oss/miniflux-v2
oss/miniflux-v2
1
0
Fork 0
mirror of https://github.com/miniflux/v2.git synced 2025-06-27 16:36:00 +00:00
Code Wiki Activity

perf(xml): optimized NewXMLDecoder

Browse source 
io.ReadAll is growing the underlying buffer progressively, while
io.Copy is able to allocate it in one go, which is significantly faster.
io.ReadAll is currently accounting for around 10% of the CPU time of rss.Parse
This commit is contained in:
jvoisin 2025-06-09 15:15:40 +02:00 • committed by Frédéric Guillot
parent 5872710d22
commit 49085daefe
1 changed files with 7 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

10
internal/reader/xml/decoder.go
View file

@ -16,11 +16,15 @@ import (
// NewXMLDecoder returns a XML decoder that filters illegal characters.
func NewXMLDecoder(data io.ReadSeeker) *xml.Decoder {
var decoder *xml.Decoder
buffer, _ := io.ReadAll(data)
enc := getEncoding(buffer)
// This is way fasted than io.ReadAll(data) as the buffer can be allocated in one go instead of dynamically grown.
buffer := &bytes.Buffer{}
io.Copy(buffer, data)
enc := getEncoding(buffer.Bytes())
if enc == "" || strings.EqualFold(enc, "utf-8") {
// filter invalid chars now, since decoder.CharsetReader not called for utf-8 content
filteredBytes := bytes.Map(filterValidXMLChar, buffer)
filteredBytes := bytes.Map(filterValidXMLChar, buffer.Bytes())
decoder = xml.NewDecoder(bytes.NewReader(filteredBytes))
} else {
// filter invalid chars later within decoder.CharsetReader