/
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/unorm.h
(21042B)
// © 2016 and later: Unicode, Inc. and others. // License & terms of use: http://www.unicode.org/copyright.html /* ******************************************************************************* * Copyright (c) 1996-2016, International Business Machines Corporation * and others. All Rights Reserved. ******************************************************************************* * File unorm.h * * Created by: Vladimir Weinstein 12052000 * * Modification history : * * Date Name Description * 02/01/01 synwee Added normalization quickcheck enum and method. */ #ifndef UNORM_H #define UNORM_H #include "unicode/utypes.h" #if !UCONFIG_NO_NORMALIZATION #include "unicode/uiter.h" #include "unicode/unorm2.h" /** * \file * \brief C API: Unicode Normalization * * Old Unicode normalization API. * * This API has been replaced by the unorm2.h API and is only available * for backward compatibility. The functions here simply delegate to the * unorm2.h functions, for example unorm2_getInstance() and unorm2_normalize(). * There is one exception: The new API does not provide a replacement for unorm_compare(). * Its declaration has been moved to unorm2.h. * * <code>unorm_normalize</code> transforms Unicode text into an equivalent composed or * decomposed form, allowing for easier sorting and searching of text. * <code>unorm_normalize</code> supports the standard normalization forms described in * <a href="http://www.unicode.org/unicode/reports/tr15/" target="unicode"> * Unicode Standard Annex #15: Unicode Normalization Forms</a>. * * Characters with accents or other adornments can be encoded in * several different ways in Unicode. For example, take the character A-acute. * In Unicode, this can be encoded as a single character (the * "composed" form): * * \code * 00C1 LATIN CAPITAL LETTER A WITH ACUTE * \endcode * * or as two separate characters (the "decomposed" form): * * \code * 0041 LATIN CAPITAL LETTER A * 0301 COMBINING ACUTE ACCENT * \endcode * * To a user of your program, however, both of these sequences should be * treated as the same "user-level" character "A with acute accent". When you are searching or * comparing text, you must ensure that these two sequences are treated * equivalently. In addition, you must handle characters with more than one * accent. Sometimes the order of a character's combining accents is * significant, while in other cases accent sequences in different orders are * really equivalent. * * Similarly, the string "ffi" can be encoded as three separate letters: * * \code * 0066 LATIN SMALL LETTER F * 0066 LATIN SMALL LETTER F * 0069 LATIN SMALL LETTER I * \endcode * * or as the single character * * \code * FB03 LATIN SMALL LIGATURE FFI * \endcode * * The ffi ligature is not a distinct semantic character, and strictly speaking * it shouldn't be in Unicode at all, but it was included for compatibility * with existing character sets that already provided it. The Unicode standard * identifies such characters by giving them "compatibility" decompositions * into the corresponding semantic characters. When sorting and searching, you * will often want to use these mappings. * * <code>unorm_normalize</code> helps solve these problems by transforming text into the * canonical composed and decomposed forms as shown in the first example above. * In addition, you can have it perform compatibility decompositions so that * you can treat compatibility characters the same as their equivalents. * Finally, <code>unorm_normalize</code> rearranges accents into the proper canonical * order, so that you do not have to worry about accent rearrangement on your * own. * * Form FCD, "Fast C or D", is also designed for collation. * It allows to work on strings that are not necessarily normalized * with an algorithm (like in collation) that works under "canonical closure", i.e., it treats precomposed * characters and their decomposed equivalents the same. * * It is not a normalization form because it does not provide for uniqueness of representation. Multiple strings * may be canonically equivalent (their NFDs are identical) and may all conform to FCD without being identical * themselves. * * The form is defined such that the "raw decomposition", the recursive canonical decomposition of each character, * results in a string that is canonically ordered. This means that precomposed characters are allowed for as long * as their decompositions do not need canonical reordering. * * Its advantage for a process like collation is that all NFD and most NFC texts - and many unnormalized texts - * already conform to FCD and do not need to be normalized (NFD) for such a process. The FCD quick check will * return UNORM_YES for most strings in practice. * * unorm_normalize(UNORM_FCD) may be implemented with UNORM_NFD. * * For more details on FCD see the collation design document: * https://htmlpreview.github.io/?https://github.com/unicode-org/icu-docs/blob/main/design/collation/ICU_collation_design.htm * * ICU collation performs either NFD or FCD normalization automatically if normalization * is turned on for the collator object. * Beyond collation and string search, normalized strings may be useful for string equivalence comparisons, * transliteration/transcription, unique representations, etc. * * The W3C generally recommends to exchange texts in NFC. * Note also that most legacy character encodings use only precomposed forms and often do not * encode any combining marks by themselves. For conversion to such character encodings the * Unicode text needs to be normalized to NFC. * For more usage examples, see the Unicode Standard Annex. */ // Do not conditionalize the following enum with #ifndef U_HIDE_DEPRECATED_API, // it is needed for layout of Normalizer object. #ifndef U_FORCE_HIDE_DEPRECATED_API /** * Constants for normalization modes. * @deprecated ICU 56 Use unorm2.h instead. */ typedef enum { /** No decomposition/composition. @deprecated ICU 56 Use unorm2.h instead. */ UNORM_NONE = 1, /** Canonical decomposition. @deprecated ICU 56 Use unorm2.h instead. */ UNORM_NFD = 2, /** Compatibility decomposition. @deprecated ICU 56 Use unorm2.h instead. */ UNORM_NFKD = 3, /** Canonical decomposition followed by canonical composition. @deprecated ICU 56 Use unorm2.h instead. */ UNORM_NFC = 4, /** Default normalization. @deprecated ICU 56 Use unorm2.h instead. */ UNORM_DEFAULT = UNORM_NFC, /** Compatibility decomposition followed by canonical composition. @deprecated ICU 56 Use unorm2.h instead. */ UNORM_NFKC =5, /** "Fast C or D" form. @deprecated ICU 56 Use unorm2.h instead. */ UNORM_FCD = 6, /** One more than the highest normalization mode constant. @deprecated ICU 56 Use unorm2.h instead. */ UNORM_MODE_COUNT } UNormalizationMode; #endif // U_FORCE_HIDE_DEPRECATED_API #ifndef U_HIDE_DEPRECATED_API /** * Constants for options flags for normalization. * Use 0 for default options, * including normalization according to the Unicode version * that is currently supported by ICU (see u_getUnicodeVersion). * @deprecated ICU 56 Use unorm2.h instead. */ enum { /** * Options bit set value to select Unicode 3.2 normalization * (except NormalizationCorrections). * At most one Unicode version can be selected at a time. * @deprecated ICU 56 Use unorm2.h instead. */ UNORM_UNICODE_3_2=0x20 }; /** * Lowest-order bit number of unorm_compare() options bits corresponding to * normalization options bits. * * The options parameter for unorm_compare() uses most bits for * itself and for various comparison and folding flags. * The most significant bits, however, are shifted down and passed on * to the normalization implementation. * (That is, from unorm_compare(..., options, ...), * options>>UNORM_COMPARE_NORM_OPTIONS_SHIFT will be passed on to the * internal normalization functions.) * * @see unorm_compare * @deprecated ICU 56 Use unorm2.h instead. */ #define UNORM_COMPARE_NORM_OPTIONS_SHIFT 20 /** * Normalize a string. * The string will be normalized according the specified normalization mode * and options. * The source and result buffers must not be the same, nor overlap. * * @param source The string to normalize. * @param sourceLength The length of source, or -1 if NUL-terminated. * @param mode The normalization mode; one of UNORM_NONE, * UNORM_NFD, UNORM_NFC, UNORM_NFKC, UNORM_NFKD, UNORM_DEFAULT. * @param options The normalization options, ORed together (0 for no options). * @param result A pointer to a buffer to receive the result string. * The result string is NUL-terminated if possible. * @param resultLength The maximum size of result. * @param status A pointer to a UErrorCode to receive any errors. * @return The total buffer size needed; if greater than resultLength, * the output was truncated, and the error code is set to U_BUFFER_OVERFLOW_ERROR. * @deprecated ICU 56 Use unorm2.h instead. */ U_DEPRECATED int32_t U_EXPORT2 unorm_normalize(const UChar *source, int32_t sourceLength, UNormalizationMode mode, int32_t options, UChar *result, int32_t resultLength, UErrorCode *status); /** * Performing quick check on a string, to quickly determine if the string is * in a particular normalization format. * Three types of result can be returned UNORM_YES, UNORM_NO or * UNORM_MAYBE. Result UNORM_YES indicates that the argument * string is in the desired normalized format, UNORM_NO determines that * argument string is not in the desired normalized format. A * UNORM_MAYBE result indicates that a more thorough check is required, * the user may have to put the string in its normalized form and compare the * results. * * @param source string for determining if it is in a normalized format * @param sourcelength length of source to test, or -1 if NUL-terminated * @param mode which normalization form to test for * @param status a pointer to a UErrorCode to receive any errors * @return UNORM_YES, UNORM_NO or UNORM_MAYBE * * @see unorm_isNormalized * @deprecated ICU 56 Use unorm2.h instead. */ U_DEPRECATED UNormalizationCheckResult U_EXPORT2 unorm_quickCheck(const UChar *source, int32_t sourcelength, UNormalizationMode mode, UErrorCode *status); /** * Performing quick check on a string; same as unorm_quickCheck but * takes an extra options parameter like most normalization functions. * * @param src String that is to be tested if it is in a normalization format. * @param srcLength Length of source to test, or -1 if NUL-terminated. * @param mode Which normalization form to test for. * @param options The normalization options, ORed together (0 for no options). * @param pErrorCode ICU error code in/out parameter. * Must fulfill U_SUCCESS before the function call. * @return UNORM_YES, UNORM_NO or UNORM_MAYBE * * @see unorm_quickCheck * @see unorm_isNormalized * @deprecated ICU 56 Use unorm2.h instead. */ U_DEPRECATED UNormalizationCheckResult U_EXPORT2 unorm_quickCheckWithOptions(const UChar *src, int32_t srcLength, UNormalizationMode mode, int32_t options, UErrorCode *pErrorCode); /** * Test if a string is in a given normalization form. * This is semantically equivalent to source.equals(normalize(source, mode)) . * * Unlike unorm_quickCheck(), this function returns a definitive result, * never a "maybe". * For NFD, NFKD, and FCD, both functions work exactly the same. * For NFC and NFKC where quickCheck may return "maybe", this function will * perform further tests to arrive at a true/false result. * * @param src String that is to be tested if it is in a normalization format. * @param srcLength Length of source to test, or -1 if NUL-terminated. * @param mode Which normalization form to test for. * @param pErrorCode ICU error code in/out parameter. * Must fulfill U_SUCCESS before the function call. * @return Boolean value indicating whether the source string is in the * "mode" normalization form. * * @see unorm_quickCheck * @deprecated ICU 56 Use unorm2.h instead. */ U_DEPRECATED UBool U_EXPORT2 unorm_isNormalized(const UChar *src, int32_t srcLength, UNormalizationMode mode, UErrorCode *pErrorCode); /** * Test if a string is in a given normalization form; same as unorm_isNormalized but * takes an extra options parameter like most normalization functions. * * @param src String that is to be tested if it is in a normalization format. * @param srcLength Length of source to test, or -1 if NUL-terminated. * @param mode Which normalization form to test for. * @param options The normalization options, ORed together (0 for no options). * @param pErrorCode ICU error code in/out parameter. * Must fulfill U_SUCCESS before the function call. * @return Boolean value indicating whether the source string is in the * "mode/options" normalization form. * * @see unorm_quickCheck * @see unorm_isNormalized * @deprecated ICU 56 Use unorm2.h instead. */ U_DEPRECATED UBool U_EXPORT2 unorm_isNormalizedWithOptions(const UChar *src, int32_t srcLength, UNormalizationMode mode, int32_t options, UErrorCode *pErrorCode); /** * Iterative normalization forward. * This function (together with unorm_previous) is somewhat * similar to the C++ Normalizer class (see its non-static functions). * * Iterative normalization is useful when only a small portion of a longer * string/text needs to be processed. * * For example, the likelihood may be high that processing the first 10% of some * text will be sufficient to find certain data. * Another example: When one wants to concatenate two normalized strings and get a * normalized result, it is much more efficient to normalize just a small part of * the result around the concatenation place instead of re-normalizing everything. * * The input text is an instance of the C character iteration API UCharIterator. * It may wrap around a simple string, a CharacterIterator, a Replaceable, or any * other kind of text object. * * If a buffer overflow occurs, then the caller needs to reset the iterator to the * old index and call the function again with a larger buffer - if the caller cares * for the actual output. * Regardless of the output buffer, the iterator will always be moved to the next * normalization boundary. * * This function (like unorm_previous) serves two purposes: * * 1) To find the next boundary so that the normalization of the part of the text * from the current position to that boundary does not affect and is not affected * by the part of the text beyond that boundary. * * 2) To normalize the text up to the boundary. * * The second step is optional, per the doNormalize parameter. * It is omitted for operations like string concatenation, where the two adjacent * string ends need to be normalized together. * In such a case, the output buffer will just contain a copy of the text up to the * boundary. * * pNeededToNormalize is an output-only parameter. Its output value is only defined * if normalization was requested (doNormalize) and successful (especially, no * buffer overflow). * It is useful for operations like a normalizing transliterator, where one would * not want to replace a piece of text if it is not modified. * * If doNormalize==true and pNeededToNormalize!=NULL then *pNeeded... is set true * if the normalization was necessary. * * If doNormalize==false then *pNeededToNormalize will be set to false. * * If the buffer overflows, then *pNeededToNormalize will be undefined; * essentially, whenever U_FAILURE is true (like in buffer overflows), this result * will be undefined. * * @param src The input text in the form of a C character iterator. * @param dest The output buffer; can be NULL if destCapacity==0 for pure preflighting. * @param destCapacity The number of UChars that fit into dest. * @param mode The normalization mode. * @param options The normalization options, ORed together (0 for no options). * @param doNormalize Indicates if the source text up to the next boundary * is to be normalized (true) or just copied (false). * @param pNeededToNormalize Output flag indicating if the normalization resulted in * different text from the input. * Not defined if an error occurs including buffer overflow. * Always false if !doNormalize. * @param pErrorCode ICU error code in/out parameter. * Must fulfill U_SUCCESS before the function call. * @return Length of output (number of UChars) when successful or buffer overflow. * * @see unorm_previous * @see unorm_normalize * * @deprecated ICU 56 Use unorm2.h instead. */ U_DEPRECATED int32_t U_EXPORT2 unorm_next(UCharIterator *src, UChar *dest, int32_t destCapacity, UNormalizationMode mode, int32_t options, UBool doNormalize, UBool *pNeededToNormalize, UErrorCode *pErrorCode); /** * Iterative normalization backward. * This function (together with unorm_next) is somewhat * similar to the C++ Normalizer class (see its non-static functions). * For all details see unorm_next. * * @param src The input text in the form of a C character iterator. * @param dest The output buffer; can be NULL if destCapacity==0 for pure preflighting. * @param destCapacity The number of UChars that fit into dest. * @param mode The normalization mode. * @param options The normalization options, ORed together (0 for no options). * @param doNormalize Indicates if the source text up to the next boundary * is to be normalized (true) or just copied (false). * @param pNeededToNormalize Output flag indicating if the normalization resulted in * different text from the input. * Not defined if an error occurs including buffer overflow. * Always false if !doNormalize. * @param pErrorCode ICU error code in/out parameter. * Must fulfill U_SUCCESS before the function call. * @return Length of output (number of UChars) when successful or buffer overflow. * * @see unorm_next * @see unorm_normalize * * @deprecated ICU 56 Use unorm2.h instead. */ U_DEPRECATED int32_t U_EXPORT2 unorm_previous(UCharIterator *src, UChar *dest, int32_t destCapacity, UNormalizationMode mode, int32_t options, UBool doNormalize, UBool *pNeededToNormalize, UErrorCode *pErrorCode); /** * Concatenate normalized strings, making sure that the result is normalized as well. * * If both the left and the right strings are in * the normalization form according to "mode/options", * then the result will be * * \code * dest=normalize(left+right, mode, options) * \endcode * * With the input strings already being normalized, * this function will use unorm_next() and unorm_previous() * to find the adjacent end pieces of the input strings. * Only the concatenation of these end pieces will be normalized and * then concatenated with the remaining parts of the input strings. * * It is allowed to have dest==left to avoid copying the entire left string. * * @param left Left source string, may be same as dest. * @param leftLength Length of left source string, or -1 if NUL-terminated. * @param right Right source string. Must not be the same as dest, nor overlap. * @param rightLength Length of right source string, or -1 if NUL-terminated. * @param dest The output buffer; can be NULL if destCapacity==0 for pure preflighting. * @param destCapacity The number of UChars that fit into dest. * @param mode The normalization mode. * @param options The normalization options, ORed together (0 for no options). * @param pErrorCode ICU error code in/out parameter. * Must fulfill U_SUCCESS before the function call. * @return Length of output (number of UChars) when successful or buffer overflow. * * @see unorm_normalize * @see unorm_next * @see unorm_previous * * @deprecated ICU 56 Use unorm2.h instead. */ U_DEPRECATED int32_t U_EXPORT2 unorm_concatenate(const UChar *left, int32_t leftLength, const UChar *right, int32_t rightLength, UChar *dest, int32_t destCapacity, UNormalizationMode mode, int32_t options, UErrorCode *pErrorCode); #endif /* U_HIDE_DEPRECATED_API */ #endif /* #if !UCONFIG_NO_NORMALIZATION */ #endif
Save
cmd:
run