CollData object by calling CollData::open.
* Then you construct a BoyerMooreSearch object from the CollData object, the pattern
* string and the target string. Then you call the search method. Here's a code sample:
*
*
* void boyerMooreExample(UCollator *collator, UnicodeString *pattern, UnicodeString *target)
* {
* UErrorCode status = U_ZERO_ERROR;
* CollData *collData = CollData::open(collator, status);
*
* if (U_FAILURE(status)) {
* // could not create a CollData object
* return;
* }
*
* BoyerMooreSearch *search = new BoyerMooreSearch(collData, *patternString, target, status);
*
* if (U_FAILURE(status)) {
* // could not create a BoyerMooreSearch object
* CollData::close(collData);
* return;
* }
*
* int32_t offset = 0, start = -1, end = -1;
*
* // Find all matches
* while (search->search(offset, start, end)) {
* // process the match between start and end
* ...
* // advance past the match
* offset = end;
* }
*
* // at this point, if offset == 0, there were no matches
* if (offset == 0) {
* // handle the case of no matches
* }
*
* delete search;
* CollData::close(collData);
*
* // CollData objects are cached, so the call to
* // CollData::close doesn't delete the object.
* // Call this if you don't need the object any more.
* CollData::flushCollDataCache();
* }
*
*
* NOTE: This is a technology preview. The final version of this API may not bear any resenblence to this API.
*
* Knows linitations:
* 1) Backwards searching has not been implemented.
*
* 2) For Han and Hangul characters, this code ignores any Collation tailorings. In general,
* this isn't a problem, but in Korean locals, at strength 1, Hangul characters are tailored
* to be equal to Han characters with the same pronounciation. Because this code ignroes
* tailorings, searching for a Hangul character will not find a Han character and visa-versa.
*
* 3) In some cases, searching for a pattern that needs to be normalized and ends
* in a discontiguous contraction may fail. The only known cases of this are with
* the Tibetan script. For example searching for the pattern
* "\u0F7F\u0F80\u0F81\u0F82\u0F83\u0F84\u0F85" will fail. (This case is artificial. We've
* been unable to find a pratical, real-world example of this failure.)
*
* @internal ICU 4.0.1 technology preview
*
* @see CollData
*/
class U_I18N_API BoyerMooreSearch : public UObject
{
public:
/**
* Construct a BoyerMooreSearch object.
*
* @param theData - A CollData object holding the Collator-sensitive data
* @param patternString - the string for which to search
* @param targetString - the string in which to search or NULL if youu will
* set it later by calling setTargetString.
* @param status - will be set if any errors occur.
*
* Note: if on return, status is set to an error code,
* the only safe thing to do with this object is to call
* the destructor.
*
* @internal ICU 4.0.1 technology preview
*/
BoyerMooreSearch(CollData *theData, const UnicodeString &patternString, const UnicodeString *targetString, UErrorCode &status);
/**
* The desstructor
*
* @internal ICU 4.0.1 technology preview
*/
~BoyerMooreSearch();
/**
* Test the pattern to see if it generates any CEs.
*
* @return TRUE if the pattern string did not generate any CEs
*
* @internal ICU 4.0.1 technology preview
*/
UBool empty();
/**
* Search for the pattern string in the target string.
*
* @param offset - the offset in the target string at which to begin the search
* @param start - will be set to the starting offset of the match, or -1 if there's no match
* @param end - will be set to the ending offset of the match, or -1 if there's no match
*
* @return TRUE if the match succeeds, FALSE otherwise.
*
* @internal ICU 4.0.1 technology preview
*/
UBool search(int32_t offset, int32_t &start, int32_t &end);
/**
* Set the target string for the match.
*
* @param targetString - the new target string
* @param status - will be set if any errors occur.
*
* @internal ICU 4.0.1 technology preview
*/
void setTargetString(const UnicodeString *targetString, UErrorCode &status);
// **** no longer need these? ****
/**
* Return the CollData object used for searching
*
* @return the CollData object used for searching
*
* @internal ICU 4.0.1 technology preview
*/
CollData *getData();
/**
* Return the CEs generated by the pattern string.
*
* @return a CEList object holding the CEs generated by the pattern string.
*
* @internal ICU 4.0.1 technology preview
*/
CEList *getPatternCEs();
/**
* Return the BadCharacterTable object computed for the pattern string.
*
* @return the BadCharacterTable object.
*
* @internal ICU 4.0.1 technology preview
*/
BadCharacterTable *getBadCharacterTable();
/**
* Return the GoodSuffixTable object computed for the pattern string.
*
* @return the GoodSuffixTable object computed for the pattern string.
*
* @internal ICU 4.0.1 technology preview
*/
GoodSuffixTable *getGoodSuffixTable();
/**
* UObject glue...
* @internal ICU 4.0.1 technology preview
*/
virtual UClassID getDynamicClassID() const;
/**
* UObject glue...
* @internal ICU 4.0.1 technology preview
*/
static UClassID getStaticClassID();
private:
CollData *data;
CEList *patCEs;
BadCharacterTable *badCharacterTable;
GoodSuffixTable *goodSuffixTable;
UnicodeString pattern;
Target *target;
};
#endif /* U_HIDE_INTERNAL_API */
U_NAMESPACE_END
#endif // #if !UCONFIG_NO_COLLATION
#endif // #ifndef B_M_SEARCH_H