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(). New values that are added for new releases
of Unicode should always be at the end of each enum, for backwards
compatibility. */

/* 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,
  /* New for Unicode 5.0: */
  ucp_Balinese,
  ucp_Cuneiform,
  ucp_Nko,
  ucp_Phags_Pa,
  ucp_Phoenician,
  /* New for Unicode 5.1: */
  ucp_Carian,
  ucp_Cham,
  ucp_Kayah_Li,
  ucp_Lepcha,
  ucp_Lycian,
  ucp_Lydian,
  ucp_Ol_Chiki,
  ucp_Rejang,
  ucp_Saurashtra,
  ucp_Sundanese,
  ucp_Vai
};

#endif

/* End of ucp.h */
1	nigel	75	/*************************************************
2	nigel	87	* Unicode Property Table handler *
3	nigel	75	*************************************************/
4
5	nigel	77	#ifndef _UCP_H
6			#define _UCP_H
7
8	nigel	87	/* This file contains definitions of the property values that are returned by
9	nigel	93	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
11			compatibility. */
12	nigel	75
13	nigel	87	/* These are the general character categories. */
14
15	nigel	75	enum {
16			ucp_C, /* Other */
17			ucp_L, /* Letter */
18			ucp_M, /* Mark */
19			ucp_N, /* Number */
20			ucp_P, /* Punctuation */
21			ucp_S, /* Symbol */
22			ucp_Z /* Separator */
23			};
24
25	nigel	87	/* These are the particular character types. */
26	nigel	75
27			enum {
28			ucp_Cc, /* Control */
29			ucp_Cf, /* Format */
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 */
58			};
59
60	nigel	87	/* These are the script identifications. */
61
62			enum {
63			ucp_Arabic,
64			ucp_Armenian,
65			ucp_Bengali,
66			ucp_Bopomofo,
67			ucp_Braille,
68			ucp_Buginese,
69			ucp_Buhid,
70			ucp_Canadian_Aboriginal,
71			ucp_Cherokee,
72			ucp_Common,
73			ucp_Coptic,
74			ucp_Cypriot,
75			ucp_Cyrillic,
76			ucp_Deseret,
77			ucp_Devanagari,
78			ucp_Ethiopic,
79			ucp_Georgian,
80			ucp_Glagolitic,
81			ucp_Gothic,
82			ucp_Greek,
83			ucp_Gujarati,
84			ucp_Gurmukhi,
85			ucp_Han,
86			ucp_Hangul,
87			ucp_Hanunoo,
88			ucp_Hebrew,
89			ucp_Hiragana,
90			ucp_Inherited,
91			ucp_Kannada,
92			ucp_Katakana,
93			ucp_Kharoshthi,
94			ucp_Khmer,
95			ucp_Lao,
96			ucp_Latin,
97			ucp_Limbu,
98			ucp_Linear_B,
99			ucp_Malayalam,
100			ucp_Mongolian,
101			ucp_Myanmar,
102			ucp_New_Tai_Lue,
103			ucp_Ogham,
104			ucp_Old_Italic,
105			ucp_Old_Persian,
106			ucp_Oriya,
107			ucp_Osmanya,
108			ucp_Runic,
109			ucp_Shavian,
110			ucp_Sinhala,
111			ucp_Syloti_Nagri,
112			ucp_Syriac,
113			ucp_Tagalog,
114			ucp_Tagbanwa,
115			ucp_Tai_Le,
116			ucp_Tamil,
117			ucp_Telugu,
118			ucp_Thaana,
119			ucp_Thai,
120			ucp_Tibetan,
121			ucp_Tifinagh,
122			ucp_Ugaritic,
123	nigel	93	ucp_Yi,
124	ph10	351	/* New for Unicode 5.0: */
125			ucp_Balinese,
126			ucp_Cuneiform,
127			ucp_Nko,
128			ucp_Phags_Pa,
129			ucp_Phoenician,
130			/* New for Unicode 5.1: */
131			ucp_Carian,
132			ucp_Cham,
133			ucp_Kayah_Li,
134			ucp_Lepcha,
135			ucp_Lycian,
136			ucp_Lydian,
137			ucp_Ol_Chiki,
138			ucp_Rejang,
139			ucp_Saurashtra,
140			ucp_Sundanese,
141			ucp_Vai
142	nigel	87	};
143
144	nigel	77	#endif
145	nigel	75
146			/* End of ucp.h */