def test_caption_timestamp_update(self):
c = Caption('00:00:00.500', '00:00:07.000')
c.start = '00:00:01.750'
c.end = '00:00:08.250'
self.assertEqual(c.start, '00:00:01.750')
self.assertEqual(c.end, '00:00:08.250')
def test_update_text_multiline(self):
c = Caption(text='Caption line #1')
c.text = 'Caption line #1\nCaption line #2'
self.assertEqual(len(c.lines), 2)
self.assertEqual(c.text, 'Caption line #1\nCaption line #2')
def _parse(self, lines):
c = None
for index, line in enumerate(lines):
if self._should_skip_line(line, index, c): # allow child classes to skip lines based on the content
continue
if self._is_timeframe_line(line):
try:
start, end = self._parse_timeframe_line(line)
except MalformedCaptionError as e:
raise MalformedCaptionError('{} in line! {}'.format(e, index + 1))
c = Caption(start, end)
elif line:
if c is None:
raise MalformedCaptionError('Caption missing timeframe in line {}.'.format(index + 1))
else:
c.add_line(line)
else:
if c is None:
continue
if not c.lines:
raise MalformedCaptionError('Caption missing text in line {}.'.format(index + 1))
self.captions.append(c)
c = None
if c is not None and c.lines:
self.captions.append(c)
def test_save_updated_identifiers(self):
os.makedirs(OUTPUT_DIR)
copy(self._get_file('using_identifiers.vtt'), OUTPUT_DIR)
self.webvtt.read(os.path.join(OUTPUT_DIR, 'using_identifiers.vtt'))
self.webvtt.captions[0].identifier = 'first caption'
self.webvtt.captions[1].identifier = None
self.webvtt.captions[3].identifier = '44'
last_caption = Caption('00:00:27.280', '00:00:29.200',
'Caption text #7')
last_caption.identifier = 'last caption'
self.webvtt.captions.append(last_caption)
self.webvtt.save(os.path.join(OUTPUT_DIR, 'new_using_identifiers.vtt'))
with open(os.path.join(OUTPUT_DIR, 'new_using_identifiers.vtt'),
'r',
encoding='utf-8') as f:
lines = [line.rstrip() for line in f.readlines()]
expected_lines = [
'WEBVTT', '', 'first caption', '00:00:00.500 --> 00:00:07.000',
'Caption text #1', '', '00:00:07.000 --> 00:00:11.890',
'Caption text #2', '', '00:00:11.890 --> 00:00:16.320',
'Caption text #3', '', '44', '00:00:16.320 --> 00:00:21.580',
'Caption text #4', '', '00:00:21.580 --> 00:00:23.880',
'Caption text #5', '', '00:00:23.880 --> 00:00:27.280',
'Caption text #6', '', 'last caption',
'00:00:27.280 --> 00:00:29.200', 'Caption text #7'
]
self.assertListEqual(lines, expected_lines)
def test_caption_timestamp_format(self):
c = Caption('01:02:03.400', '02:03:04.500')
self.assertEqual(c.start, '01:02:03.400')
self.assertEqual(c.end, '02:03:04.500')
c = Caption('02:03.400', '03:04.500')
self.assertEqual(c.start, '00:02:03.400')
self.assertEqual(c.end, '00:03:04.500')
def test_create_caption(self):
caption = Caption('00:00:00.500', '00:00:07.000',
['Caption test line 1', 'Caption test line 2'])
self.assertEqual(caption.start, '00:00:00.500')
self.assertEqual(caption.start_in_seconds, 0.5)
self.assertEqual(caption.end, '00:00:07.000')
self.assertEqual(caption.end_in_seconds, 7)
self.assertEqual(caption.lines,
['Caption test line 1', 'Caption test line 2'])
def test_write_captions(self):
os.makedirs(OUTPUT_DIR)
copy(self._get_file('one_caption.vtt'), OUTPUT_DIR)
out = io.StringIO()
self.webvtt.read(os.path.join(OUTPUT_DIR, 'one_caption.vtt'))
new_caption = Caption(
'00:00:07.000', '00:00:11.890',
['New caption text line1', 'New caption text line2'])
self.webvtt.captions.append(new_caption)
self.webvtt.write(out)
out.seek(0)
lines = [line.rstrip() for line in out.readlines()]
expected_lines = [
'WEBVTT', '', '00:00:00.500 --> 00:00:07.000', 'Caption text #1',
'', '00:00:07.000 --> 00:00:11.890', 'New caption text line1',
'New caption text line2'
]
self.assertListEqual(lines, expected_lines)
def test_save_captions(self):
os.makedirs(OUTPUT_DIR)
copy(self._get_file('one_caption.vtt'), OUTPUT_DIR)
self.webvtt.read(os.path.join(OUTPUT_DIR, 'one_caption.vtt'))
new_caption = Caption(
'00:00:07.000', '00:00:11.890',
['New caption text line1', 'New caption text line2'])
self.webvtt.captions.append(new_caption)
self.webvtt.save()
with open(os.path.join(OUTPUT_DIR, 'one_caption.vtt'),
'r',
encoding='utf-8') as f:
lines = [line.rstrip() for line in f.readlines()]
expected_lines = [
'WEBVTT', '', '00:00:00.500 --> 00:00:07.000', 'Caption text #1',
'', '00:00:07.000 --> 00:00:11.890', 'New caption text line1',
'New caption text line2'
]
self.assertListEqual(lines, expected_lines)
def _parse_cue_block(self, block):
caption = Caption()
cue_timings = None
for line_number, line in enumerate(block.lines):
if self._is_cue_timings_line(line):
if cue_timings is None:
try:
cue_timings = self._parse_timeframe_line(line)
except MalformedCaptionError as e:
raise MalformedCaptionError('{} in line {}'.format(
e, block.line_number + line_number))
else:
raise MalformedCaptionError(
'--> found in line {}'.format(block.line_number +
line_number))
elif line_number == 0:
caption.identifier = line
else:
caption.add_line(line)
caption.start = cue_timings[0]
caption.end = cue_timings[1]
return caption
def test_parse_timestamp(self):
caption = Caption(start='02:03:11.890')
self.assertEqual(caption.start_in_seconds, 7391.89)
def test_manipulate_lines(self):
c = Caption(text=['Caption line #1', 'Caption line #2'])
c.lines[0] = 'Caption line #1 updated'
self.assertEqual(c.lines[0], 'Caption line #1 updated')
def test_update_text_wrong_type(self):
c = Caption(text='Caption line #1')
self.assertRaises(AttributeError, setattr, c, 'text', 123)
def test_update_text(self):
c = Caption(text='Caption line #1')
c.text = 'Caption line #1 updated'
self.assertEqual(c.text, 'Caption line #1 updated')
def test_caption_receive_text(self):
c = Caption(text='Caption line #1\nCaption line #2')
self.assertEqual(len(c.lines), 2)
self.assertEqual(c.text, 'Caption line #1\nCaption line #2')
def test_caption_text(self):
c = Caption(text=['Caption line #1', 'Caption line #2'])
self.assertEqual(c.text, 'Caption line #1\nCaption line #2')
