encoding/xml: case-insensitive encoding recognition
From the XML spec: "XML processors should match character encoding
names in a case-insensitive way"
Fixes #12417.
Change-Id: I678c50152a49c14364be62b3f21ab9b9b009b24b
Reviewed-on: https://go-review.googlesource.com/14084
Reviewed-by: Russ Cox <rsc@golang.org>
diff --git a/src/encoding/xml/xml.go b/src/encoding/xml/xml.go
index bdd607c..70ff877 100644
--- a/src/encoding/xml/xml.go
+++ b/src/encoding/xml/xml.go
@@ -583,7 +583,7 @@
return nil, d.err
}
enc := procInst("encoding", content)
- if enc != "" && enc != "utf-8" && enc != "UTF-8" {
+ if enc != "" && enc != "utf-8" && enc != "UTF-8" && !strings.EqualFold(enc, "utf-8") {
if d.CharsetReader == nil {
d.err = fmt.Errorf("xml: encoding %q declared but Decoder.CharsetReader is nil", enc)
return nil, d.err
diff --git a/src/encoding/xml/xml_test.go b/src/encoding/xml/xml_test.go
index 19465d7..5d5e4bf 100644
--- a/src/encoding/xml/xml_test.go
+++ b/src/encoding/xml/xml_test.go
@@ -771,3 +771,35 @@
}
}
}
+
+func TestIssue12417(t *testing.T) {
+ testCases := []struct {
+ s string
+ ok bool
+ }{
+ {`<?xml encoding="UtF-8" version="1.0"?><root/>`, true},
+ {`<?xml encoding="UTF-8" version="1.0"?><root/>`, true},
+ {`<?xml encoding="utf-8" version="1.0"?><root/>`, true},
+ {`<?xml encoding="uuu-9" version="1.0"?><root/>`, false},
+ }
+ for _, tc := range testCases {
+ d := NewDecoder(strings.NewReader(tc.s))
+ var err error
+ for {
+ _, err = d.Token()
+ if err != nil {
+ if err == io.EOF {
+ err = nil
+ }
+ break
+ }
+ }
+ if err != nil && tc.ok {
+ t.Errorf("%q: Encoding charset: expected no error, got %s", tc.s, err)
+ continue
+ }
+ if err == nil && !tc.ok {
+ t.Errorf("%q: Encoding charset: expected error, got nil", tc.s)
+ }
+ }
+}