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 ffd3f22
Browse filesBrowse the repository at this point in the historyBrowse files
chore(deps): Bump openjd-* Rust crates to 0.7.0 (#359)
* chore(deps): Bump openjd-* Rust crates to 0.7.0
openjd-expr 0.6.0 -> 0.7.0, openjd-model 0.6.1 -> 0.7.0, and
openjd-sessions 0.5.6 -> 0.5.7.
Three upstream changes land, reconciled against a source diff of the
published crates rather than the changelog alone:
* openjd-rs#374 escapes control characters, quotes and backslashes in
repr_py and repr_python. Reachable here through ExprValue.__repr__,
which previously emitted literals CPython cannot parse (a raw newline
terminates the string, and a NUL cannot appear in source at all) or
that parse as a different value -- 'a\b' is a backspace.
* openjd-rs#373 changes FormatString::validate_expressions to take a
target_type and return StaticResolution. This is the breaking change
the minor bump carries, and the changelog did not mention the new
parameter. The binding passes None, matching the resolve and
resolve_string calls above, and discards the returned value: the
Python method stays pass/fail and still returns None on success.
* openjd-rs#369 bounds child output reading in the Windows session
helper runner. Not reachable from this repo's tests; openjd-sessions
forwards to it from subprocess.rs and its coverage lives upstream.
TestExprValueReprEscaping pins the #374 behaviour over 28 inputs --
quotes, backslashes, the C0 controls, DEL, and the non-ASCII characters
CPython escapes by category -- using CPython's own repr() as the oracle,
which is the contract Expression Language 2.2.6 states. It adds an
eval(repr(v)) == v round-trip and negative controls for numeric and
keyword text that must pass through unaltered. Reverting the version
pins fails 60 of these cases.
test_repr_list_path_with_format and test_repr_list_list_path_with_format
pinned the old bug: under WINDOWS the normalised '\a' was emitted
unescaped, which Python parses as BEL. Both now assert the escaped
spelling and round-trip, so nothing regressed -- the bump closed a
silent-corruption path those tests had frozen.
THIRD-PARTY-LICENSES.txt regenerated with
scripts/check_third_party_licenses.sh --update; only the three crate
versions changed, with no new transitive dependencies.
Signed-off-by: David Leong <116610336+leongdl@users.noreply.github.com>
* docs: Sync the validate_expressions docs and note the Zs control
The doc comment on the binding moved to the 3-argument crate signature
but its two derived copies did not, leaving three descriptions of one
method disagreeing.
_openjd_rs.pyi carried the old wording verbatim, including the
paragraphs above it that this branch never touched, which confirms the
stub is generated from the doc comment. Regenerated by hand: the local
scripts/generate_stubs.sh cannot run on macOS -- its GNU `sed -i` patch
step fails on BSD sed, and once applied manually the patch is inert
because building stub_gen against the local Python 3.13 defines Py_3_10,
so the `#[cfg(Py_3_10)]` guard admits a PyEncodingWarning that this pyo3
does not export. No workflow verifies stub freshness, so CI could not
have caught the staleness either way.
Also records why "a b" sits in ESCAPING_CASES. It is not a non-ASCII
space flattened in editing; it is copied from the upstream py_escape
tests, where it is the negative half of the Zs discrimination -- U+0020,
U+00A0 and U+3000 are all Zs and CPython escapes only the latter two.
The comment now says so, since the enumeration above it listed only the
characters that do get escaped.
Signed-off-by: David Leong <116610336+leongdl@users.noreply.github.com>
---------
Signed-off-by: David Leong <116610336+leongdl@users.noreply.github.com>
0 commit comments