// © 2016 and later: Unicode, Inc. and others. // License & terms of use: http://www.unicode.org/copyright.html /* ******************************************************************************* * Copyright (C) 2012-2015, International Business Machines * Corporation and others. All Rights Reserved. ******************************************************************************* * collationdatabuilder.cpp * * (replaced the former ucol_elm.cpp) * * created on: 2012apr01 * created by: Markus W. Scherer */ #include "unicode/utypes.h" #if !UCONFIG_NO_COLLATION #include "unicode/localpointer.h" #include "unicode/uchar.h" #include "unicode/ucharstrie.h" #include "unicode/ucharstriebuilder.h" #include "unicode/uniset.h" #include "unicode/unistr.h" #include "unicode/usetiter.h" #include "unicode/utf16.h" #include "cmemory.h" #include "collation.h" #include "collationdata.h" #include "collationdatabuilder.h" #include "collationfastlatinbuilder.h" #include "collationiterator.h" #include "normalizer2impl.h" #include "utrie2.h" #include "uvectr32.h" #include "uvectr64.h" #include "uvector.h" U_NAMESPACE_BEGIN CollationDataBuilder::CEModifier::~CEModifier() { … } /** * Build-time context and CE32 for a code point. * If a code point has contextual mappings, then the default (no-context) mapping * and all conditional mappings are stored in a singly-linked list * of ConditionalCE32, sorted by context strings. * * Context strings sort by prefix length, then by prefix, then by contraction suffix. * Context strings must be unique and in ascending order. */ struct ConditionalCE32 : public UMemory { … }; U_CDECL_BEGIN void U_CALLCONV uprv_deleteConditionalCE32(void *obj) { … } U_CDECL_END /** * Build-time collation element and character iterator. * Uses the runtime CollationIterator for fetching CEs for a string * but reads from the builder's unfinished data structures. * In particular, this class reads from the unfinished trie * and has to avoid CollationIterator::nextCE() and redirect other * calls to data->getCE32() and data->getCE32FromSupplementary(). * * We do this so that we need not implement the collation algorithm * again for the builder and make it behave exactly like the runtime code. * That would be more difficult to test and maintain than this indirection. * * Some CE32 tags (for example, the DIGIT_TAG) do not occur in the builder data, * so the data accesses from those code paths need not be modified. * * This class iterates directly over whole code points * so that the CollationIterator does not need the finished trie * for handling the LEAD_SURROGATE_TAG. */ class DataBuilderCollationIterator : public CollationIterator { … }; DataBuilderCollationIterator::DataBuilderCollationIterator(CollationDataBuilder &b) : … { … } DataBuilderCollationIterator::~DataBuilderCollationIterator() { … } int32_t DataBuilderCollationIterator::fetchCEs(const UnicodeString &str, int32_t start, int64_t ces[], int32_t cesLength) { … } void DataBuilderCollationIterator::resetToOffset(int32_t newOffset) { … } int32_t DataBuilderCollationIterator::getOffset() const { … } UChar32 DataBuilderCollationIterator::nextCodePoint(UErrorCode & /*errorCode*/) { … } UChar32 DataBuilderCollationIterator::previousCodePoint(UErrorCode & /*errorCode*/) { … } void DataBuilderCollationIterator::forwardNumCodePoints(int32_t num, UErrorCode & /*errorCode*/) { … } void DataBuilderCollationIterator::backwardNumCodePoints(int32_t num, UErrorCode & /*errorCode*/) { … } uint32_t DataBuilderCollationIterator::getDataCE32(UChar32 c) const { … } uint32_t DataBuilderCollationIterator::getCE32FromBuilderData(uint32_t ce32, UErrorCode &errorCode) { … } // ------------------------------------------------------------------------- *** CollationDataBuilder::CollationDataBuilder(UBool icu4xMode, UErrorCode &errorCode) : … { … } CollationDataBuilder::~CollationDataBuilder() { … } void CollationDataBuilder::initForTailoring(const CollationData *b, UErrorCode &errorCode) { … } UBool CollationDataBuilder::maybeSetPrimaryRange(UChar32 start, UChar32 end, uint32_t primary, int32_t step, UErrorCode &errorCode) { … } uint32_t CollationDataBuilder::setPrimaryRangeAndReturnNext(UChar32 start, UChar32 end, uint32_t primary, int32_t step, UErrorCode &errorCode) { … } uint32_t CollationDataBuilder::getCE32FromOffsetCE32(UBool fromBase, UChar32 c, uint32_t ce32) const { … } UBool CollationDataBuilder::isCompressibleLeadByte(uint32_t b) const { … } UBool CollationDataBuilder::isAssigned(UChar32 c) const { … } uint32_t CollationDataBuilder::getLongPrimaryIfSingleCE(UChar32 c) const { … } int64_t CollationDataBuilder::getSingleCE(UChar32 c, UErrorCode &errorCode) const { … } int32_t CollationDataBuilder::addCE(int64_t ce, UErrorCode &errorCode) { … } int32_t CollationDataBuilder::addCE32(uint32_t ce32, UErrorCode &errorCode) { … } int32_t CollationDataBuilder::addConditionalCE32(const UnicodeString &context, uint32_t ce32, UErrorCode &errorCode) { … } void CollationDataBuilder::add(const UnicodeString &prefix, const UnicodeString &s, const int64_t ces[], int32_t cesLength, UErrorCode &errorCode) { … } void CollationDataBuilder::addCE32(const UnicodeString &prefix, const UnicodeString &s, uint32_t ce32, UErrorCode &errorCode) { … } uint32_t CollationDataBuilder::encodeOneCEAsCE32(int64_t ce) { … } uint32_t CollationDataBuilder::encodeOneCE(int64_t ce, UErrorCode &errorCode) { … } uint32_t CollationDataBuilder::encodeCEs(const int64_t ces[], int32_t cesLength, UErrorCode &errorCode) { … } uint32_t CollationDataBuilder::encodeExpansion(const int64_t ces[], int32_t length, UErrorCode &errorCode) { … } uint32_t CollationDataBuilder::encodeExpansion32(const int32_t newCE32s[], int32_t length, UErrorCode &errorCode) { … } uint32_t CollationDataBuilder::copyFromBaseCE32(UChar32 c, uint32_t ce32, UBool withContext, UErrorCode &errorCode) { … } int32_t CollationDataBuilder::copyContractionsFromBaseCE32(UnicodeString &context, UChar32 c, uint32_t ce32, ConditionalCE32 *cond, UErrorCode &errorCode) { … } class CopyHelper { … }; U_CDECL_BEGIN static UBool U_CALLCONV enumRangeForCopy(const void *context, UChar32 start, UChar32 end, uint32_t value) { … } U_CDECL_END void CollationDataBuilder::copyFrom(const CollationDataBuilder &src, const CEModifier &modifier, UErrorCode &errorCode) { … } void CollationDataBuilder::optimize(const UnicodeSet &set, UErrorCode &errorCode) { … } void CollationDataBuilder::suppressContractions(const UnicodeSet &set, UErrorCode &errorCode) { … } UBool CollationDataBuilder::getJamoCE32s(uint32_t jamoCE32s[], UErrorCode &errorCode) { … } void CollationDataBuilder::setDigitTags(UErrorCode &errorCode) { … } U_CDECL_BEGIN static UBool U_CALLCONV enumRangeLeadValue(const void *context, UChar32 /*start*/, UChar32 /*end*/, uint32_t value) { … } U_CDECL_END void CollationDataBuilder::setLeadSurrogates(UErrorCode &errorCode) { … } void CollationDataBuilder::build(CollationData &data, UErrorCode &errorCode) { … } void CollationDataBuilder::buildMappings(CollationData &data, UErrorCode &errorCode) { … } void CollationDataBuilder::clearContexts() { … } void CollationDataBuilder::buildContexts(UErrorCode &errorCode) { … } uint32_t CollationDataBuilder::buildContext(ConditionalCE32 *head, UErrorCode &errorCode) { … } int32_t CollationDataBuilder::addContextTrie(uint32_t defaultCE32, UCharsTrieBuilder &trieBuilder, UErrorCode &errorCode) { … } void CollationDataBuilder::buildFastLatinTable(CollationData &data, UErrorCode &errorCode) { … } int32_t CollationDataBuilder::getCEs(const UnicodeString &s, int64_t ces[], int32_t cesLength) { … } int32_t CollationDataBuilder::getCEs(const UnicodeString &prefix, const UnicodeString &s, int64_t ces[], int32_t cesLength) { … } int32_t CollationDataBuilder::getCEs(const UnicodeString &s, int32_t start, int64_t ces[], int32_t cesLength) { … } U_NAMESPACE_END #endif // !UCONFIG_NO_COLLATION
Codebase Browser
chromium