_assert (!g_unichar_isdefined (0x169D));
 438 }
 439
 440 static void
 441 test_wide (void)
 442 {
 443   guint i;
 444   struct {
 445     gunichar c;
 446     enum {
 447       NOT_WIDE,
 448       WIDE_CJK,
 449       WIDE
 450     } wide;
 451   } examples[] = {
 452     /* Neutral */
 453     {   0x0000, NOT_WIDE },
 454     {   0x0483, NOT_WIDE },
 455     {   0x0641, NOT_WIDE },
 456     {   0xFFFC, NOT_WIDE },
 457     {  0x10000, NOT_WIDE },
 458     {  0xE0001, NOT_WIDE },
 459     {  0x2FFFE, NOT_WIDE },
 460     {  0x3FFFE, NOT_WIDE },
 461
 462     /* Narrow */
 463     {   0x0020, NOT_WIDE },
 464     {   0x0041, NOT_WIDE },
 465     {   0x27E6, NOT_WIDE },
 466
 467     /* Halfwidth */
 468     {   0x20A9, NOT_WIDE },
 469     {   0xFF61, NOT_WIDE },
 470     {   0xFF69, NOT_WIDE },
 471     {   0xFFEE, NOT_WIDE },
 472
 473     /* Ambiguous */
 474     {   0x00A1, WIDE_CJK },
 475     {   0x00BE, WIDE_CJK },
 476     {   0x02DD, WIDE_CJK },
 477     {   0x2020, WIDE_CJK },
 478     {   0xFFFD, WIDE_CJK },
 479     {   0x00A1, WIDE_CJK },
 480     {  0x1F100, WIDE_CJK },
 481     {  0xE0100, WIDE_CJK },
 482     { 0x100000, WIDE_CJK },
 483     { 0x10FFFD, WIDE_CJK },
 484
 485     /* Fullwidth */
 486     {   0x3000, WIDE },
 487     {   0xFF60, WIDE },
 488
 489     /* Wide */
 490     {   0x2329, WIDE },
 491     {   0x3001, WIDE },
 492     {   0xFE69, WIDE },
 493     {  0x30000, WIDE },
 494     {  0x3FFFD, WIDE },
 495
 496     /* Default Wide blocks */
 497     {   0x4DBF, WIDE },
 498     {   0x9FFF, WIDE },
 499     {   0xFAFF, WIDE },
 500     {  0x2A6DF, WIDE },
 501     {  0x2B73F, WIDE },
 502     {  0x2B81F, WIDE },
 503     {  0x2FA1F, WIDE },
 504
 505     /* Uniode-5.2 character additions */
 506     /* Wide */
 507     {   0x115F, WIDE },
 508
 509     /* Uniode-6.0 character additions */
 510     /* Wide */
 511     {  0x2B740, WIDE },
 512     {  0x1B000, WIDE },
 513
 514     { 0x111111, NOT_WIDE }
 515   };
 516
 517   for (i = 0; i < G_N_ELEMENTS (examples); i++)
 518     {
 519       g_assert_cmpint (g_unichar_iswide (examples[i].c), ==, (examples[i].wide == WIDE));
 520       g_assert_cmpint (g_unichar_iswide_cjk (examples[i].c), ==, (examples[i].wide != NOT_WIDE));
 521     }
 522 };
 523
 524 static void
 525 test_compose (void)
 526 {
 527   gunichar ch;
 528
 529   /* Not composable */
 530   g_assert (!g_unichar_compose (0x0041, 0x0042, &ch) && ch == 0);
 531   g_assert (!g_unichar_compose (0x0041, 0, &ch) && ch == 0);
 532   g_assert (!g_unichar_compose (0x0066, 0x0069, &ch) && ch == 0);
 533
 534   /* Tricky non-composable */
 535   g_assert (!g_unichar_compose (0x0308, 0x0301, &ch) && ch == 0); /* !0x0344 */
 536   g_assert (!g_unichar_compose (0x0F71, 0x0F72, &ch) && ch == 0); /* !0x0F73 */
 537
 538   /* Singletons should not compose */
 539   g_assert (!g_unichar_compose (0x212B, 0, &ch) && ch == 0);
 540   g_assert (!g_unichar_compose (0x00C5, 0, &ch) && ch == 0);
 541   g_assert (!g_unichar_compose (0x2126, 0, &ch) && ch == 0);
 542   g_assert (!g_unichar_compose (0x03A9, 0, &ch) && ch == 0);
 543
 544   /* Pairs */
 545   g_assert (g_unichar_compose (0x0041, 0x030A, &ch) && ch == 0x00C5);
 546   g_assert (g_unichar_compose (0x006F, 0x0302, &ch) && ch == 0x00F4);
 547   g_assert (g_unichar_compose (0x1E63, 0x0307, &ch) && ch == 0x1E69);
 548   g_assert (g_unichar_compose (0x0073, 0x0323, &ch) && ch == 0x1E63);
 549   g_assert (g_unichar_compose (0x0064, 0x0307, &ch) && ch == 0x1E0B);
 550   g_assert (g_unichar_compose (0x0064, 0x0323, &ch) && ch == 0x1E0D);
 551
 552   /* Hangul */
 553   g_assert (g_unichar_compose (0xD4CC, 0x11B6, &ch) && ch == 0xD4DB);
 554   g_assert (g_unichar_compose (0x1111, 0x1171, &ch) && ch == 0xD4CC);
 555   g_assert (g_unichar_compose (0xCE20, 0x11B8, &ch) && ch == 0xCE31);
 556   g_assert (g_unichar_compose (0x110E, 0x1173, &ch) && ch == 0xCE20);
 557 }
 558
 559 static void
 560 test_decompose (void)
 561 {
 562   gunichar a, b;
 563
 564   /* Not decomposable */
 565   g_assert (!g_unichar_decompose (0x0041, &a, &b) && a == 0x0041 && b == 0);
 566   g_assert (!g_unichar_decompose (0xFB01, &a, &b) && a == 0xFB01 && b == 0);
 567
 568   /* Singletons */
 569   g_assert (g_unichar_decompose (0x212B, &a, &b) && a == 0x00C5 && b == 0);
 570   g_assert (g_unichar_decompose (0x2126, &a, &b) && a == 0x03A9 && b == 0);
 571
 572   /* Tricky pairs */
 573   g_assert (g_unichar_decompose (0x0344, &a, &b) && a == 0x0308 && b == 0x0301);
 574   g_assert (g_unichar_decompose (0x0F73, &a, &b) && a == 0x0F71 && b == 0x0F72);
 575
 576   /* Pairs */
 577   g_assert (g_unichar_decompose (0x00C5, &a, &b) && a == 0x0041 && b == 0x030A);
 578   g_assert (g_unichar_decompose (0x00F4, &a, &b) && a == 0x006F && b == 0x0302);
 579   g_assert (g_unichar_decompose (0x1E69, &a, &b) && a == 0x1E63 && b == 0x0307);
 580   g_assert (g_unichar_decompose (0x1E63, &a, &b) && a == 0x0073 && b == 0x0323);
 581   g_assert (g_unichar_decompose (0x1E0B, &a, &b) && a == 0x0064 && b == 0x0307);
 582   g_assert (g_unichar_decompose (0x1E0D, &a, &b) && a == 0x0064 && b == 0x0323);
 583
 584   /* Hangul */
 585   g_assert (g_unichar_decompose (0xD4DB, &a, &b) && a == 0xD4CC && b == 0x11B6);
 586   g_assert (g_unichar_decompose (0xD4CC, &a, &b) && a == 0x1111 && b == 0x1171);
 587   g_assert (g_unichar_decompose (0xCE31, &a, &b) && a == 0xCE20 && b == 0x11B8);
 588   g_assert (g_unichar_decompose (0xCE20, &a, &b) && a == 0x110E && b == 0x1173);
 589 }
 590
 591 static void
 592 test_fully_decompose_canonical (void)
 593 {
 594   gunichar decomp[5];
 595   gsize len;
 596
 597 #define TEST_DECOMP(ch, expected_len, a, b, c, d) \
 598   len = g_unichar_fully_decompose (ch, FALSE, decomp, G_N_ELEMENTS (decomp)); \
 599   g_assert_cmpint (expected_len, ==, len); \
 600   if (expected_len >= 1) g_assert_cmphex (decomp[0], ==, a); \
 601   if (expected_len >= 2) g_assert_cmphex (decomp[1], ==, b); \
 602   if (expected_len >= 3) g_assert_cmphex (decomp[2], ==, c); \
 603   if (expected_len >= 4) g_assert_cmphex (decomp[3], ==, d); \
 604
 605 #define TEST0(ch)               TEST_DECOMP (ch, 1, ch, 0, 0, 0)
 606 #define TEST1(ch, a)            TEST_DECOMP (ch, 1, a, 0, 0, 0)
 607 #define TEST2(ch, a, b)         TEST_DECOMP (ch, 2, a, b, 0, 0)
 608 #define TEST3(ch, a, b, c)      TEST_DECOMP (ch, 3, a, b, c, 0)
 609 #define TEST4(ch, a, b, c, d)   TEST_DECOMP (ch, 4, a, b, c, d)
 610
 611   /* Not decomposable */
 612   TEST0 (0x0041);
 613   TEST0 (0xFB01);
 614
 615   /* Singletons */
 616   TEST2 (0x212B, 0x0041, 0x030A);
 617   TEST1 (0x2126, 0x03A9);
 618
 619   /* Tricky pairs */
 620   TEST2 (0x0344, 0x0308, 0x0301);
 621   TEST2 (0x0F73, 0x0F71, 0x0F72);
 622
 623   /* General */
 624   TEST2 (0x00C5, 0x0041, 0x030A);
 625   TEST2 (0x00F4, 0x006F, 0x0302);
 626   TEST3 (0x1E69, 0x0073, 0x0323, 0x0307);
 627   TEST2 (0x1E63, 0x0073, 0x0323);
 628   TEST2 (0x1E0B, 0x0064, 0x0307);
 629   TEST2 (0x1E0D, 0x0064, 0x0323);
 630
 631   /* Hangul */
 632   TEST3 (0xD4DB, 0x1111, 0x1171, 0x11B6);
 633   TEST2 (0xD4CC, 0x1111, 0x1171);
 634   TEST3 (0xCE31, 0x110E, 0x1173, 0x11B8);
 635   TEST2 (0xCE20, 0x110E, 0x1173);
 636
 637 #undef TEST_DECOMP
 638 }
 639
 640 static void
 641 test_canonical_decomposition (void)
 642 {
 643   gunichar *decomp;
 644   gsize len;
 645
 646 #define TEST_DECOMP(ch, expected_len, a, b, c, d) \
 647   decomp = g_unicode_canonical_decomposition (ch, &len); \
 648   g_assert_cmpint (expected_len, ==, len); \
 649   if (expected_len >= 1) g_assert_cmphex (decomp[0], ==, a); \
 650   if (expected_len >= 2) g_assert_cmphex (decomp[1], ==, b); \
 651   if (expected_len >= 3) g_assert_cmphex (decomp[2], ==, c); \
 652   if (expected_len >= 4) g_assert_cmphex (decomp[3], ==, d); \
 653   g_free (decomp);
 654
 655 #define TEST0(ch)               TEST_DECOMP (ch, 1, ch, 0, 0, 0)
 656 #define TEST1(ch, a)            TEST_DECOMP (ch, 1, a, 0, 0, 0)
 657 #define TEST2(ch, a, b)         TEST_DECOMP (ch, 2, a, b, 0, 0)
 658 #define TEST3(ch, a, b, c)      TEST_DECOMP (ch, 3, a, b, c, 0)
 659 #define TEST4(ch, a, b, c, d)   TEST_DECOMP (ch, 4, a, b, c, d)
 660
 661   /* Not decomposable */
 662   TEST0 (0x0041);
 663   TEST0 (0xFB01);
 664
 665   /* Singletons */
 666   TEST2 (0x212B, 0x0041, 0x030A);
 667   TEST1 (0x2126, 0x03A9);
 668
 669   /* Tricky pairs */
 670   TEST2 (0x0344, 0x0308, 0x0301);
 671   TEST2 (0x0F73, 0x0F71, 0x0F72);
 672
 673   /* General */
 674   TEST2 (0x00C5, 0x0041, 0x030A);
 675   TEST2 (0x00F4, 0x006F, 0x0302);
 676   TEST3 (0x1E69, 0x0073, 0x0323, 0x0307);
 677   TEST2 (0x1E63, 0x0073, 0x0323);
 678   TEST2 (0x1E0B, 0x0064, 0x0307);
 679   TEST2 (0x1E0D, 0x0064, 0x0323);
 680
 681   /* Hangul */
 682   TEST3 (0xD4DB, 0x1111, 0x1171, 0x11B6);
 683   TEST2 (0xD4CC, 0x1111, 0x1171);
 684   TEST3 (0xCE31, 0x110E, 0x1173, 0x11B8);
 685   TEST2 (0xCE20, 0x110E, 0x1173);
 686
 687 #undef TEST_DECOMP
 688 }
 689
 690 static void
 691 test_decompose_tail (void)
 692 {
 693   gunichar ch, a, b, c, d;
 694
 695   /* Test that whenever a char ch decomposes into a and b, b itself
 696    * won't decompose any further. */
 697
 698   for (ch = 0; ch < 0x110000; ch++)
 699     if (g_unichar_decompose (ch, &a, &b))
 700       g_assert (!g_unichar_decompose (b, &c, &d));
 701     else
 702       {
 703         g_assert_cmpuint (a, ==, ch);
 704         g_assert_cmpuint (b, ==, 0);
 705       }
 706 }
 707
 708 static void
 709 test_fully_decompose_len (void)
 710 {
 711   gunichar ch;
 712
 713   /* Test that all canonical decompositions are at most 4 in length,
 714    * and compatibility decompositions are at most 18 in length.
 715    */
 716
 717   for (ch = 0; ch < 0x110000; ch++) {
 718     g_assert_cmpint (g_unichar_fully_decompose (ch, FALSE, NULL, 0), <=, 4);
 719     g_assert_cmpint (g_unichar_fully_decompose (ch, TRUE,  NULL, 0), <=, 18);
 720   }
 721 }
 722
 723 static void
 724 test_iso15924 (void)
 725 {
 726   const struct {
 727     GUnicodeScript script;
 728     char four_letter_code[5];
 729   } data[] = {
 730     { G_UNICODE_SCRIPT_COMMON,             "Zyyy" },
 731     { G_UNICODE_SCRIPT_INHERITED,          "Zinh" },
 732     { G_UNICODE_SCRIPT_ARABIC,             "Arab" },
 733     { G_UNICODE_SCRIPT_ARMENIAN,           "Armn" },
 734     { G_UNICODE_SCRIPT_BENGALI,            "Beng" },
 735     { G_UNICODE_SCRIPT_BOPOMOFO,           "Bopo" },
 736     { G_UNICODE_SCRIPT_CHEROKEE,           "Cher" },
 737     { G_UNICODE_SCRIPT_COPTIC,             "Copt" },
 738     { G_UNICODE_SCRIPT_CYRILLIC,           "Cyrl" },
 739     { G_UNICODE_SCRIPT_DESERET,            "Dsrt" },
 740     { G_UNICODE_SCRIPT_DEVANAGARI,         "Deva" },
 741     { G_UNICODE_SCRIPT_ETHIOPIC,           "Ethi" },
 742     { G_UNICODE_SCRIPT_GEORGIAN,           "Geor" },
 743     { G_UNICODE_SCRIPT_GOTHIC,             "Goth" },
 744     { G_UNICODE_SCRIPT_GREEK,              "Grek" },
 745     { G_UNICODE_SCRIPT_GUJARATI,           "Gujr" },
 746     { G_UNICODE_SCRIPT_GURMUKHI,           "Guru" },
 747     { G_UNICODE_SCRIPT_HAN,                "Hani" },
 748     { G_UNICODE_SCRIPT_HANGUL,             "Hang" },
 749     { G_UNICODE_SCRIPT_HEBREW,             "Hebr" },
 750     { G_UNICODE_SCRIPT_HIRAGANA,           "Hira" },
 751     { G_UNICODE_SCRIPT_KANNADA,            "Knda" },
 752     { G_UNICODE_SCRIPT_KATAKANA,           "Kana" },
 753     { G_UNICODE_SCRIPT_KHMER,              "Khmr" },
 754     { G_UNICODE_SCRIPT_LAO,                "Laoo" },
 755     { G_UNICODE_SCRIPT_LATIN,              "Latn" },
 756     { G_UNICODE_SCRIPT_MALAYALAM,          "Mlym" },
 757     { G_UNICODE_SCRIPT_MONGOLIAN,          "Mong" },
 758     { G_UNICODE_SCRIPT_MYANMAR,            "Mymr" },
 759     { G_UNICODE_SCRIPT_OGHAM,              "Ogam" },
 760     { G_UNICODE_SCRIPT_OLD_ITALIC,         "Ital" },
 761     { G_UNICODE_SCRIPT_ORIYA,              "Orya" },
 762     { G_UNICODE_SCRIPT_RUNIC,              "Runr" },
 763     { G_UNICODE_SCRIPT_SINHALA,            "Sinh" },
 764     { G_UNICODE_SCRIPT_SYRIAC,             "Syrc" },
 765     { G_UNICODE_SCRIPT_TAMIL,              "Taml" },
 766     { G_UNICODE_SCRIPT_TELUGU,             "Telu" },
 767     { G_UNICODE_SCRIPT_THAANA,             "Thaa" },
 768     { G_UNICODE_SCRIPT_THAI,               "Thai" },
 769     { G_UNICODE_SCRIPT_TIBETAN,            "Tibt" },
 770     { G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL, "Cans" },
 771     { G_UNICODE_SCRIPT_YI,                 "Yiii" },
 772     { G_UNICODE_SCRIPT_TAGALOG,            "Tglg" },
 773     { G_UNICODE_SCRIPT_HANUNOO,            "Hano" },
 774     { G_UNICODE_SCRIPT_BUHID,              "Buhd" },
 775     { G_UNICODE_SCRIPT_TAGBANWA,           "Tagb" },
 776
 777     /* Unicode-4.0 additions */
 778     { G_UNICODE_SCRIPT_BRAILLE,            "Brai" },
 779     { G_UNICODE_SCRIPT_CYPRIOT,            "Cprt" },
 780     { G_UNICODE_SCRIPT_LIMBU,              "Limb" },
 781     { G_UNICODE_SCRIPT_OSMANYA,            "Osma" },
 782     { G_UNICODE_SCRIPT_SHAVIAN,            "Shaw" },
 783     { G_UNICODE_SCRIPT_LINEAR_B,           "Linb" },
 784     { G_UNICODE_SCRIPT_TAI_LE,             "Tale" },
 785     { G_UNICODE_SCRIPT_UGARITIC,           "Ugar" },
 786
 787     /* Unicode-4.1 additions */
 788     { G_UNICODE_SCRIPT_NEW_TAI_LUE,        "Talu" },
 789     { G_UNICODE_SCRIPT_BUGINESE,           "Bugi" },
 790     { G_UNICODE_SCRIPT_GLAGOLITIC,         "Glag" },
 791     { G_UNICODE_SCRIPT_TIFINAGH,           "Tfng" },
 792     { G_UNICODE_SCRIPT_SYLOTI_NAGRI,       "Sylo" },
 793     { G_UNICODE_SCRIPT_OLD_PERSIAN,        "Xpeo" },
 794     { G_UNICODE_SCRIPT_KHAROSHTHI,         "Khar" },
 795
 796     /* Unicode-5.0 additions */
 797     { G_UNICODE_SCRIPT_UNKNOWN,            "Zzzz" },
 798     { G_UNICODE_SCRIPT_BALINESE,           "Bali" },
 799     { G_UNICODE_SCRIPT_CUNEIFORM,          "Xsux" },
 800     { G_UNICODE_SCRIPT_PHOENICIAN,         "Phnx" },
 801     { G_UNICODE_SCRIPT_PHAGS_PA,           "Phag" },
 802     { G_UNICODE_SCRIPT_NKO,                "Nkoo" },
 803
 804     /* Unicode-5.1 additions */
 805     { G_UNICODE_SCRIPT_KAYAH_LI,           "Kali" },
 806     { G_UNICODE_SCRIPT_LEPCHA,             "Lepc" },
 807     { G_UNICODE_SCRIPT_REJANG,             "Rjng" },
 808     { G_UNICODE_SCRIPT_SUNDANESE,          "Sund" },
 809     { G_UNICODE_SCRIPT_SAURASHTRA,         "Saur" },
 810     { G_UNICODE_SCRIPT_CHAM,               "Cham" },
 811     { G_UNICODE_SCRIPT_OL_CHIKI,           "Olck" },
 812     { G_UNICODE_SCRIPT_VAI,                "Vaii" },
 813     { G_UNICODE_SCRIPT_CARIAN,             "Cari" },
 814     { G_UNICODE_SCRIPT_LYCIAN,             "Lyci" },
 815     { G_UNICODE_SCRIPT_LYDIAN,             "Lydi" },
 816
 817     /* Unicode-5.2 additions */
 818     { G_UNICODE_SCRIPT_AVESTAN,                "Avst" },
 819     { G_UNICODE_SCRIPT_BAMUM,                  "Bamu" },
 820     { G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS,   "Egyp" },
 821     { G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC,       "Armi" },
 822     { G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI,  "Phli" },
 823     { G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN, "Prti" },
 824     { G_UNICODE_SCRIPT_JAVANESE,               "Java" },
 825     { G_UNICODE_SCRIPT_KAITHI,                 "Kthi" },
 826     { G_UNICODE_SCRIPT_LISU,                   "Lisu" },
 827     { G_UNICODE_SCRIPT_MEETEI_MAYEK,           "Mtei" },
 828     { G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN,      "Sarb" },
 829     { G_UNICODE_SCRIPT_OLD_TURKIC,             "Orkh" },
 830     { G_UNICODE_SCRIPT_SAMARITAN,              "Samr" },
 831     { G_UNICODE_SCRIPT_TAI_THAM,               "Lana" },
 832     { G_UNICODE_SCRIPT_TAI_VIET,               "Tavt" },
 833
 834     /* Unicode-6.0 additions */
 835     { G_UNICODE_SCRIPT_BATAK,                  "Batk" },
 836     { G_UNICODE_SCRIPT_BRAHMI,                 "Brah" },
 837     { G_UNICODE_SCRIPT_MANDAIC,                "Mand" },
 838
 839     /* Unicode-6.1 additions */
 840     { G_UNICODE_SCRIPT_CHAKMA,                 "Cakm" },
 841     { G_UNICODE_SCRIPT_MEROITIC_CURSIVE,       "Merc" },
 842     { G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS,   "Mero" },
 843     { G_UNICODE_SCRIPT_MIAO,                   "Plrd" },
 844     { G_UNICODE_SCRIPT_SHARADA,                "Shrd" },
 845     { G_UNICODE_SCRIPT_SORA_SOMPENG,           "Sora" },
 846     { G_UNICODE_SCRIPT_TAKRI,                  "Takr" },
 847
 848     /* Unicode 7.0 additions */
 849     { G_UNICODE_SCRIPT_BASSA_VAH,              "Bass" },
 850     { G_UNICODE_SCRIPT_CAUCASIAN_ALBANIAN,     "Aghb" },
 851     { G_UNICODE_SCRIPT_DUPLOYAN,               "Dupl" },
 852     { G_UNICODE_SCRIPT_ELBASAN,                "Elba" },
 853     { G_UNICODE_SCRIPT_GRANTHA,                "Gran" },
 854     { G_UNICODE_SCRIPT_KHOJKI,                 "Khoj" },
 855     { G_UNICODE_SCRIPT_KHUDAWADI,              "Sind" },
 856     { G_UNICODE_SCRIPT_LINEAR_A,               "Lina" },
 857     { G_UNICODE_SCRIPT_MAHAJANI,               "Mahj" },
 858     { G_UNICODE_SCRIPT_MANICHAEAN,             "Manu" },
 859     { G_UNICODE_SCRIPT_MENDE_KIKAKUI,          "Mend" },
 860     { G_UNICODE_SCRIPT_MODI,                   "Modi" },
 861     { G_UNICODE_SCRIPT_MRO,                    "Mroo" },
 862     { G_UNICODE_SCRIPT_NABATAEAN,              "Nbat" },
 863     { G_UNICODE_SCRIPT_OLD_NORTH_ARABIAN,      "Narb" },
 864     { G_UNICODE_SCRIPT_OLD_PERMIC,             "Perm" },
 865     { G_UNICODE_SCRIPT_PAHAWH_HMONG,           "Hmng" },
 866     { G_UNICODE_SCRIPT_PALMYRENE,              "Palm" },
 867     { G_UNICODE_SCRIPT_PAU_CIN_HAU,            "Pauc" },
 868     { G_UNICODE_SCRIPT_PSALTER_PAHLAVI,        "Phlp" },
 869     { G_UNICODE_SCRIPT_SIDDHAM,                "Sidd" },
 870     { G_UNICODE_SCRIPT_TIRHUTA,                "Tirh" },
 871     { G_UNICODE_SCRIPT_WARANG_CITI,            "Wara" },
 872
 873     /* Unicode 8.0 additions */
 874     { G_UNICODE_SCRIPT_AHOM,                   "Ahom" },
 875     { G_UNICODE_SCRIPT_ANATOLIAN_HIEROGLYPHS,  "Hluw" },
 876     { G_UNICODE_SCRIPT_HATRAN,                 "Hatr" },
 877     { G_UNICODE_SCRIPT_MULTANI,                "Mult" },
 878     { G_UNICODE_SCRIPT_OLD_HUNGARIAN,          "Hung" },
 879     { G_UNICODE_SCRIPT_SIGNWRITING,            "Sgnw" },
 880
 881     /* Unicode 9.0 additions */
 882     { G_UNICODE_SCRIPT_ADLAM,                  "Adlm" },
 883     { G_UNICODE_SCRIPT_BHAIKSUKI,              "Bhks" },
 884     { G_UNICODE_SCRIPT_MARCHEN,                "Marc" },
 885     { G_UNICODE_SCRIPT_NEWA,                   "Newa" },
 886     { G_UNICODE_SCRIPT_OSAGE,                  "Osge" },
 887     { G_UNICODE_SCRIPT_TANGUT,                 "Tang" },
 888   };
 889   guint i;
 890
 891   g_assert_cmphex (0, ==, g_unicode_script_to_iso15924 (G_UNICODE_SCRIPT_INVALID_CODE));
 892   g_assert_cmphex (0x5A7A7A7A, ==, g_unicode_script_to_iso15924 (1000));
 893   g_assert_cmphex (0x41726162, ==, g_unicode_script_to_iso15924 (G_UNICODE_SCRIPT_ARABIC));
 894
 895   g_assert_cmphex (G_UNICODE_SCRIPT_INVALID_CODE, ==, g_unicode_script_from_iso15924 (0));
 896   g_assert_cmphex (G_UNICODE_SCRIPT_UNKNOWN, ==, g_unicode_script_from_iso15924 (0x12345678));
 897
 898 #define PACK(a,b,c,d) ((guint32)((((guint8)(a))<<24)|(((guint8)(b))<<16)|(((guint8)(c))<<8)|((guint8)(d))))
 899
 900   for (i = 0; i < G_N_ELEMENTS (data); i++)
 901     {
 902       guint32 code = PACK (data[i].four_letter_code[0],
 903                            data[i].four_letter_code[1],
 904                            data[i].four_letter_code[2],
 905                            data[i].four_letter_code[3]);
 906
 907       g_assert_cmphex (g_unicode_script_to_iso15924 (data[i].script), ==, code);
 908       g_assert_cmpint (g_unicode_script_from_iso15924 (code), ==, data[i].script);
 909     }
 910
 911 #undef PACK
 912 }
 913
 914 int
 915 main (int   argc,
 916       char *argv[])
 917 {
 918   g_test_init (&argc, &argv, NULL);
 919
 920   g_test_add_func ("/unicode/validate", test_unichar_validate);
 921   g_test_add_func ("/unicode/character-type", test_unichar_character_type);
 922   g_test_add_func ("/unicode/break-type", test_unichar_break_type);
 923   g_test_add_func ("/unicode/script", test_unichar_script);
 924   g_test_add_func ("/unicode/combining-class", test_combining_class);
 925   g_test_add_func ("/unicode/mirror", test_mirror);
 926   g_test_add_func ("/unicode/mark", test_mark);
 927   g_test_add_func ("/unicode/title", test_title);
 928   g_test_add_func ("/unicode/zero-width", test_zerowidth);
 929   g_test_add_func ("/unicode/defined", test_defined);
 930   g_test_add_func ("/unicode/wide", test_wide);
 931   g_test_add_func ("/unicode/compose", test_compose);
 932   g_test_add_func ("/unicode/decompose", test_decompose);
 933   g_test_add_func ("/unicode/fully-decompose-canonical", test_fully_decompose_canonical);
 934   g_test_add_func ("/unicode/canonical-decomposition", test_canonical_decomposition);
 935   g_test_add_func ("/unicode/decompose-tail", test_decompose_tail);
 936   g_test_add_func ("/unicode/fully-decompose-len", test_fully_decompose_len);
 937   g_test_add_func ("/unicode/iso15924", test_iso15924);
 938   g_test_add_func ("/unicode/cases", test_cases);
 939
 940   return g_test_run();
 941 }