You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
Commit 37ee3cc
Browse filesBrowse the repository at this point in the historyBrowse files
fix(internet)!: keep MH option 6 prefixes with host bits and option 27 times past 9999 (#2702) (#2709)
- The Mobile Network Prefix option fused its prefix and length into an
IPv6Network, so a prefix with bits set past its length, or a length past
128, raised a bare ValueError. RFC 3963 section 6.2 reads both fields as
given and answers a prefix it cannot use with a status, not a discard, so
the data model keeps them apart, as Home Network Prefix does: prefix_length
is a new required field and prefix is the IPv6Address captured, the breaking
change. The maker checks the length against its 8-bit field alone, takes a
prefix_length keyword, and writes the bits past it.
- The Home Network Prefix option refused a length past 128 to read and to
make. RFC 5213 section 5.3.2 answers a prefix it cannot authorise with a
status, so both take the 8-bit field's width, as option 6 does.
- The Timestamp option turned a 48-bit second count past 9999 into a datetime,
which raised a bare ValueError. RFC 5213 section 5.5 has the LMA answer such
a time with a status rather than discard it, so timestamp is None there and
pmip_timestamp keeps it. The seconds and fraction are no longer summed as one
float, which carried 23:59:59 and 65535/65536 past the year's end.
- The mutation sweep's known crashes and the maker sweep's unparsed maximum go,
and the Windows-range test reads a time past 9999 as Linux does, not raising.
New tests fail on 57a6c36 without the pcapkit/ change; MH and guard modules pass.
0 commit comments