1.1 --- /dev/null Thu Jan 01 00:00:00 1970 +0000
1.2 +++ b/security/sandbox/chromium/base/third_party/icu/icu_utf.h Wed Dec 31 06:09:35 2014 +0100
1.3 @@ -0,0 +1,388 @@
1.4 +/*
1.5 +*******************************************************************************
1.6 +*
1.7 +* Copyright (C) 1999-2004, International Business Machines
1.8 +* Corporation and others. All Rights Reserved.
1.9 +*
1.10 +*******************************************************************************
1.11 +* file name: utf.h
1.12 +* encoding: US-ASCII
1.13 +* tab size: 8 (not used)
1.14 +* indentation:4
1.15 +*
1.16 +* created on: 1999sep09
1.17 +* created by: Markus W. Scherer
1.18 +*/
1.19 +
1.20 +#ifndef BASE_THIRD_PARTY_ICU_ICU_UTF_H_
1.21 +#define BASE_THIRD_PARTY_ICU_ICU_UTF_H_
1.22 +
1.23 +#include "base/basictypes.h"
1.24 +
1.25 +namespace base_icu {
1.26 +
1.27 +typedef uint32 UChar32;
1.28 +typedef int8 UBool;
1.29 +
1.30 +// General ---------------------------------------------------------------------
1.31 +// from utf.h
1.32 +
1.33 +/**
1.34 + * This value is intended for sentinel values for APIs that
1.35 + * (take or) return single code points (UChar32).
1.36 + * It is outside of the Unicode code point range 0..0x10ffff.
1.37 + *
1.38 + * For example, a "done" or "error" value in a new API
1.39 + * could be indicated with CBU_SENTINEL.
1.40 + *
1.41 + * ICU APIs designed before ICU 2.4 usually define service-specific "done"
1.42 + * values, mostly 0xffff.
1.43 + * Those may need to be distinguished from
1.44 + * actual U+ffff text contents by calling functions like
1.45 + * CharacterIterator::hasNext() or UnicodeString::length().
1.46 + *
1.47 + * @return -1
1.48 + * @see UChar32
1.49 + * @stable ICU 2.4
1.50 + */
1.51 +#define CBU_SENTINEL (-1)
1.52 +
1.53 +/**
1.54 + * Is this code point a Unicode noncharacter?
1.55 + * @param c 32-bit code point
1.56 + * @return TRUE or FALSE
1.57 + * @stable ICU 2.4
1.58 + */
1.59 +#define CBU_IS_UNICODE_NONCHAR(c) \
1.60 + ((c)>=0xfdd0 && \
1.61 + ((uint32)(c)<=0xfdef || ((c)&0xfffe)==0xfffe) && \
1.62 + (uint32)(c)<=0x10ffff)
1.63 +
1.64 +/**
1.65 + * Is c a Unicode code point value (0..U+10ffff)
1.66 + * that can be assigned a character?
1.67 + *
1.68 + * Code points that are not characters include:
1.69 + * - single surrogate code points (U+d800..U+dfff, 2048 code points)
1.70 + * - the last two code points on each plane (U+__fffe and U+__ffff, 34 code points)
1.71 + * - U+fdd0..U+fdef (new with Unicode 3.1, 32 code points)
1.72 + * - the highest Unicode code point value is U+10ffff
1.73 + *
1.74 + * This means that all code points below U+d800 are character code points,
1.75 + * and that boundary is tested first for performance.
1.76 + *
1.77 + * @param c 32-bit code point
1.78 + * @return TRUE or FALSE
1.79 + * @stable ICU 2.4
1.80 + */
1.81 +#define CBU_IS_UNICODE_CHAR(c) \
1.82 + ((uint32)(c)<0xd800 || \
1.83 + ((uint32)(c)>0xdfff && \
1.84 + (uint32)(c)<=0x10ffff && \
1.85 + !CBU_IS_UNICODE_NONCHAR(c)))
1.86 +
1.87 +/**
1.88 + * Is this code point a surrogate (U+d800..U+dfff)?
1.89 + * @param c 32-bit code point
1.90 + * @return TRUE or FALSE
1.91 + * @stable ICU 2.4
1.92 + */
1.93 +#define CBU_IS_SURROGATE(c) (((c)&0xfffff800)==0xd800)
1.94 +
1.95 +/**
1.96 + * Assuming c is a surrogate code point (U_IS_SURROGATE(c)),
1.97 + * is it a lead surrogate?
1.98 + * @param c 32-bit code point
1.99 + * @return TRUE or FALSE
1.100 + * @stable ICU 2.4
1.101 + */
1.102 +#define CBU_IS_SURROGATE_LEAD(c) (((c)&0x400)==0)
1.103 +
1.104 +
1.105 +// UTF-8 macros ----------------------------------------------------------------
1.106 +// from utf8.h
1.107 +
1.108 +extern const uint8 utf8_countTrailBytes[256];
1.109 +
1.110 +/**
1.111 + * Count the trail bytes for a UTF-8 lead byte.
1.112 + * @internal
1.113 + */
1.114 +#define CBU8_COUNT_TRAIL_BYTES(leadByte) (base_icu::utf8_countTrailBytes[(uint8)leadByte])
1.115 +
1.116 +/**
1.117 + * Mask a UTF-8 lead byte, leave only the lower bits that form part of the code point value.
1.118 + * @internal
1.119 + */
1.120 +#define CBU8_MASK_LEAD_BYTE(leadByte, countTrailBytes) ((leadByte)&=(1<<(6-(countTrailBytes)))-1)
1.121 +
1.122 +/**
1.123 + * Does this code unit (byte) encode a code point by itself (US-ASCII 0..0x7f)?
1.124 + * @param c 8-bit code unit (byte)
1.125 + * @return TRUE or FALSE
1.126 + * @stable ICU 2.4
1.127 + */
1.128 +#define CBU8_IS_SINGLE(c) (((c)&0x80)==0)
1.129 +
1.130 +/**
1.131 + * Is this code unit (byte) a UTF-8 lead byte?
1.132 + * @param c 8-bit code unit (byte)
1.133 + * @return TRUE or FALSE
1.134 + * @stable ICU 2.4
1.135 + */
1.136 +#define CBU8_IS_LEAD(c) ((uint8)((c)-0xc0)<0x3e)
1.137 +
1.138 +/**
1.139 + * Is this code unit (byte) a UTF-8 trail byte?
1.140 + * @param c 8-bit code unit (byte)
1.141 + * @return TRUE or FALSE
1.142 + * @stable ICU 2.4
1.143 + */
1.144 +#define CBU8_IS_TRAIL(c) (((c)&0xc0)==0x80)
1.145 +
1.146 +/**
1.147 + * How many code units (bytes) are used for the UTF-8 encoding
1.148 + * of this Unicode code point?
1.149 + * @param c 32-bit code point
1.150 + * @return 1..4, or 0 if c is a surrogate or not a Unicode code point
1.151 + * @stable ICU 2.4
1.152 + */
1.153 +#define CBU8_LENGTH(c) \
1.154 + ((uint32)(c)<=0x7f ? 1 : \
1.155 + ((uint32)(c)<=0x7ff ? 2 : \
1.156 + ((uint32)(c)<=0xd7ff ? 3 : \
1.157 + ((uint32)(c)<=0xdfff || (uint32)(c)>0x10ffff ? 0 : \
1.158 + ((uint32)(c)<=0xffff ? 3 : 4)\
1.159 + ) \
1.160 + ) \
1.161 + ) \
1.162 + )
1.163 +
1.164 +/**
1.165 + * The maximum number of UTF-8 code units (bytes) per Unicode code point (U+0000..U+10ffff).
1.166 + * @return 4
1.167 + * @stable ICU 2.4
1.168 + */
1.169 +#define CBU8_MAX_LENGTH 4
1.170 +
1.171 +/**
1.172 + * Function for handling "next code point" with error-checking.
1.173 + * @internal
1.174 + */
1.175 +UChar32 utf8_nextCharSafeBody(const uint8 *s, int32 *pi, int32 length, UChar32 c, UBool strict);
1.176 +
1.177 +/**
1.178 + * Get a code point from a string at a code point boundary offset,
1.179 + * and advance the offset to the next code point boundary.
1.180 + * (Post-incrementing forward iteration.)
1.181 + * "Safe" macro, checks for illegal sequences and for string boundaries.
1.182 + *
1.183 + * The offset may point to the lead byte of a multi-byte sequence,
1.184 + * in which case the macro will read the whole sequence.
1.185 + * If the offset points to a trail byte or an illegal UTF-8 sequence, then
1.186 + * c is set to a negative value.
1.187 + *
1.188 + * @param s const uint8 * string
1.189 + * @param i string offset, i<length
1.190 + * @param length string length
1.191 + * @param c output UChar32 variable, set to <0 in case of an error
1.192 + * @see CBU8_NEXT_UNSAFE
1.193 + * @stable ICU 2.4
1.194 + */
1.195 +#define CBU8_NEXT(s, i, length, c) { \
1.196 + (c)=(s)[(i)++]; \
1.197 + if(((uint8)(c))>=0x80) { \
1.198 + if(CBU8_IS_LEAD(c)) { \
1.199 + (c)=base_icu::utf8_nextCharSafeBody((const uint8 *)s, &(i), (int32)(length), c, -1); \
1.200 + } else { \
1.201 + (c)=CBU_SENTINEL; \
1.202 + } \
1.203 + } \
1.204 +}
1.205 +
1.206 +/**
1.207 + * Append a code point to a string, overwriting 1 to 4 bytes.
1.208 + * The offset points to the current end of the string contents
1.209 + * and is advanced (post-increment).
1.210 + * "Unsafe" macro, assumes a valid code point and sufficient space in the string.
1.211 + * Otherwise, the result is undefined.
1.212 + *
1.213 + * @param s const uint8 * string buffer
1.214 + * @param i string offset
1.215 + * @param c code point to append
1.216 + * @see CBU8_APPEND
1.217 + * @stable ICU 2.4
1.218 + */
1.219 +#define CBU8_APPEND_UNSAFE(s, i, c) { \
1.220 + if((uint32)(c)<=0x7f) { \
1.221 + (s)[(i)++]=(uint8)(c); \
1.222 + } else { \
1.223 + if((uint32)(c)<=0x7ff) { \
1.224 + (s)[(i)++]=(uint8)(((c)>>6)|0xc0); \
1.225 + } else { \
1.226 + if((uint32)(c)<=0xffff) { \
1.227 + (s)[(i)++]=(uint8)(((c)>>12)|0xe0); \
1.228 + } else { \
1.229 + (s)[(i)++]=(uint8)(((c)>>18)|0xf0); \
1.230 + (s)[(i)++]=(uint8)((((c)>>12)&0x3f)|0x80); \
1.231 + } \
1.232 + (s)[(i)++]=(uint8)((((c)>>6)&0x3f)|0x80); \
1.233 + } \
1.234 + (s)[(i)++]=(uint8)(((c)&0x3f)|0x80); \
1.235 + } \
1.236 +}
1.237 +
1.238 +// UTF-16 macros ---------------------------------------------------------------
1.239 +// from utf16.h
1.240 +
1.241 +/**
1.242 + * Does this code unit alone encode a code point (BMP, not a surrogate)?
1.243 + * @param c 16-bit code unit
1.244 + * @return TRUE or FALSE
1.245 + * @stable ICU 2.4
1.246 + */
1.247 +#define CBU16_IS_SINGLE(c) !CBU_IS_SURROGATE(c)
1.248 +
1.249 +/**
1.250 + * Is this code unit a lead surrogate (U+d800..U+dbff)?
1.251 + * @param c 16-bit code unit
1.252 + * @return TRUE or FALSE
1.253 + * @stable ICU 2.4
1.254 + */
1.255 +#define CBU16_IS_LEAD(c) (((c)&0xfffffc00)==0xd800)
1.256 +
1.257 +/**
1.258 + * Is this code unit a trail surrogate (U+dc00..U+dfff)?
1.259 + * @param c 16-bit code unit
1.260 + * @return TRUE or FALSE
1.261 + * @stable ICU 2.4
1.262 + */
1.263 +#define CBU16_IS_TRAIL(c) (((c)&0xfffffc00)==0xdc00)
1.264 +
1.265 +/**
1.266 + * Is this code unit a surrogate (U+d800..U+dfff)?
1.267 + * @param c 16-bit code unit
1.268 + * @return TRUE or FALSE
1.269 + * @stable ICU 2.4
1.270 + */
1.271 +#define CBU16_IS_SURROGATE(c) CBU_IS_SURROGATE(c)
1.272 +
1.273 +/**
1.274 + * Assuming c is a surrogate code point (U16_IS_SURROGATE(c)),
1.275 + * is it a lead surrogate?
1.276 + * @param c 16-bit code unit
1.277 + * @return TRUE or FALSE
1.278 + * @stable ICU 2.4
1.279 + */
1.280 +#define CBU16_IS_SURROGATE_LEAD(c) (((c)&0x400)==0)
1.281 +
1.282 +/**
1.283 + * Helper constant for CBU16_GET_SUPPLEMENTARY.
1.284 + * @internal
1.285 + */
1.286 +#define CBU16_SURROGATE_OFFSET ((0xd800<<10UL)+0xdc00-0x10000)
1.287 +
1.288 +/**
1.289 + * Get a supplementary code point value (U+10000..U+10ffff)
1.290 + * from its lead and trail surrogates.
1.291 + * The result is undefined if the input values are not
1.292 + * lead and trail surrogates.
1.293 + *
1.294 + * @param lead lead surrogate (U+d800..U+dbff)
1.295 + * @param trail trail surrogate (U+dc00..U+dfff)
1.296 + * @return supplementary code point (U+10000..U+10ffff)
1.297 + * @stable ICU 2.4
1.298 + */
1.299 +#define CBU16_GET_SUPPLEMENTARY(lead, trail) \
1.300 + (((base_icu::UChar32)(lead)<<10UL)+(base_icu::UChar32)(trail)-CBU16_SURROGATE_OFFSET)
1.301 +
1.302 +
1.303 +/**
1.304 + * Get the lead surrogate (0xd800..0xdbff) for a
1.305 + * supplementary code point (0x10000..0x10ffff).
1.306 + * @param supplementary 32-bit code point (U+10000..U+10ffff)
1.307 + * @return lead surrogate (U+d800..U+dbff) for supplementary
1.308 + * @stable ICU 2.4
1.309 + */
1.310 +#define CBU16_LEAD(supplementary) (UChar)(((supplementary)>>10)+0xd7c0)
1.311 +
1.312 +/**
1.313 + * Get the trail surrogate (0xdc00..0xdfff) for a
1.314 + * supplementary code point (0x10000..0x10ffff).
1.315 + * @param supplementary 32-bit code point (U+10000..U+10ffff)
1.316 + * @return trail surrogate (U+dc00..U+dfff) for supplementary
1.317 + * @stable ICU 2.4
1.318 + */
1.319 +#define CBU16_TRAIL(supplementary) (UChar)(((supplementary)&0x3ff)|0xdc00)
1.320 +
1.321 +/**
1.322 + * How many 16-bit code units are used to encode this Unicode code point? (1 or 2)
1.323 + * The result is not defined if c is not a Unicode code point (U+0000..U+10ffff).
1.324 + * @param c 32-bit code point
1.325 + * @return 1 or 2
1.326 + * @stable ICU 2.4
1.327 + */
1.328 +#define CBU16_LENGTH(c) ((uint32)(c)<=0xffff ? 1 : 2)
1.329 +
1.330 +/**
1.331 + * The maximum number of 16-bit code units per Unicode code point (U+0000..U+10ffff).
1.332 + * @return 2
1.333 + * @stable ICU 2.4
1.334 + */
1.335 +#define CBU16_MAX_LENGTH 2
1.336 +
1.337 +/**
1.338 + * Get a code point from a string at a code point boundary offset,
1.339 + * and advance the offset to the next code point boundary.
1.340 + * (Post-incrementing forward iteration.)
1.341 + * "Safe" macro, handles unpaired surrogates and checks for string boundaries.
1.342 + *
1.343 + * The offset may point to the lead surrogate unit
1.344 + * for a supplementary code point, in which case the macro will read
1.345 + * the following trail surrogate as well.
1.346 + * If the offset points to a trail surrogate or
1.347 + * to a single, unpaired lead surrogate, then that itself
1.348 + * will be returned as the code point.
1.349 + *
1.350 + * @param s const UChar * string
1.351 + * @param i string offset, i<length
1.352 + * @param length string length
1.353 + * @param c output UChar32 variable
1.354 + * @stable ICU 2.4
1.355 + */
1.356 +#define CBU16_NEXT(s, i, length, c) { \
1.357 + (c)=(s)[(i)++]; \
1.358 + if(CBU16_IS_LEAD(c)) { \
1.359 + uint16 __c2; \
1.360 + if((i)<(length) && CBU16_IS_TRAIL(__c2=(s)[(i)])) { \
1.361 + ++(i); \
1.362 + (c)=CBU16_GET_SUPPLEMENTARY((c), __c2); \
1.363 + } \
1.364 + } \
1.365 +}
1.366 +
1.367 +/**
1.368 + * Append a code point to a string, overwriting 1 or 2 code units.
1.369 + * The offset points to the current end of the string contents
1.370 + * and is advanced (post-increment).
1.371 + * "Unsafe" macro, assumes a valid code point and sufficient space in the string.
1.372 + * Otherwise, the result is undefined.
1.373 + *
1.374 + * @param s const UChar * string buffer
1.375 + * @param i string offset
1.376 + * @param c code point to append
1.377 + * @see CBU16_APPEND
1.378 + * @stable ICU 2.4
1.379 + */
1.380 +#define CBU16_APPEND_UNSAFE(s, i, c) { \
1.381 + if((uint32)(c)<=0xffff) { \
1.382 + (s)[(i)++]=(uint16)(c); \
1.383 + } else { \
1.384 + (s)[(i)++]=(uint16)(((c)>>10)+0xd7c0); \
1.385 + (s)[(i)++]=(uint16)(((c)&0x3ff)|0xdc00); \
1.386 + } \
1.387 +}
1.388 +
1.389 +} // namesapce base_icu
1.390 +
1.391 +#endif // BASE_THIRD_PARTY_ICU_ICU_UTF_H_
