sub-cli/internal/format/srt/srt_test.go
2025-04-23 16:30:45 +08:00

646 lines
18 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

package srt
import (
"os"
"path/filepath"
"strings"
"testing"
"sub-cli/internal/model"
)
func TestParse(t *testing.T) {
// Create a temporary test file
content := `1
00:00:01,000 --> 00:00:04,000
This is the first line.
2
00:00:05,000 --> 00:00:08,000
This is the second line.
3
00:00:09,500 --> 00:00:12,800
This is the third line
with a line break.
`
tempDir := t.TempDir()
testFile := filepath.Join(tempDir, "test.srt")
if err := os.WriteFile(testFile, []byte(content), 0644); err != nil {
t.Fatalf("Failed to create test file: %v", err)
}
// Test parsing
entries, err := Parse(testFile)
if err != nil {
t.Fatalf("Parse failed: %v", err)
}
// Verify results
if len(entries) != 3 {
t.Errorf("Expected 3 entries, got %d", len(entries))
}
// Check first entry
if entries[0].Number != 1 {
t.Errorf("First entry number: expected 1, got %d", entries[0].Number)
}
if entries[0].StartTime.Hours != 0 || entries[0].StartTime.Minutes != 0 ||
entries[0].StartTime.Seconds != 1 || entries[0].StartTime.Milliseconds != 0 {
t.Errorf("First entry start time: expected 00:00:01,000, got %+v", entries[0].StartTime)
}
if entries[0].EndTime.Hours != 0 || entries[0].EndTime.Minutes != 0 ||
entries[0].EndTime.Seconds != 4 || entries[0].EndTime.Milliseconds != 0 {
t.Errorf("First entry end time: expected 00:00:04,000, got %+v", entries[0].EndTime)
}
if entries[0].Content != "This is the first line." {
t.Errorf("First entry content: expected 'This is the first line.', got '%s'", entries[0].Content)
}
// Check third entry
if entries[2].Number != 3 {
t.Errorf("Third entry number: expected 3, got %d", entries[2].Number)
}
expectedContent := "This is the third line\nwith a line break."
if entries[2].Content != expectedContent {
t.Errorf("Third entry content: expected '%s', got '%s'", expectedContent, entries[2].Content)
}
}
func TestGenerate(t *testing.T) {
// Create test entries
entries := []model.SRTEntry{
{
Number: 1,
StartTime: model.Timestamp{Hours: 0, Minutes: 0, Seconds: 1, Milliseconds: 0},
EndTime: model.Timestamp{Hours: 0, Minutes: 0, Seconds: 4, Milliseconds: 0},
Content: "This is the first line.",
},
{
Number: 2,
StartTime: model.Timestamp{Hours: 0, Minutes: 0, Seconds: 5, Milliseconds: 0},
EndTime: model.Timestamp{Hours: 0, Minutes: 0, Seconds: 8, Milliseconds: 0},
Content: "This is the second line.",
},
}
// Generate SRT file
tempDir := t.TempDir()
outputFile := filepath.Join(tempDir, "output.srt")
err := Generate(entries, outputFile)
if err != nil {
t.Fatalf("Generate failed: %v", err)
}
// Verify generated content
content, err := os.ReadFile(outputFile)
if err != nil {
t.Fatalf("Failed to read output file: %v", err)
}
// Check content
lines := strings.Split(string(content), "\n")
if len(lines) < 6 {
t.Fatalf("Expected at least 6 lines, got %d", len(lines))
}
if lines[0] != "1" {
t.Errorf("Expected first line to be '1', got '%s'", lines[0])
}
if lines[1] != "00:00:01,000 --> 00:00:04,000" {
t.Errorf("Expected second line to be time range, got '%s'", lines[1])
}
if lines[2] != "This is the first line." {
t.Errorf("Expected third line to be content, got '%s'", lines[2])
}
}
func TestConvertToSubtitle(t *testing.T) {
// Create a temporary test file
content := `1
00:00:01,000 --> 00:00:04,000
This is the first line.
2
00:00:05,000 --> 00:00:08,000
This is the second line.
`
tempDir := t.TempDir()
testFile := filepath.Join(tempDir, "test.srt")
if err := os.WriteFile(testFile, []byte(content), 0644); err != nil {
t.Fatalf("Failed to create test file: %v", err)
}
// Convert to subtitle
subtitle, err := ConvertToSubtitle(testFile)
if err != nil {
t.Fatalf("ConvertToSubtitle failed: %v", err)
}
// Check result
if subtitle.Format != "srt" {
t.Errorf("Expected format 'srt', got '%s'", subtitle.Format)
}
if len(subtitle.Entries) != 2 {
t.Errorf("Expected 2 entries, got %d", len(subtitle.Entries))
}
// Check first entry
if subtitle.Entries[0].Text != "This is the first line." {
t.Errorf("Expected first entry text 'This is the first line.', got '%s'", subtitle.Entries[0].Text)
}
}
func TestConvertFromSubtitle(t *testing.T) {
// Create test subtitle
subtitle := model.NewSubtitle()
subtitle.Format = "srt"
entry1 := model.NewSubtitleEntry()
entry1.Index = 1
entry1.StartTime = model.Timestamp{Hours: 0, Minutes: 0, Seconds: 1, Milliseconds: 0}
entry1.EndTime = model.Timestamp{Hours: 0, Minutes: 0, Seconds: 4, Milliseconds: 0}
entry1.Text = "This is the first line."
entry2 := model.NewSubtitleEntry()
entry2.Index = 2
entry2.StartTime = model.Timestamp{Hours: 0, Minutes: 0, Seconds: 5, Milliseconds: 0}
entry2.EndTime = model.Timestamp{Hours: 0, Minutes: 0, Seconds: 8, Milliseconds: 0}
entry2.Text = "This is the second line."
subtitle.Entries = append(subtitle.Entries, entry1, entry2)
// Convert from subtitle to SRT
tempDir := t.TempDir()
outputFile := filepath.Join(tempDir, "output.srt")
err := ConvertFromSubtitle(subtitle, outputFile)
if err != nil {
t.Fatalf("ConvertFromSubtitle failed: %v", err)
}
// Verify by parsing back
entries, err := Parse(outputFile)
if err != nil {
t.Fatalf("Failed to parse output file: %v", err)
}
if len(entries) != 2 {
t.Errorf("Expected 2 entries, got %d", len(entries))
}
if entries[0].Content != "This is the first line." {
t.Errorf("Expected first entry content 'This is the first line.', got '%s'", entries[0].Content)
}
}
func TestFormat(t *testing.T) {
// Create test file with non-sequential numbers
content := `2
00:00:01,000 --> 00:00:04,000
This is the first line.
5
00:00:05,000 --> 00:00:08,000
This is the second line.
`
tempDir := t.TempDir()
testFile := filepath.Join(tempDir, "test.srt")
if err := os.WriteFile(testFile, []byte(content), 0644); err != nil {
t.Fatalf("Failed to create test file: %v", err)
}
// Format the file
err := Format(testFile)
if err != nil {
t.Fatalf("Format failed: %v", err)
}
// Verify by parsing back
entries, err := Parse(testFile)
if err != nil {
t.Fatalf("Failed to parse formatted file: %v", err)
}
// Check that numbers are sequential
if entries[0].Number != 1 {
t.Errorf("Expected first entry number to be 1, got %d", entries[0].Number)
}
if entries[1].Number != 2 {
t.Errorf("Expected second entry number to be 2, got %d", entries[1].Number)
}
}
func TestParseSRTTimestamp(t *testing.T) {
testCases := []struct {
name string
input string
expected model.Timestamp
}{
{
name: "Standard format",
input: "00:00:01,000",
expected: model.Timestamp{Hours: 0, Minutes: 0, Seconds: 1, Milliseconds: 0},
},
{
name: "With milliseconds",
input: "00:00:01,500",
expected: model.Timestamp{Hours: 0, Minutes: 0, Seconds: 1, Milliseconds: 500},
},
{
name: "Full hours, minutes, seconds",
input: "01:02:03,456",
expected: model.Timestamp{Hours: 1, Minutes: 2, Seconds: 3, Milliseconds: 456},
},
{
name: "With dot instead of comma",
input: "00:00:01.000", // Should auto-convert . to ,
expected: model.Timestamp{Hours: 0, Minutes: 0, Seconds: 1, Milliseconds: 0},
},
{
name: "Invalid format",
input: "invalid",
expected: model.Timestamp{}, // Should return zero timestamp
},
}
for _, tc := range testCases {
t.Run(tc.name, func(t *testing.T) {
result := parseSRTTimestamp(tc.input)
if result != tc.expected {
t.Errorf("For input '%s', expected %+v, got %+v", tc.input, tc.expected, result)
}
})
}
}
func TestFormatSRTTimestamp(t *testing.T) {
testCases := []struct {
name string
input model.Timestamp
expected string
}{
{
name: "Zero timestamp",
input: model.Timestamp{},
expected: "00:00:00,000",
},
{
name: "Simple seconds",
input: model.Timestamp{Hours: 0, Minutes: 0, Seconds: 1, Milliseconds: 0},
expected: "00:00:01,000",
},
{
name: "With milliseconds",
input: model.Timestamp{Hours: 0, Minutes: 0, Seconds: 1, Milliseconds: 500},
expected: "00:00:01,500",
},
{
name: "Full timestamp",
input: model.Timestamp{Hours: 1, Minutes: 2, Seconds: 3, Milliseconds: 456},
expected: "01:02:03,456",
},
}
for _, tc := range testCases {
t.Run(tc.name, func(t *testing.T) {
result := formatSRTTimestamp(tc.input)
if result != tc.expected {
t.Errorf("For timestamp %+v, expected '%s', got '%s'", tc.input, tc.expected, result)
}
})
}
}
func TestIsEntryTimeStampUnset(t *testing.T) {
testCases := []struct {
name string
entry model.SRTEntry
expected bool
}{
{
name: "Unset timestamp",
entry: model.SRTEntry{Number: 1},
expected: true,
},
{
name: "Set timestamp",
entry: model.SRTEntry{
Number: 1,
StartTime: model.Timestamp{Hours: 0, Minutes: 0, Seconds: 1, Milliseconds: 0},
},
expected: false,
},
}
for _, tc := range testCases {
t.Run(tc.name, func(t *testing.T) {
result := isEntryTimeStampUnset(tc.entry)
if result != tc.expected {
t.Errorf("For entry %+v, expected isEntryTimeStampUnset to be %v, got %v", tc.entry, tc.expected, result)
}
})
}
}
func TestConvertToLyrics(t *testing.T) {
// Create test entries
entries := []model.SRTEntry{
{
Number: 1,
StartTime: model.Timestamp{Hours: 0, Minutes: 0, Seconds: 1, Milliseconds: 0},
EndTime: model.Timestamp{Hours: 0, Minutes: 0, Seconds: 4, Milliseconds: 0},
Content: "This is the first line.",
},
{
Number: 2,
StartTime: model.Timestamp{Hours: 0, Minutes: 0, Seconds: 5, Milliseconds: 0},
EndTime: model.Timestamp{Hours: 0, Minutes: 0, Seconds: 8, Milliseconds: 0},
Content: "This is the second line.",
},
}
// Convert to lyrics
lyrics := ConvertToLyrics(entries)
// Check result
if len(lyrics.Timeline) != 2 {
t.Errorf("Expected 2 timeline entries, got %d", len(lyrics.Timeline))
}
if len(lyrics.Content) != 2 {
t.Errorf("Expected 2 content entries, got %d", len(lyrics.Content))
}
// Check timeline entries
if lyrics.Timeline[0] != entries[0].StartTime {
t.Errorf("First timeline entry: expected %+v, got %+v", entries[0].StartTime, lyrics.Timeline[0])
}
if lyrics.Timeline[1] != entries[1].StartTime {
t.Errorf("Second timeline entry: expected %+v, got %+v", entries[1].StartTime, lyrics.Timeline[1])
}
// Check content entries
if lyrics.Content[0] != entries[0].Content {
t.Errorf("First content entry: expected '%s', got '%s'", entries[0].Content, lyrics.Content[0])
}
if lyrics.Content[1] != entries[1].Content {
t.Errorf("Second content entry: expected '%s', got '%s'", entries[1].Content, lyrics.Content[1])
}
}
func TestParse_EdgeCases(t *testing.T) {
// Test with empty file
tempDir := t.TempDir()
emptyFile := filepath.Join(tempDir, "empty.srt")
if err := os.WriteFile(emptyFile, []byte{}, 0644); err != nil {
t.Fatalf("Failed to create empty test file: %v", err)
}
entries, err := Parse(emptyFile)
if err != nil {
t.Fatalf("Parse failed on empty file: %v", err)
}
if len(entries) != 0 {
t.Errorf("Expected 0 entries for empty file, got %d", len(entries))
}
// Test with malformed file (missing timestamp line)
malformedFile := filepath.Join(tempDir, "malformed.srt")
content := `1
This is missing a timestamp line.
2
00:00:05,000 --> 00:00:08,000
This is valid.
`
if err := os.WriteFile(malformedFile, []byte(content), 0644); err != nil {
t.Fatalf("Failed to create malformed test file: %v", err)
}
entries, err = Parse(malformedFile)
if err != nil {
t.Fatalf("Parse failed on malformed file: %v", err)
}
// SRT解析器更宽容可能会解析出两个条目
if len(entries) != 2 {
t.Errorf("Expected 2 entries, got %d", len(entries))
}
// Test with incomplete last entry
incompleteFile := filepath.Join(tempDir, "incomplete.srt")
content = `1
00:00:01,000 --> 00:00:04,000
This is complete.
2
00:00:05,000 --> 00:00:08,000
`
if err := os.WriteFile(incompleteFile, []byte(content), 0644); err != nil {
t.Fatalf("Failed to create incomplete test file: %v", err)
}
entries, err = Parse(incompleteFile)
if err != nil {
t.Fatalf("Parse failed on incomplete file: %v", err)
}
// Should have one complete entry, the incomplete one is discarded due to empty content
if len(entries) != 1 {
t.Errorf("Expected 1 entry (only the completed one), got %d", len(entries))
}
}
func TestParse_FileError(t *testing.T) {
// Test with non-existent file
_, err := Parse("/nonexistent/file.srt")
if err == nil {
t.Error("Expected error when parsing non-existent file, got nil")
}
}
func TestGenerate_FileError(t *testing.T) {
// Create test entries
entries := []model.SRTEntry{
{
Number: 1,
StartTime: model.Timestamp{Hours: 0, Minutes: 0, Seconds: 1, Milliseconds: 0},
EndTime: model.Timestamp{Hours: 0, Minutes: 0, Seconds: 4, Milliseconds: 0},
Content: "This is a test line.",
},
}
// Test with invalid path
err := Generate(entries, "/nonexistent/directory/file.srt")
if err == nil {
t.Error("Expected error when generating to invalid path, got nil")
}
}
func TestFormat_FileError(t *testing.T) {
// Test with non-existent file
err := Format("/nonexistent/file.srt")
if err == nil {
t.Error("Expected error when formatting non-existent file, got nil")
}
}
func TestConvertToSubtitle_WithHTMLTags(t *testing.T) {
// Create a temporary test file with HTML tags
content := `1
00:00:01,000 --> 00:00:04,000
<i>This is in italic.</i>
2
00:00:05,000 --> 00:00:08,000
<b>This is in bold.</b>
3
00:00:09,000 --> 00:00:12,000
<u>This is underlined.</u>
`
tempDir := t.TempDir()
testFile := filepath.Join(tempDir, "styles.srt")
if err := os.WriteFile(testFile, []byte(content), 0644); err != nil {
t.Fatalf("Failed to create test file with HTML tags: %v", err)
}
// Convert to subtitle
subtitle, err := ConvertToSubtitle(testFile)
if err != nil {
t.Fatalf("ConvertToSubtitle failed: %v", err)
}
// Check if HTML tags were detected
if value, ok := subtitle.Entries[0].FormatData["has_html_tags"]; !ok || value != true {
t.Errorf("Expected FormatData to contain has_html_tags=true for entry with italic")
}
if value, ok := subtitle.Entries[0].Styles["italic"]; !ok || value != "true" {
t.Errorf("Expected Styles to contain italic=true for entry with <i> tag")
}
if value, ok := subtitle.Entries[1].Styles["bold"]; !ok || value != "true" {
t.Errorf("Expected Styles to contain bold=true for entry with <b> tag")
}
if value, ok := subtitle.Entries[2].Styles["underline"]; !ok || value != "true" {
t.Errorf("Expected Styles to contain underline=true for entry with <u> tag")
}
}
func TestConvertToSubtitle_FileError(t *testing.T) {
// Test with non-existent file
_, err := ConvertToSubtitle("/nonexistent/file.srt")
if err == nil {
t.Error("Expected error when converting non-existent file, got nil")
}
}
func TestConvertFromSubtitle_WithStyling(t *testing.T) {
// Create a subtitle with style attributes
subtitle := model.NewSubtitle()
subtitle.Format = "srt"
// Create an entry with italics
entry1 := model.NewSubtitleEntry()
entry1.Index = 1
entry1.StartTime = model.Timestamp{Hours: 0, Minutes: 0, Seconds: 1, Milliseconds: 0}
entry1.EndTime = model.Timestamp{Hours: 0, Minutes: 0, Seconds: 4, Milliseconds: 0}
entry1.Text = "This should be italic."
entry1.Styles["italic"] = "true"
// Create an entry with bold
entry2 := model.NewSubtitleEntry()
entry2.Index = 2
entry2.StartTime = model.Timestamp{Hours: 0, Minutes: 0, Seconds: 5, Milliseconds: 0}
entry2.EndTime = model.Timestamp{Hours: 0, Minutes: 0, Seconds: 8, Milliseconds: 0}
entry2.Text = "This should be bold."
entry2.Styles["bold"] = "true"
// Create an entry with underline
entry3 := model.NewSubtitleEntry()
entry3.Index = 3
entry3.StartTime = model.Timestamp{Hours: 0, Minutes: 0, Seconds: 9, Milliseconds: 0}
entry3.EndTime = model.Timestamp{Hours: 0, Minutes: 0, Seconds: 12, Milliseconds: 0}
entry3.Text = "This should be underlined."
entry3.Styles["underline"] = "true"
subtitle.Entries = append(subtitle.Entries, entry1, entry2, entry3)
// Convert from subtitle to SRT
tempDir := t.TempDir()
outputFile := filepath.Join(tempDir, "styled.srt")
err := ConvertFromSubtitle(subtitle, outputFile)
if err != nil {
t.Fatalf("ConvertFromSubtitle failed: %v", err)
}
// Verify by reading the file directly
content, err := os.ReadFile(outputFile)
if err != nil {
t.Fatalf("Failed to read output file: %v", err)
}
// Check that HTML tags were applied
contentStr := string(content)
if !strings.Contains(contentStr, "<i>This should be italic.</i>") {
t.Errorf("Expected italic HTML tags to be applied")
}
if !strings.Contains(contentStr, "<b>This should be bold.</b>") {
t.Errorf("Expected bold HTML tags to be applied")
}
if !strings.Contains(contentStr, "<u>This should be underlined.</u>") {
t.Errorf("Expected underline HTML tags to be applied")
}
}
func TestConvertFromSubtitle_FileError(t *testing.T) {
// Create simple subtitle
subtitle := model.NewSubtitle()
subtitle.Entries = append(subtitle.Entries, model.NewSubtitleEntry())
// Test with invalid path
err := ConvertFromSubtitle(subtitle, "/nonexistent/directory/file.srt")
if err == nil {
t.Error("Expected error when converting to invalid path, got nil")
}
}
func TestConvertFromSubtitle_WithExistingHTMLTags(t *testing.T) {
// Create a subtitle with text that already contains HTML tags
subtitle := model.NewSubtitle()
subtitle.Format = "srt"
// Create an entry with existing italic tags but also style attribute
entry := model.NewSubtitleEntry()
entry.Index = 1
entry.StartTime = model.Timestamp{Hours: 0, Minutes: 0, Seconds: 1, Milliseconds: 0}
entry.EndTime = model.Timestamp{Hours: 0, Minutes: 0, Seconds: 4, Milliseconds: 0}
entry.Text = "<i>Already italic text.</i>"
entry.Styles["italic"] = "true" // Should not double-wrap with <i> tags
subtitle.Entries = append(subtitle.Entries, entry)
// Convert from subtitle to SRT
tempDir := t.TempDir()
outputFile := filepath.Join(tempDir, "existing_tags.srt")
err := ConvertFromSubtitle(subtitle, outputFile)
if err != nil {
t.Fatalf("ConvertFromSubtitle failed: %v", err)
}
// Verify by reading the file directly
content, err := os.ReadFile(outputFile)
if err != nil {
t.Fatalf("Failed to read output file: %v", err)
}
// Should not have double tags
contentStr := string(content)
if strings.Contains(contentStr, "<i><i>") {
t.Errorf("Expected no duplicate italic tags, but found them")
}
}