usearch.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) 2001-2005 IBM and others. All rights reserved.
**********************************************************************
*   Date        Name        Description
*  06/28/2001   synwee      Creation.
**********************************************************************
*/
#ifndef USEARCH_H
#define USEARCH_H

#include "unicode/utypes.h"

#if !UCONFIG_NO_COLLATION

#include "unicode/ucol.h"
#include "unicode/ucoleitr.h"
#include "unicode/ubrk.h"

/**
 * \file
 * \brief C API: StringSearch
 *
 * C Apis for an engine that provides language-sensitive text searching based 
 * on the comparison rules defined in a <tt>UCollator</tt> data struct,
 * see <tt>ucol.h</tt>. This ensures that language eccentricity can be 
 * handled, e.g. for the German collator, characters &szlig; and SS will be matched 
 * if case is chosen to be ignored. 
 * See the <a href="http://dev.icu-project.org/cgi-bin/viewcvs.cgi/~checkout~/icuhtml/design/collation/ICU_collation_design.htm">
 * "ICU Collation Design Document"</a> for more information.
 * <p> 
 * The algorithm implemented is a modified form of the Boyer Moore's search.
 * For more information  see 
 * <a href="http://icu.sourceforge.net/docs/papers/efficient_text_searching_in_java.html">
 * "Efficient Text Searching in Java"</a>, published in <i>Java Report</i> 
 * in February, 1999, for further information on the algorithm.
 * <p>
 * There are 2 match options for selection:<br>
 * Let S' be the sub-string of a text string S between the offsets start and 
 * end <start, end>.
 * <br>
 * A pattern string P matches a text string S at the offsets <start, end> 
 * if
 * <pre> 
 * option 1. Some canonical equivalent of P matches some canonical equivalent 
 *           of S'
 * option 2. P matches S' and if P starts or ends with a combining mark, 
 *           there exists no non-ignorable combining mark before or after S' 
 *           in S respectively. 
 * </pre>
 * Option 2. will be the default.
 * <p>
 * This search has APIs similar to that of other text iteration mechanisms 
 * such as the break iterators in <tt>ubrk.h</tt>. Using these 
 * APIs, it is easy to scan through text looking for all occurances of 
 * a given pattern. This search iterator allows changing of direction by 
 * calling a <tt>reset</tt> followed by a <tt>next</tt> or <tt>previous</tt>. 
 * Though a direction change can occur without calling <tt>reset</tt> first,  
 * this operation comes with some speed penalty.
 * Generally, match results in the forward direction will match the result 
 * matches in the backwards direction in the reverse order
 * <p>
 * <tt>usearch.h</tt> provides APIs to specify the starting position 
 * within the text string to be searched, e.g. <tt>usearch_setOffset</tt>,
 * <tt>usearch_preceding</tt> and <tt>usearch_following</tt>. Since the 
 * starting position will be set as it is specified, please take note that 
 * there are some dangerous positions which the search may render incorrect 
 * results:
 * <ul>
 * <li> The midst of a substring that requires normalization.
 * <li> If the following match is to be found, the position should not be the
 *      second character which requires to be swapped with the preceding 
 *      character. Vice versa, if the preceding match is to be found, 
 *      position to search from should not be the first character which 
 *      requires to be swapped with the next character. E.g certain Thai and
 *      Lao characters require swapping.
 * <li> If a following pattern match is to be found, any position within a 
 *      contracting sequence except the first will fail. Vice versa if a 
 *      preceding pattern match is to be found, a invalid starting point 
 *      would be any character within a contracting sequence except the last.
 * </ul>
 * <p>
 * A breakiterator can be used if only matches at logical breaks are desired.
 * Using a breakiterator will only give you results that exactly matches the
 * boundaries given by the breakiterator. For instance the pattern "e" will
 * not be found in the string "\u00e9" if a character break iterator is used.
 * <p>
 * Options are provided to handle overlapping matches. 
 * E.g. In English, overlapping matches produces the result 0 and 2 
 * for the pattern "abab" in the text "ababab", where else mutually 
 * exclusive matches only produce the result of 0.
 * <p>
 * Though collator attributes will be taken into consideration while 
 * performing matches, there are no APIs here for setting and getting the 
 * attributes. These attributes can be set by getting the collator
 * from <tt>usearch_getCollator</tt> and using the APIs in <tt>ucol.h</tt>.
 * Lastly to update String Search to the new collator attributes, 
 * usearch_reset() has to be called.
 * <p> 
 * Restriction: <br>
 * Currently there are no composite characters that consists of a
 * character with combining class > 0 before a character with combining 
 * class == 0. However, if such a character exists in the future, the 
 * search mechanism does not guarantee the results for option 1.
 * 
 * <p>
 * Example of use:<br>
 * <pre><code>
 * char *tgtstr = "The quick brown fox jumped over the lazy fox";
 * char *patstr = "fox";
 * UChar target[64];
 * UChar pattern[16];
 * UErrorCode status = U_ZERO_ERROR;
 * u_uastrcpy(target, tgtstr);
 * u_uastrcpy(pattern, patstr);
 *
 * UStringSearch *search = usearch_open(pattern, -1, target, -1, "en_US", 
 *                                  &status);
 * if (U_SUCCESS(status)) {
 *     for (int pos = usearch_first(search, &status); 
 *                                      pos != USEARCH_DONE; 
 *                                      pos = usearch_next(search, &status)) {
 *         printf("Found match at %d pos, length is %d\n", pos, 
 *                                        usearch_getMatchLength(search));
 *     }
 * }
 * </code></pre>
 * @stable ICU 2.4
 */

/**
* DONE is returned by previous() and next() after all valid matches have 
* been returned, and by first() and last() if there are no matches at all.
* @stable ICU 2.4
*/
#define USEARCH_DONE -1

/**
* Data structure for searching
* @stable ICU 2.4
*/
struct UStringSearch;
/**
* Data structure for searching
* @stable ICU 2.4
*/
typedef struct UStringSearch UStringSearch;

/**
* @stable ICU 2.4
*/
typedef enum {
    /** Option for overlapping matches */
    USEARCH_OVERLAP,
    /** 
    Option for canonical matches. option 1 in header documentation.
    The default value will be USEARCH_OFF
    */
    USEARCH_CANONICAL_MATCH,
    USEARCH_ATTRIBUTE_COUNT
} USearchAttribute;

/**
* @stable ICU 2.4
*/
typedef enum {
    /** default value for any USearchAttribute */
    USEARCH_DEFAULT = -1,
    /** value for USEARCH_OVERLAP and USEARCH_CANONICAL_MATCH */
    USEARCH_OFF, 
    /** value for USEARCH_OVERLAP and USEARCH_CANONICAL_MATCH */
    USEARCH_ON,
    USEARCH_ATTRIBUTE_VALUE_COUNT
} USearchAttributeValue;

/* open and close ------------------------------------------------------ */

/**
* Creating a search iterator data struct using the argument locale language
* rule set. A collator will be created in the process, which will be owned by
* this search and will be deleted in <tt>usearch_close</tt>.
* @param pattern for matching
* @param patternlength length of the pattern, -1 for null-termination
* @param text text string
* @param textlength length of the text string, -1 for null-termination
* @param locale name of locale for the rules to be used
* @param breakiter A BreakIterator that will be used to restrict the points
*                  at which matches are detected. If a match is found, but 
*                  the match's start or end index is not a boundary as 
*                  determined by the <tt>BreakIterator</tt>, the match will 
*                  be rejected and another will be searched for. 
*                  If this parameter is <tt>NULL</tt>, no break detection is 
*                  attempted.
* @param status for errors if it occurs. If pattern or text is NULL, or if
*               patternlength or textlength is 0 then an 
*               U_ILLEGAL_ARGUMENT_ERROR is returned.
* @return search iterator data structure, or NULL if there is an error.
* @stable ICU 2.4
*/
U_STABLE UStringSearch * U_EXPORT2 usearch_open(const UChar          *pattern, 
                                              int32_t         patternlength, 
                                        const UChar          *text, 
                                              int32_t         textlength,
                                        const char           *locale,
                                              UBreakIterator *breakiter,
                                              UErrorCode     *status);

/**
* Creating a search iterator data struct using the argument collator language
* rule set. Note, user retains the ownership of this collator, thus the 
* responsibility of deletion lies with the user.
* NOTE: string search cannot be instantiated from a collator that has 
* collate digits as numbers (CODAN) turned on.
* @param pattern for matching
* @param patternlength length of the pattern, -1 for null-termination
* @param text text string
* @param textlength length of the text string, -1 for null-termination
* @param collator used for the language rules
* @param breakiter A BreakIterator that will be used to restrict the points
*                  at which matches are detected. If a match is found, but 
*                  the match's start or end index is not a boundary as 
*                  determined by the <tt>BreakIterator</tt>, the match will 
*                  be rejected and another will be searched for. 
*                  If this parameter is <tt>NULL</tt>, no break detection is 
*                  attempted.
* @param status for errors if it occurs. If collator, pattern or text is NULL, 
*               or if patternlength or textlength is 0 then an 
*               U_ILLEGAL_ARGUMENT_ERROR is returned.
* @return search iterator data structure, or NULL if there is an error.
* @stable ICU 2.4
*/
U_STABLE UStringSearch * U_EXPORT2 usearch_openFromCollator(
                                         const UChar *pattern, 
                                               int32_t         patternlength,
                                         const UChar          *text, 
                                               int32_t         textlength,
                                         const UCollator      *collator,
                                               UBreakIterator *breakiter,
                                               UErrorCode     *status);

/**
* Destroying and cleaning up the search iterator data struct.
* If a collator is created in <tt>usearch_open</tt>, it will be destroyed here.
* @param searchiter data struct to clean up
* @stable ICU 2.4
*/
U_STABLE void U_EXPORT2 usearch_close(UStringSearch *searchiter);

/* get and set methods -------------------------------------------------- */

/**
* Sets the current position in the text string which the next search will 
* start from. Clears previous states. 
* This method takes the argument index and sets the position in the text 
* string accordingly without checking if the index is pointing to a 
* valid starting point to begin searching. 
* Search positions that may render incorrect results are highlighted in the
* header comments
* @param strsrch search iterator data struct
* @param position position to start next search from. If position is less
*          than or greater than the text range for searching, 
*          an U_INDEX_OUTOFBOUNDS_ERROR will be returned
* @param status error status if any.
* @stable ICU 2.4
*/
U_STABLE void U_EXPORT2 usearch_setOffset(UStringSearch *strsrch, 
                                        int32_t    position,
                                        UErrorCode    *status);

/**
* Return the current index in the string text being searched.
* If the iteration has gone past the end of the text (or past the beginning 
* for a backwards search), <tt>USEARCH_DONE</tt> is returned.
* @param strsrch search iterator data struct
* @see #USEARCH_DONE
* @stable ICU 2.4
*/
U_STABLE int32_t U_EXPORT2 usearch_getOffset(const UStringSearch *strsrch);
    
/**
* Sets the text searching attributes located in the enum USearchAttribute
* with values from the enum USearchAttributeValue.
* <tt>USEARCH_DEFAULT</tt> can be used for all attributes for resetting.
* @param strsrch search iterator data struct
* @param attribute text attribute to be set
* @param value text attribute value
* @param status for errors if it occurs
* @see #usearch_getAttribute
* @stable ICU 2.4
*/
U_STABLE void U_EXPORT2 usearch_setAttribute(UStringSearch         *strsrch, 
                                           USearchAttribute       attribute,
                                           USearchAttributeValue  value,
                                           UErrorCode            *status);

/**    
* Gets the text searching attributes.
* @param strsrch search iterator data struct
* @param attribute text attribute to be retrieve
* @return text attribute value
* @see #usearch_setAttribute
* @stable ICU 2.4
*/
U_STABLE USearchAttributeValue U_EXPORT2 usearch_getAttribute(
                                         const UStringSearch    *strsrch,
                                               USearchAttribute  attribute);

/**
* Returns the index to the match in the text string that was searched.
* This call returns a valid result only after a successful call to 
* <tt>usearch_first</tt>, <tt>usearch_next</tt>, <tt>usearch_previous</tt>, 
* or <tt>usearch_last</tt>.
* Just after construction, or after a searching method returns 
* <tt>USEARCH_DONE</tt>, this method will return <tt>USEARCH_DONE</tt>.
* <p>
* Use <tt>usearch_getMatchedLength</tt> to get the matched string length.
* @param strsrch search iterator data struct
* @return index to a substring within the text string that is being 
*         searched.
* @see #usearch_first
* @see #usearch_next
* @see #usearch_previous