Problematic UTF+bom files (#6322)

Merge pull request 6322

lib/jekyll/site.rb

@@ -444,6 +444,7 @@ module Jekyll
     def configure_file_read_opts
       self.file_read_opts = {}
       self.file_read_opts[:encoding] = config["encoding"] if config["encoding"]
+      self.file_read_opts = Jekyll::Utils.merged_file_read_opts(self, {})
     end
 
     private

lib/jekyll/utils.rb

@@ -301,6 +301,9 @@ module Jekyll
     # and a given param
     def merged_file_read_opts(site, opts)
       merged = (site ? site.file_read_opts : {}).merge(opts)
+      if merged[:encoding] && !merged[:encoding].start_with?("bom|")
+        merged[:encoding] = "bom|#{merged[:encoding]}"
+      end
       if merged["encoding"] && !merged["encoding"].start_with?("bom|")
         merged["encoding"] = "bom|#{merged["encoding"]}"
       end

test/source/_encodings/UTF8CRLFandBOM.md

@@ -0,0 +1,11 @@
+---
+layout: post
+title:  "UTF8CRLFandBOM"
+date:   2017-04-05 16:16:01 -0800
+categories: bom
+---
+This file was created with CR/LFs, and encoded as UTF8 with a BOM
+
+You’ll find this post in your `_posts` directory. Go ahead and edit it and re-build the site to see your changes. You can rebuild the site in many different ways, but the most common way is to run `bundle exec jekyll serve`, which launches a web server and auto-regenerates your site when a file is updated.
+
+To add new posts, simply add a file in the `_posts` directory that follows the convention `YYYY-MM-DD-name-of-post.ext` and includes the necessary front matter. Take a look at the source for this post to get an idea about how it works.

test/test_document.rb

@@ -7,6 +7,15 @@ class TestDocument < JekyllUnitTest
     assert_equal(one[key], other[key])
   end
 
+  def setup_encoded_document(filename)
+    site = fixture_site("collections" => ["encodings"])
+    site.process
+    Document.new(site.in_source_dir(File.join("_encodings", filename)), {
+      :site       => site,
+      :collection => site.collections["encodings"],
+    }).tap(&:read)
+  end
+
   context "a document in a collection" do
     setup do
       @site = fixture_site({
@@ -529,4 +538,24 @@ class TestDocument < JekyllUnitTest
       assert_equal true, File.file?(@dest_file)
     end
   end
+
+  context "a document with UTF-8 CLRF" do
+    setup do
+      @document = setup_encoded_document "UTF8CRLFandBOM.md"
+    end
+
+    should "not throw an error" do
+      Jekyll::Renderer.new(@document.site, @document).render_document
+    end
+  end
+
+  context "a document with UTF-16LE CLRF" do
+    setup do
+      @document = setup_encoded_document "Unicode16LECRLFandBOM.md"
+    end
+
+    should "not throw an error" do
+      Jekyll::Renderer.new(@document.site, @document).render_document
+    end
+  end
 end

test/test_utils.rb

@@ -387,16 +387,21 @@ class TestUtils < JekyllUnitTest
     should "ignore encoding if it's not there" do
       opts = Utils.merged_file_read_opts(nil, {})
       assert_nil opts["encoding"]
+      assert_nil opts[:encoding]
     end
 
     should "add bom to encoding" do
-      opts = Utils.merged_file_read_opts(nil, { "encoding" => "utf-8" })
-      assert_equal "bom|utf-8", opts["encoding"]
+      opts = { "encoding" => "utf-8", :encoding => "utf-8" }
+      merged = Utils.merged_file_read_opts(nil, opts)
+      assert_equal "bom|utf-8", merged["encoding"]
+      assert_equal "bom|utf-8", merged[:encoding]
     end
 
     should "preserve bom in encoding" do
-      opts = Utils.merged_file_read_opts(nil, { "encoding" => "bom|utf-8" })
-      assert_equal "bom|utf-8", opts["encoding"]
+      opts = { "encoding" => "bom|another", :encoding => "bom|another" }
+      merged = Utils.merged_file_read_opts(nil, opts)
+      assert_equal "bom|another", merged["encoding"]
+      assert_equal "bom|another", merged[:encoding]
     end
   end
 end