1 /*************************************************
2 * Unicode Property Table handler *
3 *************************************************/
8 /* This file contains definitions of the property values that are returned by
9 the function _pcre_ucp_findprop(). New values that are added for new releases
10 of Unicode should always be at the end of each enum, for backwards
13 /* These are the general character categories. */
20 ucp_P, /* Punctuation */
25 /* These are the particular character types. */
30 ucp_Cn, /* Unassigned */
31 ucp_Co, /* Private use */
32 ucp_Cs, /* Surrogate */
33 ucp_Ll, /* Lower case letter */
34 ucp_Lm, /* Modifier letter */
35 ucp_Lo, /* Other letter */
36 ucp_Lt, /* Title case letter */
37 ucp_Lu, /* Upper case letter */
38 ucp_Mc, /* Spacing mark */
39 ucp_Me, /* Enclosing mark */
40 ucp_Mn, /* Non-spacing mark */
41 ucp_Nd, /* Decimal number */
42 ucp_Nl, /* Letter number */
43 ucp_No, /* Other number */
44 ucp_Pc, /* Connector punctuation */
45 ucp_Pd, /* Dash punctuation */
46 ucp_Pe, /* Close punctuation */
47 ucp_Pf, /* Final punctuation */
48 ucp_Pi, /* Initial punctuation */
49 ucp_Po, /* Other punctuation */
50 ucp_Ps, /* Open punctuation */
51 ucp_Sc, /* Currency symbol */
52 ucp_Sk, /* Modifier symbol */
53 ucp_Sm, /* Mathematical symbol */
54 ucp_So, /* Other symbol */
55 ucp_Zl, /* Line separator */
56 ucp_Zp, /* Paragraph separator */
57 ucp_Zs /* Space separator */
60 /* These are the script identifications. */
63 ucp_Arabic = G_UNICODE_SCRIPT_ARABIC,
64 ucp_Armenian = G_UNICODE_SCRIPT_ARMENIAN,
65 ucp_Bengali = G_UNICODE_SCRIPT_BENGALI,
66 ucp_Bopomofo = G_UNICODE_SCRIPT_BOPOMOFO,
67 ucp_Braille = G_UNICODE_SCRIPT_BRAILLE,
68 ucp_Buginese = G_UNICODE_SCRIPT_BUGINESE,
69 ucp_Buhid = G_UNICODE_SCRIPT_BUHID,
70 ucp_Canadian_Aboriginal = G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL,
71 ucp_Cherokee = G_UNICODE_SCRIPT_CHEROKEE,
72 ucp_Common = G_UNICODE_SCRIPT_COMMON,
73 ucp_Coptic = G_UNICODE_SCRIPT_COPTIC,
74 ucp_Cypriot = G_UNICODE_SCRIPT_CYPRIOT,
75 ucp_Cyrillic = G_UNICODE_SCRIPT_CYRILLIC,
76 ucp_Deseret = G_UNICODE_SCRIPT_DESERET,
77 ucp_Devanagari = G_UNICODE_SCRIPT_DEVANAGARI,
78 ucp_Ethiopic = G_UNICODE_SCRIPT_ETHIOPIC,
79 ucp_Georgian = G_UNICODE_SCRIPT_GEORGIAN,
80 ucp_Glagolitic = G_UNICODE_SCRIPT_GLAGOLITIC,
81 ucp_Gothic = G_UNICODE_SCRIPT_GOTHIC,
82 ucp_Greek = G_UNICODE_SCRIPT_GREEK,
83 ucp_Gujarati = G_UNICODE_SCRIPT_GUJARATI,
84 ucp_Gurmukhi = G_UNICODE_SCRIPT_GURMUKHI,
85 ucp_Han = G_UNICODE_SCRIPT_HAN,
86 ucp_Hangul = G_UNICODE_SCRIPT_HANGUL,
87 ucp_Hanunoo = G_UNICODE_SCRIPT_HANUNOO,
88 ucp_Hebrew = G_UNICODE_SCRIPT_HEBREW,
89 ucp_Hiragana = G_UNICODE_SCRIPT_HIRAGANA,
90 ucp_Inherited = G_UNICODE_SCRIPT_INHERITED,
91 ucp_Kannada = G_UNICODE_SCRIPT_KANNADA,
92 ucp_Katakana = G_UNICODE_SCRIPT_KATAKANA,
93 ucp_Kharoshthi = G_UNICODE_SCRIPT_KHAROSHTHI,
94 ucp_Khmer = G_UNICODE_SCRIPT_KHMER,
95 ucp_Lao = G_UNICODE_SCRIPT_LAO,
96 ucp_Latin = G_UNICODE_SCRIPT_LATIN,
97 ucp_Limbu = G_UNICODE_SCRIPT_LIMBU,
98 ucp_Linear_B = G_UNICODE_SCRIPT_LINEAR_B,
99 ucp_Malayalam = G_UNICODE_SCRIPT_MALAYALAM,
100 ucp_Mongolian = G_UNICODE_SCRIPT_MONGOLIAN,
101 ucp_Myanmar = G_UNICODE_SCRIPT_MYANMAR,
102 ucp_New_Tai_Lue = G_UNICODE_SCRIPT_NEW_TAI_LUE,
103 ucp_Ogham = G_UNICODE_SCRIPT_OGHAM,
104 ucp_Old_Italic = G_UNICODE_SCRIPT_OLD_ITALIC,
105 ucp_Old_Persian = G_UNICODE_SCRIPT_OLD_PERSIAN,
106 ucp_Oriya = G_UNICODE_SCRIPT_ORIYA,
107 ucp_Osmanya = G_UNICODE_SCRIPT_OSMANYA,
108 ucp_Runic = G_UNICODE_SCRIPT_RUNIC,
109 ucp_Shavian = G_UNICODE_SCRIPT_SHAVIAN,
110 ucp_Sinhala = G_UNICODE_SCRIPT_SINHALA,
111 ucp_Syloti_Nagri = G_UNICODE_SCRIPT_SYLOTI_NAGRI,
112 ucp_Syriac = G_UNICODE_SCRIPT_SYRIAC,
113 ucp_Tagalog = G_UNICODE_SCRIPT_TAGALOG,
114 ucp_Tagbanwa = G_UNICODE_SCRIPT_TAGBANWA,
115 ucp_Tai_Le = G_UNICODE_SCRIPT_TAI_LE,
116 ucp_Tamil = G_UNICODE_SCRIPT_TAMIL,
117 ucp_Telugu = G_UNICODE_SCRIPT_TELUGU,
118 ucp_Thaana = G_UNICODE_SCRIPT_THAANA,
119 ucp_Thai = G_UNICODE_SCRIPT_THAI,
120 ucp_Tibetan = G_UNICODE_SCRIPT_TIBETAN,
121 ucp_Tifinagh = G_UNICODE_SCRIPT_TIFINAGH,
122 ucp_Ugaritic = G_UNICODE_SCRIPT_UGARITIC,
123 ucp_Yi = G_UNICODE_SCRIPT_YI,
124 ucp_Balinese = G_UNICODE_SCRIPT_BALINESE, /* New for Unicode 5.0.0 */
125 ucp_Cuneiform = G_UNICODE_SCRIPT_CUNEIFORM, /* New for Unicode 5.0.0 */
126 ucp_Nko = G_UNICODE_SCRIPT_NKO, /* New for Unicode 5.0.0 */
127 ucp_Phags_Pa = G_UNICODE_SCRIPT_PHAGS_PA, /* New for Unicode 5.0.0 */
128 ucp_Phoenician = G_UNICODE_SCRIPT_PHOENICIAN, /* New for Unicode 5.0.0 */
129 ucp_Carian = G_UNICODE_SCRIPT_CARIAN, /* New for Unicode 5.1 */
130 ucp_Cham = G_UNICODE_SCRIPT_CHAM, /* New for Unicode 5.1 */
131 ucp_Kayah_Li = G_UNICODE_SCRIPT_KAYAH_LI, /* New for Unicode 5.1 */
132 ucp_Lepcha = G_UNICODE_SCRIPT_LEPCHA, /* New for Unicode 5.1 */
133 ucp_Lycian = G_UNICODE_SCRIPT_LYCIAN, /* New for Unicode 5.1 */
134 ucp_Lydian = G_UNICODE_SCRIPT_LYDIAN, /* New for Unicode 5.1 */
135 ucp_Ol_Chiki = G_UNICODE_SCRIPT_OL_CHIKI, /* New for Unicode 5.1 */
136 ucp_Rejang = G_UNICODE_SCRIPT_REJANG, /* New for Unicode 5.1 */
137 ucp_Saurashtra = G_UNICODE_SCRIPT_SAURASHTRA, /* New for Unicode 5.1 */
138 ucp_Sundanese = G_UNICODE_SCRIPT_SUNDANESE, /* New for Unicode 5.1 */
139 ucp_Vai = G_UNICODE_SCRIPT_VAI /* New for Unicode 5.1 */