1
0
Fork 0
mirror of https://github.com/miniflux/v2.git synced 2025-09-15 18:57:04 +00:00

Use an io.ReadSeeker instead of an io.Reader to parse feeds

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.
This commit is contained in:
jvoisin 2024-03-06 14:57:21 +01:00 committed by Frédéric Guillot
parent 3d0126be0b
commit a074773e6c
5 changed files with 75 additions and 74 deletions

View file

@ -14,13 +14,14 @@ import (
)
// NewXMLDecoder returns a XML decoder that filters illegal characters.
func NewXMLDecoder(data io.Reader) *xml.Decoder {
func NewXMLDecoder(data io.ReadSeeker) *xml.Decoder {
var decoder *xml.Decoder
buffer, _ := io.ReadAll(data)
enc := procInst("encoding", string(buffer))
if enc != "" && enc != "utf-8" && enc != "UTF-8" && !strings.EqualFold(enc, "utf-8") {
// filter invalid chars later within decoder.CharsetReader
decoder = xml.NewDecoder(bytes.NewReader(buffer))
data.Seek(0, io.SeekStart)
decoder = xml.NewDecoder(data)
} else {
// filter invalid chars now, since decoder.CharsetReader not called for utf-8 content
filteredBytes := bytes.Map(filterValidXMLChar, buffer)