handle html type atom text

src/parser/atom.go

@@ -6,6 +6,8 @@ import (
 	"html"
 	"io"
 	"strings"
+
+	"github.com/nkanaev/yarr/src/content/htmlutil"
 )
 
 type atomFeed struct {
@@ -42,6 +44,13 @@ type atomLink struct {
 
 type atomLinks []atomLink
 
+func (a *atomText) Text() string {
+	if a.Type == "html" {
+		return htmlutil.ExtractText(a.Data)
+	}
+	return a.Data
+}
+
 func (a *atomText) String() string {
 	data := a.Data
 	if a.Type == "xhtml" {
@@ -76,7 +85,7 @@ func ParseAtom(r io.Reader) (*Feed, error) {
 			GUID:     firstNonEmpty(srcitem.ID),
 			Date:     dateParse(firstNonEmpty(srcitem.Published, srcitem.Updated)),
 			URL:      firstNonEmpty(srcitem.OrigLink, srcitem.Links.First("alternate"), srcitem.Links.First("")),
-			Title:    srcitem.Title.String(),
+			Title:    srcitem.Title.Text(),
 			Content:  firstNonEmpty(srcitem.Content.String(), srcitem.Summary.String(), srcitem.firstMediaDescription()),
 			ImageURL: srcitem.firstMediaThumbnail(),
 			AudioURL: "",

src/parser/atom_test.go

@@ -77,3 +77,19 @@ func TestAtomClashingNamespaces(t *testing.T) {
 		t.FailNow()
 	}
 }
+
+func TestAtomHTMLTitle(t *testing.T) {
+	feed, _ := Parse(strings.NewReader(`
+		<?xml version="1.0" encoding="utf-8"?>
+		<feed xmlns="http://www.w3.org/2005/Atom">
+			<entry><title type="html">say &lt;code&gt;what&lt;/code&gt;?</entry>
+		</feed>
+	`))
+	have := feed.Items[0].Title
+	want := "say what?"
+	if !reflect.DeepEqual(want, have) {
+		t.Logf("want: %#v", want)
+		t.Logf("have: %#v", have)
+		t.FailNow()
+	}
+}