/src/icu/source/common/ucnvisci.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 | | * Copyright (C) 2000-2016, International Business Machines |
6 | | * Corporation and others. All Rights Reserved. |
7 | | ********************************************************************** |
8 | | * file name: ucnvisci.c |
9 | | * encoding: UTF-8 |
10 | | * tab size: 8 (not used) |
11 | | * indentation:4 |
12 | | * |
13 | | * created on: 2001JUN26 |
14 | | * created by: Ram Viswanadha |
15 | | * |
16 | | * Date Name Description |
17 | | * 24/7/2001 Ram Added support for EXT character handling |
18 | | */ |
19 | | |
20 | | #include "unicode/utypes.h" |
21 | | |
22 | | #if !UCONFIG_NO_CONVERSION && !UCONFIG_NO_LEGACY_CONVERSION && !UCONFIG_ONLY_HTML_CONVERSION |
23 | | |
24 | | #include "unicode/ucnv.h" |
25 | | #include "unicode/ucnv_cb.h" |
26 | | #include "unicode/utf16.h" |
27 | | #include "cmemory.h" |
28 | | #include "ucnv_bld.h" |
29 | | #include "ucnv_cnv.h" |
30 | | #include "cstring.h" |
31 | | #include "uassert.h" |
32 | | |
33 | 0 | #define UCNV_OPTIONS_VERSION_MASK 0xf |
34 | | #define NUKTA 0x093c |
35 | | #define HALANT 0x094d |
36 | 0 | #define ZWNJ 0x200c /* Zero Width Non Joiner */ |
37 | 0 | #define ZWJ 0x200d /* Zero width Joiner */ |
38 | | #define INVALID_CHAR 0xffff |
39 | 0 | #define ATR 0xEF /* Attribute code */ |
40 | 0 | #define EXT 0xF0 /* Extension code */ |
41 | 0 | #define DANDA 0x0964 |
42 | 0 | #define DOUBLE_DANDA 0x0965 |
43 | 0 | #define ISCII_NUKTA 0xE9 |
44 | 0 | #define ISCII_HALANT 0xE8 |
45 | 0 | #define ISCII_DANDA 0xEA |
46 | 0 | #define ISCII_INV 0xD9 |
47 | 0 | #define ISCII_VOWEL_SIGN_E 0xE0 |
48 | 0 | #define INDIC_BLOCK_BEGIN 0x0900 |
49 | 0 | #define INDIC_BLOCK_END 0x0D7F |
50 | 0 | #define INDIC_RANGE (INDIC_BLOCK_END - INDIC_BLOCK_BEGIN) |
51 | 0 | #define VOCALLIC_RR 0x0931 |
52 | 0 | #define LF 0x0A |
53 | 0 | #define ASCII_END 0xA0 |
54 | 0 | #define NO_CHAR_MARKER 0xFFFE |
55 | 0 | #define TELUGU_DELTA DELTA * TELUGU |
56 | 0 | #define DEV_ABBR_SIGN 0x0970 |
57 | 0 | #define DEV_ANUDATTA 0x0952 |
58 | 0 | #define EXT_RANGE_BEGIN 0xA1 |
59 | 0 | #define EXT_RANGE_END 0xEE |
60 | | |
61 | 0 | #define PNJ_DELTA 0x0100 |
62 | 0 | #define PNJ_BINDI 0x0A02 |
63 | 0 | #define PNJ_TIPPI 0x0A70 |
64 | 0 | #define PNJ_SIGN_VIRAMA 0x0A4D |
65 | 0 | #define PNJ_ADHAK 0x0A71 |
66 | 0 | #define PNJ_HA 0x0A39 |
67 | 0 | #define PNJ_RRA 0x0A5C |
68 | | |
69 | | typedef enum { |
70 | | DEVANAGARI =0, |
71 | | BENGALI, |
72 | | GURMUKHI, |
73 | | GUJARATI, |
74 | | ORIYA, |
75 | | TAMIL, |
76 | | TELUGU, |
77 | | KANNADA, |
78 | | MALAYALAM, |
79 | | DELTA=0x80 |
80 | | }UniLang; |
81 | | |
82 | | /** |
83 | | * Enumeration for switching code pages if <ATR>+<one of below values> |
84 | | * is encountered |
85 | | */ |
86 | | typedef enum { |
87 | | DEF = 0x40, |
88 | | RMN = 0x41, |
89 | | DEV = 0x42, |
90 | | BNG = 0x43, |
91 | | TML = 0x44, |
92 | | TLG = 0x45, |
93 | | ASM = 0x46, |
94 | | ORI = 0x47, |
95 | | KND = 0x48, |
96 | | MLM = 0x49, |
97 | | GJR = 0x4A, |
98 | | PNJ = 0x4B, |
99 | | ARB = 0x71, |
100 | | PES = 0x72, |
101 | | URD = 0x73, |
102 | | SND = 0x74, |
103 | | KSM = 0x75, |
104 | | PST = 0x76 |
105 | | }ISCIILang; |
106 | | |
107 | | typedef enum { |
108 | | DEV_MASK =0x80, |
109 | | PNJ_MASK =0x40, |
110 | | GJR_MASK =0x20, |
111 | | ORI_MASK =0x10, |
112 | | BNG_MASK =0x08, |
113 | | KND_MASK =0x04, |
114 | | MLM_MASK =0x02, |
115 | | TML_MASK =0x01, |
116 | | ZERO =0x00 |
117 | | }MaskEnum; |
118 | | |
119 | | #define ISCII_CNV_PREFIX "ISCII,version=" |
120 | | |
121 | | typedef struct { |
122 | | UChar contextCharToUnicode; /* previous Unicode codepoint for contextual analysis */ |
123 | | UChar contextCharFromUnicode; /* previous Unicode codepoint for contextual analysis */ |
124 | | uint16_t defDeltaToUnicode; /* delta for switching to default state when DEF is encountered */ |
125 | | uint16_t currentDeltaFromUnicode; /* current delta in Indic block */ |
126 | | uint16_t currentDeltaToUnicode; /* current delta in Indic block */ |
127 | | MaskEnum currentMaskFromUnicode; /* mask for current state in toUnicode */ |
128 | | MaskEnum currentMaskToUnicode; /* mask for current state in toUnicode */ |
129 | | MaskEnum defMaskToUnicode; /* mask for default state in toUnicode */ |
130 | | UBool isFirstBuffer; /* boolean for fromUnicode to see if we need to announce the first script */ |
131 | | UBool resetToDefaultToUnicode; /* boolean for resetting to default delta and mask when a newline is encountered*/ |
132 | | char name[sizeof(ISCII_CNV_PREFIX) + 1]; |
133 | | UChar32 prevToUnicodeStatus; /* Hold the previous toUnicodeStatus. This is necessary because we may need to know the last two code points. */ |
134 | | } UConverterDataISCII; |
135 | | |
136 | | typedef struct LookupDataStruct { |
137 | | UniLang uniLang; |
138 | | MaskEnum maskEnum; |
139 | | ISCIILang isciiLang; |
140 | | } LookupDataStruct; |
141 | | |
142 | | static const LookupDataStruct lookupInitialData[]={ |
143 | | { DEVANAGARI, DEV_MASK, DEV }, |
144 | | { BENGALI, BNG_MASK, BNG }, |
145 | | { GURMUKHI, PNJ_MASK, PNJ }, |
146 | | { GUJARATI, GJR_MASK, GJR }, |
147 | | { ORIYA, ORI_MASK, ORI }, |
148 | | { TAMIL, TML_MASK, TML }, |
149 | | { TELUGU, KND_MASK, TLG }, |
150 | | { KANNADA, KND_MASK, KND }, |
151 | | { MALAYALAM, MLM_MASK, MLM } |
152 | | }; |
153 | | |
154 | | /* |
155 | | * For special handling of certain Gurmukhi characters. |
156 | | * Bit 0 (value 1): PNJ consonant |
157 | | * Bit 1 (value 2): PNJ Bindi Tippi |
158 | | */ |
159 | | static const uint8_t pnjMap[80] = { |
160 | | /* 0A00..0A0F */ |
161 | | 0, 0, 0, 0, 0, 2, 0, 2, 0, 0, 0, 0, 0, 0, 0, 0, |
162 | | /* 0A10..0A1F */ |
163 | | 0, 0, 0, 0, 0, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, |
164 | | /* 0A20..0A2F */ |
165 | | 3, 3, 3, 3, 3, 3, 3, 3, 3, 0, 3, 3, 3, 3, 3, 3, |
166 | | /* 0A30..0A3F */ |
167 | | 3, 0, 0, 0, 0, 3, 3, 0, 3, 3, 0, 0, 0, 0, 0, 2, |
168 | | /* 0A40..0A4F */ |
169 | | 0, 2, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0 |
170 | | }; |
171 | | |
172 | | static UBool |
173 | 0 | isPNJConsonant(UChar32 c) { |
174 | 0 | if (c < 0xa00 || 0xa50 <= c) { |
175 | 0 | return FALSE; |
176 | 0 | } else { |
177 | 0 | return (UBool)(pnjMap[c - 0xa00] & 1); |
178 | 0 | } |
179 | 0 | } |
180 | | |
181 | | static UBool |
182 | 0 | isPNJBindiTippi(UChar32 c) { |
183 | 0 | if (c < 0xa00 || 0xa50 <= c) { |
184 | 0 | return FALSE; |
185 | 0 | } else { |
186 | 0 | return (UBool)(pnjMap[c - 0xa00] >> 1); |
187 | 0 | } |
188 | 0 | } |
189 | | U_CDECL_BEGIN |
190 | | static void U_CALLCONV |
191 | 0 | _ISCIIOpen(UConverter *cnv, UConverterLoadArgs *pArgs, UErrorCode *errorCode) { |
192 | 0 | if(pArgs->onlyTestIsLoadable) { |
193 | 0 | return; |
194 | 0 | } |
195 | | |
196 | 0 | cnv->extraInfo = uprv_malloc(sizeof(UConverterDataISCII)); |
197 | |
|
198 | 0 | if (cnv->extraInfo != NULL) { |
199 | 0 | int32_t len=0; |
200 | 0 | UConverterDataISCII *converterData= |
201 | 0 | (UConverterDataISCII *) cnv->extraInfo; |
202 | 0 | converterData->contextCharToUnicode=NO_CHAR_MARKER; |
203 | 0 | cnv->toUnicodeStatus = missingCharMarker; |
204 | 0 | converterData->contextCharFromUnicode=0x0000; |
205 | 0 | converterData->resetToDefaultToUnicode=FALSE; |
206 | | /* check if the version requested is supported */ |
207 | 0 | if ((pArgs->options & UCNV_OPTIONS_VERSION_MASK) < 9) { |
208 | | /* initialize state variables */ |
209 | 0 | converterData->currentDeltaFromUnicode |
210 | 0 | = converterData->currentDeltaToUnicode |
211 | 0 | = converterData->defDeltaToUnicode = (uint16_t)(lookupInitialData[pArgs->options & UCNV_OPTIONS_VERSION_MASK].uniLang * DELTA); |
212 | |
|
213 | 0 | converterData->currentMaskFromUnicode |
214 | 0 | = converterData->currentMaskToUnicode |
215 | 0 | = converterData->defMaskToUnicode = lookupInitialData[pArgs->options & UCNV_OPTIONS_VERSION_MASK].maskEnum; |
216 | | |
217 | 0 | converterData->isFirstBuffer=TRUE; |
218 | 0 | (void)uprv_strcpy(converterData->name, ISCII_CNV_PREFIX); |
219 | 0 | len = (int32_t)uprv_strlen(converterData->name); |
220 | 0 | converterData->name[len]= (char)((pArgs->options & UCNV_OPTIONS_VERSION_MASK) + '0'); |
221 | 0 | converterData->name[len+1]=0; |
222 | | |
223 | 0 | converterData->prevToUnicodeStatus = 0x0000; |
224 | 0 | } else { |
225 | 0 | uprv_free(cnv->extraInfo); |
226 | 0 | cnv->extraInfo = NULL; |
227 | 0 | *errorCode = U_ILLEGAL_ARGUMENT_ERROR; |
228 | 0 | } |
229 | |
|
230 | 0 | } else { |
231 | 0 | *errorCode =U_MEMORY_ALLOCATION_ERROR; |
232 | 0 | } |
233 | 0 | } |
234 | | |
235 | | static void U_CALLCONV |
236 | 0 | _ISCIIClose(UConverter *cnv) { |
237 | 0 | if (cnv->extraInfo!=NULL) { |
238 | 0 | if (!cnv->isExtraLocal) { |
239 | 0 | uprv_free(cnv->extraInfo); |
240 | 0 | } |
241 | 0 | cnv->extraInfo=NULL; |
242 | 0 | } |
243 | 0 | } |
244 | | |
245 | | static const char* U_CALLCONV |
246 | 0 | _ISCIIgetName(const UConverter* cnv) { |
247 | 0 | if (cnv->extraInfo) { |
248 | 0 | UConverterDataISCII* myData= (UConverterDataISCII*)cnv->extraInfo; |
249 | 0 | return myData->name; |
250 | 0 | } |
251 | 0 | return NULL; |
252 | 0 | } |
253 | | |
254 | | static void U_CALLCONV |
255 | 0 | _ISCIIReset(UConverter *cnv, UConverterResetChoice choice) { |
256 | 0 | UConverterDataISCII* data =(UConverterDataISCII *) (cnv->extraInfo); |
257 | 0 | if (choice<=UCNV_RESET_TO_UNICODE) { |
258 | 0 | cnv->toUnicodeStatus = missingCharMarker; |
259 | 0 | cnv->mode=0; |
260 | 0 | data->currentDeltaToUnicode=data->defDeltaToUnicode; |
261 | 0 | data->currentMaskToUnicode = data->defMaskToUnicode; |
262 | 0 | data->contextCharToUnicode=NO_CHAR_MARKER; |
263 | 0 | data->prevToUnicodeStatus = 0x0000; |
264 | 0 | } |
265 | 0 | if (choice!=UCNV_RESET_TO_UNICODE) { |
266 | 0 | cnv->fromUChar32=0x0000; |
267 | 0 | data->contextCharFromUnicode=0x00; |
268 | 0 | data->currentMaskFromUnicode=data->defMaskToUnicode; |
269 | 0 | data->currentDeltaFromUnicode=data->defDeltaToUnicode; |
270 | 0 | data->isFirstBuffer=TRUE; |
271 | 0 | data->resetToDefaultToUnicode=FALSE; |
272 | 0 | } |
273 | 0 | } |
274 | | |
275 | | /** |
276 | | * The values in validity table are indexed by the lower bits of Unicode |
277 | | * range 0x0900 - 0x09ff. The values have a structure like: |
278 | | * --------------------------------------------------------------- |
279 | | * | DEV | PNJ | GJR | ORI | BNG | TLG | MLM | TML | |
280 | | * | | | | | ASM | KND | | | |
281 | | * --------------------------------------------------------------- |
282 | | * If a code point is valid in a particular script |
283 | | * then that bit is turned on |
284 | | * |
285 | | * Unicode does not distinguish between Bengali and Assamese so we use 1 bit for |
286 | | * to represent these languages |
287 | | * |
288 | | * Telugu and Kannada have same codepoints except for Vocallic_RR which we special case |
289 | | * and combine and use 1 bit to represent these languages. |
290 | | * |
291 | | * TODO: It is probably easier to understand and maintain to change this |
292 | | * to use uint16_t and give each of the 9 Unicode/script blocks its own bit. |
293 | | */ |
294 | | |
295 | | static const uint8_t validityTable[128] = { |
296 | | /* This state table is tool generated please do not edit unless you know exactly what you are doing */ |
297 | | /* Note: This table was edited to mirror the Windows XP implementation */ |
298 | | /*ISCII:Valid:Unicode */ |
299 | | /*0xa0 : 0x00: 0x900 */ ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
300 | | /*0xa1 : 0xb8: 0x901 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + ZERO + ZERO + ZERO , |
301 | | /*0xa2 : 0xfe: 0x902 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
302 | | /*0xa3 : 0xbf: 0x903 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
303 | | /*0x00 : 0x00: 0x904 */ DEV_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
304 | | /*0xa4 : 0xff: 0x905 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
305 | | /*0xa5 : 0xff: 0x906 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
306 | | /*0xa6 : 0xff: 0x907 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
307 | | /*0xa7 : 0xff: 0x908 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
308 | | /*0xa8 : 0xff: 0x909 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
309 | | /*0xa9 : 0xff: 0x90a */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
310 | | /*0xaa : 0xfe: 0x90b */ DEV_MASK + ZERO + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
311 | | /*0x00 : 0x00: 0x90c */ DEV_MASK + ZERO + ZERO + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
312 | | /*0xae : 0x80: 0x90d */ DEV_MASK + ZERO + GJR_MASK + ZERO + ZERO + ZERO + ZERO + ZERO , |
313 | | /*0xab : 0x87: 0x90e */ DEV_MASK + ZERO + ZERO + ZERO + ZERO + KND_MASK + MLM_MASK + TML_MASK , |
314 | | /*0xac : 0xff: 0x90f */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
315 | | /*0xad : 0xff: 0x910 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
316 | | /*0xb2 : 0x80: 0x911 */ DEV_MASK + ZERO + GJR_MASK + ZERO + ZERO + ZERO + ZERO + ZERO , |
317 | | /*0xaf : 0x87: 0x912 */ DEV_MASK + ZERO + ZERO + ZERO + ZERO + KND_MASK + MLM_MASK + TML_MASK , |
318 | | /*0xb0 : 0xff: 0x913 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
319 | | /*0xb1 : 0xff: 0x914 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
320 | | /*0xb3 : 0xff: 0x915 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
321 | | /*0xb4 : 0xfe: 0x916 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
322 | | /*0xb5 : 0xfe: 0x917 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
323 | | /*0xb6 : 0xfe: 0x918 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
324 | | /*0xb7 : 0xff: 0x919 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
325 | | /*0xb8 : 0xff: 0x91a */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
326 | | /*0xb9 : 0xfe: 0x91b */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
327 | | /*0xba : 0xff: 0x91c */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
328 | | /*0xbb : 0xfe: 0x91d */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
329 | | /*0xbc : 0xff: 0x91e */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
330 | | /*0xbd : 0xff: 0x91f */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
331 | | /*0xbe : 0xfe: 0x920 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
332 | | /*0xbf : 0xfe: 0x921 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
333 | | /*0xc0 : 0xfe: 0x922 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
334 | | /*0xc1 : 0xff: 0x923 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
335 | | /*0xc2 : 0xff: 0x924 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
336 | | /*0xc3 : 0xfe: 0x925 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
337 | | /*0xc4 : 0xfe: 0x926 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
338 | | /*0xc5 : 0xfe: 0x927 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
339 | | /*0xc6 : 0xff: 0x928 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
340 | | /*0xc7 : 0x81: 0x929 */ DEV_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + TML_MASK , |
341 | | /*0xc8 : 0xff: 0x92a */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
342 | | /*0xc9 : 0xfe: 0x92b */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
343 | | /*0xca : 0xfe: 0x92c */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
344 | | /*0xcb : 0xfe: 0x92d */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
345 | | /*0xcc : 0xfe: 0x92e */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
346 | | /*0xcd : 0xff: 0x92f */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
347 | | /*0xcf : 0xff: 0x930 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
348 | | /*0xd0 : 0x87: 0x931 */ DEV_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + MLM_MASK + TML_MASK , |
349 | | /*0xd1 : 0xff: 0x932 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
350 | | /*0xd2 : 0xb7: 0x933 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + ZERO + KND_MASK + MLM_MASK + TML_MASK , |
351 | | /*0xd3 : 0x83: 0x934 */ DEV_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + MLM_MASK + TML_MASK , |
352 | | /*0xd4 : 0xff: 0x935 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + ZERO + KND_MASK + MLM_MASK + TML_MASK , |
353 | | /*0xd5 : 0xfe: 0x936 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
354 | | /*0xd6 : 0xbf: 0x937 */ DEV_MASK + ZERO + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
355 | | /*0xd7 : 0xff: 0x938 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
356 | | /*0xd8 : 0xff: 0x939 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
357 | | /*0x00 : 0x00: 0x93A */ ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
358 | | /*0x00 : 0x00: 0x93B */ ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
359 | | /*0xe9 : 0xda: 0x93c */ DEV_MASK + PNJ_MASK + ZERO + ORI_MASK + BNG_MASK + ZERO + ZERO + ZERO , |
360 | | /*0x00 : 0x00: 0x93d */ DEV_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
361 | | /*0xda : 0xff: 0x93e */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
362 | | /*0xdb : 0xff: 0x93f */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
363 | | /*0xdc : 0xff: 0x940 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
364 | | /*0xdd : 0xff: 0x941 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
365 | | /*0xde : 0xff: 0x942 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
366 | | /*0xdf : 0xbe: 0x943 */ DEV_MASK + ZERO + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
367 | | /*0x00 : 0x00: 0x944 */ DEV_MASK + ZERO + GJR_MASK + ZERO + BNG_MASK + KND_MASK + ZERO + ZERO , |
368 | | /*0xe3 : 0x80: 0x945 */ DEV_MASK + ZERO + GJR_MASK + ZERO + ZERO + ZERO + ZERO + ZERO , |
369 | | /*0xe0 : 0x87: 0x946 */ DEV_MASK + ZERO + ZERO + ZERO + ZERO + KND_MASK + MLM_MASK + TML_MASK , |
370 | | /*0xe1 : 0xff: 0x947 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
371 | | /*0xe2 : 0xff: 0x948 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
372 | | /*0xe7 : 0x80: 0x949 */ DEV_MASK + ZERO + GJR_MASK + ZERO + ZERO + ZERO + ZERO + ZERO , |
373 | | /*0xe4 : 0x87: 0x94a */ DEV_MASK + ZERO + ZERO + ZERO + ZERO + KND_MASK + MLM_MASK + TML_MASK , |
374 | | /*0xe5 : 0xff: 0x94b */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
375 | | /*0xe6 : 0xff: 0x94c */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
376 | | /*0xe8 : 0xff: 0x94d */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
377 | | /*0xec : 0x00: 0x94e */ ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
378 | | /*0xed : 0x00: 0x94f */ ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
379 | | /*0x00 : 0x00: 0x950 */ DEV_MASK + ZERO + GJR_MASK + ZERO + ZERO + ZERO + ZERO + ZERO , |
380 | | /*0x00 : 0x00: 0x951 */ DEV_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
381 | | /*0x00 : 0x00: 0x952 */ DEV_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
382 | | /*0x00 : 0x00: 0x953 */ DEV_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
383 | | /*0x00 : 0x00: 0x954 */ DEV_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
384 | | /*0x00 : 0x00: 0x955 */ ZERO + ZERO + ZERO + ZERO + ZERO + KND_MASK + ZERO + ZERO , |
385 | | /*0x00 : 0x00: 0x956 */ ZERO + ZERO + ZERO + ORI_MASK + ZERO + KND_MASK + ZERO + ZERO , |
386 | | /*0x00 : 0x00: 0x957 */ ZERO + ZERO + ZERO + ORI_MASK + BNG_MASK + ZERO + MLM_MASK + ZERO , |
387 | | /*0x00 : 0x00: 0x958 */ DEV_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
388 | | /*0x00 : 0x00: 0x959 */ DEV_MASK + PNJ_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
389 | | /*0x00 : 0x00: 0x95a */ DEV_MASK + PNJ_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
390 | | /*0x00 : 0x00: 0x95b */ DEV_MASK + PNJ_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
391 | | /*0x00 : 0x00: 0x95c */ DEV_MASK + PNJ_MASK + ZERO + ZERO + BNG_MASK + ZERO + ZERO + ZERO , |
392 | | /*0x00 : 0x00: 0x95d */ DEV_MASK + ZERO + ZERO + ORI_MASK + BNG_MASK + ZERO + ZERO + ZERO , |
393 | | /*0x00 : 0x00: 0x95e */ DEV_MASK + PNJ_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
394 | | /*0xce : 0x98: 0x95f */ DEV_MASK + ZERO + ZERO + ORI_MASK + BNG_MASK + ZERO + ZERO + ZERO , |
395 | | /*0x00 : 0x00: 0x960 */ DEV_MASK + ZERO + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
396 | | /*0x00 : 0x00: 0x961 */ DEV_MASK + ZERO + ZERO + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + ZERO , |
397 | | /*0x00 : 0x00: 0x962 */ DEV_MASK + ZERO + ZERO + ZERO + BNG_MASK + ZERO + ZERO + ZERO , |
398 | | /*0x00 : 0x00: 0x963 */ DEV_MASK + ZERO + ZERO + ZERO + BNG_MASK + ZERO + ZERO + ZERO , |
399 | | /*0xea : 0xf8: 0x964 */ DEV_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
400 | | /*0xeaea : 0x00: 0x965*/ DEV_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
401 | | /*0xf1 : 0xff: 0x966 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
402 | | /*0xf2 : 0xff: 0x967 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
403 | | /*0xf3 : 0xff: 0x968 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
404 | | /*0xf4 : 0xff: 0x969 */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
405 | | /*0xf5 : 0xff: 0x96a */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
406 | | /*0xf6 : 0xff: 0x96b */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
407 | | /*0xf7 : 0xff: 0x96c */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
408 | | /*0xf8 : 0xff: 0x96d */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
409 | | /*0xf9 : 0xff: 0x96e */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
410 | | /*0xfa : 0xff: 0x96f */ DEV_MASK + PNJ_MASK + GJR_MASK + ORI_MASK + BNG_MASK + KND_MASK + MLM_MASK + TML_MASK , |
411 | | /*0x00 : 0x80: 0x970 */ DEV_MASK + PNJ_MASK + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO , |
412 | | /* |
413 | | * The length of the array is 128 to provide values for 0x900..0x97f. |
414 | | * The last 15 entries for 0x971..0x97f of the validity table are all zero |
415 | | * because no Indic script uses such Unicode code points. |
416 | | */ |
417 | | /*0x00 : 0x00: 0x9yz */ ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO + ZERO |
418 | | }; |
419 | | |
420 | | static const uint16_t fromUnicodeTable[128]={ |
421 | | 0x00a0 ,/* 0x0900 */ |
422 | | 0x00a1 ,/* 0x0901 */ |
423 | | 0x00a2 ,/* 0x0902 */ |
424 | | 0x00a3 ,/* 0x0903 */ |
425 | | 0xa4e0 ,/* 0x0904 */ |
426 | | 0x00a4 ,/* 0x0905 */ |
427 | | 0x00a5 ,/* 0x0906 */ |
428 | | 0x00a6 ,/* 0x0907 */ |
429 | | 0x00a7 ,/* 0x0908 */ |
430 | | 0x00a8 ,/* 0x0909 */ |
431 | | 0x00a9 ,/* 0x090a */ |
432 | | 0x00aa ,/* 0x090b */ |
433 | | 0xA6E9 ,/* 0x090c */ |
434 | | 0x00ae ,/* 0x090d */ |
435 | | 0x00ab ,/* 0x090e */ |
436 | | 0x00ac ,/* 0x090f */ |
437 | | 0x00ad ,/* 0x0910 */ |
438 | | 0x00b2 ,/* 0x0911 */ |
439 | | 0x00af ,/* 0x0912 */ |
440 | | 0x00b0 ,/* 0x0913 */ |
441 | | 0x00b1 ,/* 0x0914 */ |
442 | | 0x00b3 ,/* 0x0915 */ |
443 | | 0x00b4 ,/* 0x0916 */ |
444 | | 0x00b5 ,/* 0x0917 */ |
445 | | 0x00b6 ,/* 0x0918 */ |
446 | | 0x00b7 ,/* 0x0919 */ |
447 | | 0x00b8 ,/* 0x091a */ |
448 | | 0x00b9 ,/* 0x091b */ |
449 | | 0x00ba ,/* 0x091c */ |
450 | | 0x00bb ,/* 0x091d */ |
451 | | 0x00bc ,/* 0x091e */ |
452 | | 0x00bd ,/* 0x091f */ |
453 | | 0x00be ,/* 0x0920 */ |
454 | | 0x00bf ,/* 0x0921 */ |
455 | | 0x00c0 ,/* 0x0922 */ |
456 | | 0x00c1 ,/* 0x0923 */ |
457 | | 0x00c2 ,/* 0x0924 */ |
458 | | 0x00c3 ,/* 0x0925 */ |
459 | | 0x00c4 ,/* 0x0926 */ |
460 | | 0x00c5 ,/* 0x0927 */ |
461 | | 0x00c6 ,/* 0x0928 */ |
462 | | 0x00c7 ,/* 0x0929 */ |
463 | | 0x00c8 ,/* 0x092a */ |
464 | | 0x00c9 ,/* 0x092b */ |
465 | | 0x00ca ,/* 0x092c */ |
466 | | 0x00cb ,/* 0x092d */ |
467 | | 0x00cc ,/* 0x092e */ |
468 | | 0x00cd ,/* 0x092f */ |
469 | | 0x00cf ,/* 0x0930 */ |
470 | | 0x00d0 ,/* 0x0931 */ |
471 | | 0x00d1 ,/* 0x0932 */ |
472 | | 0x00d2 ,/* 0x0933 */ |
473 | | 0x00d3 ,/* 0x0934 */ |
474 | | 0x00d4 ,/* 0x0935 */ |
475 | | 0x00d5 ,/* 0x0936 */ |
476 | | 0x00d6 ,/* 0x0937 */ |
477 | | 0x00d7 ,/* 0x0938 */ |
478 | | 0x00d8 ,/* 0x0939 */ |
479 | | 0xFFFF ,/* 0x093A */ |
480 | | 0xFFFF ,/* 0x093B */ |
481 | | 0x00e9 ,/* 0x093c */ |
482 | | 0xEAE9 ,/* 0x093d */ |
483 | | 0x00da ,/* 0x093e */ |
484 | | 0x00db ,/* 0x093f */ |
485 | | 0x00dc ,/* 0x0940 */ |
486 | | 0x00dd ,/* 0x0941 */ |
487 | | 0x00de ,/* 0x0942 */ |
488 | | 0x00df ,/* 0x0943 */ |
489 | | 0xDFE9 ,/* 0x0944 */ |
490 | | 0x00e3 ,/* 0x0945 */ |
491 | | 0x00e0 ,/* 0x0946 */ |
492 | | 0x00e1 ,/* 0x0947 */ |
493 | | 0x00e2 ,/* 0x0948 */ |
494 | | 0x00e7 ,/* 0x0949 */ |
495 | | 0x00e4 ,/* 0x094a */ |
496 | | 0x00e5 ,/* 0x094b */ |
497 | | 0x00e6 ,/* 0x094c */ |
498 | | 0x00e8 ,/* 0x094d */ |
499 | | 0x00ec ,/* 0x094e */ |
500 | | 0x00ed ,/* 0x094f */ |
501 | | 0xA1E9 ,/* 0x0950 */ /* OM Symbol */ |
502 | | 0xFFFF ,/* 0x0951 */ |
503 | | 0xF0B8 ,/* 0x0952 */ |
504 | | 0xFFFF ,/* 0x0953 */ |
505 | | 0xFFFF ,/* 0x0954 */ |
506 | | 0xFFFF ,/* 0x0955 */ |
507 | | 0xFFFF ,/* 0x0956 */ |
508 | | 0xFFFF ,/* 0x0957 */ |
509 | | 0xb3e9 ,/* 0x0958 */ |
510 | | 0xb4e9 ,/* 0x0959 */ |
511 | | 0xb5e9 ,/* 0x095a */ |
512 | | 0xbae9 ,/* 0x095b */ |
513 | | 0xbfe9 ,/* 0x095c */ |
514 | | 0xC0E9 ,/* 0x095d */ |
515 | | 0xc9e9 ,/* 0x095e */ |
516 | | 0x00ce ,/* 0x095f */ |
517 | | 0xAAe9 ,/* 0x0960 */ |
518 | | 0xA7E9 ,/* 0x0961 */ |
519 | | 0xDBE9 ,/* 0x0962 */ |
520 | | 0xDCE9 ,/* 0x0963 */ |
521 | | 0x00ea ,/* 0x0964 */ |
522 | | 0xeaea ,/* 0x0965 */ |
523 | | 0x00f1 ,/* 0x0966 */ |
524 | | 0x00f2 ,/* 0x0967 */ |
525 | | 0x00f3 ,/* 0x0968 */ |
526 | | 0x00f4 ,/* 0x0969 */ |
527 | | 0x00f5 ,/* 0x096a */ |
528 | | 0x00f6 ,/* 0x096b */ |
529 | | 0x00f7 ,/* 0x096c */ |
530 | | 0x00f8 ,/* 0x096d */ |
531 | | 0x00f9 ,/* 0x096e */ |
532 | | 0x00fa ,/* 0x096f */ |
533 | | 0xF0BF ,/* 0x0970 */ |
534 | | 0xFFFF ,/* 0x0971 */ |
535 | | 0xFFFF ,/* 0x0972 */ |
536 | | 0xFFFF ,/* 0x0973 */ |
537 | | 0xFFFF ,/* 0x0974 */ |
538 | | 0xFFFF ,/* 0x0975 */ |
539 | | 0xFFFF ,/* 0x0976 */ |
540 | | 0xFFFF ,/* 0x0977 */ |
541 | | 0xFFFF ,/* 0x0978 */ |
542 | | 0xFFFF ,/* 0x0979 */ |
543 | | 0xFFFF ,/* 0x097a */ |
544 | | 0xFFFF ,/* 0x097b */ |
545 | | 0xFFFF ,/* 0x097c */ |
546 | | 0xFFFF ,/* 0x097d */ |
547 | | 0xFFFF ,/* 0x097e */ |
548 | | 0xFFFF ,/* 0x097f */ |
549 | | }; |
550 | | static const uint16_t toUnicodeTable[256]={ |
551 | | 0x0000,/* 0x00 */ |
552 | | 0x0001,/* 0x01 */ |
553 | | 0x0002,/* 0x02 */ |
554 | | 0x0003,/* 0x03 */ |
555 | | 0x0004,/* 0x04 */ |
556 | | 0x0005,/* 0x05 */ |
557 | | 0x0006,/* 0x06 */ |
558 | | 0x0007,/* 0x07 */ |
559 | | 0x0008,/* 0x08 */ |
560 | | 0x0009,/* 0x09 */ |
561 | | 0x000a,/* 0x0a */ |
562 | | 0x000b,/* 0x0b */ |
563 | | 0x000c,/* 0x0c */ |
564 | | 0x000d,/* 0x0d */ |
565 | | 0x000e,/* 0x0e */ |
566 | | 0x000f,/* 0x0f */ |
567 | | 0x0010,/* 0x10 */ |
568 | | 0x0011,/* 0x11 */ |
569 | | 0x0012,/* 0x12 */ |
570 | | 0x0013,/* 0x13 */ |
571 | | 0x0014,/* 0x14 */ |
572 | | 0x0015,/* 0x15 */ |
573 | | 0x0016,/* 0x16 */ |
574 | | 0x0017,/* 0x17 */ |
575 | | 0x0018,/* 0x18 */ |
576 | | 0x0019,/* 0x19 */ |
577 | | 0x001a,/* 0x1a */ |
578 | | 0x001b,/* 0x1b */ |
579 | | 0x001c,/* 0x1c */ |
580 | | 0x001d,/* 0x1d */ |
581 | | 0x001e,/* 0x1e */ |
582 | | 0x001f,/* 0x1f */ |
583 | | 0x0020,/* 0x20 */ |
584 | | 0x0021,/* 0x21 */ |
585 | | 0x0022,/* 0x22 */ |
586 | | 0x0023,/* 0x23 */ |
587 | | 0x0024,/* 0x24 */ |
588 | | 0x0025,/* 0x25 */ |
589 | | 0x0026,/* 0x26 */ |
590 | | 0x0027,/* 0x27 */ |
591 | | 0x0028,/* 0x28 */ |
592 | | 0x0029,/* 0x29 */ |
593 | | 0x002a,/* 0x2a */ |
594 | | 0x002b,/* 0x2b */ |
595 | | 0x002c,/* 0x2c */ |
596 | | 0x002d,/* 0x2d */ |
597 | | 0x002e,/* 0x2e */ |
598 | | 0x002f,/* 0x2f */ |
599 | | 0x0030,/* 0x30 */ |
600 | | 0x0031,/* 0x31 */ |
601 | | 0x0032,/* 0x32 */ |
602 | | 0x0033,/* 0x33 */ |
603 | | 0x0034,/* 0x34 */ |
604 | | 0x0035,/* 0x35 */ |
605 | | 0x0036,/* 0x36 */ |
606 | | 0x0037,/* 0x37 */ |
607 | | 0x0038,/* 0x38 */ |
608 | | 0x0039,/* 0x39 */ |
609 | | 0x003A,/* 0x3A */ |
610 | | 0x003B,/* 0x3B */ |
611 | | 0x003c,/* 0x3c */ |
612 | | 0x003d,/* 0x3d */ |
613 | | 0x003e,/* 0x3e */ |
614 | | 0x003f,/* 0x3f */ |
615 | | 0x0040,/* 0x40 */ |
616 | | 0x0041,/* 0x41 */ |
617 | | 0x0042,/* 0x42 */ |
618 | | 0x0043,/* 0x43 */ |
619 | | 0x0044,/* 0x44 */ |
620 | | 0x0045,/* 0x45 */ |
621 | | 0x0046,/* 0x46 */ |
622 | | 0x0047,/* 0x47 */ |
623 | | 0x0048,/* 0x48 */ |
624 | | 0x0049,/* 0x49 */ |
625 | | 0x004a,/* 0x4a */ |
626 | | 0x004b,/* 0x4b */ |
627 | | 0x004c,/* 0x4c */ |
628 | | 0x004d,/* 0x4d */ |
629 | | 0x004e,/* 0x4e */ |
630 | | 0x004f,/* 0x4f */ |
631 | | 0x0050,/* 0x50 */ |
632 | | 0x0051,/* 0x51 */ |
633 | | 0x0052,/* 0x52 */ |
634 | | 0x0053,/* 0x53 */ |
635 | | 0x0054,/* 0x54 */ |
636 | | 0x0055,/* 0x55 */ |
637 | | 0x0056,/* 0x56 */ |
638 | | 0x0057,/* 0x57 */ |
639 | | 0x0058,/* 0x58 */ |
640 | | 0x0059,/* 0x59 */ |
641 | | 0x005a,/* 0x5a */ |
642 | | 0x005b,/* 0x5b */ |
643 | | 0x005c,/* 0x5c */ |
644 | | 0x005d,/* 0x5d */ |
645 | | 0x005e,/* 0x5e */ |
646 | | 0x005f,/* 0x5f */ |
647 | | 0x0060,/* 0x60 */ |
648 | | 0x0061,/* 0x61 */ |
649 | | 0x0062,/* 0x62 */ |
650 | | 0x0063,/* 0x63 */ |
651 | | 0x0064,/* 0x64 */ |
652 | | 0x0065,/* 0x65 */ |
653 | | 0x0066,/* 0x66 */ |
654 | | 0x0067,/* 0x67 */ |
655 | | 0x0068,/* 0x68 */ |
656 | | 0x0069,/* 0x69 */ |
657 | | 0x006a,/* 0x6a */ |
658 | | 0x006b,/* 0x6b */ |
659 | | 0x006c,/* 0x6c */ |
660 | | 0x006d,/* 0x6d */ |
661 | | 0x006e,/* 0x6e */ |
662 | | 0x006f,/* 0x6f */ |
663 | | 0x0070,/* 0x70 */ |
664 | | 0x0071,/* 0x71 */ |
665 | | 0x0072,/* 0x72 */ |
666 | | 0x0073,/* 0x73 */ |
667 | | 0x0074,/* 0x74 */ |
668 | | 0x0075,/* 0x75 */ |
669 | | 0x0076,/* 0x76 */ |
670 | | 0x0077,/* 0x77 */ |
671 | | 0x0078,/* 0x78 */ |
672 | | 0x0079,/* 0x79 */ |
673 | | 0x007a,/* 0x7a */ |
674 | | 0x007b,/* 0x7b */ |
675 | | 0x007c,/* 0x7c */ |
676 | | 0x007d,/* 0x7d */ |
677 | | 0x007e,/* 0x7e */ |
678 | | 0x007f,/* 0x7f */ |
679 | | 0x0080,/* 0x80 */ |
680 | | 0x0081,/* 0x81 */ |
681 | | 0x0082,/* 0x82 */ |
682 | | 0x0083,/* 0x83 */ |
683 | | 0x0084,/* 0x84 */ |
684 | | 0x0085,/* 0x85 */ |
685 | | 0x0086,/* 0x86 */ |
686 | | 0x0087,/* 0x87 */ |
687 | | 0x0088,/* 0x88 */ |
688 | | 0x0089,/* 0x89 */ |
689 | | 0x008a,/* 0x8a */ |
690 | | 0x008b,/* 0x8b */ |
691 | | 0x008c,/* 0x8c */ |
692 | | 0x008d,/* 0x8d */ |
693 | | 0x008e,/* 0x8e */ |
694 | | 0x008f,/* 0x8f */ |
695 | | 0x0090,/* 0x90 */ |
696 | | 0x0091,/* 0x91 */ |
697 | | 0x0092,/* 0x92 */ |
698 | | 0x0093,/* 0x93 */ |
699 | | 0x0094,/* 0x94 */ |
700 | | 0x0095,/* 0x95 */ |
701 | | 0x0096,/* 0x96 */ |
702 | | 0x0097,/* 0x97 */ |
703 | | 0x0098,/* 0x98 */ |
704 | | 0x0099,/* 0x99 */ |
705 | | 0x009a,/* 0x9a */ |
706 | | 0x009b,/* 0x9b */ |
707 | | 0x009c,/* 0x9c */ |
708 | | 0x009d,/* 0x9d */ |
709 | | 0x009e,/* 0x9e */ |
710 | | 0x009f,/* 0x9f */ |
711 | | 0x00A0,/* 0xa0 */ |
712 | | 0x0901,/* 0xa1 */ |
713 | | 0x0902,/* 0xa2 */ |
714 | | 0x0903,/* 0xa3 */ |
715 | | 0x0905,/* 0xa4 */ |
716 | | 0x0906,/* 0xa5 */ |
717 | | 0x0907,/* 0xa6 */ |
718 | | 0x0908,/* 0xa7 */ |
719 | | 0x0909,/* 0xa8 */ |
720 | | 0x090a,/* 0xa9 */ |
721 | | 0x090b,/* 0xaa */ |
722 | | 0x090e,/* 0xab */ |
723 | | 0x090f,/* 0xac */ |
724 | | 0x0910,/* 0xad */ |
725 | | 0x090d,/* 0xae */ |
726 | | 0x0912,/* 0xaf */ |
727 | | 0x0913,/* 0xb0 */ |
728 | | 0x0914,/* 0xb1 */ |
729 | | 0x0911,/* 0xb2 */ |
730 | | 0x0915,/* 0xb3 */ |
731 | | 0x0916,/* 0xb4 */ |
732 | | 0x0917,/* 0xb5 */ |
733 | | 0x0918,/* 0xb6 */ |
734 | | 0x0919,/* 0xb7 */ |
735 | | 0x091a,/* 0xb8 */ |
736 | | 0x091b,/* 0xb9 */ |
737 | | 0x091c,/* 0xba */ |
738 | | 0x091d,/* 0xbb */ |
739 | | 0x091e,/* 0xbc */ |
740 | | 0x091f,/* 0xbd */ |
741 | | 0x0920,/* 0xbe */ |
742 | | 0x0921,/* 0xbf */ |
743 | | 0x0922,/* 0xc0 */ |
744 | | 0x0923,/* 0xc1 */ |
745 | | 0x0924,/* 0xc2 */ |
746 | | 0x0925,/* 0xc3 */ |
747 | | 0x0926,/* 0xc4 */ |
748 | | 0x0927,/* 0xc5 */ |
749 | | 0x0928,/* 0xc6 */ |
750 | | 0x0929,/* 0xc7 */ |
751 | | 0x092a,/* 0xc8 */ |
752 | | 0x092b,/* 0xc9 */ |
753 | | 0x092c,/* 0xca */ |
754 | | 0x092d,/* 0xcb */ |
755 | | 0x092e,/* 0xcc */ |
756 | | 0x092f,/* 0xcd */ |
757 | | 0x095f,/* 0xce */ |
758 | | 0x0930,/* 0xcf */ |
759 | | 0x0931,/* 0xd0 */ |
760 | | 0x0932,/* 0xd1 */ |
761 | | 0x0933,/* 0xd2 */ |
762 | | 0x0934,/* 0xd3 */ |
763 | | 0x0935,/* 0xd4 */ |
764 | | 0x0936,/* 0xd5 */ |
765 | | 0x0937,/* 0xd6 */ |
766 | | 0x0938,/* 0xd7 */ |
767 | | 0x0939,/* 0xd8 */ |
768 | | 0x200D,/* 0xd9 */ |
769 | | 0x093e,/* 0xda */ |
770 | | 0x093f,/* 0xdb */ |
771 | | 0x0940,/* 0xdc */ |
772 | | 0x0941,/* 0xdd */ |
773 | | 0x0942,/* 0xde */ |
774 | | 0x0943,/* 0xdf */ |
775 | | 0x0946,/* 0xe0 */ |
776 | | 0x0947,/* 0xe1 */ |
777 | | 0x0948,/* 0xe2 */ |
778 | | 0x0945,/* 0xe3 */ |
779 | | 0x094a,/* 0xe4 */ |
780 | | 0x094b,/* 0xe5 */ |
781 | | 0x094c,/* 0xe6 */ |
782 | | 0x0949,/* 0xe7 */ |
783 | | 0x094d,/* 0xe8 */ |
784 | | 0x093c,/* 0xe9 */ |
785 | | 0x0964,/* 0xea */ |
786 | | 0xFFFF,/* 0xeb */ |
787 | | 0xFFFF,/* 0xec */ |
788 | | 0xFFFF,/* 0xed */ |
789 | | 0xFFFF,/* 0xee */ |
790 | | 0xFFFF,/* 0xef */ |
791 | | 0xFFFF,/* 0xf0 */ |
792 | | 0x0966,/* 0xf1 */ |
793 | | 0x0967,/* 0xf2 */ |
794 | | 0x0968,/* 0xf3 */ |
795 | | 0x0969,/* 0xf4 */ |
796 | | 0x096a,/* 0xf5 */ |
797 | | 0x096b,/* 0xf6 */ |
798 | | 0x096c,/* 0xf7 */ |
799 | | 0x096d,/* 0xf8 */ |
800 | | 0x096e,/* 0xf9 */ |
801 | | 0x096f,/* 0xfa */ |
802 | | 0xFFFF,/* 0xfb */ |
803 | | 0xFFFF,/* 0xfc */ |
804 | | 0xFFFF,/* 0xfd */ |
805 | | 0xFFFF,/* 0xfe */ |
806 | | 0xFFFF /* 0xff */ |
807 | | }; |
808 | | |
809 | | static const uint16_t vowelSignESpecialCases[][2]={ |
810 | | { 2 /*length of array*/ , 0 }, |
811 | | { 0xA4 , 0x0904 }, |
812 | | }; |
813 | | |
814 | | static const uint16_t nuktaSpecialCases[][2]={ |
815 | | { 16 /*length of array*/ , 0 }, |
816 | | { 0xA6 , 0x090c }, |
817 | | { 0xEA , 0x093D }, |
818 | | { 0xDF , 0x0944 }, |
819 | | { 0xA1 , 0x0950 }, |
820 | | { 0xb3 , 0x0958 }, |
821 | | { 0xb4 , 0x0959 }, |
822 | | { 0xb5 , 0x095a }, |
823 | | { 0xba , 0x095b }, |
824 | | { 0xbf , 0x095c }, |
825 | | { 0xC0 , 0x095d }, |
826 | | { 0xc9 , 0x095e }, |
827 | | { 0xAA , 0x0960 }, |
828 | | { 0xA7 , 0x0961 }, |
829 | | { 0xDB , 0x0962 }, |
830 | | { 0xDC , 0x0963 }, |
831 | | }; |
832 | | |
833 | | |
834 | 0 | #define WRITE_TO_TARGET_FROM_U(args,offsets,source,target,targetLimit,targetByteUnit,err) UPRV_BLOCK_MACRO_BEGIN { \ |
835 | 0 | int32_t offset = (int32_t)(source - args->source-1); \ |
836 | 0 | /* write the targetUniChar to target */ \ |
837 | 0 | if(target < targetLimit){ \ |
838 | 0 | if(targetByteUnit <= 0xFF){ \ |
839 | 0 | *(target)++ = (uint8_t)(targetByteUnit); \ |
840 | 0 | if(offsets){ \ |
841 | 0 | *(offsets++) = offset; \ |
842 | 0 | } \ |
843 | 0 | }else{ \ |
844 | 0 | if (targetByteUnit > 0xFFFF) { \ |
845 | 0 | *(target)++ = (uint8_t)(targetByteUnit>>16); \ |
846 | 0 | if (offsets) { \ |
847 | 0 | --offset; \ |
848 | 0 | *(offsets++) = offset; \ |
849 | 0 | } \ |
850 | 0 | } \ |
851 | 0 | if (!(target < targetLimit)) { \ |
852 | 0 | args->converter->charErrorBuffer[args->converter->charErrorBufferLength++] = \ |
853 | 0 | (uint8_t)(targetByteUnit >> 8); \ |
854 | 0 | args->converter->charErrorBuffer[args->converter->charErrorBufferLength++] = \ |
855 | 0 | (uint8_t)targetByteUnit; \ |
856 | 0 | *err = U_BUFFER_OVERFLOW_ERROR; \ |
857 | 0 | } else { \ |
858 | 0 | *(target)++ = (uint8_t)(targetByteUnit>>8); \ |
859 | 0 | if(offsets){ \ |
860 | 0 | *(offsets++) = offset; \ |
861 | 0 | } \ |
862 | 0 | if(target < targetLimit){ \ |
863 | 0 | *(target)++ = (uint8_t) targetByteUnit; \ |
864 | 0 | if(offsets){ \ |
865 | 0 | *(offsets++) = offset ; \ |
866 | 0 | } \ |
867 | 0 | }else{ \ |
868 | 0 | args->converter->charErrorBuffer[args->converter->charErrorBufferLength++] =\ |
869 | 0 | (uint8_t) (targetByteUnit); \ |
870 | 0 | *err = U_BUFFER_OVERFLOW_ERROR; \ |
871 | 0 | } \ |
872 | 0 | } \ |
873 | 0 | } \ |
874 | 0 | }else{ \ |
875 | 0 | if (targetByteUnit & 0xFF0000) { \ |
876 | 0 | args->converter->charErrorBuffer[args->converter->charErrorBufferLength++] = \ |
877 | 0 | (uint8_t) (targetByteUnit >>16); \ |
878 | 0 | } \ |
879 | 0 | if(targetByteUnit & 0xFF00){ \ |
880 | 0 | args->converter->charErrorBuffer[args->converter->charErrorBufferLength++] = \ |
881 | 0 | (uint8_t) (targetByteUnit >>8); \ |
882 | 0 | } \ |
883 | 0 | args->converter->charErrorBuffer[args->converter->charErrorBufferLength++] = \ |
884 | 0 | (uint8_t) (targetByteUnit); \ |
885 | 0 | *err = U_BUFFER_OVERFLOW_ERROR; \ |
886 | 0 | } \ |
887 | 0 | } UPRV_BLOCK_MACRO_END |
888 | | |
889 | | /* Rules: |
890 | | * Explicit Halant : |
891 | | * <HALANT> + <ZWNJ> |
892 | | * Soft Halant : |
893 | | * <HALANT> + <ZWJ> |
894 | | */ |
895 | | static void U_CALLCONV |
896 | | UConverter_fromUnicode_ISCII_OFFSETS_LOGIC( |
897 | 0 | UConverterFromUnicodeArgs * args, UErrorCode * err) { |
898 | 0 | const UChar *source = args->source; |
899 | 0 | const UChar *sourceLimit = args->sourceLimit; |
900 | 0 | unsigned char *target = (unsigned char *) args->target; |
901 | 0 | unsigned char *targetLimit = (unsigned char *) args->targetLimit; |
902 | 0 | int32_t* offsets = args->offsets; |
903 | 0 | uint32_t targetByteUnit = 0x0000; |
904 | 0 | UChar32 sourceChar = 0x0000; |
905 | 0 | UChar32 tempContextFromUnicode = 0x0000; /* For special handling of the Gurmukhi script. */ |
906 | 0 | UConverterDataISCII *converterData; |
907 | 0 | uint16_t newDelta=0; |
908 | 0 | uint16_t range = 0; |
909 | 0 | UBool deltaChanged = FALSE; |
910 | |
|
911 | 0 | if ((args->converter == NULL) || (args->targetLimit < args->target) || (args->sourceLimit < args->source)) { |
912 | 0 | *err = U_ILLEGAL_ARGUMENT_ERROR; |
913 | 0 | return; |
914 | 0 | } |
915 | | /* initialize data */ |
916 | 0 | converterData=(UConverterDataISCII*)args->converter->extraInfo; |
917 | 0 | newDelta=converterData->currentDeltaFromUnicode; |
918 | 0 | range = (uint16_t)(newDelta/DELTA); |
919 | |
|
920 | 0 | if ((sourceChar = args->converter->fromUChar32)!=0) { |
921 | 0 | goto getTrail; |
922 | 0 | } |
923 | | |
924 | | /*writing the char to the output stream */ |
925 | 0 | while (source < sourceLimit) { |
926 | | /* Write the language code following LF only if LF is not the last character. */ |
927 | 0 | if (args->converter->fromUnicodeStatus == LF) { |
928 | 0 | targetByteUnit = ATR<<8; |
929 | 0 | targetByteUnit += (uint8_t) lookupInitialData[range].isciiLang; |
930 | 0 | args->converter->fromUnicodeStatus = 0x0000; |
931 | | /* now append ATR and language code */ |
932 | 0 | WRITE_TO_TARGET_FROM_U(args,offsets,source,target,targetLimit,targetByteUnit,err); |
933 | 0 | if (U_FAILURE(*err)) { |
934 | 0 | break; |
935 | 0 | } |
936 | 0 | } |
937 | | |
938 | 0 | sourceChar = *source++; |
939 | 0 | tempContextFromUnicode = converterData->contextCharFromUnicode; |
940 | | |
941 | 0 | targetByteUnit = missingCharMarker; |
942 | | |
943 | | /*check if input is in ASCII and C0 control codes range*/ |
944 | 0 | if (sourceChar <= ASCII_END) { |
945 | 0 | args->converter->fromUnicodeStatus = sourceChar; |
946 | 0 | WRITE_TO_TARGET_FROM_U(args,offsets,source,target,targetLimit,sourceChar,err); |
947 | 0 | if (U_FAILURE(*err)) { |
948 | 0 | break; |
949 | 0 | } |
950 | 0 | continue; |
951 | 0 | } |
952 | 0 | switch (sourceChar) { |
953 | 0 | case ZWNJ: |
954 | | /* contextChar has HALANT */ |
955 | 0 | if (converterData->contextCharFromUnicode) { |
956 | 0 | converterData->contextCharFromUnicode = 0x00; |
957 | 0 | targetByteUnit = ISCII_HALANT; |
958 | 0 | } else { |
959 | | /* consume ZWNJ and continue */ |
960 | 0 | converterData->contextCharFromUnicode = 0x00; |
961 | 0 | continue; |
962 | 0 | } |
963 | 0 | break; |
964 | 0 | case ZWJ: |
965 | | /* contextChar has HALANT */ |
966 | 0 | if (converterData->contextCharFromUnicode) { |
967 | 0 | targetByteUnit = ISCII_NUKTA; |
968 | 0 | } else { |
969 | 0 | targetByteUnit =ISCII_INV; |
970 | 0 | } |
971 | 0 | converterData->contextCharFromUnicode = 0x00; |
972 | 0 | break; |
973 | 0 | default: |
974 | | /* is the sourceChar in the INDIC_RANGE? */ |
975 | 0 | if ((uint16_t)(INDIC_BLOCK_END-sourceChar) <= INDIC_RANGE) { |
976 | | /* Danda and Double Danda are valid in Northern scripts.. since Unicode |
977 | | * does not include these codepoints in all Northern scrips we need to |
978 | | * filter them out |
979 | | */ |
980 | 0 | if (sourceChar!= DANDA && sourceChar != DOUBLE_DANDA) { |
981 | | /* find out to which block the souceChar belongs*/ |
982 | 0 | range =(uint16_t)((sourceChar-INDIC_BLOCK_BEGIN)/DELTA); |
983 | 0 | newDelta =(uint16_t)(range*DELTA); |
984 | | |
985 | | /* Now are we in the same block as the previous? */ |
986 | 0 | if (newDelta!= converterData->currentDeltaFromUnicode || converterData->isFirstBuffer) { |
987 | 0 | converterData->currentDeltaFromUnicode = newDelta; |
988 | 0 | converterData->currentMaskFromUnicode = lookupInitialData[range].maskEnum; |
989 | 0 | deltaChanged =TRUE; |
990 | 0 | converterData->isFirstBuffer=FALSE; |
991 | 0 | } |
992 | | |
993 | 0 | if (converterData->currentDeltaFromUnicode == PNJ_DELTA) { |
994 | 0 | if (sourceChar == PNJ_TIPPI) { |
995 | | /* Make sure Tippi is converted to Bindi. */ |
996 | 0 | sourceChar = PNJ_BINDI; |
997 | 0 | } else if (sourceChar == PNJ_ADHAK) { |
998 | | /* This is for consonant cluster handling. */ |
999 | 0 | converterData->contextCharFromUnicode = PNJ_ADHAK; |
1000 | 0 | } |
1001 | | |
1002 | 0 | } |
1003 | | /* Normalize all Indic codepoints to Devanagari and map them to ISCII */ |
1004 | | /* now subtract the new delta from sourceChar*/ |
1005 | 0 | sourceChar -= converterData->currentDeltaFromUnicode; |
1006 | 0 | } |
1007 | | |
1008 | | /* get the target byte unit */ |
1009 | 0 | targetByteUnit=fromUnicodeTable[(uint8_t)sourceChar]; |
1010 | | |
1011 | | /* is the code point valid in current script? */ |
1012 | 0 | if ((validityTable[(uint8_t)sourceChar] & converterData->currentMaskFromUnicode)==0) { |
1013 | | /* Vocallic RR is assigned in ISCII Telugu and Unicode */ |
1014 | 0 | if (converterData->currentDeltaFromUnicode!=(TELUGU_DELTA) || sourceChar!=VOCALLIC_RR) { |
1015 | 0 | targetByteUnit=missingCharMarker; |
1016 | 0 | } |
1017 | 0 | } |
1018 | |
|
1019 | 0 | if (deltaChanged) { |
1020 | | /* we are in a script block which is different than |
1021 | | * previous sourceChar's script block write ATR and language codes |
1022 | | */ |
1023 | 0 | uint32_t temp=0; |
1024 | 0 | temp =(uint16_t)(ATR<<8); |
1025 | 0 | temp += (uint16_t)((uint8_t) lookupInitialData[range].isciiLang); |
1026 | | /* reset */ |
1027 | 0 | deltaChanged=FALSE; |
1028 | | /* now append ATR and language code */ |
1029 | 0 | WRITE_TO_TARGET_FROM_U(args,offsets,source,target,targetLimit,temp,err); |
1030 | 0 | if (U_FAILURE(*err)) { |
1031 | 0 | break; |
1032 | 0 | } |
1033 | 0 | } |
1034 | | |
1035 | 0 | if (converterData->currentDeltaFromUnicode == PNJ_DELTA && (sourceChar + PNJ_DELTA) == PNJ_ADHAK) { |
1036 | 0 | continue; |
1037 | 0 | } |
1038 | 0 | } |
1039 | | /* reset context char */ |
1040 | 0 | converterData->contextCharFromUnicode = 0x00; |
1041 | 0 | break; |
1042 | 0 | } |
1043 | 0 | if (converterData->currentDeltaFromUnicode == PNJ_DELTA && tempContextFromUnicode == PNJ_ADHAK && isPNJConsonant((sourceChar + PNJ_DELTA))) { |
1044 | | /* If the previous codepoint is Adhak and the current codepoint is a consonant, the targetByteUnit should be C + Halant + C. */ |
1045 | | /* reset context char */ |
1046 | 0 | converterData->contextCharFromUnicode = 0x0000; |
1047 | 0 | targetByteUnit = targetByteUnit << 16 | ISCII_HALANT << 8 | targetByteUnit; |
1048 | | /* write targetByteUnit to target */ |
1049 | 0 | WRITE_TO_TARGET_FROM_U(args, offsets, source, target, targetLimit, targetByteUnit,err); |
1050 | 0 | if (U_FAILURE(*err)) { |
1051 | 0 | break; |
1052 | 0 | } |
1053 | 0 | } else if (targetByteUnit != missingCharMarker) { |
1054 | 0 | if (targetByteUnit==ISCII_HALANT) { |
1055 | 0 | converterData->contextCharFromUnicode = (UChar)targetByteUnit; |
1056 | 0 | } |
1057 | | /* write targetByteUnit to target*/ |
1058 | 0 | WRITE_TO_TARGET_FROM_U(args,offsets,source,target,targetLimit,targetByteUnit,err); |
1059 | 0 | if (U_FAILURE(*err)) { |
1060 | 0 | break; |
1061 | 0 | } |
1062 | 0 | } else { |
1063 | | /* oops.. the code point is unassigned */ |
1064 | | /*check if the char is a First surrogate*/ |
1065 | 0 | if (U16_IS_SURROGATE(sourceChar)) { |
1066 | 0 | if (U16_IS_SURROGATE_LEAD(sourceChar)) { |
1067 | 0 | getTrail: |
1068 | | /*look ahead to find the trail surrogate*/ |
1069 | 0 | if (source < sourceLimit) { |
1070 | | /* test the following code unit */ |
1071 | 0 | UChar trail= (*source); |
1072 | 0 | if (U16_IS_TRAIL(trail)) { |
1073 | 0 | source++; |
1074 | 0 | sourceChar=U16_GET_SUPPLEMENTARY(sourceChar, trail); |
1075 | 0 | *err =U_INVALID_CHAR_FOUND; |
1076 | | /* convert this surrogate code point */ |
1077 | | /* exit this condition tree */ |
1078 | 0 | } else { |
1079 | | /* this is an unmatched lead code unit (1st surrogate) */ |
1080 | | /* callback(illegal) */ |
1081 | 0 | *err=U_ILLEGAL_CHAR_FOUND; |
1082 | 0 | } |
1083 | 0 | } else { |
1084 | | /* no more input */ |
1085 | 0 | *err = U_ZERO_ERROR; |
1086 | 0 | } |
1087 | 0 | } else { |
1088 | | /* this is an unmatched trail code unit (2nd surrogate) */ |
1089 | | /* callback(illegal) */ |
1090 | 0 | *err=U_ILLEGAL_CHAR_FOUND; |
1091 | 0 | } |
1092 | 0 | } else { |
1093 | | /* callback(unassigned) for a BMP code point */ |
1094 | 0 | *err = U_INVALID_CHAR_FOUND; |
1095 | 0 | } |
1096 | |
|
1097 | 0 | args->converter->fromUChar32=sourceChar; |
1098 | 0 | break; |
1099 | 0 | } |
1100 | 0 | }/* end while(mySourceIndex<mySourceLength) */ |
1101 | | |
1102 | | /*save the state and return */ |
1103 | 0 | args->source = source; |
1104 | 0 | args->target = (char*)target; |
1105 | 0 | } |
1106 | | |
1107 | | static const uint16_t lookupTable[][2]={ |
1108 | | { ZERO, ZERO }, /*DEFAULT*/ |
1109 | | { ZERO, ZERO }, /*ROMAN*/ |
1110 | | { DEVANAGARI, DEV_MASK }, |
1111 | | { BENGALI, BNG_MASK }, |
1112 | | { TAMIL, TML_MASK }, |
1113 | | { TELUGU, KND_MASK }, |
1114 | | { BENGALI, BNG_MASK }, |
1115 | | { ORIYA, ORI_MASK }, |
1116 | | { KANNADA, KND_MASK }, |
1117 | | { MALAYALAM, MLM_MASK }, |
1118 | | { GUJARATI, GJR_MASK }, |
1119 | | { GURMUKHI, PNJ_MASK } |
1120 | | }; |
1121 | | |
1122 | 0 | #define WRITE_TO_TARGET_TO_U(args,source,target,offsets,offset,targetUniChar,delta, err) UPRV_BLOCK_MACRO_BEGIN { \ |
1123 | 0 | /* add offset to current Indic Block */ \ |
1124 | 0 | if(targetUniChar>ASCII_END && \ |
1125 | 0 | targetUniChar != ZWJ && \ |
1126 | 0 | targetUniChar != ZWNJ && \ |
1127 | 0 | targetUniChar != DANDA && \ |
1128 | 0 | targetUniChar != DOUBLE_DANDA){ \ |
1129 | 0 | \ |
1130 | 0 | targetUniChar+=(uint16_t)(delta); \ |
1131 | 0 | } \ |
1132 | 0 | /* now write the targetUniChar */ \ |
1133 | 0 | if(target<args->targetLimit){ \ |
1134 | 0 | *(target)++ = (UChar)targetUniChar; \ |
1135 | 0 | if(offsets){ \ |
1136 | 0 | *(offsets)++ = (int32_t)(offset); \ |
1137 | 0 | } \ |
1138 | 0 | }else{ \ |
1139 | 0 | args->converter->UCharErrorBuffer[args->converter->UCharErrorBufferLength++] = \ |
1140 | 0 | (UChar)targetUniChar; \ |
1141 | 0 | *err = U_BUFFER_OVERFLOW_ERROR; \ |
1142 | 0 | } \ |
1143 | 0 | } UPRV_BLOCK_MACRO_END |
1144 | | |
1145 | 0 | #define GET_MAPPING(sourceChar,targetUniChar,data) UPRV_BLOCK_MACRO_BEGIN { \ |
1146 | 0 | targetUniChar = toUnicodeTable[(sourceChar)] ; \ |
1147 | 0 | /* is the code point valid in current script? */ \ |
1148 | 0 | if(sourceChar> ASCII_END && \ |
1149 | 0 | (validityTable[(targetUniChar & 0x7F)] & data->currentMaskToUnicode)==0){ \ |
1150 | 0 | /* Vocallic RR is assigned in ISCII Telugu and Unicode */ \ |
1151 | 0 | if(data->currentDeltaToUnicode!=(TELUGU_DELTA) || \ |
1152 | 0 | targetUniChar!=VOCALLIC_RR){ \ |
1153 | 0 | targetUniChar=missingCharMarker; \ |
1154 | 0 | } \ |
1155 | 0 | } \ |
1156 | 0 | } UPRV_BLOCK_MACRO_END |
1157 | | |
1158 | | /*********** |
1159 | | * Rules for ISCII to Unicode converter |
1160 | | * ISCII is stateful encoding. To convert ISCII bytes to Unicode, |
1161 | | * which has both precomposed and decomposed forms characters |
1162 | | * pre-context and post-context need to be considered. |
1163 | | * |
1164 | | * Post context |
1165 | | * i) ATR : Attribute code is used to declare the font and script switching. |
1166 | | * Currently we only switch scripts and font codes consumed without generating an error |
1167 | | * ii) EXT : Extension code is used to declare switching to Sanskrit and for obscure, |
1168 | | * obsolete characters |
1169 | | * Pre context |
1170 | | * i) Halant: if preceded by a halant then it is a explicit halant |
1171 | | * ii) Nukta : |
1172 | | * a) if preceded by a halant then it is a soft halant |
1173 | | * b) if preceded by specific consonants and the ligatures have pre-composed |
1174 | | * characters in Unicode then convert to pre-composed characters |
1175 | | * iii) Danda: If Danda is preceded by a Danda then convert to Double Danda |
1176 | | * |
1177 | | */ |
1178 | | |
1179 | | static void U_CALLCONV |
1180 | 0 | UConverter_toUnicode_ISCII_OFFSETS_LOGIC(UConverterToUnicodeArgs *args, UErrorCode* err) { |
1181 | 0 | const char *source = ( char *) args->source; |
1182 | 0 | UChar *target = args->target; |
1183 | 0 | const char *sourceLimit = args->sourceLimit; |
1184 | 0 | const UChar* targetLimit = args->targetLimit; |
1185 | 0 | uint32_t targetUniChar = 0x0000; |
1186 | 0 | uint8_t sourceChar = 0x0000; |
1187 | 0 | UConverterDataISCII* data; |
1188 | 0 | UChar32* toUnicodeStatus=NULL; |
1189 | 0 | UChar32 tempTargetUniChar = 0x0000; |
1190 | 0 | UChar* contextCharToUnicode= NULL; |
1191 | 0 | UBool found; |
1192 | 0 | int i; |
1193 | 0 | int offset = 0; |
1194 | |
|
1195 | 0 | if ((args->converter == NULL) || (target < args->target) || (source < args->source)) { |
1196 | 0 | *err = U_ILLEGAL_ARGUMENT_ERROR; |
1197 | 0 | return; |
1198 | 0 | } |
1199 | | |
1200 | 0 | data = (UConverterDataISCII*)(args->converter->extraInfo); |
1201 | 0 | contextCharToUnicode = &data->contextCharToUnicode; /* contains previous ISCII codepoint visited */ |
1202 | 0 | toUnicodeStatus = (UChar32*)&args->converter->toUnicodeStatus;/* contains the mapping to Unicode of the above codepoint*/ |
1203 | |
|
1204 | 0 | while (U_SUCCESS(*err) && source<sourceLimit) { |
1205 | |
|
1206 | 0 | targetUniChar = missingCharMarker; |
1207 | |
|
1208 | 0 | if (target < targetLimit) { |
1209 | 0 | sourceChar = (unsigned char)*(source)++; |
1210 | | |
1211 | | /* look at the post-context perform special processing */ |
1212 | 0 | if (*contextCharToUnicode==ATR) { |
1213 | | |
1214 | | /* If we have ATR in *contextCharToUnicode then we need to change our |
1215 | | * state to the Indic Script specified by sourceChar |
1216 | | */ |
1217 | | |
1218 | | /* check if the sourceChar is supported script range*/ |
1219 | 0 | if ((uint8_t)(PNJ-sourceChar)<=PNJ-DEV) { |
1220 | 0 | data->currentDeltaToUnicode = (uint16_t)(lookupTable[sourceChar & 0x0F][0] * DELTA); |
1221 | 0 | data->currentMaskToUnicode = (MaskEnum)lookupTable[sourceChar & 0x0F][1]; |
1222 | 0 | } else if (sourceChar==DEF) { |
1223 | | /* switch back to default */ |
1224 | 0 | data->currentDeltaToUnicode = data->defDeltaToUnicode; |
1225 | 0 | data->currentMaskToUnicode = data->defMaskToUnicode; |
1226 | 0 | } else { |
1227 | 0 | if ((sourceChar >= 0x21 && sourceChar <= 0x3F)) { |
1228 | | /* these are display codes consume and continue */ |
1229 | 0 | } else { |
1230 | 0 | *err =U_ILLEGAL_CHAR_FOUND; |
1231 | | /* reset */ |
1232 | 0 | *contextCharToUnicode=NO_CHAR_MARKER; |
1233 | 0 | goto CALLBACK; |
1234 | 0 | } |
1235 | 0 | } |
1236 | | |
1237 | | /* reset */ |
1238 | 0 | *contextCharToUnicode=NO_CHAR_MARKER; |
1239 | |
|
1240 | 0 | continue; |
1241 | |
|
1242 | 0 | } else if (*contextCharToUnicode==EXT) { |
1243 | | /* check if sourceChar is in 0xA1-0xEE range */ |
1244 | 0 | if ((uint8_t) (EXT_RANGE_END - sourceChar) <= (EXT_RANGE_END - EXT_RANGE_BEGIN)) { |
1245 | | /* We currently support only Anudatta and Devanagari abbreviation sign */ |
1246 | 0 | if (sourceChar==0xBF || sourceChar == 0xB8) { |
1247 | 0 | targetUniChar = (sourceChar==0xBF) ? DEV_ABBR_SIGN : DEV_ANUDATTA; |
1248 | | |
1249 | | /* find out if the mapping is valid in this state */ |
1250 | 0 | if (validityTable[(uint8_t)targetUniChar] & data->currentMaskToUnicode) { |
1251 | 0 | *contextCharToUnicode= NO_CHAR_MARKER; |
1252 | | |
1253 | | /* Write the previous toUnicodeStatus, this was delayed to handle consonant clustering for Gurmukhi script. */ |
1254 | 0 | if (data->prevToUnicodeStatus) { |
1255 | 0 | WRITE_TO_TARGET_TO_U(args,source,target,args->offsets,(source-args->source -1),data->prevToUnicodeStatus,0,err); |
1256 | 0 | data->prevToUnicodeStatus = 0x0000; |
1257 | 0 | } |
1258 | | /* write to target */ |
1259 | 0 | WRITE_TO_TARGET_TO_U(args,source,target,args->offsets,(source-args->source -2),targetUniChar,data->currentDeltaToUnicode,err); |
1260 | |
|
1261 | 0 | continue; |
1262 | 0 | } |
1263 | 0 | } |
1264 | | /* byte unit is unassigned */ |
1265 | 0 | targetUniChar = missingCharMarker; |
1266 | 0 | *err= U_INVALID_CHAR_FOUND; |
1267 | 0 | } else { |
1268 | | /* only 0xA1 - 0xEE are legal after EXT char */ |
1269 | 0 | *contextCharToUnicode= NO_CHAR_MARKER; |
1270 | 0 | *err = U_ILLEGAL_CHAR_FOUND; |
1271 | 0 | } |
1272 | 0 | goto CALLBACK; |
1273 | 0 | } else if (*contextCharToUnicode==ISCII_INV) { |
1274 | 0 | if (sourceChar==ISCII_HALANT) { |
1275 | 0 | targetUniChar = 0x0020; /* replace with space according to Indic FAQ */ |
1276 | 0 | } else { |
1277 | 0 | targetUniChar = ZWJ; |
1278 | 0 | } |
1279 | | |
1280 | | /* Write the previous toUnicodeStatus, this was delayed to handle consonant clustering for Gurmukhi script. */ |
1281 | 0 | if (data->prevToUnicodeStatus) { |
1282 | 0 | WRITE_TO_TARGET_TO_U(args,source,target,args->offsets,(source-args->source -1),data->prevToUnicodeStatus,0,err); |
1283 | 0 | data->prevToUnicodeStatus = 0x0000; |
1284 | 0 | } |
1285 | | /* write to target */ |
1286 | 0 | WRITE_TO_TARGET_TO_U(args,source,target,args->offsets,(source-args->source -2),targetUniChar,data->currentDeltaToUnicode,err); |
1287 | | /* reset */ |
1288 | 0 | *contextCharToUnicode=NO_CHAR_MARKER; |
1289 | 0 | } |
1290 | | |
1291 | | /* look at the pre-context and perform special processing */ |
1292 | 0 | switch (sourceChar) { |
1293 | 0 | case ISCII_INV: |
1294 | 0 | case EXT: |
1295 | 0 | case ATR: |
1296 | 0 | *contextCharToUnicode = (UChar)sourceChar; |
1297 | |
|
1298 | 0 | if (*toUnicodeStatus != missingCharMarker) { |
1299 | | /* Write the previous toUnicodeStatus, this was delayed to handle consonant clustering for Gurmukhi script. */ |
1300 | 0 | if (data->prevToUnicodeStatus) { |
1301 | 0 | WRITE_TO_TARGET_TO_U(args,source,target,args->offsets,(source-args->source -1),data->prevToUnicodeStatus,0,err); |
1302 | 0 | data->prevToUnicodeStatus = 0x0000; |
1303 | 0 | } |
1304 | 0 | WRITE_TO_TARGET_TO_U(args,source,target,args->offsets,(source-args->source -2),*toUnicodeStatus,data->currentDeltaToUnicode,err); |
1305 | 0 | *toUnicodeStatus = missingCharMarker; |
1306 | 0 | } |
1307 | 0 | continue; |
1308 | 0 | case ISCII_DANDA: |
1309 | | /* handle double danda*/ |
1310 | 0 | if (*contextCharToUnicode== ISCII_DANDA) { |
1311 | 0 | targetUniChar = DOUBLE_DANDA; |
1312 | | /* clear the context */ |
1313 | 0 | *contextCharToUnicode = NO_CHAR_MARKER; |
1314 | 0 | *toUnicodeStatus = missingCharMarker; |
1315 | 0 | } else { |
1316 | 0 | GET_MAPPING(sourceChar,targetUniChar,data); |
1317 | 0 | *contextCharToUnicode = sourceChar; |
1318 | 0 | } |
1319 | 0 | break; |
1320 | 0 | case ISCII_HALANT: |
1321 | | /* handle explicit halant */ |
1322 | 0 | if (*contextCharToUnicode == ISCII_HALANT) { |
1323 | 0 | targetUniChar = ZWNJ; |
1324 | | /* clear the context */ |
1325 | 0 | *contextCharToUnicode = NO_CHAR_MARKER; |
1326 | 0 | } else { |
1327 | 0 | GET_MAPPING(sourceChar,targetUniChar,data); |
1328 | 0 | *contextCharToUnicode = sourceChar; |
1329 | 0 | } |
1330 | 0 | break; |
1331 | 0 | case 0x0A: |
1332 | 0 | case 0x0D: |
1333 | 0 | data->resetToDefaultToUnicode = TRUE; |
1334 | 0 | GET_MAPPING(sourceChar,targetUniChar,data) |
1335 | 0 | ; |
1336 | 0 | *contextCharToUnicode = sourceChar; |
1337 | 0 | break; |
1338 | | |
1339 | 0 | case ISCII_VOWEL_SIGN_E: |
1340 | 0 | i=1; |
1341 | 0 | found=FALSE; |
1342 | 0 | for (; i<vowelSignESpecialCases[0][0]; i++) { |
1343 | 0 | U_ASSERT(i<UPRV_LENGTHOF(vowelSignESpecialCases)); |
1344 | 0 | if (vowelSignESpecialCases[i][0]==(uint8_t)*contextCharToUnicode) { |
1345 | 0 | targetUniChar=vowelSignESpecialCases[i][1]; |
1346 | 0 | found=TRUE; |
1347 | 0 | break; |
1348 | 0 | } |
1349 | 0 | } |
1350 | 0 | if (found) { |
1351 | | /* find out if the mapping is valid in this state */ |
1352 | 0 | if (validityTable[(uint8_t)targetUniChar] & data->currentMaskToUnicode) { |
1353 | | /*targetUniChar += data->currentDeltaToUnicode ;*/ |
1354 | 0 | *contextCharToUnicode= NO_CHAR_MARKER; |
1355 | 0 | *toUnicodeStatus = missingCharMarker; |
1356 | 0 | break; |
1357 | 0 | } |
1358 | 0 | } |
1359 | 0 | GET_MAPPING(sourceChar,targetUniChar,data); |
1360 | 0 | *contextCharToUnicode = sourceChar; |
1361 | 0 | break; |
1362 | | |
1363 | 0 | case ISCII_NUKTA: |
1364 | | /* handle soft halant */ |
1365 | 0 | if (*contextCharToUnicode == ISCII_HALANT) { |
1366 | 0 | targetUniChar = ZWJ; |
1367 | | /* clear the context */ |
1368 | 0 | *contextCharToUnicode = NO_CHAR_MARKER; |
1369 | 0 | break; |
1370 | 0 | } else if (data->currentDeltaToUnicode == PNJ_DELTA && data->contextCharToUnicode == 0xc0) { |
1371 | | /* Write the previous toUnicodeStatus, this was delayed to handle consonant clustering for Gurmukhi script. */ |
1372 | 0 | if (data->prevToUnicodeStatus) { |
1373 | 0 | WRITE_TO_TARGET_TO_U(args,source,target,args->offsets,(source-args->source -1),data->prevToUnicodeStatus,0,err); |
1374 | 0 | data->prevToUnicodeStatus = 0x0000; |
1375 | 0 | } |
1376 | | /* We got here because ISCII_NUKTA was preceded by 0xc0 and we are converting Gurmukhi. |
1377 | | * In that case we must convert (0xc0 0xe9) to (\u0a5c\u0a4d\u0a39). |
1378 | | */ |
1379 | 0 | targetUniChar = PNJ_RRA; |
1380 | 0 | WRITE_TO_TARGET_TO_U(args, source, target, args->offsets, (source-args->source)-2, targetUniChar, 0, err); |
1381 | 0 | if (U_SUCCESS(*err)) { |
1382 | 0 | targetUniChar = PNJ_SIGN_VIRAMA; |
1383 | 0 | WRITE_TO_TARGET_TO_U(args, source, target, args->offsets, (source-args->source)-2, targetUniChar, 0, err); |
1384 | 0 | if (U_SUCCESS(*err)) { |
1385 | 0 | targetUniChar = PNJ_HA; |
1386 | 0 | WRITE_TO_TARGET_TO_U(args, source, target, args->offsets, (source-args->source)-2, targetUniChar, 0, err); |
1387 | 0 | } else { |
1388 | 0 | args->converter->UCharErrorBuffer[args->converter->UCharErrorBufferLength++]= PNJ_HA; |
1389 | 0 | } |
1390 | 0 | } else { |
1391 | 0 | args->converter->UCharErrorBuffer[args->converter->UCharErrorBufferLength++]= PNJ_SIGN_VIRAMA; |
1392 | 0 | args->converter->UCharErrorBuffer[args->converter->UCharErrorBufferLength++]= PNJ_HA; |
1393 | 0 | } |
1394 | 0 | *toUnicodeStatus = missingCharMarker; |
1395 | 0 | data->contextCharToUnicode = NO_CHAR_MARKER; |
1396 | 0 | continue; |
1397 | 0 | } else { |
1398 | | /* try to handle <CHAR> + ISCII_NUKTA special mappings */ |
1399 | 0 | i=1; |
1400 | 0 | found =FALSE; |
1401 | 0 | for (; i<nuktaSpecialCases[0][0]; i++) { |
1402 | 0 | if (nuktaSpecialCases[i][0]==(uint8_t) |
1403 | 0 | *contextCharToUnicode) { |
1404 | 0 | targetUniChar=nuktaSpecialCases[i][1]; |
1405 | 0 | found =TRUE; |
1406 | 0 | break; |
1407 | 0 | } |
1408 | 0 | } |
1409 | 0 | if (found) { |
1410 | | /* find out if the mapping is valid in this state */ |
1411 | 0 | if (validityTable[(uint8_t)targetUniChar] & data->currentMaskToUnicode) { |
1412 | | /*targetUniChar += data->currentDeltaToUnicode ;*/ |
1413 | 0 | *contextCharToUnicode= NO_CHAR_MARKER; |
1414 | 0 | *toUnicodeStatus = missingCharMarker; |
1415 | 0 | if (data->currentDeltaToUnicode == PNJ_DELTA) { |
1416 | | /* Write the previous toUnicodeStatus, this was delayed to handle consonant clustering for Gurmukhi script. */ |
1417 | 0 | if (data->prevToUnicodeStatus) { |
1418 | 0 | WRITE_TO_TARGET_TO_U(args,source,target,args->offsets,(source-args->source -1),data->prevToUnicodeStatus,0,err); |
1419 | 0 | data->prevToUnicodeStatus = 0x0000; |
1420 | 0 | } |
1421 | 0 | WRITE_TO_TARGET_TO_U(args,source,target,args->offsets,(source-args->source -2),targetUniChar,data->currentDeltaToUnicode,err); |
1422 | 0 | continue; |
1423 | 0 | } |
1424 | 0 | break; |
1425 | 0 | } |
1426 | | /* else fall through to default */ |
1427 | 0 | } |
1428 | | /* else fall through to default */ |
1429 | 0 | U_FALLTHROUGH; |
1430 | 0 | } |
1431 | 0 | default:GET_MAPPING(sourceChar,targetUniChar,data) |
1432 | 0 | ; |
1433 | 0 | *contextCharToUnicode = sourceChar; |
1434 | 0 | break; |
1435 | 0 | } |
1436 | | |
1437 | 0 | if (*toUnicodeStatus != missingCharMarker) { |
1438 | | /* Check to make sure that consonant clusters are handled correct for Gurmukhi script. */ |
1439 | 0 | if (data->currentDeltaToUnicode == PNJ_DELTA && data->prevToUnicodeStatus != 0 && isPNJConsonant(data->prevToUnicodeStatus) && |
1440 | 0 | (*toUnicodeStatus + PNJ_DELTA) == PNJ_SIGN_VIRAMA && ((UChar32)(targetUniChar + PNJ_DELTA) == data->prevToUnicodeStatus)) { |
1441 | | /* Consonant clusters C + HALANT + C should be encoded as ADHAK + C */ |
1442 | 0 | offset = (int)(source-args->source - 3); |
1443 | 0 | tempTargetUniChar = PNJ_ADHAK; /* This is necessary to avoid some compiler warnings. */ |
1444 | 0 | WRITE_TO_TARGET_TO_U(args,source,target,args->offsets,offset,tempTargetUniChar,0,err); |
1445 | 0 | WRITE_TO_TARGET_TO_U(args,source,target,args->offsets,offset,data->prevToUnicodeStatus,0,err); |
1446 | 0 | data->prevToUnicodeStatus = 0x0000; /* reset the previous unicode code point */ |
1447 | 0 | *toUnicodeStatus = missingCharMarker; |
1448 | 0 | continue; |
1449 | 0 | } else { |
1450 | | /* Write the previous toUnicodeStatus, this was delayed to handle consonant clustering for Gurmukhi script. */ |
1451 | 0 | if (data->prevToUnicodeStatus) { |
1452 | 0 | WRITE_TO_TARGET_TO_U(args,source,target,args->offsets,(source-args->source -1),data->prevToUnicodeStatus,0,err); |
1453 | 0 | data->prevToUnicodeStatus = 0x0000; |
1454 | 0 | } |
1455 | | /* Check to make sure that Bindi and Tippi are handled correctly for Gurmukhi script. |
1456 | | * If 0xA2 is preceded by a codepoint in the PNJ_BINDI_TIPPI_SET then the target codepoint should be Tippi instead of Bindi. |
1457 | | */ |
1458 | 0 | if (data->currentDeltaToUnicode == PNJ_DELTA && (targetUniChar + PNJ_DELTA) == PNJ_BINDI && isPNJBindiTippi((*toUnicodeStatus + PNJ_DELTA))) { |
1459 | 0 | targetUniChar = PNJ_TIPPI - PNJ_DELTA; |
1460 | 0 | WRITE_TO_TARGET_TO_U(args,source,target,args->offsets,(source-args->source -2),*toUnicodeStatus,PNJ_DELTA,err); |
1461 | 0 | } else if (data->currentDeltaToUnicode == PNJ_DELTA && (targetUniChar + PNJ_DELTA) == PNJ_SIGN_VIRAMA && isPNJConsonant((*toUnicodeStatus + PNJ_DELTA))) { |
1462 | | /* Store the current toUnicodeStatus code point for later handling of consonant cluster in Gurmukhi. */ |
1463 | 0 | data->prevToUnicodeStatus = *toUnicodeStatus + PNJ_DELTA; |
1464 | 0 | } else { |
1465 | | /* write the previously mapped codepoint */ |
1466 | 0 | WRITE_TO_TARGET_TO_U(args,source,target,args->offsets,(source-args->source -2),*toUnicodeStatus,data->currentDeltaToUnicode,err); |
1467 | 0 | } |
1468 | 0 | } |
1469 | 0 | *toUnicodeStatus = missingCharMarker; |
1470 | 0 | } |
1471 | | |
1472 | 0 | if (targetUniChar != missingCharMarker) { |
1473 | | /* now save the targetUniChar for delayed write */ |
1474 | 0 | *toUnicodeStatus = (UChar) targetUniChar; |
1475 | 0 | if (data->resetToDefaultToUnicode==TRUE) { |
1476 | 0 | data->currentDeltaToUnicode = data->defDeltaToUnicode; |
1477 | 0 | data->currentMaskToUnicode = data->defMaskToUnicode; |
1478 | 0 | data->resetToDefaultToUnicode=FALSE; |
1479 | 0 | } |
1480 | 0 | } else { |
1481 | | |
1482 | | /* we reach here only if targetUniChar == missingCharMarker |
1483 | | * so assign codes to reason and err |
1484 | | */ |
1485 | 0 | *err = U_INVALID_CHAR_FOUND; |
1486 | 0 | CALLBACK: |
1487 | 0 | args->converter->toUBytes[0] = (uint8_t) sourceChar; |
1488 | 0 | args->converter->toULength = 1; |
1489 | 0 | break; |
1490 | 0 | } |
1491 | |
|
1492 | 0 | } else { |
1493 | 0 | *err =U_BUFFER_OVERFLOW_ERROR; |
1494 | 0 | break; |
1495 | 0 | } |
1496 | 0 | } |
1497 | | |
1498 | 0 | if (U_SUCCESS(*err) && args->flush && source == sourceLimit) { |
1499 | | /* end of the input stream */ |
1500 | 0 | UConverter *cnv = args->converter; |
1501 | |
|
1502 | 0 | if (*contextCharToUnicode==ATR || *contextCharToUnicode==EXT || *contextCharToUnicode==ISCII_INV) { |
1503 | | /* set toUBytes[] */ |
1504 | 0 | cnv->toUBytes[0] = (uint8_t)*contextCharToUnicode; |
1505 | 0 | cnv->toULength = 1; |
1506 | | |
1507 | | /* avoid looping on truncated sequences */ |
1508 | 0 | *contextCharToUnicode = NO_CHAR_MARKER; |
1509 | 0 | } else { |
1510 | 0 | cnv->toULength = 0; |
1511 | 0 | } |
1512 | |
|
1513 | 0 | if (*toUnicodeStatus != missingCharMarker) { |
1514 | | /* output a remaining target character */ |
1515 | 0 | WRITE_TO_TARGET_TO_U(args,source,target,args->offsets,(source - args->source -1),*toUnicodeStatus,data->currentDeltaToUnicode,err); |
1516 | 0 | *toUnicodeStatus = missingCharMarker; |
1517 | 0 | } |
1518 | 0 | } |
1519 | |
|
1520 | 0 | args->target = target; |
1521 | 0 | args->source = source; |
1522 | 0 | } |
1523 | | |
1524 | | /* structure for SafeClone calculations */ |
1525 | | struct cloneISCIIStruct { |
1526 | | UConverter cnv; |
1527 | | UConverterDataISCII mydata; |
1528 | | }; |
1529 | | |
1530 | | static UConverter * U_CALLCONV |
1531 | | _ISCII_SafeClone(const UConverter *cnv, |
1532 | | void *stackBuffer, |
1533 | | int32_t *pBufferSize, |
1534 | | UErrorCode *status) |
1535 | 0 | { |
1536 | 0 | struct cloneISCIIStruct * localClone; |
1537 | 0 | int32_t bufferSizeNeeded = sizeof(struct cloneISCIIStruct); |
1538 | |
|
1539 | 0 | if (U_FAILURE(*status)) { |
1540 | 0 | return 0; |
1541 | 0 | } |
1542 | | |
1543 | 0 | if (*pBufferSize == 0) { /* 'preflighting' request - set needed size into *pBufferSize */ |
1544 | 0 | *pBufferSize = bufferSizeNeeded; |
1545 | 0 | return 0; |
1546 | 0 | } |
1547 | | |
1548 | 0 | localClone = (struct cloneISCIIStruct *)stackBuffer; |
1549 | | /* ucnv.c/ucnv_safeClone() copied the main UConverter already */ |
1550 | |
|
1551 | 0 | uprv_memcpy(&localClone->mydata, cnv->extraInfo, sizeof(UConverterDataISCII)); |
1552 | 0 | localClone->cnv.extraInfo = &localClone->mydata; |
1553 | 0 | localClone->cnv.isExtraLocal = TRUE; |
1554 | |
|
1555 | 0 | return &localClone->cnv; |
1556 | 0 | } |
1557 | | |
1558 | | static void U_CALLCONV |
1559 | | _ISCIIGetUnicodeSet(const UConverter *cnv, |
1560 | | const USetAdder *sa, |
1561 | | UConverterUnicodeSet which, |
1562 | | UErrorCode *pErrorCode) |
1563 | 0 | { |
1564 | 0 | (void)cnv; |
1565 | 0 | (void)which; |
1566 | 0 | (void)pErrorCode; |
1567 | 0 | int32_t idx, script; |
1568 | 0 | uint8_t mask; |
1569 | | |
1570 | | /* Since all ISCII versions allow switching to other ISCII |
1571 | | scripts, we add all roundtrippable characters to this set. */ |
1572 | 0 | sa->addRange(sa->set, 0, ASCII_END); |
1573 | 0 | for (script = DEVANAGARI; script <= MALAYALAM; script++) { |
1574 | 0 | mask = (uint8_t)(lookupInitialData[script].maskEnum); |
1575 | 0 | for (idx = 0; idx < DELTA; idx++) { |
1576 | | /* added check for TELUGU character */ |
1577 | 0 | if ((validityTable[idx] & mask) || (script==TELUGU && idx==0x31)) { |
1578 | 0 | sa->add(sa->set, idx + (script * DELTA) + INDIC_BLOCK_BEGIN); |
1579 | 0 | } |
1580 | 0 | } |
1581 | 0 | } |
1582 | 0 | sa->add(sa->set, DANDA); |
1583 | 0 | sa->add(sa->set, DOUBLE_DANDA); |
1584 | 0 | sa->add(sa->set, ZWNJ); |
1585 | 0 | sa->add(sa->set, ZWJ); |
1586 | 0 | } |
1587 | | U_CDECL_END |
1588 | | static const UConverterImpl _ISCIIImpl={ |
1589 | | |
1590 | | UCNV_ISCII, |
1591 | | |
1592 | | NULL, |
1593 | | NULL, |
1594 | | |
1595 | | _ISCIIOpen, |
1596 | | _ISCIIClose, |
1597 | | _ISCIIReset, |
1598 | | |
1599 | | UConverter_toUnicode_ISCII_OFFSETS_LOGIC, |
1600 | | UConverter_toUnicode_ISCII_OFFSETS_LOGIC, |
1601 | | UConverter_fromUnicode_ISCII_OFFSETS_LOGIC, |
1602 | | UConverter_fromUnicode_ISCII_OFFSETS_LOGIC, |
1603 | | NULL, |
1604 | | |
1605 | | NULL, |
1606 | | _ISCIIgetName, |
1607 | | NULL, |
1608 | | _ISCII_SafeClone, |
1609 | | _ISCIIGetUnicodeSet, |
1610 | | NULL, |
1611 | | NULL |
1612 | | }; |
1613 | | |
1614 | | static const UConverterStaticData _ISCIIStaticData={ |
1615 | | sizeof(UConverterStaticData), |
1616 | | "ISCII", |
1617 | | 0, |
1618 | | UCNV_IBM, |
1619 | | UCNV_ISCII, |
1620 | | 1, |
1621 | | 4, |
1622 | | { 0x1a, 0, 0, 0 }, |
1623 | | 0x1, |
1624 | | FALSE, |
1625 | | FALSE, |
1626 | | 0x0, |
1627 | | 0x0, |
1628 | | { 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0 }, /* reserved */ |
1629 | | |
1630 | | }; |
1631 | | |
1632 | | const UConverterSharedData _ISCIIData= |
1633 | | UCNV_IMMUTABLE_SHARED_DATA_INITIALIZER(&_ISCIIStaticData, &_ISCIIImpl); |
1634 | | |
1635 | | #endif /* #if !UCONFIG_NO_LEGACY_CONVERSION */ |