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 UCD access macros. New values that are added for new releases of Unicode
should always be at the end of each enum, for backwards compatibility.

IMPORTANT: Note also that the specific numeric values of the enums have to be
the same as the values that are generated by the maint/MultiStage2.py script,
where the equivalent property descriptive names are listed in vectors. */

/* 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 categories. */

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 grapheme break properties. Note that the code for processing them
assumes that the values are less than 16. If more values are added that take
the number to 16 or more, the code will have to be rewritten. */

enum {
  ucp_gbCR,                /*  0 */
  ucp_gbLF,                /*  1 */
  ucp_gbControl,           /*  2 */
  ucp_gbExtend,            /*  3 */
  ucp_gbPrepend,           /*  4 */
  ucp_gbSpacingMark,       /*  5 */
  ucp_gbL,                 /*  6 Hangul syllable type L */
  ucp_gbV,                 /*  7 Hangul syllable type V */
  ucp_gbT,                 /*  8 Hangul syllable type T */
  ucp_gbLV,                /*  9 Hangul syllable type LV */
  ucp_gbLVT,               /* 10 Hangul syllable type LVT */
  ucp_gbRegionalIndicator, /* 11 */
  ucp_gbOther              /* 12 */
};

/* 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,
  /* New for Unicode 5.2: */
  ucp_Avestan,
  ucp_Bamum,
  ucp_Egyptian_Hieroglyphs,
  ucp_Imperial_Aramaic,
  ucp_Inscriptional_Pahlavi,
  ucp_Inscriptional_Parthian,
  ucp_Javanese,
  ucp_Kaithi,
  ucp_Lisu,
  ucp_Meetei_Mayek,
  ucp_Old_South_Arabian,
  ucp_Old_Turkic,
  ucp_Samaritan,
  ucp_Tai_Tham,
  ucp_Tai_Viet,
  /* New for Unicode 6.0.0: */
  ucp_Batak,
  ucp_Brahmi,
  ucp_Mandaic,
  /* New for Unicode 6.1.0: */
  ucp_Chakma,
  ucp_Meroitic_Cursive,
  ucp_Meroitic_Hieroglyphs,
  ucp_Miao,
  ucp_Sharada,
  ucp_Sora_Sompeng,
  ucp_Takri
};

#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	ph10	387	the UCD access macros. New values that are added for new releases of Unicode
10	ph10	1011	should always be at the end of each enum, for backwards compatibility.
11	nigel	75
12	ph10	1011	IMPORTANT: Note also that the specific numeric values of the enums have to be
13			the same as the values that are generated by the maint/MultiStage2.py script,
14			where the equivalent property descriptive names are listed in vectors. */
15
16	nigel	87	/* These are the general character categories. */
17
18	nigel	75	enum {
19			ucp_C, /* Other */
20			ucp_L, /* Letter */
21			ucp_M, /* Mark */
22			ucp_N, /* Number */
23			ucp_P, /* Punctuation */
24			ucp_S, /* Symbol */
25			ucp_Z /* Separator */
26			};
27
28	ph10	1011	/* These are the particular character categories. */
29	nigel	75
30			enum {
31			ucp_Cc, /* Control */
32			ucp_Cf, /* Format */
33			ucp_Cn, /* Unassigned */
34			ucp_Co, /* Private use */
35			ucp_Cs, /* Surrogate */
36			ucp_Ll, /* Lower case letter */
37			ucp_Lm, /* Modifier letter */
38			ucp_Lo, /* Other letter */
39			ucp_Lt, /* Title case letter */
40			ucp_Lu, /* Upper case letter */
41			ucp_Mc, /* Spacing mark */
42			ucp_Me, /* Enclosing mark */
43			ucp_Mn, /* Non-spacing mark */
44			ucp_Nd, /* Decimal number */
45			ucp_Nl, /* Letter number */
46			ucp_No, /* Other number */
47			ucp_Pc, /* Connector punctuation */
48			ucp_Pd, /* Dash punctuation */
49			ucp_Pe, /* Close punctuation */
50			ucp_Pf, /* Final punctuation */
51			ucp_Pi, /* Initial punctuation */
52			ucp_Po, /* Other punctuation */
53			ucp_Ps, /* Open punctuation */
54			ucp_Sc, /* Currency symbol */
55			ucp_Sk, /* Modifier symbol */
56			ucp_Sm, /* Mathematical symbol */
57			ucp_So, /* Other symbol */
58			ucp_Zl, /* Line separator */
59			ucp_Zp, /* Paragraph separator */
60			ucp_Zs /* Space separator */
61			};
62
63	ph10	1221	/* These are grapheme break properties. Note that the code for processing them
64			assumes that the values are less than 16. If more values are added that take
65	ph10	1011	the number to 16 or more, the code will have to be rewritten. */
66
67			enum {
68	chpe	1050	ucp_gbCR, /* 0 */
69			ucp_gbLF, /* 1 */
70			ucp_gbControl, /* 2 */
71			ucp_gbExtend, /* 3 */
72			ucp_gbPrepend, /* 4 */
73			ucp_gbSpacingMark, /* 5 */
74			ucp_gbL, /* 6 Hangul syllable type L */
75			ucp_gbV, /* 7 Hangul syllable type V */
76			ucp_gbT, /* 8 Hangul syllable type T */
77			ucp_gbLV, /* 9 Hangul syllable type LV */
78			ucp_gbLVT, /* 10 Hangul syllable type LVT */
79			ucp_gbRegionalIndicator, /* 11 */
80			ucp_gbOther /* 12 */
81	ph10	1011	};
82
83	nigel	87	/* These are the script identifications. */
84
85			enum {
86			ucp_Arabic,
87			ucp_Armenian,
88			ucp_Bengali,
89			ucp_Bopomofo,
90			ucp_Braille,
91			ucp_Buginese,
92			ucp_Buhid,
93			ucp_Canadian_Aboriginal,
94			ucp_Cherokee,
95			ucp_Common,
96			ucp_Coptic,
97			ucp_Cypriot,
98			ucp_Cyrillic,
99			ucp_Deseret,
100			ucp_Devanagari,
101			ucp_Ethiopic,
102			ucp_Georgian,
103			ucp_Glagolitic,
104			ucp_Gothic,
105			ucp_Greek,
106			ucp_Gujarati,
107			ucp_Gurmukhi,
108			ucp_Han,
109			ucp_Hangul,
110			ucp_Hanunoo,
111			ucp_Hebrew,
112			ucp_Hiragana,
113			ucp_Inherited,
114			ucp_Kannada,
115			ucp_Katakana,
116			ucp_Kharoshthi,
117			ucp_Khmer,
118			ucp_Lao,
119			ucp_Latin,
120			ucp_Limbu,
121			ucp_Linear_B,
122			ucp_Malayalam,
123			ucp_Mongolian,
124			ucp_Myanmar,
125			ucp_New_Tai_Lue,
126			ucp_Ogham,
127			ucp_Old_Italic,
128			ucp_Old_Persian,
129			ucp_Oriya,
130			ucp_Osmanya,
131			ucp_Runic,
132			ucp_Shavian,
133			ucp_Sinhala,
134			ucp_Syloti_Nagri,
135			ucp_Syriac,
136			ucp_Tagalog,
137			ucp_Tagbanwa,
138			ucp_Tai_Le,
139			ucp_Tamil,
140			ucp_Telugu,
141			ucp_Thaana,
142			ucp_Thai,
143			ucp_Tibetan,
144			ucp_Tifinagh,
145			ucp_Ugaritic,
146	nigel	93	ucp_Yi,
147	ph10	351	/* New for Unicode 5.0: */
148			ucp_Balinese,
149			ucp_Cuneiform,
150			ucp_Nko,
151			ucp_Phags_Pa,
152			ucp_Phoenician,
153			/* New for Unicode 5.1: */
154			ucp_Carian,
155			ucp_Cham,
156			ucp_Kayah_Li,
157			ucp_Lepcha,
158			ucp_Lycian,
159			ucp_Lydian,
160			ucp_Ol_Chiki,
161			ucp_Rejang,
162			ucp_Saurashtra,
163			ucp_Sundanese,
164	ph10	491	ucp_Vai,
165			/* New for Unicode 5.2: */
166			ucp_Avestan,
167			ucp_Bamum,
168			ucp_Egyptian_Hieroglyphs,
169			ucp_Imperial_Aramaic,
170			ucp_Inscriptional_Pahlavi,
171			ucp_Inscriptional_Parthian,
172			ucp_Javanese,
173			ucp_Kaithi,
174			ucp_Lisu,
175			ucp_Meetei_Mayek,
176			ucp_Old_South_Arabian,
177			ucp_Old_Turkic,
178			ucp_Samaritan,
179			ucp_Tai_Tham,
180	ph10	592	ucp_Tai_Viet,
181			/* New for Unicode 6.0.0: */
182			ucp_Batak,
183			ucp_Brahmi,
184	ph10	942	ucp_Mandaic,
185			/* New for Unicode 6.1.0: */
186			ucp_Chakma,
187			ucp_Meroitic_Cursive,
188			ucp_Meroitic_Hieroglyphs,
189			ucp_Miao,
190			ucp_Sharada,
191			ucp_Sora_Sompeng,
192			ucp_Takri
193	nigel	87	};
194
195	nigel	77	#endif
196	nigel	75
197			/* End of ucp.h */