INNER CODE UNIT · Ruby

replace_multi_period_abbreviations

grobidOrg/grobid · grobid-home/sentence-segmentation/pragmatic_segmenter/abbreviation_replacer.rb:90

    def replace_multi_period_abbreviations(txt)
      mpa = txt.scan(@language::MULTI_PERIOD_ABBREVIATION_REGEX)
      return txt if mpa.empty?
      mpa.each do |r|
        txt.gsub!(/#{Regexp.escape(r)}/, "#{r.gsub!('.', '∯')}")
      end
      txt
    end

    def replace_pre_number_abbr(txt, abbr)
      txt.gsub!(/(?<=\s#{abbr.strip})\.(?=\s\d)|(?<=^#{abbr.strip})\.(?=\s\d)/, '∯')
      txt.gsub!(/(?<=\s#{abbr.strip})\.(?=\s+\()|(?<=^#{abbr.strip})\.(?=\s+\()/, '∯')
      txt
    end

    def replace_prepositive_abbr(txt, abbr)
      txt.gsub!(/(?<=\s#{abbr.strip})\.(?=\s)|(?<=^#{abbr.strip})\.(?=\s)/, '∯')
      txt.gsub!(/(?<=\s#{abbr.strip})\.(?=:\d+)|(?<=^#{abbr.strip})\.(?=:\d+)/, '∯')

View source record →