Update CI

.github/workflows/main.yml

@@ -1,47 +1,37 @@
 name: CI
-
-on:
-  push:
-    branches: [ master ]
-  pull_request:
-    branches: [ master ]
-
+on: [push, pull_request]
 jobs:
-  build:
-
+  test:
     runs-on: ubuntu-latest
     strategy:
       fail-fast: false
       matrix:
         include:
+        - python-version: "3.9"
+          toxenv: min
         - python-version: "3.9"
         - python-version: "3.10"
         - python-version: "3.11"
         - python-version: "3.12"
         - python-version: "3.13"
-
+        - python-version: "3.13"
+          toxenv: pre-commit
+        - python-version: "3.13"
+          toxenv: mypy
+        - python-version: "3.13"
+          toxenv: pylint
+        - python-version: "3.13"
+          toxenv: twinecheck
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
     - name: libddb
       run: |
         sudo apt-get install libdb-dev
-
     - name: Set up Python ${{ matrix.python-version }}
       uses: actions/setup-python@v5
       with:
         python-version: ${{ matrix.python-version }}
-    - name: Cache pip
-      uses: actions/cache@v2
-      with:
-         path: ~/.cache/pip
-         key: ${{ runner.os}}-pip-${{ hashFiles('tests/requirements-test.txt') }}
-         restore-keys: |
-           ${{  runner.os}}-pip-
-           ${{ runner.os}}-
-    - name: Install dependencies
-      run: |
-        python -m pip install --upgrade pip
-        pip install -r tests/requirements-test.txt
-    - name: Test with pytest
+    - name: Run
       run: |
-        pytest
+        pip install -U tox
+        tox -e ${{ matrix.toxenv }}

pyproject.toml

@@ -1,3 +1,74 @@
+[tool.coverage.run]
+branch = true
+include = ["scrapy_deltafetch/*"]
+omit = ["tests/*"]
+disable_warnings = ["include-ignored"]
+
+[tool.coverage.paths]
+source = [
+    "scrapy_deltafetch",
+    ".tox/**/site-packages/scrapy-deltafetch"
+]
+
+[tool.coverage.report]
+# https://github.com/nedbat/coveragepy/issues/831#issuecomment-517778185
+exclude_lines = ["pragma: no cover", "if TYPE_CHECKING:"]
+
+
+
+[tool.pylint.MASTER]
+persistent = "no"
+jobs = 1          # >1 hides results
+
+[tool.pylint."MESSAGES CONTROL"]
+enable = [
+    "useless-suppression",
+]
+disable = [
+    # Ones we want to ignore
+    "attribute-defined-outside-init",
+    "broad-exception-caught",
+    "consider-using-with",
+    "cyclic-import",
+    "disallowed-name",
+    "duplicate-code",  # https://github.com/pylint-dev/pylint/issues/214
+    "fixme",
+    "import-outside-toplevel",
+    "inherit-non-class",  # false positives with create_deprecated_class()
+    "invalid-name",
+    "invalid-overridden-method",
+    "isinstance-second-argument-not-valid-type",  # false positives with create_deprecated_class()
+    "line-too-long",
+    "logging-format-interpolation",
+    "logging-fstring-interpolation",
+    "logging-not-lazy",
+    "missing-docstring",
+    "no-member",
+    "no-name-in-module",  # caught by mypy already
+    "no-value-for-parameter",  # https://github.com/pylint-dev/pylint/issues/3268
+    "not-callable",
+    "protected-access",
+    "redefined-builtin",
+    "redefined-outer-name",
+    "too-few-public-methods",
+    "too-many-ancestors",
+    "too-many-arguments",
+    "too-many-branches",
+    "too-many-function-args",
+    "too-many-instance-attributes",
+    "too-many-lines",
+    "too-many-locals",
+    "too-many-positional-arguments",
+    "too-many-public-methods",
+    "too-many-return-statements",
+    "unused-argument",
+    "unused-import",
+    "unused-variable",
+    "useless-import-alias",  # used as a hint to mypy
+    "useless-return",  # https://github.com/pylint-dev/pylint/issues/6530
+    "wrong-import-position",
+]
+
 [tool.ruff.lint]
 extend-select = [
     # flake8-bugbear
@@ -103,3 +174,6 @@ ignore = [
 [tool.ruff.lint.per-file-ignores]
 # D102: Missing docstring in public method
 "tests/**" = ["D102"]
+
+[tool.ruff.lint.pydocstyle]
+convention = "pep257"

scrapy_deltafetch/middleware.py

@@ -6,7 +6,6 @@
 from scrapy import signals
 from scrapy.exceptions import NotConfigured
 from scrapy.http import Request
-from scrapy.item import Item
 from scrapy.utils.project import data_path
 from scrapy.utils.python import to_bytes
 
@@ -36,6 +35,8 @@ def from_crawler(cls, crawler):  # noqa: D102
         dir = data_path(s.get("DELTAFETCH_DIR", "deltafetch"))
         reset = s.getbool("DELTAFETCH_RESET")
         o = cls(dir, reset, crawler.stats)
+        if o.stats is None:
+            o.stats = crawler.stats
         crawler.signals.connect(o.spider_opened, signal=signals.spider_opened)
         crawler.signals.connect(o.spider_closed, signal=signals.spider_closed)
 
@@ -56,14 +57,14 @@ def spider_opened(self, spider):  # noqa: D102
         reset = self.reset or getattr(spider, "deltafetch_reset", False)
         flag = "n" if reset else "c"
         try:
-            self.db = dbm.open(dbpath, flag=flag)  # noqa: SIM115
+            self.db = dbm.open(str(dbpath), flag=flag)  # noqa: SIM115
         except Exception:
             logger.warning(
                 f"Failed to open DeltaFetch database at {dbpath}, trying to recreate it"
             )
             if dbpath.exists():
                 dbpath.unlink()
-            self.db = dbm.open(dbpath, "c")  # noqa: SIM115
+            self.db = dbm.open(str(dbpath), "c")  # noqa: SIM115
 
     def spider_closed(self, spider):  # noqa: D102
         self.db.close()
@@ -77,7 +78,7 @@ def process_spider_output(self, response, result, spider):  # noqa: D102
                     if self.stats:
                         self.stats.inc_value("deltafetch/skipped", spider=spider)
                     continue
-            elif isinstance(r, (Item, dict)):
+            else:
                 key = self._get_key(response.request)
                 self.db[key] = str(time.time())
                 if self.stats: