/* ********************************************************************** * Copyright (C) 2001 IBM and others. All rights reserved. ********************************************************************** * Date Name Description * 06/28/2001 synwee Creation. ********************************************************************** */ #ifndef USEARCH_H #define USEARCH_H #include "unicode/utypes.h" #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 UCollator data struct, * see ucol.h. This ensures that language eccentricity can be * handled, e.g. for the German collator, characters ß and SS will be matched * if case is chosen to be ignored. * See the * "ICU Collation Design Document" for more information. *

* The algorithm implemented is a modified form of the Boyer Moore's search. * For more information see * * "Efficient Text Searching in Java", published in Java Report * in February, 1999, for further information on the algorithm. *

* There are 2 match options for selection:
* Let S' be the sub-string of a text string S between the offsets start and * end . *
* A pattern string P matches a text string S at the offsets * if *

 
 * 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. 
 * 
* Option 2. will be the default· *

* This search has APIs similar to that of other text iteration mechanisms * such as the break iterators in ubrk.h. 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 reset followed by a next or previous. * Though a direction change can occur without calling reset 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 *

* usearch.h provides APIs to specify the starting position * within the text string to be searched, e.g. usearch_setOffset, * usearch_preceding and usearch_following. 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: *

*

* 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. *

* 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. *

* 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 usearch_getCollator and using the APIs in ucol.h. * Lastly to update String Search to the new collator attributes, * usearch_reset() has to be called. *

* Restriction:
* 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. * *

* Example of use:
*


 * 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));
 *     }
 * }
 * 
* @since ICU 2.0 */ /** * 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. */ #define USEARCH_DONE -1 /** * Data structure for searching */ struct UStringSearch; /** * Data structure for searching */ typedef struct UStringSearch UStringSearch; 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; 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 usearch_close. * @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 BreakIterator, the match will * be rejected and another will be searched for. * If this parameter is NULL, 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. * @draft ICU 2.0 */ U_CAPI 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. * @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 BreakIterator, the match will * be rejected and another will be searched for. * If this parameter is NULL, 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. * @draft ICU 2.0 */ U_CAPI 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 usearch_open, it will be destroyed here. * @param searchiter data struct to clean up * @draft ICU 2.0 */ U_CAPI void U_EXPORT2 usearch_close(UStringSearch *strsrch); /* 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. * @draft ICU 2.0 */ U_CAPI 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), USEARCH_DONE is returned. * @param strsrch search iterator data struct * @see #USEARCH_DONE * @draft ICU 2.0 */ U_CAPI 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. * USEARCH_DEFAULT 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 * @draft ICU 2.0 */ U_CAPI 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 * @draft ICU 2.0 */ U_CAPI 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 * usearch_first, usearch_next, usearch_previous, * or usearch_last. * Just after construction, or after a searching method returns * USEARCH_DONE, this method will return USEARCH_DONE. *

* Use usearch_getMatchedLength 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 * @see #usearch_last * @see #USEARCH_DONE * @draft ICU 2.0 */ U_CAPI int32_t U_EXPORT2 usearch_getMatchedStart( const UStringSearch *strsrch); /** * Returns the length of text in the string which matches the search pattern. * This call returns a valid result only after a successful call to * usearch_first, usearch_next, usearch_previous, * or usearch_last. * Just after construction, or after a searching method returns * USEARCH_DONE, this method will return 0. * @param strsrch search iterator data struct * @return The length of the match in the string text, or 0 if there is no * match currently. * @see #usearch_first * @see #usearch_next * @see #usearch_previous * @see #usearch_last * @see #USEARCH_DONE * @draft ICU 2.0 */ U_CAPI int32_t U_EXPORT2 usearch_getMatchedLength( const UStringSearch *strsrch); /** * Returns the text that was matched by the most recent call to * usearch_first, usearch_next, usearch_previous, * or usearch_last. * If the iterator is not pointing at a valid match (e.g. just after * construction or after USEARCH_DONE has been returned, returns * an empty string. If result is not large enough to store the matched text, * result will be filled with the partial text and an U_BUFFER_OVERFLOW_ERROR * will be returned in status. result will be null-terminated whenever * possible. If the buffer fits the matched text exactly, a null-termination * is not possible, then a U_STRING_NOT_TERMINATED_ERROR set in status. * Pre-flighting can be either done with length = 0 or the API * usearch_getMatchLength. * @param strsrch search iterator data struct * @param result UChar buffer to store the matched string * @param resultCapacity length of the result buffer * @param status error returned if result is not large enough * @return exact length of the matched text, not counting the null-termination * @see #usearch_first * @see #usearch_next * @see #usearch_previous * @see #usearch_last * @see #USEARCH_DONE * @draft ICU 2.0 */ U_CAPI int32_t U_EXPORT2 usearch_getMatchedText(const UStringSearch *strsrch, UChar *result, int32_t resultCapacity, UErrorCode *status); /** * Set the BreakIterator that will be used to restrict the points at which * matches are detected. * @param strsrch search iterator data struct * @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 BreakIterator, the match will * be rejected and another will be searched for. * If this parameter is NULL, no break detection is * attempted. * @param status for errors if it occurs * @see #usearch_getBreakIterator * @draft ICU 2.0 */ U_CAPI void U_EXPORT2 usearch_setBreakIterator(UStringSearch *strsrch, UBreakIterator *breakiter, UErrorCode *status); /** * Returns the BreakIterator that is used to restrict the points at which * matches are detected. This will be the same object that was passed to the * constructor or to usearch_setBreakIterator. Note that * NULL * is a legal value; it means that break detection should not be attempted. * @param strsrch search iterator data struct * @return break iterator used * @see #usearch_setBreakIterator * @draft ICU 2.0 */ U_CAPI const UBreakIterator * U_EXPORT2 usearch_getBreakIterator( const UStringSearch *strsrch); /** * Set the string text to be searched. Text iteration will hence begin at the * start of the text string. This method is useful if you want to re-use an * iterator to search for the same pattern within a different body of text. * @param strsrch search iterator data struct * @param text new string to look for match * @param textlength length of the new string, -1 for null-termination * @param status for errors if it occurs. If text is NULL, or textlength is 0 * then an U_ILLEGAL_ARGUMENT_ERROR is returned with no change * done to strsrch. * @see #usearch_getText * @draft ICU 2.0 */ U_CAPI void U_EXPORT2 usearch_setText( UStringSearch *strsrch, const UChar *text, int32_t textlength, UErrorCode *status); /** * Return the string text to be searched. * @param strsrch search iterator data struct * @param length returned string text length * @return string text * @see #usearch_setText * @draft ICU 2.0 */ U_CAPI const UChar * U_EXPORT2 usearch_getText(const UStringSearch *strsrch, int32_t *length); /** * Gets the collator used for the language rules. *

* Deleting the returned UCollator before calling * usearch_close would cause the string search to fail. * usearch_close will delete the collator if this search owns it. * @param strsrch search iterator data struct * @return collator * @draft ICU 2.0 */ U_CAPI UCollator * U_EXPORT2 usearch_getCollator( const UStringSearch *strsrch); /** * Sets the collator used for the language rules. User retains the ownership * of this collator, thus the responsibility of deletion lies with the user. * This method causes internal data such as Boyer-Moore shift tables to * be recalculated, but the iterator's position is unchanged. * @param strsrch search iterator data struct * @param collator to be used * @param status for errors if it occurs * @draft ICU 2.0 */ U_CAPI void U_EXPORT2 usearch_setCollator( UStringSearch *strsrch, const UCollator *collator, UErrorCode *status); /** * Sets the pattern used for matching. * Internal data like the Boyer Moore table will be recalculated, but the * iterator's position is unchanged. * @param strsrch search iterator data struct * @param pattern string * @param patternlength pattern length, -1 for null-terminated string * @param status for errors if it occurs. If text is NULL, or textlength is 0 * then an U_ILLEGAL_ARGUMENT_ERROR is returned with no change * done to strsrch. * @draft ICU 2.0 */ U_CAPI void U_EXPORT2 usearch_setPattern( UStringSearch *strsrch, const UChar *pattern, int32_t patternlength, UErrorCode *status); /** * Gets the search pattern * @param strsrch search iterator data struct * @param length return length of the pattern, -1 indicates that the pattern * is null-terminated * @return pattern string * @draft ICU 2.0 */ U_CAPI const UChar * U_EXPORT2 usearch_getPattern( const UStringSearch *strsrch, int32_t *length); /* methods ------------------------------------------------------------- */ /** * Returns the first index at which the string text matches the search * pattern. * The iterator is adjusted so that its current index (as returned by * usearch_getOffset) is the match position if one was found. * If a match is not found, USEARCH_DONE will be returned and * the iterator will be adjusted to the index USEARCH_DONE. * @param strsrch search iterator data struct * @param status for errors if it occurs * @return The character index of the first match, or * USEARCH_DONE if there are no matches. * @see #usearch_getOffset * @see #USEARCH_DONE * @draft ICU 2.0 */ U_CAPI int32_t U_EXPORT2 usearch_first(UStringSearch *strsrch, UErrorCode *status); /** * Returns the first index greater than position at which the string * text * matches the search pattern. The iterator is adjusted so that its current * index (as returned by usearch_getOffset) is the match position if * one was found. * If a match is not found, USEARCH_DONE will be returned and * the iterator will be adjusted to the index USEARCH_DONE *

* Search positions that may render incorrect results are highlighted in the * header comments. If position is less than or greater than the text range * for searching, an U_INDEX_OUTOFBOUNDS_ERROR will be returned * @param strsrch search iterator data struct * @param position to start the search at * @param status for errors if it occurs * @return The character index of the first match following pos, * or USEARCH_DONE if there are no matches. * @see #usearch_getOffset * @see #USEARCH_DONE * @draft ICU 2.0 */ U_CAPI int32_t U_EXPORT2 usearch_following(UStringSearch *strsrch, int32_t position, UErrorCode *status); /** * Returns the last index in the target text at which it matches the search * pattern. The iterator is adjusted so that its current * index (as returned by usearch_getOffset) is the match position if * one was found. * If a match is not found, USEARCH_DONE will be returned and * the iterator will be adjusted to the index USEARCH_DONE. * @param strsrch search iterator data struct * @param status for errors if it occurs * @return The index of the first match, or USEARCH_DONE if there * are no matches. * @see #usearch_getOffset * @see #USEARCH_DONE * @draft ICU 2.0 */ U_CAPI int32_t U_EXPORT2 usearch_last(UStringSearch *strsrch, UErrorCode *status); /** * Returns the first index less than position at which the string text * matches the search pattern. The iterator is adjusted so that its current * index (as returned by usearch_getOffset) is the match position if * one was found. * If a match is not found, USEARCH_DONE will be returned and * the iterator will be adjusted to the index USEARCH_DONE *

* Search positions that may render incorrect results are highlighted in the * header comments. If position is less than or greater than the text range * for searching, an U_INDEX_OUTOFBOUNDS_ERROR will be returned * @param strsrch search iterator data struct * @param position index position the search is to begin at * @param status for errors if it occurs * @return The character index of the first match preceding pos, * or USEARCH_DONE if there are no matches. * @see #usearch_getOffset * @see #USEARCH_DONE * @draft ICU 2.0 */ U_CAPI int32_t U_EXPORT2 usearch_preceding(UStringSearch *strsrch, int32_t position, UErrorCode *status); /** * Returns the index of the next point at which the string text matches the * search pattern, starting from the current position. * The iterator is adjusted so that its current * index (as returned by usearch_getOffset) is the match position if * one was found. * If a match is not found, USEARCH_DONE will be returned and * the iterator will be adjusted to the index USEARCH_DONE * @param strsrch search iterator data struct * @param status for errors if it occurs * @return The index of the next match after the current position, or * USEARCH_DONE if there are no more matches. * @see #usearch_first * @see #usearch_getOffset * @see #USEARCH_DONE * @draft ICU 2.0 */ U_CAPI int32_t U_EXPORT2 usearch_next(UStringSearch *strsrch, UErrorCode *status); /** * Returns the index of the previous point at which the string text matches * the search pattern, starting at the current position. * The iterator is adjusted so that its current * index (as returned by usearch_getOffset) is the match position if * one was found. * If a match is not found, USEARCH_DONE will be returned and * the iterator will be adjusted to the index USEARCH_DONE * @param strsrch search iterator data struct * @param status for errors if it occurs * @return The index of the previous match before the current position, * or USEARCH_DONE if there are no more matches. * @see #usearch_last * @see #usearch_getOffset * @see #USEARCH_DONE * @draft ICU 2.0 */ U_CAPI int32_t U_EXPORT2 usearch_previous(UStringSearch *strsrch, UErrorCode *status); /** * Reset the iteration. * Search will begin at the start of the text string if a forward iteration * is initiated before a backwards iteration. Otherwise if a backwards * iteration is initiated before a forwards iteration, the search will begin * at the end of the text string. * @param strsrch search iterator data struct * @see #usearch_first * @draft ICU 2.0 */ U_CAPI void U_EXPORT2 usearch_reset(UStringSearch *strsrch); #endif