jst-parser 0.0.1

checksums.yaml

@@ -0,0 +1,15 @@
+---
+!binary "U0hBMQ==":
+  metadata.gz: !binary |-
+    Y2IyNDAwNGQzZTVlODFhNWJhZGFlYmZlZmQ0ZmQ1YjljYmI5YmFiYQ==
+  data.tar.gz: !binary |-
+    ZDMwZWYzYTMzY2JjMzUyYWJiN2IzZWUxNTAyOWJhOTZmZDNlMzkwZg==
+!binary "U0hBNTEy":
+  metadata.gz: !binary |-
+    MjAyNjc0ODE2YmZhNGM2NGIzODQwOGE2MjAyNWQyNjM0MTY0YWE3NjM4YWVi
+    NDkwOGQ5NjY4MWRiMmVhMjcwODgwZmM2MTMyNDZkMDY3OWY3ZmE4MmNmNzM1
+    NDk4MTY0NTRjNTYwYTNkYzM5ZDg3MzAzYzBjMTA5YWQ4OTc2MDc=
+  data.tar.gz: !binary |-
+    ODYxMTdjNGNjMzBmNjQ0M2ZlZmE0YWIwNjNhYTA2MTQxMTJjOTM1YTBjNTRh
+    YjlhNTViMDEwYzU1YTAyNGRiMTEwMWNlMzNkMWRlZmIwMTYxMDdiNGUxNDRj
+    MDQ0M2IzNzUzNTQ0NGM2MjI5NjkyNGFlMGM3ZGEzMWMzYTZmYTU=

data/.gitignore

@@ -0,0 +1,5 @@
+*.gem
+pkg/
+coverage/
+spec/cassettes
+spec/cassettes/*

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# PDF Parser
+gem 'pdf-reader', '~> 1.3.3'

data/Gemfile.lock

@@ -0,0 +1,20 @@
+GEM
+  remote: https://rubygems.org/
+  specs:
+    Ascii85 (1.0.2)
+    afm (0.2.0)
+    hashery (2.1.0)
+    pdf-reader (1.3.3)
+      Ascii85 (~> 1.0.0)
+      afm (~> 0.2.0)
+      hashery (~> 2.0)
+      ruby-rc4
+      ttfunk
+    ruby-rc4 (0.1.5)
+    ttfunk (1.0.3)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  pdf-reader (~> 1.3.3)

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2013 Chris Little
+
+MIT License
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
+LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
+OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
+WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.

data/README.md

@@ -0,0 +1,51 @@
+-- Nothing yet.  Stay tuned! --
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+    gem 'jst-parser'
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install jst-parser
+
+## Usage
+
+	The JST::Parser object accepts a PDF of type IO::File, and will return a hash containing the following
+	name,
+	rank,
+	education,
+	[experience:
+		branch,
+		date_begin,
+		date_end,
+		title,
+		description],
+	skills,
+	skills_lower,
+	skills_upper,
+	skills_vocational,
+	skills_graduate,
+
+## Code Example
+
+	require 'jst'
+
+	your_pdf = File.open('path/to/pdf')
+    parsed_document = JST::Parser.parse(your_pdf)
+
+    parsed_document[:name]
+
+
+## Contributing
+
+1. Fork it
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create new Pull Request

data/Rakefile

@@ -0,0 +1,14 @@
+require 'bundler'
+require "bundler/gem_tasks"
+
+Bundler::GemHelper.install_tasks
+
+require 'rspec/core/rake_task'
+
+RSpec::Core::RakeTask.new(:spec) do |t|
+  t.rspec_opts = '--color'
+  t.pattern = 'spec/**/*_spec.rb'
+end
+
+desc 'Run Tests'
+task :default => :spec

data/jst-parser.gemspec

@@ -0,0 +1,31 @@
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+
+require 'jst/version'
+
+Gem::Specification.new do |s|
+  s.name        = 'jst-parser'
+  s.version     = JST::VERSION
+  s.platform    = Gem::Platform::RUBY
+  s.date        = '2013-05-30'
+
+  s.summary     = 'Joint Service Transcript (JST) parsing utility.'
+  s.description = 'A PDF parser for the Joint Service Transcript (JST), a standardized
+                  service transcript for Army, Marine Corps, Navy, and Coast Guard personnel. 
+                  (https://jst.doded.mil/faq.html)
+                  Returns accumulated skills, military experience, and education as JSON.'
+  s.authors     = ['Chris Little']
+  s.email       = 'razenghan@gmail.com'
+  s.homepage    = 'http://rubygems.org/gems/jst-parser'
+  s.license     = 'MIT'
+  s.files       = `git ls-files`.split($/)
+  s.test_files  = s.files.grep(%r{^(test|spec|features)/})
+  s.require_path  = 'lib'
+
+  # PDF Parser
+  s.add_dependency 'pdf-reader', '~> 1.3.3'
+
+  # Development
+  s.add_development_dependency "bundler", "~> 1.3"
+  s.add_development_dependency "rake"
+end

data/lib/jst.rb

@@ -0,0 +1,265 @@
+require 'pdf-reader'
+
+module JST
+	class Parser
+		attr_accessor	:debug
+		attr_writer		:jst_response, :name, :rank, :educations, :positions, :skills_all,
+						:skills_lower, :skills_upper, :skills_vocational, :skills_graduate
+
+		BRANCH_ARMY = 'United States Army'
+		BRANCH_NAVY = 'United States Navy'
+		BRANCH_AIR = 'United States Air Force'
+		BRANCH_MARINES = 'United States Marine Corps'
+		BRANCH_COAST = 'United States Coast Guard'
+		BRANCH_DOD = 'Department of Defense'
+
+		class BadPDFError < StandardError ; end
+
+	 	def parse(pdf_file)
+	 		unless @debug
+	 			@debug = false
+	 		end
+
+			unless pdf_file.nil? || pdf_file.size <= 0
+				begin
+					pdf_reader = PDF::Reader.new(pdf_file)
+
+					# Iterate through each page & concat
+					pdf_text = ''
+					pdf_reader.pages.each do |page|
+						pdf_text += page.text
+					end
+
+				 	# Pull out various attributes
+					@name ||= pdf_text.match(/Name:(.+)$/)
+					@name = @name[@name.length - 1].gsub!(/^\s+/,'') unless @name.nil?
+
+					@rank ||= pdf_text.match(/Rank:(.+)$/)
+					@rank = @rank[@rank.length - 1].gsub!(/^\s+/,'') unless @rank.nil?
+
+					@status ||= pdf_text.match(/Status:(.+)$/)
+					@status = @status[@status.length - 1].gsub!(/^\s+/,'') unless @status.nil?
+
+					parse_experience(pdf_text)
+					create_response()
+
+					return @jst_response
+				rescue PDF::Reader::MalformedPDFError
+					raise JST::Parser::BadPDFError, "Could not parse JST."
+				end
+			end
+	  	end
+
+		private
+		def parse_experience(content)
+			experience_section_start = /Military Experience/
+			experience_section_end = /College Level Test Scores|Other Learning Experiences/
+			#experience_regexp = /[A-Z]{2,4}\-.{2,4}\-.{2,4}\s+\d{2}\-\w{3}-\d{4}/
+			#experience_regexp = /([A-Z]{2,4}\-.{2,4}\-.{2,4})|(NONE ASSIGNED)\s+\d{2}\-\w{3}-\d{4}/
+			experience_regexp = /([A-Z]{2,4}\-.{2,4}\-.{2,4}\s+\d{2}\-\w{3}-\d{4})|(NONE ASSIGNED)\s+\d{2}\-\w{3}-\d{4}/
+			experience_date = /(\d{2}\-[A-Z]{3}\-\d{2,4})\D*(\d{2}\-[A-Z]{3}\-\d{4})?/
+			skills_lower_regexp = /(.+)\s+(\d)\s+\w{2}\s+L/
+			skills_upper_regexp = /(.+)\s+(\d)\s+\w{2}\s+U/
+			skills_vocational_regexp = /(.+)\s+(\d)\s+\w{2}\s+V/
+			skills_graduate_regexp = /(.+)\s+(\d)\s+\w{2}\s+G/
+			ignore_privacy_regexp = /PRIVACY ACT INFORMATION/
+			ignore_date_regexp = /\(\d{1,2}\/\d{1,2}\)\(\d{1,2}\/\d{1,2}\)/
+			ignore_misc_regexp = /None|NONE ASSIGNED/
+			ignore_orphaned_skills = /^(\d|L|U|V|G|SH)$/
+			ignore_list = nil
+			@positions = []
+			@skills_all = {}
+			@skills_lower = {}
+			@skills_upper = {}
+			@skills_vocational = {}
+			@skills_graduate = {}
+			position = {}
+			position_branch = ''
+			position_date_begin = ''
+			position_date_end = ''
+			position_title = ''
+			position_desc = ''
+			inside_experience_section = false
+			at_job_title = false
+			at_job_desc = false
+			content_array = content.split("\n")
+
+		 	content_array.each do |line|
+		 		line.strip!
+		 		next if line.empty?
+				if line.match(experience_section_start)
+					# Reached the job experience section.  Begin parsing out.
+					inside_experience_section = true
+					puts "-- -- -- -- -- -- --  INSIDE EXPERIENCE, PARSING -- -- -- -- -- -- -- " if @debug
+					next
+				end
+				if line.match(experience_section_end)
+					puts "-- -- -- -- -- -- --  FINISHED PARSING -- -- -- -- -- -- -- " if @debug
+
+					# Finished last job position.  Appent previous job position.
+					if !position_title.empty? && !position_desc.empty?
+						puts '-- -- -- -- -- -- --  APPENDING POSITION -- -- -- -- -- -- -- ' if @debug
+
+						append_position(position_branch, position_date_begin, position_date_end, position_title, position_desc)
+						position_branch = ''
+						position_date_begin = ''
+						position_date_end = ''
+						position_title = ''
+						position_desc = ''
+					end
+					break
+				end
+
+				if inside_experience_section
+					if line.match(experience_regexp)
+						puts "~~~~~ NEW EXPERIENCE: #{line}" if @debug
+
+						# Determine which branch this job title falls under
+						position_branch = BRANCH_ARMY if line.match(/AR-/)
+						position_branch = BRANCH_AIR if line.match(/AF-/)
+						position_branch = BRANCH_NAVY if line.match(/NV-|NEC-|NER-|LDO-|NWO-/)
+						position_branch = BRANCH_MARINES if line.match(/MC-|MCE-/)
+						position_branch = BRANCH_COAST if line.match(/CG-|CGR-|CGW-/)
+						position_branch = BRANCH_DOD if line.match(/DD-/)
+
+						# Determine the service date (dd-MMM-yyyy)
+						if date_match = line.match(experience_date)
+							puts " ^^^^^ PARSING DATE ^^^^^^ "
+							position_date_begin = date_match[1] unless date_match[1].nil?
+							position_date_end = date_match[2] unless date_match[2].nil?
+						end
+
+						# Next line will be the job titles
+						at_job_title = true
+
+						# Since we're at the next job position, append the previous job position.
+						if !position_title.empty? && !position_desc.empty?
+							append_position(position_branch, position_date_begin, position_date_end, position_title, position_desc)
+							position_branch = ''
+							position_date_begin = ''
+							position_date_end = ''
+							position_title = ''
+							position_desc = ''
+						end
+
+						next
+					end
+
+					if at_job_title
+						puts "~~~~~ JOB TITLE: #{line}" if @debug
+						at_job_title = false
+						position_title = line
+
+						# Next line will be the job description starting point
+						puts "~~~~~ AT JOB DESC" if @debug
+						at_job_desc = true
+						next
+					end
+
+					if skills_match = line.match(skills_lower_regexp)
+						skill_is_lower = true
+					elsif skills_match = line.match(skills_upper_regexp)
+						skill_is_upper = true
+					elsif skills_match = line.match(skills_vocational_regexp)
+						skill_is_vocational = true
+					elsif skills_match = line.match(skills_graduate_regexp)
+						skill_is_graduate = true
+					end
+
+					if skill_is_lower || skill_is_upper || skill_is_vocational || skill_is_graduate
+						unless skills_match[1].empty?
+							# Strip out skill name
+							skill_name = skills_match[1].strip!
+
+							puts "**** SKILL: #{skill_name}" if @debug
+
+							# Init skill name key, if none exists
+							@skills_all[skill_name] = 0 if @skills_all[skill_name].nil?
+							@skills_lower[skill_name] = 0 if @skills_lower[skill_name].nil? && skill_is_lower
+							@skills_upper[skill_name] = 0 if @skills_upper[skill_name].nil? && skill_is_upper
+							@skills_vocational[skill_name] = 0 if @skills_vocational[skill_name].nil? && skill_is_vocational
+							@skills_graduate[skill_name] = 0 if @skills_graduate[skill_name].nil? && skill_is_graduate
+							
+							# Strip out skill value (in credits).  Add to skills hash
+							if !skills_match[1].empty? && is_numeric?(skills_match[2])
+								@skills_all[skill_name] = @skills_all[skill_name] + skills_match[2].to_i
+								@skills_lower[skill_name] = @skills_lower[skill_name] + skills_match[2].to_i if skill_is_lower
+								@skills_upper[skill_name] = @skills_upper[skill_name] + skills_match[2].to_i if skill_is_upper
+								@skills_vocational[skill_name] = @skills_vocational[skill_name] + skills_match[2].to_i if skill_is_vocational
+								@skills_graduate[skill_name] = @skills_graduate[skill_name] + skills_match[2].to_i if skill_is_graduate
+							end
+
+						end
+						next
+					end
+
+					if at_job_desc
+						unless line.match(ignore_privacy_regexp) || line.match(ignore_date_regexp) || line.match(ignore_misc_regexp) || line.match(ignore_orphaned_skills)
+							puts "m: #{line}" if @debug
+							position_desc += line
+						end
+					end
+				end
+			end
+			# skills.sort_by {|key, value| value}
+		end
+
+		def append_position(branch, date_begin, date_end, title, description)
+			position = {}
+			position[:branch] = branch
+			position[:date_begin] = date_begin
+			position[:date_end] = date_end
+			position[:title] = title
+			position[:description] = description
+			@positions.push(position)
+
+			# @positions[position_title] = position_desc
+			# position_title = ''
+			# position_desc = ''
+		end
+
+		def create_response
+			@jst_response = {}
+			@jst_response[:name] = @name
+			@jst_response[:rank] = @rank
+			@jst_response[:education] = @educations
+			@jst_response[:experience] = @positions
+			@jst_response[:skills] = @skills_all
+			@jst_response[:skills_lower] = @skills_lower
+			@jst_response[:skills_upper] = @skills_upper
+			@jst_response[:skills_vocational] = @skills_vocational
+			@jst_response[:skills_graduate] = @skills_graduate
+		end
+
+		# We'll clean up coursework later....
+		# def parse_coursework(content)
+		# 	# Define regexp matchers
+		# 	coursework_regexp = /\-[0-9]{4}\-[0-9]{4}/
+		# 	experience_regexp = /Military Experience/
+		# 	ignore_regexp = /\*\* PRIVACY ACT INFORMATION \*\*/
+
+		# 	@coursework = []
+		# 	course = ''
+		# 	inside_course_content = false
+		#  	content_array = content.split("\n")
+
+		#  	content_array.each do |line|
+		#  		puts "LINE: #{line}" if @debug
+		# 		if line.match(coursework_regexp) || line.match(experience_regexp)
+		# 			# At the next course.  Append previous course information
+		# 			inside_course_content = true
+		# 			@coursework << course unless course.empty?
+		# 			course = line
+		# 			line.match(experience_regexp) ? break : next
+		# 		end
+		# 		if inside_course_content
+		# 			course += line unless line.match(ignore_regexp)
+		# 		end
+		# 	end
+		# end
+
+		def is_numeric?(obj)
+	      true if Float(obj) rescue false
+	    end
+	end
+end

data/lib/jst/version.rb

@@ -0,0 +1,3 @@
+module JST
+    VERSION = "0.0.1"
+end

data/startup.rb

@@ -0,0 +1,12 @@
+# `irb -r ./startup.rb`
+# Just an easy delete & reinstall mechanism
+
+# Remove all previous gem installations
+`gem uninstall -Ia jst-parser`
+`rm -rf pkg/`
+
+## Install local source code as gem
+`rake install`
+
+## Require the gem
+require 'jst'

metadata

@@ -0,0 +1,98 @@
+--- !ruby/object:Gem::Specification
+name: jst-parser
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+platform: ruby
+authors:
+- Chris Little
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2013-05-30 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: pdf-reader
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.3.3
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: 1.3.3
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '1.3'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: ! "A PDF parser for the Joint Service Transcript (JST), a standardized\n
+  \                 service transcript for Army, Marine Corps, Navy, and Coast Guard
+  personnel. \n                  (https://jst.doded.mil/faq.html)\n                  Returns
+  accumulated skills, military experience, and education as JSON."
+email: razenghan@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- .gitignore
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.md
+- Rakefile
+- jst-parser.gemspec
+- lib/jst.rb
+- lib/jst/version.rb
+- startup.rb
+homepage: http://rubygems.org/gems/jst-parser
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.0.3
+signing_key: 
+specification_version: 4
+summary: Joint Service Transcript (JST) parsing utility.
+test_files: []