a6c62d77df
Fourth and final R7b batch-2 port, checklist-first recipe (docs/design/php-kernel-port-checklist.md). Grammar bump first, validated standalone with the diff ENUMERATED + CLASSIFIED (unlike rust/ruby the php bump is NOT graph-neutral): tree-sitter-php ^0.22 (tree-sitter-wasms, 2023) → v0.24.2, the full HTML-interleaving `php` variant (the walker calls LANGUAGE_PHP, never PHP_ONLY) — crate pinned =0.24.2, wasm built from tag 5b5627f's checked-in php/src/parser.c + scanner.c + shared common/scanner.h (all sha-matched against the crates.io tarball, ABI 14→15). Old-vs-new full-init diffs decompose completely into: (1) the anonymous_class wrapper shape (anon-class nodes/methods re-shape — 2,532 rows), (2) grouped nested-clause skip (absent in the gate repos, fixture-pinned), (3) 32 formerly-erroring files parsing clean (monolog Level.php, symfony Request/Response with 8.4 property hooks), (4) a survey-missed category found at gate time: the 8.4 parenthesis-free `new X()->m()` chaining misparse fix (86 garbage instantiates refs disappear, precision-positive), plus resolution RIPPLE proven mechanically (every remaining ref-table flip pairs 1:1 with a resolved edge on the opposite side; node rows byte-stable outside 1/3/4). Walker (java.rs chassis + the php specifics) preserves bug-for-bug: the visitNode hook (const_declaration at ANY scope → bare `constant` nodes, values never walked; trait-use → implements refs WITH filePath via the ruby port's REF_FLAG_FILE_PATH wire slot), FIRST-namespace whole-file scoping (braced namespaces scope nothing; namespaced files DROP top-level const value-ref targets), the import trio (single/aliased/grouped incl. the nested-clause skip, include/require static-literal-only, `Foo\Bar::Baz` use refs), the call-encoding zoo (DOT-joined scoped calls, `this->prop.m` #1251 encoding, `Cls::factory().m` fluent with inner args dropped, nullsafe `?->` emitting nothing, unsuppressed literal receivers), interface multi-extends first-base-only drop, anon-class methods as file-level functions (top) or vanishing (in-body), property type-hints emitting no field refs, the final-modifier-as-type signature quirk, HOF-gated string callables (skipGate) + array callables, and the `name`-node value-ref reader. Gates: sweeps 0-diff monolog 217/217, laravel-framework 3007/3008, symfony 10726/10737 (13,950 files byte-parity; 12 deferrals = exactly the predicted genuinely-broken fixtures, ≈0–0.1%); full-init dumps byte-identical ×3 (16.1k/354.2k/702.8k lines); kernel-php-parity suite (torture + drupal .module + leading-HTML fixtures, CRLF variants, wire-flag pin, defer) + php grammar-parity row; full suite 2,622 green ×2 under CODEGRAPH_KERNEL_EXPECT=1. DEFAULT_ROUTED += php (13 languages). Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
52 lines
1.8 KiB
TOML
52 lines
1.8 KiB
TOML
[package]
|
|
name = "codegraph-kernel"
|
|
version = "0.1.0"
|
|
edition = "2021"
|
|
license = "MIT"
|
|
publish = false
|
|
description = "Native extraction kernel for CodeGraph — tree-sitter parse+extract with one JS boundary crossing per file"
|
|
|
|
[lib]
|
|
crate-type = ["cdylib"]
|
|
|
|
[dependencies]
|
|
napi = { version = "3", default-features = false, features = ["napi8"] }
|
|
napi-derive = "3"
|
|
tree-sitter = "0.25"
|
|
sha2 = "0.10"
|
|
regex = "1"
|
|
|
|
# Grammars — MUST stay revision-matched with the wasm grammars the fallback
|
|
# path loads (tree-sitter-wasms npm package / src/extraction/wasm/). The
|
|
# kernel-grammar-parity test asserts node-kind-table equality at test time;
|
|
# bump these together with the wasm side or that gate fails.
|
|
tree-sitter-typescript = "0.23"
|
|
tree-sitter-javascript = "0.25"
|
|
tree-sitter-java = "0.23"
|
|
tree-sitter-python = "0.23"
|
|
tree-sitter-go = "0.23"
|
|
# Pinned exact: the vendored wasm (src/extraction/wasm/) was built from these
|
|
# tags' checked-in parser.c, sha-matched against these registry tarballs
|
|
# (R7a prep, #1345). A patch bump here without re-vendoring breaks the match.
|
|
tree-sitter-c = "=0.24.2"
|
|
tree-sitter-cpp = "=0.23.4"
|
|
tree-sitter-rust = "=0.24.2"
|
|
# csharp: the vendored wasm (#717) predates the kernel and was verified
|
|
# table-identical to this crate's tarball (ABI 15, STATE_COUNT 8053, node-kind
|
|
# and field tables — csharp checklist header). Bump crate + wasm together.
|
|
tree-sitter-c-sharp = "=0.23.5"
|
|
# ruby: content bump, ABI stays 14 (the v0.23.1 tag predates the ABI-15
|
|
# generator) — kernel-grammar-parity asserts same-revision, not same-ABI.
|
|
tree-sitter-ruby = "=0.23.1"
|
|
# php: the walker calls LANGUAGE_PHP (the full HTML-interleaving variant the
|
|
# wasm ships) — NEVER LANGUAGE_PHP_ONLY, which errors on leading HTML.
|
|
tree-sitter-php = "=0.24.2"
|
|
|
|
[build-dependencies]
|
|
napi-build = "2"
|
|
|
|
[profile.release]
|
|
lto = true
|
|
codegen-units = 1
|
|
strip = "symbols"
|