From c9e0f0b3e42e51c5a9b3fe57ac1ffc005d525912 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Fr=C3=A9d=C3=A9ric=20Guillot?= <f@miniflux.net>
Date: Fri, 4 Mar 2022 14:18:43 -0800
Subject: [PATCH] Do not fallback to InnerXML if XHTML title is empty

---
 reader/atom/atom_10.go      |  9 +++----
 reader/atom/atom_10_test.go | 51 ++++++++++++++++++++-----------------
 2 files changed, 31 insertions(+), 29 deletions(-)

diff --git a/reader/atom/atom_10.go b/reader/atom/atom_10.go
index 71e7c697..4b45603b 100644
--- a/reader/atom/atom_10.go
+++ b/reader/atom/atom_10.go
@@ -227,6 +227,9 @@ type atom10Text struct {
 	XHTMLRootElement atomXHTMLRootElement `xml:"http://www.w3.org/1999/xhtml div"`
 }
 
+// Text: https://datatracker.ietf.org/doc/html/rfc4287#section-3.1.1.1
+// HTML: https://datatracker.ietf.org/doc/html/rfc4287#section-3.1.1.2
+// XHTML: https://datatracker.ietf.org/doc/html/rfc4287#section-3.1.1.3
 func (a *atom10Text) String() string {
 	var content string
 	switch {
@@ -237,11 +240,7 @@ func (a *atom10Text) String() string {
 			content = a.InnerXML
 		}
 	case a.Type == "xhtml":
-		if a.XHTMLRootElement.InnerXML != "" {
-			content = a.XHTMLRootElement.InnerXML
-		} else {
-			content = a.InnerXML
-		}
+		content = a.XHTMLRootElement.InnerXML
 	default:
 		content = a.CharData
 	}
diff --git a/reader/atom/atom_10_test.go b/reader/atom/atom_10_test.go
index 6aec8dbf..51381765 100644
--- a/reader/atom/atom_10_test.go
+++ b/reader/atom/atom_10_test.go
@@ -339,14 +339,6 @@ func TestParseEntryWithXHTMLTitle(t *testing.T) {
 	  <title>Example Feed</title>
 	  <link href="http://example.org/"/>
 
-	  <entry>
-		<title type="xhtml"><code>Test</code> Test</title>
-		<link href="http://example.org/a"/>
-		<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
-		<updated>2003-12-13T18:30:02Z</updated>
-		<summary>Some text.</summary>
-	  </entry>
-
 	  <entry>
 		<title type="xhtml">
 			<div xmlns="http://www.w3.org/1999/xhtml">
@@ -366,11 +358,34 @@ func TestParseEntryWithXHTMLTitle(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	if feed.Entries[0].Title != `<code>Test</code> Test` {
-		t.Errorf("Incorrect entry title, got: %q", feed.Entries[0].Title)
+	if feed.Entries[0].Title != `This is <b>XHTML</b> content.` {
+		t.Errorf("Incorrect entry title, got: %q", feed.Entries[1].Title)
+	}
+}
+
+func TestParseEntryWithEmptyXHTMLTitle(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/"/>
+
+	  <entry>
+		<title type="xhtml">
+			<div xmlns="http://www.w3.org/1999/xhtml"/>
+		</title>
+		<link href="http://example.org/entry"/>
+		<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
+		<updated>2003-12-13T18:30:02Z</updated>
+	  </entry>
+
+	</feed>`
+
+	feed, err := Parse("https://example.org/", bytes.NewBufferString(data))
+	if err != nil {
+		t.Fatal(err)
 	}
 
-	if feed.Entries[1].Title != `This is <b>XHTML</b> content.` {
+	if feed.Entries[0].Title != `http://example.org/entry` {
 		t.Errorf("Incorrect entry title, got: %q", feed.Entries[1].Title)
 	}
 }
@@ -433,14 +448,6 @@ func TestParseEntryWithXHTMLSummary(t *testing.T) {
 	  <title>Example Feed</title>
 	  <link href="http://example.org/"/>
 
-	  <entry>
-		<title type="xhtml">Example</title>
-		<link href="http://example.org/2003/12/13/atom03"/>
-		<id>urn:uuid:1225c695-cfb8-4ebb-aaaa-80da344efa6a</id>
-		<updated>2003-12-13T18:30:02Z</updated>
-		<summary type="xhtml"><p>Some text.</p></summary>
-	  </entry>
-
 	  <entry>
 		<title type="xhtml">Example</title>
 		<link href="http://example.org/2003/12/13/atom03"/>
@@ -456,11 +463,7 @@ func TestParseEntryWithXHTMLSummary(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	if feed.Entries[0].Content != `<p>Some text.</p>` {
-		t.Errorf("Incorrect entry content, got: %s", feed.Entries[0].Content)
-	}
-
-	if feed.Entries[1].Content != `<p>Test: <code>std::unique_ptr&lt;S&gt;</code></p>` {
+	if feed.Entries[0].Content != `<p>Test: <code>std::unique_ptr&lt;S&gt;</code></p>` {
 		t.Errorf("Incorrect entry content, got: %s", feed.Entries[1].Content)
 	}
 }