pdfkit 0.8.0 → 0.8.7.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: d761c045627c5f9435b7ea06b44d5e23abbbcdd6
-  data.tar.gz: 9f55905b443cfb6532696bf373173fd55435be56
+SHA256:
+  metadata.gz: dd9ab1711dcc1f5dc4c9ec2b0f5a203394cc8276291f34bd59230dd832c6b51c
+  data.tar.gz: 0ec141cfe484aea9ae00488c34da32573f8f84d7ae3a5a3d5c954a0d4acfbee5
 SHA512:
-  metadata.gz: 19210027b8208466fd91c6c3604b205739973e95ffb876feaecc6f0e0df76d2a78103dd2747c6f00e0d0af171da4235f31518f03da495fe5c9c638a804e3883d
-  data.tar.gz: 7a82596a5548c9ab3fb2557aef2aae5445f0dbae59196c436fd2c6846b2d6d9c1f51be0b6b85e4073c4da07bd160801d028601206ac04de2f81839c0b081dc5e
+  metadata.gz: d8cf1754028c05b1dab1f382c91b86672a8a2808bbabbe66132fdb78501a731b1a651b5d276c0818efba1b537a685d2f55cb2a281935edf8c7b5b58c3aed1f1a
+  data.tar.gz: 93f26e92cc31dd7f4fdaf1d5a20c2b2c5463d66588bc465bfacbfa4aecbbbe19662b1e605c1ac69593e1974fc0d606ff92298cfdace4c55313d977b87d128fc4

data/.github/workflows/release-drafter.yml

@@ -0,0 +1,19 @@
+name: Release Drafter
+
+on:
+  push:
+    # branches to consider in the event; optional, defaults to all
+    branches:
+      - master
+
+jobs:
+  update_release_draft:
+    runs-on: ubuntu-latest
+    steps:
+      # Drafts your next Release notes as Pull Requests are merged into "master"
+      - uses: release-drafter/release-drafter@v5
+        # with:
+          # (Optional) specify config name to use, relative to .github/. Default: release-drafter.yml
+          # config-name: my-config.yml
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}

data/.github/workflows/stale.yml

@@ -0,0 +1,19 @@
+name: Mark stale issues and pull requests
+
+on:
+  schedule:
+  - cron: "0 0 * * *"
+
+jobs:
+  stale:
+
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/stale@v1
+      with:
+        repo-token: ${{ secrets.GITHUB_TOKEN }}
+        stale-issue-message: 'This issue has been marked as stale and will be automatically closed.'
+        stale-pr-message: 'This pull request has been marked as stale and will be automatically closed.'
+        stale-issue-label: 'no-issue-activity'
+        stale-pr-label: 'no-pr-activity'

data/.github/workflows/test.yml

@@ -0,0 +1,59 @@
+name: Test workflow
+
+on: [push, pull_request]
+
+jobs:
+  test:
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest]
+        ruby:
+          - '2.5'
+          - '2.6'
+          - '2.7'
+          - '3.0'
+          - '3.1'
+        rails:
+          - '~> 4.1'
+          - '~> 5.2'
+          - '~> 6.0.0'
+          - '~> 6.1'
+          - '~> 7.0.0'
+        exclude:
+          - ruby: '2.5'
+            rails: '~> 7.0.0'
+          - ruby: '2.6'
+            rails: '~> 7.0.0'
+          - ruby: '2.7'
+            rails: '~> 4.1'
+          - ruby: '3.0'
+            rails: '~> 4.1'
+          - ruby: '3.0'
+            rails: '~> 5.2'
+          - ruby: '3.1'
+            rails: '~> 4.1'
+          - ruby: '3.1'
+            rails: '~> 5.2'
+          - ruby: '3.1'
+            rails: '~> 6.0.0'
+    runs-on: ${{ matrix.os }}
+    env:
+      RAILS_VERSION: ${{ matrix.rails }}
+    steps:
+    - uses: actions/checkout@v2
+    - uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: ${{ matrix.ruby }}
+        rubygems: latest
+        bundler: latest
+        bundler-cache: true
+
+    - name: Setup wkhtmltopdf
+      run: |
+        sudo apt-get install -y xfonts-base xfonts-75dpi
+        wget https://github.com/wkhtmltopdf/packaging/releases/download/0.12.6-1/wkhtmltox_0.12.6-1.bionic_amd64.deb
+        sudo dpkg -i wkhtmltox_0.12.6-1.bionic_amd64.deb
+
+    - name: Run tests
+      run: bundle exec rake

data/.ruby-version

@@ -1 +1 @@
-ruby-2.0.0
+2.6.9

data/.travis.yml

@@ -1,12 +1,46 @@
+language: ruby
+
 rvm:
-- 1.9.2
-- 1.9.3
-- 2.0
-- 2.1
+- 2.5
+- 2.6
+- 2.7
+- 3.0
+- 3.1
+
+env:
+  matrix:
+    - RAILS_VERSION="~> 4.1"
+    - RAILS_VERSION="~> 5.2"
+    - RAILS_VERSION="~> 6.0.0"
+    - RAILS_VERSION="~> 6.1"
+    - RAILS_VERSION="~> 7.0.0"
+
+jobs:
+  exclude:
+  - rvm: 2.5
+    env: RAILS_VERSION="~> 7.0.0"
+  - rvm: 2.6
+    env: RAILS_VERSION="~> 7.0.0"
+  - rvm: 2.7
+    env: RAILS_VERSION="~> 4.1"
+  - rvm: 3.0
+    env: RAILS_VERSION="~> 4.1"
+  - rvm: 3.0
+    env: RAILS_VERSION="~> 5.2"
+  - rvm: 3.1
+    env: RAILS_VERSION="~> 4.1"
+  - rvm: 3.1
+    env: RAILS_VERSION="~> 5.2"
+  - rvm: 3.1
+    env: RAILS_VERSION="~> 6.0.0"
+
+cache: bundler
+
+before_install:
+  - gem update --system
+  - gem update bundler
 
 before_script:
-  - "export DISPLAY=:99.0"
-  - "sh -e /etc/init.d/xvfb start"
   - "sudo apt-get -qq -y install fontconfig libxrender1"
-  - "wget http://downloads.sourceforge.net/project/wkhtmltopdf/archive/0.12.1/wkhtmltox-0.12.1_linux-precise-amd64.deb"
-  - "sudo dpkg -i wkhtmltox-0.12.1_linux-precise-amd64.deb"
+  - "wget https://github.com/wkhtmltopdf/wkhtmltopdf/releases/download/0.12.5/wkhtmltox_0.12.5-1.xenial_amd64.deb"
+  - "sudo apt-get install ./wkhtmltox_0.12.5-1.xenial_amd64.deb"

data/CHANGELOG.md

@@ -1,6 +1,76 @@
+2022-10-17
+=================
+  * Bump to 0.8.7.1
+  * Support non-lower-case Content-Type header provided by app (#516)
+
+2022-10-02
+=================
+  * Bump to 0.8.7
+  * Lowercase the header names for rack 3 changes (#511)
+  * Partially escaped URLs should be escaped (#509)
+
+2022-04-11
+=================
+  * Bump to 0.8.6
+  * Update ruby and rails versions
+
+2021-01-23
+=================
+  * Bump to 0.8.5
+  * Make `PDFKit::VERSION` public (#484) 
+  * Fix to render stylesheets as html safe string on Rails 6 (#483)
+      * Adds support for Rails 6
+
+2020-08-16
+=================
+  * Bump to 0.8.4.3.2
+  * Reduce scope of middleware exception handling (#476)
+
+2020-07-05
+=================
+  * Bump to 0.8.4.3.1
+  * Don't override request level Content-Disposition header if it exists (#466)
+  * Update rake (#471)
+  * Add missing require statements for tempfile (#467)
+  * Only grab last line of bundle exec which output (#464)
+  * Return 500 status when an exception is caught in middleware (#469)
+  * Update Travis CI URL for wkhtmltopf (#473)
+  
+2020-04-01
+=================
+  * Bump to 0.8.4.2
+  * Improve path detection feedback (#460)
+  * Fix typos (#444)
+  * Update readme (#439)
+  
+2019-02-22
+=================
+  * Bump to 0.8.4.1
+  * Make PDFkit threadsafe (#377)
+  * Update activesupport (#434)
+
+2019-02-21
+=================
+  * Bump to 0.8.4
+  * Removed support for Ruby < 2.2
+  * Xvfb support (#277)
+  * Remove 'config.protocol' from the README (#389)
+
+2015-08-26
+=================
+  * Bump to 0.8.2
+  * Fix URI errors for users using PDFKit in contexts with 'uri' not
+    already required (thanks christhekeele)
+
+2015-08-20
+=================
+  * Bump to 0.8.1
+  * Fix shell escaping issues for Windows (thanks muness)
+  * Fix shell escaping issues for URLs, introduced in 0.5.3 release
+
 2015-07-08
 =================
-  * Bump to 0.7.1
+  * Bump to 0.8.0
   * Support Cover and Table Of Contents options (thanks @nicpillinger)
   * Fix repeatings keys with string values
   * Fix caching bug (thanks @jocranford)

data/Gemfile

@@ -1,7 +1,7 @@
 source 'https://rubygems.org'
 
 group :test do
-  gem 'activesupport', '~> 3.0'
+  gem 'activesupport', ENV['RAILS_VERSION'] || '~> 4.1'
   gem 'simplecov', require: false
 end
 

data/README.md

@@ -2,6 +2,11 @@
 
 Create PDFs using plain old HTML+CSS. Uses [wkhtmltopdf](http://github.com/antialize/wkhtmltopdf) on the back-end which renders HTML using Webkit.
 
+## Supported versions
+
+- Ruby 2.5, 2.6, 2.7, 3.0, 3.1
+- Rails 4.2, 5.2, 6.0, 6.1, 7.0
+
 ## Install
 
 ### PDFKit
@@ -14,7 +19,7 @@ gem install pdfkit
 
     <https://github.com/pdfkit/pdfkit/wiki/Installing-WKHTMLTOPDF>
 
-2.  Try using the `wkhtmltopdf-binary` gem (mac + linux i386)
+2.  Try using the `wkhtmltopdf-binary-edge` gem (mac + linux i386)
 ```
 gem install wkhtmltopdf-binary
 ```
@@ -34,7 +39,7 @@ pdf = kit.to_pdf
 file = kit.to_file('/path/to/save/pdf')
 
 # PDFKit.new can optionally accept a URL or a File.
-# Stylesheets can not be added when source is provided as a URL of File.
+# Stylesheets can not be added when source is provided as a URL or File.
 kit = PDFKit.new('http://google.com')
 kit = PDFKit.new(File.new('/path/to/html'))
 
@@ -43,8 +48,22 @@ PDFKit.new('<html><head><meta name="pdfkit-page_size" content="Letter"')
 PDFKit.new('<html><head><meta name="pdfkit-cookie cookie_name1" content="cookie_value1"')
 PDFKit.new('<html><head><meta name="pdfkit-cookie cookie_name2" content="cookie_value2"')
 ```
+
+### Resolving relative URLs and protocols
+
+If the source HTML has relative URLs (`/images/cat.png`) or
+[protocols](https://en.wikipedia.org/wiki/Uniform_Resource_Locator#prurl)
+(`//example.com/site.css`) that need to be resolved, you can pass `:root_url`
+and `:protocol` options to PDFKit:
+
+```ruby
+PDFKit.new(html, root_url: 'http://mysite.com/').to_file
+# or:
+PDFKit.new(html, protocol: 'https').to_file
+```
+
 ### Using cookies in scraping
-If you want to pass a cookie to cookie to pdfkit to scrape a website, you can 
+If you want to pass a cookie to pdfkit to scrape a website, you can
 pass it in a hash:
 ```ruby
 kit = PDFKit.new(url, cookie: {cookie_name: :cookie_value})
@@ -102,6 +121,13 @@ config.middleware.use PDFKit::Middleware, {}, :except => [%r[^/prawn], %r[^/secr
 # conditions can be strings (either one or an array)
 config.middleware.use PDFKit::Middleware, {}, :except => ['/secret']
 ```
+**With conditions to force download**
+```ruby
+# force download with attachment disposition
+config.middleware.use PDFKit::Middleware, {}, :disposition => 'attachment'
+# conditions can force a filename
+config.middleware.use PDFKit::Middleware, {}, :disposition => 'attachment; filename=report.pdf'
+```
 **Saving the generated .pdf to disk**
 
 Setting the `PDFKit-save-pdf` header will cause PDFKit to write the generated .pdf to the file indicated by the value of the header.
@@ -111,7 +137,7 @@ For example:
 headers['PDFKit-save-pdf'] = 'path/to/saved.pdf'
 ```
 
-Will cause the .pdf to be saved to `path/to/saved.pdf` in addition to being sent back to the client.  If the path is not writable/non-existant the write will fail silently.  The `PDFKit-save-pdf` header is never sent back to the client.
+Will cause the .pdf to be saved to `path/to/saved.pdf` in addition to being sent back to the client.  If the path is not writable/non-existent the write will fail silently.  The `PDFKit-save-pdf` header is never sent back to the client.
 
 ## Troubleshooting
 
@@ -126,13 +152,13 @@ Will cause the .pdf to be saved to `path/to/saved.pdf` in addition to being sent
    around this issue you may want to run a server with multiple workers
    like Passenger or try to embed your resources within your HTML to
    avoid extra HTTP requests.
-   
-   Example solution (rails / bundler), add unicorn to the development 
-   group in your Gemfile `gem 'unicorn'` then run `bundle`. Next, add a 
+
+   Example solution (rails / bundler), add unicorn to the development
+   group in your Gemfile `gem 'unicorn'` then run `bundle`. Next, add a
    file `config/unicorn.conf` with
-   
+
         worker_processes 3
-   
+
    Then to run the app `unicorn_rails -c config/unicorn.conf` (from rails_root)
 
 *  **Resources aren't included in the PDF:** Images, CSS, or JavaScript
@@ -146,7 +172,7 @@ Will cause the .pdf to be saved to `path/to/saved.pdf` in addition to being sent
    asset host.
 
 *  **Mangled output in the browser:** Be sure that your HTTP response
-   headers specify "Content-Type: application/pdf" 
+   headers specify "content-type: application/pdf"
 
 ## Note on Patches/Pull Requests
 

data/lib/pdfkit/configuration.rb

@@ -1,10 +1,14 @@
+# frozen_string_literal: true
+
 class PDFKit
   class Configuration
-    attr_accessor :meta_tag_prefix, :default_options, :root_url
-    attr_writer :wkhtmltopdf, :verbose
+    attr_accessor :meta_tag_prefix, :root_url
+    attr_writer :use_xvfb, :verbose
+    attr_reader :default_options
 
     def initialize
       @verbose         = false
+      @use_xvfb        = false
       @meta_tag_prefix = 'pdfkit-'
       @default_options = {
         :disable_smart_shrinking => false,
@@ -19,7 +23,33 @@ class PDFKit
     end
 
     def wkhtmltopdf
-      @wkhtmltopdf ||= (defined?(Bundler::GemfileError) && File.exists?('Gemfile') ? `bundle exec which wkhtmltopdf` : `which wkhtmltopdf`).chomp
+      @wkhtmltopdf ||= default_wkhtmltopdf
+    end
+
+    def default_wkhtmltopdf
+      return @default_command_path if @default_command_path
+      if defined?(Bundler::GemfileError) && File.exist?('Gemfile')
+        @default_command_path = `bundle exec which wkhtmltopdf`.chomp.lines.last
+      end
+      @default_command_path = `which wkhtmltopdf`.chomp if @default_command_path.nil? || @default_command_path.empty?
+      @default_command_path
+    end
+
+    def wkhtmltopdf=(path)
+      if File.exist?(path)
+        @wkhtmltopdf = path
+      else
+        warn "No executable found at #{path}. Will fall back to #{default_wkhtmltopdf}"
+        @wkhtmltopdf = default_wkhtmltopdf
+      end
+    end
+
+    def executable
+      using_xvfb? ? "xvfb-run #{wkhtmltopdf}" : wkhtmltopdf
+    end
+
+    def using_xvfb?
+      @use_xvfb
     end
 
     def quiet?
@@ -29,6 +59,10 @@ class PDFKit
     def verbose?
       @verbose
     end
+
+    def default_options=(options)
+      @default_options.merge!(options)
+    end
   end
 
   class << self
@@ -41,6 +75,7 @@ class PDFKit
   # @example
   #   PDFKit.configure do |config|
   #     config.wkhtmltopdf = '/usr/bin/wkhtmltopdf'
+  #     config.use_xvfb    = true
   #     config.verbose     = true
   #   end
 

data/lib/pdfkit/html_preprocessor.rb

@@ -0,0 +1,25 @@
+# frozen_string_literal: true
+
+class PDFKit
+  module HTMLPreprocessor
+
+    # Change relative paths to absolute, and relative protocols to absolute protocols
+    def self.process(html, root_url, protocol)
+      html = translate_relative_paths(html, root_url) if root_url
+      html = translate_relative_protocols(html, protocol) if protocol
+      html
+    end
+
+    private
+
+    def self.translate_relative_paths(html, root_url)
+      # Try out this regexp using rubular http://rubular.com/r/hiAxBNX7KE
+      html.gsub(/(href|src)=(['"])\/([^\/"']([^\"']*|[^"']*))?['"]/, "\\1=\\2#{root_url}\\3\\2")
+    end
+
+    def self.translate_relative_protocols(body, protocol)
+      # Try out this regexp using rubular http://rubular.com/r/0Ohk0wFYxV
+      body.gsub(/(href|src)=(['"])\/\/([^\"']*|[^"']*)['"]/, "\\1=\\2#{protocol}://\\3\\2")
+    end
+  end
+end

data/lib/pdfkit/middleware.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 class PDFKit
   class Middleware
     def initialize(app, options = {}, conditions = {})
@@ -9,31 +11,51 @@ class PDFKit
     end
 
     def call(env)
+      dup._call(env)
+    end
+
+    def _call(env)
       @request    = Rack::Request.new(env)
       @render_pdf = false
 
       set_request_to_render_as_pdf(env) if render_as_pdf?
       status, headers, response = @app.call(env)
 
-      if rendering_pdf? && headers['Content-Type'] =~ /text\/html|application\/xhtml\+xml/
-        body = response.respond_to?(:body) ? response.body : response.join
-        body = body.join if body.is_a?(Array)
-        body = PDFKit.new(translate_paths(body, env), @options).to_pdf
-        response = [body]
-
-        if headers['PDFKit-save-pdf']
-          File.open(headers['PDFKit-save-pdf'], 'wb') { |file| file.write(body) } rescue nil
-          headers.delete('PDFKit-save-pdf')
-        end
-
-        unless @caching
-          # Do not cache PDFs
-          headers.delete('ETag')
-          headers.delete('Cache-Control')
+      begin
+        content_type_header = headers.has_key?('Content-Type') ? 'Content-Type' : 'content-type'
+        if rendering_pdf? && headers[content_type_header] =~ /text\/html|application\/xhtml\+xml/
+          body = response.respond_to?(:body) ? response.body : response.join
+          body = body.join if body.is_a?(Array)
+
+          root_url = root_url(env)
+          protocol = protocol(env)
+          options = @options.merge(root_url: root_url, protocol: protocol)
+
+          if headers['PDFKit-javascript-delay']
+            options.merge!(javascript_delay: headers.delete('PDFKit-javascript-delay').to_i)
+          end
+
+          body = PDFKit.new(body, options).to_pdf
+          response = [body]
+
+          if headers['PDFKit-save-pdf']
+            File.open(headers['PDFKit-save-pdf'], 'wb') { |file| file.write(body) } rescue nil
+            headers.delete('PDFKit-save-pdf')
+          end
+
+          unless @caching
+            # Do not cache PDFs
+            headers.delete('etag')
+            headers.delete('cache-control')
+          end
+
+          headers['content-length'] = (body.respond_to?(:bytesize) ? body.bytesize : body.size).to_s
+          headers[content_type_header]   = 'application/pdf'
+          headers['content-disposition'] ||= @conditions[:disposition] || 'inline'
         end
-
-        headers['Content-Length']         = (body.respond_to?(:bytesize) ? body.bytesize : body.size).to_s
-        headers['Content-Type']           = 'application/pdf'
+      rescue StandardError => e
+        status = 500
+        response = [e.message]
       end
 
       [status, headers, response]
@@ -41,22 +63,12 @@ class PDFKit
 
     private
 
-    # Change relative paths to absolute, and relative protocols to absolute protocols
-    def translate_paths(body, env)
-      body = translate_relative_paths(body, env)
-      translate_relative_protocols(body, env)
+    def root_url(env)
+      PDFKit.configuration.root_url || "#{env['rack.url_scheme']}://#{env['HTTP_HOST']}/"
     end
 
-    def translate_relative_paths(body, env)
-      root = PDFKit.configuration.root_url || "#{env['rack.url_scheme']}://#{env['HTTP_HOST']}/"
-      # Try out this regexp using rubular http://rubular.com/r/hiAxBNX7KE
-      body.gsub(/(href|src)=(['"])\/([^\/"']([^\"']*|[^"']*))?['"]/, "\\1=\\2#{root}\\3\\2")
-    end
-
-    def translate_relative_protocols(body, env)
-      protocol = "#{env['rack.url_scheme']}://"
-      # Try out this regexp using rubular http://rubular.com/r/0Ohk0wFYxV
-      body.gsub(/(href|src)=(['"])\/\/([^\"']*|[^"']*)['"]/, "\\1=\\2#{protocol}\\3\\2")
+    def protocol(env)
+      env['rack.url_scheme']
     end
 
     def rendering_pdf?
@@ -65,20 +77,18 @@ class PDFKit
 
     def render_as_pdf?
       request_path = @request.path
-      request_path_is_pdf = request_path.match(%r{\.pdf$})
+      return false unless request_path.end_with?('.pdf')
 
-      if request_path_is_pdf && @conditions[:only]
+      if @conditions[:only]
         conditions_as_regexp(@conditions[:only]).any? do |pattern|
-          request_path =~ pattern
+          pattern === request_path
         end
-      elsif request_path_is_pdf && @conditions[:except]
-        conditions_as_regexp(@conditions[:except]).each do |pattern|
-          return false if request_path =~ pattern
+      elsif @conditions[:except]
+        conditions_as_regexp(@conditions[:except]).none? do |pattern|
+          pattern === request_path
         end
-
-        return true
       else
-        request_path_is_pdf
+        true
       end
     end
 
@@ -99,8 +109,8 @@ class PDFKit
     end
 
     def conditions_as_regexp(conditions)
-      [conditions].flatten.map do |pattern|
-        pattern.is_a?(Regexp) ? pattern : Regexp.new('^' + pattern)
+      Array(conditions).map do |pattern|
+        pattern.is_a?(Regexp) ? pattern : Regexp.new("^#{pattern}")
       end
     end
   end

data/lib/pdfkit/os.rb

@@ -0,0 +1,21 @@
+# frozen_string_literal: true
+
+require 'rbconfig'
+
+class PDFKit
+  module OS
+    def self.host_is_windows?
+      !(RbConfig::CONFIG['host_os'] =~ /mswin|msys|mingw|cygwin|bccwin|wince/).nil?
+    end
+
+    def self.shell_escape_for_os(args)
+      if (host_is_windows?)
+        # Windows reserved shell characters are: & | ( ) < > ^
+        # See http://technet.microsoft.com/en-us/library/cc723564.aspx#XSLTsection123121120120
+        args.map { |arg| arg.gsub(/([&|()<>^])/,'^\1') }.join(" ")
+      else
+        args.shelljoin
+      end
+    end
+  end
+end