Adding captions module for videos.

TODO.md

@@ -14,3 +14,5 @@ Code TODO
 =========
 1. Example plugin based off videos plugin
     1. Check that videos can be removed or renamed
+    1. Plugin has support for systemd so it can start it's own service
+    1. Plugin has support for cronjobs

requirements.txt

@@ -6,5 +6,4 @@ Jinja2>=2.10.1
 mock>=3.0.5
 psycopg2-binary>=2.8.3
 pyyaml>=5.1.2
-youtube-dl>=2019.8.13
 pytest>=5.2.1

test/example.en.vtt

@@ -0,0 +1,48 @@
+WEBVTT
+Kind: captions
+Language: en
+
+00:00:00.000 --> 00:00:05.269 align:start position:0%
+ 
+okay<00:00:01.310><c> welcome</c><00:00:02.310><c> to</c><00:00:02.429><c> this</c><00:00:02.550><c> session</c><00:00:04.130><c> this</c><00:00:05.130><c> is</c>
+
+00:00:05.269 --> 00:00:05.279 align:start position:0%
+okay welcome to this session this is
+ 
+
+00:00:05.279 --> 00:00:07.760 align:start position:0%
+okay welcome to this session this is
+called<00:00:05.879><c> the</c><00:00:05.970><c> kinetic</c><00:00:06.420><c> bunny</c><00:00:06.690><c> need</c><00:00:07.319><c> to</c><00:00:07.529><c> meet</c>
+
+00:00:07.760 --> 00:00:07.770 align:start position:0%
+called the kinetic bunny need to meet
+ 
+
+00:00:07.770 --> 00:00:11.450 align:start position:0%
+called the kinetic bunny need to meet
+the<00:00:07.890><c> virtual</c><00:00:08.280><c> bonnie</c><00:00:08.519><c> emilio</c><00:00:09.380><c> stop</c><00:00:10.380><c> this</c><00:00:11.340><c> is</c>
+
+00:00:11.450 --> 00:00:11.460 align:start position:0%
+the virtual bonnie emilio stop this is
+ 
+
+00:00:11.460 --> 00:00:15.410 align:start position:0%
+the virtual bonnie emilio stop this is
+jana<00:00:11.639><c> car</c><00:00:11.880><c> who</c><00:00:13.700><c> just</c><00:00:14.700><c> to</c><00:00:14.759><c> give</c><00:00:14.940><c> a</c><00:00:14.969><c> little</c><00:00:15.030><c> bit</c>
+
+00:00:15.410 --> 00:00:15.420 align:start position:0%
+jana car who just to give a little bit
+ 
+
+00:00:15.420 --> 00:00:18.859 align:start position:0%
+jana car who just to give a little bit
+of<00:00:15.529><c> background</c><00:00:16.529><c> information</c><00:00:17.390><c> we</c><00:00:18.390><c> come</c><00:00:18.630><c> from</c><00:00:18.750><c> a</c>
+
+00:00:18.859 --> 00:00:18.869 align:start position:0%
+of background information we come from a
+ 
+
+00:00:18.869 --> 00:00:21.109 align:start position:0%
+of background information we come from a
+company<00:00:19.109><c> called</c><00:00:19.199><c> le</c><00:00:19.529><c> code</c><00:00:19.740><c> from</c><00:00:20.550><c> finland</c><00:00:20.939><c> and</c>
+

wrolpi/plugins/example_plugin/requirements.txt

@@ -0,0 +1 @@
+# Add your pip requirements here

wrolpi/plugins/videos/api.py

@@ -71,6 +71,7 @@ def json_statuses_streamer(func):
         '{"success": "stream-complete"}\n'
     """
 
+    @wraps(func)
     def wrap(*a, **kw):
         yield from (json.dumps({'status': i}) + '\n' for i in func(*a, **kw))
         yield json.dumps({'success': 'stream-complete'}) + '\n'

wrolpi/plugins/videos/captions.py

@@ -0,0 +1,20 @@
+#! /usr/bin/env python3
+from typing import Generator
+
+import webvtt
+
+
+def get_caption_text(vtt_path: str) -> Generator:
+    for caption in webvtt.read(vtt_path):
+        text = str(caption.text).strip()
+        yield text
+
+
+def get_unique_caption_lines(vtt_path: str) -> Generator:
+    last_line = None
+    for text in get_caption_text(vtt_path):
+        for line in text.split('\n'):
+            if line and line != last_line:
+                last_line = line
+                yield line
+

wrolpi/plugins/videos/requirements.txt

@@ -0,0 +1,2 @@
+youtube-dl>=2019.8.13
+webvtt-py==0.4.2

wrolpi/plugins/videos/test/test_captions.py

@@ -0,0 +1,30 @@
+import unittest
+
+from wrolpi.plugins.videos import captions
+
+
+class TestCaption(unittest.TestCase):
+
+    def test_example_en_vtt(self):
+        vtt_path = 'test/example.en.vtt'
+
+        expected = ['okay welcome to this session this is',
+                    'okay welcome to this session this is',
+                    'okay welcome to this session this is\ncalled the kinetic bunny need to meet',
+                    'called the kinetic bunny need to meet',
+                    'called the kinetic bunny need to meet\nthe virtual bonnie emilio stop this is',
+                    'the virtual bonnie emilio stop this is',
+                    'the virtual bonnie emilio stop this is\njana car who just to give a little bit',
+                    'jana car who just to give a little bit',
+                    'jana car who just to give a little bit\nof background information we come from a',
+                    'of background information we come from a',
+                    'of background information we come from a\ncompany called le code from finland and']
+        self.assertEqual(list(captions.get_caption_text(vtt_path)), expected)
+
+        expected = ['okay welcome to this session this is',
+                    'called the kinetic bunny need to meet',
+                    'the virtual bonnie emilio stop this is',
+                    'jana car who just to give a little bit',
+                    'of background information we come from a',
+                    'company called le code from finland and']
+        self.assertEqual(list(captions.get_unique_caption_lines(vtt_path)), expected)

wrolpi/web.py

@@ -21,7 +21,7 @@ ROOT_CONFIG = {
 class ClientRoot(object):
 
     def __init__(self):
-        # Install plugins defined in plugins.plugins
+        # Install plugins defined in user_plugins
         for name, plugin in PLUGINS.items():
             setattr(self, name, plugin.ClientRoot())