From 36d773223481dd42d31499b3ea73e6999ff9f58e Mon Sep 17 00:00:00 2001
From: Frédéric Guillot <fred@miniflux.net>
Date: Wed, 18 Sep 2019 22:27:25 -0700
Subject: Disable strict XML parsing

This change should improve parsing of broken XML feeds.

See https://golang.org/pkg/encoding/xml/#Decoder
---
 reader/atom/parser.go      |  1 +
 reader/atom/parser_test.go | 19 +++++++++++++++++++
 2 files changed, 20 insertions(+)

(limited to 'reader/atom')

diff --git a/reader/atom/parser.go b/reader/atom/parser.go
index 85be4b5..4749c1a 100644
--- a/reader/atom/parser.go
+++ b/reader/atom/parser.go
@@ -18,6 +18,7 @@ func Parse(data io.Reader) (*model.Feed, *errors.LocalizedError) {
 	atomFeed := new(atomFeed)
 	decoder := xml.NewDecoder(data)
 	decoder.Entity = xml.HTMLEntity
+	decoder.Strict = false
 	decoder.CharsetReader = encoding.CharsetReader
 
 	err := decoder.Decode(atomFeed)
diff --git a/reader/atom/parser_test.go b/reader/atom/parser_test.go
index dc42575..746c767 100644
--- a/reader/atom/parser_test.go
+++ b/reader/atom/parser_test.go
@@ -577,3 +577,22 @@ func TestParseWithHTMLEntity(t *testing.T) {
 		t.Errorf(`Incorrect title, got: %q`, feed.Title)
 	}
 }
+
+func TestParseWithInvalidCharacterEntity(t *testing.T) {
+	data := `
+		<?xml version="1.0" encoding="utf-8"?>
+		<feed xmlns="http://www.w3.org/2005/Atom">
+			<title>Example Feed</title>
+			<link href="http://example.org/a&b"/>
+		</feed>
+	`
+
+	feed, err := Parse(bytes.NewBufferString(data))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if feed.SiteURL != "http://example.org/a&b" {
+		t.Errorf(`Incorrect URL, got: %q`, feed.SiteURL)
+	}
+}
-- 
cgit v1.2.3