From f16033b584058fe666c53ad3aabf1edce2012132 Mon Sep 17 00:00:00 2001
From: lars <Lars.Noack@outlook.de>
Date: Sun, 30 Oct 2022 20:30:59 +0100
Subject: [PATCH] implemented the file and folder paths in the db

---
 src/download_links.py               |  1 -
 src/metadata/database.py            | 47 ++++++++++++++++++++++++-----
 src/metadata/database_structure.sql |  4 ++-
 src/url_to_path.py                  | 20 +++---------
 4 files changed, 48 insertions(+), 24 deletions(-)

diff --git a/src/download_links.py b/src/download_links.py
index 22baec6..1e196d2 100644
--- a/src/download_links.py
+++ b/src/download_links.py
@@ -1,6 +1,5 @@
 import json
 import os.path
-import pandas as pd
 import requests
 import logging
 
diff --git a/src/metadata/database.py b/src/metadata/database.py
index c101ded..9c42439 100644
--- a/src/metadata/database.py
+++ b/src/metadata/database.py
@@ -148,11 +148,12 @@ SELECT DISTINCT
                 )
             )
         ),
+        'id', track.id,
         'musicbrainz_releasetrackid', track.id,
         'musicbrainz_albumid', release_.id,
-        'track', track.track,
+        'title', track.track,
         'isrc', track.isrc,
-        'title', release_.title,
+        'album', release_.title,
         'copyright', release_.copyright,
         'album_status', release_.album_status,
         'language', release_.language,
@@ -164,7 +165,12 @@ SELECT DISTINCT
         'albumsort', release_group.albumsort,
         'musicbrainz_albumtype', release_group.musicbrainz_albumtype,
         'compilation', release_group.compilation,
-        'album_artist_id', release_group.album_artist_id
+        'album_artist_id', release_group.album_artist_id,
+        'path', track.path,
+        'file', track.file,
+        'genre', track.genre,
+        'url', track.url,
+        'src', track.src
         )
 FROM track, release_, release_group,artist, artist_track
 WHERE
@@ -196,14 +202,41 @@ def get_tracks_without_isrc():
     return get_custom_track(["track.isrc IS NULL"])
 
 
+def get_tracks_without_filepath():
+    return get_custom_track(["(track.file IS NULL OR track.path IS NULL OR track.genre IS NULL)"])
+
+
+def update_download_status(track_id: str):
+    pass
+
+
+def set_download_data(track_id: str, url: str, src: str):
+    query = f"""
+UPDATE track
+SET url = ?,
+    src = ?
+WHERE '{track_id}' == id;
+        """
+    cursor.execute(query, (url, src))
+    connection.commit()
+
+
+def set_filepath(track_id: str, file: str, path: str, genre: str):
+    query = f"""
+UPDATE track
+SET file = ?,
+    path = ?,
+    genre = ?
+WHERE '{track_id}' == id;
+    """
+    cursor.execute(query, (file, path, genre))
+    connection.commit()
+
+
 init_db(cursor=cursor, connection=connection, reset_anyways=False)
 
 if __name__ == "__main__":
     logging.basicConfig(level=logging.DEBUG)
 
-    # get_track(["track.downloaded == 0", "track.isrc IS NOT NULL"])
-    #
     for track in get_tracks_without_isrc():
         print(track['track'], [artist['name'] for artist in track['artists']])
-
-    # print(get_track_metadata("a85d5ed5-20e5-4f95-8034-d204d81a36dd"))
diff --git a/src/metadata/database_structure.sql b/src/metadata/database_structure.sql
index 9f7fc29..d4d0e9f 100644
--- a/src/metadata/database_structure.sql
+++ b/src/metadata/database_structure.sql
@@ -47,7 +47,9 @@ CREATE TABLE track (
     release_id TEXT NOT NULL,
     track TEXT,
     isrc TEXT,
-    filepath TEXT,
+    genre TEXT,
+    path TEXT,
+    file TEXT,
     url TEXT,
     src TEXT
 );
diff --git a/src/url_to_path.py b/src/url_to_path.py
index 301741c..3862df5 100644
--- a/src/url_to_path.py
+++ b/src/url_to_path.py
@@ -1,29 +1,19 @@
 import os.path
-import shlex
-import pandas as pd
 import json
 
+from metadata import database
+
 
 class UrlPath:
     def __init__(self, genre: str, temp: str = "temp", file: str = ".cache3.csv", step_two_file: str = ".cache2.csv"):
         self.temp = temp
         self.file = file
-        self.metadata = pd.read_csv(os.path.join(self.temp, step_two_file), index_col=0)
 
         self.genre = genre
 
-        new_metadata = []
-
-        for idx, row in self.metadata.iterrows():
+        for row in database.get_tracks_without_filepath():
             file, path = self.get_path_from_row(row)
-            new_row = dict(row)
-            new_row['path'] = path
-            new_row['file'] = file
-            new_row['genre'] = self.genre
-            new_metadata.append(new_row)
-
-        new_df = pd.DataFrame(new_metadata)
-        new_df.to_csv(os.path.join(self.temp, self.file))
+            database.set_filepath(row['id'], file, path, genre)
 
 
     def get_path_from_row(self, row):
@@ -45,7 +35,7 @@ class UrlPath:
         return self.escape_part(row['album'])
 
     def get_artist(self, row):
-        artists = json.loads(row['artist'].replace("'", '"'))
+        artists = [artist['name'] for artist in row['artists']]
         return self.escape_part(artists[0])
 
     def get_song(self, row):