html2pdf 0.0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 86055351d30cb9e5bd6264f6204ccdddd2bb98f0
+  data.tar.gz: f23ee237e3db6277ae2f6f69f92d2113be1fc8e3
+SHA512:
+  metadata.gz: 9e4d6713bffc9498dc839303d0a24ded97615d3ea18b4f947e22263ade100c17ee8c999491bc2cf36bbd4cd245933428f1297dc8c4573f94b1a7bc1735f76ee4
+  data.tar.gz: 53877751901e76b3046b57b1844e2f09a056f4312fb3b55f2c9192f36657d1862a2923352b4c64328f1b70ed3de5c29f5f9f7962076403c18a2cd49ecf7f4ed7

data/.gitignore

@@ -0,0 +1,21 @@
+*.gem
+*.rbc
+.bundle
+.config
+.yardoc
+Gemfile.lock
+InstalledFiles
+_yardoc
+coverage
+doc/
+lib/bundler/man
+pkg
+rdoc
+spec/reports
+test/tmp
+test/version_tmp
+tmp
+# ctags
+tags
+# generated file
+output.tar.gz

data/.rubocop.yml

@@ -0,0 +1 @@
+inherit_from: rubocop-todo.yml

data/.ruby-version

@@ -0,0 +1 @@
+2.1.1

data/Gemfile

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

data/Guardfile

@@ -0,0 +1,15 @@
+# A sample Guardfile
+# More info at https://github.com/guard/guard#readme
+guard 'minitest' do
+
+  # with Minitest::Unit
+  watch(%r|^test/(.*)\/?test_(.*)\.rb|)
+  watch(%r|^lib/(.*)([^/]+)\.rb|)     { |m| "test/#{m[1]}test_#{m[2]}.rb" }
+  watch(%r|^test/test_helper\.rb|)    { "test" }
+
+  # with Minitest::Spec
+  # watch(%r|^spec/(.*)_spec\.rb|)
+  # watch(%r|^lib/(.*)([^/]+)\.rb|)     { |m| "spec/#{m[1]}#{m[2]}_spec.rb" }
+  # watch(%r|^spec/spec_helper\.rb|)    { "spec" }
+
+end

data/LICENSE.txt

@@ -0,0 +1,22 @@
+Copyright (c) 2014 Burin Choomnuan
+
+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 +1,112 @@
+## Html2Pdf
+
+[![Gem Version](https://badge.fury.io/rb/html2pdf.svg)](http://badge.fury.io/rb/html2pdf)
+
+Convert multiple html or xhtml files to pdfs using the power of
+[Ghostscript][] and [Wkhtmltopdf][].
+
+### Installation
+
+#### Mandatory Requirement
+
+- [Ghostscript][]
+- [Wkhtmltopdf][]
+
+This gem is built on top of my other gems
+
+- [agile_utils][] gem
+- [code_lister][] gem
+
+### Dependencies
+
+- wkhtmltopdf (Linux/OSX)
+- Ghostscript (Linux/OSX)
+- OSX or Linux (no Windows sorry)
+
+## Usage
+```sh
+gem install html2pdf
+```
+For list of usage type
+
+```sh
+html2pdf
+```
+Which should give the following options
+```
+Usage:
+html2pdf export [OPTIONS]
+
+Options:
+  -b, [--base-dir=BASE_DIR]                # Base directory
+                                           # Default: . (current directory)
+  -n, [--inc-words=one two three]          # List of words to be included in the result
+  -x, [--exc-words=one two three]          # List of words to be excluded from the result
+  -i, [--ignore-case], [--no-ignore-case]  # Match case insensitively
+                                           # Default: true
+  -r, [--recursive], [--no-recursive]      # Search for files recursively
+                                           # Default: true
+  -v, [--version], [--no-version]          # Display version information
+```
+### Example Usage
+
+- Convert all `xhtml` and `html` from `test/fixtures/samples` directory
+  recursively
+```
+html2pdf -b test/fixtures/samples -e html xhtml -r
+```
+Before the run
+```
+test/fixtures/samples/
+├── demo1_xxx.rb.xhtml
+├── demo2_xxx.rb.xhtml
+└── sub_dir
+    ├── demo3_xxx.rb.xhtml
+    └── demo4_xxx.rb.xhtml
+```
+After the above command is executed:
+```
+test/fixtures/samples/
+├── demo1_xxx.rb.xhtml
+├── demo1_xxx.rb.xhtml.pdf
+├── demo2_xxx.rb.xhtml
+├── demo2_xxx.rb.xhtml.pdf
+└── sub_dir
+    ├── demo3_xxx.rb.xhtml
+    ├── demo3_xxx.rb.xhtml.pdf
+    ├── demo4_xxx.rb.xhtml
+    └── demo4_xxx.rb.xhtml.pdf
+```
+
+### Usage Tips
+
+This is my personal use case
+
+- Use [vim_printer][] which export any source code to list of (x)html files in
+a single tar.gzipped file.
+
+- Use the output from [vim_printer][] as input to this program so that you get
+the pdf version of it.
+
+- Then combine the generated pdf files using [pdfs2pdf][] gem to produce one pdf file
+
+### Changelogs
+
+#### 0.0.1
+
+- Initial release
+
+### Contributing
+
+1. Fork it ( http://github.com/<my-github-username>/code_exporter/fork )
+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
+
+[Ghostscript]: http://www.ghostscript.com/
+[Wkhtmltopdf]: http://wkhtmltopdf.org/
+[agile_utils]: https://github.com/agilecreativity/agile_utils
+[code_lister]: https://github.com/agilecreativity/code_lister
+[vim_printer]: https://github.com/agilecreativity/vim_printer
+[pdfs2pdf]: https://github.com/agilecreativity/pdfs2pdf

data/Rakefile

@@ -0,0 +1,30 @@
+require 'bundler/gem_tasks'
+require 'rake/testtask'
+
+project_name = 'html2pdf'
+Rake::TestTask.new do |t|
+  t.libs << "lib/#{project_name}"
+  t.test_files = FileList["test/lib/#{project_name}/test_*.rb"]
+  t.verbose = true
+end
+
+task default: :test
+
+task :pry do
+  require 'pry'
+  require 'awesome_print'
+  require_relative './lib/html2pdf'
+  include Html2Pdf
+  ARGV.clear
+  Pry.start
+end
+
+require 'rubocop/rake_task'
+desc 'Run RuboCop on the lib directory'
+Rubocop::RakeTask.new(:rubocop) do |task|
+  task.patterns = ['lib/**/*.rb']
+  # only show the files with failures
+  task.formatters = ['files']
+  # don't abort rake on failure
+  task.fail_on_error = false
+end

data/TODOs.md

@@ -0,0 +1,13 @@
+### TODOs
+
+- Remove the options that need to be default
+  e.g. `--exts xhtml html` should be default and should not be changed by user.
+
+- Find minitest related to file-system test so that the code can be hooked to
+  [TravisCI][]
+
+- Add test using [minitest-filesystem][]
+
+- Add more tests
+
+[minitest-filesystem]: https://github.com/stefanozanella/minitest-filesystem

data/bin/html2pdf

@@ -0,0 +1,4 @@
+#!/usr/bin/env ruby
+require_relative '../lib/html2pdf'
+include Html2Pdf
+Html2Pdf::CLI.start(ARGV)

data/html2pdf.gemspec

@@ -0,0 +1,37 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'html2pdf/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'html2pdf'
+  spec.version       = Html2Pdf::VERSION
+  spec.authors       = ['Burin Choomnuan']
+  spec.email         = ['agilecreativity@gmail.com']
+  spec.summary       = %q{Export any list of html or xhtml files to pdfs}
+  spec.description   = %q{Batch export html files to pdfs}
+  spec.homepage      = 'https://github.com/agilecreativity/html2pdf'
+  spec.license       = 'MIT'
+  spec.files         = `git ls-files`.split($/)
+  spec.executables   = spec.files.grep(%r{^bin/}) { |f| File.basename(f) }
+  spec.test_files    = spec.files.grep(%r{^(test|spec|features)/})
+  spec.require_paths = ["lib"]
+
+  spec.add_runtime_dependency 'thor'
+  spec.add_runtime_dependency 'agile_utils', '~> 0.0.5'
+  spec.add_runtime_dependency 'code_lister', '~> 0.0.6'
+
+  spec.add_development_dependency 'awesome_print', '~> 1.2'
+  spec.add_development_dependency 'bundler', '~> 1.5'
+  spec.add_development_dependency 'gem-ctags', '~> 1.0'
+  spec.add_development_dependency 'guard', '~> 2.6'
+  spec.add_development_dependency 'guard-minitest', '~> 2.2'
+  spec.add_development_dependency 'minitest', '~> 4.2'
+  spec.add_development_dependency 'minitest-filesystem', '~> 1.2.0'
+  spec.add_development_dependency 'minitest-spec-context', '~> 0.0.3'
+  spec.add_development_dependency 'pry', '~> 0.9'
+  spec.add_development_dependency 'rake', '~> 10.1'
+  spec.add_development_dependency 'rubocop', '~> 0.20'
+  spec.add_development_dependency 'yard', '~> 0.8'
+
+end

data/lib/html2pdf.rb

@@ -0,0 +1,6 @@
+require 'agile_utils'
+require 'code_lister'
+require_relative './html2pdf/utils'
+require_relative './html2pdf/cli'
+include AgileUtils::Options
+include CodeLister

data/lib/html2pdf/cli.rb

@@ -0,0 +1,53 @@
+require 'thor'
+require 'tmpdir'
+require 'fileutils'
+require_relative '../html2pdf'
+module Html2Pdf
+  class CLI < Thor
+    desc 'export', 'export html files to pdfs'
+
+    method_option *AgileUtils::Options::BASE_DIR
+    method_option *AgileUtils::Options::INC_WORDS
+    method_option *AgileUtils::Options::EXC_WORDS
+    method_option *AgileUtils::Options::IGNORE_CASE
+    method_option *AgileUtils::Options::RECURSIVE
+    method_option *AgileUtils::Options::VERSION
+
+    def export
+      unless Html2Pdf::Utils.required_softwares?
+        fail 'You must have valid `wkhtmltopdf` and `ghostscript` installation'
+      end
+
+      input_files = CodeLister.files base_dir: options[:base_dir],
+                                     exts: %w(html xhtml),
+                                     recursive: true
+      elapsed = AgileUtils::FileUtil.time do
+        Html2Pdf::Utils.to_pdfs(input_files)
+      end
+      puts "Convert files to pdfs took #{elapsed} ms"
+    end
+
+    desc 'usage', 'Display usage information'
+    def usage
+      puts <<-EOT
+Usage:
+  html2pdf export [OPTIONS]
+
+Options:
+  -b, [--base-dir=BASE_DIR]                # Base directory
+                                           # Default: /Users/agilecreativity/codes/github/html2pdf
+  -n, [--inc-words=one two three]          # List of words to be included in the result
+  -x, [--exc-words=one two three]          # List of words to be excluded from the result
+  -i, [--ignore-case], [--no-ignore-case]  # Match case insensitively
+                                           # Default: true
+  -r, [--recursive], [--no-recursive]      # Search for files recursively
+                                           # Default: true
+  -v, [--version], [--no-version]          # Display version information
+
+export html files to pdfs
+      EOT
+    end
+
+    default_task :usage
+  end
+end

data/lib/html2pdf/utils.rb

@@ -0,0 +1,63 @@
+require 'open3'
+require 'fileutils'
+require_relative '../html2pdf'
+
+module Html2Pdf
+  module Utils
+    class << self
+      # Batch convert to pdf using `wkhtmltopdf` tool
+      #
+      # @param [Array<String>] files the input file list
+      # @param [String] base_dir the base directory
+      def to_pdfs(files)
+        files.each_with_index do |file, index|
+          puts "Convert file #{index + 1} of #{files.size} : #{file}"
+          to_pdf(file)
+        end
+      end
+
+      # Convert '*.xhtml' or '*.html' to pdf
+      #
+      # @param filename input filename
+      def to_pdf(filename)
+        # see: http://madalgo.au.dk/~jakobt/wkhtmltoxdoc/wkhtmltopdf_0.10.0_rc2-doc.html#Footers And Headers
+        #  - may be only allow "*.html" and "*.xhtml"
+        #  - allow the options to be passed in so that we can use different theme
+        #    '--no-background'
+        fail "Invalid input file #{filename}" unless File.exist?(filename)
+        command = [
+          'wkhtmltopdf',
+          '--margin-top 4',
+          '--margin-bottom 4',
+          '--margin-left 4',
+          '--margin-right 4',
+          # Note: working correctly but long URL
+          '--header-center "[webpage] :: [page]/[topage]"',
+          # header section
+          # TODO: not yet working properly
+          # "--header-center #{filename.gsub(base_dir,File.basename(base_dir))} \"[page]/[topage]\"",
+          # "--header-center #{filename} \"[page]/[topage]\"",
+          '--header-spacing 1',
+          '--header-font-size 8',
+          '--header-line',
+          # footer section
+          '--footer-spacing 1',
+          '--footer-font-size 8',
+          '--footer-line',
+          "#{filename}",
+          "#{filename}.pdf",
+          '> /dev/null']
+        _stdin, _stderr, status = Open3.capture3(command.join(' '))
+        # puts "FYI: to_pdf command: #{command.join(' ')}"
+        # Note: may be log it and continue
+        fail "Problem processing #{filename}" unless status.success?
+      end
+
+      # Check and verify that the proper softwares are available.
+      #
+      def required_softwares?
+        AgileUtils::Helper.which('gs') && AgileUtils::Helper.which('gs')
+      end
+    end
+  end
+end

data/lib/html2pdf/version.rb

@@ -0,0 +1,3 @@
+module Html2Pdf
+  VERSION = '0.0.1'
+end

data/rubocop-todo.yml

@@ -0,0 +1,84 @@
+# This configuration was generated by `rubocop --auto-gen-config`
+# on 2014-04-23 20:34:48 +1000 using RuboCop version 0.20.1.
+# The point is for the user to remove these configuration records
+# one by one as the offenses are removed from the code base.
+# Note that changes in the inspected code, or installation of new
+# versions of RuboCop, may require this file to be generated again.
+
+# Offense count: 9
+AmbiguousOperator:
+  Enabled: false
+
+# Offense count: 1
+# Cop supports --auto-correct.
+# Configuration parameters: PreferredMethods.
+CollectionMethods:
+  Enabled: false
+
+# Offense count: 1
+CyclomaticComplexity:
+  Max: 7
+
+# Offense count: 5
+Documentation:
+  Enabled: false
+
+# Offense count: 1
+# Cop supports --auto-correct.
+EmptyLinesAroundBody:
+  Enabled: true
+
+# Offense count: 1
+# Cop supports --auto-correct.
+# Configuration parameters: EnforcedStyle, SupportedStyles.
+HashSyntax:
+  Enabled: true
+
+# Offense count: 4
+# Cop supports --auto-correct.
+LeadingCommentSpace:
+  Enabled: true
+
+# Offense count: 18
+LineLength:
+  Max: 108
+
+# Offense count: 8
+# Configuration parameters: CountComments.
+MethodLength:
+  Max: 30
+
+# Offense count: 1
+# Cop supports --auto-correct.
+SpaceAfterComma:
+  Enabled: true
+
+# Offense count: 1
+# Cop supports --auto-correct.
+# Configuration parameters: EnforcedStyle, SupportedStyles, EnforcedStyleForEmptyBraces, SpaceBeforeBlockParameters.
+SpaceInsideBlockBraces:
+  Enabled: true
+
+# Offense count: 1
+# Cop supports --auto-correct.
+SpecialGlobalVars:
+  Enabled: true
+
+# Offense count: 16
+# Cop supports --auto-correct.
+# Configuration parameters: EnforcedStyle, SupportedStyles.
+StringLiterals:
+  Enabled: false
+
+# Offense count: 1
+UnreachableCode:
+  Enabled: true
+
+# Offense count: 1
+UselessAssignment:
+  Enabled: false
+
+# Offense count: 1
+# Cop supports --auto-correct.
+WordArray:
+  MinSize: 2