From c355daa00eaee2b4718f64874581b5355a59d64d Mon Sep 17 00:00:00 2001
From: Mihaela Mihaljevic <mihaelamj@me.com>
Date: Wed, 24 Jun 2026 03:04:45 +0200
Subject: [PATCH] test(xslt): decode non-UTF-8 conformance sources via the
 library's encoding detection (#261)

The Xalan harness read source and stylesheet files as UTF-8, so a UTF-16
source (output80) or other non-UTF-8 input (attribvaltemplate08) was refused
as unreadable before the transform ran. Read them through PureXML's own
ByteDecoder (BOM or XML-declaration detection, UTF-8 fallback), as the harness
already does for gold files. The library round-trips them correctly, so both
cases now pass.

Closes Apache Xalan conformance cases output80 and attribvaltemplate08.
---
 CHANGELOG.md                      |  2 ++
 Tests/Fixtures/xalan-baseline.txt |  2 --
 Tests/XalanConfSuiteTests.swift   | 19 ++++++++++++++-----
 3 files changed, 16 insertions(+), 7 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 970a267..1f571d6 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -52,6 +52,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Fixed
 
+- The XSLT conformance harness now decodes source and stylesheet files through the library's own encoding detection (a BOM or the XML declaration) rather than assuming UTF-8, so a non-UTF-8 corpus input is fed to the transform instead of refused. This confirms the library round-trips a UTF-16 source correctly and closes Apache Xalan conformance cases `output80` (UTF-16) and `attribvaltemplate08`, which were unreadable by the harness, not library failures.
+
 - The `html` output method now serializes an element whose expanded-name has a non-null namespace URI as XML rather than HTML (XSLT 1.0 16.2). When the result's document element is namespaced, the tree is serialized through the XML path (empty elements self-close, the namespace is declared once and inherited) while the html method still omits the XML declaration; previously such a tree was emitted as HTML, leaving empty namespaced elements unclosed and repeating the `xmlns` declaration on every element, which is not well-formed XML. A null-namespace tree is unchanged. The rule is applied at document-element granularity rather than per element, so a tree mixing null- and non-null-namespace elements follows its document element's path (the realistic result is all-null or all-namespaced). (Apache Xalan `output63` exercises this rule but remains baselined: its gold differs further only in attribute order, which is not normative.)
 
 - The `html` output method now names the document type declaration `HTML` rather than the document element name (XSLT 1.0 16.2: "The name following the `<!DOCTYPE` should be HTML or html"). With `method="html"` and a `doctype-public` or `doctype-system`, the emitted declaration is `<!DOCTYPE HTML PUBLIC "...">` regardless of the result's root element; the `xml` method still uses the document element name (16.1). Closes Apache Xalan conformance cases `output40`, `output48`, and `output60`.
diff --git a/Tests/Fixtures/xalan-baseline.txt b/Tests/Fixtures/xalan-baseline.txt
index 478ce94..ad4f890 100644
--- a/Tests/Fixtures/xalan-baseline.txt
+++ b/Tests/Fixtures/xalan-baseline.txt
@@ -2,7 +2,6 @@
 # one category/name per line, exact in both directions: a fixed case
 # must leave this list and a regression shows up as a new failure.
 attribset/attribset44
-attribvaltemplate/attribvaltemplate08
 axes/axes116
 conflictres/conflictres29
 conflictres/conflictres30
@@ -34,7 +33,6 @@ output/output70
 output/output72
 output/output73
 output/output75
-output/output80
 output/output86
 position/position106
 processorinfo/processorinfo03
diff --git a/Tests/XalanConfSuiteTests.swift b/Tests/XalanConfSuiteTests.swift
index 5b90fdf..5127d8f 100644
--- a/Tests/XalanConfSuiteTests.swift
+++ b/Tests/XalanConfSuiteTests.swift
@@ -74,10 +74,21 @@ struct XalanConfSuiteTests {
         #expect(fixed.isEmpty, "\(fixed.count) baselined cases now pass (remove from xalan-baseline.txt): \(fixed.prefix(40))")
     }
 
+    /// Reads a file and decodes it through PureXML's own encoding detection (a
+    /// BOM or the XML declaration), falling back to UTF-8, so a non-UTF-8 source
+    /// is decoded rather than refused. nil when the file is missing.
+    private static func decodeFile(_ path: String) -> String? {
+        guard let data = FileManager.default.contents(atPath: path) else { return nil }
+        return (try? PureXML.Parsing.ByteDecoder.decode([UInt8](data))) ?? String(data: data, encoding: .utf8)
+    }
+
     private func runCase(category: String, name: String, root: String, goldPath: String) -> String? {
         let directory = root + "/conf/" + category
-        guard let stylesheet = try? String(contentsOfFile: directory + "/" + name + ".xsl", encoding: .utf8),
-              let source = try? String(contentsOfFile: directory + "/" + name + ".xml", encoding: .utf8)
+        // Decode inputs the way PureXML decodes any document, by detecting the
+        // encoding (a BOM or the XML declaration) rather than assuming UTF-8, so
+        // a UTF-16 or other non-UTF-8 source is fed to the transform, not refused.
+        guard let stylesheet = Self.decodeFile(directory + "/" + name + ".xsl"),
+              let source = Self.decodeFile(directory + "/" + name + ".xml")
         else {
             return "unreadable inputs"
         }
@@ -86,9 +97,7 @@ struct XalanConfSuiteTests {
         else {
             return "unreadable gold"
         }
-        let loader: (String) -> String? = { uri in
-            (try? String(contentsOfFile: directory + "/" + uri, encoding: .utf8))
-        }
+        let loader: (String) -> String? = { uri in Self.decodeFile(directory + "/" + uri) }
         let actual: String
         do {
             actual = try PureXML.XSLT.transform(