Jruby script which parses the PDF/doc/docx files.

doc_pdf_crawler.rb

JARS_PATH = File.join(RAILS_ROOT, "lib/jars")
Dir["#{JARS_PATH}/*jar"].each {|j| require j} #Suck the jars.

require "java"

import org.apache.pdfbox.pdfparser.PDFParser
import org.apache.pdfbox.pdmodel.PDDocument
import org.apache.pdfbox.util.PDFTextStripper
import org.apache.poi.extractor.ExtractorFactory
#importing all the required classes.


#PDF parsing
pdf_path = "sample.pdf"
pdf_file=PDDocument.load pdf_path 
pdf_text=PDFTextStripper.new.getText(doc)
pdf_file.close
puts pdf_text #text inside the pdf file


#Doc/docx Parsing
doc_path = "sample.doc"
doc_file=java.io.FileInputStream.new(resume)
extractor=ExtractorFactory.createExtractor(fs)
doc_file.close
puts extractor.text #text inside doc file


puts "Whoa, im done" #super cool
#Make sure to run this script using jruby and not the system ruby.
#To execute the script, execute the command "ruby doc_pdf_crawler.rb" in your terminal.