1
0
Fork 0
mirror of https://github.com/miniflux/v2.git synced 2025-06-27 16:36:00 +00:00

Filter valid XML characters for UTF-8 XML documents before decoding

This change should reduce "illegal character code" XML errors.
This commit is contained in:
Jebbs 2019-12-20 10:31:52 +08:00 committed by Frédéric Guillot
parent a4ebb33cd5
commit a155ab6deb
2 changed files with 96 additions and 4 deletions

View file

@ -11,19 +11,74 @@ import (
"testing"
)
func TestIllegalCharacters(t *testing.T) {
func TestUTF8WithIllegalCharacters(t *testing.T) {
type myxml struct {
XMLName xml.Name `xml:"rss"`
Version string `xml:"version,attr"`
Title string `xml:"title"`
}
data := fmt.Sprintf(`<?xml version="1.0" encoding="windows-1251"?><rss version="2.0"><title>%s</title></rss>`, "\x10")
expected := "Title & 中文标题"
data := fmt.Sprintf(`<?xml version="1.0" encoding="UTF-8"?><rss version="2.0"><title>Title & 中文%s标题</title></rss>`, "\x10")
reader := strings.NewReader(data)
var x myxml
decoder := NewDecoder(strings.NewReader(data))
decoder := NewDecoder(reader)
err := decoder.Decode(&x)
if err != nil {
t.Error(err)
return
}
if x.Title != expected {
t.Errorf("Incorrect entry title, expected: %s, got: %s", expected, x.Title)
}
}
func TestWindows251WithIllegalCharacters(t *testing.T) {
type myxml struct {
XMLName xml.Name `xml:"rss"`
Version string `xml:"version,attr"`
Title string `xml:"title"`
}
expected := "Title & 中文标题"
data := fmt.Sprintf(`<?xml version="1.0" encoding="windows-1251"?><rss version="2.0"><title>Title & 中文%s标题</title></rss>`, "\x10")
reader := strings.NewReader(data)
var x myxml
decoder := NewDecoder(reader)
err := decoder.Decode(&x)
if err != nil {
t.Error(err)
return
}
if x.Title != expected {
t.Errorf("Incorrect entry title, expected: %s, got: %s", expected, x.Title)
}
}
func TestIllegalEncodingField(t *testing.T) {
type myxml struct {
XMLName xml.Name `xml:"rss"`
Version string `xml:"version,attr"`
Title string `xml:"title"`
}
expected := "Title & 中文标题"
data := fmt.Sprintf(`<?xml version="1.0" encoding="invalid"?><rss version="2.0"><title>Title & 中文%s标题</title></rss>`, "\x10")
reader := strings.NewReader(data)
var x myxml
decoder := NewDecoder(reader)
err := decoder.Decode(&x)
if err != nil {
t.Error(err)
return
}
if x.Title != expected {
t.Errorf("Incorrect entry title, expected: %s, got: %s", expected, x.Title)
}
}