/src/skia/third_party/externals/icu/source/common/udata.cpp
Line | Count | Source (jump to first uncovered line) |
1 | | // © 2016 and later: Unicode, Inc. and others. |
2 | | // License & terms of use: http://www.unicode.org/copyright.html |
3 | | /* |
4 | | ****************************************************************************** |
5 | | * |
6 | | * Copyright (C) 1999-2016, International Business Machines |
7 | | * Corporation and others. All Rights Reserved. |
8 | | * |
9 | | ****************************************************************************** |
10 | | * file name: udata.cpp |
11 | | * encoding: UTF-8 |
12 | | * tab size: 8 (not used) |
13 | | * indentation:4 |
14 | | * |
15 | | * created on: 1999oct25 |
16 | | * created by: Markus W. Scherer |
17 | | */ |
18 | | |
19 | | #include "unicode/utypes.h" /* U_PLATFORM etc. */ |
20 | | |
21 | | #ifdef __GNUC__ |
22 | | /* if gcc |
23 | | #define ATTRIBUTE_WEAK __attribute__ ((weak)) |
24 | | might have to #include some other header |
25 | | */ |
26 | | #endif |
27 | | |
28 | | #include "unicode/putil.h" |
29 | | #include "unicode/udata.h" |
30 | | #include "unicode/uversion.h" |
31 | | #include "charstr.h" |
32 | | #include "cmemory.h" |
33 | | #include "cstring.h" |
34 | | #include "mutex.h" |
35 | | #include "putilimp.h" |
36 | | #include "restrace.h" |
37 | | #include "uassert.h" |
38 | | #include "ucln_cmn.h" |
39 | | #include "ucmndata.h" |
40 | | #include "udatamem.h" |
41 | | #include "uhash.h" |
42 | | #include "umapfile.h" |
43 | | #include "umutex.h" |
44 | | |
45 | | /*********************************************************************** |
46 | | * |
47 | | * Notes on the organization of the ICU data implementation |
48 | | * |
49 | | * All of the public API is defined in udata.h |
50 | | * |
51 | | * The implementation is split into several files... |
52 | | * |
53 | | * - udata.c (this file) contains higher level code that knows about |
54 | | * the search paths for locating data, caching opened data, etc. |
55 | | * |
56 | | * - umapfile.c contains the low level platform-specific code for actually loading |
57 | | * (memory mapping, file reading, whatever) data into memory. |
58 | | * |
59 | | * - ucmndata.c deals with the tables of contents of ICU data items within |
60 | | * an ICU common format data file. The implementation includes |
61 | | * an abstract interface and support for multiple TOC formats. |
62 | | * All knowledge of any specific TOC format is encapsulated here. |
63 | | * |
64 | | * - udatamem.c has code for managing UDataMemory structs. These are little |
65 | | * descriptor objects for blocks of memory holding ICU data of |
66 | | * various types. |
67 | | */ |
68 | | |
69 | | /* configuration ---------------------------------------------------------- */ |
70 | | |
71 | | /* If you are excruciatingly bored turn this on .. */ |
72 | | /* #define UDATA_DEBUG 1 */ |
73 | | |
74 | | #if defined(UDATA_DEBUG) |
75 | | # include <stdio.h> |
76 | | #endif |
77 | | |
78 | | U_NAMESPACE_USE |
79 | | |
80 | | /* |
81 | | * Forward declarations |
82 | | */ |
83 | | static UDataMemory *udata_findCachedData(const char *path, UErrorCode &err); |
84 | | |
85 | | /*********************************************************************** |
86 | | * |
87 | | * static (Global) data |
88 | | * |
89 | | ************************************************************************/ |
90 | | |
91 | | /* |
92 | | * Pointers to the common ICU data. |
93 | | * |
94 | | * We store multiple pointers to ICU data packages and iterate through them |
95 | | * when looking for a data item. |
96 | | * |
97 | | * It is possible to combine this with dependency inversion: |
98 | | * One or more data package libraries may export |
99 | | * functions that each return a pointer to their piece of the ICU data, |
100 | | * and this file would import them as weak functions, without a |
101 | | * strong linker dependency from the common library on the data library. |
102 | | * |
103 | | * Then we can have applications depend on only that part of ICU's data |
104 | | * that they really need, reducing the size of binaries that take advantage |
105 | | * of this. |
106 | | */ |
107 | | static UDataMemory *gCommonICUDataArray[10] = { NULL }; // Access protected by icu global mutex. |
108 | | |
109 | | static u_atomic_int32_t gHaveTriedToLoadCommonData = ATOMIC_INT32_T_INITIALIZER(0); // See extendICUData(). |
110 | | |
111 | | static UHashtable *gCommonDataCache = NULL; /* Global hash table of opened ICU data files. */ |
112 | | static icu::UInitOnce gCommonDataCacheInitOnce = U_INITONCE_INITIALIZER; |
113 | | |
114 | | #if !defined(ICU_DATA_DIR_WINDOWS) |
115 | | static UDataFileAccess gDataFileAccess = UDATA_DEFAULT_ACCESS; // Access not synchronized. |
116 | | // Modifying is documented as thread-unsafe. |
117 | | #else |
118 | | // If we are using the Windows data directory, then look in one spot only. |
119 | | static UDataFileAccess gDataFileAccess = UDATA_NO_FILES; |
120 | | #endif |
121 | | |
122 | | static UBool U_CALLCONV |
123 | | udata_cleanup(void) |
124 | 0 | { |
125 | 0 | int32_t i; |
126 | |
|
127 | 0 | if (gCommonDataCache) { /* Delete the cache of user data mappings. */ |
128 | 0 | uhash_close(gCommonDataCache); /* Table owns the contents, and will delete them. */ |
129 | 0 | gCommonDataCache = NULL; /* Cleanup is not thread safe. */ |
130 | 0 | } |
131 | 0 | gCommonDataCacheInitOnce.reset(); |
132 | |
|
133 | 0 | for (i = 0; i < UPRV_LENGTHOF(gCommonICUDataArray) && gCommonICUDataArray[i] != NULL; ++i) { |
134 | 0 | udata_close(gCommonICUDataArray[i]); |
135 | 0 | gCommonICUDataArray[i] = NULL; |
136 | 0 | } |
137 | 0 | gHaveTriedToLoadCommonData = 0; |
138 | |
|
139 | 0 | return TRUE; /* Everything was cleaned up */ |
140 | 0 | } |
141 | | |
142 | | static UBool U_CALLCONV |
143 | | findCommonICUDataByName(const char *inBasename, UErrorCode &err) |
144 | 2 | { |
145 | 2 | UBool found = FALSE; |
146 | 2 | int32_t i; |
147 | | |
148 | 2 | UDataMemory *pData = udata_findCachedData(inBasename, err); |
149 | 2 | if (U_FAILURE(err) || pData == NULL) |
150 | 2 | return FALSE; |
151 | | |
152 | 0 | { |
153 | 0 | Mutex lock; |
154 | 0 | for (i = 0; i < UPRV_LENGTHOF(gCommonICUDataArray); ++i) { |
155 | 0 | if ((gCommonICUDataArray[i] != NULL) && (gCommonICUDataArray[i]->pHeader == pData->pHeader)) { |
156 | | /* The data pointer is already in the array. */ |
157 | 0 | found = TRUE; |
158 | 0 | break; |
159 | 0 | } |
160 | 0 | } |
161 | 0 | } |
162 | 0 | return found; |
163 | 0 | } |
164 | | |
165 | | |
166 | | /* |
167 | | * setCommonICUData. Set a UDataMemory to be the global ICU Data |
168 | | */ |
169 | | static UBool |
170 | | setCommonICUData(UDataMemory *pData, /* The new common data. Belongs to caller, we copy it. */ |
171 | | UBool warn, /* If true, set USING_DEFAULT warning if ICUData was */ |
172 | | /* changed by another thread before we got to it. */ |
173 | | UErrorCode *pErr) |
174 | 2 | { |
175 | 2 | UDataMemory *newCommonData = UDataMemory_createNewInstance(pErr); |
176 | 2 | int32_t i; |
177 | 2 | UBool didUpdate = FALSE; |
178 | 2 | if (U_FAILURE(*pErr)) { |
179 | 0 | return FALSE; |
180 | 0 | } |
181 | | |
182 | | /* For the assignment, other threads must cleanly see either the old */ |
183 | | /* or the new, not some partially initialized new. The old can not be */ |
184 | | /* deleted - someone may still have a pointer to it lying around in */ |
185 | | /* their locals. */ |
186 | 2 | UDatamemory_assign(newCommonData, pData); |
187 | 2 | umtx_lock(NULL); |
188 | 2 | for (i = 0; i < UPRV_LENGTHOF(gCommonICUDataArray); ++i) { |
189 | 2 | if (gCommonICUDataArray[i] == NULL) { |
190 | 2 | gCommonICUDataArray[i] = newCommonData; |
191 | 2 | didUpdate = TRUE; |
192 | 2 | break; |
193 | 0 | } else if (gCommonICUDataArray[i]->pHeader == pData->pHeader) { |
194 | | /* The same data pointer is already in the array. */ |
195 | 0 | break; |
196 | 0 | } |
197 | 2 | } |
198 | 2 | umtx_unlock(NULL); |
199 | | |
200 | 2 | if (i == UPRV_LENGTHOF(gCommonICUDataArray) && warn) { |
201 | 0 | *pErr = U_USING_DEFAULT_WARNING; |
202 | 0 | } |
203 | 2 | if (didUpdate) { |
204 | 2 | ucln_common_registerCleanup(UCLN_COMMON_UDATA, udata_cleanup); |
205 | 0 | } else { |
206 | 0 | uprv_free(newCommonData); |
207 | 0 | } |
208 | 2 | return didUpdate; |
209 | 2 | } |
210 | | |
211 | | #if !defined(ICU_DATA_DIR_WINDOWS) |
212 | | |
213 | | static UBool |
214 | 2 | setCommonICUDataPointer(const void *pData, UBool /*warn*/, UErrorCode *pErrorCode) { |
215 | 2 | UDataMemory tData; |
216 | 2 | UDataMemory_init(&tData); |
217 | 2 | UDataMemory_setData(&tData, pData); |
218 | 2 | udata_checkCommonData(&tData, pErrorCode); |
219 | 2 | return setCommonICUData(&tData, FALSE, pErrorCode); |
220 | 2 | } |
221 | | |
222 | | #endif |
223 | | |
224 | | static const char * |
225 | 6 | findBasename(const char *path) { |
226 | 6 | const char *basename=uprv_strrchr(path, U_FILE_SEP_CHAR); |
227 | 6 | if(basename==NULL) { |
228 | 6 | return path; |
229 | 0 | } else { |
230 | 0 | return basename+1; |
231 | 0 | } |
232 | 6 | } |
233 | | |
234 | | #ifdef UDATA_DEBUG |
235 | | static const char * |
236 | | packageNameFromPath(const char *path) |
237 | | { |
238 | | if((path == NULL) || (*path == 0)) { |
239 | | return U_ICUDATA_NAME; |
240 | | } |
241 | | |
242 | | path = findBasename(path); |
243 | | |
244 | | if((path == NULL) || (*path == 0)) { |
245 | | return U_ICUDATA_NAME; |
246 | | } |
247 | | |
248 | | return path; |
249 | | } |
250 | | #endif |
251 | | |
252 | | /*----------------------------------------------------------------------* |
253 | | * * |
254 | | * Cache for common data * |
255 | | * Functions for looking up or adding entries to a cache of * |
256 | | * data that has been previously opened. Avoids a potentially * |
257 | | * expensive operation of re-opening the data for subsequent * |
258 | | * uses. * |
259 | | * * |
260 | | * Data remains cached for the duration of the process. * |
261 | | * * |
262 | | *----------------------------------------------------------------------*/ |
263 | | |
264 | | typedef struct DataCacheElement { |
265 | | char *name; |
266 | | UDataMemory *item; |
267 | | } DataCacheElement; |
268 | | |
269 | | |
270 | | |
271 | | /* |
272 | | * Deleter function for DataCacheElements. |
273 | | * udata cleanup function closes the hash table; hash table in turn calls back to |
274 | | * here for each entry. |
275 | | */ |
276 | 0 | static void U_CALLCONV DataCacheElement_deleter(void *pDCEl) { |
277 | 0 | DataCacheElement *p = (DataCacheElement *)pDCEl; |
278 | 0 | udata_close(p->item); /* unmaps storage */ |
279 | 0 | uprv_free(p->name); /* delete the hash key string. */ |
280 | 0 | uprv_free(pDCEl); /* delete 'this' */ |
281 | 0 | } |
282 | | |
283 | 2 | static void U_CALLCONV udata_initHashTable(UErrorCode &err) { |
284 | 2 | U_ASSERT(gCommonDataCache == NULL); |
285 | 2 | gCommonDataCache = uhash_open(uhash_hashChars, uhash_compareChars, NULL, &err); |
286 | 2 | if (U_FAILURE(err)) { |
287 | 0 | return; |
288 | 0 | } |
289 | 2 | U_ASSERT(gCommonDataCache != NULL); |
290 | 2 | uhash_setValueDeleter(gCommonDataCache, DataCacheElement_deleter); |
291 | 2 | ucln_common_registerCleanup(UCLN_COMMON_UDATA, udata_cleanup); |
292 | 2 | } |
293 | | |
294 | | /* udata_getCacheHashTable() |
295 | | * Get the hash table used to store the data cache entries. |
296 | | * Lazy create it if it doesn't yet exist. |
297 | | */ |
298 | 4 | static UHashtable *udata_getHashTable(UErrorCode &err) { |
299 | 4 | umtx_initOnce(gCommonDataCacheInitOnce, &udata_initHashTable, err); |
300 | 4 | return gCommonDataCache; |
301 | 4 | } |
302 | | |
303 | | |
304 | | |
305 | | static UDataMemory *udata_findCachedData(const char *path, UErrorCode &err) |
306 | 4 | { |
307 | 4 | UHashtable *htable; |
308 | 4 | UDataMemory *retVal = NULL; |
309 | 4 | DataCacheElement *el; |
310 | 4 | const char *baseName; |
311 | | |
312 | 4 | htable = udata_getHashTable(err); |
313 | 4 | if (U_FAILURE(err)) { |
314 | 2 | return NULL; |
315 | 2 | } |
316 | | |
317 | 2 | baseName = findBasename(path); /* Cache remembers only the base name, not the full path. */ |
318 | 2 | umtx_lock(NULL); |
319 | 2 | el = (DataCacheElement *)uhash_get(htable, baseName); |
320 | 2 | umtx_unlock(NULL); |
321 | 2 | if (el != NULL) { |
322 | 0 | retVal = el->item; |
323 | 0 | } |
324 | | #ifdef UDATA_DEBUG |
325 | | fprintf(stderr, "Cache: [%s] -> %p\n", baseName, (void*) retVal); |
326 | | #endif |
327 | 2 | return retVal; |
328 | 2 | } |
329 | | |
330 | | |
331 | 0 | static UDataMemory *udata_cacheDataItem(const char *path, UDataMemory *item, UErrorCode *pErr) { |
332 | 0 | DataCacheElement *newElement; |
333 | 0 | const char *baseName; |
334 | 0 | int32_t nameLen; |
335 | 0 | UHashtable *htable; |
336 | 0 | DataCacheElement *oldValue = NULL; |
337 | 0 | UErrorCode subErr = U_ZERO_ERROR; |
338 | |
|
339 | 0 | htable = udata_getHashTable(*pErr); |
340 | 0 | if (U_FAILURE(*pErr)) { |
341 | 0 | return NULL; |
342 | 0 | } |
343 | | |
344 | | /* Create a new DataCacheElement - the thingy we store in the hash table - |
345 | | * and copy the supplied path and UDataMemoryItems into it. |
346 | | */ |
347 | 0 | newElement = (DataCacheElement *)uprv_malloc(sizeof(DataCacheElement)); |
348 | 0 | if (newElement == NULL) { |
349 | 0 | *pErr = U_MEMORY_ALLOCATION_ERROR; |
350 | 0 | return NULL; |
351 | 0 | } |
352 | 0 | newElement->item = UDataMemory_createNewInstance(pErr); |
353 | 0 | if (U_FAILURE(*pErr)) { |
354 | 0 | uprv_free(newElement); |
355 | 0 | return NULL; |
356 | 0 | } |
357 | 0 | UDatamemory_assign(newElement->item, item); |
358 | |
|
359 | 0 | baseName = findBasename(path); |
360 | 0 | nameLen = (int32_t)uprv_strlen(baseName); |
361 | 0 | newElement->name = (char *)uprv_malloc(nameLen+1); |
362 | 0 | if (newElement->name == NULL) { |
363 | 0 | *pErr = U_MEMORY_ALLOCATION_ERROR; |
364 | 0 | uprv_free(newElement->item); |
365 | 0 | uprv_free(newElement); |
366 | 0 | return NULL; |
367 | 0 | } |
368 | 0 | uprv_strcpy(newElement->name, baseName); |
369 | | |
370 | | /* Stick the new DataCacheElement into the hash table. |
371 | | */ |
372 | 0 | umtx_lock(NULL); |
373 | 0 | oldValue = (DataCacheElement *)uhash_get(htable, path); |
374 | 0 | if (oldValue != NULL) { |
375 | 0 | subErr = U_USING_DEFAULT_WARNING; |
376 | 0 | } |
377 | 0 | else { |
378 | 0 | uhash_put( |
379 | 0 | htable, |
380 | 0 | newElement->name, /* Key */ |
381 | 0 | newElement, /* Value */ |
382 | 0 | &subErr); |
383 | 0 | } |
384 | 0 | umtx_unlock(NULL); |
385 | |
|
386 | | #ifdef UDATA_DEBUG |
387 | | fprintf(stderr, "Cache: [%s] <<< %p : %s. vFunc=%p\n", newElement->name, |
388 | | (void*) newElement->item, u_errorName(subErr), (void*) newElement->item->vFuncs); |
389 | | #endif |
390 | |
|
391 | 0 | if (subErr == U_USING_DEFAULT_WARNING || U_FAILURE(subErr)) { |
392 | 0 | *pErr = subErr; /* copy sub err unto fillin ONLY if something happens. */ |
393 | 0 | uprv_free(newElement->name); |
394 | 0 | uprv_free(newElement->item); |
395 | 0 | uprv_free(newElement); |
396 | 0 | return oldValue ? oldValue->item : NULL; |
397 | 0 | } |
398 | | |
399 | 0 | return newElement->item; |
400 | 0 | } |
401 | | |
402 | | /*----------------------------------------------------------------------*============== |
403 | | * * |
404 | | * Path management. Could be shared with other tools/etc if need be * |
405 | | * later on. * |
406 | | * * |
407 | | *----------------------------------------------------------------------*/ |
408 | | |
409 | | U_NAMESPACE_BEGIN |
410 | | |
411 | | class UDataPathIterator |
412 | | { |
413 | | public: |
414 | | UDataPathIterator(const char *path, const char *pkg, |
415 | | const char *item, const char *suffix, UBool doCheckLastFour, |
416 | | UErrorCode *pErrorCode); |
417 | | const char *next(UErrorCode *pErrorCode); |
418 | | |
419 | | private: |
420 | | const char *path; /* working path (u_icudata_Dir) */ |
421 | | const char *nextPath; /* path following this one */ |
422 | | const char *basename; /* item's basename (icudt22e_mt.res)*/ |
423 | | |
424 | | StringPiece suffix; /* item suffix (can be null) */ |
425 | | |
426 | | uint32_t basenameLen; /* length of basename */ |
427 | | |
428 | | CharString itemPath; /* path passed in with item name */ |
429 | | CharString pathBuffer; /* output path for this it'ion */ |
430 | | CharString packageStub; /* example: "/icudt28b". Will ignore that leaf in set paths. */ |
431 | | |
432 | | UBool checkLastFour; /* if TRUE then allow paths such as '/foo/myapp.dat' |
433 | | * to match, checks last 4 chars of suffix with |
434 | | * last 4 of path, then previous chars. */ |
435 | | }; |
436 | | |
437 | | /** |
438 | | * @param iter The iterator to be initialized. Its current state does not matter. |
439 | | * @param inPath The full pathname to be iterated over. If NULL, defaults to U_ICUDATA_NAME |
440 | | * @param pkg Package which is being searched for, ex "icudt28l". Will ignore leaf directories such as /icudt28l |
441 | | * @param item Item to be searched for. Can include full path, such as /a/b/foo.dat |
442 | | * @param inSuffix Optional item suffix, if not-null (ex. ".dat") then 'path' can contain 'item' explicitly. |
443 | | * Ex: 'stuff.dat' would be found in '/a/foo:/tmp/stuff.dat:/bar/baz' as item #2. |
444 | | * '/blarg/stuff.dat' would also be found. |
445 | | * Note: inSuffix may also be the 'item' being searched for as well, (ex: "ibm-5348_P100-1997.cnv"), in which case |
446 | | * the 'item' parameter is often the same as pkg. (Though sometimes might have a tree part as well, ex: "icudt62l-curr"). |
447 | | */ |
448 | | UDataPathIterator::UDataPathIterator(const char *inPath, const char *pkg, |
449 | | const char *item, const char *inSuffix, UBool doCheckLastFour, |
450 | | UErrorCode *pErrorCode) |
451 | 2 | { |
452 | | #ifdef UDATA_DEBUG |
453 | | fprintf(stderr, "SUFFIX1=%s PATH=%s\n", inSuffix, inPath); |
454 | | #endif |
455 | | /** Path **/ |
456 | 2 | if(inPath == NULL) { |
457 | 0 | path = u_getDataDirectory(); |
458 | 2 | } else { |
459 | 2 | path = inPath; |
460 | 2 | } |
461 | | |
462 | | /** Package **/ |
463 | 2 | if(pkg != NULL) { |
464 | 2 | packageStub.append(U_FILE_SEP_CHAR, *pErrorCode).append(pkg, *pErrorCode); |
465 | | #ifdef UDATA_DEBUG |
466 | | fprintf(stderr, "STUB=%s [%d]\n", packageStub.data(), packageStub.length()); |
467 | | #endif |
468 | 2 | } |
469 | | |
470 | | /** Item **/ |
471 | 2 | basename = findBasename(item); |
472 | 2 | basenameLen = (int32_t)uprv_strlen(basename); |
473 | | |
474 | | /** Item path **/ |
475 | 2 | if(basename == item) { |
476 | 2 | nextPath = path; |
477 | 0 | } else { |
478 | 0 | itemPath.append(item, (int32_t)(basename-item), *pErrorCode); |
479 | 0 | nextPath = itemPath.data(); |
480 | 0 | } |
481 | | #ifdef UDATA_DEBUG |
482 | | fprintf(stderr, "SUFFIX=%s [%p]\n", inSuffix, (void*) inSuffix); |
483 | | #endif |
484 | | |
485 | | /** Suffix **/ |
486 | 2 | if(inSuffix != NULL) { |
487 | 2 | suffix = inSuffix; |
488 | 0 | } else { |
489 | 0 | suffix = ""; |
490 | 0 | } |
491 | | |
492 | 2 | checkLastFour = doCheckLastFour; |
493 | | |
494 | | /* pathBuffer will hold the output path strings returned by this iterator */ |
495 | | |
496 | | #ifdef UDATA_DEBUG |
497 | | fprintf(stderr, "0: init %s -> [path=%s], [base=%s], [suff=%s], [itempath=%s], [nextpath=%s], [checklast4=%s]\n", |
498 | | item, |
499 | | path, |
500 | | basename, |
501 | | suffix.data(), |
502 | | itemPath.data(), |
503 | | nextPath, |
504 | | checkLastFour?"TRUE":"false"); |
505 | | #endif |
506 | 2 | } |
507 | | |
508 | | /** |
509 | | * Get the next path on the list. |
510 | | * |
511 | | * @param iter The Iter to be used |
512 | | * @param len If set, pointer to the length of the returned path, for convenience. |
513 | | * @return Pointer to the next path segment, or NULL if there are no more. |
514 | | */ |
515 | | const char *UDataPathIterator::next(UErrorCode *pErrorCode) |
516 | 2 | { |
517 | 2 | if(U_FAILURE(*pErrorCode)) { |
518 | 0 | return NULL; |
519 | 0 | } |
520 | | |
521 | 2 | const char *currentPath = NULL; |
522 | 2 | int32_t pathLen = 0; |
523 | 2 | const char *pathBasename; |
524 | | |
525 | 2 | do |
526 | 4 | { |
527 | 4 | if( nextPath == NULL ) { |
528 | 2 | break; |
529 | 2 | } |
530 | 2 | currentPath = nextPath; |
531 | | |
532 | 2 | if(nextPath == itemPath.data()) { /* we were processing item's path. */ |
533 | 0 | nextPath = path; /* start with regular path next tm. */ |
534 | 0 | pathLen = (int32_t)uprv_strlen(currentPath); |
535 | 2 | } else { |
536 | | /* fix up next for next time */ |
537 | 2 | nextPath = uprv_strchr(currentPath, U_PATH_SEP_CHAR); |
538 | 2 | if(nextPath == NULL) { |
539 | | /* segment: entire path */ |
540 | 2 | pathLen = (int32_t)uprv_strlen(currentPath); |
541 | 0 | } else { |
542 | | /* segment: until next segment */ |
543 | 0 | pathLen = (int32_t)(nextPath - currentPath); |
544 | | /* skip divider */ |
545 | 0 | nextPath ++; |
546 | 0 | } |
547 | 2 | } |
548 | | |
549 | 2 | if(pathLen == 0) { |
550 | 2 | continue; |
551 | 2 | } |
552 | | |
553 | | #ifdef UDATA_DEBUG |
554 | | fprintf(stderr, "rest of path (IDD) = %s\n", currentPath); |
555 | | fprintf(stderr, " "); |
556 | | { |
557 | | int32_t qqq; |
558 | | for(qqq=0;qqq<pathLen;qqq++) |
559 | | { |
560 | | fprintf(stderr, " "); |
561 | | } |
562 | | |
563 | | fprintf(stderr, "^\n"); |
564 | | } |
565 | | #endif |
566 | 0 | pathBuffer.clear().append(currentPath, pathLen, *pErrorCode); |
567 | | |
568 | | /* check for .dat files */ |
569 | 0 | pathBasename = findBasename(pathBuffer.data()); |
570 | |
|
571 | 0 | if(checkLastFour == TRUE && |
572 | 0 | (pathLen>=4) && |
573 | 0 | uprv_strncmp(pathBuffer.data() +(pathLen-4), suffix.data(), 4)==0 && /* suffix matches */ |
574 | 0 | uprv_strncmp(findBasename(pathBuffer.data()), basename, basenameLen)==0 && /* base matches */ |
575 | 0 | uprv_strlen(pathBasename)==(basenameLen+4)) { /* base+suffix = full len */ |
576 | |
|
577 | | #ifdef UDATA_DEBUG |
578 | | fprintf(stderr, "Have %s file on the path: %s\n", suffix.data(), pathBuffer.data()); |
579 | | #endif |
580 | | /* do nothing */ |
581 | 0 | } |
582 | 0 | else |
583 | 0 | { /* regular dir path */ |
584 | 0 | if(pathBuffer[pathLen-1] != U_FILE_SEP_CHAR) { |
585 | 0 | if((pathLen>=4) && |
586 | 0 | uprv_strncmp(pathBuffer.data()+(pathLen-4), ".dat", 4) == 0) |
587 | 0 | { |
588 | | #ifdef UDATA_DEBUG |
589 | | fprintf(stderr, "skipping non-directory .dat file %s\n", pathBuffer.data()); |
590 | | #endif |
591 | 0 | continue; |
592 | 0 | } |
593 | | |
594 | | /* Check if it is a directory with the same name as our package */ |
595 | 0 | if(!packageStub.isEmpty() && |
596 | 0 | (pathLen > packageStub.length()) && |
597 | 0 | !uprv_strcmp(pathBuffer.data() + pathLen - packageStub.length(), packageStub.data())) { |
598 | | #ifdef UDATA_DEBUG |
599 | | fprintf(stderr, "Found stub %s (will add package %s of len %d)\n", packageStub.data(), basename, basenameLen); |
600 | | #endif |
601 | 0 | pathBuffer.truncate(pathLen - packageStub.length()); |
602 | 0 | } |
603 | 0 | pathBuffer.append(U_FILE_SEP_CHAR, *pErrorCode); |
604 | 0 | } |
605 | | |
606 | | /* + basename */ |
607 | 0 | pathBuffer.append(packageStub.data()+1, packageStub.length()-1, *pErrorCode); |
608 | |
|
609 | 0 | if (!suffix.empty()) /* tack on suffix */ |
610 | 0 | { |
611 | 0 | if (suffix.length() > 4) { |
612 | | // If the suffix is actually an item ("ibm-5348_P100-1997.cnv") and not an extension (".res") |
613 | | // then we need to ensure that the path ends with a separator. |
614 | 0 | pathBuffer.ensureEndsWithFileSeparator(*pErrorCode); |
615 | 0 | } |
616 | 0 | pathBuffer.append(suffix, *pErrorCode); |
617 | 0 | } |
618 | 0 | } |
619 | |
|
620 | | #ifdef UDATA_DEBUG |
621 | | fprintf(stderr, " --> %s\n", pathBuffer.data()); |
622 | | #endif |
623 | |
|
624 | 0 | return pathBuffer.data(); |
625 | | |
626 | 2 | } while(path); |
627 | | |
628 | | /* fell way off the end */ |
629 | 2 | return NULL; |
630 | 2 | } |
631 | | |
632 | | U_NAMESPACE_END |
633 | | |
634 | | /* ==================================================================================*/ |
635 | | |
636 | | |
637 | | /*----------------------------------------------------------------------* |
638 | | * * |
639 | | * Add a static reference to the common data library * |
640 | | * Unless overridden by an explicit udata_setCommonData, this will be * |
641 | | * our common data. * |
642 | | * * |
643 | | *----------------------------------------------------------------------*/ |
644 | | #if !defined(ICU_DATA_DIR_WINDOWS) |
645 | | // When using the Windows system data, we expect only a single data file. |
646 | | extern "C" const ICU_Data_Header U_DATA_API U_ICUDATA_ENTRY_POINT; |
647 | | #endif |
648 | | |
649 | | /* |
650 | | * This would be a good place for weak-linkage declarations of |
651 | | * partial-data-library access functions where each returns a pointer |
652 | | * to its data package, if it is linked in. |
653 | | */ |
654 | | /* |
655 | | extern const void *uprv_getICUData_collation(void) ATTRIBUTE_WEAK; |
656 | | extern const void *uprv_getICUData_conversion(void) ATTRIBUTE_WEAK; |
657 | | */ |
658 | | |
659 | | /*----------------------------------------------------------------------* |
660 | | * * |
661 | | * openCommonData Attempt to open a common format (.dat) file * |
662 | | * Map it into memory (if it's not there already) * |
663 | | * and return a UDataMemory object for it. * |
664 | | * * |
665 | | * If the requested data is already open and cached * |
666 | | * just return the cached UDataMem object. * |
667 | | * * |
668 | | *----------------------------------------------------------------------*/ |
669 | | static UDataMemory * |
670 | | openCommonData(const char *path, /* Path from OpenChoice? */ |
671 | | int32_t commonDataIndex, /* ICU Data (index >= 0) if path == NULL */ |
672 | | UErrorCode *pErrorCode) |
673 | 39.6k | { |
674 | 39.6k | UDataMemory tData; |
675 | 39.6k | const char *pathBuffer; |
676 | 39.6k | const char *inBasename; |
677 | | |
678 | 39.6k | if (U_FAILURE(*pErrorCode)) { |
679 | 0 | return NULL; |
680 | 0 | } |
681 | | |
682 | 39.6k | UDataMemory_init(&tData); |
683 | | |
684 | | /* ??????? TODO revisit this */ |
685 | 39.6k | if (commonDataIndex >= 0) { |
686 | | /* "mini-cache" for common ICU data */ |
687 | 39.6k | if(commonDataIndex >= UPRV_LENGTHOF(gCommonICUDataArray)) { |
688 | 0 | return NULL; |
689 | 0 | } |
690 | 39.6k | { |
691 | 39.6k | Mutex lock; |
692 | 39.6k | if(gCommonICUDataArray[commonDataIndex] != NULL) { |
693 | 39.6k | return gCommonICUDataArray[commonDataIndex]; |
694 | 39.6k | } |
695 | 4 | #if !defined(ICU_DATA_DIR_WINDOWS) |
696 | | // When using the Windows system data, we expect only a single data file. |
697 | 4 | int32_t i; |
698 | 4 | for(i = 0; i < commonDataIndex; ++i) { |
699 | 2 | if(gCommonICUDataArray[i]->pHeader == &U_ICUDATA_ENTRY_POINT.hdr) { |
700 | | /* The linked-in data is already in the list. */ |
701 | 2 | return NULL; |
702 | 2 | } |
703 | 2 | } |
704 | 4 | #endif |
705 | 4 | } |
706 | | |
707 | | /* Add the linked-in data to the list. */ |
708 | | /* |
709 | | * This is where we would check and call weakly linked partial-data-library |
710 | | * access functions. |
711 | | */ |
712 | | /* |
713 | | if (uprv_getICUData_collation) { |
714 | | setCommonICUDataPointer(uprv_getICUData_collation(), FALSE, pErrorCode); |
715 | | } |
716 | | if (uprv_getICUData_conversion) { |
717 | | setCommonICUDataPointer(uprv_getICUData_conversion(), FALSE, pErrorCode); |
718 | | } |
719 | | */ |
720 | 4 | #if !defined(ICU_DATA_DIR_WINDOWS) |
721 | | // When using the Windows system data, we expect only a single data file. |
722 | 2 | setCommonICUDataPointer(&U_ICUDATA_ENTRY_POINT.hdr, FALSE, pErrorCode); |
723 | 2 | { |
724 | 2 | Mutex lock; |
725 | 2 | return gCommonICUDataArray[commonDataIndex]; |
726 | 2 | } |
727 | 2 | #endif |
728 | 2 | } |
729 | | |
730 | | |
731 | | /* request is NOT for ICU Data. */ |
732 | | |
733 | | /* Find the base name portion of the supplied path. */ |
734 | | /* inBasename will be left pointing somewhere within the original path string. */ |
735 | 2 | inBasename = findBasename(path); |
736 | | #ifdef UDATA_DEBUG |
737 | | fprintf(stderr, "inBasename = %s\n", inBasename); |
738 | | #endif |
739 | | |
740 | 2 | if(*inBasename==0) { |
741 | | /* no basename. This will happen if the original path was a directory name, */ |
742 | | /* like "a/b/c/". (Fallback to separate files will still work.) */ |
743 | | #ifdef UDATA_DEBUG |
744 | | fprintf(stderr, "ocd: no basename in %s, bailing.\n", path); |
745 | | #endif |
746 | 0 | if (U_SUCCESS(*pErrorCode)) { |
747 | 0 | *pErrorCode=U_FILE_ACCESS_ERROR; |
748 | 0 | } |
749 | 0 | return NULL; |
750 | 0 | } |
751 | | |
752 | | /* Is the requested common data file already open and cached? */ |
753 | | /* Note that the cache is keyed by the base name only. The rest of the path, */ |
754 | | /* if any, is not considered. */ |
755 | 2 | UDataMemory *dataToReturn = udata_findCachedData(inBasename, *pErrorCode); |
756 | 2 | if (dataToReturn != NULL || U_FAILURE(*pErrorCode)) { |
757 | 0 | return dataToReturn; |
758 | 0 | } |
759 | | |
760 | | /* Requested item is not in the cache. |
761 | | * Hunt it down, trying all the path locations |
762 | | */ |
763 | | |
764 | 2 | UDataPathIterator iter(u_getDataDirectory(), inBasename, path, ".dat", TRUE, pErrorCode); |
765 | | |
766 | 2 | while ((UDataMemory_isLoaded(&tData)==FALSE) && (pathBuffer = iter.next(pErrorCode)) != NULL) |
767 | 0 | { |
768 | | #ifdef UDATA_DEBUG |
769 | | fprintf(stderr, "ocd: trying path %s - ", pathBuffer); |
770 | | #endif |
771 | 0 | uprv_mapFile(&tData, pathBuffer, pErrorCode); |
772 | | #ifdef UDATA_DEBUG |
773 | | fprintf(stderr, "%s\n", UDataMemory_isLoaded(&tData)?"LOADED":"not loaded"); |
774 | | #endif |
775 | 0 | } |
776 | 2 | if (U_FAILURE(*pErrorCode)) { |
777 | 0 | return NULL; |
778 | 0 | } |
779 | | |
780 | | #if defined(OS390_STUBDATA) && defined(OS390BATCH) |
781 | | if (!UDataMemory_isLoaded(&tData)) { |
782 | | char ourPathBuffer[1024]; |
783 | | /* One more chance, for extendCommonData() */ |
784 | | uprv_strncpy(ourPathBuffer, path, 1019); |
785 | | ourPathBuffer[1019]=0; |
786 | | uprv_strcat(ourPathBuffer, ".dat"); |
787 | | uprv_mapFile(&tData, ourPathBuffer, pErrorCode); |
788 | | } |
789 | | #endif |
790 | | |
791 | 2 | if (U_FAILURE(*pErrorCode)) { |
792 | 0 | return NULL; |
793 | 0 | } |
794 | 2 | if (!UDataMemory_isLoaded(&tData)) { |
795 | | /* no common data */ |
796 | 2 | *pErrorCode=U_FILE_ACCESS_ERROR; |
797 | 2 | return NULL; |
798 | 2 | } |
799 | | |
800 | | /* we have mapped a file, check its header */ |
801 | 0 | udata_checkCommonData(&tData, pErrorCode); |
802 | | |
803 | | |
804 | | /* Cache the UDataMemory struct for this .dat file, |
805 | | * so we won't need to hunt it down and map it again next time |
806 | | * something is needed from it. */ |
807 | 0 | return udata_cacheDataItem(inBasename, &tData, pErrorCode); |
808 | 0 | } |
809 | | |
810 | | |
811 | | /*----------------------------------------------------------------------* |
812 | | * * |
813 | | * extendICUData If the full set of ICU data was not loaded at * |
814 | | * program startup, load it now. This function will * |
815 | | * be called when the lookup of an ICU data item in * |
816 | | * the common ICU data fails. * |
817 | | * * |
818 | | * return true if new data is loaded, false otherwise.* |
819 | | * * |
820 | | *----------------------------------------------------------------------*/ |
821 | | static UBool extendICUData(UErrorCode *pErr) |
822 | 2 | { |
823 | 2 | UDataMemory *pData; |
824 | 2 | UDataMemory copyPData; |
825 | 2 | UBool didUpdate = FALSE; |
826 | | |
827 | | /* |
828 | | * There is a chance for a race condition here. |
829 | | * Normally, ICU data is loaded from a DLL or via mmap() and |
830 | | * setCommonICUData() will detect if the same address is set twice. |
831 | | * If ICU is built with data loading via fread() then the address will |
832 | | * be different each time the common data is loaded and we may add |
833 | | * multiple copies of the data. |
834 | | * In this case, use a mutex to prevent the race. |
835 | | * Use a specific mutex to avoid nested locks of the global mutex. |
836 | | */ |
837 | | #if MAP_IMPLEMENTATION==MAP_STDIO |
838 | | static UMutex extendICUDataMutex; |
839 | | umtx_lock(&extendICUDataMutex); |
840 | | #endif |
841 | 2 | if(!umtx_loadAcquire(gHaveTriedToLoadCommonData)) { |
842 | | /* See if we can explicitly open a .dat file for the ICUData. */ |
843 | 2 | pData = openCommonData( |
844 | 2 | U_ICUDATA_NAME, /* "icudt20l" , for example. */ |
845 | 2 | -1, /* Pretend we're not opening ICUData */ |
846 | 2 | pErr); |
847 | | |
848 | | /* How about if there is no pData, eh... */ |
849 | | |
850 | 2 | UDataMemory_init(©PData); |
851 | 2 | if(pData != NULL) { |
852 | 0 | UDatamemory_assign(©PData, pData); |
853 | 0 | copyPData.map = 0; /* The mapping for this data is owned by the hash table */ |
854 | 0 | copyPData.mapAddr = 0; /* which will unmap it when ICU is shut down. */ |
855 | | /* CommonICUData is also unmapped when ICU is shut down.*/ |
856 | | /* To avoid unmapping the data twice, zero out the map */ |
857 | | /* fields in the UDataMemory that we're assigning */ |
858 | | /* to CommonICUData. */ |
859 | |
|
860 | 0 | didUpdate = /* no longer using this result */ |
861 | 0 | setCommonICUData(©PData,/* The new common data. */ |
862 | 0 | FALSE, /* No warnings if write didn't happen */ |
863 | 0 | pErr); /* setCommonICUData honors errors; NOP if error set */ |
864 | 0 | } |
865 | | |
866 | 2 | umtx_storeRelease(gHaveTriedToLoadCommonData, 1); |
867 | 2 | } |
868 | | |
869 | 2 | didUpdate = findCommonICUDataByName(U_ICUDATA_NAME, *pErr); /* Return 'true' when a racing writes out the extended */ |
870 | | /* data after another thread has failed to see it (in openCommonData), so */ |
871 | | /* extended data can be examined. */ |
872 | | /* Also handles a race through here before gHaveTriedToLoadCommonData is set. */ |
873 | | |
874 | | #if MAP_IMPLEMENTATION==MAP_STDIO |
875 | | umtx_unlock(&extendICUDataMutex); |
876 | | #endif |
877 | 2 | return didUpdate; /* Return true if ICUData pointer was updated. */ |
878 | | /* (Could potentially have been done by another thread racing */ |
879 | | /* us through here, but that's fine, we still return true */ |
880 | | /* so that current thread will also examine extended data. */ |
881 | 2 | } |
882 | | |
883 | | /*----------------------------------------------------------------------* |
884 | | * * |
885 | | * udata_setCommonData * |
886 | | * * |
887 | | *----------------------------------------------------------------------*/ |
888 | | U_CAPI void U_EXPORT2 |
889 | 0 | udata_setCommonData(const void *data, UErrorCode *pErrorCode) { |
890 | 0 | UDataMemory dataMemory; |
891 | |
|
892 | 0 | if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) { |
893 | 0 | return; |
894 | 0 | } |
895 | | |
896 | 0 | if(data==NULL) { |
897 | 0 | *pErrorCode=U_ILLEGAL_ARGUMENT_ERROR; |
898 | 0 | return; |
899 | 0 | } |
900 | | |
901 | | /* set the data pointer and test for validity */ |
902 | 0 | UDataMemory_init(&dataMemory); |
903 | 0 | UDataMemory_setData(&dataMemory, data); |
904 | 0 | udata_checkCommonData(&dataMemory, pErrorCode); |
905 | 0 | if (U_FAILURE(*pErrorCode)) {return;} |
906 | | |
907 | | /* we have good data */ |
908 | | /* Set it up as the ICU Common Data. */ |
909 | 0 | setCommonICUData(&dataMemory, TRUE, pErrorCode); |
910 | 0 | } |
911 | | |
912 | | /*--------------------------------------------------------------------------- |
913 | | * |
914 | | * udata_setAppData |
915 | | * |
916 | | *---------------------------------------------------------------------------- */ |
917 | | U_CAPI void U_EXPORT2 |
918 | | udata_setAppData(const char *path, const void *data, UErrorCode *err) |
919 | 0 | { |
920 | 0 | UDataMemory udm; |
921 | |
|
922 | 0 | if(err==NULL || U_FAILURE(*err)) { |
923 | 0 | return; |
924 | 0 | } |
925 | 0 | if(data==NULL) { |
926 | 0 | *err=U_ILLEGAL_ARGUMENT_ERROR; |
927 | 0 | return; |
928 | 0 | } |
929 | | |
930 | 0 | UDataMemory_init(&udm); |
931 | 0 | UDataMemory_setData(&udm, data); |
932 | 0 | udata_checkCommonData(&udm, err); |
933 | 0 | udata_cacheDataItem(path, &udm, err); |
934 | 0 | } |
935 | | |
936 | | /*----------------------------------------------------------------------------* |
937 | | * * |
938 | | * checkDataItem Given a freshly located/loaded data item, either * |
939 | | * an entry in a common file or a separately loaded file, * |
940 | | * sanity check its header, and see if the data is * |
941 | | * acceptable to the app. * |
942 | | * If the data is good, create and return a UDataMemory * |
943 | | * object that can be returned to the application. * |
944 | | * Return NULL on any sort of failure. * |
945 | | * * |
946 | | *----------------------------------------------------------------------------*/ |
947 | | static UDataMemory * |
948 | | checkDataItem |
949 | | ( |
950 | | const DataHeader *pHeader, /* The data item to be checked. */ |
951 | | UDataMemoryIsAcceptable *isAcceptable, /* App's call-back function */ |
952 | | void *context, /* pass-thru param for above. */ |
953 | | const char *type, /* pass-thru param for above. */ |
954 | | const char *name, /* pass-thru param for above. */ |
955 | | UErrorCode *nonFatalErr, /* Error code if this data was not acceptable */ |
956 | | /* but openChoice should continue with */ |
957 | | /* trying to get data from fallback path. */ |
958 | | UErrorCode *fatalErr /* Bad error, caller should return immediately */ |
959 | | ) |
960 | 39.6k | { |
961 | 39.6k | UDataMemory *rDataMem = NULL; /* the new UDataMemory, to be returned. */ |
962 | | |
963 | 39.6k | if (U_FAILURE(*fatalErr)) { |
964 | 0 | return NULL; |
965 | 0 | } |
966 | | |
967 | 39.6k | if(pHeader->dataHeader.magic1==0xda && |
968 | 39.6k | pHeader->dataHeader.magic2==0x27 && |
969 | 39.6k | (isAcceptable==NULL || isAcceptable(context, type, name, &pHeader->info)) |
970 | 39.6k | ) { |
971 | 39.6k | rDataMem=UDataMemory_createNewInstance(fatalErr); |
972 | 39.6k | if (U_FAILURE(*fatalErr)) { |
973 | 0 | return NULL; |
974 | 0 | } |
975 | 39.6k | rDataMem->pHeader = pHeader; |
976 | 0 | } else { |
977 | | /* the data is not acceptable, look further */ |
978 | | /* If we eventually find something good, this errorcode will be */ |
979 | | /* cleared out. */ |
980 | 0 | *nonFatalErr=U_INVALID_FORMAT_ERROR; |
981 | 0 | } |
982 | 39.6k | return rDataMem; |
983 | 39.6k | } |
984 | | |
985 | | /** |
986 | | * @return 0 if not loaded, 1 if loaded or err |
987 | | */ |
988 | | static UDataMemory *doLoadFromIndividualFiles(const char *pkgName, |
989 | | const char *dataPath, const char *tocEntryPathSuffix, |
990 | | /* following arguments are the same as doOpenChoice itself */ |
991 | | const char *path, const char *type, const char *name, |
992 | | UDataMemoryIsAcceptable *isAcceptable, void *context, |
993 | | UErrorCode *subErrorCode, |
994 | | UErrorCode *pErrorCode) |
995 | 0 | { |
996 | 0 | const char *pathBuffer; |
997 | 0 | UDataMemory dataMemory; |
998 | 0 | UDataMemory *pEntryData; |
999 | | |
1000 | | /* look in ind. files: package\nam.typ ========================= */ |
1001 | | /* init path iterator for individual files */ |
1002 | 0 | UDataPathIterator iter(dataPath, pkgName, path, tocEntryPathSuffix, FALSE, pErrorCode); |
1003 | |
|
1004 | 0 | while ((pathBuffer = iter.next(pErrorCode)) != NULL) |
1005 | 0 | { |
1006 | | #ifdef UDATA_DEBUG |
1007 | | fprintf(stderr, "UDATA: trying individual file %s\n", pathBuffer); |
1008 | | #endif |
1009 | 0 | if (uprv_mapFile(&dataMemory, pathBuffer, pErrorCode)) |
1010 | 0 | { |
1011 | 0 | pEntryData = checkDataItem(dataMemory.pHeader, isAcceptable, context, type, name, subErrorCode, pErrorCode); |
1012 | 0 | if (pEntryData != NULL) { |
1013 | | /* Data is good. |
1014 | | * Hand off ownership of the backing memory to the user's UDataMemory. |
1015 | | * and return it. */ |
1016 | 0 | pEntryData->mapAddr = dataMemory.mapAddr; |
1017 | 0 | pEntryData->map = dataMemory.map; |
1018 | |
|
1019 | | #ifdef UDATA_DEBUG |
1020 | | fprintf(stderr, "** Mapped file: %s\n", pathBuffer); |
1021 | | #endif |
1022 | 0 | return pEntryData; |
1023 | 0 | } |
1024 | | |
1025 | | /* the data is not acceptable, or some error occurred. Either way, unmap the memory */ |
1026 | 0 | udata_close(&dataMemory); |
1027 | | |
1028 | | /* If we had a nasty error, bail out completely. */ |
1029 | 0 | if (U_FAILURE(*pErrorCode)) { |
1030 | 0 | return NULL; |
1031 | 0 | } |
1032 | | |
1033 | | /* Otherwise remember that we found data but didn't like it for some reason */ |
1034 | 0 | *subErrorCode=U_INVALID_FORMAT_ERROR; |
1035 | 0 | } |
1036 | | #ifdef UDATA_DEBUG |
1037 | | fprintf(stderr, "%s\n", UDataMemory_isLoaded(&dataMemory)?"LOADED":"not loaded"); |
1038 | | #endif |
1039 | 0 | } |
1040 | 0 | return NULL; |
1041 | 0 | } |
1042 | | |
1043 | | /** |
1044 | | * @return 0 if not loaded, 1 if loaded or err |
1045 | | */ |
1046 | | static UDataMemory *doLoadFromCommonData(UBool isICUData, const char * /*pkgName*/, |
1047 | | const char * /*dataPath*/, const char * /*tocEntryPathSuffix*/, const char *tocEntryName, |
1048 | | /* following arguments are the same as doOpenChoice itself */ |
1049 | | const char *path, const char *type, const char *name, |
1050 | | UDataMemoryIsAcceptable *isAcceptable, void *context, |
1051 | | UErrorCode *subErrorCode, |
1052 | | UErrorCode *pErrorCode) |
1053 | 39.6k | { |
1054 | 39.6k | UDataMemory *pEntryData; |
1055 | 39.6k | const DataHeader *pHeader; |
1056 | 39.6k | UDataMemory *pCommonData; |
1057 | 39.6k | int32_t commonDataIndex; |
1058 | 39.6k | UBool checkedExtendedICUData = FALSE; |
1059 | | /* try to get common data. The loop is for platforms such as the 390 that do |
1060 | | * not initially load the full set of ICU data. If the lookup of an ICU data item |
1061 | | * fails, the full (but slower to load) set is loaded, the and the loop repeats, |
1062 | | * trying the lookup again. Once the full set of ICU data is loaded, the loop wont |
1063 | | * repeat because the full set will be checked the first time through. |
1064 | | * |
1065 | | * The loop also handles the fallback to a .dat file if the application linked |
1066 | | * to the stub data library rather than a real library. |
1067 | | */ |
1068 | 39.6k | for (commonDataIndex = isICUData ? 0 : -1;;) { |
1069 | 39.6k | pCommonData=openCommonData(path, commonDataIndex, subErrorCode); /** search for pkg **/ |
1070 | | |
1071 | 39.6k | if(U_SUCCESS(*subErrorCode) && pCommonData!=NULL) { |
1072 | 39.6k | int32_t length; |
1073 | | |
1074 | | /* look up the data piece in the common data */ |
1075 | 39.6k | pHeader=pCommonData->vFuncs->Lookup(pCommonData, tocEntryName, &length, subErrorCode); |
1076 | | #ifdef UDATA_DEBUG |
1077 | | fprintf(stderr, "%s: pHeader=%p - %s\n", tocEntryName, (void*) pHeader, u_errorName(*subErrorCode)); |
1078 | | #endif |
1079 | | |
1080 | 39.6k | if(pHeader!=NULL) { |
1081 | 39.6k | pEntryData = checkDataItem(pHeader, isAcceptable, context, type, name, subErrorCode, pErrorCode); |
1082 | | #ifdef UDATA_DEBUG |
1083 | | fprintf(stderr, "pEntryData=%p\n", (void*) pEntryData); |
1084 | | #endif |
1085 | 39.6k | if (U_FAILURE(*pErrorCode)) { |
1086 | 0 | return NULL; |
1087 | 0 | } |
1088 | 39.6k | if (pEntryData != NULL) { |
1089 | 39.6k | pEntryData->length = length; |
1090 | 39.6k | return pEntryData; |
1091 | 39.6k | } |
1092 | 4 | } |
1093 | 39.6k | } |
1094 | | // If we failed due to being out-of-memory, then stop early and report the error. |
1095 | 4 | if (*subErrorCode == U_MEMORY_ALLOCATION_ERROR) { |
1096 | 0 | *pErrorCode = *subErrorCode; |
1097 | 0 | return NULL; |
1098 | 0 | } |
1099 | | /* Data wasn't found. If we were looking for an ICUData item and there is |
1100 | | * more data available, load it and try again, |
1101 | | * otherwise break out of this loop. */ |
1102 | 4 | if (!isICUData) { |
1103 | 0 | return NULL; |
1104 | 4 | } else if (pCommonData != NULL) { |
1105 | 2 | ++commonDataIndex; /* try the next data package */ |
1106 | 2 | } else if ((!checkedExtendedICUData) && extendICUData(subErrorCode)) { |
1107 | 0 | checkedExtendedICUData = TRUE; |
1108 | | /* try this data package slot again: it changed from NULL to non-NULL */ |
1109 | 2 | } else { |
1110 | 2 | return NULL; |
1111 | 2 | } |
1112 | 4 | } |
1113 | 39.6k | } |
1114 | | |
1115 | | /* |
1116 | | * Identify the Time Zone resources that are subject to special override data loading. |
1117 | | */ |
1118 | 39.6k | static UBool isTimeZoneFile(const char *name, const char *type) { |
1119 | 39.6k | return ((uprv_strcmp(type, "res") == 0) && |
1120 | 6 | (uprv_strcmp(name, "zoneinfo64") == 0 || |
1121 | 6 | uprv_strcmp(name, "timezoneTypes") == 0 || |
1122 | 6 | uprv_strcmp(name, "windowsZones") == 0 || |
1123 | 6 | uprv_strcmp(name, "metaZones") == 0)); |
1124 | 39.6k | } |
1125 | | |
1126 | | /* |
1127 | | * A note on the ownership of Mapped Memory |
1128 | | * |
1129 | | * For common format files, ownership resides with the UDataMemory object |
1130 | | * that lives in the cache of opened common data. These UDataMemorys are private |
1131 | | * to the udata implementation, and are never seen directly by users. |
1132 | | * |
1133 | | * The UDataMemory objects returned to users will have the address of some desired |
1134 | | * data within the mapped region, but they wont have the mapping info itself, and thus |
1135 | | * won't cause anything to be removed from memory when they are closed. |
1136 | | * |
1137 | | * For individual data files, the UDataMemory returned to the user holds the |
1138 | | * information necessary to unmap the data on close. If the user independently |
1139 | | * opens the same data file twice, two completely independent mappings will be made. |
1140 | | * (There is no cache of opened data items from individual files, only a cache of |
1141 | | * opened Common Data files, that is, files containing a collection of data items.) |
1142 | | * |
1143 | | * For common data passed in from the user via udata_setAppData() or |
1144 | | * udata_setCommonData(), ownership remains with the user. |
1145 | | * |
1146 | | * UDataMemory objects themselves, as opposed to the memory they describe, |
1147 | | * can be anywhere - heap, stack/local or global. |
1148 | | * They have a flag to indicate when they're heap allocated and thus |
1149 | | * must be deleted when closed. |
1150 | | */ |
1151 | | |
1152 | | |
1153 | | /*----------------------------------------------------------------------------* |
1154 | | * * |
1155 | | * main data loading functions * |
1156 | | * * |
1157 | | *----------------------------------------------------------------------------*/ |
1158 | | static UDataMemory * |
1159 | | doOpenChoice(const char *path, const char *type, const char *name, |
1160 | | UDataMemoryIsAcceptable *isAcceptable, void *context, |
1161 | | UErrorCode *pErrorCode) |
1162 | 39.6k | { |
1163 | 39.6k | UDataMemory *retVal = NULL; |
1164 | | |
1165 | 39.6k | const char *dataPath; |
1166 | | |
1167 | 39.6k | int32_t tocEntrySuffixIndex; |
1168 | 39.6k | const char *tocEntryPathSuffix; |
1169 | 39.6k | UErrorCode subErrorCode=U_ZERO_ERROR; |
1170 | 39.6k | const char *treeChar; |
1171 | | |
1172 | 39.6k | UBool isICUData = FALSE; |
1173 | | |
1174 | | |
1175 | 39.6k | FileTracer::traceOpen(path, type, name); |
1176 | | |
1177 | | |
1178 | | /* Is this path ICU data? */ |
1179 | 39.6k | if(path == NULL || |
1180 | 39.6k | !strcmp(path, U_ICUDATA_ALIAS) || /* "ICUDATA" */ |
1181 | 39.6k | !uprv_strncmp(path, U_ICUDATA_NAME U_TREE_SEPARATOR_STRING, /* "icudt26e-" */ |
1182 | 39.6k | uprv_strlen(U_ICUDATA_NAME U_TREE_SEPARATOR_STRING)) || |
1183 | 0 | !uprv_strncmp(path, U_ICUDATA_ALIAS U_TREE_SEPARATOR_STRING, /* "ICUDATA-" */ |
1184 | 39.6k | uprv_strlen(U_ICUDATA_ALIAS U_TREE_SEPARATOR_STRING))) { |
1185 | 39.6k | isICUData = TRUE; |
1186 | 39.6k | } |
1187 | | |
1188 | | #if (U_FILE_SEP_CHAR != U_FILE_ALT_SEP_CHAR) /* Windows: try "foo\bar" and "foo/bar" */ |
1189 | | /* remap from alternate path char to the main one */ |
1190 | | CharString altSepPath; |
1191 | | if(path) { |
1192 | | if(uprv_strchr(path,U_FILE_ALT_SEP_CHAR) != NULL) { |
1193 | | altSepPath.append(path, *pErrorCode); |
1194 | | char *p; |
1195 | | while ((p = uprv_strchr(altSepPath.data(), U_FILE_ALT_SEP_CHAR)) != NULL) { |
1196 | | *p = U_FILE_SEP_CHAR; |
1197 | | } |
1198 | | #if defined (UDATA_DEBUG) |
1199 | | fprintf(stderr, "Changed path from [%s] to [%s]\n", path, altSepPath.s); |
1200 | | #endif |
1201 | | path = altSepPath.data(); |
1202 | | } |
1203 | | } |
1204 | | #endif |
1205 | | |
1206 | 39.6k | CharString tocEntryName; /* entry name in tree format. ex: 'icudt28b/coll/ar.res' */ |
1207 | 39.6k | CharString tocEntryPath; /* entry name in path format. ex: 'icudt28b\\coll\\ar.res' */ |
1208 | | |
1209 | 39.6k | CharString pkgName; |
1210 | 39.6k | CharString treeName; |
1211 | | |
1212 | | /* ======= Set up strings */ |
1213 | 39.6k | if(path==NULL) { |
1214 | 0 | pkgName.append(U_ICUDATA_NAME, *pErrorCode); |
1215 | 39.6k | } else { |
1216 | 39.6k | const char *pkg; |
1217 | 39.6k | const char *first; |
1218 | 39.6k | pkg = uprv_strrchr(path, U_FILE_SEP_CHAR); |
1219 | 39.6k | first = uprv_strchr(path, U_FILE_SEP_CHAR); |
1220 | 39.6k | if(uprv_pathIsAbsolute(path) || (pkg != first)) { /* more than one slash in the path- not a tree name */ |
1221 | | /* see if this is an /absolute/path/to/package path */ |
1222 | 0 | if(pkg) { |
1223 | 0 | pkgName.append(pkg+1, *pErrorCode); |
1224 | 0 | } else { |
1225 | 0 | pkgName.append(path, *pErrorCode); |
1226 | 0 | } |
1227 | 39.6k | } else { |
1228 | 39.6k | treeChar = uprv_strchr(path, U_TREE_SEPARATOR); |
1229 | 39.6k | if(treeChar) { |
1230 | 39.6k | treeName.append(treeChar+1, *pErrorCode); /* following '-' */ |
1231 | 39.6k | if(isICUData) { |
1232 | 39.6k | pkgName.append(U_ICUDATA_NAME, *pErrorCode); |
1233 | 0 | } else { |
1234 | 0 | pkgName.append(path, (int32_t)(treeChar-path), *pErrorCode); |
1235 | 0 | if (first == NULL) { |
1236 | | /* |
1237 | | This user data has no path, but there is a tree name. |
1238 | | Look up the correct path from the data cache later. |
1239 | | */ |
1240 | 0 | path = pkgName.data(); |
1241 | 0 | } |
1242 | 0 | } |
1243 | 0 | } else { |
1244 | 0 | if(isICUData) { |
1245 | 0 | pkgName.append(U_ICUDATA_NAME, *pErrorCode); |
1246 | 0 | } else { |
1247 | 0 | pkgName.append(path, *pErrorCode); |
1248 | 0 | } |
1249 | 0 | } |
1250 | 39.6k | } |
1251 | 39.6k | } |
1252 | | |
1253 | | #ifdef UDATA_DEBUG |
1254 | | fprintf(stderr, " P=%s T=%s\n", pkgName.data(), treeName.data()); |
1255 | | #endif |
1256 | | |
1257 | | /* setting up the entry name and file name |
1258 | | * Make up a full name by appending the type to the supplied |
1259 | | * name, assuming that a type was supplied. |
1260 | | */ |
1261 | | |
1262 | | /* prepend the package */ |
1263 | 39.6k | tocEntryName.append(pkgName, *pErrorCode); |
1264 | 39.6k | tocEntryPath.append(pkgName, *pErrorCode); |
1265 | 39.6k | tocEntrySuffixIndex = tocEntryName.length(); |
1266 | | |
1267 | 39.6k | if(!treeName.isEmpty()) { |
1268 | 39.6k | tocEntryName.append(U_TREE_ENTRY_SEP_CHAR, *pErrorCode).append(treeName, *pErrorCode); |
1269 | 39.6k | tocEntryPath.append(U_FILE_SEP_CHAR, *pErrorCode).append(treeName, *pErrorCode); |
1270 | 39.6k | } |
1271 | | |
1272 | 39.6k | tocEntryName.append(U_TREE_ENTRY_SEP_CHAR, *pErrorCode).append(name, *pErrorCode); |
1273 | 39.6k | tocEntryPath.append(U_FILE_SEP_CHAR, *pErrorCode).append(name, *pErrorCode); |
1274 | 39.6k | if(type!=NULL && *type!=0) { |
1275 | 39.6k | tocEntryName.append(".", *pErrorCode).append(type, *pErrorCode); |
1276 | 39.6k | tocEntryPath.append(".", *pErrorCode).append(type, *pErrorCode); |
1277 | 39.6k | } |
1278 | | // The +1 is for the U_FILE_SEP_CHAR that is always appended above. |
1279 | 39.6k | tocEntryPathSuffix = tocEntryPath.data() + tocEntrySuffixIndex + 1; /* suffix starts here */ |
1280 | | |
1281 | | #ifdef UDATA_DEBUG |
1282 | | fprintf(stderr, " tocEntryName = %s\n", tocEntryName.data()); |
1283 | | fprintf(stderr, " tocEntryPath = %s\n", tocEntryName.data()); |
1284 | | #endif |
1285 | | |
1286 | 39.6k | #if !defined(ICU_DATA_DIR_WINDOWS) |
1287 | 39.6k | if(path == NULL) { |
1288 | 0 | path = COMMON_DATA_NAME; /* "icudt26e" */ |
1289 | 0 | } |
1290 | | #else |
1291 | | // When using the Windows system data, we expects only a single data file. |
1292 | | path = COMMON_DATA_NAME; /* "icudt26e" */ |
1293 | | #endif |
1294 | | |
1295 | | /************************ Begin loop looking for ind. files ***************/ |
1296 | | #ifdef UDATA_DEBUG |
1297 | | fprintf(stderr, "IND: inBasename = %s, pkg=%s\n", "(n/a)", packageNameFromPath(path)); |
1298 | | #endif |
1299 | | |
1300 | | /* End of dealing with a null basename */ |
1301 | 39.6k | dataPath = u_getDataDirectory(); |
1302 | | |
1303 | | /**** Time zone individual files override */ |
1304 | 39.6k | if (isICUData && isTimeZoneFile(name, type)) { |
1305 | 0 | const char *tzFilesDir = u_getTimeZoneFilesDirectory(pErrorCode); |
1306 | 0 | if (tzFilesDir[0] != 0) { |
1307 | | #ifdef UDATA_DEBUG |
1308 | | fprintf(stderr, "Trying Time Zone Files directory = %s\n", tzFilesDir); |
1309 | | #endif |
1310 | 0 | retVal = doLoadFromIndividualFiles(/* pkgName.data() */ "", tzFilesDir, tocEntryPathSuffix, |
1311 | 0 | /* path */ "", type, name, isAcceptable, context, &subErrorCode, pErrorCode); |
1312 | 0 | if((retVal != NULL) || U_FAILURE(*pErrorCode)) { |
1313 | 0 | return retVal; |
1314 | 0 | } |
1315 | 39.6k | } |
1316 | 0 | } |
1317 | | |
1318 | | /**** COMMON PACKAGE - only if packages are first. */ |
1319 | 39.6k | if(gDataFileAccess == UDATA_PACKAGES_FIRST) { |
1320 | | #ifdef UDATA_DEBUG |
1321 | | fprintf(stderr, "Trying packages (UDATA_PACKAGES_FIRST)\n"); |
1322 | | #endif |
1323 | | /* #2 */ |
1324 | 0 | retVal = doLoadFromCommonData(isICUData, |
1325 | 0 | pkgName.data(), dataPath, tocEntryPathSuffix, tocEntryName.data(), |
1326 | 0 | path, type, name, isAcceptable, context, &subErrorCode, pErrorCode); |
1327 | 0 | if((retVal != NULL) || U_FAILURE(*pErrorCode)) { |
1328 | 0 | return retVal; |
1329 | 0 | } |
1330 | 39.6k | } |
1331 | | |
1332 | | /**** INDIVIDUAL FILES */ |
1333 | 39.6k | if((gDataFileAccess==UDATA_PACKAGES_FIRST) || |
1334 | 39.6k | (gDataFileAccess==UDATA_FILES_FIRST)) { |
1335 | | #ifdef UDATA_DEBUG |
1336 | | fprintf(stderr, "Trying individual files\n"); |
1337 | | #endif |
1338 | | /* Check to make sure that there is a dataPath to iterate over */ |
1339 | 39.6k | if ((dataPath && *dataPath) || !isICUData) { |
1340 | 0 | retVal = doLoadFromIndividualFiles(pkgName.data(), dataPath, tocEntryPathSuffix, |
1341 | 0 | path, type, name, isAcceptable, context, &subErrorCode, pErrorCode); |
1342 | 0 | if((retVal != NULL) || U_FAILURE(*pErrorCode)) { |
1343 | 0 | return retVal; |
1344 | 0 | } |
1345 | 39.6k | } |
1346 | 39.6k | } |
1347 | | |
1348 | | /**** COMMON PACKAGE */ |
1349 | 39.6k | if((gDataFileAccess==UDATA_ONLY_PACKAGES) || |
1350 | 39.6k | (gDataFileAccess==UDATA_FILES_FIRST)) { |
1351 | | #ifdef UDATA_DEBUG |
1352 | | fprintf(stderr, "Trying packages (UDATA_ONLY_PACKAGES || UDATA_FILES_FIRST)\n"); |
1353 | | #endif |
1354 | 39.6k | retVal = doLoadFromCommonData(isICUData, |
1355 | 39.6k | pkgName.data(), dataPath, tocEntryPathSuffix, tocEntryName.data(), |
1356 | 39.6k | path, type, name, isAcceptable, context, &subErrorCode, pErrorCode); |
1357 | 39.6k | if((retVal != NULL) || U_FAILURE(*pErrorCode)) { |
1358 | 39.6k | return retVal; |
1359 | 39.6k | } |
1360 | 2 | } |
1361 | | |
1362 | | /* Load from DLL. If we haven't attempted package load, we also haven't had any chance to |
1363 | | try a DLL (static or setCommonData/etc) load. |
1364 | | If we ever have a "UDATA_ONLY_FILES", add it to the or list here. */ |
1365 | 2 | if(gDataFileAccess==UDATA_NO_FILES) { |
1366 | | #ifdef UDATA_DEBUG |
1367 | | fprintf(stderr, "Trying common data (UDATA_NO_FILES)\n"); |
1368 | | #endif |
1369 | 0 | retVal = doLoadFromCommonData(isICUData, |
1370 | 0 | pkgName.data(), "", tocEntryPathSuffix, tocEntryName.data(), |
1371 | 0 | path, type, name, isAcceptable, context, &subErrorCode, pErrorCode); |
1372 | 0 | if((retVal != NULL) || U_FAILURE(*pErrorCode)) { |
1373 | 0 | return retVal; |
1374 | 0 | } |
1375 | 2 | } |
1376 | | |
1377 | | /* data not found */ |
1378 | 2 | if(U_SUCCESS(*pErrorCode)) { |
1379 | 2 | if(U_SUCCESS(subErrorCode)) { |
1380 | | /* file not found */ |
1381 | 0 | *pErrorCode=U_FILE_ACCESS_ERROR; |
1382 | 2 | } else { |
1383 | | /* entry point not found or rejected */ |
1384 | 2 | *pErrorCode=subErrorCode; |
1385 | 2 | } |
1386 | 2 | } |
1387 | 2 | return retVal; |
1388 | 2 | } |
1389 | | |
1390 | | |
1391 | | |
1392 | | /* API ---------------------------------------------------------------------- */ |
1393 | | |
1394 | | U_CAPI UDataMemory * U_EXPORT2 |
1395 | | udata_open(const char *path, const char *type, const char *name, |
1396 | 39.6k | UErrorCode *pErrorCode) { |
1397 | | #ifdef UDATA_DEBUG |
1398 | | fprintf(stderr, "udata_open(): Opening: %s : %s . %s\n", (path?path:"NULL"), name, type); |
1399 | | fflush(stderr); |
1400 | | #endif |
1401 | | |
1402 | 39.6k | if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) { |
1403 | 0 | return NULL; |
1404 | 39.6k | } else if(name==NULL || *name==0) { |
1405 | 0 | *pErrorCode=U_ILLEGAL_ARGUMENT_ERROR; |
1406 | 0 | return NULL; |
1407 | 39.6k | } else { |
1408 | 39.6k | return doOpenChoice(path, type, name, NULL, NULL, pErrorCode); |
1409 | 39.6k | } |
1410 | 39.6k | } |
1411 | | |
1412 | | |
1413 | | |
1414 | | U_CAPI UDataMemory * U_EXPORT2 |
1415 | | udata_openChoice(const char *path, const char *type, const char *name, |
1416 | | UDataMemoryIsAcceptable *isAcceptable, void *context, |
1417 | 6 | UErrorCode *pErrorCode) { |
1418 | | #ifdef UDATA_DEBUG |
1419 | | fprintf(stderr, "udata_openChoice(): Opening: %s : %s . %s\n", (path?path:"NULL"), name, type); |
1420 | | #endif |
1421 | | |
1422 | 6 | if(pErrorCode==NULL || U_FAILURE(*pErrorCode)) { |
1423 | 0 | return NULL; |
1424 | 6 | } else if(name==NULL || *name==0 || isAcceptable==NULL) { |
1425 | 0 | *pErrorCode=U_ILLEGAL_ARGUMENT_ERROR; |
1426 | 0 | return NULL; |
1427 | 6 | } else { |
1428 | 6 | return doOpenChoice(path, type, name, isAcceptable, context, pErrorCode); |
1429 | 6 | } |
1430 | 6 | } |
1431 | | |
1432 | | |
1433 | | |
1434 | | U_CAPI void U_EXPORT2 |
1435 | 0 | udata_getInfo(UDataMemory *pData, UDataInfo *pInfo) { |
1436 | 0 | if(pInfo!=NULL) { |
1437 | 0 | if(pData!=NULL && pData->pHeader!=NULL) { |
1438 | 0 | const UDataInfo *info=&pData->pHeader->info; |
1439 | 0 | uint16_t dataInfoSize=udata_getInfoSize(info); |
1440 | 0 | if(pInfo->size>dataInfoSize) { |
1441 | 0 | pInfo->size=dataInfoSize; |
1442 | 0 | } |
1443 | 0 | uprv_memcpy((uint16_t *)pInfo+1, (const uint16_t *)info+1, pInfo->size-2); |
1444 | 0 | if(info->isBigEndian!=U_IS_BIG_ENDIAN) { |
1445 | | /* opposite endianness */ |
1446 | 0 | uint16_t x=info->reservedWord; |
1447 | 0 | pInfo->reservedWord=(uint16_t)((x<<8)|(x>>8)); |
1448 | 0 | } |
1449 | 0 | } else { |
1450 | 0 | pInfo->size=0; |
1451 | 0 | } |
1452 | 0 | } |
1453 | 0 | } |
1454 | | |
1455 | | |
1456 | | U_CAPI void U_EXPORT2 udata_setFileAccess(UDataFileAccess access, UErrorCode * /*status*/) |
1457 | 0 | { |
1458 | | // Note: this function is documented as not thread safe. |
1459 | 0 | gDataFileAccess = access; |
1460 | 0 | } |