1
0
Fork 0
mirror of https://github.com/miniflux/v2.git synced 2025-08-06 17:41:00 +00:00
miniflux-v2/internal/reader/rewrite/url_rewrite.go
jvoisin f455c18c66 perf(rewrite): anchor the rewrite regex
There is no need to try to match the regexp over the whole input, having it
anchored is enough. If we feel extra-lenient, we might strip spaces in
front/tail, but I don't think it's necessary.

This commit also invert a condition to reduce the level of nested indentation,
and make a condition stricter.
2025-07-10 19:23:54 -07:00

50 lines
1.4 KiB
Go

// SPDX-FileCopyrightText: Copyright The Miniflux Authors. All rights reserved.
// SPDX-License-Identifier: Apache-2.0
package rewrite // import "miniflux.app/v2/internal/reader/rewrite"
import (
"log/slog"
"regexp"
"miniflux.app/v2/internal/model"
)
var customReplaceRuleRegex = regexp.MustCompile(`^rewrite\("([^"]+)"\|"([^"]+)"\)$`)
func RewriteEntryURL(feed *model.Feed, entry *model.Entry) string {
if feed.UrlRewriteRules == "" {
return entry.URL
}
var rewrittenURL = entry.URL
parts := customReplaceRuleRegex.FindStringSubmatch(feed.UrlRewriteRules)
if len(parts) == 3 {
re, err := regexp.Compile(parts[1])
if err != nil {
slog.Error("Failed on regexp compilation",
slog.String("url_rewrite_rules", feed.UrlRewriteRules),
slog.Any("error", err),
)
return rewrittenURL
}
rewrittenURL = re.ReplaceAllString(entry.URL, parts[2])
slog.Debug("Rewriting entry URL",
slog.String("original_entry_url", entry.URL),
slog.String("rewritten_entry_url", rewrittenURL),
slog.Int64("feed_id", feed.ID),
slog.String("feed_url", feed.FeedURL),
)
} else {
slog.Debug("Cannot find search and replace terms for replace rule",
slog.String("original_entry_url", entry.URL),
slog.String("rewritten_entry_url", rewrittenURL),
slog.Int64("feed_id", feed.ID),
slog.String("feed_url", feed.FeedURL),
slog.String("url_rewrite_rules", feed.UrlRewriteRules),
)
}
return rewrittenURL
}