FM / unicode

/usr/include/unicode

Name	Size	Mode	Actions
alphaindex.h	27158	0644	edit dl rm
appendable.h	8739	0644	edit dl rm
basictz.h	10163	0644	edit dl rm
brkiter.h	28478	0644	edit dl rm
bytestream.h	11013	0644	edit dl rm
bytestrie.h	21268	0644	edit dl rm
bytestriebuilder.h	7640	0644	edit dl rm
calendar.h	108424	0644	edit dl rm
caniter.h	7621	0644	edit dl rm
casemap.h	25933	0644	edit dl rm
char16ptr.h	7393	0644	edit dl rm
chariter.h	24638	0644	edit dl rm
choicfmt.h	24544	0644	edit dl rm
coleitr.h	14102	0644	edit dl rm
coll.h	57615	0644	edit dl rm
compactdecimalformat.h	7047	0644	edit dl rm
curramt.h	3869	0644	edit dl rm
currpinf.h	7479	0644	edit dl rm
currunit.h	4112	0644	edit dl rm
datefmt.h	41690	0644	edit dl rm
dbbi.h	1223	0644	edit dl rm
dcfmtsym.h	21101	0644	edit dl rm
decimfmt.h	89676	0644	edit dl rm
docmain.h	7380	0644	edit dl rm
dtfmtsym.h	39126	0644	edit dl rm
dtintrv.h	3935	0644	edit dl rm
dtitvfmt.h	50448	0644	edit dl rm
dtitvinf.h	19072	0644	edit dl rm
dtptngen.h	26692	0644	edit dl rm
dtrule.h	8898	0644	edit dl rm
edits.h	21237	0644	edit dl rm
enumset.h	2130	0644	edit dl rm
errorcode.h	4956	0644	edit dl rm
fieldpos.h	8906	0644	edit dl rm
filteredbrk.h	5501	0644	edit dl rm
fmtable.h	25020	0644	edit dl rm
format.h	12802	0644	edit dl rm
formattedvalue.h	9987	0644	edit dl rm
fpositer.h	3107	0644	edit dl rm
gender.h	3408	0644	edit dl rm
gregocal.h	32642	0644	edit dl rm
icudataver.h	1049	0644	edit dl rm
icuplug.h	12109	0644	edit dl rm
idna.h	13000	0644	edit dl rm
listformatter.h	9004	0644	edit dl rm
localebuilder.h	11350	0644	edit dl rm
localematcher.h	27467	0644	edit dl rm
localpointer.h	19825	0644	edit dl rm
locdspnm.h	7292	0644	edit dl rm
locid.h	48804	0644	edit dl rm
measfmt.h	11690	0644	edit dl rm
measunit.h	107613	0644	edit dl rm
measure.h	4431	0644	edit dl rm
messagepattern.h	34517	0644	edit dl rm
msgfmt.h	45278	0644	edit dl rm
normalizer2.h	34466	0644	edit dl rm
normlzr.h	31690	0644	edit dl rm
nounit.h	2305	0644	edit dl rm
numberformatter.h	94505	0644	edit dl rm
numberrangeformatter.h	25790	0644	edit dl rm
numfmt.h	51034	0644	edit dl rm
numsys.h	7509	0644	edit dl rm
parseerr.h	3155	0644	edit dl rm
parsepos.h	5699	0644	edit dl rm
platform.h	28768	0644	edit dl rm
plurfmt.h	25847	0644	edit dl rm
plurrule.h	21316	0644	edit dl rm
ptypes.h	3577	0644	edit dl rm
putil.h	6471	0644	edit dl rm
rbbi.h	28413	0644	edit dl rm
rbnf.h	50021	0644	edit dl rm
rbtz.h	16210	0644	edit dl rm
regex.h	86385	0644	edit dl rm
region.h	9402	0644	edit dl rm
reldatefmt.h	22751	0644	edit dl rm
rep.h	9599	0644	edit dl rm
resbund.h	18513	0644	edit dl rm
schriter.h	6511	0644	edit dl rm
scientificnumberformatter.h	6589	0644	edit dl rm
search.h	22755	0644	edit dl rm
selfmt.h	14686	0644	edit dl rm
simpleformatter.h	12888	0644	edit dl rm
simpletz.h	46798	0644	edit dl rm
smpdtfmt.h	72778	0644	edit dl rm
sortkey.h	11452	0644	edit dl rm
std_string.h	1076	0644	edit dl rm
strenum.h	10157	0644	edit dl rm
stringoptions.h	5926	0644	edit dl rm
stringpiece.h	10287	0644	edit dl rm
stringtriebuilder.h	15842	0644	edit dl rm
stsearch.h	21926	0644	edit dl rm
symtable.h	4374	0644	edit dl rm
tblcoll.h	37801	0644	edit dl rm
timezone.h	44858	0644	edit dl rm
tmunit.h	3479	0644	edit dl rm
tmutamt.h	5029	0644	edit dl rm
tmutfmt.h	7602	0644	edit dl rm
translit.h	67397	0644	edit dl rm
tzfmt.h	43961	0644	edit dl rm
tznames.h	17251	0644	edit dl rm
tzrule.h	36450	0644	edit dl rm
tztrans.h	6278	0644	edit dl rm
ubidi.h	91759	0644	edit dl rm
ubiditransform.h	13003	0644	edit dl rm
ubrk.h	25043	0644	edit dl rm
ucal.h	62463	0644	edit dl rm
ucasemap.h	15579	0644	edit dl rm
ucat.h	5478	0644	edit dl rm
uchar.h	148111	0644	edit dl rm
ucharstrie.h	23066	0644	edit dl rm
ucharstriebuilder.h	7645	0644	edit dl rm
uchriter.h	13747	0644	edit dl rm
uclean.h	11468	0644	edit dl rm
ucnv.h	85051	0644	edit dl rm
ucnvsel.h	6339	0644	edit dl rm
ucnv_cb.h	6738	0644	edit dl rm
ucnv_err.h	21481	0644	edit dl rm
ucol.h	62987	0644	edit dl rm
ucoleitr.h	10056	0644	edit dl rm
uconfig.h	12356	0644	edit dl rm
ucpmap.h	5663	0644	edit dl rm
ucptrie.h	23044	0644	edit dl rm
ucsdet.h	15043	0644	edit dl rm
ucurr.h	17122	0644	edit dl rm
udat.h	63902	0644	edit dl rm
udata.h	16004	0644	edit dl rm
udateintervalformat.h	12218	0644	edit dl rm
udatpg.h	27405	0644	edit dl rm
udisplaycontext.h	6084	0644	edit dl rm
uenum.h	7981	0644	edit dl rm
ufieldpositer.h	4513	0644	edit dl rm
uformattable.h	11233	0644	edit dl rm
uformattedvalue.h	12600	0644	edit dl rm
ugender.h	2106	0644	edit dl rm
uidna.h	34229	0644	edit dl rm
uiter.h	23299	0644	edit dl rm
uldnames.h	10733	0644	edit dl rm
ulistformatter.h	11043	0644	edit dl rm
uloc.h	55936	0644	edit dl rm
ulocdata.h	11572	0644	edit dl rm
umachine.h	16439	0644	edit dl rm
umisc.h	1365	0644	edit dl rm
umsg.h	24832	0644	edit dl rm
umutablecptrie.h	8490	0644	edit dl rm
unifilt.h	4091	0644	edit dl rm
unifunct.h	4151	0644	edit dl rm
unimatch.h	6244	0644	edit dl rm
unirepl.h	3464	0644	edit dl rm
uniset.h	68108	0644	edit dl rm
unistr.h	174627	0644	edit dl rm
unorm.h	21042	0644	edit dl rm
unorm2.h	25269	0644	edit dl rm
unum.h	56269	0644	edit dl rm
unumberformatter.h	31177	0644	edit dl rm
unumberrangeformatter.h	15737	0644	edit dl rm
unumsys.h	7430	0644	edit dl rm
uobject.h	10934	0644	edit dl rm
upluralrules.h	8997	0644	edit dl rm
uregex.h	73719	0644	edit dl rm
uregion.h	10047	0644	edit dl rm
ureldatefmt.h	17448	0644	edit dl rm
urename.h	137853	0644	edit dl rm
urep.h	5507	0644	edit dl rm
ures.h	37418	0644	edit dl rm
uscript.h	28291	0644	edit dl rm
usearch.h	40153	0644	edit dl rm
uset.h	45503	0644	edit dl rm
usetiter.h	9910	0644	edit dl rm
ushape.h	18430	0644	edit dl rm
uspoof.h	67425	0644	edit dl rm
usprep.h	8382	0644	edit dl rm
ustdio.h	39482	0644	edit dl rm
ustream.h	1934	0644	edit dl rm
ustring.h	74096	0644	edit dl rm
ustringtrie.h	3224	0644	edit dl rm
utext.h	59471	0644	edit dl rm
utf.h	8057	0644	edit dl rm
utf8.h	31572	0644	edit dl rm
utf16.h	23910	0644	edit dl rm
utf32.h	763	0644	edit dl rm
utf_old.h	46929	0644	edit dl rm
utmscale.h	14107	0644	edit dl rm
utrace.h	17595	0644	edit dl rm
utrans.h	26157	0644	edit dl rm
utypes.h	31807	0644	edit dl rm
uvernum.h	6839	0644	edit dl rm
uversion.h	6137	0644	edit dl rm
vtzone.h	21303	0644	edit dl rm

Edit: /usr/include/unicode/normalizer2.h (34466B)

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
*
*   Copyright (C) 2009-2013, International Business Machines
*   Corporation and others.  All Rights Reserved.
*
*******************************************************************************
*   file name:  normalizer2.h
*   encoding:   UTF-8
*   tab size:   8 (not used)
*   indentation:4
*
*   created on: 2009nov22
*   created by: Markus W. Scherer
*/

#ifndef __NORMALIZER2_H__
#define __NORMALIZER2_H__

/**
 * \file
 * \brief C++ API: New API for Unicode Normalization.
 */

#include "unicode/utypes.h"

#if U_SHOW_CPLUSPLUS_API

#if !UCONFIG_NO_NORMALIZATION

#include "unicode/stringpiece.h"
#include "unicode/uniset.h"
#include "unicode/unistr.h"
#include "unicode/unorm2.h"

U_NAMESPACE_BEGIN

class ByteSink;

/**
 * Unicode normalization functionality for standard Unicode normalization or
 * for using custom mapping tables.
 * All instances of this class are unmodifiable/immutable.
 * Instances returned by getInstance() are singletons that must not be deleted by the caller.
 * The Normalizer2 class is not intended for public subclassing.
 *
 * The primary functions are to produce a normalized string and to detect whether
 * a string is already normalized.
 * The most commonly used normalization forms are those defined in
 * http://www.unicode.org/unicode/reports/tr15/
 * However, this API supports additional normalization forms for specialized purposes.
 * For example, NFKC_Casefold is provided via getInstance("nfkc_cf", COMPOSE)
 * and can be used in implementations of UTS #46.
 *
 * Not only are the standard compose and decompose modes supplied,
 * but additional modes are provided as documented in the Mode enum.
 *
 * Some of the functions in this class identify normalization boundaries.
 * At a normalization boundary, the portions of the string
 * before it and starting from it do not interact and can be handled independently.
 *
 * The spanQuickCheckYes() stops at a normalization boundary.
 * When the goal is a normalized string, then the text before the boundary
 * can be copied, and the remainder can be processed with normalizeSecondAndAppend().
 *
 * The hasBoundaryBefore(), hasBoundaryAfter() and isInert() functions test whether
 * a character is guaranteed to be at a normalization boundary,
 * regardless of context.
 * This is used for moving from one normalization boundary to the next
 * or preceding boundary, and for performing iterative normalization.
 *
 * Iterative normalization is useful when only a small portion of a
 * longer string needs to be processed.
 * For example, in ICU, iterative normalization is used by the NormalizationTransliterator
 * (to avoid replacing already-normalized text) and ucol_nextSortKeyPart()
 * (to process only the substring for which sort key bytes are computed).
 *
 * The set of normalization boundaries returned by these functions may not be
 * complete: There may be more boundaries that could be returned.
 * Different functions may return different boundaries.
 * @stable ICU 4.4
 */
class U_COMMON_API Normalizer2 : public UObject {
public:
    /**
     * Destructor.
     * @stable ICU 4.4
     */
    ~Normalizer2();

/**
     * Returns a Normalizer2 instance for Unicode NFC normalization.
     * Same as getInstance(NULL, "nfc", UNORM2_COMPOSE, errorCode).
     * Returns an unmodifiable singleton instance. Do not delete it.
     * @param errorCode 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
     */
    static const Normalizer2 *
    getNFCInstance(UErrorCode &errorCode);

/**
     * Returns a Normalizer2 instance for Unicode NFD normalization.
     * Same as getInstance(NULL, "nfc", UNORM2_DECOMPOSE, errorCode).
     * Returns an unmodifiable singleton instance. Do not delete it.
     * @param errorCode 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
     */
    static const Normalizer2 *
    getNFDInstance(UErrorCode &errorCode);

/**
     * Returns a Normalizer2 instance for Unicode NFKC normalization.
     * Same as getInstance(NULL, "nfkc", UNORM2_COMPOSE, errorCode).
     * Returns an unmodifiable singleton instance. Do not delete it.
     * @param errorCode 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
     */
    static const Normalizer2 *
    getNFKCInstance(UErrorCode &errorCode);

/**
     * Returns a Normalizer2 instance for Unicode NFKD normalization.
     * Same as getInstance(NULL, "nfkc", UNORM2_DECOMPOSE, errorCode).
     * Returns an unmodifiable singleton instance. Do not delete it.
     * @param errorCode 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
     */
    static const Normalizer2 *
    getNFKDInstance(UErrorCode &errorCode);

/**
     * Returns a Normalizer2 instance for Unicode NFKC_Casefold normalization.
     * Same as getInstance(NULL, "nfkc_cf", UNORM2_COMPOSE, errorCode).
     * Returns an unmodifiable singleton instance. Do not delete it.
     * @param errorCode 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
     */
    static const Normalizer2 *
    getNFKCCasefoldInstance(UErrorCode &errorCode);

/**
     * Returns a Normalizer2 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 errorCode 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 4.4
     */
    static const Normalizer2 *
    getInstance(const char *packageName,
                const char *name,
                UNormalization2Mode mode,
                UErrorCode &errorCode);

/**
     * Returns the normalized form of the source string.
     * @param src source string
     * @param errorCode 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 normalized src
     * @stable ICU 4.4
     */
    UnicodeString
    normalize(const UnicodeString &src, UErrorCode &errorCode) const {
        UnicodeString result;
        normalize(src, result, errorCode);
        return result;
    }
    /**
     * Writes the normalized form of the source string to the destination string
     * (replacing its contents) and returns the destination string.
     * The source and destination strings must be different objects.
     * @param src source string
     * @param dest destination string; its contents is replaced with normalized src
     * @param errorCode 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
     */
    virtual UnicodeString &
    normalize(const UnicodeString &src,
              UnicodeString &dest,
              UErrorCode &errorCode) const = 0;

/**
     * Normalizes a UTF-8 string and optionally records how source substrings
     * relate to changed and unchanged result substrings.
     *
     * Implemented completely for all built-in modes except for FCD.
     * The base class implementation converts to & from UTF-16 and does not support edits.
     *
     * @param options   Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT and U_EDITS_NO_RESET.
     * @param src       Source UTF-8 string.
     * @param sink      A ByteSink to which the normalized UTF-8 result string is written.
     *                  sink.Flush() is called at the end.
     * @param edits     Records edits for index mapping, working with styled text,
     *                  and getting only changes (if any).
     *                  The Edits contents is undefined if any error occurs.
     *                  This function calls edits->reset() first unless
     *                  options includes U_EDITS_NO_RESET. edits can be nullptr.
     * @param errorCode 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.)
     * @stable ICU 60
     */
    virtual void
    normalizeUTF8(uint32_t options, StringPiece src, ByteSink &sink,
                  Edits *edits, UErrorCode &errorCode) const;

/**
     * Appends the normalized form of the second string to the first string
     * (merging them at the boundary) and returns the first string.
     * The result is normalized if the first string was normalized.
     * The first and second strings must be different objects.
     * @param first string, should be normalized
     * @param second string, will be normalized
     * @param errorCode 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
     */
    virtual UnicodeString &
    normalizeSecondAndAppend(UnicodeString &first,
                             const UnicodeString &second,
                             UErrorCode &errorCode) const = 0;
    /**
     * Appends the second string to the first string
     * (merging them at the boundary) and returns the first string.
     * The result is normalized if both the strings were normalized.
     * The first and second strings must be different objects.
     * @param first string, should be normalized
     * @param second string, should be normalized
     * @param errorCode 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
     */
    virtual UnicodeString &
    append(UnicodeString &first,
           const UnicodeString &second,
           UErrorCode &errorCode) const = 0;

/**
     * Gets the decomposition mapping of c.
     * Roughly equivalent to normalizing the String form of c
     * on a UNORM2_DECOMPOSE Normalizer2 instance, but much faster, and except that this function
     * returns false 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 Normalizer2.
     * @param c code point
     * @param decomposition String object which will be set to c's
     *                      decomposition mapping, if there is one.
     * @return true if c has a decomposition, otherwise false
     * @stable ICU 4.6
     */
    virtual UBool
    getDecomposition(UChar32 c, UnicodeString &decomposition) const = 0;

/**
     * Gets the raw decomposition mapping of c.
     *
     * This is similar to the getDecomposition() method 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, getDecomposition() returns the processed,
     * recursively-decomposed version of this mapping.
     *
     * When used on a standard NFKC Normalizer2 instance,
     * 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 char16_ts).
     *
     * This function is independent of the mode of the Normalizer2.
     * The default implementation returns false.
     * @param c code point
     * @param decomposition String object which will be set to c's
     *                      raw decomposition mapping, if there is one.
     * @return true if c has a decomposition, otherwise false
     * @stable ICU 49
     */
    virtual UBool
    getRawDecomposition(UChar32 c, UnicodeString &decomposition) const;

/**
     * 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 Normalizer2.
     * The default implementation returns a negative value.
     * @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
     */
    virtual UChar32
    composePair(UChar32 a, UChar32 b) const;

/**
     * Gets the combining class of c.
     * The default implementation returns 0
     * but all standard implementations return the Unicode Canonical_Combining_Class value.
     * @param c code point
     * @return c's combining class
     * @stable ICU 49
     */
    virtual uint8_t
    getCombiningClass(UChar32 c) const;

/**
     * 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 s input string
     * @param errorCode 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
     */
    virtual UBool
    isNormalized(const UnicodeString &s, UErrorCode &errorCode) const = 0;
    /**
     * Tests if the UTF-8 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.
     *
     * This works for all normalization modes.
     * It is optimized for UTF-8 for all built-in modes except for FCD.
     * The base class implementation converts to UTF-16 and calls isNormalized().
     *
     * @param s UTF-8 input string
     * @param errorCode 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 60
     */
    virtual UBool
    isNormalizedUTF8(StringPiece s, UErrorCode &errorCode) const;

/**
     * 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 s input string
     * @param errorCode 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
     */
    virtual UNormalizationCheckResult
    quickCheck(const UnicodeString &s, UErrorCode &errorCode) const = 0;

/**
     * 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 s input string
     * @param errorCode 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
     */
    virtual int32_t
    spanQuickCheckYes(const UnicodeString &s, UErrorCode &errorCode) const = 0;

/**
     * Tests if the character always has a normalization boundary before it,
     * regardless of context.
     * If true, then the character does not normalization-interact with
     * preceding characters.
     * In other words, a string containing this character can be normalized
     * by processing portions before this character and starting from this
     * character independently.
     * This is used for iterative normalization. See the class documentation for details.
     * @param c character to test
     * @return true if c has a normalization boundary before it
     * @stable ICU 4.4
     */
    virtual UBool hasBoundaryBefore(UChar32 c) const = 0;

/**
     * Tests if the character always has a normalization boundary after it,
     * regardless of context.
     * If true, then the character does not normalization-interact with
     * following characters.
     * In other words, a string containing this character can be normalized
     * by processing portions up to this character and after this
     * character independently.
     * This is used for iterative normalization. See the class documentation for details.
     * Note that this operation may be significantly slower than hasBoundaryBefore().
     * @param c character to test
     * @return true if c has a normalization boundary after it
     * @stable ICU 4.4
     */
    virtual UBool hasBoundaryAfter(UChar32 c) const = 0;

/**
     * Tests if the character is normalization-inert.
     * If true, then the character does not change, nor normalization-interact with
     * preceding or following characters.
     * In other words, a string containing this character can be normalized
     * by processing portions before this character and after this
     * character independently.
     * This is used for iterative normalization. See the class documentation for details.
     * Note that this operation may be significantly slower than hasBoundaryBefore().
     * @param c character to test
     * @return true if c is normalization-inert
     * @stable ICU 4.4
     */
    virtual UBool isInert(UChar32 c) const = 0;
};

/**
 * Normalization filtered by a UnicodeSet.
 * Normalizes portions of the text contained in the filter set and leaves
 * portions not contained in the filter set unchanged.
 * Filtering is done via UnicodeSet::span(..., USET_SPAN_SIMPLE).
 * Not-in-the-filter text is treated as "is normalized" and "quick check yes".
 * This class implements all of (and only) the Normalizer2 API.
 * An instance of this class is unmodifiable/immutable but is constructed and
 * must be destructed by the owner.
 * @stable ICU 4.4
 */
class U_COMMON_API FilteredNormalizer2 : public Normalizer2 {
public:
    /**
     * Constructs a filtered normalizer wrapping any Normalizer2 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 n2 wrapped Normalizer2 instance
     * @param filterSet UnicodeSet which determines the characters to be normalized
     * @stable ICU 4.4
     */
    FilteredNormalizer2(const Normalizer2 &n2, const UnicodeSet &filterSet) :
            norm2(n2), set(filterSet) {}

/**
     * Destructor.
     * @stable ICU 4.4
     */
    ~FilteredNormalizer2();

/**
     * Writes the normalized form of the source string to the destination string
     * (replacing its contents) and returns the destination string.
     * The source and destination strings must be different objects.
     * @param src source string
     * @param dest destination string; its contents is replaced with normalized src
     * @param errorCode 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
     */
    virtual UnicodeString &
    normalize(const UnicodeString &src,
              UnicodeString &dest,
              UErrorCode &errorCode) const U_OVERRIDE;

/**
     * Normalizes a UTF-8 string and optionally records how source substrings
     * relate to changed and unchanged result substrings.
     *
     * Implemented completely for most built-in modes except for FCD.
     * The base class implementation converts to & from UTF-16 and does not support edits.
     *
     * @param options   Options bit set, usually 0. See U_OMIT_UNCHANGED_TEXT and U_EDITS_NO_RESET.
     * @param src       Source UTF-8 string.
     * @param sink      A ByteSink to which the normalized UTF-8 result string is written.
     *                  sink.Flush() is called at the end.
     * @param edits     Records edits for index mapping, working with styled text,
     *                  and getting only changes (if any).
     *                  The Edits contents is undefined if any error occurs.
     *                  This function calls edits->reset() first unless
     *                  options includes U_EDITS_NO_RESET. edits can be nullptr.
     * @param errorCode 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.)
     * @stable ICU 60
     */
    virtual void
    normalizeUTF8(uint32_t options, StringPiece src, ByteSink &sink,
                  Edits *edits, UErrorCode &errorCode) const U_OVERRIDE;

/**
     * Appends the normalized form of the second string to the first string
     * (merging them at the boundary) and returns the first string.
     * The result is normalized if the first string was normalized.
     * The first and second strings must be different objects.
     * @param first string, should be normalized
     * @param second string, will be normalized
     * @param errorCode 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
     */
    virtual UnicodeString &
    normalizeSecondAndAppend(UnicodeString &first,
                             const UnicodeString &second,
                             UErrorCode &errorCode) const U_OVERRIDE;
    /**
     * Appends the second string to the first string
     * (merging them at the boundary) and returns the first string.
     * The result is normalized if both the strings were normalized.
     * The first and second strings must be different objects.
     * @param first string, should be normalized
     * @param second string, should be normalized
     * @param errorCode 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
     */
    virtual UnicodeString &
    append(UnicodeString &first,
           const UnicodeString &second,
           UErrorCode &errorCode) const U_OVERRIDE;

/**
     * Gets the decomposition mapping of c.
     * For details see the base class documentation.
     *
     * This function is independent of the mode of the Normalizer2.
     * @param c code point
     * @param decomposition String object which will be set to c's
     *                      decomposition mapping, if there is one.
     * @return true if c has a decomposition, otherwise false
     * @stable ICU 4.6
     */
    virtual UBool
    getDecomposition(UChar32 c, UnicodeString &decomposition) const U_OVERRIDE;

/**
     * Gets the raw decomposition mapping of c.
     * For details see the base class documentation.
     *
     * This function is independent of the mode of the Normalizer2.
     * @param c code point
     * @param decomposition String object which will be set to c's
     *                      raw decomposition mapping, if there is one.
     * @return true if c has a decomposition, otherwise false
     * @stable ICU 49
     */
    virtual UBool
    getRawDecomposition(UChar32 c, UnicodeString &decomposition) const U_OVERRIDE;

/**
     * Performs pairwise composition of a & b and returns the composite if there is one.
     * For details see the base class documentation.
     *
     * This function is independent of the mode of the Normalizer2.
     * @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
     */
    virtual UChar32
    composePair(UChar32 a, UChar32 b) const U_OVERRIDE;

/**
     * Tests if the string is normalized.
     * For details see the Normalizer2 base class documentation.
     * @param s input string
     * @param errorCode 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
     */
    virtual UBool
    isNormalized(const UnicodeString &s, UErrorCode &errorCode) const U_OVERRIDE;
    /**
     * Tests if the UTF-8 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.
     *
     * This works for all normalization modes.
     * It is optimized for UTF-8 for all built-in modes except for FCD.
     * The base class implementation converts to UTF-16 and calls isNormalized().
     *
     * @param s UTF-8 input string
     * @param errorCode 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 60
     */
    virtual UBool
    isNormalizedUTF8(StringPiece s, UErrorCode &errorCode) const U_OVERRIDE;
    /**
     * Tests if the string is normalized.
     * For details see the Normalizer2 base class documentation.
     * @param s input string
     * @param errorCode 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
     */
    virtual UNormalizationCheckResult
    quickCheck(const UnicodeString &s, UErrorCode &errorCode) const U_OVERRIDE;
    /**
     * Returns the end of the normalized substring of the input string.
     * For details see the Normalizer2 base class documentation.
     * @param s input string
     * @param errorCode 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
     */
    virtual int32_t
    spanQuickCheckYes(const UnicodeString &s, UErrorCode &errorCode) const U_OVERRIDE;

/**
     * Tests if the character always has a normalization boundary before it,
     * regardless of context.
     * For details see the Normalizer2 base class documentation.
     * @param c character to test
     * @return true if c has a normalization boundary before it
     * @stable ICU 4.4
     */
    virtual UBool hasBoundaryBefore(UChar32 c) const U_OVERRIDE;

/**
     * Tests if the character always has a normalization boundary after it,
     * regardless of context.
     * For details see the Normalizer2 base class documentation.
     * @param c character to test
     * @return true if c has a normalization boundary after it
     * @stable ICU 4.4
     */
    virtual UBool hasBoundaryAfter(UChar32 c) const U_OVERRIDE;

/**
     * Tests if the character is normalization-inert.
     * For details see the Normalizer2 base class documentation.
     * @param c character to test
     * @return true if c is normalization-inert
     * @stable ICU 4.4
     */
    virtual UBool isInert(UChar32 c) const U_OVERRIDE;
private:
    UnicodeString &
    normalize(const UnicodeString &src,
              UnicodeString &dest,
              USetSpanCondition spanCondition,
              UErrorCode &errorCode) const;

void
    normalizeUTF8(uint32_t options, const char *src, int32_t length,
                  ByteSink &sink, Edits *edits,
                  USetSpanCondition spanCondition,
                  UErrorCode &errorCode) const;

UnicodeString &
    normalizeSecondAndAppend(UnicodeString &first,
                             const UnicodeString &second,
                             UBool doNormalize,
                             UErrorCode &errorCode) const;

const Normalizer2 &norm2;
    const UnicodeSet &set;
};

U_NAMESPACE_END

#endif  // !UCONFIG_NO_NORMALIZATION

#endif /* U_SHOW_CPLUSPLUS_API */

#endif  // __NORMALIZER2_H__

cmd: