format_parser_pdf 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: dc2beb605a5a7311a69fbac08d5c23d829d222e98ac0b28eef049e8900eb817d
+  data.tar.gz: 406cf82d28db153d083e8cfaf8fc8c4eb46a9ea18f7fb893842239096815bd0b
+SHA512:
+  metadata.gz: 4febc76c910e9c35bcffc68d782e1bf8bc2b8204b8b3b5eedaaace3a64e2b4ea0deb8ff4711363b14f477685b6bafa344191425ca254f9e9aac56d2893ee85d7
+  data.tar.gz: 05cce2295783953dbddd3fd34fbb10527433d5a12a7022baf516e18e526a48d5deeffe24444e17c4b2080b08f6fee866992ba869a29fbad25f6299c9bb1a5cc8

data/.gitignore

@@ -0,0 +1,12 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+Gemfile.lock
+
+# rspec failure tracking
+.rspec_status

data/.rspec

@@ -0,0 +1,3 @@
+--format documentation
+--color
+--require spec_helper

data/.rubocop.yml

@@ -0,0 +1,2 @@
+inherit_gem:
+  wetransfer_style: ruby/default.yml

data/.travis.yml

@@ -0,0 +1,11 @@
+sudo: false
+language: ruby
+cache: bundler
+rvm:
+- 2.2.0
+- 2.3.0
+- 2.4.2
+- 2.5.0
+- jruby-9.0
+before_install: gem install bundler -v 1.16.2
+

data/CODE_OF_CONDUCT.md

@@ -0,0 +1,74 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+In the interest of fostering an open and welcoming environment, we as
+contributors and maintainers pledge to making participation in our project and
+our community a harassment-free experience for everyone, regardless of age, body
+size, disability, ethnicity, gender identity and expression, level of experience,
+nationality, personal appearance, race, religion, or sexual identity and
+orientation.
+
+## Our Standards
+
+Examples of behavior that contributes to creating a positive environment
+include:
+
+* Using welcoming and inclusive language
+* Being respectful of differing viewpoints and experiences
+* Gracefully accepting constructive criticism
+* Focusing on what is best for the community
+* Showing empathy towards other community members
+
+Examples of unacceptable behavior by participants include:
+
+* The use of sexualized language or imagery and unwelcome sexual attention or
+advances
+* Trolling, insulting/derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or electronic
+  address, without explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Our Responsibilities
+
+Project maintainers are responsible for clarifying the standards of acceptable
+behavior and are expected to take appropriate and fair corrective action in
+response to any instances of unacceptable behavior.
+
+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.
+
+## Scope
+
+This Code of Conduct applies both within project spaces and in public spaces
+when an individual is representing the project or its community. Examples of
+representing a project or community include using an official project e-mail
+address, posting via an official social media account, or acting as an appointed
+representative at an online or offline event. Representation of a project may be
+further defined and clarified by project maintainers.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported by contacting the project team at gerard@wetransfer.com. All
+complaints will be reviewed and investigated and will result in a response that
+is deemed necessary and appropriate to the circumstances. The project team is
+obligated to maintain confidentiality with regard to the reporter of an incident.
+Further details of specific enforcement policies may be posted separately.
+
+Project maintainers who do not follow or enforce the Code of Conduct in good
+faith may face temporary or permanent repercussions as determined by other
+members of the project's leadership.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
+available at [http://contributor-covenant.org/version/1/4][version]
+
+[homepage]: http://contributor-covenant.org
+[version]: http://contributor-covenant.org/version/1/4/

data/Gemfile

@@ -0,0 +1,3 @@
+source "https://rubygems.org"
+
+gemspec

data/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2018 WeTransfer
+
+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) 2018 grdw
+
+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 +1,34 @@
+# Format parser PDF
+
+[![Build Status](https://travis-ci.com/WeTransfer/format_parser_pdf.svg?token=9FxKF7M1tP265s2qQFFJ&branch=master)](https://travis-ci.com/WeTransfer/format_parser_pdf)
+
+An extension gem for [format_parser](https://github.com/WeTransfer/format_parser) that uses [pdf-reader](https://github.com/yob/pdf-reader) to detect page count in PDF files.
+
+## Installation
+
+In your `Gemfile`, in addition to the `format_parser` gem add the `format_parser_pdf`:
+
+```ruby
+source :rubygems
+
+# ...
+gem 'format_parser'
+gem 'format_parser_pdf'
+```
+
+If you only use `Bundler.setup` in your code and require gems manually, you need to explicitly `require` the library so that the built-in
+PDF parser in the `format_parser` gem gets replaced with the extended version. If you use `Bundler.require` it will happen automatically.
+
+## Usage
+
+Anywhere in your code use the standard `FormatParser.parse(io)` calls and related methods, for PDFs the extended version will be used.
+
+## 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/WeTransfer/format_parser_pdf

data/Rakefile

@@ -0,0 +1,8 @@
+require "bundler/gem_tasks"
+require "rspec/core/rake_task"
+require 'rubocop/rake_task'
+
+RuboCop::RakeTask.new(:rubocop)
+RSpec::Core::RakeTask.new(:spec)
+
+task default: [:spec, :rubocop]

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "format_parser_pdf"
+
+# 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(__FILE__)

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/format_parser_pdf.gemspec

@@ -0,0 +1,32 @@
+
+lib = File.expand_path("../lib", __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "format_parser_pdf/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = "format_parser_pdf"
+  spec.version       = FormatParserPDF::VERSION
+  spec.authors       = ["grdw"]
+  spec.email         = ["gerard@wetransfer.com"]
+
+  spec.summary       = %q{An adapter for format_parser to parse PDF files using pdf-reader.}
+  spec.description   = %q{An adapter for format_parser to parse PDF files using pdf-reader. Replaces the standard PDF parser module.}
+  spec.homepage      = "https://github.com/WeTransfer/format_parser_pdf"
+  spec.license       = "MIT"
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the RubyGem that have been added into git.
+  spec.files         = Dir.chdir(File.expand_path('..', __FILE__)) do
+    `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  end
+  spec.bindir        = "exe"
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ["lib"]
+
+  spec.add_dependency 'pdf-reader', '~> 2.1'
+  spec.add_dependency 'format_parser', '~> 0', '< 1.0'
+  spec.add_development_dependency "bundler", "~> 1.16"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec", "~> 3.0"
+  spec.add_development_dependency "wetransfer_style", "0.6.0"
+end

data/lib/format_parser_pdf.rb

@@ -0,0 +1,43 @@
+require 'pdf-reader'
+require 'format_parser'
+require 'format_parser_pdf/io_extension'
+require 'format_parser_pdf/version'
+
+module FormatParserPDF
+  class Parser
+    include FormatParser::IOUtils
+
+    PDF_MARKER = /%PDF-1\.[0-9]{1}/
+
+    def call(io)
+      io = FormatParser::IOConstraint.new(io)
+
+      return unless safe_read(io, 9) =~ PDF_MARKER
+      parse_using_pdf_reader(io)
+    end
+
+    def parse_using_pdf_reader(io)
+      pdf_reader = PDF::Reader.new(IOExtension.new(io))
+      page_count = pdf_reader.page_count
+      # We might want to recover more useful items (such as page dimensions -
+      # media box, trim box, bleed box, art box and a few dozens other boxes)
+      # later on. At the moment FormatParser::Document does not have `intrinsics' which
+      # is an omission we need to sort out on format_parser itself
+      # intrinsics = {
+      #   pdf_version: pdf_reader.pdf_version,
+      #   info: pdf_reader.info,
+      #   metadata: pdf_reader.metadata,
+      # }
+      FormatParser::Document.new(format: :pdf, page_count: page_count) # , intrinsics: intrinsics)
+    rescue PDF::Reader::MalformedPDFError
+      nil
+    end
+  end
+
+  # FormatParser includes a builtin PDF parser that only checks for the PDF magic comment
+  # at the start of file. That one needs to be disabled first
+  FormatParser.deregister_parser(FormatParser::PDFParser)
+
+  # ...and replaced with ours
+  FormatParser.register_parser Parser, natures: :document, formats: :pdf
+end

data/lib/format_parser_pdf/io_extension.rb

@@ -0,0 +1,43 @@
+module FormatParserPDF
+  class Parser
+    class IOExtension < FormatParser::IOConstraint
+      def initialize(io)
+        @io = io
+      end
+
+      def seek(n, seek_mode = IO::SEEK_SET)
+        absolute_offset = case seek_mode
+                          when IO::SEEK_SET
+            n
+                          when IO::SEEK_CUR
+            @io.pos + n
+                          when IO::SEEK_END
+            @io.size + n
+          else
+            raise Errno::EINVAL
+          end
+
+        if absolute_offset < 0
+          # Raise a special exception that FormatParser ignores - it will stop the parser and skip to the next one
+          msg = "Can only seek to positive absolute offsets (requested seek to #{absolute_offset})"
+          raise FormatParser::IOUtils::InvalidRead, msg
+        end
+        @io.seek(absolute_offset)
+      end
+
+      def rewind
+        @io.seek(0)
+      end
+
+      def readchar
+        @io.read(1)
+      end
+
+      def getbyte
+        if byte = @io.read(1)
+          byte.unpack('C').first
+        end
+      end
+    end
+  end
+end

data/lib/format_parser_pdf/version.rb

@@ -0,0 +1,3 @@
+module FormatParserPDF
+  VERSION = "0.1.0"
+end

metadata

@@ -0,0 +1,151 @@
+--- !ruby/object:Gem::Specification
+name: format_parser_pdf
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- grdw
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2018-07-16 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: pdf-reader
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.1'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.1'
+- !ruby/object:Gem::Dependency
+  name: format_parser
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0'
+    - - "<"
+      - !ruby/object:Gem::Version
+        version: '1.0'
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.16'
+- !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: wetransfer_style
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.6.0
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - '='
+      - !ruby/object:Gem::Version
+        version: 0.6.0
+description: An adapter for format_parser to parse PDF files using pdf-reader. Replaces
+  the standard PDF parser module.
+email:
+- gerard@wetransfer.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- ".rspec"
+- ".rubocop.yml"
+- ".travis.yml"
+- CODE_OF_CONDUCT.md
+- Gemfile
+- LICENSE
+- LICENSE.txt
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- format_parser_pdf.gemspec
+- lib/format_parser_pdf.rb
+- lib/format_parser_pdf/io_extension.rb
+- lib/format_parser_pdf/version.rb
+homepage: https://github.com/WeTransfer/format_parser_pdf
+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: 2.7.3
+signing_key: 
+specification_version: 4
+summary: An adapter for format_parser to parse PDF files using pdf-reader.
+test_files: []