miniflux/reader/rss/parser.go
Frédéric Guillot 36d7732234 Disable strict XML parsing
This change should improve parsing of broken XML feeds.

See https://golang.org/pkg/encoding/xml/#Decoder
2019-09-18 22:45:56 -07:00

30 lines
773 B
Go

// Copyright 2017 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 rss // import "miniflux.app/reader/rss"
import (
"encoding/xml"
"io"
"miniflux.app/errors"
"miniflux.app/model"
"miniflux.app/reader/encoding"
)
// Parse returns a normalized feed struct from a RSS feed.
func Parse(data io.Reader) (*model.Feed, *errors.LocalizedError) {
feed := new(rssFeed)
decoder := xml.NewDecoder(data)
decoder.Entity = xml.HTMLEntity
decoder.Strict = false
decoder.CharsetReader = encoding.CharsetReader
err := decoder.Decode(feed)
if err != nil {
return nil, errors.NewLocalizedError("Unable to parse RSS feed: %q", err)
}
return feed.Transform(), nil
}