OLD | NEW |
1 /* | 1 /* |
2 ******************************************************************************* | 2 ******************************************************************************* |
3 * | 3 * |
4 * Copyright (C) 1999-2004, International Business Machines | 4 * Copyright (C) 1999-2004, International Business Machines |
5 * Corporation and others. All Rights Reserved. | 5 * Corporation and others. All Rights Reserved. |
6 * | 6 * |
7 ******************************************************************************* | 7 ******************************************************************************* |
8 * file name: utf.h | 8 * file name: utf.h |
9 * encoding: US-ASCII | 9 * encoding: US-ASCII |
10 * tab size: 8 (not used) | 10 * tab size: 8 (not used) |
11 * indentation:4 | 11 * indentation:4 |
12 * | 12 * |
13 * created on: 1999sep09 | 13 * created on: 1999sep09 |
14 * created by: Markus W. Scherer | 14 * created by: Markus W. Scherer |
15 */ | 15 */ |
16 | 16 |
17 #ifndef BASE_THIRD_PARTY_ICU_ICU_UTF_H_ | 17 #ifndef BASE_THIRD_PARTY_ICU_ICU_UTF_H_ |
18 #define BASE_THIRD_PARTY_ICU_ICU_UTF_H_ | 18 #define BASE_THIRD_PARTY_ICU_ICU_UTF_H_ |
19 | 19 |
20 #include "base/basictypes.h" | 20 #include <stdint.h> |
21 | 21 |
22 namespace base_icu { | 22 namespace base_icu { |
23 | 23 |
24 typedef int32 UChar32; | 24 typedef int32_t UChar32; |
25 typedef uint16 UChar; | 25 typedef uint16_t UChar; |
26 typedef int8 UBool; | 26 typedef int8_t UBool; |
27 | 27 |
28 // General --------------------------------------------------------------------- | 28 // General --------------------------------------------------------------------- |
29 // from utf.h | 29 // from utf.h |
30 | 30 |
31 /** | 31 /** |
32 * This value is intended for sentinel values for APIs that | 32 * This value is intended for sentinel values for APIs that |
33 * (take or) return single code points (UChar32). | 33 * (take or) return single code points (UChar32). |
34 * It is outside of the Unicode code point range 0..0x10ffff. | 34 * It is outside of the Unicode code point range 0..0x10ffff. |
35 * | 35 * |
36 * For example, a "done" or "error" value in a new API | 36 * For example, a "done" or "error" value in a new API |
(...skipping 10 matching lines...) Expand all Loading... |
47 * @stable ICU 2.4 | 47 * @stable ICU 2.4 |
48 */ | 48 */ |
49 #define CBU_SENTINEL (-1) | 49 #define CBU_SENTINEL (-1) |
50 | 50 |
51 /** | 51 /** |
52 * Is this code point a Unicode noncharacter? | 52 * Is this code point a Unicode noncharacter? |
53 * @param c 32-bit code point | 53 * @param c 32-bit code point |
54 * @return TRUE or FALSE | 54 * @return TRUE or FALSE |
55 * @stable ICU 2.4 | 55 * @stable ICU 2.4 |
56 */ | 56 */ |
57 #define CBU_IS_UNICODE_NONCHAR(c) \ | 57 #define CBU_IS_UNICODE_NONCHAR(c) \ |
58 ((c)>=0xfdd0 && \ | 58 ((c) >= 0xfdd0 && ((uint32_t)(c) <= 0xfdef || ((c)&0xfffe) == 0xfffe) && \ |
59 ((uint32)(c)<=0xfdef || ((c)&0xfffe)==0xfffe) && \ | 59 (uint32_t)(c) <= 0x10ffff) |
60 (uint32)(c)<=0x10ffff) | |
61 | 60 |
62 /** | 61 /** |
63 * Is c a Unicode code point value (0..U+10ffff) | 62 * Is c a Unicode code point value (0..U+10ffff) |
64 * that can be assigned a character? | 63 * that can be assigned a character? |
65 * | 64 * |
66 * Code points that are not characters include: | 65 * Code points that are not characters include: |
67 * - single surrogate code points (U+d800..U+dfff, 2048 code points) | 66 * - single surrogate code points (U+d800..U+dfff, 2048 code points) |
68 * - the last two code points on each plane (U+__fffe and U+__ffff, 34 code poin
ts) | 67 * - the last two code points on each plane (U+__fffe and U+__ffff, 34 code poin
ts) |
69 * - U+fdd0..U+fdef (new with Unicode 3.1, 32 code points) | 68 * - U+fdd0..U+fdef (new with Unicode 3.1, 32 code points) |
70 * - the highest Unicode code point value is U+10ffff | 69 * - the highest Unicode code point value is U+10ffff |
71 * | 70 * |
72 * This means that all code points below U+d800 are character code points, | 71 * This means that all code points below U+d800 are character code points, |
73 * and that boundary is tested first for performance. | 72 * and that boundary is tested first for performance. |
74 * | 73 * |
75 * @param c 32-bit code point | 74 * @param c 32-bit code point |
76 * @return TRUE or FALSE | 75 * @return TRUE or FALSE |
77 * @stable ICU 2.4 | 76 * @stable ICU 2.4 |
78 */ | 77 */ |
79 #define CBU_IS_UNICODE_CHAR(c) \ | 78 #define CBU_IS_UNICODE_CHAR(c) \ |
80 ((uint32)(c)<0xd800 || \ | 79 ((uint32_t)(c) < 0xd800 || \ |
81 ((uint32)(c)>0xdfff && \ | 80 ((uint32_t)(c) > 0xdfff && (uint32_t)(c) <= 0x10ffff && \ |
82 (uint32)(c)<=0x10ffff && \ | 81 !CBU_IS_UNICODE_NONCHAR(c))) |
83 !CBU_IS_UNICODE_NONCHAR(c))) | |
84 | 82 |
85 /** | 83 /** |
86 * Is this code point a surrogate (U+d800..U+dfff)? | 84 * Is this code point a surrogate (U+d800..U+dfff)? |
87 * @param c 32-bit code point | 85 * @param c 32-bit code point |
88 * @return TRUE or FALSE | 86 * @return TRUE or FALSE |
89 * @stable ICU 2.4 | 87 * @stable ICU 2.4 |
90 */ | 88 */ |
91 #define CBU_IS_SURROGATE(c) (((c)&0xfffff800)==0xd800) | 89 #define CBU_IS_SURROGATE(c) (((c)&0xfffff800)==0xd800) |
92 | 90 |
93 /** | 91 /** |
94 * Assuming c is a surrogate code point (U_IS_SURROGATE(c)), | 92 * Assuming c is a surrogate code point (U_IS_SURROGATE(c)), |
95 * is it a lead surrogate? | 93 * is it a lead surrogate? |
96 * @param c 32-bit code point | 94 * @param c 32-bit code point |
97 * @return TRUE or FALSE | 95 * @return TRUE or FALSE |
98 * @stable ICU 2.4 | 96 * @stable ICU 2.4 |
99 */ | 97 */ |
100 #define CBU_IS_SURROGATE_LEAD(c) (((c)&0x400)==0) | 98 #define CBU_IS_SURROGATE_LEAD(c) (((c)&0x400)==0) |
101 | 99 |
102 | 100 |
103 // UTF-8 macros ---------------------------------------------------------------- | 101 // UTF-8 macros ---------------------------------------------------------------- |
104 // from utf8.h | 102 // from utf8.h |
105 | 103 |
106 extern const uint8 utf8_countTrailBytes[256]; | 104 extern const uint8_t utf8_countTrailBytes[256]; |
107 | 105 |
108 /** | 106 /** |
109 * Count the trail bytes for a UTF-8 lead byte. | 107 * Count the trail bytes for a UTF-8 lead byte. |
110 * @internal | 108 * @internal |
111 */ | 109 */ |
112 #define CBU8_COUNT_TRAIL_BYTES(leadByte) (base_icu::utf8_countTrailBytes[(uint8)
leadByte]) | 110 #define CBU8_COUNT_TRAIL_BYTES(leadByte) \ |
| 111 (base_icu::utf8_countTrailBytes[(uint8_t)leadByte]) |
113 | 112 |
114 /** | 113 /** |
115 * Mask a UTF-8 lead byte, leave only the lower bits that form part of the code
point value. | 114 * Mask a UTF-8 lead byte, leave only the lower bits that form part of the code
point value. |
116 * @internal | 115 * @internal |
117 */ | 116 */ |
118 #define CBU8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(coun
tTrailBytes)))-1) | 117 #define CBU8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(coun
tTrailBytes)))-1) |
119 | 118 |
120 /** | 119 /** |
121 * Does this code unit (byte) encode a code point by itself (US-ASCII 0..0x7f)? | 120 * Does this code unit (byte) encode a code point by itself (US-ASCII 0..0x7f)? |
122 * @param c 8-bit code unit (byte) | 121 * @param c 8-bit code unit (byte) |
123 * @return TRUE or FALSE | 122 * @return TRUE or FALSE |
124 * @stable ICU 2.4 | 123 * @stable ICU 2.4 |
125 */ | 124 */ |
126 #define CBU8_IS_SINGLE(c) (((c)&0x80)==0) | 125 #define CBU8_IS_SINGLE(c) (((c)&0x80)==0) |
127 | 126 |
128 /** | 127 /** |
129 * Is this code unit (byte) a UTF-8 lead byte? | 128 * Is this code unit (byte) a UTF-8 lead byte? |
130 * @param c 8-bit code unit (byte) | 129 * @param c 8-bit code unit (byte) |
131 * @return TRUE or FALSE | 130 * @return TRUE or FALSE |
132 * @stable ICU 2.4 | 131 * @stable ICU 2.4 |
133 */ | 132 */ |
134 #define CBU8_IS_LEAD(c) ((uint8)((c)-0xc0)<0x3e) | 133 #define CBU8_IS_LEAD(c) ((uint8_t)((c)-0xc0) < 0x3e) |
135 | 134 |
136 /** | 135 /** |
137 * Is this code unit (byte) a UTF-8 trail byte? | 136 * Is this code unit (byte) a UTF-8 trail byte? |
138 * @param c 8-bit code unit (byte) | 137 * @param c 8-bit code unit (byte) |
139 * @return TRUE or FALSE | 138 * @return TRUE or FALSE |
140 * @stable ICU 2.4 | 139 * @stable ICU 2.4 |
141 */ | 140 */ |
142 #define CBU8_IS_TRAIL(c) (((c)&0xc0)==0x80) | 141 #define CBU8_IS_TRAIL(c) (((c)&0xc0)==0x80) |
143 | 142 |
144 /** | 143 /** |
145 * How many code units (bytes) are used for the UTF-8 encoding | 144 * How many code units (bytes) are used for the UTF-8 encoding |
146 * of this Unicode code point? | 145 * of this Unicode code point? |
147 * @param c 32-bit code point | 146 * @param c 32-bit code point |
148 * @return 1..4, or 0 if c is a surrogate or not a Unicode code point | 147 * @return 1..4, or 0 if c is a surrogate or not a Unicode code point |
149 * @stable ICU 2.4 | 148 * @stable ICU 2.4 |
150 */ | 149 */ |
151 #define CBU8_LENGTH(c) \ | 150 #define CBU8_LENGTH(c) \ |
152 ((uint32)(c)<=0x7f ? 1 : \ | 151 ((uint32_t)(c) <= 0x7f \ |
153 ((uint32)(c)<=0x7ff ? 2 : \ | 152 ? 1 \ |
154 ((uint32)(c)<=0xd7ff ? 3 : \ | 153 : ((uint32_t)(c) <= 0x7ff \ |
155 ((uint32)(c)<=0xdfff || (uint32)(c)>0x10ffff ? 0 : \ | 154 ? 2 \ |
156 ((uint32)(c)<=0xffff ? 3 : 4)\ | 155 : ((uint32_t)(c) <= 0xd7ff \ |
157 ) \ | 156 ? 3 \ |
158 ) \ | 157 : ((uint32_t)(c) <= 0xdfff || (uint32_t)(c) > 0x10ffff \ |
159 ) \ | 158 ? 0 \ |
160 ) | 159 : ((uint32_t)(c) <= 0xffff ? 3 : 4))))) |
161 | 160 |
162 /** | 161 /** |
163 * The maximum number of UTF-8 code units (bytes) per Unicode code point (U+0000
..U+10ffff). | 162 * The maximum number of UTF-8 code units (bytes) per Unicode code point (U+0000
..U+10ffff). |
164 * @return 4 | 163 * @return 4 |
165 * @stable ICU 2.4 | 164 * @stable ICU 2.4 |
166 */ | 165 */ |
167 #define CBU8_MAX_LENGTH 4 | 166 #define CBU8_MAX_LENGTH 4 |
168 | 167 |
169 /** | 168 /** |
170 * Function for handling "next code point" with error-checking. | 169 * Function for handling "next code point" with error-checking. |
171 * @internal | 170 * @internal |
172 */ | 171 */ |
173 UChar32 utf8_nextCharSafeBody(const uint8 *s, int32 *pi, int32 length, UChar32 c
, UBool strict); | 172 UChar32 utf8_nextCharSafeBody(const uint8_t* s, |
| 173 int32_t* pi, |
| 174 int32_t length, |
| 175 UChar32 c, |
| 176 UBool strict); |
174 | 177 |
175 /** | 178 /** |
176 * Get a code point from a string at a code point boundary offset, | 179 * Get a code point from a string at a code point boundary offset, |
177 * and advance the offset to the next code point boundary. | 180 * and advance the offset to the next code point boundary. |
178 * (Post-incrementing forward iteration.) | 181 * (Post-incrementing forward iteration.) |
179 * "Safe" macro, checks for illegal sequences and for string boundaries. | 182 * "Safe" macro, checks for illegal sequences and for string boundaries. |
180 * | 183 * |
181 * The offset may point to the lead byte of a multi-byte sequence, | 184 * The offset may point to the lead byte of a multi-byte sequence, |
182 * in which case the macro will read the whole sequence. | 185 * in which case the macro will read the whole sequence. |
183 * If the offset points to a trail byte or an illegal UTF-8 sequence, then | 186 * If the offset points to a trail byte or an illegal UTF-8 sequence, then |
184 * c is set to a negative value. | 187 * c is set to a negative value. |
185 * | 188 * |
186 * @param s const uint8 * string | 189 * @param s const uint8_t * string |
187 * @param i string offset, i<length | 190 * @param i string offset, i<length |
188 * @param length string length | 191 * @param length string length |
189 * @param c output UChar32 variable, set to <0 in case of an error | 192 * @param c output UChar32 variable, set to <0 in case of an error |
190 * @see CBU8_NEXT_UNSAFE | 193 * @see CBU8_NEXT_UNSAFE |
191 * @stable ICU 2.4 | 194 * @stable ICU 2.4 |
192 */ | 195 */ |
193 #define CBU8_NEXT(s, i, length, c) { \ | 196 #define CBU8_NEXT(s, i, length, c) \ |
194 (c)=(s)[(i)++]; \ | 197 { \ |
195 if(((uint8)(c))>=0x80) { \ | 198 (c) = (s)[(i)++]; \ |
196 if(CBU8_IS_LEAD(c)) { \ | 199 if (((uint8_t)(c)) >= 0x80) { \ |
197 (c)=base_icu::utf8_nextCharSafeBody((const uint8 *)s, &(i), (int32)(
length), c, -1); \ | 200 if (CBU8_IS_LEAD(c)) { \ |
198 } else { \ | 201 (c) = base_icu::utf8_nextCharSafeBody((const uint8_t*)s, &(i), \ |
199 (c)=CBU_SENTINEL; \ | 202 (int32_t)(length), c, -1); \ |
200 } \ | 203 } else { \ |
201 } \ | 204 (c) = CBU_SENTINEL; \ |
202 } | 205 } \ |
| 206 } \ |
| 207 } |
203 | 208 |
204 /** | 209 /** |
205 * Append a code point to a string, overwriting 1 to 4 bytes. | 210 * Append a code point to a string, overwriting 1 to 4 bytes. |
206 * The offset points to the current end of the string contents | 211 * The offset points to the current end of the string contents |
207 * and is advanced (post-increment). | 212 * and is advanced (post-increment). |
208 * "Unsafe" macro, assumes a valid code point and sufficient space in the string
. | 213 * "Unsafe" macro, assumes a valid code point and sufficient space in the |
| 214 * string. |
209 * Otherwise, the result is undefined. | 215 * Otherwise, the result is undefined. |
210 * | 216 * |
211 * @param s const uint8 * string buffer | 217 * @param s const uint8_t * string buffer |
212 * @param i string offset | 218 * @param i string offset |
213 * @param c code point to append | 219 * @param c code point to append |
214 * @see CBU8_APPEND | 220 * @see CBU8_APPEND |
215 * @stable ICU 2.4 | 221 * @stable ICU 2.4 |
216 */ | 222 */ |
217 #define CBU8_APPEND_UNSAFE(s, i, c) { \ | 223 #define CBU8_APPEND_UNSAFE(s, i, c) \ |
218 if((uint32)(c)<=0x7f) { \ | 224 { \ |
219 (s)[(i)++]=(uint8)(c); \ | 225 if ((uint32_t)(c) <= 0x7f) { \ |
220 } else { \ | 226 (s)[(i)++] = (uint8_t)(c); \ |
221 if((uint32)(c)<=0x7ff) { \ | 227 } else { \ |
222 (s)[(i)++]=(uint8)(((c)>>6)|0xc0); \ | 228 if ((uint32_t)(c) <= 0x7ff) { \ |
223 } else { \ | 229 (s)[(i)++] = (uint8_t)(((c) >> 6) | 0xc0); \ |
224 if((uint32)(c)<=0xffff) { \ | 230 } else { \ |
225 (s)[(i)++]=(uint8)(((c)>>12)|0xe0); \ | 231 if ((uint32_t)(c) <= 0xffff) { \ |
226 } else { \ | 232 (s)[(i)++] = (uint8_t)(((c) >> 12) | 0xe0); \ |
227 (s)[(i)++]=(uint8)(((c)>>18)|0xf0); \ | 233 } else { \ |
228 (s)[(i)++]=(uint8)((((c)>>12)&0x3f)|0x80); \ | 234 (s)[(i)++] = (uint8_t)(((c) >> 18) | 0xf0); \ |
229 } \ | 235 (s)[(i)++] = (uint8_t)((((c) >> 12) & 0x3f) | 0x80); \ |
230 (s)[(i)++]=(uint8)((((c)>>6)&0x3f)|0x80); \ | 236 } \ |
231 } \ | 237 (s)[(i)++] = (uint8_t)((((c) >> 6) & 0x3f) | 0x80); \ |
232 (s)[(i)++]=(uint8)(((c)&0x3f)|0x80); \ | 238 } \ |
233 } \ | 239 (s)[(i)++] = (uint8_t)(((c)&0x3f) | 0x80); \ |
234 } | 240 } \ |
| 241 } |
235 | 242 |
236 // UTF-16 macros --------------------------------------------------------------- | 243 // UTF-16 macros --------------------------------------------------------------- |
237 // from utf16.h | 244 // from utf16.h |
238 | 245 |
239 /** | 246 /** |
240 * Does this code unit alone encode a code point (BMP, not a surrogate)? | 247 * Does this code unit alone encode a code point (BMP, not a surrogate)? |
241 * @param c 16-bit code unit | 248 * @param c 16-bit code unit |
242 * @return TRUE or FALSE | 249 * @return TRUE or FALSE |
243 * @stable ICU 2.4 | 250 * @stable ICU 2.4 |
244 */ | 251 */ |
(...skipping 73 matching lines...) Expand 10 before | Expand all | Expand 10 after Loading... |
318 #define CBU16_TRAIL(supplementary) \ | 325 #define CBU16_TRAIL(supplementary) \ |
319 (base_icu::UChar)(((supplementary)&0x3ff)|0xdc00) | 326 (base_icu::UChar)(((supplementary)&0x3ff)|0xdc00) |
320 | 327 |
321 /** | 328 /** |
322 * How many 16-bit code units are used to encode this Unicode code point? (1 or
2) | 329 * How many 16-bit code units are used to encode this Unicode code point? (1 or
2) |
323 * The result is not defined if c is not a Unicode code point (U+0000..U+10ffff)
. | 330 * The result is not defined if c is not a Unicode code point (U+0000..U+10ffff)
. |
324 * @param c 32-bit code point | 331 * @param c 32-bit code point |
325 * @return 1 or 2 | 332 * @return 1 or 2 |
326 * @stable ICU 2.4 | 333 * @stable ICU 2.4 |
327 */ | 334 */ |
328 #define CBU16_LENGTH(c) ((uint32)(c)<=0xffff ? 1 : 2) | 335 #define CBU16_LENGTH(c) ((uint32_t)(c) <= 0xffff ? 1 : 2) |
329 | 336 |
330 /** | 337 /** |
331 * The maximum number of 16-bit code units per Unicode code point (U+0000..U+10f
fff). | 338 * The maximum number of 16-bit code units per Unicode code point (U+0000..U+10f
fff). |
332 * @return 2 | 339 * @return 2 |
333 * @stable ICU 2.4 | 340 * @stable ICU 2.4 |
334 */ | 341 */ |
335 #define CBU16_MAX_LENGTH 2 | 342 #define CBU16_MAX_LENGTH 2 |
336 | 343 |
337 /** | 344 /** |
338 * Get a code point from a string at a code point boundary offset, | 345 * Get a code point from a string at a code point boundary offset, |
339 * and advance the offset to the next code point boundary. | 346 * and advance the offset to the next code point boundary. |
340 * (Post-incrementing forward iteration.) | 347 * (Post-incrementing forward iteration.) |
341 * "Safe" macro, handles unpaired surrogates and checks for string boundaries. | 348 * "Safe" macro, handles unpaired surrogates and checks for string boundaries. |
342 * | 349 * |
343 * The offset may point to the lead surrogate unit | 350 * The offset may point to the lead surrogate unit |
344 * for a supplementary code point, in which case the macro will read | 351 * for a supplementary code point, in which case the macro will read |
345 * the following trail surrogate as well. | 352 * the following trail surrogate as well. |
346 * If the offset points to a trail surrogate or | 353 * If the offset points to a trail surrogate or |
347 * to a single, unpaired lead surrogate, then that itself | 354 * to a single, unpaired lead surrogate, then that itself |
348 * will be returned as the code point. | 355 * will be returned as the code point. |
349 * | 356 * |
350 * @param s const UChar * string | 357 * @param s const UChar * string |
351 * @param i string offset, i<length | 358 * @param i string offset, i<length |
352 * @param length string length | 359 * @param length string length |
353 * @param c output UChar32 variable | 360 * @param c output UChar32 variable |
354 * @stable ICU 2.4 | 361 * @stable ICU 2.4 |
355 */ | 362 */ |
356 #define CBU16_NEXT(s, i, length, c) { \ | 363 #define CBU16_NEXT(s, i, length, c) \ |
357 (c)=(s)[(i)++]; \ | 364 { \ |
358 if(CBU16_IS_LEAD(c)) { \ | 365 (c) = (s)[(i)++]; \ |
359 uint16 __c2; \ | 366 if (CBU16_IS_LEAD(c)) { \ |
360 if((i)<(length) && CBU16_IS_TRAIL(__c2=(s)[(i)])) { \ | 367 uint16_t __c2; \ |
361 ++(i); \ | 368 if ((i) < (length) && CBU16_IS_TRAIL(__c2 = (s)[(i)])) { \ |
362 (c)=CBU16_GET_SUPPLEMENTARY((c), __c2); \ | 369 ++(i); \ |
363 } \ | 370 (c) = CBU16_GET_SUPPLEMENTARY((c), __c2); \ |
364 } \ | 371 } \ |
365 } | 372 } \ |
| 373 } |
366 | 374 |
367 /** | 375 /** |
368 * Append a code point to a string, overwriting 1 or 2 code units. | 376 * Append a code point to a string, overwriting 1 or 2 code units. |
369 * The offset points to the current end of the string contents | 377 * The offset points to the current end of the string contents |
370 * and is advanced (post-increment). | 378 * and is advanced (post-increment). |
371 * "Unsafe" macro, assumes a valid code point and sufficient space in the string
. | 379 * "Unsafe" macro, assumes a valid code point and sufficient space in the string
. |
372 * Otherwise, the result is undefined. | 380 * Otherwise, the result is undefined. |
373 * | 381 * |
374 * @param s const UChar * string buffer | 382 * @param s const UChar * string buffer |
375 * @param i string offset | 383 * @param i string offset |
376 * @param c code point to append | 384 * @param c code point to append |
377 * @see CBU16_APPEND | 385 * @see CBU16_APPEND |
378 * @stable ICU 2.4 | 386 * @stable ICU 2.4 |
379 */ | 387 */ |
380 #define CBU16_APPEND_UNSAFE(s, i, c) { \ | 388 #define CBU16_APPEND_UNSAFE(s, i, c) \ |
381 if((uint32)(c)<=0xffff) { \ | 389 { \ |
382 (s)[(i)++]=(uint16)(c); \ | 390 if ((uint32_t)(c) <= 0xffff) { \ |
383 } else { \ | 391 (s)[(i)++] = (uint16_t)(c); \ |
384 (s)[(i)++]=(uint16)(((c)>>10)+0xd7c0); \ | 392 } else { \ |
385 (s)[(i)++]=(uint16)(((c)&0x3ff)|0xdc00); \ | 393 (s)[(i)++] = (uint16_t)(((c) >> 10) + 0xd7c0); \ |
386 } \ | 394 (s)[(i)++] = (uint16_t)(((c)&0x3ff) | 0xdc00); \ |
387 } | 395 } \ |
| 396 } |
388 | 397 |
389 } // namesapce base_icu | 398 } // namesapce base_icu |
390 | 399 |
391 #endif // BASE_THIRD_PARTY_ICU_ICU_UTF_H_ | 400 #endif // BASE_THIRD_PARTY_ICU_ICU_UTF_H_ |
OLD | NEW |