def test_timed_data_parses_correctly(self):
subs = utils.get_data_file_path('timed_text.srt')
parsed = babelsubs.load_from_file(subs, type='srt', language='en')
self.assertNotEquals(parsed, None)
try:
srt = parsed.to('srt')
self.assertNotEquals(srt, None)
except Exception, e:
self.fail(e)
def test_normalize_time(self):
content_str = open(utils.get_data_file_path("normalize-time.dfxp") ).read()
dfxp = storage.SubtitleSet('en', content_str, normalize_time=True)
subs = dfxp.get_subtitles()
self.assertTrue(len(dfxp) )
for el in subs:
self.assertIn("begin", el.attrib)
self.assertTrue(storage.TIME_EXPRESSION_CLOCK_TIME.match(el.attrib['begin']))
self.assertIn("end", el.attrib)
self.assertTrue(storage.TIME_EXPRESSION_CLOCK_TIME.match(el.attrib['end']))
self.assertNotIn('dur', el.attrib)
def test_timed_data_parses_correctly(self):
subs = utils.get_data_file_path('timed_text.srt')
parsed = babelsubs.load_from_file(subs, type='srt', language='en')
self.assertNotEquals(parsed, None)
try:
srt = parsed.to('srt')
self.assertNotEquals(srt, None)
except Exception, e:
self.fail(e)
def test_normalize_time(self):
content_str = open(utils.get_data_file_path("normalize-time.dfxp") ).read()
dfxp = storage.SubtitleSet('en', content_str, normalize_time=True)
subs = dfxp.get_subtitles()
self.assertTrue(len(dfxp) )
for el in subs:
self.assertIn("begin", el.attrib)
self.assertTrue(storage.TIME_EXPRESSION_CLOCK_TIME.match(el.attrib['begin']))
self.assertIn("end", el.attrib)
self.assertTrue(storage.TIME_EXPRESSION_CLOCK_TIME.match(el.attrib['end']))
self.assertNotIn('dur', el.attrib)
def test_load_from_dfxp(self):
subs = self.loader.load('en', utils.get_data_file_path("simple.dfxp"))
# since we are loading directly from DFXP, we should keep the
# styling/layout the same as the file
head = subs._ttml.find(TTML + 'head')
styling = head.find(TTML + 'styling')
styles = styling.findall(TTML + 'style')
self.assertEquals(len(styles), 1)
self.assertEquals(styles[0].attrib, {
'id': "defaultCaption",
TTS + 'fontSize': "14px",
TTS + 'fontFamily': "Arial",
TTS + 'fontWeight': "normal",
TTS + 'fontStyle': "normal",
TTS + 'textDecoration': "none",
TTS + 'color': "white",
TTS + 'backgroundColor': "black",
TTS + 'textAlign': "center",
})
self.assertEquals(head.find(TTML + 'layout'), None)
def _get_subs(self, filename):
return YoutubeParser(
open(utils.get_data_file_path(filename)).read(),
'en').to_internal()
def test_type_specified(self):
subs = load_from_file(utils.get_data_file_path("simple.srt"), type='srt')
parsed = subs.to_internal()
self.assertEquals(len(parsed), 19)
def test_from_string_requires_type(self):
data = open(utils.get_data_file_path("simple-srt.badextension"), 'r').read()
self.assertRaises(TypeError, load_from, data)
def test_from_string(self):
subs = load_from(open(utils.get_data_file_path("simple-srt.badextension"), 'r').read() ,type='srt')
parsed = subs.to_internal()
self.assertEquals(len(parsed), 19)
def test_type_override(self):
subs = load_from_file(utils.get_data_file_path("simple-srt.badextension"), type='srt')
parsed = subs.to_internal()
self.assertEquals(len(parsed), 19)
def test_type_guessing(self):
subs = load_from_file(utils.get_data_file_path("simple.srt"))
parsed = subs.to_internal()
self.assertEquals(len(parsed), 19)
def test_type_override(self):
subs = load_from_file(
utils.get_data_file_path("simple-srt.badextension"), type='srt')
parsed = subs.to_internal()
self.assertEquals(len(parsed), 19)
def test_load_from_string(self):
filename = utils.get_data_file_path('simple.dfxp')
with open(filename) as f:
s = f.read()
load_from(s, type='dfxp').to_internal()
def test_load(self):
subs = self.loader.load('en', utils.get_data_file_path("simple.srt"))
self.check_srt_import(subs)
def test_cleanup_namespace(self):
input_string = open(utils.get_data_file_path("pre-dmr.dfxp")).read()
cleaned = _cleanup_legacy_namespace(input_string)
self.assertEqual(cleaned.find(TTML_NAMESPACE_URI_LEGACY), -1)
sset = SubtitleSet(language_code='en', initial_data=cleaned)
self.assertEqual(len(sset), 419)
def _get_subs(self, filename):
return YoutubeParser(open(utils.get_data_file_path(filename)).read(), 'en').to_internal()
def test_type_specified(self):
subs = load_from_file(utils.get_data_file_path("simple.srt"),
type='srt')
parsed = subs.to_internal()
self.assertEquals(len(parsed), 19)
def test_from_string_requires_type(self):
data = open(utils.get_data_file_path("simple-srt.badextension"),
'r').read()
self.assertRaises(TypeError, load_from, data)
def test_from_string(self):
subs = load_from(open(
utils.get_data_file_path("simple-srt.badextension"), 'r').read(),
type='srt')
parsed = subs.to_internal()
self.assertEquals(len(parsed), 19)
def test_load_from_string(self):
content = open(utils.get_data_file_path("simple.srt")).read()
subs = self.loader.loads('en', content, 'srt')
self.check_srt_import(subs)
def test_load_from_string(self):
filename = utils.get_data_file_path('simple.dfxp')
with open(filename) as f:
s = f.read()
load_from(s, type='dfxp').to_internal()
def test_cleanup_namespace(self):
input_string = open(utils.get_data_file_path("pre-dmr.dfxp")).read()
cleaned = _cleanup_legacy_namespace(input_string)
self.assertEqual(cleaned.find(TTML_NAMESPACE_URI_LEGACY), -1)
sset = SubtitleSet(language_code='en', initial_data=cleaned)
self.assertEqual(len(sset), 419)
def test_type_guessing(self):
subs = load_from_file(utils.get_data_file_path("simple.srt"))
parsed = subs.to_internal()
self.assertEquals(len(parsed), 19)
