/
usr
/
include
/
unicode
/
/usr/include/unicode
mkdir
upload
Name
Size
Mode
Actions
alphaindex.h
27158
0644
edit
dl
rm
appendable.h
8739
0644
edit
dl
rm
basictz.h
10163
0644
edit
dl
rm
brkiter.h
28478
0644
edit
dl
rm
bytestream.h
11013
0644
edit
dl
rm
bytestrie.h
21268
0644
edit
dl
rm
bytestriebuilder.h
7640
0644
edit
dl
rm
calendar.h
108424
0644
edit
dl
rm
caniter.h
7621
0644
edit
dl
rm
casemap.h
25933
0644
edit
dl
rm
char16ptr.h
7393
0644
edit
dl
rm
chariter.h
24638
0644
edit
dl
rm
choicfmt.h
24544
0644
edit
dl
rm
coleitr.h
14102
0644
edit
dl
rm
coll.h
57615
0644
edit
dl
rm
compactdecimalformat.h
7047
0644
edit
dl
rm
curramt.h
3869
0644
edit
dl
rm
currpinf.h
7479
0644
edit
dl
rm
currunit.h
4112
0644
edit
dl
rm
datefmt.h
41690
0644
edit
dl
rm
dbbi.h
1223
0644
edit
dl
rm
dcfmtsym.h
21101
0644
edit
dl
rm
decimfmt.h
89676
0644
edit
dl
rm
docmain.h
7380
0644
edit
dl
rm
dtfmtsym.h
39126
0644
edit
dl
rm
dtintrv.h
3935
0644
edit
dl
rm
dtitvfmt.h
50448
0644
edit
dl
rm
dtitvinf.h
19072
0644
edit
dl
rm
dtptngen.h
26692
0644
edit
dl
rm
dtrule.h
8898
0644
edit
dl
rm
edits.h
21237
0644
edit
dl
rm
enumset.h
2130
0644
edit
dl
rm
errorcode.h
4956
0644
edit
dl
rm
fieldpos.h
8906
0644
edit
dl
rm
filteredbrk.h
5501
0644
edit
dl
rm
fmtable.h
25020
0644
edit
dl
rm
format.h
12802
0644
edit
dl
rm
formattedvalue.h
9987
0644
edit
dl
rm
fpositer.h
3107
0644
edit
dl
rm
gender.h
3408
0644
edit
dl
rm
gregocal.h
32642
0644
edit
dl
rm
icudataver.h
1049
0644
edit
dl
rm
icuplug.h
12109
0644
edit
dl
rm
idna.h
13000
0644
edit
dl
rm
listformatter.h
9004
0644
edit
dl
rm
localebuilder.h
11350
0644
edit
dl
rm
localematcher.h
27467
0644
edit
dl
rm
localpointer.h
19825
0644
edit
dl
rm
locdspnm.h
7292
0644
edit
dl
rm
locid.h
48804
0644
edit
dl
rm
measfmt.h
11690
0644
edit
dl
rm
measunit.h
107613
0644
edit
dl
rm
measure.h
4431
0644
edit
dl
rm
messagepattern.h
34517
0644
edit
dl
rm
msgfmt.h
45278
0644
edit
dl
rm
normalizer2.h
34466
0644
edit
dl
rm
normlzr.h
31690
0644
edit
dl
rm
nounit.h
2305
0644
edit
dl
rm
numberformatter.h
94505
0644
edit
dl
rm
numberrangeformatter.h
25790
0644
edit
dl
rm
numfmt.h
51034
0644
edit
dl
rm
numsys.h
7509
0644
edit
dl
rm
parseerr.h
3155
0644
edit
dl
rm
parsepos.h
5699
0644
edit
dl
rm
platform.h
28768
0644
edit
dl
rm
plurfmt.h
25847
0644
edit
dl
rm
plurrule.h
21316
0644
edit
dl
rm
ptypes.h
3577
0644
edit
dl
rm
putil.h
6471
0644
edit
dl
rm
rbbi.h
28413
0644
edit
dl
rm
rbnf.h
50021
0644
edit
dl
rm
rbtz.h
16210
0644
edit
dl
rm
regex.h
86385
0644
edit
dl
rm
region.h
9402
0644
edit
dl
rm
reldatefmt.h
22751
0644
edit
dl
rm
rep.h
9599
0644
edit
dl
rm
resbund.h
18513
0644
edit
dl
rm
schriter.h
6511
0644
edit
dl
rm
scientificnumberformatter.h
6589
0644
edit
dl
rm
search.h
22755
0644
edit
dl
rm
selfmt.h
14686
0644
edit
dl
rm
simpleformatter.h
12888
0644
edit
dl
rm
simpletz.h
46798
0644
edit
dl
rm
smpdtfmt.h
72778
0644
edit
dl
rm
sortkey.h
11452
0644
edit
dl
rm
std_string.h
1076
0644
edit
dl
rm
strenum.h
10157
0644
edit
dl
rm
stringoptions.h
5926
0644
edit
dl
rm
stringpiece.h
10287
0644
edit
dl
rm
stringtriebuilder.h
15842
0644
edit
dl
rm
stsearch.h
21926
0644
edit
dl
rm
symtable.h
4374
0644
edit
dl
rm
tblcoll.h
37801
0644
edit
dl
rm
timezone.h
44858
0644
edit
dl
rm
tmunit.h
3479
0644
edit
dl
rm
tmutamt.h
5029
0644
edit
dl
rm
tmutfmt.h
7602
0644
edit
dl
rm
translit.h
67397
0644
edit
dl
rm
tzfmt.h
43961
0644
edit
dl
rm
tznames.h
17251
0644
edit
dl
rm
tzrule.h
36450
0644
edit
dl
rm
tztrans.h
6278
0644
edit
dl
rm
ubidi.h
91759
0644
edit
dl
rm
ubiditransform.h
13003
0644
edit
dl
rm
ubrk.h
25043
0644
edit
dl
rm
ucal.h
62463
0644
edit
dl
rm
ucasemap.h
15579
0644
edit
dl
rm
ucat.h
5478
0644
edit
dl
rm
uchar.h
148111
0644
edit
dl
rm
ucharstrie.h
23066
0644
edit
dl
rm
ucharstriebuilder.h
7645
0644
edit
dl
rm
uchriter.h
13747
0644
edit
dl
rm
uclean.h
11468
0644
edit
dl
rm
ucnv.h
85051
0644
edit
dl
rm
ucnvsel.h
6339
0644
edit
dl
rm
ucnv_cb.h
6738
0644
edit
dl
rm
ucnv_err.h
21481
0644
edit
dl
rm
ucol.h
62987
0644
edit
dl
rm
ucoleitr.h
10056
0644
edit
dl
rm
uconfig.h
12356
0644
edit
dl
rm
ucpmap.h
5663
0644
edit
dl
rm
ucptrie.h
23044
0644
edit
dl
rm
ucsdet.h
15043
0644
edit
dl
rm
ucurr.h
17122
0644
edit
dl
rm
udat.h
63902
0644
edit
dl
rm
udata.h
16004
0644
edit
dl
rm
udateintervalformat.h
12218
0644
edit
dl
rm
udatpg.h
27405
0644
edit
dl
rm
udisplaycontext.h
6084
0644
edit
dl
rm
uenum.h
7981
0644
edit
dl
rm
ufieldpositer.h
4513
0644
edit
dl
rm
uformattable.h
11233
0644
edit
dl
rm
uformattedvalue.h
12600
0644
edit
dl
rm
ugender.h
2106
0644
edit
dl
rm
uidna.h
34229
0644
edit
dl
rm
uiter.h
23299
0644
edit
dl
rm
uldnames.h
10733
0644
edit
dl
rm
ulistformatter.h
11043
0644
edit
dl
rm
uloc.h
55936
0644
edit
dl
rm
ulocdata.h
11572
0644
edit
dl
rm
umachine.h
16439
0644
edit
dl
rm
umisc.h
1365
0644
edit
dl
rm
umsg.h
24832
0644
edit
dl
rm
umutablecptrie.h
8490
0644
edit
dl
rm
unifilt.h
4091
0644
edit
dl
rm
unifunct.h
4151
0644
edit
dl
rm
unimatch.h
6244
0644
edit
dl
rm
unirepl.h
3464
0644
edit
dl
rm
uniset.h
68108
0644
edit
dl
rm
unistr.h
174627
0644
edit
dl
rm
unorm.h
21042
0644
edit
dl
rm
unorm2.h
25269
0644
edit
dl
rm
unum.h
56269
0644
edit
dl
rm
unumberformatter.h
31177
0644
edit
dl
rm
unumberrangeformatter.h
15737
0644
edit
dl
rm
unumsys.h
7430
0644
edit
dl
rm
uobject.h
10934
0644
edit
dl
rm
upluralrules.h
8997
0644
edit
dl
rm
uregex.h
73719
0644
edit
dl
rm
uregion.h
10047
0644
edit
dl
rm
ureldatefmt.h
17448
0644
edit
dl
rm
urename.h
137853
0644
edit
dl
rm
urep.h
5507
0644
edit
dl
rm
ures.h
37418
0644
edit
dl
rm
uscript.h
28291
0644
edit
dl
rm
usearch.h
40153
0644
edit
dl
rm
uset.h
45503
0644
edit
dl
rm
usetiter.h
9910
0644
edit
dl
rm
ushape.h
18430
0644
edit
dl
rm
uspoof.h
67425
0644
edit
dl
rm
usprep.h
8382
0644
edit
dl
rm
ustdio.h
39482
0644
edit
dl
rm
ustream.h
1934
0644
edit
dl
rm
ustring.h
74096
0644
edit
dl
rm
ustringtrie.h
3224
0644
edit
dl
rm
utext.h
59471
0644
edit
dl
rm
utf.h
8057
0644
edit
dl
rm
utf8.h
31572
0644
edit
dl
rm
utf16.h
23910
0644
edit
dl
rm
utf32.h
763
0644
edit
dl
rm
utf_old.h
46929
0644
edit
dl
rm
utmscale.h
14107
0644
edit
dl
rm
utrace.h
17595
0644
edit
dl
rm
utrans.h
26157
0644
edit
dl
rm
utypes.h
31807
0644
edit
dl
rm
uvernum.h
6839
0644
edit
dl
rm
uversion.h
6137
0644
edit
dl
rm
vtzone.h
21303
0644
edit
dl
rm
Edit:
/usr/include/unicode/ucptrie.h
(23044B)
// © 2017 and later: Unicode, Inc. and others. // License & terms of use: http://www.unicode.org/copyright.html // ucptrie.h (modified from utrie2.h) // created: 2017dec29 Markus W. Scherer #ifndef __UCPTRIE_H__ #define __UCPTRIE_H__ #include "unicode/utypes.h" #include "unicode/ucpmap.h" #include "unicode/utf8.h" #if U_SHOW_CPLUSPLUS_API #include "unicode/localpointer.h" #endif // U_SHOW_CPLUSPLUS_API U_CDECL_BEGIN /** * \file * * This file defines an immutable Unicode code point trie. * * @see UCPTrie * @see UMutableCPTrie */ #ifndef U_IN_DOXYGEN /** @internal */ typedef union UCPTrieData { /** @internal */ const void *ptr0; /** @internal */ const uint16_t *ptr16; /** @internal */ const uint32_t *ptr32; /** @internal */ const uint8_t *ptr8; } UCPTrieData; #endif /** * Immutable Unicode code point trie structure. * Fast, reasonably compact, map from Unicode code points (U+0000..U+10FFFF) to integer values. * For details see https://icu.unicode.org/design/struct/utrie * * Do not access UCPTrie fields directly; use public functions and macros. * Functions are easy to use: They support all trie types and value widths. * * When performance is really important, macros provide faster access. * Most macros are specific to either "fast" or "small" tries, see UCPTrieType. * There are "fast" macros for special optimized use cases. * * The macros will return bogus values, or may crash, if used on the wrong type or value width. * * @see UMutableCPTrie * @stable ICU 63 */ struct UCPTrie { #ifndef U_IN_DOXYGEN /** @internal */ const uint16_t *index; /** @internal */ UCPTrieData data; /** @internal */ int32_t indexLength; /** @internal */ int32_t dataLength; /** Start of the last range which ends at U+10FFFF. @internal */ UChar32 highStart; /** highStart>>12 @internal */ uint16_t shifted12HighStart; /** @internal */ int8_t type; // UCPTrieType /** @internal */ int8_t valueWidth; // UCPTrieValueWidth /** padding/reserved @internal */ uint32_t reserved32; /** padding/reserved @internal */ uint16_t reserved16; /** * Internal index-3 null block offset. * Set to an impossibly high value (e.g., 0xffff) if there is no dedicated index-3 null block. * @internal */ uint16_t index3NullOffset; /** * Internal data null block offset, not shifted. * Set to an impossibly high value (e.g., 0xfffff) if there is no dedicated data null block. * @internal */ int32_t dataNullOffset; /** @internal */ uint32_t nullValue; #ifdef UCPTRIE_DEBUG /** @internal */ const char *name; #endif #endif }; #ifndef U_IN_DOXYGEN typedef struct UCPTrie UCPTrie; #endif /** * Selectors for the type of a UCPTrie. * Different trade-offs for size vs. speed. * * @see umutablecptrie_buildImmutable * @see ucptrie_openFromBinary * @see ucptrie_getType * @stable ICU 63 */ enum UCPTrieType { /** * For ucptrie_openFromBinary() to accept any type. * ucptrie_getType() will return the actual type. * @stable ICU 63 */ UCPTRIE_TYPE_ANY = -1, /** * Fast/simple/larger BMP data structure. Use functions and "fast" macros. * @stable ICU 63 */ UCPTRIE_TYPE_FAST, /** * Small/slower BMP data structure. Use functions and "small" macros. * @stable ICU 63 */ UCPTRIE_TYPE_SMALL }; #ifndef U_IN_DOXYGEN typedef enum UCPTrieType UCPTrieType; #endif /** * Selectors for the number of bits in a UCPTrie data value. * * @see umutablecptrie_buildImmutable * @see ucptrie_openFromBinary * @see ucptrie_getValueWidth * @stable ICU 63 */ enum UCPTrieValueWidth { /** * For ucptrie_openFromBinary() to accept any data value width. * ucptrie_getValueWidth() will return the actual data value width. * @stable ICU 63 */ UCPTRIE_VALUE_BITS_ANY = -1, /** * The trie stores 16 bits per data value. * It returns them as unsigned values 0..0xffff=65535. * @stable ICU 63 */ UCPTRIE_VALUE_BITS_16, /** * The trie stores 32 bits per data value. * @stable ICU 63 */ UCPTRIE_VALUE_BITS_32, /** * The trie stores 8 bits per data value. * It returns them as unsigned values 0..0xff=255. * @stable ICU 63 */ UCPTRIE_VALUE_BITS_8 }; #ifndef U_IN_DOXYGEN typedef enum UCPTrieValueWidth UCPTrieValueWidth; #endif /** * Opens a trie from its binary form, stored in 32-bit-aligned memory. * Inverse of ucptrie_toBinary(). * * The memory must remain valid and unchanged as long as the trie is used. * You must ucptrie_close() the trie once you are done using it. * * @param type selects the trie type; results in an * U_INVALID_FORMAT_ERROR if it does not match the binary data; * use UCPTRIE_TYPE_ANY to accept any type * @param valueWidth selects the number of bits in a data value; results in an * U_INVALID_FORMAT_ERROR if it does not match the binary data; * use UCPTRIE_VALUE_BITS_ANY to accept any data value width * @param data a pointer to 32-bit-aligned memory containing the binary data of a UCPTrie * @param length the number of bytes available at data; * can be more than necessary * @param pActualLength receives the actual number of bytes at data taken up by the trie data; * can be NULL * @param pErrorCode an in/out ICU UErrorCode * @return the trie * * @see umutablecptrie_open * @see umutablecptrie_buildImmutable * @see ucptrie_toBinary * @stable ICU 63 */ U_CAPI UCPTrie * U_EXPORT2 ucptrie_openFromBinary(UCPTrieType type, UCPTrieValueWidth valueWidth, const void *data, int32_t length, int32_t *pActualLength, UErrorCode *pErrorCode); /** * Closes a trie and releases associated memory. * * @param trie the trie * @stable ICU 63 */ U_CAPI void U_EXPORT2 ucptrie_close(UCPTrie *trie); /** * Returns the trie type. * * @param trie the trie * @return the trie type * @see ucptrie_openFromBinary * @see UCPTRIE_TYPE_ANY * @stable ICU 63 */ U_CAPI UCPTrieType U_EXPORT2 ucptrie_getType(const UCPTrie *trie); /** * Returns the number of bits in a trie data value. * * @param trie the trie * @return the number of bits in a trie data value * @see ucptrie_openFromBinary * @see UCPTRIE_VALUE_BITS_ANY * @stable ICU 63 */ U_CAPI UCPTrieValueWidth U_EXPORT2 ucptrie_getValueWidth(const UCPTrie *trie); /** * Returns the value for a code point as stored in the trie, with range checking. * Returns the trie error value if c is not in the range 0..U+10FFFF. * * Easier to use than UCPTRIE_FAST_GET() and similar macros but slower. * Easier to use because, unlike the macros, this function works on all UCPTrie * objects, for all types and value widths. * * @param trie the trie * @param c the code point * @return the trie value, * or the trie error value if the code point is not in the range 0..U+10FFFF * @stable ICU 63 */ U_CAPI uint32_t U_EXPORT2 ucptrie_get(const UCPTrie *trie, UChar32 c); /** * Returns the last code point such that all those from start to there have the same value. * Can be used to efficiently iterate over all same-value ranges in a trie. * (This is normally faster than iterating over code points and get()ting each value, * but much slower than a data structure that stores ranges directly.) * * If the UCPMapValueFilter function pointer is not NULL, then * the value to be delivered is passed through that function, and the return value is the end * of the range where all values are modified to the same actual value. * The value is unchanged if that function pointer is NULL. * * Example: * \code * UChar32 start = 0, end; * uint32_t value; * while ((end = ucptrie_getRange(trie, start, UCPMAP_RANGE_NORMAL, 0, * NULL, NULL, &value)) >= 0) { * // Work with the range start..end and its value. * start = end + 1; * } * \endcode * * @param trie the trie * @param start range start * @param option defines whether surrogates are treated normally, * or as having the surrogateValue; usually UCPMAP_RANGE_NORMAL * @param surrogateValue value for surrogates; ignored if option==UCPMAP_RANGE_NORMAL * @param filter a pointer to a function that may modify the trie data value, * or NULL if the values from the trie are to be used unmodified * @param context an opaque pointer that is passed on to the filter function * @param pValue if not NULL, receives the value that every code point start..end has; * may have been modified by filter(context, trie value) * if that function pointer is not NULL * @return the range end code point, or -1 if start is not a valid code point * @stable ICU 63 */ U_CAPI UChar32 U_EXPORT2 ucptrie_getRange(const UCPTrie *trie, UChar32 start, UCPMapRangeOption option, uint32_t surrogateValue, UCPMapValueFilter *filter, const void *context, uint32_t *pValue); /** * Writes a memory-mappable form of the trie into 32-bit aligned memory. * Inverse of ucptrie_openFromBinary(). * * @param trie the trie * @param data a pointer to 32-bit-aligned memory to be filled with the trie data; * can be NULL if capacity==0 * @param capacity the number of bytes available at data, or 0 for pure preflighting * @param pErrorCode an in/out ICU UErrorCode; * U_BUFFER_OVERFLOW_ERROR if the capacity is too small * @return the number of bytes written or (if buffer overflow) needed for the trie * * @see ucptrie_openFromBinary() * @stable ICU 63 */ U_CAPI int32_t U_EXPORT2 ucptrie_toBinary(const UCPTrie *trie, void *data, int32_t capacity, UErrorCode *pErrorCode); /** * Macro parameter value for a trie with 16-bit data values. * Use the name of this macro as a "dataAccess" parameter in other macros. * Do not use this macro in any other way. * * @see UCPTRIE_VALUE_BITS_16 * @stable ICU 63 */ #define UCPTRIE_16(trie, i) ((trie)->data.ptr16[i]) /** * Macro parameter value for a trie with 32-bit data values. * Use the name of this macro as a "dataAccess" parameter in other macros. * Do not use this macro in any other way. * * @see UCPTRIE_VALUE_BITS_32 * @stable ICU 63 */ #define UCPTRIE_32(trie, i) ((trie)->data.ptr32[i]) /** * Macro parameter value for a trie with 8-bit data values. * Use the name of this macro as a "dataAccess" parameter in other macros. * Do not use this macro in any other way. * * @see UCPTRIE_VALUE_BITS_8 * @stable ICU 63 */ #define UCPTRIE_8(trie, i) ((trie)->data.ptr8[i]) /** * Returns a trie value for a code point, with range checking. * Returns the trie error value if c is not in the range 0..U+10FFFF. * * @param trie (const UCPTrie *, in) the trie; must have type UCPTRIE_TYPE_FAST * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width * @param c (UChar32, in) the input code point * @return The code point's trie value. * @stable ICU 63 */ #define UCPTRIE_FAST_GET(trie, dataAccess, c) dataAccess(trie, _UCPTRIE_CP_INDEX(trie, 0xffff, c)) /** * Returns a 16-bit trie value for a code point, with range checking. * Returns the trie error value if c is not in the range U+0000..U+10FFFF. * * @param trie (const UCPTrie *, in) the trie; must have type UCPTRIE_TYPE_SMALL * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width * @param c (UChar32, in) the input code point * @return The code point's trie value. * @stable ICU 63 */ #define UCPTRIE_SMALL_GET(trie, dataAccess, c) \ dataAccess(trie, _UCPTRIE_CP_INDEX(trie, UCPTRIE_SMALL_MAX, c)) /** * UTF-16: Reads the next code point (UChar32 c, out), post-increments src, * and gets a value from the trie. * Sets the trie error value if c is an unpaired surrogate. * * @param trie (const UCPTrie *, in) the trie; must have type UCPTRIE_TYPE_FAST * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width * @param src (const UChar *, in/out) the source text pointer * @param limit (const UChar *, in) the limit pointer for the text, or NULL if NUL-terminated * @param c (UChar32, out) variable for the code point * @param result (out) variable for the trie lookup result * @stable ICU 63 */ #define UCPTRIE_FAST_U16_NEXT(trie, dataAccess, src, limit, c, result) UPRV_BLOCK_MACRO_BEGIN { \ (c) = *(src)++; \ int32_t __index; \ if (!U16_IS_SURROGATE(c)) { \ __index = _UCPTRIE_FAST_INDEX(trie, c); \ } else { \ uint16_t __c2; \ if (U16_IS_SURROGATE_LEAD(c) && (src) != (limit) && U16_IS_TRAIL(__c2 = *(src))) { \ ++(src); \ (c) = U16_GET_SUPPLEMENTARY((c), __c2); \ __index = _UCPTRIE_SMALL_INDEX(trie, c); \ } else { \ __index = (trie)->dataLength - UCPTRIE_ERROR_VALUE_NEG_DATA_OFFSET; \ } \ } \ (result) = dataAccess(trie, __index); \ } UPRV_BLOCK_MACRO_END /** * UTF-16: Reads the previous code point (UChar32 c, out), pre-decrements src, * and gets a value from the trie. * Sets the trie error value if c is an unpaired surrogate. * * @param trie (const UCPTrie *, in) the trie; must have type UCPTRIE_TYPE_FAST * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width * @param start (const UChar *, in) the start pointer for the text * @param src (const UChar *, in/out) the source text pointer * @param c (UChar32, out) variable for the code point * @param result (out) variable for the trie lookup result * @stable ICU 63 */ #define UCPTRIE_FAST_U16_PREV(trie, dataAccess, start, src, c, result) UPRV_BLOCK_MACRO_BEGIN { \ (c) = *--(src); \ int32_t __index; \ if (!U16_IS_SURROGATE(c)) { \ __index = _UCPTRIE_FAST_INDEX(trie, c); \ } else { \ uint16_t __c2; \ if (U16_IS_SURROGATE_TRAIL(c) && (src) != (start) && U16_IS_LEAD(__c2 = *((src) - 1))) { \ --(src); \ (c) = U16_GET_SUPPLEMENTARY(__c2, (c)); \ __index = _UCPTRIE_SMALL_INDEX(trie, c); \ } else { \ __index = (trie)->dataLength - UCPTRIE_ERROR_VALUE_NEG_DATA_OFFSET; \ } \ } \ (result) = dataAccess(trie, __index); \ } UPRV_BLOCK_MACRO_END /** * UTF-8: Post-increments src and gets a value from the trie. * Sets the trie error value for an ill-formed byte sequence. * * Unlike UCPTRIE_FAST_U16_NEXT() this UTF-8 macro does not provide the code point * because it would be more work to do so and is often not needed. * If the trie value differs from the error value, then the byte sequence is well-formed, * and the code point can be assembled without revalidation. * * @param trie (const UCPTrie *, in) the trie; must have type UCPTRIE_TYPE_FAST * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width * @param src (const char *, in/out) the source text pointer * @param limit (const char *, in) the limit pointer for the text (must not be NULL) * @param result (out) variable for the trie lookup result * @stable ICU 63 */ #define UCPTRIE_FAST_U8_NEXT(trie, dataAccess, src, limit, result) UPRV_BLOCK_MACRO_BEGIN { \ int32_t __lead = (uint8_t)*(src)++; \ if (!U8_IS_SINGLE(__lead)) { \ uint8_t __t1, __t2, __t3; \ if ((src) != (limit) && \ (__lead >= 0xe0 ? \ __lead < 0xf0 ? /* U+0800..U+FFFF except surrogates */ \ U8_LEAD3_T1_BITS[__lead &= 0xf] & (1 << ((__t1 = *(src)) >> 5)) && \ ++(src) != (limit) && (__t2 = *(src) - 0x80) <= 0x3f && \ (__lead = ((int32_t)(trie)->index[(__lead << 6) + (__t1 & 0x3f)]) + __t2, 1) \ : /* U+10000..U+10FFFF */ \ (__lead -= 0xf0) <= 4 && \ U8_LEAD4_T1_BITS[(__t1 = *(src)) >> 4] & (1 << __lead) && \ (__lead = (__lead << 6) | (__t1 & 0x3f), ++(src) != (limit)) && \ (__t2 = *(src) - 0x80) <= 0x3f && \ ++(src) != (limit) && (__t3 = *(src) - 0x80) <= 0x3f && \ (__lead = __lead >= (trie)->shifted12HighStart ? \ (trie)->dataLength - UCPTRIE_HIGH_VALUE_NEG_DATA_OFFSET : \ ucptrie_internalSmallU8Index((trie), __lead, __t2, __t3), 1) \ : /* U+0080..U+07FF */ \ __lead >= 0xc2 && (__t1 = *(src) - 0x80) <= 0x3f && \ (__lead = (int32_t)(trie)->index[__lead & 0x1f] + __t1, 1))) { \ ++(src); \ } else { \ __lead = (trie)->dataLength - UCPTRIE_ERROR_VALUE_NEG_DATA_OFFSET; /* ill-formed*/ \ } \ } \ (result) = dataAccess(trie, __lead); \ } UPRV_BLOCK_MACRO_END /** * UTF-8: Pre-decrements src and gets a value from the trie. * Sets the trie error value for an ill-formed byte sequence. * * Unlike UCPTRIE_FAST_U16_PREV() this UTF-8 macro does not provide the code point * because it would be more work to do so and is often not needed. * If the trie value differs from the error value, then the byte sequence is well-formed, * and the code point can be assembled without revalidation. * * @param trie (const UCPTrie *, in) the trie; must have type UCPTRIE_TYPE_FAST * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width * @param start (const char *, in) the start pointer for the text * @param src (const char *, in/out) the source text pointer * @param result (out) variable for the trie lookup result * @stable ICU 63 */ #define UCPTRIE_FAST_U8_PREV(trie, dataAccess, start, src, result) UPRV_BLOCK_MACRO_BEGIN { \ int32_t __index = (uint8_t)*--(src); \ if (!U8_IS_SINGLE(__index)) { \ __index = ucptrie_internalU8PrevIndex((trie), __index, (const uint8_t *)(start), \ (const uint8_t *)(src)); \ (src) -= __index & 7; \ __index >>= 3; \ } \ (result) = dataAccess(trie, __index); \ } UPRV_BLOCK_MACRO_END /** * Returns a trie value for an ASCII code point, without range checking. * * @param trie (const UCPTrie *, in) the trie (of either fast or small type) * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width * @param c (UChar32, in) the input code point; must be U+0000..U+007F * @return The ASCII code point's trie value. * @stable ICU 63 */ #define UCPTRIE_ASCII_GET(trie, dataAccess, c) dataAccess(trie, c) /** * Returns a trie value for a BMP code point (U+0000..U+FFFF), without range checking. * Can be used to look up a value for a UTF-16 code unit if other parts of * the string processing check for surrogates. * * @param trie (const UCPTrie *, in) the trie; must have type UCPTRIE_TYPE_FAST * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width * @param c (UChar32, in) the input code point, must be U+0000..U+FFFF * @return The BMP code point's trie value. * @stable ICU 63 */ #define UCPTRIE_FAST_BMP_GET(trie, dataAccess, c) dataAccess(trie, _UCPTRIE_FAST_INDEX(trie, c)) /** * Returns a trie value for a supplementary code point (U+10000..U+10FFFF), * without range checking. * * @param trie (const UCPTrie *, in) the trie; must have type UCPTRIE_TYPE_FAST * @param dataAccess UCPTRIE_16, UCPTRIE_32, or UCPTRIE_8 according to the trie’s value width * @param c (UChar32, in) the input code point, must be U+10000..U+10FFFF * @return The supplementary code point's trie value. * @stable ICU 63 */ #define UCPTRIE_FAST_SUPP_GET(trie, dataAccess, c) dataAccess(trie, _UCPTRIE_SMALL_INDEX(trie, c)) /* Internal definitions ----------------------------------------------------- */ #ifndef U_IN_DOXYGEN /** * Internal implementation constants. * These are needed for the API macros, but users should not use these directly. * @internal */ enum { /** @internal */ UCPTRIE_FAST_SHIFT = 6, /** Number of entries in a data block for code points below the fast limit. 64=0x40 @internal */ UCPTRIE_FAST_DATA_BLOCK_LENGTH = 1 << UCPTRIE_FAST_SHIFT, /** Mask for getting the lower bits for the in-fast-data-block offset. @internal */ UCPTRIE_FAST_DATA_MASK = UCPTRIE_FAST_DATA_BLOCK_LENGTH - 1, /** @internal */ UCPTRIE_SMALL_MAX = 0xfff, /** * Offset from dataLength (to be subtracted) for fetching the * value returned for out-of-range code points and ill-formed UTF-8/16. * @internal */ UCPTRIE_ERROR_VALUE_NEG_DATA_OFFSET = 1, /** * Offset from dataLength (to be subtracted) for fetching the * value returned for code points highStart..U+10FFFF. * @internal */ UCPTRIE_HIGH_VALUE_NEG_DATA_OFFSET = 2 }; /* Internal functions and macros -------------------------------------------- */ // Do not conditionalize with #ifndef U_HIDE_INTERNAL_API, needed for public API /** @internal */ U_CAPI int32_t U_EXPORT2 ucptrie_internalSmallIndex(const UCPTrie *trie, UChar32 c); /** @internal */ U_CAPI int32_t U_EXPORT2 ucptrie_internalSmallU8Index(const UCPTrie *trie, int32_t lt1, uint8_t t2, uint8_t t3); /** * Internal function for part of the UCPTRIE_FAST_U8_PREVxx() macro implementations. * Do not call directly. * @internal */ U_CAPI int32_t U_EXPORT2 ucptrie_internalU8PrevIndex(const UCPTrie *trie, UChar32 c, const uint8_t *start, const uint8_t *src); /** Internal trie getter for a code point below the fast limit. Returns the data index. @internal */ #define _UCPTRIE_FAST_INDEX(trie, c) \ ((int32_t)(trie)->index[(c) >> UCPTRIE_FAST_SHIFT] + ((c) & UCPTRIE_FAST_DATA_MASK)) /** Internal trie getter for a code point at or above the fast limit. Returns the data index. @internal */ #define _UCPTRIE_SMALL_INDEX(trie, c) \ ((c) >= (trie)->highStart ? \ (trie)->dataLength - UCPTRIE_HIGH_VALUE_NEG_DATA_OFFSET : \ ucptrie_internalSmallIndex(trie, c)) /** * Internal trie getter for a code point, with checking that c is in U+0000..10FFFF. * Returns the data index. * @internal */ #define _UCPTRIE_CP_INDEX(trie, fastMax, c) \ ((uint32_t)(c) <= (uint32_t)(fastMax) ? \ _UCPTRIE_FAST_INDEX(trie, c) : \ (uint32_t)(c) <= 0x10ffff ? \ _UCPTRIE_SMALL_INDEX(trie, c) : \ (trie)->dataLength - UCPTRIE_ERROR_VALUE_NEG_DATA_OFFSET) U_CDECL_END #endif // U_IN_DOXYGEN #if U_SHOW_CPLUSPLUS_API U_NAMESPACE_BEGIN /** * \class LocalUCPTriePointer * "Smart pointer" class, closes a UCPTrie via ucptrie_close(). * For most methods see the LocalPointerBase base class. * * @see LocalPointerBase * @see LocalPointer * @stable ICU 63 */ U_DEFINE_LOCAL_OPEN_POINTER(LocalUCPTriePointer, UCPTrie, ucptrie_close); U_NAMESPACE_END #endif // U_SHOW_CPLUSPLUS_API #endif
Save
cmd:
run