[test] Test subtitle extraction from DASH manifests

2 files changed, 477 insertions, 5 deletions

diff --git a/test/test_InfoExtractor.py b/test/test_InfoExtractor.py
index b4984b5ed..5fbea0473 100644
--- a/test/test_InfoExtractor.py
+++ b/test/test_InfoExtractor.py
@@ -949,7 +949,8 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'tbr': 5997.485,
                     'width': 1920,
                     'height': 1080,
-                }]
+                }],
+                {},
             ), (
                 # https://github.com/ytdl-org/youtube-dl/pull/14844
                 'urls_only',
@@ -1032,7 +1033,8 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'tbr': 4400,
                     'width': 1920,
                     'height': 1080,
-                }]
+                }],
+                {},
             ), (
                 # https://github.com/ytdl-org/youtube-dl/issues/20346
                 # Media considered unfragmented even though it contains
@@ -1078,18 +1080,137 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
                     'width': 360,
                     'height': 360,
                     'fps': 30,
-                }]
+                }],
+                {},
+            ), (
+                'subtitles',
+                'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
+                'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/',
+                [{
+                    "format_id": "audio=128001",
+                    "manifest_url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd",
+                    "ext": "m4a",
+                    "tbr": 128.001,
+                    "asr": 48000,
+                    "format_note": "DASH audio",
+                    "container": "m4a_dash",
+                    "vcodec": "none",
+                    "acodec": "mp4a.40.2",
+                    "url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd",
+                    "fragment_base_url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/dash/",
+                    "protocol": "http_dash_segments",
+                    "audio_ext": "m4a",
+                    "video_ext": "none",
+                    "abr": 128.001,
+                }, {
+                    "format_id": "video=100000",
+                    "manifest_url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd",
+                    "ext": "mp4",
+                    "width": 336,
+                    "height": 144,
+                    "tbr": 100,
+                    "format_note": "DASH video",
+                    "container": "mp4_dash",
+                    "vcodec": "avc1.4D401F",
+                    "acodec": "none",
+                    "url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd",
+                    "fragment_base_url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/dash/",
+                    "protocol": "http_dash_segments",
+                    "video_ext": "mp4",
+                    "audio_ext": "none",
+                    "vbr": 100,
+                }, {
+                    "format_id": "video=326000",
+                    "manifest_url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd",
+                    "ext": "mp4",
+                    "width": 562,
+                    "height": 240,
+                    "tbr": 326,
+                    "format_note": "DASH video",
+                    "container": "mp4_dash",
+                    "vcodec": "avc1.4D401F",
+                    "acodec": "none",
+                    "url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd",
+                    "fragment_base_url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/dash/",
+                    "protocol": "http_dash_segments",
+                    "video_ext": "mp4",
+                    "audio_ext": "none",
+                    "vbr": 326,
+                }, {
+                    "format_id": "video=698000",
+                    "manifest_url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd",
+                    "ext": "mp4",
+                    "width": 844,
+                    "height": 360,
+                    "tbr": 698,
+                    "format_note": "DASH video",
+                    "container": "mp4_dash",
+                    "vcodec": "avc1.4D401F",
+                    "acodec": "none",
+                    "url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd",
+                    "fragment_base_url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/dash/",
+                    "protocol": "http_dash_segments",
+                    "video_ext": "mp4",
+                    "audio_ext": "none",
+                    "vbr": 698,
+                }, {
+                    "format_id": "video=1493000",
+                    "manifest_url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd",
+                    "ext": "mp4",
+                    "width": 1126,
+                    "height": 480,
+                    "tbr": 1493,
+                    "format_note": "DASH video",
+                    "container": "mp4_dash",
+                    "vcodec": "avc1.4D401F",
+                    "acodec": "none",
+                    "url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd",
+                    "fragment_base_url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/dash/",
+                    "protocol": "http_dash_segments",
+                    "video_ext": "mp4",
+                    "audio_ext": "none",
+                    "vbr": 1493,
+                }, {
+                    "format_id": "video=4482000",
+                    "manifest_url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd",
+                    "ext": "mp4",
+                    "width": 1688,
+                    "height": 720,
+                    "tbr": 4482,
+                    "format_note": "DASH video",
+                    "container": "mp4_dash",
+                    "vcodec": "avc1.4D401F",
+                    "acodec": "none",
+                    "url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd",
+                    "fragment_base_url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/dash/",
+                    "protocol": "http_dash_segments",
+                    "video_ext": "mp4",
+                    "audio_ext": "none",
+                    "vbr": 4482,
+                }],
+                {
+                    "en": [
+                        {
+                            "ext": "mp4",
+                            "manifest_url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd",
+                            "url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd",
+                            "fragment_base_url": "https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/dash/",
+                            "protocol": "http_dash_segments",
+                        }
+                    ]
+                },
             )
         ]
 
-        for mpd_file, mpd_url, mpd_base_url, expected_formats in _TEST_CASES:
+        for mpd_file, mpd_url, mpd_base_url, expected_formats, expected_subtitles in _TEST_CASES:
             with io.open('./test/testdata/mpd/%s.mpd' % mpd_file,
                          mode='r', encoding='utf-8') as f:
-                formats = self.ie._parse_mpd_formats(
+                formats, subtitles = self.ie._parse_mpd_formats_and_subtitles(
                     compat_etree_fromstring(f.read().encode('utf-8')),
                     mpd_base_url=mpd_base_url, mpd_url=mpd_url)
                 self.ie._sort_formats(formats)
                 expect_value(self, formats, expected_formats, None)
+                expect_value(self, subtitles, expected_subtitles, None)
 
     def test_parse_f4m_formats(self):
         _TEST_CASES = [
diff --git a/test/testdata/mpd/subtitles.mpd b/test/testdata/mpd/subtitles.mpd
new file mode 100644
index 000000000..6f948adba
--- /dev/null
+++ b/test/testdata/mpd/subtitles.mpd
@@ -0,0 +1,351 @@
+<?xml version="1.0" encoding="utf-8"?>
+<!-- Created with Unified Streaming Platform (version=1.10.18-20255) -->
+<MPD
+  xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+  xmlns="urn:mpeg:dash:schema:mpd:2011"
+  xsi:schemaLocation="urn:mpeg:dash:schema:mpd:2011 http://standards.iso.org/ittf/PubliclyAvailableStandards/MPEG-DASH_schema_files/DASH-MPD.xsd"
+  type="static"
+  mediaPresentationDuration="PT14M48S"
+  maxSegmentDuration="PT1M"
+  minBufferTime="PT10S"
+  profiles="urn:mpeg:dash:profile:isoff-live:2011">
+  <Period
+    id="1"
+    duration="PT14M48S">
+    <BaseURL>dash/</BaseURL>
+    <AdaptationSet
+      id="1"
+      group="1"
+      contentType="audio"
+      segmentAlignment="true"
+      audioSamplingRate="48000"
+      mimeType="audio/mp4"
+      codecs="mp4a.40.2"
+      startWithSAP="1">
+      <AudioChannelConfiguration
+        schemeIdUri="urn:mpeg:dash:23003:3:audio_channel_configuration:2011"
+        value="2" />
+      <Role schemeIdUri="urn:mpeg:dash:role:2011" value="main" />
+      <SegmentTemplate
+        timescale="48000"
+        initialization="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$.dash"
+        media="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$-$Time$.dash">
+        <SegmentTimeline>
+          <S t="0" d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="96256" r="2" />
+          <S d="95232" />
+          <S d="3584" />
+        </SegmentTimeline>
+      </SegmentTemplate>
+      <Representation
+        id="audio=128001"
+        bandwidth="128001">
+      </Representation>
+    </AdaptationSet>
+    <AdaptationSet
+      id="2"
+      group="3"
+      contentType="text"
+      lang="en"
+      mimeType="application/mp4"
+      codecs="stpp"
+      startWithSAP="1">
+      <Role schemeIdUri="urn:mpeg:dash:role:2011" value="subtitle" />
+      <SegmentTemplate
+        timescale="1000"
+        initialization="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$.dash"
+        media="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$-$Time$.dash">
+        <SegmentTimeline>
+          <S t="0" d="60000" r="9" />
+          <S d="24000" />
+        </SegmentTimeline>
+      </SegmentTemplate>
+      <Representation
+        id="textstream_eng=1000"
+        bandwidth="1000">
+      </Representation>
+    </AdaptationSet>
+    <AdaptationSet
+      id="3"
+      group="2"
+      contentType="video"
+      par="960:409"
+      minBandwidth="100000"
+      maxBandwidth="4482000"
+      maxWidth="1689"
+      maxHeight="720"
+      segmentAlignment="true"
+      mimeType="video/mp4"
+      codecs="avc1.4D401F"
+      startWithSAP="1">
+      <Role schemeIdUri="urn:mpeg:dash:role:2011" value="main" />
+      <SegmentTemplate
+        timescale="12288"
+        initialization="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$.dash"
+        media="3144-kZT4LWMQw6Rh7Kpd-$RepresentationID$-$Time$.dash">
+        <SegmentTimeline>
+          <S t="0" d="24576" r="443" />
+        </SegmentTimeline>
+      </SegmentTemplate>
+      <Representation
+        id="video=100000"
+        bandwidth="100000"
+        width="336"
+        height="144"
+        sar="2880:2863"
+        scanType="progressive">
+      </Representation>
+      <Representation
+        id="video=326000"
+        bandwidth="326000"
+        width="562"
+        height="240"
+        sar="115200:114929"
+        scanType="progressive">
+      </Representation>
+      <Representation
+        id="video=698000"
+        bandwidth="698000"
+        width="844"
+        height="360"
+        sar="86400:86299"
+        scanType="progressive">
+      </Representation>
+      <Representation
+        id="video=1493000"
+        bandwidth="1493000"
+        width="1126"
+        height="480"
+        sar="230400:230267"
+        scanType="progressive">
+      </Representation>
+      <Representation
+        id="video=4482000"
+        bandwidth="4482000"
+        width="1688"
+        height="720"
+        sar="86400:86299"
+        scanType="progressive">
+      </Representation>
+    </AdaptationSet>
+  </Period>
+</MPD>