From 7cf6640caaa8117fec5dd798372dcbe52be5a1cd Mon Sep 17 00:00:00 2001
From: Michael Osthege <michael.osthege@outlook.com>
Date: Sun, 20 Jun 2021 13:35:16 +0200
Subject: [PATCH] Analyze included/excluded test files based on YAML job matrix

Compared to the previous regex-based approach, this can distinguish by OS and floatX setting, allowing for more informative outputs.
---
 .pre-commit-config.yaml                |   1 +
 scripts/check_all_tests_are_covered.py | 101 +++++++++++++++++++------
 2 files changed, 79 insertions(+), 23 deletions(-)

diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
index 4739980765..cef12c6d4b 100644
--- a/.pre-commit-config.yaml
+++ b/.pre-commit-config.yaml
@@ -36,6 +36,7 @@ repos:
 - repo: local
   hooks:
     - id: check-no-tests-are-ignored
+      additional_dependencies: [pandas,pyyaml]
       entry: python scripts/check_all_tests_are_covered.py
       files: ^\.github/workflows/pytest\.yml$
       language: python
diff --git a/scripts/check_all_tests_are_covered.py b/scripts/check_all_tests_are_covered.py
index 4076ef552a..0f38437ec0 100644
--- a/scripts/check_all_tests_are_covered.py
+++ b/scripts/check_all_tests_are_covered.py
@@ -6,38 +6,93 @@
 This is intended to be used as a pre-commit hook, see `.pre-commit-config.yaml`.
 You can run it manually with `pre-commit run check-no-tests-are-ignored --all`.
 """
+import itertools
 import logging
-import re
+import os
 
 from pathlib import Path
 
+import pandas
+import yaml
+
 _log = logging.getLogger(__file__)
+logging.basicConfig(level=logging.DEBUG)
 
 
-if __name__ == "__main__":
-    testing_workflows = ["jaxtests.yml", "pytest.yml"]
-    ignored = set()
-    non_ignored = set()
-    for wfyml in testing_workflows:
-        pytest_ci_job = Path(".github") / "workflows" / wfyml
-        txt = pytest_ci_job.read_text()
-        ignored = set(re.findall(r"(?<=--ignore=)(pymc3/tests.*\.py)", txt))
-        non_ignored = non_ignored.union(set(re.findall(r"(?<!--ignore=)(pymc3/tests.*\.py)", txt)))
-    # Summarize
-    ignored_by_all = ignored.difference(non_ignored)
-    run_multiple_times = non_ignored.difference(ignored)
+def find_testfiles():
+    dp_repo = Path(__file__).parent.parent
+    all_tests = {
+        str(fp.relative_to(dp_repo)).replace(os.sep, "/")
+        for fp in (dp_repo / "pymc3" / "tests").glob("**/test_*.py")
+    }
+    _log.info("Found %i tests in total.", len(all_tests))
+    return all_tests
+
+
+def from_yaml():
+    """Determins how often each test file is run per platform and floatX setting.
+
+    An exception is raised if tests run multiple times with the same configuration.
+    """
+    # First collect the matrix definitions from testing workflows
+    matrices = {}
+    for wf in ["pytest.yml", "windows.yml", "arviz_compat.yml", "jaxtests.yml"]:
+        wfname = wf.strip(".yml")
+        wfdef = yaml.safe_load(open(Path(".github", "workflows", wf)))
+        for jobname, jobdef in wfdef["jobs"].items():
+            matrix = jobdef.get("strategy", {}).get("matrix", {})
+            if matrix:
+                matrices[(wfname, jobname)] = matrix
+            else:
+                _log.warning("No matrix in %s/%s", wf, jobname)
+
+    # Now create an empty DataFrame to count based on OS/floatX/testfile
+    all_os = []
+    all_floatX = []
+    for matrix in matrices.values():
+        all_os += matrix["os"]
+        all_floatX += matrix["floatx"]
+    all_os = tuple(sorted(set(all_os)))
+    all_floatX = tuple(sorted(set(all_floatX)))
+    all_tests = find_testfiles()
+
+    df = pandas.DataFrame(
+        columns=pandas.MultiIndex.from_product(
+            [sorted(all_floatX), sorted(all_os)], names=["floatX", "os"]
+        ),
+        index=pandas.Index(sorted(all_tests), name="testfile"),
+    )
+    df.loc[:, :] = 0
+
+    # Count how often the testfiles are included in job definitions
+    for matrix in matrices.values():
+        for os_, floatX, subset in itertools.product(
+            matrix["os"], matrix["floatx"], matrix["test-subset"]
+        ):
+            testfiles = subset.split("\n")
+            ignored = {item.strip("--ignore=") for item in testfiles if item.startswith("--ignore")}
+            included = {item for item in testfiles if item and not item.startswith("--ignore")}
+            if ignored and not included:
+                # if no testfile is specified explicitly pytest runs all except the ignored ones
+                included = all_tests - ignored
+
+            for testfile in included:
+                df.loc[testfile, (floatX, os_)] += 1
+
+    ignored_by_all = set(df[df.eq(0).all(axis=1)].index)
+    run_multiple_times = set(df[df.gt(1).any(axis=1)].index)
+
+    # Print summary, warnings and raise errors on unwanted configurations
+    _log.info("Number of test runs (❌=0, ✅=once)\n%s", df.replace(0, "❌").replace(1, "✅"))
 
     if ignored_by_all:
-        _log.warning(
-            f"The following {len(ignored_by_all)} tests are completely ignored: {ignored_by_all}"
-        )
+        _log.warning("%i tests are completely ignored:\n%s", len(ignored_by_all), ignored_by_all)
     if run_multiple_times:
-        _log.warning(
-            f"The following {len(run_multiple_times)} tests are run multiple times: {run_multiple_times}"
+        raise Exception(
+            f"{len(run_multiple_times)} tests are run multiple times with the same OS and floatX setting:\n{run_multiple_times}"
         )
-    if not (ignored_by_all or run_multiple_times):
-        print(f"✔ All tests will run exactly once.")
+    return
+
 
-    # Temporarily disabled as we're bringing features back for v4:
-    # assert not ignored_by_all
-    assert not run_multiple_times
+if __name__ == "__main__":
+    from_yaml()