1 // © 2016 and later: Unicode, Inc. and others.
2 // License & terms of use: http://www.unicode.org/copyright.html
3 /*
4 ***************************************************************************
5 * Copyright (C) 2008-2015, International Business Machines Corporation
6 * and others. All Rights Reserved.
7 ***************************************************************************
8 * file name: uspoof.cpp
9 * encoding: UTF-8
10 * tab size: 8 (not used)
11 * indentation:4
12 *
13 * created on: 2008Feb13
14 * created by: Andy Heninger
15 *
16 * Unicode Spoof Detection
17 */
18 #include "unicode/utypes.h"
19 #include "unicode/normalizer2.h"
20 #include "unicode/uspoof.h"
21 #include "unicode/ustring.h"
22 #include "unicode/utf16.h"
23 #include "cmemory.h"
24 #include "cstring.h"
25 #include "mutex.h"
26 #include "scriptset.h"
27 #include "uassert.h"
28 #include "ucln_in.h"
29 #include "uspoof_impl.h"
30 #include "umutex.h"
31
32
33 #if !UCONFIG_NO_NORMALIZATION
34
35 U_NAMESPACE_USE
36
37
38 //
39 // Static Objects used by the spoof impl, their thread safe initialization and their cleanup.
40 //
41 static UnicodeSet *gInclusionSet = NULL;
42 static UnicodeSet *gRecommendedSet = NULL;
43 static const Normalizer2 *gNfdNormalizer = NULL;
44 static UInitOnce gSpoofInitStaticsOnce = U_INITONCE_INITIALIZER;
45
46 static UBool U_CALLCONV
uspoof_cleanup(void)47 uspoof_cleanup(void) {
48 delete gInclusionSet;
49 gInclusionSet = NULL;
50 delete gRecommendedSet;
51 gRecommendedSet = NULL;
52 gNfdNormalizer = NULL;
53 gSpoofInitStaticsOnce.reset();
54 return TRUE;
55 }
56
initializeStatics(UErrorCode & status)57 static void U_CALLCONV initializeStatics(UErrorCode &status) {
58 static const char16_t *inclusionPat =
59 u"['\\-.\\:\\u00B7\\u0375\\u058A\\u05F3\\u05F4\\u06FD\\u06FE\\u0F0B\\u200C"
60 u"\\u200D\\u2010\\u2019\\u2027\\u30A0\\u30FB]";
61 gInclusionSet = new UnicodeSet(UnicodeString(inclusionPat), status);
62 if (gInclusionSet == NULL) {
63 status = U_MEMORY_ALLOCATION_ERROR;
64 return;
65 }
66 gInclusionSet->freeze();
67
68 // Note: data from IdentifierStatus.txt & IdentifierType.txt
69 // There is tooling to generate this constant in the unicodetools project:
70 // org.unicode.text.tools.RecommendedSetGenerator
71 // It will print the Java and C++ code to the console for easy copy-paste into this file.
72 // Note: concatenated string constants do not work with UNICODE_STRING_SIMPLE on all platforms.
73 static const char16_t *recommendedPat =
74 u"[0-9A-Z_a-z\\u00C0-\\u00D6\\u00D8-\\u00F6\\u00F8-\\u0131\\u0134-\\u013E"
75 u"\\u0141-\\u0148\\u014A-\\u017E\\u018F\\u01A0\\u01A1\\u01AF\\u01B0\\u01CD-"
76 u"\\u01DC\\u01DE-\\u01E3\\u01E6-\\u01F0\\u01F4\\u01F5\\u01F8-\\u021B\\u021E"
77 u"\\u021F\\u0226-\\u0233\\u0259\\u02BB\\u02BC\\u02EC\\u0300-\\u0304\\u0306-"
78 u"\\u030C\\u030F-\\u0311\\u0313\\u0314\\u031B\\u0323-\\u0328\\u032D\\u032E"
79 u"\\u0330\\u0331\\u0335\\u0338\\u0339\\u0342\\u0345\\u037B-\\u037D\\u0386"
80 u"\\u0388-\\u038A\\u038C\\u038E-\\u03A1\\u03A3-\\u03CE\\u03FC-\\u045F\\u048A-"
81 u"\\u0529\\u052E\\u052F\\u0531-\\u0556\\u0559\\u0560-\\u0586\\u0588\\u05B4"
82 u"\\u05D0-\\u05EA\\u05EF-\\u05F2\\u0620-\\u063F\\u0641-\\u0655\\u0660-\\u0669"
83 u"\\u0670-\\u0672\\u0674\\u0679-\\u068D\\u068F-\\u06D3\\u06D5\\u06E5\\u06E6"
84 u"\\u06EE-\\u06FC\\u06FF\\u0750-\\u07B1\\u08A0-\\u08AC\\u08B2\\u08B6-\\u08BD"
85 u"\\u0901-\\u094D\\u094F\\u0950\\u0956\\u0957\\u0960-\\u0963\\u0966-\\u096F"
86 u"\\u0971-\\u0977\\u0979-\\u097F\\u0981-\\u0983\\u0985-\\u098C\\u098F\\u0990"
87 u"\\u0993-\\u09A8\\u09AA-\\u09B0\\u09B2\\u09B6-\\u09B9\\u09BC-\\u09C4\\u09C7"
88 u"\\u09C8\\u09CB-\\u09CE\\u09D7\\u09E0-\\u09E3\\u09E6-\\u09F1\\u09FC\\u09FE"
89 u"\\u0A01-\\u0A03\\u0A05-\\u0A0A\\u0A0F\\u0A10\\u0A13-\\u0A28\\u0A2A-\\u0A30"
90 u"\\u0A32\\u0A35\\u0A38\\u0A39\\u0A3C\\u0A3E-\\u0A42\\u0A47\\u0A48\\u0A4B-"
91 u"\\u0A4D\\u0A5C\\u0A66-\\u0A74\\u0A81-\\u0A83\\u0A85-\\u0A8D\\u0A8F-\\u0A91"
92 u"\\u0A93-\\u0AA8\\u0AAA-\\u0AB0\\u0AB2\\u0AB3\\u0AB5-\\u0AB9\\u0ABC-\\u0AC5"
93 u"\\u0AC7-\\u0AC9\\u0ACB-\\u0ACD\\u0AD0\\u0AE0-\\u0AE3\\u0AE6-\\u0AEF\\u0AFA-"
94 u"\\u0AFF\\u0B01-\\u0B03\\u0B05-\\u0B0C\\u0B0F\\u0B10\\u0B13-\\u0B28\\u0B2A-"
95 u"\\u0B30\\u0B32\\u0B33\\u0B35-\\u0B39\\u0B3C-\\u0B43\\u0B47\\u0B48\\u0B4B-"
96 u"\\u0B4D\\u0B56\\u0B57\\u0B5F-\\u0B61\\u0B66-\\u0B6F\\u0B71\\u0B82\\u0B83"
97 u"\\u0B85-\\u0B8A\\u0B8E-\\u0B90\\u0B92-\\u0B95\\u0B99\\u0B9A\\u0B9C\\u0B9E"
98 u"\\u0B9F\\u0BA3\\u0BA4\\u0BA8-\\u0BAA\\u0BAE-\\u0BB9\\u0BBE-\\u0BC2\\u0BC6-"
99 u"\\u0BC8\\u0BCA-\\u0BCD\\u0BD0\\u0BD7\\u0BE6-\\u0BEF\\u0C01-\\u0C0C\\u0C0E-"
100 u"\\u0C10\\u0C12-\\u0C28\\u0C2A-\\u0C33\\u0C35-\\u0C39\\u0C3D-\\u0C44\\u0C46-"
101 u"\\u0C48\\u0C4A-\\u0C4D\\u0C55\\u0C56\\u0C60\\u0C61\\u0C66-\\u0C6F\\u0C80"
102 u"\\u0C82\\u0C83\\u0C85-\\u0C8C\\u0C8E-\\u0C90\\u0C92-\\u0CA8\\u0CAA-\\u0CB3"
103 u"\\u0CB5-\\u0CB9\\u0CBC-\\u0CC4\\u0CC6-\\u0CC8\\u0CCA-\\u0CCD\\u0CD5\\u0CD6"
104 u"\\u0CE0-\\u0CE3\\u0CE6-\\u0CEF\\u0CF1\\u0CF2\\u0D00\\u0D02\\u0D03\\u0D05-"
105 u"\\u0D0C\\u0D0E-\\u0D10\\u0D12-\\u0D43\\u0D46-\\u0D48\\u0D4A-\\u0D4E\\u0D54-"
106 u"\\u0D57\\u0D60\\u0D61\\u0D66-\\u0D6F\\u0D7A-\\u0D7F\\u0D82\\u0D83\\u0D85-"
107 u"\\u0D8E\\u0D91-\\u0D96\\u0D9A-\\u0DA5\\u0DA7-\\u0DB1\\u0DB3-\\u0DBB\\u0DBD"
108 u"\\u0DC0-\\u0DC6\\u0DCA\\u0DCF-\\u0DD4\\u0DD6\\u0DD8-\\u0DDE\\u0DF2\\u0E01-"
109 u"\\u0E32\\u0E34-\\u0E3A\\u0E40-\\u0E4E\\u0E50-\\u0E59\\u0E81\\u0E82\\u0E84"
110 u"\\u0E87\\u0E88\\u0E8A\\u0E8D\\u0E94-\\u0E97\\u0E99-\\u0E9F\\u0EA1-\\u0EA3"
111 u"\\u0EA5\\u0EA7\\u0EAA\\u0EAB\\u0EAD-\\u0EB2\\u0EB4-\\u0EB9\\u0EBB-\\u0EBD"
112 u"\\u0EC0-\\u0EC4\\u0EC6\\u0EC8-\\u0ECD\\u0ED0-\\u0ED9\\u0EDE\\u0EDF\\u0F00"
113 u"\\u0F20-\\u0F29\\u0F35\\u0F37\\u0F3E-\\u0F42\\u0F44-\\u0F47\\u0F49-\\u0F4C"
114 u"\\u0F4E-\\u0F51\\u0F53-\\u0F56\\u0F58-\\u0F5B\\u0F5D-\\u0F68\\u0F6A-\\u0F6C"
115 u"\\u0F71\\u0F72\\u0F74\\u0F7A-\\u0F80\\u0F82-\\u0F84\\u0F86-\\u0F92\\u0F94-"
116 u"\\u0F97\\u0F99-\\u0F9C\\u0F9E-\\u0FA1\\u0FA3-\\u0FA6\\u0FA8-\\u0FAB\\u0FAD-"
117 u"\\u0FB8\\u0FBA-\\u0FBC\\u0FC6\\u1000-\\u1049\\u1050-\\u109D\\u10C7\\u10CD"
118 u"\\u10D0-\\u10F0\\u10F7-\\u10FA\\u10FD-\\u10FF\\u1200-\\u1248\\u124A-\\u124D"
119 u"\\u1250-\\u1256\\u1258\\u125A-\\u125D\\u1260-\\u1288\\u128A-\\u128D\\u1290-"
120 u"\\u12B0\\u12B2-\\u12B5\\u12B8-\\u12BE\\u12C0\\u12C2-\\u12C5\\u12C8-\\u12D6"
121 u"\\u12D8-\\u1310\\u1312-\\u1315\\u1318-\\u135A\\u135D-\\u135F\\u1380-\\u138F"
122 u"\\u1780-\\u17A2\\u17A5-\\u17A7\\u17A9-\\u17B3\\u17B6-\\u17CA\\u17D2\\u17D7"
123 u"\\u17DC\\u17E0-\\u17E9\\u1C80-\\u1C88\\u1C90-\\u1CBA\\u1CBD-\\u1CBF\\u1E00-"
124 u"\\u1E99\\u1E9E\\u1EA0-\\u1EF9\\u1F00-\\u1F15\\u1F18-\\u1F1D\\u1F20-\\u1F45"
125 u"\\u1F48-\\u1F4D\\u1F50-\\u1F57\\u1F59\\u1F5B\\u1F5D\\u1F5F-\\u1F70\\u1F72"
126 u"\\u1F74\\u1F76\\u1F78\\u1F7A\\u1F7C\\u1F80-\\u1FB4\\u1FB6-\\u1FBA\\u1FBC"
127 u"\\u1FC2-\\u1FC4\\u1FC6-\\u1FC8\\u1FCA\\u1FCC\\u1FD0-\\u1FD2\\u1FD6-\\u1FDA"
128 u"\\u1FE0-\\u1FE2\\u1FE4-\\u1FEA\\u1FEC\\u1FF2-\\u1FF4\\u1FF6-\\u1FF8\\u1FFA"
129 u"\\u1FFC\\u2D27\\u2D2D\\u2D80-\\u2D96\\u2DA0-\\u2DA6\\u2DA8-\\u2DAE\\u2DB0-"
130 u"\\u2DB6\\u2DB8-\\u2DBE\\u2DC0-\\u2DC6\\u2DC8-\\u2DCE\\u2DD0-\\u2DD6\\u2DD8-"
131 u"\\u2DDE\\u3005-\\u3007\\u3041-\\u3096\\u3099\\u309A\\u309D\\u309E\\u30A1-"
132 u"\\u30FA\\u30FC-\\u30FE\\u3105-\\u312F\\u31A0-\\u31BA\\u3400-\\u4DB5\\u4E00-"
133 u"\\u9FEF\\uA660\\uA661\\uA674-\\uA67B\\uA67F\\uA69F\\uA717-\\uA71F\\uA788"
134 u"\\uA78D\\uA78E\\uA790-\\uA793\\uA7A0-\\uA7AA\\uA7AE\\uA7AF\\uA7B8\\uA7B9"
135 u"\\uA7FA\\uA9E7-\\uA9FE\\uAA60-\\uAA76\\uAA7A-\\uAA7F\\uAB01-\\uAB06\\uAB09-"
136 u"\\uAB0E\\uAB11-\\uAB16\\uAB20-\\uAB26\\uAB28-\\uAB2E\\uAC00-\\uD7A3\\uFA0E"
137 u"\\uFA0F\\uFA11\\uFA13\\uFA14\\uFA1F\\uFA21\\uFA23\\uFA24\\uFA27-\\uFA29"
138 u"\\U0001133B\\U0001B002-\\U0001B11E\\U00020000-\\U0002A6D6\\U0002A700-"
139 u"\\U0002B734\\U0002B740-\\U0002B81D\\U0002B820-\\U0002CEA1\\U0002CEB0-"
140 u"\\U0002EBE0]";
141
142 gRecommendedSet = new UnicodeSet(UnicodeString(recommendedPat), status);
143 if (gRecommendedSet == NULL) {
144 status = U_MEMORY_ALLOCATION_ERROR;
145 delete gInclusionSet;
146 return;
147 }
148 gRecommendedSet->freeze();
149 gNfdNormalizer = Normalizer2::getNFDInstance(status);
150 ucln_i18n_registerCleanup(UCLN_I18N_SPOOF, uspoof_cleanup);
151 }
152
uspoof_internalInitStatics(UErrorCode * status)153 U_CFUNC void uspoof_internalInitStatics(UErrorCode *status) {
154 umtx_initOnce(gSpoofInitStaticsOnce, &initializeStatics, *status);
155 }
156
157 U_CAPI USpoofChecker * U_EXPORT2
uspoof_open(UErrorCode * status)158 uspoof_open(UErrorCode *status) {
159 umtx_initOnce(gSpoofInitStaticsOnce, &initializeStatics, *status);
160 if (U_FAILURE(*status)) {
161 return NULL;
162 }
163 SpoofImpl *si = new SpoofImpl(*status);
164 if (si == NULL) {
165 *status = U_MEMORY_ALLOCATION_ERROR;
166 return NULL;
167 }
168 if (U_FAILURE(*status)) {
169 delete si;
170 return NULL;
171 }
172 return si->asUSpoofChecker();
173 }
174
175
176 U_CAPI USpoofChecker * U_EXPORT2
uspoof_openFromSerialized(const void * data,int32_t length,int32_t * pActualLength,UErrorCode * status)177 uspoof_openFromSerialized(const void *data, int32_t length, int32_t *pActualLength,
178 UErrorCode *status) {
179 if (U_FAILURE(*status)) {
180 return NULL;
181 }
182
183 if (data == NULL) {
184 *status = U_ILLEGAL_ARGUMENT_ERROR;
185 return NULL;
186 }
187
188 umtx_initOnce(gSpoofInitStaticsOnce, &initializeStatics, *status);
189 if (U_FAILURE(*status))
190 {
191 return NULL;
192 }
193
194 SpoofData *sd = new SpoofData(data, length, *status);
195 if (sd == NULL) {
196 *status = U_MEMORY_ALLOCATION_ERROR;
197 return NULL;
198 }
199
200 if (U_FAILURE(*status)) {
201 delete sd;
202 return NULL;
203 }
204
205 SpoofImpl *si = new SpoofImpl(sd, *status);
206 if (si == NULL) {
207 *status = U_MEMORY_ALLOCATION_ERROR;
208 delete sd; // explicit delete as the destructor for si won't be called.
209 return NULL;
210 }
211
212 if (U_FAILURE(*status)) {
213 delete si; // no delete for sd, as the si destructor will delete it.
214 return NULL;
215 }
216
217 if (pActualLength != NULL) {
218 *pActualLength = sd->size();
219 }
220 return si->asUSpoofChecker();
221 }
222
223
224 U_CAPI USpoofChecker * U_EXPORT2
uspoof_clone(const USpoofChecker * sc,UErrorCode * status)225 uspoof_clone(const USpoofChecker *sc, UErrorCode *status) {
226 const SpoofImpl *src = SpoofImpl::validateThis(sc, *status);
227 if (src == NULL) {
228 return NULL;
229 }
230 SpoofImpl *result = new SpoofImpl(*src, *status); // copy constructor
231 if (result == NULL) {
232 *status = U_MEMORY_ALLOCATION_ERROR;
233 return NULL;
234 }
235 if (U_FAILURE(*status)) {
236 delete result;
237 result = NULL;
238 }
239 return result->asUSpoofChecker();
240 }
241
242
243 U_CAPI void U_EXPORT2
uspoof_close(USpoofChecker * sc)244 uspoof_close(USpoofChecker *sc) {
245 UErrorCode status = U_ZERO_ERROR;
246 SpoofImpl *This = SpoofImpl::validateThis(sc, status);
247 delete This;
248 }
249
250
251 U_CAPI void U_EXPORT2
uspoof_setChecks(USpoofChecker * sc,int32_t checks,UErrorCode * status)252 uspoof_setChecks(USpoofChecker *sc, int32_t checks, UErrorCode *status) {
253 SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
254 if (This == NULL) {
255 return;
256 }
257
258 // Verify that the requested checks are all ones (bits) that
259 // are acceptable, known values.
260 if (checks & ~(USPOOF_ALL_CHECKS | USPOOF_AUX_INFO)) {
261 *status = U_ILLEGAL_ARGUMENT_ERROR;
262 return;
263 }
264
265 This->fChecks = checks;
266 }
267
268
269 U_CAPI int32_t U_EXPORT2
uspoof_getChecks(const USpoofChecker * sc,UErrorCode * status)270 uspoof_getChecks(const USpoofChecker *sc, UErrorCode *status) {
271 const SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
272 if (This == NULL) {
273 return 0;
274 }
275 return This->fChecks;
276 }
277
278 U_CAPI void U_EXPORT2
uspoof_setRestrictionLevel(USpoofChecker * sc,URestrictionLevel restrictionLevel)279 uspoof_setRestrictionLevel(USpoofChecker *sc, URestrictionLevel restrictionLevel) {
280 UErrorCode status = U_ZERO_ERROR;
281 SpoofImpl *This = SpoofImpl::validateThis(sc, status);
282 if (This != NULL) {
283 This->fRestrictionLevel = restrictionLevel;
284 This->fChecks |= USPOOF_RESTRICTION_LEVEL;
285 }
286 }
287
288 U_CAPI URestrictionLevel U_EXPORT2
uspoof_getRestrictionLevel(const USpoofChecker * sc)289 uspoof_getRestrictionLevel(const USpoofChecker *sc) {
290 UErrorCode status = U_ZERO_ERROR;
291 const SpoofImpl *This = SpoofImpl::validateThis(sc, status);
292 if (This == NULL) {
293 return USPOOF_UNRESTRICTIVE;
294 }
295 return This->fRestrictionLevel;
296 }
297
298 U_CAPI void U_EXPORT2
uspoof_setAllowedLocales(USpoofChecker * sc,const char * localesList,UErrorCode * status)299 uspoof_setAllowedLocales(USpoofChecker *sc, const char *localesList, UErrorCode *status) {
300 SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
301 if (This == NULL) {
302 return;
303 }
304 This->setAllowedLocales(localesList, *status);
305 }
306
307 U_CAPI const char * U_EXPORT2
uspoof_getAllowedLocales(USpoofChecker * sc,UErrorCode * status)308 uspoof_getAllowedLocales(USpoofChecker *sc, UErrorCode *status) {
309 SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
310 if (This == NULL) {
311 return NULL;
312 }
313 return This->getAllowedLocales(*status);
314 }
315
316
317 U_CAPI const USet * U_EXPORT2
uspoof_getAllowedChars(const USpoofChecker * sc,UErrorCode * status)318 uspoof_getAllowedChars(const USpoofChecker *sc, UErrorCode *status) {
319 const UnicodeSet *result = uspoof_getAllowedUnicodeSet(sc, status);
320 return result->toUSet();
321 }
322
323 U_CAPI const UnicodeSet * U_EXPORT2
uspoof_getAllowedUnicodeSet(const USpoofChecker * sc,UErrorCode * status)324 uspoof_getAllowedUnicodeSet(const USpoofChecker *sc, UErrorCode *status) {
325 const SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
326 if (This == NULL) {
327 return NULL;
328 }
329 return This->fAllowedCharsSet;
330 }
331
332
333 U_CAPI void U_EXPORT2
uspoof_setAllowedChars(USpoofChecker * sc,const USet * chars,UErrorCode * status)334 uspoof_setAllowedChars(USpoofChecker *sc, const USet *chars, UErrorCode *status) {
335 const UnicodeSet *set = UnicodeSet::fromUSet(chars);
336 uspoof_setAllowedUnicodeSet(sc, set, status);
337 }
338
339
340 U_CAPI void U_EXPORT2
uspoof_setAllowedUnicodeSet(USpoofChecker * sc,const UnicodeSet * chars,UErrorCode * status)341 uspoof_setAllowedUnicodeSet(USpoofChecker *sc, const UnicodeSet *chars, UErrorCode *status) {
342 SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
343 if (This == NULL) {
344 return;
345 }
346 if (chars->isBogus()) {
347 *status = U_ILLEGAL_ARGUMENT_ERROR;
348 return;
349 }
350 UnicodeSet *clonedSet = static_cast<UnicodeSet *>(chars->clone());
351 if (clonedSet == NULL || clonedSet->isBogus()) {
352 *status = U_MEMORY_ALLOCATION_ERROR;
353 return;
354 }
355 clonedSet->freeze();
356 delete This->fAllowedCharsSet;
357 This->fAllowedCharsSet = clonedSet;
358 This->fChecks |= USPOOF_CHAR_LIMIT;
359 }
360
361
362 U_CAPI int32_t U_EXPORT2
uspoof_check(const USpoofChecker * sc,const UChar * id,int32_t length,int32_t * position,UErrorCode * status)363 uspoof_check(const USpoofChecker *sc,
364 const UChar *id, int32_t length,
365 int32_t *position,
366 UErrorCode *status) {
367
368 // Backwards compatibility:
369 if (position != NULL) {
370 *position = 0;
371 }
372
373 // Delegate to uspoof_check2
374 return uspoof_check2(sc, id, length, NULL, status);
375 }
376
377
378 U_CAPI int32_t U_EXPORT2
uspoof_check2(const USpoofChecker * sc,const UChar * id,int32_t length,USpoofCheckResult * checkResult,UErrorCode * status)379 uspoof_check2(const USpoofChecker *sc,
380 const UChar* id, int32_t length,
381 USpoofCheckResult* checkResult,
382 UErrorCode *status) {
383
384 const SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
385 if (This == NULL) {
386 return 0;
387 }
388 if (length < -1) {
389 *status = U_ILLEGAL_ARGUMENT_ERROR;
390 return 0;
391 }
392 UnicodeString idStr((length == -1), id, length); // Aliasing constructor.
393 int32_t result = uspoof_check2UnicodeString(sc, idStr, checkResult, status);
394 return result;
395 }
396
397
398 U_CAPI int32_t U_EXPORT2
uspoof_checkUTF8(const USpoofChecker * sc,const char * id,int32_t length,int32_t * position,UErrorCode * status)399 uspoof_checkUTF8(const USpoofChecker *sc,
400 const char *id, int32_t length,
401 int32_t *position,
402 UErrorCode *status) {
403
404 // Backwards compatibility:
405 if (position != NULL) {
406 *position = 0;
407 }
408
409 // Delegate to uspoof_check2
410 return uspoof_check2UTF8(sc, id, length, NULL, status);
411 }
412
413
414 U_CAPI int32_t U_EXPORT2
uspoof_check2UTF8(const USpoofChecker * sc,const char * id,int32_t length,USpoofCheckResult * checkResult,UErrorCode * status)415 uspoof_check2UTF8(const USpoofChecker *sc,
416 const char *id, int32_t length,
417 USpoofCheckResult* checkResult,
418 UErrorCode *status) {
419
420 if (U_FAILURE(*status)) {
421 return 0;
422 }
423 UnicodeString idStr = UnicodeString::fromUTF8(StringPiece(id, length>=0 ? length : static_cast<int32_t>(uprv_strlen(id))));
424 int32_t result = uspoof_check2UnicodeString(sc, idStr, checkResult, status);
425 return result;
426 }
427
428
429 U_CAPI int32_t U_EXPORT2
uspoof_areConfusable(const USpoofChecker * sc,const UChar * id1,int32_t length1,const UChar * id2,int32_t length2,UErrorCode * status)430 uspoof_areConfusable(const USpoofChecker *sc,
431 const UChar *id1, int32_t length1,
432 const UChar *id2, int32_t length2,
433 UErrorCode *status) {
434 SpoofImpl::validateThis(sc, *status);
435 if (U_FAILURE(*status)) {
436 return 0;
437 }
438 if (length1 < -1 || length2 < -1) {
439 *status = U_ILLEGAL_ARGUMENT_ERROR;
440 return 0;
441 }
442
443 UnicodeString id1Str((length1==-1), id1, length1); // Aliasing constructor
444 UnicodeString id2Str((length2==-1), id2, length2); // Aliasing constructor
445 return uspoof_areConfusableUnicodeString(sc, id1Str, id2Str, status);
446 }
447
448
449 U_CAPI int32_t U_EXPORT2
uspoof_areConfusableUTF8(const USpoofChecker * sc,const char * id1,int32_t length1,const char * id2,int32_t length2,UErrorCode * status)450 uspoof_areConfusableUTF8(const USpoofChecker *sc,
451 const char *id1, int32_t length1,
452 const char *id2, int32_t length2,
453 UErrorCode *status) {
454 SpoofImpl::validateThis(sc, *status);
455 if (U_FAILURE(*status)) {
456 return 0;
457 }
458 if (length1 < -1 || length2 < -1) {
459 *status = U_ILLEGAL_ARGUMENT_ERROR;
460 return 0;
461 }
462 UnicodeString id1Str = UnicodeString::fromUTF8(StringPiece(id1, length1>=0? length1 : static_cast<int32_t>(uprv_strlen(id1))));
463 UnicodeString id2Str = UnicodeString::fromUTF8(StringPiece(id2, length2>=0? length2 : static_cast<int32_t>(uprv_strlen(id2))));
464 int32_t results = uspoof_areConfusableUnicodeString(sc, id1Str, id2Str, status);
465 return results;
466 }
467
468
469 U_CAPI int32_t U_EXPORT2
uspoof_areConfusableUnicodeString(const USpoofChecker * sc,const icu::UnicodeString & id1,const icu::UnicodeString & id2,UErrorCode * status)470 uspoof_areConfusableUnicodeString(const USpoofChecker *sc,
471 const icu::UnicodeString &id1,
472 const icu::UnicodeString &id2,
473 UErrorCode *status) {
474 const SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
475 if (U_FAILURE(*status)) {
476 return 0;
477 }
478 //
479 // See section 4 of UAX 39 for the algorithm for checking whether two strings are confusable,
480 // and for definitions of the types (single, whole, mixed-script) of confusables.
481
482 // We only care about a few of the check flags. Ignore the others.
483 // If no tests relavant to this function have been specified, return an error.
484 // TODO: is this really the right thing to do? It's probably an error on the caller's part,
485 // but logically we would just return 0 (no error).
486 if ((This->fChecks & USPOOF_CONFUSABLE) == 0) {
487 *status = U_INVALID_STATE_ERROR;
488 return 0;
489 }
490
491 // Compute the skeletons and check for confusability.
492 UnicodeString id1Skeleton;
493 uspoof_getSkeletonUnicodeString(sc, 0 /* deprecated */, id1, id1Skeleton, status);
494 UnicodeString id2Skeleton;
495 uspoof_getSkeletonUnicodeString(sc, 0 /* deprecated */, id2, id2Skeleton, status);
496 if (U_FAILURE(*status)) { return 0; }
497 if (id1Skeleton != id2Skeleton) {
498 return 0;
499 }
500
501 // If we get here, the strings are confusable. Now we just need to set the flags for the appropriate classes
502 // of confusables according to UTS 39 section 4.
503 // Start by computing the resolved script sets of id1 and id2.
504 ScriptSet id1RSS;
505 This->getResolvedScriptSet(id1, id1RSS, *status);
506 ScriptSet id2RSS;
507 This->getResolvedScriptSet(id2, id2RSS, *status);
508
509 // Turn on all applicable flags
510 int32_t result = 0;
511 if (id1RSS.intersects(id2RSS)) {
512 result |= USPOOF_SINGLE_SCRIPT_CONFUSABLE;
513 } else {
514 result |= USPOOF_MIXED_SCRIPT_CONFUSABLE;
515 if (!id1RSS.isEmpty() && !id2RSS.isEmpty()) {
516 result |= USPOOF_WHOLE_SCRIPT_CONFUSABLE;
517 }
518 }
519
520 // Turn off flags that the user doesn't want
521 if ((This->fChecks & USPOOF_SINGLE_SCRIPT_CONFUSABLE) == 0) {
522 result &= ~USPOOF_SINGLE_SCRIPT_CONFUSABLE;
523 }
524 if ((This->fChecks & USPOOF_MIXED_SCRIPT_CONFUSABLE) == 0) {
525 result &= ~USPOOF_MIXED_SCRIPT_CONFUSABLE;
526 }
527 if ((This->fChecks & USPOOF_WHOLE_SCRIPT_CONFUSABLE) == 0) {
528 result &= ~USPOOF_WHOLE_SCRIPT_CONFUSABLE;
529 }
530
531 return result;
532 }
533
534
535 U_CAPI int32_t U_EXPORT2
uspoof_checkUnicodeString(const USpoofChecker * sc,const icu::UnicodeString & id,int32_t * position,UErrorCode * status)536 uspoof_checkUnicodeString(const USpoofChecker *sc,
537 const icu::UnicodeString &id,
538 int32_t *position,
539 UErrorCode *status) {
540
541 // Backwards compatibility:
542 if (position != NULL) {
543 *position = 0;
544 }
545
546 // Delegate to uspoof_check2
547 return uspoof_check2UnicodeString(sc, id, NULL, status);
548 }
549
checkImpl(const SpoofImpl * This,const UnicodeString & id,CheckResult * checkResult,UErrorCode * status)550 static int32_t checkImpl(const SpoofImpl* This, const UnicodeString& id, CheckResult* checkResult, UErrorCode* status) {
551 U_ASSERT(This != NULL);
552 U_ASSERT(checkResult != NULL);
553 checkResult->clear();
554 int32_t result = 0;
555
556 if (0 != (This->fChecks & USPOOF_RESTRICTION_LEVEL)) {
557 URestrictionLevel idRestrictionLevel = This->getRestrictionLevel(id, *status);
558 if (idRestrictionLevel > This->fRestrictionLevel) {
559 result |= USPOOF_RESTRICTION_LEVEL;
560 }
561 checkResult->fRestrictionLevel = idRestrictionLevel;
562 }
563
564 if (0 != (This->fChecks & USPOOF_MIXED_NUMBERS)) {
565 UnicodeSet numerics;
566 This->getNumerics(id, numerics, *status);
567 if (numerics.size() > 1) {
568 result |= USPOOF_MIXED_NUMBERS;
569 }
570 checkResult->fNumerics = numerics; // UnicodeSet::operator=
571 }
572
573 if (0 != (This->fChecks & USPOOF_HIDDEN_OVERLAY)) {
574 int32_t index = This->findHiddenOverlay(id, *status);
575 if (index != -1) {
576 result |= USPOOF_HIDDEN_OVERLAY;
577 }
578 }
579
580
581 if (0 != (This->fChecks & USPOOF_CHAR_LIMIT)) {
582 int32_t i;
583 UChar32 c;
584 int32_t length = id.length();
585 for (i=0; i<length ;) {
586 c = id.char32At(i);
587 i += U16_LENGTH(c);
588 if (!This->fAllowedCharsSet->contains(c)) {
589 result |= USPOOF_CHAR_LIMIT;
590 break;
591 }
592 }
593 }
594
595 if (0 != (This->fChecks & USPOOF_INVISIBLE)) {
596 // This check needs to be done on NFD input
597 UnicodeString nfdText;
598 gNfdNormalizer->normalize(id, nfdText, *status);
599 int32_t nfdLength = nfdText.length();
600
601 // scan for more than one occurence of the same non-spacing mark
602 // in a sequence of non-spacing marks.
603 int32_t i;
604 UChar32 c;
605 UChar32 firstNonspacingMark = 0;
606 UBool haveMultipleMarks = FALSE;
607 UnicodeSet marksSeenSoFar; // Set of combining marks in a single combining sequence.
608
609 for (i=0; i<nfdLength ;) {
610 c = nfdText.char32At(i);
611 i += U16_LENGTH(c);
612 if (u_charType(c) != U_NON_SPACING_MARK) {
613 firstNonspacingMark = 0;
614 if (haveMultipleMarks) {
615 marksSeenSoFar.clear();
616 haveMultipleMarks = FALSE;
617 }
618 continue;
619 }
620 if (firstNonspacingMark == 0) {
621 firstNonspacingMark = c;
622 continue;
623 }
624 if (!haveMultipleMarks) {
625 marksSeenSoFar.add(firstNonspacingMark);
626 haveMultipleMarks = TRUE;
627 }
628 if (marksSeenSoFar.contains(c)) {
629 // report the error, and stop scanning.
630 // No need to find more than the first failure.
631 result |= USPOOF_INVISIBLE;
632 break;
633 }
634 marksSeenSoFar.add(c);
635 }
636 }
637
638 checkResult->fChecks = result;
639 return checkResult->toCombinedBitmask(This->fChecks);
640 }
641
642 U_CAPI int32_t U_EXPORT2
uspoof_check2UnicodeString(const USpoofChecker * sc,const icu::UnicodeString & id,USpoofCheckResult * checkResult,UErrorCode * status)643 uspoof_check2UnicodeString(const USpoofChecker *sc,
644 const icu::UnicodeString &id,
645 USpoofCheckResult* checkResult,
646 UErrorCode *status) {
647 const SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
648 if (This == NULL) {
649 return FALSE;
650 }
651
652 if (checkResult != NULL) {
653 CheckResult* ThisCheckResult = CheckResult::validateThis(checkResult, *status);
654 if (ThisCheckResult == NULL) {
655 return FALSE;
656 }
657 return checkImpl(This, id, ThisCheckResult, status);
658 } else {
659 // Stack-allocate the checkResult since this method doesn't return it
660 CheckResult stackCheckResult;
661 return checkImpl(This, id, &stackCheckResult, status);
662 }
663 }
664
665
666 U_CAPI int32_t U_EXPORT2
uspoof_getSkeleton(const USpoofChecker * sc,uint32_t type,const UChar * id,int32_t length,UChar * dest,int32_t destCapacity,UErrorCode * status)667 uspoof_getSkeleton(const USpoofChecker *sc,
668 uint32_t type,
669 const UChar *id, int32_t length,
670 UChar *dest, int32_t destCapacity,
671 UErrorCode *status) {
672
673 SpoofImpl::validateThis(sc, *status);
674 if (U_FAILURE(*status)) {
675 return 0;
676 }
677 if (length<-1 || destCapacity<0 || (destCapacity==0 && dest!=NULL)) {
678 *status = U_ILLEGAL_ARGUMENT_ERROR;
679 return 0;
680 }
681
682 UnicodeString idStr((length==-1), id, length); // Aliasing constructor
683 UnicodeString destStr;
684 uspoof_getSkeletonUnicodeString(sc, type, idStr, destStr, status);
685 destStr.extract(dest, destCapacity, *status);
686 return destStr.length();
687 }
688
689
690
691 U_I18N_API UnicodeString & U_EXPORT2
uspoof_getSkeletonUnicodeString(const USpoofChecker * sc,uint32_t,const UnicodeString & id,UnicodeString & dest,UErrorCode * status)692 uspoof_getSkeletonUnicodeString(const USpoofChecker *sc,
693 uint32_t /*type*/,
694 const UnicodeString &id,
695 UnicodeString &dest,
696 UErrorCode *status) {
697 const SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
698 if (U_FAILURE(*status)) {
699 return dest;
700 }
701
702 UnicodeString nfdId;
703 gNfdNormalizer->normalize(id, nfdId, *status);
704
705 // Apply the skeleton mapping to the NFD normalized input string
706 // Accumulate the skeleton, possibly unnormalized, in a UnicodeString.
707 int32_t inputIndex = 0;
708 UnicodeString skelStr;
709 int32_t normalizedLen = nfdId.length();
710 for (inputIndex=0; inputIndex < normalizedLen; ) {
711 UChar32 c = nfdId.char32At(inputIndex);
712 inputIndex += U16_LENGTH(c);
713 This->fSpoofData->confusableLookup(c, skelStr);
714 }
715
716 gNfdNormalizer->normalize(skelStr, dest, *status);
717 return dest;
718 }
719
720
721 U_CAPI int32_t U_EXPORT2
uspoof_getSkeletonUTF8(const USpoofChecker * sc,uint32_t type,const char * id,int32_t length,char * dest,int32_t destCapacity,UErrorCode * status)722 uspoof_getSkeletonUTF8(const USpoofChecker *sc,
723 uint32_t type,
724 const char *id, int32_t length,
725 char *dest, int32_t destCapacity,
726 UErrorCode *status) {
727 SpoofImpl::validateThis(sc, *status);
728 if (U_FAILURE(*status)) {
729 return 0;
730 }
731 if (length<-1 || destCapacity<0 || (destCapacity==0 && dest!=NULL)) {
732 *status = U_ILLEGAL_ARGUMENT_ERROR;
733 return 0;
734 }
735
736 UnicodeString srcStr = UnicodeString::fromUTF8(StringPiece(id, length>=0 ? length : static_cast<int32_t>(uprv_strlen(id))));
737 UnicodeString destStr;
738 uspoof_getSkeletonUnicodeString(sc, type, srcStr, destStr, status);
739 if (U_FAILURE(*status)) {
740 return 0;
741 }
742
743 int32_t lengthInUTF8 = 0;
744 u_strToUTF8(dest, destCapacity, &lengthInUTF8,
745 destStr.getBuffer(), destStr.length(), status);
746 return lengthInUTF8;
747 }
748
749
750 U_CAPI int32_t U_EXPORT2
uspoof_serialize(USpoofChecker * sc,void * buf,int32_t capacity,UErrorCode * status)751 uspoof_serialize(USpoofChecker *sc,void *buf, int32_t capacity, UErrorCode *status) {
752 SpoofImpl *This = SpoofImpl::validateThis(sc, *status);
753 if (This == NULL) {
754 U_ASSERT(U_FAILURE(*status));
755 return 0;
756 }
757
758 return This->fSpoofData->serialize(buf, capacity, *status);
759 }
760
761 U_CAPI const USet * U_EXPORT2
uspoof_getInclusionSet(UErrorCode * status)762 uspoof_getInclusionSet(UErrorCode *status) {
763 umtx_initOnce(gSpoofInitStaticsOnce, &initializeStatics, *status);
764 return gInclusionSet->toUSet();
765 }
766
767 U_CAPI const USet * U_EXPORT2
uspoof_getRecommendedSet(UErrorCode * status)768 uspoof_getRecommendedSet(UErrorCode *status) {
769 umtx_initOnce(gSpoofInitStaticsOnce, &initializeStatics, *status);
770 return gRecommendedSet->toUSet();
771 }
772
773 U_I18N_API const UnicodeSet * U_EXPORT2
uspoof_getInclusionUnicodeSet(UErrorCode * status)774 uspoof_getInclusionUnicodeSet(UErrorCode *status) {
775 umtx_initOnce(gSpoofInitStaticsOnce, &initializeStatics, *status);
776 return gInclusionSet;
777 }
778
779 U_I18N_API const UnicodeSet * U_EXPORT2
uspoof_getRecommendedUnicodeSet(UErrorCode * status)780 uspoof_getRecommendedUnicodeSet(UErrorCode *status) {
781 umtx_initOnce(gSpoofInitStaticsOnce, &initializeStatics, *status);
782 return gRecommendedSet;
783 }
784
785 //------------------
786 // CheckResult APIs
787 //------------------
788
789 U_CAPI USpoofCheckResult* U_EXPORT2
uspoof_openCheckResult(UErrorCode * status)790 uspoof_openCheckResult(UErrorCode *status) {
791 CheckResult* checkResult = new CheckResult();
792 if (checkResult == NULL) {
793 *status = U_MEMORY_ALLOCATION_ERROR;
794 return NULL;
795 }
796 return checkResult->asUSpoofCheckResult();
797 }
798
799 U_CAPI void U_EXPORT2
uspoof_closeCheckResult(USpoofCheckResult * checkResult)800 uspoof_closeCheckResult(USpoofCheckResult* checkResult) {
801 UErrorCode status = U_ZERO_ERROR;
802 CheckResult* This = CheckResult::validateThis(checkResult, status);
803 delete This;
804 }
805
806 U_CAPI int32_t U_EXPORT2
uspoof_getCheckResultChecks(const USpoofCheckResult * checkResult,UErrorCode * status)807 uspoof_getCheckResultChecks(const USpoofCheckResult *checkResult, UErrorCode *status) {
808 const CheckResult* This = CheckResult::validateThis(checkResult, *status);
809 if (U_FAILURE(*status)) { return 0; }
810 return This->fChecks;
811 }
812
813 U_CAPI URestrictionLevel U_EXPORT2
uspoof_getCheckResultRestrictionLevel(const USpoofCheckResult * checkResult,UErrorCode * status)814 uspoof_getCheckResultRestrictionLevel(const USpoofCheckResult *checkResult, UErrorCode *status) {
815 const CheckResult* This = CheckResult::validateThis(checkResult, *status);
816 if (U_FAILURE(*status)) { return USPOOF_UNRESTRICTIVE; }
817 return This->fRestrictionLevel;
818 }
819
820 U_CAPI const USet* U_EXPORT2
uspoof_getCheckResultNumerics(const USpoofCheckResult * checkResult,UErrorCode * status)821 uspoof_getCheckResultNumerics(const USpoofCheckResult *checkResult, UErrorCode *status) {
822 const CheckResult* This = CheckResult::validateThis(checkResult, *status);
823 if (U_FAILURE(*status)) { return NULL; }
824 return This->fNumerics.toUSet();
825 }
826
827
828
829 #endif // !UCONFIG_NO_NORMALIZATION
830