FM / unicode

/usr/include/unicode

Name	Size	Mode	Actions
basictz.h	8913	0644	edit dl rm
bms.h	8664	0644	edit dl rm
bmsearch.h	7316	0644	edit dl rm
brkiter.h	23001	0644	edit dl rm
bytestream.h	8531	0644	edit dl rm
calendar.h	90659	0644	edit dl rm
caniter.h	7288	0644	edit dl rm
chariter.h	24186	0644	edit dl rm
choicfmt.h	29528	0644	edit dl rm
coleitr.h	12990	0644	edit dl rm
coll.h	48468	0644	edit dl rm
colldata.h	11957	0644	edit dl rm
curramt.h	3659	0644	edit dl rm
currpinf.h	7061	0644	edit dl rm
currunit.h	3057	0644	edit dl rm
datefmt.h	27946	0644	edit dl rm
dbbi.h	966	0644	edit dl rm
dcfmtsym.h	14040	0644	edit dl rm
decimfmt.h	88612	0644	edit dl rm
docmain.h	6003	0644	edit dl rm
dtfmtsym.h	26145	0644	edit dl rm
dtintrv.h	3734	0644	edit dl rm
dtitvfmt.h	39700	0644	edit dl rm
dtitvinf.h	18704	0644	edit dl rm
dtptngen.h	17303	0644	edit dl rm
dtrule.h	8718	0644	edit dl rm
errorcode.h	4361	0644	edit dl rm
fieldpos.h	8713	0644	edit dl rm
fmtable.h	18794	0644	edit dl rm
format.h	12083	0644	edit dl rm
gregocal.h	33797	0644	edit dl rm
locid.h	30241	0644	edit dl rm
measfmt.h	1897	0644	edit dl rm
measunit.h	1635	0644	edit dl rm
measure.h	3321	0644	edit dl rm
msgfmt.h	39435	0644	edit dl rm
normlzr.h	30337	0644	edit dl rm
numfmt.h	33987	0644	edit dl rm
numsys.h	5004	0644	edit dl rm
parseerr.h	3044	0644	edit dl rm
parsepos.h	5468	0644	edit dl rm
platform.h	9961	0644	edit dl rm
plurfmt.h	23079	0644	edit dl rm
plurrule.h	9901	0644	edit dl rm
ppalmos.h	6992	0644	edit dl rm
putil.h	6686	0644	edit dl rm
pwin32.h	8668	0644	edit dl rm
rbbi.h	26993	0644	edit dl rm
rbnf.h	45681	0644	edit dl rm
rbtz.h	15695	0644	edit dl rm
regex.h	52316	0644	edit dl rm
rep.h	9559	0644	edit dl rm
resbund.h	18130	0644	edit dl rm
schriter.h	6293	0644	edit dl rm
search.h	22357	0644	edit dl rm
simpletz.h	46179	0644	edit dl rm
smpdtfmt.h	48325	0644	edit dl rm
sortkey.h	11111	0644	edit dl rm
std_string.h	1769	0644	edit dl rm
strenum.h	9888	0644	edit dl rm
stringpiece.h	5484	0644	edit dl rm
stsearch.h	22287	0644	edit dl rm
symtable.h	4199	0644	edit dl rm
tblcoll.h	38199	0644	edit dl rm
timezone.h	34584	0644	edit dl rm
tmunit.h	3454	0644	edit dl rm
tmutamt.h	4787	0644	edit dl rm
tmutfmt.h	8669	0644	edit dl rm
translit.h	54780	0644	edit dl rm
tzrule.h	36057	0644	edit dl rm
tztrans.h	6101	0644	edit dl rm
ubidi.h	83092	0644	edit dl rm
ubrk.h	17688	0644	edit dl rm
ucal.h	40177	0644	edit dl rm
ucasemap.h	16420	0644	edit dl rm
ucat.h	5371	0644	edit dl rm
uchar.h	111062	0644	edit dl rm
uchriter.h	13132	0644	edit dl rm
uclean.h	11855	0644	edit dl rm
ucnv.h	83111	0644	edit dl rm
ucnvsel.h	5630	0644	edit dl rm
ucnv_cb.h	6635	0644	edit dl rm
ucnv_err.h	21375	0644	edit dl rm
ucol.h	48826	0644	edit dl rm
ucoleitr.h	12356	0644	edit dl rm
uconfig.h	6035	0644	edit dl rm
ucsdet.h	12464	0644	edit dl rm
ucurr.h	11572	0644	edit dl rm
udat.h	34496	0644	edit dl rm
udata.h	14265	0644	edit dl rm
udatpg.h	18715	0644	edit dl rm
udeprctd.h	2284	0644	edit dl rm
udraft.h	7600	0644	edit dl rm
uenum.h	5796	0644	edit dl rm
uidna.h	15918	0644	edit dl rm
uintrnal.h	15752	0644	edit dl rm
uiter.h	23234	0644	edit dl rm
uloc.h	44548	0644	edit dl rm
ulocdata.h	9739	0644	edit dl rm
umachine.h	11360	0644	edit dl rm
umisc.h	1255	0644	edit dl rm
umsg.h	26076	0644	edit dl rm
unifilt.h	3770	0644	edit dl rm
unifunct.h	3966	0644	edit dl rm
unimatch.h	6071	0644	edit dl rm
unirepl.h	3290	0644	edit dl rm
uniset.h	61771	0644	edit dl rm
unistr.h	161321	0644	edit dl rm
unorm.h	23621	0644	edit dl rm
unum.h	32145	0644	edit dl rm
uobject.h	11393	0644	edit dl rm
uobslete.h	852	0644	edit dl rm
uregex.h	43948	0644	edit dl rm
urename.h	92538	0644	edit dl rm
urep.h	5394	0644	edit dl rm
ures.h	36348	0644	edit dl rm
uscript.h	11360	0644	edit dl rm
usearch.h	34223	0644	edit dl rm
uset.h	39868	0644	edit dl rm
usetiter.h	9606	0644	edit dl rm
ushape.h	17907	0644	edit dl rm
uspoof.h	38752	0644	edit dl rm
usprep.h	7750	0644	edit dl rm
ustdio.h	35333	0644	edit dl rm
ustream.h	1891	0644	edit dl rm
ustring.h	69383	0644	edit dl rm
usystem.h	1925	0644	edit dl rm
utext.h	58394	0644	edit dl rm
utf.h	8273	0644	edit dl rm
utf8.h	20512	0644	edit dl rm
utf16.h	18776	0644	edit dl rm
utf32.h	653	0644	edit dl rm
utf_old.h	43646	0644	edit dl rm
utmscale.h	13689	0644	edit dl rm
utrace.h	13355	0644	edit dl rm
utrans.h	23129	0644	edit dl rm
utypes.h	34513	0644	edit dl rm
uversion.h	10902	0644	edit dl rm
vtzone.h	20048	0644	edit dl rm

Edit: /usr/include/unicode/normlzr.h (30337B)

/*
 ********************************************************************
 * COPYRIGHT:
 * Copyright (c) 1996-2006, International Business Machines Corporation and
 * others. All Rights Reserved.
 ********************************************************************
 */

#ifndef NORMLZR_H
#define NORMLZR_H

#include "unicode/utypes.h"

/**
 * \file 
 * \brief C++ API: Unicode Normalization
 */
 
#if !UCONFIG_NO_NORMALIZATION

#include "unicode/uobject.h"
#include "unicode/unistr.h"
#include "unicode/chariter.h"
#include "unicode/unorm.h"

struct UCharIterator;
typedef struct UCharIterator UCharIterator; /**< C typedef for struct UCharIterator. @stable ICU 2.1 */

U_NAMESPACE_BEGIN
/**
 * The Normalizer class 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>.
 *
 * The Normalizer class consists of two parts:
 * - static functions that normalize strings or test if strings are normalized
 * - a Normalizer object is an iterator that takes any kind of text and
 * provides iteration over its normalized form
 *
 * The Normalizer class is not suitable for subclassing.
 *
 * The static functions are basically wrappers around the C implementation,
 * using UnicodeString instead of UChar*.
 * For basic information about normalization forms and details about the C API
 * please see the documentation in unorm.h.
 *
 * The iterator API with the Normalizer constructors and the non-static functions
 * uses a CharacterIterator as input. It is possible to pass a string which
 * is then internally wrapped in a CharacterIterator.
 * The input text is not normalized all at once, but incrementally where needed
 * (providing efficient random access).
 * This allows to pass in a large text but spend only a small amount of time
 * normalizing a small part of that text.
 * However, if the entire text is normalized, then the iterator will be
 * slower than normalizing the entire text at once and iterating over the result.
 * A possible use of the Normalizer iterator is also to report an index into the
 * original text that is close to where the normalized characters come from.
 *
 * Important: The iterator API was cleaned up significantly for ICU 2.0.
 * The earlier implementation reported the getIndex() inconsistently,
 * and previous() could not be used after setIndex(), next(), first(), and current().
 *
 * Normalizer allows to start normalizing from anywhere in the input text by
 * calling setIndexOnly(), first(), or last().
 * Without calling any of these, the iterator will start at the beginning of the text.
 *
 * At any time, next() returns the next normalized code point (UChar32),
 * with post-increment semantics (like CharacterIterator::next32PostInc()).
 * previous() returns the previous normalized code point (UChar32),
 * with pre-decrement semantics (like CharacterIterator::previous32()).
 *
 * current() returns the current code point
 * (respectively the one at the newly set index) without moving
 * the getIndex(). Note that if the text at the current position
 * needs to be normalized, then these functions will do that.
 * (This is why current() is not const.)
 * It is more efficient to call setIndexOnly() instead, which does not
 * normalize.
 *
 * getIndex() always refers to the position in the input text where the normalized
 * code points are returned from. It does not always change with each returned
 * code point.
 * The code point that is returned from any of the functions
 * corresponds to text at or after getIndex(), according to the
 * function's iteration semantics (post-increment or pre-decrement).
 *
 * next() returns a code point from at or after the getIndex()
 * from before the next() call. After the next() call, the getIndex()
 * might have moved to where the next code point will be returned from
 * (from a next() or current() call).
 * This is semantically equivalent to array access with array[index++]
 * (post-increment semantics).
 *
 * previous() returns a code point from at or after the getIndex()
 * from after the previous() call.
 * This is semantically equivalent to array access with array[--index]
 * (pre-decrement semantics).
 *
 * Internally, the Normalizer iterator normalizes a small piece of text
 * starting at the getIndex() and ending at a following "safe" index.
 * The normalized results is stored in an internal string buffer, and
 * the code points are iterated from there.
 * With multiple iteration calls, this is repeated until the next piece
 * of text needs to be normalized, and the getIndex() needs to be moved.
 *
 * The following "safe" index, the internal buffer, and the secondary
 * iteration index into that buffer are not exposed on the API.
 * This also means that it is currently not practical to return to
 * a particular, arbitrary position in the text because one would need to
 * know, and be able to set, in addition to the getIndex(), at least also the
 * current index into the internal buffer.
 * It is currently only possible to observe when getIndex() changes
 * (with careful consideration of the iteration semantics),
 * at which time the internal index will be 0.
 * For example, if getIndex() is different after next() than before it,
 * then the internal index is 0 and one can return to this getIndex()
 * later with setIndexOnly().
 *
 * @author Laura Werner, Mark Davis, Markus Scherer
 * @stable ICU 2.0
 */
class U_COMMON_API Normalizer : public UObject {
public:
 /**
 * If DONE is returned from an iteration function that returns a code point,
 * then there are no more normalization results available.
 * @stable ICU 2.0
 */
 enum {
 DONE=0xffff
 };

// Constructors

/**
 * Creates a new <code>Normalizer</code> object for iterating over the
 * normalized form of a given string.
 * 
 * @param str The string to be normalized. The normalization
 * will start at the beginning of the string.
 *
 * @param mode The normalization mode.
 * @stable ICU 2.0
 */
 Normalizer(const UnicodeString& str, UNormalizationMode mode);

/**
 * Creates a new <code>Normalizer</code> object for iterating over the
 * normalized form of a given string.
 * 
 * @param str The string to be normalized. The normalization
 * will start at the beginning of the string.
 *
 * @param length Length of the string, or -1 if NUL-terminated.
 * @param mode The normalization mode.
 * @stable ICU 2.0
 */
 Normalizer(const UChar* str, int32_t length, UNormalizationMode mode);

/**
 * Creates a new <code>Normalizer</code> object for iterating over the
 * normalized form of the given text.
 * 
 * @param iter The input text to be normalized. The normalization
 * will start at the beginning of the string.
 *
 * @param mode The normalization mode.
 * @stable ICU 2.0
 */
 Normalizer(const CharacterIterator& iter, UNormalizationMode mode);

/**
   * Copy constructor.
   * @param copy The object to be copied.
   * @stable ICU 2.0
   */
  Normalizer(const Normalizer& copy);

/**
   * Destructor
   * @stable ICU 2.0
   */
  virtual ~Normalizer();

//-------------------------------------------------------------------------
  // Static utility methods
  //-------------------------------------------------------------------------

/**
 * Normalizes a <code>UnicodeString</code> according to the specified normalization mode.
 * This is a wrapper for unorm_normalize(), using UnicodeString's.
 *
 * The <code>options</code> parameter specifies which optional
 * <code>Normalizer</code> features are to be enabled for this operation.
 *
 * @param source the input string to be normalized.
 * @param mode the normalization mode
 * @param options the optional features to be enabled (0 for no options)
 * @param result The normalized string (on output).
 * @param status The error code.
 * @stable ICU 2.0
 */
 static void U_EXPORT2 normalize(const UnicodeString& source,
 UNormalizationMode mode, int32_t options,
 UnicodeString& result,
 UErrorCode &status);

/**
 * Compose a <code>UnicodeString</code>.
 * This is equivalent to normalize() with mode UNORM_NFC or UNORM_NFKC.
 * This is a wrapper for unorm_normalize(), using UnicodeString's.
 *
 * The <code>options</code> parameter specifies which optional
 * <code>Normalizer</code> features are to be enabled for this operation.
 *
 * @param source the string to be composed.
 * @param compat Perform compatibility decomposition before composition.
 * If this argument is <code>FALSE</code>, only canonical
 * decomposition will be performed.
 * @param options the optional features to be enabled (0 for no options)
 * @param result The composed string (on output).
 * @param status The error code.
 * @stable ICU 2.0
 */
 static void U_EXPORT2 compose(const UnicodeString& source,
 UBool compat, int32_t options,
 UnicodeString& result,
 UErrorCode &status);

/**
 * Static method to decompose a <code>UnicodeString</code>.
 * This is equivalent to normalize() with mode UNORM_NFD or UNORM_NFKD.
 * This is a wrapper for unorm_normalize(), using UnicodeString's.
 *
 * The <code>options</code> parameter specifies which optional
 * <code>Normalizer</code> features are to be enabled for this operation.
 *
 * @param source the string to be decomposed.
 * @param compat Perform compatibility decomposition.
 * If this argument is <code>FALSE</code>, only canonical
 * decomposition will be performed.
 * @param options the optional features to be enabled (0 for no options)
 * @param result The decomposed string (on output).
 * @param status The error code.
 * @stable ICU 2.0
 */
 static void U_EXPORT2 decompose(const UnicodeString& source,
 UBool compat, int32_t options,
 UnicodeString& result,
 UErrorCode &status);

/**
   * Performing quick check on a string, to quickly determine if the string is
   * in a particular normalization format.
   * This is a wrapper for unorm_quickCheck(), using a UnicodeString.
   *
   * 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 mode         normalization format
   * @param status A reference to a UErrorCode to receive any errors
   * @return UNORM_YES, UNORM_NO or UNORM_MAYBE
   *
   * @see isNormalized
   * @stable ICU 2.0
   */
  static inline UNormalizationCheckResult
  quickCheck(const UnicodeString &source, UNormalizationMode mode, UErrorCode &status);

/**
   * Performing quick check on a string; same as the other version of quickCheck
   * but takes an extra options parameter like most normalization functions.
   *
   * @param source       string for determining if it is in a normalized format
   * @param mode         normalization format
   * @param options      the optional features to be enabled (0 for no options)
   * @param status A reference to a UErrorCode to receive any errors
   * @return UNORM_YES, UNORM_NO or UNORM_MAYBE
   *
   * @see isNormalized
   * @stable ICU 2.6
   */
  static inline UNormalizationCheckResult
  quickCheck(const UnicodeString &source, UNormalizationMode mode, int32_t options, UErrorCode &status);

/**
   * 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 mode       Which normalization form to test for.
   * @param errorCode  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 quickCheck
   * @stable ICU 2.2
   */
  static inline UBool
  isNormalized(const UnicodeString &src, UNormalizationMode mode, UErrorCode &errorCode);

/**
   * Test if a string is in a given normalization form; same as the other version of 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 mode       Which normalization form to test for.
   * @param options      the optional features to be enabled (0 for no options)
   * @param errorCode  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 quickCheck
   * @stable ICU 2.6
   */
  static inline UBool
  isNormalized(const UnicodeString &src, UNormalizationMode mode, int32_t options, UErrorCode &errorCode);

/**
   * 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
   *
   * For details see unorm_concatenate in unorm.h.
   *
   * @param left Left source string.
   * @param right Right source string.
   * @param result The output string.
   * @param mode The normalization mode.
   * @param options A bit set of normalization options.
   * @param errorCode ICU error code in/out parameter.
   *                   Must fulfill U_SUCCESS before the function call.
   * @return result
   *
   * @see unorm_concatenate
   * @see normalize
   * @see unorm_next
   * @see unorm_previous
   *
   * @stable ICU 2.1
   */
  static UnicodeString &
  U_EXPORT2 concatenate(UnicodeString &left, UnicodeString &right,
              UnicodeString &result,
              UNormalizationMode mode, int32_t options,
              UErrorCode &errorCode);

/**
 * Compare 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(s1)), NFD(foldCase(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 s2 Second source string.
 *
 * @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 errorCode 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_compare
 * @see normalize
 * @see UNORM_FCD
 * @see u_strCompare
 * @see u_strCaseCompare
 *
 * @stable ICU 2.2
 */
 static inline int32_t
 compare(const UnicodeString &s1, const UnicodeString &s2,
 uint32_t options,
 UErrorCode &errorCode);

//-------------------------------------------------------------------------
  // Iteration API
  //-------------------------------------------------------------------------

/**
   * Return the current character in the normalized text.
   * current() may need to normalize some text at getIndex().
   * The getIndex() is not changed.
   *
   * @return the current normalized code point
   * @stable ICU 2.0
   */
  UChar32              current(void);

/**
   * Return the first character in the normalized text.
   * This is equivalent to setIndexOnly(startIndex()) followed by next().
   * (Post-increment semantics.)
   *
   * @return the first normalized code point
   * @stable ICU 2.0
   */
  UChar32              first(void);

/**
   * Return the last character in the normalized text.
   * This is equivalent to setIndexOnly(endIndex()) followed by previous().
   * (Pre-decrement semantics.)
   *
   * @return the last normalized code point
   * @stable ICU 2.0
   */
  UChar32              last(void);

/**
 * Return the next character in the normalized text.
 * (Post-increment semantics.)
 * If the end of the text has already been reached, DONE is returned.
 * The DONE value could be confused with a U+FFFF non-character code point
 * in the text. If this is possible, you can test getIndex()<endIndex()
 * before calling next(), or (getIndex()<endIndex() || last()!=DONE)
 * after calling next(). (Calling last() will change the iterator state!)
 *
 * The C API unorm_next() is more efficient and does not have this ambiguity.
 *
 * @return the next normalized code point
 * @stable ICU 2.0
 */
 UChar32 next(void);

/**
   * Return the previous character in the normalized text and decrement.
   * (Pre-decrement semantics.)
   * If the beginning of the text has already been reached, DONE is returned.
   * The DONE value could be confused with a U+FFFF non-character code point
   * in the text. If this is possible, you can test
   * (getIndex()>startIndex() || first()!=DONE). (Calling first() will change
   * the iterator state!)
   *
   * The C API unorm_previous() is more efficient and does not have this ambiguity.
   *
   * @return the previous normalized code point
   * @stable ICU 2.0
   */
  UChar32              previous(void);

/**
   * Set the iteration position in the input text that is being normalized,
   * without any immediate normalization.
   * After setIndexOnly(), getIndex() will return the same index that is
   * specified here.
   *
   * @param index the desired index in the input text.
   * @stable ICU 2.0
   */
  void                 setIndexOnly(int32_t index);

/**
   * Reset the index to the beginning of the text.
   * This is equivalent to setIndexOnly(startIndex)).
   * @stable ICU 2.0
   */
  void                reset(void);

/**
   * Retrieve the current iteration position in the input text that is
   * being normalized.
   *
   * A following call to next() will return a normalized code point from
   * the input text at or after this index.
   *
   * After a call to previous(), getIndex() will point at or before the
   * position in the input text where the normalized code point
   * was returned from with previous().
   *
   * @return the current index in the input text
   * @stable ICU 2.0
   */
  int32_t            getIndex(void) const;

/**
 * Retrieve the index of the start of the input text. This is the begin index
 * of the <code>CharacterIterator</code> or the start (i.e. index 0) of the string
 * over which this <code>Normalizer</code> is iterating.
 *
 * @return the smallest index in the input text where the Normalizer operates
 * @stable ICU 2.0
 */
 int32_t startIndex(void) const;

/**
 * Retrieve the index of the end of the input text. This is the end index
 * of the <code>CharacterIterator</code> or the length of the string
 * over which this <code>Normalizer</code> is iterating.
 * This end index is exclusive, i.e., the Normalizer operates only on characters
 * before this index.
 *
 * @return the first index in the input text where the Normalizer does not operate
 * @stable ICU 2.0
 */
 int32_t endIndex(void) const;

/**
   * Returns TRUE when both iterators refer to the same character in the same
   * input text.
   *
   * @param that a Normalizer object to compare this one to
   * @return comparison result
   * @stable ICU 2.0
   */
  UBool        operator==(const Normalizer& that) const;

/**
   * Returns FALSE when both iterators refer to the same character in the same
   * input text.
   *
   * @param that a Normalizer object to compare this one to
   * @return comparison result
   * @stable ICU 2.0
   */
  inline UBool        operator!=(const Normalizer& that) const;

/**
   * Returns a pointer to a new Normalizer that is a clone of this one.
   * The caller is responsible for deleting the new clone.
   * @return a pointer to a new Normalizer
   * @stable ICU 2.0
   */
  Normalizer*        clone(void) const;

/**
   * Generates a hash code for this iterator.
   *
   * @return the hash code
   * @stable ICU 2.0
   */
  int32_t                hashCode(void) const;

//-------------------------------------------------------------------------
  // Property access methods
  //-------------------------------------------------------------------------

/**
 * Set the normalization mode for this object.
 * 
 * Note:If the normalization mode is changed while iterating
 * over a string, calls to {@link #next() } and {@link #previous() } may
 * return previously buffers characters in the old normalization mode
 * until the iteration is able to re-sync at the next base character.
 * It is safest to call {@link #setIndexOnly }, {@link #reset() },
 * {@link #setText }, {@link #first() },
 * {@link #last() }, etc. after calling <code>setMode</code>.
 * 
 * @param newMode the new mode for this <code>Normalizer</code>.
 * @see #getUMode
 * @stable ICU 2.0
 */
 void setMode(UNormalizationMode newMode);

/**
 * Return the normalization mode for this object.
 *
 * This is an unusual name because there used to be a getMode() that
 * returned a different type.
 *
 * @return the mode for this <code>Normalizer</code>
 * @see #setMode
 * @stable ICU 2.0
 */
 UNormalizationMode getUMode(void) const;

/**
 * Set options that affect this <code>Normalizer</code>'s operation.
 * Options do not change the basic composition or decomposition operation
 * that is being performed, but they control whether
 * certain optional portions of the operation are done.
 * Currently the only available option is obsolete.
 *
 * It is possible to specify multiple options that are all turned on or off.
 *
 * @param option the option(s) whose value is/are to be set.
 * @param value the new setting for the option. Use <code>TRUE</code> to
 * turn the option(s) on and <code>FALSE</code> to turn it/them off.
 *
 * @see #getOption
 * @stable ICU 2.0
 */
 void setOption(int32_t option,
 UBool value);

/**
 * Determine whether an option is turned on or off.
 * If multiple options are specified, then the result is TRUE if any
 * of them are set.
 * 
 * @param option the option(s) that are to be checked
 * @return TRUE if any of the option(s) are set
 * @see #setOption
 * @stable ICU 2.0
 */
 UBool getOption(int32_t option) const;

/**
 * Set the input text over which this <code>Normalizer</code> will iterate.
 * The iteration position is set to the beginning.
 *
 * @param newText a CharacterIterator object that replaces the current input text
 * @param status a UErrorCode
 * @stable ICU 2.0
 */
 void setText(const CharacterIterator& newText,
 UErrorCode &status);

/**
 * Set the input text over which this <code>Normalizer</code> will iterate.
 * The iteration position is set to the beginning.
 *
 * @param newText a string that replaces the current input text
 * @param length the length of the string, or -1 if NUL-terminated
 * @param status a UErrorCode
 * @stable ICU 2.0
 */
 void setText(const UChar* newText,
 int32_t length,
 UErrorCode &status);
 /**
 * Copies the input text into the UnicodeString argument.
 *
 * @param result Receives a copy of the text under iteration.
 * @stable ICU 2.0
 */
 void getText(UnicodeString& result);

/**
   * ICU "poor man's RTTI", returns a UClassID for this class.
   * @returns a UClassID for this class.
   * @stable ICU 2.2
   */
  static UClassID U_EXPORT2 getStaticClassID();

/**
   * ICU "poor man's RTTI", returns a UClassID for the actual class.
   * @return a UClassID for the actual class.
   * @stable ICU 2.2
   */
  virtual UClassID getDynamicClassID() const;

private:
  //-------------------------------------------------------------------------
  // Private functions
  //-------------------------------------------------------------------------

Normalizer(); // default constructor not implemented
  Normalizer &operator=(const Normalizer &that); // assignment operator not implemented

// Private utility methods for iteration
  // For documentation, see the source code
  UBool nextNormalize();
  UBool previousNormalize();

void    init(CharacterIterator *iter);
  void    clearBuffer(void);

//-------------------------------------------------------------------------
  // Private data
  //-------------------------------------------------------------------------

UNormalizationMode  fUMode;
  int32_t             fOptions;

// The input text and our position in it
  UCharIterator       *text;

// The normalization buffer is the result of normalization
  // of the source in [currentIndex..nextIndex[ .
  int32_t         currentIndex, nextIndex;

// A buffer for holding intermediate results
  UnicodeString       buffer;
  int32_t         bufferPos;

};

//-------------------------------------------------------------------------
// Inline implementations
//-------------------------------------------------------------------------

inline UBool
Normalizer::operator!= (const Normalizer& other) const
{ return ! operator==(other); }

inline UNormalizationCheckResult
Normalizer::quickCheck(const UnicodeString& source,
                       UNormalizationMode mode,
                       UErrorCode &status) {
    if(U_FAILURE(status)) {
        return UNORM_MAYBE;
    }

return unorm_quickCheck(source.getBuffer(), source.length(),
                            mode, &status);
}

inline UNormalizationCheckResult
Normalizer::quickCheck(const UnicodeString& source,
                       UNormalizationMode mode, int32_t options,
                       UErrorCode &status) {
    if(U_FAILURE(status)) {
        return UNORM_MAYBE;
    }

return unorm_quickCheckWithOptions(source.getBuffer(), source.length(),
                                       mode, options, &status);
}

inline UBool
Normalizer::isNormalized(const UnicodeString& source,
                         UNormalizationMode mode,
                         UErrorCode &status) {
    if(U_FAILURE(status)) {
        return FALSE;
    }

return unorm_isNormalized(source.getBuffer(), source.length(),
                              mode, &status);
}

inline UBool
Normalizer::isNormalized(const UnicodeString& source,
                         UNormalizationMode mode, int32_t options,
                         UErrorCode &status) {
    if(U_FAILURE(status)) {
        return FALSE;
    }

return unorm_isNormalizedWithOptions(source.getBuffer(), source.length(),
                                         mode, options, &status);
}

inline int32_t
Normalizer::compare(const UnicodeString &s1, const UnicodeString &s2,
                    uint32_t options,
                    UErrorCode &errorCode) {
  // all argument checking is done in unorm_compare
  return unorm_compare(s1.getBuffer(), s1.length(),
                       s2.getBuffer(), s2.length(),
                       options,
                       &errorCode);
}

U_NAMESPACE_END

#endif /* #if !UCONFIG_NO_NORMALIZATION */

#endif // NORMLZR_H

cmd: