Sha256: 3f0370e4621ea00f535488346e9f8a84fce52a4b0468844ac756412b2cf4f9d0
Contents?: true
Size: 866 Bytes
Versions: 18
Compression:
Stored size: 866 Bytes
Contents
module PragmaticSegmenter
module Languages
class Hindi
class Process < PragmaticSegmenter::Process
private
def sentence_boundary_punctuation(txt)
PragmaticSegmenter::Languages::Hindi::SentenceBoundaryPunctuation.new(text: txt).split
end
def punctuation_array
PragmaticSegmenter::Languages::Hindi::Punctuation.new.punct
end
end
class Cleaner < PragmaticSegmenter::Cleaner
end
class SentenceBoundaryPunctuation < PragmaticSegmenter::SentenceBoundaryPunctuation
SENTENCE_BOUNDARY = /.*?[।\|!\?]|.*?$/
def split
text.scan(SENTENCE_BOUNDARY)
end
end
class Punctuation < PragmaticSegmenter::Punctuation
PUNCT = ['।', '|', '.', '!', '?']
def punct
PUNCT
end
end
end
end
end
Version data entries
18 entries across 18 versions & 1 rubygems