golden hour
/opt/alt/libicu65/usr/include/unicode
⬆️ Go Up
Upload
File/Folder
Size
Actions
alphaindex.h
26.48 KB
Del
OK
appendable.h
8.49 KB
Del
OK
basictz.h
9.15 KB
Del
OK
brkiter.h
27.8 KB
Del
OK
bytestream.h
9.6 KB
Del
OK
bytestrie.h
20.77 KB
Del
OK
bytestriebuilder.h
7.08 KB
Del
OK
calendar.h
105.74 KB
Del
OK
caniter.h
7.43 KB
Del
OK
casemap.h
25.33 KB
Del
OK
char16ptr.h
7.22 KB
Del
OK
chariter.h
24.05 KB
Del
OK
choicfmt.h
23.91 KB
Del
OK
coleitr.h
13.76 KB
Del
OK
coll.h
56.23 KB
Del
OK
compactdecimalformat.h
6.88 KB
Del
OK
curramt.h
3.76 KB
Del
OK
currpinf.h
7.3 KB
Del
OK
currunit.h
4.05 KB
Del
OK
datefmt.h
40.67 KB
Del
OK
dbbi.h
1.19 KB
Del
OK
dcfmtsym.h
20.13 KB
Del
OK
decimfmt.h
87.38 KB
Del
OK
docmain.h
6.97 KB
Del
OK
dtfmtsym.h
37.7 KB
Del
OK
dtintrv.h
3.84 KB
Del
OK
dtitvfmt.h
46.63 KB
Del
OK
dtitvinf.h
18.51 KB
Del
OK
dtptngen.h
25.08 KB
Del
OK
dtrule.h
8.68 KB
Del
OK
edits.h
20.74 KB
Del
OK
enumset.h
2.08 KB
Del
OK
errorcode.h
4.84 KB
Del
OK
fieldpos.h
8.69 KB
Del
OK
filteredbrk.h
5.37 KB
Del
OK
fmtable.h
24.42 KB
Del
OK
format.h
12.5 KB
Del
OK
formattedvalue.h
10.27 KB
Del
OK
fpositer.h
3.04 KB
Del
OK
gender.h
3.33 KB
Del
OK
gregocal.h
31.71 KB
Del
OK
icudataver.h
1.03 KB
Del
OK
icuplug.h
11.88 KB
Del
OK
idna.h
12.7 KB
Del
OK
listformatter.h
9.47 KB
Del
OK
localebuilder.h
11.27 KB
Del
OK
localematcher.h
22.5 KB
Del
OK
localpointer.h
19.69 KB
Del
OK
locdspnm.h
7.12 KB
Del
OK
locid.h
47.4 KB
Del
OK
measfmt.h
11.33 KB
Del
OK
measunit.h
93.31 KB
Del
OK
measure.h
4.32 KB
Del
OK
messagepattern.h
33.71 KB
Del
OK
msgfmt.h
44.11 KB
Del
OK
normalizer2.h
34.03 KB
Del
OK
normlzr.h
30.94 KB
Del
OK
nounit.h
2.69 KB
Del
OK
numberformatter.h
86.31 KB
Del
OK
numberrangeformatter.h
30.14 KB
Del
OK
numfmt.h
49.81 KB
Del
OK
numsys.h
7.19 KB
Del
OK
parseerr.h
3.08 KB
Del
OK
parsepos.h
5.56 KB
Del
OK
platform.h
28.08 KB
Del
OK
plurfmt.h
25.2 KB
Del
OK
plurrule.h
18.39 KB
Del
OK
ptypes.h
3.49 KB
Del
OK
putil.h
6.33 KB
Del
OK
rbbi.h
26.58 KB
Del
OK
rbnf.h
48.73 KB
Del
OK
rbtz.h
15.6 KB
Del
OK
regex.h
84.36 KB
Del
OK
region.h
9.18 KB
Del
OK
reldatefmt.h
22.62 KB
Del
OK
rep.h
9.37 KB
Del
OK
resbund.h
18.07 KB
Del
OK
schriter.h
6.32 KB
Del
OK
scientificnumberformatter.h
6.4 KB
Del
OK
search.h
22.22 KB
Del
OK
selfmt.h
14.3 KB
Del
OK
simpleformatter.h
12.59 KB
Del
OK
simpletz.h
45.44 KB
Del
OK
smpdtfmt.h
70.97 KB
Del
OK
sortkey.h
11.18 KB
Del
OK
std_string.h
1.05 KB
Del
OK
strenum.h
9.92 KB
Del
OK
stringoptions.h
5.79 KB
Del
OK
stringpiece.h
7.38 KB
Del
OK
stringtriebuilder.h
15.33 KB
Del
OK
stsearch.h
21.3 KB
Del
OK
symtable.h
4.27 KB
Del
OK
tblcoll.h
36.61 KB
Del
OK
timezone.h
41.02 KB
Del
OK
tmunit.h
3.38 KB
Del
OK
tmutamt.h
4.9 KB
Del
OK
tmutfmt.h
7.85 KB
Del
OK
translit.h
65.82 KB
Del
OK
tzfmt.h
42.89 KB
Del
OK
tznames.h
16.85 KB
Del
OK
tzrule.h
35.37 KB
Del
OK
tztrans.h
6.12 KB
Del
OK
ubidi.h
89.56 KB
Del
OK
ubiditransform.h
12.65 KB
Del
OK
ubrk.h
23.97 KB
Del
OK
ucal.h
56.9 KB
Del
OK
ucasemap.h
15.18 KB
Del
OK
ucat.h
5.36 KB
Del
OK
uchar.h
140.56 KB
Del
OK
ucharstrie.h
22.58 KB
Del
OK
ucharstriebuilder.h
7.21 KB
Del
OK
uchriter.h
13.2 KB
Del
OK
uclean.h
11.21 KB
Del
OK
ucnv.h
83.09 KB
Del
OK
ucnv_cb.h
6.59 KB
Del
OK
ucnv_err.h
20.99 KB
Del
OK
ucnvsel.h
6.14 KB
Del
OK
ucol.h
61.46 KB
Del
OK
ucoleitr.h
9.46 KB
Del
OK
uconfig.h
12.07 KB
Del
OK
ucpmap.h
5.53 KB
Del
OK
ucptrie.h
22.46 KB
Del
OK
ucsdet.h
14.67 KB
Del
OK
ucurr.h
16.12 KB
Del
OK
udat.h
60.88 KB
Del
OK
udata.h
15.56 KB
Del
OK
udateintervalformat.h
10.03 KB
Del
OK
udatpg.h
26.01 KB
Del
OK
udisplaycontext.h
5.89 KB
Del
OK
uenum.h
7.78 KB
Del
OK
ufieldpositer.h
4.36 KB
Del
OK
uformattable.h
10.94 KB
Del
OK
uformattedvalue.h
12.14 KB
Del
OK
ugender.h
2 KB
Del
OK
uidna.h
33.37 KB
Del
OK
uiter.h
22.77 KB
Del
OK
uldnames.h
10.45 KB
Del
OK
ulistformatter.h
8.83 KB
Del
OK
uloc.h
52.54 KB
Del
OK
ulocdata.h
11.26 KB
Del
OK
umachine.h
14.53 KB
Del
OK
umisc.h
1.33 KB
Del
OK
umsg.h
24.23 KB
Del
OK
umutablecptrie.h
8.24 KB
Del
OK
unifilt.h
3.96 KB
Del
OK
unifunct.h
4.04 KB
Del
OK
unimatch.h
6.1 KB
Del
OK
unirepl.h
3.38 KB
Del
OK
uniset.h
64.9 KB
Del
OK
unistr.h
170.43 KB
Del
OK
unorm.h
20.52 KB
Del
OK
unorm2.h
24.66 KB
Del
OK
unum.h
53.62 KB
Del
OK
unumberformatter.h
25.36 KB
Del
OK
unumsys.h
7.21 KB
Del
OK
uobject.h
10.68 KB
Del
OK
upluralrules.h
7.88 KB
Del
OK
uregex.h
72.05 KB
Del
OK
uregion.h
9.84 KB
Del
OK
ureldatefmt.h
17.26 KB
Del
OK
urename.h
130.97 KB
Del
OK
urep.h
5.38 KB
Del
OK
ures.h
36.54 KB
Del
OK
uscript.h
26.87 KB
Del
OK
usearch.h
38.12 KB
Del
OK
uset.h
40 KB
Del
OK
usetiter.h
9.55 KB
Del
OK
ushape.h
18 KB
Del
OK
uspoof.h
65.9 KB
Del
OK
usprep.h
8.14 KB
Del
OK
ustdio.h
38.54 KB
Del
OK
ustream.h
1.89 KB
Del
OK
ustring.h
72.47 KB
Del
OK
ustringtrie.h
3.15 KB
Del
OK
utext.h
58.13 KB
Del
OK
utf.h
7.86 KB
Del
OK
utf16.h
23.32 KB
Del
OK
utf32.h
763 B
Del
OK
utf8.h
30.96 KB
Del
OK
utf_old.h
45.83 KB
Del
OK
utmscale.h
13.78 KB
Del
OK
utrace.h
15.73 KB
Del
OK
utrans.h
25.52 KB
Del
OK
utypes.h
30.74 KB
Del
OK
uvernum.h
6.67 KB
Del
OK
uversion.h
6 KB
Del
OK
vtzone.h
20.3 KB
Del
OK
Edit: unorm2.h
// © 2016 and later: Unicode, Inc. and others. // License & terms of use: http://www.unicode.org/copyright.html /* ******************************************************************************* * * Copyright (C) 2009-2015, International Business Machines * Corporation and others. All Rights Reserved. * ******************************************************************************* * file name: unorm2.h * encoding: UTF-8 * tab size: 8 (not used) * indentation:4 * * created on: 2009dec15 * created by: Markus W. Scherer */ #ifndef __UNORM2_H__ #define __UNORM2_H__ /** * \file * \brief C API: New API for Unicode Normalization. * * Unicode normalization functionality for standard Unicode normalization or * for using custom mapping tables. * All instances of UNormalizer2 are unmodifiable/immutable. * Instances returned by unorm2_getInstance() are singletons that must not be deleted by the caller. * For more details see the Normalizer2 C++ class. */ #include "unicode/utypes.h" #include "unicode/localpointer.h" #include "unicode/stringoptions.h" #include "unicode/uset.h" /** * Constants for normalization modes. * For details about standard Unicode normalization forms * and about the algorithms which are also used with custom mapping tables * see http://www.unicode.org/unicode/reports/tr15/ * @stable ICU 4.4 */ typedef enum { /** * Decomposition followed by composition. * Same as standard NFC when using an "nfc" instance. * Same as standard NFKC when using an "nfkc" instance. * For details about standard Unicode normalization forms * see http://www.unicode.org/unicode/reports/tr15/ * @stable ICU 4.4 */ UNORM2_COMPOSE, /** * Map, and reorder canonically. * Same as standard NFD when using an "nfc" instance. * Same as standard NFKD when using an "nfkc" instance. * For details about standard Unicode normalization forms * see http://www.unicode.org/unicode/reports/tr15/ * @stable ICU 4.4 */ UNORM2_DECOMPOSE, /** * "Fast C or D" form. * If a string is in this form, then further decomposition <i>without reordering</i> * would yield the same form as DECOMPOSE. * Text in "Fast C or D" form can be processed efficiently with data tables * that are "canonically closed", that is, that provide equivalent data for * equivalent text, without having to be fully normalized. * Not a standard Unicode normalization form. * Not a unique form: Different FCD strings can be canonically equivalent. * For details see http://www.unicode.org/notes/tn5/#FCD * @stable ICU 4.4 */ UNORM2_FCD, /** * Compose only contiguously. * Also known as "FCC" or "Fast C Contiguous". * The result will often but not always be in NFC. * The result will conform to FCD which is useful for processing. * Not a standard Unicode normalization form. * For details see http://www.unicode.org/notes/tn5/#FCC * @stable ICU 4.4 */ UNORM2_COMPOSE_CONTIGUOUS } UNormalization2Mode; /** * Result values for normalization quick check functions. * For details see http://www.unicode.org/reports/tr15/#Detecting_Normalization_Forms * @stable ICU 2.0 */ typedef enum UNormalizationCheckResult { /** * The input string is not in the normalization form. * @stable ICU 2.0 */ UNORM_NO, /** * The input string is in the normalization form. * @stable ICU 2.0 */ UNORM_YES, /** * The input string may or may not be in the normalization form. * This value is only returned for composition forms like NFC and FCC, * when a backward-combining character is found for which the surrounding text * would have to be analyzed further. * @stable ICU 2.0 */ UNORM_MAYBE } UNormalizationCheckResult; /** * Opaque C service object type for the new normalization API. * @stable ICU 4.4 */ struct UNormalizer2; typedef struct UNormalizer2 UNormalizer2; /**< C typedef for struct UNormalizer2. @stable ICU 4.4 */ #if !UCONFIG_NO_NORMALIZATION /** * Returns a UNormalizer2 instance for Unicode NFC normalization. * Same as unorm2_getInstance(NULL, "nfc", UNORM2_COMPOSE, pErrorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 49 */ U_STABLE const UNormalizer2 * U_EXPORT2 unorm2_getNFCInstance(UErrorCode *pErrorCode); /** * Returns a UNormalizer2 instance for Unicode NFD normalization. * Same as unorm2_getInstance(NULL, "nfc", UNORM2_DECOMPOSE, pErrorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 49 */ U_STABLE const UNormalizer2 * U_EXPORT2 unorm2_getNFDInstance(UErrorCode *pErrorCode); /** * Returns a UNormalizer2 instance for Unicode NFKC normalization. * Same as unorm2_getInstance(NULL, "nfkc", UNORM2_COMPOSE, pErrorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 49 */ U_STABLE const UNormalizer2 * U_EXPORT2 unorm2_getNFKCInstance(UErrorCode *pErrorCode); /** * Returns a UNormalizer2 instance for Unicode NFKD normalization. * Same as unorm2_getInstance(NULL, "nfkc", UNORM2_DECOMPOSE, pErrorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 49 */ U_STABLE const UNormalizer2 * U_EXPORT2 unorm2_getNFKDInstance(UErrorCode *pErrorCode); /** * Returns a UNormalizer2 instance for Unicode NFKC_Casefold normalization. * Same as unorm2_getInstance(NULL, "nfkc_cf", UNORM2_COMPOSE, pErrorCode). * Returns an unmodifiable singleton instance. Do not delete it. * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested Normalizer2, if successful * @stable ICU 49 */ U_STABLE const UNormalizer2 * U_EXPORT2 unorm2_getNFKCCasefoldInstance(UErrorCode *pErrorCode); /** * Returns a UNormalizer2 instance which uses the specified data file * (packageName/name similar to ucnv_openPackage() and ures_open()/ResourceBundle) * and which composes or decomposes text according to the specified mode. * Returns an unmodifiable singleton instance. Do not delete it. * * Use packageName=NULL for data files that are part of ICU's own data. * Use name="nfc" and UNORM2_COMPOSE/UNORM2_DECOMPOSE for Unicode standard NFC/NFD. * Use name="nfkc" and UNORM2_COMPOSE/UNORM2_DECOMPOSE for Unicode standard NFKC/NFKD. * Use name="nfkc_cf" and UNORM2_COMPOSE for Unicode standard NFKC_CF=NFKC_Casefold. * * @param packageName NULL for ICU built-in data, otherwise application data package name * @param name "nfc" or "nfkc" or "nfkc_cf" or name of custom data file * @param mode normalization mode (compose or decompose etc.) * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested UNormalizer2, if successful * @stable ICU 4.4 */ U_STABLE const UNormalizer2 * U_EXPORT2 unorm2_getInstance(const char *packageName, const char *name, UNormalization2Mode mode, UErrorCode *pErrorCode); /** * Constructs a filtered normalizer wrapping any UNormalizer2 instance * and a filter set. * Both are aliased and must not be modified or deleted while this object * is used. * The filter set should be frozen; otherwise the performance will suffer greatly. * @param norm2 wrapped UNormalizer2 instance * @param filterSet USet which determines the characters to be normalized * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the requested UNormalizer2, if successful * @stable ICU 4.4 */ U_STABLE UNormalizer2 * U_EXPORT2 unorm2_openFiltered(const UNormalizer2 *norm2, const USet *filterSet, UErrorCode *pErrorCode); /** * Closes a UNormalizer2 instance from unorm2_openFiltered(). * Do not close instances from unorm2_getInstance()! * @param norm2 UNormalizer2 instance to be closed * @stable ICU 4.4 */ U_STABLE void U_EXPORT2 unorm2_close(UNormalizer2 *norm2); #if U_SHOW_CPLUSPLUS_API U_NAMESPACE_BEGIN /** * \class LocalUNormalizer2Pointer * "Smart pointer" class, closes a UNormalizer2 via unorm2_close(). * For most methods see the LocalPointerBase base class. * * @see LocalPointerBase * @see LocalPointer * @stable ICU 4.4 */ U_DEFINE_LOCAL_OPEN_POINTER(LocalUNormalizer2Pointer, UNormalizer2, unorm2_close); U_NAMESPACE_END #endif /** * Writes the normalized form of the source string to the destination string * (replacing its contents) and returns the length of the destination string. * The source and destination strings must be different buffers. * @param norm2 UNormalizer2 instance * @param src source string * @param length length of the source string, or -1 if NUL-terminated * @param dest destination string; its contents is replaced with normalized src * @param capacity number of UChars that can be written to dest * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return dest * @stable ICU 4.4 */ U_STABLE int32_t U_EXPORT2 unorm2_normalize(const UNormalizer2 *norm2, const UChar *src, int32_t length, UChar *dest, int32_t capacity, UErrorCode *pErrorCode); /** * Appends the normalized form of the second string to the first string * (merging them at the boundary) and returns the length of the first string. * The result is normalized if the first string was normalized. * The first and second strings must be different buffers. * @param norm2 UNormalizer2 instance * @param first string, should be normalized * @param firstLength length of the first string, or -1 if NUL-terminated * @param firstCapacity number of UChars that can be written to first * @param second string, will be normalized * @param secondLength length of the source string, or -1 if NUL-terminated * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return first * @stable ICU 4.4 */ U_STABLE int32_t U_EXPORT2 unorm2_normalizeSecondAndAppend(const UNormalizer2 *norm2, UChar *first, int32_t firstLength, int32_t firstCapacity, const UChar *second, int32_t secondLength, UErrorCode *pErrorCode); /** * Appends the second string to the first string * (merging them at the boundary) and returns the length of the first string. * The result is normalized if both the strings were normalized. * The first and second strings must be different buffers. * @param norm2 UNormalizer2 instance * @param first string, should be normalized * @param firstLength length of the first string, or -1 if NUL-terminated * @param firstCapacity number of UChars that can be written to first * @param second string, should be normalized * @param secondLength length of the source string, or -1 if NUL-terminated * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return first * @stable ICU 4.4 */ U_STABLE int32_t U_EXPORT2 unorm2_append(const UNormalizer2 *norm2, UChar *first, int32_t firstLength, int32_t firstCapacity, const UChar *second, int32_t secondLength, UErrorCode *pErrorCode); /** * Gets the decomposition mapping of c. * Roughly equivalent to normalizing the String form of c * on a UNORM2_DECOMPOSE UNormalizer2 instance, but much faster, and except that this function * returns a negative value and does not write a string * if c does not have a decomposition mapping in this instance's data. * This function is independent of the mode of the UNormalizer2. * @param norm2 UNormalizer2 instance * @param c code point * @param decomposition String buffer which will be set to c's * decomposition mapping, if there is one. * @param capacity number of UChars that can be written to decomposition * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the non-negative length of c's decomposition, if there is one; otherwise a negative value * @stable ICU 4.6 */ U_STABLE int32_t U_EXPORT2 unorm2_getDecomposition(const UNormalizer2 *norm2, UChar32 c, UChar *decomposition, int32_t capacity, UErrorCode *pErrorCode); /** * Gets the raw decomposition mapping of c. * * This is similar to the unorm2_getDecomposition() function but returns the * raw decomposition mapping as specified in UnicodeData.txt or * (for custom data) in the mapping files processed by the gennorm2 tool. * By contrast, unorm2_getDecomposition() returns the processed, * recursively-decomposed version of this mapping. * * When used on a standard NFKC Normalizer2 instance, * unorm2_getRawDecomposition() returns the Unicode Decomposition_Mapping (dm) property. * * When used on a standard NFC Normalizer2 instance, * it returns the Decomposition_Mapping only if the Decomposition_Type (dt) is Canonical (Can); * in this case, the result contains either one or two code points (=1..4 UChars). * * This function is independent of the mode of the UNormalizer2. * @param norm2 UNormalizer2 instance * @param c code point * @param decomposition String buffer which will be set to c's * raw decomposition mapping, if there is one. * @param capacity number of UChars that can be written to decomposition * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return the non-negative length of c's raw decomposition, if there is one; otherwise a negative value * @stable ICU 49 */ U_STABLE int32_t U_EXPORT2 unorm2_getRawDecomposition(const UNormalizer2 *norm2, UChar32 c, UChar *decomposition, int32_t capacity, UErrorCode *pErrorCode); /** * Performs pairwise composition of a & b and returns the composite if there is one. * * Returns a composite code point c only if c has a two-way mapping to a+b. * In standard Unicode normalization, this means that * c has a canonical decomposition to a+b * and c does not have the Full_Composition_Exclusion property. * * This function is independent of the mode of the UNormalizer2. * @param norm2 UNormalizer2 instance * @param a A (normalization starter) code point. * @param b Another code point. * @return The non-negative composite code point if there is one; otherwise a negative value. * @stable ICU 49 */ U_STABLE UChar32 U_EXPORT2 unorm2_composePair(const UNormalizer2 *norm2, UChar32 a, UChar32 b); /** * Gets the combining class of c. * The default implementation returns 0 * but all standard implementations return the Unicode Canonical_Combining_Class value. * @param norm2 UNormalizer2 instance * @param c code point * @return c's combining class * @stable ICU 49 */ U_STABLE uint8_t U_EXPORT2 unorm2_getCombiningClass(const UNormalizer2 *norm2, UChar32 c); /** * Tests if the string is normalized. * Internally, in cases where the quickCheck() method would return "maybe" * (which is only possible for the two COMPOSE modes) this method * resolves to "yes" or "no" to provide a definitive result, * at the cost of doing more work in those cases. * @param norm2 UNormalizer2 instance * @param s input string * @param length length of the string, or -1 if NUL-terminated * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return TRUE if s is normalized * @stable ICU 4.4 */ U_STABLE UBool U_EXPORT2 unorm2_isNormalized(const UNormalizer2 *norm2, const UChar *s, int32_t length, UErrorCode *pErrorCode); /** * Tests if the string is normalized. * For the two COMPOSE modes, the result could be "maybe" in cases that * would take a little more work to resolve definitively. * Use spanQuickCheckYes() and normalizeSecondAndAppend() for a faster * combination of quick check + normalization, to avoid * re-checking the "yes" prefix. * @param norm2 UNormalizer2 instance * @param s input string * @param length length of the string, or -1 if NUL-terminated * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return UNormalizationCheckResult * @stable ICU 4.4 */ U_STABLE UNormalizationCheckResult U_EXPORT2 unorm2_quickCheck(const UNormalizer2 *norm2, const UChar *s, int32_t length, UErrorCode *pErrorCode); /** * Returns the end of the normalized substring of the input string. * In other words, with <code>end=spanQuickCheckYes(s, ec);</code> * the substring <code>UnicodeString(s, 0, end)</code> * will pass the quick check with a "yes" result. * * The returned end index is usually one or more characters before the * "no" or "maybe" character: The end index is at a normalization boundary. * (See the class documentation for more about normalization boundaries.) * * When the goal is a normalized string and most input strings are expected * to be normalized already, then call this method, * and if it returns a prefix shorter than the input string, * copy that prefix and use normalizeSecondAndAppend() for the remainder. * @param norm2 UNormalizer2 instance * @param s input string * @param length length of the string, or -1 if NUL-terminated * @param pErrorCode Standard ICU error code. Its input value must * pass the U_SUCCESS() test, or else the function returns * immediately. Check for U_FAILURE() on output or use with * function chaining. (See User Guide for details.) * @return "yes" span end index * @stable ICU 4.4 */ U_STABLE int32_t U_EXPORT2 unorm2_spanQuickCheckYes(const UNormalizer2 *norm2, const UChar *s, int32_t length, UErrorCode *pErrorCode); /** * Tests if the character always has a normalization boundary before it, * regardless of context. * For details see the Normalizer2 base class documentation. * @param norm2 UNormalizer2 instance * @param c character to test * @return TRUE if c has a normalization boundary before it * @stable ICU 4.4 */ U_STABLE UBool U_EXPORT2 unorm2_hasBoundaryBefore(const UNormalizer2 *norm2, UChar32 c); /** * Tests if the character always has a normalization boundary after it, * regardless of context. * For details see the Normalizer2 base class documentation. * @param norm2 UNormalizer2 instance * @param c character to test * @return TRUE if c has a normalization boundary after it * @stable ICU 4.4 */ U_STABLE UBool U_EXPORT2 unorm2_hasBoundaryAfter(const UNormalizer2 *norm2, UChar32 c); /** * Tests if the character is normalization-inert. * For details see the Normalizer2 base class documentation. * @param norm2 UNormalizer2 instance * @param c character to test * @return TRUE if c is normalization-inert * @stable ICU 4.4 */ U_STABLE UBool U_EXPORT2 unorm2_isInert(const UNormalizer2 *norm2, UChar32 c); /** * Compares two strings for canonical equivalence. * Further options include case-insensitive comparison and * code point order (as opposed to code unit order). * * Canonical equivalence between two strings is defined as their normalized * forms (NFD or NFC) being identical. * This function compares strings incrementally instead of normalizing * (and optionally case-folding) both strings entirely, * improving performance significantly. * * Bulk normalization is only necessary if the strings do not fulfill the FCD * conditions. Only in this case, and only if the strings are relatively long, * is memory allocated temporarily. * For FCD strings and short non-FCD strings there is no memory allocation. * * Semantically, this is equivalent to * strcmp[CodePointOrder](NFD(foldCase(NFD(s1))), NFD(foldCase(NFD(s2)))) * where code point order and foldCase are all optional. * * UAX 21 2.5 Caseless Matching specifies that for a canonical caseless match * the case folding must be performed first, then the normalization. * * @param s1 First source string. * @param length1 Length of first source string, or -1 if NUL-terminated. * * @param s2 Second source string. * @param length2 Length of second source string, or -1 if NUL-terminated. * * @param options A bit set of options: * - U_FOLD_CASE_DEFAULT or 0 is used for default options: * Case-sensitive comparison in code unit order, and the input strings * are quick-checked for FCD. * * - UNORM_INPUT_IS_FCD * Set if the caller knows that both s1 and s2 fulfill the FCD conditions. * If not set, the function will quickCheck for FCD * and normalize if necessary. * * - U_COMPARE_CODE_POINT_ORDER * Set to choose code point order instead of code unit order * (see u_strCompare for details). * * - U_COMPARE_IGNORE_CASE * Set to compare strings case-insensitively using case folding, * instead of case-sensitively. * If set, then the following case folding options are used. * * - Options as used with case-insensitive comparisons, currently: * * - U_FOLD_CASE_EXCLUDE_SPECIAL_I * (see u_strCaseCompare for details) * * - regular normalization options shifted left by UNORM_COMPARE_NORM_OPTIONS_SHIFT * * @param pErrorCode ICU error code in/out parameter. * Must fulfill U_SUCCESS before the function call. * @return <0 or 0 or >0 as usual for string comparisons * * @see unorm_normalize * @see UNORM_FCD * @see u_strCompare * @see u_strCaseCompare * * @stable ICU 2.2 */ U_STABLE int32_t U_EXPORT2 unorm_compare(const UChar *s1, int32_t length1, const UChar *s2, int32_t length2, uint32_t options, UErrorCode *pErrorCode); #endif /* !UCONFIG_NO_NORMALIZATION */ #endif /* __UNORM2_H__ */
Save