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

perf(reader): optimize RemoveTrackingParameters

A bit more than 10% of processor.ProcessFeedEntries' CPU time is spent in
urlcleaner.RemoveTrackingParameters, specifically calling url.Parse, so let's
extract this operation outside of it, and do it once before calling
urlcleaner.RemoveTrackingParameters multiple times.

Co-authored-by: Frédéric Guillot <f@miniflux.net>
This commit is contained in:
jvoisin 2025-06-09 14:08:55 +02:00 committed by Frédéric Guillot
parent 0caadf82f2
commit 7c857bdc72
4 changed files with 23 additions and 28 deletions

View file

@ -5,6 +5,7 @@ package processor // import "miniflux.app/v2/internal/reader/processor"
import (
"log/slog"
"net/url"
"regexp"
"time"
@ -36,6 +37,10 @@ func ProcessFeedEntries(store *storage.Storage, feed *model.Feed, userID int64,
return
}
// The errors are handled in RemoveTrackingParameters.
parsedFeedURL, _ := url.Parse(feed.FeedURL)
parsedSiteURL, _ := url.Parse(feed.SiteURL)
// Process older entries first
for i := len(feed.Entries) - 1; i >= 0; i-- {
entry := feed.Entries[i]
@ -52,7 +57,8 @@ func ProcessFeedEntries(store *storage.Storage, feed *model.Feed, userID int64,
continue
}
if cleanedURL, err := urlcleaner.RemoveTrackingParameters(feed.FeedURL, feed.SiteURL, entry.URL); err == nil {
parsedInputUrl, _ := url.Parse(entry.URL)
if cleanedURL, err := urlcleaner.RemoveTrackingParameters(parsedFeedURL, parsedSiteURL, parsedInputUrl); err == nil {
entry.URL = cleanedURL
}