@@ -198,7 +198,7 @@ What is left, and why:
198198 It wants a registry of its own rather than
199199 :meth: `~pcapkit.protocols.protocol.Protocol._decode_next_layer `, which is
200200 only ever called at a layer boundary and appends to the frame's protocol chain.
201- An MLD address record inside a mobility option did not follow MH on the wire,
201+ An MLD address record inside a mobility option does not follow MH on the wire,
202202 so putting it in that chain would make ``layer= `` and ``protocol= `` limits
203203 behave wrongly. Changing the parsed shape from :obj: `bytes ` to
204204 :class: `~pcapkit.protocols.misc.raw.Raw ` also changes what existing captures dump to, so
@@ -276,7 +276,7 @@ complaint and yields nothing useful.
276276 :attr: `TCP.__proto__ <pcapkit.protocols.transport.tcp.TCP.__proto__> ` and
277277 :attr: `UDP.__proto__ <pcapkit.protocols.transport.udp.UDP.__proto__> `, out of
278278 a registry carrying every IANA service name: TCP 20 to FTP-DATA and 21 to FTP,
279- ports 80 and 8080 to HTTP on both TCP and UDP, and UDP 1701 to L2TP .
279+ ports 80 and 8080 to HTTP on both TCP and UDP, and UDP 1701 to L2TPv2 .
280280* :class: `~pcapkit.const.sctp.payload_protocol_identifier.PayloadProtocolIdentifier `
281281 -- the values in :attr: `SCTP.__proto__
282282 <pcapkit.protocols.transport.sctp.SCTP.__proto__> `: PPIDs 60 and 66, each to
@@ -386,8 +386,8 @@ suspect -- is 0.0% of its own cost and 4.4% of a parse, and the logging
386386integration is 0.03% even in the heaviest shape, since every call site is a lazy
387387``%s ``. The IO-batching idea the thread proposed was never the bottleneck.
388388
389- The larger wins this section listed, all outside the parse path, have landed in
390- full or in part:
389+ The larger costs this section listed all lie outside the parse path, and each is
390+ addressed in full or in part:
391391
392392* **The flow dumper reopens its output file once per frame **, in
393393 :class: `~pcapkit.dumpkit.pcap.PCAPIO `'s ``__call__ ``. It does not
@@ -407,11 +407,11 @@ full or in part:
407407 measured at 86% of the IP-reassembly cost plus a 133 ms garbage-collection
408408 bill. Whether unfragmented frames should be emitted at all is the design
409409 question that is left, and it is worth settling deliberately.
410- * **Done. ** Every option was parsed twice -- 2274 schema unpacks for 1137
411- options, the pre-parse always discarded, about 15% of a PCAP-NG extraction.
412- :class: ` ~pcapkit.corekit.fields.collections.OptionField ` reads only the base
413- schema's type field to choose the option schema, rather than unpacking the
414- whole base schema and throwing it away .
410+ * **Done. ** :class: ` ~pcapkit.corekit.fields.collections.OptionField ` reads only
411+ the base schema's type field to choose the option schema, rather than unpacking
412+ the whole base schema and throwing it away. Unpacking it parsed every option
413+ twice -- 2274 schema unpacks for 1137 options, the pre-parse always discarded,
414+ about 15% of a PCAP-NG extraction .
415415
416416Some traps for anyone benchmarking this library. ``reassembly=True `` and
417417``trace=True `` are **no-ops ** without ``ip= ``/``tcp= ``, so a benchmark that passes
@@ -423,10 +423,10 @@ Recursive Dissection, With a Depth Limit
423423
424424**Decided, open to revisit. ** Each layer dissects the next from inside
425425its own parse, so dissecting a frame recurses once per layer, at 9 to 12 Python
426- frames a layer. Deep nesting -- IP in IP, stacked 802.1Q tags, long chains of
427- IPv6 extension headers -- used to exhaust the recursion limit and leave the rest
428- of the frame raw, silently, at a depth that varied with the interpreter and the
429- caller's stack (:issue: `1604 `, :issue: `1610 `).
426+ frames a layer. Without a bound, deep nesting -- IP in IP, stacked 802.1Q tags,
427+ long chains of IPv6 extension headers -- exhausts the recursion limit and leaves the
428+ rest of the frame raw, silently, at a depth that varies with the interpreter and
429+ the caller's stack (:issue: `1604 `, :issue: `1610 `).
430430
431431Recursion stays, with a counted bound:
432432:data: `~pcapkit.utilities.config.FRAME_LAYER_LIMIT ` caps a frame at 64 layers by
@@ -622,9 +622,9 @@ Anyone wanting to run the tests wants the repository, which is where they are.
622622
623623 ``dictdumper ``'s ``PLIST `` writer formats every :class: `~datetime.datetime ` as
624624 ``'%Y-%m-%dT%H:%M:%S.%fZ' ``, always with six fractional digits, and
625- :mod: `plistlib `'s ``<date> `` pattern admits none, so :func: ` plistlib.load `
626- failed on every ``format='plist' `` report with `` AttributeError: 'NoneType'
627- object has no attribute 'groupdict' ``. The upstream defect is
625+ :mod: `plistlib `'s ``<date> `` pattern admits none, so without the workaround
626+ below :func: ` plistlib.load ` fails on every ``format='plist' `` report with
627+ `` AttributeError: 'NoneType' object has no attribute 'groupdict' ``. The upstream defect is
628628 `JarryShaw/DictDumper#122 <https://github.com/JarryShaw/DictDumper/issues/122 >`__.
629629 :func: `pcapkit.dumpkit.common.make_dumper ` works around it (:issue: `1448 `): it
630630 writes each date in UTC to whole seconds, as :func: `plistlib.dump ` does. The
0 commit comments