def test_no_space_after_colon_in_metadata_section():
# see issue #14
ref = SSAFile.from_string(AEGISUB_PROJECT_GARBAGE_FILE)
subs = SSAFile.from_string(AEGISUB_PROJECT_GARBAGE_FILE_WITHOUT_SPACE_AFTER_COLON)
assert ref.equals(subs)
assert ref.aegisub_project == subs.aegisub_project
def test_simple_parsing():
test_input1 = "[123][456] Line 1"
subs1 = SSAFile.from_string(test_input1)
assert len(subs1) == 1
assert subs1[0] == SSAEvent(start=make_time(ms=12300),
end=make_time(ms=45600),
text="Line 1")
test_input2 = "[123][456] / Line 1| Line 2/2"
subs2 = SSAFile.from_string(test_input2)
assert len(subs2) == 1
assert subs2[0] == SSAEvent(start=make_time(ms=12300),
end=make_time(ms=45600),
text="{\i1}Line 1{\i0}\\NLine2/2")
test_input3 = dedent("""
[123][456] Line 1
[321][456] / Line 2| Line 3
(123)(456)This line should not be parsed
This line should also not be parsed
[789][1234] /Line 4""")
subs3 = SSAFile.from_string(test_input3)
assert len(subs3) == 3
assert subs3[0] == SSAEvent(start=make_time(ms=12300),
end=make_time(ms=45600),
text="Line 1")
assert subs3[1] == SSAEvent(start=make_time(ms=32100),
end=make_time(ms=45600),
text="{\i1}Line 2{\i0}\\NLine 3")
assert subs3[2] == SSAEvent(start=make_time(ms=78900),
end=make_time(ms=123400),
text="{\i1}Line 4{\i0}")
def test_simple_read():
ref = build_ref()
subs1 = SSAFile.from_string(SIMPLE_ASS_REF)
subs2 = SSAFile.from_string(SIMPLE_SSA_REF)
assert ref.equals(subs1)
assert ref.equals(subs2)
def test_simple_read():
ref = build_ref()
subs1 = SSAFile.from_string(SIMPLE_ASS_REF)
subs2 = SSAFile.from_string(SIMPLE_SSA_REF)
assert ref.equals(subs1)
assert ref.equals(subs2)
def test_keep_unknown_html_tags():
# see issue #26
text = dedent("""\
1
00:00:10,500 --> 00:00:13,000
<i>Elephant's <sub>Little</sub> Dream</i>
2
00:00:15,000 --> 00:00:18,000
<font color="cyan">At the left we can see...</font>
""")
ref_default = SSAFile()
ref_default.append(SSAEvent(start=make_time(s=10.5), end=make_time(s=13), text="{\\i1}Elephant's Little Dream{\\i0}"))
ref_default.append(SSAEvent(start=make_time(s=15), end=make_time(s=18), text="At the left we can see..."))
ref_keep = SSAFile()
ref_keep.append(SSAEvent(start=make_time(s=10.5), end=make_time(s=13), text="{\\i1}Elephant's <sub>Little</sub> Dream{\\i0}"))
ref_keep.append(SSAEvent(start=make_time(s=15), end=make_time(s=18), text="<font color=\"cyan\">At the left we can see...</font>"))
subs_default = SSAFile.from_string(text)
subs_keep = SSAFile.from_string(text, keep_unknown_html_tags=True)
assert subs_default.equals(ref_default)
assert subs_keep.equals(ref_keep)
assert subs_keep.to_string("srt") == ref_keep.to_string("srt")
def test_read_position_styling():
"""position is ignored, italic is converted, color is ignored"""
text = dedent("""\
1
00:00:10,500 --> 00:00:13,000 X1:63 X2:223 Y1:43 Y2:58
<i>Elephant's Dream</i>
2
00:00:15,000 --> 00:00:18,000 X1:53 X2:303 Y1:438 Y2:453
<font color="cyan">At the left we can see...</font>
""")
ref = SSAFile()
ref.append(
SSAEvent(start=make_time(s=10.5),
end=make_time(s=13),
text="{\\i1}Elephant's Dream{\\i0}"))
ref.append(
SSAEvent(start=make_time(s=15),
end=make_time(s=18),
text="At the left we can see..."))
subs = SSAFile.from_string(text)
assert subs.equals(ref)
def test_read_complex():
# regression test for #30
text = dedent("""\
WEBVTT
X-TIMESTAMP-MAP=LOCAL:00:00:00.000,MPEGTS:0
00:50.099 --> 00:53.299 line:85% align:middle
Cuidem do seu grupo.
Cuidem de suas fileiras.
01:54.255 --> 01:55.455 line:85% align:middle
Parem!
01:58.155 --> 01:59.555 line:85% align:middle
E, parem!
""")
ref = SSAFile()
ref.append(
SSAEvent(start=make_time(s=50, ms=99),
end=make_time(s=53, ms=299),
text=r"Cuidem do seu grupo.\NCuidem de suas fileiras."))
ref.append(
SSAEvent(start=make_time(m=1, s=54, ms=255),
end=make_time(m=1, s=55, ms=455),
text="Parem!"))
ref.append(
SSAEvent(start=make_time(m=1, s=58, ms=155),
end=make_time(m=1, s=59, ms=555),
text="E, parem!"))
subs = SSAFile.from_string(text)
assert subs.equals(ref)
def test_empty_subtitles():
# regression test for issue #11
text = dedent("""
392
00:29:27,46 --> 00:29:29,83
I'm Liza Minnelli..
393
00:00:00,00 --> 00:00:00,00
394
00:00:00,00 --> 00:00:00,00
""")
ref = SSAFile()
ref.append(
SSAEvent(start=make_time(m=29, s=27, ms=460),
end=make_time(m=29, s=29, ms=830),
text="I'm Liza Minnelli.."))
ref.append(SSAEvent(start=0, end=0, text=""))
ref.append(SSAEvent(start=0, end=0, text=""))
subs = SSAFile.from_string(text)
assert subs.equals(ref)
def test_negative_timestamp_read():
ref = build_ref()
subs = SSAFile.from_string(NEGATIVE_TIMESTAMP_ASS_REF)
# negative timestamp is read correctly
assert subs[0].start == -make_time(1, 59, 54, 930)
# negative times are flushed to zero on output
assert ref.to_string("ass") == subs.to_string("ass")
def get_empty_sub():
text = '''
1
00:00:00,000 --> 00:00:05,000
An example SubRip file.
'''
subs = SSAFile.from_string(text)
subs.__delitem__(0)
return subs
def test_extra_whitespace_parsing():
f = dedent("""\
{ 0 } { 0 } 1000.0
{ 10 }{ 20} Hello!
""")
subs = SSAFile.from_string(f)
assert subs[0] == SSAEvent(start=10, end=20, text="Hello!")
def test_extra_whitespace_parsing():
f = dedent("""\
{ 0 } { 0 } 1000.0
{ 10 }{ 20} Hello!
""")
subs = SSAFile.from_string(f)
assert subs[0] == SSAEvent(start=10, end=20, text="Hello!")
def test_aegisub_project_garbage():
subs = SSAFile.from_string(AEGISUB_PROJECT_GARBAGE_FILE)
garbage_section = dedent("""
[Aegisub Project Garbage]
Last Style Storage: Default
Video File: ?dummy:23.976000:40000:640:480:47:163:254:
Video AR Value: 1.333333
Video Zoom Percent: 0.500000
Active Line: 2""")
assert garbage_section in subs.to_string("ass")
def test_aegisub_project_garbage():
subs = SSAFile.from_string(AEGISUB_PROJECT_GARBAGE_FILE)
garbage_section = dedent("""
[Aegisub Project Garbage]
Last Style Storage: Default
Video File: ?dummy:23.976000:40000:640:480:47:163:254:
Video AR Value: 1.333333
Video Zoom Percent: 0.500000
Active Line: 2""")
assert garbage_section in subs.to_string("ass")
def test_tags_parsing():
f1 = "{10}{20}{Y:i,u}Hello!"
subs1 = SSAFile.from_string(f1, fps=1000)
assert subs1[0].text == "{\\i1\\u1}Hello!"
f2 = "{10}{20}Hello, {f:Comic Sans MS}world!"
subs2 = SSAFile.from_string(f2, fps=1000)
assert subs2[0].text == r"Hello, {\fnComic Sans MS}world!"
# the C tag is not supported, unsupported tags are copied verbatim
f3 = "{10}{20}Hello, {c:$0000FF}world!"
subs3 = SSAFile.from_string(f3, fps=1000)
assert subs3[0].text == r"Hello, {c:$0000FF}world!"
f4 = "{10}{20}Hello, {P:100,200}world!"
subs4 = SSAFile.from_string(f4, fps=1000)
assert subs4[0].text == r"Hello, {\pos(100,200)}world!"
f5 = "{10}{20}Hello, {s:72}world!"
subs5 = SSAFile.from_string(f5, fps=1000)
assert subs5[0].text == r"Hello, {\fs72}world!"
def test_simple_read():
text = dedent("""\
00:00:00:ten--chars
00:01:00:ten--chars-ten-chars
""")
#calculate endtime from starttime + 500 miliseconds + 67 miliseconds per each character (15 chars per second)
ref = SSAFile()
ref.append(SSAEvent(start=0, end=make_time(ms=1840), text="ten--chars"))
ref.append(SSAEvent(start=make_time(m=1), end=make_time(ms=62510), text="ten--chars-ten-chars"))
subs = SSAFile.from_string(text)
assert subs.equals(ref)
def test_tags_parsing():
f1 = "{10}{20}{Y:i,u}Hello!"
subs1 = SSAFile.from_string(f1, fps=1000)
assert subs1[0].text == "{\\i1\\u1}Hello!"
f2 = "{10}{20}Hello, {f:Comic Sans MS}world!"
subs2 = SSAFile.from_string(f2, fps=1000)
assert subs2[0].text == r"Hello, {\fnComic Sans MS}world!"
# the C tag is not supported, unsupported tags are copied verbatim
f3 = "{10}{20}Hello, {c:$0000FF}world!"
subs3 = SSAFile.from_string(f3, fps=1000)
assert subs3[0].text == r"Hello, {c:$0000FF}world!"
f4 = "{10}{20}Hello, {P:100,200}world!"
subs4 = SSAFile.from_string(f4, fps=1000)
assert subs4[0].text == r"Hello, {\pos(100,200)}world!"
f5 = "{10}{20}Hello, {s:72}world!"
subs5 = SSAFile.from_string(f5, fps=1000)
assert subs5[0].text == r"Hello, {\fs72}world!"
def test_overlapping_read():
# see issue #35
text = dedent("""\
00:00:12:I ... this is some long text ... ... this is some long text ...
00:00:14:observing ... ... this is some long text ... ... this is some long text ...
00:00:18:and ... ... this is some long text ... ... this is some long text ...
00:00:22:You ... ... this is some long text ... ... this is some long text ...
""")
subs = SSAFile.from_string(text)
assert subs[0].start == make_time(s=12)
assert subs[0].end == subs[1].start == make_time(s=14)
assert subs[1].end == subs[2].start == make_time(s=18)
assert subs[2].end == subs[3].start == make_time(s=22)
def test_simple_parsing():
test_input1 = "[123][456] Line 1"
subs1 = SSAFile.from_string(test_input1)
assert len(subs1) == 1
assert subs1[0] == SSAEvent(start=make_time(ms=12300), end=make_time(ms=45600), text="Line 1")
test_input2 = "[123][456] / Line 1| Line 2/2"
subs2 = SSAFile.from_string(test_input2)
assert len(subs2) == 1
assert subs2[0] == SSAEvent(start=make_time(ms=12300), end=make_time(ms=45600), text="{\i1}Line 1{\i0}\\NLine2/2")
test_input3 = dedent("""
[123][456] Line 1
[321][456] / Line 2| Line 3
(123)(456)This line should not be parsed
This line should also not be parsed
[789][1234] /Line 4""")
subs3 = SSAFile.from_string(test_input3)
assert len(subs3) == 3
assert subs3[0] == SSAEvent(start=make_time(ms=12300), end=make_time(ms=45600), text="Line 1")
assert subs3[1] == SSAEvent(start=make_time(ms=32100), end=make_time(ms=45600), text="{\i1}Line 2{\i0}\\NLine 3")
assert subs3[2] == SSAEvent(start=make_time(ms=78900), end=make_time(ms=123400), text="{\i1}Line 4{\i0}")
def test_read_bad_tags():
"""missing opening/closing tag, bad nesting, extra whitespace"""
text = dedent("""\
1
00:00:10,500 --> 00:00:13,000
< u><i><font color="red" >Elephant's < s>Dream< / i > Is Long</s> And Badly Nested</xyz>
""")
ref = SSAFile()
ref.append(SSAEvent(start=make_time(s=10.5), end=make_time(s=13), text="{\\u1}{\\i1}Elephant's {\\s1}Dream{\\i0} Is Long{\\s0} And Badly Nested"))
subs = SSAFile.from_string(text)
assert subs.equals(ref)
def test_read_bad_tags():
"""missing opening/closing tag, bad nesting, extra whitespace"""
text = dedent("""\
1
00:00:10,500 --> 00:00:13,000
< u><i><font color="red" >Elephant's < s>Dream< / i > Is Long</s> And Badly Nested</xyz>
""")
ref = SSAFile()
ref.append(SSAEvent(start=make_time(s=10.5), end=make_time(s=13), text="{\\u1}{\\i1}Elephant's {\\s1}Dream{\\i0} Is Long{\\s0} And Badly Nested"))
subs = SSAFile.from_string(text)
assert subs.equals(ref)
def test_write_read():
subs = SSAFile()
e1 = SSAEvent(text="Hello, world!")
e2 = SSAEvent(text="The other subtitle.\\NWith two lines.", style="custom style")
s1 = SSAStyle(italic=True, primarycolor=Color(r=255, g=0, b=0, a=0))
subs.append(e1)
subs.append(e2)
subs.styles["custom style"] = s1
json_text = subs.to_string("json")
subs2 = SSAFile.from_string(json_text, "json")
assert subs2.equals(subs)
def test_write_read():
subs = SSAFile()
e1 = SSAEvent(text="Hello, world!")
e2 = SSAEvent(text="The other subtitle.\\NWith two lines.",
style="custom style")
s1 = SSAStyle(italic=True, primarycolor=Color(r=255, g=0, b=0, a=0))
subs.append(e1)
subs.append(e2)
subs.styles["custom style"] = s1
json_text = subs.to_string("json")
subs2 = SSAFile.from_string(json_text, "json")
assert subs2.equals(subs)
def test_read_malformed():
"""no line number, no empty line, leading whitespace, bad timestamp format"""
text = dedent("""\
00:00:00.000 ->00:01:00.000
An example subtitle.
0:01:00,00 --> 0:02:00,00
Subtitle number
two.
""")
ref = SSAFile()
ref.append(SSAEvent(start=0, end=make_time(m=1), text="An example subtitle."))
ref.append(SSAEvent(start=make_time(m=1), end=make_time(m=2), text="Subtitle number\\Ntwo."))
subs = SSAFile.from_string(text)
assert subs.equals(ref)
def test_parser_skipping_lines():
f = dedent("""\
Ook!
{0}{0}23.976
> Hi!
{10}{20}Hello!
1
00:00:00,000 --> 00:00:05,000
When editing their SRT files,
some people get so careless
as to paste them in their MicroDVD files!
""")
subs = SSAFile.from_string(f, format_="microdvd")
assert len(subs) == 1
assert subs[0].text == "Hello!"
def test_parser_skipping_lines():
f = dedent("""\
Ook!
{0}{0}23.976
> Hi!
{10}{20}Hello!
1
00:00:00,000 --> 00:00:05,000
When editing their SRT files,
some people get so careless
as to paste them in their MicroDVD files!
""")
subs = SSAFile.from_string(f, format_="microdvd")
assert len(subs) == 1
assert subs[0].text == "Hello!"
def test_read_malformed():
"""no line number, no empty line, leading whitespace, bad timestamp format"""
text = dedent("""\
00:00:00.000 ->00:01:00.000
An example subtitle.
0:01:00,00 --> 0:02:00,00
Subtitle number
two.
""")
ref = SSAFile()
ref.append(SSAEvent(start=0, end=make_time(m=1), text="An example subtitle."))
ref.append(SSAEvent(start=make_time(m=1), end=make_time(m=2), text="Subtitle number\\Ntwo."))
subs = SSAFile.from_string(text)
assert subs.equals(ref)
def test_simple_read():
text = dedent("""\
1
00:00:00,000 --> 00:01:00,000
An example subtitle.
2
00:01:00,000 --> 00:02:00,000
Subtitle number
two.
""")
ref = SSAFile()
ref.append(SSAEvent(start=0, end=make_time(m=1), text="An example subtitle."))
ref.append(SSAEvent(start=make_time(m=1), end=make_time(m=2), text="Subtitle number\\Ntwo."))
subs = SSAFile.from_string(text)
assert subs.equals(ref)
def test_simple_read():
text = dedent("""\
1
00:00:00,000 --> 00:01:00,000
An example subtitle.
2
00:01:00,000 --> 00:02:00,000
Subtitle number
two.
""")
ref = SSAFile()
ref.append(SSAEvent(start=0, end=make_time(m=1), text="An example subtitle."))
ref.append(SSAEvent(start=make_time(m=1), end=make_time(m=2), text="Subtitle number\\Ntwo."))
subs = SSAFile.from_string(text)
assert subs.equals(ref)
def test_read_position_styling():
"""position is ignored, italic is converted, color is ignored"""
text = dedent("""\
1
00:00:10,500 --> 00:00:13,000 X1:63 X2:223 Y1:43 Y2:58
<i>Elephant's Dream</i>
2
00:00:15,000 --> 00:00:18,000 X1:53 X2:303 Y1:438 Y2:453
<font color="cyan">At the left we can see...</font>
""")
ref = SSAFile()
ref.append(SSAEvent(start=make_time(s=10.5), end=make_time(s=13), text="{\\i1}Elephant's Dream{\\i0}"))
ref.append(SSAEvent(start=make_time(s=15), end=make_time(s=18), text="At the left we can see..."))
subs = SSAFile.from_string(text)
assert subs.equals(ref)
def test_framerate_inference():
fps = 1000.0
has_fps = dedent("""\
{0}{0}1000.0
{10}{20}Hello!
""")
no_fps = dedent("""\
{10}{20}Hello!
""")
ignored_fps = dedent("""\
{0}{0}23.976
{10}{20}Hello!
""")
illegal_fps = dedent("""\
{0}{0}-23.976
{10}{20}Hello!
""")
subs1 = SSAFile.from_string(has_fps)
assert subs1.fps == fps
assert len(subs1) == 1
assert subs1[0] == SSAEvent(start=10, end=20, text="Hello!")
subs2 = SSAFile.from_string(no_fps, fps=fps)
assert subs2.fps == fps
assert len(subs2) == 1
assert subs2[0] == SSAEvent(start=10, end=20, text="Hello!")
# fps argument takes preference over what the file says, first line is kept
subs3 = SSAFile.from_string(ignored_fps, fps=fps)
assert subs3.fps == fps
assert len(subs3) == 2
assert subs3[0] == SSAEvent(start=0, end=0, text="23.976")
assert subs3[1] == SSAEvent(start=10, end=20, text="Hello!")
with assert_raises(UnknownFPSError):
SSAFile.from_string(no_fps)
with assert_raises(ValueError):
SSAFile.from_string(illegal_fps)
def test_framerate_inference():
fps = 1000.0
has_fps = dedent("""\
{0}{0}1000.0
{10}{20}Hello!
""")
no_fps = dedent("""\
{10}{20}Hello!
""")
ignored_fps = dedent("""\
{0}{0}23.976
{10}{20}Hello!
""")
illegal_fps = dedent("""\
{0}{0}-23.976
{10}{20}Hello!
""")
subs1 = SSAFile.from_string(has_fps)
assert subs1.fps == fps
assert len(subs1) == 1
assert subs1[0] == SSAEvent(start=10, end=20, text="Hello!")
subs2 = SSAFile.from_string(no_fps, fps=fps)
assert subs2.fps == fps
assert len(subs2) == 1
assert subs2[0] == SSAEvent(start=10, end=20, text="Hello!")
# fps argument takes preference over what the file says, first line is kept
subs3 = SSAFile.from_string(ignored_fps, fps=fps)
assert subs3.fps == fps
assert len(subs3) == 2
assert subs3[0] == SSAEvent(start=0, end=0, text="23.976")
assert subs3[1] == SSAEvent(start=10, end=20, text="Hello!")
with assert_raises(UnknownFPSError):
SSAFile.from_string(no_fps)
with assert_raises(ValueError):
SSAFile.from_string(illegal_fps)
def test_empty_subtitles():
# regression test for issue #11
text = dedent("""
392
00:29:27,46 --> 00:29:29,83
I'm Liza Minnelli..
393
00:00:00,00 --> 00:00:00,00
394
00:00:00,00 --> 00:00:00,00
""")
ref = SSAFile()
ref.append(SSAEvent(start=make_time(m=29, s=27, ms=460), end=make_time(m=29, s=29, ms=830), text="I'm Liza Minnelli.."))
ref.append(SSAEvent(start=0, end=0, text=""))
ref.append(SSAEvent(start=0, end=0, text=""))
subs = SSAFile.from_string(text)
assert subs.equals(ref)
def test_newlines_parsing():
f = "{10}{20} So|Many||Newlines ||| "
subs = SSAFile.from_string(f, fps=1000)
assert subs[0].text == r"So\NMany\N\NNewlines \N\N\N"
def test_hex_color_in_ssa():
# see issue #32
subs = SSAFile.from_string(HEX_COLOR_IN_SSA)
style = subs.styles["Default"]
assert style.primarycolor == Color(r=0xff, g=0xff, b=0xff)
assert style.secondarycolor == Color(r=0xff, g=0xff, b=0x00)
def test_newlines_parsing():
f = "{10}{20} So|Many||Newlines ||| "
subs = SSAFile.from_string(f, fps=1000)
assert subs[0].text == r"So\NMany\N\NNewlines \N\N\N"
