ubrk.h

linux下开源浏览器WebKit的源码,市面上的很多商用浏览器都是移植自WebKit

/*
* Copyright (C) 1996-2004, International Business Machines Corporation and others. All Rights Reserved.
*****************************************************************************************
*/

#ifndef UBRK_H
#define UBRK_H

#include "unicode/utypes.h"
#include "unicode/uloc.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.
 * <P>
 * Line boundary analysis determines where a text string can be broken
 * when line-wrapping. The mechanism correctly handles punctuation and
 * hyphenated words.
 * <P>
 * Sentence boundary analysis allows selection with correct
 * interpretation of periods within numbers and abbreviations, and
 * trailing punctuation marks such as quotation marks and parentheses.
 * <P>
 * 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.
 * <P>
 * Character boundary analysis allows users to interact with
 * characters as they expect to, for example, when moving the cursor
 * through a text string. Character boundary analysis provides correct
 * navigation of through character strings, regardless of how the
 * character is stored.  For example, an accented character might be
 * stored as a base character and a diacritical mark. What users
 * consider to be a character can differ between languages.
 * <P>
 * Title boundary analysis locates all positions,
 * typically starts of words, that should be set to Title Case
 * when title casing the text.
 * <P>
 *
 * This is the interface for all text boundaries.
 * <P>
 * Examples:
 * <P>
 * Helper function to output text
 * <pre>
 * \code
 *    void printTextRange(UChar* str, int32_t start, int32_t end ) {
 *         UChar* result;
 *         UChar* temp;
 *         const char* res;
 *         temp=(UChar*)malloc(sizeof(UChar) * ((u_strlen(str)-start)+1));
 *         result=(UChar*)malloc(sizeof(UChar) * ((end-start)+1));
 *         u_strcpy(temp, &str[start]);
 *         u_strncpy(result, temp, end-start);
 *         res=(char*)malloc(sizeof(char) * (u_strlen(result)+1));
 *         u_austrcpy(res, result);
 *         printf("%s\n", res);
 *    }
 * \endcode
 * </pre>
 * Print each element in order:
 * <pre>
 * \code
 *    void printEachForward( UBreakIterator* boundary, UChar* str) {
 *       int32_t end;
 *       int32_t start = ubrk_first(boundary);
 *       for (end = ubrk_next(boundary)); end != UBRK_DONE; start = end, end = ubrk_next(boundary)) {
 *             printTextRange(str, start, end );
 *         }
 *    }
 * \endcode
 * </pre>
 * Print each element in reverse order:
 * <pre>
 * \code
 *    void printEachBackward( UBreakIterator* boundary, UChar* str) {
 *       int32_t start;
 *       int32_t end = ubrk_last(boundary);
 *       for (start = ubrk_previous(boundary); start != UBRK_DONE;  end = start, start =ubrk_previous(boundary)) {
 *             printTextRange( str, start, end );
 *         }
 *    }
 * \endcode
 * </pre>
 * Print first element
 * <pre>
 * \code
 *    void printFirst(UBreakIterator* boundary, UChar* str) {
 *        int32_t end;
 *        int32_t start = ubrk_first(boundary);
 *        end = ubrk_next(boundary);
 *        printTextRange( str, start, end );
 *    }
 * \endcode
 * </pre>
 * Print last element
 * <pre>
 * \code
 *    void printLast(UBreakIterator* boundary, UChar* str) {
 *        int32_t start;
 *        int32_t end = ubrk_last(boundary);
 *        start = ubrk_previous(boundary);
 *        printTextRange(str, start, end );
 *    }
 * \endcode
 * </pre>
 * Print the element at a specified position
 * <pre>
 * \code
 *    void printAt(UBreakIterator* boundary, int32_t pos , UChar* str) {
 *        int32_t start;
 *        int32_t end = ubrk_following(boundary, pos);
 *        start = ubrk_previous(boundary);
 *        printTextRange(str, start, end );
 *    }
 * \endcode
 * </pre>
 * Creating and using text boundaries
 * <pre>
 * \code
 *       void BreakIterator_Example( void ) {
 *           UBreakIterator* boundary;
 *           UChar *stringToExamine;
 *           stringToExamine=(UChar*)malloc(sizeof(UChar) * (strlen("Aaa bbb ccc. Ddd eee fff.")+1) );
 *           u_uastrcpy(stringToExamine, "Aaa bbb ccc. Ddd eee fff.");
 *           printf("Examining: "Aaa bbb ccc. Ddd eee fff.");
 *
 *           //print each sentence in forward and reverse order
 *           boundary = ubrk_open(UBRK_SENTENCE, "en_us", stringToExamine, u_strlen(stringToExamine), &status);
 *           printf("----- forward: -----------\n");
 *           printEachForward(boundary, stringToExamine);
 *           printf("----- backward: ----------\n");
 *           printEachBackward(boundary, stringToExamine);
 *           ubrk_close(boundary);
 *
 *           //print each word in order
 *           boundary = ubrk_open(UBRK_WORD, "en_us", stringToExamine, u_strlen(stringToExamine), &status);
 *           printf("----- forward: -----------\n");
 *           printEachForward(boundary, stringToExamine);
 *           printf("----- backward: ----------\n");
 *           printEachBackward(boundary, stringToExamine);
 *           //print first element
 *           printf("----- first: -------------\n");
 *           printFirst(boundary, stringToExamine);
 *           //print last element
 *           printf("----- last: --------------\n");
 *           printLast(boundary, stringToExamine);
 *           //print word at charpos 10
 *           printf("----- at pos 10: ---------\n");
 *           printAt(boundary, 10 , stringToExamine);
 *
 *           ubrk_close(boundary);
 *       }
 * \endcode
 * </pre>
 */

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

#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
#endif /* U_HIDE_DEPRECATED_API */

} 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.
 *  @draft 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.
 *  @draft ICU 2.8
*/
typedef enum USentenceBreakTag {
    /** Tag value for for sentences  ending with a sentence terminator
      * ('.', '?', '!', etc.) character, possibly followed by a