Contents

# Author::    Lucas Carlson  (mailto:[e-mail])
# Copyright:: Copyright (c) 2005 Lucas Carlson
# License::   LGPL

module ClassifierReborn
  module Summarizer
    extend self

    def summary( str, count=10, separator=" [...] " )
      perform_lsi split_sentences(str), count, separator
    end

    def paragraph_summary( str, count=1, separator=" [...] " )
      perform_lsi split_paragraphs(str), count, separator
    end

    def split_sentences(str)
      str.split(/(\.|\!|\?)/) # TODO: make this less primitive
    end

    def split_paragraphs(str)
      str.split(/(\n\n|\r\r|\r\n\r\n)/) # TODO: make this less primitive
    end

    def perform_lsi(chunks, count, separator)
      lsi = ClassifierReborn::LSI.new :auto_rebuild => false
      chunks.each { |chunk| lsi << chunk unless chunk.strip.empty? || chunk.strip.split.size == 1 }
      lsi.build_index
      summaries = lsi.highest_relative_content count
      return summaries.reject { |chunk| !summaries.include? chunk }.map { |x| x.strip }.join(separator)
    end
  end
end

Version data entries

1 entries across 1 versions & 1 rubygems

Version	Path
classifier-reborn-2.0.4	lib/classifier-reborn/lsi/summarizer.rb