support python >= 3.11

.github/workflows/ci.yml

@@ -19,7 +19,7 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.11'
       - name: Install minimum dependencies
         run: |
           python -m pip install --upgrade pip
@@ -35,7 +35,7 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        python-version: ['3.10', '3.11', '3.12', '3.13', '3.14']
+        python-version: ['3.11', '3.12', '3.13', '3.14']
     steps:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5

INSTALL.rst

@@ -27,11 +27,11 @@ For development, install in editable mode with the ``dev`` extra, which adds
 Requirements
 --------------------------------------------------------------------------------
 
-+  `Python 3.10 <https://python.org>`__
++  `Python 3.11 <https://python.org>`__
 +  `requests 2.28 <https://requests.readthedocs.io>`__
 +  `beautifulsoup4 4.11 <https://www.crummy.com/software/BeautifulSoup>`__
 +  `PyYAML 6.0 <https://pyyaml.org>`__
-+  `pandas 1.5 <https://pandas.pydata.org>`__
++  `pandas 2.2.3 <https://pandas.pydata.org>`__
 +  `airr 2.0 <https://airr-standards.readthedocs.io>`__
 +  `tqdm 4.64 <https://tqdm.github.io>`__
 

docs/conf.py

@@ -1,5 +1,4 @@
 #!/usr/bin/env python3
-# -*- coding: utf-8 -*-
 #
 # sourcerer documentation build configuration file
 #

pyproject.toml

@@ -7,7 +7,7 @@ name = "sourcerer"
 dynamic = ["version"]
 description = "Download data from online immune repertoire databases and format it for Immcantation"
 readme = "README.rst"
-requires-python = ">=3.10"
+requires-python = ">=3.11"
 license = {file = "LICENSE"}
 authors = [{name = "Susanna Marquez"}]
 keywords = ["AIRR", "antibody", "repertoire", "immcantation", "OAS"]
@@ -21,11 +21,17 @@ classifiers = [
 # NB: the airr floor is 2.0 because the streaming validation report depends on
 # RearrangementSchema.validate_header/validate_row. This still satisfies changeo's
 # airr>=1.3.1, so the two coexist in the Immcantation container.
+#
+# NB: the pandas floor is 2.2.3 (not the older 1.5 that satisfies our own code)
+# because pandas wheels built before numpy 2.0 existed are ABI-incompatible with
+# a numpy>=2 runtime: pip resolves the newest numpy that satisfies pandas's own
+# (unbounded) requirement, so an older pandas floor gets paired with a numpy it
+# was never built against. 2.2.3 is the first pandas release built for numpy 2.x.
 dependencies = [
     "requests>=2.28",
     "beautifulsoup4>=4.11",
     "PyYAML>=6.0",
-    "pandas>=1.5",
+    "pandas>=2.2.3",
     "airr>=2.0",
     "tqdm>=4.64",
 ]
@@ -50,7 +56,7 @@ packages = ["src/sourcerer"]
 
 [tool.ruff]
 line-length = 90
-target-version = "py310"
+target-version = "py311"
 
 [tool.ruff.lint]
 select = ["I", "E1", "E4", "E7", "E9", "F", "UP", "N"]

requirements.txt

@@ -1,6 +1,6 @@
 requests>=2.28
 beautifulsoup4>=4.11
 PyYAML>=6.0
-pandas>=1.5
+pandas>=2.2.3
 airr>=2.0
 tqdm>=4.64

src/sourcerer/Provenance.py

@@ -18,7 +18,7 @@
 # Imports
 import logging
 import sys
-from datetime import datetime, timezone
+from datetime import UTC, datetime
 from pathlib import Path
 
 import yaml
@@ -43,7 +43,7 @@ def timestamp():
     Returns:
       str: the current time as an ISO 8601 UTC string.
     """
-    return datetime.now(timezone.utc).strftime('%Y-%m-%dT%H:%M:%SZ')
+    return datetime.now(UTC).strftime('%Y-%m-%dT%H:%M:%SZ')
 
 
 def relativize(path, root):

src/sourcerer/Sources/Oas.py

@@ -25,6 +25,7 @@
 import json
 import logging
 import re
+from datetime import UTC
 from pathlib import Path
 from urllib.parse import urlparse
 
@@ -964,7 +965,7 @@ def harvestSchema(self):
         Returns:
           SourceSchema: the harvested snapshot.
         """
-        from datetime import datetime, timezone
+        from datetime import datetime
 
         from sourcerer.Schema import Collection, Field, SourceSchema
         from sourcerer.Version import __version__
@@ -980,7 +981,7 @@ def harvestSchema(self):
 
         return SourceSchema(
             source=self.name,
-            harvested=datetime.now(timezone.utc).strftime('%Y-%m-%dT%H:%M:%SZ'),
+            harvested=datetime.now(UTC).strftime('%Y-%m-%dT%H:%M:%SZ'),
             harvested_by='sourcerer %s' % __version__,
             source_urls={'paired_form': PAIRED_FORM_URL,
                          'unpaired_form': UNPAIRED_FORM_URL,
@@ -1106,13 +1107,13 @@ def enrichCatalog(self, rows, limit=None, force=False):
         Returns:
           int: how many units were successfully enriched.
         """
-        from datetime import datetime, timezone
+        from datetime import datetime
 
         pending = list(rows) if force else [x for x in rows if needsDetail(x)]
         if limit is not None:
             pending = pending[:limit]
 
-        stamp = datetime.now(timezone.utc).strftime('%Y-%m-%dT%H:%M:%SZ')
+        stamp = datetime.now(UTC).strftime('%Y-%m-%dT%H:%M:%SZ')
         enriched = 0
         for row in pending:
             url = '%s?unit=%s' % (DETAIL_URL % row['collection'], row['unit_id'])

tests/test_Packaging.py

@@ -8,9 +8,8 @@
 # Imports
 import os
 import re
-import unittest
-
 import tomllib
+import unittest
 
 # Sourcerer imports
 import sourcerer