From 200b1c304b999191a29f36d4122e7aa05481125c Mon Sep 17 00:00:00 2001
From: Frédéric Guillot <fred@miniflux.net>
Date: Mon, 23 Dec 2019 14:39:54 -0800
Subject: Improve Dublin Core support for RDF feeds

---
 reader/rdf/dublincore.go  | 17 ++++++++++++++++
 reader/rdf/parser_test.go | 33 ++++++++++++++++++++++++++++++
 reader/rdf/rdf.go         | 51 +++++++++++++++++++++++++++++++++--------------
 3 files changed, 86 insertions(+), 15 deletions(-)
 create mode 100644 reader/rdf/dublincore.go

diff --git a/reader/rdf/dublincore.go b/reader/rdf/dublincore.go
new file mode 100644
index 0000000..f06456d
--- /dev/null
+++ b/reader/rdf/dublincore.go
@@ -0,0 +1,17 @@
+// Copyright 2019 Frédéric Guillot. All rights reserved.
+// Use of this source code is governed by the Apache 2.0
+// license that can be found in the LICENSE file.
+
+package rdf // import "miniflux.app/reader/rdf"
+
+// DublinCoreFeedElement represents Dublin Core feed XML elements.
+type DublinCoreFeedElement struct {
+	DublinCoreCreator string `xml:"http://purl.org/dc/elements/1.1/ channel>creator"`
+}
+
+// DublinCoreEntryElement represents Dublin Core entry XML elements.
+type DublinCoreEntryElement struct {
+	DublinCoreDate    string `xml:"http://purl.org/dc/elements/1.1/ date"`
+	DublinCoreCreator string `xml:"http://purl.org/dc/elements/1.1/ creator"`
+	DublinCoreContent string `xml:"http://purl.org/rss/1.0/modules/content/ encoded"`
+}
diff --git a/reader/rdf/parser_test.go b/reader/rdf/parser_test.go
index 87410f8..0958f3c 100644
--- a/reader/rdf/parser_test.go
+++ b/reader/rdf/parser_test.go
@@ -486,3 +486,36 @@ func TestParseFeedWithURLWrappedInSpaces(t *testing.T) {
 		t.Errorf(`Unexpected entry URL, got %q`, feed.Entries[0].URL)
 	}
 }
+
+func TestParseRDFWithContentEncoded(t *testing.T) {
+	data := `<?xml version="1.0" encoding="utf-8"?>
+	<rdf:RDF
+		xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
+		xmlns="http://purl.org/rss/1.0/"
+		xmlns:content="http://purl.org/rss/1.0/modules/content/">
+		<channel>
+			<title>Example Feed</title>
+			<link>http://example.org/</link>
+		</channel>
+		<item>
+			<title>Item Title</title>
+			<link>http://example.org/</link>
+			<content:encoded><![CDATA[<p>Test</p>]]></content:encoded>
+		</item>
+	</rdf:RDF>`
+
+	feed, err := Parse(bytes.NewBufferString(data))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if len(feed.Entries) != 1 {
+		t.Fatalf(`Unexpected number of entries, got %d`, len(feed.Entries))
+	}
+
+	expected := `<p>Test</p>`
+	result := feed.Entries[0].Content
+	if result != expected {
+		t.Errorf(`Unexpected entry URL, got %q instead of %q`, result, expected)
+	}
+}
diff --git a/reader/rdf/rdf.go b/reader/rdf/rdf.go
index 7061883..df4296b 100644
--- a/reader/rdf/rdf.go
+++ b/reader/rdf/rdf.go
@@ -21,8 +21,8 @@ type rdfFeed struct {
 	XMLName xml.Name  `xml:"RDF"`
 	Title   string    `xml:"channel>title"`
 	Link    string    `xml:"channel>link"`
-	Creator string    `xml:"channel>creator"`
 	Items   []rdfItem `xml:"item"`
+	DublinCoreFeedElement
 }
 
 func (r *rdfFeed) Transform() *model.Feed {
@@ -32,9 +32,10 @@ func (r *rdfFeed) Transform() *model.Feed {
 
 	for _, item := range r.Items {
 		entry := item.Transform()
-		if entry.Author == "" && r.Creator != "" {
-			entry.Author = sanitizer.StripTags(r.Creator)
+		if entry.Author == "" && r.DublinCoreCreator != "" {
+			entry.Author = strings.TrimSpace(r.DublinCoreCreator)
 		}
+		entry.Author = sanitizer.StripTags(entry.Author)
 
 		if entry.URL == "" {
 			entry.URL = feed.SiteURL
@@ -55,24 +56,44 @@ type rdfItem struct {
 	Title       string `xml:"title"`
 	Link        string `xml:"link"`
 	Description string `xml:"description"`
-	Creator     string `xml:"creator"`
-	Date        string `xml:"date"`
+	DublinCoreEntryElement
 }
 
 func (r *rdfItem) Transform() *model.Entry {
 	entry := new(model.Entry)
-	entry.Title = strings.TrimSpace(r.Title)
-	entry.Author = strings.TrimSpace(r.Creator)
-	entry.URL = strings.TrimSpace(r.Link)
-	entry.Content = r.Description
-	entry.Hash = getHash(r)
-	entry.Date = getDate(r)
+	entry.Title = r.entryTitle()
+	entry.Author = r.entryAuthor()
+	entry.URL = r.entryURL()
+	entry.Content = r.entryContent()
+	entry.Hash = r.entryHash()
+	entry.Date = r.entryDate()
 	return entry
 }
 
-func getDate(r *rdfItem) time.Time {
-	if r.Date != "" {
-		result, err := date.Parse(r.Date)
+func (r *rdfItem) entryTitle() string {
+	return strings.TrimSpace(r.Title)
+}
+
+func (r *rdfItem) entryContent() string {
+	switch {
+	case r.DublinCoreContent != "":
+		return r.DublinCoreContent
+	default:
+		return r.Description
+	}
+}
+
+func (r *rdfItem) entryAuthor() string {
+	return strings.TrimSpace(r.DublinCoreCreator)
+}
+
+func (r *rdfItem) entryURL() string {
+	return strings.TrimSpace(r.Link)
+}
+
+func (r *rdfItem) entryDate() time.Time {
+	if r.DublinCoreDate != "" {
+		result, err := date.Parse(r.DublinCoreDate)
 		if err != nil {
 			logger.Error("rdf: %v", err)
 			return time.Now()
@@ -84,7 +105,7 @@ func getDate(r *rdfItem) time.Time {
 	return time.Now()
 }
 
-func getHash(r *rdfItem) string {
+func (r *rdfItem) entryHash() string {
 	value := r.Link
 	if value == "" {
 		value = r.Title + r.Description
-- 
cgit v1.2.3