[NO-ISSUE] Add lightweight option

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/tubesync.iml" filepath="$PROJECT_DIR$/.idea/tubesync.iml" />
+    </modules>
+  </component>
+</project>

.idea/tubesync.iml

@@ -0,0 +1,20 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="PyDocumentationSettings">
+    <option name="format" value="PLAIN" />
+    <option name="myDocStringFormat" value="Plain" />
+  </component>
+  <component name="TemplatesService">
+    <option name="TEMPLATE_CONFIGURATION" value="Jinja2" />
+    <option name="TEMPLATE_FOLDERS">
+      <list>
+        <option value="$MODULE_DIR$/tubesync/common/templates" />
+      </list>
+    </option>
+  </component>
+</module>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

docs/other-database-backends.md

@@ -79,14 +79,6 @@ entry in the container or stdout logs:
 If you see a line similar to the above and the web interface loads, congratulations,
 you are now using an external database server for your TubeSync data!
 
-## Database Compression (For MariaDB)
-With a lot of media files the `sync_media` table grows in size quickly.
-You can save space using column compression using the following steps while using MariaDB:
-
- 1. Stop tubesync 
- 2. Execute `ALTER TABLE sync_media MODIFY metadata LONGTEXT COMPRESSED;` on database tubesync
- 3. Start tunesync and confirm the connection still works.
-
 ## Docker Compose
 
 If you're using Docker Compose and simply want to connect to another container with
@@ -126,7 +118,6 @@ database before it can be written to. This file should contain:
 CREATE DATABASE tubesync;
 ```
 
-
 Then it must be mapped to `/docker-entrypoint-initdb.d/init.sql` for it
 to be executed on first startup of the container. See the `tubesync-db`
 volume mapping above for how to do this.

tubesync/sync/migrations/0021_add_delete_files_on_disk.py

@@ -1,17 +0,0 @@
-# Generated by pac
-
-from django.db import migrations, models
-
-class Migration(migrations.Migration):
-
-    dependencies = [
-        ('sync', '0020_auto_20231024_1825'),
-    ]
-
-    operations = [
-        migrations.AddField(
-            model_name='source',
-            name='delete_files_on_disk',
-            field=models.BooleanField(default=False, help_text='Delete files on disk when they are removed from TubeSync', verbose_name='delete files on disk'),
-        ),
-    ]

tubesync/sync/migrations/0021_add_lightweight_metadata.py

@@ -0,0 +1,22 @@
+# Generated by pac
+
+from django.db import migrations, models
+from sync.models import Source
+
+
+class Migration(migrations.Migration):
+    dependencies = [
+        ('sync', '0020_auto_20231024_1825'),
+    ]
+
+    operations = [
+        migrations.AddField(
+            model_name='source',
+            name='lightweight_metadata',
+            field=models.CharField(max_length=20,
+                                   default=Source.LIGHTWEIGHT_METADATA_TYPE_RAW,
+                                   choices=Source.LIGHTWEIGHT_METADATA_TYPE_CHOICES,
+                                   help_text='Lightweight metadata',
+                                   verbose_name='lightweight metadata'),
+        ),
+    ]

tubesync/sync/models.py

@@ -107,6 +107,7 @@ class Source(models.Model):
     EXTENSION_MKV = 'mkv'
     EXTENSIONS = (EXTENSION_M4A, EXTENSION_OGG, EXTENSION_MKV)
 
+
     # as stolen from: https://wiki.sponsor.ajay.app/w/Types / https://github.com/yt-dlp/yt-dlp/blob/master/yt_dlp/postprocessor/sponsorblock.py
     SPONSORBLOCK_CATEGORIES_CHOICES = (
         ('sponsor', 'Sponsor'),
@@ -120,14 +121,15 @@ class Source(models.Model):
     )
     
     sponsorblock_categories = CommaSepChoiceField(
-        _(''),
+            _(''),
-        possible_choices=SPONSORBLOCK_CATEGORIES_CHOICES,
+            possible_choices=SPONSORBLOCK_CATEGORIES_CHOICES,
-        all_choice='all',
+            all_choice="all",
-        allow_all=True,
+            allow_all=True,
-        all_label='(all options)',
+            all_label="(all options)",
-        default='all',
+            default="all",
-        help_text=_('Select the sponsorblocks you want to enforce')
+            help_text=_("Select the sponsorblocks you want to enforce")
-    )
+        )
+
     embed_metadata = models.BooleanField(
         _('embed metadata'),
         default=False,
@@ -138,12 +140,14 @@ class Source(models.Model):
         default=False,
         help_text=_('Embed thumbnail into the file')
     )
+
     enable_sponsorblock = models.BooleanField(
         _('enable sponsorblock'),
         default=True,
         help_text=_('Use SponsorBlock?')
     )
 
+
     # Fontawesome icons used for the source on the front end
     ICONS = {
         SOURCE_TYPE_YOUTUBE_CHANNEL: '<i class="fab fa-youtube"></i>',
@@ -296,11 +300,6 @@ class Source(models.Model):
         default=False,
         help_text=_('Delete media that is no longer on this playlist')
     )
-    delete_files_on_disk = models.BooleanField(
-        _('delete files on disk'),
-        default=False,
-        help_text=_('Delete files on disk when they are removed from TubeSync')
-    )
     source_resolution = models.CharField(
         _('source resolution'),
         max_length=8,
@@ -388,6 +387,24 @@ class Source(models.Model):
         ]
     )
 
+    LIGHTWEIGHT_METADATA_TYPE_RAW = 'RAW'
+    LIGHTWEIGHT_METADATA_TYPE_UNNECESSARY = 'UNNECESSARY'
+    LIGHTWEIGHT_METADATA_TYPE_FEATHER = 'FEATHER'
+    LIGHTWEIGHT_METADATA_TYPES = (LIGHTWEIGHT_METADATA_TYPE_RAW, LIGHTWEIGHT_METADATA_TYPE_UNNECESSARY, LIGHTWEIGHT_METADATA_TYPE_FEATHER)
+    LIGHTWEIGHT_METADATA_TYPE_CHOICES = (
+        (LIGHTWEIGHT_METADATA_TYPE_RAW, _("(LARGE) Save raw metadata")),
+        (LIGHTWEIGHT_METADATA_TYPE_UNNECESSARY, _("(MEDIUM) Treeshake unnecessary metadata json keys")),
+        (LIGHTWEIGHT_METADATA_TYPE_FEATHER, _("(TINY) if the capacity is large, Treeshake it event if it is in use")),
+    )
+
+    lightweight_metadata = models.CharField(
+        _('lightweight metadata'),
+        max_length=20,
+        default=LIGHTWEIGHT_METADATA_TYPE_RAW,
+        choices=LIGHTWEIGHT_METADATA_TYPE_CHOICES,
+        help_text=_('Lightweight metadata')
+    )
+
     def __str__(self):
         return self.name
 
@@ -1237,6 +1254,7 @@ class Media(models.Model):
             acodec = self.downloaded_audio_codec
             if acodec is None:
                 raise TypeError() # nothing here.
+            
             acodec = acodec.lower()
             if acodec == "mp4a":
                 return "audio/mp4"
@@ -1245,6 +1263,7 @@ class Media(models.Model):
             else:
                 # fall-fall-back.
                 return 'audio/ogg'
+
         vcodec = vcodec.lower()
         if vcodec == 'vp9':
             return 'video/webm'
@@ -1268,22 +1287,6 @@ class Media(models.Model):
         showtitle.text = str(self.source.name).strip()
         showtitle.tail = '\n  '
         nfo.append(showtitle)
-        # season = upload date year
-        season = nfo.makeelement('season', {})
-        if self.source.source_type == Source.SOURCE_TYPE_YOUTUBE_PLAYLIST:
-            # If it's a playlist, set season to 1
-            season.text = '1'
-        else:
-            # If it's not a playlist, set season to upload date year
-            season.text = str(self.upload_date.year) if self.upload_date else ''
-        season.tail = '\n  '
-        nfo.append(season)
-        # episode = number of video in the year
-        episode = nfo.makeelement('episode', {})
-        episode_number = self.calculate_episode_number()
-        episode.text = str(episode_number) if episode_number else ''
-        episode.tail = '\n  '
-        nfo.append(episode)
         # ratings = media metadata youtube rating
         value = nfo.makeelement('value', {})
         value.text = str(self.rating)
@@ -1392,7 +1395,7 @@ class Media(models.Model):
         # Download the media with youtube-dl
         download_youtube_media(self.url, format_str, self.source.extension,
                                str(self.filepath), self.source.write_json, 
-                               self.source.sponsorblock_categories.selected_choices, self.source.embed_thumbnail,
+                               self.source.sponsorblock_categories, self.source.embed_thumbnail,
                                self.source.embed_metadata, self.source.enable_sponsorblock,
                               self.source.write_subtitles, self.source.auto_subtitles,self.source.sub_langs )
         # Return the download paramaters
@@ -1408,19 +1411,6 @@ class Media(models.Model):
                             f'has no indexer')
         return indexer(self.url)
 
-    def calculate_episode_number(self):
-        if self.source.source_type == Source.SOURCE_TYPE_YOUTUBE_PLAYLIST:
-            sorted_media = Media.objects.filter(source=self.source)
-        else:
-            self_year = self.upload_date.year if self.upload_date else self.created.year
-            filtered_media = Media.objects.filter(source=self.source, published__year=self_year)
-            sorted_media = sorted(filtered_media, key=lambda x: (x.upload_date, x.key))
-        position_counter = 1
-        for media in sorted_media:
-            if media == self:
-                return position_counter
-            position_counter += 1
-
 
 class MediaServer(models.Model):
     '''

tubesync/sync/signals.py

@@ -1,5 +1,4 @@
 import os
-import glob
 from django.conf import settings
 from django.db.models.signals import pre_save, post_save, pre_delete, post_delete
 from django.dispatch import receiver
@@ -75,7 +74,6 @@ def source_pre_delete(sender, instance, **kwargs):
         media.delete()
 
 
-
 @receiver(post_delete, sender=Source)
 def source_post_delete(sender, instance, **kwargs):
     # Triggered after a source is deleted
@@ -224,16 +222,6 @@ def media_pre_delete(sender, instance, **kwargs):
     if thumbnail_url:
         delete_task_by_media('sync.tasks.download_media_thumbnail',
                              (str(instance.pk), thumbnail_url))
-    if instance.source.delete_files_on_disk and (instance.media_file or instance.thumb):
-        # Delete all media files if it contains filename
-        filepath = instance.media_file.path if instance.media_file else instance.thumb.path
-        barefilepath, fileext = os.path.splitext(filepath)
-        # Get all files that start with the bare file path
-        all_related_files = glob.glob(f'{barefilepath}.*')
-        for file in all_related_files:
-            log.info(f'Deleting file for: {instance} path: {file}')
-            delete_file(file)
-
 
 
 @receiver(post_delete, sender=Media)

tubesync/sync/tasks.py

@@ -236,6 +236,12 @@ def download_media_metadata(media_id):
         return
     source = media.source
     metadata = media.index_metadata()
+    if source.lightweight_metadata == Source.LIGHTWEIGHT_METADATA_TYPE_FEATHER:
+        del metadata["formats"]
+        del metadata["thumbnails"]
+        del metadata["automatic_captions"]
+        del metadata["requested_formats"]
+        del metadata["heatmap"]
     media.metadata = json.dumps(metadata, default=json_serial)
     upload_date = media.upload_date
     # Media must have a valid upload date

tubesync/sync/templates/sync/media-item.html

@@ -132,6 +132,8 @@
         <td><span class="hide-on-med-and-up">Can download?<br></span><strong>{% if media.can_download %}<i class="fas fa-check"></i>{% else %}<i class="fas fa-times"></i>{% endif %}</strong></td>
       </tr>
       {% endif %}
+
+    {%  if media.source.lightweight_metadata == "RAW" %}
       <tr title="The available media formats">
         <td class="hide-on-small-only">Available formats</td>
         <td><span class="hide-on-med-and-up">Available formats<br></span>
@@ -155,7 +157,10 @@
           Video: <strong>{% if video_format %}{{ video_format }} {% if video_exact %}(exact match){% else %}(fallback){% endif %}{% else %}no match{% endif %}
         </strong></td>
       </tr>
+    {% endif %}
     </table>
+  <p>{{ media.source.lightweight_metadata }}</p>
+  <p>{{ media.source }}</p>
   </div>
 </div>
 {% if media.downloaded %}

tubesync/sync/templates/sync/source-delete.html

@@ -9,8 +9,8 @@
     <p>
       Are you sure you want to delete this source? Deleting a source is permanent.
       By default, deleting a source does not delete any saved media files. You can
-      <strong>tick the &quot;also delete downloaded media&quot; checkbox to also remove directory {{ source.directory_path }}
+      tick the &quot;also delete downloaded media&quot; checkbox to also remove save
-	  </strong>when you delete the source. Deleting a source cannot be undone.
+      media when you delete the source. Deleting a source cannot be undone.
     </p>
   </div>
 </div>

tubesync/sync/templates/sync/source.html

@@ -122,10 +122,6 @@
       <tr title="Delete media that is no longer on this playlist?">
         <td class="hide-on-small-only">Delete removed media</td>
         <td><span class="hide-on-med-and-up">Delete removed media<br></span><strong>{% if source.delete_removed_media %}<i class="fas fa-check"></i>{% else %}<i class="fas fa-times"></i>{% endif %}</strong></td>
-      </tr>
-        <tr title="Delete files on disk when they are removed from TubeSync?">
-        <td class="hide-on-small-only">Delete files on disk</td>
-        <td><span class="hide-on-med-and-up">Delete files on disk<br></span><strong>{% if source.delete_files_on_disk %}<i class="fas fa-check"></i>{% else %}<i class="fas fa-times"></i>{% endif %}</strong></td>
       </tr>
       {% if source.delete_old_media and source.days_to_keep > 0 %}
       <tr title="Days after which your media from this source will be locally deleted">
@@ -191,6 +187,16 @@
       </tr>
       {% endif %}
 
+      {% if source.lightweight_metadata %}
+      <tr title="{{ _('Are auto subs accepted?') }}">
+        <td class="hide-on-small-only">{{ _("Auto-generated subtitles?") }}:</td>
+        <td><span class="hide-on-med-and-up">{{ _("Auto-generated subtitles?") }}:</span><strong><i class="fas {% if source.auto_subtitles %}fa-check{% else %}fa-times{% endif %}"></i></strong></td>
+      </tr>
+      <tr title="{{ _('Subs langs?') }}">
+        <td class="hide-on-small-only">{{ _("Subs langs?") }}:</td>
+        <td><span class="hide-on-med-and-up">{{ _("Subs langs?") }}:</span><strong>{{source.sub_langs}}</strong></td>
+      </tr>
+      {% endif %}
     </table>
   </div>
 </div>

tubesync/sync/tests.py

@@ -661,8 +661,6 @@ class MediaTestCase(TestCase):
             '<episodedetails>',
             '  <title>no fancy stuff title</title>',
             '  <showtitle>testname</showtitle>',
-            '  <season>2017</season>',
-            '  <episode></episode>',
             '  <ratings>',
             '    <rating default="True" max="5" name="youtube">',
             '      <value>1.2345</value>',

tubesync/sync/views.py

@@ -1,9 +1,7 @@
-import glob
 import os
 import json
 from base64 import b64decode
 import pathlib
-import shutil
 import sys
 from django.conf import settings
 from django.http import FileResponse, Http404, HttpResponseNotFound, HttpResponseRedirect
@@ -61,7 +59,7 @@ class DashboardView(TemplateView):
         # Disk usage
         disk_usage = Media.objects.filter(
             downloaded=True, downloaded_filesize__isnull=False
-        ).defer('metadata').aggregate(Sum('downloaded_filesize'))
+        ).aggregate(Sum('downloaded_filesize'))
         data['disk_usage_bytes'] = disk_usage['downloaded_filesize__sum']
         if not data['disk_usage_bytes']:
             data['disk_usage_bytes'] = 0
@@ -73,11 +71,11 @@ class DashboardView(TemplateView):
         # Latest downloads
         data['latest_downloads'] = Media.objects.filter(
             downloaded=True, downloaded_filesize__isnull=False
-        ).defer('metadata').order_by('-download_date')[:10]
+        ).order_by('-download_date')[:10]
         # Largest downloads
         data['largest_downloads'] = Media.objects.filter(
             downloaded=True, downloaded_filesize__isnull=False
-        ).defer('metadata').order_by('-downloaded_filesize')[:10]
+        ).order_by('-downloaded_filesize')[:10]
         # UID and GID
         data['uid'] = os.getuid()
         data['gid'] = os.getgid()
@@ -298,11 +296,11 @@ class EditSourceMixin:
     model = Source
     fields = ('source_type', 'key', 'name', 'directory', 'filter_text', 'media_format',
               'index_schedule', 'download_media', 'download_cap', 'delete_old_media',
-              'delete_removed_media', 'delete_files_on_disk', 'days_to_keep', 'source_resolution',
+              'delete_removed_media', 'days_to_keep', 'source_resolution', 'source_vcodec',
-              'source_vcodec', 'source_acodec', 'prefer_60fps', 'prefer_hdr', 'fallback',
+              'source_acodec', 'prefer_60fps', 'prefer_hdr', 'fallback', 'copy_thumbnails',
-              'copy_thumbnails', 'write_nfo', 'write_json', 'embed_metadata', 'embed_thumbnail',
+              'write_nfo', 'write_json', 'embed_metadata', 'embed_thumbnail',
               'enable_sponsorblock', 'sponsorblock_categories', 'write_subtitles',
-              'auto_subtitles', 'sub_langs')
+              'auto_subtitles', 'sub_langs', 'lightweight_metadata')
     errors = {
         'invalid_media_format': _('Invalid media format, the media format contains '
                                   'errors or is empty. Check the table at the end of '
@@ -406,7 +404,7 @@ class SourceView(DetailView):
             error_message = get_error_message(error)
             setattr(error, 'error_message', error_message)
             data['errors'].append(error)
-        data['media'] = Media.objects.filter(source=self.object).order_by('-published').defer('metadata')
+        data['media'] = Media.objects.filter(source=self.object).order_by('-published')
         return data
 
 
@@ -437,13 +435,14 @@ class DeleteSourceView(DeleteView, FormMixin):
             source = self.get_object()
             for media in Media.objects.filter(source=source):
                 if media.media_file:
-                    file_path = media.media_file.path
+                    # Delete the media file
-                    matching_files = glob.glob(os.path.splitext(file_path)[0] + '.*')
+                    delete_file(media.media_file.path)
-                    for file in matching_files:
+                    # Delete thumbnail copy if it exists
-                        delete_file(file)
+                    delete_file(media.thumbpath)
-            directory_path = source.directory_path
+                    # Delete NFO file if it exists
-            if os.path.exists(directory_path):
+                    delete_file(media.nfopath)
-                shutil.rmtree(directory_path, True)
+                    # Delete JSON file if it exists
+                    delete_file(media.jsonpath)
         return super().post(request, *args, **kwargs)
 
     def get_success_url(self):
@@ -654,13 +653,12 @@ class MediaSkipView(FormView, SingleObjectMixin):
         delete_task_by_media('sync.tasks.download_media', (str(self.object.pk),))
         # If the media file exists on disk, delete it
         if self.object.media_file_exists:
-            # Delete all files which contains filename
+            delete_file(self.object.media_file.path)
-            filepath = self.object.media_file.path
+            self.object.media_file = None
-            barefilepath, fileext = os.path.splitext(filepath)
+            # If the media has an associated thumbnail copied, also delete it
-            # Get all files that start with the bare file path
+            delete_file(self.object.thumbpath)
-            all_related_files = glob.glob(f'{barefilepath}.*')
+            # If the media has an associated NFO file with it, also delete it
-            for file in all_related_files:
+            delete_file(self.object.nfopath)
-                delete_file(file)
         # Reset all download data
         self.object.metadata = None
         self.object.downloaded = False

tubesync/sync/youtube.py

@@ -1,5 +1,5 @@
 '''
-    Wrapper for the yt-dlp library. Used so if there are any library interface
+    Wrapper for the youtube-dl library. Used so if there are any library interface
     updates we only need to udpate them in one place.
 '''
 
@@ -65,7 +65,7 @@ def get_media_info(url):
 
 
 def download_media(url, media_format, extension, output_file, info_json, 
-                   sponsor_categories=None,
+                   sponsor_categories="all", 
                    embed_thumbnail=False, embed_metadata=False, skip_sponsors=True, 
                    write_subtitles=False, auto_subtitles=False, sub_langs='en'):
     '''
@@ -106,8 +106,8 @@ def download_media(url, media_format, extension, output_file, info_json,
                      f'{total_size_str} in {elapsed_str}')
         else:
             log.warn(f'[youtube-dl] unknown event: {str(event)}')
-
     hook.download_progress = 0
+
     ytopts = {
         'format': media_format,
         'merge_output_format': extension,
@@ -120,23 +120,27 @@ def download_media(url, media_format, extension, output_file, info_json,
         'writeautomaticsub': auto_subtitles,
         'subtitleslangs': sub_langs.split(','),
     }
-    if not sponsor_categories:
+    
-        sponsor_categories = []
     sbopt = {
         'key': 'SponsorBlock',
-        'categories': sponsor_categories
+        'categories': [sponsor_categories]
     }
     ffmdopt = {
         'key': 'FFmpegMetadata',
-        'add_chapters': embed_metadata,
+        'add_chapters': True,
-        'add_metadata': embed_metadata
+        'add_metadata': True
     }
+
     opts = get_yt_opts()
     if embed_thumbnail:
         ytopts['postprocessors'].append({'key': 'EmbedThumbnail'})
+    if embed_metadata:
+        ffmdopt["add_metadata"] = True
     if skip_sponsors:
         ytopts['postprocessors'].append(sbopt)
+    
     ytopts['postprocessors'].append(ffmdopt)
+        
     opts.update(ytopts)
         
     with yt_dlp.YoutubeDL(opts) as y:

tubesync/tubesync/local_settings.py.container

@@ -25,6 +25,9 @@ DEBUG = True if os.getenv('TUBESYNC_DEBUG', False) else False
 FORCE_SCRIPT_NAME = os.getenv('DJANGO_FORCE_SCRIPT_NAME', DJANGO_URL_PREFIX)
 
 
+TIME_ZONE = os.getenv('TZ', 'UTC')
+
+
 database_dict = {}
 database_connection_env = os.getenv('DATABASE_CONNECTION', '')
 if database_connection_env:

tubesync/tubesync/settings.py

@@ -1,4 +1,3 @@
-import os
 from pathlib import Path
 
 
@@ -97,7 +96,7 @@ AUTH_PASSWORD_VALIDATORS = [
 
 
 LANGUAGE_CODE = 'en-us'
-TIME_ZONE = os.getenv('TZ', 'UTC')
+TIME_ZONE = 'UTC'
 USE_I18N = True
 USE_L10N = True
 USE_TZ = True