#include "ddcConfig.h"
#include <stdint.h>
#include <stdio.h>
#include <assert.h>
#include <stdarg.h>
#include <string.h>
#include <ctype.h>
#include <string>
#include <algorithm>
#include <stdexcept>
#include <vector>
#include "set"
#include "stack"
#include "map"
#include "time.h"
#include <unistd.h>
Go to the source code of this file.
#define WIN32_LEAN_AND_MEAN |
#define _QM | ( | X | ) | (((QWORD)1)<<X) |
Referenced by CLemWord::AddDes(), ConvertToPlural(), CLemWord::DelDes(), CGraLine::DelDes(), CAncodePattern::DeleteAncodesByGrammemIfCan(), FiniteFormCoordRussian(), GenderNumber(), GenderNumberCaseAnimRussian(), GenderNumberCaseNotAnimRussian(), GenderNumberGerman(), GetGramInfosFromWord(), CGraphmatFile::GetGraphematicalLine(), CRusGramTab::GleicheGenderNumberCase(), CAgramtab::grammems_to_str(), CLemWord::HasDes(), CUnitHolder::HasDescr(), CAncodePattern::HasGrammem(), CGraLine::HasMacroSyntaxDelimiter(), CRusGramTab::is_morph_personal_pronoun(), CGraLine::IsWordOrNumberOrAbbr(), CGraLine::MakeSpaces(), MixedGleiche(), parse_gra_descriptors(), CLemWord::ProcessGraphematicalDescriptors(), CRusGramTab::ProcessPOSAndGrammems(), CAgramtab::ProcessPOSAndGrammems(), CGraLine::SetDes(), SoloGleiche(), SubjectPredicate(), SubjectPredicateGerman(), and WeakGleiche().
typedef unsigned char BYTE |
typedef unsigned int DWORD |
typedef unsigned short WORD |
typedef long long QWORD |
typedef unsigned int UINT |
typedef vector<string> StringVector |
typedef set<string> StringSet |
typedef vector<DWORD> DwordVector |
typedef QWORD file_off_t |
enum MorphLanguageEnum |
enum KillHomonymsEnum |
enum EThesType |
enum EUnitType |
enum RegisterEnum |
QWORD GetMaxQWORD | ( | ) | [inline] |
bool FileExists | ( | const char * | FName | ) |
Referenced by CCOMSyntaxHolder::BuildBeforeSyntax(), CHitBorders::CBreakCollection::ClearAll(), CConcIndexator::DestroyIndex(), CIndexSetForQueryingStage::DestroyIndexSet(), CStringIndexSet::DestroyIndexSet(), CConcXml::FinalSaveBibliography(), IsRmlRegistered(), LoadHosts(), CIndexSetForBigrams::LoadIndexSet(), main(), MakePath(), CHitBorders::RemoveHitBordersFileAndClear(), RemoveWithPrint(), SortWithFiles(), and CConcXml::UniteBibliography().
file_off_t FileSize | ( | const char * | filename | ) |
References FSeek(), and FTell().
Referenced by CConcXml::CheckBibl(), ConvertBufferOffsetToTokenId(), CIndexSetForBigrams::ConvertTempBigramsToPersistent(), CIndexSetForBigrams::CreateRightBigrams(), CIndexSetForQueryingStage::GetOccurrsFileSize(), CIndexSetForQueryingStage::LoadPeriodDevision(), CShortStringHolder::ReadShortStringHolder(), ReadVector(), SortWithFiles(), UnionBinaryFiles(), and CConcXml::UniteBibliography().
bool FSeek | ( | FILE * | fp, | |
file_off_t | pos, | |||
int | origin | |||
) |
References _fseeki64().
Referenced by CStringIndexSet::DumpStorage(), FileSize(), CConcXml::GetFullBibliographyOfHit(), CStringIndexSet::GetTokensFromStorage(), ReadOccurrences(), CIndexBigram::ReadSecondWords(), and CStringIndexSet::SaveOnePartOfUnionTokenStorage().
file_off_t FTell | ( | FILE * | fp | ) |
Referenced by FileSize(), and CItemIndexForLoading::ReadFromTemporalFile().
void ErrorMessage | ( | const string & | Titul, | |
const string & | Message | |||
) |
References GlobalErrorMessage.
Referenced by CIndexSetForQueryingStage::AddOneIndexItem(), CIndexSetForQueryingStage::AssertHasPath(), CConcIndexator::AssertHasPath(), CCOMSyntaxHolder::BuildBeforeSyntax(), CConcIndexatorInvoker::BuildIndex(), CGraphanDicts::BuildOborot(), CGraphanDicts::BuildOborottos(), CCOMSyntaxHolder::BuildSyntax(), MorphoWizard::check_paradigm(), CheckEvaluationTime(), CShortStringHolder::CreateFromSequence(), CConcIndexator::CreateMorphIndex(), CMyTimeSpanHolder::EndTimer(), ErrorMessage(), MorphoWizard::find_lemm(), MorphoWizard::find_wordforms(), CConcHolder::GenerateHitStrings(), CConcHolder::GenerateOneHitString(), CConcHolder::GenerateOneHitStringJson(), CConcHolder::GetContext(), CConcHolder::GetContextJson(), GetCWBFormattedStringRecursive(), CDDCServerListenHost::GetFirstHitsFromCorpora(), CConcHolder::GetHits(), CDDCServerListenHost::GetHitStringsFromOneCorpora(), CConcHolder::GetOccurrences(), GetTextFromXMLRecursive(), CStringIndexator::IndexOneToken(), InitAlphabet(), CAncodePattern::InitAncodePattern(), InitMorphologySystem(), CMorphDict::Load(), CMorphAutomat::Load(), CConcXml::LoadBibl(), CConcIndexator::LoadCorpusFiles(), CConcIndexator::LoadFileIntoGraphan(), CMorphologyHolder::LoadGraphanAndLemmatizer(), CConcIndexator::LoadOptionsFromString(), CConcIndexator::LoadProject(), CSyntaxHolder::LoadSyntax(), CCOMSyntaxHolder::LoadSyntax(), CCOMSyntaxHolder::LoadSyntaxModule(), CConcIndexator::LoadXmlFile(), CAncodePattern::ModifyGrammems(), MorphoWizard::predict_lemm(), CHomonym::ProcessLemmaAndGrammems(), CConcXml::CFreeBiblIndex::ReadFromDisk(), ReadTimeOutFromRegistry(), CHitBorders::RegisterBorderIndices(), CHitBorders::RegisterBreak(), CStringIndexator::RegisterStringIndices(), CMorphDict::Save(), CMorphAutomat::Save(), CConcHolder::SimpleQuery(), CHitBorders::StartIndexing(), WriteVector(), and WriteVectorInner().
void ErrorMessage | ( | const string & | Message | ) |
string MakeFName | ( | const string & | InpitFileName, | |
const string & | Ext | |||
) |
Referenced by CIndexSetForLoadingStage::AddMemoryLoadIndexToMainLoadIndex(), CIndexSetForLoadingStage::CreateTempFiles(), CConcXml::GetBiblDateIndexFileName(), CConcXml::GetBiblFileName(), CConcXml::GetBiblIndexFileName(), CHitBorders::CBreakCollection::GetBreakFileName(), CConcIndexatorInvoker::GetErrorLogFileName(), CConcIndexator::GetFileNameForCorpusFileNames(), CIndexSetForQueryingStage::GetFileNameForInfos(), CConcIndexator::GetFileNameForMaskedFiles(), CConcXml::CFreeBiblIndex::GetIndexFileName(), CStringIndexSet::GetLeftBigramsFileName(), CIndexSetForQueryingStage::GetOccHdrFileName(), CIndexSetForQueryingStage::GetOccursFileName(), CHitBorders::GetPageBreaksFileName(), CIndexSetForQueryingStage::GetPeriodsDevisionFileName(), CIndexSetForBigrams::GetRightToLeftPerdiv(), CStringIndexator::GetSearchPeriodsFileName(), CStringIndexSet::GetStorageFileName(), CConcXml::CFreeBiblStringIndex::GetStringFileName(), CConcIndexatorInvoker::GetTimeStatisticsFileName(), CBigrams::Initialize(), CMorphDict::Load(), CConcIndexator::LoadSourceFilesAndOptions(), main(), CGraphanDicts::ReadAbbrevations(), CMorphDict::Save(), and CConcIndexator::SaveOptions().
bool MakePath | ( | const char * | RossPath, | |
const char * | FileName, | |||
char * | FullPath | |||
) |
References FileExists().
Referenced by TRoss::FullLoad(), TRoss::LoadOnlyConstants(), and TRoss::ReadUnitComments().
string GetPathByFile | ( | string | FileName | ) |
Referenced by CConcIndexatorInvoker::BuildIndex(), MorphoWizard::get_predict_src_file_path(), and GetFullPathByName().
bool IsBinFile | ( | const char * | FileName | ) |
Referenced by TRoss::BuildCorteges(), TRoss::BuildUnits(), and TRoss::ReadUnitComments().
bool IsEmptyLine | ( | const char * | t | ) |
bool IsHtmlFile | ( | const string & | FileName | ) |
References EngMakeLower(), and FileExtension().
Referenced by CGraphmatFile::LoadFileToGraphan(), and ReadSourceFile().
bool IsTableFile | ( | const string & | FileName | ) |
bool IsJsonFile | ( | const string & | FileName | ) |
string FileExtension | ( | const string & | FileName | ) |
Referenced by IsHtmlFile(), IsJsonFile(), and IsTableFile().
void AddFile | ( | const char * | MainFile, | |
const char * | ToAdd | |||
) |
References _MAX_PATH.
Referenced by CConcXml::UniteBibliography().
bool RmlMoveFile | ( | const char * | oldpath, | |
const char * | newpath | |||
) |
References RmlCopyFile().
Referenced by CIndexSetForLoadingStage::AddMemoryLoadIndexToMainLoadIndex(), ConvertBufferOffsetToTokenId(), SetRegistryString(), SortWithFiles(), and UnionBinaryFiles().
bool RmlCopyFile | ( | const char * | oldpath, | |
const char * | newpath | |||
) |
string CreateTempFileName | ( | ) |
References _MAX_PATH.
Referenced by ConvertBufferOffsetToTokenId(), CIndexSetForBigrams::ConvertTempBigramsToPersistent(), SetRegistryString(), SortWithFiles(), and UnionBinaryFiles().
bool MakeDir | ( | const string & | txt | ) |
bool RemoveWithPrint | ( | const string & | FileName | ) |
References FileExists().
Referenced by CIndexSetForBigrams::CreateRightBigrams(), CIndexSetForLoadingStage::DeleteTempFiles(), CIndexSetForBigrams::DestroyIndexSet(), and CIndexBigram::RemoveFiles().
string GetRegistryString | ( | string | RegistryPath | ) |
References GetIniFilePath(), GetRmlVariable(), and GetStringInnerFromTheFile().
Referenced by CCOMSyntaxHolder::BuildBeforeSyntax(), CanGetRegistryString(), concord_daemon_log(), CreateLockFile(), GetThesaurusPath(), CGraphmatFile::LoadDicts(), CGraphanDicts::ReadAbbrevations(), and ReadTimeOutFromRegistry().
string GetRegistryStringFromLocalIniFile | ( | string | RegistryPath | ) |
References GetStringInnerFromTheFile().
Referenced by ReadTimeOutFromRegistry().
bool CanGetRegistryString | ( | string | RegistryPath | ) |
References GetRegistryString().
Referenced by GetThesaurusPath().
void SetRegistryString | ( | string | RegistryPath, | |
string | Value | |||
) |
References CreateTempFileName(), GetIniFilePath(), RmlMoveFile(), and Trim().
bool IsRmlRegistered | ( | string & | Error | ) |
References FileExists(), GetIniFilePath(), and CExpc::m_strCause.
Referenced by LoadDDCServer(), LoadLocalCorpora(), and main().
bool CheckEvaluationTime | ( | ) |
struct tm RmlGetCurrentTime | ( | ) | [read] |
Referenced by CheckEvaluationTime(), concord_daemon_log(), CDictionary::SetUnitCurrentTime(), and TUnitComment::TUnitComment().
bool ReadTimeOutFromRegistry | ( | bool | bReadFromLocalFile, | |
int & | TimeOut | |||
) |
References ErrorMessage(), GetRegistryString(), and GetRegistryStringFromLocalIniFile().
string GetIniFilePath | ( | ) |
References GetRmlVariable().
Referenced by GetRegistryString(), IsRmlRegistered(), LoadDDCServer(), LoadLocalCorpora(), main(), and SetRegistryString().
string GetRmlVariable | ( | ) |
References Trim().
Referenced by BuildRMLPath(), GetIniFilePath(), GetRegistryString(), and CLemmatizer::LoadDictionariesRegistry().
string BuildRMLPath | ( | const char * | s | ) |
char* rtrim | ( | char * | s | ) |
bool IsSuperEqualChar | ( | BYTE | ch1, | |
BYTE | ch2, | |||
MorphLanguageEnum | langua | |||
) |
References is_english_upper(), is_russian_upper(), ReverseChar(), and rtolower().
Referenced by CGraphmatFile::FindKeySequence(), strscmp(), and StrSpacingCompare().
bool strscmp | ( | const char * | s1, | |
const char * | s2, | |||
size_t | l, | |||
MorphLanguageEnum | langua | |||
) |
References IsSuperEqualChar().
Referenced by FindSimilarHeadings(), and CUnitHolder::StrSuperCompare().
int CompareWithoutRegister | ( | const char * | s1, | |
const char * | s2, | |||
size_t | l, | |||
MorphLanguageEnum | langua | |||
) |
References ReverseChar().
Referenced by CGraphanDicts::FindInIdents().
bool force_to_rus | ( | char * | dest, | |
const char * | sour, | |||
size_t | len | |||
) |
References force_rus_char(), and is_russian_alpha().
Referenced by CRusCorpXmlFile::CreateGraTable(), and CGraphmatFile::InitNonContextDescriptors().
char* IntToStr | ( | int | Value, | |
char * | Buffer | |||
) |
string& IntToStr | ( | int | Value, | |
string & | oBuffer | |||
) |
string Format | ( | const char * | format, | |
... | ||||
) |
Referenced by MorphoWizard::add_lemma(), CTempArticle::AddCortegeToVector(), AddMessage(), CIndexSetForQueryingStage::AddOneIndexItem(), CHost::AnswerByRequest(), CCOMSyntaxHolder::BuildBeforeSyntax(), TItemContainer::BuildDomens(), CConcIndexatorInvoker::BuildIndex(), CGraphanDicts::BuildOborottos(), TItemContainer::BuildOneFieldFormat(), CConcIndexatorInvoker::BuildOnlyMorphIndex(), MorphoWizard::check_paradigm(), CTempArticle::CheckCortegeVector(), concord_daemon_log(), create_socket(), CHost::CreateListener(), CMyTimeSpanHolder::EndTimer(), escapeCString(), escapeJsonString(), CConcIndexatorInvoker::FinalizeIndex(), CFormInfo::FormatAsInPlmLine(), CConcHolder::GenerateHitStrings(), CConcHolder::GenerateOneHitString(), CConcHolder::GenerateOneHitStringJson(), CHost::GetAddressStr(), GetBigramsAsString(), GetBindErrorLinux(), CHitBorders::GetBorderIndicesString(), CHitBorders::CBreakCollection::GetBreakFileName(), GetConnectedWords(), CConcHolder::GetContext(), CConcHolder::GetContextJson(), GetCWBFormattedStringRecursive(), CLemWord::GetDebugString(), CConcXml::CFreeBiblIndex::GetDescriptionStr(), CConcHolder::GetFileSnippets(), CDDCServerListenHost::GetFirstHitsFromCorpora(), CConcXml::GetFreeBibiAttributesDescr(), CConcHolder::GetHitIds(), CDDCServerListenHost::GetHitStringsFromOneCorpora(), CConcIndexator::GetHtmlReference(), CStringIndexator::GetIndicesString(), CMorphologyHolder::GetParadigmIdsByNormAndAncode(), CLemWord::GetPlmStr(), CPlmLine::GetStr(), CConcXml::CFreeBiblIndex::GetStringValue(), CConcXml::GetTextAreaElements(), CConcXml::GetTextAreasDescr(), GetTextFromXMLRecursive(), CConcHolder::GetTokensFromStorageByBreak(), TRoss::GetUnitTextHeader(), CConcXml::CFreeBiblStringIndex::GetValueForDDCFilter(), GetWordForms(), CMorphologyHolder::id_to_paradigm(), CMorphologyHolder::id_to_string(), CDictionary::ImportFromText(), CConcIndexator::IndexOneTableTextArea(), CStringIndexator::IndexOneToken(), CConcIndexator::IndexTextOrHtmlFile(), CAncodePattern::InitAncodePattern(), CConcHolder::InitLessByRank(), InitMorphologySystem(), TRoss::InsertDomItem(), CMorphDict::Load(), CMorphAutomat::Load(), CConcXml::LoadBibl(), CConcIndexator::LoadCorpusFiles(), LoadDDCServer(), CConcIndexator::LoadFileIntoGraphan(), CGraphmatFile::LoadFileToGraphan(), CDDCCorpusListenHost::LoadHolder(), LoadLocalCorpora(), CConcIndexator::LoadMaskedFiles(), TRoss::LoadOnlyConstants(), CConcIndexator::LoadOptionsFromString(), CConcIndexator::LoadProject(), CConcIndexator::LoadSourceFilesAndOptions(), CGraphmatFile::LoadStringToGraphan(), CConcXml::LoadXmlAndReadBibliography(), CConcIndexator::LoadXmlFile(), CTempArticle::MarkUp(), CAncodePattern::ModifyGrammems(), CHomonym::ProcessLemmaAndGrammems(), CDictionary::ProcessOneArticle(), CPlmLineCollection::ProcessPlmLines(), CDDCServerListenHost::ProcessSocketString(), CDDCCorpusListenHost::ProcessSocketString(), QPEncodeString(), CConcXml::CFreeBiblIndex::ReadFromDisk(), CDumpParadigm::ReadFromFile(), CConcXml::ReadMorphXmlFileIntoGraTable(), MorphoWizard::ReadNextParadigmFromFile(), ReadOccurrences(), MorphoWizard::ReadSessions(), ReadVectorInner(), CHitBorders::RegisterBorderIndices(), CConcXml::RegisterFreeBiblAttributes(), ReloadCorpus(), CDDCServerListenHost::ReloadCorpusProcessSignal(), CDDCServerListenHost::ReplaceHolderIfNeeded(), CHost::RunThread(), CMorphDict::Save(), CMorphAutomat::Save(), MorphoWizard::save_mrd(), CConcHolder::SaveOccurrences(), CConcIndexator::SaveOptionsToString(), SaveTrigger(), send_buffer(), CPlmLine::SetMorph(), MorphoWizard::show_differences_in_two_paradigms(), CConcHolder::ShowBibliographyForTable(), CConcHolder::ShowBibliographyForTextOrHtml(), CConcHolder::SimpleQuery(), CHitBorders::StartIndexing(), tar_header::th_get_pathname(), CAccentModel::ToString(), CMorphSession::ToString(), CHighlightTags::ToString(), UnionBinaryFiles(), and TItemContainer::WriteDomens().
string& TrimLeft | ( | string & | str | ) |
string& TrimRight | ( | string & | str | ) |
string& Trim | ( | string & | str | ) |
References TrimLeft(), and TrimRight().
Referenced by AddMessage(), MorphoWizard::AddPrefixSet(), BuildHtmlHitStrWithHighlighting(), MorphoWizard::check_common_grammems(), MorphoWizard::check_prefixes(), CQueryTokenNode::CreateFileList(), CRusCorpXmlFile::CreateGraTable(), DeleteEmptyLines(), MorphoWizard::find_wordforms(), CHitBorders::GetBorderIndicesString(), GetCWBFormattedStringRecursive(), CStringIndexator::GetIndicesString(), GetInterfacePOS(), GetRmlVariable(), GetStringInnerFromTheFile(), GetTextFromXMLRecursive(), GetValue(), CDictionary::ImportFromText(), CConcIndexator::IndexOneTableTextArea(), CMorphDict::Load(), CConcIndexator::LoadCorpusFiles(), LoadHosts(), CConcIndexator::LoadMaskedFiles(), CConcIndexator::LoadOptionsFromString(), CPlmLine::LoadPlmLineFromString(), NormalizeOborotStr(), CQueryParser::ParseQuery(), CQueryParser::ParseQueryOperators(), CQueryParser::ParseSortAndFilterOperators(), CDDCServerListenHost::ProcessSocketString(), CConcXml::ProcessTextAreaNoInQueryStr(), ReadAbbrevationsFromOneFile(), CConcXml::CFreeBiblStringIndex::ReadBiblStringItems(), TRoss::ReadConfig(), ReadFlexiaModels(), CDumpParadigm::ReadFromFile(), ReadFromHtml(), CFlexiaModel::ReadFromString(), CHost::ReadFromString(), CHighlightTags::ReadFromString(), CBibliography::ReadFromString(), CGraphanDicts::ReadIdents(), CConcXml::ReadMorphXmlFileIntoGraTable(), MorphoWizard::ReadOnePrefixSet(), CLemmatizer::ReadOptions(), CDwdsThesaurus::ReadPathFromString(), CDDCServerListenHost::ReadPossibleHosts(), CSourceFileHolder::ReadSourceFileList(), ReadXmlField(), CConcXml::CFreeBiblStringIndex::RegisterBiblStringItemId(), CHitBorders::RegisterBorderIndices(), CConcXml::RegisterFreeBiblAttributes(), CStringIndexator::RegisterStringIndices(), CConcXml::RegisterTextAreas(), SetRegistryString(), and MorphoWizard::slf_to_mrd().
void rml_TRACE | ( | const char * | format, | |
... | ||||
) |
bool LoadFileToString | ( | string | FileName, | |
string & | Result | |||
) |
References ReadVector().
Referenced by CGraphmatFile::LoadFileToGraphan(), CConcIndexator::LoadOptionsFromString(), CConcIndexator::LoadSourceFilesAndOptions(), and CLemmatizer::ReadOptions().
void SqueezeSpacesAndDeleteEoln | ( | string & | s | ) |
void KOI8ToWin | ( | string & | s | ) |
void WinToKOI8 | ( | string & | s | ) |
DWORD StringCrc32 | ( | const char * | szString | ) |
void QPEncodeString | ( | string & | s | ) |
void QPDecodeString | ( | string & | s | ) |
void strrev | ( | char * | s | ) |
int GetPredictionPartOfSpeech | ( | const string & | PartOfSpeech, | |
MorphLanguageEnum | langua | |||
) |
References morphEnglish, morphGerman, morphRussian, and UnknownPartOfSpeech.
Referenced by CMorphDictBuilder::GenerateUnitedFlexModels(), and MorphoWizard::predict_lemm().
bool GetLanguageByString | ( | string | s, | |
MorphLanguageEnum & | Result | |||
) |
References EngRusMakeUpper().
Referenced by MorphoWizard::load_wizard(), and CConcIndexator::LoadOptionsFromString().
string GetStringByLanguage | ( | MorphLanguageEnum | Langua | ) |
References morphEnglish, morphGeneric, morphGerman, morphRussian, and morphURL.
Referenced by InitMorphologySystem(), CMorphAutomat::Load(), MorphoWizard::load_gramtab(), MorphoWizard::load_static(), CConcIndexator::LoadOptionsFromString(), and CConcIndexator::SaveOptionsToString().
void ClearVector | ( | vector< T > & | V | ) |
References TinyXPath::dummy.
Referenced by CUnitHolder::ClearInputBuffer(), CItemIndexForLoading::ClearOccurrences(), CQueryResult::ClearQueryResults(), CIndexSetForQueryingStage::DestroyIndexSet(), CStringIndexSet::DestroyIndexSet(), CUnitHolder::FreeTable(), CSyntaxHolder::GetSentencesFromSynAn(), CPlmLineCollection::ProcessPlmLines(), and CQueryNode::~CQueryNode().
int isbracket | ( | BYTE | x | ) |
Referenced by CGraphmatFile::InitNonContextDescriptors(), is_word_delim(), and CGraLine::ReadWord().
size_t dual_bracket | ( | BYTE | x | ) |
bool is_upper_roman_digit | ( | BYTE | ch | ) |
References ASCII, and UpRomDigits.
Referenced by SimilarBullets().
bool is_lower_roman_digit | ( | BYTE | ch | ) |
References ASCII, and LwRomDigits.
Referenced by SimilarBullets().
bool is_roman_number | ( | const char * | s, | |
size_t | len | |||
) |
References ASCII, LwRomDigits, and UpRomDigits.
Referenced by CPlmLine::LoadPlmLineFromString(), and CLemWord::ProcessGraphematicalDescriptors().
bool is_pseudo_graph | ( | BYTE | x | ) |
Referenced by is_word_delim(), and CGraLine::ReadWord().
bool is_word_delim | ( | BYTE | x | ) |
References cCompanyChar, cEllipseChar, cIonChar, cNumberChar, cPiChar, is_pseudo_graph(), and isbracket().
bool is_spc_fill | ( | BYTE | x | ) |
Referenced by CGraLine::ReadWord(), and StrSpacingCompare().
bool is_english_upper | ( | BYTE | x | ) |
References ASCII, and EngUpper.
Referenced by gtolower(), is_english_alpha(), is_upper_alpha(), CUnitHolder::is_uppercase(), IsSuperEqualChar(), and ReverseChar().
bool is_english_lower | ( | BYTE | x | ) |
References ASCII, and EngLower.
Referenced by EngMakeUpper(), EngRusMakeUpper(), GerEngRusMakeUpperTemplate(), gtoupper(), is_english_alpha(), is_lower_alpha(), CUnitHolder::is_lowercase(), and ReverseChar().
bool is_german_upper | ( | BYTE | x | ) |
References ASCII, and GerUpper.
Referenced by HaveEquCase(), is_german_alpha(), is_upper_alpha(), and CUnitHolder::is_uppercase().
bool is_german_lower | ( | BYTE | x | ) |
References ASCII, and GerLower.
Referenced by GerEngRusMakeUpperTemplate(), GerMakeUpper(), HaveEquCase(), is_german_alpha(), is_lower_alpha(), and CUnitHolder::is_lowercase().
bool is_russian_upper | ( | BYTE | x | ) |
References ASCII, and RusUpper.
Referenced by TItemContainer::CanBeRusAbbr(), EngRusMakeLower(), HaveEquCase(), is_russian_alpha(), is_russian_upper_consonant(), is_upper_alpha(), CUnitHolder::is_uppercase(), IsSuperEqualChar(), ReverseChar(), rtolower(), and RusMakeLower().
bool is_russian_lower | ( | BYTE | x | ) |
References ASCII, and RusLower.
Referenced by EngRusMakeUpper(), GerEngRusMakeUpperTemplate(), HaveEquCase(), is_lower_alpha(), CUnitHolder::is_lowercase(), is_russian_alpha(), is_russian_lower_consonant(), ReverseChar(), rtoupper(), and RusMakeUpper().
bool is_lower_consonant | ( | BYTE | x, | |
MorphLanguageEnum | Langua | |||
) |
bool is_upper_consonant | ( | BYTE | x, | |
MorphLanguageEnum | Langua | |||
) |
References is_upper_alpha(), and is_upper_vowel().
Referenced by CLemmatizer::CheckAbbreviation().
bool is_lower_vowel | ( | BYTE | x, | |
MorphLanguageEnum | Langua | |||
) |
References is_english_lower_vowel(), is_german_lower_vowel(), is_russian_lower_vowel(), morphEnglish, morphGerman, and morphRussian.
Referenced by is_lower_consonant(), MorphoWizard::slf_to_mrd(), and TransferReverseVowelNoToCharNo().
bool is_upper_vowel | ( | BYTE | x, | |
MorphLanguageEnum | Langua | |||
) |
References is_english_upper_vowel(), is_german_upper_vowel(), is_russian_upper_vowel(), morphEnglish, morphGerman, and morphRussian.
Referenced by is_upper_consonant(), and TransferReverseVowelNoToCharNo().
bool is_english_alpha | ( | BYTE | x | ) |
References is_english_lower(), and is_english_upper().
Referenced by CGraphmatFile::DealExtensionsAndLocalFileNames(), is_alpha(), is_generic_alpha(), CUnitHolder::is_latin_alpha(), and CDDCServerListenHost::ReadPossibleHosts().
bool is_russian_alpha | ( | BYTE | x | ) |
References is_russian_lower(), and is_russian_upper().
Referenced by TItemContainer::CanBeRusAbbr(), TItemContainer::CanBeRusColloc(), force_to_rus(), CGraphmatFile::InitNonContextDescriptors(), is_alpha(), TItemContainer::IsStandardRusLexeme(), and CGraLine::LengthUntilDelimiters().
bool is_german_alpha | ( | BYTE | x | ) |
References is_german_lower(), and is_german_upper().
Referenced by is_alpha(), and CUnitHolder::is_latin_alpha().
bool is_alpha | ( | BYTE | x | ) |
References is_german_alpha(), and is_russian_alpha().
Referenced by GetMorphSignPosition(), InitAlphabet(), CGraLine::LengthUntilDelimiters(), NormalizeOborotStr(), and RmlPcreMakeTables().
bool is_alpha | ( | BYTE | x, | |
MorphLanguageEnum | langua | |||
) |
References is_english_alpha(), is_generic_alpha(), is_german_alpha(), is_russian_alpha(), is_URL_alpha(), morphEnglish, morphGeneric, morphGerman, morphRussian, and morphURL.
bool is_lower_alpha | ( | BYTE | x, | |
MorphLanguageEnum | langua | |||
) |
References is_english_lower(), is_generic_lower(), is_german_lower(), is_russian_lower(), morphEnglish, morphGeneric, morphGerman, morphRussian, and morphURL.
Referenced by AddFormsWithDifferentRegisters(), TItemContainer::CanBeRusAbbr(), is_lower_consonant(), and RmlPcreMakeTables().
bool is_upper_alpha | ( | BYTE | x, | |
MorphLanguageEnum | langua | |||
) |
References is_english_upper(), is_generic_upper(), is_german_upper(), is_russian_upper(), morphEnglish, morphGeneric, morphGerman, morphRussian, and morphURL.
Referenced by AbbrevIsEqualToString(), CConcIndexator::CreateMorphIndex(), GetWordForms(), InitAlphabet(), is_upper_consonant(), IsUpper(), MorphoWizard::ReadOnePrefixSet(), and RmlPcreMakeTables().
bool isnspace | ( | BYTE | x | ) |
Referenced by EngMakeUpper(), EngRusMakeUpper(), GerEngRusMakeUpperTemplate(), gtoupper(), and ReverseChar().
Referenced by EngRusMakeLower(), gtolower(), and ReverseChar().
References Apostrophe, is_russian_lower(), LowerJO, and UpperJO.
Referenced by EngRusMakeUpper(), GerEngRusMakeUpperTemplate(), ReverseChar(), and RusMakeUpper().
References Apostrophe, is_russian_upper(), LowerJO, and UpperJO.
Referenced by EngRusMakeLower(), IsSuperEqualChar(), ReverseChar(), and RusMakeLower().
References Auml, auml, etoupper(), is_english_lower(), Ouml, ouml, Uuml, and uuml.
Referenced by GerEngRusMakeUpperTemplate(), and GerMakeUpper().
References auml, Auml, etolower(), is_english_upper(), ouml, Ouml, uuml, and Uuml.
BYTE ReverseChar | ( | BYTE | ch, | |
MorphLanguageEnum | langua | |||
) |
References auml, Auml, etolower(), etoupper(), is_english_lower(), is_english_upper(), is_russian_lower(), is_russian_upper(), morphGeneric, morphGerman, ouml, Ouml, rtolower(), rtoupper(), uuml, and Uuml.
Referenced by AddFormsWithDifferentRegisters(), CompareWithoutRegister(), GetWordForms(), CGraphmatFile::IsKey(), IsSuperEqualChar(), CGraphanDicts::ReadIdents(), and RmlPcreMakeTables().
char* RusMakeUpper | ( | char * | word | ) |
References is_russian_lower(), RegisterConverter(), and rtoupper().
char* EngMakeUpper | ( | char * | word | ) |
References etoupper(), is_english_lower(), and RegisterConverter().
Referenced by CConcHolder::GetResultFormatByString().
string& EngMakeUpper | ( | string & | word | ) |
string& EngMakeLower | ( | string & | word | ) |
References RegisterConverter().
Referenced by IsHtmlFile(), IsJsonFile(), and IsTableFile().
char* GerMakeUpper | ( | char * | word | ) |
References gtoupper(), is_german_lower(), and RegisterConverter().
Referenced by CHomonym::SetLemma().
string& GerMakeUpper | ( | string & | word | ) |
char* RusMakeLower | ( | char * | word | ) |
References is_russian_upper(), RegisterConverter(), and rtolower().
string& EngRusMakeLower | ( | string & | word | ) |
References etolower(), is_russian_upper(), and rtolower().
Referenced by CXmlMorphAnnot::BuildRusCorpAnnot(), and RmlMakeLower().
char* EngRusMakeLower | ( | char * | word | ) |
References etolower(), is_russian_upper(), and rtolower().
char* RmlMakeUpper | ( | char * | word, | |
MorphLanguageEnum | langua | |||
) |
References GerEngRusMakeUpperTemplate().
Referenced by AddFormsWithDifferentRegisters(), CQueryTokenNode::CreateThesPattern(), MorphoWizard::find_lemm(), CLemmatizer::LemmatizeWord(), CUnitHolder::MakeOneWord(), NormalizeOborotStr(), ReadAbbrevationsFromOneFile(), CGraphanDicts::ReadENames(), CGraphanDicts::ReadKeyboard(), MorphoWizard::ReadOnePrefixSet(), CLemWord::SetWordStr(), and MorphoWizard::slf_to_mrd().
string& RmlMakeUpper | ( | string & | word, | |
MorphLanguageEnum | langua | |||
) |
string& RmlMakeLower | ( | string & | word, | |
MorphLanguageEnum | langua | |||
) |
References EngRusMakeLower(), morphGerman, and RegisterConverter().
Referenced by AddFormsWithDifferentRegisters(), CQueryTokenNode::CreateTokenPattern(), MorphoWizard::get_lemm_string_with_accents(), CFormInfo::GetAccentedVowel(), GetWordForms(), CConcIndexator::LoadOptionsFromString(), MorphoWizard::mrd_to_slf(), and CConcXml::RegisterTextAreas().
string& EngRusMakeUpper | ( | string & | word | ) |
References etoupper(), is_russian_lower(), and rtoupper().
Referenced by CBigrams::GetBigrams(), GetLanguageByString(), CGraphanDicts::ReadExtensions(), and CPlmLine::SetWord().
char* EngRusMakeUpper | ( | char * | word | ) |
References etoupper(), is_english_lower(), is_russian_lower(), and rtoupper().
bool IsRussian | ( | const char * | word | ) |
References CheckLanguage(), and morphRussian.
Referenced by TRoss::ReadFromStrWithOneSignatura().
bool IsRussian | ( | const string & | word | ) |
bool IsEnglish | ( | const char * | word | ) |
bool IsEnglish | ( | const string & | word | ) |
bool IsGerman | ( | const char * | word | ) |
bool IsGerman | ( | const string & | word | ) |
bool CheckLanguage | ( | const char * | word, | |
MorphLanguageEnum | langua | |||
) |
bool CheckLanguage | ( | const string & | word, | |
MorphLanguageEnum | langua | |||
) |
void ConvertJO2Je | ( | string & | src | ) |
void ConvertJO2Je | ( | char * | src | ) |
void ConvertJO2Je | ( | char * | src, | |
size_t | Length | |||
) |
References ConvertJO2JeTemplate().
Referenced by CRusCorpXmlFile::CreateGraTable(), CLemmatizerRussian::FilterSrc(), CGraphmatFile::GraphmatMain(), and MorphoWizard::prepare_for_RML().
string ConvertASCIIToHtmlSymbols | ( | const string & | txt | ) |
Referenced by BuildHtmlHitStrWithHighlighting(), CConSent::GetString(), and CConcHolder::ShowBibliographyForTable().
T& RegisterConverter | ( | T & | word, | |
size_t | Len, | |||
Pred | P, | |||
Conv | C | |||
) |
Referenced by EngMakeLower(), EngMakeUpper(), GerEngRusMakeUpperTemplate(), GerMakeUpper(), RmlMakeLower(), RusMakeLower(), and RusMakeUpper().
T& GerEngRusMakeUpperTemplate | ( | T & | word, | |
MorphLanguageEnum | Langua, | |||
size_t | Len | |||
) |
References etoupper(), gtoupper(), is_english_lower(), is_german_lower(), is_russian_lower(), morphGerman, RegisterConverter(), and rtoupper().
Referenced by CUnitHolder::BuildUnitBufferUpper(), and RmlMakeUpper().
const unsigned int _MAX_PATH = 512 |
Referenced by AddFile(), CConcIndexatorInvoker::BuildIndex(), and CreateTempFileName().
const BYTE cHyphenChar = (BYTE) '-' |
Referenced by CGraphmatFile::InitNonContextDescriptors().
const BYTE cPeriodChar = (BYTE) '.' |
const BYTE cSpaceChar = (BYTE) 32 |
const BYTE cParagraph = (BYTE) 21 |
Referenced by CGraLine::ReadWord().
const BYTE cCompanyChar = (BYTE) 176 |
Referenced by is_word_delim(), and CGraLine::ReadWord().
Referenced by is_word_delim(), and CGraLine::ReadWord().
const BYTE cNumberChar = (BYTE) 0xB9 |
Referenced by is_word_delim(), and CGraLine::ReadWord().
Referenced by is_word_delim(), and CGraLine::ReadWord().
const BYTE cEllipseChar = (BYTE) 133 |
Referenced by is_word_delim(), CUnitHolder::IsSentenceEndMark(), and CGraLine::ReadWord().
const BYTE UnknownPartOfSpeech = 0xff |
Referenced by CPlmLine::CPlmLine(), GetGramInfosFromWord(), CAgramtab::GetPartOfSpeech(), GetPredictionPartOfSpeech(), CAgramtab::GetTabStringByGramCode(), GetTagFromStr(), CLemmatizer::LemmatizeWord(), MorphoWizard::load_gramtab(), MorphoWizard::predict_lemm(), and CAgramtab::ProcessPOSAndGrammems().
const int UnknownSyntaxElement = 0xffff |
Referenced by HTML::GetTextFromHTMLBuffer(), gtolower(), gtoupper(), and ReverseChar().
Referenced by HTML::GetTextFromHTMLBuffer(), gtolower(), gtoupper(), and ReverseChar().
Referenced by HTML::GetTextFromHTMLBuffer(), gtolower(), gtoupper(), and ReverseChar().
Referenced by HTML::GetTextFromHTMLBuffer(), gtolower(), gtoupper(), and ReverseChar().
Referenced by etolower(), etoupper(), HTML::GetTextFromHTMLBuffer(), gtolower(), gtoupper(), and ReverseChar().
Referenced by etolower(), etoupper(), HTML::GetTextFromHTMLBuffer(), gtolower(), gtoupper(), and ReverseChar().
Referenced by HTML::GetTextFromHTMLBuffer(), and CGraphmatFile::InitNonContextDescriptors().
Referenced by CGraphmatFile::InitNonContextDescriptors().
Referenced by HTML::GetTextFromHTMLBuffer().
Referenced by HTML::GetTextFromHTMLBuffer().
Referenced by HTML::GetTextFromHTMLBuffer().
Referenced by ConvertJO2JeTemplate(), rtolower(), and rtoupper().
Referenced by ConvertJO2JeTemplate(), rtolower(), and rtoupper().
const BYTE Apostrophe = 39 |
Referenced by CGraLine::LengthUntilDelimiters(), rtolower(), and rtoupper().