Sha256: 3fb4ea97cf7db3547be452c366b246f6203b5177d00595a0df8eca766d6a5cae
Contents?: true
Size: 639 Bytes
Versions: 9
Compression:
Stored size: 639 Bytes
Contents
module PragmaticSegmenter
module Languages
module Persian
include Languages::Common
SENTENCE_BOUNDARY_REGEX = /.*?[:\.!\?؟]|.*?\z|.*?$/
Punctuations = ['?', '!', ':', '.', '؟'].freeze
ReplaceColonBetweenNumbersRule = Rule.new(/(?<=\d):(?=\d)/, '♭')
ReplaceNonSentenceBoundaryCommaRule = Rule.new(/،(?=\s\S+،)/, '♬')
class AbbreviationReplacer < AbbreviationReplacer
SENTENCE_STARTERS = [].freeze
private
def scan_for_replacements(txt, am, index, character_array)
txt.gsub!(/(?<=#{am})\./, '∯')
txt
end
end
end
end
end
Version data entries
9 entries across 9 versions & 1 rubygems