code/trunk/ucp.h

/*************************************************
*          Unicode Property Table handler        *
*************************************************/

#ifndef _UCP_H
#define _UCP_H

/* This file contains definitions of the property values that are returned by
the function _pcre_ucp_findprop(). */

/* These are the general character categories. */

enum {
  ucp_C,     /* Other */
  ucp_L,     /* Letter */
  ucp_M,     /* Mark */
  ucp_N,     /* Number */
  ucp_P,     /* Punctuation */
  ucp_S,     /* Symbol */
  ucp_Z      /* Separator */
};

/* These are the particular character types. */

enum {
  ucp_Cc,    /* Control */
  ucp_Cf,    /* Format */
  ucp_Cn,    /* Unassigned */
  ucp_Co,    /* Private use */
  ucp_Cs,    /* Surrogate */
  ucp_Ll,    /* Lower case letter */
  ucp_Lm,    /* Modifier letter */
  ucp_Lo,    /* Other letter */
  ucp_Lt,    /* Title case letter */
  ucp_Lu,    /* Upper case letter */
  ucp_Mc,    /* Spacing mark */
  ucp_Me,    /* Enclosing mark */
  ucp_Mn,    /* Non-spacing mark */
  ucp_Nd,    /* Decimal number */
  ucp_Nl,    /* Letter number */
  ucp_No,    /* Other number */
  ucp_Pc,    /* Connector punctuation */
  ucp_Pd,    /* Dash punctuation */
  ucp_Pe,    /* Close punctuation */
  ucp_Pf,    /* Final punctuation */
  ucp_Pi,    /* Initial punctuation */
  ucp_Po,    /* Other punctuation */
  ucp_Ps,    /* Open punctuation */
  ucp_Sc,    /* Currency symbol */
  ucp_Sk,    /* Modifier symbol */
  ucp_Sm,    /* Mathematical symbol */
  ucp_So,    /* Other symbol */
  ucp_Zl,    /* Line separator */
  ucp_Zp,    /* Paragraph separator */
  ucp_Zs     /* Space separator */
};

/* These are the script identifications. */

enum {
  ucp_Arabic,
  ucp_Armenian,
  ucp_Bengali,
  ucp_Bopomofo,
  ucp_Braille,
  ucp_Buginese,
  ucp_Buhid,
  ucp_Canadian_Aboriginal,
  ucp_Cherokee,
  ucp_Common,
  ucp_Coptic,
  ucp_Cypriot,
  ucp_Cyrillic,
  ucp_Deseret,
  ucp_Devanagari,
  ucp_Ethiopic,
  ucp_Georgian,
  ucp_Glagolitic,
  ucp_Gothic,
  ucp_Greek,
  ucp_Gujarati,
  ucp_Gurmukhi,
  ucp_Han,
  ucp_Hangul,
  ucp_Hanunoo,
  ucp_Hebrew,
  ucp_Hiragana,
  ucp_Inherited,
  ucp_Kannada,
  ucp_Katakana,
  ucp_Kharoshthi,
  ucp_Khmer,
  ucp_Lao,
  ucp_Latin,
  ucp_Limbu,
  ucp_Linear_B,
  ucp_Malayalam,
  ucp_Mongolian,
  ucp_Myanmar,
  ucp_New_Tai_Lue,
  ucp_Ogham,
  ucp_Old_Italic,
  ucp_Old_Persian,
  ucp_Oriya,
  ucp_Osmanya,
  ucp_Runic,
  ucp_Shavian,
  ucp_Sinhala,
  ucp_Syloti_Nagri,
  ucp_Syriac,
  ucp_Tagalog,
  ucp_Tagbanwa,
  ucp_Tai_Le,
  ucp_Tamil,
  ucp_Telugu,
  ucp_Thaana,
  ucp_Thai,
  ucp_Tibetan,
  ucp_Tifinagh,
  ucp_Ugaritic,
  ucp_Yi
};

#endif

/* End of ucp.h */
1	/*************************************************
2	* Unicode Property Table handler *
3	*************************************************/
4
5	#ifndef _UCP_H
6	#define _UCP_H
7
8	/* This file contains definitions of the property values that are returned by
9	the function _pcre_ucp_findprop(). */
10
11	/* These are the general character categories. */
12
13	enum {
14	ucp_C, /* Other */
15	ucp_L, /* Letter */
16	ucp_M, /* Mark */
17	ucp_N, /* Number */
18	ucp_P, /* Punctuation */
19	ucp_S, /* Symbol */
20	ucp_Z /* Separator */
21	};
22
23	/* These are the particular character types. */
24
25	enum {
26	ucp_Cc, /* Control */
27	ucp_Cf, /* Format */
28	ucp_Cn, /* Unassigned */
29	ucp_Co, /* Private use */
30	ucp_Cs, /* Surrogate */
31	ucp_Ll, /* Lower case letter */
32	ucp_Lm, /* Modifier letter */
33	ucp_Lo, /* Other letter */
34	ucp_Lt, /* Title case letter */
35	ucp_Lu, /* Upper case letter */
36	ucp_Mc, /* Spacing mark */
37	ucp_Me, /* Enclosing mark */
38	ucp_Mn, /* Non-spacing mark */
39	ucp_Nd, /* Decimal number */
40	ucp_Nl, /* Letter number */
41	ucp_No, /* Other number */
42	ucp_Pc, /* Connector punctuation */
43	ucp_Pd, /* Dash punctuation */
44	ucp_Pe, /* Close punctuation */
45	ucp_Pf, /* Final punctuation */
46	ucp_Pi, /* Initial punctuation */
47	ucp_Po, /* Other punctuation */
48	ucp_Ps, /* Open punctuation */
49	ucp_Sc, /* Currency symbol */
50	ucp_Sk, /* Modifier symbol */
51	ucp_Sm, /* Mathematical symbol */
52	ucp_So, /* Other symbol */
53	ucp_Zl, /* Line separator */
54	ucp_Zp, /* Paragraph separator */
55	ucp_Zs /* Space separator */
56	};
57
58	/* These are the script identifications. */
59
60	enum {
61	ucp_Arabic,
62	ucp_Armenian,
63	ucp_Bengali,
64	ucp_Bopomofo,
65	ucp_Braille,
66	ucp_Buginese,
67	ucp_Buhid,
68	ucp_Canadian_Aboriginal,
69	ucp_Cherokee,
70	ucp_Common,
71	ucp_Coptic,
72	ucp_Cypriot,
73	ucp_Cyrillic,
74	ucp_Deseret,
75	ucp_Devanagari,
76	ucp_Ethiopic,
77	ucp_Georgian,
78	ucp_Glagolitic,
79	ucp_Gothic,
80	ucp_Greek,
81	ucp_Gujarati,
82	ucp_Gurmukhi,
83	ucp_Han,
84	ucp_Hangul,
85	ucp_Hanunoo,
86	ucp_Hebrew,
87	ucp_Hiragana,
88	ucp_Inherited,
89	ucp_Kannada,
90	ucp_Katakana,
91	ucp_Kharoshthi,
92	ucp_Khmer,
93	ucp_Lao,
94	ucp_Latin,
95	ucp_Limbu,
96	ucp_Linear_B,
97	ucp_Malayalam,
98	ucp_Mongolian,
99	ucp_Myanmar,
100	ucp_New_Tai_Lue,
101	ucp_Ogham,
102	ucp_Old_Italic,
103	ucp_Old_Persian,
104	ucp_Oriya,
105	ucp_Osmanya,
106	ucp_Runic,
107	ucp_Shavian,
108	ucp_Sinhala,
109	ucp_Syloti_Nagri,
110	ucp_Syriac,
111	ucp_Tagalog,
112	ucp_Tagbanwa,
113	ucp_Tai_Le,
114	ucp_Tamil,
115	ucp_Telugu,
116	ucp_Thaana,
117	ucp_Thai,
118	ucp_Tibetan,
119	ucp_Tifinagh,
120	ucp_Ugaritic,
121	ucp_Yi
122	};
123
124	#endif
125
126	/* End of ucp.h */