Module: PragmaticSegmenter::Languages::Persian

Includes:

Common

Defined in:

lib/pragmatic_segmenter/languages/persian.rb

Defined Under Namespace

Classes: AbbreviationReplacer

Constant Summary

SENTENCE_BOUNDARY_REGEX =

/.*?[:\.!\?؟]|.*?\z|.*?$/

Punctuations =

['?', '!', ':', '.', '؟'].freeze

ReplaceColonBetweenNumbersRule =

Rule.new(/(?<=\d):(?=\d)/, '♭')

ReplaceNonSentenceBoundaryCommaRule =

Rule.new(/،(?=\s\S+،)/, '♬')

Constants included from Common

Common::BETWEEN_DOUBLE_QUOTES_REGEX, Common::CONTINUOUS_PUNCTUATION_REGEX, Common::ExtraWhiteSpaceRule, Common::FileFormatRule, Common::GeoLocationRule, Common::KommanditgesellschaftRule, Common::MULTI_PERIOD_ABBREVIATION_REGEX, Common::NUMBERED_REFERENCE_REGEX, Common::PARENS_BETWEEN_DOUBLE_QUOTES_REGEX, Common::PossessiveAbbreviationRule, Common::QUOTATION_AT_END_OF_SENTENCE_REGEX, Common::QuestionMarkInQuotationRule, Common::SPLIT_SPACE_QUOTATION_AT_END_OF_SENTENCE_REGEX, Common::SingleNewLineRule, Common::SubSingleQuoteRule