Contents

# Open Document to text conversion

require 'zip/zip'
PlainTextExtractor.new {
  every :odt
  as 'application/vnd.oasis.opendocument.text'
  aka "Open Document Format for text"
  extract_content_with {|source|
    Zip::ZipFile.open(source){|zipfile|
      zipfile.read("content.xml").split(/</).grep(/^text:(p|span)/).collect{|l|
        l.sub(/^[^>]+>/,'')
      }.join("\n")
    }
  }
  which_should_for_example_extract 'written with OpenOffice.org', :from => 'basic.odt'
}

Version data entries

1 entries across 1 versions & 1 rubygems

Version	Path
picolena-0.2.2	lib/picolena/templates/lib/plain_text_extractors/opendocument.text.rb