l3thal

#!/usr/bin/ruby

require 'zip'
require 'nokogiri'

#Zip::ZipFile.open("sample.pptx").each{ |entry| puts Nokogiri::XML.parse(zip.find_entry(entry.to_s).get_input_stream).text.split(' ').uniq.length if entry.to_s.match(/ppt\/slides\/slide[0-9]+\.xml$/) }

class Pptx

  def self.word_count(file, zip=Zip::ZipFile.open(file), count=nil)

l3thal

#!/usr/bin/ruby

require 'zip'
require 'nokogiri'

class Docx
  def self.word_count(file, zip=Zip::ZipFile.open(file))
    Nokogiri::XML.parse(zip.find_entry("word/document.xml").get_input_stream).text.split(" ").uniq.length
  end
end

l3thal

#!/bin/bash
# rename doc files with spaces
find . -depth -name '*.doc' | while IFS= read -r f ; do mv -i "$f" "$(dirname "$f")/$(basename "$f"|tr ' ' _)" 2>/dev/null; done

# convert doc files to docx
for i in `find ./ -name "*.doc" 2>/dev/null`
do
    dir=$(dirname ${i})"/";
    libreoffice --headless --convert-to docx:"MS Word 2007 XML" --outdir $dir $i;
done

l3thal

Keybase proof

I hereby claim:

• I am l3thal on github.
• I am l3thal (https://keybase.io/l3thal) on keybase.
• I have a public key whose fingerprint is 5E04 F2F0 E0A1 E915 25DB 6052 BEDD DFF2 5540 86B5

To claim this, I am signing this object:

l3thal

def flatten(list, result=[])
  list.each do |item|
    if item.is_a? Integer
      result << item
    else
      result += flatten(item)
    end
  end
  res
end