Migrate to Python 3.12

.github/workflows/python_actions.yaml

@@ -32,17 +32,15 @@ jobs:
           --health-timeout 5s
           --health-retries 5
     steps:
-    - uses: actions/checkout@v2
-    - uses: actions/setup-python@v2
+    - uses: actions/checkout@v7
+    - uses: actions/setup-python@v5
       with:
-        python-version: '3.8'
+        python-version: '3.12'
 
     - name: Install dependencies
       run: |
-        python -m pip install --upgrade wheel setuptools==57 pip
-        pip install -r requirements.txt
-        pip install -r dev-requirements.txt
-
+        pip install ".[dev]"
+
     - name: Run unittests
       run: |
          py.test

config.py

@@ -14,7 +14,7 @@
 IMAGE_PROXY_RETRIES = 1 # Number of retries for failed upstream image requests (Cantaloupe cold-cache)
 IMAGE_PROXY_RETRY_DELAY = 2 # Seconds to wait between retries
 
-SQLALCHEMY_DATABASE_URI = 'postgres://scan_explorer:scan_explorer@postgres_service/scan_explorer_service'
+SQLALCHEMY_DATABASE_URI = 'postgresql+psycopg2://scan_explorer:scan_explorer@postgres_service/scan_explorer_service'
 SQLALCHEMY_TRACK_MODIFICATIONS = False
 
 OPEN_SEARCH_URL = 'http://opensearch-node1:9200'

pyproject.toml

@@ -0,0 +1,54 @@
+[project]
+name = "scan_explorer_service"
+version = "0.0.1"
+description = "ADS Scan Explorer Service"
+authors = [{ name = "ADS Team", email = "adshelp@cfa.harvard.edu" }]
+license = { text = "MIT" }
+readme = "README.md"
+dependencies = [
+    "adsmutils @ git+https://github.com/adsabs/ADSMicroserviceUtils.git@v2.0.0",
+    "Flask-Limiter==3.8.0",
+    "Flask-Compress==1.24",
+    "iiif-prezi==0.3.0",
+    "SQLAlchemy-Utils==0.42.1",
+    "Jinja2==3.1.6",
+    "markupsafe==3.0.3",
+    "itsdangerous==2.2.0",
+    "werkzeug==2.3.8",
+    "psycopg2-binary==2.9.12",
+    "opensearch-py==3.2.0",
+    "alembic==1.19.1",
+    "img2pdf==0.6.3",
+    "appmap==3.0.1",
+    "boto3==1.43.67",
+    "redis==5.0.8"
+]
+
+[project.optional-dependencies]
+dev = [
+    "Flask-Testing==0.8.1",
+    "testing.postgresql==1.3.0",
+    "pytest==9.1.1",
+    "pytest-cov==7.1.0",
+    "coverage==7.15.4"
+]
+
+[build-system]
+requires = ["setuptools>=62.0.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[tool.setuptools.packages.find]
+include = ["scan_explorer_service*"]
+exclude = ["scan_explorer_service.tests*"]
+
+[tool.pytest.ini_options]
+addopts = "--cov=scan_explorer_service --cov-report=term-missing"
+testpaths = ["scan_explorer_service/tests"]
+pythonpath = ["."]
+
+[tool.black]
+line-length = 88
+target-version = ['py312']
+
+[tool.isort]
+profile = "black"

scan_explorer_service/models.py

@@ -1,7 +1,6 @@
 from flask import current_app
-from sqlalchemy.ext.declarative import declarative_base
 from sqlalchemy import Column, ForeignKey, Integer, String, Table, UniqueConstraint, Enum, Index, or_
-from sqlalchemy.orm import relationship
+from sqlalchemy.orm import declarative_base, relationship
 from sqlalchemy_utils.models import Timestamp
 from scan_explorer_service.utils.utils import url_for_proxy
 import enum

scan_explorer_service/tests/test_metadata.py

@@ -317,15 +317,15 @@ def setUp(self):
     def test_collection_serialized_no_pages(self):
         """S3: Collection.serialized returns thumbnail=None when no pages exist."""
         with self.app.app_context():
-            col = self.app.db.session.query(Collection).get(self.collection_id)
+            col = self.app.db.session.get(Collection, self.collection_id)
             data = col.serialized
             self.assertIsNone(data['thumbnail'])
             self.assertEqual(data['pages'], 0)
 
     def test_article_serialized_no_pages(self):
         """S3: Article.serialized returns thumbnail=None when no pages exist."""
         with self.app.app_context():
-            art = self.app.db.session.query(Article).get(self.article_id)
+            art = self.app.db.session.get(Article, self.article_id)
             data = art.serialized
             self.assertIsNone(data['thumbnail'])
             self.assertEqual(data['pages'], 0)

scan_explorer_service/utils/search_utils.py

@@ -55,7 +55,7 @@ class OrderOptions(str, enum.Enum):
 
 def parse_query_args(args):
     """Parse HTTP request args into a search query string, field dict, pagination, and sort order."""
-    qs = re.sub(':\s*', ':', args.get('q', '', str))
+    qs = re.sub(r':\s*', ':', args.get('q', '', str))
     if not qs or not qs.strip():
         raise ValueError('Query string is required')
 
@@ -88,7 +88,7 @@ def parse_query_string(qs):
 
     check_query(qs_dict)
     #Adds a () around each free search to force OS to look for each individual entry against all default fields
-    for parameter in re.split('\s+', qs_only_free):
+    for parameter in re.split(r'\s+', qs_only_free):
         if parameter.upper() not in ['AND', 'OR', '']:
             qs = qs.replace(str(parameter), "(" + str(parameter) + ")")
 

scan_explorer_service/views/image_proxy.py

@@ -182,7 +182,7 @@ def fetch_article(item, memory_limit):
         return send_file(
             file_stream,
             as_attachment=True,
-            attachment_filename=object_name,
+            download_name=object_name,
             mimetype='application/pdf'
         )
     except Exception as e: