pdf_extractor 0.1.1

data/.ruby-version

@@ -0,0 +1 @@
+2.4.0

data/.travis.yml

@@ -0,0 +1,7 @@
+---
+sudo: false
+language: ruby
+cache: bundler
+rvm:
+  - 2.4.0
+before_install: gem install bundler -v 2.0.2

data/Gemfile

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

data/Gemfile.lock

@@ -0,0 +1,61 @@
+PATH
+  remote: .
+  specs:
+    pdf_extractor (0.1.0)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    ansi (1.5.0)
+    ast (2.4.0)
+    builder (3.2.3)
+    docile (1.3.2)
+    jaro_winkler (1.5.3)
+    jaro_winkler (1.5.3-java)
+    json (2.2.0)
+    json (2.2.0-java)
+    minitest (5.11.3)
+    minitest-reporters (1.3.6)
+      ansi
+      builder
+      minitest (>= 5.0)
+      ruby-progressbar
+    minitest-reporters-json_reporter (1.0.0)
+      minitest-reporters (~> 1.1, >= 1.1.8)
+    nexus (1.4.0)
+    parallel (1.17.0)
+    parser (2.6.3.0)
+      ast (~> 2.4.0)
+    rainbow (3.0.0)
+    rake (10.5.0)
+    rubocop (0.71.0)
+      jaro_winkler (~> 1.5.1)
+      parallel (~> 1.10)
+      parser (>= 2.6)
+      rainbow (>= 2.2.2, < 4.0)
+      ruby-progressbar (~> 1.7)
+      unicode-display_width (>= 1.4.0, < 1.7)
+    ruby-progressbar (1.10.1)
+    simplecov (0.16.1)
+      docile (~> 1.1)
+      json (>= 1.8, < 3)
+      simplecov-html (~> 0.10.0)
+    simplecov-html (0.10.2)
+    unicode-display_width (1.6.0)
+
+PLATFORMS
+  java
+  ruby
+
+DEPENDENCIES
+  bundler (~> 2.0)
+  minitest (~> 5.0)
+  minitest-reporters-json_reporter (~> 1.0, >= 1.0.0)
+  nexus (~> 1.4, >= 1.4.0)
+  pdf_extractor!
+  rake (~> 10.0)
+  rubocop (~> 0.58, >= 0.58.2)
+  simplecov (~> 0.16, >= 0.16.1)
+
+BUNDLED WITH
+   2.0.2

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2019 Jindrich Skupa
+
+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 +1,62 @@
+# PdfExtractor
+
+Extracts PDF information via [PDFtk](https://www.pdflabs.com/tools/pdftk-the-pdf-toolkit/)
+
+## Dependencies
+
+* [PDFtk](https://www.pdflabs.com/tools/pdftk-the-pdf-toolkit/)
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'pdf_extractor'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install pdf_extractor
+
+## Usage
+
+```ruby
+require 'pdf_extractor'
+form = PdfExtractor.dump_data_fields("~/Downloads/testing_pdf.pdf")
+puts form.first.inspect
+# => {"FieldType"=>"Text", "FieldName"=>"customerNumber", "FieldNameAlt"=>"Customer ID number", "FieldFlags"=>"12582912", "FieldValue"=>"ID0000011", "FieldJustification"=>"Left"}
+```
+
+or
+
+```ruby
+form = PdfExtractor.dump_data_fields_key_value("test/fixtures/testing_pdf.pdf")
+puts form.inspect
+# => {"customerNumber"=>"ID0000011"}
+```
+
+or
+
+```ruby
+meta = PdfExtractor.dump_data("test/fixtures/testing_pdf.pdf")
+puts meta.inspect
+# => {"Creator"=>"PDFescape Online - https://www.pdfescape.com", "Title"=>"testing_pdf", "Producer"=>"RAD PDF 3.9.6.0 - https://www.radpdf.com", "ModDate"=>"D:20190625142342Z", "CreationDate"=>"D:20190625142056Z", "PdfID0"=>"fd1f5ca5bedbac4d46fa47241f696430", "PdfID1"=>"fd1f5ca5bedbac4d46fa47241f696430", "NumberOfPages"=>"1", "PageMediaNumber"=>"1", "PageMediaRotation"=>"0", "PageMediaRect"=>"0 0 595.28 841.89", "PageMediaDimensions"=>"595.28 841.89"}
+```
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. Then, run `rake test` 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/jindrichskupa/pdf_extractor.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).

data/Rakefile

@@ -0,0 +1,10 @@
+require "bundler/gem_tasks"
+require "rake/testtask"
+
+Rake::TestTask.new(:test) do |t|
+  t.libs << "test"
+  t.libs << "lib"
+  t.test_files = FileList["test/**/*_test.rb"]
+end
+
+task default: :test

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "pdf_extractor"
+
+# 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/lib/pdf_extractor.rb

@@ -0,0 +1,25 @@
+# frozen_string_literal: true
+
+require 'pdf_extractor/version'
+require 'pdf_extractor/pdf_tk'
+require 'pdf_extractor/output_parser'
+
+# PdfExtractor module to extract PDF form data
+module PdfExtractor
+  class Error < StandardError; end
+  # Your code goes here...
+  def self.dump_data_fields(file = nil)
+    output = PdfTk.dump_data_fields(file)
+    OutputParser.dump_data_fields(output)
+  end
+
+  def self.dump_data_fields_key_value(file = nil)
+    output = PdfTk.dump_data_fields(file)
+    OutputParser.dump_data_fields_key_value(output)
+  end
+
+  def self.dump_data(file = nil)
+    output = PdfTk.dump_data(file)
+    OutputParser.dump_data(output)
+  end
+end

data/lib/pdf_extractor/output_parser.rb

@@ -0,0 +1,63 @@
+# frozen_string_literal: true
+
+module PdfExtractor
+  # Parse PDFTk outputs
+  class OutputParser
+    def self.dump_data(output = nil)
+      fields = {}
+      pending_key = pending_value = nil
+      output.each do |line|
+        key, value = line.split(': ').map(&:strip)
+        next if %w[InfoBegin PageMediaBegin].include? key
+
+        if key == 'InfoKey'
+          pending_key = value
+          if both_not_nil?(pending_key, pending_value)
+            fields[pending_key] = pending_value
+            pending_key = pending_value = nil
+          end
+        elsif key == 'InfoValue'
+          pending_value = value
+          if both_not_nil?(pending_key, pending_value)
+            fields[pending_key] = pending_value
+            pending_key = pending_value = nil
+          end
+        else
+          fields[key] = value
+        end
+      end
+      fields
+    end
+
+    def self.dump_data_fields(output = nil)
+      return if output.nil?
+
+      fields = []
+      field = {}
+      output.each do |line|
+        if line.strip == '---'
+          fields << field unless field.empty?
+          field = {}
+        else
+          key, value = line.split(': ')
+          field[key] = value.strip
+        end
+      end
+      fields << field unless field.empty?
+      fields
+    end
+
+    def self.dump_data_fields_key_value(output = nil)
+      field_array = dump_data_fields(output)
+      return if field_array.empty?
+
+      form = field_array.map { |i| { i['FieldName'] => i['FieldValue'] } }.each {  hash }
+      Hash[*form.collect(&:to_a).flatten]
+    end
+
+    def self.both_not_nil?(a = nil, b = nil)
+      !a.nil? && !b.nil?
+    end
+
+  end
+end

data/lib/pdf_extractor/pdf_tk.rb

@@ -0,0 +1,20 @@
+# frozen_string_literal: true
+
+module PdfExtractor
+  # Call PDFTk with params
+  class PdfTk
+    def self.dump_data_fields(file = nil)
+      return if file.nil?
+
+      command = IO.popen("pdftk #{file} dump_data_fields", 'r+')
+      command.readlines
+    end
+
+    def self.dump_data(file = nil)
+      return if file.nil?
+
+      command = IO.popen("pdftk #{file} dump_data", 'r+')
+      command.readlines
+    end
+  end
+end

data/lib/pdf_extractor/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module PdfExtractor
+  VERSION = '0.1.1'
+end

data/pdf_extractor.gemspec

@@ -0,0 +1,36 @@
+lib = File.expand_path("lib", __dir__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require "pdf_extractor/version"
+
+Gem::Specification.new do |spec|
+  spec.name          = 'pdf_extractor'
+  spec.version       = PdfExtractor::VERSION
+  spec.authors       = ['Jindrich Skupa']
+  spec.email         = ['jindrich.skupa@gmail.com']
+
+  spec.summary       = %q(PDFTk wrapper to extract form fiels)
+  spec.description   = %q(PDFTk wrapper to extract form fiels)
+  spec.homepage      = 'https://github.com/jindrichskupa/pdf-extractor'
+  spec.license       = 'MIT'
+
+  spec.metadata['homepage_uri'] = spec.homepage
+  spec.metadata['source_code_uri'] = spec.homepage
+  spec.metadata['changelog_uri'] = spec.homepage
+
+  # 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_development_dependency 'bundler', '~> 2.0'
+  spec.add_development_dependency 'minitest', '~> 5.0'
+  spec.add_development_dependency 'minitest-reporters-json_reporter', '~> 1.0', '>= 1.0.0'
+  spec.add_development_dependency 'nexus', '~> 1.4', '>= 1.4.0'
+  spec.add_development_dependency 'rubocop', '~> 0.58', '>= 0.58.2'
+  spec.add_development_dependency 'simplecov', '~> 0.16', '>= 0.16.1'
+  spec.add_development_dependency 'rake', '~> 10.0'
+end

data/script/changelog.sh

@@ -0,0 +1,41 @@
+#!/bin/bash
+[ -z "$1" ] && { echo "missing type: major, minor, patch, none"; exit 1; }
+
+old_version="$(git describe --tags --abbrev=0)"
+
+[ -z "$old_version" ] && { echo "missing previous tag"; exit 1; }
+
+old_version=$(echo "$old_version" | tr -d '[:lower:]')
+
+new_version=$(echo "$old_version" | awk -F. -v CHANGE="$1" -v SPECIAL="$2" '
+BEGIN{type=CHANGE;special=SPECIAL}
+{
+  if (special != "")
+      special="-"special
+  if (type=="patch")
+    print $1"."$2"."$3+1""special ;
+  else if (type == "minor")
+    print $1"."$2+1".0"special ;
+  else if (type == "major")
+    print $1+1".0.0"special ;
+  else if (type == "none")
+    print $1"."$2"."$3""special
+}')
+
+new_version="$new_version"
+
+change_log_header="# PDF Extractor ($new_version) RELEASED\n"
+change_log_changes=$(git log "$old_version"..HEAD --oneline --no-merges --format='  * %s' | sort | uniq)
+change_log_authors=$(git log "$old_version"..HEAD --oneline --format='* %aN' | sort -u)
+
+[ -f CHANGELOG.MD ] || touch CHANGELOG.MD
+
+{
+    echo -e "$change_log_header"
+    echo -e "$change_log_changes"
+    echo -e "\nAuthors\n"
+    echo -e "$change_log_authors\n"
+} | cat - CHANGELOG.MD > CHANGELOG.work.MD && mv CHANGELOG.work.MD CHANGELOG.MD
+
+echo "Check updated CHANGELOG.MD: $old_version -> $new_version"
+echo "Tag this version with $new_version"

data/script/dependencies.sh

@@ -0,0 +1,17 @@
+#!/bin/bash
+
+echo '{' > libraries.json
+echo '"libraries":[' >> libraries.json
+comma=""
+bundle show | tr -d '()' | sed 1d | awk '{print $2" "$3}' | while read gem version; do
+    echo "    $comma{\"bundle\": \"$gem\", \"version_code\": \"$version\", \"type\": \"Gem\"}"
+    comma="," 
+done >> libraries.json
+echo ']' >> libraries.json
+echo '}' >> libraries.json
+
+curl -H "X-App-Token: ${KRAKEN_APP_TOKEN}" \
+  -H "X-App-Version: ${CI_COMMIT_TAG}" \
+  -H "Content-Type: application/json" \
+  -X POST -d @libraries.json https://versions.eman.cz/api/packages
+

data/script/publish.sh

@@ -0,0 +1,6 @@
+#!/bin/bash
+
+bundle install
+gem build pdf_extractor.gemspec
+gem install pdf_extractor-${CI_COMMIT_TAG}.gem
+gem nexus pdf_extractor-${CI_COMMIT_TAG}.gem --url https://nexus.eman.cz/repository/eman-gems/ --credential "$NEXUS_USER:$NEXUS_PASSWORD"

data/script/release.sh

@@ -0,0 +1,29 @@
+#!/bin/bash
+
+current_tag=${CI_COMMIT_TAG}
+prev_tag=$(git tag | sort --version-sort | grep -B 1 ${CI_COMMIT_TAG} | head -1)
+
+change_log_header="# ${CI_PROJECT_NAME} (${current_tag}) RELEASED\n"
+change_log_changes=$(git log ${prev_tag}..${current_tag} --oneline --no-merges --format='  * %s' | sort | uniq | sed 's/$/\\n/' | tr -d \"\'\\n)
+change_log_authors=$(git log ${prev_tag}.."$current_tag" --format='* %aN\n' | sort -u | tr -d \"\'\\n)
+
+cat << EOF > release.json
+{
+  "tag_name": "$current_tag",
+  "description": "$change_log_header\n$change_log_changes\nAuthors\n\n$change_log_authors"
+}
+EOF
+
+RET=$(curl -s -o /dev/null -w "%{http_code}" -XPOST \
+  -H "PRIVATE-TOKEN: $GL_PRIVATE_TOKEN" \
+  -H 'Content-type: application/json' \
+  -d @release.json \
+  https://gitlab.eman.cz/api/v4/projects/${CI_PROJECT_ID}/repository/tags/${CI_COMMIT_TAG}/release)
+
+[ $RET -eq 409 ] && RET=$(curl -s -o /dev/null -w "%{http_code}" -XPUT \
+  -H "PRIVATE-TOKEN: $GL_PRIVATE_TOKEN" \
+  -H 'Content-type: application/json' \
+  -d @release.json \
+  https://gitlab.eman.cz/api/v4/projects/${CI_PROJECT_ID}/repository/tags/${CI_COMMIT_TAG}/release)
+
+exit 0