bug处理

internal/service/subtitle_convert.go

@@ -27,6 +27,7 @@ func srtToVTT(body string) string {
 func assToVTT(body string) string {
 	out := strings.Builder{}
 	out.WriteString("WEBVTT\n\n")
+	seen := make(map[string]struct{})
 	for i, line := range strings.Split(body, "\n") {
 		line = strings.TrimSpace(line)
 		if !strings.HasPrefix(line, "Dialogue:") {
@@ -36,11 +37,22 @@ func assToVTT(body string) string {
 		if len(parts) < 10 {
 			continue
 		}
+		start := normaliseTimecode(parts[1])
+		end := normaliseTimecode(parts[2])
+		text := stripASSTags(parts[9])
+		if text == "" {
+			continue
+		}
+		key := start + "\x00" + end + "\x00" + text
+		if _, duplicate := seen[key]; duplicate {
+			continue
+		}
+		seen[key] = struct{}{}
 		fmt.Fprintf(&out, "%d\n%s --> %s\n%s\n\n",
 			i,
-			normaliseTimecode(parts[1]),
-			normaliseTimecode(parts[2]),
-			stripASSTags(parts[9]),
+			start,
+			end,
+			text,
 		)
 	}
 	return out.String()
@@ -86,5 +98,9 @@ func normaliseTimecode(t string) string {
 var assTag = regexp.MustCompile(`\{[^}]*\}`)
 
 func stripASSTags(s string) string {
-	return assTag.ReplaceAllString(s, "")
+	s = assTag.ReplaceAllString(s, "")
+	s = strings.ReplaceAll(s, `\N`, "\n")
+	s = strings.ReplaceAll(s, `\n`, "\n")
+	s = strings.ReplaceAll(s, `\h`, "\u00a0")
+	return strings.TrimSpace(s)
 }

internal/service/subtitle_test.go

@@ -5,6 +5,7 @@ import (
 	"encoding/json"
 	"os"
 	"path/filepath"
+	"strings"
 	"testing"
 
 	"github.com/glebarez/sqlite"
@@ -84,6 +85,25 @@ func TestNormaliseTimecode(t *testing.T) {
 	}
 }
 
+func TestAssToVTTDeduplicatesDialogueAndNormalisesLineBreaks(t *testing.T) {
+	body := strings.Join([]string{
+		`Dialogue: 0,0:00:01.00,0:00:02.00,Default,,0,0,0,,{\an2}第一行\N第二行`,
+		`Dialogue: 1,0:00:01.00,0:00:02.00,Copy,,0,0,0,,{\bord2}第一行\N第二行`,
+		`Dialogue: 0,0:00:03.00,0:00:04.00,Default,,0,0,0,,{\i1}`,
+	}, "\n")
+
+	got := assToVTT(body)
+	if strings.Count(got, "第一行\n第二行") != 1 {
+		t.Fatalf("duplicate ASS dialogue was not collapsed:\n%s", got)
+	}
+	if strings.Contains(got, `\N`) || strings.Contains(got, `\an2`) {
+		t.Fatalf("ASS control sequences leaked into WebVTT:\n%s", got)
+	}
+	if strings.Contains(got, "00:00:03.000 --> 00:00:04.000") {
+		t.Fatalf("empty styled dialogue should be omitted:\n%s", got)
+	}
+}
+
 func TestSubtitleServeRawWritesSourceBytes(t *testing.T) {
 	db, err := gorm.Open(sqlite.Open("file::memory:?cache=shared"), &gorm.Config{})
 	if err != nil {