|
| 1 | +# Cross-tool oracle — verified false-positive baseline. |
| 2 | +# |
| 3 | +# Each line is one own-only finding that was triaged against the target's REAL |
| 4 | +# source (at the run commit) and confirmed NOT to be a leak. The comparator |
| 5 | +# (scripts/oracle_compare.py --baseline) moves these out of "Own.NET only" into a |
| 6 | +# separate "Known FP (baselined)" section, so a re-run's triage queue shows only |
| 7 | +# genuinely-new findings. Full per-entry rationale: docs/notes/oracle-known-fps.md. |
| 8 | +# |
| 9 | +# Format (|-delimited, '#' starts a full-line comment, blank lines ignored): |
| 10 | +# <owner/repo> | <file-basename> | <OWN code> | <message-substring> | <reason> |
| 11 | +# |
| 12 | +# The match key is (repo, basename, OWN code, message-substring) — deliberately |
| 13 | +# NOT the line number: re-runs clone the target at its current HEAD and the lines |
| 14 | +# drift, but the field/event/local name in the message is stable. Keep substrings |
| 15 | +# specific enough to bind to exactly the intended finding. |
| 16 | +# |
| 17 | +# This file suppresses ONLY confirmed false positives. True findings stay visible |
| 18 | +# even when benign — e.g. serilog BatchingSink._shutdownSignal (a CTS never |
| 19 | +# Dispose()d) and NLog's XmlParser._xmlSource / FileTarget._reusable*Stream |
| 20 | +# (fields genuinely never disposed, but wrapping managed-memory-only resources). |
| 21 | +# Those are NOT baselined; they are real catches the oracle's leak query misses. |
| 22 | + |
| 23 | +# --- NLog/NLog : all WaitForDispose timer FPs fixed at the source ---------------- |
| 24 | +# All five NLog timers disposed through the `WaitForDispose(this Timer)` sink are now |
| 25 | +# cleared in the extractor — no baseline entries remain. Four (AsyncTaskTarget |
| 26 | +# _taskTimeoutTimer/_lazyWriterTimer, AsyncTargetWrapper _lazyWriterTimer, |
| 27 | +# BufferingTargetWrapper _flushTimer) by CallReleasesReceiver (direct / simple-alias |
| 28 | +# receiver), and TimeoutContinuation _timeoutTimer by RefExchangeNulledField (its |
| 29 | +# receiver is the `Interlocked.Exchange(ref _timeoutTimer, null)` result, now bound to |
| 30 | +# the field). The three remaining NLog own-only findings (XmlParser _xmlSource, |
| 31 | +# FileTarget _reusable*Stream) are genuine undisposed fields, kept visible. |
| 32 | + |
| 33 | +# --- protobuf-net/protobuf-net -------------------------------------------------- |
| 34 | +protobuf-net/protobuf-net | ProtoWriter.BufferWriter.cs | OWN001 | _nullWriter | intentional null-object kept attached for pooled reuse; Dispose() documents "don't cascade dispose to the null one" |
| 35 | +protobuf-net/protobuf-net | ProtoTranscoder.cs | OWN001 | 'sync' | non-product (protobuf 'assorted' sample/extension tree); NetTranscoder is a long-lived singleton holding one ReaderWriterLockSlim for app lifetime |
| 36 | +# CommandLineOptions XsltMessageEncountered was here (self-cycle: source `XsltOptions` is |
| 37 | +# a get-only property over a constructed XsltArgumentList field, handler captures `this`). |
| 38 | +# Now fixed at the source by PropertyReturnsOwnedMember — confirmed cleared on a live |
| 39 | +# protobuf oracle run (own-only 0, the finding absent from own-only and baselined) — deleted. |
| 40 | +protobuf-net/protobuf-net | Page.xaml.cs | OWN001 | local 'timer' | non-product (assorted/ Silverlight sample); the timer is disposed by an enclosing `using (timer) { ... }` the extractor missed |
| 41 | + |
| 42 | +# --- JamesNK/Newtonsoft.Json ---------------------------------------------------- |
| 43 | +JamesNK/Newtonsoft.Json | TraceJsonReader.cs | OWN001 | _textWriter | no-op dispose: a JsonTextWriter over an in-memory StringWriter/StringBuilder holds no unmanaged resource, so leaving it undisposed releases nothing |
| 44 | +JamesNK/Newtonsoft.Json | JsonSerializer.cs | OWN001 | serializer.Error | intra-call self-subscription: the serializer is freshly created from the same JsonSerializerSettings whose .Error handler it subscribes; source and handler are co-lifetimed |
| 45 | + |
| 46 | +# --- JoshClose/CsvHelper -------------------------------------------------------- |
| 47 | +JoshClose/CsvHelper | ConsoleHost.cs | OWN014 | AppDomain.CurrentDomain.ProcessExit | non-product (docs-src/ doc-generator) + process-lived subscriber: ConsoleHost itself lives for the whole process, so promoting it to a process-lived event source changes nothing |
| 48 | +JoshClose/CsvHelper | ConsoleHost.cs | OWN014 | Console.CancelKeyPress | non-product (docs-src/ doc-generator) + process-lived subscriber: same — a process-lived host subscribing to a process-lived event source is not a lifetime leak |
0 commit comments