mirror of
https://github.com/unicode-org/icu.git
synced 2025-04-16 18:25:57 +00:00
ICU-1030
New implementation for Unicode Boyer Moore string search. X-SVN-Rev: 5587
This commit is contained in:
Syn Wee Quek
parent
8e4ca45744
commit
75adf07067
13 changed files with 5595 additions and 9 deletions
|
|
@ -72,7 +72,8 @@ unifltlg.o unirange.o uniset.o unitohex.o unum.o \
|
|||
dbbi.o dbbi_tbl.o rbbi.o rbbi_tbl.o brkdict.o nultrans.o jamohang.o hangjamo.o \
|
||||
remtrans.o utrans.o \
|
||||
titletrn.o tolowtrn.o toupptrn.o xformtrn.o name2uni.o uni2name.o nortrans.o \
|
||||
unifilt.o quant.o strmatch.o transreg.o
|
||||
unifilt.o quant.o strmatch.o transreg.o usearch.o search.o stsearch.o
|
||||
|
||||
|
||||
STATIC_OBJECTS = $(OBJECTS:.o=.$(STATIC_O))
|
||||
|
||||
|
|
|
|||
|
|
@ -234,6 +234,10 @@ SOURCE=.\remtrans.cpp
|
|||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
SOURCE=.\search.cpp
|
||||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
SOURCE=.\simpletz.cpp
|
||||
# End Source File
|
||||
# Begin Source File
|
||||
|
|
@ -250,6 +254,10 @@ SOURCE=.\strmatch.cpp
|
|||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
SOURCE=.\stsearch.cpp
|
||||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
SOURCE=.\tblcoll.cpp
|
||||
# End Source File
|
||||
# Begin Source File
|
||||
|
|
@ -350,6 +358,10 @@ SOURCE=.\unum.cpp
|
|||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
SOURCE=.\usearch.cpp
|
||||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
SOURCE=.\utrans.cpp
|
||||
# End Source File
|
||||
# Begin Source File
|
||||
|
|
@ -1119,6 +1131,25 @@ SOURCE=.\unicode\remtrans.h
|
|||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
SOURCE=.\unicode\search.h
|
||||
|
||||
!IF "$(CFG)" == "i18n - Win32 Release"
|
||||
|
||||
!ELSEIF "$(CFG)" == "i18n - Win32 Debug"
|
||||
|
||||
# Begin Custom Build
|
||||
InputPath=.\unicode\search.h
|
||||
|
||||
"..\..\include\unicode\search.h" : $(SOURCE) "$(INTDIR)" "$(OUTDIR)"
|
||||
copy unicode\search.h ..\..\include\unicode
|
||||
|
||||
# End Custom Build
|
||||
|
||||
!ENDIF
|
||||
|
||||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
SOURCE=.\unicode\simpletz.h
|
||||
|
||||
!IF "$(CFG)" == "i18n - Win32 Release"
|
||||
|
|
@ -1204,6 +1235,25 @@ SOURCE=.\strmatch.h
|
|||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
SOURCE=.\unicode\stsearch.h
|
||||
|
||||
!IF "$(CFG)" == "i18n - Win32 Release"
|
||||
|
||||
!ELSEIF "$(CFG)" == "i18n - Win32 Debug"
|
||||
|
||||
# Begin Custom Build
|
||||
InputPath=.\unicode\stsearch.h
|
||||
|
||||
"..\..\include\unicode\stsearch.h" : $(SOURCE) "$(INTDIR)" "$(OUTDIR)"
|
||||
copy unicode\stsearch.h ..\..\include\unicode
|
||||
|
||||
# End Custom Build
|
||||
|
||||
!ENDIF
|
||||
|
||||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
SOURCE=.\unicode\tblcoll.h
|
||||
|
||||
!IF "$(CFG)" == "i18n - Win32 Release"
|
||||
|
|
@ -1676,6 +1726,29 @@ InputPath=.\unicode\unum.h
|
|||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
SOURCE=.\unicode\usearch.h
|
||||
|
||||
!IF "$(CFG)" == "i18n - Win32 Release"
|
||||
|
||||
!ELSEIF "$(CFG)" == "i18n - Win32 Debug"
|
||||
|
||||
# Begin Custom Build
|
||||
InputPath=.\unicode\usearch.h
|
||||
|
||||
"..\..\include\unicode\usearch.h" : $(SOURCE) "$(INTDIR)" "$(OUTDIR)"
|
||||
copy unicode\usearch.h ..\..\include\unicode
|
||||
|
||||
# End Custom Build
|
||||
|
||||
!ENDIF
|
||||
|
||||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
SOURCE=.\usrchimp.h
|
||||
# End Source File
|
||||
# Begin Source File
|
||||
|
||||
SOURCE=.\unicode\utrans.h
|
||||
|
||||
!IF "$(CFG)" == "i18n - Win32 Release"
|
||||
|
|
|
|||
357
icu4c/source/i18n/search.cpp
Normal file
357
icu4c/source/i18n/search.cpp
Normal file
|
|
@ -0,0 +1,357 @@
|
|||
/*
|
||||
**********************************************************************
|
||||
* Copyright (C) 2001 IBM and others. All rights reserved.
|
||||
**********************************************************************
|
||||
* Date Name Description
|
||||
* 03/22/2000 helena Creation.
|
||||
**********************************************************************
|
||||
*/
|
||||
|
||||
#include "unicode/brkiter.h"
|
||||
#include "unicode/schriter.h"
|
||||
#include "unicode/search.h"
|
||||
#include "usrchimp.h"
|
||||
#include "cmemory.h"
|
||||
|
||||
// public constructors and destructors -----------------------------------
|
||||
|
||||
SearchIterator::SearchIterator(const SearchIterator &other)
|
||||
{
|
||||
if (other != *this) {
|
||||
m_breakiterator_ = other.m_breakiterator_;
|
||||
m_text_ = other.m_text_;
|
||||
m_search_ = (USearch *)uprv_malloc(sizeof(USearch));
|
||||
m_search_->breakIter = other.m_search_->breakIter;
|
||||
m_search_->isCanonicalMatch = other.m_search_->isCanonicalMatch;
|
||||
m_search_->isOverlap = other.m_search_->isOverlap;
|
||||
m_search_->matchedIndex = other.m_search_->matchedIndex;
|
||||
m_search_->matchedLength = other.m_search_->matchedLength;
|
||||
m_search_->text = other.m_search_->text;
|
||||
m_search_->textLength = other.m_search_->textLength;
|
||||
}
|
||||
}
|
||||
|
||||
SearchIterator::~SearchIterator()
|
||||
{
|
||||
if (m_search_ != NULL) {
|
||||
uprv_free(m_search_);
|
||||
}
|
||||
}
|
||||
|
||||
// public get and set methods ----------------------------------------
|
||||
|
||||
void SearchIterator::setAttribute(USearchAttribute attribute,
|
||||
USearchAttributeValue value,
|
||||
UErrorCode &status)
|
||||
{
|
||||
if (U_SUCCESS(status)) {
|
||||
switch (attribute)
|
||||
{
|
||||
case USEARCH_OVERLAP :
|
||||
m_search_->isOverlap = (value == USEARCH_ON ? TRUE : FALSE);
|
||||
break;
|
||||
case USEARCH_CANONICAL_MATCH :
|
||||
m_search_->isCanonicalMatch = (value == USEARCH_ON ? TRUE : FALSE);
|
||||
break;
|
||||
default:
|
||||
status = U_ILLEGAL_ARGUMENT_ERROR;
|
||||
}
|
||||
}
|
||||
if (value == USEARCH_ATTRIBUTE_VALUE_COUNT) {
|
||||
status = U_ILLEGAL_ARGUMENT_ERROR;
|
||||
}
|
||||
}
|
||||
|
||||
USearchAttributeValue SearchIterator::getAttribute(
|
||||
USearchAttribute attribute) const
|
||||
{
|
||||
switch (attribute) {
|
||||
case USEARCH_ATTRIBUTE_COUNT :
|
||||
return USEARCH_DEFAULT;
|
||||
case USEARCH_OVERLAP :
|
||||
return (m_search_->isOverlap == TRUE ? USEARCH_ON : USEARCH_OFF);
|
||||
case USEARCH_CANONICAL_MATCH :
|
||||
return (m_search_->isCanonicalMatch == TRUE ? USEARCH_ON :
|
||||
USEARCH_OFF);
|
||||
}
|
||||
return USEARCH_DEFAULT;
|
||||
}
|
||||
|
||||
UTextOffset SearchIterator::getMatchedStart() const
|
||||
{
|
||||
return m_search_->matchedIndex;
|
||||
}
|
||||
|
||||
int32_t SearchIterator::getMatchedLength() const
|
||||
{
|
||||
return m_search_->matchedLength;
|
||||
}
|
||||
|
||||
void SearchIterator::getMatchedText(UnicodeString &result) const
|
||||
{
|
||||
UTextOffset matchedindex = m_search_->matchedIndex;
|
||||
int32_t matchedlength = m_search_->matchedLength;
|
||||
if (matchedindex != USEARCH_DONE && matchedlength != 0) {
|
||||
result.setTo(m_search_->text + matchedindex, matchedlength);
|
||||
}
|
||||
else {
|
||||
result.remove();
|
||||
}
|
||||
}
|
||||
|
||||
void SearchIterator::setBreakIterator(BreakIterator *breakiter,
|
||||
UErrorCode &status)
|
||||
{
|
||||
if (U_SUCCESS(status)) {
|
||||
m_search_->breakIter = NULL;
|
||||
// the c++ breakiterator may not make use of ubreakiterator.
|
||||
// so we'll have to keep track of it ourselves.
|
||||
m_breakiterator_ = breakiter;
|
||||
}
|
||||
}
|
||||
|
||||
const BreakIterator * SearchIterator::getBreakIterator(void) const
|
||||
{
|
||||
return m_breakiterator_;
|
||||
}
|
||||
|
||||
void SearchIterator::setText(const UnicodeString &text, UErrorCode &status)
|
||||
{
|
||||
if (U_SUCCESS(status)) {
|
||||
if (text.length() == 0) {
|
||||
status = U_ILLEGAL_ARGUMENT_ERROR;
|
||||
}
|
||||
else {
|
||||
m_text_ = text;
|
||||
m_search_->text = m_text_.fArray;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
void SearchIterator::setText(CharacterIterator &text, UErrorCode &status)
|
||||
{
|
||||
if (U_SUCCESS(status)) {
|
||||
text.getText(m_text_);
|
||||
setText(m_text_, status);
|
||||
}
|
||||
}
|
||||
|
||||
const UnicodeString & SearchIterator::getText(void) const
|
||||
{
|
||||
return m_text_;
|
||||
}
|
||||
|
||||
// operator overloading ----------------------------------------------
|
||||
|
||||
UBool SearchIterator::operator==(const SearchIterator &that) const
|
||||
{
|
||||
if (this == &that) {
|
||||
return TRUE;
|
||||
}
|
||||
return (m_breakiterator_ == that.m_breakiterator_ &&
|
||||
m_search_->isCanonicalMatch == that.m_search_->isCanonicalMatch &&
|
||||
m_search_->isOverlap == that.m_search_->isOverlap &&
|
||||
m_search_->matchedIndex == that.m_search_->matchedIndex &&
|
||||
m_search_->matchedLength == that.m_search_->matchedLength &&
|
||||
m_search_->textLength == that.m_search_->textLength &&
|
||||
getOffset() == that.getOffset() &&
|
||||
(uprv_memcmp(m_search_->text, that.m_search_->text,
|
||||
m_search_->textLength * sizeof(UChar)) == 0));
|
||||
}
|
||||
|
||||
// public methods ----------------------------------------------------
|
||||
|
||||
UTextOffset SearchIterator::first(UErrorCode &status)
|
||||
{
|
||||
setOffset(0, status);
|
||||
return handleNext(0, status);
|
||||
}
|
||||
|
||||
UTextOffset SearchIterator::following(UTextOffset position,
|
||||
UErrorCode &status)
|
||||
{
|
||||
setOffset(position, status);
|
||||
return handleNext(position, status);
|
||||
}
|
||||
|
||||
UTextOffset SearchIterator::last(UErrorCode &status)
|
||||
{
|
||||
setOffset(m_search_->textLength, status);
|
||||
return handlePrev(m_search_->textLength, status);
|
||||
}
|
||||
|
||||
UTextOffset SearchIterator::preceding(UTextOffset position,
|
||||
UErrorCode &status)
|
||||
{
|
||||
setOffset(position, status);
|
||||
return handlePrev(position, status);
|
||||
}
|
||||
|
||||
UTextOffset SearchIterator::next(UErrorCode &status)
|
||||
{
|
||||
if (U_SUCCESS(status)) {
|
||||
UTextOffset offset = getOffset();
|
||||
UTextOffset matchindex = m_search_->matchedIndex;
|
||||
int32_t matchlength = m_search_->matchedLength;
|
||||
m_search_->reset = FALSE;
|
||||
if (m_search_->isForwardSearching == TRUE) {
|
||||
int32_t textlength = m_search_->textLength;
|
||||
if (offset == textlength || matchindex == textlength ||
|
||||
(matchindex != USEARCH_DONE &&
|
||||
matchindex + matchlength >= textlength)) {
|
||||
// not enough characters to match
|
||||
setMatchNotFound();
|
||||
return USEARCH_DONE;
|
||||
}
|
||||
}
|
||||
else {
|
||||
// switching direction.
|
||||
// if matchedIndex == USEARCH_DONE, it means that either a
|
||||
// setOffset has been called or that previous ran off the text
|
||||
// string. the iterator would have been set to offset 0 if a
|
||||
// match is not found.
|
||||
m_search_->isForwardSearching = TRUE;
|
||||
if (m_search_->matchedIndex != USEARCH_DONE) {
|
||||
// there's no need to set the collation element iterator
|
||||
// the next call to next will set the offset.
|
||||
return matchindex;
|
||||
}
|
||||
}
|
||||
|
||||
if (matchindex != USEARCH_DONE) {
|
||||
return handleNext(matchindex + matchlength, status);
|
||||
}
|
||||
return handleNext(offset, status);
|
||||
}
|
||||
return USEARCH_DONE;
|
||||
}
|
||||
|
||||
UTextOffset SearchIterator::previous(UErrorCode &status)
|
||||
{
|
||||
if (U_SUCCESS(status)) {
|
||||
UTextOffset offset;
|
||||
if (m_search_->reset) {
|
||||
offset = m_search_->textLength;
|
||||
m_search_->isForwardSearching = FALSE;
|
||||
m_search_->reset = FALSE;
|
||||
}
|
||||
else {
|
||||
offset = getOffset();
|
||||
}
|
||||
|
||||
UTextOffset matchindex = m_search_->matchedIndex;
|
||||
if (m_search_->isForwardSearching == TRUE) {
|
||||
// switching direction.
|
||||
// if matchedIndex == USEARCH_DONE, it means that either a
|
||||
// setOffset has been called or that next ran off the text
|
||||
// string. the iterator would have been set to offset textLength if
|
||||
// a match is not found.
|
||||
m_search_->isForwardSearching = FALSE;
|
||||
if (matchindex != USEARCH_DONE) {
|
||||
return matchindex;
|
||||
}
|
||||
}
|
||||
else {
|
||||
if (offset == 0 || matchindex == 0) {
|
||||
// not enough characters to match
|
||||
setMatchNotFound();
|
||||
return USEARCH_DONE;
|
||||
}
|
||||
}
|
||||
|
||||
if (matchindex != USEARCH_DONE) {
|
||||
return handlePrev(matchindex, status);
|
||||
}
|
||||
return handlePrev(offset, status);
|
||||
}
|
||||
return USEARCH_DONE;
|
||||
}
|
||||
|
||||
void SearchIterator::reset()
|
||||
{
|
||||
setMatchNotFound();
|
||||
m_search_->isOverlap = FALSE;
|
||||
m_search_->isCanonicalMatch = FALSE;
|
||||
m_search_->isForwardSearching = TRUE;
|
||||
m_search_->reset = TRUE;
|
||||
}
|
||||
|
||||
// protected constructors and destructors -----------------------------
|
||||
|
||||
SearchIterator::SearchIterator() : m_breakiterator_(NULL)
|
||||
{
|
||||
m_search_ = (USearch *)uprv_malloc(sizeof(USearch));
|
||||
m_search_->breakIter = NULL;
|
||||
m_search_->isOverlap = FALSE;
|
||||
m_search_->isCanonicalMatch = FALSE;
|
||||
m_search_->isForwardSearching = TRUE;
|
||||
m_search_->reset = TRUE;
|
||||
m_search_->matchedIndex = USEARCH_DONE;
|
||||
m_search_->matchedLength = 0;
|
||||
m_search_->text = NULL;
|
||||
m_search_->textLength = 0;
|
||||
}
|
||||
|
||||
SearchIterator::SearchIterator(const UnicodeString &text,
|
||||
BreakIterator *breakiter) :
|
||||
m_breakiterator_(breakiter),
|
||||
m_text_(text)
|
||||
{
|
||||
m_search_ = (USearch *)uprv_malloc(sizeof(USearch));
|
||||
m_search_->breakIter = NULL;
|
||||
m_search_->isOverlap = FALSE;
|
||||
m_search_->isCanonicalMatch = FALSE;
|
||||
m_search_->isForwardSearching = TRUE;
|
||||
m_search_->reset = TRUE;
|
||||
m_search_->matchedIndex = USEARCH_DONE;
|
||||
m_search_->matchedLength = 0;
|
||||
m_search_->text = m_text_.fArray;
|
||||
m_search_->textLength = text.length();
|
||||
}
|
||||
|
||||
SearchIterator::SearchIterator(CharacterIterator &text,
|
||||
BreakIterator *breakiter) :
|
||||
m_breakiterator_(breakiter)
|
||||
{
|
||||
m_search_ = (USearch *)uprv_malloc(sizeof(USearch));
|
||||
m_search_->breakIter = NULL;
|
||||
m_search_->isOverlap = FALSE;
|
||||
m_search_->isCanonicalMatch = FALSE;
|
||||
m_search_->isForwardSearching = TRUE;
|
||||
m_search_->reset = TRUE;
|
||||
m_search_->matchedIndex = USEARCH_DONE;
|
||||
m_search_->matchedLength = 0;
|
||||
text.getText(m_text_);
|
||||
m_search_->text = m_text_.fArray;
|
||||
m_search_->textLength = m_text_.length();
|
||||
m_breakiterator_ = breakiter;
|
||||
}
|
||||
|
||||
// protected methods ------------------------------------------------------
|
||||
|
||||
void SearchIterator::setMatchLength(int32_t length)
|
||||
{
|
||||
m_search_->matchedLength = length;
|
||||
}
|
||||
|
||||
void SearchIterator::setMatchStart(UTextOffset position)
|
||||
{
|
||||
m_search_->matchedIndex = position;
|
||||
}
|
||||
|
||||
void SearchIterator::setMatchNotFound()
|
||||
{
|
||||
setMatchStart(USEARCH_DONE);
|
||||
setMatchLength(0);
|
||||
UErrorCode status = U_ZERO_ERROR;
|
||||
// by default no errors should be returned here since offsets are within
|
||||
// range.
|
||||
if (m_search_->isForwardSearching) {
|
||||
setOffset(m_search_->textLength, status);
|
||||
}
|
||||
else {
|
||||
setOffset(0, status);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
387
icu4c/source/i18n/stsearch.cpp
Normal file
387
icu4c/source/i18n/stsearch.cpp
Normal file
|
|
@ -0,0 +1,387 @@
|
|||
/*
|
||||
**********************************************************************
|
||||
* Copyright (C) 2001 IBM and others. All rights reserved.
|
||||
**********************************************************************
|
||||
* Date Name Description
|
||||
* 03/22/2000 helena Creation.
|
||||
**********************************************************************
|
||||
*/
|
||||
|
||||
#include "unicode/stsearch.h"
|
||||
#include "cmemory.h"
|
||||
#include "usrchimp.h"
|
||||
|
||||
// public constructors and destructors -----------------------------------
|
||||
|
||||
StringSearch::StringSearch(const UnicodeString &pattern,
|
||||
const UnicodeString &text,
|
||||
const Locale &locale,
|
||||
BreakIterator *breakiter,
|
||||
UErrorCode &status) :
|
||||
SearchIterator(text, breakiter),
|
||||
m_collator_(),
|
||||
m_pattern_(pattern)
|
||||
{
|
||||
m_strsrch_ = usearch_open(m_pattern_.fArray, m_pattern_.fLength,
|
||||
m_text_.fArray, m_text_.fLength,
|
||||
locale.getName(), NULL, &status);
|
||||
uprv_free(m_search_);
|
||||
m_search_ = NULL;
|
||||
|
||||
if (U_SUCCESS(status)) {
|
||||
int32_t length;
|
||||
const UChar *rules = ucol_getRules(m_strsrch_->collator, &length);
|
||||
m_collation_rules_.setTo(rules, length);
|
||||
m_collator_.setUCollator((UCollator *)m_strsrch_->collator,
|
||||
&m_collation_rules_);
|
||||
// m_search_ has been created by the base SearchIterator class
|
||||
m_search_ = m_strsrch_->search;
|
||||
}
|
||||
}
|
||||
|
||||
StringSearch::StringSearch(const UnicodeString &pattern,
|
||||
const UnicodeString &text,
|
||||
RuleBasedCollator *coll,
|
||||
BreakIterator *breakiter,
|
||||
UErrorCode &status) :
|
||||
SearchIterator(text, breakiter),
|
||||
m_collator_(),
|
||||
m_pattern_(pattern)
|
||||
{
|
||||
if (coll == NULL) {
|
||||
status = U_ILLEGAL_ARGUMENT_ERROR;
|
||||
m_strsrch_ = NULL;
|
||||
return;
|
||||
}
|
||||
m_strsrch_ = usearch_openFromCollator(m_pattern_.fArray,
|
||||
m_pattern_.fLength, m_text_.fArray,
|
||||
m_text_.fLength, coll->ucollator,
|
||||
NULL, &status);
|
||||
uprv_free(m_search_);
|
||||
m_search_ = NULL;
|
||||
|
||||
if (U_SUCCESS(status)) {
|
||||
int32_t length;
|
||||
const UChar *rules = ucol_getRules(m_strsrch_->collator, &length);
|
||||
m_collation_rules_.setTo(rules, length);
|
||||
m_collator_.setUCollator((UCollator *)m_strsrch_->collator,
|
||||
&m_collation_rules_);
|
||||
// m_search_ has been created by the base SearchIterator class
|
||||
m_search_ = m_strsrch_->search;
|
||||
}
|
||||
}
|
||||
|
||||
StringSearch::StringSearch(const UnicodeString &pattern,
|
||||
CharacterIterator &text,
|
||||
const Locale &locale,
|
||||
BreakIterator *breakiter,
|
||||
UErrorCode &status) :
|
||||
SearchIterator(text, breakiter),
|
||||
m_collator_(),
|
||||
m_pattern_(pattern)
|
||||
{
|
||||
m_strsrch_ = usearch_open(m_pattern_.fArray, m_pattern_.fLength,
|
||||
m_text_.fArray, m_text_.fLength,
|
||||
locale.getName(), NULL, &status);
|
||||
uprv_free(m_search_);
|
||||
m_search_ = NULL;
|
||||
|
||||
if (U_SUCCESS(status)) {
|
||||
int32_t length;
|
||||
const UChar *rules = ucol_getRules(m_strsrch_->collator, &length);
|
||||
m_collation_rules_.setTo(rules, length);
|
||||
m_collator_.setUCollator((UCollator *)m_strsrch_->collator,
|
||||
&m_collation_rules_);
|
||||
// m_search_ has been created by the base SearchIterator class
|
||||
m_search_ = m_strsrch_->search;
|
||||
}
|
||||
}
|
||||
|
||||
StringSearch::StringSearch(const UnicodeString &pattern,
|
||||
CharacterIterator &text,
|
||||
RuleBasedCollator *coll,
|
||||
BreakIterator *breakiter,
|
||||
UErrorCode &status) :
|
||||
SearchIterator(text, breakiter),
|
||||
m_collator_(),
|
||||
m_pattern_(pattern)
|
||||
{
|
||||
if (coll == NULL) {
|
||||
status = U_ILLEGAL_ARGUMENT_ERROR;
|
||||
m_strsrch_ = NULL;
|
||||
return;
|
||||
}
|
||||
m_strsrch_ = usearch_openFromCollator(m_pattern_.fArray,
|
||||
m_pattern_.fLength, m_text_.fArray,
|
||||
m_text_.fLength, coll->ucollator,
|
||||
NULL, &status);
|
||||
uprv_free(m_search_);
|
||||
m_search_ = NULL;
|
||||
|
||||
if (U_SUCCESS(status)) {
|
||||
int32_t length;
|
||||
const UChar *rules = ucol_getRules(m_strsrch_->collator, &length);
|
||||
m_collation_rules_.setTo(rules, length);
|
||||
m_collator_.setUCollator((UCollator *)m_strsrch_->collator,
|
||||
&m_collation_rules_);
|
||||
// m_search_ has been created by the base SearchIterator class
|
||||
m_search_ = m_strsrch_->search;
|
||||
}
|
||||
}
|
||||
|
||||
StringSearch::StringSearch(const StringSearch &that) :
|
||||
SearchIterator(that.m_text_, that.m_breakiterator_),
|
||||
m_collator_(),
|
||||
m_pattern_(that.m_pattern_)
|
||||
{
|
||||
UErrorCode status = U_ZERO_ERROR;
|
||||
if (that.m_strsrch_ == NULL) {
|
||||
m_strsrch_ = NULL;
|
||||
status = U_ILLEGAL_ARGUMENT_ERROR;
|
||||
}
|
||||
else {
|
||||
m_strsrch_ = usearch_openFromCollator(m_pattern_.fArray,
|
||||
m_pattern_.fLength,
|
||||
m_text_.fArray, m_text_.fLength,
|
||||
that.m_strsrch_->collator,
|
||||
NULL, &status);
|
||||
}
|
||||
uprv_free(m_search_);
|
||||
m_search_ = NULL;
|
||||
|
||||
if (U_SUCCESS(status)) {
|
||||
int32_t length;
|
||||
const UChar *rules = ucol_getRules(m_strsrch_->collator, &length);
|
||||
m_collation_rules_.setTo(rules, length);
|
||||
m_collator_.setUCollator((UCollator *)m_strsrch_->collator,
|
||||
&m_collation_rules_);
|
||||
// m_search_ has been created by the base SearchIterator class
|
||||
m_search_ = m_strsrch_->search;
|
||||
m_breakiterator_ = that.m_breakiterator_;
|
||||
}
|
||||
}
|
||||
|
||||
StringSearch::~StringSearch()
|
||||
{
|
||||
usearch_close(m_strsrch_);
|
||||
m_search_ = NULL;
|
||||
}
|
||||
|
||||
// operator overloading ---------------------------------------------
|
||||
StringSearch & StringSearch::operator=(const StringSearch &that)
|
||||
{
|
||||
if ((*this) != that) {
|
||||
UErrorCode status = U_ZERO_ERROR;
|
||||
m_text_ = that.m_text_;
|
||||
m_breakiterator_ = that.m_breakiterator_;
|
||||
m_pattern_ = that.m_pattern_;
|
||||
// all m_search_ in the parent class is linked up with m_strsrch_
|
||||
usearch_close(m_strsrch_);
|
||||
m_strsrch_ = usearch_openFromCollator(m_pattern_.fArray,
|
||||
m_pattern_.fLength,
|
||||
m_text_.fArray,
|
||||
m_text_.fLength,
|
||||
that.m_strsrch_->collator,
|
||||
NULL, &status);
|
||||
int32_t length;
|
||||
const UChar *rules = ucol_getRules(m_strsrch_->collator, &length);
|
||||
m_collation_rules_.setTo(rules, length);
|
||||
m_collator_.setUCollator((UCollator *)m_strsrch_->collator,
|
||||
&m_collation_rules_);
|
||||
m_search_ = m_strsrch_->search;
|
||||
}
|
||||
return *this;
|
||||
}
|
||||
|
||||
UBool StringSearch::operator==(const SearchIterator &that) const
|
||||
{
|
||||
if (this == &that) {
|
||||
return TRUE;
|
||||
}
|
||||
if (SearchIterator::operator ==(that)) {
|
||||
StringSearch &thatsrch = (StringSearch &)that;
|
||||
return (this->m_pattern_ == thatsrch.m_pattern_ &&
|
||||
this->m_strsrch_->collator == thatsrch.m_strsrch_->collator);
|
||||
}
|
||||
return FALSE;
|
||||
}
|
||||
|
||||
// public get and set methods ----------------------------------------
|
||||
|
||||
void StringSearch::setOffset(UTextOffset position, UErrorCode &status)
|
||||
{
|
||||
usearch_setOffset(m_strsrch_, position, &status);
|
||||
}
|
||||
|
||||
UTextOffset StringSearch::getOffset(void) const
|
||||
{
|
||||
return usearch_getOffset(m_strsrch_);
|
||||
}
|
||||
|
||||
void StringSearch::setText(const UnicodeString &text, UErrorCode &status)
|
||||
{
|
||||
m_text_ = text;
|
||||
usearch_setText(m_strsrch_, text.fArray, text.fLength, &status);
|
||||
}
|
||||
|
||||
void StringSearch::setText(CharacterIterator &text, UErrorCode &status)
|
||||
{
|
||||
text.getText(m_text_);
|
||||
usearch_setText(m_strsrch_, m_text_.fArray, m_text_.fLength, &status);
|
||||
}
|
||||
|
||||
RuleBasedCollator * StringSearch::getCollator() const
|
||||
{
|
||||
return (RuleBasedCollator *)&m_collator_;
|
||||
}
|
||||
|
||||
void StringSearch::setCollator(RuleBasedCollator *coll, UErrorCode &status)
|
||||
{
|
||||
usearch_setCollator(m_strsrch_, coll->getUCollator(), &status);
|
||||
m_collation_rules_.setTo(coll->getRules());
|
||||
m_collator_.setUCollator((UCollator *)m_strsrch_->collator,
|
||||
&m_collation_rules_);
|
||||
}
|
||||
|
||||
void StringSearch::setPattern(const UnicodeString &pattern,
|
||||
UErrorCode &status)
|
||||
{
|
||||
m_pattern_ = pattern;
|
||||
usearch_setPattern(m_strsrch_, m_pattern_.fArray, m_pattern_.fLength,
|
||||
&status);
|
||||
}
|
||||
|
||||
const UnicodeString & StringSearch::getPattern() const
|
||||
{
|
||||
return m_pattern_;
|
||||
}
|
||||
|
||||
// public methods ----------------------------------------------------
|
||||
|
||||
void StringSearch::reset()
|
||||
{
|
||||
usearch_reset(m_strsrch_);
|
||||
}
|
||||
|
||||
SearchIterator * StringSearch::safeClone(void) const
|
||||
{
|
||||
UErrorCode status = U_ZERO_ERROR;
|
||||
StringSearch *result = new StringSearch(m_pattern_, m_text_,
|
||||
(RuleBasedCollator *)&m_collator_,
|
||||
m_breakiterator_,
|
||||
status);
|
||||
result->setOffset(getOffset(), status);
|
||||
result->setMatchStart(m_strsrch_->search->matchedIndex);
|
||||
result->setMatchLength(m_strsrch_->search->matchedLength);
|
||||
if (U_FAILURE(status)) {
|
||||
return NULL;
|
||||
}
|
||||
return result;
|
||||
}
|
||||
|
||||
// protected method -------------------------------------------------
|
||||
|
||||
UTextOffset StringSearch::handleNext(int32_t position, UErrorCode &status)
|
||||
{
|
||||
// values passed here are already in the pre-shift position
|
||||
if (U_SUCCESS(status)) {
|
||||
if (m_strsrch_->pattern.CELength == 0) {
|
||||
m_search_->matchedIndex =
|
||||
m_search_->matchedIndex == USEARCH_DONE ?
|
||||
getOffset() : m_search_->matchedIndex + 1;
|
||||
m_search_->matchedLength = 0;
|
||||
ucol_setOffset(m_strsrch_->textIter, m_search_->matchedIndex,
|
||||
&status);
|
||||
if (m_search_->matchedIndex == m_search_->textLength) {
|
||||
m_search_->matchedIndex = USEARCH_DONE;
|
||||
}
|
||||
}
|
||||
else {
|
||||
// looking at usearch.cpp, this part is shifted out to
|
||||
// StringSearch instead of SearchIterator because m_strsrch_ is
|
||||
// not accessible in SearchIterator
|
||||
if (!m_search_->isOverlap &&
|
||||
position + m_strsrch_->pattern.defaultShiftSize >
|
||||
m_search_->textLength) {
|
||||
setMatchNotFound();
|
||||
return USEARCH_DONE;
|
||||
}
|
||||
while (TRUE) {
|
||||
if (m_search_->isCanonicalMatch) {
|
||||
// can't use exact here since extra accents are allowed.
|
||||
usearch_handleNextCanonical(m_strsrch_, &status);
|
||||
}
|
||||
else {
|
||||
usearch_handleNextExact(m_strsrch_, &status);
|
||||
}
|
||||
if (U_FAILURE(status)) {
|
||||
return USEARCH_DONE;
|
||||
}
|
||||
if (m_breakiterator_ == NULL ||
|
||||
m_search_->matchedIndex == USEARCH_DONE ||
|
||||
(m_breakiterator_->isBoundary(m_search_->matchedIndex) &&
|
||||
m_breakiterator_->isBoundary(m_search_->matchedIndex +
|
||||
m_search_->matchedLength))) {
|
||||
return m_search_->matchedIndex;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
return USEARCH_DONE;
|
||||
}
|
||||
|
||||
UTextOffset StringSearch::handlePrev(int32_t position, UErrorCode &status)
|
||||
{
|
||||
// values passed here are already in the pre-shift position
|
||||
if (U_SUCCESS(status)) {
|
||||
if (m_strsrch_->pattern.CELength == 0) {
|
||||
m_search_->matchedIndex =
|
||||
(m_search_->matchedIndex == USEARCH_DONE ? getOffset() :
|
||||
m_search_->matchedIndex);
|
||||
if (m_search_->matchedIndex == 0) {
|
||||
setMatchNotFound();
|
||||
}
|
||||
else {
|
||||
m_search_->matchedIndex --;
|
||||
ucol_setOffset(m_strsrch_->textIter, m_search_->matchedIndex,
|
||||
&status);
|
||||
m_search_->matchedLength = 0;
|
||||
}
|
||||
}
|
||||
else {
|
||||
// looking at usearch.cpp, this part is shifted out to
|
||||
// StringSearch instead of SearchIterator because m_strsrch_ is
|
||||
// not accessible in SearchIterator
|
||||
if (!m_search_->isOverlap &&
|
||||
position - m_strsrch_->pattern.defaultShiftSize < 0) {
|
||||
setMatchNotFound();
|
||||
return USEARCH_DONE;
|
||||
}
|
||||
while (TRUE) {
|
||||
if (m_search_->isCanonicalMatch) {
|
||||
// can't use exact here since extra accents are allowed.
|
||||
usearch_handlePreviousCanonical(m_strsrch_, &status);
|
||||
}
|
||||
else {
|
||||
usearch_handlePreviousExact(m_strsrch_, &status);
|
||||
}
|
||||
if (U_FAILURE(status)) {
|
||||
return USEARCH_DONE;
|
||||
}
|
||||
if (m_breakiterator_ == NULL ||
|
||||
m_search_->matchedIndex == USEARCH_DONE ||
|
||||
(m_breakiterator_->isBoundary(m_search_->matchedIndex) &&
|
||||
m_breakiterator_->isBoundary(m_search_->matchedIndex +
|
||||
m_search_->matchedLength))) {
|
||||
return m_search_->matchedIndex;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return m_search_->matchedIndex;
|
||||
}
|
||||
return USEARCH_DONE;
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
|
@ -326,18 +326,12 @@ Collator* RuleBasedCollator::clone() const
|
|||
return new RuleBasedCollator(*this);
|
||||
}
|
||||
|
||||
/**
|
||||
* Create a CollationElementIterator object that will iterator over the
|
||||
* elements in a string, using the collation rules defined in this
|
||||
* RuleBasedCollator
|
||||
*/
|
||||
CollationElementIterator* RuleBasedCollator::createCollationElementIterator
|
||||
(const UnicodeString& source) const
|
||||
{
|
||||
UErrorCode status = U_ZERO_ERROR;
|
||||
CollationElementIterator *result = new CollationElementIterator(source, this,
|
||||
status);
|
||||
|
||||
if (U_FAILURE(status))
|
||||
return NULL;
|
||||
|
||||
|
|
|
|||
|
|
@ -368,6 +368,13 @@ ucol_cloneRuleData(const UCollator *coll, int32_t *length, UErrorCode *status);
|
|||
#define getExpansionCount(CE) ((CE)&0xF)
|
||||
#define isCEIgnorable(CE) (((CE) & 0xFFFFFFBF) == 0)
|
||||
|
||||
/* StringSearch internal use */
|
||||
#define inNormBuf(coleiter) ((coleiter)->iteratordata_.flags & UCOL_ITER_INNORMBUF)
|
||||
#define isFCDPointerNull(coleiter) ((coleiter)->iteratordata_.fcdPosition == NULL)
|
||||
#define getExpansionPrefix(coleiter) ((coleiter)->iteratordata_.toReturn - (coleiter)->iteratordata_.CEs)
|
||||
#define setExpansionPrefix(coleiter, offset) ((coleiter)->iteratordata_.CEs + offset)
|
||||
#define getExpansionSuffix(coleiter) ((coleiter)->iteratordata_.CEpos - (coleiter)->iteratordata_.toReturn)
|
||||
#define setExpansionSuffix(coleiter, offset) ((coleiter)->iteratordata_.toReturn = (coleiter)->iteratordata_.CEpos - leftoverces)
|
||||
|
||||
#define UCA_DATA_TYPE "dat"
|
||||
#define UCA_DATA_NAME "ucadata"
|
||||
|
|
|
|||
|
|
@ -223,6 +223,9 @@ ucol_setOffset(UCollationElements *elems,
|
|||
collIterate *ci = &(elems->iteratordata_);
|
||||
ci->pos = ci->string + offset;
|
||||
ci->CEpos = ci->toReturn = ci->CEs;
|
||||
if (ci->flags & UCOL_ITER_INNORMBUF) {
|
||||
ci->flags = ci->origFlags;
|
||||
}
|
||||
if ((ci->flags & UCOL_ITER_HASLEN) == 0) {
|
||||
ci->endp = ci->string + u_strlen(ci->string);
|
||||
}
|
||||
|
|
|
|||
466
icu4c/source/i18n/unicode/search.h
Normal file
466
icu4c/source/i18n/unicode/search.h
Normal file
|
|
@ -0,0 +1,466 @@
|
|||
/*
|
||||
**********************************************************************
|
||||
* Copyright (C) 2001 IBM and others. All rights reserved.
|
||||
**********************************************************************
|
||||
* Date Name Description
|
||||
* 03/22/2000 helena Creation.
|
||||
**********************************************************************
|
||||
*/
|
||||
|
||||
#ifndef SEARCH_H
|
||||
#define SEARCH_H
|
||||
|
||||
#include "unicode/unistr.h"
|
||||
#include "unicode/chariter.h"
|
||||
#include "unicode/brkiter.h"
|
||||
#include "unicode/usearch.h"
|
||||
|
||||
/**
|
||||
* <tt>SearchIterator</tt> is an abstract base class that provides
|
||||
* methods to search for a pattern within a text string. Instances of
|
||||
* <tt>SearchIterator</tt> maintain a current position and scans over the
|
||||
* target text, returning the indices the pattern is matched and the length
|
||||
* of each match.
|
||||
* <p>
|
||||
* <tt>SearchIterator</tt> defines a protocol for text searching.
|
||||
* Subclasses provide concrete implementations of various search algorithms.
|
||||
* For example, {@link StringSearch} implements language-sensitive pattern
|
||||
* matching based on the comparison rules defined in a
|
||||
* {@link RuleBasedCollator} object.
|
||||
* <p>
|
||||
* Other options for searching includes using a BreakIterator to restrict
|
||||
* the points at which matches are detected.
|
||||
* <p>
|
||||
* <tt>SearchIterator</tt> provides an API that is similar to that of
|
||||
* other text iteration classes such as <tt>BreakIterator</tt>. Using
|
||||
* this class, it is easy to scan through text looking for all occurances of
|
||||
* a given pattern. The following example uses a <tt>StringSearch</tt>
|
||||
* object to find all instances of "fox" in the target string. Any other
|
||||
* subclass of <tt>SearchIterator</tt> can be used in an identical
|
||||
* manner.
|
||||
* <pre><code>
|
||||
* UnicodeString target("The quick brown fox jumped over the lazy fox");
|
||||
* UnicodeString pattern("fox");
|
||||
*
|
||||
* SearchIterator *iter = new StringSearch(pattern, target);
|
||||
*
|
||||
* for (int pos = iter->first(); pos != USEARCH_DONE;
|
||||
* pos = iter->next()) {
|
||||
* printf("Found match at %d pos, length is %d\n", pos,
|
||||
* iter.getMatchLength());
|
||||
* }
|
||||
* </code></pre>
|
||||
*
|
||||
* @see StringSearch
|
||||
*/
|
||||
|
||||
struct USearch;
|
||||
typedef struct USearch USearch;
|
||||
|
||||
/**
|
||||
* Data structure for searching
|
||||
*/
|
||||
class U_I18N_API SearchIterator {
|
||||
|
||||
public:
|
||||
|
||||
// public constructors and destructors -------------------------------
|
||||
|
||||
/**
|
||||
* Copy constructor that creates a SearchIterator instance with the same
|
||||
* behavior, and iterating over the same text.
|
||||
* @param other the SearchIterator instance to be copied.
|
||||
*/
|
||||
SearchIterator(const SearchIterator &other);
|
||||
|
||||
/**
|
||||
* Destructor. Cleans up the search iterator data struct.
|
||||
*/
|
||||
virtual ~SearchIterator();
|
||||
|
||||
// public get and set methods ----------------------------------------
|
||||
|
||||
/**
|
||||
* Sets the index to point to the given position, and clears any state
|
||||
* that's affected.
|
||||
* <p>
|
||||
* 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.
|
||||
* @param position within the text to be set
|
||||
* @param status for errors if it occurs
|
||||
*/
|
||||
virtual void setOffset(UTextOffset position, UErrorCode &status) = 0;
|
||||
|
||||
/**
|
||||
* Return the current index in the text being searched.
|
||||
* If the iteration has gone past the end of the text
|
||||
* (or past the beginning for a backwards search), {@link #USEARCH_DONE}
|
||||
* is returned.
|
||||
* @return current index in the text being searched.
|
||||
*/
|
||||
virtual UTextOffset getOffset(void) const = 0;
|
||||
|
||||
/**
|
||||
* 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 attribute text attribute (enum USearchAttribute) to be set
|
||||
* @param value text attribute value
|
||||
* @param status for errors if it occurs
|
||||
*/
|
||||
void setAttribute(USearchAttribute attribute,
|
||||
USearchAttributeValue value,
|
||||
UErrorCode &status);
|
||||
|
||||
/**
|
||||
* Gets the text searching attributes
|
||||
* @param attribute text attribute (enum USearchAttribute) to be retrieve
|
||||
* @return text attribute value
|
||||
*/
|
||||
USearchAttributeValue getAttribute(USearchAttribute attribute) const;
|
||||
|
||||
/**
|
||||
* 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
|
||||
* {@link #first}, {@link #next}, {@link #previous}, or {@link #last}.
|
||||
* Just after construction, or after a searching method returns
|
||||
* <tt>USEARCH_DONE</tt>, this method will return <tt>USEARCH_DONE</tt>.
|
||||
* <p>
|
||||
* Use getMatchedLength to get the matched string length.
|
||||
* @return index of a substring within the text string that is being
|
||||
* searched.
|
||||
*/
|
||||
UTextOffset getMatchedStart(void) const;
|
||||
|
||||
/**
|
||||
* 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 {@link #first}, {@link #next}, {@link #previous}, or {@link #last}.
|
||||
* Just after construction, or after a searching method returns
|
||||
* <tt>USEARCH_DONE</tt>, this method will return 0.
|
||||
* @return The length of the match in the target text, or 0 if there
|
||||
* is no match currently.
|
||||
*/
|
||||
int32_t getMatchedLength(void) const;
|
||||
|
||||
/**
|
||||
* Returns the text that was matched by the most recent call to
|
||||
* {@link #first}, {@link #next}, {@link #previous}, or {@link #last}.
|
||||
* If the iterator is not pointing at a valid match (e.g. just after
|
||||
* construction or after <tt>USEARCH_DONE</tt> has been returned,
|
||||
* returns an empty string.
|
||||
* @param result stores the matched string or an empty string if a match
|
||||
* is not found.
|
||||
*/
|
||||
void getMatchedText(UnicodeString &result) const;
|
||||
|
||||
/**
|
||||
* Set the BreakIterator that will be used to restrict the points
|
||||
* at which matches are detected. The user is responsible for deleting
|
||||
* the breakiterator.
|
||||
* @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
|
||||
*/
|
||||
void setBreakIterator(BreakIterator *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 <tt>setBreakIterator</tt>.
|
||||
* Note that <tt>NULL</tt> is a legal value; it means that break
|
||||
* detection should not be attempted.
|
||||
* @return BreakIterator used to restrict matchings.
|
||||
*/
|
||||
const BreakIterator * getBreakIterator(void) const;
|
||||
|
||||
/**
|
||||
* 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. The user is responsible for deleting the text.
|
||||
* @param text string to be searched.
|
||||
* @param status for errors if it occurs
|
||||
*/
|
||||
virtual void setText(const UnicodeString &text, UErrorCode &status);
|
||||
|
||||
/**
|
||||
* 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.
|
||||
* <p>
|
||||
* Note: No parsing of the text within the <tt>CharacterIterator</tt>
|
||||
* will be done during searching for this version. The block of text
|
||||
* in <tt>CharacterIterator</tt> will be used as it is.
|
||||
* The user is responsible for deleting the text.
|
||||
* @param text string iterator to be searched.
|
||||
* @param status for errors if it occurs
|
||||
*/
|
||||
virtual void setText(CharacterIterator &text, UErrorCode &status);
|
||||
|
||||
/**
|
||||
* Return the string text to be searched.
|
||||
* @return text string to be searched.
|
||||
*/
|
||||
const UnicodeString & getText(void) const;
|
||||
|
||||
// operator overloading ----------------------------------------------
|
||||
|
||||
/**
|
||||
* Equality operator.
|
||||
* @param that SearchIterator instance to be compared.
|
||||
* @return TRUE if both BreakIterators are of the same class, have the
|
||||
* same behavior, terates over the same text and have the same
|
||||
* attributes. FALSE otherwise.
|
||||
*/
|
||||
virtual UBool operator==(const SearchIterator &that) const;
|
||||
|
||||
/**
|
||||
* Not-equal operator.
|
||||
* @param that SearchIterator instance to be compared.
|
||||
* @return FALSE if operator== returns TRUE, and vice versa.
|
||||
*/
|
||||
UBool operator!=(const SearchIterator &that) const;
|
||||
|
||||
// public methods ----------------------------------------------------
|
||||
|
||||
/**
|
||||
* Returns a copy of SearchIterator with the same behavior, and
|
||||
* iterating over the same text, as this one. Note that all data will be
|
||||
* replicated, except for the text string to be searched.
|
||||
* @return cloned object
|
||||
*/
|
||||
virtual SearchIterator* safeClone(void) const = 0;
|
||||
|
||||
/**
|
||||
* 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 {@link #usearch_getOffset}) is the match position if one
|
||||
* was found.
|
||||
* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and
|
||||
* the iterator will be adjusted to the index USEARCH_DONE
|
||||
* @param status for errors if it occurs
|
||||
* @return The character index of the first match, or
|
||||
* <tt>USEARCH_DONE</tt> if there are no matches.
|
||||
*/
|
||||
UTextOffset first(UErrorCode &status);
|
||||
|
||||
/**
|
||||
* Returns the first index greater than <tt>position</tt> at which the
|
||||
* string text matches the search pattern. The iterator is adjusted so
|
||||
* that its current index (as returned by {@link #getOffset}) is the
|
||||
* match position if one was found. If a match is not found,
|
||||
* <tt>USEARCH_DONE</tt> will be returned and the iterator will be
|
||||
* adjusted to the index USEARCH_DONE
|
||||
* @param position where search if to start from
|
||||
* @param status for errors if it occurs
|
||||
* @return The character index of the first match following
|
||||
* <tt>position</tt>, or <tt>USEARCH_DONE</tt> if there are no
|
||||
* matches.
|
||||
*/
|
||||
UTextOffset following(UTextOffset 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 {@link #getOffset}) is the match position if one was
|
||||
* found.
|
||||
* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and
|
||||
* the iterator will be adjusted to the index USEARCH_DONE.
|
||||
* @param status for errors if it occurs
|
||||
* @return The index of the first match, or <tt>USEARCH_DONE</tt> if
|
||||
* there are no matches.
|
||||
*/
|
||||
UTextOffset last(UErrorCode &status);
|
||||
|
||||
/**
|
||||
* Returns the first index less than <tt>position</tt> at which the string
|
||||
* text matches the search pattern. The iterator is adjusted so that its
|
||||
* current index (as returned by {@link #getOffset}) is the match
|
||||
* position if one was found. If a match is not found,
|
||||
* <tt>USEARCH_DONE</tt> will be returned and the iterator will be
|
||||
* adjusted to the index USEARCH_DONE
|
||||
* @param position where search is to start from
|
||||
* @param status for errors if it occurs
|
||||
* @return The character index of the first match preceding
|
||||
* <tt>position</tt>, or <tt>USEARCH_DONE</tt> if there are
|
||||
* no matches.
|
||||
*/
|
||||
UTextOffset preceding(UTextOffset position, UErrorCode &status);
|
||||
|
||||
/**
|
||||
* Returns the index of the next point at which the text matches the
|
||||
* search pattern, starting from the current position
|
||||
* The iterator is adjusted so that its current index (as returned by
|
||||
* {@link #getIndex}) is the match position if one was found.
|
||||
* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and
|
||||
* the iterator will be adjusted to a position after the end of the text
|
||||
* string.
|
||||
* @param status for errors if it occurs
|
||||
* @return The index of the next match after the current position,
|
||||
* or <tt>USEARCH_DONE</tt> if there are no more matches.
|
||||
*/
|
||||
UTextOffset next(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
|
||||
* {@link #getOffset}) is the match position if one was found.
|
||||
* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and
|
||||
* the iterator will be adjusted to the index USEARCH_DONE
|
||||
* @param status for errors if it occurs
|
||||
* @return The index of the previous match before the current position,
|
||||
* or <tt>USEARCH_DONE</tt> if there are no more matches.
|
||||
*/
|
||||
UTextOffset previous(UErrorCode &status);
|
||||
|
||||
/**
|
||||
* Resets 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.
|
||||
*/
|
||||
virtual void reset();
|
||||
|
||||
protected:
|
||||
// protected data members ---------------------------------------------
|
||||
|
||||
/**
|
||||
* C search data struct
|
||||
*/
|
||||
USearch *m_search_;
|
||||
|
||||
/**
|
||||
* Break iterator.
|
||||
* Currently the C++ breakiterator does not have getRules etc to reproduce
|
||||
* another in C. Hence we keep the original around and do the verification
|
||||
* at the end of the match. The user is responsible for deleting this
|
||||
* break iterator.
|
||||
*/
|
||||
BreakIterator *m_breakiterator_;
|
||||
|
||||
/**
|
||||
* Unicode string version of the search text
|
||||
*/
|
||||
UnicodeString m_text_;
|
||||
|
||||
// protected constructors and destructors -----------------------------
|
||||
|
||||
/**
|
||||
* Default constructor.
|
||||
* Initializes data to the default values.
|
||||
*/
|
||||
SearchIterator();
|
||||
|
||||
/**
|
||||
* Constructor for use by subclasses.
|
||||
* @param text The target text to be searched.
|
||||
* @param breakiter A {@link BreakIterator} that is used to restrict the
|
||||
* points at which matches are detected. If
|
||||
* <tt>handleNext</tt> or <tt>handlePrev</tt> finds a
|
||||
* match, but the match's start or end index is not a
|
||||
* boundary as determined by the <tt>BreakIterator</tt>,
|
||||
* the match is rejected and <tt>handleNext</tt> or
|
||||
* <tt>handlePrev</tt> is called again. If this parameter
|
||||
* is <tt>NULL</tt>, no break detection is attempted.
|
||||
* @param status error status
|
||||
*/
|
||||
SearchIterator(const UnicodeString &text,
|
||||
BreakIterator *breakiter = NULL);
|
||||
|
||||
/**
|
||||
* Constructor for use by subclasses.
|
||||
* <p>
|
||||
* Note: No parsing of the text within the <tt>CharacterIterator</tt>
|
||||
* will be done during searching for this version. The block of text
|
||||
* in <tt>CharacterIterator</tt> will be used as it is.
|
||||
* @param text The target text to be searched.
|
||||
* @param breakiter A {@link BreakIterator} that is used to restrict the
|
||||
* points at which matches are detected. If
|
||||
* <tt>handleNext</tt> or <tt>handlePrev</tt> finds a
|
||||
* match, but the match's start or end index is not a
|
||||
* boundary as determined by the <tt>BreakIterator</tt>,
|
||||
* the match is rejected and <tt>handleNext</tt> or
|
||||
* <tt>handlePrev</tt> is called again. If this parameter
|
||||
* is <tt>NULL</tt>, no break detection is attempted.
|
||||
*/
|
||||
SearchIterator(CharacterIterator &text, BreakIterator *breakiter = NULL);
|
||||
|
||||
// protected methods --------------------------------------------------
|
||||
|
||||
/**
|
||||
* Abstract method which subclasses override to provide the mechanism
|
||||
* for finding the next match in the target text. This allows different
|
||||
* subclasses to provide different search algorithms.
|
||||
* <p>
|
||||
* If a match is found, the implementation should return the index at
|
||||
* which the match starts and should call
|
||||
* {@link #setMatchLength setMatchLength} with the number of characters
|
||||
* in the target text that make up the match. If no match is found, the
|
||||
* method should return USEARCH_DONE.
|
||||
* <p>
|
||||
* @param position The index in the target text at which the search
|
||||
* should start.
|
||||
* @param status for error codes if it occurs.
|
||||
*/
|
||||
virtual UTextOffset handleNext(UTextOffset position, UErrorCode &status)
|
||||
= 0;
|
||||
|
||||
/**
|
||||
* Abstract method which subclasses override to provide the mechanism for
|
||||
* finding the previous match in the target text. This allows different
|
||||
* subclasses to provide different search algorithms.
|
||||
* <p>
|
||||
* If a match is found, the implementation should return the index at
|
||||
* which the match starts and should call
|
||||
* {@link #setMatchLength setMatchLength} with the number of characters
|
||||
* in the target text that make up the match. If no match is found, the
|
||||
* method should return USEARCH_DONE.
|
||||
* <p>
|
||||
* @param position The index in the target text at which the search
|
||||
* should start.
|
||||
* @param status for error codes if it occurs.
|
||||
*/
|
||||
virtual UTextOffset handlePrev(UTextOffset position, UErrorCode &status)
|
||||
= 0;
|
||||
|
||||
/**
|
||||
* Sets the length of the currently matched string in the text string to
|
||||
* be searched.
|
||||
* Subclasses' <tt>handleNext</tt> and <tt>handlePrev</tt>
|
||||
* methods should call this when they find a match in the target text.
|
||||
* @param length length of the matched text.
|
||||
*/
|
||||
virtual void setMatchLength(int32_t length);
|
||||
|
||||
/**
|
||||
* Sets the offset of the currently matched string in the text string to
|
||||
* be searched.
|
||||
* Subclasses' <tt>handleNext</tt> and <tt>handlePrev</tt>
|
||||
* methods should call this when they find a match in the target text.
|
||||
* @param position start offset of the matched text.
|
||||
*/
|
||||
virtual void setMatchStart(UTextOffset position);
|
||||
|
||||
/**
|
||||
* sets match not found
|
||||
*/
|
||||
void setMatchNotFound();
|
||||
};
|
||||
|
||||
inline UBool SearchIterator::operator!=(const SearchIterator &that) const
|
||||
{
|
||||
return !operator==(that);
|
||||
}
|
||||
|
||||
#endif
|
||||
|
||||
433
icu4c/source/i18n/unicode/stsearch.h
Normal file
433
icu4c/source/i18n/unicode/stsearch.h
Normal file
|
|
@ -0,0 +1,433 @@
|
|||
/*
|
||||
**********************************************************************
|
||||
* Copyright (C) 2001 IBM and others. All rights reserved.
|
||||
**********************************************************************
|
||||
* Date Name Description
|
||||
* 03/22/2000 helena Creation.
|
||||
**********************************************************************
|
||||
*/
|
||||
|
||||
#ifndef STSEARCH_H
|
||||
#define STSEARCH_H
|
||||
|
||||
#include "unicode/tblcoll.h"
|
||||
#include "unicode/coleitr.h"
|
||||
#include "unicode/search.h"
|
||||
|
||||
/**
|
||||
* <tt>StringSearch</tt> is a <tt>SearchIterator</tt> that provides
|
||||
* language-sensitive text searching based on the comparison rules defined
|
||||
* in a {@link RuleBasedCollator} object.
|
||||
* StringSearch 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 <a href=http://oss.software.ibm.com/icu/develop/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://oss.software.ibm.com/icu/docs/papers/text-search.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>BreakIterator</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.
|
||||
* Match results in the forward direction will match the result matches in
|
||||
* the backwards direction in the reverse order
|
||||
* <p>
|
||||
* <tt>SearchIterator</tt> provides APIs to specify the starting position
|
||||
* within the text string to be searched, e.g. <tt>setOffset</tt>,
|
||||
* <tt>preceding</tt> and <tt>following</tt>. Since the
|
||||
* starting position will be set as it is specified, please take note that
|
||||
* there are some danger points 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.
|
||||
* <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>getCollator</tt> and using the APIs in <tt>coll.h</tt>.
|
||||
* <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,
|
||||
* StringSearch does not guarantee the results for option 1.
|
||||
* <p>
|
||||
* Consult the <tt>SearchIterator</tt> documentation for information on
|
||||
* and examples of how to use instances of this class to implement text
|
||||
* searching.
|
||||
* <pre><code>
|
||||
* UnicodeString target("The quick brown fox jumped over the lazy fox");
|
||||
* UnicodeString pattern("fox");
|
||||
*
|
||||
* SearchIterator *iter = new StringSearch(pattern, target);
|
||||
*
|
||||
* for (int pos = iter->first(); pos != USEARCH_DONE;
|
||||
* pos = iter->next()) {
|
||||
* printf("Found match at %d pos, length is %d\n", pos,
|
||||
* iter.getMatchLength());
|
||||
* }
|
||||
* </code></pre>
|
||||
* @see SearchIterator
|
||||
* @see RuleBasedCollator
|
||||
*/
|
||||
|
||||
class U_I18N_API StringSearch : public SearchIterator
|
||||
{
|
||||
public:
|
||||
|
||||
// public constructors and destructors --------------------------------
|
||||
|
||||
/**
|
||||
* Creating a <tt>StringSearch</tt> instance using the argument locale
|
||||
* language rule set. A collator will be created in the process, which
|
||||
* will be owned by this instance and will be deleted in during
|
||||
* destruction
|
||||
* @param pattern The text for which this object will search.
|
||||
* @param text The text in which to search for the pattern.
|
||||
* @param locale A locale which defines the language-sensitive
|
||||
* comparison rules used to determine whether text in the
|
||||
* pattern and target matches.
|
||||
* @param breakiter A <tt>BreakIterator</tt> object used to constrain
|
||||
* the matches that are found. Matches whose start and end
|
||||
* indices in the target text are not boundaries as
|
||||
* determined by the <tt>BreakIterator</tt> are
|
||||
* ignored. If this behavior is not desired,
|
||||
* <tt>NULL</tt> can be passed in instead.
|
||||
* @param status for errors if any
|
||||
*/
|
||||
StringSearch(const UnicodeString &pattern, const UnicodeString &text,
|
||||
const Locale &locale,
|
||||
BreakIterator *breakiter,
|
||||
UErrorCode &status);
|
||||
|
||||
/**
|
||||
* Creating a <tt>StringSearch</tt> instance using the argument collator
|
||||
* language rule set. Note, user retains the ownership of this collator,
|
||||
* it does not get destroyed during this instance's destruction.
|
||||
* @param pattern The text for which this object will search.
|
||||
* @param text The text in which to search for the pattern.
|
||||
* @param coll A <tt>RuleBasedCollator</tt> object which defines
|
||||
* the language-sensitive comparison rules used to
|
||||
* determine whether text in the pattern and target
|
||||
* matches. User is responsible for the clearing of this
|
||||
* object.
|
||||
* @param breakiter A <tt>BreakIterator</tt> object used to constrain
|
||||
* the matches that are found. Matches whose start and end
|
||||
* indices in the target text are not boundaries as
|
||||
* determined by the <tt>BreakIterator</tt> are
|
||||
* ignored. If this behavior is not desired,
|
||||
* <tt>NULL</tt> can be passed in instead.
|
||||
* @param status for errors if any
|
||||
*/
|
||||
StringSearch(const UnicodeString &pattern,
|
||||
const UnicodeString &text,
|
||||
RuleBasedCollator *coll,
|
||||
BreakIterator *breakiter,
|
||||
UErrorCode &status);
|
||||
|
||||
/**
|
||||
* Creating a <tt>StringSearch</tt> instance using the argument locale
|
||||
* language rule set. A collator will be created in the process, which
|
||||
* will be owned by this instance and will be deleted in during
|
||||
* destruction
|
||||
* <p>
|
||||
* Note: No parsing of the text within the <tt>CharacterIterator</tt>
|
||||
* will be done during searching for this version. The block of text
|
||||
* in <tt>CharacterIterator</tt> will be used as it is.
|
||||
* @param pattern The text for which this object will search.
|
||||
* @param text The text iterator in which to search for the pattern.
|
||||
* @param locale A locale which defines the language-sensitive
|
||||
* comparison rules used to determine whether text in the
|
||||
* pattern and target matches. User is responsible for
|
||||
* the clearing of this object.
|
||||
* @param breakiter A <tt>BreakIterator</tt> object used to constrain
|
||||
* the matches that are found. Matches whose start and end
|
||||
* indices in the target text are not boundaries as
|
||||
* determined by the <tt>BreakIterator</tt> are
|
||||
* ignored. If this behavior is not desired,
|
||||
* <tt>NULL</tt> can be passed in instead.
|
||||
* @param status for errors if any
|
||||
*/
|
||||
StringSearch(const UnicodeString &pattern, CharacterIterator &text,
|
||||
const Locale &locale,
|
||||
BreakIterator *breakiter,
|
||||
UErrorCode &status);
|
||||
|
||||
/**
|
||||
* Creating a <tt>StringSearch</tt> instance using the argument collator
|
||||
* language rule set. Note, user retains the ownership of this collator,
|
||||
* it does not get destroyed during this instance's destruction.
|
||||
* <p>
|
||||
* Note: No parsing of the text within the <tt>CharacterIterator</tt>
|
||||
* will be done during searching for this version. The block of text
|
||||
* in <tt>CharacterIterator</tt> will be used as it is.
|
||||
* @param pattern The text for which this object will search.
|
||||
* @param text The text in which to search for the pattern.
|
||||
* @param coll A <tt>RuleBasedCollator</tt> object which defines
|
||||
* the language-sensitive comparison rules used to
|
||||
* determine whether text in the pattern and target
|
||||
* matches. User is responsible for the clearing of this
|
||||
* object.
|
||||
* @param breakiter A <tt>BreakIterator</tt> object used to constrain
|
||||
* the matches that are found. Matches whose start and end
|
||||
* indices in the target text are not boundaries as
|
||||
* determined by the <tt>BreakIterator</tt> are
|
||||
* ignored. If this behavior is not desired,
|
||||
* <tt>NULL</tt> can be passed in instead.
|
||||
* @param status for errors if any
|
||||
*/
|
||||
StringSearch(const UnicodeString &pattern, CharacterIterator &text,
|
||||
RuleBasedCollator *coll,
|
||||
BreakIterator *breakiter,
|
||||
UErrorCode &status);
|
||||
|
||||
/**
|
||||
* Copy constructor that creates a StringSearch instance with the same
|
||||
* behavior, and iterating over the same text.
|
||||
* @param that StringSearch instance to be copied.
|
||||
*/
|
||||
StringSearch(const StringSearch &that);
|
||||
|
||||
/**
|
||||
* Destructor. Cleans up the search iterator data struct.
|
||||
* If a collator is created in the constructor, it will be destroyed here.
|
||||
*/
|
||||
virtual ~StringSearch(void);
|
||||
|
||||
// operator overloading ---------------------------------------------
|
||||
|
||||
/**
|
||||
* Assignment operator. Sets this iterator to have the same behavior,
|
||||
* and iterate over the same text, as the one passed in.
|
||||
* @param that instance to be copied.
|
||||
*/
|
||||
virtual StringSearch & operator=(const StringSearch &that);
|
||||
|
||||
/**
|
||||
* Equality operator.
|
||||
* @param that instance to be compared.
|
||||
* @return TRUE if both instances have the same attributes,
|
||||
* breakiterators, collators and iterate over the same text
|
||||
* while looking for the same pattern.
|
||||
*/
|
||||
virtual UBool operator==(const SearchIterator &that) const;
|
||||
|
||||
// public get and set methods ----------------------------------------
|
||||
|
||||
/**
|
||||
* Sets the index to point to the given position, and clears any state
|
||||
* that's affected.
|
||||
* <p>
|
||||
* 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.
|
||||
* @param position within the text to be set
|
||||
* @param status for errors if it occurs
|
||||
*/
|
||||
virtual void setOffset(UTextOffset position, UErrorCode &status);
|
||||
|
||||
/**
|
||||
* Return the current index in the text being searched.
|
||||
* If the iteration has gone past the end of the text
|
||||
* (or past the beginning for a backwards search), {@link #USEARCH_DONE}
|
||||
* is returned.
|
||||
* @return current index in the text being searched.
|
||||
*/
|
||||
virtual UTextOffset getOffset(void) const;
|
||||
|
||||
/**
|
||||
* Set the target 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 text text string to be searched
|
||||
* @param status for errors if any
|
||||
*/
|
||||
virtual void setText(const UnicodeString &text, UErrorCode &status);
|
||||
|
||||
/**
|
||||
* Set the target 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.
|
||||
* Note: No parsing of the text within the <tt>CharacterIterator</tt>
|
||||
* will be done during searching for this version. The block of text
|
||||
* in <tt>CharacterIterator</tt> will be used as it is.
|
||||
* @param text text string to be searched
|
||||
* @param status for errors if any
|
||||
*/
|
||||
virtual void setText(CharacterIterator &text, UErrorCode &status);
|
||||
|
||||
/**
|
||||
* Gets the collator used for the language rules.
|
||||
* <p>
|
||||
* Deleting the returned <tt>RuleBasedCollator</tt> before calling
|
||||
* the destructor would cause the string search to fail.
|
||||
* The destructor will delete the collator if this instance owns it
|
||||
* @return collator used for string search
|
||||
*/
|
||||
RuleBasedCollator * getCollator() const;
|
||||
|
||||
/**
|
||||
* 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 coll collator
|
||||
* @param status for errors if any
|
||||
*/
|
||||
void setCollator(RuleBasedCollator *coll, 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 pattern search pattern to be found
|
||||
* @param status for errors if any
|
||||
*/
|
||||
void setPattern(const UnicodeString &pattern, UErrorCode &status);
|
||||
|
||||
/**
|
||||
* Gets the search pattern.
|
||||
* @return pattern used for matching
|
||||
*/
|
||||
const UnicodeString & getPattern() const;
|
||||
|
||||
// public methods ----------------------------------------------------
|
||||
|
||||
/**
|
||||
* 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.
|
||||
*/
|
||||
virtual void reset();
|
||||
|
||||
/**
|
||||
* Returns a copy of StringSearch with the same behavior, and
|
||||
* iterating over the same text, as this one. Note that all data will be
|
||||
* replicated, except for the user-specified collator and the
|
||||
* breakiterator.
|
||||
* @return cloned object
|
||||
*/
|
||||
virtual SearchIterator * safeClone(void) const;
|
||||
|
||||
protected:
|
||||
|
||||
// protected method -------------------------------------------------
|
||||
|
||||
/**
|
||||
* Search forward for matching text, starting at a given location.
|
||||
* Clients should not call this method directly; instead they should
|
||||
* call {@link SearchIterator#next}.
|
||||
* <p>
|
||||
* If a match is found, this method returns the index at which the match
|
||||
* starts and calls {@link SearchIterator#setMatchLength} with the number
|
||||
* of characters in the target text that make up the match. If no match
|
||||
* is found, the method returns <tt>USEARCH_DONE</tt>.
|
||||
* <p>
|
||||
* The <tt>StringSearch</tt> is adjusted so that its current index
|
||||
* (as returned by {@link #getOffset}) is the match position if one was
|
||||
* found.
|
||||
* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and
|
||||
* the <tt>StringSearch</tt> will be adjusted to the index USEARCH_DONE.
|
||||
* @param position The index in the target text at which the search
|
||||
* starts
|
||||
* @param status for errors if any occurs
|
||||
* @return The index at which the matched text in the target starts, or
|
||||
* USEARCH_DONE if no match was found.
|
||||
*/
|
||||
virtual UTextOffset handleNext(UTextOffset position, UErrorCode &status);
|
||||
|
||||
/**
|
||||
* Search backward for matching text, starting at a given location.
|
||||
* Clients should not call this method directly; instead they should call
|
||||
* <tt>SearchIterator.previous()</tt>, which this method overrides.
|
||||
* <p>
|
||||
* If a match is found, this method returns the index at which the match
|
||||
* starts and calls {@link SearchIterator#setMatchLength} with the number
|
||||
* of characters in the target text that make up the match. If no match
|
||||
* is found, the method returns <tt>USEARCH_DONE</tt>.
|
||||
* <p>
|
||||
* The <tt>StringSearch</tt> is adjusted so that its current index
|
||||
* (as returned by {@link #getOffset}) is the match position if one was
|
||||
* found.
|
||||
* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and
|
||||
* the <tt>StringSearch</tt> will be adjusted to the index USEARCH_DONE.
|
||||
* @param position The index in the target text at which the search
|
||||
* starts.
|
||||
* @param status for errors if any occurs
|
||||
* @return The index at which the matched text in the target starts, or
|
||||
* USEARCH_DONE if no match was found.
|
||||
*/
|
||||
virtual UTextOffset handlePrev(UTextOffset position, UErrorCode &status);
|
||||
|
||||
private :
|
||||
|
||||
// private data members ----------------------------------------------
|
||||
|
||||
/**
|
||||
* RuleBasedCollator, contains exactly the same UCollator * in m_strsrch_
|
||||
*/
|
||||
RuleBasedCollator m_collator_;
|
||||
/**
|
||||
* Pattern text
|
||||
*/
|
||||
UnicodeString m_pattern_;
|
||||
/**
|
||||
* Corresponding collation rules
|
||||
*/
|
||||
UnicodeString m_collation_rules_;
|
||||
/**
|
||||
* String search struct data
|
||||
*/
|
||||
UStringSearch *m_strsrch_;
|
||||
};
|
||||
|
||||
#endif
|
||||
|
||||
|
|
@ -849,6 +849,11 @@ private:
|
|||
*/
|
||||
friend class Collator;
|
||||
|
||||
/**
|
||||
* Searching over collation elements in a character source
|
||||
*/
|
||||
friend class StringSearch;
|
||||
|
||||
// private constructors --------------------------------------------------
|
||||
|
||||
/**
|
||||
|
|
@ -893,10 +898,24 @@ private:
|
|||
/**
|
||||
* Creates the c struct for ucollator
|
||||
* @param collator new ucollator data
|
||||
* @param status error status
|
||||
*/
|
||||
void setUCollator(UCollator *collator);
|
||||
|
||||
/**
|
||||
* Creates the c struct for ucollator. This used internally by StringSearch.
|
||||
* Hence the responsibility of cleaning up the ucollator is not done by
|
||||
* this RuleBasedCollator. The isDataOwned flag is set to FALSE.
|
||||
* @param collator new ucollator data
|
||||
* @param rules corresponding collation rules
|
||||
*/
|
||||
void setUCollator(UCollator *collator, UnicodeString *rules);
|
||||
|
||||
/**
|
||||
* Get UCollator data struct. Used only by StringSearch.
|
||||
* @return UCollator data struct
|
||||
*/
|
||||
const UCollator * getUCollator();
|
||||
|
||||
/**
|
||||
* Converts C's UCollationResult to EComparisonResult
|
||||
* @param result member of the enum UComparisonResult
|
||||
|
|
@ -947,11 +966,29 @@ inline void RuleBasedCollator::setUCollator(const Locale &locale,
|
|||
|
||||
inline void RuleBasedCollator::setUCollator(UCollator *collator)
|
||||
{
|
||||
if (ucollator && dataIsOwned)
|
||||
if (ucollator && dataIsOwned) {
|
||||
ucol_close(ucollator);
|
||||
}
|
||||
ucollator = collator;
|
||||
}
|
||||
|
||||
inline void RuleBasedCollator::setUCollator(UCollator *collator,
|
||||
UnicodeString *rules)
|
||||
{
|
||||
if (ucollator && dataIsOwned) {
|
||||
ucol_close(ucollator);
|
||||
delete urulestring;
|
||||
}
|
||||
ucollator = collator;
|
||||
urulestring = rules;
|
||||
dataIsOwned = FALSE;
|
||||
}
|
||||
|
||||
inline const UCollator * RuleBasedCollator::getUCollator()
|
||||
{
|
||||
return ucollator;
|
||||
}
|
||||
|
||||
inline Collator::EComparisonResult RuleBasedCollator::getEComparisonResult(
|
||||
const UCollationResult &result) const
|
||||
{
|
||||
|
|
|
|||
546
icu4c/source/i18n/unicode/usearch.h
Normal file
546
icu4c/source/i18n/unicode/usearch.h
Normal file
|
|
@ -0,0 +1,546 @@
|
|||
/*
|
||||
**********************************************************************
|
||||
* 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"
|
||||
|
||||
/**
|
||||
* 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 ß and SS will be matched
|
||||
* if case is chosen to be ignored.
|
||||
* See the <a href=http://oss.software.ibm.com/icu/develop/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://oss.software.ibm.com/icu/docs/papers/text-search.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.
|
||||
* <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>.
|
||||
* <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);
|
||||
* pos != USEARCH_DONE;
|
||||
* pos = usearch_next(search)) {
|
||||
* printf("Found match at %d pos, length is %d\n", pos,
|
||||
* usearch_getMatchLength(search));
|
||||
* }
|
||||
* }
|
||||
* </code></pre>
|
||||
*/
|
||||
|
||||
/**
|
||||
* 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;
|
||||
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 <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
|
||||
* @return search iterator data structure
|
||||
*/
|
||||
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 <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
|
||||
* @return search iterator data structure
|
||||
*/
|
||||
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
|
||||
*/
|
||||
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.
|
||||
* @param status error status if any.
|
||||
*/
|
||||
U_CAPI void U_EXPORT2 usearch_setOffset(UStringSearch *strsrch,
|
||||
UTextOffset 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), {@link #USEARCH_DONE} is returned.
|
||||
* @param strsrch search iterator data struct
|
||||
*/
|
||||
U_CAPI UTextOffset 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
|
||||
*/
|
||||
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
|
||||
*/
|
||||
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
|
||||
* {@link #usearch_first}, {@link #usearch_next},
|
||||
* {@link #usearch_previous}, or {@link #usearch_last}.
|
||||
* Just after construction, or after a searching method returns
|
||||
* <tt>USEARCH_DONE</tt>, this method will return <tt>USEARCH_DONE</tt>.
|
||||
* <p>
|
||||
* 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.
|
||||
*/
|
||||
U_CAPI UTextOffset 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
|
||||
* {@link #usearch_first}, {@link #usearch_next},
|
||||
* {@link #usearch_previous}, or {@link #usearch_last}.
|
||||
* Just after construction, or after a searching method returns
|
||||
* <tt>USEARCH_DONE</tt>, 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.
|
||||
*/
|
||||
U_CAPI int32_t U_EXPORT2 usearch_getMatchedLength(
|
||||
const UStringSearch *strsrch);
|
||||
|
||||
/**
|
||||
* Returns the text that was matched by the most recent call to
|
||||
* {@link #usearch_first}, {@link #usearch_next},
|
||||
* {@link #usearch_previous}, or {@link #usearch_last}.
|
||||
* If the iterator is not pointing at a valid match (e.g. just after
|
||||
* construction or after <tt>USEARCH_DONE</tt> 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
|
||||
*/
|
||||
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 <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
|
||||
* @see #usearch_getBreakIterator
|
||||
*/
|
||||
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 <tt>usearch_setBreakIterator</tt>. Note that
|
||||
* <tt>NULL</tt>
|
||||
* 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
|
||||
*/
|
||||
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
|
||||
* @see #usearch_getText
|
||||
*/
|
||||
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
|
||||
*/
|
||||
U_CAPI const UChar * U_EXPORT2 usearch_getText(const UStringSearch *strsrch,
|
||||
int32_t *length);
|
||||
|
||||
/**
|
||||
* Gets the collator used for the language rules.
|
||||
* <p>
|
||||
* Deleting the returned <tt>UCollator</tt> before calling
|
||||
* <tt>usearch_close</tt> would cause the string search to fail.
|
||||
* <tt>usearch_close</tt> will delete the collator if this search owns it.
|
||||
* @param strsrch search iterator data struct
|
||||
* @return collator
|
||||
*/
|
||||
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
|
||||
*/
|
||||
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
|
||||
*/
|
||||
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
|
||||
*/
|
||||
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
|
||||
* {@link #usearch_getOffset}) is the match position if one was found.
|
||||
* If a match is not found, <tt>USEARCH_DONE</tt> 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
|
||||
* <tt>USEARCH_DONE</tt> if there are no matches.
|
||||
*/
|
||||
U_CAPI UTextOffset U_EXPORT2 usearch_first(UStringSearch *strsrch,
|
||||
UErrorCode *status);
|
||||
|
||||
/**
|
||||
* Returns the first index greater than <tt>position</tt> at which the string
|
||||
* text
|
||||
* matches the search pattern. The iterator is adjusted so that its current
|
||||
* index (as returned by {@link #usearch_getOffset}) is the match position if
|
||||
* one was found.
|
||||
* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and
|
||||
* the iterator will be adjusted to the index USEARCH_DONE
|
||||
* <p>
|
||||
* Search positions that may render incorrect results are highlighted in the
|
||||
* header comments.
|
||||
* @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 <tt>pos</tt>,
|
||||
* or <tt>USEARCH_DONE</tt> if there are no matches.
|
||||
*/
|
||||
U_CAPI UTextOffset U_EXPORT2 usearch_following(UStringSearch *strsrch,
|
||||
UTextOffset 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 {@link #usearch_getOffset}) is the match position if
|
||||
* one was found.
|
||||
* If a match is not found, <tt>USEARCH_DONE</tt> 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 <tt>USEARCH_DONE</tt> if there
|
||||
* are no matches.
|
||||
*/
|
||||
U_CAPI UTextOffset U_EXPORT2 usearch_last(UStringSearch *strsrch,
|
||||
UErrorCode *status);
|
||||
|
||||
/**
|
||||
* Returns the first index less than <tt>position</tt> at which the string text
|
||||
* matches the search pattern. The iterator is adjusted so that its current
|
||||
* index (as returned by {@link #usearch_getOffset}) is the match position if
|
||||
* one was found.
|
||||
* If a match is not found, <tt>USEARCH_DONE</tt> will be returned and
|
||||
* the iterator will be adjusted to the index USEARCH_DONE
|
||||
* <p>
|
||||
* Search positions that may render incorrect results are highlighted in the
|
||||
* header comments.
|
||||
* @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 <tt>pos</tt>,
|
||||
* or <tt>USEARCH_DONE</tt> if there are no matches.
|
||||
*/
|
||||
U_CAPI UTextOffset U_EXPORT2 usearch_preceding(UStringSearch *strsrch,
|
||||
UTextOffset 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 {@link #usearch_getOffset}) is the match position if
|
||||
* one was found.
|
||||
* If a match is not found, <tt>USEARCH_DONE</tt> 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
|
||||
* <tt>USEARCH_DONE</tt> if there are no more matches.
|
||||
* @see #usearch_first
|
||||
*/
|
||||
U_CAPI UTextOffset 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 {@link #usearch_getOffset}) is the match position if
|
||||
* one was found.
|
||||
* If a match is not found, <tt>USEARCH_DONE</tt> 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 <tt>USEARCH_DONE</tt> if there are no more matches.
|
||||
*/
|
||||
U_CAPI UTextOffset 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
|
||||
*/
|
||||
U_CAPI void U_EXPORT2 usearch_reset(UStringSearch *strsrch);
|
||||
|
||||
#endif
|
||||
|
||||
|
||||
3159
icu4c/source/i18n/usearch.cpp
Normal file
3159
icu4c/source/i18n/usearch.cpp
Normal file
File diff suppressed because it is too large
Load diff
123
icu4c/source/i18n/usrchimp.h
Normal file
123
icu4c/source/i18n/usrchimp.h
Normal file
|
|
@ -0,0 +1,123 @@
|
|||
/*
|
||||
**********************************************************************
|
||||
* Copyright (C) 2001 IBM and others. All rights reserved.
|
||||
**********************************************************************
|
||||
* Date Name Description
|
||||
* 08/13/2001 synwee Creation.
|
||||
**********************************************************************
|
||||
*/
|
||||
#ifndef USRCHIMP_H
|
||||
#define USRCHIMP_H
|
||||
|
||||
#include "unicode/utypes.h"
|
||||
#include "unicode/ucol.h"
|
||||
#include "unicode/ucoleitr.h"
|
||||
#include "unicode/ubrk.h"
|
||||
|
||||
#define INITIAL_ARRAY_SIZE_ 256
|
||||
#define MAX_TABLE_SIZE_ 256
|
||||
|
||||
struct USearch {
|
||||
// required since collation element iterator does not have a getText API
|
||||
const UChar *text;
|
||||
int32_t textLength; // exact length
|
||||
UBool isOverlap;
|
||||
UBool isCanonicalMatch;
|
||||
UBreakIterator *breakIter;
|
||||
// value USEARCH_DONE is the default value
|
||||
// if we are not at the start of the text or the end of the text,
|
||||
// depending on the iteration direction and matchedIndex is USEARCH_DONE
|
||||
// it means that we can find any more matches in that particular direction
|
||||
UTextOffset matchedIndex;
|
||||
int32_t matchedLength;
|
||||
UBool isForwardSearching;
|
||||
UBool reset;
|
||||
};
|
||||
|
||||
struct UPattern {
|
||||
const UChar *text;
|
||||
int32_t textLength; // exact length
|
||||
// length required for backwards ce comparison
|
||||
int32_t CELength;
|
||||
uint32_t *CE;
|
||||
uint32_t CEBuffer[INITIAL_ARRAY_SIZE_];
|
||||
UBool hasPrefixAccents;
|
||||
UBool hasSuffixAccents;
|
||||
int32_t defaultShiftSize;
|
||||
int32_t shift[MAX_TABLE_SIZE_];
|
||||
int32_t backShift[MAX_TABLE_SIZE_];
|
||||
};
|
||||
|
||||
struct UStringSearch {
|
||||
struct USearch *search;
|
||||
struct UPattern pattern;
|
||||
const UCollator *collator;
|
||||
// positions within the collation element iterator is used to determine
|
||||
// if we are at the start of the text.
|
||||
UCollationElements *textIter;
|
||||
UBool ownCollator;
|
||||
UBool toNormalize;
|
||||
UCollationStrength strength;
|
||||
uint32_t ceMask;
|
||||
uint32_t variableTop;
|
||||
UBool toShift;
|
||||
UChar canonicalPrefixAccents[INITIAL_ARRAY_SIZE_];
|
||||
UChar canonicalSuffixAccents[INITIAL_ARRAY_SIZE_];
|
||||
};
|
||||
|
||||
/**
|
||||
* Exact matches without checking for the ends for extra accents.
|
||||
* The match after the position within the collation element iterator is to be
|
||||
* found.
|
||||
* After a match is found the offset in the collation element iterator will be
|
||||
* shifted to the start of the match.
|
||||
* Implementation note:
|
||||
* For tertiary we can't use the collator->tertiaryMask, that is a
|
||||
* preprocessed mask that takes into account case options. since we are only
|
||||
* concerned with exact matches, we don't need that.
|
||||
* Alternate handling - since only the 16 most significant digits is only used,
|
||||
* we can safely do a compare without masking if the ce is a variable, we mask
|
||||
* and get only the primary values no shifting to quartenary is required since
|
||||
* all primary values less than variabletop will need to be masked off anyway.
|
||||
* If the end character is composite and the pattern ce does not match the text
|
||||
* ce, we skip it until we find a match in the end composite character or when
|
||||
* it has passed the character. This is so that we can match pattern "a" with
|
||||
* the text "\u00e6"
|
||||
* @param strsrch string search data
|
||||
* @param status error status if any
|
||||
* @return TRUE if an exact match is found, FALSE otherwise
|
||||
*/
|
||||
UBool usearch_handleNextExact(UStringSearch *strsrch, UErrorCode *status);
|
||||
|
||||
/**
|
||||
* Canonical matches.
|
||||
* According to the definition, matches found here will include the whole span
|
||||
* of beginning and ending accents if it overlaps that region.
|
||||
* @param strsrch string search data
|
||||
* @param status error status if any
|
||||
* @return TRUE if a canonical match is found, FALSE otherwise
|
||||
*/
|
||||
UBool usearch_handleNextCanonical(UStringSearch *strsrch, UErrorCode *status);
|
||||
|
||||
/**
|
||||
* Gets the previous match.
|
||||
* Comments follows from handleNextExact
|
||||
* @param strsrch string search data
|
||||
* @param status error status if any
|
||||
*/
|
||||
UBool usearch_handlePreviousExact(UStringSearch *strsrch, UErrorCode *status);
|
||||
|
||||
/**
|
||||
* Canonical matches.
|
||||
* According to the definition, matches found here will include the whole span
|
||||
* of beginning and ending accents if it overlaps that region.
|
||||
* @param strsrch string search data
|
||||
* @param status error status if any
|
||||
* @return TRUE if a canonical match is found, FALSE otherwise
|
||||
*/
|
||||
UBool usearch_handlePreviousCanonical(UStringSearch *strsrch,
|
||||
UErrorCode *status);
|
||||
|
||||
#endif
|
||||
|
||||
|
||||
Loading…
Add table
Reference in a new issue