convert SRT content to WBVTT

fixes COMMS-1971

Test Plan:
** DO THESE BEFORE CHECKING OUT THE PS
- With notorious running create a bunch of videos with
  the rce or submission contents
- while watching the video click on the cc button
  on the video
- add a bunch of closed captions of SRT type (or media tracks
  as they are stored in the db)
- notice that the cc play on the video
CHECK OUT THE PS
- migrate your db
- notice the column on MediaTracks that you added called
  webvtt_content is now populated
- upload another srt file to a video
- notice it still plays

Change-Id: Iba0004ace0a248d8ed28ffe3015dbf5c5d3ddeee
Reviewed-on: https://gerrit.instructure.com/188126
Reviewed-by: Landon Gilbert-Bland <[email protected]>
QA-Review: Landon Gilbert-Bland <[email protected]>
Tested-by: Jenkins
Product-Review: Steven Burnett <[email protected]>

app/models/media_track.rb

@@ -18,12 +18,27 @@
 class MediaTrack < ActiveRecord::Base
   belongs_to :user
   belongs_to :media_object, :touch => true
-  validates_presence_of :media_object_id, :content
+  before_save :convert_srt_to_wvtt
+  validates :media_object_id, presence: true
+  validates :content, presence: true
 
-  RE_LOOKS_LIKE_TTMl = /<tt\s+xml/i
+  RE_LOOKS_LIKE_TTML = /<tt\s+xml/i
   validates :content, format: {
-    without: RE_LOOKS_LIKE_TTMl,
-    message: "TTML tracks are not allowed because they are susceptible to xss attacks"
+    without: RE_LOOKS_LIKE_TTML,
+    message: 'TTML tracks are not allowed because they are susceptible to xss attacks'
   }
 
+  def webvtt_content
+    self.read_attribute(:webvtt_content) || self.content
+  end
+
+  def convert_srt_to_wvtt
+    if self.content.exclude?('WEBVTT') && (self.content_changed? || self.read_attribute(:webvtt_content).nil?)
+      srt_content = self.content.dup
+      srt_content.gsub!(/(:|^)(\d)(,|:)/, '\10\2\3')
+      srt_content.gsub!(/([0-9]{2}:[0-9]{2}:[0-9]{2})([,])([0-9]{3})/, '\1.\3')
+      srt_content.gsub!("\r\n", "\n")
+      self.webvtt_content = "WEBVTT\n\n#{srt_content}".strip
+    end
+  end
 end

db/migrate/20190403131808_add_column_to_media_track.rb

@@ -0,0 +1,24 @@
+#
+# Copyright (C) 2019 - present Instructure, Inc.
+#
+# This file is part of Canvas.
+#
+# Canvas is free software: you can redistribute it and/or modify it under
+# the terms of the GNU Affero General Public License as published by the Free
+# Software Foundation, version 3 of the License.
+#
+# Canvas is distributed in the hope that it will be useful, but WITHOUT ANY
+# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
+# A PARTICULAR PURPOSE. See the GNU Affero General Public License for more
+# details.
+#
+# You should have received a copy of the GNU Affero General Public License along
+# with this program. If not, see <http://www.gnu.org/licenses/>.
+
+class AddColumnToMediaTrack < ActiveRecord::Migration[5.1]
+  tag :predeploy
+
+  def change
+    add_column :media_tracks, :webvtt_content, :text
+  end
+end

db/migrate/20190405134013_populate_media_tracks_web_vtt_content.rb

@@ -0,0 +1,29 @@
+#
+# Copyright (C) 2019 - present Instructure, Inc.
+#
+# This file is part of Canvas.
+#
+# Canvas is free software: you can redistribute it and/or modify it under
+# the terms of the GNU Affero General Public License as published by the Free
+# Software Foundation, version 3 of the License.
+#
+# Canvas is distributed in the hope that it will be useful, but WITHOUT ANY
+# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
+# A PARTICULAR PURPOSE. See the GNU Affero General Public License for more
+# details.
+#
+# You should have received a copy of the GNU Affero General Public License along
+# with this program. If not, see <http://www.gnu.org/licenses/>.
+
+class PopulateMediaTracksWebVttContent < ActiveRecord::Migration[5.1]
+  tag :postdeploy
+
+  def change
+    DataFixup::PopulateMediaTracksWebVttContent.send_later_if_production_enqueue_args(
+      :run,
+      priority: Delayed::LOW_PRIORITY,
+      max_attempts: 1,
+      n_strand: "DataFixup::PopulateMediaTracksWebVttContent:#{Shard.current.database_server.id}"
+    )
+  end
+end

lib/data_fixup/populate_media_tracks_web_vtt_content.rb

@@ -0,0 +1,25 @@
+#
+# Copyright (C) 2019 - present Instructure, Inc.
+#
+# This file is part of Canvas.
+#
+# Canvas is free software: you can redistribute it and/or modify it under
+# the terms of the GNU Affero General Public License as published by the Free
+# Software Foundation, version 3 of the License.
+#
+# Canvas is distributed in the hope that it will be useful, but WITHOUT ANY
+# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
+# A PARTICULAR PURPOSE. See the GNU Affero General Public License for more
+# details.
+#
+# You should have received a copy of the GNU Affero General Public License along
+# with this program. If not, see <http://www.gnu.org/licenses/>.
+
+module DataFixup::PopulateMediaTracksWebVttContent
+  def self.run
+    MediaTrack.find_each do |mt|
+      mt.convert_srt_to_wvtt
+      mt.save if mt.changed?
+    end
+  end
+end

spec/migrations/data_fixup/populate_media_tracks_web_vtt_content_spec.rb

@@ -0,0 +1,74 @@
+#
+# Copyright (C) 2019 - present Instructure, Inc.
+#
+# This file is part of Canvas.
+#
+# Canvas is free software: you can redistribute it and/or modify it under
+# the terms of the GNU Affero General Public License as published by the Free
+# Software Foundation, version 3 of the License.
+#
+# Canvas is distributed in the hope that it will be useful, but WITHOUT ANY
+# WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR
+# A PARTICULAR PURPOSE. See the GNU Affero General Public License for more
+# details.
+#
+# You should have received a copy of the GNU Affero General Public License along
+# with this program. If not, see <http://www.gnu.org/licenses/>.
+
+require_relative '../../spec_helper'
+
+RSpec.describe DataFixup::PopulateMediaTracksWebVttContent do
+  def webvtt_content
+    <<-HEREDOC
+      WEBVTT
+
+      00:01.000 --> 00:04.000
+      Never drink liquid nitrogen.
+
+      00:05.000 --> 00:09.000
+      - It will perforate your stomach.
+      - You could die.
+        end
+    HEREDOC
+  end
+
+  def srt_content
+    <<-HEREDOC
+      1
+      00:00:01,600 --> 00:00:04,200
+      English (US)
+
+      2
+      00:00:05,900 --> 00:00:07,999
+      This is a subtitle in American English
+
+      3
+      00:00:10,000 --> 00:00:14,000
+      Adding subtitles is very easy to do
+    HEREDOC
+  end
+
+  it 'converts content of type srt to web_vtt' do
+    mo = MediaObject.create!(media_id: 'm1234')
+    mt = MediaTrack.create!(content: srt_content, media_object: mo)
+    DataFixup::PopulateMediaTracksWebVttContent.run
+    expect(mt.read_attribute(:webvtt_content)).not_to be_nil
+    expect(mt.read_attribute(:webvtt_content)).to include('WEBVTT')
+  end
+
+  it 'will not convert content if already webvtt' do
+    mo = MediaObject.create!(media_id: 'm1234')
+    mt = MediaTrack.create!(content: webvtt_content, media_object: mo)
+    DataFixup::PopulateMediaTracksWebVttContent.run
+    expect(mt.read_attribute(:webvtt_content)).to be_nil
+    expect(mt.read_attribute(:content)).to include('WEBVTT')
+  end
+
+  it 'will attempt to convert bad formatted srt' do
+    mo = MediaObject.create!(media_id: 'm1234')
+    mt = MediaTrack.create!(content: '123$%blah#badmanbad', media_object: mo)
+    DataFixup::PopulateMediaTracksWebVttContent.run
+    expect(mt.read_attribute(:webvtt_content)).not_to be_nil
+    expect(mt.read_attribute(:webvtt_content)).to include('WEBVTT')
+  end
+end