crawlserv++  [under development]
Application for crawling and analyzing textual content of websites.
crawlservpp::Data::Corpus Member List

This is the complete list of members for crawlservpp::Data::Corpus, including all inherited members.

ArticleFunc typedefcrawlservpp::Data::Corpus
articleMapcrawlservpp::Data::Corpusprotected
clear()crawlservpp::Data::Corpusinline
combineContinuous(Tokens &chunks, std::vector< TextMap > &articleMaps, std::vector< TextMap > &dateMaps, bool deleteInputData)crawlservpp::Data::Corpusinline
combineTokenized(Tokens &chunks, Sizes &tokenNums, std::vector< TextMap > &articleMaps, std::vector< TextMap > &dateMaps, std::vector< SentenceMap > &sentenceMaps, bool deleteInputData)crawlservpp::Data::Corpusinline
copyChunksContinuous(std::size_t chunkSize, Tokens &to, std::vector< TextMap > &articleMapsTo, std::vector< TextMap > &dateMapsTo) constcrawlservpp::Data::Corpusinline
copyChunksTokenized(std::size_t chunkSize, Tokens &to, Sizes &tokenNumsTo, std::vector< TextMap > &articleMapsTo, std::vector< TextMap > &dateMapsTo, std::vector< SentenceMap > &sentenceMapsTo) constcrawlservpp::Data::Corpusinline
copyContinuous(std::string &to) constcrawlservpp::Data::Corpusinline
copyContinuous(std::string &to, TextMap &articleMapTo, TextMap &dateMapTo) constcrawlservpp::Data::Corpusinline
Corpus(bool consistencyChecks)crawlservpp::Data::Corpusinlineexplicit
Corpus(std::vector< Corpus > &others, bool consistencyChecks, StatusSetter &statusSetter)crawlservpp::Data::Corpusinline
corpuscrawlservpp::Data::Corpusprotected
create(Tokens &texts, bool deleteInputData)crawlservpp::Data::Corpusinline
create(Tokens &texts, std::vector< std::string > &articleIds, std::vector< std::string > &dateTimes, bool deleteInputData)crawlservpp::Data::Corpusinline
DateArticleSentenceMap typedefcrawlservpp::Data::Corpus
dateMapcrawlservpp::Data::Corpusprotected
empty() constcrawlservpp::Data::Corpusinline
filterArticles(const ArticleFunc &callbackArticle, StatusSetter &statusSetter)crawlservpp::Data::Corpusinline
filterByDate(const std::string &from, const std::string &to)crawlservpp::Data::Corpusinline
get(std::size_t index) constcrawlservpp::Data::Corpusinline
get(const std::string &id) constcrawlservpp::Data::Corpusinline
getArticleMap()crawlservpp::Data::Corpusinline
getArticles() constcrawlservpp::Data::Corpusinline
getcArticleMap() constcrawlservpp::Data::Corpusinline
getcCorpus() constcrawlservpp::Data::Corpusinline
getcDateMap() constcrawlservpp::Data::Corpusinline
getCorpus()crawlservpp::Data::Corpusinline
getcSentenceMap() constcrawlservpp::Data::Corpusinline
getcTokens() constcrawlservpp::Data::Corpusinline
getDate(const std::string &date) constcrawlservpp::Data::Corpusinline
getDateMap()crawlservpp::Data::Corpusinline
getDateTokenized(const std::string &date) constcrawlservpp::Data::Corpusinline
getNumTokens() constcrawlservpp::Data::Corpusinline
getSentenceMap()crawlservpp::Data::Corpusinline
getTokenized(std::size_t index) constcrawlservpp::Data::Corpusinline
getTokenized(const std::string &id) constcrawlservpp::Data::Corpusinline
getTokens()crawlservpp::Data::Corpusinline
hasArticleMap() constcrawlservpp::Data::Corpusinline
hasDateMap() constcrawlservpp::Data::Corpusinline
hasSentenceMap() constcrawlservpp::Data::Corpusinline
isTokenized() constcrawlservpp::Data::Corpusinline
PositionLength typedefcrawlservpp::Data::Corpus
SentenceFunc typedefcrawlservpp::Data::Corpus
sentenceMapcrawlservpp::Data::Corpusprotected
SentenceMap typedefcrawlservpp::Data::Corpus
SentenceMapEntry typedefcrawlservpp::Data::Corpus
size() constcrawlservpp::Data::Corpusinline
Sizes typedefcrawlservpp::Data::Corpus
substr(std::size_t from, std::size_t len)crawlservpp::Data::Corpusinline
tokenize(const std::vector< std::uint16_t > &manipulators, const std::vector< std::string > &models, const std::vector< std::string > &dictionaries, const std::vector< std::string > &languages, std::uint64_t freeMemoryEvery, StatusSetter &statusSetter)crawlservpp::Data::Corpusinline
tokenizeCustom(const std::optional< SentenceFunc > &callback, std::uint64_t freeMemoryEvery, StatusSetter &statusSetter)crawlservpp::Data::Corpusinline
Tokens typedefcrawlservpp::Data::Corpus
tokenscrawlservpp::Data::Corpusprotected