LibTextCodec: Fix ISO-2022-JP encoder U+FFFD handling

Martin005 · Martin005 · commit b4322febe9b9 · 2026-05-29T11:38:24.000+02:00
The jis0208 index contains 0xFFFD placeholder entries for unmapped
pointers. The generator-produced inverse accessor would match these
when encoding U+FFFD itself, returning a bogus JIS pointer instead of
reporting the code point as unmappable.

Guard at the call site in the ISO-2022-JP encoder rather than modifying
the Python generator, to avoid changing inverse accessors for other
indexes (big5, euc_kr, gb18030, etc.) which don't exhibit this bug.

This fixes 4 WPT subtests in iso-2022-jp-encoder.html.
diff --git a/Libraries/LibTextCodec/Encoder.cpp b/Libraries/LibTextCodec/Encoder.cpp
@@ -272,7 +272,16 @@ ErrorOr<ISO2022JPEncoder::State> ISO2022JPEncoder::process_item(u32 item, State
     }
 
     // 10. Let pointer be the index pointer for code point in index jis0208.
-    auto pointer = code_point_jis0208_index(item);
+    //
+    // AD-HOC: The jis0208 index contains 0xFFFD placeholder entries for unmapped pointers.
+    // The generated inverse accessor code_point_jis0208_index() would match these
+    // and return a bogus pointer for U+FFFD itself. We guard here rather than in
+    // the Python generator to avoid changing inverse accessors for other indexes.
+    Optional<u32> pointer;
+    if (item == 0xFFFD)
+        pointer = {};
+    else
+        pointer = code_point_jis0208_index(item);
 
     // 11. If pointer is null, then:
     if (!pointer.has_value()) {
diff --git a/Tests/LibWeb/Text/expected/wpt-import/encoding/iso-2022-jp-encoder.txt b/Tests/LibWeb/Text/expected/wpt-import/encoding/iso-2022-jp-encoder.txt
@@ -0,0 +1,17 @@
+Harness status: OK
+
+Found 12 tests
+
+12 Pass
+Pass	iso-2022-jp encoder: very basic
+Pass	iso-2022-jp encoder: basics
+Pass	iso-2022-jp encoder: Katakana
+Pass	iso-2022-jp encoder: jis0208
+Pass	iso-2022-jp encoder: SO/SI ESC
+Pass	iso-2022-jp encoder: Roman SO/SI ESC
+Pass	iso-2022-jp encoder: Katakana SO/SI ESC
+Pass	iso-2022-jp encoder: jis0208 SO/SI ESC
+Pass	iso-2022-jp encoder: U+FFFD
+Pass	iso-2022-jp encoder: Roman U+FFFD
+Pass	iso-2022-jp encoder: Katakana U+FFFD
+Pass	iso-2022-jp encoder: jis0208 U+FFFD
diff --git a/Tests/LibWeb/Text/input/wpt-import/encoding/iso-2022-jp-encoder.html b/Tests/LibWeb/Text/input/wpt-import/encoding/iso-2022-jp-encoder.html
@@ -0,0 +1,27 @@
+<!doctype html>
+<meta charset=iso-2022-jp> <!-- if the server overrides this, it is stupid, as this is a testsuite -->
+<script src=../resources/testharness.js></script>
+<script src=../resources/testharnessreport.js></script>
+<div id=log></div>
+<script>
+ function encode(input, output, desc) {
+   test(function() {
+     var a = document.createElement("a") // <a> uses document encoding for URL's query
+     a.href = "https://example.com/?" + input
+     assert_equals(a.search.substr(1), output) // remove leading "?"
+   }, "iso-2022-jp encoder: " + desc)
+ }
+
+ encode("s", "s", "very basic");
+ encode("\u00A5\u203Es\\\uFF90\u4F69", "%1B(J\\~s%1B(B\\%1B$B%_PP%1B(B", "basics");
+ encode("\uFF61", "%1B$B!%23%1B(B", "Katakana");
+ encode("\u0393", "%1B$B&%23%1B(B", "jis0208");
+ encode("\x0E\x0F\x1Bx", "%26%2365533%3B%26%2365533%3B%26%2365533%3Bx", "SO/SI ESC");
+ encode("\u203E\x0E\x0F\x1Bx", "%1B(J~%26%2365533%3B%26%2365533%3B%26%2365533%3Bx%1B(B", "Roman SO/SI ESC");
+ encode("\uFF61\x0E\x0F\x1Bx", "%1B$B!%23%1B(B%26%2365533%3B%26%2365533%3B%26%2365533%3Bx", "Katakana SO/SI ESC");
+ encode("\u0393\x0E\x0F\x1Bx", "%1B$B&%23%1B(B%26%2365533%3B%26%2365533%3B%26%2365533%3Bx", "jis0208 SO/SI ESC");
+ encode("\uFFFD", "%26%2365533%3B", "U+FFFD");
+ encode("\u203E\uFFFD", "%1B(J~%26%2365533%3B%1B(B", "Roman U+FFFD");
+ encode("\uFF61\uFFFD", "%1B$B!%23%1B(B%26%2365533%3B", "Katakana U+FFFD");
+ encode("\u0393\uFFFD", "%1B$B&%23%1B(B%26%2365533%3B", "jis0208 U+FFFD");
+</script>
