Ruff fixes

museum_map/cli/__init__.py

@@ -2,7 +2,6 @@
 import logging
 import os
 import sys
-from typing import Union
 
 import click
 import yaml
@@ -298,7 +297,7 @@ def cli(ctx, verbose, config):
         logger.error(f"Configuration file {config} not found")
         sys.exit(1)
     with open(config) as in_f:
-        config = yaml.load(in_f, Loader=yaml.FullLoader)
+        config = yaml.safe_load(in_f)
         ctx.obj["config"] = validate_config(config)
 
 

museum_map/cli/db.py

@@ -53,7 +53,7 @@ def load(ctx, source):
 @click.argument("source")
 @click.argument("target")
 @click.pass_context
-def load_images(ctx, source, target):
+def load_images(ctx, source, target):  # noqa: ARG001
     """Load and convert images."""
     progress = ClickIndeterminate("Loading images")
     progress.start()
@@ -66,10 +66,26 @@ def load_images(ctx, source, target):
                 image_target = os.path.join(target, *image_id, filename)
                 shutil.copy(image_source, image_target)
                 subprocess.run(
-                    ["gm", "convert", image_source, "-resize", "240x240", image_target.replace(".jpg", "-240.jpg")]
+                    [  # noqa: S603 S607
+                        "gm",
+                        "convert",
+                        image_source,
+                        "-resize",
+                        "240x240",
+                        image_target.replace(".jpg", "-240.jpg"),
+                    ],
+                    check=True,
                 )
                 subprocess.run(
-                    ["gm", "convert", image_source, "-resize", "320x320", image_target.replace(".jpg", "-320.jpg")]
+                    [  # noqa: S603 S607
+                        "gm",
+                        "convert",
+                        image_source,
+                        "-resize",
+                        "320x320",
+                        image_target.replace(".jpg", "-320.jpg"),
+                    ],
+                    check=True,
                 )
     progress.stop()
 

museum_map/cli/groups.py

@@ -29,7 +29,7 @@ async def generate_groups_impl(config):
             for item in progress:
                 for category in item.attributes["_categories"]:
                     categories.append(category.lower())
-        counts = [(cat, count) for cat, count in Counter(categories).most_common() if count >= 15]
+        counts = [(cat, count) for cat, count in Counter(categories).most_common() if count >= 15]  # noqa: PLR2004
         counts.sort(key=lambda c: c[1])
         max_groups = len(counts)
         with click.progressbar(length=max_groups, label="Generating groups") as progress:
@@ -52,7 +52,9 @@ async def generate_groups_impl(config):
                     for category in item.attributes["_categories"]:
                         categories.append(category.lower())
                 old_counts = len(counts)
-                counts = [(cat, count) for cat, count in Counter(categories).most_common() if count >= 15]
+                counts = [
+                    (cat, count) for cat, count in Counter(categories).most_common() if count >= 15  # noqa: PLR2004
+                ]
                 counts.sort(key=lambda c: c[1])
                 progress.update(old_counts - len(counts))
         await dbsession.commit()
@@ -111,7 +113,9 @@ def split_by_attribute(dbsession, group, attr):
     for item in group.items:
         if attr in item.attributes and item.attributes[attr]:
             values.extend(item.attributes[attr])
-    categories = [(v, c) for v, c in Counter(values).most_common() if c < len(group.items) * 0.6666 and c >= 15]
+    categories = [
+        (v, c) for v, c in Counter(values).most_common() if c < len(group.items) * 0.6666 and c >= 15  # noqa: PLR2004
+    ]
     if categories:
         category_values = [v for v, _ in categories]
         has_values = 0
@@ -123,7 +127,7 @@ def split_by_attribute(dbsession, group, attr):
                     break
             if found:
                 has_values = has_values + 1
-        if has_values / len(group.items) > 0.9:
+        if has_values / len(group.items) > 0.9:  # noqa: PLR2004
             categories.reverse()
             for category in categories:
                 new_group = Group(
@@ -151,12 +155,12 @@ def split_by_year(config, dbsession, group):
         if config["data"]["year_field"] in item.attributes and item.attributes[config["data"]["year_field"]]:
             years.append(item.attributes[config["data"]["year_field"]])
             with_year = with_year + 1
-    if with_year / len(group.items) > 0.95:
+    if with_year / len(group.items) > 0.95:  # noqa: PLR2004
         common = [(int(v), c) for v, c in Counter(years).most_common()]
         start_year = min([c for c, _ in common])
         end_year = max([c for c, _ in common])
         if start_year != end_year:
-            if (end_year - start_year) <= 100 and (end_year - start_year) > 10:
+            if (end_year - start_year) <= 100 and (end_year - start_year) > 10:  # noqa: PLR2004
                 start_decade = math.floor(start_year / 10)
                 end_decade = math.floor(end_year / 10)
                 decades = []
@@ -176,7 +180,7 @@ def split_by_year(config, dbsession, group):
                                     decades[-1][1] = decades[-1][1] + 1
                 idx = 0
                 while idx < len(decades) - 1:
-                    if decades[idx][1] + decades[idx + 1][1] < 100:
+                    if decades[idx][1] + decades[idx + 1][1] < 100:  # noqa: PLR2004
                         decades[idx][0].extend(decades[idx + 1][0])
                         decades[idx][1] = decades[idx][1] + decades[idx + 1][1]
                         decades.pop(idx + 1)
@@ -212,7 +216,7 @@ def split_by_year(config, dbsession, group):
                     for item in list(group.items):
                         item.group = new_group
                 return True
-            elif (end_year - start_year) > 100:
+            elif (end_year - start_year) > 100:  # noqa: PLR2004
                 start_century = math.floor(start_year / 100)
                 end_century = math.floor(end_year / 100)
                 centuries = []
@@ -232,7 +236,7 @@ def split_by_year(config, dbsession, group):
                                     centuries[-1][1] = centuries[-1][1] + 1
                 idx = 0
                 while idx < len(centuries) - 1:
-                    if centuries[idx][1] + centuries[idx + 1][1] < 100:
+                    if centuries[idx][1] + centuries[idx + 1][1] < 100:  # noqa: PLR2004
                         centuries[idx][0].extend(centuries[idx + 1][0])
                         centuries[idx][1] = centuries[idx][1] + centuries[idx + 1][1]
                         centuries.pop(idx + 1)
@@ -252,30 +256,30 @@ def split_by_year(config, dbsession, group):
                                 if new_group is None:
                                     if len(years) == 1:
                                         century = math.floor(years[0] / 100) + 1
-                                        if century % 10 == 1 and century != 11:
+                                        if century % 10 == 1 and century != 11:  # noqa: PLR2004
                                             label = f"{century}st"
-                                        elif century % 10 == 2 and century != 12:
+                                        elif century % 10 == 2 and century != 12:  # noqa: PLR2004
                                             label = f"{century}nd"
-                                        elif century % 10 == 3 and century != 13:
+                                        elif century % 10 == 3 and century != 13:  # noqa: PLR2004
                                             label = f"{century}rd"
                                         else:
                                             label = f"{century}th"
                                     else:
                                         century = math.floor(years[0] / 100) + 1
-                                        if century % 10 == 1 and century != 11:
+                                        if century % 10 == 1 and century != 11:  # noqa: PLR2004
                                             start_label = f"{century}st"
-                                        elif century % 10 == 2 and century != 12:
+                                        elif century % 10 == 2 and century != 12:  # noqa: PLR2004
                                             start_label = f"{century}nd"
-                                        elif century % 10 == 3 and century != 13:
+                                        elif century % 10 == 3 and century != 13:  # noqa: PLR2004
                                             start_label = f"{century}rd"
                                         else:
                                             start_label = f"{century}th"
                                         century = math.floor(years[-1] / 100) + 1
-                                        if century % 10 == 1 and century != 11:
+                                        if century % 10 == 1 and century != 11:  # noqa: PLR2004
                                             end_label = f"{century}st"
-                                        elif century % 10 == 2 and century != 12:
+                                        elif century % 10 == 2 and century != 12:  # noqa: PLR2004
                                             end_label = f"{century}nd"
-                                        elif century % 10 == 3 and century != 13:
+                                        elif century % 10 == 3 and century != 13:  # noqa: PLR2004
                                             end_label = f"{century}rd"
                                         else:
                                             end_label = f"{century}th"
@@ -309,13 +313,13 @@ async def split_large_groups_impl(config):
             result = await dbsession.execute(stmt)
             for group in result.scalars():
                 if len(group.children) == 0:
-                    if len(group.items) > 120 and len(group.items) < 300:
+                    if len(group.items) > 120 and len(group.items) < 300:  # noqa: PLR2004
                         if split_by_year(config, dbsession, group):
                             splitting = True
                         else:
                             split_by_similarity(dbsession, group)
                             splitting = True
-                    elif len(group.items) >= 300:
+                    elif len(group.items) >= 300:  # noqa: PLR2004
                         if split_by_attribute(dbsession, group, "concepts"):
                             splitting = True
                         elif split_by_attribute(dbsession, group, "subjects"):
@@ -403,7 +407,7 @@ async def add_parent_groups_impl(config):
                                     dbsession.add(group)
                                 group.parent = parent_group
                                 mapped = True
-                                group = parent_group
+                                group = parent_group  # noqa: PLW2901
                                 if group.parent_id:
                                     break
                             if mapped:

museum_map/cli/items.py

@@ -134,7 +134,7 @@ def apply_nlp(category):
         return []
 
 
-def apply_aat(category, merge=True):
+def apply_aat(category, merge=True):  # noqa: FBT002
     """Expand the category using the AAT."""
     if os.path.exists("aat.json"):
         with open("aat.json") as in_f:
@@ -146,26 +146,29 @@ def apply_aat(category, merge=True):
         response = requests.get(
             "http://vocabsservices.getty.edu/AATService.asmx/AATGetTermMatch",
             params=[("term", f'"{category}"'), ("logop", "and"), ("notes", "")],
+            timeout=300,
         )
-        if response.status_code == 200:
-            subjects = etree.fromstring(response.content).xpath("Subject/Subject_ID/text()")
+        if response.status_code == 200:  # noqa: PLR2004
+            subjects = etree.fromstring(response.content).xpath("Subject/Subject_ID/text()")  # noqa: S320
             hierarchies = []
             for subject in subjects:
                 response2 = requests.get(
-                    "http://vocabsservices.getty.edu/AATService.asmx/AATGetSubject", params=[("subjectID", subject)]
+                    "http://vocabsservices.getty.edu/AATService.asmx/AATGetSubject",
+                    params=[("subjectID", subject)],
+                    timeout=300,
                 )
-                if response.status_code == 200:
-                    hierarchy_text = etree.fromstring(response2.content).xpath("Subject/Hierarchy/text()")
+                if response.status_code == 200:  # noqa: PLR2004
+                    hierarchy_text = etree.fromstring(response2.content).xpath("Subject/Hierarchy/text()")  # noqa: S320
                     if hierarchy_text:
                         hierarchy = []
                         for entry in [h.strip() for h in hierarchy_text[0].split("|") if "<" not in h]:
-                            entry = entry.lower()
+                            entry = entry.lower()  # noqa: PLW2901
                             if "(" in entry:
-                                entry = entry[: entry.find("(")].strip()
+                                entry = entry[: entry.find("(")].strip()  # noqa: PLW2901
                             if entry.endswith(" facet"):
-                                entry = entry[: entry.find(" facet")].strip()
+                                entry = entry[: entry.find(" facet")].strip()  # noqa: PLW2901
                             if entry.endswith(" genres"):
-                                entry = entry[: entry.find(" genres")].strip()
+                                entry = entry[: entry.find(" genres")].strip()  # noqa: PLW2901
                             if entry not in hierarchy:
                                 hierarchy.append(entry)
                         hierarchies.append(hierarchy)

museum_map/cli/layout.py

@@ -1,7 +1,7 @@
 import asyncio
 import math
 from copy import deepcopy
-from random import choice, sample
+from random import choice
 
 import click
 from inflection import pluralize
@@ -166,7 +166,7 @@ async def summarise_rooms(dbsession):
         rooms.scalars(), length=rooms_count.scalar_one(), label="Generating room summaries"
     ) as progress:
         for room in progress:
-            room.sample = choice(room.items)
+            room.sample = choice(room.items)  # noqa: S311
             dbsession.add(room)
     await dbsession.commit()
 
@@ -190,7 +190,7 @@ async def summarise_floors(dbsession):
                     size = await count_items(dbsession, group)
                     while group.split in ["time", "similar", "attribute", "inner"]:
                         parent_result = await dbsession.execute(select(Group).filter(Group.id == group.parent_id))
-                        group = parent_result.scalar_one()
+                        group = parent_result.scalar_one()  # noqa: PLW2901
                     if group in floor_groups:
                         floor_groups[group] = floor_groups[group] + size
                     else:
@@ -202,7 +202,7 @@ async def summarise_floors(dbsession):
                 for group, size in group_sizes:
                     sub_total = sub_total + size
                     dbsession.add(FloorTopic(label=pluralize_label(group.label), group=group, floor=floor, size=size))
-                    if sub_total / total > 0.66666:
+                    if sub_total / total > 0.66666:  # noqa: PLR2004
                         break
             items_result = await dbsession.execute(
                 select(Item).filter(Item.room_id.in_([room.id for room in floor.rooms]))

museum_map/cli/search.py

@@ -20,7 +20,7 @@ async def index_impl(config):
                 index = await client.get_index("items")
                 task = await index.delete()
                 await wait_for_task(client, task.task_uid, timeout_in_ms=None)
-            except Exception:
+            except Exception:  # noqa: S110
                 pass
             items_idx = await client.create_index("items", primary_key="mmap_id")
             stmt = select(Room).options(selectinload(Room.items))

museum_map/cli/server.py

@@ -1,11 +1,9 @@
 from importlib import resources
 
 import click
-from sqlalchemy.ext.asyncio import create_async_engine
 from tornado.ioloop import IOLoop
 from tornado.web import Application, StaticFileHandler
 
-from museum_map.models import create_engine
 from museum_map.server.handlers import (
     APICollectionHandler,
     APIConfigHandler,

museum_map/models/__init__.py

@@ -15,7 +15,7 @@
 
 def create_engine(config) -> AsyncEngine:
     """Get a new singleton DB engine."""
-    global engine
+    global engine  # noqa: PLW0603
     if engine is None:
         engine = create_async_engine(config["db"]["dsn"])
     return engine
@@ -26,7 +26,7 @@ def create_engine(config) -> AsyncEngine:
 
 def create_sessionmaker(config) -> Callable[[], AsyncSession]:
     """Get a new singleton DB session maker."""
-    global async_sessionmaker
+    global async_sessionmaker  # noqa: PLW0603
     if async_sessionmaker is None:
         async_sessionmaker = sessionmaker(create_engine(config), expire_on_commit=False, class_=AsyncSession)
     return async_sessionmaker

museum_map/models/floor.py

@@ -1,6 +1,5 @@
-from sqlalchemy import Column, ForeignKey, Index, Integer, Table, Unicode, UnicodeText
+from sqlalchemy import Column, ForeignKey, Index, Integer, Table, Unicode
 from sqlalchemy.orm import relationship
-from sqlalchemy_json import NestedMutableJson
 
 from museum_map.models.base import Base
 
@@ -15,7 +14,7 @@
 class Floor(Base):
     __tablename__ = "floors"
 
-    id = Column(Integer, primary_key=True)
+    id = Column(Integer, primary_key=True)  # noqa: A003
     label = Column(Unicode(255))
     level = Column(Integer)
 
@@ -42,7 +41,7 @@ def as_jsonapi(self):
 class FloorTopic(Base):
     __tablename__ = "floor_topics"
 
-    id = Column(Integer, primary_key=True)
+    id = Column(Integer, primary_key=True)  # noqa: A003
     group_id = Column(Integer, ForeignKey("groups.id"))
     floor_id = Column(Integer, ForeignKey("floors.id"))
     label = Column(Unicode(255))

museum_map/models/group.py

@@ -1,14 +1,13 @@
 from sqlalchemy import Column, ForeignKey, Index, Integer, Unicode
 from sqlalchemy.orm import relationship
-from sqlalchemy_json import NestedMutableJson
 
 from museum_map.models.base import Base
 
 
 class Group(Base):
     __tablename__ = "groups"
 
-    id = Column(Integer, primary_key=True)
+    id = Column(Integer, primary_key=True)  # noqa: A003
     parent_id = Column(Integer, ForeignKey("groups.id"))
     value = Column(Unicode(255))
     label = Column(Unicode(255))

museum_map/models/item.py

@@ -8,7 +8,7 @@
 class Item(Base):
     __tablename__ = "items"
 
-    id = Column(Integer, primary_key=True)
+    id = Column(Integer, primary_key=True)  # noqa: A003
     group_id = Column(Integer, ForeignKey("groups.id"))
     room_id = Column(Integer, ForeignKey("rooms.id"))
     attributes = Column(NestedMutableJson)

museum_map/models/room.py

@@ -8,7 +8,7 @@
 class Room(Base):
     __tablename__ = "rooms"
 
-    id = Column(Integer, primary_key=True)
+    id = Column(Integer, primary_key=True)  # noqa: A003
     floor_id = Column(Integer, ForeignKey("floors.id"))
     group_id = Column(Integer, ForeignKey("groups.id"))
     item_id = Column(Integer, ForeignKey("items.id"))