]>
Commit | Line | Data |
---|---|---|
b75a7d8f A |
1 | /******************************************************************** |
2 | * COPYRIGHT: | |
374ca955 | 3 | * Copyright (c) 1997-2004, International Business Machines Corporation and |
b75a7d8f A |
4 | * others. All Rights Reserved. |
5 | ********************************************************************/ | |
6 | /******************************************************************************** | |
7 | * | |
8 | * File CCONVTST.C | |
9 | * | |
10 | * Modification History: | |
11 | * Name Description | |
12 | * Madhu Katragadda 7/7/2000 Converter Tests for extended code coverage | |
13 | ********************************************************************************* | |
14 | */ | |
15 | #include <stdio.h> | |
374ca955 A |
16 | #include <stdlib.h> |
17 | #include <string.h> | |
b75a7d8f A |
18 | #include "unicode/uloc.h" |
19 | #include "unicode/ucnv.h" | |
20 | #include "unicode/utypes.h" | |
21 | #include "unicode/ustring.h" | |
22 | #include "unicode/uset.h" | |
23 | #include "cintltst.h" | |
24 | ||
25 | #define MAX_LENGTH 999 | |
26 | ||
27 | #define UNICODE_LIMIT 0x10FFFF | |
28 | #define SURROGATE_HIGH_START 0xD800 | |
29 | #define SURROGATE_LOW_END 0xDFFF | |
30 | ||
31 | static int32_t gInBufferSize = 0; | |
32 | static int32_t gOutBufferSize = 0; | |
33 | static char gNuConvTestName[1024]; | |
34 | ||
35 | #define nct_min(x,y) ((x<y) ? x : y) | |
36 | #define LENGTHOF(array) (int32_t)(sizeof(array)/sizeof((array)[0])) | |
37 | ||
38 | static void printSeq(const unsigned char* a, int len); | |
39 | static void printSeqErr(const unsigned char* a, int len); | |
40 | static void printUSeq(const UChar* a, int len); | |
41 | static void printUSeqErr(const UChar* a, int len); | |
42 | static UBool convertFromU( const UChar *source, int sourceLen, const uint8_t *expect, int expectLen, | |
43 | const char *codepage, const int32_t *expectOffsets, UBool doFlush, UErrorCode expectedStatus); | |
44 | static UBool convertToU( const uint8_t *source, int sourceLen, const UChar *expect, int expectLen, | |
45 | const char *codepage, const int32_t *expectOffsets, UBool doFlush, UErrorCode expectedStatus); | |
46 | ||
47 | static UBool testConvertFromU( const UChar *source, int sourceLen, const uint8_t *expect, int expectLen, | |
48 | const char *codepage, UConverterFromUCallback callback, const int32_t *expectOffsets, UBool testReset); | |
49 | static UBool testConvertToU( const uint8_t *source, int sourcelen, const UChar *expect, int expectlen, | |
50 | const char *codepage, UConverterToUCallback callback, const int32_t *expectOffsets, UBool testReset); | |
51 | ||
52 | static void setNuConvTestName(const char *codepage, const char *direction) | |
53 | { | |
374ca955 A |
54 | sprintf(gNuConvTestName, "[Testing %s %s Unicode, InputBufSiz=%d, OutputBufSiz=%d]", |
55 | codepage, | |
56 | direction, | |
57 | (int)gInBufferSize, | |
58 | (int)gOutBufferSize); | |
b75a7d8f A |
59 | } |
60 | ||
61 | ||
62 | static void TestSurrogateBehaviour(void); | |
63 | static void TestErrorBehaviour(void); | |
64 | static void TestToUnicodeErrorBehaviour(void); | |
65 | static void TestGetNextErrorBehaviour(void); | |
66 | static void TestRegressionUTF8(void); | |
67 | static void TestRegressionUTF32(void); | |
68 | static void TestAvailableConverters(void); | |
69 | static void TestFlushInternalBuffer(void); /*for improved code coverage in ucnv_cnv.c*/ | |
70 | static void TestResetBehaviour(void); | |
71 | static void TestTruncated(void); | |
72 | static void TestUnicodeSet(void); | |
73 | ||
74 | static void TestWithBufferSize(int32_t osize, int32_t isize); | |
75 | ||
76 | ||
77 | static void printSeq(const unsigned char* a, int len) | |
78 | { | |
79 | int i=0; | |
80 | log_verbose("\n{"); | |
81 | while (i<len) | |
82 | log_verbose("0x%02X ", a[i++]); | |
83 | log_verbose("}\n"); | |
84 | } | |
85 | ||
86 | static void printUSeq(const UChar* a, int len) | |
87 | { | |
88 | int i=0; | |
89 | log_verbose("\n{"); | |
90 | while (i<len) | |
91 | log_verbose("%0x04X ", a[i++]); | |
92 | log_verbose("}\n"); | |
93 | } | |
94 | ||
95 | static void printSeqErr(const unsigned char* a, int len) | |
96 | { | |
97 | int i=0; | |
98 | fprintf(stderr, "\n{"); | |
99 | while (i<len) fprintf(stderr, "0x%02X ", a[i++]); | |
100 | fprintf(stderr, "}\n"); | |
101 | } | |
102 | ||
103 | static void printUSeqErr(const UChar* a, int len) | |
104 | { | |
105 | int i=0; | |
106 | fprintf(stderr, "\n{"); | |
107 | while (i<len) | |
108 | fprintf(stderr, "0x%04X ", a[i++]); | |
109 | fprintf(stderr,"}\n"); | |
110 | } | |
111 | ||
112 | void addExtraTests(TestNode** root); | |
113 | ||
114 | void addExtraTests(TestNode** root) | |
115 | { | |
116 | addTest(root, &TestSurrogateBehaviour, "tsconv/ncnvtst/TestSurrogateBehaviour"); | |
117 | addTest(root, &TestErrorBehaviour, "tsconv/ncnvtst/TestErrorBehaviour"); | |
118 | addTest(root, &TestToUnicodeErrorBehaviour, "tsconv/ncnvtst/ToUnicodeErrorBehaviour"); | |
119 | addTest(root, &TestGetNextErrorBehaviour, "tsconv/ncnvtst/TestGetNextErrorBehaviour"); | |
120 | addTest(root, &TestAvailableConverters, "tsconv/ncnvtst/TestAvailableConverters"); | |
121 | addTest(root, &TestFlushInternalBuffer, "tsconv/ncnvtst/TestFlushInternalBuffer"); | |
122 | addTest(root, &TestResetBehaviour, "tsconv/ncnvtst/TestResetBehaviour"); | |
123 | addTest(root, &TestRegressionUTF8, "tsconv/ncnvtst/TestRegressionUTF8"); | |
124 | addTest(root, &TestRegressionUTF32, "tsconv/ncnvtst/TestRegressionUTF32"); | |
125 | addTest(root, &TestTruncated, "tsconv/ncnvtst/TestTruncated"); | |
126 | addTest(root, &TestUnicodeSet, "tsconv/ncnvtst/TestUnicodeSet"); | |
127 | } | |
128 | ||
129 | /*test surrogate behaviour*/ | |
130 | static void TestSurrogateBehaviour(){ | |
131 | log_verbose("Testing for SBCS and LATIN_1\n"); | |
132 | { | |
133 | UChar sampleText[] = {0x0031, 0xd801, 0xdc01, 0x0032}; | |
134 | const uint8_t expected[] = {0x31, 0x1a, 0x32}; | |
135 | /*SBCS*/ | |
136 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
137 | expected, sizeof(expected), "ibm-920", 0 , TRUE, U_ZERO_ERROR)) | |
138 | log_err("u-> ibm-920 [UCNV_SBCS] not match.\n"); | |
139 | ||
140 | /*LATIN_1*/ | |
141 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
142 | expected, sizeof(expected), "LATIN_1", 0, TRUE, U_ZERO_ERROR )) | |
143 | log_err("u-> LATIN_1 not match.\n"); | |
144 | ||
145 | } | |
146 | log_verbose("Testing for DBCS and MBCS\n"); | |
147 | { | |
148 | UChar sampleText[] = {0x00a1, 0xd801, 0xdc01, 0x00a4}; | |
149 | const uint8_t expected[] = {0xa2, 0xae, 0xa1, 0xe0, 0xa2, 0xb4}; | |
150 | int32_t offsets[] = {0x00, 0x00, 0x01, 0x01, 0x03, 0x03 }; | |
151 | ||
152 | /*DBCS*/ | |
153 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
154 | expected, sizeof(expected), "ibm-1363", 0 , TRUE, U_ZERO_ERROR)) | |
155 | log_err("u-> ibm-1363 [UCNV_DBCS portion] not match.\n"); | |
156 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
157 | expected, sizeof(expected), "ibm-1363", offsets , TRUE, U_ZERO_ERROR)) | |
158 | log_err("u-> ibm-1363 [UCNV_DBCS portion] not match.\n"); | |
159 | /*MBCS*/ | |
160 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
161 | expected, sizeof(expected), "ibm-1363", 0 , TRUE, U_ZERO_ERROR)) | |
162 | log_err("u-> ibm-1363 [UCNV_MBCS] not match.\n"); | |
163 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
164 | expected, sizeof(expected), "ibm-1363", offsets, TRUE, U_ZERO_ERROR)) | |
165 | log_err("u-> ibm-1363 [UCNV_MBCS] not match.\n"); | |
166 | } | |
167 | log_verbose("Testing for ISO-2022-jp\n"); | |
168 | { | |
169 | UChar sampleText[] = { 0x4e00, 0x04e01, 0x0031, 0xd801, 0xdc01, 0x0032}; | |
170 | ||
171 | const uint8_t expected[] = {0x1b, 0x24, 0x42,0x30,0x6c,0x43,0x7a,0x1b,0x28,0x42, | |
172 | 0x31,0x1A, 0x32}; | |
173 | ||
174 | ||
175 | int32_t offsets[] = {0,0,0,0,0,1,1,2,2,2,2,3,5 }; | |
176 | ||
177 | /*iso-2022-jp*/ | |
178 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
179 | expected, sizeof(expected), "iso-2022-jp", 0 , TRUE, U_ZERO_ERROR)) | |
180 | log_err("u-> not match.\n"); | |
181 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
182 | expected, sizeof(expected), "iso-2022-jp", offsets , TRUE, U_ZERO_ERROR)) | |
183 | log_err("u-> not match.\n"); | |
184 | } | |
185 | log_verbose("Testing for ISO-2022-cn\n"); | |
186 | { | |
187 | static const UChar sampleText[] = { 0x4e00, 0x04e01, 0x0031, 0xd801, 0xdc01, 0x0032}; | |
188 | ||
189 | static const uint8_t expected[] = { | |
190 | 0x1B, 0x24, 0x29, 0x41, 0x0E, 0x52, 0x3B, | |
191 | 0x36, 0x21, | |
192 | 0x0F, 0x31, | |
193 | 0x1A, | |
374ca955 | 194 | 0x32 |
b75a7d8f A |
195 | }; |
196 | ||
197 | ||
198 | ||
199 | static const int32_t offsets[] = { | |
200 | 0, 0, 0, 0, 0, 0, 0, | |
201 | 1, 1, | |
202 | 2, 2, | |
203 | 3, | |
374ca955 | 204 | 5, }; |
b75a7d8f A |
205 | |
206 | /*iso-2022-CN*/ | |
207 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
208 | expected, sizeof(expected), "iso-2022-cn", 0 , TRUE, U_ZERO_ERROR)) | |
209 | log_err("u-> not match.\n"); | |
210 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
211 | expected, sizeof(expected), "iso-2022-cn", offsets , TRUE, U_ZERO_ERROR)) | |
212 | log_err("u-> not match.\n"); | |
213 | } | |
214 | log_verbose("Testing for ISO-2022-kr\n"); | |
215 | { | |
216 | static const UChar sampleText[] = { 0x4e00,0xd801, 0xdc01, 0x04e01, 0x0031, 0xd801, 0xdc01, 0x0032}; | |
217 | ||
218 | static const uint8_t expected[] = {0x1B, 0x24, 0x29, 0x43, | |
219 | 0x0E, 0x6C, 0x69, | |
220 | 0x0f, 0x1A, | |
221 | 0x0e, 0x6F, 0x4B, | |
222 | 0x0F, 0x31, | |
223 | 0x1A, | |
224 | 0x32 }; | |
225 | ||
226 | static const int32_t offsets[] = {-1, -1, -1, -1, | |
227 | 0, 0, 0, | |
228 | 1, 1, | |
229 | 3, 3, 3, | |
230 | 4, 4, | |
231 | 5, | |
232 | 7, | |
233 | }; | |
234 | ||
235 | /*iso-2022-kr*/ | |
236 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
237 | expected, sizeof(expected), "iso-2022-kr", 0 , TRUE, U_ZERO_ERROR)) | |
238 | log_err("u-> iso-2022-kr [UCNV_DBCS] not match.\n"); | |
239 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
240 | expected, sizeof(expected), "iso-2022-kr", offsets , TRUE, U_ZERO_ERROR)) | |
241 | log_err("u-> iso-2022-kr [UCNV_DBCS] not match.\n"); | |
242 | } | |
243 | log_verbose("Testing for HZ\n"); | |
244 | { | |
245 | static const UChar sampleText[] = { 0x4e00, 0xd801, 0xdc01, 0x04e01, 0x0031, 0xd801, 0xdc01, 0x0032}; | |
246 | ||
247 | static const uint8_t expected[] = {0x7E, 0x7B, 0x52, 0x3B, | |
248 | 0x7E, 0x7D, 0x1A, | |
249 | 0x7E, 0x7B, 0x36, 0x21, | |
250 | 0x7E, 0x7D, 0x31, | |
251 | 0x1A, | |
252 | 0x32 }; | |
253 | ||
254 | ||
255 | static const int32_t offsets[] = {0,0,0,0, | |
256 | 1,1,1, | |
257 | 3,3,3,3, | |
258 | 4,4,4, | |
259 | 5, | |
260 | 7,}; | |
261 | ||
262 | /*hz*/ | |
263 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
264 | expected, sizeof(expected), "HZ", 0 , TRUE, U_ZERO_ERROR)) | |
265 | log_err("u-> not match.\n"); | |
266 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
267 | expected, sizeof(expected), "HZ", offsets , TRUE, U_ZERO_ERROR)) | |
268 | log_err("u-> not match.\n"); | |
269 | } | |
270 | /*UTF-8*/ | |
271 | log_verbose("Testing for UTF8\n"); | |
272 | { | |
273 | static const UChar sampleText[] = { 0x4e00, 0x0701, 0x0031, 0xbfc1, 0xd801, 0xdc01, 0x0032}; | |
274 | static const int32_t offsets[]={0x00, 0x00, 0x00, 0x01, 0x01, 0x02, | |
275 | 0x03, 0x03, 0x03, 0x04, 0x04, 0x04, | |
276 | 0x04, 0x06 }; | |
277 | static const uint8_t expected[] = {0xe4, 0xb8, 0x80, 0xdc, 0x81, 0x31, | |
278 | 0xeb, 0xbf, 0x81, 0xF0, 0x90, 0x90, 0x81, 0x32}; | |
279 | ||
280 | ||
281 | static const int32_t fromOffsets[] = { 0x0000, 0x0003, 0x0005, 0x0006, 0x0009, 0x0009, 0x000D }; | |
282 | /*UTF-8*/ | |
283 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
284 | expected, sizeof(expected), "UTF8", offsets, TRUE, U_ZERO_ERROR )) | |
285 | log_err("u-> UTF8 with offsets and flush true did not match.\n"); | |
286 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
287 | expected, sizeof(expected), "UTF8", 0, TRUE, U_ZERO_ERROR )) | |
288 | log_err("u-> UTF8 with offsets and flush true did not match.\n"); | |
289 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
290 | expected, sizeof(expected), "UTF8", offsets, FALSE, U_ZERO_ERROR )) | |
291 | log_err("u-> UTF8 with offsets and flush true did not match.\n"); | |
292 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
293 | expected, sizeof(expected), "UTF8", 0, FALSE, U_ZERO_ERROR )) | |
294 | log_err("u-> UTF8 with offsets and flush true did not match.\n"); | |
295 | ||
296 | if(!convertToU(expected, sizeof(expected), | |
297 | sampleText, sizeof(sampleText)/sizeof(sampleText[0]), "UTF8", 0, TRUE, U_ZERO_ERROR )) | |
298 | log_err("UTF8 -> did not match.\n"); | |
299 | if(!convertToU(expected, sizeof(expected), | |
300 | sampleText, sizeof(sampleText)/sizeof(sampleText[0]), "UTF8", 0, FALSE, U_ZERO_ERROR )) | |
301 | log_err("UTF8 -> did not match.\n"); | |
302 | if(!convertToU(expected, sizeof(expected), | |
303 | sampleText, sizeof(sampleText)/sizeof(sampleText[0]), "UTF8", fromOffsets, TRUE, U_ZERO_ERROR )) | |
304 | log_err("UTF8 -> did not match.\n"); | |
305 | if(!convertToU(expected, sizeof(expected), | |
306 | sampleText, sizeof(sampleText)/sizeof(sampleText[0]), "UTF8", fromOffsets, FALSE, U_ZERO_ERROR )) | |
307 | log_err("UTF8 -> did not match.\n"); | |
308 | ||
309 | } | |
310 | ||
311 | ||
312 | ||
313 | } | |
314 | ||
315 | /*test various error behaviours*/ | |
316 | static void TestErrorBehaviour(){ | |
317 | log_verbose("Testing for SBCS and LATIN_1\n"); | |
318 | { | |
319 | static const UChar sampleText[] = { 0x0031, 0xd801}; | |
320 | static const UChar sampleText2[] = { 0x0031, 0xd801, 0x0032}; | |
374ca955 A |
321 | static const uint8_t expected0[] = { 0x31}; |
322 | static const uint8_t expected[] = { 0x31, 0x1a}; | |
b75a7d8f A |
323 | static const uint8_t expected2[] = { 0x31, 0x1a, 0x32}; |
324 | ||
325 | /*SBCS*/ | |
326 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
374ca955 | 327 | expected, sizeof(expected), "ibm-920", 0, TRUE, U_ZERO_ERROR)) |
b75a7d8f A |
328 | log_err("u-> ibm-920 [UCNV_SBCS] \n"); |
329 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
374ca955 | 330 | expected0, sizeof(expected0), "ibm-920", 0, FALSE, U_ZERO_ERROR)) |
b75a7d8f A |
331 | log_err("u-> ibm-920 [UCNV_SBCS] \n"); |
332 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
333 | expected2, sizeof(expected2), "ibm-920", 0, TRUE, U_ZERO_ERROR)) | |
334 | log_err("u-> ibm-920 [UCNV_SBCS] did not match\n"); | |
335 | ||
336 | ||
337 | /*LATIN_1*/ | |
338 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
374ca955 | 339 | expected, sizeof(expected), "LATIN_1", 0, TRUE, U_ZERO_ERROR)) |
b75a7d8f A |
340 | log_err("u-> LATIN_1 is supposed to fail\n"); |
341 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
374ca955 | 342 | expected0, sizeof(expected0), "LATIN_1", 0, FALSE, U_ZERO_ERROR)) |
b75a7d8f A |
343 | log_err("u-> LATIN_1 is supposed to fail\n"); |
344 | ||
345 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
346 | expected2, sizeof(expected2), "LATIN_1", 0, TRUE, U_ZERO_ERROR)) | |
347 | log_err("u-> LATIN_1 did not match\n"); | |
348 | } | |
349 | ||
350 | ||
351 | log_verbose("Testing for DBCS and MBCS\n"); | |
352 | { | |
353 | static const UChar sampleText[] = { 0x00a1, 0xd801}; | |
354 | static const uint8_t expected[] = { 0xa2, 0xae}; | |
374ca955 A |
355 | static const int32_t offsets[] = { 0x00, 0x00}; |
356 | static const uint8_t expectedSUB[] = { 0xa2, 0xae, 0xa1, 0xe0}; | |
357 | static const int32_t offsetsSUB[] = { 0x00, 0x00, 0x01, 0x01}; | |
b75a7d8f A |
358 | |
359 | static const UChar sampleText2[] = { 0x00a1, 0xd801, 0x00a4}; | |
360 | static const uint8_t expected2[] = { 0xa2, 0xae, 0xa1, 0xe0, 0xa2, 0xb4}; | |
361 | static const int32_t offsets2[] = { 0x00, 0x00, 0x01, 0x01, 0x02, 0x02}; | |
362 | ||
363 | static const UChar sampleText3MBCS[] = { 0x0001, 0x00a4, 0xdc01}; | |
364 | static const uint8_t expected3MBCS[] = { 0x01, 0xa2, 0xb4, 0xa1, 0xe0}; | |
365 | static const int32_t offsets3MBCS[] = { 0x00, 0x01, 0x01, 0x02, 0x02}; | |
366 | ||
367 | static const UChar sampleText4MBCS[] = { 0x0061, 0x00a6, 0xdc01}; | |
368 | static const uint8_t expected4MBCS[] = { 0x61, 0x8f, 0xa2, 0xc3, 0xf4, 0xfe}; | |
369 | static const int32_t offsets4MBCS[] = { 0x00, 0x01, 0x01, 0x01, 0x02, 0x02 }; | |
370 | ||
371 | ||
372 | ||
373 | ||
374 | ||
375 | /*DBCS*/ | |
376 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
374ca955 | 377 | expectedSUB, sizeof(expectedSUB), "ibm-1363", 0, TRUE, U_ZERO_ERROR)) |
b75a7d8f A |
378 | log_err("u-> ibm-1363 [UCNV_DBCS portion] is supposed to fail\n"); |
379 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
380 | expected, sizeof(expected), "ibm-1363", 0, FALSE, U_ZERO_ERROR)) | |
381 | log_err("u-> ibm-1363 [UCNV_DBCS portion] is supposed to fail\n"); | |
382 | ||
383 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
374ca955 | 384 | expectedSUB, sizeof(expectedSUB), "ibm-1363", offsetsSUB, TRUE, U_ZERO_ERROR)) |
b75a7d8f A |
385 | log_err("u-> ibm-1363 [UCNV_DBCS portion] is supposed to fail\n"); |
386 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
387 | expected, sizeof(expected), "ibm-1363", offsets, FALSE, U_ZERO_ERROR)) | |
388 | log_err("u-> ibm-1363 [UCNV_DBCS portion] is supposed to fail\n"); | |
389 | ||
390 | ||
391 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
392 | expected2, sizeof(expected2), "ibm-1363", 0, TRUE, U_ZERO_ERROR)) | |
393 | log_err("u-> ibm-1363 [UCNV_DBCS portion] did not match \n"); | |
394 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
395 | expected2, sizeof(expected2), "ibm-1363", offsets2, TRUE, U_ZERO_ERROR)) | |
396 | log_err("u-> ibm-1363 [UCNV_DBCS portion] did not match \n"); | |
397 | ||
398 | /*MBCS*/ | |
399 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
374ca955 | 400 | expectedSUB, sizeof(expectedSUB), "ibm-1363", 0, TRUE, U_ZERO_ERROR)) |
b75a7d8f A |
401 | log_err("u-> ibm-1363 [UCNV_MBCS] \n"); |
402 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
403 | expected, sizeof(expected), "ibm-1363", 0, FALSE, U_ZERO_ERROR)) | |
404 | log_err("u-> ibm-1363 [UCNV_MBCS] \n"); | |
405 | ||
406 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
407 | expected2, sizeof(expected2), "ibm-1363", 0, TRUE, U_ZERO_ERROR)) | |
408 | log_err("u-> ibm-1363 [UCNV_DBCS] did not match\n"); | |
409 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
410 | expected2, sizeof(expected2), "ibm-1363", 0, FALSE, U_ZERO_ERROR)) | |
411 | log_err("u-> ibm-1363 [UCNV_DBCS] did not match\n"); | |
412 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
413 | expected2, sizeof(expected2), "ibm-1363", offsets2, FALSE, U_ZERO_ERROR)) | |
414 | log_err("u-> ibm-1363 [UCNV_DBCS] did not match\n"); | |
415 | ||
416 | if(!convertFromU(sampleText3MBCS, sizeof(sampleText3MBCS)/sizeof(sampleText3MBCS[0]), | |
417 | expected3MBCS, sizeof(expected3MBCS), "ibm-1363", offsets3MBCS, TRUE, U_ZERO_ERROR)) | |
418 | log_err("u-> ibm-1363 [UCNV_MBCS] \n"); | |
419 | if(!convertFromU(sampleText3MBCS, sizeof(sampleText3MBCS)/sizeof(sampleText3MBCS[0]), | |
420 | expected3MBCS, sizeof(expected3MBCS), "ibm-1363", offsets3MBCS, FALSE, U_ZERO_ERROR)) | |
421 | log_err("u-> ibm-1363 [UCNV_MBCS] \n"); | |
422 | ||
423 | if(!convertFromU(sampleText4MBCS, sizeof(sampleText4MBCS)/sizeof(sampleText4MBCS[0]), | |
424 | expected4MBCS, sizeof(expected4MBCS), "euc-jp", offsets4MBCS, TRUE, U_ZERO_ERROR)) | |
425 | log_err("u-> euc-jp [UCNV_MBCS] \n"); | |
426 | if(!convertFromU(sampleText4MBCS, sizeof(sampleText4MBCS)/sizeof(sampleText4MBCS[0]), | |
427 | expected4MBCS, sizeof(expected4MBCS), "euc-jp", offsets4MBCS, FALSE, U_ZERO_ERROR)) | |
428 | log_err("u-> euc-jp [UCNV_MBCS] \n"); | |
429 | } | |
430 | /*iso-2022-jp*/ | |
431 | log_verbose("Testing for iso-2022-jp\n"); | |
432 | { | |
433 | static const UChar sampleText[] = { 0x0031, 0xd801}; | |
434 | static const uint8_t expected[] = { 0x31}; | |
374ca955 A |
435 | static const uint8_t expectedSUB[] = { 0x31, 0x1a}; |
436 | static const int32_t offsets[] = { 0x00, 1}; | |
b75a7d8f A |
437 | |
438 | static const UChar sampleText2[] = { 0x0031, 0xd801, 0x0032}; | |
439 | static const uint8_t expected2[] = { 0x31,0x1A,0x32}; | |
440 | static const int32_t offsets2[] = { 0x00,0x01,0x02}; | |
441 | ||
b75a7d8f A |
442 | static const UChar sampleText4MBCS[] = { 0x0061, 0x4e00, 0xdc01}; |
443 | static const uint8_t expected4MBCS[] = { 0x61, 0x1b, 0x24, 0x42, 0x30, 0x6c,0x1b,0x28,0x42,0x1a}; | |
444 | static const int32_t offsets4MBCS[] = { 0x00, 0x01, 0x01 ,0x01, 0x01, 0x01,0x02,0x02,0x02,0x02 }; | |
445 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
374ca955 | 446 | expectedSUB, sizeof(expectedSUB), "iso-2022-jp", offsets, TRUE, U_ZERO_ERROR)) |
b75a7d8f A |
447 | log_err("u-> iso-2022-jp [UCNV_MBCS] \n"); |
448 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
449 | expected, sizeof(expected), "iso-2022-jp", offsets, FALSE, U_ZERO_ERROR)) | |
450 | log_err("u-> ibm-1363 [UCNV_MBCS] \n"); | |
451 | ||
452 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
453 | expected2, sizeof(expected2), "iso-2022-jp", offsets2, TRUE, U_ZERO_ERROR)) | |
454 | log_err("u->iso-2022-jp[UCNV_DBCS] did not match\n"); | |
455 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
456 | expected2, sizeof(expected2), "iso-2022-jp", offsets2, FALSE, U_ZERO_ERROR)) | |
457 | log_err("u-> iso-2022-jp [UCNV_DBCS] did not match\n"); | |
458 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
459 | expected2, sizeof(expected2), "iso-2022-jp", offsets2, FALSE, U_ZERO_ERROR)) | |
460 | log_err("u-> iso-2022-jp [UCNV_DBCS] did not match\n"); | |
461 | ||
b75a7d8f A |
462 | if(!convertFromU(sampleText4MBCS, sizeof(sampleText4MBCS)/sizeof(sampleText4MBCS[0]), |
463 | expected4MBCS, sizeof(expected4MBCS), "iso-2022-jp", offsets4MBCS, TRUE, U_ZERO_ERROR)) | |
464 | log_err("u-> iso-2022-jp [UCNV_MBCS] \n"); | |
465 | if(!convertFromU(sampleText4MBCS, sizeof(sampleText4MBCS)/sizeof(sampleText4MBCS[0]), | |
466 | expected4MBCS, sizeof(expected4MBCS), "iso-2022-jp", offsets4MBCS, FALSE, U_ZERO_ERROR)) | |
467 | log_err("u-> iso-2022-jp [UCNV_MBCS] \n"); | |
468 | } | |
469 | /*iso-2022-cn*/ | |
470 | log_verbose("Testing for iso-2022-cn\n"); | |
471 | { | |
472 | static const UChar sampleText[] = { 0x0031, 0xd801}; | |
374ca955 A |
473 | static const uint8_t expected[] = { 0x31}; |
474 | static const uint8_t expectedSUB[] = { 0x31, 0x1A}; | |
475 | static const int32_t offsets[] = { 0x00, 1}; | |
b75a7d8f A |
476 | |
477 | static const UChar sampleText2[] = { 0x0031, 0xd801, 0x0032}; | |
374ca955 A |
478 | static const uint8_t expected2[] = { 0x31, 0x1A,0x32}; |
479 | static const int32_t offsets2[] = { 0x00, 0x01,0x02}; | |
b75a7d8f A |
480 | |
481 | static const UChar sampleText3MBCS[] = { 0x0051, 0x0050, 0xdc01}; | |
374ca955 A |
482 | static const uint8_t expected3MBCS[] = {0x51, 0x50, 0x1A}; |
483 | static const int32_t offsets3MBCS[] = { 0x00, 0x01, 0x02 }; | |
b75a7d8f A |
484 | |
485 | static const UChar sampleText4MBCS[] = { 0x0061, 0x4e00, 0xdc01}; | |
374ca955 A |
486 | static const uint8_t expected4MBCS[] = { 0x61, 0x1b, 0x24, 0x29, 0x41, 0x0e, 0x52, 0x3b, 0x0f, 0x1a }; |
487 | static const int32_t offsets4MBCS[] = { 0x00, 0x01, 0x01 ,0x01, 0x01, 0x01, 0x01, 0x01, 0x02, 0x02 }; | |
b75a7d8f | 488 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), |
374ca955 | 489 | expectedSUB, sizeof(expectedSUB), "iso-2022-cn", offsets, TRUE, U_ZERO_ERROR)) |
b75a7d8f A |
490 | log_err("u-> iso-2022-cn [UCNV_MBCS] \n"); |
491 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
492 | expected, sizeof(expected), "iso-2022-cn", offsets, FALSE, U_ZERO_ERROR)) | |
493 | log_err("u-> ibm-1363 [UCNV_MBCS] \n"); | |
494 | ||
495 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
496 | expected2, sizeof(expected2), "iso-2022-cn", offsets2, TRUE, U_ZERO_ERROR)) | |
497 | log_err("u->iso-2022-cn[UCNV_DBCS] did not match\n"); | |
498 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
499 | expected2, sizeof(expected2), "iso-2022-cn", offsets2, FALSE, U_ZERO_ERROR)) | |
500 | log_err("u-> iso-2022-cn [UCNV_DBCS] did not match\n"); | |
501 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
502 | expected2, sizeof(expected2), "iso-2022-cn", offsets2, FALSE, U_ZERO_ERROR)) | |
503 | log_err("u-> iso-2022-cn [UCNV_DBCS] did not match\n"); | |
504 | ||
505 | if(!convertFromU(sampleText3MBCS, sizeof(sampleText3MBCS)/sizeof(sampleText3MBCS[0]), | |
506 | expected3MBCS, sizeof(expected3MBCS), "iso-2022-cn", offsets3MBCS, TRUE, U_ZERO_ERROR)) | |
507 | log_err("u->iso-2022-cn [UCNV_MBCS] \n"); | |
508 | if(!convertFromU(sampleText3MBCS, sizeof(sampleText3MBCS)/sizeof(sampleText3MBCS[0]), | |
509 | expected3MBCS, sizeof(expected3MBCS), "iso-2022-cn", offsets3MBCS, FALSE, U_ZERO_ERROR)) | |
510 | log_err("u-> iso-2022-cn[UCNV_MBCS] \n"); | |
511 | ||
512 | if(!convertFromU(sampleText4MBCS, sizeof(sampleText4MBCS)/sizeof(sampleText4MBCS[0]), | |
513 | expected4MBCS, sizeof(expected4MBCS), "iso-2022-cn", offsets4MBCS, TRUE, U_ZERO_ERROR)) | |
514 | log_err("u-> iso-2022-cn [UCNV_MBCS] \n"); | |
515 | if(!convertFromU(sampleText4MBCS, sizeof(sampleText4MBCS)/sizeof(sampleText4MBCS[0]), | |
516 | expected4MBCS, sizeof(expected4MBCS), "iso-2022-cn", offsets4MBCS, FALSE, U_ZERO_ERROR)) | |
517 | log_err("u-> iso-2022-cn [UCNV_MBCS] \n"); | |
518 | } | |
519 | /*iso-2022-kr*/ | |
520 | log_verbose("Testing for iso-2022-kr\n"); | |
521 | { | |
522 | static const UChar sampleText[] = { 0x0031, 0xd801}; | |
523 | static const uint8_t expected[] = { 0x1b, 0x24, 0x29, 0x43, 0x31}; | |
374ca955 A |
524 | static const uint8_t expectedSUB[] = { 0x1b, 0x24, 0x29, 0x43, 0x31, 0x1A}; |
525 | static const int32_t offsets[] = { -1, -1, -1, -1, 0x00, 1}; | |
b75a7d8f A |
526 | |
527 | static const UChar sampleText2[] = { 0x0031, 0xd801, 0x0032}; | |
528 | static const uint8_t expected2[] = { 0x1b, 0x24, 0x29, 0x43, 0x31, 0x1A, 0x32}; | |
529 | static const int32_t offsets2[] = { -1, -1, -1, -1, 0x00, 0x01, 0x02}; | |
530 | ||
531 | static const UChar sampleText3MBCS[] = { 0x0051, 0x0050, 0xdc01}; | |
532 | static const uint8_t expected3MBCS[] = { 0x1b, 0x24, 0x29, 0x43, 0x51, 0x50, 0x1A }; | |
533 | static const int32_t offsets3MBCS[] = { -1, -1, -1, -1, 0x00, 0x01, 0x02, 0x02 }; | |
534 | ||
b75a7d8f | 535 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), |
374ca955 | 536 | expectedSUB, sizeof(expectedSUB), "iso-2022-kr", offsets, TRUE, U_ZERO_ERROR)) |
b75a7d8f A |
537 | log_err("u-> iso-2022-kr [UCNV_MBCS] \n"); |
538 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
539 | expected, sizeof(expected), "iso-2022-kr", offsets, FALSE, U_ZERO_ERROR)) | |
540 | log_err("u-> ibm-1363 [UCNV_MBCS] \n"); | |
541 | ||
542 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
543 | expected2, sizeof(expected2), "iso-2022-kr", offsets2, TRUE, U_ZERO_ERROR)) | |
544 | log_err("u->iso-2022-kr[UCNV_DBCS] did not match\n"); | |
545 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
546 | expected2, sizeof(expected2), "iso-2022-kr", offsets2, FALSE, U_ZERO_ERROR)) | |
547 | log_err("u-> iso-2022-kr [UCNV_DBCS] did not match\n"); | |
548 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
549 | expected2, sizeof(expected2), "iso-2022-kr", offsets2, FALSE, U_ZERO_ERROR)) | |
550 | log_err("u-> iso-2022-kr [UCNV_DBCS] did not match\n"); | |
551 | ||
552 | if(!convertFromU(sampleText3MBCS, sizeof(sampleText3MBCS)/sizeof(sampleText3MBCS[0]), | |
553 | expected3MBCS, sizeof(expected3MBCS), "iso-2022-kr", offsets3MBCS, TRUE, U_ZERO_ERROR)) | |
554 | log_err("u->iso-2022-kr [UCNV_MBCS] \n"); | |
555 | if(!convertFromU(sampleText3MBCS, sizeof(sampleText3MBCS)/sizeof(sampleText3MBCS[0]), | |
556 | expected3MBCS, sizeof(expected3MBCS), "iso-2022-kr", offsets3MBCS, FALSE, U_ZERO_ERROR)) | |
557 | log_err("u-> iso-2022-kr[UCNV_MBCS] \n"); | |
b75a7d8f A |
558 | } |
559 | ||
560 | /*HZ*/ | |
561 | log_verbose("Testing for HZ\n"); | |
562 | { | |
563 | static const UChar sampleText[] = { 0x0031, 0xd801}; | |
564 | static const uint8_t expected[] = { 0x7e, 0x7d, 0x31}; | |
374ca955 A |
565 | static const uint8_t expectedSUB[] = { 0x7e, 0x7d, 0x31, 0x1A}; |
566 | static const int32_t offsets[] = { 0x00, 0x00, 0x00, 1}; | |
b75a7d8f A |
567 | |
568 | static const UChar sampleText2[] = { 0x0031, 0xd801, 0x0032}; | |
569 | static const uint8_t expected2[] = { 0x7e, 0x7d, 0x31, 0x1A, 0x32 }; | |
570 | static const int32_t offsets2[] = { 0x00, 0x00, 0x00, 0x01, 0x02 }; | |
571 | ||
572 | static const UChar sampleText3MBCS[] = { 0x0051, 0x0050, 0xdc01}; | |
573 | static const uint8_t expected3MBCS[] = { 0x7e, 0x7d, 0x51, 0x50, 0x1A }; | |
574 | static const int32_t offsets3MBCS[] = { 0x00, 0x00, 0x00, 0x01, 0x02}; | |
575 | ||
576 | static const UChar sampleText4MBCS[] = { 0x0061, 0x4e00, 0xdc01}; | |
577 | static const uint8_t expected4MBCS[] = { 0x7e, 0x7d, 0x61, 0x7e, 0x7b, 0x52, 0x3b, 0x7e, 0x7d, 0x1a }; | |
578 | static const int32_t offsets4MBCS[] = { 0x00, 0x00, 0x00, 0x01, 0x01, 0x01 ,0x01, 0x02, 0x02, 0x02 }; | |
579 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
374ca955 | 580 | expectedSUB, sizeof(expectedSUB), "HZ", offsets, TRUE, U_ZERO_ERROR)) |
b75a7d8f A |
581 | log_err("u-> HZ [UCNV_MBCS] \n"); |
582 | if(!convertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
583 | expected, sizeof(expected), "HZ", offsets, FALSE, U_ZERO_ERROR)) | |
584 | log_err("u-> ibm-1363 [UCNV_MBCS] \n"); | |
585 | ||
586 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
587 | expected2, sizeof(expected2), "HZ", offsets2, TRUE, U_ZERO_ERROR)) | |
588 | log_err("u->HZ[UCNV_DBCS] did not match\n"); | |
589 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
590 | expected2, sizeof(expected2), "HZ", offsets2, FALSE, U_ZERO_ERROR)) | |
591 | log_err("u-> HZ [UCNV_DBCS] did not match\n"); | |
592 | if(!convertFromU(sampleText2, sizeof(sampleText2)/sizeof(sampleText2[0]), | |
593 | expected2, sizeof(expected2), "HZ", offsets2, FALSE, U_ZERO_ERROR)) | |
594 | log_err("u-> HZ [UCNV_DBCS] did not match\n"); | |
595 | ||
596 | if(!convertFromU(sampleText3MBCS, sizeof(sampleText3MBCS)/sizeof(sampleText3MBCS[0]), | |
597 | expected3MBCS, sizeof(expected3MBCS), "HZ", offsets3MBCS, TRUE, U_ZERO_ERROR)) | |
598 | log_err("u->HZ [UCNV_MBCS] \n"); | |
599 | if(!convertFromU(sampleText3MBCS, sizeof(sampleText3MBCS)/sizeof(sampleText3MBCS[0]), | |
600 | expected3MBCS, sizeof(expected3MBCS), "HZ", offsets3MBCS, FALSE, U_ZERO_ERROR)) | |
601 | log_err("u-> HZ[UCNV_MBCS] \n"); | |
602 | ||
603 | if(!convertFromU(sampleText4MBCS, sizeof(sampleText4MBCS)/sizeof(sampleText4MBCS[0]), | |
604 | expected4MBCS, sizeof(expected4MBCS), "HZ", offsets4MBCS, TRUE, U_ZERO_ERROR)) | |
605 | log_err("u-> HZ [UCNV_MBCS] \n"); | |
606 | if(!convertFromU(sampleText4MBCS, sizeof(sampleText4MBCS)/sizeof(sampleText4MBCS[0]), | |
607 | expected4MBCS, sizeof(expected4MBCS), "HZ", offsets4MBCS, FALSE, U_ZERO_ERROR)) | |
608 | log_err("u-> HZ [UCNV_MBCS] \n"); | |
609 | } | |
610 | ||
611 | ||
612 | } | |
613 | ||
614 | /*test different convertToUnicode error behaviours*/ | |
615 | static void TestToUnicodeErrorBehaviour() | |
616 | { | |
617 | log_verbose("Testing error conditions for DBCS\n"); | |
618 | { | |
619 | uint8_t sampleText[] = { 0xa2, 0xae, 0x03, 0x04}; | |
620 | const UChar expected[] = { 0x00a1 }; | |
621 | ||
b75a7d8f A |
622 | if(!convertToU(sampleText, sizeof(sampleText), |
623 | expected, sizeof(expected)/sizeof(expected[0]), "ibm-1363", 0, TRUE, U_ZERO_ERROR )) | |
624 | log_err("DBCS (ibm-1363)->Unicode did not match.\n"); | |
625 | if(!convertToU(sampleText, sizeof(sampleText), | |
626 | expected, sizeof(expected)/sizeof(expected[0]), "ibm-1363", 0, FALSE, U_ZERO_ERROR )) | |
627 | log_err("DBCS (ibm-1363)->Unicode with flush = false did not match.\n"); | |
b75a7d8f A |
628 | } |
629 | log_verbose("Testing error conditions for SBCS\n"); | |
630 | { | |
631 | uint8_t sampleText[] = { 0xa2, 0xFF}; | |
632 | const UChar expected[] = { 0x00c2 }; | |
633 | ||
634 | /* uint8_t sampleText2[] = { 0xa2, 0x70 }; | |
635 | const UChar expected2[] = { 0x0073 };*/ | |
636 | ||
637 | if(!convertToU(sampleText, sizeof(sampleText), | |
638 | expected, sizeof(expected)/sizeof(expected[0]), "ibm-1051", 0, TRUE, U_ZERO_ERROR )) | |
639 | log_err("SBCS (ibm-1051)->Unicode did not match.\n"); | |
640 | if(!convertToU(sampleText, sizeof(sampleText), | |
641 | expected, sizeof(expected)/sizeof(expected[0]), "ibm-1051", 0, FALSE, U_ZERO_ERROR )) | |
642 | log_err("SBCS (ibm-1051)->Unicode with flush = false did not match.\n"); | |
643 | ||
644 | } | |
b75a7d8f A |
645 | } |
646 | ||
647 | static void TestGetNextErrorBehaviour(){ | |
648 | /*Test for unassigned character*/ | |
649 | #define INPUT_SIZE 1 | |
650 | static const char input1[INPUT_SIZE]={ 0x70 }; | |
651 | const char* source=(const char*)input1; | |
652 | UErrorCode err=U_ZERO_ERROR; | |
653 | UChar32 c=0; | |
654 | UConverter *cnv=ucnv_open("ibm-424", &err); | |
655 | if(U_FAILURE(err)) { | |
656 | log_data_err("Unable to open a SBCS(ibm-424) converter: %s\n", u_errorName(err)); | |
657 | return; | |
658 | } | |
659 | c=ucnv_getNextUChar(cnv, &source, source + INPUT_SIZE, &err); | |
660 | if(err != U_INVALID_CHAR_FOUND && c!=0xfffd){ | |
661 | log_err("FAIL in TestGetNextErrorBehaviour(unassigned): Expected: U_INVALID_CHAR_ERROR or 0xfffd ----Got:%s and 0x%lx\n", myErrorName(err), c); | |
662 | } | |
663 | ucnv_close(cnv); | |
664 | } | |
665 | ||
666 | #define MAX_UTF16_LEN 2 | |
667 | #define MAX_UTF8_LEN 4 | |
668 | ||
669 | /*Regression test for utf8 converter*/ | |
670 | static void TestRegressionUTF8(){ | |
671 | UChar32 currCh = 0; | |
672 | int32_t offset8; | |
673 | int32_t offset16; | |
674 | UChar *standardForm = (UChar*)malloc(MAX_LENGTH*sizeof(UChar)); | |
675 | uint8_t *utf8 = (uint8_t*)malloc(MAX_LENGTH); | |
676 | ||
677 | while (currCh <= UNICODE_LIMIT) { | |
678 | offset16 = 0; | |
679 | offset8 = 0; | |
680 | while(currCh <= UNICODE_LIMIT | |
681 | && offset16 < (MAX_LENGTH/sizeof(UChar) - MAX_UTF16_LEN) | |
682 | && offset8 < (MAX_LENGTH - MAX_UTF8_LEN)) | |
683 | { | |
684 | if (currCh == SURROGATE_HIGH_START) { | |
685 | currCh = SURROGATE_LOW_END + 1; /* Skip surrogate range */ | |
686 | } | |
687 | UTF16_APPEND_CHAR_SAFE(standardForm, offset16, MAX_LENGTH, currCh); | |
688 | UTF8_APPEND_CHAR_SAFE(utf8, offset8, MAX_LENGTH, currCh); | |
689 | currCh++; | |
690 | } | |
691 | if(!convertFromU(standardForm, offset16, | |
692 | utf8, offset8, "UTF8", 0, TRUE, U_ZERO_ERROR )) { | |
693 | log_err("Unicode->UTF8 did not match.\n"); | |
694 | } | |
695 | if(!convertToU(utf8, offset8, | |
696 | standardForm, offset16, "UTF8", 0, TRUE, U_ZERO_ERROR )) { | |
697 | log_err("UTF8->Unicode did not match.\n"); | |
698 | } | |
699 | } | |
700 | free(standardForm); | |
701 | free(utf8); | |
702 | } | |
703 | ||
704 | #define MAX_UTF32_LEN 1 | |
705 | ||
706 | static void TestRegressionUTF32(){ | |
707 | UChar32 currCh = 0; | |
708 | int32_t offset32; | |
709 | int32_t offset16; | |
710 | UChar *standardForm = (UChar*)malloc(MAX_LENGTH*sizeof(UChar)); | |
711 | UChar32 *utf32 = (UChar32*)malloc(MAX_LENGTH*sizeof(UChar32)); | |
712 | ||
713 | while (currCh <= UNICODE_LIMIT) { | |
714 | offset16 = 0; | |
715 | offset32 = 0; | |
716 | while(currCh <= UNICODE_LIMIT | |
717 | && offset16 < (MAX_LENGTH/sizeof(UChar) - MAX_UTF16_LEN) | |
718 | && offset32 < (MAX_LENGTH/sizeof(UChar32) - MAX_UTF32_LEN)) | |
719 | { | |
720 | if (currCh == SURROGATE_HIGH_START) { | |
721 | currCh = SURROGATE_LOW_END + 1; /* Skip surrogate range */ | |
722 | } | |
723 | UTF16_APPEND_CHAR_SAFE(standardForm, offset16, MAX_LENGTH, currCh); | |
724 | UTF32_APPEND_CHAR_SAFE(utf32, offset32, MAX_LENGTH, currCh); | |
725 | currCh++; | |
726 | } | |
727 | if(!convertFromU(standardForm, offset16, | |
728 | (const uint8_t *)utf32, offset32*sizeof(UChar32), "UTF32_PlatformEndian", 0, TRUE, U_ZERO_ERROR )) { | |
729 | log_err("Unicode->UTF32 did not match.\n"); | |
730 | } | |
731 | if(!convertToU((const uint8_t *)utf32, offset32*sizeof(UChar32), | |
732 | standardForm, offset16, "UTF32_PlatformEndian", 0, TRUE, U_ZERO_ERROR )) { | |
733 | log_err("UTF32->Unicode did not match.\n"); | |
734 | } | |
735 | } | |
736 | free(standardForm); | |
737 | free(utf32); | |
738 | } | |
739 | ||
740 | /*Walk through the available converters*/ | |
741 | static void TestAvailableConverters(){ | |
742 | UErrorCode status=U_ZERO_ERROR; | |
743 | UConverter *conv=NULL; | |
744 | int32_t i=0; | |
745 | for(i=0; i < ucnv_countAvailable(); i++){ | |
746 | status=U_ZERO_ERROR; | |
747 | conv=ucnv_open(ucnv_getAvailableName(i), &status); | |
748 | if(U_FAILURE(status)){ | |
749 | log_err("ERROR: converter creation failed. Failure in alias table or the data table for \n converter=%s. Error=%s\n", | |
750 | ucnv_getAvailableName(i), myErrorName(status)); | |
751 | continue; | |
752 | } | |
753 | ucnv_close(conv); | |
754 | } | |
755 | ||
756 | } | |
757 | ||
758 | static void TestFlushInternalBuffer(){ | |
759 | TestWithBufferSize(MAX_LENGTH, 1); | |
760 | TestWithBufferSize(1, 1); | |
761 | TestWithBufferSize(1, MAX_LENGTH); | |
762 | TestWithBufferSize(MAX_LENGTH, MAX_LENGTH); | |
763 | } | |
764 | ||
765 | static void TestWithBufferSize(int32_t insize, int32_t outsize){ | |
766 | ||
767 | gInBufferSize =insize; | |
768 | gOutBufferSize = outsize; | |
769 | ||
770 | log_verbose("Testing fromUnicode for UTF-8 with UCNV_TO_U_CALLBACK_SUBSTITUTE \n"); | |
771 | { | |
772 | UChar sampleText[] = | |
773 | { 0x0031, 0x0032, 0x0033, 0x0000, 0x4e00, 0x4e8c, 0x4e09, 0x002E }; | |
774 | const uint8_t expectedUTF8[] = | |
775 | { 0x31, 0x32, 0x33, 0x00, 0xe4, 0xb8, 0x80, 0xe4, 0xba, 0x8c, 0xe4, 0xb8, 0x89, 0x2E }; | |
776 | int32_t toUTF8Offs[] = | |
777 | { 0x00, 0x01, 0x02, 0x03, 0x04, 0x04, 0x04, 0x05, 0x05, 0x05, 0x06, 0x06, 0x06, 0x07}; | |
778 | /* int32_t fmUTF8Offs[] = | |
779 | { 0x0000, 0x0001, 0x0002, 0x0003, 0x0004, 0x0007, 0x000a, 0x000d };*/ | |
780 | ||
781 | /*UTF-8*/ | |
782 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
783 | expectedUTF8, sizeof(expectedUTF8), "UTF8", UCNV_FROM_U_CALLBACK_SUBSTITUTE, toUTF8Offs ,FALSE)) | |
784 | log_err("u-> UTF8 did not match.\n"); | |
785 | } | |
786 | ||
787 | log_verbose("Testing fromUnicode with UCNV_FROM_U_CALLBACK_ESCAPE \n"); | |
788 | { | |
789 | UChar inputTest[] = { 0x0061, 0xd801, 0xdc01, 0xd801, 0x0061 }; | |
790 | const uint8_t toIBM943[]= { 0x61, | |
791 | 0x25, 0x55, 0x44, 0x38, 0x30, 0x31, | |
792 | 0x25, 0x55, 0x44, 0x43, 0x30, 0x31, | |
793 | 0x25, 0x55, 0x44, 0x38, 0x30, 0x31, | |
794 | 0x61 }; | |
795 | int32_t offset[]= {0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 3, 3, 3, 3, 3, 3, 4}; | |
796 | ||
797 | if(!testConvertFromU(inputTest, sizeof(inputTest)/sizeof(inputTest[0]), | |
798 | toIBM943, sizeof(toIBM943), "ibm-943", | |
799 | (UConverterFromUCallback)UCNV_FROM_U_CALLBACK_ESCAPE, offset,FALSE)) | |
800 | log_err("u-> ibm-943 with subst with value did not match.\n"); | |
801 | } | |
802 | ||
803 | log_verbose("Testing fromUnicode for UTF-8 with UCNV_TO_U_CALLBACK_SUBSTITUTE \n"); | |
804 | { | |
805 | const uint8_t sampleText1[] = { 0x31, 0xe4, 0xba, 0x8c, | |
806 | 0xe0, 0x80, 0x61}; | |
807 | UChar expected1[] = { 0x0031, 0x4e8c, 0xfffd, 0x0061}; | |
808 | int32_t offsets1[] = { 0x0000, 0x0001, 0x0004, 0x0006}; | |
809 | ||
810 | if(!testConvertToU(sampleText1, sizeof(sampleText1), | |
811 | expected1, sizeof(expected1)/sizeof(expected1[0]),"utf8", UCNV_TO_U_CALLBACK_SUBSTITUTE, offsets1,FALSE)) | |
812 | log_err("utf8->u with substitute did not match.\n");; | |
813 | } | |
814 | ||
815 | ||
816 | log_verbose("Testing toUnicode with UCNV_TO_U_CALLBACK_ESCAPE \n"); | |
817 | /*to Unicode*/ | |
818 | { | |
819 | const uint8_t sampleTxtToU[]= { 0x00, 0x9f, 0xaf, | |
820 | 0x81, 0xad, /*unassigned*/ | |
821 | 0x89, 0xd3 }; | |
822 | UChar IBM_943toUnicode[] = { 0x0000, 0x6D63, | |
823 | 0x25, 0x58, 0x38, 0x31, 0x25, 0x58, 0x41, 0x44, | |
824 | 0x7B87}; | |
825 | int32_t fromIBM943Offs [] = { 0, 1, 3, 3, 3, 3, 3, 3, 3, 3, 5}; | |
826 | ||
827 | if(!testConvertToU(sampleTxtToU, sizeof(sampleTxtToU), | |
828 | IBM_943toUnicode, sizeof(IBM_943toUnicode)/sizeof(IBM_943toUnicode[0]),"ibm-943", | |
829 | (UConverterToUCallback)UCNV_TO_U_CALLBACK_ESCAPE, fromIBM943Offs,FALSE)) | |
830 | log_err("ibm-943->u with substitute with value did not match.\n"); | |
831 | ||
832 | } | |
833 | ||
834 | } | |
835 | ||
836 | static UBool convertFromU( const UChar *source, int sourceLen, const uint8_t *expect, int expectLen, | |
837 | const char *codepage, const int32_t *expectOffsets, UBool doFlush, UErrorCode expectedStatus) | |
838 | { | |
839 | ||
840 | int32_t i=0; | |
841 | uint8_t *p=0; | |
842 | const UChar *src; | |
843 | uint8_t buffer[MAX_LENGTH]; | |
844 | int32_t offsetBuffer[MAX_LENGTH]; | |
845 | int32_t *offs=0; | |
846 | uint8_t *targ; | |
847 | uint8_t *targetLimit; | |
848 | UChar *sourceLimit=0; | |
849 | UErrorCode status = U_ZERO_ERROR; | |
850 | UConverter *conv = 0; | |
851 | conv = ucnv_open(codepage, &status); | |
852 | if(U_FAILURE(status)) | |
853 | { | |
854 | log_data_err("Couldn't open converter %s\n",codepage); | |
855 | return TRUE; | |
856 | } | |
857 | log_verbose("Converter %s opened..\n", ucnv_getName(conv, &status)); | |
858 | ||
859 | for(i=0; i<MAX_LENGTH; i++){ | |
860 | buffer[i]=0xF0; | |
861 | offsetBuffer[i]=0xFF; | |
862 | } | |
863 | ||
864 | src=source; | |
865 | sourceLimit=(UChar*)src+(sourceLen); | |
866 | targ=buffer; | |
867 | targetLimit=targ+MAX_LENGTH; | |
868 | offs=offsetBuffer; | |
869 | ucnv_fromUnicode (conv, | |
870 | (char **)&targ, | |
871 | (const char *)targetLimit, | |
872 | &src, | |
873 | sourceLimit, | |
874 | expectOffsets ? offs : NULL, | |
875 | doFlush, | |
876 | &status); | |
877 | ucnv_close(conv); | |
878 | if(status != expectedStatus){ | |
879 | log_err("ucnv_fromUnicode() failed for codepage=%s. Error =%s Expected=%s\n", codepage, myErrorName(status), myErrorName(expectedStatus)); | |
880 | return FALSE; | |
881 | } | |
882 | ||
883 | log_verbose("\nConversion done [%d uchars in -> %d chars out]. \nResult :", | |
884 | sourceLen, targ-buffer); | |
885 | ||
886 | if(expectLen != targ-buffer) | |
887 | { | |
888 | log_err("Expected %d chars out, got %d FROM Unicode to %s\n", expectLen, targ-buffer, codepage); | |
889 | log_verbose("Expected %d chars out, got %d FROM Unicode to %s\n", expectLen, targ-buffer, codepage); | |
890 | printSeqErr((const unsigned char *)buffer, targ-buffer); | |
891 | printSeqErr((const unsigned char*)expect, expectLen); | |
892 | return FALSE; | |
893 | } | |
894 | ||
895 | if(memcmp(buffer, expect, expectLen)){ | |
896 | log_err("String does not match. FROM Unicode to codePage%s\n", codepage); | |
374ca955 | 897 | log_info("\nGot:"); |
b75a7d8f | 898 | printSeqErr((const unsigned char *)buffer, expectLen); |
374ca955 | 899 | log_info("\nExpected:"); |
b75a7d8f A |
900 | printSeqErr((const unsigned char *)expect, expectLen); |
901 | return FALSE; | |
902 | } | |
903 | else { | |
904 | log_verbose("Matches!\n"); | |
905 | } | |
906 | ||
907 | if (expectOffsets != 0){ | |
908 | log_verbose("comparing %d offsets..\n", targ-buffer); | |
909 | if(memcmp(offsetBuffer,expectOffsets,(targ-buffer) * sizeof(int32_t) )){ | |
910 | log_err("did not get the expected offsets. for FROM Unicode to %s\n", codepage); | |
374ca955 | 911 | log_info("\nGot : "); |
b75a7d8f A |
912 | printSeqErr((const unsigned char*)buffer, targ-buffer); |
913 | for(p=buffer;p<targ;p++) | |
374ca955 A |
914 | log_info("%d, ", offsetBuffer[p-buffer]); |
915 | log_info("\nExpected: "); | |
b75a7d8f | 916 | for(i=0; i< (targ-buffer); i++) |
374ca955 | 917 | log_info("%d,", expectOffsets[i]); |
b75a7d8f A |
918 | } |
919 | } | |
920 | ||
921 | return TRUE; | |
922 | } | |
923 | ||
924 | ||
925 | static UBool convertToU( const uint8_t *source, int sourceLen, const UChar *expect, int expectLen, | |
926 | const char *codepage, const int32_t *expectOffsets, UBool doFlush, UErrorCode expectedStatus) | |
927 | { | |
928 | UErrorCode status = U_ZERO_ERROR; | |
929 | UConverter *conv = 0; | |
930 | int32_t i=0; | |
931 | UChar *p=0; | |
932 | const uint8_t* src; | |
933 | UChar buffer[MAX_LENGTH]; | |
934 | int32_t offsetBuffer[MAX_LENGTH]; | |
935 | int32_t *offs=0; | |
936 | UChar *targ; | |
937 | UChar *targetLimit; | |
938 | uint8_t *sourceLimit=0; | |
939 | ||
940 | ||
941 | ||
942 | conv = ucnv_open(codepage, &status); | |
943 | if(U_FAILURE(status)) | |
944 | { | |
945 | log_data_err("Couldn't open converter %s\n",codepage); | |
946 | return TRUE; | |
947 | } | |
948 | log_verbose("Converter %s opened..\n", ucnv_getName(conv, &status)); | |
949 | ||
950 | ||
951 | ||
952 | for(i=0; i<MAX_LENGTH; i++){ | |
953 | buffer[i]=0xFFFE; | |
954 | offsetBuffer[i]=-1; | |
955 | } | |
956 | ||
957 | src=source; | |
958 | sourceLimit=(uint8_t*)(src+(sourceLen)); | |
959 | targ=buffer; | |
960 | targetLimit=targ+MAX_LENGTH; | |
961 | offs=offsetBuffer; | |
962 | ||
963 | ||
964 | ||
965 | ucnv_toUnicode (conv, | |
966 | &targ, | |
967 | targetLimit, | |
968 | (const char **)&src, | |
969 | (const char *)sourceLimit, | |
970 | expectOffsets ? offs : NULL, | |
971 | doFlush, | |
972 | &status); | |
973 | ||
974 | ucnv_close(conv); | |
975 | if(status != expectedStatus){ | |
976 | log_err("ucnv_fromUnicode() failed for codepage=%s. Error =%s Expected=%s\n", codepage, myErrorName(status), myErrorName(expectedStatus)); | |
977 | return FALSE; | |
978 | } | |
979 | log_verbose("\nConversion done [%d uchars in -> %d chars out]. \nResult :", | |
980 | sourceLen, targ-buffer); | |
981 | ||
982 | ||
983 | ||
984 | ||
985 | log_verbose("comparing %d uchars (%d bytes)..\n",expectLen,expectLen*2); | |
986 | ||
987 | if (expectOffsets != 0) { | |
988 | if(memcmp(offsetBuffer, expectOffsets, (targ-buffer) * sizeof(int32_t))){ | |
989 | ||
990 | log_err("did not get the expected offsets from %s To UNICODE\n", codepage); | |
374ca955 | 991 | log_info("\nGot : "); |
b75a7d8f | 992 | for(p=buffer;p<targ;p++) |
374ca955 A |
993 | log_info("%d, ", offsetBuffer[p-buffer]); |
994 | log_info("\nExpected: "); | |
b75a7d8f | 995 | for(i=0; i<(targ-buffer); i++) |
374ca955 A |
996 | log_info("%d, ", expectOffsets[i]); |
997 | log_info("\nGot result:"); | |
b75a7d8f | 998 | for(i=0; i<(targ-buffer); i++) |
374ca955 A |
999 | log_info("0x%04X,", buffer[i]); |
1000 | log_info("\nFrom Input:"); | |
b75a7d8f | 1001 | for(i=0; i<(src-source); i++) |
374ca955 A |
1002 | log_info("0x%02X,", (unsigned char)source[i]); |
1003 | log_info("\n"); | |
b75a7d8f A |
1004 | } |
1005 | } | |
1006 | if(memcmp(buffer, expect, expectLen*2)){ | |
1007 | log_err("String does not match. from codePage %s TO Unicode\n", codepage); | |
374ca955 | 1008 | log_info("\nGot:"); |
b75a7d8f | 1009 | printUSeqErr(buffer, expectLen); |
374ca955 | 1010 | log_info("\nExpected:"); |
b75a7d8f A |
1011 | printUSeqErr(expect, expectLen); |
1012 | return FALSE; | |
1013 | } | |
1014 | else { | |
1015 | log_verbose("Matches!\n"); | |
1016 | } | |
1017 | ||
1018 | return TRUE; | |
1019 | } | |
1020 | ||
1021 | ||
1022 | static UBool testConvertFromU( const UChar *source, int sourceLen, const uint8_t *expect, int expectLen, | |
1023 | const char *codepage, UConverterFromUCallback callback , const int32_t *expectOffsets, UBool testReset) | |
1024 | { | |
1025 | UErrorCode status = U_ZERO_ERROR; | |
1026 | UConverter *conv = 0; | |
1027 | uint8_t junkout[MAX_LENGTH]; /* FIX */ | |
1028 | int32_t junokout[MAX_LENGTH]; /* FIX */ | |
1029 | uint8_t *p; | |
1030 | const UChar *src; | |
1031 | uint8_t *end; | |
1032 | uint8_t *targ; | |
1033 | int32_t *offs; | |
1034 | int i; | |
1035 | int32_t realBufferSize; | |
1036 | uint8_t *realBufferEnd; | |
1037 | const UChar *realSourceEnd; | |
1038 | const UChar *sourceLimit; | |
1039 | UBool checkOffsets = TRUE; | |
1040 | UBool doFlush; | |
1041 | ||
1042 | UConverterFromUCallback oldAction = NULL; | |
1043 | const void* oldContext = NULL; | |
1044 | ||
1045 | for(i=0;i<MAX_LENGTH;i++) | |
1046 | junkout[i] = 0xF0; | |
1047 | for(i=0;i<MAX_LENGTH;i++) | |
1048 | junokout[i] = 0xFF; | |
1049 | ||
1050 | setNuConvTestName(codepage, "FROM"); | |
1051 | ||
1052 | log_verbose("\n========= %s\n", gNuConvTestName); | |
1053 | ||
1054 | conv = ucnv_open(codepage, &status); | |
1055 | if(U_FAILURE(status)) | |
1056 | { | |
1057 | log_data_err("Couldn't open converter %s\n",codepage); | |
1058 | return TRUE; | |
1059 | } | |
1060 | ||
1061 | log_verbose("Converter opened..\n"); | |
1062 | /*----setting the callback routine----*/ | |
1063 | ucnv_setFromUCallBack (conv, callback, NULL, &oldAction, &oldContext, &status); | |
1064 | if (U_FAILURE(status)) { | |
1065 | log_err("FAILURE in setting the callback Function! %s\n", myErrorName(status)); | |
1066 | } | |
1067 | /*------------------------*/ | |
1068 | ||
1069 | src = source; | |
1070 | targ = junkout; | |
1071 | offs = junokout; | |
1072 | ||
1073 | realBufferSize = (sizeof(junkout)/sizeof(junkout[0])); | |
1074 | realBufferEnd = junkout + realBufferSize; | |
1075 | realSourceEnd = source + sourceLen; | |
1076 | ||
1077 | if ( gOutBufferSize != realBufferSize ) | |
1078 | checkOffsets = FALSE; | |
1079 | ||
1080 | if( gInBufferSize != MAX_LENGTH ) | |
1081 | checkOffsets = FALSE; | |
1082 | ||
1083 | do | |
1084 | { | |
1085 | end = nct_min(targ + gOutBufferSize, realBufferEnd); | |
1086 | sourceLimit = nct_min(src + gInBufferSize, realSourceEnd); | |
1087 | ||
1088 | doFlush = (UBool)(sourceLimit == realSourceEnd); | |
1089 | ||
1090 | if(targ == realBufferEnd) | |
1091 | { | |
1092 | log_err("Error, overflowed the real buffer while about to call fromUnicode! targ=%08lx %s", targ, gNuConvTestName); | |
1093 | return FALSE; | |
1094 | } | |
1095 | log_verbose("calling fromUnicode @ SOURCE:%08lx to %08lx TARGET: %08lx to %08lx, flush=%s\n", src,sourceLimit, targ,end, doFlush?"TRUE":"FALSE"); | |
1096 | ||
1097 | ||
1098 | status = U_ZERO_ERROR; | |
1099 | if(gInBufferSize ==999 && gOutBufferSize==999) | |
1100 | doFlush = FALSE; | |
1101 | ucnv_fromUnicode (conv, | |
1102 | (char **)&targ, | |
1103 | (const char *)end, | |
1104 | &src, | |
1105 | sourceLimit, | |
1106 | offs, | |
1107 | doFlush, /* flush if we're at the end of the input data */ | |
1108 | &status); | |
1109 | if(testReset) | |
1110 | ucnv_resetToUnicode(conv); | |
1111 | if(gInBufferSize ==999 && gOutBufferSize==999) | |
1112 | ucnv_resetToUnicode(conv); | |
1113 | ||
1114 | } while ( (status == U_BUFFER_OVERFLOW_ERROR) || (U_SUCCESS(status) && sourceLimit < realSourceEnd) ); | |
1115 | ||
1116 | if(U_FAILURE(status)) { | |
1117 | log_err("Problem doing fromUnicode to %s, errcode %s %s\n", codepage, myErrorName(status), gNuConvTestName); | |
1118 | return FALSE; | |
1119 | } | |
1120 | ||
1121 | log_verbose("\nConversion done [%d uchars in -> %d chars out]. \nResult :", | |
1122 | sourceLen, targ-junkout); | |
1123 | if(VERBOSITY) | |
1124 | { | |
1125 | char junk[999]; | |
1126 | char offset_str[999]; | |
1127 | uint8_t *ptr; | |
1128 | ||
1129 | junk[0] = 0; | |
1130 | offset_str[0] = 0; | |
1131 | for(ptr = junkout;ptr<targ;ptr++) | |
1132 | { | |
1133 | sprintf(junk + strlen(junk), "0x%02x, ", (0xFF) & (unsigned int)*ptr); | |
1134 | sprintf(offset_str + strlen(offset_str), "0x%02x, ", (0xFF) & (unsigned int)junokout[ptr-junkout]); | |
1135 | } | |
1136 | ||
1137 | log_verbose(junk); | |
1138 | printSeq((const unsigned char *)expect, expectLen); | |
1139 | if ( checkOffsets ) | |
1140 | { | |
1141 | log_verbose("\nOffsets:"); | |
1142 | log_verbose(offset_str); | |
1143 | } | |
1144 | log_verbose("\n"); | |
1145 | } | |
1146 | ucnv_close(conv); | |
1147 | ||
1148 | ||
1149 | if(expectLen != targ-junkout) | |
1150 | { | |
1151 | log_err("Expected %d chars out, got %d %s\n", expectLen, targ-junkout, gNuConvTestName); | |
1152 | log_verbose("Expected %d chars out, got %d %s\n", expectLen, targ-junkout, gNuConvTestName); | |
374ca955 | 1153 | log_info("\nGot:"); |
b75a7d8f | 1154 | printSeqErr((const unsigned char*)junkout, targ-junkout); |
374ca955 | 1155 | log_info("\nExpected:"); |
b75a7d8f A |
1156 | printSeqErr((const unsigned char*)expect, expectLen); |
1157 | return FALSE; | |
1158 | } | |
1159 | ||
1160 | if (checkOffsets && (expectOffsets != 0) ) | |
1161 | { | |
1162 | log_verbose("comparing %d offsets..\n", targ-junkout); | |
1163 | if(memcmp(junokout,expectOffsets,(targ-junkout) * sizeof(int32_t) )){ | |
1164 | log_err("did not get the expected offsets. %s", gNuConvTestName); | |
1165 | log_err("Got : "); | |
1166 | printSeqErr((const unsigned char*)junkout, targ-junkout); | |
1167 | for(p=junkout;p<targ;p++) | |
1168 | log_err("%d, ", junokout[p-junkout]); | |
1169 | log_err("\nExpected: "); | |
1170 | for(i=0; i<(targ-junkout); i++) | |
1171 | log_err("%d,", expectOffsets[i]); | |
1172 | } | |
1173 | } | |
1174 | ||
1175 | log_verbose("comparing..\n"); | |
1176 | if(!memcmp(junkout, expect, expectLen)) | |
1177 | { | |
1178 | log_verbose("Matches!\n"); | |
1179 | return TRUE; | |
1180 | } | |
1181 | else | |
1182 | { | |
1183 | log_err("String does not match. %s\n", gNuConvTestName); | |
1184 | printUSeqErr(source, sourceLen); | |
374ca955 | 1185 | log_info("\nGot:"); |
b75a7d8f | 1186 | printSeqErr((const unsigned char *)junkout, expectLen); |
374ca955 | 1187 | log_info("\nExpected:"); |
b75a7d8f A |
1188 | printSeqErr((const unsigned char *)expect, expectLen); |
1189 | ||
1190 | return FALSE; | |
1191 | } | |
1192 | } | |
1193 | ||
1194 | static UBool testConvertToU( const uint8_t *source, int sourcelen, const UChar *expect, int expectlen, | |
1195 | const char *codepage, UConverterToUCallback callback, const int32_t *expectOffsets, UBool testReset) | |
1196 | { | |
1197 | UErrorCode status = U_ZERO_ERROR; | |
1198 | UConverter *conv = 0; | |
1199 | UChar junkout[MAX_LENGTH]; /* FIX */ | |
1200 | int32_t junokout[MAX_LENGTH]; /* FIX */ | |
1201 | const uint8_t *src; | |
1202 | const uint8_t *realSourceEnd; | |
1203 | const uint8_t *srcLimit; | |
1204 | UChar *p; | |
1205 | UChar *targ; | |
1206 | UChar *end; | |
1207 | int32_t *offs; | |
1208 | int i; | |
1209 | UBool checkOffsets = TRUE; | |
1210 | int32_t realBufferSize; | |
1211 | UChar *realBufferEnd; | |
1212 | UBool doFlush; | |
1213 | ||
1214 | UConverterToUCallback oldAction = NULL; | |
1215 | const void* oldContext = NULL; | |
1216 | ||
1217 | ||
1218 | for(i=0;i<MAX_LENGTH;i++) | |
1219 | junkout[i] = 0xFFFE; | |
1220 | ||
1221 | for(i=0;i<MAX_LENGTH;i++) | |
1222 | junokout[i] = -1; | |
1223 | ||
1224 | setNuConvTestName(codepage, "TO"); | |
1225 | ||
1226 | log_verbose("\n========= %s\n", gNuConvTestName); | |
1227 | ||
1228 | conv = ucnv_open(codepage, &status); | |
1229 | if(U_FAILURE(status)) | |
1230 | { | |
1231 | log_data_err("Couldn't open converter %s\n",gNuConvTestName); | |
1232 | return TRUE; | |
1233 | } | |
1234 | ||
1235 | log_verbose("Converter opened..\n"); | |
1236 | /*----setting the callback routine----*/ | |
1237 | ucnv_setToUCallBack (conv, callback, NULL, &oldAction, &oldContext, &status); | |
1238 | if (U_FAILURE(status)) { | |
1239 | log_err("FAILURE in setting the callback Function! %s\n", myErrorName(status)); | |
1240 | } | |
1241 | /*-------------------------------------*/ | |
1242 | ||
1243 | src = source; | |
1244 | targ = junkout; | |
1245 | offs = junokout; | |
1246 | ||
1247 | realBufferSize = (sizeof(junkout)/sizeof(junkout[0])); | |
1248 | realBufferEnd = junkout + realBufferSize; | |
1249 | realSourceEnd = src + sourcelen; | |
1250 | ||
1251 | if ( gOutBufferSize != realBufferSize ) | |
1252 | checkOffsets = FALSE; | |
1253 | ||
1254 | if( gInBufferSize != MAX_LENGTH ) | |
1255 | checkOffsets = FALSE; | |
1256 | ||
1257 | do | |
1258 | { | |
1259 | end = nct_min( targ + gOutBufferSize, realBufferEnd); | |
1260 | srcLimit = nct_min(realSourceEnd, src + gInBufferSize); | |
1261 | ||
1262 | if(targ == realBufferEnd) | |
1263 | { | |
1264 | log_err("Error, the end would overflow the real output buffer while about to call toUnicode! tarjey=%08lx %s",targ,gNuConvTestName); | |
1265 | return FALSE; | |
1266 | } | |
1267 | log_verbose("calling toUnicode @ %08lx to %08lx\n", targ,end); | |
1268 | ||
1269 | /* oldTarg = targ; */ | |
1270 | ||
1271 | status = U_ZERO_ERROR; | |
1272 | doFlush=(UBool)((gInBufferSize ==999 && gOutBufferSize==999)?(srcLimit == realSourceEnd) : FALSE); | |
1273 | ||
1274 | ucnv_toUnicode (conv, | |
1275 | &targ, | |
1276 | end, | |
1277 | (const char **)&src, | |
1278 | (const char *)srcLimit, | |
1279 | offs, | |
1280 | doFlush, /* flush if we're at the end of hte source data */ | |
1281 | &status); | |
1282 | if(testReset) | |
1283 | ucnv_resetFromUnicode(conv); | |
1284 | if(gInBufferSize ==999 && gOutBufferSize==999) | |
1285 | ucnv_resetToUnicode(conv); | |
1286 | /* offs += (targ-oldTarg); */ | |
1287 | ||
1288 | } while ( (status == U_BUFFER_OVERFLOW_ERROR) || (U_SUCCESS(status) && (srcLimit < realSourceEnd)) ); /* while we just need another buffer */ | |
1289 | ||
1290 | if(U_FAILURE(status)) | |
1291 | { | |
1292 | log_err("Problem doing %s toUnicode, errcode %s %s\n", codepage, myErrorName(status), gNuConvTestName); | |
1293 | return FALSE; | |
1294 | } | |
1295 | ||
1296 | log_verbose("\nConversion done. %d bytes -> %d chars.\nResult :", | |
1297 | sourcelen, targ-junkout); | |
1298 | if(VERBOSITY) | |
1299 | { | |
1300 | char junk[999]; | |
1301 | char offset_str[999]; | |
1302 | ||
1303 | UChar *ptr; | |
1304 | ||
1305 | junk[0] = 0; | |
1306 | offset_str[0] = 0; | |
1307 | ||
1308 | for(ptr = junkout;ptr<targ;ptr++) | |
1309 | { | |
1310 | sprintf(junk + strlen(junk), "0x%04x, ", (0xFFFF) & (unsigned int)*ptr); | |
1311 | sprintf(offset_str + strlen(offset_str), "0x%04x, ", (0xFFFF) & (unsigned int)junokout[ptr-junkout]); | |
1312 | } | |
1313 | ||
1314 | log_verbose(junk); | |
1315 | ||
1316 | if ( checkOffsets ) | |
1317 | { | |
1318 | log_verbose("\nOffsets:"); | |
1319 | log_verbose(offset_str); | |
1320 | } | |
1321 | log_verbose("\n"); | |
1322 | } | |
1323 | ucnv_close(conv); | |
1324 | ||
1325 | log_verbose("comparing %d uchars (%d bytes)..\n",expectlen,expectlen*2); | |
1326 | ||
1327 | if (checkOffsets && (expectOffsets != 0)) | |
1328 | { | |
1329 | if(memcmp(junokout,expectOffsets,(targ-junkout) * sizeof(int32_t))){ | |
1330 | ||
1331 | log_err("did not get the expected offsets. %s",gNuConvTestName); | |
1332 | for(p=junkout;p<targ;p++) | |
1333 | log_err("%d, ", junokout[p-junkout]); | |
1334 | log_err("\nExpected: "); | |
1335 | for(i=0; i<(targ-junkout); i++) | |
1336 | log_err("%d,", expectOffsets[i]); | |
1337 | log_err(""); | |
1338 | for(i=0; i<(targ-junkout); i++) | |
1339 | log_err("%X,", junkout[i]); | |
1340 | log_err(""); | |
1341 | for(i=0; i<(src-source); i++) | |
1342 | log_err("%X,", (unsigned char)source[i]); | |
1343 | } | |
1344 | } | |
1345 | ||
1346 | if(!memcmp(junkout, expect, expectlen*2)) | |
1347 | { | |
1348 | log_verbose("Matches!\n"); | |
1349 | return TRUE; | |
1350 | } | |
1351 | else | |
1352 | { | |
1353 | log_err("String does not match. %s\n", gNuConvTestName); | |
1354 | log_verbose("String does not match. %s\n", gNuConvTestName); | |
374ca955 | 1355 | log_info("\nGot:"); |
b75a7d8f | 1356 | printUSeq(junkout, expectlen); |
374ca955 | 1357 | log_info("\nExpected:"); |
b75a7d8f A |
1358 | printUSeq(expect, expectlen); |
1359 | return FALSE; | |
1360 | } | |
1361 | } | |
1362 | ||
1363 | ||
1364 | static void TestResetBehaviour(void){ | |
b75a7d8f A |
1365 | log_verbose("Testing Reset for DBCS and MBCS\n"); |
1366 | { | |
1367 | static const UChar sampleText[] = {0x00a1, 0xd801, 0xdc01, 0x00a4}; | |
1368 | static const uint8_t expected[] = {0xa2, 0xae, 0xa1, 0xe0, 0xa2, 0xb4}; | |
1369 | static const int32_t offsets[] = {0x00, 0x00, 0x01, 0x01, 0x03, 0x03 }; | |
1370 | ||
1371 | ||
1372 | static const UChar sampleText1[] = {0x00a1, 0x00a4, 0x00a7, 0x00a8}; | |
1373 | static const uint8_t expected1[] = {0xa2, 0xae,0xA2,0xB4,0xA1,0xD7,0xA1,0xA7}; | |
1374 | static const int32_t offsets1[] = { 0,2,4,6}; | |
1375 | ||
1376 | /*DBCS*/ | |
1377 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
1378 | expected, sizeof(expected), "ibm-1363", UCNV_FROM_U_CALLBACK_SUBSTITUTE , NULL, TRUE)) | |
1379 | log_err("u-> ibm-1363 [UCNV_DBCS portion] not match.\n"); | |
1380 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
1381 | expected, sizeof(expected), "ibm-1363", UCNV_FROM_U_CALLBACK_SUBSTITUTE,offsets , TRUE)) | |
1382 | log_err("u-> ibm-1363 [UCNV_DBCS portion] not match.\n"); | |
1383 | ||
1384 | if(!testConvertToU(expected1, sizeof(expected1), | |
1385 | sampleText1, sizeof(sampleText1)/sizeof(sampleText1[0]), "ibm-1363",UCNV_TO_U_CALLBACK_SUBSTITUTE , | |
1386 | offsets1, TRUE)) | |
1387 | log_err("ibm-1363 -> did not match.\n"); | |
1388 | /*MBCS*/ | |
1389 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
1390 | expected, sizeof(expected), "ibm-1363", UCNV_FROM_U_CALLBACK_SUBSTITUTE , NULL, TRUE)) | |
1391 | log_err("u-> ibm-1363 [UCNV_MBCS] not match.\n"); | |
1392 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
1393 | expected, sizeof(expected), "ibm-1363", UCNV_FROM_U_CALLBACK_SUBSTITUTE,offsets , TRUE)) | |
1394 | log_err("u-> ibm-1363 [UCNV_MBCS] not match.\n"); | |
1395 | ||
1396 | if(!testConvertToU(expected1, sizeof(expected1), | |
1397 | sampleText1, sizeof(sampleText1)/sizeof(sampleText1[0]), "ibm-1363",UCNV_TO_U_CALLBACK_SUBSTITUTE , | |
1398 | offsets1, TRUE)) | |
1399 | log_err("ibm-1363 -> did not match.\n"); | |
1400 | ||
1401 | } | |
1402 | log_verbose("Testing Reset for ISO-2022-jp\n"); | |
1403 | { | |
1404 | static const UChar sampleText[] = { 0x4e00, 0x04e01, 0x0031, 0xd801, 0xdc01, 0x0032}; | |
1405 | ||
1406 | static const uint8_t expected[] = {0x1b, 0x24, 0x42,0x30,0x6c,0x43,0x7a,0x1b,0x28,0x42, | |
1407 | 0x31,0x1A, 0x32}; | |
1408 | ||
1409 | ||
1410 | static const int32_t offsets[] = {0,0,0,0,0,1,1,2,2,2,2,3,5 }; | |
1411 | ||
1412 | ||
1413 | static const UChar sampleText1[] = {0x4e00, 0x04e01, 0x0031,0x001A, 0x0032}; | |
1414 | static const uint8_t expected1[] = {0x1b, 0x24, 0x42,0x30,0x6c,0x43,0x7a,0x1b,0x28,0x42, | |
1415 | 0x31,0x1A, 0x32}; | |
1416 | static const int32_t offsets1[] = { 3,5,10,11,12}; | |
1417 | ||
1418 | /*iso-2022-jp*/ | |
1419 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
1420 | expected, sizeof(expected), "iso-2022-jp", UCNV_FROM_U_CALLBACK_SUBSTITUTE , NULL, TRUE)) | |
1421 | log_err("u-> not match.\n"); | |
1422 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
1423 | expected, sizeof(expected), "iso-2022-jp", UCNV_FROM_U_CALLBACK_SUBSTITUTE,offsets , TRUE)) | |
1424 | log_err("u-> not match.\n"); | |
1425 | ||
1426 | if(!testConvertToU(expected1, sizeof(expected1), | |
1427 | sampleText1, sizeof(sampleText1)/sizeof(sampleText1[0]), "iso-2022-jp",UCNV_TO_U_CALLBACK_SUBSTITUTE , | |
1428 | offsets1, TRUE)) | |
1429 | log_err("iso-2022-jp -> did not match.\n"); | |
1430 | ||
1431 | } | |
1432 | log_verbose("Testing Reset for ISO-2022-cn\n"); | |
1433 | { | |
1434 | static const UChar sampleText[] = { 0x4e00, 0x04e01, 0x0031, 0xd801, 0xdc01, 0x0032}; | |
1435 | ||
1436 | static const uint8_t expected[] = { | |
1437 | 0x1B, 0x24, 0x29, 0x41, 0x0E, 0x52, 0x3B, | |
1438 | 0x36, 0x21, | |
1439 | 0x0f, 0x31, | |
1440 | 0x1A, | |
374ca955 | 1441 | 0x32 |
b75a7d8f A |
1442 | }; |
1443 | ||
1444 | ||
1445 | static const int32_t offsets[] = { | |
1446 | 0, 0, 0, 0, 0, 0, 0, | |
1447 | 1, 1, | |
1448 | 2, 2, | |
1449 | 3, | |
374ca955 | 1450 | 5, }; |
b75a7d8f A |
1451 | |
1452 | UChar sampleText1[] = {0x4e00, 0x04e01, 0x0031,0x001A, 0x0032}; | |
1453 | static const uint8_t expected1[] = { | |
1454 | 0x1B, 0x24, 0x29, 0x41, 0x0E, 0x52, 0x3B, | |
1455 | 0x36, 0x21, | |
374ca955 | 1456 | 0x1B, 0x24, 0x29, 0x47, 0x24, 0x22, |
b75a7d8f A |
1457 | 0x0f, 0x1A, |
1458 | 0x32 | |
1459 | }; | |
374ca955 | 1460 | static const int32_t offsets1[] = { 5,7,13,16,17}; |
b75a7d8f A |
1461 | |
1462 | /*iso-2022-CN*/ | |
1463 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
1464 | expected, sizeof(expected), "iso-2022-cn", UCNV_FROM_U_CALLBACK_SUBSTITUTE , NULL, TRUE)) | |
1465 | log_err("u-> not match.\n"); | |
1466 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
1467 | expected, sizeof(expected), "iso-2022-cn", UCNV_FROM_U_CALLBACK_SUBSTITUTE,offsets , TRUE)) | |
1468 | log_err("u-> not match.\n"); | |
1469 | ||
1470 | if(!testConvertToU(expected1, sizeof(expected1), | |
1471 | sampleText1, sizeof(sampleText1)/sizeof(sampleText1[0]), "iso-2022-cn",UCNV_TO_U_CALLBACK_SUBSTITUTE , | |
1472 | offsets1, TRUE)) | |
1473 | log_err("iso-2022-cn -> did not match.\n"); | |
1474 | } | |
1475 | log_verbose("Testing Reset for ISO-2022-kr\n"); | |
1476 | { | |
1477 | UChar sampleText[] = { 0x4e00,0xd801, 0xdc01, 0x04e01, 0x0031, 0xd801, 0xdc01, 0x0032}; | |
1478 | ||
1479 | static const uint8_t expected[] = {0x1B, 0x24, 0x29, 0x43, | |
1480 | 0x0E, 0x6C, 0x69, | |
1481 | 0x0f, 0x1A, | |
1482 | 0x0e, 0x6F, 0x4B, | |
1483 | 0x0F, 0x31, | |
1484 | 0x1A, | |
1485 | 0x32 }; | |
1486 | ||
1487 | static const int32_t offsets[] = {-1, -1, -1, -1, | |
1488 | 0, 0, 0, | |
1489 | 1, 1, | |
1490 | 3, 3, 3, | |
1491 | 4, 4, | |
1492 | 5, | |
1493 | 7, | |
1494 | }; | |
1495 | static const UChar sampleText1[] = { 0x4e00,0x0041, 0x04e01, 0x0031, 0x0042, 0x0032}; | |
1496 | ||
1497 | static const uint8_t expected1[] = {0x1B, 0x24, 0x29, 0x43, | |
1498 | 0x0E, 0x6C, 0x69, | |
1499 | 0x0f, 0x41, | |
1500 | 0x0e, 0x6F, 0x4B, | |
1501 | 0x0F, 0x31, | |
1502 | 0x42, | |
1503 | 0x32 }; | |
1504 | ||
1505 | static const int32_t offsets1[] = { | |
1506 | 5, 8, 10, | |
1507 | 13, 14, 15 | |
1508 | ||
1509 | }; | |
1510 | /*iso-2022-kr*/ | |
1511 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
1512 | expected, sizeof(expected), "iso-2022-kr", UCNV_FROM_U_CALLBACK_SUBSTITUTE , NULL, TRUE)) | |
1513 | log_err("u-> iso-2022-kr [UCNV_DBCS] not match.\n"); | |
1514 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
1515 | expected, sizeof(expected), "iso-2022-kr", UCNV_FROM_U_CALLBACK_SUBSTITUTE,offsets , TRUE)) | |
1516 | log_err("u-> iso-2022-kr [UCNV_DBCS] not match.\n"); | |
1517 | if(!testConvertToU(expected1, sizeof(expected1), | |
1518 | sampleText1, sizeof(sampleText1)/sizeof(sampleText1[0]), "iso-2022-kr",UCNV_TO_U_CALLBACK_SUBSTITUTE , | |
1519 | offsets1, TRUE)) | |
1520 | log_err("iso-2022-kr -> did not match.\n"); | |
1521 | } | |
1522 | log_verbose("Testing Reset for HZ\n"); | |
1523 | { | |
1524 | static const UChar sampleText[] = { 0x4e00, 0xd801, 0xdc01, 0x04e01, 0x0031, 0xd801, 0xdc01, 0x0032}; | |
1525 | ||
1526 | static const uint8_t expected[] = {0x7E, 0x7B, 0x52, 0x3B, | |
1527 | 0x7E, 0x7D, 0x1A, | |
1528 | 0x7E, 0x7B, 0x36, 0x21, | |
1529 | 0x7E, 0x7D, 0x31, | |
1530 | 0x1A, | |
1531 | 0x32 }; | |
1532 | ||
1533 | ||
1534 | static const int32_t offsets[] = {0,0,0,0, | |
1535 | 1,1,1, | |
1536 | 3,3,3,3, | |
1537 | 4,4,4, | |
1538 | 5, | |
1539 | 7,}; | |
1540 | static const UChar sampleText1[] = { 0x4e00, 0x0035, 0x04e01, 0x0031, 0x0041, 0x0032}; | |
1541 | ||
1542 | static const uint8_t expected1[] = {0x7E, 0x7B, 0x52, 0x3B, | |
1543 | 0x7E, 0x7D, 0x35, | |
1544 | 0x7E, 0x7B, 0x36, 0x21, | |
1545 | 0x7E, 0x7D, 0x31, | |
1546 | 0x41, | |
1547 | 0x32 }; | |
1548 | ||
1549 | ||
1550 | static const int32_t offsets1[] = {2,6,9,13,14,15 | |
1551 | }; | |
1552 | ||
1553 | /*hz*/ | |
1554 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
1555 | expected, sizeof(expected), "HZ", UCNV_FROM_U_CALLBACK_SUBSTITUTE,NULL , TRUE)) | |
1556 | log_err("u-> not match.\n"); | |
1557 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
1558 | expected, sizeof(expected), "HZ", UCNV_FROM_U_CALLBACK_SUBSTITUTE,offsets , TRUE)) | |
1559 | log_err("u-> not match.\n"); | |
1560 | if(!testConvertToU(expected1, sizeof(expected1), | |
1561 | sampleText1, sizeof(sampleText1)/sizeof(sampleText1[0]), "hz",UCNV_TO_U_CALLBACK_SUBSTITUTE , | |
1562 | offsets1, TRUE)) | |
1563 | log_err("hz -> did not match.\n"); | |
1564 | } | |
1565 | /*UTF-8*/ | |
1566 | log_verbose("Testing for UTF8\n"); | |
1567 | { | |
1568 | static const UChar sampleText[] = { 0x4e00, 0x0701, 0x0031, 0xbfc1, 0xd801, 0xdc01, 0x0032}; | |
1569 | int32_t offsets[]={0x00, 0x00, 0x00, 0x01, 0x01, 0x02, | |
1570 | 0x03, 0x03, 0x03, 0x04, 0x04, 0x04, | |
1571 | 0x04, 0x06 }; | |
1572 | static const uint8_t expected[] = {0xe4, 0xb8, 0x80, 0xdc, 0x81, 0x31, | |
1573 | 0xeb, 0xbf, 0x81, 0xF0, 0x90, 0x90, 0x81, 0x32}; | |
1574 | ||
1575 | ||
1576 | static const int32_t fromOffsets[] = { 0x0000, 0x0003, 0x0005, 0x0006, 0x0009, 0x0009, 0x000D }; | |
1577 | /*UTF-8*/ | |
1578 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
1579 | expected, sizeof(expected), "UTF8", UCNV_FROM_U_CALLBACK_SUBSTITUTE,offsets , TRUE)) | |
1580 | log_err("u-> UTF8 with offsets and flush true did not match.\n"); | |
1581 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
1582 | expected, sizeof(expected), "UTF8", UCNV_FROM_U_CALLBACK_SUBSTITUTE,NULL , TRUE)) | |
1583 | log_err("u-> UTF8 with offsets and flush true did not match.\n"); | |
1584 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
1585 | expected, sizeof(expected), "UTF8", UCNV_FROM_U_CALLBACK_SUBSTITUTE,offsets , TRUE)) | |
1586 | log_err("u-> UTF8 with offsets and flush true did not match.\n"); | |
1587 | if(!testConvertFromU(sampleText, sizeof(sampleText)/sizeof(sampleText[0]), | |
1588 | expected, sizeof(expected), "UTF8", UCNV_FROM_U_CALLBACK_SUBSTITUTE,NULL , TRUE)) | |
1589 | log_err("u-> UTF8 with offsets and flush true did not match.\n"); | |
1590 | if(!testConvertToU(expected, sizeof(expected), | |
1591 | sampleText, sizeof(sampleText)/sizeof(sampleText[0]), "UTF8",UCNV_TO_U_CALLBACK_SUBSTITUTE , NULL, TRUE)) | |
1592 | log_err("UTF8 -> did not match.\n"); | |
1593 | if(!testConvertToU(expected, sizeof(expected), | |
1594 | sampleText, sizeof(sampleText)/sizeof(sampleText[0]), "UTF8", UCNV_TO_U_CALLBACK_SUBSTITUTE , NULL, TRUE)) | |
1595 | log_err("UTF8 -> did not match.\n"); | |
1596 | if(!testConvertToU(expected, sizeof(expected), | |
1597 | sampleText, sizeof(sampleText)/sizeof(sampleText[0]), "UTF8",UCNV_TO_U_CALLBACK_SUBSTITUTE , fromOffsets, TRUE)) | |
1598 | log_err("UTF8 -> did not match.\n"); | |
1599 | if(!testConvertToU(expected, sizeof(expected), | |
1600 | sampleText, sizeof(sampleText)/sizeof(sampleText[0]), "UTF8", UCNV_TO_U_CALLBACK_SUBSTITUTE , fromOffsets, TRUE)) | |
1601 | log_err("UTF8 -> did not match.\n"); | |
1602 | ||
1603 | } | |
1604 | ||
1605 | } | |
1606 | ||
1607 | /* Test that U_TRUNCATED_CHAR_FOUND is set. */ | |
1608 | static void | |
1609 | doTestTruncated(const char *cnvName, const uint8_t *bytes, int32_t length) { | |
1610 | UConverter *cnv; | |
1611 | ||
1612 | UChar buffer[2]; | |
1613 | UChar *target, *targetLimit; | |
1614 | const char *source, *sourceLimit; | |
1615 | ||
1616 | UErrorCode errorCode; | |
1617 | ||
1618 | errorCode=U_ZERO_ERROR; | |
1619 | cnv=ucnv_open(cnvName, &errorCode); | |
1620 | if(U_FAILURE(errorCode)) { | |
1621 | log_data_err("error TestTruncated: unable to open \"%s\" - %s\n", cnvName, u_errorName(errorCode)); | |
1622 | return; | |
1623 | } | |
374ca955 A |
1624 | ucnv_setToUCallBack(cnv, UCNV_TO_U_CALLBACK_STOP, NULL, NULL, NULL, &errorCode); |
1625 | if(U_FAILURE(errorCode)) { | |
1626 | log_data_err("error TestTruncated: unable to set the stop callback on \"%s\" - %s\n", | |
1627 | cnvName, u_errorName(errorCode)); | |
1628 | ucnv_close(cnv); | |
1629 | return; | |
1630 | } | |
b75a7d8f A |
1631 | |
1632 | source=(const char *)bytes; | |
1633 | sourceLimit=source+length; | |
1634 | target=buffer; | |
1635 | targetLimit=buffer+LENGTHOF(buffer); | |
1636 | ||
1637 | /* 1. input bytes with flush=FALSE, then input nothing with flush=TRUE */ | |
1638 | ucnv_toUnicode(cnv, &target, targetLimit, &source, sourceLimit, NULL, FALSE, &errorCode); | |
1639 | if(U_FAILURE(errorCode) || source!=sourceLimit || target!=buffer) { | |
1640 | log_err("error TestTruncated(%s, 1a): input bytes[%d], flush=FALSE: %s, input left %d, output %d\n", | |
1641 | cnvName, length, u_errorName(errorCode), (int)(sourceLimit-source), (int)(target-buffer)); | |
1642 | } | |
1643 | ||
1644 | errorCode=U_ZERO_ERROR; | |
1645 | source=sourceLimit; | |
1646 | target=buffer; | |
1647 | ucnv_toUnicode(cnv, &target, targetLimit, &source, sourceLimit, NULL, TRUE, &errorCode); | |
1648 | if(errorCode!=U_TRUNCATED_CHAR_FOUND || target!=buffer) { | |
374ca955 A |
1649 | log_err("error TestTruncated(%s, 1b): no input (previously %d), flush=TRUE: %s (should be U_TRUNCATED_CHAR_FOUND), output %d\n", |
1650 | cnvName, (int)length, u_errorName(errorCode), (int)(target-buffer)); | |
b75a7d8f A |
1651 | } |
1652 | ||
b75a7d8f A |
1653 | /* 2. input bytes with flush=TRUE */ |
1654 | ucnv_resetToUnicode(cnv); | |
1655 | ||
1656 | errorCode=U_ZERO_ERROR; | |
1657 | source=(const char *)bytes; | |
1658 | target=buffer; | |
1659 | ucnv_toUnicode(cnv, &target, targetLimit, &source, sourceLimit, NULL, TRUE, &errorCode); | |
374ca955 | 1660 | if(errorCode!=U_TRUNCATED_CHAR_FOUND || source!=sourceLimit || target!=buffer) { |
b75a7d8f A |
1661 | log_err("error TestTruncated(%s, 2): input bytes[%d], flush=TRUE: %s (should be U_TRUNCATED_CHAR_FOUND), input left %d, output %d\n", |
1662 | cnvName, length, u_errorName(errorCode), (int)(sourceLimit-source), (int)(target-buffer)); | |
1663 | } | |
1664 | ||
1665 | ||
1666 | ucnv_close(cnv); | |
1667 | } | |
1668 | ||
1669 | static void | |
1670 | TestTruncated() { | |
1671 | static const struct { | |
1672 | const char *cnvName; | |
1673 | uint8_t bytes[8]; /* partial input bytes resulting in no output */ | |
1674 | int32_t length; | |
1675 | } testCases[]={ | |
1676 | { "IMAP-mailbox-name", { 0x26 }, 1 }, /* & */ | |
1677 | { "IMAP-mailbox-name", { 0x26, 0x42 }, 2 }, /* &B */ | |
1678 | { "IMAP-mailbox-name", { 0x26, 0x42, 0x42 }, 3 }, /* &BB */ | |
1679 | { "IMAP-mailbox-name", { 0x26, 0x41, 0x41 }, 3 }, /* &AA */ | |
1680 | ||
1681 | { "UTF-7", { 0x2b, 0x42 }, 2 }, /* +B */ | |
1682 | { "UTF-8", { 0xd1 }, 1 }, | |
1683 | ||
1684 | { "UTF-16BE", { 0x4e }, 1 }, | |
1685 | { "UTF-16LE", { 0x4e }, 1 }, | |
1686 | { "UTF-16", { 0x4e }, 1 }, | |
1687 | { "UTF-16", { 0xff }, 1 }, | |
1688 | { "UTF-16", { 0xfe, 0xff, 0x4e }, 3 }, | |
1689 | ||
1690 | { "UTF-32BE", { 0, 0, 0x4e }, 3 }, | |
1691 | { "UTF-32LE", { 0x4e }, 1 }, | |
1692 | { "UTF-32", { 0, 0, 0x4e }, 3 }, | |
1693 | { "UTF-32", { 0xff }, 1 }, | |
1694 | { "UTF-32", { 0, 0, 0xfe, 0xff, 0 }, 5 }, | |
1695 | ||
1696 | { "SCSU", { 0x0e, 0x4e }, 2 }, /* SQU 0x4e */ | |
1697 | { "BOCU-1", { 0xd5 }, 1 }, | |
1698 | ||
1699 | { "Shift-JIS", { 0xe0 }, 1 }, | |
1700 | ||
1701 | { "ibm-939", { 0x0e, 0x41 }, 2 } /* SO 0x41 */ | |
1702 | }; | |
1703 | int32_t i; | |
1704 | ||
1705 | for(i=0; i<LENGTHOF(testCases); ++i) { | |
1706 | doTestTruncated(testCases[i].cnvName, testCases[i].bytes, testCases[i].length); | |
1707 | } | |
1708 | } | |
1709 | ||
1710 | typedef struct NameRange { | |
1711 | const char *name; | |
1712 | UChar32 start, end, start2, end2, notStart, notEnd; | |
1713 | } NameRange; | |
1714 | ||
1715 | static void | |
1716 | TestUnicodeSet() { | |
1717 | UErrorCode errorCode; | |
1718 | UConverter *cnv; | |
1719 | USet *set; | |
1720 | const char *name; | |
1721 | int32_t i, count; | |
1722 | ||
1723 | static const char *const completeSetNames[]={ | |
1724 | "UTF-7", | |
1725 | "UTF-8", | |
1726 | "UTF-16", | |
1727 | "UTF-16BE", | |
1728 | "UTF-16LE", | |
1729 | "UTF-32", | |
1730 | "UTF-32BE", | |
1731 | "UTF-32LE", | |
1732 | "SCSU", | |
1733 | "BOCU-1", | |
1734 | "CESU-8", | |
1735 | "gb18030", | |
374ca955 A |
1736 | "IMAP-mailbox-name" |
1737 | }; | |
1738 | ||
1739 | static const char *const lmbcsNames[]={ | |
b75a7d8f A |
1740 | "LMBCS-1", |
1741 | "LMBCS-2", | |
1742 | "LMBCS-3", | |
1743 | "LMBCS-4", | |
1744 | "LMBCS-5", | |
1745 | "LMBCS-6", | |
1746 | "LMBCS-8", | |
1747 | "LMBCS-11", | |
1748 | "LMBCS-16", | |
1749 | "LMBCS-17", | |
1750 | "LMBCS-18", | |
1751 | "LMBCS-19" | |
1752 | }; | |
1753 | ||
1754 | static const NameRange nameRanges[]={ | |
1755 | { "US-ASCII", 0, 0x7f, -1, -1, 0x80, 0x10ffff }, | |
1756 | { "ibm-367", 0, 0x7f, -1, -1, 0x80, 0x10ffff }, | |
1757 | { "ISO-8859-1", 0, 0x7f, -1, -1, 0x100, 0x10ffff }, | |
1758 | { "UTF-8", 0, 0xd7ff, 0xe000, 0x10ffff, 0xd800, 0xdfff }, | |
1759 | { "windows-1251", 0, 0x7f, 0x410, 0x44f, 0x3000, 0xd7ff }, | |
1760 | { "HZ", 0x410, 0x44f, 0x4e00, 0x4eff, 0xac00, 0xd7ff }, | |
1761 | { "shift-jis", 0x3041, 0x3093, 0x30a1, 0x30f3, 0x900, 0x1cff } | |
1762 | }; | |
1763 | ||
1764 | /* open an empty set */ | |
1765 | set=uset_open(1, 0); | |
1766 | ||
1767 | count=ucnv_countAvailable(); | |
1768 | for(i=0; i<count; ++i) { | |
1769 | errorCode=U_ZERO_ERROR; | |
1770 | name=ucnv_getAvailableName(i); | |
1771 | cnv=ucnv_open(name, &errorCode); | |
1772 | if(U_FAILURE(errorCode)) { | |
1773 | log_err("error: unable to open converter %s - %s\n", | |
1774 | name, u_errorName(errorCode)); | |
1775 | continue; | |
1776 | } | |
1777 | ||
1778 | uset_clear(set); | |
1779 | ucnv_getUnicodeSet(cnv, set, UCNV_ROUNDTRIP_SET, &errorCode); | |
1780 | if(U_FAILURE(errorCode)) { | |
1781 | log_err("error: ucnv_getUnicodeSet(%s) failed - %s\n", | |
1782 | name, u_errorName(errorCode)); | |
1783 | } else if(uset_size(set)==0) { | |
1784 | log_err("error: ucnv_getUnicodeSet(%s) returns an empty set\n", name); | |
1785 | } | |
1786 | ||
1787 | ucnv_close(cnv); | |
1788 | } | |
1789 | ||
1790 | /* test converters that are known to convert all of Unicode (except maybe for surrogates) */ | |
1791 | for(i=0; i<LENGTHOF(completeSetNames); ++i) { | |
1792 | errorCode=U_ZERO_ERROR; | |
1793 | name=completeSetNames[i]; | |
1794 | cnv=ucnv_open(name, &errorCode); | |
1795 | if(U_FAILURE(errorCode)) { | |
1796 | log_err("error: unable to open converter %s - %s\n", | |
1797 | name, u_errorName(errorCode)); | |
1798 | continue; | |
1799 | } | |
1800 | ||
1801 | uset_clear(set); | |
1802 | ucnv_getUnicodeSet(cnv, set, UCNV_ROUNDTRIP_SET, &errorCode); | |
1803 | if(U_FAILURE(errorCode)) { | |
1804 | log_err("error: ucnv_getUnicodeSet(%s) failed - %s\n", | |
1805 | name, u_errorName(errorCode)); | |
1806 | } else if(!uset_containsRange(set, 0, 0xd7ff) || !uset_containsRange(set, 0xe000, 0x10ffff)) { | |
1807 | log_err("error: ucnv_getUnicodeSet(%s) does not return an all-Unicode set\n", name); | |
1808 | } | |
1809 | ||
1810 | ucnv_close(cnv); | |
1811 | } | |
1812 | ||
374ca955 A |
1813 | /* test LMBCS variants which convert all of Unicode except for U+F6xx */ |
1814 | for(i=0; i<LENGTHOF(lmbcsNames); ++i) { | |
1815 | errorCode=U_ZERO_ERROR; | |
1816 | name=lmbcsNames[i]; | |
1817 | cnv=ucnv_open(name, &errorCode); | |
1818 | if(U_FAILURE(errorCode)) { | |
1819 | log_err("error: unable to open converter %s - %s\n", | |
1820 | name, u_errorName(errorCode)); | |
1821 | continue; | |
1822 | } | |
1823 | ||
1824 | uset_clear(set); | |
1825 | ucnv_getUnicodeSet(cnv, set, UCNV_ROUNDTRIP_SET, &errorCode); | |
1826 | if(U_FAILURE(errorCode)) { | |
1827 | log_err("error: ucnv_getUnicodeSet(%s) failed - %s\n", | |
1828 | name, u_errorName(errorCode)); | |
1829 | } else if(!uset_containsRange(set, 0, 0xf5ff) || !uset_containsRange(set, 0xf700, 0x10ffff)) { | |
1830 | log_err("error: ucnv_getUnicodeSet(%s) does not return an all-Unicode set (minus U+F6xx)\n", name); | |
1831 | } | |
1832 | ||
1833 | ucnv_close(cnv); | |
1834 | } | |
1835 | ||
b75a7d8f A |
1836 | /* test specific sets */ |
1837 | for(i=0; i<LENGTHOF(nameRanges); ++i) { | |
1838 | errorCode=U_ZERO_ERROR; | |
1839 | name=nameRanges[i].name; | |
1840 | cnv=ucnv_open(name, &errorCode); | |
1841 | if(U_FAILURE(errorCode)) { | |
1842 | log_data_err("error: unable to open converter %s - %s\n", | |
1843 | name, u_errorName(errorCode)); | |
1844 | continue; | |
1845 | } | |
1846 | ||
1847 | uset_clear(set); | |
1848 | ucnv_getUnicodeSet(cnv, set, UCNV_ROUNDTRIP_SET, &errorCode); | |
1849 | if(U_FAILURE(errorCode)) { | |
1850 | log_err("error: ucnv_getUnicodeSet(%s) failed - %s\n", | |
1851 | name, u_errorName(errorCode)); | |
1852 | } else if( | |
1853 | !uset_containsRange(set, nameRanges[i].start, nameRanges[i].end) || | |
1854 | (nameRanges[i].start2>=0 && !uset_containsRange(set, nameRanges[i].start2, nameRanges[i].end2)) | |
1855 | ) { | |
1856 | log_err("error: ucnv_getUnicodeSet(%s) does not contain the expected ranges\n", name); | |
1857 | } else if(nameRanges[i].notStart>=0) { | |
1858 | /* simulate containsAny() with the C API */ | |
1859 | uset_complement(set); | |
1860 | if(!uset_containsRange(set, nameRanges[i].notStart, nameRanges[i].notEnd)) { | |
1861 | log_err("error: ucnv_getUnicodeSet(%s) contains part of the unexpected range\n", name); | |
1862 | } | |
1863 | } | |
1864 | ||
1865 | ucnv_close(cnv); | |
1866 | } | |
1867 | ||
1868 | uset_close(set); | |
1869 | } |