feat!: XSLT docs are parsed with additional ParseOptions

Closes #1940

CHANGELOG.md

@@ -4,6 +4,18 @@ Nokogiri follows [Semantic Versioning](https://semver.org/), please see the [REA
 
 ---
 
+## next / unreleased
+
+### Changed
+
+* Introduce `Nokogiri::XML::ParseOptions::DEFAULT_XSLT` which adds the libxslt-preferred options of `NOENT | DTDLOAD | DTDATTR | NOCDATA` to `ParseOptions::DEFAULT_XML`.
+
+
+### Fixed
+
+* `Nokogiri.XSLT` parses the stylesheet using `ParseOptions::DEFAULT_XSLT`, which should make some edge-case XSL transformations match libxslt's default behavior. [[#1940](https://github.com/sparklemotion/nokogiri/issues/1940)]
+
+
 ## 1.11.3 / 2021-04-07
 
 ### Fixed

lib/nokogiri/xml/parse_options.rb

@@ -71,6 +71,8 @@ class ParseOptions
 
       # the default options used for parsing XML documents
       DEFAULT_XML  = RECOVER | NONET
+      # the default options used for parsing XSLT stylesheets
+      DEFAULT_XSLT = RECOVER | NONET | NOENT | DTDLOAD | DTDATTR | NOCDATA
       # the default options used for parsing HTML documents
       DEFAULT_HTML = RECOVER | NOERROR | NOWARNING | NONET
       # the default options used for parsing XML schemas

lib/nokogiri/xslt.rb

@@ -27,10 +27,11 @@ def parse(string, modules = {})
           XSLT.register(url, klass)
         end
 
+        doc = XML::Document.parse(string, nil, nil, XML::ParseOptions::DEFAULT_XSLT)
         if Nokogiri.jruby?
-          Stylesheet.parse_stylesheet_doc(XML.parse(string), string)
+          Stylesheet.parse_stylesheet_doc(doc, string)
         else
-          Stylesheet.parse_stylesheet_doc(XML.parse(string))
+          Stylesheet.parse_stylesheet_doc(doc)
         end
       end
 

test/test_xslt_transforms.rb

@@ -367,5 +367,38 @@ def test_non_html_xslt_transform
       end
       assert_match(/decimal/, exception.message)
     end
+
+    describe "DEFAULT_XSLT parse options" do
+      it "is the union of DEFAULT_XML and libxslt's XSLT_PARSE_OPTIONS" do
+        xslt_parse_options = Nokogiri::XML::ParseOptions.new.noent.dtdload.dtdattr.nocdata
+        expected = Nokogiri::XML::ParseOptions::DEFAULT_XML | xslt_parse_options.options
+        assert_equal(expected, Nokogiri::XML::ParseOptions::DEFAULT_XSLT)
+      end
+
+      it "parses docs the same as xsltproc" do
+        skip_unless_libxml2("JRuby implementation disallows this edge case XSLT")
+
+        # see https://github.com/sparklemotion/nokogiri/issues/1940
+        xml = "<t></t>"
+        xsl = <<~EOF
+          <?xml version="1.0"?>
+          <xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">
+          <xsl:output method="text" omit-xml-declaration="no" />
+            <xsl:template match="/">
+              <xsl:text disable-output-escaping="yes"><![CDATA[<>]]></xsl:text>
+            </xsl:template>
+          </xsl:stylesheet>
+        EOF
+
+        doc = Nokogiri::XML(xml)
+        stylesheet = Nokogiri::XSLT(xsl)
+
+        # TODO: ideally I'd like to be able to access the parse options in the final object
+        # assert_equal(Nokogiri::XML::ParseOptions::DEFAULT_XSLT, stylesheet.document.parse_options)
+
+        result = stylesheet.transform(doc)
+        assert_equal("<>", result.children.to_xml)
+      end
+    end
   end
 end