feat: analyse stored legacy captures
This commit is contained in:
parent
792d92d5ca
commit
22466f0e9e
|
|
@ -41,7 +41,7 @@ Depends on Pass 0 for the selected slice.
|
|||
- [x] WD1.1 Define `schemas/diagnostic.schema.json` with explicit version, metadata, system, collection status, observations, findings, and warnings; adapt fields to actual evidence.
|
||||
- [x] WD1.2 Define stable finding IDs, severity/confidence semantics, evidence references, and how raw evidence is retained. Missing, skipped, and failed checks must not imply health.
|
||||
- [x] WD1.3 Document mapping from legacy capture schemas 1 and 2, including unsupported versions and information that cannot be recovered.
|
||||
- [ ] WD1.4 Define independent collection/offline-analysis CLI contracts: input/output paths, errors, exit codes, dependencies, and compatibility policy.
|
||||
- [x] WD1.4 Define independent collection/offline-analysis CLI contracts: input/output paths, errors, exit codes, dependencies, and compatibility policy.
|
||||
- [x] WD1.5 Add synthetic valid/invalid schema examples and validation tests; document the interface for downstream report adapters without importing their implementation.
|
||||
|
||||
Exit: a consumer can understand and validate diagnostic output using a documented
|
||||
|
|
@ -53,8 +53,8 @@ Depends on Pass 1.
|
|||
|
||||
- [ ] WD2.1 Migrate collection incrementally, preserving Compact/Mid/Full behavior and explicit administrator-only/unavailable checks; do not silently modify the system.
|
||||
- [ ] WD2.2 Separate structured evidence from console presentation; retain raw records where practical and avoid machine-specific absolute paths.
|
||||
- [ ] WD2.3 Implement offline normalization of stored captures without Typst, live Windows access, or sibling repositories.
|
||||
- [ ] WD2.4 Test supported capture versions/modes, malformed input, missing sections, partial collection, and preservation of evidence references against the baseline.
|
||||
- [x] WD2.3 Implement offline normalization of stored captures without Typst, live Windows access, or sibling repositories.
|
||||
- [x] WD2.4 Test supported capture versions/modes, malformed input, missing sections, partial collection, and preservation of evidence references against the baseline.
|
||||
|
||||
Exit: supported evidence can be collected and stored captures normalized through
|
||||
the public interface, with collection limitations documented.
|
||||
|
|
@ -65,9 +65,9 @@ Depends on normalized evidence and the diagnostic contract.
|
|||
|
||||
- [ ] WD3.1 Port reusable rules and watchlist matching with traceable evidence; keep investigation-specific conclusions and organisational recommendations outside this engine.
|
||||
- [ ] WD3.2 Preserve and test event grouping, deduplication, correlation, unknown-event behavior, collection completeness, severity, and confidence.
|
||||
- [ ] WD3.3 Make time-dependent analysis repeatable using a defined reference time; document intentional differences from legacy behavior.
|
||||
- [ ] WD3.4 Emit schema-valid `diagnostic.json`; verify every finding's evidence reference resolves and raw observations remain available.
|
||||
- [ ] WD3.5 Run sanitized regression fixtures for known diagnostic situations without the original machine; record exact commands and results.
|
||||
- [x] WD3.3 Make time-dependent analysis repeatable using a defined reference time; document intentional differences from legacy behavior.
|
||||
- [x] WD3.4 Emit schema-valid `diagnostic.json`; verify every finding's evidence reference resolves and raw observations remain available.
|
||||
- [x] WD3.5 Run sanitized regression fixtures for known diagnostic situations without the original machine; record exact commands and results.
|
||||
|
||||
Exit: offline analysis produces deterministic, evidence-backed diagnostic output
|
||||
without any rendering or report-content dependency.
|
||||
|
|
@ -76,7 +76,7 @@ without any rendering or report-content dependency.
|
|||
|
||||
Depends on the working diagnostic slice.
|
||||
|
||||
- [ ] WD4.1 Correct Jenkins' instruction-file check; enable schema, fixture, and analysis checks as they become available, with accurate coverage reporting.
|
||||
- [x] WD4.1 Correct Jenkins' instruction-file check; enable schema, fixture, and analysis checks as they become available, with accurate coverage reporting.
|
||||
- [ ] WD4.2 Validate native collection on supported Windows/PowerShell environments; clearly document anything not tested by the non-Windows Jenkins agent.
|
||||
- [ ] WD4.3 Document installation, collection, offline analysis, output schema, privacy, dependencies, and troubleshooting from a fresh standalone clone.
|
||||
- [ ] WD4.4 Verify the standalone clone needs neither Reportist, beffroi-reports, the macro repository, nor legacy sources; audit fixtures for identifying data.
|
||||
|
|
@ -87,6 +87,24 @@ valid diagnostic result independently of reporting tools.
|
|||
|
||||
## Handoff log
|
||||
|
||||
### 2026-09-15 — First offline analyser slice
|
||||
|
||||
- Completed WD1.4, WD2.3–WD2.4, WD3.3–WD3.5 and WD4.1 for the bounded first
|
||||
slice. `tools/analyse.py` accepts legacy schemas 1/2, normalizes section status,
|
||||
preserves raw event values/pointers, groups duplicate events and emits validated
|
||||
diagnostic v1 JSON with explicit reference time and source hash.
|
||||
- Migrated the reviewed Service Control Manager Event 7000 rule. Unmatched events
|
||||
are retained as `unanalysed` with zero confidence; partial collection caps known
|
||||
rule confidence at 50. The other 52 rules and watchlist matching remain WD3.1.
|
||||
- Added nine analysis tests across all five sanitized fixtures, deterministic
|
||||
output, evidence links, malformed/missing input, incomplete/unsupported states,
|
||||
and outside-CWD CLI use.
|
||||
- Validation: 19 component tests pass on Python 3.11.14. The integration workspace
|
||||
runs raw fixture → analyser → adapter → Reportist → PDF. Native Windows collection
|
||||
and full legacy-rule parity remain untested.
|
||||
- Next: migrate remaining generic rules in reviewed groups and implement watchlist
|
||||
matching/correlation before native collector work.
|
||||
|
||||
### 2026-09-15 — Planning pass
|
||||
|
||||
- Completed WD0.1–WD0.2; added roadmap and corrected README navigation.
|
||||
|
|
|
|||
|
|
@ -91,7 +91,7 @@ pipeline {
|
|||
conclusion: 'SUCCESS',
|
||||
name: 'Win Diagnostics CI',
|
||||
summary: 'Win Diagnostics passed all currently implemented CI checks.',
|
||||
text: 'Repository and diagnostic contract tests passed. Collector and analysis-engine execution remain pending.',
|
||||
text: 'Repository, diagnostic contract, and first offline-analysis fixture tests passed. Native collection and remaining rules remain pending.',
|
||||
title: 'Win Diagnostics CI passed'
|
||||
)
|
||||
|
||||
|
|
|
|||
17
README.md
17
README.md
|
|
@ -32,7 +32,22 @@ acceptance criteria, and the next-pass handoff.
|
|||
|
||||
The version-1 schema, standalone validator, and synthetic examples are available.
|
||||
See [contract documentation](docs/diagnostic-contract.md) for setup and validation commands.
|
||||
Collection/analysis and PDF rendering are still separate migration tasks.
|
||||
The first offline analysis slice supports stored legacy capture schemas 1 and 2:
|
||||
|
||||
```bash
|
||||
python tools/analyse.py /path/to/capture.json \
|
||||
--evidence-root /path/to \
|
||||
--output /path/to/diagnostic.json \
|
||||
--reference-time 2026-09-15T12:00:00Z \
|
||||
--producer-version "$(git rev-parse HEAD)"
|
||||
```
|
||||
|
||||
It normalizes collection coverage, preserves event values and JSON Pointers,
|
||||
implements the reviewed Service Control Manager Event 7000 rule, and leaves all
|
||||
other events explicitly `unanalysed`. Reference time and producer version are
|
||||
required for reproducibility. Existing output requires `--force`. Exit codes are
|
||||
0 for validated output, 1 for input, validation, or I/O failure, and 2 for invalid
|
||||
CLI usage. Remaining rules and native Windows collection are still migration work.
|
||||
|
||||
## License
|
||||
|
||||
|
|
|
|||
|
|
@ -82,7 +82,25 @@ structure and internal relationships only; it does not prove raw evidence exists
|
|||
With it, the validator checks the capture hash/version, resolves every observation
|
||||
pointer, compares raw values, and rejects paths whose symlinks escape the root.
|
||||
|
||||
## Mapping legacy captures (contract, not yet an implemented converter)
|
||||
## Offline analysis command
|
||||
|
||||
The first converter/analyser slice is available as:
|
||||
|
||||
```bash
|
||||
python tools/analyse.py capture.json \
|
||||
--evidence-root . \
|
||||
--output diagnostic.json \
|
||||
--reference-time 2026-09-15T12:00:00Z \
|
||||
--producer-version VERSION
|
||||
```
|
||||
|
||||
Input must be inside the explicit evidence root so output retains a portable
|
||||
source path. Existing output requires `--force`. Exit codes are 0 for a validated
|
||||
artifact, 1 for input, validation, or I/O failure, and 2 for invalid invocation.
|
||||
The current rule catalog contains only Service Control Manager Event 7000; other
|
||||
captured events remain traceable `unanalysed` findings.
|
||||
|
||||
## Mapping legacy captures
|
||||
|
||||
| Legacy input | Version-1 artifact mapping |
|
||||
| --- | --- |
|
||||
|
|
@ -106,7 +124,8 @@ remain migration comparisons, not new-schema examples.
|
|||
Consumers select by explicit artifact version and reject unsupported versions.
|
||||
Breaking field or semantic changes require a new version and documented migration.
|
||||
Do not relabel raw captures or silently reshape historical artifacts. Contract v1
|
||||
is the initial implementation; no converter or production producer is claimed yet.
|
||||
is the initial implementation. The offline analyser is a bounded migration slice,
|
||||
not yet the complete legacy rule/watchlist engine or collector.
|
||||
|
||||
Schema and format behavior follow [JSON Schema Draft 2020-12](https://json-schema.org/draft/2020-12/json-schema-validation)
|
||||
and the [jsonschema validator documentation](https://python-jsonschema.readthedocs.io/en/stable/validate/).
|
||||
|
|
|
|||
|
|
@ -0,0 +1,124 @@
|
|||
import copy
|
||||
import importlib.util
|
||||
import json
|
||||
from pathlib import Path
|
||||
import subprocess
|
||||
import sys
|
||||
import tempfile
|
||||
import unittest
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[1]
|
||||
FIXTURES = ROOT / "tests" / "fixtures" / "legacy"
|
||||
spec = importlib.util.spec_from_file_location("diagnostic_analyse", ROOT / "tools" / "analyse.py")
|
||||
analyser = importlib.util.module_from_spec(spec)
|
||||
spec.loader.exec_module(analyser)
|
||||
|
||||
|
||||
class AnalyseTests(unittest.TestCase):
|
||||
reference_time = "2026-09-15T12:00:00Z"
|
||||
|
||||
def setUp(self):
|
||||
self.temporary = tempfile.TemporaryDirectory()
|
||||
self.work = Path(self.temporary.name)
|
||||
|
||||
def tearDown(self):
|
||||
self.temporary.cleanup()
|
||||
|
||||
def run_fixture(self, name, output_name=None):
|
||||
return analyser.analyse_file(
|
||||
FIXTURES / name, FIXTURES, self.work / (output_name or name),
|
||||
self.reference_time, "test-revision")
|
||||
|
||||
def test_all_sanitized_legacy_fixtures_produce_valid_artifacts(self):
|
||||
expected = {
|
||||
"windiagnostics-v1.json": ("complete", 1, 1),
|
||||
"windiagnostics-v2-compact.json": ("partial", 0, 0),
|
||||
"windiagnostics-v2-full.json": ("partial", 3, 1),
|
||||
"windiagnostics-v2-partial.json": ("partial", 3, 1),
|
||||
"windiagnostics-watchlist.json": ("partial", 3, 1),
|
||||
}
|
||||
for name, values in expected.items():
|
||||
with self.subTest(name=name):
|
||||
result = self.run_fixture(name)
|
||||
self.assertEqual((result["collection"]["status"], len(result["observations"]),
|
||||
len(result["findings"])), values)
|
||||
|
||||
def test_service_event_rule_is_traceable(self):
|
||||
result = self.run_fixture("windiagnostics-v1.json")
|
||||
finding = result["findings"][0]
|
||||
observation = result["observations"][0]
|
||||
self.assertEqual((finding["severity"], finding["confidence"]), ("warning", 90))
|
||||
self.assertEqual(finding["evidence"], [observation["id"]])
|
||||
self.assertEqual(observation["source_pointer"], "/sections/recent_system_errors/data/0")
|
||||
self.assertEqual(observation["value"]["Id"], 7000)
|
||||
|
||||
def test_unknown_duplicate_events_are_grouped_without_interpretation(self):
|
||||
result = self.run_fixture("windiagnostics-v2-full.json")
|
||||
self.assertEqual(len(result["findings"]), 1)
|
||||
self.assertEqual(result["findings"][0]["severity"], "unanalysed")
|
||||
self.assertEqual(result["findings"][0]["confidence"], 0)
|
||||
self.assertEqual(len(result["findings"][0]["evidence"]), 3)
|
||||
|
||||
def test_partial_collection_caps_known_rule_confidence(self):
|
||||
capture = analyser.validation.load_json(FIXTURES / "windiagnostics-v1.json")
|
||||
capture = copy.deepcopy(capture)
|
||||
capture["sections"]["storage"] = {"status": "unavailable", "count": 0,
|
||||
"data": [], "error": "Synthetic failure"}
|
||||
result = analyser.analyse(capture, "capture.json", "0" * 64,
|
||||
self.reference_time, "test-revision")
|
||||
self.assertEqual(result["collection"]["status"], "partial")
|
||||
self.assertEqual(result["findings"][0]["confidence"], 50)
|
||||
|
||||
def test_unsupported_status_is_preserved_as_limitation(self):
|
||||
result = self.run_fixture("windiagnostics-v2-partial.json")
|
||||
unexpected = [section for section in result["collection"]["sections"].values()
|
||||
if section.get("reason", "").startswith("Legacy capture used unsupported")]
|
||||
self.assertTrue(unexpected)
|
||||
self.assertTrue(any("incomplete" in warning for warning in result["warnings"]))
|
||||
|
||||
def test_unsupported_version_and_bad_reference_time_fail(self):
|
||||
capture = analyser.validation.load_json(FIXTURES / "windiagnostics-v1.json")
|
||||
invalid = copy.deepcopy(capture)
|
||||
invalid["schema_version"] = 3
|
||||
with self.assertRaisesRegex(ValueError, "unsupported"):
|
||||
analyser.analyse(invalid, "capture.json", "0" * 64,
|
||||
self.reference_time, "test-revision")
|
||||
with self.assertRaisesRegex(ValueError, "reference-time"):
|
||||
analyser.analyse(capture, "capture.json", "0" * 64,
|
||||
"2026-09-15", "test-revision")
|
||||
|
||||
def test_missing_sections_and_malformed_json_fail(self):
|
||||
capture = analyser.validation.load_json(FIXTURES / "windiagnostics-v1.json")
|
||||
del capture["sections"]
|
||||
with self.assertRaisesRegex(ValueError, "/sections"):
|
||||
analyser.analyse(capture, "capture.json", "0" * 64,
|
||||
self.reference_time, "test-revision")
|
||||
malformed = self.work / "malformed.json"
|
||||
malformed.write_text('{"schema_version":', encoding="utf-8")
|
||||
with self.assertRaises(ValueError):
|
||||
analyser.analyse_file(malformed, self.work, self.work / "output.json",
|
||||
self.reference_time, "test-revision")
|
||||
|
||||
def test_output_is_deterministic_and_not_overwritten_implicitly(self):
|
||||
first = self.run_fixture("windiagnostics-v1.json", "first.json")
|
||||
second = self.run_fixture("windiagnostics-v1.json", "second.json")
|
||||
self.assertEqual(first, second)
|
||||
self.assertEqual((self.work / "first.json").read_bytes(),
|
||||
(self.work / "second.json").read_bytes())
|
||||
with self.assertRaisesRegex(ValueError, "output exists"):
|
||||
self.run_fixture("windiagnostics-v1.json", "first.json")
|
||||
|
||||
def test_cli_runs_outside_repository(self):
|
||||
output = self.work / "diagnostic.json"
|
||||
result = subprocess.run([
|
||||
sys.executable, str(ROOT / "tools" / "analyse.py"),
|
||||
str(FIXTURES / "windiagnostics-v1.json"),
|
||||
"--evidence-root", str(FIXTURES), "--output", str(output),
|
||||
"--reference-time", self.reference_time, "--producer-version", "test-revision",
|
||||
], cwd=self.work, text=True, capture_output=True)
|
||||
self.assertEqual(result.returncode, 0, result.stderr)
|
||||
self.assertTrue(output.is_file())
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
|
@ -0,0 +1,219 @@
|
|||
#!/usr/bin/env python3
|
||||
"""Analyse a stored legacy capture into a validated diagnostic v1 artifact."""
|
||||
|
||||
import argparse
|
||||
from collections import OrderedDict
|
||||
from datetime import datetime
|
||||
import hashlib
|
||||
import importlib.util
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
import re
|
||||
import sys
|
||||
import tempfile
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[1]
|
||||
spec = importlib.util.spec_from_file_location("diagnostic_validation", ROOT / "tools" / "validate.py")
|
||||
validation = importlib.util.module_from_spec(spec)
|
||||
spec.loader.exec_module(validation)
|
||||
|
||||
EVENT_RULES = {
|
||||
("Service Control Manager", 7000): {
|
||||
"severity": "warning",
|
||||
"confidence": 90,
|
||||
"title": "Service Control Manager event 7000",
|
||||
"description": "A configured service or driver failed to start.",
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
def pointer(*parts):
|
||||
return "/" + "/".join(str(part).replace("~", "~0").replace("/", "~1") for part in parts)
|
||||
|
||||
|
||||
def slug(value):
|
||||
result = re.sub(r"[^A-Za-z0-9._:-]+", "-", str(value)).strip("-").lower()
|
||||
return result or "unknown"
|
||||
|
||||
|
||||
def valid_timestamp(value):
|
||||
if not isinstance(value, str):
|
||||
return None
|
||||
try:
|
||||
parsed = datetime.fromisoformat(value.replace("Z", "+00:00"))
|
||||
except ValueError:
|
||||
return None
|
||||
return value if parsed.tzinfo is not None else None
|
||||
|
||||
|
||||
def normalize_section(section):
|
||||
if not isinstance(section, dict):
|
||||
return {"status": "unavailable", "record_count": None, "truncated": False,
|
||||
"reason": "Legacy section is not an object."}
|
||||
source_status = section.get("status")
|
||||
status = source_status if source_status in ("ok", "skipped", "unavailable") else "unavailable"
|
||||
count = section.get("count")
|
||||
if type(count) is not int or count < 0:
|
||||
data = section.get("data")
|
||||
count = len(data) if isinstance(data, list) else None
|
||||
result = {"status": status, "record_count": count,
|
||||
"truncated": bool(section.get("truncated", False))}
|
||||
if status != "ok":
|
||||
reason = section.get("error")
|
||||
if not isinstance(reason, str) or not reason.strip():
|
||||
reason = (f"Legacy capture used unsupported section status: {source_status}."
|
||||
if source_status not in ("skipped", "unavailable")
|
||||
else f"Legacy capture marked section {status} without a reason.")
|
||||
result["reason"] = reason
|
||||
return result
|
||||
|
||||
|
||||
def selected_event_sections(capture):
|
||||
sections = capture["sections"]
|
||||
version = capture["schema_version"]
|
||||
names = (("recent_system_errors", "recent_application_errors") if version == 1 else
|
||||
("recent_system_events", "recent_application_events"))
|
||||
return [(name, sections[name]) for name in names if name in sections]
|
||||
|
||||
|
||||
def analyse(capture, artifact, artifact_hash, reference_time, producer_version):
|
||||
version = capture.get("schema_version")
|
||||
if type(version) is not int or version not in (1, 2):
|
||||
raise ValueError(f"unsupported legacy capture schema version: {version!r}")
|
||||
if not isinstance(capture.get("sections"), dict):
|
||||
raise ValueError("legacy capture requires an object at /sections")
|
||||
collected_at = valid_timestamp(capture.get("generated_at"))
|
||||
if collected_at is None:
|
||||
raise ValueError("/generated_at: expected a timezone-qualified ISO timestamp")
|
||||
if valid_timestamp(reference_time) is None:
|
||||
raise ValueError("--reference-time: expected a timezone-qualified ISO timestamp")
|
||||
|
||||
collection_sections = {name: normalize_section(section)
|
||||
for name, section in capture["sections"].items()}
|
||||
complete = bool(collection_sections) and all(
|
||||
section["status"] == "ok" and not section["truncated"]
|
||||
for section in collection_sections.values())
|
||||
collection_status = "complete" if complete else "partial"
|
||||
observations = []
|
||||
groups = OrderedDict()
|
||||
for section_name, section in selected_event_sections(capture):
|
||||
data = section.get("data", []) if isinstance(section, dict) else []
|
||||
if not isinstance(data, list):
|
||||
continue
|
||||
for index, event in enumerate(data):
|
||||
if not isinstance(event, dict):
|
||||
continue
|
||||
observation_id = f"event-{slug(section_name)}-{index + 1}"
|
||||
observation = {"id": observation_id, "section": section_name,
|
||||
"source_pointer": pointer("sections", section_name, "data", index),
|
||||
"value": event}
|
||||
observed_at = valid_timestamp(event.get("TimeCreated"))
|
||||
if observed_at:
|
||||
observation["observed_at"] = observed_at
|
||||
observations.append(observation)
|
||||
provider = str(event.get("ProviderName", "Unknown provider"))
|
||||
raw_event_id = event.get("Id", "unknown")
|
||||
event_id = raw_event_id if type(raw_event_id) in (int, str) else "unknown"
|
||||
groups.setdefault((provider, event_id), []).append(observation_id)
|
||||
|
||||
findings = []
|
||||
for (provider, event_id), evidence in groups.items():
|
||||
rule = EVENT_RULES.get((provider, event_id))
|
||||
if rule:
|
||||
confidence = min(rule["confidence"], 50) if collection_status != "complete" else rule["confidence"]
|
||||
findings.append({"id": f"event-{slug(provider)}-{slug(event_id)}",
|
||||
"severity": rule["severity"], "confidence": confidence,
|
||||
"title": rule["title"], "description": rule["description"],
|
||||
"evidence": evidence})
|
||||
else:
|
||||
findings.append({"id": f"event-{slug(provider)}-{slug(event_id)}",
|
||||
"severity": "unanalysed", "confidence": 0,
|
||||
"title": f"Unanalysed event: {provider} / {event_id}",
|
||||
"description": "The event is preserved for review; no migrated technical rule matches it.",
|
||||
"evidence": evidence})
|
||||
|
||||
warnings = [str(item) for item in capture.get("warnings", []) if str(item).strip()]
|
||||
if collection_status != "complete":
|
||||
warnings.append("Legacy capture collection is incomplete; finding confidence is capped at 50.")
|
||||
warnings.append(f"Initial migrated analyser supports {len(EVENT_RULES)} event rule; unmatched events remain unanalysed.")
|
||||
system = {"host": capture.get("host", {})}
|
||||
if isinstance(capture.get("summary"), dict):
|
||||
system["legacy_summary"] = capture["summary"]
|
||||
return {
|
||||
"schema_version": 1,
|
||||
"metadata": {"producer": {"name": "win-diagnostics", "version": producer_version},
|
||||
"collected_at": collected_at, "analysis_reference_time": reference_time,
|
||||
"source": {"artifact": artifact, "schema_version": version,
|
||||
"sha256": artifact_hash}},
|
||||
"system": system,
|
||||
"collection": {"mode": capture.get("mode", "Full"), "status": collection_status,
|
||||
"sections": collection_sections},
|
||||
"observations": observations,
|
||||
"findings": findings,
|
||||
"warnings": warnings,
|
||||
}
|
||||
|
||||
|
||||
def analyse_file(input_path, evidence_root, output_path, reference_time, producer_version, force=False):
|
||||
if input_path.is_symlink():
|
||||
raise ValueError(f"{input_path}: input symlinks are not supported")
|
||||
input_path = input_path.resolve()
|
||||
evidence_root = evidence_root.resolve()
|
||||
output_path = output_path.resolve()
|
||||
if not input_path.is_relative_to(evidence_root):
|
||||
raise ValueError(f"{input_path}: input must be inside --evidence-root")
|
||||
if output_path == input_path:
|
||||
raise ValueError("input and output paths must differ")
|
||||
artifact = input_path.relative_to(evidence_root).as_posix()
|
||||
capture = validation.load_json(input_path)
|
||||
result = analyse(capture, artifact, hashlib.sha256(input_path.read_bytes()).hexdigest(),
|
||||
reference_time, producer_version)
|
||||
errors = validation.validate_document(result)
|
||||
if not errors:
|
||||
errors = validation.verify_evidence(result, evidence_root)
|
||||
if errors:
|
||||
raise ValueError("generated diagnostic is invalid:\n" + "\n".join(errors))
|
||||
if output_path.exists() and not force:
|
||||
raise ValueError(f"{output_path}: output exists; use --force to replace it")
|
||||
output_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
descriptor, temporary_name = tempfile.mkstemp(prefix=f".{output_path.name}.", dir=output_path.parent)
|
||||
temporary = Path(temporary_name)
|
||||
try:
|
||||
with os.fdopen(descriptor, "w", encoding="utf-8") as stream:
|
||||
json.dump(result, stream, indent=2, ensure_ascii=False, allow_nan=False)
|
||||
stream.write("\n")
|
||||
if force:
|
||||
os.replace(temporary, output_path)
|
||||
else:
|
||||
os.link(temporary, output_path)
|
||||
finally:
|
||||
temporary.unlink(missing_ok=True)
|
||||
return result
|
||||
|
||||
|
||||
def parser():
|
||||
result = argparse.ArgumentParser(description=__doc__)
|
||||
result.add_argument("input", type=Path)
|
||||
result.add_argument("--evidence-root", required=True, type=Path)
|
||||
result.add_argument("--output", required=True, type=Path)
|
||||
result.add_argument("--reference-time", required=True)
|
||||
result.add_argument("--producer-version", required=True)
|
||||
result.add_argument("--force", action="store_true")
|
||||
return result
|
||||
|
||||
|
||||
def main(argv=None):
|
||||
args = parser().parse_args(argv)
|
||||
try:
|
||||
analyse_file(args.input, args.evidence_root, args.output, args.reference_time,
|
||||
args.producer_version, args.force)
|
||||
except (OSError, ValueError, KeyError, TypeError, RecursionError) as error:
|
||||
print(f"error: {error}", file=sys.stderr)
|
||||
return 1
|
||||
print(f"Wrote validated diagnostic v1: {args.output}")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
sys.exit(main())
|
||||
Reference in New Issue