2 * Copyright 1999 Computing Research Labs, New Mexico State University
4 * Permission is hereby granted, free of charge, to any person obtaining a
5 * copy of this software and associated documentation files (the "Software"),
6 * to deal in the Software without restriction, including without limitation
7 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
8 * and/or sell copies of the Software, and to permit persons to whom the
9 * Software is furnished to do so, subject to the following conditions:
11 * The above copyright notice and this permission notice shall be included in
12 * all copies or substantial portions of the Software.
14 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
15 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
16 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
17 * THE COMPUTING RESEARCH LAB OR NEW MEXICO STATE UNIVERSITY BE LIABLE FOR ANY
18 * CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT
19 * OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR
20 * THE USE OR OTHER DEALINGS IN THE SOFTWARE.
26 * $Id: ucdata.h,v 1.5 1999/11/19 15:24:29 mleisher Exp $
40 #define UCDATA_VERSION "2.3"
42 /**************************************************************************
44 * Masks and macros for character properties.
46 **************************************************************************/
49 * Values that can appear in the `mask1' parameter of the ucisprop()
52 #define UC_MN 0x00000001 /* Mark, Non-Spacing */
53 #define UC_MC 0x00000002 /* Mark, Spacing Combining */
54 #define UC_ME 0x00000004 /* Mark, Enclosing */
55 #define UC_ND 0x00000008 /* Number, Decimal Digit */
56 #define UC_NL 0x00000010 /* Number, Letter */
57 #define UC_NO 0x00000020 /* Number, Other */
58 #define UC_ZS 0x00000040 /* Separator, Space */
59 #define UC_ZL 0x00000080 /* Separator, Line */
60 #define UC_ZP 0x00000100 /* Separator, Paragraph */
61 #define UC_CC 0x00000200 /* Other, Control */
62 #define UC_CF 0x00000400 /* Other, Format */
63 #define UC_OS 0x00000800 /* Other, Surrogate */
64 #define UC_CO 0x00001000 /* Other, Private Use */
65 #define UC_CN 0x00002000 /* Other, Not Assigned */
66 #define UC_LU 0x00004000 /* Letter, Uppercase */
67 #define UC_LL 0x00008000 /* Letter, Lowercase */
68 #define UC_LT 0x00010000 /* Letter, Titlecase */
69 #define UC_LM 0x00020000 /* Letter, Modifier */
70 #define UC_LO 0x00040000 /* Letter, Other */
71 #define UC_PC 0x00080000 /* Punctuation, Connector */
72 #define UC_PD 0x00100000 /* Punctuation, Dash */
73 #define UC_PS 0x00200000 /* Punctuation, Open */
74 #define UC_PE 0x00400000 /* Punctuation, Close */
75 #define UC_PO 0x00800000 /* Punctuation, Other */
76 #define UC_SM 0x01000000 /* Symbol, Math */
77 #define UC_SC 0x02000000 /* Symbol, Currency */
78 #define UC_SK 0x04000000 /* Symbol, Modifier */
79 #define UC_SO 0x08000000 /* Symbol, Other */
80 #define UC_L 0x10000000 /* Left-To-Right */
81 #define UC_R 0x20000000 /* Right-To-Left */
82 #define UC_EN 0x40000000 /* European Number */
83 #define UC_ES 0x80000000 /* European Number Separator */
86 * Values that can appear in the `mask2' parameter of the ucisprop()
89 #define UC_ET 0x00000001 /* European Number Terminator */
90 #define UC_AN 0x00000002 /* Arabic Number */
91 #define UC_CS 0x00000004 /* Common Number Separator */
92 #define UC_B 0x00000008 /* Block Separator */
93 #define UC_S 0x00000010 /* Segment Separator */
94 #define UC_WS 0x00000020 /* Whitespace */
95 #define UC_ON 0x00000040 /* Other Neutrals */
97 * Implementation specific character properties.
99 #define UC_CM 0x00000080 /* Composite */
100 #define UC_NB 0x00000100 /* Non-Breaking */
101 #define UC_SY 0x00000200 /* Symmetric */
102 #define UC_HD 0x00000400 /* Hex Digit */
103 #define UC_QM 0x00000800 /* Quote Mark */
104 #define UC_MR 0x00001000 /* Mirroring */
105 #define UC_SS 0x00002000 /* Space, other */
107 #define UC_CP 0x00004000 /* Defined */
110 * Added for UnicodeData-2.1.3.
112 #define UC_PI 0x00008000 /* Punctuation, Initial */
113 #define UC_PF 0x00010000 /* Punctuation, Final */
116 * This is the primary function for testing to see if a character has some set
117 * of properties. The macros that test for various character properties all
118 * call this function with some set of masks.
120 extern int ucisprop __((unsigned long code, unsigned long mask1,
121 unsigned long mask2));
123 #define ucisalpha(cc) ucisprop(cc, UC_LU|UC_LL|UC_LM|UC_LO|UC_LT, 0)
124 #define ucisdigit(cc) ucisprop(cc, UC_ND, 0)
125 #define ucisalnum(cc) ucisprop(cc, UC_LU|UC_LL|UC_LM|UC_LO|UC_LT|UC_ND, 0)
126 #define uciscntrl(cc) ucisprop(cc, UC_CC|UC_CF, 0)
127 #define ucisspace(cc) ucisprop(cc, UC_ZS|UC_SS, 0)
128 #define ucisblank(cc) ucisprop(cc, UC_ZS, 0)
129 #define ucispunct(cc) ucisprop(cc, UC_PD|UC_PS|UC_PE|UC_PO, UC_PI|UC_PF)
130 #define ucisgraph(cc) ucisprop(cc, UC_MN|UC_MC|UC_ME|UC_ND|UC_NL|UC_NO|\
131 UC_LU|UC_LL|UC_LT|UC_LM|UC_LO|UC_PC|UC_PD|\
132 UC_PS|UC_PE|UC_PO|UC_SM|UC_SM|UC_SC|UC_SK|\
134 #define ucisprint(cc) ucisprop(cc, UC_MN|UC_MC|UC_ME|UC_ND|UC_NL|UC_NO|\
135 UC_LU|UC_LL|UC_LT|UC_LM|UC_LO|UC_PC|UC_PD|\
136 UC_PS|UC_PE|UC_PO|UC_SM|UC_SM|UC_SC|UC_SK|\
137 UC_SO|UC_ZS, UC_PI|UC_PF)
138 #define ucisupper(cc) ucisprop(cc, UC_LU, 0)
139 #define ucislower(cc) ucisprop(cc, UC_LL, 0)
140 #define ucistitle(cc) ucisprop(cc, UC_LT, 0)
141 #define ucisxdigit(cc) ucisprop(cc, 0, UC_HD)
143 #define ucisisocntrl(cc) ucisprop(cc, UC_CC, 0)
144 #define ucisfmtcntrl(cc) ucisprop(cc, UC_CF, 0)
146 #define ucissymbol(cc) ucisprop(cc, UC_SM|UC_SC|UC_SO|UC_SK, 0)
147 #define ucisnumber(cc) ucisprop(cc, UC_ND|UC_NO|UC_NL, 0)
148 #define ucisnonspacing(cc) ucisprop(cc, UC_MN, 0)
149 #define ucisopenpunct(cc) ucisprop(cc, UC_PS, 0)
150 #define ucisclosepunct(cc) ucisprop(cc, UC_PE, 0)
151 #define ucisinitialpunct(cc) ucisprop(cc, 0, UC_PI)
152 #define ucisfinalpunct(cc) ucisprop(cc, 0, UC_PF)
154 #define uciscomposite(cc) ucisprop(cc, 0, UC_CM)
155 #define ucishex(cc) ucisprop(cc, 0, UC_HD)
156 #define ucisquote(cc) ucisprop(cc, 0, UC_QM)
157 #define ucissymmetric(cc) ucisprop(cc, 0, UC_SY)
158 #define ucismirroring(cc) ucisprop(cc, 0, UC_MR)
159 #define ucisnonbreaking(cc) ucisprop(cc, 0, UC_NB)
162 * Directionality macros.
164 #define ucisrtl(cc) ucisprop(cc, UC_R, 0)
165 #define ucisltr(cc) ucisprop(cc, UC_L, 0)
166 #define ucisstrong(cc) ucisprop(cc, UC_L|UC_R, 0)
167 #define ucisweak(cc) ucisprop(cc, UC_EN|UC_ES, UC_ET|UC_AN|UC_CS)
168 #define ucisneutral(cc) ucisprop(cc, 0, UC_B|UC_S|UC_WS|UC_ON)
169 #define ucisseparator(cc) ucisprop(cc, 0, UC_B|UC_S)
172 * Other macros inspired by John Cowan.
174 #define ucismark(cc) ucisprop(cc, UC_MN|UC_MC|UC_ME, 0)
175 #define ucismodif(cc) ucisprop(cc, UC_LM, 0)
176 #define ucisletnum(cc) ucisprop(cc, UC_NL, 0)
177 #define ucisconnect(cc) ucisprop(cc, UC_PC, 0)
178 #define ucisdash(cc) ucisprop(cc, UC_PD, 0)
179 #define ucismath(cc) ucisprop(cc, UC_SM, 0)
180 #define uciscurrency(cc) ucisprop(cc, UC_SC, 0)
181 #define ucismodifsymbol(cc) ucisprop(cc, UC_SK, 0)
182 #define ucisnsmark(cc) ucisprop(cc, UC_MN, 0)
183 #define ucisspmark(cc) ucisprop(cc, UC_MC, 0)
184 #define ucisenclosing(cc) ucisprop(cc, UC_ME, 0)
185 #define ucisprivate(cc) ucisprop(cc, UC_CO, 0)
186 #define ucissurrogate(cc) ucisprop(cc, UC_OS, 0)
187 #define ucislsep(cc) ucisprop(cc, UC_ZL, 0)
188 #define ucispsep(cc) ucisprop(cc, UC_ZP, 0)
190 #define ucisidentstart(cc) ucisprop(cc, UC_LU|UC_LL|UC_LT|UC_LO|UC_NL, 0)
191 #define ucisidentpart(cc) ucisprop(cc, UC_LU|UC_LL|UC_LT|UC_LO|UC_NL|\
192 UC_MN|UC_MC|UC_ND|UC_PC|UC_CF, 0)
194 #define ucisdefined(cc) ucisprop(cc, 0, UC_CP)
195 #define ucisundefined(cc) !ucisprop(cc, 0, UC_CP)
198 * Other miscellaneous character property macros.
200 #define ucishan(cc) (((cc) >= 0x4e00 && (cc) <= 0x9fff) ||\
201 ((cc) >= 0xf900 && (cc) <= 0xfaff))
202 #define ucishangul(cc) ((cc) >= 0xac00 && (cc) <= 0xd7ff)
204 /**************************************************************************
206 * Functions for case conversion.
208 **************************************************************************/
210 extern unsigned long uctoupper __((unsigned long code));
211 extern unsigned long uctolower __((unsigned long code));
212 extern unsigned long uctotitle __((unsigned long code));
214 /**************************************************************************
216 * Functions for getting decompositions.
218 **************************************************************************/
221 * This routine determines if the code has a decomposition. If it returns 0,
222 * there is no decomposition. Any other value indicates a decomposition was
225 extern int ucdecomp __((unsigned long code, unsigned long *num,
227 unsigned long **decomp));
230 * If the code is a Hangul syllable, this routine decomposes it into the array
231 * passed. The array size should be at least 3.
233 extern int ucdecomp_hangul __((unsigned long code, unsigned long *num,
234 unsigned long decomp[]));
236 /**************************************************************************
238 * Functions for getting combining classes.
240 **************************************************************************/
243 * This will return the combining class for a character to be used with the
244 * Canonical Ordering algorithm.
246 extern unsigned long uccombining_class __((unsigned long code));
248 /**************************************************************************
250 * Functions for getting numbers and digits.
252 **************************************************************************/
259 extern int ucnumber_lookup __((unsigned long code, struct ucnumber *num));
260 extern int ucdigit_lookup __((unsigned long code, int *digit));
263 * For compatibility with John Cowan's "uctype" package.
265 extern struct ucnumber ucgetnumber __((unsigned long code));
266 extern int ucgetdigit __((unsigned long code));
268 /**************************************************************************
270 * Functions library initialization and cleanup.
272 **************************************************************************/
275 * Macros for specifying the data tables to be loaded, unloaded, or reloaded
276 * by the ucdata_load(), ucdata_unload(), and ucdata_reload() routines.
278 #define UCDATA_CASE 0x01
279 #define UCDATA_CTYPE 0x02
280 #define UCDATA_DECOMP 0x04
281 #define UCDATA_CMBCL 0x08
282 #define UCDATA_NUM 0x10
284 #define UCDATA_ALL (UCDATA_CASE|UCDATA_CTYPE|UCDATA_DECOMP|\
285 UCDATA_CMBCL|UCDATA_NUM)
288 * Functions to load, unload, and reload specific data files.
290 extern void ucdata_load __((char *paths, int mask));
291 extern void ucdata_unload __((int mask));
292 extern void ucdata_reload __((char *paths, int mask));
295 * Deprecated functions, now just compatibility macros.
297 #define ucdata_setup(p) ucdata_load(p, UCDATA_ALL)
298 #define ucdata_cleanup() ucdata_unload(UCDATA_ALL)
306 #endif /* _h_ucdata */