Sort name for autocomplete

generate_lastfm_tasks.py

@@ -2,7 +2,7 @@ import csv
 import json
 from multiprocessing.pool import ThreadPool
 
-from task_tracker_drone.src.tt_drone.api import TaskTrackerApi, Worker
+from task_tracker_drone.src.tt_drone.api import TaskTrackerApi, Worker, LOG_TRACE
 
 TT_API_URL = "https://tt.simon987.net/api"
 TT_PROJECT = 1

process_lastfm_data.py

@@ -69,7 +69,7 @@ def patch(lastfm_data):
     with open("repo/lastfm_artist.csv", "w") as out:
         writer = csv.writer(out)
         writer.writerow([
-            "id:ID(Artist)", "name", "year:short", ":LABEL", "listeners:int", "playcount:int"
+            "id:ID(Artist)", "name", "sortname", "year:short", "comment",  ":LABEL", "listeners:int", "playcount:int"
         ])
 
         with open("repo/artist.csv") as f:
@@ -82,6 +82,8 @@ def patch(lastfm_data):
                     row[1],
                     row[2],
                     row[3],
+                    row[4],
+                    row[5],
                     artist_listeners.get(row[0], (0, 0))[0],
                     artist_listeners.get(row[0], (0, 0))[1],
                 ])

process_mb_dump.py

@@ -1,5 +1,6 @@
 import os
 from collections import defaultdict
+import re
 
 links = dict()
 link_types = dict()
@@ -188,14 +189,24 @@ with open("repo/area.csv", "w") as out:
 out_artist = open("repo/artist.csv", "w")
 out_artist_area = open("repo/artist_area.csv", "w")
 
-out_artist.write("id:ID(Artist),name,year:int,:LABEL\n")
+out_artist.write("id:ID(Artist),name,sortname,year:int,comment,:LABEL\n")
 out_artist_area.write(":START_ID(Artist),:END_ID(Area)\n")
 
+ASCII_RE = re.compile(r"[^a-zA-Z0-9.\-!?& ]")
+ALPHANUM_RE = re.compile(r"[^\w.\-!?& ]")
+
 for _, artist in artists.items():
+
+    sortname = ASCII_RE.sub("_", artist[2]).upper()
+    if sortname.replace("_", "").strip() == "":
+        sortname = ALPHANUM_RE.sub("_", artist[3]).upper()
+
     out_artist.write(",".join((
         artist[1],
         '"' + artist[2].replace("\"", "\"\"") + '"',
+        sortname,
         artist[4] if artist[4] != "\\N" else "0",
+        ('"' + artist[13].replace("\"", "\"\"") + '"') if artist[13] != "\\N" else "",
         "Artist" + (";Group\n" if artist[10] == "2" else "\n")
     )))
 

seed.cypher

@@ -1,3 +1,3 @@
 CREATE INDEX ON :Artist(id);
-CREATE INDEX ON :Artist(name);
+CREATE INDEX ON :Artist(sortname);
 CREATE INDEX ON :Release(id);