INNER CODE UNIT · Ruby

regex

grobidOrg/grobid · grobid-home/sentence-segmentation/pragmatic_segmenter/abbreviation_replacer.rb:84

        regex   = /(U∯S|U\.S|U∯K|E∯U|E\.U|U∯S∯A|U\.S\.A|I|i.v|I.V)∯(?=\s#{escaped}\s)/
        txt.gsub!(regex, '\1.')
      end
      txt
    end

    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+\()/, '∯')

View source record →