Skip to content

Commit

Permalink
Use an io.ReadSeeker instead of an io.Reader to parse feeds
Browse files Browse the repository at this point in the history 
This will allow to make use of func (*Reader) Seek, instead of re-recreating a
new reader. It's a large commit for a small change, but anything to simply the
reader/buffer/ReadAll/… mess is a step in the right direction I think, and it
should enable more follow-up simplifications.
  • Loading branch information
@jvoisin @fguillot
jvoisin authored and fguillot committed Mar 7, 2024
1 parent 3d0126b commit a074773
Show file tree
Hide file tree
Showing 5 changed files with 75 additions and 74 deletions.
2 changes: 1 addition & 1 deletion internal/reader/rdf/parser.go
View file
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ import (
)

// Parse returns a normalized feed struct from a RDF feed.
func Parse(baseURL string, data io.Reader) (*model.Feed, error) {
func Parse(baseURL string, data io.ReadSeeker) (*model.Feed, error) {
feed := new(rdfFeed)
if err := xml.NewXMLDecoder(data).Decode(feed); err != nil {
return nil, fmt.Errorf("rdf: unable to parse feed: %w", err)
Expand Down
36 changes: 18 additions & 18 deletions internal/reader/rdf/parser_test.go
View file
Original file line number Diff line number Diff line change
Expand Up @@ -75,7 +75,7 @@ func TestParseRDFSample(t *testing.T) {
</rdf:RDF>`

feed, err := Parse("http://xml.com/pub/rdf.xml", bytes.NewBufferString(data))
feed, err := Parse("http://xml.com/pub/rdf.xml", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand Down Expand Up @@ -186,7 +186,7 @@ func TestParseRDFSampleWithDublinCore(t *testing.T) {
</rdf:RDF>`

feed, err := Parse("http://meerkat.oreillynet.com/feed.rdf", bytes.NewBufferString(data))
feed, err := Parse("http://meerkat.oreillynet.com/feed.rdf", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand Down Expand Up @@ -253,7 +253,7 @@ func TestParseItemWithOnlyFeedAuthor(t *testing.T) {
</item>
</rdf:RDF>`

feed, err := Parse("http://meerkat.oreillynet.com", bytes.NewBufferString(data))
feed, err := Parse("http://meerkat.oreillynet.com", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand All @@ -278,7 +278,7 @@ func TestParseItemRelativeURL(t *testing.T) {
</item>
</rdf:RDF>`

feed, err := Parse("http://meerkat.oreillynet.com", bytes.NewBufferString(data))
feed, err := Parse("http://meerkat.oreillynet.com", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand Down Expand Up @@ -307,7 +307,7 @@ func TestParseItemWithoutLink(t *testing.T) {
</item>
</rdf:RDF>`

feed, err := Parse("http://meerkat.oreillynet.com", bytes.NewBufferString(data))
feed, err := Parse("http://meerkat.oreillynet.com", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand Down Expand Up @@ -338,7 +338,7 @@ func TestParseItemWithDublicCoreDate(t *testing.T) {
</item>
</rdf:RDF>`

feed, err := Parse("http://example.org", bytes.NewBufferString(data))
feed, err := Parse("http://example.org", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand Down Expand Up @@ -366,7 +366,7 @@ func TestParseItemWithEncodedHTMLInDCCreatorField(t *testing.T) {
</item>
</rdf:RDF>`

feed, err := Parse("http://example.org", bytes.NewBufferString(data))
feed, err := Parse("http://example.org", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand All @@ -392,7 +392,7 @@ func TestParseItemWithoutDate(t *testing.T) {
</item>
</rdf:RDF>`

feed, err := Parse("http://example.org", bytes.NewBufferString(data))
feed, err := Parse("http://example.org", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand All @@ -419,7 +419,7 @@ func TestParseItemWithEncodedHTMLTitle(t *testing.T) {
</item>
</rdf:RDF>`

feed, err := Parse("http://example.org", bytes.NewBufferString(data))
feed, err := Parse("http://example.org", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand All @@ -431,7 +431,7 @@ func TestParseItemWithEncodedHTMLTitle(t *testing.T) {

func TestParseInvalidXml(t *testing.T) {
data := `garbage`
_, err := Parse("http://example.org", bytes.NewBufferString(data))
_, err := Parse("http://example.org", bytes.NewReader([]byte(data)))
if err == nil {
t.Fatal("Parse should returns an error")
}
Expand All @@ -446,7 +446,7 @@ func TestParseFeedWithHTMLEntity(t *testing.T) {
</channel>
</rdf:RDF>`

feed, err := Parse("http://example.org", bytes.NewBufferString(data))
feed, err := Parse("http://example.org", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand All @@ -465,7 +465,7 @@ func TestParseFeedWithInvalidCharacterEntity(t *testing.T) {
</channel>
</rdf:RDF>`

feed, err := Parse("http://example.org", bytes.NewBufferString(data))
feed, err := Parse("http://example.org", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand Down Expand Up @@ -521,7 +521,7 @@ func TestParseFeedWithURLWrappedInSpaces(t *testing.T) {
</item>
</rdf:RDF>`

feed, err := Parse("http://biorxiv.org", bytes.NewBufferString(data))
feed, err := Parse("http://biorxiv.org", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand Down Expand Up @@ -556,7 +556,7 @@ func TestParseRDFWithContentEncoded(t *testing.T) {
</item>
</rdf:RDF>`

feed, err := Parse("http://example.org/", bytes.NewBufferString(data))
feed, err := Parse("http://example.org/", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand Down Expand Up @@ -589,7 +589,7 @@ func TestParseRDFWithEncodedHTMLDescription(t *testing.T) {
</item>
</rdf:RDF>`

feed, err := Parse("http://example.org/", bytes.NewBufferString(data))
feed, err := Parse("http://example.org/", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand Down Expand Up @@ -623,7 +623,7 @@ func TestParseRDFItemWithDuplicateTitleElement(t *testing.T) {
</item>
</rdf:RDF>`

feed, err := Parse("http://example.org/", bytes.NewBufferString(data))
feed, err := Parse("http://example.org/", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand Down Expand Up @@ -656,7 +656,7 @@ func TestParseRDFItemWithDublinCoreTitleElement(t *testing.T) {
</item>
</rdf:RDF>`

feed, err := Parse("http://example.org/", bytes.NewBufferString(data))
feed, err := Parse("http://example.org/", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand Down Expand Up @@ -688,7 +688,7 @@ func TestParseRDFItemWitEmptyTitleElement(t *testing.T) {
</item>
</rdf:RDF>`

feed, err := Parse("http://example.org/", bytes.NewBufferString(data))
feed, err := Parse("http://example.org/", bytes.NewReader([]byte(data)))
if err != nil {
t.Fatal(err)
}
Expand Down
2 changes: 1 addition & 1 deletion internal/reader/rss/parser.go
View file
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@ import (
)

// Parse returns a normalized feed struct from a RSS feed.
func Parse(baseURL string, data io.Reader) (*model.Feed, error) {
func Parse(baseURL string, data io.ReadSeeker) (*model.Feed, error) {
feed := new(rssFeed)
if err := xml.NewXMLDecoder(data).Decode(feed); err != nil {
return nil, fmt.Errorf("rss: unable to parse feed: %w", err)
Expand Down

0 comments on commit a074773

Please sign in to comment.