Parse <category> from Feeds (RSS, Atom and JSON)

reader/atom/atom_10.go

@@ -80,14 +80,15 @@ func (a *atom10Feed) Transform(baseURL string) *model.Feed {
 }
 
 type atom10Entry struct {
-	ID        string      `xml:"id"`
-	Title     atom10Text  `xml:"title"`
-	Published string      `xml:"published"`
-	Updated   string      `xml:"updated"`
-	Links     atomLinks   `xml:"link"`
-	Summary   atom10Text  `xml:"summary"`
-	Content   atom10Text  `xml:"http://www.w3.org/2005/Atom content"`
-	Authors   atomAuthors `xml:"author"`
+	ID         string           `xml:"id"`
+	Title      atom10Text       `xml:"title"`
+	Published  string           `xml:"published"`
+	Updated    string           `xml:"updated"`
+	Links      atomLinks        `xml:"link"`
+	Summary    atom10Text       `xml:"summary"`
+	Content    atom10Text       `xml:"http://www.w3.org/2005/Atom content"`
+	Authors    atomAuthors      `xml:"author"`
+	Categories []atom10Category `xml:"category"`
 	media.Element
 }
 
@@ -101,6 +102,7 @@ func (a *atom10Entry) Transform() *model.Entry {
 	entry.Title = a.entryTitle()
 	entry.Enclosures = a.entryEnclosures()
 	entry.CommentsURL = a.entryCommentsURL()
+	entry.Tags = a.entryCategories()
 	return entry
 }
 
@@ -214,6 +216,20 @@ func (a *atom10Entry) entryEnclosures() model.EnclosureList {
 	return enclosures
 }
 
+func (r *atom10Entry) entryCategories() []string {
+	var categoryList []string
+
+	for _, atomCategory := range r.Categories {
+		if strings.TrimSpace(atomCategory.Label) != "" {
+			categoryList = append(categoryList, strings.TrimSpace(atomCategory.Label))
+		} else {
+			categoryList = append(categoryList, strings.TrimSpace(atomCategory.Term))
+		}
+	}
+
+	return categoryList
+}
+
 // See https://tools.ietf.org/html/rfc4685#section-4
 // If the type attribute of the atom:link is omitted, its value is assumed to be "application/atom+xml".
 // We accept only HTML or XHTML documents for now since the intention is to have the same behavior as RSS.
@@ -232,6 +248,11 @@ type atom10Text struct {
 	XHTMLRootElement atomXHTMLRootElement `xml:"http://www.w3.org/1999/xhtml div"`
 }
 
+type atom10Category struct {
+	Term  string `xml:"term,attr"`
+	Label string `xml:"label,attr"`
+}
+
 // 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

reader/atom/atom_10_test.go

@@ -1604,3 +1604,48 @@ func TestAbsoluteCommentsURL(t *testing.T) {
 		t.Errorf("Incorrect entry comments URL, got: %s", feed.Entries[0].CommentsURL)
 	}
 }
+
+func TestParseFeedWithCategories(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/"/>
+	  <author>
+		<name>Alice</name>
+	  </author>
+	  <author>
+		<name>Bob</name>
+	  </author>
+
+	  <entry>
+		<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>Some text.</summary>
+		<category term='Tech' />
+		<category term='Technology' label='Science' />
+	  </entry>
+
+	</feed>`
+
+	feed, err := Parse("https://example.org/", bytes.NewBufferString(data))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	if len(feed.Entries[0].Tags) != 2 {
+		t.Errorf("Incorrect number of tags, got: %d", len(feed.Entries[0].Tags))
+	}
+
+	expected := "Tech"
+	result := feed.Entries[0].Tags[0]
+	if result != expected {
+		t.Errorf("Incorrect entry category, got %q instead of %q", result, expected)
+	}
+
+	expected = "Science"
+	result = feed.Entries[0].Tags[1]
+	if result != expected {
+		t.Errorf("Incorrect entry category, got %q instead of %q", result, expected)
+	}
+}