pdfkit 0.8.6 → 0.8.7.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2c5255fcf07a7c382fc239a68a805d8a2950df682166a5913ca60c34bac9fe44
-  data.tar.gz: 43555629ecdba193f051ab0ea10f025f7917acf558af58ea30ae69cac6f6b210
+  metadata.gz: dd9ab1711dcc1f5dc4c9ec2b0f5a203394cc8276291f34bd59230dd832c6b51c
+  data.tar.gz: 0ec141cfe484aea9ae00488c34da32573f8f84d7ae3a5a3d5c954a0d4acfbee5
 SHA512:
-  metadata.gz: eb5f31eb9f0f84eb8d9b626c5c804f4f58ab0230b410740cad8810c4b0f673608ebb4874a0aa5f3fffade6c78b551e2a3fa339075fe0aad0f446117eb4af23bb
-  data.tar.gz: a9e6dd403b4ec4795e9af96fd1d2e896d1d1cb497adaca1fd96044504877bf264dfd5cf3a161012430a5930aaf4921271b1ad4ee294ec1e357f3e39366ec6be3
+  metadata.gz: d8cf1754028c05b1dab1f382c91b86672a8a2808bbabbe66132fdb78501a731b1a651b5d276c0818efba1b537a685d2f55cb2a281935edf8c7b5b58c3aed1f1a
+  data.tar.gz: 93f26e92cc31dd7f4fdaf1d5a20c2b2c5463d66588bc465bfacbfa4aecbbbe19662b1e605c1ac69593e1974fc0d606ff92298cfdace4c55313d977b87d128fc4

data/CHANGELOG.md

@@ -1,3 +1,14 @@
+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

data/README.md

@@ -63,7 +63,7 @@ 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})
@@ -172,7 +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/middleware.rb

@@ -22,7 +22,8 @@ class PDFKit
       status, headers, response = @app.call(env)
 
       begin
-        if rendering_pdf? && headers['Content-Type'] =~ /text\/html|application\/xhtml\+xml/
+        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)
 
@@ -44,13 +45,13 @@ class PDFKit
 
           unless @caching
             # Do not cache PDFs
-            headers.delete('ETag')
-            headers.delete('Cache-Control')
+            headers.delete('etag')
+            headers.delete('cache-control')
           end
 
-          headers['Content-Length'] = (body.respond_to?(:bytesize) ? body.bytesize : body.size).to_s
-          headers['Content-Type']   = 'application/pdf'
-          headers['Content-Disposition'] ||= @conditions[:disposition] || 'inline'
+          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
       rescue StandardError => e
         status = 500

data/lib/pdfkit/source.rb

@@ -46,7 +46,7 @@ class PDFKit
     end
 
     def url_needs_escaping?
-      URI::DEFAULT_PARSER.unescape(@source) == @source
+      URI::DEFAULT_PARSER.escape(URI::DEFAULT_PARSER.unescape(@source)) != @source
     end
   end
 end

data/lib/pdfkit/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 class PDFKit
-  VERSION = '0.8.6'
+  VERSION = '0.8.7.1'
 end

data/spec/middleware_spec.rb

@@ -19,7 +19,7 @@ end
 
 describe PDFKit::Middleware do
   let(:headers) do
-    {'Content-Type' => "text/html"}
+    {'content-type' => "text/html"}
   end
 
   describe "#call" do
@@ -55,36 +55,36 @@ describe PDFKit::Middleware do
     describe "caching" do
       let(:headers) do
         {
-          'Content-Type' => "text/html",
-          'ETag' => 'foo',
-          'Cache-Control' => 'max-age=2592000, public'
+          'content-type' => "text/html",
+          'etag' => 'foo',
+          'cache-control' => 'max-age=2592000, public'
         }
       end
 
       context "by default" do
         before { mock_app }
 
-        it "deletes ETag" do
+        it "deletes etag" do
           get 'http://www.example.org/public/test.pdf'
-          expect(last_response.headers["ETag"]).to be_nil
+          expect(last_response.headers["etag"]).to be_nil
         end
-        it "deletes Cache-Control" do
+        it "deletes cache-control" do
           get 'http://www.example.org/public/test.pdf'
-          expect(last_response.headers["Cache-Control"]).to be_nil
+          expect(last_response.headers["cache-control"]).to be_nil
         end
       end
 
       context "when on" do
         before { mock_app({}, :caching => true) }
 
-        it "preserves ETag" do
+        it "preserves etag" do
           get 'http://www.example.org/public/test.pdf'
-          expect(last_response.headers["ETag"]).not_to be_nil
+          expect(last_response.headers["etag"]).not_to be_nil
         end
 
-        it "preserves Cache-Control" do
+        it "preserves cache-control" do
           get 'http://www.example.org/public/test.pdf'
-          expect(last_response.headers["Cache-Control"]).not_to be_nil
+          expect(last_response.headers["cache-control"]).not_to be_nil
         end
       end
     end
@@ -99,7 +99,7 @@ describe PDFKit::Middleware do
             context "matching" do
               specify do
                 get 'http://www.example.org/public/test.pdf'
-                expect(last_response.headers["Content-Type"]).to eq("application/pdf")
+                expect(last_response.headers["content-type"]).to eq("application/pdf")
                 expect(last_response.body.bytesize).to eq(PDFKit.new("Hello world!").to_pdf.bytesize)
               end
             end
@@ -107,7 +107,7 @@ describe PDFKit::Middleware do
             context "not matching" do
               specify do
                 get 'http://www.example.org/secret/test.pdf'
-                expect(last_response.headers["Content-Type"]).to eq("text/html")
+                expect(last_response.headers["content-type"]).to eq("text/html")
                 expect(last_response.body).to eq("Hello world!")
               end
             end
@@ -119,7 +119,7 @@ describe PDFKit::Middleware do
             context "matching" do
               specify do
                 get 'http://www.example.org/public/test.pdf'
-                expect(last_response.headers["Content-Type"]).to eq("application/pdf")
+                expect(last_response.headers["content-type"]).to eq("application/pdf")
                 expect(last_response.body.bytesize).to eq(PDFKit.new("Hello world!").to_pdf.bytesize)
               end
             end
@@ -127,7 +127,7 @@ describe PDFKit::Middleware do
             context "not matching" do
               specify do
                 get 'http://www.example.org/secret/test.pdf'
-                expect(last_response.headers["Content-Type"]).to eq("text/html")
+                expect(last_response.headers["content-type"]).to eq("text/html")
                 expect(last_response.body).to eq("Hello world!")
               end
             end
@@ -141,7 +141,7 @@ describe PDFKit::Middleware do
             context "matching" do
               specify do
                 get 'http://www.example.org/public/test.pdf'
-                expect(last_response.headers["Content-Type"]).to eq("application/pdf")
+                expect(last_response.headers["content-type"]).to eq("application/pdf")
                 expect(last_response.body.bytesize).to eq(PDFKit.new("Hello world!").to_pdf.bytesize)
               end
             end
@@ -149,7 +149,7 @@ describe PDFKit::Middleware do
             context "not matching" do
               specify do
                 get 'http://www.example.org/secret/test.pdf'
-                expect(last_response.headers["Content-Type"]).to eq("text/html")
+                expect(last_response.headers["content-type"]).to eq("text/html")
                 expect(last_response.body).to eq("Hello world!")
               end
             end
@@ -161,7 +161,7 @@ describe PDFKit::Middleware do
             context "matching" do
               specify do
                 get 'http://www.example.org/public/test.pdf'
-                expect(last_response.headers["Content-Type"]).to eq("application/pdf")
+                expect(last_response.headers["content-type"]).to eq("application/pdf")
                 expect(last_response.body.bytesize).to eq(PDFKit.new("Hello world!").to_pdf.bytesize)
               end
             end
@@ -169,7 +169,7 @@ describe PDFKit::Middleware do
             context "not matching" do
               specify do
                 get 'http://www.example.org/secret/test.pdf'
-                expect(last_response.headers["Content-Type"]).to eq("text/html")
+                expect(last_response.headers["content-type"]).to eq("text/html")
                 expect(last_response.body).to eq("Hello world!")
               end
             end
@@ -187,7 +187,7 @@ describe PDFKit::Middleware do
             context "matching" do
               specify do
                 get 'http://www.example.org/public/test.pdf'
-                expect(last_response.headers["Content-Type"]).to eq("application/pdf")
+                expect(last_response.headers["content-type"]).to eq("application/pdf")
                 expect(last_response.body.bytesize).to eq(PDFKit.new("Hello world!").to_pdf.bytesize)
               end
             end
@@ -195,7 +195,7 @@ describe PDFKit::Middleware do
             context "not matching" do
               specify do
                 get 'http://www.example.org/secret/test.pdf'
-                expect(last_response.headers["Content-Type"]).to eq("text/html")
+                expect(last_response.headers["content-type"]).to eq("text/html")
                 expect(last_response.body).to eq("Hello world!")
               end
             end
@@ -207,7 +207,7 @@ describe PDFKit::Middleware do
             context "matching" do
               specify do
                 get 'http://www.example.org/public/test.pdf'
-                expect(last_response.headers["Content-Type"]).to eq("application/pdf")
+                expect(last_response.headers["content-type"]).to eq("application/pdf")
                 expect(last_response.body.bytesize).to eq(PDFKit.new("Hello world!").to_pdf.bytesize)
               end
             end
@@ -215,7 +215,7 @@ describe PDFKit::Middleware do
             context "not matching" do
               specify do
                 get 'http://www.example.org/secret/test.pdf'
-                expect(last_response.headers["Content-Type"]).to eq("text/html")
+                expect(last_response.headers["content-type"]).to eq("text/html")
                 expect(last_response.body).to eq("Hello world!")
               end
             end
@@ -229,7 +229,7 @@ describe PDFKit::Middleware do
             context "matching" do
               specify do
                 get 'http://www.example.org/public/test.pdf'
-                expect(last_response.headers["Content-Type"]).to eq("application/pdf")
+                expect(last_response.headers["content-type"]).to eq("application/pdf")
                 expect(last_response.body.bytesize).to eq(PDFKit.new("Hello world!").to_pdf.bytesize)
               end
             end
@@ -237,7 +237,7 @@ describe PDFKit::Middleware do
             context "not matching" do
               specify do
                 get 'http://www.example.org/secret/test.pdf'
-                expect(last_response.headers["Content-Type"]).to eq("text/html")
+                expect(last_response.headers["content-type"]).to eq("text/html")
                 expect(last_response.body).to eq("Hello world!")
               end
             end
@@ -249,7 +249,7 @@ describe PDFKit::Middleware do
             context "matching" do
               specify do
                 get 'http://www.example.org/public/test.pdf'
-                expect(last_response.headers["Content-Type"]).to eq("application/pdf")
+                expect(last_response.headers["content-type"]).to eq("application/pdf")
                 expect(last_response.body.bytesize).to eq(PDFKit.new("Hello world!").to_pdf.bytesize)
               end
             end
@@ -257,7 +257,7 @@ describe PDFKit::Middleware do
             context "not matching" do
               specify do
                 get 'http://www.example.org/secret/test.pdf'
-                expect(last_response.headers["Content-Type"]).to eq("text/html")
+                expect(last_response.headers["content-type"]).to eq("text/html")
                 expect(last_response.body).to eq("Hello world!")
               end
             end
@@ -348,14 +348,14 @@ describe PDFKit::Middleware do
         describe "doesn't overwrite existing value" do
           let(:headers) do
             super().merge({
-              'Content-Disposition' => 'attachment; filename=report-20200101.pdf'
+              'content-disposition' => 'attachment; filename=report-20200101.pdf'
             })
           end
 
           specify do
             mock_app({}, { :disposition => 'inline' })
             get 'http://www.example.org/public/test.pdf'
-            expect(last_response.headers["Content-Disposition"]).to eq('attachment; filename=report-20200101.pdf')
+            expect(last_response.headers["content-disposition"]).to eq('attachment; filename=report-20200101.pdf')
           end
         end
 
@@ -364,7 +364,7 @@ describe PDFKit::Middleware do
             specify do
               mock_app
               get 'http://www.example.org/public/test.pdf'
-              expect(last_response.headers["Content-Disposition"]).to eq("inline")
+              expect(last_response.headers["content-disposition"]).to eq("inline")
             end
           end
 
@@ -372,7 +372,7 @@ describe PDFKit::Middleware do
             specify do
               mock_app({}, { :disposition => 'inline'  })
               get 'http://www.example.org/public/test.pdf'
-              expect(last_response.headers["Content-Disposition"]).to eq("inline")
+              expect(last_response.headers["content-disposition"]).to eq("inline")
             end
           end
         end
@@ -382,7 +382,7 @@ describe PDFKit::Middleware do
             specify do
               mock_app({}, { :disposition => 'attachment'  })
               get 'http://www.example.org/public/test.pdf'
-              expect(last_response.headers["Content-Disposition"]).to eq("attachment")
+              expect(last_response.headers["content-disposition"]).to eq("attachment")
             end
           end
 
@@ -390,7 +390,7 @@ describe PDFKit::Middleware do
             specify do
               mock_app({}, { :disposition => 'attachment; filename=report.pdf'  })
               get 'http://www.example.org/public/test.pdf'
-              expect(last_response.headers["Content-Disposition"]).to eq("attachment; filename=report.pdf")
+              expect(last_response.headers["content-disposition"]).to eq("attachment; filename=report.pdf")
             end
           end
         end
@@ -422,6 +422,29 @@ describe PDFKit::Middleware do
       end
     end
 
+    describe "content type header" do
+      before { mock_app }
+
+      context "lower case" do
+        specify "header gets correctly updated" do
+          get 'http://www.example.org/public/test.pdf'
+          expect(last_response.headers["content-type"]).to eq("application/pdf")
+        end
+      end
+
+      context "mixed case" do
+        let(:headers) do
+          {'Content-Type' => "text/html"}
+        end
+
+        specify "header gets correctly updated" do
+          pending("this test only applies to rack 2.x and is rejected by rack 3.x") if Rack.release >= "3.0.0"
+          get 'http://www.example.org/public/test.pdf'
+          expect(last_response.headers["Content-Type"]).to eq("application/pdf")
+        end
+      end
+    end
+
     describe "remove .pdf from PATH_INFO and REQUEST_URI" do
       before { mock_app }
 
@@ -446,7 +469,7 @@ describe PDFKit::Middleware do
           main_app = lambda { |env|
             @env = env
             @env['SCRIPT_NAME'] = '/example.org'
-            headers = {'Content-Type' => "text/html"}
+            headers = {'content-type' => "text/html"}
             [200, headers, @body || ['Hello world!']]
           }
 

data/spec/source_spec.rb

@@ -80,6 +80,11 @@ describe PDFKit::Source do
       expect(source.to_input_for_command).to eq "\"https://www.google.com/search?q='cat%3Cdev/zero%3E/dev/null'\""
     end
 
+    it "URI escapes source URI only escape part of it" do
+      source = PDFKit::Source.new("https://www.google.com/search?q='%20 sleep 5'")
+      expect(source.to_input_for_command).to eq "\"https://www.google.com/search?q='%2520%20sleep%205'\""
+    end
+
     it "does not URI escape previously escaped source URLs" do
       source = PDFKit::Source.new("https://www.google.com/search?q='cat%3Cdev/zero%3E/dev/null'")
       expect(source.to_input_for_command).to eq "\"https://www.google.com/search?q='cat%3Cdev/zero%3E/dev/null'\""

metadata

@@ -1,15 +1,15 @@
 --- !ruby/object:Gem::Specification
 name: pdfkit
 version: !ruby/object:Gem::Version
-  version: 0.8.6
+  version: 0.8.7.1
 platform: ruby
 authors:
 - Jared Pace
 - Relevance
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2022-04-11 00:00:00.000000000 Z
+date: 2022-10-17 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: activesupport
@@ -141,7 +141,7 @@ homepage: https://github.com/pdfkit/pdfkit
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -158,7 +158,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
 requirements:
 - wkhtmltopdf
 rubygems_version: 3.0.3.1
-signing_key: 
+signing_key:
 specification_version: 4
 summary: HTML+CSS -> PDF
 test_files: