grover 0.2.0 → 0.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: cf861057bca3ab2b9c59bf0c52b329bb70cd1e5c
-  data.tar.gz: 910e24710cfd955ca779b600680ce7b50bc8458b
+  metadata.gz: ec9fbd6ca4d7cd40c4a8d3a0da2627bb599bbe20
+  data.tar.gz: 169db229a825e41c40914bedb74057bb9935de4a
 SHA512:
-  metadata.gz: 6c101f3d8bf4b9cdefa35ed26994e24498c9eede363ed798450b1cc849b288547b34e28ded856387bda3e3d20335b76aed0547527baaa5632a6e3164f5bbc1a8
-  data.tar.gz: 3fbc34457ebb9a151c85e01217ddc884baaac14c36532c0eec77856557188b7351389f6ec73cdc400ad2379589fccf158fd0b20c5f2626f27de5e850ffa7ff31
+  metadata.gz: c7a89544aefdf652135d81e4d8f565bd63dc131604717c158affb77a97523abc5e5ea6192263842484727a6c617215ebf92b76fc662293ee4b861e127dd06f65
+  data.tar.gz: 757d7d1f0df9958f29cd6f5f52fb7d2a00424570ba8e3b231cd95de40b806ffd93c105948ed24948bdb7d05b7c95cb57d703e8a1e892e6508edf8c4565e58d1e

data/lib/grover.rb

@@ -2,6 +2,7 @@ require 'grover/version'
 
 require 'grover/utils'
 require 'grover/processor'
+require 'grover/html_preprocessor'
 require 'grover/middleware'
 
 #

data/lib/grover/html_preprocessor.rb

@@ -0,0 +1,28 @@
+class Grover
+  #
+  # Helper module for preparing HTML for conversion
+  #
+  # Sourced from the PDFKit project
+  # @see https://github.com/pdfkit/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
+
+    def self.translate_relative_paths(html, root_url)
+      # Try out this regexp using rubular http://rubular.com/r/hiAxBNX7KE
+      html.gsub(%r{(href|src)=(['"])/([^/"']([^\"']*|[^"']*))?['"]}, "\\1=\\2#{root_url}\\3\\2")
+    end
+    private_class_method :translate_relative_paths
+
+    def self.translate_relative_protocols(body, protocol)
+      # Try out this regexp using rubular http://rubular.com/r/0Ohk0wFYxV
+      body.gsub(%r{(href|src)=(['"])//([^\"']*|[^"']*)['"]}, "\\1=\\2#{protocol}://\\3\\2")
+    end
+    private_class_method :translate_relative_protocols
+  end
+end

data/lib/grover/middleware.rb

@@ -2,6 +2,9 @@ class Grover
   #
   # Rack middleware for catching PDF requests and returning the upstream HTML as a PDF
   #
+  # Much of this code was sourced from the PDFKit project
+  # @see https://github.com/pdfkit/pdfkit
+  #
   class Middleware
     def initialize(app)
       @app = app
@@ -12,22 +15,12 @@ class Grover
       @request = Rack::Request.new(env)
       @render_pdf = false
 
-      set_request_to_render_as_pdf(env) if render_as_pdf?
+      configure_env_for_pdf_request(env) if render_as_pdf?
       status, headers, response = @app.call(env)
 
-      if rendering_pdf? && headers['Content-Type'] =~ %r{text/html|application/xhtml\+xml}
-        body = response.respond_to?(:body) ? response.body : response.join
-        body = body.join if body.is_a?(Array)
-
-        body = Grover.new(body).to_pdf
-        response = [body]
-
-        # Do not cache PDFs
-        headers.delete 'ETag'
-        headers.delete 'Cache-Control'
-
-        headers['Content-Length'] = (body.respond_to?(:bytesize) ? body.bytesize : body.size).to_s
-        headers['Content-Type'] = 'application/pdf'
+      if rendering_pdf? && html_content?(headers)
+        response = convert_to_pdf response
+        update_headers headers, body
       end
 
       [status, headers, response]
@@ -43,13 +36,49 @@ class Grover
       @request.path.end_with?('.pdf')
     end
 
-    def set_request_to_render_as_pdf(env)
+    def html_content?(headers)
+      headers['Content-Type'] =~ %r{text/html|application/xhtml\+xml}
+    end
+
+    def convert_to_pdf(response)
+      body = response.respond_to?(:body) ? response.body : response.join
+      body = body.join if body.is_a?(Array)
+
+      body = HTMLPreprocessor.process body, request_url, protocol
+      body = Grover.new(body).to_pdf
+      [body]
+    end
+
+    def update_headers(headers, body)
+      # Do not cache PDFs
+      headers.delete 'ETag'
+      headers.delete 'Cache-Control'
+
+      headers['Content-Length'] = (body.respond_to?(:bytesize) ? body.bytesize : body.size).to_s
+      headers['Content-Type'] = 'application/pdf'
+    end
+
+    def configure_env_for_pdf_request(env)
       @render_pdf = true
+
+      path = @request.path.sub(/\.pdf$/, '')
+      path = path.sub(@request.script_name, '')
+
+      %w[PATH_INFO REQUEST_URI].each { |e| env[e] = path }
+
       env['HTTP_ACCEPT'] = concat(env['HTTP_ACCEPT'], Rack::Mime.mime_type('.html'))
     end
 
     def concat(accepts, type)
       (accepts || '').split(',').unshift(type).compact.join(',')
     end
+
+    def request_url
+      "#{env['rack.url_scheme']}://#{env['HTTP_HOST']}/"
+    end
+
+    def protocol
+      env['rack.url_scheme']
+    end
   end
 end

data/lib/grover/processor.rb

@@ -21,7 +21,7 @@ class Grover
           if (url.match(/^http/i)) {
             await page.goto(url, { waitUntil: 'networkidle2' });
           } else {
-            await page.setContent(url);
+            await page.goto(`data:text/html,${url}`, { waitUntil: 'networkidle0' });
           }
           return await page.pdf(options);
         } finally {

data/lib/grover/version.rb

@@ -1,3 +1,3 @@
 class Grover
-  VERSION = '0.2.0'.freeze
+  VERSION = '0.2.1'.freeze
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: grover
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.1
 platform: ruby
 authors:
 - Andrew Bromwich
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-08-22 00:00:00.000000000 Z
+date: 2018-08-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: schmooze
@@ -102,6 +102,7 @@ extensions: []
 extra_rdoc_files: []
 files:
 - lib/grover.rb
+- lib/grover/html_preprocessor.rb
 - lib/grover/middleware.rb
 - lib/grover/processor.rb
 - lib/grover/utils.rb