1 /*
2 * chvalid.c: this module implements the character range
3 * validation APIs
4 *
5 * This file is automatically generated from the cvs source
6 * definition files using the genChRanges.py Python script
7 *
8 * Generation date: Mon Mar 27 11:09:48 2006
9 * Sources: chvalid.def
10 * William Brack <wbrack@mmm.com.hk>
11 */
12
13 #define IN_LIBXML
14 #include "libxml.h"
15 #include <libxml/chvalid.h>
16
17 #include <stddef.h>
18
19 /*
20 * The initial tables ({func_name}_tab) are used to validate whether a
21 * single-byte character is within the specified group. Each table
22 * contains 256 bytes, with each byte representing one of the 256
23 * possible characters. If the table byte is set, the character is
24 * allowed.
25 *
26 */
27 const unsigned char xmlIsPubidChar_tab[256] = {
28 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x00,
29 0x00, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
30 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x00, 0x01,
31 0x01, 0x01, 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
32 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
33 0x00, 0x01, 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
34 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
35 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, 0x01,
36 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
37 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
38 0x01, 0x01, 0x01, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
39 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
40 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
41 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
42 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
43 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
44 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
45 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
46 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
47 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
48 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
49 0x00, 0x00, 0x00, 0x00 };
50
51 static const xmlChSRange xmlIsBaseChar_srng[] = { {0x100, 0x131},
52 {0x134, 0x13e}, {0x141, 0x148}, {0x14a, 0x17e}, {0x180, 0x1c3},
53 {0x1cd, 0x1f0}, {0x1f4, 0x1f5}, {0x1fa, 0x217}, {0x250, 0x2a8},
54 {0x2bb, 0x2c1}, {0x386, 0x386}, {0x388, 0x38a}, {0x38c, 0x38c},
55 {0x38e, 0x3a1}, {0x3a3, 0x3ce}, {0x3d0, 0x3d6}, {0x3da, 0x3da},
56 {0x3dc, 0x3dc}, {0x3de, 0x3de}, {0x3e0, 0x3e0}, {0x3e2, 0x3f3},
57 {0x401, 0x40c}, {0x40e, 0x44f}, {0x451, 0x45c}, {0x45e, 0x481},
58 {0x490, 0x4c4}, {0x4c7, 0x4c8}, {0x4cb, 0x4cc}, {0x4d0, 0x4eb},
59 {0x4ee, 0x4f5}, {0x4f8, 0x4f9}, {0x531, 0x556}, {0x559, 0x559},
60 {0x561, 0x586}, {0x5d0, 0x5ea}, {0x5f0, 0x5f2}, {0x621, 0x63a},
61 {0x641, 0x64a}, {0x671, 0x6b7}, {0x6ba, 0x6be}, {0x6c0, 0x6ce},
62 {0x6d0, 0x6d3}, {0x6d5, 0x6d5}, {0x6e5, 0x6e6}, {0x905, 0x939},
63 {0x93d, 0x93d}, {0x958, 0x961}, {0x985, 0x98c}, {0x98f, 0x990},
64 {0x993, 0x9a8}, {0x9aa, 0x9b0}, {0x9b2, 0x9b2}, {0x9b6, 0x9b9},
65 {0x9dc, 0x9dd}, {0x9df, 0x9e1}, {0x9f0, 0x9f1}, {0xa05, 0xa0a},
66 {0xa0f, 0xa10}, {0xa13, 0xa28}, {0xa2a, 0xa30}, {0xa32, 0xa33},
67 {0xa35, 0xa36}, {0xa38, 0xa39}, {0xa59, 0xa5c}, {0xa5e, 0xa5e},
68 {0xa72, 0xa74}, {0xa85, 0xa8b}, {0xa8d, 0xa8d}, {0xa8f, 0xa91},
69 {0xa93, 0xaa8}, {0xaaa, 0xab0}, {0xab2, 0xab3}, {0xab5, 0xab9},
70 {0xabd, 0xabd}, {0xae0, 0xae0}, {0xb05, 0xb0c}, {0xb0f, 0xb10},
71 {0xb13, 0xb28}, {0xb2a, 0xb30}, {0xb32, 0xb33}, {0xb36, 0xb39},
72 {0xb3d, 0xb3d}, {0xb5c, 0xb5d}, {0xb5f, 0xb61}, {0xb85, 0xb8a},
73 {0xb8e, 0xb90}, {0xb92, 0xb95}, {0xb99, 0xb9a}, {0xb9c, 0xb9c},
74 {0xb9e, 0xb9f}, {0xba3, 0xba4}, {0xba8, 0xbaa}, {0xbae, 0xbb5},
75 {0xbb7, 0xbb9}, {0xc05, 0xc0c}, {0xc0e, 0xc10}, {0xc12, 0xc28},
76 {0xc2a, 0xc33}, {0xc35, 0xc39}, {0xc60, 0xc61}, {0xc85, 0xc8c},
77 {0xc8e, 0xc90}, {0xc92, 0xca8}, {0xcaa, 0xcb3}, {0xcb5, 0xcb9},
78 {0xcde, 0xcde}, {0xce0, 0xce1}, {0xd05, 0xd0c}, {0xd0e, 0xd10},
79 {0xd12, 0xd28}, {0xd2a, 0xd39}, {0xd60, 0xd61}, {0xe01, 0xe2e},
80 {0xe30, 0xe30}, {0xe32, 0xe33}, {0xe40, 0xe45}, {0xe81, 0xe82},
81 {0xe84, 0xe84}, {0xe87, 0xe88}, {0xe8a, 0xe8a}, {0xe8d, 0xe8d},
82 {0xe94, 0xe97}, {0xe99, 0xe9f}, {0xea1, 0xea3}, {0xea5, 0xea5},
83 {0xea7, 0xea7}, {0xeaa, 0xeab}, {0xead, 0xeae}, {0xeb0, 0xeb0},
84 {0xeb2, 0xeb3}, {0xebd, 0xebd}, {0xec0, 0xec4}, {0xf40, 0xf47},
85 {0xf49, 0xf69}, {0x10a0, 0x10c5}, {0x10d0, 0x10f6}, {0x1100, 0x1100},
86 {0x1102, 0x1103}, {0x1105, 0x1107}, {0x1109, 0x1109}, {0x110b, 0x110c},
87 {0x110e, 0x1112}, {0x113c, 0x113c}, {0x113e, 0x113e}, {0x1140, 0x1140},
88 {0x114c, 0x114c}, {0x114e, 0x114e}, {0x1150, 0x1150}, {0x1154, 0x1155},
89 {0x1159, 0x1159}, {0x115f, 0x1161}, {0x1163, 0x1163}, {0x1165, 0x1165},
90 {0x1167, 0x1167}, {0x1169, 0x1169}, {0x116d, 0x116e}, {0x1172, 0x1173},
91 {0x1175, 0x1175}, {0x119e, 0x119e}, {0x11a8, 0x11a8}, {0x11ab, 0x11ab},
92 {0x11ae, 0x11af}, {0x11b7, 0x11b8}, {0x11ba, 0x11ba}, {0x11bc, 0x11c2},
93 {0x11eb, 0x11eb}, {0x11f0, 0x11f0}, {0x11f9, 0x11f9}, {0x1e00, 0x1e9b},
94 {0x1ea0, 0x1ef9}, {0x1f00, 0x1f15}, {0x1f18, 0x1f1d}, {0x1f20, 0x1f45},
95 {0x1f48, 0x1f4d}, {0x1f50, 0x1f57}, {0x1f59, 0x1f59}, {0x1f5b, 0x1f5b},
96 {0x1f5d, 0x1f5d}, {0x1f5f, 0x1f7d}, {0x1f80, 0x1fb4}, {0x1fb6, 0x1fbc},
97 {0x1fbe, 0x1fbe}, {0x1fc2, 0x1fc4}, {0x1fc6, 0x1fcc}, {0x1fd0, 0x1fd3},
98 {0x1fd6, 0x1fdb}, {0x1fe0, 0x1fec}, {0x1ff2, 0x1ff4}, {0x1ff6, 0x1ffc},
99 {0x2126, 0x2126}, {0x212a, 0x212b}, {0x212e, 0x212e}, {0x2180, 0x2182},
100 {0x3041, 0x3094}, {0x30a1, 0x30fa}, {0x3105, 0x312c}, {0xac00, 0xd7a3}};
101 const xmlChRangeGroup xmlIsBaseCharGroup =
102 {197, 0, xmlIsBaseChar_srng, (xmlChLRangePtr)0};
103
104 static const xmlChSRange xmlIsChar_srng[] = { {0x100, 0xd7ff},
105 {0xe000, 0xfffd}};
106 static const xmlChLRange xmlIsChar_lrng[] = { {0x10000, 0x10ffff}};
107 const xmlChRangeGroup xmlIsCharGroup =
108 {2, 1, xmlIsChar_srng, xmlIsChar_lrng};
109
110 static const xmlChSRange xmlIsCombining_srng[] = { {0x300, 0x345},
111 {0x360, 0x361}, {0x483, 0x486}, {0x591, 0x5a1}, {0x5a3, 0x5b9},
112 {0x5bb, 0x5bd}, {0x5bf, 0x5bf}, {0x5c1, 0x5c2}, {0x5c4, 0x5c4},
113 {0x64b, 0x652}, {0x670, 0x670}, {0x6d6, 0x6dc}, {0x6dd, 0x6df},
114 {0x6e0, 0x6e4}, {0x6e7, 0x6e8}, {0x6ea, 0x6ed}, {0x901, 0x903},
115 {0x93c, 0x93c}, {0x93e, 0x94c}, {0x94d, 0x94d}, {0x951, 0x954},
116 {0x962, 0x963}, {0x981, 0x983}, {0x9bc, 0x9bc}, {0x9be, 0x9be},
117 {0x9bf, 0x9bf}, {0x9c0, 0x9c4}, {0x9c7, 0x9c8}, {0x9cb, 0x9cd},
118 {0x9d7, 0x9d7}, {0x9e2, 0x9e3}, {0xa02, 0xa02}, {0xa3c, 0xa3c},
119 {0xa3e, 0xa3e}, {0xa3f, 0xa3f}, {0xa40, 0xa42}, {0xa47, 0xa48},
120 {0xa4b, 0xa4d}, {0xa70, 0xa71}, {0xa81, 0xa83}, {0xabc, 0xabc},
121 {0xabe, 0xac5}, {0xac7, 0xac9}, {0xacb, 0xacd}, {0xb01, 0xb03},
122 {0xb3c, 0xb3c}, {0xb3e, 0xb43}, {0xb47, 0xb48}, {0xb4b, 0xb4d},
123 {0xb56, 0xb57}, {0xb82, 0xb83}, {0xbbe, 0xbc2}, {0xbc6, 0xbc8},
124 {0xbca, 0xbcd}, {0xbd7, 0xbd7}, {0xc01, 0xc03}, {0xc3e, 0xc44},
125 {0xc46, 0xc48}, {0xc4a, 0xc4d}, {0xc55, 0xc56}, {0xc82, 0xc83},
126 {0xcbe, 0xcc4}, {0xcc6, 0xcc8}, {0xcca, 0xccd}, {0xcd5, 0xcd6},
127 {0xd02, 0xd03}, {0xd3e, 0xd43}, {0xd46, 0xd48}, {0xd4a, 0xd4d},
128 {0xd57, 0xd57}, {0xe31, 0xe31}, {0xe34, 0xe3a}, {0xe47, 0xe4e},
129 {0xeb1, 0xeb1}, {0xeb4, 0xeb9}, {0xebb, 0xebc}, {0xec8, 0xecd},
130 {0xf18, 0xf19}, {0xf35, 0xf35}, {0xf37, 0xf37}, {0xf39, 0xf39},
131 {0xf3e, 0xf3e}, {0xf3f, 0xf3f}, {0xf71, 0xf84}, {0xf86, 0xf8b},
132 {0xf90, 0xf95}, {0xf97, 0xf97}, {0xf99, 0xfad}, {0xfb1, 0xfb7},
133 {0xfb9, 0xfb9}, {0x20d0, 0x20dc}, {0x20e1, 0x20e1}, {0x302a, 0x302f},
134 {0x3099, 0x3099}, {0x309a, 0x309a}};
135 const xmlChRangeGroup xmlIsCombiningGroup =
136 {95, 0, xmlIsCombining_srng, (xmlChLRangePtr)0};
137
138 static const xmlChSRange xmlIsDigit_srng[] = { {0x660, 0x669},
139 {0x6f0, 0x6f9}, {0x966, 0x96f}, {0x9e6, 0x9ef}, {0xa66, 0xa6f},
140 {0xae6, 0xaef}, {0xb66, 0xb6f}, {0xbe7, 0xbef}, {0xc66, 0xc6f},
141 {0xce6, 0xcef}, {0xd66, 0xd6f}, {0xe50, 0xe59}, {0xed0, 0xed9},
142 {0xf20, 0xf29}};
143 const xmlChRangeGroup xmlIsDigitGroup =
144 {14, 0, xmlIsDigit_srng, (xmlChLRangePtr)0};
145
146 static const xmlChSRange xmlIsExtender_srng[] = { {0x2d0, 0x2d0},
147 {0x2d1, 0x2d1}, {0x387, 0x387}, {0x640, 0x640}, {0xe46, 0xe46},
148 {0xec6, 0xec6}, {0x3005, 0x3005}, {0x3031, 0x3035}, {0x309d, 0x309e},
149 {0x30fc, 0x30fe}};
150 const xmlChRangeGroup xmlIsExtenderGroup =
151 {10, 0, xmlIsExtender_srng, (xmlChLRangePtr)0};
152
153 static const xmlChSRange xmlIsIdeographic_srng[] = { {0x3007, 0x3007},
154 {0x3021, 0x3029}, {0x4e00, 0x9fa5}};
155 const xmlChRangeGroup xmlIsIdeographicGroup =
156 {3, 0, xmlIsIdeographic_srng, (xmlChLRangePtr)0};
157
158
159 /**
160 * xmlCharInRange:
161 * @val: character to be validated
162 * @rptr: pointer to range to be used to validate
163 *
164 * Does a binary search of the range table to determine if char
165 * is valid
166 *
167 * Returns: true if character valid, false otherwise
168 */
169 int
xmlCharInRange(unsigned int val,const xmlChRangeGroup * rptr)170 xmlCharInRange (unsigned int val, const xmlChRangeGroup *rptr) {
171 int low, high, mid;
172 const xmlChSRange *sptr;
173 const xmlChLRange *lptr;
174
175 if (rptr == NULL) return(0);
176 if (val < 0x10000) { /* is val in 'short' or 'long' array? */
177 if (rptr->nbShortRange == 0)
178 return 0;
179 low = 0;
180 high = rptr->nbShortRange - 1;
181 sptr = rptr->shortRange;
182 while (low <= high) {
183 mid = (low + high) / 2;
184 if ((unsigned short) val < sptr[mid].low) {
185 high = mid - 1;
186 } else {
187 if ((unsigned short) val > sptr[mid].high) {
188 low = mid + 1;
189 } else {
190 return 1;
191 }
192 }
193 }
194 } else {
195 if (rptr->nbLongRange == 0) {
196 return 0;
197 }
198 low = 0;
199 high = rptr->nbLongRange - 1;
200 lptr = rptr->longRange;
201 while (low <= high) {
202 mid = (low + high) / 2;
203 if (val < lptr[mid].low) {
204 high = mid - 1;
205 } else {
206 if (val > lptr[mid].high) {
207 low = mid + 1;
208 } else {
209 return 1;
210 }
211 }
212 }
213 }
214 return 0;
215 }
216
217
218 /**
219 * xmlIsBaseChar:
220 * @ch: character to validate
221 *
222 * This function is DEPRECATED.
223 * Use xmlIsBaseChar_ch or xmlIsBaseCharQ instead
224 *
225 * Returns true if argument valid, false otherwise
226 */
227 int
xmlIsBaseChar(unsigned int ch)228 xmlIsBaseChar(unsigned int ch) {
229 return(xmlIsBaseCharQ(ch));
230 }
231
232
233 /**
234 * xmlIsBlank:
235 * @ch: character to validate
236 *
237 * This function is DEPRECATED.
238 * Use xmlIsBlank_ch or xmlIsBlankQ instead
239 *
240 * Returns true if argument valid, false otherwise
241 */
242 int
xmlIsBlank(unsigned int ch)243 xmlIsBlank(unsigned int ch) {
244 return(xmlIsBlankQ(ch));
245 }
246
247
248 /**
249 * xmlIsChar:
250 * @ch: character to validate
251 *
252 * This function is DEPRECATED.
253 * Use xmlIsChar_ch or xmlIsCharQ instead
254 *
255 * Returns true if argument valid, false otherwise
256 */
257 int
xmlIsChar(unsigned int ch)258 xmlIsChar(unsigned int ch) {
259 return(xmlIsCharQ(ch));
260 }
261
262
263 /**
264 * xmlIsCombining:
265 * @ch: character to validate
266 *
267 * This function is DEPRECATED.
268 * Use xmlIsCombiningQ instead
269 *
270 * Returns true if argument valid, false otherwise
271 */
272 int
xmlIsCombining(unsigned int ch)273 xmlIsCombining(unsigned int ch) {
274 return(xmlIsCombiningQ(ch));
275 }
276
277
278 /**
279 * xmlIsDigit:
280 * @ch: character to validate
281 *
282 * This function is DEPRECATED.
283 * Use xmlIsDigit_ch or xmlIsDigitQ instead
284 *
285 * Returns true if argument valid, false otherwise
286 */
287 int
xmlIsDigit(unsigned int ch)288 xmlIsDigit(unsigned int ch) {
289 return(xmlIsDigitQ(ch));
290 }
291
292
293 /**
294 * xmlIsExtender:
295 * @ch: character to validate
296 *
297 * This function is DEPRECATED.
298 * Use xmlIsExtender_ch or xmlIsExtenderQ instead
299 *
300 * Returns true if argument valid, false otherwise
301 */
302 int
xmlIsExtender(unsigned int ch)303 xmlIsExtender(unsigned int ch) {
304 return(xmlIsExtenderQ(ch));
305 }
306
307
308 /**
309 * xmlIsIdeographic:
310 * @ch: character to validate
311 *
312 * This function is DEPRECATED.
313 * Use xmlIsIdeographicQ instead
314 *
315 * Returns true if argument valid, false otherwise
316 */
317 int
xmlIsIdeographic(unsigned int ch)318 xmlIsIdeographic(unsigned int ch) {
319 return(xmlIsIdeographicQ(ch));
320 }
321
322
323 /**
324 * xmlIsPubidChar:
325 * @ch: character to validate
326 *
327 * This function is DEPRECATED.
328 * Use xmlIsPubidChar_ch or xmlIsPubidCharQ instead
329 *
330 * Returns true if argument valid, false otherwise
331 */
332 int
xmlIsPubidChar(unsigned int ch)333 xmlIsPubidChar(unsigned int ch) {
334 return(xmlIsPubidCharQ(ch));
335 }
336
337