From 40c5973d5ac74f4d6f0a2fd9ee3d7b58ea9cbcfe Mon Sep 17 00:00:00 2001
From: Mihaela Mihaljevic <mihaelamj@me.com>
Date: Tue, 9 Jun 2026 05:29:14 +0200
Subject: [PATCH] feat(html): SVG element-name case adjustment in foreign
 content (#83)

---
 CHANGELOG.md                           |  1 +
 README.md                              |  2 +-
 Sources/HTML/HTMLDocumentBuilder.swift |  7 +++++--
 Sources/HTML/HTMLForeignNames.swift    | 23 +++++++++++++++++++++++
 Tests/HTMLForeignContentTests.swift    | 16 ++++++++++++++++
 5 files changed, 46 insertions(+), 3 deletions(-)
 create mode 100644 Sources/HTML/HTMLForeignNames.swift

diff --git a/CHANGELOG.md b/CHANGELOG.md
index a7f90dd..8ac2c89 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -13,6 +13,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Added
 
+- HTML5 SVG element-name case adjustment (#83, stage 3): an SVG element written in mixed case (which the tokenizer lowercases) is restored to its canonical camel case in the tree, so `<foreignObject>`, `<linearGradient>`, `<clipPath>`, and the rest carry their correct SVG names. Applies only in the SVG namespace; same-named HTML elements keep their lowercased name.
 - HTML5 foreign content (#83, stage 2): an `<svg>` or `<math>` element and all of its descendants now carry the SVG (`http://www.w3.org/2000/svg`) or MathML (`http://www.w3.org/1998/Math/MathML`) namespace on their `QualifiedName`, so foreign elements are distinguishable from same-named HTML; ordinary HTML content (including content after a closed `<svg>`) stays in no namespace. (SVG/MathML element- and attribute-name case adjustment, and HTML integration points, are a later refinement.)
 - HTML5 table tree construction (#83, stage 1): a `<table>` written without its section and row wrappers now nests correctly. A `<tr>` directly inside a `<table>` gets an implied `<tbody>`, a `<td>`/`<th>` gets an implied `<tr>` (and section), consecutive rows share one implied `<tbody>`, and an explicit `<thead>`/`<tbody>`/`<tfoot>` is not duplicated, all inside an open table only.
 - HTML tokenizer correctness (#84, partial): numeric character references are now range/surrogate-validated (zero, surrogates, and values above U+10FFFF yield U+FFFD) with the Windows-1252 C1 fixup table (`&#x80;` -> euro, etc.); named references are decoded by longest match with or without a trailing semicolon; a literal NUL byte becomes U+FFFD; RCDATA elements (`title`, `textarea`) decode character references while raw-text elements (`script`, `style`) take their content verbatim; and a single leading newline after `<textarea>` is stripped. (The full ~2,000-entry named-entity table remains deferred to vendoring from the authoritative WHATWG data, the same policy as the legacy encodings.)
diff --git a/README.md b/README.md
index c56f4e3..4ca1bde 100644
--- a/README.md
+++ b/README.md
@@ -89,7 +89,7 @@ flowchart TB
 
 PureXML is a working, dependency-free XML library today: parse, emit, validate,
 query, and stream documents on macOS, Linux, Windows, and WASM. The test suite
-currently runs **725 tests in 114 suites** (`swift test`).
+currently runs **727 tests in 114 suites** (`swift test`).
 
 ### Shipped (libxml2-aligned surface)
 
diff --git a/Sources/HTML/HTMLDocumentBuilder.swift b/Sources/HTML/HTMLDocumentBuilder.swift
index 2be066b..0c29f34 100644
--- a/Sources/HTML/HTMLDocumentBuilder.swift
+++ b/Sources/HTML/HTMLDocumentBuilder.swift
@@ -201,9 +201,12 @@ private final class HTMLDocument {
     }
 
     /// A qualified name carrying its foreign-content namespace URI, so an SVG or
-    /// MathML element is distinguishable from same-named HTML.
+    /// MathML element is distinguishable from same-named HTML. SVG element names
+    /// are restored to their canonical camel case (`foreignObject`, not the
+    /// tokenizer's lowercased `foreignobject`).
     private func qualifiedName(_ name: String, _ namespace: String?) -> PureXML.Model.QualifiedName {
-        PureXML.Model.QualifiedName(prefix: nil, localName: name, namespaceURI: namespace)
+        let local = namespace == ForeignNamespace.svg ? (PureXML.HTML.ForeignNames.svgElements[name] ?? name) : name
+        return PureXML.Model.QualifiedName(prefix: nil, localName: local, namespaceURI: namespace)
     }
 
     /// HTML table tree construction: a `<tr>` inside a bare `<table>` gets an
diff --git a/Sources/HTML/HTMLForeignNames.swift b/Sources/HTML/HTMLForeignNames.swift
new file mode 100644
index 0000000..a1ae9f6
--- /dev/null
+++ b/Sources/HTML/HTMLForeignNames.swift
@@ -0,0 +1,23 @@
+extension PureXML.HTML {
+    /// The HTML5 "adjust SVG element names" table: the SVG elements whose correct
+    /// names are camel-cased, keyed by the lowercased form the tokenizer produces.
+    /// Applied when materializing an element in the SVG namespace so a parsed
+    /// `<foreignObject>` or `<lineargradient>` carries its canonical SVG name.
+    enum ForeignNames {
+        static let svgElements: [String: String] = [
+            "altglyph": "altGlyph", "altglyphdef": "altGlyphDef", "altglyphitem": "altGlyphItem",
+            "animatecolor": "animateColor", "animatemotion": "animateMotion", "animatetransform": "animateTransform",
+            "clippath": "clipPath", "feblend": "feBlend", "fecolormatrix": "feColorMatrix",
+            "fecomponenttransfer": "feComponentTransfer", "fecomposite": "feComposite", "feconvolvematrix": "feConvolveMatrix",
+            "fediffuselighting": "feDiffuseLighting", "fedisplacementmap": "feDisplacementMap", "fedistantlight": "feDistantLight",
+            "fedropshadow": "feDropShadow", "feflood": "feFlood", "fefunca": "feFuncA",
+            "fefuncb": "feFuncB", "fefuncg": "feFuncG", "fefuncr": "feFuncR",
+            "fegaussianblur": "feGaussianBlur", "feimage": "feImage", "femerge": "feMerge",
+            "femergenode": "feMergeNode", "femorphology": "feMorphology", "feoffset": "feOffset",
+            "fepointlight": "fePointLight", "fespecularlighting": "feSpecularLighting", "fespotlight": "feSpotLight",
+            "fetile": "feTile", "feturbulence": "feTurbulence", "foreignobject": "foreignObject",
+            "glyphref": "glyphRef", "lineargradient": "linearGradient", "radialgradient": "radialGradient",
+            "textpath": "textPath",
+        ]
+    }
+}
diff --git a/Tests/HTMLForeignContentTests.swift b/Tests/HTMLForeignContentTests.swift
index d999109..d07d50d 100644
--- a/Tests/HTMLForeignContentTests.swift
+++ b/Tests/HTMLForeignContentTests.swift
@@ -49,4 +49,20 @@ struct HTMLForeignContentTests {
         #expect(find("rect", in: html)?.name.namespaceURI == svg)
         #expect(find("p", in: html)?.name.namespaceURI == nil)
     }
+
+    @Test("SVG element names are restored to their canonical camel case")
+    func test_svgNameCaseAdjustment() {
+        let html = "<svg><foreignObject></foreignObject><lineargradient></lineargradient></svg>"
+        #expect(find("foreignObject", in: html)?.name.namespaceURI == svg)
+        #expect(find("linearGradient", in: html)?.name.namespaceURI == svg)
+        // The lowercased forms the tokenizer produced are not what landed in the tree.
+        #expect(find("foreignobject", in: html) == nil)
+    }
+
+    @Test("A same-named HTML element keeps its lowercased name")
+    func test_htmlNameNotAdjusted() {
+        // Outside SVG, no case adjustment applies.
+        #expect(find("clippath", in: "<clippath></clippath>")?.name.namespaceURI == nil)
+        #expect(find("clipPath", in: "<clippath></clippath>") == nil)
+    }
 }