aboutsummaryrefslogtreecommitdiff
path: root/test/test_utils.py
diff options
context:
space:
mode:
authorYen Chi Hsuan <yan12125@gmail.com>2017-09-16 12:18:38 +0800
committerYen Chi Hsuan <yan12125@gmail.com>2017-09-16 12:18:38 +0800
commit3869028ffb6be6ab719e5cf1004276dfdfd1216d (patch)
tree86301ec756a57fea9248042be358a42b6af6d7c2 /test/test_utils.py
parent68d43a61b552007a718894967b869c0f1d8ff00f (diff)
[utils] Use bytes-like objects in dfxp2srt
This fixes handling of non-UTF8 TTML subtitles Closes #14191
Diffstat (limited to 'test/test_utils.py')
-rw-r--r--test/test_utils.py26
1 files changed, 23 insertions, 3 deletions
diff --git a/test/test_utils.py b/test/test_utils.py
index e50f3764e..efa73d0f4 100644
--- a/test/test_utils.py
+++ b/test/test_utils.py
@@ -1064,7 +1064,7 @@ ffmpeg version 2.4.4 Copyright (c) 2000-2014 the FFmpeg ...'''), '2.4.4')
<p begin="3" dur="-1">Ignored, three</p>
</div>
</body>
- </tt>'''
+ </tt>'''.encode('utf-8')
srt_data = '''1
00:00:00,000 --> 00:00:01,000
The following line contains Chinese characters and special symbols
@@ -1089,7 +1089,7 @@ Line
<p begin="0" end="1">The first line</p>
</div>
</body>
- </tt>'''
+ </tt>'''.encode('utf-8')
srt_data = '''1
00:00:00,000 --> 00:00:01,000
The first line
@@ -1115,7 +1115,7 @@ The first line
<p style="s1" tts:textDecoration="underline" begin="00:00:09.56" id="p2" end="00:00:12.36"><span style="s2" tts:color="lime">inner<br /> </span>style</p>
</div>
</body>
-</tt>'''
+</tt>'''.encode('utf-8')
srt_data = '''1
00:00:02,080 --> 00:00:05,839
<font color="white" face="sansSerif" size="16">default style<font color="red">custom style</font></font>
@@ -1138,6 +1138,26 @@ part 3</font></u>
'''
self.assertEqual(dfxp2srt(dfxp_data_with_style), srt_data)
+ dfxp_data_non_utf8 = '''<?xml version="1.0" encoding="UTF-16"?>
+ <tt xmlns="http://www.w3.org/ns/ttml" xml:lang="en" xmlns:tts="http://www.w3.org/ns/ttml#parameter">
+ <body>
+ <div xml:lang="en">
+ <p begin="0" end="1">Line 1</p>
+ <p begin="1" end="2">第二行</p>
+ </div>
+ </body>
+ </tt>'''.encode('utf-16')
+ srt_data = '''1
+00:00:00,000 --> 00:00:01,000
+Line 1
+
+2
+00:00:01,000 --> 00:00:02,000
+第二行
+
+'''
+ self.assertEqual(dfxp2srt(dfxp_data_non_utf8), srt_data)
+
def test_cli_option(self):
self.assertEqual(cli_option({'proxy': '127.0.0.1:3128'}, '--proxy', 'proxy'), ['--proxy', '127.0.0.1:3128'])
self.assertEqual(cli_option({'proxy': None}, '--proxy', 'proxy'), [])