INNER CODE UNIT · Ruby

next_word_start

grobidOrg/grobid · grobid-home/sentence-segmentation/pragmatic_segmenter/abbreviation_replacer.rb:39

        next_word_start = /(?<=#{Regexp.escape(stripped)} ).{1}/
        character_array = @text.scan(next_word_start)
        abbrev_match.each_with_index do |am, index|
          txt = scan_for_replacements(txt, am, index, character_array)
        end
      end
      txt
    end

    def scan_for_replacements(txt, am, index, character_array)
      character = character_array[index]
      prepositive = @language::Abbreviation::PREPOSITIVE_ABBREVIATIONS
      number_abbr = @language::Abbreviation::NUMBER_ABBREVIATIONS
      upper = /[[:upper:]]/.match(character.to_s)
      if upper.nil? || prepositive.include?(Unicode::downcase(am.strip))
        if prepositive.include?(Unicode::downcase(am.strip))
          txt = replace_prepositive_abbr(txt, am)
        elsif number_abbr.include?(Unicode::downcase(am.strip))

View source record →