1 /*************************************************
2 * Unicode Property Table handler *
3 *************************************************/
8 /* This file contains definitions of the property values that are returned by
9 the UCD access macros. New values that are added for new releases of Unicode
10 should always be at the end of each enum, for backwards compatibility. */
12 /* These are the general character categories. */
19 ucp_P, /* Punctuation */
24 /* These are the particular character types. */
29 ucp_Cn, /* Unassigned */
30 ucp_Co, /* Private use */
31 ucp_Cs, /* Surrogate */
32 ucp_Ll, /* Lower case letter */
33 ucp_Lm, /* Modifier letter */
34 ucp_Lo, /* Other letter */
35 ucp_Lt, /* Title case letter */
36 ucp_Lu, /* Upper case letter */
37 ucp_Mc, /* Spacing mark */
38 ucp_Me, /* Enclosing mark */
39 ucp_Mn, /* Non-spacing mark */
40 ucp_Nd, /* Decimal number */
41 ucp_Nl, /* Letter number */
42 ucp_No, /* Other number */
43 ucp_Pc, /* Connector punctuation */
44 ucp_Pd, /* Dash punctuation */
45 ucp_Pe, /* Close punctuation */
46 ucp_Pf, /* Final punctuation */
47 ucp_Pi, /* Initial punctuation */
48 ucp_Po, /* Other punctuation */
49 ucp_Ps, /* Open punctuation */
50 ucp_Sc, /* Currency symbol */
51 ucp_Sk, /* Modifier symbol */
52 ucp_Sm, /* Mathematical symbol */
53 ucp_So, /* Other symbol */
54 ucp_Zl, /* Line separator */
55 ucp_Zp, /* Paragraph separator */
56 ucp_Zs /* Space separator */
59 /* These are the script identifications. */
62 ucp_Arabic = G_UNICODE_SCRIPT_ARABIC,
63 ucp_Armenian = G_UNICODE_SCRIPT_ARMENIAN,
64 ucp_Bengali = G_UNICODE_SCRIPT_BENGALI,
65 ucp_Bopomofo = G_UNICODE_SCRIPT_BOPOMOFO,
66 ucp_Braille = G_UNICODE_SCRIPT_BRAILLE,
67 ucp_Buginese = G_UNICODE_SCRIPT_BUGINESE,
68 ucp_Buhid = G_UNICODE_SCRIPT_BUHID,
69 ucp_Canadian_Aboriginal = G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL,
70 ucp_Cherokee = G_UNICODE_SCRIPT_CHEROKEE,
71 ucp_Common = G_UNICODE_SCRIPT_COMMON,
72 ucp_Coptic = G_UNICODE_SCRIPT_COPTIC,
73 ucp_Cypriot = G_UNICODE_SCRIPT_CYPRIOT,
74 ucp_Cyrillic = G_UNICODE_SCRIPT_CYRILLIC,
75 ucp_Deseret = G_UNICODE_SCRIPT_DESERET,
76 ucp_Devanagari = G_UNICODE_SCRIPT_DEVANAGARI,
77 ucp_Ethiopic = G_UNICODE_SCRIPT_ETHIOPIC,
78 ucp_Georgian = G_UNICODE_SCRIPT_GEORGIAN,
79 ucp_Glagolitic = G_UNICODE_SCRIPT_GLAGOLITIC,
80 ucp_Gothic = G_UNICODE_SCRIPT_GOTHIC,
81 ucp_Greek = G_UNICODE_SCRIPT_GREEK,
82 ucp_Gujarati = G_UNICODE_SCRIPT_GUJARATI,
83 ucp_Gurmukhi = G_UNICODE_SCRIPT_GURMUKHI,
84 ucp_Han = G_UNICODE_SCRIPT_HAN,
85 ucp_Hangul = G_UNICODE_SCRIPT_HANGUL,
86 ucp_Hanunoo = G_UNICODE_SCRIPT_HANUNOO,
87 ucp_Hebrew = G_UNICODE_SCRIPT_HEBREW,
88 ucp_Hiragana = G_UNICODE_SCRIPT_HIRAGANA,
89 ucp_Inherited = G_UNICODE_SCRIPT_INHERITED,
90 ucp_Kannada = G_UNICODE_SCRIPT_KANNADA,
91 ucp_Katakana = G_UNICODE_SCRIPT_KATAKANA,
92 ucp_Kharoshthi = G_UNICODE_SCRIPT_KHAROSHTHI,
93 ucp_Khmer = G_UNICODE_SCRIPT_KHMER,
94 ucp_Lao = G_UNICODE_SCRIPT_LAO,
95 ucp_Latin = G_UNICODE_SCRIPT_LATIN,
96 ucp_Limbu = G_UNICODE_SCRIPT_LIMBU,
97 ucp_Linear_B = G_UNICODE_SCRIPT_LINEAR_B,
98 ucp_Malayalam = G_UNICODE_SCRIPT_MALAYALAM,
99 ucp_Mongolian = G_UNICODE_SCRIPT_MONGOLIAN,
100 ucp_Myanmar = G_UNICODE_SCRIPT_MYANMAR,
101 ucp_New_Tai_Lue = G_UNICODE_SCRIPT_NEW_TAI_LUE,
102 ucp_Ogham = G_UNICODE_SCRIPT_OGHAM,
103 ucp_Old_Italic = G_UNICODE_SCRIPT_OLD_ITALIC,
104 ucp_Old_Persian = G_UNICODE_SCRIPT_OLD_PERSIAN,
105 ucp_Oriya = G_UNICODE_SCRIPT_ORIYA,
106 ucp_Osmanya = G_UNICODE_SCRIPT_OSMANYA,
107 ucp_Runic = G_UNICODE_SCRIPT_RUNIC,
108 ucp_Shavian = G_UNICODE_SCRIPT_SHAVIAN,
109 ucp_Sinhala = G_UNICODE_SCRIPT_SINHALA,
110 ucp_Syloti_Nagri = G_UNICODE_SCRIPT_SYLOTI_NAGRI,
111 ucp_Syriac = G_UNICODE_SCRIPT_SYRIAC,
112 ucp_Tagalog = G_UNICODE_SCRIPT_TAGALOG,
113 ucp_Tagbanwa = G_UNICODE_SCRIPT_TAGBANWA,
114 ucp_Tai_Le = G_UNICODE_SCRIPT_TAI_LE,
115 ucp_Tamil = G_UNICODE_SCRIPT_TAMIL,
116 ucp_Telugu = G_UNICODE_SCRIPT_TELUGU,
117 ucp_Thaana = G_UNICODE_SCRIPT_THAANA,
118 ucp_Thai = G_UNICODE_SCRIPT_THAI,
119 ucp_Tibetan = G_UNICODE_SCRIPT_TIBETAN,
120 ucp_Tifinagh = G_UNICODE_SCRIPT_TIFINAGH,
121 ucp_Ugaritic = G_UNICODE_SCRIPT_UGARITIC,
122 ucp_Yi = G_UNICODE_SCRIPT_YI,
123 ucp_Balinese = G_UNICODE_SCRIPT_BALINESE,
124 ucp_Cuneiform = G_UNICODE_SCRIPT_CUNEIFORM,
125 ucp_Nko = G_UNICODE_SCRIPT_NKO,
126 ucp_Phags_Pa = G_UNICODE_SCRIPT_PHAGS_PA,
127 ucp_Phoenician = G_UNICODE_SCRIPT_PHOENICIAN,
128 ucp_Carian = G_UNICODE_SCRIPT_CARIAN,
129 ucp_Cham = G_UNICODE_SCRIPT_CHAM,
130 ucp_Kayah_Li = G_UNICODE_SCRIPT_KAYAH_LI,
131 ucp_Lepcha = G_UNICODE_SCRIPT_LEPCHA,
132 ucp_Lycian = G_UNICODE_SCRIPT_LYCIAN,
133 ucp_Lydian = G_UNICODE_SCRIPT_LYDIAN,
134 ucp_Ol_Chiki = G_UNICODE_SCRIPT_OL_CHIKI,
135 ucp_Rejang = G_UNICODE_SCRIPT_REJANG,
136 ucp_Saurashtra = G_UNICODE_SCRIPT_SAURASHTRA,
137 ucp_Sundanese = G_UNICODE_SCRIPT_SUNDANESE,
138 ucp_Vai = G_UNICODE_SCRIPT_VAI,
139 ucp_Avestan = G_UNICODE_SCRIPT_AVESTAN,
140 ucp_Bamum = G_UNICODE_SCRIPT_BAMUM,
141 ucp_Egyptian_Hieroglyphs = G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS,
142 ucp_Imperial_Aramaic = G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC,
143 ucp_Inscriptional_Pahlavi = G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI,
144 ucp_Inscriptional_Parthian = G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN,
145 ucp_Javanese = G_UNICODE_SCRIPT_JAVANESE,
146 ucp_Kaithi = G_UNICODE_SCRIPT_KAITHI,
147 ucp_Lisu = G_UNICODE_SCRIPT_LISU,
148 ucp_Meetei_Mayek = G_UNICODE_SCRIPT_MEETEI_MAYEK,
149 ucp_Old_South_Arabian = G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN,
150 ucp_Old_Turkic = G_UNICODE_SCRIPT_OLD_TURKISH,
151 ucp_Samaritan = G_UNICODE_SCRIPT_SAMARITAN,
152 ucp_Tai_Tham = G_UNICODE_SCRIPT_TAI_THAM,
153 ucp_Tai_Viet = G_UNICODE_SCRIPT_TAI_VIET