Gecko [ dallasfobana2023.variationbd.com ]

Name	Size	Permission
alphaindex.h	26.54 KB	-rw-r--r--
appendable.h	8.54 KB	-rw-r--r--
basictz.h	9.99 KB	-rw-r--r--
brkiter.h	27.83 KB	-rw-r--r--
bytestream.h	10.75 KB	-rw-r--r--
bytestrie.h	20.8 KB	-rw-r--r--
bytestriebuilder.h	7.48 KB	-rw-r--r--
calendar.h	107.68 KB	-rw-r--r--
caniter.h	7.53 KB	-rw-r--r--
casemap.h	25.42 KB	-rw-r--r--
char16ptr.h	7.22 KB	-rw-r--r--
chariter.h	23.79 KB	-rw-r--r--
choicfmt.h	23.99 KB	-rw-r--r--
coleitr.h	13.77 KB	-rw-r--r--
coll.h	56.28 KB	-rw-r--r--
compactdecimalformat.h	6.88 KB	-rw-r--r--
curramt.h	3.67 KB	-rw-r--r--
currpinf.h	7.3 KB	-rw-r--r--
currunit.h	4.02 KB	-rw-r--r--
datefmt.h	40.7 KB	-rw-r--r--
dbbi.h	1.19 KB	-rw-r--r--
dcfmtsym.h	20.93 KB	-rw-r--r--
decimfmt.h	87.46 KB	-rw-r--r--
displayoptions.h	7.08 KB	-rw-r--r--
docmain.h	7.46 KB	-rw-r--r--
dtfmtsym.h	38.21 KB	-rw-r--r--
dtintrv.h	3.84 KB	-rw-r--r--
dtitvfmt.h	48.87 KB	-rw-r--r--
dtitvinf.h	18.63 KB	-rw-r--r--
dtptngen.h	28.05 KB	-rw-r--r--
dtrule.h	8.66 KB	-rw-r--r--
edits.h	20.73 KB	-rw-r--r--
enumset.h	2.08 KB	-rw-r--r--
errorcode.h	4.84 KB	-rw-r--r--
fieldpos.h	8.69 KB	-rw-r--r--
filteredbrk.h	5.37 KB	-rw-r--r--
fmtable.h	24.36 KB	-rw-r--r--
format.h	12.5 KB	-rw-r--r--
formattednumber.h	6.28 KB	-rw-r--r--
formattedvalue.h	9.75 KB	-rw-r--r--
fpositer.h	3.03 KB	-rw-r--r--
gender.h	3.35 KB	-rw-r--r--
gregocal.h	30.3 KB	-rw-r--r--
icudataver.h	1.02 KB	-rw-r--r--
icuplug.h	12.1 KB	-rw-r--r--
idna.h	12.71 KB	-rw-r--r--
listformatter.h	8.59 KB	-rw-r--r--
localebuilder.h	11.08 KB	-rw-r--r--
localematcher.h	26.86 KB	-rw-r--r--
localpointer.h	19.55 KB	-rw-r--r--
locdspnm.h	7.12 KB	-rw-r--r--
locid.h	48.31 KB	-rw-r--r--
measfmt.h	11.41 KB	-rw-r--r--
measunit.h	108.23 KB	-rw-r--r--
measure.h	4.68 KB	-rw-r--r--
messageformat2.h	18.13 KB	-rw-r--r--
messageformat2_arguments.h	4.3 KB	-rw-r--r--
messageformat2_data_model.h	123 KB	-rw-r--r--
messageformat2_data_model_name...	784 B	-rw-r--r--
messageformat2_formattable.h	38.29 KB	-rw-r--r--
messageformat2_function_regist...	18 KB	-rw-r--r--
messagepattern.h	33.72 KB	-rw-r--r--
msgfmt.h	44.2 KB	-rw-r--r--
normalizer2.h	34.73 KB	-rw-r--r--
normlzr.h	30.79 KB	-rw-r--r--
nounit.h	2.24 KB	-rw-r--r--
numberformatter.h	90.74 KB	-rw-r--r--
numberrangeformatter.h	26.05 KB	-rw-r--r--
numfmt.h	50.16 KB	-rw-r--r--
numsys.h	7.22 KB	-rw-r--r--
parseerr.h	3.08 KB	-rw-r--r--
parsepos.h	5.56 KB	-rw-r--r--
platform.h	26.66 KB	-rw-r--r--
plurfmt.h	25.07 KB	-rw-r--r--
plurrule.h	20.63 KB	-rw-r--r--
ptypes.h	2.16 KB	-rw-r--r--
putil.h	6.32 KB	-rw-r--r--
rbbi.h	32.04 KB	-rw-r--r--
rbnf.h	50.53 KB	-rw-r--r--
rbtz.h	15.75 KB	-rw-r--r--
regex.h	84.45 KB	-rw-r--r--
region.h	9.2 KB	-rw-r--r--
reldatefmt.h	22.36 KB	-rw-r--r--
rep.h	9.38 KB	-rw-r--r--
resbund.h	18.03 KB	-rw-r--r--
schriter.h	6.09 KB	-rw-r--r--
scientificnumberformatter.h	6.44 KB	-rw-r--r--
search.h	22.21 KB	-rw-r--r--
selfmt.h	14.35 KB	-rw-r--r--
simpleformatter.h	12.58 KB	-rw-r--r--
simplenumberformatter.h	9.18 KB	-rw-r--r--
simpletz.h	45.62 KB	-rw-r--r--
smpdtfmt.h	57.06 KB	-rw-r--r--
sortkey.h	11.12 KB	-rw-r--r--
std_string.h	1.05 KB	-rw-r--r--
strenum.h	9.96 KB	-rw-r--r--
stringoptions.h	5.79 KB	-rw-r--r--
stringpiece.h	10.02 KB	-rw-r--r--
stringtriebuilder.h	15.5 KB	-rw-r--r--
stsearch.h	21.43 KB	-rw-r--r--
symtable.h	4.28 KB	-rw-r--r--
tblcoll.h	36.93 KB	-rw-r--r--
timezone.h	45.64 KB	-rw-r--r--
tmunit.h	3.4 KB	-rw-r--r--
tmutamt.h	4.9 KB	-rw-r--r--
tmutfmt.h	7.42 KB	-rw-r--r--
translit.h	65.8 KB	-rw-r--r--
tzfmt.h	42.95 KB	-rw-r--r--
tznames.h	16.85 KB	-rw-r--r--
tzrule.h	34.81 KB	-rw-r--r--
tztrans.h	6.11 KB	-rw-r--r--
ubidi.h	89.61 KB	-rw-r--r--
ubiditransform.h	12.71 KB	-rw-r--r--
ubrk.h	24.43 KB	-rw-r--r--
ucal.h	64.01 KB	-rw-r--r--
ucasemap.h	15.21 KB	-rw-r--r--
ucat.h	5.35 KB	-rw-r--r--
uchar.h	150.13 KB	-rw-r--r--
ucharstrie.h	22.56 KB	-rw-r--r--
ucharstriebuilder.h	7.48 KB	-rw-r--r--
uchriter.h	13.24 KB	-rw-r--r--
uclean.h	11.21 KB	-rw-r--r--
ucnv.h	83.34 KB	-rw-r--r--
ucnv_cb.h	6.58 KB	-rw-r--r--
ucnv_err.h	20.98 KB	-rw-r--r--
ucnvsel.h	6.24 KB	-rw-r--r--
ucol.h	62.7 KB	-rw-r--r--
ucoleitr.h	9.82 KB	-rw-r--r--
uconfig.h	12.56 KB	-rw-r--r--
ucpmap.h	5.54 KB	-rw-r--r--
ucptrie.h	22.51 KB	-rw-r--r--
ucsdet.h	14.69 KB	-rw-r--r--
ucurr.h	16.72 KB	-rw-r--r--
udat.h	62.36 KB	-rw-r--r--
udata.h	15.63 KB	-rw-r--r--
udateintervalformat.h	11.93 KB	-rw-r--r--
udatpg.h	30.13 KB	-rw-r--r--
udisplaycontext.h	5.94 KB	-rw-r--r--
udisplayoptions.h	8.86 KB	-rw-r--r--
uenum.h	7.79 KB	-rw-r--r--
ufieldpositer.h	4.41 KB	-rw-r--r--
uformattable.h	10.97 KB	-rw-r--r--
uformattednumber.h	8.09 KB	-rw-r--r--
uformattedvalue.h	12.25 KB	-rw-r--r--
ugender.h	2.06 KB	-rw-r--r--
uidna.h	33.43 KB	-rw-r--r--
uiter.h	22.75 KB	-rw-r--r--
uldnames.h	10.48 KB	-rw-r--r--
ulistformatter.h	10.78 KB	-rw-r--r--
uloc.h	55.38 KB	-rw-r--r--
ulocale.h	6.35 KB	-rw-r--r--
ulocbuilder.h	16.73 KB	-rw-r--r--
ulocdata.h	11.3 KB	-rw-r--r--
umachine.h	14.59 KB	-rw-r--r--
umisc.h	1.34 KB	-rw-r--r--
umsg.h	24.25 KB	-rw-r--r--
umutablecptrie.h	8.3 KB	-rw-r--r--
unifilt.h	4 KB	-rw-r--r--
unifunct.h	4.05 KB	-rw-r--r--
unimatch.h	6.1 KB	-rw-r--r--
unirepl.h	3.38 KB	-rw-r--r--
uniset.h	66.82 KB	-rw-r--r--
unistr.h	171.33 KB	-rw-r--r--
unorm.h	20.55 KB	-rw-r--r--
unorm2.h	25.71 KB	-rw-r--r--
unum.h	55.16 KB	-rw-r--r--
unumberformatter.h	19.68 KB	-rw-r--r--
unumberoptions.h	5.23 KB	-rw-r--r--
unumberrangeformatter.h	15.35 KB	-rw-r--r--
unumsys.h	7.26 KB	-rw-r--r--
uobject.h	10.66 KB	-rw-r--r--
upluralrules.h	8.79 KB	-rw-r--r--
uregex.h	71.99 KB	-rw-r--r--
uregion.h	9.81 KB	-rw-r--r--
ureldatefmt.h	16.98 KB	-rw-r--r--
urename.h	141.31 KB	-rw-r--r--
urep.h	5.38 KB	-rw-r--r--
ures.h	36.65 KB	-rw-r--r--
uscript.h	27.89 KB	-rw-r--r--
usearch.h	39.21 KB	-rw-r--r--
uset.h	45.56 KB	-rw-r--r--
usetiter.h	9.63 KB	-rw-r--r--
ushape.h	18 KB	-rw-r--r--
usimplenumberformatter.h	7.63 KB	-rw-r--r--
uspoof.h	80.32 KB	-rw-r--r--
usprep.h	8.19 KB	-rw-r--r--
ustdio.h	38.56 KB	-rw-r--r--
ustream.h	1.89 KB	-rw-r--r--
ustring.h	72.13 KB	-rw-r--r--
ustringtrie.h	3.15 KB	-rw-r--r--
utext.h	58.1 KB	-rw-r--r--
utf.h	7.87 KB	-rw-r--r--
utf16.h	23.35 KB	-rw-r--r--
utf32.h	763 B	-rw-r--r--
utf8.h	30.83 KB	-rw-r--r--
utf_old.h	45.8 KB	-rw-r--r--
utmscale.h	13.78 KB	-rw-r--r--
utrace.h	17.18 KB	-rw-r--r--
utrans.h	25.54 KB	-rw-r--r--
utypes.h	33.71 KB	-rw-r--r--
uvernum.h	6.33 KB	-rw-r--r--
uversion.h	5.99 KB	-rw-r--r--
vtzone.h	20.68 KB	-rw-r--r--

Code Editor : 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/stringoptions.h"
#include "unicode/uset.h"

#if U_SHOW_CPLUSPLUS_API
#include "unicode/localpointer.h"
#endif   // U_SHOW_CPLUSPLUS_API

/**
 * 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_CAPI 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_CAPI 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_CAPI 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_CAPI const UNormalizer2 * U_EXPORT2
unorm2_getNFKDInstance(UErrorCode *pErrorCode);

/**
 * Returns a UNormalizer2 instance for Unicode toNFKC_Casefold() normalization
 * which is equivalent to applying the NFKC_Casefold mappings and then NFC.
 * See https://www.unicode.org/reports/tr44/#NFKC_Casefold
 *
 * 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_CAPI const UNormalizer2 * U_EXPORT2
unorm2_getNFKCCasefoldInstance(UErrorCode *pErrorCode);

#ifndef U_HIDE_DRAFT_API
/**
 * Returns a UNormalizer2 instance for a variant of Unicode toNFKC_Casefold() normalization
 * which is equivalent to applying the NFKC_Simple_Casefold mappings and then NFC.
 * See https://www.unicode.org/reports/tr44/#NFKC_Simple_Casefold
 *
 * Same as unorm2_getInstance(NULL, "nfkc_scf", 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
 * @draft ICU 74
 */
U_CAPI const UNormalizer2 * U_EXPORT2
unorm2_getNFKCSimpleCasefoldInstance(UErrorCode *pErrorCode);
#endif  // U_HIDE_DRAFT_API

/**
 * 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 "nfkc_scf" 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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_CAPI 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__ */

${this.title}

Code Editor : unorm2.h