paper-pdf-parser 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 06668fe35399dc8cf22a2e1ab7f7995d475b47e6
+  data.tar.gz: 3d0e919a167d6177c5dc084c53eda5faf54c0437
+SHA512:
+  metadata.gz: 132a5d20bea7072830895040cd9caccd43019257b05ffc9c6ad9f2a8f7ae981330a146bf5b0cfed78905b66c5a1d2b7dd29c8bafca5e32fd4a250ec932fc3296
+  data.tar.gz: 35042f63ddf507c1bb8233081fcf65753c8d7b9e2659b2cc8ac70b949c073e17cddcb17f9632ab2ce6344b18680ad0f85e989fd85b7f025df526fc01c99ffdb7

data/.gitignore

@@ -0,0 +1,11 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+vendor
+.idea

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/.travis.yml

@@ -0,0 +1,5 @@
+sudo: false
+language: ruby
+rvm:
+  - 2.2.3
+before_install: gem install bundler -v 1.12.1

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,49 @@
+# Contributor Code of Conduct
+
+As contributors and maintainers of this project, and in the interest of
+fostering an open and welcoming community, we pledge to respect all people who
+contribute through reporting issues, posting feature requests, updating
+documentation, submitting pull requests or patches, and other activities.
+
+We are committed to making participation in this project a harassment-free
+experience for everyone, regardless of level of experience, gender, gender
+identity and expression, sexual orientation, disability, personal appearance,
+body size, race, ethnicity, age, religion, or nationality.
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery
+* Personal attacks
+* Trolling or insulting/derogatory comments
+* Public or private harassment
+* Publishing other's private information, such as physical or electronic
+  addresses, without explicit permission
+* Other unethical or unprofessional conduct
+
+Project maintainers have the right and responsibility to remove, edit, or
+reject comments, commits, code, wiki edits, issues, and other contributions
+that are not aligned to this Code of Conduct, or to ban temporarily or
+permanently any contributor for other behaviors that they deem inappropriate,
+threatening, offensive, or harmful.
+
+By adopting this Code of Conduct, project maintainers commit themselves to
+fairly and consistently applying these principles to every aspect of managing
+this project. Project maintainers who do not follow or enforce the Code of
+Conduct may be permanently removed from the project team.
+
+This code of conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community.
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting a project maintainer at takahiro_nishimura@r.recruit.co.jp. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. Maintainers are
+obligated to maintain confidentiality with regard to the reporter of an
+incident.
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 1.3.0, available at
+[http://contributor-covenant.org/version/1/3/0/][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/3/0/

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in paper-pdf-parser.gemspec
+gemspec

data/LICENSE

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2016 Takahiro Nishimura
+
+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/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2016 Takahiro Nishimura
+
+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 +1,65 @@
+
+
+
+# Paper::Pdf::Parser
+
+Welcome to your new gem! In this directory, you'll find the files you need to be able to package up your Ruby library into a gem. Put your Ruby code in the file `lib/paper/pdf/parser`. To experiment with that code, run `bin/console` for an interactive prompt.
+
+
+## Dependencies
+
+- k2pdfopt (http://www.willus.com/k2pdfopt/)
+
+## Installation
+### Install k2pdfopt
+
+1. Access [this url](http://www.willus.com/k2pdfopt/download/)
+2. Select version by OS and 32/64 bit
+3. Put CAPTHA and download
+4. Move to `/usr/local/bin`
+5. Confirm to use `k2pdfopt` command
+
+### Install paper pdf parser
+
+```ruby
+gem 'paper-pdf-parser'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install paper-pdf-parser
+
+## Usage
+
+```
+Commands:
+  p3 help [COMMAND]  # Describe available commands or one specific command
+  p3 path            # Extract references from local file
+  p3 url             # Extract references from pdf URL
+
+  Options:
+  Working dir, [--work-dir=WORK_DIR]   # Set working dir(default: /tmp)
+                                       # Default: /tmp
+  Working in dir, [--dir], [--no-dir]  # work to make dir or not(default: true)
+                                       # Default: true
+```
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake spec` to run the tests. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/paper-pdf-parser. This project is intended to be a safe, welcoming space for collaboration, and contributors are expected to adhere to the [Contributor Covenant](http://contributor-covenant.org) code of conduct.
+
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](http://opensource.org/licenses/MIT).
+

data/Rakefile

@@ -0,0 +1,6 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+
+RSpec::Core::RakeTask.new(:spec)
+
+task :default => :spec

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "paper/pdf/parser"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/exe/p3

@@ -0,0 +1,6 @@
+require 'pathname'
+lib = Pathname.new(__FILE__).dirname.join('..','lib/paper/pdf').expand_path.to_s
+$:.unshift lib
+require 'parser'
+PaperPdfParser::CLI.start
+

data/lib/paper/pdf/parser.rb

@@ -0,0 +1,14 @@
+require 'pathname'
+lib = Pathname.new(__FILE__).dirname.join().expand_path.to_s
+$:.unshift lib
+
+require 'paper/pdf/parser/paper-pdf-parser'
+require "paper/pdf/parser/version"
+
+module Paper
+  module Pdf
+    module Parser
+      # Your code goes here...
+    end
+  end
+end

data/lib/paper/pdf/parser/P3.rb

@@ -0,0 +1,128 @@
+require 'digest/sha2'
+require 'time'
+require 'fileutils'
+require 'pty'
+require 'expect'
+require 'pdf-reader'
+require 'open-uri'
+
+class P3
+  REFERENCE_START_REGEXP = Regexp.new('\n*[rR][eE][fF][eE][rR][eE][nN][cC][eE][sS]?( +|\n+)?$')
+  REFERENCE_REGEXP = Regexp.new('(\[[0-9]?[0-9]\]|\[.+?\])')
+
+  def self.makeId
+    return Digest::SHA256.hexdigest Time.now.strftime('%F %H:%M:%S')
+  end
+
+  def self.makeDir(id, work_dir)
+    Dir.mkdir("#{work_dir}/#{id}")
+  end
+
+  def self.removeDir(id, work_dir)
+    FileUtils.rm_rf("#{work_dir}/#{id}")
+  end
+
+  def self.makeFile(id, work_dir, use_dir)
+    if use_dir || use_dir.nil?
+      return "#{work_dir}/#{id}/output.pdf"
+    else
+      return "#{work_dir}/#{id}-output.pdf"
+    end
+  end
+
+  def self.getK2Pdf(id, work_dir, use_dir)
+    if use_dir
+      return "#{work_dir}/#{id}/output_k2opt.pdf"
+    else
+      return "#{work_dir}/#{id}-output_k2opt.pdf"
+    end
+  end
+
+  def self.removeFile(id, work_dir)
+    File.delete("#{work_dir}/#{id}-output.pdf")
+    File.delete("#{work_dir}/#{id}-output_k2opt.pdf")
+  end
+
+  def self.fetchPdfFile(pdfUrl, file_name)
+    open(file_name, 'wb') do |o|
+      open(pdfUrl) do |data|
+        o.write(data.read)
+      end
+    end
+  end
+
+  def self.convertSingleColPdf(file_name)
+    cmd = "k2pdfopt -dev kpw #{file_name}"
+    PTY.spawn(cmd) do |i, o|
+      o.sync = true
+      i.expect(/\S.*Enter option above \(h=help, q=quit\):/, 10) {
+        o.puts "\n"
+        o.flush
+      }
+      while (i.eof? == false)
+        res = i.gets
+        print res
+        unless res.index('written').nil?
+          return res.match(/\/[\a-zA-Z0-9_]+.pdf/).to_s
+        end
+      end
+    end
+  end
+
+  def self.fetchReference(file_name)
+    puts file_name
+    reader = PDF::Reader.new(file_name)
+    page_no = reader.
+        pages.
+        reject { |i|
+      i.text.index(REFERENCE_START_REGEXP).nil?
+    }.
+        map(&:number).
+        sort.
+        shift
+
+    ref_page = reader.
+        pages.
+        select { |i|
+      i.number >= page_no
+    }.
+        map { |i|
+      i.text.gsub(/\n\n+/, "\n").gsub(/ +/, ' ').gsub(/-\n +/, '')
+    }
+
+    ref_page.shift
+
+    ref_page = ref_page.
+        join(' ').
+        gsub(REFERENCE_REGEXP, "\n\\1")
+
+    ref_page = ref_page.
+        split(/\n *\n/).
+        map { |i| i.gsub("\n", '') }.
+        select { |i| i.length > 15 }
+    return ref_page
+  end
+
+  def self.fetchFromPdfPath(path, work_dir=true, use_dir=true)
+    executed_pdf = convertSingleColPdf(path)
+    references = fetchReference(executed_pdf)
+    if use_dir || use_dir.nil?
+      removeDir(@job_id, work_dir)
+    else
+      removeFile(@job_id, work_dir)
+    end
+    return references
+  end
+
+  def self.fetchFromPdfUrl(pdfUrl, work_dir=true, use_dir=true)
+    @job_id = makeId
+    makeDir(@job_id, work_dir) if use_dir || use_dir.nil?
+    file_name = makeFile(@job_id, work_dir, use_dir)
+    fetchPdfFile(pdfUrl, file_name)
+    return self.parse(file_name, work_dir, use_dir)
+  end
+
+  class << self
+    alias :parse :fetchFromPdfPath
+  end
+end

data/lib/paper/pdf/parser/P3Util.rb

@@ -0,0 +1,12 @@
+$:.unshift Pathname.new(__FILE__).dirname.join().expand_path.to_s
+require 'P3'
+
+module P3Util
+  def self.fetchFromPath(pathName, work_dir, use_dir)
+    return P3.fetchFromPdfPath(pathName, work_dir, use_dir)
+  end
+
+  def self.fetchFromPdfUrl(pdfUrl, work_dir, use_dir)
+    return P3.fetchFromPdfUrl(pdfUrl, work_dir, use_dir)
+  end
+end

data/lib/paper/pdf/parser/paper-pdf-parser.rb

@@ -0,0 +1,27 @@
+# coding: utf-8
+
+require 'thor'
+require 'pathname'
+lib = Pathname.new(__FILE__).dirname.join().expand_path
+$:.unshift lib.to_s
+require 'P3Util'
+require 'json'
+
+
+module PaperPdfParser
+  class CLI < Thor
+    include P3Util
+    class_option 'work_dir', type: :string, aliases: 'Working dir', desc: 'Set working dir(default: /tmp)', default: '/tmp'
+    class_option 'dir', type: :boolean, aliases: 'Working in dir', desc: 'work to make dir or not(default: true)', default: true
+
+    desc 'path', 'Extract references from local file'
+    def path(pathName)
+      puts P3Util.fetchFromPath(pathName, options[:work_dir], options[:use_dir]).to_json
+    end
+
+    desc 'url', 'Extract references from pdf URL'
+    def url(pdfUrlName)
+      puts P3Util.fetchFromPdfUrl(pdfUrlName, options[:work_dir], options[:use_dir]).to_json
+    end
+  end
+end

data/lib/paper/pdf/parser/version.rb

@@ -0,0 +1,7 @@
+module Paper
+  module Pdf
+    module Parser
+      VERSION = "0.1.0"
+    end
+  end
+end

data/paper-pdf-parser.gemspec

@@ -0,0 +1,36 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'paper/pdf/parser/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = "paper-pdf-parser"
+  spec.version       = Paper::Pdf::Parser::VERSION
+  spec.authors       = ["Takahiro Nishimura"]
+  spec.email         = ["tkhr.nishimura@gmail.com"]
+
+  spec.summary       = %q{Fetch citation list to parse paper pdf }
+  spec.description   = %q{All paper certainly has citation list. However it is hard to extract reference list cuz part of citation list locate lowest part in pdf and all browser is so slow to show pdf file of paper that we get tired to fetch paper. Moreover using pdftohtml or pdftotext, this command cannnot parse multi-column pdf. I develop suitablly-parse multi-column pdf file and fetch citation list.}
+  spec.homepage      = "https://github.com/nishimuuu/paper-pdf-parser"
+  spec.license       = "MIT"
+
+  # Prevent pushing this gem to RubyGems.org. To allow pushes either set the 'allowed_push_host'
+  # to allow pushing to a single host or delete this section to allow pushing to any host.
+  if spec.respond_to?(:metadata)
+    spec.metadata['allowed_push_host'] = "https://rubygems.org"
+  else
+    raise "RubyGems 2.0 or newer is required to protect against public gem pushes."
+  end
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_development_dependency "bundler", "~> 1.12"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+  spec.add_dependency 'thor', "~> 0.19"
+  spec.add_dependency 'pdf-reader', "~> 1.4"
+  spec.add_dependency 'nokogiri', "~> 1.6"
+end

metadata

@@ -0,0 +1,152 @@
+--- !ruby/object:Gem::Specification
+name: paper-pdf-parser
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Takahiro Nishimura
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2016-05-14 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.12'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.12'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '3.0'
+- !ruby/object:Gem::Dependency
+  name: thor
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.19'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.19'
+- !ruby/object:Gem::Dependency
+  name: pdf-reader
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.4'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.4'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.6'
+description: All paper certainly has citation list. However it is hard to extract
+  reference list cuz part of citation list locate lowest part in pdf and all browser
+  is so slow to show pdf file of paper that we get tired to fetch paper. Moreover
+  using pdftohtml or pdftotext, this command cannnot parse multi-column pdf. I develop
+  suitablly-parse multi-column pdf file and fetch citation list.
+email:
+- tkhr.nishimura@gmail.com
+executables:
+- p3
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".travis.yml"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- LICENSE
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- exe/p3
+- lib/paper/pdf/parser.rb
+- lib/paper/pdf/parser/P3.rb
+- lib/paper/pdf/parser/P3Util.rb
+- lib/paper/pdf/parser/paper-pdf-parser.rb
+- lib/paper/pdf/parser/version.rb
+- paper-pdf-parser.gemspec
+homepage: https://github.com/nishimuuu/paper-pdf-parser
+licenses:
+- MIT
+metadata:
+  allowed_push_host: https://rubygems.org
+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: 2.4.5.1
+signing_key: 
+specification_version: 4
+summary: Fetch citation list to parse paper pdf
+test_files: []