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	27.86 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	106.52 KB	-rw-r--r--
caniter.h	7.47 KB	-rw-r--r--
casemap.h	25.42 KB	-rw-r--r--
char16ptr.h	7.22 KB	-rw-r--r--
chariter.h	24.06 KB	-rw-r--r--
choicfmt.h	24 KB	-rw-r--r--
coleitr.h	13.78 KB	-rw-r--r--
coll.h	56.3 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	40.72 KB	-rw-r--r--
dbbi.h	1.19 KB	-rw-r--r--
dcfmtsym.h	20.94 KB	-rw-r--r--
decimfmt.h	87.54 KB	-rw-r--r--
displayoptions.h	7.08 KB	-rw-r--r--
docmain.h	7.3 KB	-rw-r--r--
dtfmtsym.h	38.23 KB	-rw-r--r--
dtintrv.h	3.85 KB	-rw-r--r--
dtitvfmt.h	49.26 KB	-rw-r--r--
dtitvinf.h	18.63 KB	-rw-r--r--
dtptngen.h	28.64 KB	-rw-r--r--
dtrule.h	8.69 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	8.7 KB	-rw-r--r--
filteredbrk.h	5.37 KB	-rw-r--r--
fmtable.h	24.45 KB	-rw-r--r--
format.h	12.5 KB	-rw-r--r--
formattednumber.h	6.15 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	30.03 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	26.83 KB	-rw-r--r--
localpointer.h	19.44 KB	-rw-r--r--
locdspnm.h	7.12 KB	-rw-r--r--
locid.h	48.27 KB	-rw-r--r--
measfmt.h	11.42 KB	-rw-r--r--
measunit.h	107.38 KB	-rw-r--r--
measure.h	4.69 KB	-rw-r--r--
messagepattern.h	33.72 KB	-rw-r--r--
msgfmt.h	44.21 KB	-rw-r--r--
normalizer2.h	34.73 KB	-rw-r--r--
normlzr.h	30.97 KB	-rw-r--r--
nounit.h	2.25 KB	-rw-r--r--
numberformatter.h	90.03 KB	-rw-r--r--
numberrangeformatter.h	25.32 KB	-rw-r--r--
numfmt.h	50.26 KB	-rw-r--r--
numsys.h	7.23 KB	-rw-r--r--
parseerr.h	3.08 KB	-rw-r--r--
parsepos.h	5.57 KB	-rw-r--r--
platform.h	27.8 KB	-rw-r--r--
plurfmt.h	25.25 KB	-rw-r--r--
plurrule.h	20.64 KB	-rw-r--r--
ptypes.h	3.49 KB	-rw-r--r--
putil.h	6.32 KB	-rw-r--r--
rbbi.h	32.07 KB	-rw-r--r--
rbnf.h	49.92 KB	-rw-r--r--
rbtz.h	15.77 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	18.11 KB	-rw-r--r--
schriter.h	6.1 KB	-rw-r--r--
scientificnumberformatter.h	6.44 KB	-rw-r--r--
search.h	22.24 KB	-rw-r--r--
selfmt.h	14.35 KB	-rw-r--r--
simpleformatter.h	12.6 KB	-rw-r--r--
simplenumberformatter.h	8.88 KB	-rw-r--r--
simpletz.h	45.65 KB	-rw-r--r--
smpdtfmt.h	71.85 KB	-rw-r--r--
sortkey.h	11.19 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	10.05 KB	-rw-r--r--
stringtriebuilder.h	15.5 KB	-rw-r--r--
stsearch.h	21.44 KB	-rw-r--r--
symtable.h	4.28 KB	-rw-r--r--
tblcoll.h	36.94 KB	-rw-r--r--
timezone.h	45.67 KB	-rw-r--r--
tmunit.h	3.4 KB	-rw-r--r--
tmutamt.h	4.91 KB	-rw-r--r--
tmutfmt.h	7.42 KB	-rw-r--r--
translit.h	65.83 KB	-rw-r--r--
tzfmt.h	42.96 KB	-rw-r--r--
tznames.h	16.85 KB	-rw-r--r--
tzrule.h	34.86 KB	-rw-r--r--
tztrans.h	6.13 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	64.28 KB	-rw-r--r--
ucasemap.h	15.21 KB	-rw-r--r--
ucat.h	5.35 KB	-rw-r--r--
uchar.h	145.7 KB	-rw-r--r--
ucharstrie.h	22.56 KB	-rw-r--r--
ucharstriebuilder.h	7.48 KB	-rw-r--r--
uchriter.h	13.42 KB	-rw-r--r--
uclean.h	11.21 KB	-rw-r--r--
ucnv.h	83.46 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	12.31 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	54.66 KB	-rw-r--r--
ulocale.h	6.35 KB	-rw-r--r--
ulocbuilder.h	16.72 KB	-rw-r--r--
ulocdata.h	11.3 KB	-rw-r--r--
umachine.h	15 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	66.85 KB	-rw-r--r--
unistr.h	171.35 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	140.82 KB	-rw-r--r--
urep.h	5.38 KB	-rw-r--r--
ures.h	36.65 KB	-rw-r--r--
uscript.h	27.8 KB	-rw-r--r--
usearch.h	39.21 KB	-rw-r--r--
uset.h	45.61 KB	-rw-r--r--
usetiter.h	9.63 KB	-rw-r--r--
ushape.h	18 KB	-rw-r--r--
usimplenumberformatter.h	7.46 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	31.06 KB	-rw-r--r--
uvernum.h	6.33 KB	-rw-r--r--
uversion.h	5.99 KB	-rw-r--r--
vtzone.h	20.69 KB	-rw-r--r--

Code Editor : unorm.h

// © 2016 and later: Unicode, Inc. and others.
// License & terms of use: http://www.unicode.org/copyright.html
/*
*******************************************************************************
* Copyright (c) 1996-2016, International Business Machines Corporation
*               and others. All Rights Reserved.
*******************************************************************************
* File unorm.h
*
* Created by: Vladimir Weinstein 12052000
*
* Modification history :
*
* Date        Name        Description
* 02/01/01    synwee      Added normalization quickcheck enum and method.
*/
#ifndef UNORM_H
#define UNORM_H

#include "unicode/utypes.h"

#if !UCONFIG_NO_NORMALIZATION

#include "unicode/uiter.h"
#include "unicode/unorm2.h"

/**
 * \file
 * \brief C API: Unicode Normalization
 *
 * Old Unicode normalization API.
 *
 * This API has been replaced by the unorm2.h API and is only available
 * for backward compatibility. The functions here simply delegate to the
 * unorm2.h functions, for example unorm2_getInstance() and unorm2_normalize().
 * There is one exception: The new API does not provide a replacement for unorm_compare().
 * Its declaration has been moved to unorm2.h.
 *
 * <code>unorm_normalize</code> transforms Unicode text into an equivalent composed or
 * decomposed form, allowing for easier sorting and searching of text.
 * <code>unorm_normalize</code> supports the standard normalization forms described in
 * <a href="http://www.unicode.org/unicode/reports/tr15/" target="unicode">
 * Unicode Standard Annex #15: Unicode Normalization Forms</a>.
 *
 * Characters with accents or other adornments can be encoded in
 * several different ways in Unicode.  For example, take the character A-acute.
 * In Unicode, this can be encoded as a single character (the
 * "composed" form):
 *
 * \code
 *      00C1    LATIN CAPITAL LETTER A WITH ACUTE
 * \endcode
 *
 * or as two separate characters (the "decomposed" form):
 *
 * \code
 *      0041    LATIN CAPITAL LETTER A
 *      0301    COMBINING ACUTE ACCENT
 * \endcode
 *
 * To a user of your program, however, both of these sequences should be
 * treated as the same "user-level" character "A with acute accent".  When you are searching or
 * comparing text, you must ensure that these two sequences are treated
 * equivalently.  In addition, you must handle characters with more than one
 * accent.  Sometimes the order of a character's combining accents is
 * significant, while in other cases accent sequences in different orders are
 * really equivalent.
 *
 * Similarly, the string "ffi" can be encoded as three separate letters:
 *
 * \code
 *      0066    LATIN SMALL LETTER F
 *      0066    LATIN SMALL LETTER F
 *      0069    LATIN SMALL LETTER I
 * \endcode
 *
 * or as the single character
 *
 * \code
 *      FB03    LATIN SMALL LIGATURE FFI
 * \endcode
 *
 * The ffi ligature is not a distinct semantic character, and strictly speaking
 * it shouldn't be in Unicode at all, but it was included for compatibility
 * with existing character sets that already provided it.  The Unicode standard
 * identifies such characters by giving them "compatibility" decompositions
 * into the corresponding semantic characters.  When sorting and searching, you
 * will often want to use these mappings.
 *
 * <code>unorm_normalize</code> helps solve these problems by transforming text into the
 * canonical composed and decomposed forms as shown in the first example above.
 * In addition, you can have it perform compatibility decompositions so that
 * you can treat compatibility characters the same as their equivalents.
 * Finally, <code>unorm_normalize</code> rearranges accents into the proper canonical
 * order, so that you do not have to worry about accent rearrangement on your
 * own.
 *
 * Form FCD, "Fast C or D", is also designed for collation.
 * It allows to work on strings that are not necessarily normalized
 * with an algorithm (like in collation) that works under "canonical closure", i.e., it treats precomposed
 * characters and their decomposed equivalents the same.
 *
 * It is not a normalization form because it does not provide for uniqueness of representation. Multiple strings
 * may be canonically equivalent (their NFDs are identical) and may all conform to FCD without being identical
 * themselves.
 *
 * The form is defined such that the "raw decomposition", the recursive canonical decomposition of each character,
 * results in a string that is canonically ordered. This means that precomposed characters are allowed for as long
 * as their decompositions do not need canonical reordering.
 *
 * Its advantage for a process like collation is that all NFD and most NFC texts - and many unnormalized texts -
 * already conform to FCD and do not need to be normalized (NFD) for such a process. The FCD quick check will
 * return UNORM_YES for most strings in practice.
 *
 * unorm_normalize(UNORM_FCD) may be implemented with UNORM_NFD.
 *
 * For more details on FCD see the collation design document:
 * https://htmlpreview.github.io/?https://github.com/unicode-org/icu-docs/blob/main/design/collation/ICU_collation_design.htm
 *
 * ICU collation performs either NFD or FCD normalization automatically if normalization
 * is turned on for the collator object.
 * Beyond collation and string search, normalized strings may be useful for string equivalence comparisons,
 * transliteration/transcription, unique representations, etc.
 *
 * The W3C generally recommends to exchange texts in NFC.
 * Note also that most legacy character encodings use only precomposed forms and often do not
 * encode any combining marks by themselves. For conversion to such character encodings the
 * Unicode text needs to be normalized to NFC.
 * For more usage examples, see the Unicode Standard Annex.
 */

// Do not conditionalize the following enum with #ifndef U_HIDE_DEPRECATED_API,
// it is needed for layout of Normalizer object.
#ifndef U_FORCE_HIDE_DEPRECATED_API

/**
 * Constants for normalization modes.
 * @deprecated ICU 56 Use unorm2.h instead.
 */
typedef enum {
  /** No decomposition/composition. @deprecated ICU 56 Use unorm2.h instead. */
  UNORM_NONE = 1,
  /** Canonical decomposition. @deprecated ICU 56 Use unorm2.h instead. */
  UNORM_NFD = 2,
  /** Compatibility decomposition. @deprecated ICU 56 Use unorm2.h instead. */
  UNORM_NFKD = 3,
  /** Canonical decomposition followed by canonical composition. @deprecated ICU 56 Use unorm2.h instead. */
  UNORM_NFC = 4,
  /** Default normalization. @deprecated ICU 56 Use unorm2.h instead. */
  UNORM_DEFAULT = UNORM_NFC,
  /** Compatibility decomposition followed by canonical composition. @deprecated ICU 56 Use unorm2.h instead. */
  UNORM_NFKC =5,
  /** "Fast C or D" form. @deprecated ICU 56 Use unorm2.h instead. */
  UNORM_FCD = 6,

/** One more than the highest normalization mode constant. @deprecated ICU 56 Use unorm2.h instead. */
  UNORM_MODE_COUNT
} UNormalizationMode;

#endif  // U_FORCE_HIDE_DEPRECATED_API

#ifndef U_HIDE_DEPRECATED_API

/**
 * Constants for options flags for normalization.
 * Use 0 for default options,
 * including normalization according to the Unicode version
 * that is currently supported by ICU (see u_getUnicodeVersion).
 * @deprecated ICU 56 Use unorm2.h instead.
 */
enum {
    /**
     * Options bit set value to select Unicode 3.2 normalization
     * (except NormalizationCorrections).
     * At most one Unicode version can be selected at a time.
     * @deprecated ICU 56 Use unorm2.h instead.
     */
    UNORM_UNICODE_3_2=0x20
};

/**
 * Lowest-order bit number of unorm_compare() options bits corresponding to
 * normalization options bits.
 *
 * The options parameter for unorm_compare() uses most bits for
 * itself and for various comparison and folding flags.
 * The most significant bits, however, are shifted down and passed on
 * to the normalization implementation.
 * (That is, from unorm_compare(..., options, ...),
 * options>>UNORM_COMPARE_NORM_OPTIONS_SHIFT will be passed on to the
 * internal normalization functions.)
 *
 * @see unorm_compare
 * @deprecated ICU 56 Use unorm2.h instead.
 */
#define UNORM_COMPARE_NORM_OPTIONS_SHIFT 20

/**
 * Normalize a string.
 * The string will be normalized according the specified normalization mode
 * and options.
 * The source and result buffers must not be the same, nor overlap.
 *
 * @param source The string to normalize.
 * @param sourceLength The length of source, or -1 if NUL-terminated.
 * @param mode The normalization mode; one of UNORM_NONE,
 *             UNORM_NFD, UNORM_NFC, UNORM_NFKC, UNORM_NFKD, UNORM_DEFAULT.
 * @param options The normalization options, ORed together (0 for no options).
 * @param result A pointer to a buffer to receive the result string.
 *               The result string is NUL-terminated if possible.
 * @param resultLength The maximum size of result.
 * @param status A pointer to a UErrorCode to receive any errors.
 * @return The total buffer size needed; if greater than resultLength,
 *         the output was truncated, and the error code is set to U_BUFFER_OVERFLOW_ERROR.
 * @deprecated ICU 56 Use unorm2.h instead.
 */
U_DEPRECATED int32_t U_EXPORT2
unorm_normalize(const UChar *source, int32_t sourceLength,
                UNormalizationMode mode, int32_t options,
                UChar *result, int32_t resultLength,
                UErrorCode *status);

/**
 * Performing quick check on a string, to quickly determine if the string is
 * in a particular normalization format.
 * Three types of result can be returned UNORM_YES, UNORM_NO or
 * UNORM_MAYBE. Result UNORM_YES indicates that the argument
 * string is in the desired normalized format, UNORM_NO determines that
 * argument string is not in the desired normalized format. A
 * UNORM_MAYBE result indicates that a more thorough check is required,
 * the user may have to put the string in its normalized form and compare the
 * results.
 *
 * @param source       string for determining if it is in a normalized format
 * @param sourcelength length of source to test, or -1 if NUL-terminated
 * @param mode         which normalization form to test for
 * @param status       a pointer to a UErrorCode to receive any errors
 * @return UNORM_YES, UNORM_NO or UNORM_MAYBE
 *
 * @see unorm_isNormalized
 * @deprecated ICU 56 Use unorm2.h instead.
 */
U_DEPRECATED UNormalizationCheckResult U_EXPORT2
unorm_quickCheck(const UChar *source, int32_t sourcelength,
                 UNormalizationMode mode,
                 UErrorCode *status);

/**
 * Performing quick check on a string; same as unorm_quickCheck but
 * takes an extra options parameter like most normalization functions.
 *
 * @param src        String that is to be tested if it is in a normalization format.
 * @param srcLength  Length of source to test, or -1 if NUL-terminated.
 * @param mode       Which normalization form to test for.
 * @param options    The normalization options, ORed together (0 for no options).
 * @param pErrorCode ICU error code in/out parameter.
 *                   Must fulfill U_SUCCESS before the function call.
 * @return UNORM_YES, UNORM_NO or UNORM_MAYBE
 *
 * @see unorm_quickCheck
 * @see unorm_isNormalized
 * @deprecated ICU 56 Use unorm2.h instead.
 */
U_DEPRECATED UNormalizationCheckResult U_EXPORT2
unorm_quickCheckWithOptions(const UChar *src, int32_t srcLength,
                            UNormalizationMode mode, int32_t options,
                            UErrorCode *pErrorCode);

/**
 * Test if a string is in a given normalization form.
 * This is semantically equivalent to source.equals(normalize(source, mode)) .
 *
 * Unlike unorm_quickCheck(), this function returns a definitive result,
 * never a "maybe".
 * For NFD, NFKD, and FCD, both functions work exactly the same.
 * For NFC and NFKC where quickCheck may return "maybe", this function will
 * perform further tests to arrive at a true/false result.
 *
 * @param src        String that is to be tested if it is in a normalization format.
 * @param srcLength  Length of source to test, or -1 if NUL-terminated.
 * @param mode       Which normalization form to test for.
 * @param pErrorCode ICU error code in/out parameter.
 *                   Must fulfill U_SUCCESS before the function call.
 * @return Boolean value indicating whether the source string is in the
 *         "mode" normalization form.
 *
 * @see unorm_quickCheck
 * @deprecated ICU 56 Use unorm2.h instead.
 */
U_DEPRECATED UBool U_EXPORT2
unorm_isNormalized(const UChar *src, int32_t srcLength,
                   UNormalizationMode mode,
                   UErrorCode *pErrorCode);

/**
 * Test if a string is in a given normalization form; same as unorm_isNormalized but
 * takes an extra options parameter like most normalization functions.
 *
 * @param src        String that is to be tested if it is in a normalization format.
 * @param srcLength  Length of source to test, or -1 if NUL-terminated.
 * @param mode       Which normalization form to test for.
 * @param options    The normalization options, ORed together (0 for no options).
 * @param pErrorCode ICU error code in/out parameter.
 *                   Must fulfill U_SUCCESS before the function call.
 * @return Boolean value indicating whether the source string is in the
 *         "mode/options" normalization form.
 *
 * @see unorm_quickCheck
 * @see unorm_isNormalized
 * @deprecated ICU 56 Use unorm2.h instead.
 */
U_DEPRECATED UBool U_EXPORT2
unorm_isNormalizedWithOptions(const UChar *src, int32_t srcLength,
                              UNormalizationMode mode, int32_t options,
                              UErrorCode *pErrorCode);

/**
 * Iterative normalization forward.
 * This function (together with unorm_previous) is somewhat
 * similar to the C++ Normalizer class (see its non-static functions).
 *
 * Iterative normalization is useful when only a small portion of a longer
 * string/text needs to be processed.
 *
 * For example, the likelihood may be high that processing the first 10% of some
 * text will be sufficient to find certain data.
 * Another example: When one wants to concatenate two normalized strings and get a
 * normalized result, it is much more efficient to normalize just a small part of
 * the result around the concatenation place instead of re-normalizing everything.
 *
 * The input text is an instance of the C character iteration API UCharIterator.
 * It may wrap around a simple string, a CharacterIterator, a Replaceable, or any
 * other kind of text object.
 *
 * If a buffer overflow occurs, then the caller needs to reset the iterator to the
 * old index and call the function again with a larger buffer - if the caller cares
 * for the actual output.
 * Regardless of the output buffer, the iterator will always be moved to the next
 * normalization boundary.
 *
 * This function (like unorm_previous) serves two purposes:
 *
 * 1) To find the next boundary so that the normalization of the part of the text
 * from the current position to that boundary does not affect and is not affected
 * by the part of the text beyond that boundary.
 *
 * 2) To normalize the text up to the boundary.
 *
 * The second step is optional, per the doNormalize parameter.
 * It is omitted for operations like string concatenation, where the two adjacent
 * string ends need to be normalized together.
 * In such a case, the output buffer will just contain a copy of the text up to the
 * boundary.
 *
 * pNeededToNormalize is an output-only parameter. Its output value is only defined
 * if normalization was requested (doNormalize) and successful (especially, no
 * buffer overflow).
 * It is useful for operations like a normalizing transliterator, where one would
 * not want to replace a piece of text if it is not modified.
 *
 * If doNormalize==true and pNeededToNormalize!=NULL then *pNeeded... is set true
 * if the normalization was necessary.
 *
 * If doNormalize==false then *pNeededToNormalize will be set to false.
 *
 * If the buffer overflows, then *pNeededToNormalize will be undefined;
 * essentially, whenever U_FAILURE is true (like in buffer overflows), this result
 * will be undefined.
 *
 * @param src The input text in the form of a C character iterator.
 * @param dest The output buffer; can be NULL if destCapacity==0 for pure preflighting.
 * @param destCapacity The number of UChars that fit into dest.
 * @param mode The normalization mode.
 * @param options The normalization options, ORed together (0 for no options).
 * @param doNormalize Indicates if the source text up to the next boundary
 *                    is to be normalized (true) or just copied (false).
 * @param pNeededToNormalize Output flag indicating if the normalization resulted in
 *                           different text from the input.
 *                           Not defined if an error occurs including buffer overflow.
 *                           Always false if !doNormalize.
 * @param pErrorCode ICU error code in/out parameter.
 *                   Must fulfill U_SUCCESS before the function call.
 * @return Length of output (number of UChars) when successful or buffer overflow.
 *
 * @see unorm_previous
 * @see unorm_normalize
 *
 * @deprecated ICU 56 Use unorm2.h instead.
 */
U_DEPRECATED int32_t U_EXPORT2
unorm_next(UCharIterator *src,
           UChar *dest, int32_t destCapacity,
           UNormalizationMode mode, int32_t options,
           UBool doNormalize, UBool *pNeededToNormalize,
           UErrorCode *pErrorCode);

/**
 * Iterative normalization backward.
 * This function (together with unorm_next) is somewhat
 * similar to the C++ Normalizer class (see its non-static functions).
 * For all details see unorm_next.
 *
 * @param src The input text in the form of a C character iterator.
 * @param dest The output buffer; can be NULL if destCapacity==0 for pure preflighting.
 * @param destCapacity The number of UChars that fit into dest.
 * @param mode The normalization mode.
 * @param options The normalization options, ORed together (0 for no options).
 * @param doNormalize Indicates if the source text up to the next boundary
 *                    is to be normalized (true) or just copied (false).
 * @param pNeededToNormalize Output flag indicating if the normalization resulted in
 *                           different text from the input.
 *                           Not defined if an error occurs including buffer overflow.
 *                           Always false if !doNormalize.
 * @param pErrorCode ICU error code in/out parameter.
 *                   Must fulfill U_SUCCESS before the function call.
 * @return Length of output (number of UChars) when successful or buffer overflow.
 *
 * @see unorm_next
 * @see unorm_normalize
 *
 * @deprecated ICU 56 Use unorm2.h instead.
 */
U_DEPRECATED int32_t U_EXPORT2
unorm_previous(UCharIterator *src,
               UChar *dest, int32_t destCapacity,
               UNormalizationMode mode, int32_t options,
               UBool doNormalize, UBool *pNeededToNormalize,
               UErrorCode *pErrorCode);

/**
 * Concatenate normalized strings, making sure that the result is normalized as well.
 *
 * If both the left and the right strings are in
 * the normalization form according to "mode/options",
 * then the result will be
 *
 * \code
 *     dest=normalize(left+right, mode, options)
 * \endcode
 *
 * With the input strings already being normalized,
 * this function will use unorm_next() and unorm_previous()
 * to find the adjacent end pieces of the input strings.
 * Only the concatenation of these end pieces will be normalized and
 * then concatenated with the remaining parts of the input strings.
 *
 * It is allowed to have dest==left to avoid copying the entire left string.
 *
 * @param left Left source string, may be same as dest.
 * @param leftLength Length of left source string, or -1 if NUL-terminated.
 * @param right Right source string. Must not be the same as dest, nor overlap.
 * @param rightLength Length of right source string, or -1 if NUL-terminated.
 * @param dest The output buffer; can be NULL if destCapacity==0 for pure preflighting.
 * @param destCapacity The number of UChars that fit into dest.
 * @param mode The normalization mode.
 * @param options The normalization options, ORed together (0 for no options).
 * @param pErrorCode ICU error code in/out parameter.
 *                   Must fulfill U_SUCCESS before the function call.
 * @return Length of output (number of UChars) when successful or buffer overflow.
 *
 * @see unorm_normalize
 * @see unorm_next
 * @see unorm_previous
 *
 * @deprecated ICU 56 Use unorm2.h instead.
 */
U_DEPRECATED int32_t U_EXPORT2
unorm_concatenate(const UChar *left, int32_t leftLength,
                  const UChar *right, int32_t rightLength,
                  UChar *dest, int32_t destCapacity,
                  UNormalizationMode mode, int32_t options,
                  UErrorCode *pErrorCode);

#endif  /* U_HIDE_DEPRECATED_API */
#endif /* #if !UCONFIG_NO_NORMALIZATION */
#endif

${this.title}

Code Editor : unorm.h