ci: add mypy check

Author: yedpodtrzitko

.github/workflows/mypy.yaml

@@ -0,0 +1,33 @@
+name: MyPy
+
+on: [ push, pull_request ]
+
+
+jobs:
+  mypy:
+    name: Run MyPy
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          # pyside 6.6.3 has some issue in their .pyi files
+          pip install PySide6==6.6.2
+          pip install -r requirements.txt
+          pip install mypy==1.10.0
+
+      - name: Run MyPy
+        run: |
+          cd tagstudio
+          mkdir -p .mypy_cache
+          mypy --install-types --non-interactive 
+          mypy --config-file ../pyproject.toml .

pyproject.toml

@@ -1,2 +1,7 @@
 [tool.ruff]
 exclude = ["main_window.py", "home_ui.py", "resources.py", "resources_rc.py"]
+
+[tool.mypy]
+strict_optional = false
+disable_error_code = ["union-attr", "annotation-unchecked", "import-untyped"]
+explicit_package_bases = true

requirements-dev.txt

@@ -1,3 +1,4 @@
 ruff==0.4.2
 pre-commit==3.7.0
 Pyinstaller==6.6.0
+mypy==1.10.0

tagstudio/src/cli/ts_cli.py

@@ -1,3 +1,4 @@
+# type: ignore
 # Copyright (C) 2024 Travis Abendshien (CyanVoxel).
 # Licensed under the GPL-3.0 License.
 # Created for TagStudio: https://github.com/CyanVoxel/TagStudio

tagstudio/src/core/field_template.py

@@ -19,7 +19,7 @@ def __repr__(self) -> str:
 
     def to_compressed_obj(self) -> dict:
         """An alternative to __dict__ that only includes fields containing non-default data."""
-        obj = {}
+        obj: dict = {}
         # All Field fields (haha) are mandatory, so no value checks are done.
         obj["id"] = self.id
         obj["name"] = self.name

tagstudio/src/core/json_typing.py

@@ -8,6 +8,7 @@ class JsonLibary(TypedDict("", {"ts-version": str})):
     fields: list  # TODO
     macros: "list[JsonMacro]"
     entries: "list[JsonEntry]"
+    ignored_extensions: list[str]
 
 
 class JsonBase(TypedDict):

tagstudio/src/core/library.py

@@ -6,14 +6,18 @@
 
 import datetime
 import glob
-import json
 import logging
 import os
 import sys
 import time
 import traceback
 import xml.etree.ElementTree as ET
 from enum import Enum
+from pathlib import Path
+from typing import cast, Generator
+
+from typing_extensions import Self
+
 import ujson
 
 from src.core.json_typing import JsonCollation, JsonEntry, JsonLibary, JsonTag
@@ -42,7 +46,7 @@ def __init__(self, id: int, filename: str, path: str, fields: list[dict]) -> Non
         self.id = int(id)
         self.filename = filename
         self.path = path
-        self.fields = fields
+        self.fields: list[dict] = fields
         self.type = None
 
         # Optional Fields ======================================================
@@ -75,6 +79,7 @@ def __repr__(self) -> str:
         return self.__str__()
 
     def __eq__(self, __value: object) -> bool:
+        __value = cast(Self, object)
         if os.name == "nt":
             return (
                 int(self.id) == int(__value.id)
@@ -129,18 +134,16 @@ def remove_tag(self, library: "Library", tag_id: int, field_index=-1):
                         )
                         t.remove(tag_id)
                     elif field_index < 0:
-                        t: list[int] = library.get_field_attr(f, "content")
+                        t = library.get_field_attr(f, "content")
                         while tag_id in t:
                             t.remove(tag_id)
 
     def add_tag(
-        self, library: "Library", tag_id: int, field_id: int, field_index: int = None
+        self, library: "Library", tag_id: int, field_id: int, field_index: int = -1
     ):
-        # field_index: int = -1
         # if self.fields:
         # if field_index != -1:
         # logging.info(f'[LIBRARY] ADD TAG to E:{self.id}, F-DI:{field_id}, F-INDEX:{field_index}')
-        field_index = -1 if field_index is None else field_index
         for i, f in enumerate(self.fields):
             if library.get_field_attr(f, "id") == field_id:
                 field_index = i
@@ -183,7 +186,7 @@ def __init__(
         self.shorthand = shorthand
         self.aliases = aliases
         # Ensures no duplicates while retaining order.
-        self.subtag_ids = []
+        self.subtag_ids: list[int] = []
         for s in subtags_ids:
             if int(s) not in self.subtag_ids:
                 self.subtag_ids.append(int(s))
@@ -276,18 +279,19 @@ def __repr__(self) -> str:
         return self.__str__()
 
     def __eq__(self, __value: object) -> bool:
+        __value = cast(Self, __value)
         if os.name == "nt":
             return (
-                int(self.id) == int(__value.id_)
-                and self.filename.lower() == __value.filename.lower()
-                and self.path.lower() == __value.path.lower()
+                int(self.id) == int(__value.id)
+                and self.filename.lower() == __value.filename.lower()  # type: ignore
+                and self.path.lower() == __value.path.lower()  # type: ignore
                 and self.fields == __value.fields
             )
         else:
             return (
-                int(self.id) == int(__value.id_)
-                and self.filename == __value.filename
-                and self.path == __value.path
+                int(self.id) == int(__value.id)
+                and self.filename == __value.filename  # type: ignore
+                and self.path == __value.path  # type: ignore
                 and self.fields == __value.fields
             )
 
@@ -342,7 +346,7 @@ def __init__(self) -> None:
         self.files_not_in_library: list[str] = []
         self.missing_files: list[str] = []
         self.fixed_files: list[str] = []  # TODO: Get rid of this.
-        self.missing_matches = {}
+        self.missing_matches: dict = {}
         # Duplicate Files
         # Defined by files that are exact or similar copies to others. Generated by DupeGuru.
         # (Filepath, Matched Filepath, Match Percentage)
@@ -393,7 +397,7 @@ def __init__(self) -> None:
         # 	Tag(id=1, name='Favorite', shorthand='', aliases=['Favorited, Favorites, Likes, Liked, Loved'], subtags_ids=[], color='yellow'),
         # ]
 
-        self.default_fields = [
+        self.default_fields: list[dict] = [
             {"id": 0, "name": "Title", "type": "text_line"},
             {"id": 1, "name": "Author", "type": "text_line"},
             {"id": 2, "name": "Artist", "type": "text_line"},
@@ -512,8 +516,8 @@ def open_library(self, path: str) -> int:
                     ),
                     "r",
                     encoding="utf-8",
-                ) as f:
-                    json_dump: JsonLibary = ujson.load(f)
+                ) as file:
+                    json_dump: JsonLibary = ujson.load(file)
                     self.library_dir = str(path)
                     self.verify_ts_folders()
                     major, minor, patch = json_dump["ts-version"].split(".")
@@ -591,7 +595,7 @@ def open_library(self, path: str) -> int:
 
                             filename = entry.get("filename", "")
                             e_path = entry.get("path", "")
-                            fields = []
+                            fields: list = []
                             if "fields" in entry:
                                 # Cast JSON str keys to ints
                                 for f in entry["fields"]:
@@ -688,14 +692,14 @@ def open_library(self, path: str) -> int:
                                 self._next_collation_id = id + 1
 
                             title = collation.get("title", "")
-                            e_ids_and_pages = collation.get("e_ids_and_pages", "")
-                            sort_order = collation.get("sort_order", [])
-                            cover_id = collation.get("cover_id", [])
+                            e_ids_and_pages = collation.get("e_ids_and_pages", [])
+                            sort_order = collation.get("sort_order", "")
+                            cover_id = collation.get("cover_id", -1)
 
                             c = Collation(
                                 id=id,
                                 title=title,
-                                e_ids_and_pages=e_ids_and_pages,
+                                e_ids_and_pages=e_ids_and_pages,  # type: ignore
                                 sort_order=sort_order,
                                 cover_id=cover_id,
                             )
@@ -861,33 +865,33 @@ def clear_internal_vars(self):
         self.is_legacy_library = False
 
         self.entries.clear()
-        self._next_entry_id: int = 0
+        self._next_entry_id = 0
         # self.filtered_entries.clear()
         self._entry_id_to_index_map.clear()
 
         self._collation_id_to_index_map.clear()
 
         self.missing_matches = {}
-        self.dir_file_count: int = -1
+        self.dir_file_count = -1
         self.files_not_in_library.clear()
         self.missing_files.clear()
         self.fixed_files.clear()
-        self.filename_to_entry_id_map: dict[str, int] = {}
+        self.filename_to_entry_id_map = {}
         self.ignored_extensions = self.default_ext_blacklist
 
         self.tags.clear()
-        self._next_tag_id: int = 1000
-        self._tag_strings_to_id_map: dict[str, list[int]] = {}
-        self._tag_id_to_cluster_map: dict[int, list[int]] = {}
-        self._tag_id_to_index_map: dict[int, int] = {}
+        self._next_tag_id = 1000
+        self._tag_strings_to_id_map = {}
+        self._tag_id_to_cluster_map = {}
+        self._tag_id_to_index_map = {}
         self._tag_entry_ref_map.clear()
 
-    def refresh_dir(self):
+    def refresh_dir(self) -> Generator:
         """Scans a directory for files, and adds those relative filenames to internal variables."""
 
         # Reset file interfacing variables.
         # -1 means uninitialized, aka a scan like this was never attempted before.
-        self.dir_file_count: int = 0
+        self.dir_file_count = 0
         self.files_not_in_library.clear()
 
         # Scans the directory for files, keeping track of:
@@ -1210,7 +1214,8 @@ def fix_missing_files(self):
             # (int, str)
 
         self._map_filenames_to_entry_ids()
-        self.remove_missing_matches(fixed_indices)
+        # TODO - the type here doesnt match but I cant reproduce calling this
+        self.remove_missing_matches(fixed_indices)  # type: ignore
 
         # for i in fixed_indices:
         # 	# print(json_dump[i])
@@ -1330,10 +1335,11 @@ def get_collation(self, collation_id: int) -> Collation:
         return self.collations[self._collation_id_to_index_map[int(collation_id)]]
 
     # @deprecated('Use new Entry ID system.')
-    def get_entry_from_index(self, index: int) -> Entry:
+    def get_entry_from_index(self, index: int) -> Entry | None:
         """Returns a Library Entry object given its index in the unfiltered Entries list."""
         if self.entries:
             return self.entries[int(index)]
+        return None
 
     # @deprecated('Use new Entry ID system.')
     def get_entry_id_from_filepath(self, filename):
@@ -1368,7 +1374,7 @@ def search_library(
 
         if query:
             # start_time = time.time()
-            query: str = query.strip().lower()
+            query = query.strip().lower()
             query_words: list[str] = query.split(" ")
             all_tag_terms: list[str] = []
             only_untagged: bool = "untagged" in query or "no tags" in query
@@ -1548,7 +1554,7 @@ def search_library(
         else:
             for entry in self.entries:
                 added = False
-                allowed_ext: bool = (
+                allowed_ext = (
                     os.path.splitext(entry.filename)[1][1:].lower()
                     not in self.ignored_extensions
                 )
@@ -1756,7 +1762,7 @@ def search_tags(
 
         # if context and id_weights:
         # 	time.sleep(3)
-        [final.append(idw[0]) for idw in id_weights if idw[0] not in final]
+        [final.append(idw[0]) for idw in id_weights if idw[0] not in final]  # type: ignore
         # print(f'Final IDs: \"{[self.get_tag_from_id(id).display_name(self) for id in final]}\"')
         # print('')
         return final
@@ -1774,7 +1780,7 @@ def get_all_child_tag_ids(self, tag_id: int) -> list[int]:
 
         return subtag_ids
 
-    def filter_field_templates(self: str, query) -> list[int]:
+    def filter_field_templates(self, query: str) -> list[int]:
         """Returns a list of Field Template IDs returned from a string query."""
 
         matches: list[int] = []
@@ -2127,12 +2133,12 @@ def add_field_to_entry(self, entry_id: int, field_id: int) -> None:
     def mirror_entry_fields(self, entry_ids: list[int]) -> None:
         """Combines and mirrors all fields across a list of given Entry IDs."""
 
-        all_fields = []
-        all_ids = []  # Parallel to all_fields
+        all_fields: list = []
+        all_ids: list = []  # Parallel to all_fields
         # Extract and merge all fields from all given Entries.
         for id in entry_ids:
             if id:
-                entry: Entry = self.get_entry(id)
+                entry = self.get_entry(id)
                 if entry and entry.fields:
                     for field in entry.fields:
                         # First checks if their are matching tag_boxes to append to
@@ -2153,7 +2159,7 @@ def mirror_entry_fields(self, entry_ids: list[int]) -> None:
 
         # Replace each Entry's fields with the new merged ones.
         for id in entry_ids:
-            entry: Entry = self.get_entry(id)
+            entry = self.get_entry(id)
             if entry:
                 entry.fields = all_fields
 
@@ -2181,7 +2187,7 @@ def mirror_entry_fields(self, entry_ids: list[int]) -> None:
     # 	pass
     # 	# TODO: Implement.
 
-    def get_field_attr(self, entry_field, attribute: str):
+    def get_field_attr(self, entry_field: dict, attribute: str):
         """Returns the value of a specified attribute inside an Entry field."""
         if attribute.lower() == "id":
             return list(entry_field.keys())[0]
@@ -2236,7 +2242,7 @@ def _map_tag_strings_to_tag_id(self, tag: Tag) -> None:
         self._tag_strings_to_id_map[shorthand].append(tag.id)
 
         for alias in tag.aliases:
-            alias: str = strip_punctuation(alias).lower()
+            alias = strip_punctuation(alias).lower()
             if alias not in self._tag_strings_to_id_map:
                 self._tag_strings_to_id_map[alias] = []
             self._tag_strings_to_id_map[alias].append(tag.id)

tagstudio/src/core/palette.py

@@ -5,7 +5,7 @@
 from enum import Enum
 
 
-class ColorType(Enum):
+class ColorType(int, Enum):
     PRIMARY = 0
     TEXT = 1
     BORDER = 2
@@ -278,7 +278,7 @@ class ColorType(Enum):
 }
 
 
-def get_tag_color(type: ColorType, color: str):
+def get_tag_color(type, color):
     color = color.lower()
     try:
         if type == ColorType.TEXT:

tagstudio/src/core/ts_core.py

@@ -300,7 +300,7 @@ def match_conditions(self, entry_id: int) -> None:
             # input()
             pass
 
-    def build_url(self, entry_id: int, source: str) -> str:
+    def build_url(self, entry_id: int, source: str):
         """Tries to rebuild a source URL given a specific filename structure."""
 
         source = source.lower().replace("-", " ").replace("_", " ")