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/ubrk.h (17688B)

/*
******************************************************************************
* Copyright (C) 1996-2009, International Business Machines Corporation and others.
* All Rights Reserved.
******************************************************************************
*/

#ifndef UBRK_H
#define UBRK_H

#include "unicode/utypes.h"
#include "unicode/uloc.h"
#include "unicode/utext.h"

/**
 * A text-break iterator.
 *  For usage in C programs.
 */
#ifndef UBRK_TYPEDEF_UBREAK_ITERATOR
#   define UBRK_TYPEDEF_UBREAK_ITERATOR
    /**
     *  Opaque type representing an ICU Break iterator object.
     *  @stable ICU 2.0
     */
    typedef void UBreakIterator;
#endif

#if !UCONFIG_NO_BREAK_ITERATION

#include "unicode/parseerr.h"

/**
 * \file
 * \brief C API: BreakIterator
 *
 * <h2> BreakIterator C API </h2>
 *
 * The BreakIterator C API defines methods for finding the location
 * of boundaries in text. Pointer to a UBreakIterator maintain a
 * current position and scan over text returning the index of characters
 * where boundaries occur.
 * 
 * Line boundary analysis determines where a text string can be broken
 * when line-wrapping. The mechanism correctly handles punctuation and
 * hyphenated words.
 * 
 * Sentence boundary analysis allows selection with correct
 * interpretation of periods within numbers and abbreviations, and
 * trailing punctuation marks such as quotation marks and parentheses.
 * 
 * Word boundary analysis is used by search and replace functions, as
 * well as within text editing applications that allow the user to
 * select words with a double click. Word selection provides correct
 * interpretation of punctuation marks within and following
 * words. Characters that are not part of a word, such as symbols or
 * punctuation marks, have word-breaks on both sides.
 * 
 * Character boundary analysis identifies the boundaries of
 * "Extended Grapheme Clusters", which are groupings of codepoints
 * that should be treated as character-like units for many text operations.
 * Please see Unicode Standard Annex #29, Unicode Text Segmentation,
 * http://www.unicode.org/reports/tr29/ for additional information 
 * on grapheme clusters and guidelines on their use.
 * 
 * Title boundary analysis locates all positions,
 * typically starts of words, that should be set to Title Case
 * when title casing the text.
 * 
 * The text boundary positions are found according to the rules
 * described in Unicode Standard Annex #29, Text Boundaries, and
 * Unicode Standard Annex #14, Line Breaking Properties. These
 * are available at http://www.unicode.org/reports/tr14/ and
 * http://www.unicode.org/reports/tr29/.
 * 
 * In addition to the plain C API defined in this header file, an
 * object oriented C++ API with equivalent functionality is defined in the
 * file brkiter.h.
 * 
 * Code snippits illustrating the use of the Break Iterator APIs
 * are available in the ICU User Guide,
 * http://icu-project.org/userguide/boundaryAnalysis.html
 * and in the sample program icu/source/samples/break/break.cpp"
 */

/** The possible types of text boundaries.  @stable ICU 2.0 */
typedef enum UBreakIteratorType {
  /** Character breaks  @stable ICU 2.0 */
  UBRK_CHARACTER = 0,
  /** Word breaks @stable ICU 2.0 */
  UBRK_WORD = 1,
  /** Line breaks @stable ICU 2.0 */
  UBRK_LINE = 2,
  /** Sentence breaks @stable ICU 2.0 */
  UBRK_SENTENCE = 3,

#ifndef U_HIDE_DEPRECATED_API
  /**
   * Title Case breaks
   * The iterator created using this type locates title boundaries as described for
   * Unicode 3.2 only. For Unicode 4.0 and above title boundary iteration,
   * please use Word Boundary iterator.
   *
   * @deprecated ICU 2.8 Use the word break iterator for titlecasing for Unicode 4 and later.
   */
  UBRK_TITLE = 4,
#endif /* U_HIDE_DEPRECATED_API */
  UBRK_COUNT = 5
} UBreakIteratorType;

/** Value indicating all text boundaries have been returned.
 *  @stable ICU 2.0
 */
#define UBRK_DONE ((int32_t) -1)

/**
 *  Enum constants for the word break tags returned by
 *  getRuleStatus().  A range of values is defined for each category of
 *  word, to allow for further subdivisions of a category in future releases.
 *  Applications should check for tag values falling within the range, rather
 *  than for single individual values.
 *  @stable ICU 2.2
*/
typedef enum UWordBreak {
    /** Tag value for "words" that do not fit into any of other categories.
     *  Includes spaces and most punctuation. */
    UBRK_WORD_NONE           = 0,
    /** Upper bound for tags for uncategorized words. */
    UBRK_WORD_NONE_LIMIT     = 100,
    /** Tag value for words that appear to be numbers, lower limit.    */
    UBRK_WORD_NUMBER         = 100,
    /** Tag value for words that appear to be numbers, upper limit.    */
    UBRK_WORD_NUMBER_LIMIT   = 200,
    /** Tag value for words that contain letters, excluding
     *  hiragana, katakana or ideographic characters, lower limit.    */
    UBRK_WORD_LETTER         = 200,
    /** Tag value for words containing letters, upper limit  */
    UBRK_WORD_LETTER_LIMIT   = 300,
    /** Tag value for words containing kana characters, lower limit */
    UBRK_WORD_KANA           = 300,
    /** Tag value for words containing kana characters, upper limit */
    UBRK_WORD_KANA_LIMIT     = 400,
    /** Tag value for words containing ideographic characters, lower limit */
    UBRK_WORD_IDEO           = 400,
    /** Tag value for words containing ideographic characters, upper limit */
    UBRK_WORD_IDEO_LIMIT     = 500
} UWordBreak;

/**
 *  Enum constants for the line break tags returned by getRuleStatus().
 *  A range of values is defined for each category of
 *  word, to allow for further subdivisions of a category in future releases.
 *  Applications should check for tag values falling within the range, rather
 *  than for single individual values.
 *  @stable ICU 2.8
*/
typedef enum ULineBreakTag {
    /** Tag value for soft line breaks, positions at which a line break
      *  is acceptable but not required                */
    UBRK_LINE_SOFT            = 0,
    /** Upper bound for soft line breaks.              */
    UBRK_LINE_SOFT_LIMIT      = 100,
    /** Tag value for a hard, or mandatory line break  */
    UBRK_LINE_HARD            = 100,
    /** Upper bound for hard line breaks.              */
    UBRK_LINE_HARD_LIMIT      = 200
} ULineBreakTag;

/**
 *  Enum constants for the sentence break tags returned by getRuleStatus().
 *  A range of values is defined for each category of
 *  sentence, to allow for further subdivisions of a category in future releases.
 *  Applications should check for tag values falling within the range, rather
 *  than for single individual values.
 *  @stable ICU 2.8
*/
typedef enum USentenceBreakTag {
    /** Tag value for for sentences  ending with a sentence terminator
      * ('.', '?', '!', etc.) character, possibly followed by a
      * hard separator (CR, LF, PS, etc.)
      */
    UBRK_SENTENCE_TERM       = 0,
    /** Upper bound for tags for sentences ended by sentence terminators.    */
    UBRK_SENTENCE_TERM_LIMIT = 100,
    /** Tag value for for sentences that do not contain an ending
      * sentence terminator ('.', '?', '!', etc.) character, but
      * are ended only by a hard separator (CR, LF, PS, etc.) or end of input.
      */
    UBRK_SENTENCE_SEP        = 100,
    /** Upper bound for tags for sentences ended by a separator.              */
    UBRK_SENTENCE_SEP_LIMIT  = 200
    /** Tag value for a hard, or mandatory line break  */
} USentenceBreakTag;

/**
 * Open a new UBreakIterator for locating text boundaries for a specified locale.
 * A UBreakIterator may be used for detecting character, line, word,
 * and sentence breaks in text.
 * @param type The type of UBreakIterator to open: one of UBRK_CHARACTER, UBRK_WORD,
 * UBRK_LINE, UBRK_SENTENCE
 * @param locale The locale specifying the text-breaking conventions.
 * @param text The text to be iterated over.
 * @param textLength The number of characters in text, or -1 if null-terminated.
 * @param status A UErrorCode to receive any errors.
 * @return A UBreakIterator for the specified locale.
 * @see ubrk_openRules
 * @stable ICU 2.0
 */
U_STABLE UBreakIterator* U_EXPORT2
ubrk_open(UBreakIteratorType type,
      const char *locale,
      const UChar *text,
      int32_t textLength,
      UErrorCode *status);

/**
 * Open a new UBreakIterator for locating text boundaries using specified breaking rules.
 * The rule syntax is ... (TBD)
 * @param rules A set of rules specifying the text breaking conventions.
 * @param rulesLength The number of characters in rules, or -1 if null-terminated.
 * @param text The text to be iterated over.  May be null, in which case ubrk_setText() is
 *        used to specify the text to be iterated.
 * @param textLength The number of characters in text, or -1 if null-terminated.
 * @param parseErr   Receives position and context information for any syntax errors
 *                   detected while parsing the rules.
 * @param status A UErrorCode to receive any errors.
 * @return A UBreakIterator for the specified rules.
 * @see ubrk_open
 * @stable ICU 2.2
 */
U_STABLE UBreakIterator* U_EXPORT2
ubrk_openRules(const UChar     *rules,
               int32_t         rulesLength,
               const UChar     *text,
               int32_t          textLength,
               UParseError     *parseErr,
               UErrorCode      *status);

/**
 * Thread safe cloning operation
 * @param bi iterator to be cloned
 * @param stackBuffer user allocated space for the new clone. If NULL new memory will be allocated.
 *  If buffer is not large enough, new memory will be allocated.
 *  Clients can use the U_BRK_SAFECLONE_BUFFERSIZE. This will probably be enough to avoid memory allocations.
 * @param pBufferSize pointer to size of allocated space.
 *  If *pBufferSize == 0, a sufficient size for use in cloning will
 *  be returned ('pre-flighting')
 *  If *pBufferSize is not enough for a stack-based safe clone,
 *  new memory will be allocated.
 * @param status to indicate whether the operation went on smoothly or there were errors
 *  An informational status value, U_SAFECLONE_ALLOCATED_ERROR, is used if any allocations were necessary.
 * @return pointer to the new clone
 * @stable ICU 2.0
 */
U_STABLE UBreakIterator * U_EXPORT2
ubrk_safeClone(
          const UBreakIterator *bi,
          void *stackBuffer,
          int32_t *pBufferSize,
          UErrorCode *status);

/**
  * A recommended size (in bytes) for the memory buffer to be passed to ubrk_saveClone().
  * @stable ICU 2.0
  */
#define U_BRK_SAFECLONE_BUFFERSIZE 512

/**
* Close a UBreakIterator.
* Once closed, a UBreakIterator may no longer be used.
* @param bi The break iterator to close.
 * @stable ICU 2.0
*/
U_STABLE void U_EXPORT2
ubrk_close(UBreakIterator *bi);

/**
 * Sets an existing iterator to point to a new piece of text
 * @param bi The iterator to use
 * @param text The text to be set
 * @param textLength The length of the text
 * @param status The error code
 * @stable ICU 2.0
 */
U_STABLE void U_EXPORT2
ubrk_setText(UBreakIterator* bi,
             const UChar*    text,
             int32_t         textLength,
             UErrorCode*     status);

/**
 * Sets an existing iterator to point to a new piece of text
 * @param bi The iterator to use
 * @param text The text to be set.
 *             This function makes a shallow clone of the supplied UText.  This means
 *             that the caller is free to immediately close or otherwise reuse the
 *             UText that was passed as a parameter, but that the underlying text itself
 *             must not be altered while being referenced by the break iterator.
 * @param status The error code
 * @stable ICU 3.4
 */
U_STABLE void U_EXPORT2
ubrk_setUText(UBreakIterator* bi,
             UText*          text,
             UErrorCode*     status);

/**
 * Determine the most recently-returned text boundary.
 *
 * @param bi The break iterator to use.
 * @return The character index most recently returned by \ref ubrk_next, \ref ubrk_previous,
 * \ref ubrk_first, or \ref ubrk_last.
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
ubrk_current(const UBreakIterator *bi);

/**
 * Determine the text boundary following the current text boundary.
 *
 * @param bi The break iterator to use.
 * @return The character index of the next text boundary, or UBRK_DONE
 * if all text boundaries have been returned.
 * @see ubrk_previous
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
ubrk_next(UBreakIterator *bi);

/**
 * Determine the text boundary preceding the current text boundary.
 *
 * @param bi The break iterator to use.
 * @return The character index of the preceding text boundary, or UBRK_DONE
 * if all text boundaries have been returned.
 * @see ubrk_next
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
ubrk_previous(UBreakIterator *bi);

/**
 * Determine the index of the first character in the text being scanned.
 * This is not always the same as index 0 of the text.
 * @param bi The break iterator to use.
 * @return The character index of the first character in the text being scanned.
 * @see ubrk_last
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
ubrk_first(UBreakIterator *bi);

/**
 * Determine the index immediately beyond the last character in the text being
 * scanned.
 * This is not the same as the last character.
 * @param bi The break iterator to use.
 * @return The character offset immediately beyond the last character in the
 * text being scanned.
 * @see ubrk_first
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
ubrk_last(UBreakIterator *bi);

/**
 * Determine the text boundary preceding the specified offset.
 * The value returned is always smaller than offset, or UBRK_DONE.
 * @param bi The break iterator to use.
 * @param offset The offset to begin scanning.
 * @return The text boundary preceding offset, or UBRK_DONE.
 * @see ubrk_following
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
ubrk_preceding(UBreakIterator *bi,
           int32_t offset);

/**
 * Determine the text boundary following the specified offset.
 * The value returned is always greater than offset, or UBRK_DONE.
 * @param bi The break iterator to use.
 * @param offset The offset to begin scanning.
 * @return The text boundary following offset, or UBRK_DONE.
 * @see ubrk_preceding
 * @stable ICU 2.0
 */
U_STABLE int32_t U_EXPORT2
ubrk_following(UBreakIterator *bi,
           int32_t offset);

/**
* Get a locale for which text breaking information is available.
* A UBreakIterator in a locale returned by this function will perform the correct
* text breaking for the locale.
* @param index The index of the desired locale.
* @return A locale for which number text breaking information is available, or 0 if none.
* @see ubrk_countAvailable
* @stable ICU 2.0
*/
U_STABLE const char* U_EXPORT2
ubrk_getAvailable(int32_t index);

/**
* Determine how many locales have text breaking information available.
* This function is most useful as determining the loop ending condition for
* calls to \ref ubrk_getAvailable.
* @return The number of locales for which text breaking information is available.
* @see ubrk_getAvailable
* @stable ICU 2.0
*/
U_STABLE int32_t U_EXPORT2
ubrk_countAvailable(void);

/**
* Returns true if the specfied position is a boundary position.  As a side
* effect, leaves the iterator pointing to the first boundary position at
* or after "offset".
* @param bi The break iterator to use.
* @param offset the offset to check.
* @return True if "offset" is a boundary position.
* @stable ICU 2.0
*/
U_STABLE  UBool U_EXPORT2
ubrk_isBoundary(UBreakIterator *bi, int32_t offset);

/**
 * Return the status from the break rule that determined the most recently
 * returned break position. The values appear in the rule source
 * within brackets, {123}, for example. For rules that do not specify a
 * status, a default value of 0 is returned.
 * 
 * For word break iterators, the possible values are defined in enum UWordBreak.
 * @stable ICU 2.2
 */
U_STABLE int32_t U_EXPORT2
ubrk_getRuleStatus(UBreakIterator *bi);

/**
 * Get the statuses from the break rules that determined the most recently
 * returned break position. The values appear in the rule source
 * within brackets, {123}, for example. The default status value for rules
 * that do not explicitly provide one is zero.
 * 
 * For word break iterators, the possible values are defined in enum UWordBreak.
 * @param bi The break iterator to use
 * @param fillInVec an array to be filled in with the status values.
 * @param capacity the length of the supplied vector. A length of zero causes
 * the function to return the number of status values, in the
 * normal way, without attemtping to store any values.
 * @param status receives error codes.
 * @return The number of rule status values from rules that determined
 * the most recent boundary returned by the break iterator.
 * @stable ICU 3.0
 */
U_STABLE int32_t U_EXPORT2
ubrk_getRuleStatusVec(UBreakIterator *bi, int32_t *fillInVec, int32_t capacity, UErrorCode *status);

/**
 * Return the locale of the break iterator. You can choose between the valid and
 * the actual locale.
 * @param bi break iterator
 * @param type locale type (valid or actual)
 * @param status error code
 * @return locale string
 * @stable ICU 2.8
 */
U_STABLE const char* U_EXPORT2
ubrk_getLocaleByType(const UBreakIterator *bi, ULocDataLocaleType type, UErrorCode* status);

#endif /* #if !UCONFIG_NO_BREAK_ITERATION */

#endif

cmd: