feat(xslt): implement xsl:output cdata-section-elements

The text content of the named result elements is emitted in CDATA
sections rather than escaped: the result tree's text children of those
elements are converted to CDATA nodes before serialization, leaving
nested and other elements unaffected. Part of #82.

CHANGELOG.md

@@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- XSLT `xsl:output cdata-section-elements` (#82). The text content of the named result elements is emitted in `<![CDATA[…]]>` sections instead of escaped, leaving nested elements and other elements unaffected.
 - XSLT `xsl:output` `doctype-public`/`doctype-system` (#82). When either is set, a `<!DOCTYPE>` for the result's root element (PUBLIC when both are given, SYSTEM otherwise) is emitted before the serialized output, for XML and HTML methods.
 - XSLT `key()` over a node-set second argument (#82). `key(name, node-set)` (including `key('k', .)`) now unions the matches for every node's string value and de-duplicates, rather than using only the first node's string value.
 - XSLT `method="html"` output (#82). An `xsl:output method="html"` result is now serialized by the HTML rules (void elements like `<br>` emitted without a self-closing slash, raw-text elements like `<script>`/`<style>` left unescaped) instead of as XML.

Sources/XSLT/XSLTModel.swift

@@ -102,6 +102,8 @@ public extension PureXML.XSLT {
         /// a `<!DOCTYPE>` for the result's root element is emitted before it.
         public var doctypePublic: String?
         public var doctypeSystem: String?
+        /// Element names whose text content is emitted in `<![CDATA[…]]>` sections.
+        public var cdataSectionElements: Set<String>
 
         public init(
             method: String? = nil,
@@ -112,6 +114,7 @@ public extension PureXML.XSLT {
             standalone: Bool? = nil,
             doctypePublic: String? = nil,
             doctypeSystem: String? = nil,
+            cdataSectionElements: Set<String> = [],
         ) {
             self.method = method
             self.indent = indent
@@ -121,6 +124,7 @@ public extension PureXML.XSLT {
             self.standalone = standalone
             self.doctypePublic = doctypePublic
             self.doctypeSystem = doctypeSystem
+            self.cdataSectionElements = cdataSectionElements
         }
 
         /// This output's settings with `other`'s non-nil settings layered over them.
@@ -134,6 +138,7 @@ public extension PureXML.XSLT {
                 standalone: other.standalone ?? standalone,
                 doctypePublic: other.doctypePublic ?? doctypePublic,
                 doctypeSystem: other.doctypeSystem ?? doctypeSystem,
+                cdataSectionElements: cdataSectionElements.union(other.cdataSectionElements),
             )
         }
     }

Sources/XSLT/XSLTParser.swift

@@ -167,6 +167,7 @@ extension PureXML.XSLT {
                 standalone: XSLTNode.attribute(node, "standalone").map { $0 == "yes" },
                 doctypePublic: XSLTNode.attribute(node, "doctype-public"),
                 doctypeSystem: XSLTNode.attribute(node, "doctype-system"),
+                cdataSectionElements: Set((XSLTNode.attribute(node, "cdata-section-elements") ?? "").split(whereSeparator: \.isWhitespace).map(String.init)),
             )
         }
 

Sources/XSLT/XSLTTransform.swift

@@ -17,12 +17,35 @@ public extension PureXML.XSLT {
         let result = transformer.run()
         if let message = transformer.terminationMessage { throw XSLTError.terminated(message) }
         if sheet.output.method == "text" { return textValue(of: result) }
-        let body = sheet.output.method == "html"
-            ? PureXML.HTML.serialize(result)
-            : PureXML.serialize(result, options: options.applying(sheet.output))
+        let body: String
+        if sheet.output.method == "html" {
+            body = PureXML.HTML.serialize(result)
+        } else {
+            let prepared = withCDATASections(result, sheet.output.cdataSectionElements)
+            body = PureXML.serialize(prepared, options: options.applying(sheet.output))
+        }
         return doctype(for: result, sheet.output) + body
     }
 
+    /// Returns `node` with the text children of any element named in `names`
+    /// replaced by CDATA nodes, so the serializer emits them as CDATA sections.
+    private static func withCDATASections(_ node: PureXML.Model.Node, _ names: Set<String>) -> PureXML.Model.Node {
+        guard !names.isEmpty else { return node }
+        switch node {
+        case let .document(children):
+            return .document(children.map { withCDATASections($0, names) })
+        case let .element(element):
+            let wrap = names.contains(element.name.localName) || names.contains(element.name.description)
+            let children = element.children.map { child -> PureXML.Model.Node in
+                if wrap, case let .text(value) = child { return .cdata(value) }
+                return withCDATASections(child, names)
+            }
+            return .element(.init(name: element.name, attributes: element.attributes, children: children))
+        default:
+            return node
+        }
+    }
+
     /// The `<!DOCTYPE …>` prologue for the result's root element when the output
     /// declares `doctype-system` (optionally with `doctype-public`), else empty.
     private static func doctype(for result: PureXML.Model.Node, _ output: Output) -> String {

Tests/XSLTCDATASectionTests.swift

@@ -0,0 +1,44 @@
+@testable import PureXML
+import Testing
+
+@Suite("XSLT xsl:output cdata-section-elements")
+struct XSLTCDATASectionTests {
+    private let xsl = "xmlns:xsl=\"http://www.w3.org/1999/XSL/Transform\""
+
+    private func transform(_ stylesheet: String, _ source: String) throws -> String {
+        try PureXML.XSLT.transform(stylesheet: stylesheet, source: source)
+    }
+
+    private func style(_ cdataElements: String, _ body: String) -> String {
+        """
+        <xsl:stylesheet version="1.0" \(xsl)>
+          <xsl:output method="xml" omit-xml-declaration="yes" cdata-section-elements="\(cdataElements)"/>
+          <xsl:template match="/">\(body)</xsl:template>
+        </xsl:stylesheet>
+        """
+    }
+
+    @Test("A named element's text is emitted as a CDATA section")
+    func test_wrapped() throws {
+        let out = try transform(style("script", "<script>if (a &lt; b) go()</script>"), "<x/>")
+        #expect(out == "<script><![CDATA[if (a < b) go()]]></script>")
+    }
+
+    @Test("An element not named keeps escaped text")
+    func test_notNamed() throws {
+        let out = try transform(style("script", "<data>a &lt; b</data>"), "<x/>")
+        #expect(out == "<data>a &lt; b</data>")
+    }
+
+    @Test("Only the named element's own text is wrapped, not nested elements")
+    func test_nestedUnaffected() throws {
+        let out = try transform(style("outer", "<outer>x<inner>y &lt; z</inner></outer>"), "<x/>")
+        #expect(out == "<outer><![CDATA[x]]><inner>y &lt; z</inner></outer>")
+    }
+
+    @Test("Multiple element names can be listed")
+    func test_multiple() throws {
+        let out = try transform(style("a b", "<root><a>1 &amp; 2</a><b>3 &amp; 4</b></root>"), "<x/>")
+        #expect(out == "<root><a><![CDATA[1 & 2]]></a><b><![CDATA[3 & 4]]></b></root>")
+    }
+}