def test_update_end_time(self):
dfxp = utils.get_subs("pre-drm.dfxp").to_internal()
dfxp_updated = utils.get_subs("pre-drm.dfxp").to_internal()
for i in xrange(0, len(dfxp)):
dfxp_updated.update(i, to_ms=1000*i)
for i,sub in enumerate(dfxp_updated.subtitle_items()):
self.assertEqual(i * 1000, sub.end_time)
def test_update_end_time(self):
dfxp = utils.get_subs("pre-dmr.dfxp").to_internal()
dfxp_updated = utils.get_subs("pre-dmr.dfxp").to_internal()
for i in xrange(0, len(dfxp)):
dfxp_updated.update(i, to_ms=1000 * i)
for i, sub in enumerate(dfxp_updated.subtitle_items()):
self.assertEqual(i * 1000, sub.end_time)
def test_ttfa(self):
subs = utils.get_subs("pre-dmr.dfxp")
self.assertEquals(len(subs), 419)
# make sure the right namespace is in
subs.subtitle_set._ttml.tag = '{http://www.w3.org/ns/ttml}tt'
self.assertEqual(subs.subtitle_set._ttml.nsmap[None] , TTML_NAMESPACE_URI)
subs = utils.get_subs("pre-dmr2.dfxp")
self.assertEquals(len(subs), 19)
# make sure the right namespace is in
subs.subtitle_set._ttml.tag = '{http://www.w3.org/ns/ttml}tt'
def test_ttfa(self):
subs = utils.get_subs("pre-dmr.dfxp")
self.assertEquals(len(subs), 419)
# make sure the right namespace is in
subs.subtitle_set._ttml.tag = '{http://www.w3.org/ns/ttml}tt'
self.assertEqual(subs.subtitle_set._ttml.nsmap[None] , TTML_NAMESPACE_URI)
subs = utils.get_subs("pre-dmr2.dfxp")
self.assertEquals(len(subs), 19)
# make sure the right namespace is in
subs.subtitle_set._ttml.tag = '{http://www.w3.org/ns/ttml}tt'
def test_regions(self):
subs = utils.get_subs("regions.vtt")
items = subs.to_internal().subtitle_items()
for sub in items[:4]:
self.assertEquals(sub.region, "top")
for sub in items[4:]:
self.assertEquals(sub.region, None)
def test_ampersand_escaping(self):
subs = utils.get_subs("basic.vtt")
parsed = subs.to_internal()
sub_data = [x for x in parsed.subtitle_items(WEBVTTGenerator.MAPPINGS)]
self.assertEquals(
sub_data[16].text,
"such as MP4, theora, webM and <i>&</i> HTML 5.")
def test_regions(self):
subs = utils.get_subs("regions.vtt")
items = subs.to_internal().subtitle_items()
for sub in items[:4]:
self.assertEquals(sub.region, "top")
for sub in items[4:]:
self.assertEquals(sub.region, None)
def test_internal_format(self):
subs = utils.get_subs("simple.srt")
parsed = subs.to_internal()
sub_data = [x for x in parsed.subtitle_items(SRTGenerator.MAPPINGS)]
self.assertEquals(sub_data[0].start_time, 4)
self.assertEquals(sub_data[0].end_time, 2093)
self.assertEquals(sub_data[0].text, "We started <b>Universal Subtitles</b> because we believe")
def test_internal_format(self):
subs = utils.get_subs("simple.dfxp")
parsed = subs.to_internal()
sub_data = [x for x in parsed.subtitle_items()]
self.assertEquals(sub_data[0][0], 1200)
self.assertEquals(sub_data[0][1], 4467)
self.assertEquals(sub_data[3][2], 'at least 7,000 years ago.')
def test_internal_format(self):
subs = utils.get_subs("simple.dfxp")
parsed = subs.to_internal()
sub_data = [x for x in parsed.subtitle_items()]
self.assertEquals(sub_data[0][0], 1200)
self.assertEquals(sub_data[0][1], 4467)
self.assertEquals(sub_data[3][2], 'at least 7,000 years ago.')
def test_internal_format(self):
subs = utils.get_subs("simple.sbv")
parsed = subs.to_internal()
sub_data = [x for x in parsed.subtitle_items()]
self.assertEquals(sub_data[0][0], 48)
self.assertEquals(sub_data[0][1], 2932)
self.assertEquals(sub_data[0][2], 'We started Universal Subtitles because we believe')
def test_internal_format(self):
subs = utils.get_subs("simple.sbv")
parsed = subs.to_internal()
sub_data = [x for x in parsed.subtitle_items()]
self.assertEquals(sub_data[0][0], 48)
self.assertEquals(sub_data[0][1], 2932)
self.assertEquals(sub_data[0][2],
'We started Universal Subtitles because we believe')
def test_basic(self):
subs = utils.get_subs("simple.srt")
self.assertEquals(len(subs), 19)
json_subs = JSONGenerator.generate(subs.to_internal())
json_subs = json.loads(json_subs)
self.assertEquals(len(json_subs), 19)
def test_self_generate(self):
parsed_subs1 = utils.get_subs("simple.dfxp")
parsed_subs2 = DFXPParser(
DFXPGenerator(parsed_subs1.subtitle_set, 'en').__unicode__())
for x1, x2 in zip([x for x in parsed_subs1.to_internal()],
[x for x in parsed_subs2.to_internal()]):
self.assertEquals(x1, x2)
def test_internal_format(self):
subs = utils.get_subs("simple.srt")
parsed = subs.to_internal()
sub_data = [x for x in parsed.subtitle_items(SRTGenerator.MAPPINGS)]
self.assertEquals(sub_data[0].start_time, 4)
self.assertEquals(sub_data[0].end_time, 2093)
self.assertEquals(sub_data[0].text,
"We started Universal Subtitles because we believe")
def test_basic(self):
subs = utils.get_subs("simple.srt")
self.assertEquals(len(subs), 19)
json_subs = JSONGenerator.generate(subs.to_internal())
json_subs = json.loads(json_subs)
self.assertEquals(len(json_subs), 19)
def test_with_information_headers(self):
# we ignore those headers for now, but at least we shouldn't fail on them
subs = utils.get_subs("with-information-header.sbv")
parsed = subs.to_internal()
sub_data = [x for x in parsed.subtitle_items()]
self.assertEquals(sub_data[0][0], 48)
self.assertEquals(sub_data[0][1], 2932)
self.assertEquals(sub_data[0][2], 'We started Universal Subtitles because we believe')
def test_generated_formatting(self):
dfxp = utils.get_subs("with-formatting.dfxp").to_internal()
subs = dfxp.subtitle_items(mappings=WEBVTTGenerator.MAPPINGS)
self.assertEqual(subs[2].text,'It has <b>bold</b> formatting' )
self.assertEqual(subs[3].text,'It has <i>italics</i> too' )
self.assertEqual(subs[4].text,'And why not <u>underline</u>' )
self.assertEqual(subs[5].text,'It has a html tag <a> should be in brackets' )
self.assertEqual(subs[6].text,'It has speaker changes >>>' )
def test_whitespace(self):
subs = utils.get_subs("pre-dmr.dfxp")
sub = subs.subtitle_set.subtitle_items(
mappings=SRTGenerator.MAPPINGS)[0]
self.assertEqual(
sub.text,
'''Last time, we began talking about\nresonance structures. And I'd like'''
)
def test_nested_with_markup(self):
dfxp = utils.get_subs("simple.dfxp").to_internal()
# FIXME: actually this is wrong, as it's nested and we should have
# the same text with underline and italics. At least we're not
# loosing any text, and that's good enough for now, should be
# fixed though.
self.assertEqual( dfxp.get_content_with_markup(dfxp.get_subtitles()[38], SRTGenerator.MAPPINGS),
'a <u>word on </u><i>nested spans</i>')
def test_generated_formatting(self):
dfxp = utils.get_subs("with-formatting.dfxp").to_internal()
subs = dfxp.subtitle_items(mappings=WEBVTTGenerator.MAPPINGS)
self.assertEqual(subs[2].text, 'It has <b>bold</b> formatting')
self.assertEqual(subs[3].text, 'It has <i>italics</i> too')
self.assertEqual(subs[4].text, 'And why not <u>underline</u>')
self.assertEqual(subs[5].text,
'It has a html tag <a> should be in brackets')
self.assertEqual(subs[6].text, 'It has speaker changes >>>')
def test_round_trip(self):
subs1 = utils.get_subs("simple.sbv")
parsed1 = subs1.to_internal()
output = unicode(SBVGenerator(parsed1))
subs2 = SBVParser(output, 'en')
parsed2 = subs2.to_internal()
self.assertEquals(len(subs1), len(subs2))
for x1, x2 in zip([x for x in parsed1.subtitle_items()], [x for x in parsed2.subtitle_items()]):
self.assertEquals(x1, x2)
def test_with_information_headers(self):
# we ignore those headers for now, but at least we shouldn't fail on them
subs = utils.get_subs("with-information-header.sbv")
parsed = subs.to_internal()
sub_data = [x for x in parsed.subtitle_items()]
self.assertEquals(sub_data[0][0], 48)
self.assertEquals(sub_data[0][1], 2932)
self.assertEquals(sub_data[0][2],
'We started Universal Subtitles because we believe')
def test_round_trip(self):
subs1 = utils.get_subs("simple.sbv")
parsed1 = subs1.to_internal()
output = unicode(SBVGenerator(parsed1))
subs2 = SBVParser(output, 'en')
parsed2 = subs2.to_internal()
self.assertEquals(len(subs1), len(subs2))
for x1, x2 in zip([x for x in parsed1.subtitle_items()],
[x for x in parsed2.subtitle_items()]):
self.assertEquals(x1, x2)
def test_nested_with_markup(self):
dfxp = utils.get_subs("simple.dfxp").to_internal()
self.assertEqual(
dfxp.get_content_with_markup(
dfxp.get_subtitles()[38],
dict(linebreaks="\r\n",
bold="<b>%s</b>",
italics="<i>%s</i>",
underline="<u>%s</u>")),
'a <u>word on <i>nested spans</i></u>')
def test_mixed_newlines(self):
# some folks will have valid srts, then edit them on an editor
# that will save line breaks on the current platform separator
# e.g. \n on unix , \r...
# make sure we normalize this stuff
subs = utils.get_subs("Untimed_text.srt")
parsed = subs.to_internal()
self.assertEqual(len(subs), 43)
# second sub should have a line break
self.assertIn('<p begin="99:59:59.000" end="99:59:59.000">I\'m gutted. <br/>Absolutely gutted.</p>',
parsed.to_xml())
def test_round_trip(self):
subs1 = utils.get_subs("simple.srt")
parsed1 = subs1.to_internal()
srt_ouput = unicode(SRTGenerator(parsed1))
subs2 = SRTParser(srt_ouput, 'en')
parsed2 = subs2.to_internal()
self.assertEquals(len(subs1), len(subs2))
for x1, x2 in zip([x for x in parsed1.subtitle_items(SRTGenerator.MAPPINGS)], \
[x for x in parsed2.subtitle_items(SRTGenerator.MAPPINGS)]):
self.assertEquals(x1, x2)
def test_round_trip(self):
subs1 = utils.get_subs("simple.srt")
parsed1 = subs1.to_internal()
srt_ouput = unicode(SRTGenerator(parsed1))
subs2 = SRTParser(srt_ouput, 'en')
parsed2 = subs2.to_internal()
self.assertEquals(len(subs1), len(subs2))
for x1, x2 in zip([x for x in parsed1.subtitle_items(SRTGenerator.MAPPINGS)], \
[x for x in parsed2.subtitle_items(SRTGenerator.MAPPINGS)]):
self.assertEquals(x1, x2)
def test_line_breaks(self):
subs = utils.get_subs("simple.sbv")
parsed = subs.to_internal()
lines = [
text
for _, _, text, _ in parsed.subtitle_items(SBVGenerator.MAPPINGS)
]
self.assertEquals(
lines[13],
'We support videos on [br]YouTube, Blip.TV, Ustream, and many more.'
)
def test_mixed_newlines(self):
# some folks will have valid srts, then edit them on an editor
# that will save line breaks on the current platform separator
# e.g. \n on unix , \r...
# make sure we normalize this stuff
subs = utils.get_subs("Untimed_text.srt")
parsed = subs.to_internal()
self.assertEqual(len(subs), 43)
# second sub should have a line break
self.assertIn(
'<p begin="99:59:59.000" end="99:59:59.000">I\'m gutted. <br/>Absolutely gutted.</p>',
parsed.to_xml())
def test_equality_ignores_whitespace(self):
subs_1 = utils.get_subs('pre-dmr.dfxp').subtitle_set
subs_2 = utils.get_subs('pre-dmr-whitespace.dfxp').subtitle_set
self.assertEqual(subs_1, subs_2)
def test_complex_formatting(self):
# this is the srt used in our selenium tests
subs = utils.get_subs("Timed_en.srt")
self.assertEqual(len(subs), 72)
def test_timing_parser(self):
parsed_subs = utils.get_subs("simple.ssa")
subs = [a for a in parsed_subs.to_internal().subtitle_items()]
self.assertEqual(subs[0][0], 40)
self.assertEqual(subs[0][1], 2930)
def test_complex_formatting(self):
# this is the srt used in our selenium tests
subs = utils.get_subs("Timed_en.srt")
self.assertEqual(len(subs), 72)
def setUp(self):
self.dfxp = utils.get_subs("multiline-italics.dfxp").to_internal()
def test_unsynced_as_generated_from_frontend(self):
dfxp = utils.get_subs("dfxp-as-front-end-no-sync.dfxp").to_internal()
for sub in dfxp.subtitle_items():
self.assertEqual(None, sub.start_time)
self.assertEqual(None, sub.end_time)
def test_basic(self):
subs = utils.get_subs("simple.srt")
self.assertEquals(len(subs), 19)
def setUp(self):
subs = utils.get_subs("simple.srt")
self.parsed = subs.to_internal()
self.sub_data = [x for x in self.parsed.subtitle_items(HTMLGenerator.MAPPINGS)]
def test_xml_literals(self):
dfxp = utils.get_subs("with-xml-literals.dfxp").to_internal()
subs = dfxp.subtitle_items()
self.assertEqual(subs[2].text, 'It has <b>bold</b> formatting')
self.assertEqual(subs[3].text, 'It has <i>italics</i> too')
self.assertEqual(subs[4].text, 'And why not <u>underline</u>')
def test_whitespace(self):
subs = utils.get_subs("pre-dmr.dfxp")
sub = subs.subtitle_set.subtitle_items(mappings=SRTGenerator.MAPPINGS)[0]
self.assertEqual(sub.text,
'''Last time, we began talking about\nresonance structures. And I'd like''')
def test_self_generate(self):
parsed_subs1 = utils.get_subs("simple.ssa")
generated = SSAParser(unicode(parsed_subs1), 'en')
for x1, x2 in zip([x for x in parsed_subs1.to_internal()], [x for x in generated.to_internal()]):
self.assertEquals(x1, x2)
def test_regions(self):
subs = utils.get_subs("regions.dfxp")
items = subs.to_internal().subtitle_items()
self.assertEquals(items[0].region, "top")
for item in items[1:]:
self.assertEquals(item.region, None)
def test_unsynced(self):
sset = utils.get_subs('i-2376.dfxp').subtitle_set
self.assertFalse(sset.fully_synced)
def test_curly_brackets(self):
subs = utils.get_subs("curly_brackets.srt")
parsed = subs.to_internal()
sub_data = list(parsed.subtitle_items(SRTGenerator.MAPPINGS))
self.assertEquals(len(sub_data), 1)
self.assertEquals(sub_data[0].text, "{ a } {{ b }} c")
def setUp(self):
self.dfxp = utils.get_subs("with-formatting.dfxp").to_internal()
self.subs = self.dfxp.subtitle_items(mappings=SRTGenerator.MAPPINGS)
def test_equality_ignores_whitespace(self):
subs_1 = utils.get_subs('pre-dmr.dfxp').subtitle_set
subs_2 = utils.get_subs('pre-dmr-whitespace.dfxp').subtitle_set
self.assertEqual(subs_1, subs_2)
def test_curly_brackets(self):
subs = utils.get_subs("curly_brackets.srt")
parsed = subs.to_internal()
sub_data = list(parsed.subtitle_items(SRTGenerator.MAPPINGS))
self.assertEquals(len(sub_data), 1)
self.assertEquals(sub_data[0].text, "{ a } {{ b }} c")
def test_basic(self):
subs = utils.get_subs("simple.dfxp")
self.assertEquals(len(subs), 76)
def test_nested_tags(self):
dfxp = utils.get_subs("simple.dfxp").to_internal()
self.assertEqual( storage.get_contents(dfxp.get_subtitles()[37]), 'nested spans')
self.assertEqual( storage.get_contents(dfxp.get_subtitles()[38]), 'a word on nested spans')
def test_unsynced(self):
sset = utils.get_subs('i-2376.dfxp').subtitle_set
self.assertFalse(sset.fully_synced)
def test_pre_drm_dfxp(self):
# tests a pretty feature rich dfpx file
dfxp = utils.get_subs("pre-drm.dfxp").to_internal()
self.assertEqual(len(dfxp), 419)
dfxp = utils.get_subs("pre-drm2.dfxp").to_internal()
self.assertEqual(len(dfxp), 19)
def test_self_generate(self):
parsed_subs1 = utils.get_subs("simple.dfxp")
parsed_subs2 = DFXPParser(DFXPGenerator(parsed_subs1.subtitle_set, 'en').__unicode__())
for x1, x2 in zip([x for x in parsed_subs1.to_internal()], [x for x in parsed_subs2.to_internal()]):
self.assertEquals(x1, x2)
def test_ampersand_escaping(self):
subs = utils.get_subs("simple.srt")
parsed = subs.to_internal()
sub_data = [x for x in parsed.subtitle_items(SRTGenerator.MAPPINGS)]
self.assertEquals(sub_data[16].text,
"such as MP4, theora, webM and & HTML 5.")
def test_nested_with_markup(self):
dfxp = utils.get_subs("simple.dfxp").to_internal()
self.assertEqual( dfxp.get_content_with_markup(dfxp.get_subtitles()[38], SRTGenerator.MAPPINGS),
'a <u>word on <i>nested spans</i></u>')
def test_comments(self):
# test that the subtitle_items() method doesn't throw an exception
# when there are comments in the DFXP. See gh-841 for details.
dfxp = utils.get_subs("comments.dfxp").to_internal()
list(dfxp.subtitle_items())
list(dfxp.subtitle_items(mappings=HTMLGenerator.MAPPINGS))
def test_update_language_code(self):
subs = utils.get_subs("simple.dfxp").to_internal()
subs.set_language('fr')
lang_attr_name = '{http://www.w3.org/XML/1998/namespace}lang'
self.assertEquals(subs._ttml.get(lang_attr_name), 'fr')
def setUp(self):
self.dfxp = utils.get_subs("with-formatting.dfxp").to_internal()
self.subs = self.dfxp.subtitle_items(mappings=SRTGenerator.MAPPINGS)
def test_unsyced_parsing(self):
subs = utils.get_subs("Untimed_text.sbv")
self.assertEquals(len(subs), 43)
def setUp(self):
self.dfxp = utils.get_subs("multiline-italics.dfxp").to_internal()
def test_ampersand_escaping(self):
subs = utils.get_subs("simple.srt")
parsed = subs.to_internal()
sub_data = [x for x in parsed.subtitle_items(SRTGenerator.MAPPINGS)]
self.assertEquals(sub_data[16].text,
"such as MP4, theora, webM and <i>&</i> HTML 5.")
