462 lines
20 KiB
Python
462 lines
20 KiB
Python
#!/usr/bin/env python3
|
|
"""check_coverage.py -- a lane module no collected cell reads is invisible (Q85).
|
|
|
|
THE DEFECT THIS GRADES
|
|
`beam/CHECK` runs every `test_*.py` in this lane through `run_lane_tests.py`.
|
|
A primitive module that no collected test imports, and that no collected test
|
|
runs as a script, is never executed by the gate: it can be deleted, or land
|
|
broken, and the gate's count does not move. Q85 measured the shape three
|
|
times over (`083981e` added `zeller_dow.py`, 38 lines, and `CHECK` read
|
|
`Ran 214` before and after). Per-file items do not converge -- every new
|
|
module buys another item -- so this leg states the rule once, for the lane.
|
|
|
|
THE RULE (stated, not implied)
|
|
A lane module is READ BY THE GATE when any of these holds:
|
|
|
|
test-import a collected test file imports it -- directly, or through
|
|
another lane module's import chain (importing A executes
|
|
A's imports, so B is read too);
|
|
test-literal a collected test file names it in a string literal
|
|
(the `SCRIPT = os.path.join(HERE, "shadow_lint.py")` and
|
|
`from csv_rfc4180 import ...` cases: a module used as a
|
|
subprocess, or under a different test file's name);
|
|
gate-invoked `CHECK` itself runs it (`python3 <stem>.py`), i.e. the
|
|
gate executes it on every tick.
|
|
|
|
"No file named `test_<module>.py`" is NOT the fault -- `csv_rfc4180` has no
|
|
such file and is covered. "Read by nothing the gate runs" is.
|
|
|
|
Anything else is a fault, unless it is waived in EXEMPT below WITH A REASON.
|
|
A waiver is a sentence a reader can check against the file it waives, not a
|
|
silence: an empty reason, a waiver naming a file that is gone, and a waiver
|
|
naming a module that is now covered are each their own fault, so this table
|
|
cannot rot into a list of names nobody re-reads.
|
|
|
|
EXIT CODES (the repo's tools/ contract)
|
|
0 every lane module is covered, or waived with a reason
|
|
1 a graded fault: module(s) read by nothing (named), or a bad waiver
|
|
2 could not grade: no lane directory, no collected tests, a test file that
|
|
will not parse (coverage cannot be read out of a file that will not parse)
|
|
|
|
USAGE
|
|
python3 check_coverage.py [--lane DIR] [--json OUT] [--list] [--selftest]
|
|
"""
|
|
|
|
import argparse
|
|
import ast
|
|
import glob
|
|
import json
|
|
import os
|
|
import re
|
|
import sys
|
|
|
|
DEFAULT_LANE = os.path.dirname(os.path.abspath(__file__))
|
|
|
|
# Modules read by nothing the gate runs, each with the reason. Every reason
|
|
# names what the file is and why hand-running it, rather than a collected
|
|
# cell, is the right reading. Keep this list short: it is a record of
|
|
# exceptions, not a coverage plan.
|
|
EXEMPT = {
|
|
"verify_toposort_none.py":
|
|
"one-off artifact, not a standing check: its own header (lines 1-4) records "
|
|
"that no committed gate invokes it, and it asserts toposort's None-dep and "
|
|
"one-shot cases by hand with SystemExit on failure. Its subject, toposort.py, "
|
|
"is covered by test_toposort.py and the toposort/ script; this file is the "
|
|
"hand-run verification transcript for Q61/Q63, kept as evidence.",
|
|
"verify_toposort_gen.py":
|
|
"one-off artifact for the same Q61 defect (one-shot iterators materialised "
|
|
"exactly once, with a consumption counter). Hand-run against toposort.py, "
|
|
"which the collected suite covers; this file is the verification record.",
|
|
"verify_wordcount_test.py":
|
|
"one-off artifact for wordcount.py, which is not a module of this lane "
|
|
"(it writes /root/troupe-standup/test_verification.txt from a __main__ and "
|
|
"compares a subprocess run against `wc`). It is a host-path transcript, not "
|
|
"a primitive; nothing in the lane imports it.",
|
|
"CHECK_toposort.py":
|
|
"hand-run check for toposort_kahn.py, named CHECK_ so the collector does not "
|
|
"take it (it is not unittest or bare-test shaped for the runner either: its "
|
|
"three graphs are `def test_dag` style cells with no runner). Its subject is "
|
|
"covered from this commit by test_toposort_kahn.py, which ports these three "
|
|
"graphs and adds the cycle cases; kept as the original reading.",
|
|
"_run_ng.py":
|
|
"five-line hand runner: it imports test_next_greater and calls every test_* "
|
|
"in it, printing PASS per cell. Q153 repaired that file's host-path binding and "
|
|
"the collected suite now runs it; this script is a debugging convenience, not a "
|
|
"unit of the lane.",
|
|
"conftest.py":
|
|
"pytest collection hook (two lines: put the lane on sys.path), read by the "
|
|
"collector rather than imported by a test. The lane's gate does not use pytest "
|
|
"at all (Q128), so no cell can import it.",
|
|
}
|
|
|
|
|
|
def module_stem(path):
|
|
return os.path.splitext(os.path.basename(path))[0]
|
|
|
|
|
|
def _parse(path):
|
|
"""ast.parse one file, or None when it will not parse."""
|
|
try:
|
|
with open(path, "r", encoding="utf-8", errors="replace") as fh:
|
|
return ast.parse(fh.read(), filename=path)
|
|
except (OSError, SyntaxError):
|
|
return None
|
|
|
|
|
|
def imported_names(tree):
|
|
"""First components of every import in one parsed file."""
|
|
names = set()
|
|
for node in ast.walk(tree):
|
|
if isinstance(node, ast.Import):
|
|
for alias in node.names:
|
|
names.add(alias.name.split(".")[0])
|
|
elif isinstance(node, ast.ImportFrom):
|
|
if node.level == 0 and node.module:
|
|
names.add(node.module.split(".")[0])
|
|
return names
|
|
|
|
|
|
def string_literals(tree):
|
|
"""Every string constant in one parsed file."""
|
|
return {
|
|
node.value
|
|
for node in ast.walk(tree)
|
|
if isinstance(node, ast.Constant) and isinstance(node.value, str)
|
|
}
|
|
|
|
|
|
def grade(lane, exempt=None):
|
|
"""Grade one lane directory. Returns (rc, rows, notes).
|
|
|
|
rows: list of dicts {module, state, why} -- state is one of
|
|
covered-test-import, covered-transitive, covered-literal, covered-gate,
|
|
exempt, UNCOVERED, WAIVER-MISSING, WAIVER-STALE, WAIVER-NO-REASON.
|
|
"""
|
|
exempt = dict(EXEMPT if exempt is None else exempt)
|
|
# Waivers are keyed by filename ("probe.py"); a bare stem is accepted and
|
|
# normalised here so the table and the census speak the same keys.
|
|
waivers = {}
|
|
for key, reason in exempt.items():
|
|
fname = key if key.endswith(".py") else key + ".py"
|
|
waivers[fname] = reason
|
|
notes = []
|
|
rows = []
|
|
|
|
if not os.path.isdir(lane):
|
|
return 2, rows, ["no lane directory: %s" % lane]
|
|
|
|
lane_py = sorted(glob.glob(os.path.join(lane, "*.py")))
|
|
tests = [p for p in lane_py if os.path.basename(p).startswith("test_")]
|
|
modules = [p for p in lane_py if not os.path.basename(p).startswith("test_")]
|
|
|
|
if not tests:
|
|
return 2, rows, ["no collected tests (test_*.py) in %s: nothing can be read" % lane]
|
|
if not modules:
|
|
return 2, rows, ["no lane modules (*.py minus test_*) in %s: nothing to grade" % lane]
|
|
|
|
lane_names = {module_stem(p) for p in modules}
|
|
files = {module_stem(p): p for p in modules}
|
|
|
|
# --- parse the collected tests; a broken test file is ungradable -------
|
|
test_trees = {}
|
|
for t in tests:
|
|
tree = _parse(t)
|
|
if tree is None:
|
|
return 2, rows, ["collected test file will not parse: %s" % os.path.basename(t)]
|
|
test_trees[t] = tree
|
|
|
|
# --- direct imports and literals from the collected tests --------------
|
|
seeds, seed_why, literals = set(), {}, set()
|
|
for t, tree in test_trees.items():
|
|
for name in imported_names(tree) & lane_names:
|
|
seeds.add(name)
|
|
seed_why.setdefault(name, os.path.basename(t))
|
|
literals |= string_literals(tree)
|
|
|
|
covered, why = {}, {}
|
|
|
|
def cover(name, state, reason):
|
|
if name not in covered:
|
|
covered[name] = state
|
|
why[name] = reason
|
|
|
|
for name in sorted(seeds):
|
|
cover(name, "covered-test-import", "imported by %s" % seed_why[name])
|
|
|
|
for name in sorted(lane_names):
|
|
if name in covered:
|
|
continue
|
|
# A literal counts only when it IS a path to the file: the bare
|
|
# filename (`"shadow_lint.py"`) or a path ending in it
|
|
# (`os.path.join(HERE, "shadow_lint.py")`, `"/root/.../sha256_manifest.py"`).
|
|
# A mention inside prose -- a docstring saying "test_sha256_manifest.py
|
|
# grades ..." -- is not a read, and counting prose is exactly the
|
|
# substring-grep defect Q85's own census had (it reported four modules
|
|
# invisible while a sixth was read by a path constant only).
|
|
def _is_path_literal(lit):
|
|
return (os.path.basename(lit.strip()) == name + ".py"
|
|
and not any(ch.isspace() for ch in lit))
|
|
|
|
if any(_is_path_literal(lit) for lit in literals):
|
|
cover(name, "covered-literal", "the test names the file's path in a literal")
|
|
|
|
# --- transitive closure over the lane's own import graph ---------------
|
|
edges = {}
|
|
for name, path in files.items():
|
|
tree = _parse(path)
|
|
edges[name] = (imported_names(tree) if tree is not None else set()) & lane_names
|
|
if tree is None:
|
|
notes.append("lane module will not parse (its imports are unread): %s.py" % name)
|
|
queue = [n for n in covered if covered[n] == "covered-test-import"]
|
|
while queue:
|
|
cur = queue.pop()
|
|
for nxt in sorted(edges.get(cur, ())):
|
|
if nxt not in covered:
|
|
cover(nxt, "covered-transitive", "imported through %s.py" % cur)
|
|
queue.append(nxt)
|
|
|
|
# --- what the gate itself runs ----------------------------------------
|
|
check_path = os.path.join(lane, "CHECK")
|
|
gate_text = ""
|
|
if os.path.isfile(check_path):
|
|
with open(check_path, "r", encoding="utf-8", errors="replace") as fh:
|
|
gate_text = fh.read()
|
|
else:
|
|
notes.append("no CHECK in %s: gate-invoked coverage is unread" % lane)
|
|
for name in sorted(lane_names):
|
|
if name in covered:
|
|
continue
|
|
if re.search(r"python3\s+(?:\./)?%s\.py\b" % re.escape(name), gate_text):
|
|
cover(name, "covered-gate", "run by CHECK (python3 %s.py)" % name)
|
|
|
|
# --- every module accounted for ---------------------------------------
|
|
for name in sorted(lane_names):
|
|
if name in covered:
|
|
rows.append({"module": name, "state": covered[name], "why": why[name]})
|
|
elif (name + ".py") in waivers:
|
|
reason = (waivers[name + ".py"] or "").strip()
|
|
if not reason:
|
|
rows.append({"module": name, "state": "WAIVER-NO-REASON",
|
|
"why": "waived in EXEMPT with no reason: a waiver needs a sentence"})
|
|
else:
|
|
rows.append({"module": name, "state": "exempt", "why": reason})
|
|
else:
|
|
rows.append({"module": name, "state": "UNCOVERED",
|
|
"why": "imported by no collected test, named by no literal, run by no CHECK step"})
|
|
|
|
# --- the waiver table is itself graded --------------------------------
|
|
for fname in sorted(waivers):
|
|
stem = module_stem(fname)
|
|
if os.path.basename(fname) != fname:
|
|
rows.append({"module": fname, "state": "WAIVER-MISSING",
|
|
"why": "EXEMPT names a path, not a lane module: %r" % fname})
|
|
elif fname not in {os.path.basename(p) for p in modules}:
|
|
rows.append({"module": stem, "state": "WAIVER-MISSING",
|
|
"why": "EXEMPT waives %r, which is not a module in this lane" % fname})
|
|
elif stem in covered:
|
|
rows.append({"module": stem, "state": "WAIVER-STALE",
|
|
"why": "%s is now covered (%s): delete this waiver" % (fname, covered[stem])})
|
|
|
|
faults = [r for r in rows if r["state"] in
|
|
("UNCOVERED", "WAIVER-MISSING", "WAIVER-STALE", "WAIVER-NO-REASON")]
|
|
return (1 if faults else 0), rows, notes
|
|
|
|
|
|
def report(lane, rc, rows, notes, out=sys.stdout):
|
|
states = {}
|
|
for r in rows:
|
|
states[r["state"]] = states.get(r["state"], 0) + 1
|
|
out.write("coverage: %s\n" % lane)
|
|
for r in rows:
|
|
if r["state"] not in ("covered-test-import", "covered-transitive", "covered-gate"):
|
|
out.write(" %-14s %-26s %s\n" % (r["state"], r["module"], r["why"]))
|
|
for note in notes:
|
|
out.write(" note %s\n" % note)
|
|
out.write(
|
|
"coverage: %d module(s): %d covered by a collected test, %d through an import "
|
|
"chain, %d by literal, %d run by CHECK, %d exempt, %d fault(s)\n"
|
|
% (len(rows),
|
|
states.get("covered-test-import", 0), states.get("covered-transitive", 0),
|
|
states.get("covered-literal", 0), states.get("covered-gate", 0),
|
|
states.get("exempt", 0),
|
|
sum(states.get(s, 0) for s in
|
|
("UNCOVERED", "WAIVER-MISSING", "WAIVER-STALE", "WAIVER-NO-REASON"))))
|
|
out.write("coverage: %s\n" % {0: "PASS", 1: "FAULT", 2: "UNGRADABLE"}[rc])
|
|
|
|
|
|
# --------------------------------------------------------------------------
|
|
# selftest: fixture lanes built in a throwaway directory, each one cell.
|
|
# --------------------------------------------------------------------------
|
|
def _fixture(root, name, files, exempt=None, check_text=None):
|
|
"""Build one fixture lane; returns (lane_dir, exempt_dict)."""
|
|
lane = os.path.join(root, name)
|
|
os.makedirs(lane, exist_ok=True)
|
|
for rel, body in files.items():
|
|
path = os.path.join(lane, rel)
|
|
os.makedirs(os.path.dirname(path), exist_ok=True)
|
|
with open(path, "w", encoding="utf-8") as fh:
|
|
fh.write(body)
|
|
if check_text is not None:
|
|
with open(os.path.join(lane, "CHECK"), "w", encoding="utf-8") as fh:
|
|
fh.write(check_text)
|
|
return lane, (exempt or {})
|
|
|
|
|
|
def selftest(tmp):
|
|
cases = []
|
|
|
|
def cell(name, lane, exempt, want_rc, want_states, want_named=None):
|
|
rc, rows, notes = grade(lane, exempt)
|
|
got = {r["module"]: r["state"] for r in rows}
|
|
ok = rc == want_rc
|
|
detail = "rc=%d want %d" % (rc, want_rc)
|
|
for mod, state in want_states.items():
|
|
if got.get(mod) != state:
|
|
ok = False
|
|
detail += "; %s=%r want %r" % (mod, got.get(mod), state)
|
|
if want_named:
|
|
text = "\n".join("%s %s" % (r["state"], r["module"]) for r in rows)
|
|
for needle in want_named:
|
|
if needle not in text:
|
|
ok = False
|
|
detail += "; %r not in the report" % needle
|
|
cases.append({"case": name, "ok": ok, "detail": detail})
|
|
return rc, rows, notes
|
|
|
|
cover_test = "from helper import value\nassert value() == 1\n"
|
|
chain_test = "from first import one\nassert one() == 1\n"
|
|
literal_test = 'import os, subprocess\nSCRIPT = os.path.join(os.path.dirname(__file__), "helper.py")\n'
|
|
|
|
# 1 a collected test imports the module
|
|
lane, ex = _fixture(tmp, "import-covered", {
|
|
"helper.py": "def value():\n return 1\n",
|
|
"test_helper.py": cover_test,
|
|
})
|
|
cell("import-covered", lane, ex, 0, {"helper": "covered-test-import"})
|
|
|
|
# 2 the import chain covers the second module
|
|
lane, ex = _fixture(tmp, "transitive-covered", {
|
|
"first.py": "from second import two\ndef one():\n return two()\n",
|
|
"second.py": "def two():\n return 1\n",
|
|
"test_first.py": chain_test,
|
|
})
|
|
cell("transitive-covered", lane, ex, 0,
|
|
{"first": "covered-test-import", "second": "covered-transitive"})
|
|
|
|
# 3 a filename literal covers a module the test runs, not imports
|
|
lane, ex = _fixture(tmp, "literal-covered", {
|
|
"helper.py": "print('hi')\n",
|
|
"test_run.py": literal_test,
|
|
})
|
|
cell("literal-covered", lane, ex, 0, {"helper": "covered-literal"})
|
|
|
|
# 4 nothing reads it -> red, and the report names it
|
|
lane, ex = _fixture(tmp, "uncovered", {
|
|
"orphan.py": "def f():\n return 1\n",
|
|
"test_other.py": "def test_x():\n assert True\n",
|
|
})
|
|
cell("uncovered-is-red", lane, ex, 1, {"orphan": "UNCOVERED"}, want_named=["UNCOVERED orphan"])
|
|
|
|
# 5 a waiver with a reason is a pass, and the reason is printed
|
|
lane, ex = _fixture(tmp, "exempt-reason", {
|
|
"probe.py": "print('hand run')\n",
|
|
"test_other.py": "def test_x():\n assert True\n",
|
|
}, exempt={"probe.py": "one-off probe, hand-run against a subject the suite covers"})
|
|
rc, rows, _ = cell("exempt-with-reason", lane, ex, 0, {"probe": "exempt"})
|
|
if not any("one-off probe" in r["why"] for r in rows):
|
|
cases[-1]["ok"] = False
|
|
cases[-1]["detail"] += "; reason not printed"
|
|
|
|
# 6 a waiver without a reason is a fault, not a silence
|
|
lane, ex = _fixture(tmp, "exempt-silent", {
|
|
"probe.py": "print('hand run')\n",
|
|
"test_other.py": "def test_x():\n assert True\n",
|
|
}, exempt={"probe.py": " "})
|
|
cell("waiver-needs-a-reason", lane, ex, 1, {"probe": "WAIVER-NO-REASON"})
|
|
|
|
# 7 a waiver naming a file that is gone is a fault
|
|
lane, ex = _fixture(tmp, "exempt-missing", {
|
|
"kept.py": "def f():\n return 1\n",
|
|
"test_kept.py": "from kept import f\nassert f() == 1\n",
|
|
}, exempt={"deleted_last_year.py": "was a probe"})
|
|
cell("waiver-names-a-missing-file", lane, ex, 1,
|
|
{"deleted_last_year": "WAIVER-MISSING"})
|
|
|
|
# 8 a waiver left standing over a now-covered module is a fault
|
|
lane, ex = _fixture(tmp, "exempt-stale", {
|
|
"helper.py": "def value():\n return 1\n",
|
|
"test_helper.py": cover_test,
|
|
}, exempt={"helper.py": "used to be uncovered"})
|
|
cell("waiver-now-covered", lane, ex, 1, {"helper": "WAIVER-STALE"})
|
|
|
|
# 9 a module CHECK runs is covered by the gate itself
|
|
lane, ex = _fixture(tmp, "gate-invoked", {
|
|
"gate_script.py": "print('gate')\n",
|
|
"test_other.py": "def test_x():\n assert True\n",
|
|
}, check_text="#!/bin/bash\npython3 gate_script.py\n")
|
|
cell("gate-invoked", lane, ex, 0, {"gate_script": "covered-gate"})
|
|
|
|
# 10 no collected tests -> cannot grade, rather than "all covered"
|
|
lane, ex = _fixture(tmp, "no-tests", {"orphan.py": "x = 1\n"})
|
|
cell("no-tests-is-ungradable", lane, ex, 2, {})
|
|
|
|
# 11 a test file that will not parse -> cannot grade
|
|
lane, ex = _fixture(tmp, "bad-test", {
|
|
"orphan.py": "x = 1\n",
|
|
"test_broken.py": "def test_x(:\n pass\n",
|
|
})
|
|
cell("unparseable-test-is-ungradable", lane, ex, 2, {})
|
|
|
|
# 12 the falsifiability cell: delete the one test file, the fixture reds
|
|
lane, ex = _fixture(tmp, "mutation", {
|
|
"helper.py": "def value():\n return 1\n",
|
|
"test_helper.py": cover_test,
|
|
})
|
|
first = grade(lane, ex)[0]
|
|
os.remove(os.path.join(lane, "test_helper.py"))
|
|
with open(os.path.join(lane, "test_other.py"), "w", encoding="utf-8") as fh:
|
|
fh.write("def test_x():\n assert True\n")
|
|
second = grade(lane, ex)[0]
|
|
ok = first == 0 and second == 1
|
|
cases.append({"case": "removing-the-cell-reds-it",
|
|
"ok": ok, "detail": "rc %d -> %d (want 0 -> 1)" % (first, second)})
|
|
|
|
# 13 no lane directory
|
|
cases.append({"case": "missing-lane-is-ungradable",
|
|
"ok": grade(os.path.join(tmp, "does-not-exist"), {})[0] == 2,
|
|
"detail": "rc=%d" % grade(os.path.join(tmp, "does-not-exist"), {})[0]})
|
|
|
|
bad = [c for c in cases if not c["ok"]]
|
|
for c in cases:
|
|
print("%-4s %-32s %s" % ("ok" if c["ok"] else "FAIL", c["case"], c["detail"]))
|
|
print("selftest: %d cell(s), %d failed" % (len(cases), len(bad)))
|
|
return 1 if bad else 0
|
|
|
|
|
|
def main(argv=None):
|
|
ap = argparse.ArgumentParser(description="grade lane-module coverage for one lane")
|
|
ap.add_argument("--lane", default=DEFAULT_LANE)
|
|
ap.add_argument("--json", default=None, help="write the row table here")
|
|
ap.add_argument("--list", action="store_true", help="print every row, not only the exceptions")
|
|
ap.add_argument("--selftest", action="store_true")
|
|
args = ap.parse_args(argv)
|
|
|
|
if args.selftest:
|
|
import tempfile
|
|
with tempfile.TemporaryDirectory(prefix="coverage-selftest.") as tmp:
|
|
return selftest(tmp)
|
|
|
|
rc, rows, notes = grade(args.lane)
|
|
if args.list:
|
|
for r in rows:
|
|
print("%-20s %-26s %s" % (r["state"], r["module"], r["why"]))
|
|
report(args.lane, rc, rows, notes)
|
|
if args.json:
|
|
with open(args.json, "w", encoding="utf-8") as fh:
|
|
json.dump({"lane": args.lane, "rc": rc, "rows": rows, "notes": notes}, fh, indent=1)
|
|
return rc
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|