FM / unicode

/usr/include/unicode

Name	Size	Mode	Actions
alphaindex.h	27118	0644	edit dl rm
appendable.h	8694	0644	edit dl rm
basictz.h	9491	0644	edit dl rm
brkiter.h	28464	0644	edit dl rm
bytestream.h	11037	0644	edit dl rm
bytestrie.h	21266	0644	edit dl rm
bytestriebuilder.h	7248	0644	edit dl rm
calendar.h	108278	0644	edit dl rm
caniter.h	7611	0644	edit dl rm
casemap.h	25933	0644	edit dl rm
char16ptr.h	7393	0644	edit dl rm
chariter.h	24632	0644	edit dl rm
choicfmt.h	24482	0644	edit dl rm
coleitr.h	14094	0644	edit dl rm
coll.h	57581	0644	edit dl rm
compactdecimalformat.h	7047	0644	edit dl rm
curramt.h	3851	0644	edit dl rm
currpinf.h	7473	0644	edit dl rm
currunit.h	4094	0644	edit dl rm
datefmt.h	41641	0644	edit dl rm
dbbi.h	1223	0644	edit dl rm
dcfmtsym.h	20897	0644	edit dl rm
decimfmt.h	89278	0644	edit dl rm
docmain.h	7142	0644	edit dl rm
dtfmtsym.h	38609	0644	edit dl rm
dtintrv.h	3930	0644	edit dl rm
dtitvfmt.h	47634	0644	edit dl rm
dtitvinf.h	19064	0644	edit dl rm
dtptngen.h	26419	0644	edit dl rm
dtrule.h	8888	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	8899	0644	edit dl rm
filteredbrk.h	5501	0644	edit dl rm
fmtable.h	25007	0644	edit dl rm
format.h	12802	0644	edit dl rm
formattedvalue.h	9987	0644	edit dl rm
fpositer.h	3109	0644	edit dl rm
gender.h	3408	0644	edit dl rm
gregocal.h	32472	0644	edit dl rm
icudataver.h	1051	0644	edit dl rm
icuplug.h	12166	0644	edit dl rm
idna.h	13000	0644	edit dl rm
listformatter.h	9493	0644	edit dl rm
localebuilder.h	11502	0644	edit dl rm
localematcher.h	25147	0644	edit dl rm
localpointer.h	19829	0644	edit dl rm
locdspnm.h	7292	0644	edit dl rm
locid.h	48821	0644	edit dl rm
measfmt.h	11603	0644	edit dl rm
measunit.h	97563	0644	edit dl rm
measure.h	4423	0644	edit dl rm
messagepattern.h	34521	0644	edit dl rm
msgfmt.h	45168	0644	edit dl rm
normalizer2.h	34851	0644	edit dl rm
normlzr.h	31682	0644	edit dl rm
nounit.h	2754	0644	edit dl rm
numberformatter.h	86276	0644	edit dl rm
numberrangeformatter.h	28617	0644	edit dl rm
numfmt.h	50950	0644	edit dl rm
numsys.h	7500	0644	edit dl rm
parseerr.h	3155	0644	edit dl rm
parsepos.h	5692	0644	edit dl rm
platform.h	28751	0644	edit dl rm
plurfmt.h	25800	0644	edit dl rm
plurrule.h	18780	0644	edit dl rm
ptypes.h	3577	0644	edit dl rm
putil.h	6487	0644	edit dl rm
rbbi.h	27218	0644	edit dl rm
rbnf.h	49899	0644	edit dl rm
rbtz.h	15979	0644	edit dl rm
regex.h	86367	0644	edit dl rm
region.h	9404	0644	edit dl rm
reldatefmt.h	22801	0644	edit dl rm
rep.h	9599	0644	edit dl rm
resbund.h	18503	0644	edit dl rm
schriter.h	6475	0644	edit dl rm
scientificnumberformatter.h	6553	0644	edit dl rm
search.h	22757	0644	edit dl rm
selfmt.h	14643	0644	edit dl rm
simpleformatter.h	12888	0644	edit dl rm
simpletz.h	46527	0644	edit dl rm
smpdtfmt.h	72713	0644	edit dl rm
sortkey.h	11444	0644	edit dl rm
std_string.h	1076	0644	edit dl rm
strenum.h	10158	0644	edit dl rm
stringoptions.h	5926	0644	edit dl rm
stringpiece.h	10597	0644	edit dl rm
stringtriebuilder.h	15698	0644	edit dl rm
stsearch.h	21810	0644	edit dl rm
symtable.h	4374	0644	edit dl rm
tblcoll.h	37489	0644	edit dl rm
timezone.h	42005	0644	edit dl rm
tmunit.h	3461	0644	edit dl rm
tmutamt.h	5015	0644	edit dl rm
tmutfmt.h	8042	0644	edit dl rm
translit.h	67400	0644	edit dl rm
tzfmt.h	43916	0644	edit dl rm
tznames.h	17252	0644	edit dl rm
tzrule.h	36215	0644	edit dl rm
tztrans.h	6271	0644	edit dl rm
ubidi.h	91711	0644	edit dl rm
ubiditransform.h	12950	0644	edit dl rm
ubrk.h	24547	0644	edit dl rm
ucal.h	58265	0644	edit dl rm
ucasemap.h	15546	0644	edit dl rm
ucat.h	5484	0644	edit dl rm
uchar.h	144630	0644	edit dl rm
ucharstrie.h	23120	0644	edit dl rm
ucharstriebuilder.h	7378	0644	edit dl rm
uchriter.h	13521	0644	edit dl rm
uclean.h	11474	0644	edit dl rm
ucnv.h	85085	0644	edit dl rm
ucnvsel.h	6283	0644	edit dl rm
ucnv_cb.h	6748	0644	edit dl rm
ucnv_err.h	21492	0644	edit dl rm
ucol.h	62939	0644	edit dl rm
ucoleitr.h	9684	0644	edit dl rm
uconfig.h	12356	0644	edit dl rm
ucpmap.h	5663	0644	edit dl rm
ucptrie.h	23002	0644	edit dl rm
ucsdet.h	15018	0644	edit dl rm
ucurr.h	16507	0644	edit dl rm
udat.h	62851	0644	edit dl rm
udata.h	15930	0644	edit dl rm
udateintervalformat.h	10995	0644	edit dl rm
udatpg.h	27447	0644	edit dl rm
udisplaycontext.h	6029	0644	edit dl rm
uenum.h	7970	0644	edit dl rm
ufieldpositer.h	4461	0644	edit dl rm
uformattable.h	11198	0644	edit dl rm
uformattedvalue.h	12413	0644	edit dl rm
ugender.h	2052	0644	edit dl rm
uidna.h	34169	0644	edit dl rm
uiter.h	23319	0644	edit dl rm
uldnames.h	10702	0644	edit dl rm
ulistformatter.h	11086	0644	edit dl rm
uloc.h	54432	0644	edit dl rm
ulocdata.h	11533	0644	edit dl rm
umachine.h	14884	0644	edit dl rm
umisc.h	1365	0644	edit dl rm
umsg.h	24812	0644	edit dl rm
umutablecptrie.h	8435	0644	edit dl rm
unifilt.h	4055	0644	edit dl rm
unifunct.h	4141	0644	edit dl rm
unimatch.h	6244	0644	edit dl rm
unirepl.h	3464	0644	edit dl rm
uniset.h	66459	0644	edit dl rm
unistr.h	174523	0644	edit dl rm
unorm.h	21015	0644	edit dl rm
unorm2.h	25254	0644	edit dl rm
unum.h	54743	0644	edit dl rm
unumberformatter.h	25824	0644	edit dl rm
unumsys.h	7387	0644	edit dl rm
uobject.h	10936	0644	edit dl rm
upluralrules.h	8013	0644	edit dl rm
uregex.h	73784	0644	edit dl rm
uregion.h	10073	0644	edit dl rm
ureldatefmt.h	17409	0644	edit dl rm
urename.h	134449	0644	edit dl rm
urep.h	5507	0644	edit dl rm
ures.h	37415	0644	edit dl rm
uscript.h	27867	0644	edit dl rm
usearch.h	39039	0644	edit dl rm
uset.h	40958	0644	edit dl rm
usetiter.h	9781	0644	edit dl rm
ushape.h	18432	0644	edit dl rm
uspoof.h	67480	0644	edit dl rm
usprep.h	8331	0644	edit dl rm
ustdio.h	39469	0644	edit dl rm
ustream.h	1934	0644	edit dl rm
ustring.h	74211	0644	edit dl rm
ustringtrie.h	3224	0644	edit dl rm
utext.h	59527	0644	edit dl rm
utf.h	8046	0644	edit dl rm
utf8.h	31700	0644	edit dl rm
utf16.h	23878	0644	edit dl rm
utf32.h	763	0644	edit dl rm
utf_old.h	46929	0644	edit dl rm
utmscale.h	14113	0644	edit dl rm
utrace.h	17706	0644	edit dl rm
utrans.h	26130	0644	edit dl rm
utypes.h	31481	0644	edit dl rm
uvernum.h	6832	0644	edit dl rm
uversion.h	6145	0644	edit dl rm
vtzone.h	20784	0644	edit dl rm

Edit: /usr/include/unicode/unorm2.h (25254B)

// © 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__ */

cmd: