refactor(processor): extract some functions into an utils.go file

internal/reader/processor/processor.go

@@ -10,9 +10,6 @@ import (
 	"slices"
 	"time"
 
-	"github.com/tdewolff/minify/v2"
-	"github.com/tdewolff/minify/v2/html"
-
 	"miniflux.app/v2/internal/config"
 	"miniflux.app/v2/internal/metric"
 	"miniflux.app/v2/internal/model"
@@ -117,7 +114,7 @@ func ProcessFeedEntries(store *storage.Storage, feed *model.Feed, userID int64,
 				)
 			} else if extractedContent != "" {
 				// We replace the entry content only if the scraper doesn't return any error.
-				entry.Content = minifyEntryContent(extractedContent)
+				entry.Content = minifyContent(extractedContent)
 			}
 		}
 
@@ -177,7 +174,7 @@ func ProcessEntryWebPage(feed *model.Feed, entry *model.Entry, user *model.User)
 	}
 
 	if extractedContent != "" {
-		entry.Content = minifyEntryContent(extractedContent)
+		entry.Content = minifyContent(extractedContent)
 		if user.ShowReadingTime {
 			entry.ReadingTime = readingtime.EstimateReadingTime(entry.Content, user.DefaultReadingSpeed, user.CJKReadingSpeed)
 		}
@@ -230,19 +227,3 @@ func isRecentEntry(entry *model.Entry) bool {
 	}
 	return false
 }
-
-func minifyEntryContent(entryContent string) string {
-	m := minify.New()
-
-	// Options required to avoid breaking the HTML content.
-	m.Add("text/html", &html.Minifier{
-		KeepEndTags: true,
-		KeepQuotes:  true,
-	})
-
-	if minifiedHTML, err := m.String("text/html", entryContent); err == nil {
-		entryContent = minifiedHTML
-	}
-
-	return entryContent
-}

internal/reader/processor/processor_test.go

@@ -118,7 +118,7 @@ func TestIsRecentEntry(t *testing.T) {
 func TestMinifyEntryContent(t *testing.T) {
 	input := `<p>    Some text with a <a href="http://example.org/"> link   </a>    </p>`
 	expected := `<p>Some text with a <a href="http://example.org/">link</a></p>`
-	result := minifyEntryContent(input)
+	result := minifyContent(input)
 	if expected != result {
 		t.Errorf(`Unexpected result, got %q`, result)
 	}

internal/reader/processor/utils.go

@@ -0,0 +1,82 @@
+// SPDX-FileCopyrightText: Copyright The Miniflux Authors. All rights reserved.
+// SPDX-License-Identifier: Apache-2.0
+
+package processor // import "miniflux.app/v2/internal/reader/processor"
+
+import (
+	"errors"
+	"fmt"
+	"regexp"
+	"strconv"
+	"time"
+
+	"github.com/tdewolff/minify/v2"
+	"github.com/tdewolff/minify/v2/html"
+)
+
+// TODO: use something less horrible than a regex to parse ISO 8601 durations.
+
+var (
+	iso8601Regex = regexp.MustCompile(`^P((?P<year>\d+)Y)?((?P<month>\d+)M)?((?P<week>\d+)W)?((?P<day>\d+)D)?(T((?P<hour>\d+)H)?((?P<minute>\d+)M)?((?P<second>\d+)S)?)?$`)
+)
+
+func parseISO8601(from string) (time.Duration, error) {
+	var match []string
+	var d time.Duration
+
+	if iso8601Regex.MatchString(from) {
+		match = iso8601Regex.FindStringSubmatch(from)
+	} else {
+		return 0, errors.New("youtube: could not parse duration string")
+	}
+
+	for i, name := range iso8601Regex.SubexpNames() {
+		part := match[i]
+		if i == 0 || name == "" || part == "" {
+			continue
+		}
+
+		val, err := strconv.ParseInt(part, 10, 64)
+		if err != nil {
+			return 0, err
+		}
+
+		switch name {
+		case "hour":
+			d += time.Duration(val) * time.Hour
+		case "minute":
+			d += time.Duration(val) * time.Minute
+		case "second":
+			d += time.Duration(val) * time.Second
+		default:
+			return 0, fmt.Errorf("youtube: unknown field %s", name)
+		}
+	}
+
+	return d, nil
+}
+
+func minifyContent(content string) string {
+	m := minify.New()
+
+	// Options required to avoid breaking the HTML content.
+	m.Add("text/html", &html.Minifier{
+		KeepEndTags: true,
+		KeepQuotes:  true,
+	})
+
+	if minifiedHTML, err := m.String("text/html", content); err == nil {
+		content = minifiedHTML
+	}
+
+	return content
+}
+
+func containsRegexPattern(pattern string, entries []string) bool {
+	for _, entry := range entries {
+		if matched, _ := regexp.MatchString(pattern, entry); matched {
+			return true
+		}
+	}
+	return false
+}

internal/reader/processor/youtube.go

@@ -24,7 +24,6 @@ import (
 
 var (
 	youtubeRegex = regexp.MustCompile(`youtube\.com/watch\?v=(.*)$`)
-	iso8601Regex = regexp.MustCompile(`^P((?P<year>\d+)Y)?((?P<month>\d+)M)?((?P<week>\d+)W)?((?P<day>\d+)D)?(T((?P<hour>\d+)H)?((?P<minute>\d+)M)?((?P<second>\d+)S)?)?$`)
 )
 
 func isYouTubeVideoURL(websiteURL string) bool {
@@ -160,42 +159,6 @@ func fetchYouTubeWatchTimeFromApiInBulk(videoIDs []string) (map[string]time.Dura
 	return watchTimeMap, nil
 }
 
-func parseISO8601(from string) (time.Duration, error) {
-	var match []string
-	var d time.Duration
-
-	if iso8601Regex.MatchString(from) {
-		match = iso8601Regex.FindStringSubmatch(from)
-	} else {
-		return 0, errors.New("youtube: could not parse duration string")
-	}
-
-	for i, name := range iso8601Regex.SubexpNames() {
-		part := match[i]
-		if i == 0 || name == "" || part == "" {
-			continue
-		}
-
-		val, err := strconv.ParseInt(part, 10, 64)
-		if err != nil {
-			return 0, err
-		}
-
-		switch name {
-		case "hour":
-			d += time.Duration(val) * time.Hour
-		case "minute":
-			d += time.Duration(val) * time.Minute
-		case "second":
-			d += time.Duration(val) * time.Second
-		default:
-			return 0, fmt.Errorf("youtube: unknown field %s", name)
-		}
-	}
-
-	return d, nil
-}
-
 type youtubeVideoListResponse struct {
 	Items []struct {
 		ID             string `json:"id"`