better typing

benchmark.py

@@ -28,7 +28,7 @@ def benchmark_query(query: SelectQuery, filename: str = None) -> Tuple[float, fl
     return result["Planning Time"], result["Execution Time"]
 
 
-def statistics(query: SelectQuery, filename: str, repeats: int = 500):
+def statistics(query: SelectQuery, filename: str, repeats: int = 500) -> None:
     ts = shutil.get_terminal_size((80, 20))
     print(filename.center(ts.columns, "-"))
     planning_times = []

data.py

@@ -1,3 +1,6 @@
+from dataclasses import dataclass
+from typing import Optional
+
 colors_c1 = {
     "Travis": "#7592a4",
     "Marisha": "#bd6b1e",
@@ -72,24 +75,32 @@ single_speaker = {
 
 assert set(single_speaker["Handbooker Helper"].keys()) == set(range(1, 44 + 1))
 
-series_data = [
-    {
-        "name": "Campaign 1",
-        "playlist_id": "PL1tiwbzkOjQz7D0l_eLJGAISVtcL7oRu_",
-    },
-    {
-        "name": "Campaign 2",
-        "playlist_id": "PL1tiwbzkOjQxD0jjAE7PsWoaCrs0EkBH2"
 
-    },
-    {
-        "name": "Handbooker Helper",
-        "playlist_id": "PL1tiwbzkOjQyr6-gqJ8r29j_rJkR49uDN",
-        "single_speaker": True
-    },
-    {
-        "name": "Mini Primetime",
-        "playlist_id": "PL1tiwbzkOjQz9kKDaPRPrX2E7RPTaxEZd",
-        "initial_speaker": "Will"
-    }
+@dataclass
+class SeriesData:
+    name: str
+    playlist_id: str
+    single_speaker: bool = False
+    initial_speaker: Optional[str] = None
+
+
+series_data = [
+    SeriesData(
+        name="Campaign 1",
+        playlist_id="PL1tiwbzkOjQz7D0l_eLJGAISVtcL7oRu_"
+    ),
+    SeriesData(
+        name="Campaign 2",
+        playlist_id="PL1tiwbzkOjQxD0jjAE7PsWoaCrs0EkBH2"
+    ),
+    SeriesData(
+        name="Handbooker Helper",
+        playlist_id="PL1tiwbzkOjQyr6-gqJ8r29j_rJkR49uDN",
+        single_speaker=True
+    ),
+    SeriesData(
+        name="Mini Primetime",
+        playlist_id="PL1tiwbzkOjQz9kKDaPRPrX2E7RPTaxEZd",
+        initial_speaker="Will"
+    ),
 ]

fetch.py

@@ -13,11 +13,11 @@ from models import Episode, Series, Line, Phrase
 from utils import srtdir, pretty_title
 
 
-def main():
+def main() -> None:
     os.nice(15)
     for series in series_data:
-        name = series["name"]
-        playlist_id = series["playlist_id"]
+        name = series.name
+        playlist_id = series.playlist_id
         is_campaign = "Campaign" in name
         try:
             s = Series.select().where(Series.title == name).get()
@@ -26,7 +26,7 @@ def main():
             s.title = name
 
         s.is_campaign = is_campaign
-        s.single_speaker = "single_speaker" in series and series["single_speaker"]
+        s.single_speaker = series.single_speaker
         s.save()
         ydl_opts = {
             'extract_flat': True
@@ -37,7 +37,7 @@ def main():
 
         print(v["url"] for v in videos)
 
-        ydl_opts = {
+        ydl_opts_download = {
             "writesubtitles": True,
             "subtitleslangs": ["en", "en-US"],
             "skip_download": True,
@@ -58,6 +58,8 @@ def main():
             if s.is_campaign:
                 try:
                     match = regex.search(video["title"])
+                    if not match:
+                        raise ValueError("No episode number found in title")
                     e.episode_number = int(match.group(1))
                 except AttributeError:
                     if s.title == "Campaign 1":  # one-shots at the end of campaign 1
@@ -71,8 +73,8 @@ def main():
             print(e.series.id, e.episode_number, e.pretty_title)
 
             vttfile = srtdir / str(e.id)
-            ydl_opts["outtmpl"] = str(vttfile)
-            with youtube_dl.YoutubeDL(ydl_opts) as ydl:
+            ydl_opts_download["outtmpl"] = str(vttfile)
+            with youtube_dl.YoutubeDL(ydl_opts_download) as ydl:
                 ydl.download([f'https://www.youtube.com/watch?v={e.youtube_id}'])
             if vttfile.with_suffix(".en-US.vtt").exists():
                 # few videos have en-US as language code instead of en

import.py

@@ -1,7 +1,7 @@
 import os
 import re
 from html import unescape
-from typing import List, Optional
+from typing import List, Optional, Set
 
 from alive_progress import alive_bar
 from peewee import fn, chunked
@@ -28,7 +28,7 @@ def add_to_text(text: str, add: str) -> str:
     return add
 
 
-def insert_subtitle(text: str, person: str, subline: Subtitle, episode: Episode, order: int,
+def insert_subtitle(text: str, person: Optional[Person], subline: Subtitle, episode: Episode, order: int,
                     isnote: bool = False, ismeta: bool = False) -> Line:
     dbline = Line()
     if not text:
@@ -46,9 +46,9 @@ def insert_subtitle(text: str, person: str, subline: Subtitle, episode: Episode,
     return dbline
 
 
-def main():
+def main() -> None:
     os.nice(15)
-    all_people = set()
+    all_people: Set[str] = set()
     for series in Series.select().order_by(Series.id):
         for episode in Episode.select().where(
                 (Episode.text_imported == False) & (Episode.series == series) & (Episode.downloaded)

mypy.ini

@@ -0,0 +1,8 @@
+[mypy]
+warn_return_any = True
+warn_unused_configs = True
+disallow_untyped_defs = True
+disallow_incomplete_defs = True
+ignore_missing_imports = True
+check_untyped_defs=True
+warn_redundant_casts=True

server.py

@@ -1,4 +1,3 @@
-import logging
 from typing import List
 
 from flask import request, jsonify, Response
@@ -10,12 +9,13 @@ from psycopg2._psycopg import cursor
 from app import app
 from models import *
 
+
 # logger = logging.getLogger('peewee')
 # logger.addHandler(logging.StreamHandler())
 # logger.setLevel(logging.DEBUG)
 
 
-def add_cors(response):
+def add_cors(response: Response) -> Response:
     header = response.headers
     header['Access-Control-Allow-Origin'] = '*'
     return response