mirror of
https://github.com/abhigyanpatwari/GitNexus.git
synced 2026-09-23 00:41:36 +00:00
Merge branch 'main' into fix/no-stats-flag-effective
This commit is contained in:
commit
ab999eb41b
123 changed files with 9445 additions and 281 deletions
4
.github/workflows/claude.yml
vendored
4
.github/workflows/claude.yml
vendored
|
|
@ -158,6 +158,8 @@ jobs:
|
|||
github_token: ${{ secrets.GITHUB_TOKEN }}
|
||||
allowed_non_write_users: '*'
|
||||
show_full_output: true
|
||||
# Review posts use Bash (`gh`, etc.); default mode asks for approval — impossible in CI.
|
||||
claude_args: '--dangerously-skip-permissions'
|
||||
plugin_marketplaces: 'https://github.com/anthropics/claude-code.git'
|
||||
plugins: 'code-review@claude-code-plugins'
|
||||
prompt: '/code-review:code-review ${{ github.repository }}/pull/${{ steps.pr.outputs.number }}'
|
||||
prompt: '/code-review:code-review https://github.com/${{ github.repository }}/pull/${{ steps.pr.outputs.number }} --comment'
|
||||
|
|
|
|||
|
|
@ -149,11 +149,16 @@ Indexed as **GitNexus** (4325 symbols, 10556 relationships, 300 execution flows)
|
|||
## Keeping the Index Fresh
|
||||
|
||||
```bash
|
||||
npx gitnexus analyze # basic refresh; preserves any existing embeddings
|
||||
npx gitnexus analyze # incremental by default; preserves embeddings
|
||||
npx gitnexus analyze --force # full rebuild from scratch (opt out of incremental)
|
||||
npx gitnexus analyze --embeddings # also generate embeddings for new/changed nodes
|
||||
npx gitnexus analyze --drop-embeddings # explicit opt-in to wipe existing embeddings
|
||||
```
|
||||
|
||||
`analyze` runs **incrementally by default**. The pipeline still parses every file every run (cross-file resolution requires it), but tree-sitter parsing is **served from a content-addressed cache** at `.gitnexus/parse-cache.json` for chunks whose file contents haven't changed since the last run. Only changed-file rows (and their importers) are rewritten in LadybugDB; unchanged-file rows are preserved. Output is byte-equivalent to a full rebuild. Pass `--force` to wipe and re-index from scratch (e.g., to recover from a corrupt index, or after upgrading GitNexus).
|
||||
|
||||
The parse cache key is **content-addressed and version-tagged**: it survives `--force` runs, and is automatically invalidated by a `gitnexus` package upgrade (so a new tree-sitter grammar doesn't silently replay stale parse output). Safe to delete `.gitnexus/parse-cache.json` at any time — it'll be rebuilt on the next analyze.
|
||||
|
||||
Check `.gitnexus/meta.json` `stats.embeddings` (0 = none). A plain `analyze` no longer drops existing vectors — pass `--drop-embeddings` to wipe.
|
||||
|
||||
> Claude Code: PostToolUse hook detects a stale index after `git commit` and `git merge` and prompts the agent to run `analyze`. The hook does not invoke `analyze` itself.
|
||||
|
|
|
|||
|
|
@ -30,9 +30,15 @@ Format: **Trigger → Instruction → Reason**. Append new Signs when the same m
|
|||
### Stale graph after edits
|
||||
|
||||
- **Trigger:** MCP warns index is behind `HEAD`, or search doesn't match latest commit.
|
||||
- **Do:** `npx gitnexus analyze` (plus `--embeddings` if used).
|
||||
- **Do:** `npx gitnexus analyze` (plus `--embeddings` if used). Runs incrementally by default — the pipeline parses every file every run (cross-file resolution requires it), but tree-sitter dispatch is skipped for unchanged file chunks via the content-addressed cache, and only changed-file rows (plus their importers, transitively) are rewritten in LadybugDB.
|
||||
- **Why:** Tools query LadybugDB from last analyze; git changes are invisible until re-indexed.
|
||||
|
||||
### Index seems corrupt or "incremental" is misbehaving
|
||||
|
||||
- **Trigger:** `analyze` produces unexpected results, or `meta.json.incrementalInProgress` is set, or the index is in a half-state after a crash.
|
||||
- **Do:** `npx gitnexus analyze --force` to rebuild from scratch. The dirty-flag check forces this automatically when a previous incremental run didn't complete cleanly, but `--force` is the manual escape hatch. Safe to delete `.gitnexus/parse-cache.json` at any time — content-addressed, will be regenerated.
|
||||
- **Why:** Incremental writeback is selective DB row replacement; if the on-disk state is inconsistent for any reason, a full rebuild is the cheapest path back to a known-good index.
|
||||
|
||||
### Embeddings vanished after analyze
|
||||
|
||||
- **Trigger:** Semantic search quality drops; `stats.embeddings` in `meta.json` is 0 after refresh.
|
||||
|
|
|
|||
|
|
@ -40,11 +40,27 @@ export interface MethodDispatchIndex {
|
|||
readonly mroByOwnerDefId: ReadonlyMap<DefId, readonly DefId[]>;
|
||||
/** Interfaces / traits → classes that implement them. */
|
||||
readonly implsByInterfaceDefId: ReadonlyMap<DefId, readonly DefId[]>;
|
||||
/**
|
||||
* Optional parallel MRO view that EXCLUDES mixin-like augmentation
|
||||
* (e.g., PHP traits). Populated only when the input supplies
|
||||
* `computeExtendsOnlyMro`. Used by the super-branch dispatch in
|
||||
* `receiver-bound-calls` so that `parent::method()` walks the
|
||||
* inheritance chain only, not the trait-augmented one. Undefined for
|
||||
* languages without mixin-like semantics — callers should fall back
|
||||
* to `mroFor` when this is missing.
|
||||
*/
|
||||
readonly extendsOnlyMroByOwnerDefId?: ReadonlyMap<DefId, readonly DefId[]>;
|
||||
|
||||
/** `mroByOwnerDefId.get`, with an empty frozen array on miss. */
|
||||
mroFor(ownerDefId: DefId): readonly DefId[];
|
||||
/** `implsByInterfaceDefId.get`, with an empty frozen array on miss. */
|
||||
implementorsOf(interfaceDefId: DefId): readonly DefId[];
|
||||
/**
|
||||
* `extendsOnlyMroByOwnerDefId.get`, with an empty frozen array on miss.
|
||||
* Undefined when `extendsOnlyMroByOwnerDefId` was not populated; callers
|
||||
* should treat this as equivalent to `mroFor` for non-mixin languages.
|
||||
*/
|
||||
readonly extendsOnlyMroFor?: (ownerDefId: DefId) => readonly DefId[];
|
||||
}
|
||||
|
||||
export interface MethodDispatchInput {
|
||||
|
|
@ -81,12 +97,25 @@ export interface MethodDispatchInput {
|
|||
* write-wins policy and fires at most once per unique owner.
|
||||
*/
|
||||
readonly implementsOf: (ownerDefId: DefId) => readonly DefId[];
|
||||
/**
|
||||
* Optional: return the EXTENDS-only ancestor chain for `ownerDefId`,
|
||||
* excluding the owner itself AND any mixin-like augmentation (e.g.,
|
||||
* PHP traits). Languages without mixin semantics leave this undefined
|
||||
* and the index's `extendsOnlyMroByOwnerDefId` stays unpopulated.
|
||||
*
|
||||
* Same contract as `computeMro`: pure, deterministic, `[]` on no parents.
|
||||
* Called at most once per unique owner (first-write-wins).
|
||||
*/
|
||||
readonly computeExtendsOnlyMro?: (ownerDefId: DefId) => readonly DefId[];
|
||||
}
|
||||
|
||||
// ─── Builder ────────────────────────────────────────────────────────────────
|
||||
|
||||
export function buildMethodDispatchIndex(input: MethodDispatchInput): MethodDispatchIndex {
|
||||
const mroByOwnerDefId = new Map<DefId, readonly DefId[]>();
|
||||
const extendsOnlyByOwnerDefId = input.computeExtendsOnlyMro
|
||||
? new Map<DefId, readonly DefId[]>()
|
||||
: undefined;
|
||||
const implsBuilding = new Map<DefId, DefId[]>();
|
||||
const implsSeen = new Map<DefId, Set<DefId>>();
|
||||
|
||||
|
|
@ -97,6 +126,14 @@ export function buildMethodDispatchIndex(input: MethodDispatchInput): MethodDisp
|
|||
const chain = input.computeMro(ownerId);
|
||||
mroByOwnerDefId.set(ownerId, Object.freeze(chain.slice()));
|
||||
}
|
||||
if (
|
||||
input.computeExtendsOnlyMro !== undefined &&
|
||||
extendsOnlyByOwnerDefId !== undefined &&
|
||||
!extendsOnlyByOwnerDefId.has(ownerId)
|
||||
) {
|
||||
const extOnly = input.computeExtendsOnlyMro(ownerId);
|
||||
extendsOnlyByOwnerDefId.set(ownerId, Object.freeze(extOnly.slice()));
|
||||
}
|
||||
|
||||
for (const ifaceId of input.implementsOf(ownerId)) {
|
||||
let seen = implsSeen.get(ifaceId);
|
||||
|
|
@ -121,7 +158,7 @@ export function buildMethodDispatchIndex(input: MethodDispatchInput): MethodDisp
|
|||
implsByInterfaceDefId.set(ifaceId, Object.freeze(owners.slice()));
|
||||
}
|
||||
|
||||
return wrapIndex(mroByOwnerDefId, implsByInterfaceDefId);
|
||||
return wrapIndex(mroByOwnerDefId, implsByInterfaceDefId, extendsOnlyByOwnerDefId);
|
||||
}
|
||||
|
||||
// ─── Internal ───────────────────────────────────────────────────────────────
|
||||
|
|
@ -131,8 +168,9 @@ const EMPTY: readonly DefId[] = Object.freeze([]);
|
|||
function wrapIndex(
|
||||
mroByOwnerDefId: Map<DefId, readonly DefId[]>,
|
||||
implsByInterfaceDefId: Map<DefId, readonly DefId[]>,
|
||||
extendsOnlyMroByOwnerDefId: Map<DefId, readonly DefId[]> | undefined,
|
||||
): MethodDispatchIndex {
|
||||
return {
|
||||
const base: MethodDispatchIndex = {
|
||||
mroByOwnerDefId,
|
||||
implsByInterfaceDefId,
|
||||
mroFor(ownerDefId: DefId): readonly DefId[] {
|
||||
|
|
@ -142,4 +180,14 @@ function wrapIndex(
|
|||
return implsByInterfaceDefId.get(interfaceDefId) ?? EMPTY;
|
||||
},
|
||||
};
|
||||
if (extendsOnlyMroByOwnerDefId !== undefined) {
|
||||
return {
|
||||
...base,
|
||||
extendsOnlyMroByOwnerDefId,
|
||||
extendsOnlyMroFor(ownerDefId: DefId): readonly DefId[] {
|
||||
return extendsOnlyMroByOwnerDefId.get(ownerDefId) ?? EMPTY;
|
||||
},
|
||||
};
|
||||
}
|
||||
return base;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -423,13 +423,30 @@ function applyArityFilter(
|
|||
}
|
||||
|
||||
let anyCompatible = false;
|
||||
let anyUnknown = false;
|
||||
for (const state of perCandidate.values()) {
|
||||
const verdict = arityFn(callsite, state.def);
|
||||
state.signals.arityVerdict = verdict;
|
||||
if (verdict === 'compatible') anyCompatible = true;
|
||||
else if (verdict === 'unknown') anyUnknown = true;
|
||||
}
|
||||
|
||||
if (!anyCompatible) return;
|
||||
// When ALL candidates are 'incompatible' (none compatible, none unknown),
|
||||
// the call is genuinely arity-broken — drop every candidate so the
|
||||
// registry returns no resolution. This matches the PHP variadic case
|
||||
// f(int $req, ...$rest) called with zero args: every candidate definitively
|
||||
// rejects, and emitting an edge to a definitively-rejected callable is
|
||||
// a false positive. When some candidates are 'unknown' (missing metadata),
|
||||
// keep the set so downstream evidence can break the tie — that's the
|
||||
// original safety-fallback behavior.
|
||||
if (!anyCompatible) {
|
||||
if (!anyUnknown) {
|
||||
for (const defId of perCandidate.keys()) {
|
||||
perCandidate.delete(defId);
|
||||
}
|
||||
}
|
||||
return;
|
||||
}
|
||||
|
||||
// Filter: when at least one compatible candidate exists, drop incompatibles.
|
||||
for (const [defId, state] of perCandidate) {
|
||||
|
|
|
|||
30
gitnexus/package-lock.json
generated
30
gitnexus/package-lock.json
generated
|
|
@ -1600,9 +1600,9 @@
|
|||
"license": "BSD-3-Clause"
|
||||
},
|
||||
"node_modules/@protobufjs/codegen": {
|
||||
"version": "2.0.4",
|
||||
"resolved": "https://registry.npmjs.org/@protobufjs/codegen/-/codegen-2.0.4.tgz",
|
||||
"integrity": "sha512-YyFaikqM5sH0ziFZCN3xDC7zeGaB/d0IUb9CATugHWbd1FRFwWwt4ld4OYMPWu5a3Xe01mGAULCdqhMlPl29Jg==",
|
||||
"version": "2.0.5",
|
||||
"resolved": "https://registry.npmjs.org/@protobufjs/codegen/-/codegen-2.0.5.tgz",
|
||||
"integrity": "sha512-zgXFLzW3Ap33e6d0Wlj4MGIm6Ce8O89n/apUaGNB/jx+hw+ruWEp7EwGUshdLKVRCxZW12fp9r40E1mQrf/34g==",
|
||||
"license": "BSD-3-Clause"
|
||||
},
|
||||
"node_modules/@protobufjs/eventemitter": {
|
||||
|
|
@ -1628,9 +1628,9 @@
|
|||
"license": "BSD-3-Clause"
|
||||
},
|
||||
"node_modules/@protobufjs/inquire": {
|
||||
"version": "1.1.0",
|
||||
"resolved": "https://registry.npmjs.org/@protobufjs/inquire/-/inquire-1.1.0.tgz",
|
||||
"integrity": "sha512-kdSefcPdruJiFMVSbn801t4vFK7KB/5gd2fYvrxhuJYg8ILrmn9SKSX2tZdV6V+ksulWqS7aXjBcRXl3wHoD9Q==",
|
||||
"version": "1.1.1",
|
||||
"resolved": "https://registry.npmjs.org/@protobufjs/inquire/-/inquire-1.1.1.tgz",
|
||||
"integrity": "sha512-mnzgDV26ueAvk7rsbt9L7bE0SuAoqyuys/sMMrmVcN5x9VsxpcG3rqAUSgDyLp0UZlmNfIbQ4fHfCtreVBk8Ew==",
|
||||
"license": "BSD-3-Clause"
|
||||
},
|
||||
"node_modules/@protobufjs/path": {
|
||||
|
|
@ -1646,9 +1646,9 @@
|
|||
"license": "BSD-3-Clause"
|
||||
},
|
||||
"node_modules/@protobufjs/utf8": {
|
||||
"version": "1.1.0",
|
||||
"resolved": "https://registry.npmjs.org/@protobufjs/utf8/-/utf8-1.1.0.tgz",
|
||||
"integrity": "sha512-Vvn3zZrhQZkkBE8LSuW3em98c0FwgO4nxzv6OdSxPKJIEKY2bGbHn+mhGIPerzI4twdxaP8/0+06HBpwf345Lw==",
|
||||
"version": "1.1.1",
|
||||
"resolved": "https://registry.npmjs.org/@protobufjs/utf8/-/utf8-1.1.1.tgz",
|
||||
"integrity": "sha512-oOAWABowe8EAbMyWKM0tYDKi8Yaox52D+HWZhAIJqQXbqe0xI/GV7FhLWqlEKreMkfDjshR5FKgi3mnle0h6Eg==",
|
||||
"license": "BSD-3-Clause"
|
||||
},
|
||||
"node_modules/@rolldown/binding-android-arm64": {
|
||||
|
|
@ -4543,22 +4543,22 @@
|
|||
"license": "MIT"
|
||||
},
|
||||
"node_modules/protobufjs": {
|
||||
"version": "7.5.5",
|
||||
"resolved": "https://registry.npmjs.org/protobufjs/-/protobufjs-7.5.5.tgz",
|
||||
"integrity": "sha512-3wY1AxV+VBNW8Yypfd1yQY9pXnqTAN+KwQxL8iYm3/BjKYMNg4i0owhEe26PWDOMaIrzeeF98Lqd5NGz4omiIg==",
|
||||
"version": "7.5.8",
|
||||
"resolved": "https://registry.npmjs.org/protobufjs/-/protobufjs-7.5.8.tgz",
|
||||
"integrity": "sha512-dvpCIeLPbXZS/Ete7yLaO7RenOdken2NHKykBXbsaGxZT0UTltcarBciw+A78SRQs9iMAAVpsYA+l8b1hTePIA==",
|
||||
"hasInstallScript": true,
|
||||
"license": "BSD-3-Clause",
|
||||
"dependencies": {
|
||||
"@protobufjs/aspromise": "^1.1.2",
|
||||
"@protobufjs/base64": "^1.1.2",
|
||||
"@protobufjs/codegen": "^2.0.4",
|
||||
"@protobufjs/codegen": "^2.0.5",
|
||||
"@protobufjs/eventemitter": "^1.1.0",
|
||||
"@protobufjs/fetch": "^1.1.0",
|
||||
"@protobufjs/float": "^1.0.2",
|
||||
"@protobufjs/inquire": "^1.1.0",
|
||||
"@protobufjs/inquire": "^1.1.1",
|
||||
"@protobufjs/path": "^1.1.2",
|
||||
"@protobufjs/pool": "^1.1.0",
|
||||
"@protobufjs/utf8": "^1.1.0",
|
||||
"@protobufjs/utf8": "^1.1.1",
|
||||
"@types/node": ">=13.7.0",
|
||||
"long": "^5.0.0"
|
||||
},
|
||||
|
|
|
|||
76
gitnexus/src/core/incremental/shadow-candidates.ts
Normal file
76
gitnexus/src/core/incremental/shadow-candidates.ts
Normal file
|
|
@ -0,0 +1,76 @@
|
|||
/**
|
||||
* Shadow-candidate path derivation for incremental indexing.
|
||||
*
|
||||
* Background — Bugbot review on PR #1479:
|
||||
* queryImporters() on a NEWLY ADDED file returns 0 importers in the
|
||||
* pre-pipeline DB, because the new file's IMPORTS rows haven't been
|
||||
* written yet. But pre-existing files may have IMPORTS edges that
|
||||
* *resolved to a sibling path*, and the newcomer can now steal that
|
||||
* resolution under standard JS/TS module-resolution rules. Without
|
||||
* pulling those pre-existing files into the writable set, their
|
||||
* stale CALLS edges remain pointing at the OLD resolution target.
|
||||
*
|
||||
* Given an added file path, this helper enumerates the pre-existing
|
||||
* file paths whose import-resolution claim the newcomer can steal.
|
||||
* Caller filters the candidates against the prior-run `fileHashes`
|
||||
* map so we only query importers of paths that actually existed.
|
||||
*
|
||||
* Shadow patterns covered (resolution-priority-aware):
|
||||
*
|
||||
* (a) Same basename, different extension —
|
||||
* added `foo/bar.ts` shadows `foo/bar.{tsx,js,jsx,mjs,cjs,d.ts}`.
|
||||
* (b) Bare-file beats directory-style index —
|
||||
* added `foo/bar.ts` shadows `foo/bar/index.{ts,tsx,...}`.
|
||||
* (c) Directory-index beats bare-file —
|
||||
* added `foo/index.ts` shadows `foo.{ts,tsx,...}` (rare but real,
|
||||
* e.g. converting a single-file module into a directory module).
|
||||
*
|
||||
* Resolution-order priority is conservatively wide: we enumerate ALL
|
||||
* common extensions because we don't know which the importer actually
|
||||
* specified, and over-seeding is harmless (extra BFS work, but the
|
||||
* subgraph extract still gates write-back by file membership).
|
||||
*
|
||||
* Cross-platform path separators: candidates are emitted with both `/`
|
||||
* and `\` for shadow pattern (b), since the caller's prior fileHashes
|
||||
* map may use either depending on the OS that wrote it.
|
||||
*/
|
||||
|
||||
const SHADOW_EXTS = ['.d.ts', '.tsx', '.ts', '.jsx', '.js', '.mjs', '.cjs'];
|
||||
|
||||
/**
|
||||
* Enumerate pre-existing paths whose import-resolution `added` can steal.
|
||||
*
|
||||
* @param added — repo-relative path of a newly-added file
|
||||
* @returns deduplicated list of candidate paths (NOT filtered against
|
||||
* any known-files set — caller does that)
|
||||
*/
|
||||
export const shadowCandidatesFor = (added: string): string[] => {
|
||||
const ext = SHADOW_EXTS.find((e) => added.endsWith(e));
|
||||
if (!ext) return [];
|
||||
|
||||
const noExt = added.slice(0, -ext.length);
|
||||
const out = new Set<string>();
|
||||
|
||||
// (a) Same basename, different extension.
|
||||
for (const alt of SHADOW_EXTS) {
|
||||
if (alt !== ext) out.add(noExt + alt);
|
||||
}
|
||||
|
||||
// (b) Bare file beats sibling directory-style index.
|
||||
for (const idx of SHADOW_EXTS) {
|
||||
out.add(`${noExt}/index${idx}`);
|
||||
out.add(`${noExt}\\index${idx}`);
|
||||
}
|
||||
|
||||
// (c) New `foo/index.ext` shadows old `foo.ext`.
|
||||
const idxSuffixSlash = '/index';
|
||||
const idxSuffixBack = '\\index';
|
||||
let dir: string | null = null;
|
||||
if (noExt.endsWith(idxSuffixSlash)) dir = noExt.slice(0, -idxSuffixSlash.length);
|
||||
else if (noExt.endsWith(idxSuffixBack)) dir = noExt.slice(0, -idxSuffixBack.length);
|
||||
if (dir !== null) {
|
||||
for (const alt of SHADOW_EXTS) out.add(dir + alt);
|
||||
}
|
||||
|
||||
return [...out];
|
||||
};
|
||||
123
gitnexus/src/core/incremental/subgraph-extract.ts
Normal file
123
gitnexus/src/core/incremental/subgraph-extract.ts
Normal file
|
|
@ -0,0 +1,123 @@
|
|||
/**
|
||||
* Subgraph extraction for incremental DB writeback.
|
||||
*
|
||||
* Given the FULL ctx.graph produced by the pipeline (all files parsed,
|
||||
* all phases run) and the set of file paths whose DB rows must be
|
||||
* replaced, produce a smaller KnowledgeGraph that contains:
|
||||
*
|
||||
* - Every node whose `properties.filePath` is in `toWriteSet`.
|
||||
* - Every graph-wide node (Community, Process) — these are regenerated
|
||||
* each run by the communities/processes phases and must be fully
|
||||
* rewritten.
|
||||
* - Every relationship where AT LEAST ONE endpoint is in the writable
|
||||
* set above. Relationships entirely between unchanged-file nodes
|
||||
* are skipped — their rows are still in the DB and re-inserting
|
||||
* them would PK-conflict at COPY time.
|
||||
*
|
||||
* The resulting subgraph is what gets passed to `loadGraphToLbug` after
|
||||
* the orchestrator has deleted the corresponding DB rows. Hydrated
|
||||
* unchanged-file rows are never touched in the DB.
|
||||
*
|
||||
* # Cross-file edge consistency (Finding 1)
|
||||
*
|
||||
* `extractChangedSubgraph` intentionally does NOT expand the set it is
|
||||
* given — expansion is the orchestrator's job, so the SAME expanded set
|
||||
* can be fed to both `deleteNodesForFile` and this function (asymmetry
|
||||
* between the delete set and the write set silently corrupts the DB).
|
||||
* `computeEffectiveWriteSet` below performs the boundary-crossing 1-hop
|
||||
* walk; the orchestrator composes it with its importer-BFS expansion and
|
||||
* passes the result here.
|
||||
*
|
||||
* Why the 1-hop walk is needed: consider a barrel re-export change —
|
||||
* file C (a barrel) shifts `export { foo } from './b'` to
|
||||
* `export { foo } from './d'`. After scope resolution, file A's CALLS
|
||||
* edge to `foo` resolves to D instead of B, even though A's content is
|
||||
* byte-for-byte identical:
|
||||
*
|
||||
* - Old A→B edge survives in DB (neither A nor B is changed → not deleted)
|
||||
* - New A→D edge is missing (neither A nor D in writable set → skipped)
|
||||
*
|
||||
* Pulling the unchanged-side file of every writable-boundary-crossing
|
||||
* edge into the write set fixes both halves: the orchestrator's
|
||||
* `DETACH DELETE` cleans up the stale unchanged-side rows, and the new
|
||||
* cross-file edges land because at least one endpoint is now writable.
|
||||
*
|
||||
* Limitation (documented): if a file X *stopped* importing from a
|
||||
* changed file C, X has no edge to C in the new graph, so this 1-hop
|
||||
* walk doesn't catch it. The orchestrator's importer-BFS (which reads
|
||||
* IMPORTS from the pre-pipeline DB) covers that case instead.
|
||||
*/
|
||||
|
||||
import type { GraphNode, GraphRelationship } from 'gitnexus-shared';
|
||||
import { createKnowledgeGraph } from '../graph/graph.js';
|
||||
import type { KnowledgeGraph } from '../graph/types.js';
|
||||
|
||||
const isGraphWide = (label: string): boolean => label === 'Community' || label === 'Process';
|
||||
|
||||
/**
|
||||
* Build a Map<nodeId, filePath> for every File-bound node in the graph.
|
||||
* Graph-wide nodes (Community/Process) have no filePath and are filtered.
|
||||
*/
|
||||
const indexNodeFilePaths = (fullGraph: KnowledgeGraph): Map<string, string> => {
|
||||
const idx = new Map<string, string>();
|
||||
fullGraph.forEachNode((n: GraphNode) => {
|
||||
const fp = n.properties?.filePath as string | undefined;
|
||||
if (fp) idx.set(n.id, fp);
|
||||
});
|
||||
return idx;
|
||||
};
|
||||
|
||||
export const extractChangedSubgraph = (
|
||||
fullGraph: KnowledgeGraph,
|
||||
toWriteSet: ReadonlySet<string>,
|
||||
): KnowledgeGraph => {
|
||||
const sub = createKnowledgeGraph();
|
||||
const writableNodeIds = new Set<string>();
|
||||
|
||||
fullGraph.forEachNode((n: GraphNode) => {
|
||||
const filePath = n.properties?.filePath as string | undefined;
|
||||
const include = (filePath && toWriteSet.has(filePath)) || isGraphWide(n.label);
|
||||
if (include) {
|
||||
sub.addNode(n);
|
||||
writableNodeIds.add(n.id);
|
||||
}
|
||||
});
|
||||
|
||||
fullGraph.forEachRelationship((r: GraphRelationship) => {
|
||||
if (writableNodeIds.has(r.sourceId) || writableNodeIds.has(r.targetId)) {
|
||||
sub.addRelationship(r);
|
||||
}
|
||||
});
|
||||
|
||||
return sub;
|
||||
};
|
||||
|
||||
/**
|
||||
* Public — derive the EFFECTIVE write-set: `toWriteSet` expanded by one
|
||||
* hop along every edge in the new graph that crosses the writable
|
||||
* boundary (one endpoint in a writable file, the other in an unchanged
|
||||
* file). The unchanged-side file is pulled in so its stale rows are
|
||||
* deleted + rewritten in lockstep with the changed side.
|
||||
*
|
||||
* Single pass over the edge list. Does NOT mutate `toWriteSet`. The
|
||||
* orchestrator MUST feed the returned set to both `deleteNodesForFile`
|
||||
* and `extractChangedSubgraph` — feeding the unexpanded set to either
|
||||
* one leaves stale rows or PK-conflicts at COPY time.
|
||||
*/
|
||||
export const computeEffectiveWriteSet = (
|
||||
fullGraph: KnowledgeGraph,
|
||||
toWriteSet: ReadonlySet<string>,
|
||||
): Set<string> => {
|
||||
const nodeFilePaths = indexNodeFilePaths(fullGraph);
|
||||
const expanded = new Set<string>(toWriteSet);
|
||||
fullGraph.forEachRelationship((r: GraphRelationship) => {
|
||||
const sourcePath = nodeFilePaths.get(r.sourceId);
|
||||
const targetPath = nodeFilePaths.get(r.targetId);
|
||||
if (!sourcePath || !targetPath) return; // skip edges to graph-wide nodes
|
||||
const sourceWritable = toWriteSet.has(sourcePath);
|
||||
const targetWritable = toWriteSet.has(targetPath);
|
||||
if (sourceWritable && !targetWritable) expanded.add(targetPath);
|
||||
else if (targetWritable && !sourceWritable) expanded.add(sourcePath);
|
||||
});
|
||||
return expanded;
|
||||
};
|
||||
|
|
@ -42,12 +42,14 @@ import { isVerboseIngestionEnabled } from './utils/verbose.js';
|
|||
import { yieldToEventLoop } from './utils/event-loop.js';
|
||||
import { parseSourceSafe } from '../tree-sitter/safe-parse.js';
|
||||
import {
|
||||
CLASS_CONTAINER_TYPES,
|
||||
FUNCTION_NODE_TYPES,
|
||||
findEnclosingClassId,
|
||||
findEnclosingClassInfo,
|
||||
genericFuncName,
|
||||
inferFunctionLabel,
|
||||
} from './utils/ast-helpers.js';
|
||||
import type { FieldInfo, FieldExtractorContext } from './field-types.js';
|
||||
import type { LanguageProvider } from './language-provider.js';
|
||||
import { typeTagForId, constTagForId, buildCollisionGroups } from './utils/method-props.js';
|
||||
import type { MethodInfo } from './method-types.js';
|
||||
import {
|
||||
|
|
@ -77,6 +79,62 @@ import type { LiteralTypeInferrer } from './type-extractors/types.js';
|
|||
import type { SyntaxNode } from './utils/ast-helpers.js';
|
||||
|
||||
import { logger } from '../logger.js';
|
||||
|
||||
// ── Property-prepass helpers (parity with parse-worker.ts) ──
|
||||
// These mirror the sequential-path equivalents in parse-worker.ts so the main-
|
||||
// thread `processCalls` pre-pass produces byte-identical Property nodes/symbols
|
||||
// to the worker pool. Drift between the two paths breaks the
|
||||
// `incremental ≡ --force` invariant the moment a repo crosses the worker
|
||||
// threshold between runs.
|
||||
|
||||
/** Walk up to the nearest enclosing class/struct/interface AST node. */
|
||||
const findEnclosingClassNode = (node: SyntaxNode): SyntaxNode | null => {
|
||||
let current = node.parent;
|
||||
while (current) {
|
||||
if (CLASS_CONTAINER_TYPES.has(current.type)) return current;
|
||||
current = current.parent;
|
||||
}
|
||||
return null;
|
||||
};
|
||||
|
||||
/** No-op SymbolTable stub for FieldExtractorContext — matches parse-worker. */
|
||||
const NOOP_SYMBOL_TABLE: SymbolTableReader = {
|
||||
lookupExact: () => undefined,
|
||||
lookupExactFull: () => undefined,
|
||||
lookupExactAll: () => [],
|
||||
lookupCallableByName: () => [],
|
||||
getFiles: () => [][Symbol.iterator](),
|
||||
getStats: () => ({ fileCount: 0 }),
|
||||
};
|
||||
|
||||
/**
|
||||
* Extract (and cache) field info for a class node. Cache is passed in so it
|
||||
* stays scoped to a single `processCalls` invocation rather than leaking
|
||||
* across analyze runs (worker uses module-level caching because each worker
|
||||
* process is short-lived; the main thread is not).
|
||||
*
|
||||
* Cache key is `${filePath}:${classNode.startIndex}` — startIndex alone is a
|
||||
* per-file byte offset, so almost every Ruby/Python file's leading class lands
|
||||
* at byte 0 and would collide across files in the shared map.
|
||||
*/
|
||||
const getFieldInfo = (
|
||||
classNode: SyntaxNode,
|
||||
provider: LanguageProvider,
|
||||
context: FieldExtractorContext,
|
||||
cache: Map<string, Map<string, FieldInfo>>,
|
||||
): Map<string, FieldInfo> | undefined => {
|
||||
if (!provider.fieldExtractor) return undefined;
|
||||
const cacheKey = `${context.filePath}:${classNode.startIndex}`;
|
||||
const cached = cache.get(cacheKey);
|
||||
if (cached) return cached;
|
||||
const result = provider.fieldExtractor.extract(classNode, context);
|
||||
if (!result?.fields?.length) return undefined;
|
||||
const map = new Map<string, FieldInfo>();
|
||||
for (const field of result.fields) map.set(field.name, field);
|
||||
cache.set(cacheKey, map);
|
||||
return map;
|
||||
};
|
||||
|
||||
/** Per-file resolved type bindings for exported symbols.
|
||||
* Populated during call processing, consumed by Phase 14 re-resolution pass. */
|
||||
export type ExportedTypeMap = Map<string, Map<string, string>>;
|
||||
|
|
@ -860,6 +918,120 @@ export const processCalls = async (
|
|||
prepared.push({ file, language, provider, tree, matches, parentMap, typeEnv });
|
||||
}
|
||||
|
||||
// ── Property-registration pre-pass ──
|
||||
// Register all routed properties (e.g. Ruby attr_accessor) BEFORE the
|
||||
// resolution loop so cross-file field-type lookups (e.g.
|
||||
// `user.address.save → Address#save`) succeed regardless of file
|
||||
// processing order. This MUST stay in lockstep with the equivalent
|
||||
// worker-path block in parse-worker.ts (kind === 'properties') — any
|
||||
// divergence between the two paths breaks the `incremental ≡ --force`
|
||||
// invariant once a repo crosses the worker threshold between runs.
|
||||
const fieldInfoCache = new Map<string, Map<string, FieldInfo>>();
|
||||
for (const { file, language, provider, matches, typeEnv } of prepared) {
|
||||
const callRouter = provider.callRouter;
|
||||
if (!callRouter) continue;
|
||||
matches.forEach((match) => {
|
||||
const captureMap: Record<string, any> = {};
|
||||
match.captures.forEach((c) => (captureMap[c.name] = c.node));
|
||||
if (!captureMap['call']) return;
|
||||
const callNameNode = captureMap['call.name'];
|
||||
if (!callNameNode) return;
|
||||
const routed = callRouter(callNameNode.text, captureMap['call']);
|
||||
if (!routed || routed.kind !== 'properties') return;
|
||||
|
||||
const propEnclosingInfo = findEnclosingClassInfo(
|
||||
captureMap['call'],
|
||||
file.path,
|
||||
provider.resolveEnclosingOwner,
|
||||
);
|
||||
const propEnclosingClassId = propEnclosingInfo?.classId ?? null;
|
||||
|
||||
// Enrich routed properties with FieldExtractor metadata so types
|
||||
// discovered from constructor assignments (e.g. `@address = Address.new`)
|
||||
// are propagated even when the routing payload itself lacks declaredType.
|
||||
let routedFieldMap: Map<string, FieldInfo> | undefined;
|
||||
if (provider.fieldExtractor && typeEnv) {
|
||||
const classNode = findEnclosingClassNode(captureMap['call']);
|
||||
if (classNode) {
|
||||
routedFieldMap = getFieldInfo(
|
||||
classNode,
|
||||
provider,
|
||||
{
|
||||
typeEnv,
|
||||
symbolTable: NOOP_SYMBOL_TABLE,
|
||||
filePath: file.path,
|
||||
language,
|
||||
},
|
||||
fieldInfoCache,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
const fileId = generateId('File', file.path);
|
||||
for (const item of routed.items) {
|
||||
const routedFieldInfo = routedFieldMap?.get(item.propName);
|
||||
const propQualifiedName = propEnclosingInfo
|
||||
? `${propEnclosingInfo.className}.${item.propName}`
|
||||
: item.propName;
|
||||
const nodeId = generateId('Property', `${file.path}:${propQualifiedName}`);
|
||||
graph.addNode({
|
||||
id: nodeId,
|
||||
label: 'Property',
|
||||
properties: {
|
||||
name: item.propName,
|
||||
filePath: file.path,
|
||||
startLine: item.startLine,
|
||||
endLine: item.endLine,
|
||||
language,
|
||||
isExported: true,
|
||||
description: item.accessorType,
|
||||
...(item.declaredType
|
||||
? { declaredType: item.declaredType }
|
||||
: routedFieldInfo?.type
|
||||
? { declaredType: routedFieldInfo.type }
|
||||
: {}),
|
||||
...(routedFieldInfo?.visibility !== undefined
|
||||
? { visibility: routedFieldInfo.visibility }
|
||||
: {}),
|
||||
...(routedFieldInfo?.isStatic !== undefined
|
||||
? { isStatic: routedFieldInfo.isStatic }
|
||||
: {}),
|
||||
...(routedFieldInfo?.isReadonly !== undefined
|
||||
? { isReadonly: routedFieldInfo.isReadonly }
|
||||
: {}),
|
||||
},
|
||||
});
|
||||
ctx.model.symbols.add(file.path, item.propName, nodeId, 'Property', {
|
||||
...(propEnclosingClassId ? { ownerId: propEnclosingClassId } : {}),
|
||||
...(item.declaredType
|
||||
? { declaredType: item.declaredType }
|
||||
: routedFieldInfo?.type
|
||||
? { declaredType: routedFieldInfo.type }
|
||||
: {}),
|
||||
});
|
||||
const relId = generateId('DEFINES', `${fileId}->${nodeId}`);
|
||||
graph.addRelationship({
|
||||
id: relId,
|
||||
sourceId: fileId,
|
||||
targetId: nodeId,
|
||||
type: 'DEFINES',
|
||||
confidence: 1.0,
|
||||
reason: '',
|
||||
});
|
||||
if (propEnclosingClassId) {
|
||||
graph.addRelationship({
|
||||
id: generateId('HAS_PROPERTY', `${propEnclosingClassId}->${nodeId}`),
|
||||
sourceId: propEnclosingClassId,
|
||||
targetId: nodeId,
|
||||
type: 'HAS_PROPERTY',
|
||||
confidence: 1.0,
|
||||
reason: '',
|
||||
});
|
||||
}
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
// ── Resolution loop: verify constructor bindings and resolve calls ──
|
||||
// The accumulator (if present) is now fully populated from the preparation
|
||||
// loop above, so verifyConstructorBindings sees all provider bindings
|
||||
|
|
@ -930,9 +1102,10 @@ export const processCalls = async (
|
|||
provider,
|
||||
);
|
||||
const srcId = enclosing || generateId('File', file.path);
|
||||
// Defer resolution: Ruby attr_accessor properties are registered during
|
||||
// this same loop, so cross-file lookups fail if the declaring file hasn't
|
||||
// been processed yet. Collect now, resolve after all files are done.
|
||||
// Defer resolution so write-access tracking sees the FINAL graph
|
||||
// state — properties from the pre-pass are present, but receiver-type
|
||||
// resolution can still depend on inference that completes during the
|
||||
// main loop. Resolve after all files have been processed.
|
||||
pendingWrites.push({ receiverTypeName, propertyName, filePath: file.path, srcId });
|
||||
}
|
||||
// Assignment-only capture (no @call sibling): skip the rest of this
|
||||
|
|
@ -1053,47 +1226,8 @@ export const processCalls = async (
|
|||
return;
|
||||
|
||||
case 'properties': {
|
||||
const fileId = generateId('File', file.path);
|
||||
const propEnclosingClassId = findEnclosingClassId(captureMap['call'], file.path);
|
||||
for (const item of routed.items) {
|
||||
const nodeId = generateId('Property', `${file.path}:${item.propName}`);
|
||||
graph.addNode({
|
||||
id: nodeId,
|
||||
label: 'Property',
|
||||
properties: {
|
||||
name: item.propName,
|
||||
filePath: file.path,
|
||||
startLine: item.startLine,
|
||||
endLine: item.endLine,
|
||||
language,
|
||||
isExported: true,
|
||||
description: item.accessorType,
|
||||
},
|
||||
});
|
||||
ctx.model.symbols.add(file.path, item.propName, nodeId, 'Property', {
|
||||
...(propEnclosingClassId ? { ownerId: propEnclosingClassId } : {}),
|
||||
...(item.declaredType ? { declaredType: item.declaredType } : {}),
|
||||
});
|
||||
const relId = generateId('DEFINES', `${fileId}->${nodeId}`);
|
||||
graph.addRelationship({
|
||||
id: relId,
|
||||
sourceId: fileId,
|
||||
targetId: nodeId,
|
||||
type: 'DEFINES',
|
||||
confidence: 1.0,
|
||||
reason: '',
|
||||
});
|
||||
if (propEnclosingClassId) {
|
||||
graph.addRelationship({
|
||||
id: generateId('HAS_PROPERTY', `${propEnclosingClassId}->${nodeId}`),
|
||||
sourceId: propEnclosingClassId,
|
||||
targetId: nodeId,
|
||||
type: 'HAS_PROPERTY',
|
||||
confidence: 1.0,
|
||||
reason: '',
|
||||
});
|
||||
}
|
||||
}
|
||||
// Properties already registered in the pre-pass above.
|
||||
// Skip to avoid duplicate nodes/edges.
|
||||
return;
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -41,6 +41,24 @@ interface LeidenDetailedResult {
|
|||
modularity: number;
|
||||
}
|
||||
|
||||
/**
|
||||
* Deterministic PRNG (mulberry32) seed for the vendored Leiden algorithm.
|
||||
* Vendored Leiden defaults `rng: Math.random`, which makes community
|
||||
* assignment non-deterministic across runs. Passing a seeded RNG gives us
|
||||
* reproducible community/modularity output, which is required for the
|
||||
* incremental-indexing equivalence test (incremental ≡ full rebuild).
|
||||
*/
|
||||
const LEIDEN_SEED = 0xc0de;
|
||||
function createSeededRng(seed: number): () => number {
|
||||
let s = seed >>> 0;
|
||||
return () => {
|
||||
s = (s + 0x6d2b79f5) >>> 0;
|
||||
let t = Math.imul(s ^ (s >>> 15), 1 | s);
|
||||
t = (t + Math.imul(t ^ (t >>> 7), 61 | t)) ^ t;
|
||||
return ((t ^ (t >>> 14)) >>> 0) / 4294967296;
|
||||
};
|
||||
}
|
||||
|
||||
// ============================================================================
|
||||
// TYPES
|
||||
// ============================================================================
|
||||
|
|
@ -150,6 +168,7 @@ export const processCommunities = async (
|
|||
leiden.detailed(graph, {
|
||||
resolution: isLarge ? 2.0 : 1.0,
|
||||
maxIterations: isLarge ? 3 : 0,
|
||||
rng: createSeededRng(LEIDEN_SEED),
|
||||
}),
|
||||
),
|
||||
new Promise<never>((_, reject) =>
|
||||
|
|
|
|||
|
|
@ -128,7 +128,21 @@ export const resolveImportPath = (
|
|||
|
||||
if (importPath.startsWith('.')) {
|
||||
const resolved = tryResolveWithExtensions(basePath, allFiles);
|
||||
return cache(resolved);
|
||||
if (resolved) return cache(resolved);
|
||||
|
||||
// TypeScript ESM: imports use .js/.jsx/.mjs/.cjs but source files are
|
||||
// .ts/.tsx/.mts/.cts. Strip the JS-family extension and re-resolve.
|
||||
// NOTE: This fallback only applies to relative imports. Path alias imports
|
||||
// (e.g. @/utils.js via tsconfig paths) do not yet strip .js extensions —
|
||||
// that is a known limitation tracked for follow-up.
|
||||
if (language === SupportedLanguages.TypeScript || language === SupportedLanguages.JavaScript) {
|
||||
const stripped = stripJsExtension(basePath);
|
||||
if (stripped !== null) {
|
||||
return cache(tryResolveWithExtensions(stripped, allFiles));
|
||||
}
|
||||
}
|
||||
|
||||
return cache(null);
|
||||
}
|
||||
|
||||
// ---- Generic package/absolute import resolution (suffix matching) ----
|
||||
|
|
@ -182,3 +196,19 @@ export function resolveStandard(
|
|||
export function createStandardStrategy(language: SupportedLanguages): ImportResolverStrategy {
|
||||
return (raw, fp, ctx) => resolveStandard(raw, fp, ctx, language);
|
||||
}
|
||||
|
||||
// ============================================================================
|
||||
// ESM extension helpers
|
||||
// ============================================================================
|
||||
|
||||
/** JS-family extensions that TypeScript ESM maps to TS equivalents. */
|
||||
const JS_EXTENSION_PATTERN = /\.(js|jsx|mjs|cjs)$/;
|
||||
|
||||
/**
|
||||
* Strip a JS-family extension from a path, returning the stem.
|
||||
* Returns `null` if the path does not end with a JS-family extension.
|
||||
*/
|
||||
export function stripJsExtension(path: string): string | null {
|
||||
const match = JS_EXTENSION_PATTERN.exec(path);
|
||||
return match ? path.slice(0, -match[0].length) : null;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -9,8 +9,12 @@ export const EXTENSIONS = [
|
|||
// TypeScript/JavaScript
|
||||
'.tsx',
|
||||
'.ts',
|
||||
'.mts',
|
||||
'.cts',
|
||||
'.jsx',
|
||||
'.js',
|
||||
'.mjs',
|
||||
'.cjs',
|
||||
'.vue',
|
||||
'/index.tsx',
|
||||
'/index.ts',
|
||||
|
|
|
|||
|
|
@ -27,6 +27,17 @@ import { javaMethodConfig } from '../method-extractors/configs/jvm.js';
|
|||
import { createVariableExtractor } from '../variable-extractors/generic.js';
|
||||
import { javaVariableConfig } from '../variable-extractors/configs/jvm.js';
|
||||
import { createHeritageExtractor } from '../heritage-extractors/generic.js';
|
||||
import {
|
||||
emitJavaScopeCaptures,
|
||||
interpretJavaImport,
|
||||
interpretJavaTypeBinding,
|
||||
javaBindingScopeFor,
|
||||
javaImportOwningScope,
|
||||
javaMergeBindings,
|
||||
javaReceiverBinding,
|
||||
javaArityCompatibility,
|
||||
resolveJavaImportTarget,
|
||||
} from './java/index.js';
|
||||
|
||||
export const javaProvider = defineLanguage({
|
||||
id: SupportedLanguages.Java,
|
||||
|
|
@ -65,4 +76,15 @@ export const javaProvider = defineLanguage({
|
|||
variableExtractor: createVariableExtractor(javaVariableConfig),
|
||||
classExtractor: createClassExtractor(javaClassConfig),
|
||||
heritageExtractor: createHeritageExtractor(SupportedLanguages.Java),
|
||||
|
||||
// ── RFC #909 Ring 3: scope-based resolution hooks ──
|
||||
emitScopeCaptures: emitJavaScopeCaptures,
|
||||
interpretImport: interpretJavaImport,
|
||||
interpretTypeBinding: interpretJavaTypeBinding,
|
||||
bindingScopeFor: javaBindingScopeFor,
|
||||
importOwningScope: javaImportOwningScope,
|
||||
mergeBindings: (_scope, bindings) => javaMergeBindings(bindings),
|
||||
receiverBinding: javaReceiverBinding,
|
||||
arityCompatibility: javaArityCompatibility,
|
||||
resolveImportTarget: resolveJavaImportTarget,
|
||||
});
|
||||
|
|
|
|||
49
gitnexus/src/core/ingestion/languages/java/arity-metadata.ts
Normal file
49
gitnexus/src/core/ingestion/languages/java/arity-metadata.ts
Normal file
|
|
@ -0,0 +1,49 @@
|
|||
/**
|
||||
* Extract Java arity metadata from a method-like tree-sitter node —
|
||||
* `method_declaration` or `constructor_declaration`.
|
||||
*
|
||||
* Reuses `javaMethodConfig.extractParameters` so scope-extracted defs
|
||||
* carry the same arity semantics as the legacy parse-worker path:
|
||||
* - varargs (`...`) collapses `parameterCount` to `undefined`
|
||||
* - `parameterTypes` collects declared type names; a literal
|
||||
* `'varargs'` marker is appended for variadic methods so
|
||||
* `javaArityCompatibility` can detect them.
|
||||
*/
|
||||
|
||||
import type { SyntaxNode } from '../../utils/ast-helpers.js';
|
||||
import { javaMethodConfig } from '../../method-extractors/configs/jvm.js';
|
||||
|
||||
export interface JavaArityMetadata {
|
||||
readonly parameterCount: number | undefined;
|
||||
readonly requiredParameterCount: number | undefined;
|
||||
readonly parameterTypes: readonly string[] | undefined;
|
||||
}
|
||||
|
||||
export function computeJavaArityMetadata(fnNode: SyntaxNode): JavaArityMetadata {
|
||||
const params = javaMethodConfig.extractParameters?.(fnNode) ?? [];
|
||||
|
||||
let hasVariadic = false;
|
||||
const types: string[] = [];
|
||||
for (const p of params) {
|
||||
if (p.isVariadic) hasVariadic = true;
|
||||
if (p.type !== null) types.push(p.type);
|
||||
}
|
||||
if (hasVariadic) types.push('varargs');
|
||||
|
||||
const total = params.length;
|
||||
// For varargs methods, `parameterCount` (max) is unknown — any number of
|
||||
// trailing arguments is valid. But the fixed-prefix parameters (everything
|
||||
// before the variadic `...` param) are still required, so we preserve that
|
||||
// count in `requiredParameterCount` so `javaArityCompatibility` can reject
|
||||
// calls that undersupply the fixed prefix (e.g. `f(int x, String... args)`
|
||||
// called with 0 args).
|
||||
const fixedCount = params.filter((p) => !p.isVariadic).length;
|
||||
const parameterCount = hasVariadic ? undefined : total;
|
||||
const requiredParameterCount = hasVariadic ? fixedCount : total;
|
||||
|
||||
return {
|
||||
parameterCount,
|
||||
requiredParameterCount,
|
||||
parameterTypes: types.length > 0 ? types : undefined,
|
||||
};
|
||||
}
|
||||
31
gitnexus/src/core/ingestion/languages/java/arity.ts
Normal file
31
gitnexus/src/core/ingestion/languages/java/arity.ts
Normal file
|
|
@ -0,0 +1,31 @@
|
|||
/**
|
||||
* Java arity check, accommodating varargs (`...`).
|
||||
*
|
||||
* Verdicts:
|
||||
* - `'compatible'` — argCount matches parameterCount, OR varargs present.
|
||||
* - `'incompatible'` — argCount mismatches with no varargs.
|
||||
* - `'unknown'` — metadata absent / incomplete.
|
||||
*/
|
||||
|
||||
import type { Callsite, SymbolDefinition } from 'gitnexus-shared';
|
||||
|
||||
export function javaArityCompatibility(
|
||||
def: SymbolDefinition,
|
||||
callsite: Callsite,
|
||||
): 'compatible' | 'unknown' | 'incompatible' {
|
||||
const max = def.parameterCount;
|
||||
const min = def.requiredParameterCount;
|
||||
if (max === undefined && min === undefined) return 'unknown';
|
||||
|
||||
const argCount = callsite.arity;
|
||||
if (!Number.isFinite(argCount) || argCount < 0) return 'unknown';
|
||||
|
||||
const hasVarArgs =
|
||||
def.parameterTypes !== undefined &&
|
||||
def.parameterTypes.some((t) => t === 'varargs' || t.includes('...'));
|
||||
|
||||
if (min !== undefined && argCount < min) return 'incompatible';
|
||||
if (max !== undefined && argCount > max && !hasVarArgs) return 'incompatible';
|
||||
|
||||
return 'compatible';
|
||||
}
|
||||
30
gitnexus/src/core/ingestion/languages/java/cache-stats.ts
Normal file
30
gitnexus/src/core/ingestion/languages/java/cache-stats.ts
Normal file
|
|
@ -0,0 +1,30 @@
|
|||
/**
|
||||
* Dev-mode counters for the cross-phase scope-captures parse cache
|
||||
* (Java mirror of `languages/csharp/cache-stats.ts`).
|
||||
*
|
||||
* Gated by `PROF_SCOPE_RESOLUTION=1`. Production builds fold every
|
||||
* increment into dead code via the module-level `PROF` constant, so
|
||||
* the hot path in `captures.ts` stays branch-free.
|
||||
*/
|
||||
|
||||
const PROF = process.env.PROF_SCOPE_RESOLUTION === '1';
|
||||
|
||||
let CACHE_HITS = 0;
|
||||
let CACHE_MISSES = 0;
|
||||
|
||||
export function recordCacheHit(): void {
|
||||
if (PROF) CACHE_HITS++;
|
||||
}
|
||||
|
||||
export function recordCacheMiss(): void {
|
||||
if (PROF) CACHE_MISSES++;
|
||||
}
|
||||
|
||||
export function getJavaCaptureCacheStats(): { hits: number; misses: number } {
|
||||
return { hits: CACHE_HITS, misses: CACHE_MISSES };
|
||||
}
|
||||
|
||||
export function resetJavaCaptureCacheStats(): void {
|
||||
CACHE_HITS = 0;
|
||||
CACHE_MISSES = 0;
|
||||
}
|
||||
235
gitnexus/src/core/ingestion/languages/java/captures.ts
Normal file
235
gitnexus/src/core/ingestion/languages/java/captures.ts
Normal file
|
|
@ -0,0 +1,235 @@
|
|||
/**
|
||||
* `emitScopeCaptures` for Java.
|
||||
*
|
||||
* Drives the Java scope query against tree-sitter-java and groups raw
|
||||
* matches into `CaptureMatch[]` for the central extractor. Layers:
|
||||
*
|
||||
* 1. **Decomposed import declarations** — each `import_declaration`
|
||||
* is re-emitted with `@import.kind/source/name` markers.
|
||||
* 2. **Receiver binding synthesis** — `this`/`super` type-bindings
|
||||
* on instance methods.
|
||||
* 3. **Arity metadata** on method/constructor declarations.
|
||||
* 4. **Reference arity** on call sites.
|
||||
*
|
||||
* Pure given the input source text. No I/O, no globals consulted.
|
||||
*/
|
||||
|
||||
import type { Capture, CaptureMatch } from 'gitnexus-shared';
|
||||
import { findNodeAtRange, nodeToCapture, syntheticCapture } from '../../utils/ast-helpers.js';
|
||||
import { splitImportDeclaration } from './import-decomposer.js';
|
||||
import { computeJavaArityMetadata } from './arity-metadata.js';
|
||||
import { synthesizeJavaReceiverBinding } from './receiver-binding.js';
|
||||
import { getJavaParser, getJavaScopeQuery } from './query.js';
|
||||
import { recordCacheHit, recordCacheMiss } from './cache-stats.js';
|
||||
import { getTreeSitterBufferSize } from '../../constants.js';
|
||||
import { parseSourceSafe } from '../../../tree-sitter/safe-parse.js';
|
||||
|
||||
/** Declaration anchors that carry function-like arity metadata. */
|
||||
const FUNCTION_DECL_TAGS = ['@declaration.method', '@declaration.constructor'] as const;
|
||||
|
||||
/** tree-sitter-java node types that the method extractor accepts. */
|
||||
const FUNCTION_NODE_TYPES = ['method_declaration', 'constructor_declaration'] as const;
|
||||
|
||||
/** Suppress read.member emissions when the field_access is already
|
||||
* covered by a method_invocation (object of a call) or an
|
||||
* assignment_expression (write target). */
|
||||
function shouldEmitReadMember(memberNode: SyntaxNode): boolean {
|
||||
const parent = memberNode.parent;
|
||||
if (parent === null) return true;
|
||||
|
||||
switch (parent.type) {
|
||||
case 'method_invocation':
|
||||
// Don't emit read.member when the field_access is the object of a method_invocation
|
||||
// (the method call already handles this relationship)
|
||||
return parent.childForFieldName('object')?.id !== memberNode.id;
|
||||
case 'assignment_expression':
|
||||
return parent.childForFieldName('left')?.id !== memberNode.id;
|
||||
default:
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
export function emitJavaScopeCaptures(
|
||||
sourceText: string,
|
||||
_filePath: string,
|
||||
cachedTree?: unknown,
|
||||
): readonly CaptureMatch[] {
|
||||
let tree = cachedTree as ReturnType<ReturnType<typeof getJavaParser>['parse']> | undefined;
|
||||
if (tree === undefined) {
|
||||
tree = parseSourceSafe(getJavaParser(), sourceText, undefined, {
|
||||
bufferSize: getTreeSitterBufferSize(sourceText),
|
||||
});
|
||||
recordCacheMiss();
|
||||
} else {
|
||||
recordCacheHit();
|
||||
}
|
||||
|
||||
const rawMatches = getJavaScopeQuery().matches(tree.rootNode);
|
||||
const out: CaptureMatch[] = [];
|
||||
|
||||
for (const m of rawMatches) {
|
||||
const grouped: Record<string, Capture> = {};
|
||||
for (const c of m.captures) {
|
||||
const tag = '@' + c.name;
|
||||
grouped[tag] = nodeToCapture(tag, c.node);
|
||||
}
|
||||
if (Object.keys(grouped).length === 0) continue;
|
||||
|
||||
// Decompose each `import_declaration`.
|
||||
if (grouped['@import.statement'] !== undefined) {
|
||||
const stmtCapture = grouped['@import.statement'];
|
||||
const stmtNode = findNodeAtRange(tree.rootNode, stmtCapture.range, 'import_declaration');
|
||||
if (stmtNode !== null) {
|
||||
const decomposed = splitImportDeclaration(stmtNode);
|
||||
if (decomposed !== null) {
|
||||
out.push(decomposed);
|
||||
continue;
|
||||
}
|
||||
}
|
||||
out.push(grouped);
|
||||
continue;
|
||||
}
|
||||
|
||||
// Skip free-call matches that are actually member calls. The query
|
||||
// matches ALL method_invocations as @reference.call.free (without
|
||||
// negation) because tree-sitter-java's query engine drops !object
|
||||
// patterns when a positive object: pattern exists for the same node
|
||||
// type. Filter here: if the match has @reference.call.free but also
|
||||
// has @reference.receiver, it's a member call — skip the free match
|
||||
// (the separate @reference.call.member match covers it).
|
||||
if (
|
||||
grouped['@reference.call.free'] !== undefined &&
|
||||
grouped['@reference.receiver'] !== undefined
|
||||
) {
|
||||
continue;
|
||||
}
|
||||
|
||||
// Filter read.member when it's a child of method_invocation or assignment.
|
||||
if (grouped['@reference.read.member'] !== undefined) {
|
||||
const anchor = grouped['@reference.read.member'];
|
||||
const memberNode = findNodeAtRange(tree.rootNode, anchor.range, 'field_access');
|
||||
if (memberNode === null || !shouldEmitReadMember(memberNode)) {
|
||||
continue;
|
||||
}
|
||||
}
|
||||
|
||||
// Synthesize `this` / `super` receiver type-bindings on every
|
||||
// instance method-like.
|
||||
if (grouped['@scope.function'] !== undefined) {
|
||||
out.push(grouped);
|
||||
const anchor = grouped['@scope.function']!;
|
||||
const fnNode = findFunctionNode(tree.rootNode, anchor.range);
|
||||
if (fnNode !== null) {
|
||||
for (const synth of synthesizeJavaReceiverBinding(fnNode)) {
|
||||
out.push(synth);
|
||||
}
|
||||
}
|
||||
continue;
|
||||
}
|
||||
|
||||
// Synthesize arity metadata on function-like declarations.
|
||||
const declTag = FUNCTION_DECL_TAGS.find((t) => grouped[t] !== undefined);
|
||||
if (declTag !== undefined) {
|
||||
const anchor = grouped[declTag]!;
|
||||
const fnNode = findFunctionNode(tree.rootNode, anchor.range);
|
||||
if (fnNode !== null) {
|
||||
const arity = computeJavaArityMetadata(fnNode);
|
||||
if (arity.parameterCount !== undefined) {
|
||||
grouped['@declaration.parameter-count'] = syntheticCapture(
|
||||
'@declaration.parameter-count',
|
||||
fnNode,
|
||||
String(arity.parameterCount),
|
||||
);
|
||||
}
|
||||
if (arity.requiredParameterCount !== undefined) {
|
||||
grouped['@declaration.required-parameter-count'] = syntheticCapture(
|
||||
'@declaration.required-parameter-count',
|
||||
fnNode,
|
||||
String(arity.requiredParameterCount),
|
||||
);
|
||||
}
|
||||
if (arity.parameterTypes !== undefined) {
|
||||
grouped['@declaration.parameter-types'] = syntheticCapture(
|
||||
'@declaration.parameter-types',
|
||||
fnNode,
|
||||
JSON.stringify(arity.parameterTypes),
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Synthesize `@reference.arity` on every callsite.
|
||||
const callTag = (
|
||||
['@reference.call.free', '@reference.call.member', '@reference.call.constructor'] as const
|
||||
).find((t) => grouped[t] !== undefined);
|
||||
if (callTag !== undefined && grouped['@reference.arity'] === undefined) {
|
||||
const anchor = grouped[callTag]!;
|
||||
const callNode =
|
||||
findNodeAtRange(tree.rootNode, anchor.range, 'method_invocation') ??
|
||||
findNodeAtRange(tree.rootNode, anchor.range, 'object_creation_expression');
|
||||
if (callNode !== null) {
|
||||
const argList = callNode.childForFieldName('arguments');
|
||||
const args =
|
||||
argList === null
|
||||
? []
|
||||
: argList.namedChildren.filter((c) => c !== null && c.type !== 'comment');
|
||||
grouped['@reference.arity'] = syntheticCapture(
|
||||
'@reference.arity',
|
||||
callNode,
|
||||
String(args.length),
|
||||
);
|
||||
|
||||
const argTypes = args.map((arg) => inferArgType(arg!));
|
||||
grouped['@reference.parameter-types'] = syntheticCapture(
|
||||
'@reference.parameter-types',
|
||||
callNode,
|
||||
JSON.stringify(argTypes),
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
out.push(grouped);
|
||||
}
|
||||
|
||||
return out;
|
||||
}
|
||||
|
||||
type SyntaxNode = ReturnType<ReturnType<typeof getJavaParser>['parse']>['rootNode'];
|
||||
|
||||
/** Infer a Java argument's static type from literal patterns. */
|
||||
function inferArgType(argNode: SyntaxNode): string {
|
||||
switch (argNode.type) {
|
||||
case 'decimal_integer_literal':
|
||||
case 'hex_integer_literal':
|
||||
case 'octal_integer_literal':
|
||||
case 'binary_integer_literal':
|
||||
return 'int';
|
||||
case 'decimal_floating_point_literal':
|
||||
case 'hex_floating_point_literal':
|
||||
return 'double';
|
||||
case 'string_literal':
|
||||
return 'String';
|
||||
case 'character_literal':
|
||||
return 'char';
|
||||
case 'true':
|
||||
case 'false':
|
||||
return 'boolean';
|
||||
case 'null_literal':
|
||||
return 'null';
|
||||
case 'object_creation_expression': {
|
||||
const typeNode = argNode.childForFieldName('type');
|
||||
return typeNode?.text ?? '';
|
||||
}
|
||||
default:
|
||||
return '';
|
||||
}
|
||||
}
|
||||
|
||||
/** Find the first Java function-like node at the given range. */
|
||||
function findFunctionNode(rootNode: SyntaxNode, range: Capture['range']): SyntaxNode | null {
|
||||
for (const nodeType of FUNCTION_NODE_TYPES) {
|
||||
const n = findNodeAtRange(rootNode, range, nodeType);
|
||||
if (n !== null) return n as SyntaxNode;
|
||||
}
|
||||
return null;
|
||||
}
|
||||
104
gitnexus/src/core/ingestion/languages/java/import-decomposer.ts
Normal file
104
gitnexus/src/core/ingestion/languages/java/import-decomposer.ts
Normal file
|
|
@ -0,0 +1,104 @@
|
|||
/**
|
||||
* Decompose a Java `import_declaration` into a `CaptureMatch` carrying
|
||||
* the synthesized markers `@import.kind` / `@import.source` /
|
||||
* `@import.name` that `interpretJavaImport` consumes.
|
||||
*
|
||||
* Unlike C#'s using-directive decomposer, Java has four import forms:
|
||||
*
|
||||
* import com.example.User; → named
|
||||
* import com.example.*; → wildcard
|
||||
* import static com.example.Utils.format; → static
|
||||
* import static com.example.Utils.*; → static-wildcard
|
||||
*
|
||||
* Each produces exactly one import. The decomposer inspects the raw
|
||||
* source text and tree-sitter children to determine the flavor.
|
||||
*/
|
||||
|
||||
import type { Capture, CaptureMatch } from 'gitnexus-shared';
|
||||
import { nodeToCapture, syntheticCapture, type SyntaxNode } from '../../utils/ast-helpers.js';
|
||||
|
||||
type ImportKind = 'named' | 'wildcard' | 'static' | 'static-wildcard';
|
||||
|
||||
interface ImportSpec {
|
||||
readonly kind: ImportKind;
|
||||
/** Full dotted path: `com.example.User`. */
|
||||
readonly source: string;
|
||||
/** Local binding name — last path segment for named/static,
|
||||
* `'*'` for wildcard/static-wildcard. */
|
||||
readonly name: string;
|
||||
/** Node to anchor the synthesized captures (range-wise). */
|
||||
readonly atNode: SyntaxNode;
|
||||
}
|
||||
|
||||
export function splitImportDeclaration(stmtNode: SyntaxNode): CaptureMatch | null {
|
||||
if (stmtNode.type !== 'import_declaration') return null;
|
||||
const spec = parseImportDeclaration(stmtNode);
|
||||
if (spec === null) return null;
|
||||
return buildImportMatch(stmtNode, spec);
|
||||
}
|
||||
|
||||
function parseImportDeclaration(node: SyntaxNode): ImportSpec | null {
|
||||
// Detect `static` by checking for an anonymous `static` token child.
|
||||
let isStatic = false;
|
||||
for (let i = 0; i < node.childCount; i++) {
|
||||
const child = node.child(i);
|
||||
if (child !== null && child.type === 'static') {
|
||||
isStatic = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// Detect wildcard by checking for `asterisk` named child.
|
||||
let isWildcard = false;
|
||||
for (let i = 0; i < node.namedChildCount; i++) {
|
||||
const child = node.namedChild(i);
|
||||
if (child !== null && child.type === 'asterisk') {
|
||||
isWildcard = true;
|
||||
break;
|
||||
}
|
||||
}
|
||||
|
||||
// Find the scoped_identifier (or identifier for single-segment imports).
|
||||
let pathNode: SyntaxNode | null = null;
|
||||
for (let i = 0; i < node.namedChildCount; i++) {
|
||||
const child = node.namedChild(i);
|
||||
if (child !== null && (child.type === 'scoped_identifier' || child.type === 'identifier')) {
|
||||
pathNode = child;
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (pathNode === null) return null;
|
||||
|
||||
const fullPath = pathNode.text;
|
||||
if (fullPath === '') return null;
|
||||
|
||||
if (isStatic && isWildcard) {
|
||||
// `import static com.example.Utils.*;`
|
||||
return { kind: 'static-wildcard', source: fullPath, name: '*', atNode: node };
|
||||
}
|
||||
if (isStatic) {
|
||||
// `import static com.example.Utils.format;`
|
||||
const lastDot = fullPath.lastIndexOf('.');
|
||||
const name = lastDot >= 0 ? fullPath.slice(lastDot + 1) : fullPath;
|
||||
return { kind: 'static', source: fullPath, name, atNode: node };
|
||||
}
|
||||
if (isWildcard) {
|
||||
// `import com.example.*;`
|
||||
return { kind: 'wildcard', source: fullPath, name: '*', atNode: node };
|
||||
}
|
||||
|
||||
// `import com.example.User;`
|
||||
const lastDot = fullPath.lastIndexOf('.');
|
||||
const name = lastDot >= 0 ? fullPath.slice(lastDot + 1) : fullPath;
|
||||
return { kind: 'named', source: fullPath, name, atNode: node };
|
||||
}
|
||||
|
||||
function buildImportMatch(stmtNode: SyntaxNode, spec: ImportSpec): CaptureMatch {
|
||||
const m: Record<string, Capture> = {
|
||||
'@import.statement': nodeToCapture('@import.statement', stmtNode),
|
||||
'@import.kind': syntheticCapture('@import.kind', spec.atNode, spec.kind),
|
||||
'@import.source': syntheticCapture('@import.source', spec.atNode, spec.source),
|
||||
'@import.name': syntheticCapture('@import.name', spec.atNode, spec.name),
|
||||
};
|
||||
return m;
|
||||
}
|
||||
108
gitnexus/src/core/ingestion/languages/java/import-target.ts
Normal file
108
gitnexus/src/core/ingestion/languages/java/import-target.ts
Normal file
|
|
@ -0,0 +1,108 @@
|
|||
/**
|
||||
* Adapter from `(ParsedImport, WorkspaceIndex)` → concrete file path.
|
||||
*
|
||||
* Converts Java package paths (dots → slashes) and tries:
|
||||
* 1. Exact file match: `com/example/User.java`
|
||||
* 2. Suffix match for nested layouts
|
||||
* 3. Directory match (wildcard imports)
|
||||
* 4. Progressive prefix stripping for non-standard layouts
|
||||
*
|
||||
* Returns `null` for unresolvable / JDK imports.
|
||||
*/
|
||||
|
||||
import type { ParsedImport, WorkspaceIndex } from 'gitnexus-shared';
|
||||
|
||||
export interface JavaResolveContext {
|
||||
readonly fromFile: string;
|
||||
readonly allFilePaths: ReadonlySet<string>;
|
||||
}
|
||||
|
||||
export function resolveJavaImportTarget(
|
||||
parsedImport: ParsedImport,
|
||||
workspaceIndex: WorkspaceIndex,
|
||||
): string | null {
|
||||
const ctx = workspaceIndex as JavaResolveContext | undefined;
|
||||
if (
|
||||
ctx === undefined ||
|
||||
typeof (ctx as { fromFile?: unknown }).fromFile !== 'string' ||
|
||||
!((ctx as { allFilePaths?: unknown }).allFilePaths instanceof Set)
|
||||
) {
|
||||
return null;
|
||||
}
|
||||
if (parsedImport.kind === 'dynamic-unresolved') return null;
|
||||
if (parsedImport.targetRaw === null || parsedImport.targetRaw === '') return null;
|
||||
|
||||
// Strip trailing `.*` for wildcard imports: `com.example.*` → `com.example`
|
||||
let target = parsedImport.targetRaw;
|
||||
if (target.endsWith('.*')) {
|
||||
target = target.slice(0, -2);
|
||||
}
|
||||
|
||||
// Package path: `com.example.User` → `com/example/User`
|
||||
const pathLike = target.replace(/\./g, '/');
|
||||
const suffix = `/${pathLike}`;
|
||||
|
||||
let exactFile: string | null = null;
|
||||
let suffixFile: string | null = null;
|
||||
let directoryChild: string | null = null;
|
||||
const dirPrefix = `${pathLike}/`;
|
||||
const suffixDirPrefix = `/${dirPrefix}`;
|
||||
|
||||
for (const raw of ctx.allFilePaths) {
|
||||
const f = raw.replace(/\\/g, '/');
|
||||
if (!f.endsWith('.java')) continue;
|
||||
if (f === `${pathLike}.java`) {
|
||||
exactFile = raw;
|
||||
break;
|
||||
}
|
||||
if (suffixFile === null && f.endsWith(`${suffix}.java`)) {
|
||||
suffixFile = raw;
|
||||
}
|
||||
if (directoryChild === null) {
|
||||
const atRoot = f.startsWith(dirPrefix);
|
||||
const atNested = f.includes(suffixDirPrefix);
|
||||
if (atRoot || atNested) {
|
||||
const idx = atRoot ? 0 : f.indexOf(suffixDirPrefix) + 1;
|
||||
const after = f.slice(idx + dirPrefix.length);
|
||||
if (after.length > 0 && !after.includes('/')) {
|
||||
directoryChild = raw;
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if (exactFile !== null) return exactFile;
|
||||
if (suffixFile !== null) return suffixFile;
|
||||
if (directoryChild !== null) return directoryChild;
|
||||
|
||||
// Progressive prefix stripping — handles `import com.example.User;`
|
||||
// in a repo laid out `User.java` (no `com/example/` prefix).
|
||||
const segments = pathLike.split('/').filter(Boolean);
|
||||
for (let skip = 1; skip < segments.length; skip++) {
|
||||
const tail = segments.slice(skip).join('/');
|
||||
if (tail === '') continue;
|
||||
const tailFile = `${tail}.java`;
|
||||
const tailSuffix = `/${tailFile}`;
|
||||
const tailDir = `${tail}/`;
|
||||
const tailSuffixDir = `/${tailDir}`;
|
||||
let tailDirectChild: string | null = null;
|
||||
for (const raw of ctx.allFilePaths) {
|
||||
const f = raw.replace(/\\/g, '/');
|
||||
if (!f.endsWith('.java')) continue;
|
||||
if (f === tailFile) return raw;
|
||||
if (f.endsWith(tailSuffix)) return raw;
|
||||
if (tailDirectChild === null) {
|
||||
const atRoot = f.startsWith(tailDir);
|
||||
const atNested = f.includes(tailSuffixDir);
|
||||
if (atRoot || atNested) {
|
||||
const idx = atRoot ? 0 : f.indexOf(tailSuffixDir) + 1;
|
||||
const after = f.slice(idx + tailDir.length);
|
||||
if (after.length > 0 && !after.includes('/')) tailDirectChild = raw;
|
||||
}
|
||||
}
|
||||
}
|
||||
if (tailDirectChild !== null) return tailDirectChild;
|
||||
}
|
||||
|
||||
return null;
|
||||
}
|
||||
30
gitnexus/src/core/ingestion/languages/java/index.ts
Normal file
30
gitnexus/src/core/ingestion/languages/java/index.ts
Normal file
|
|
@ -0,0 +1,30 @@
|
|||
/**
|
||||
* Java scope-resolution hooks (RFC #909 Ring 3).
|
||||
*
|
||||
* Public API barrel. Consumers should import from this file rather than
|
||||
* the individual modules.
|
||||
*
|
||||
* Module layout:
|
||||
*
|
||||
* - `query.ts` — tree-sitter query + lazy parser/query singletons
|
||||
* - `captures.ts` — `emitJavaScopeCaptures` orchestrator
|
||||
* - `import-decomposer.ts` — each `import` → ParsedImport-shaped captures
|
||||
* - `interpret.ts` — capture-match → `ParsedImport` / `ParsedTypeBinding`
|
||||
* - `simple-hooks.ts` — small hooks made explicit
|
||||
* - `receiver-binding.ts` — synthesize `this`/`super` type-bindings on
|
||||
* instance-method entry
|
||||
* - `merge-bindings.ts` — Java import precedence
|
||||
* - `arity.ts` — Java arity compatibility (varargs)
|
||||
* - `arity-metadata.ts` — synthesize arity metadata from declarations
|
||||
* - `import-target.ts` — `(ParsedImport, WorkspaceIndex) → file path` adapter
|
||||
* - `scope-resolver.ts` — `ScopeResolver` registered in `SCOPE_RESOLVERS`
|
||||
* - `cache-stats.ts` — PROF_SCOPE_RESOLUTION cache hit/miss counters
|
||||
*/
|
||||
|
||||
export { emitJavaScopeCaptures } from './captures.js';
|
||||
export { getJavaCaptureCacheStats, resetJavaCaptureCacheStats } from './cache-stats.js';
|
||||
export { interpretJavaImport, interpretJavaTypeBinding } from './interpret.js';
|
||||
export { javaMergeBindings } from './merge-bindings.js';
|
||||
export { javaArityCompatibility } from './arity.js';
|
||||
export { resolveJavaImportTarget, type JavaResolveContext } from './import-target.js';
|
||||
export { javaBindingScopeFor, javaImportOwningScope, javaReceiverBinding } from './simple-hooks.js';
|
||||
141
gitnexus/src/core/ingestion/languages/java/interpret.ts
Normal file
141
gitnexus/src/core/ingestion/languages/java/interpret.ts
Normal file
|
|
@ -0,0 +1,141 @@
|
|||
/**
|
||||
* Capture-match → semantic-shape interpreters for Java.
|
||||
*
|
||||
* - `interpretJavaImport` → `ParsedImport`
|
||||
* - `interpretJavaTypeBinding` → `ParsedTypeBinding`
|
||||
*
|
||||
* Import matches arrive pre-decomposed by `emitJavaScopeCaptures`
|
||||
* (one import per match, with synthesized `@import.kind/source/name`
|
||||
* markers). Type-binding matches arrive from the raw query captures.
|
||||
*/
|
||||
|
||||
import type { CaptureMatch, ParsedImport, ParsedTypeBinding, TypeRef } from 'gitnexus-shared';
|
||||
|
||||
// ─── interpretImport ──────────────────────────────────────────────────────
|
||||
|
||||
export function interpretJavaImport(captures: CaptureMatch): ParsedImport | null {
|
||||
const kindCap = captures['@import.kind'];
|
||||
const sourceCap = captures['@import.source'];
|
||||
const nameCap = captures['@import.name'];
|
||||
|
||||
const kind = kindCap?.text;
|
||||
if (kind === undefined || sourceCap === undefined) return null;
|
||||
|
||||
switch (kind) {
|
||||
case 'named': {
|
||||
// `import com.example.User;`
|
||||
return {
|
||||
kind: 'named',
|
||||
localName: nameCap?.text ?? sourceCap.text.split('.').pop() ?? sourceCap.text,
|
||||
importedName: sourceCap.text,
|
||||
targetRaw: sourceCap.text,
|
||||
};
|
||||
}
|
||||
case 'wildcard': {
|
||||
// `import com.example.*;`
|
||||
return {
|
||||
kind: 'wildcard',
|
||||
targetRaw: sourceCap.text + '.*',
|
||||
};
|
||||
}
|
||||
case 'static': {
|
||||
// `import static com.example.Utils.format;`
|
||||
// The source contains the full path including the member name
|
||||
// (e.g. `com.example.Utils.format`). For file resolution we need
|
||||
// the class path (`com.example.Utils`), so strip the final member
|
||||
// segment. The local binding name is the member itself.
|
||||
const fullSource = sourceCap.text;
|
||||
const lastDot = fullSource.lastIndexOf('.');
|
||||
const classPath = lastDot >= 0 ? fullSource.slice(0, lastDot) : fullSource;
|
||||
return {
|
||||
kind: 'named',
|
||||
localName: nameCap?.text ?? (lastDot >= 0 ? fullSource.slice(lastDot + 1) : fullSource),
|
||||
importedName: fullSource,
|
||||
targetRaw: classPath,
|
||||
};
|
||||
}
|
||||
case 'static-wildcard': {
|
||||
// `import static com.example.Utils.*;`
|
||||
// The source is the class path (e.g. `com.example.Utils`).
|
||||
// Resolution should target the class file, not a wildcard directory
|
||||
// scan — `Utils.java` is the file that contains the static members.
|
||||
return {
|
||||
kind: 'wildcard',
|
||||
targetRaw: sourceCap.text + '.*',
|
||||
};
|
||||
}
|
||||
default:
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
// ─── interpretTypeBinding ─────────────────────────────────────────────────
|
||||
|
||||
export function interpretJavaTypeBinding(captures: CaptureMatch): ParsedTypeBinding | null {
|
||||
const nameCap = captures['@type-binding.name'];
|
||||
const typeCap = captures['@type-binding.type'];
|
||||
if (nameCap === undefined || typeCap === undefined) return null;
|
||||
|
||||
// Strip qualifier first so that `com.example.BaseModel<T>` becomes
|
||||
// `BaseModel<T>` before stripGeneric — the JVM-erasure fallback pattern
|
||||
// requires an unqualified identifier at the start of the string.
|
||||
const rawType = stripGeneric(stripQualifier(typeCap.text.trim()));
|
||||
|
||||
// Skip `var` — tree-sitter-java parses `var` as type_identifier with
|
||||
// text "var". When used without a constructor initializer, there's no
|
||||
// concrete type to bind.
|
||||
if (rawType === 'var') return null;
|
||||
|
||||
let source: TypeRef['source'] = 'parameter-annotation';
|
||||
if (captures['@type-binding.self'] !== undefined) source = 'self';
|
||||
else if (captures['@type-binding.constructor'] !== undefined) source = 'constructor-inferred';
|
||||
else if (captures['@type-binding.annotation'] !== undefined) source = 'annotation';
|
||||
else if (captures['@type-binding.return'] !== undefined) source = 'return-annotation';
|
||||
|
||||
return { boundName: nameCap.text, rawTypeName: rawType, source };
|
||||
}
|
||||
|
||||
/**
|
||||
* Unwrap generic type parameters from Java types.
|
||||
*
|
||||
* Three tiers, checked in order:
|
||||
* 1. Known single-arg collection wrappers → extract the element type
|
||||
* (`List<User>` → `User`, `Optional<User>` → `User`).
|
||||
* 2. Known two-arg map/container types → extract the value type
|
||||
* (`Map<String, User>` → `User`).
|
||||
* 3. **Fallback (JVM type erasure):** any other generic type →
|
||||
* strip the generic parameters and keep the raw class name
|
||||
* (`BaseModel<T>` → `BaseModel`, `CustomList<Foo>` → `CustomList`).
|
||||
* This ensures receiver bindings (`this`/`super`) on classes with
|
||||
* generic superclasses resolve to the correct class file.
|
||||
*/
|
||||
function stripGeneric(text: string): string {
|
||||
// Single-type-argument containers — extract the element type.
|
||||
const single = text.match(
|
||||
/^(?:[A-Za-z_][A-Za-z0-9_.]*\.)?(?:List|ArrayList|LinkedList|Set|HashSet|TreeSet|SortedSet|LinkedHashSet|Collection|Iterable|Iterator|Optional|Stream|CompletableFuture|Future|Queue|Deque|ArrayDeque|PriorityQueue|Vector|Stack|Supplier|Consumer|Predicate|Function)<([^,<>]+)>$/,
|
||||
);
|
||||
if (single !== null) return single[1].trim();
|
||||
|
||||
// Two-type-argument map/container types — extract the value type (second arg).
|
||||
const twoArg = text.match(
|
||||
/^(?:[A-Za-z_][A-Za-z0-9_.]*\.)?(?:Map|HashMap|TreeMap|LinkedHashMap|ConcurrentHashMap|ConcurrentMap|SortedMap|NavigableMap|Hashtable|EnumMap|WeakHashMap|IdentityHashMap|BiFunction|BiConsumer|BiPredicate|Pair|Entry)<[^,<>]+,\s*([^,<>]+)>$/,
|
||||
);
|
||||
if (twoArg !== null) return twoArg[1].trim();
|
||||
|
||||
// Fallback: strip generic parameters from any unrecognized generic type.
|
||||
// `BaseModel<T>` → `BaseModel`, `Builder<Self>` → `Builder`.
|
||||
// This mirrors JVM type erasure — the raw class name is the resolvable symbol.
|
||||
// The pattern matches up to the first `<` to handle nested generics safely
|
||||
// (e.g. `BaseModel<List<String>>` → `BaseModel`).
|
||||
const fallback = text.match(/^([A-Za-z_$][A-Za-z0-9_$]*)<.+>$/s);
|
||||
if (fallback !== null) return fallback[1].trim();
|
||||
|
||||
return text;
|
||||
}
|
||||
|
||||
/** `com.example.User` → `User`. */
|
||||
function stripQualifier(text: string): string {
|
||||
const lastDot = text.lastIndexOf('.');
|
||||
if (lastDot === -1) return text;
|
||||
return text.slice(lastDot + 1);
|
||||
}
|
||||
44
gitnexus/src/core/ingestion/languages/java/merge-bindings.ts
Normal file
44
gitnexus/src/core/ingestion/languages/java/merge-bindings.ts
Normal file
|
|
@ -0,0 +1,44 @@
|
|||
/**
|
||||
* Java shadowing precedence for the `mergeBindings` hook.
|
||||
*
|
||||
* Tier ranking (lower wins):
|
||||
* - 0: `local` — class member, method, local variable, parameter
|
||||
* - 1: `import` / `namespace` / `reexport` — explicit imports
|
||||
* - 2: `wildcard` — wildcard imports (`import x.y.*`)
|
||||
*
|
||||
* Within a surviving tier: de-dup by DefId, last-write-wins.
|
||||
*/
|
||||
|
||||
import type { BindingRef } from 'gitnexus-shared';
|
||||
|
||||
const TIER_LOCAL = 0;
|
||||
const TIER_IMPORT = 1;
|
||||
const TIER_WILDCARD = 2;
|
||||
const TIER_UNKNOWN = 3;
|
||||
|
||||
function tierOf(b: BindingRef): number {
|
||||
switch (b.origin) {
|
||||
case 'local':
|
||||
return TIER_LOCAL;
|
||||
case 'reexport':
|
||||
case 'import':
|
||||
case 'namespace':
|
||||
return TIER_IMPORT;
|
||||
case 'wildcard':
|
||||
return TIER_WILDCARD;
|
||||
default:
|
||||
return TIER_UNKNOWN;
|
||||
}
|
||||
}
|
||||
|
||||
export function javaMergeBindings(bindings: readonly BindingRef[]): readonly BindingRef[] {
|
||||
if (bindings.length === 0) return bindings;
|
||||
|
||||
let bestTier = Number.POSITIVE_INFINITY;
|
||||
for (const b of bindings) bestTier = Math.min(bestTier, tierOf(b));
|
||||
const survivors = bindings.filter((b) => tierOf(b) === bestTier);
|
||||
|
||||
const seen = new Map<string, BindingRef>();
|
||||
for (const b of survivors) seen.set(b.def.nodeId, b);
|
||||
return [...seen.values()];
|
||||
}
|
||||
197
gitnexus/src/core/ingestion/languages/java/query.ts
Normal file
197
gitnexus/src/core/ingestion/languages/java/query.ts
Normal file
|
|
@ -0,0 +1,197 @@
|
|||
/**
|
||||
* Tree-sitter query for Java scope captures (RFC §5.1).
|
||||
*
|
||||
* Captures the structural skeleton the generic scope-resolution
|
||||
* pipeline consumes: scopes (module/class/function), declarations
|
||||
* (class-likes, method-likes, fields, variables), imports (import
|
||||
* declarations), type bindings (parameter annotations, variable
|
||||
* annotations, constructor inference), and references (call sites,
|
||||
* member writes/reads).
|
||||
*
|
||||
* Java specifics that shape this query:
|
||||
*
|
||||
* - Java uses `program` as the root node (not `compilation_unit`).
|
||||
* - `import_declaration` nodes carry `scoped_identifier` children
|
||||
* and optional `asterisk` for wildcard imports.
|
||||
* - `static` imports are detected by an anonymous `static` token
|
||||
* child within `import_declaration`.
|
||||
* - `var` (Java 10+ local variable type inference) parses as a
|
||||
* `type_identifier` with text `"var"`, not a dedicated node type.
|
||||
* - Modifiers (`public`, `static`, etc.) are grouped under a
|
||||
* `modifiers` named child with anonymous keyword tokens.
|
||||
* - Superclass inheritance uses a `superclass:` field containing
|
||||
* a `superclass` node wrapping a `type_identifier`.
|
||||
*
|
||||
* Exposes lazy `Parser` and `Query` singletons so callers don't pay
|
||||
* tree-sitter init cost per file.
|
||||
*/
|
||||
|
||||
import Parser from 'tree-sitter';
|
||||
import Java from 'tree-sitter-java';
|
||||
|
||||
const JAVA_SCOPE_QUERY = `
|
||||
;; Scopes
|
||||
(program) @scope.module
|
||||
|
||||
(class_declaration) @scope.class
|
||||
(interface_declaration) @scope.class
|
||||
(enum_declaration) @scope.class
|
||||
(record_declaration) @scope.class
|
||||
(annotation_type_declaration) @scope.class
|
||||
|
||||
(method_declaration) @scope.function
|
||||
(constructor_declaration) @scope.function
|
||||
|
||||
;; Declarations — types
|
||||
(class_declaration
|
||||
name: (identifier) @declaration.name) @declaration.class
|
||||
|
||||
(interface_declaration
|
||||
name: (identifier) @declaration.name) @declaration.interface
|
||||
|
||||
(enum_declaration
|
||||
name: (identifier) @declaration.name) @declaration.enum
|
||||
|
||||
(record_declaration
|
||||
name: (identifier) @declaration.name) @declaration.record
|
||||
|
||||
(annotation_type_declaration
|
||||
name: (identifier) @declaration.name) @declaration.class
|
||||
|
||||
;; Declarations — methods / constructors
|
||||
(method_declaration
|
||||
name: (identifier) @declaration.name) @declaration.method
|
||||
|
||||
(constructor_declaration
|
||||
name: (identifier) @declaration.name) @declaration.constructor
|
||||
|
||||
;; Declarations — fields
|
||||
(field_declaration
|
||||
declarator: (variable_declarator
|
||||
name: (identifier) @declaration.name)) @declaration.variable
|
||||
|
||||
;; Declarations — local variables
|
||||
(local_variable_declaration
|
||||
declarator: (variable_declarator
|
||||
name: (identifier) @declaration.name)) @declaration.variable
|
||||
|
||||
;; Imports — single anchor per import_declaration
|
||||
(import_declaration) @import.statement
|
||||
|
||||
;; Type bindings — parameter annotations: void f(User u)
|
||||
(formal_parameter
|
||||
type: (type_identifier) @type-binding.type
|
||||
name: (identifier) @type-binding.name) @type-binding.parameter
|
||||
|
||||
(formal_parameter
|
||||
type: (generic_type) @type-binding.type
|
||||
name: (identifier) @type-binding.name) @type-binding.parameter
|
||||
|
||||
(formal_parameter
|
||||
type: (scoped_type_identifier) @type-binding.type
|
||||
name: (identifier) @type-binding.name) @type-binding.parameter
|
||||
|
||||
;; Type bindings — local variable annotations: User u = new User();
|
||||
(local_variable_declaration
|
||||
type: (type_identifier) @type-binding.type
|
||||
declarator: (variable_declarator
|
||||
name: (identifier) @type-binding.name)) @type-binding.annotation
|
||||
|
||||
(local_variable_declaration
|
||||
type: (generic_type) @type-binding.type
|
||||
declarator: (variable_declarator
|
||||
name: (identifier) @type-binding.name)) @type-binding.annotation
|
||||
|
||||
;; Type bindings — var u = new User(); (Java 10+ local variable type inference)
|
||||
;; tree-sitter-java parses \`var\` as a \`type_identifier\` with text "var".
|
||||
;; The type-binding.constructor anchor fires when the rhs is an
|
||||
;; object_creation_expression so interpretJavaTypeBinding can infer
|
||||
;; the concrete type from the constructor call.
|
||||
(local_variable_declaration
|
||||
type: (type_identifier) @_var_type
|
||||
declarator: (variable_declarator
|
||||
name: (identifier) @type-binding.name
|
||||
value: (object_creation_expression
|
||||
type: (type_identifier) @type-binding.type))) @type-binding.constructor
|
||||
|
||||
;; Type bindings — field declarations: private User user;
|
||||
(field_declaration
|
||||
type: (type_identifier) @type-binding.type
|
||||
declarator: (variable_declarator
|
||||
name: (identifier) @type-binding.name)) @type-binding.annotation
|
||||
|
||||
(field_declaration
|
||||
type: (generic_type) @type-binding.type
|
||||
declarator: (variable_declarator
|
||||
name: (identifier) @type-binding.name)) @type-binding.annotation
|
||||
|
||||
;; Type bindings — method return type: public User getUser() { }
|
||||
(method_declaration
|
||||
type: (type_identifier) @type-binding.type
|
||||
name: (identifier) @type-binding.name) @type-binding.return
|
||||
|
||||
(method_declaration
|
||||
type: (generic_type) @type-binding.type
|
||||
name: (identifier) @type-binding.name) @type-binding.return
|
||||
|
||||
;; Type bindings — enhanced for: for (User u : list)
|
||||
(enhanced_for_statement
|
||||
type: (type_identifier) @type-binding.type
|
||||
name: (identifier) @type-binding.name) @type-binding.annotation
|
||||
|
||||
(enhanced_for_statement
|
||||
type: (generic_type) @type-binding.type
|
||||
name: (identifier) @type-binding.name) @type-binding.annotation
|
||||
|
||||
;; References — all method calls: foo() and obj.method()
|
||||
;; tree-sitter-java's query engine drops negation-based \`!object\`
|
||||
;; patterns when a positive \`object:\` pattern exists for the same
|
||||
;; node type, so we match all calls here and classify free vs
|
||||
;; member in captures.ts based on the presence of @reference.receiver.
|
||||
(method_invocation
|
||||
object: (_) @reference.receiver
|
||||
name: (identifier) @reference.name) @reference.call.member
|
||||
|
||||
(method_invocation
|
||||
name: (identifier) @reference.name) @reference.call.free
|
||||
|
||||
;; References — constructor calls: new User(...)
|
||||
(object_creation_expression
|
||||
type: (type_identifier) @reference.name) @reference.call.constructor
|
||||
|
||||
(object_creation_expression
|
||||
type: (generic_type
|
||||
(type_identifier) @reference.name)) @reference.call.constructor
|
||||
|
||||
(object_creation_expression
|
||||
type: (scoped_type_identifier) @reference.call.constructor.qualified) @reference.call.constructor
|
||||
|
||||
;; References — field/property writes: obj.name = "x"
|
||||
(assignment_expression
|
||||
left: (field_access
|
||||
object: (_) @reference.receiver
|
||||
field: (identifier) @reference.name)) @reference.write.member
|
||||
|
||||
;; References — field/property reads: obj.name
|
||||
(field_access
|
||||
object: (_) @reference.receiver
|
||||
field: (identifier) @reference.name) @reference.read.member
|
||||
`;
|
||||
|
||||
let _parser: Parser | null = null;
|
||||
let _query: Parser.Query | null = null;
|
||||
|
||||
export function getJavaParser(): Parser {
|
||||
if (_parser === null) {
|
||||
_parser = new Parser();
|
||||
_parser.setLanguage(Java as Parameters<Parser['setLanguage']>[0]);
|
||||
}
|
||||
return _parser;
|
||||
}
|
||||
|
||||
export function getJavaScopeQuery(): Parser.Query {
|
||||
if (_query === null) {
|
||||
_query = new Parser.Query(Java as Parameters<Parser['setLanguage']>[0], JAVA_SCOPE_QUERY);
|
||||
}
|
||||
return _query;
|
||||
}
|
||||
103
gitnexus/src/core/ingestion/languages/java/receiver-binding.ts
Normal file
103
gitnexus/src/core/ingestion/languages/java/receiver-binding.ts
Normal file
|
|
@ -0,0 +1,103 @@
|
|||
/**
|
||||
* Synthesize `@type-binding.self` captures for Java instance methods —
|
||||
* one for `this` (always on non-static methods inside a type
|
||||
* declaration) and optionally one for `super` (only on class methods
|
||||
* when the enclosing class has a `superclass`).
|
||||
*
|
||||
* Mirrors `languages/csharp/receiver-binding.ts` in structure.
|
||||
*/
|
||||
|
||||
import type { Capture, CaptureMatch } from 'gitnexus-shared';
|
||||
import { nodeToCapture, syntheticCapture, type SyntaxNode } from '../../utils/ast-helpers.js';
|
||||
|
||||
const TYPE_DECL_NODE_TYPES = new Set([
|
||||
'class_declaration',
|
||||
'interface_declaration',
|
||||
'enum_declaration',
|
||||
'record_declaration',
|
||||
]);
|
||||
|
||||
const FUNCTION_NODE_TYPES = new Set(['method_declaration', 'constructor_declaration']);
|
||||
|
||||
/** Walk up to the enclosing type declaration. */
|
||||
function findEnclosingTypeDeclaration(node: SyntaxNode): SyntaxNode | null {
|
||||
let cur: SyntaxNode | null = node.parent;
|
||||
while (cur !== null) {
|
||||
if (TYPE_DECL_NODE_TYPES.has(cur.type)) return cur;
|
||||
cur = cur.parent;
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
function typeName(typeNode: SyntaxNode): string | null {
|
||||
return typeNode.childForFieldName('name')?.text ?? null;
|
||||
}
|
||||
|
||||
/** First superclass text. tree-sitter-java uses a `superclass` field
|
||||
* containing a `superclass` node wrapping a `type_identifier`. */
|
||||
function firstSuperclassText(typeNode: SyntaxNode): string | null {
|
||||
const superclass = typeNode.childForFieldName('superclass');
|
||||
if (superclass === null) return null;
|
||||
// The superclass node wraps the type_identifier
|
||||
for (let i = 0; i < superclass.namedChildCount; i++) {
|
||||
const child = superclass.namedChild(i);
|
||||
if (child !== null && (child.type === 'type_identifier' || child.type === 'generic_type')) {
|
||||
return child.text;
|
||||
}
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
/** Check if a method has the `static` modifier. In tree-sitter-java,
|
||||
* modifiers are grouped under a `modifiers` named child with anonymous
|
||||
* keyword tokens. */
|
||||
function isStaticMethod(fnNode: SyntaxNode): boolean {
|
||||
for (let i = 0; i < fnNode.namedChildCount; i++) {
|
||||
const child = fnNode.namedChild(i);
|
||||
if (child !== null && child.type === 'modifiers') {
|
||||
for (let j = 0; j < child.childCount; j++) {
|
||||
const mod = child.child(j);
|
||||
if (mod !== null && mod.text.trim() === 'static') return true;
|
||||
}
|
||||
}
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
export function synthesizeJavaReceiverBinding(fnNode: SyntaxNode): CaptureMatch[] {
|
||||
if (!FUNCTION_NODE_TYPES.has(fnNode.type)) return [];
|
||||
if (isStaticMethod(fnNode)) return [];
|
||||
|
||||
const enclosingType = findEnclosingTypeDeclaration(fnNode);
|
||||
if (enclosingType === null) return [];
|
||||
|
||||
const enclosingName = typeName(enclosingType);
|
||||
if (enclosingName === null) return [];
|
||||
|
||||
// Anchor to the method body so the synthesized captures are inside
|
||||
// the function scope.
|
||||
const anchorNode = fnNode.childForFieldName('body');
|
||||
if (anchorNode === null) return [];
|
||||
|
||||
const out: CaptureMatch[] = [];
|
||||
out.push(buildReceiverMatch(anchorNode, 'this', enclosingName));
|
||||
|
||||
// `super` applies only to class/record methods with an explicit superclass.
|
||||
if (enclosingType.type === 'class_declaration' || enclosingType.type === 'record_declaration') {
|
||||
const superText = firstSuperclassText(enclosingType);
|
||||
if (superText !== null) {
|
||||
out.push(buildReceiverMatch(anchorNode, 'super', superText));
|
||||
}
|
||||
}
|
||||
|
||||
return out;
|
||||
}
|
||||
|
||||
function buildReceiverMatch(anchorNode: SyntaxNode, name: string, typeText: string): CaptureMatch {
|
||||
const m: Record<string, Capture> = {
|
||||
'@type-binding.self': nodeToCapture('@type-binding.self', anchorNode),
|
||||
'@type-binding.name': syntheticCapture('@type-binding.name', anchorNode, name),
|
||||
'@type-binding.type': syntheticCapture('@type-binding.type', anchorNode, typeText),
|
||||
};
|
||||
return m;
|
||||
}
|
||||
97
gitnexus/src/core/ingestion/languages/java/scope-resolver.ts
Normal file
97
gitnexus/src/core/ingestion/languages/java/scope-resolver.ts
Normal file
|
|
@ -0,0 +1,97 @@
|
|||
/**
|
||||
* Java `ScopeResolver` registered in `SCOPE_RESOLVERS` and consumed by
|
||||
* the generic `runScopeResolution` orchestrator (RFC #909 Ring 3).
|
||||
*
|
||||
* ## Registry-primary parity status
|
||||
*
|
||||
* Java is **not** in `MIGRATED_LANGUAGES` — the scope-resolution
|
||||
* registry runs in shadow mode only. Parity in forced registry mode
|
||||
* (`REGISTRY_PRIMARY_JAVA=1`) is 143/172 (83%). The 29 gaps fall into:
|
||||
*
|
||||
* - switch pattern binding / sealed-class exhaustiveness
|
||||
* - Map.values() / entrySet() iteration type propagation
|
||||
* - assignment / method chain return-type propagation across files
|
||||
* - virtual dispatch / interface default methods
|
||||
*
|
||||
* These are the same category of advanced-resolution gaps seen in prior
|
||||
* migrations (Python, C#, Go). Parity is below the ≥99% flip threshold
|
||||
* per RFC §6.4.
|
||||
*
|
||||
* **CI visibility:** Because Java is absent from `MIGRATED_LANGUAGES`,
|
||||
* the parity CI workflow (`ci-scope-parity.yml`) does not run Java in
|
||||
* either `REGISTRY_PRIMARY_JAVA=0` or `=1` mode. Regressions in forced
|
||||
* mode are only visible via manual `REGISTRY_PRIMARY_JAVA=1 npx vitest
|
||||
* run java.test.ts`. Before flipping Java to registry-primary, a
|
||||
* non-required CI step should be added to run Java tests in forced mode
|
||||
* and report parity as a dashboard input.
|
||||
*
|
||||
* **Parity baseline (29 failures):** The 29 gaps in forced registry mode
|
||||
* are tracked in this PR (#1482) and this JSDoc. If the gap count
|
||||
* changes (up or down), update this baseline accordingly.
|
||||
*
|
||||
* ### Known flip-blockers (must fix before adding to MIGRATED_LANGUAGES)
|
||||
*
|
||||
* - Varargs arity: fixed-prefix count is now preserved, but no
|
||||
* integration fixture exercises the 0-arg rejection path yet.
|
||||
* - Static import resolution: `import static X.Y.m` now correctly
|
||||
* resolves to `X/Y.java` (the class), not `X/Y/m.java` (the member).
|
||||
* Edge cases with nested classes may remain.
|
||||
* - Generic superclass receiver binding: `BaseModel<T>` now strips
|
||||
* to `BaseModel` via JVM type-erasure fallback in `stripGeneric`.
|
||||
* - Wildcard import (`import com.example.*`) file selection is
|
||||
* nondeterministic when multiple classes share a package directory.
|
||||
* May produce wrong-file edges in forced mode.
|
||||
* - Qualified generic type parameters in field/parameter annotations
|
||||
* (`com.example.BaseModel<T>`) — rare in practice but may miss
|
||||
* resolution when the full qualifier is present with generics.
|
||||
*/
|
||||
|
||||
import type { ParsedFile } from 'gitnexus-shared';
|
||||
import { SupportedLanguages } from 'gitnexus-shared';
|
||||
import { buildMro, defaultLinearize } from '../../scope-resolution/passes/mro.js';
|
||||
import { populateClassOwnedMembers } from '../../scope-resolution/scope/walkers.js';
|
||||
import type { ScopeResolver } from '../../scope-resolution/contract/scope-resolver.js';
|
||||
import { javaProvider } from '../java.js';
|
||||
import {
|
||||
javaArityCompatibility,
|
||||
javaMergeBindings,
|
||||
resolveJavaImportTarget,
|
||||
type JavaResolveContext,
|
||||
} from './index.js';
|
||||
|
||||
const javaScopeResolver: ScopeResolver = {
|
||||
language: SupportedLanguages.Java,
|
||||
languageProvider: javaProvider,
|
||||
importEdgeReason: 'java-scope: import',
|
||||
|
||||
resolveImportTarget: (targetRaw, fromFile, allFilePaths) => {
|
||||
const ws: JavaResolveContext = { fromFile, allFilePaths };
|
||||
return resolveJavaImportTarget(
|
||||
{ kind: 'named', localName: '_', importedName: '_', targetRaw },
|
||||
ws,
|
||||
);
|
||||
},
|
||||
|
||||
mergeBindings: (existing, incoming) => [...javaMergeBindings([...existing, ...incoming])],
|
||||
|
||||
arityCompatibility: (callsite, def) => javaArityCompatibility(def, callsite),
|
||||
|
||||
buildMro: (graph, parsedFiles, nodeLookup) =>
|
||||
buildMro(graph, parsedFiles, nodeLookup, defaultLinearize),
|
||||
|
||||
populateOwners: (parsed: ParsedFile) => populateClassOwnedMembers(parsed),
|
||||
|
||||
isSuperReceiver: (text) => text.trim() === 'super',
|
||||
|
||||
// Java is statically typed — field-fallback heuristic stays off
|
||||
fieldFallbackOnMethodLookup: false,
|
||||
propagatesReturnTypesAcrossImports: true,
|
||||
|
||||
// Java doesn't collapse member calls
|
||||
collapseMemberCallsByCallerTarget: false,
|
||||
|
||||
// Hoist return-type bindings to Module scope for cross-file propagation
|
||||
hoistTypeBindingsToModule: true,
|
||||
};
|
||||
|
||||
export { javaScopeResolver };
|
||||
54
gitnexus/src/core/ingestion/languages/java/simple-hooks.ts
Normal file
54
gitnexus/src/core/ingestion/languages/java/simple-hooks.ts
Normal file
|
|
@ -0,0 +1,54 @@
|
|||
/**
|
||||
* Small hooks for the Java provider. Each is a few lines; they make
|
||||
* the provider's choice explicit rather than relying on defaults.
|
||||
*/
|
||||
|
||||
import type {
|
||||
CaptureMatch,
|
||||
ParsedImport,
|
||||
Scope,
|
||||
ScopeId,
|
||||
ScopeTree,
|
||||
TypeRef,
|
||||
} from 'gitnexus-shared';
|
||||
|
||||
// ─── bindingScopeFor ──────────────────────────────────────────────────────
|
||||
|
||||
/** Method return-type bindings hoist to Module scope so cross-file
|
||||
* `propagateImportedReturnTypes` and chain-follow can find them. */
|
||||
export function javaBindingScopeFor(
|
||||
decl: CaptureMatch,
|
||||
innermost: Scope,
|
||||
tree: ScopeTree,
|
||||
): ScopeId | null {
|
||||
if (decl['@type-binding.return'] !== undefined) {
|
||||
let cur: Scope | undefined = innermost;
|
||||
while (cur !== undefined && cur.kind !== 'Module') {
|
||||
const parentId: ScopeId | null = cur.parent ?? null;
|
||||
if (parentId === null) break;
|
||||
cur = tree.getScope(parentId);
|
||||
}
|
||||
if (cur !== undefined && cur.kind === 'Module') return cur.id;
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
// ─── importOwningScope ────────────────────────────────────────────────────
|
||||
|
||||
/** Java imports are always at compilation-unit (Module) level (JLS §7.5).
|
||||
* Return `null` unconditionally so the default Module scope is used. */
|
||||
export function javaImportOwningScope(
|
||||
_imp: ParsedImport,
|
||||
_innermost: Scope,
|
||||
_tree: ScopeTree,
|
||||
): ScopeId | null {
|
||||
return null;
|
||||
}
|
||||
|
||||
// ─── receiverBinding ──────────────────────────────────────────────────────
|
||||
|
||||
/** Look up `this` or `super` in the function scope's type bindings. */
|
||||
export function javaReceiverBinding(functionScope: Scope): TypeRef | null {
|
||||
if (functionScope.kind !== 'Function') return null;
|
||||
return functionScope.typeBindings.get('this') ?? functionScope.typeBindings.get('super') ?? null;
|
||||
}
|
||||
|
|
@ -5,12 +5,22 @@
|
|||
* and standard export/import resolution. PHP files can use a variety of
|
||||
* extensions from legacy versions through modern PHP 8.
|
||||
*/
|
||||
import {
|
||||
emitPhpScopeCaptures,
|
||||
interpretPhpImport,
|
||||
interpretPhpTypeBinding,
|
||||
phpArityCompatibility,
|
||||
phpMergeBindings,
|
||||
resolvePhpImportTarget,
|
||||
phpBindingScopeFor,
|
||||
phpImportOwningScope,
|
||||
phpReceiverBinding,
|
||||
} from './php/index.js';
|
||||
|
||||
import { SupportedLanguages } from 'gitnexus-shared';
|
||||
import { createClassExtractor } from '../class-extractors/generic.js';
|
||||
import { phpClassConfig } from '../class-extractors/configs/php.js';
|
||||
import { defineLanguage } from '../language-provider.js';
|
||||
import type { AstFrameworkPatternConfig } from '../language-provider.js';
|
||||
import { defineLanguage, type AstFrameworkPatternConfig } from '../language-provider.js';
|
||||
import { typeConfig as phpConfig } from '../type-extractors/php.js';
|
||||
import { phpExportChecker } from '../export-detection.js';
|
||||
import { createImportResolver } from '../import-resolvers/resolver-factory.js';
|
||||
|
|
@ -289,4 +299,18 @@ export const phpProvider = defineLanguage({
|
|||
descriptionExtractor: phpDescriptionExtractor,
|
||||
isRouteFile: isPhpRouteFile,
|
||||
builtInNames: BUILT_INS,
|
||||
// ── RFC #909 Ring 3: scope-based resolution hooks ──────────────────────
|
||||
emitScopeCaptures: emitPhpScopeCaptures,
|
||||
interpretImport: interpretPhpImport,
|
||||
interpretTypeBinding: interpretPhpTypeBinding,
|
||||
// LanguageProvider uses (def, callsite); phpArityCompatibility uses (def, callsite) — same.
|
||||
arityCompatibility: phpArityCompatibility,
|
||||
// LanguageProvider adapter: (parsedImport, workspaceIndex) → string | null
|
||||
resolveImportTarget: resolvePhpImportTarget,
|
||||
// mergeBindings on LanguageProvider: (scope, bindings) — ignore scope id,
|
||||
// delegate to phpMergeBindings which uses binding origin tiers.
|
||||
mergeBindings: (_scope, bindings) => [...phpMergeBindings(bindings)],
|
||||
bindingScopeFor: phpBindingScopeFor,
|
||||
importOwningScope: phpImportOwningScope,
|
||||
receiverBinding: phpReceiverBinding,
|
||||
});
|
||||
|
|
|
|||
73
gitnexus/src/core/ingestion/languages/php/arity-metadata.ts
Normal file
73
gitnexus/src/core/ingestion/languages/php/arity-metadata.ts
Normal file
|
|
@ -0,0 +1,73 @@
|
|||
/**
|
||||
* Extract PHP arity metadata from a method-like tree-sitter node —
|
||||
* `method_declaration` or `function_definition`.
|
||||
*
|
||||
* Reuses `phpMethodConfig.extractParameters` so scope-extracted defs
|
||||
* carry the same arity semantics as the legacy parse-worker path:
|
||||
* - `variadic_parameter` (`...$args`) collapses `parameterCount` to
|
||||
* `undefined`, which `phpArityCompatibility` then treats as
|
||||
* "max unknown" — the candidate stays eligible at `argCount >= required`.
|
||||
* - Defaulted parameters (`= expr`) contribute to `optionalCount`;
|
||||
* `requiredParameterCount = total − optionalCount − (variadic ? 1 : 0)`.
|
||||
* The variadic slot itself accepts zero args so it is subtracted from
|
||||
* the required count — `f(int $a, ...$rest)` requires exactly 1 arg,
|
||||
* not 2, and `f(...$rest)` requires 0.
|
||||
* - `property_promotion_parameter` (constructor-promoted) is counted
|
||||
* the same as `simple_parameter` since both consume an argument slot.
|
||||
* - `parameterTypes` collects declared type names; a literal `'...'`
|
||||
* marker is appended for variadic methods so `phpArityCompatibility`
|
||||
* can detect them without re-reading the AST.
|
||||
*/
|
||||
|
||||
import type { SyntaxNode } from '../../utils/ast-helpers.js';
|
||||
import { phpMethodConfig } from '../../method-extractors/configs/php.js';
|
||||
|
||||
interface PhpArityMetadata {
|
||||
readonly parameterCount: number | undefined;
|
||||
readonly requiredParameterCount: number | undefined;
|
||||
readonly parameterTypes: readonly string[] | undefined;
|
||||
}
|
||||
|
||||
export function computePhpArityMetadata(fnNode: SyntaxNode): PhpArityMetadata {
|
||||
const params = phpMethodConfig.extractParameters?.(fnNode) ?? [];
|
||||
|
||||
let hasVariadic = false;
|
||||
let optionalCount = 0;
|
||||
const types: string[] = [];
|
||||
|
||||
for (const p of params) {
|
||||
if (p.isVariadic) {
|
||||
hasVariadic = true;
|
||||
} else if (p.isOptional) {
|
||||
optionalCount++;
|
||||
}
|
||||
if (p.type !== null) types.push(p.type);
|
||||
}
|
||||
// PHP variadic marker convention: append the literal '...' string to
|
||||
// `parameterTypes`. This is intentionally DIFFERENT from C#, which uses
|
||||
// the literal 'params' (its source-language keyword). The shared
|
||||
// `narrowOverloadCandidates` pass in `scope-resolution/passes/overload-
|
||||
// narrowing.ts` checks for the C# 'params' marker — that branch is
|
||||
// dead code for PHP because PHP variadic methods set `parameterCount
|
||||
// = undefined` (see line below), which skips the `max !== undefined`
|
||||
// gate that hosts the 'params' check. PHP's actual variadic-aware
|
||||
// arity logic lives in `phpArityCompatibility` (arity.ts) and now
|
||||
// also in `phpEmitUnresolvedReceiverEdges` (scope-resolver.ts), both
|
||||
// of which check `'...'`. Finding 9 of PR #1497 adversarial review.
|
||||
if (hasVariadic) types.push('...');
|
||||
|
||||
const total = params.length;
|
||||
// Variadic methods accept any arg count ≥ required — leave `parameterCount`
|
||||
// undefined so the registry treats max as unknown.
|
||||
const parameterCount = hasVariadic ? undefined : total;
|
||||
// The variadic slot itself accepts zero args; subtract it from the required
|
||||
// count so PHP's ArgumentCountError-equivalent calls (too few args before
|
||||
// the variadic) are correctly rejected by arity compatibility.
|
||||
const requiredParameterCount = total - optionalCount - (hasVariadic ? 1 : 0);
|
||||
|
||||
return {
|
||||
parameterCount,
|
||||
requiredParameterCount,
|
||||
parameterTypes: types.length > 0 ? types : undefined,
|
||||
};
|
||||
}
|
||||
47
gitnexus/src/core/ingestion/languages/php/arity.ts
Normal file
47
gitnexus/src/core/ingestion/languages/php/arity.ts
Normal file
|
|
@ -0,0 +1,47 @@
|
|||
/**
|
||||
* PHP arity check, accommodating variadic (`...$args`) and default parameters.
|
||||
*
|
||||
* The `def` metadata synthesized by `arity-metadata.ts`:
|
||||
* - `parameterCount` — total formal parameters; `undefined` when
|
||||
* the method has a variadic `...$param`.
|
||||
* - `requiredParameterCount` — min required (excludes defaulted params
|
||||
* and the variadic itself).
|
||||
* - `parameterTypes` — declared type strings; contains the
|
||||
* literal `'...'` when the method is variadic.
|
||||
*
|
||||
* Verdicts:
|
||||
* - `'compatible'` — `required <= argCount <= max`, OR the def has
|
||||
* variadic (any `argCount >= required`).
|
||||
* - `'incompatible'` — argCount below required, or above max with no variadic.
|
||||
* - `'unknown'` — metadata absent / incomplete; named-args can satisfy
|
||||
* any arity so we return unknown when we detect them.
|
||||
*
|
||||
* PHP supports named arguments (PHP 8.0+): `save(force: true)`. Named-arg
|
||||
* call sites cannot be arity-checked statically without parsing arg names,
|
||||
* so we return `'unknown'` when the callsite carries named args (signalled
|
||||
* by a negative `arity` value per the shared Callsite contract).
|
||||
*/
|
||||
|
||||
import type { Callsite, SymbolDefinition } from 'gitnexus-shared';
|
||||
|
||||
export function phpArityCompatibility(
|
||||
def: SymbolDefinition,
|
||||
callsite: Callsite,
|
||||
): 'compatible' | 'unknown' | 'incompatible' {
|
||||
const max = def.parameterCount;
|
||||
const min = def.requiredParameterCount;
|
||||
if (max === undefined && min === undefined) return 'unknown';
|
||||
|
||||
const argCount = callsite.arity;
|
||||
// Negative arity signals named-argument call sites — can't narrow statically.
|
||||
if (!Number.isFinite(argCount) || argCount < 0) return 'unknown';
|
||||
|
||||
const hasVarArgs =
|
||||
def.parameterTypes !== undefined &&
|
||||
def.parameterTypes.some((t) => t === '...' || t.startsWith('...'));
|
||||
|
||||
if (min !== undefined && argCount < min) return 'incompatible';
|
||||
if (max !== undefined && argCount > max && !hasVarArgs) return 'incompatible';
|
||||
|
||||
return 'compatible';
|
||||
}
|
||||
30
gitnexus/src/core/ingestion/languages/php/cache-stats.ts
Normal file
30
gitnexus/src/core/ingestion/languages/php/cache-stats.ts
Normal file
|
|
@ -0,0 +1,30 @@
|
|||
/**
|
||||
* Dev-mode counters for the cross-phase scope-captures parse cache
|
||||
* (PHP mirror of `languages/csharp/cache-stats.ts`).
|
||||
*
|
||||
* Gated by `PROF_SCOPE_RESOLUTION=1`. Production builds fold every
|
||||
* increment into dead code via the module-level `PROF` constant, so
|
||||
* the hot path in `captures.ts` stays branch-free.
|
||||
*/
|
||||
|
||||
const PROF = process.env.PROF_SCOPE_RESOLUTION === '1';
|
||||
|
||||
let CACHE_HITS = 0;
|
||||
let CACHE_MISSES = 0;
|
||||
|
||||
export function recordCacheHit(): void {
|
||||
if (PROF) CACHE_HITS++;
|
||||
}
|
||||
|
||||
export function recordCacheMiss(): void {
|
||||
if (PROF) CACHE_MISSES++;
|
||||
}
|
||||
|
||||
export function getPhpCaptureCacheStats(): { hits: number; misses: number } {
|
||||
return { hits: CACHE_HITS, misses: CACHE_MISSES };
|
||||
}
|
||||
|
||||
export function resetPhpCaptureCacheStats(): void {
|
||||
CACHE_HITS = 0;
|
||||
CACHE_MISSES = 0;
|
||||
}
|
||||
806
gitnexus/src/core/ingestion/languages/php/captures.ts
Normal file
806
gitnexus/src/core/ingestion/languages/php/captures.ts
Normal file
|
|
@ -0,0 +1,806 @@
|
|||
/**
|
||||
* `emitScopeCaptures` for PHP (RFC #909 Ring 3 LANG-php).
|
||||
*
|
||||
* Drives the PHP scope query against tree-sitter-php and groups raw
|
||||
* matches into `CaptureMatch[]` for the central extractor. Layers two
|
||||
* synthesized streams on top:
|
||||
*
|
||||
* 1. **Decomposed use declarations** — each `namespace_use_declaration`
|
||||
* is re-emitted with `@import.kind/source/name/alias` markers so
|
||||
* `interpretPhpImport` can recover the ParsedImport shape without
|
||||
* re-parsing raw text. Grouped uses fan out to one match per clause.
|
||||
*
|
||||
* 2. **Receiver-binding synthesis** — `$this` and `parent` type-bindings
|
||||
* are synthesized on every non-static method entry. PHP's grammar
|
||||
* does not express "implicit receiver of a non-static class method"
|
||||
* via a clean `.scm` pattern, so we walk up the AST in code.
|
||||
*
|
||||
* 3. **Arity metadata synthesis** — `@declaration.parameter-count` /
|
||||
* `@declaration.required-parameter-count` / `@declaration.parameter-types`
|
||||
* are synthesized on function-like declarations so the registry can
|
||||
* narrow overloads.
|
||||
*
|
||||
* 4. **PHPDoc synthesis** — @param and @return annotations in comment
|
||||
* nodes preceding method/function declarations are extracted and emitted
|
||||
* as `@type-binding.parameter` and `@type-binding.return` matches.
|
||||
*
|
||||
* 5. **Foreach loop synthesis** — `foreach ($users as $user)` emits
|
||||
* a `@type-binding.alias` match binding the loop variable to the
|
||||
* element type of the iterable (resolved from PHPDoc or scopeEnv).
|
||||
*
|
||||
* Pure given the input source text. No I/O, no globals consulted.
|
||||
*/
|
||||
|
||||
import type { Capture, CaptureMatch } from 'gitnexus-shared';
|
||||
import { findNodeAtRange, nodeToCapture, syntheticCapture } from '../../utils/ast-helpers.js';
|
||||
import { splitNamespaceUseDeclaration } from './import-decomposer.js';
|
||||
import { computePhpArityMetadata } from './arity-metadata.js';
|
||||
import { synthesizePhpReceiverBinding } from './receiver-binding.js';
|
||||
import { getPhpParser, getPhpScopeQuery } from './query.js';
|
||||
import { recordCacheHit, recordCacheMiss } from './cache-stats.js';
|
||||
import { getTreeSitterBufferSize } from '../../constants.js';
|
||||
import { parseSourceSafe } from '../../../tree-sitter/safe-parse.js';
|
||||
|
||||
type SyntaxNode = ReturnType<ReturnType<typeof getPhpParser>['parse']>['rootNode'];
|
||||
|
||||
/** Declaration anchors that carry function-like arity metadata. */
|
||||
const FUNCTION_DECL_TAGS = ['@declaration.method', '@declaration.function'] as const;
|
||||
|
||||
/** tree-sitter-php node types that the method extractor accepts. */
|
||||
const FUNCTION_NODE_TYPES = [
|
||||
'method_declaration',
|
||||
'function_definition',
|
||||
'anonymous_function',
|
||||
'arrow_function',
|
||||
] as const;
|
||||
|
||||
export function emitPhpScopeCaptures(
|
||||
sourceText: string,
|
||||
_filePath: string,
|
||||
cachedTree?: unknown,
|
||||
): readonly CaptureMatch[] {
|
||||
// Skip the parse when the caller already produced a Tree for this source.
|
||||
// The cachedTree parameter is typed as `unknown` at the LanguageProvider
|
||||
// contract layer; cast here at the use site.
|
||||
let tree = cachedTree as ReturnType<ReturnType<typeof getPhpParser>['parse']> | undefined;
|
||||
if (tree === undefined) {
|
||||
tree = parseSourceSafe(getPhpParser(), sourceText, undefined, {
|
||||
bufferSize: getTreeSitterBufferSize(sourceText),
|
||||
});
|
||||
recordCacheMiss();
|
||||
} else {
|
||||
recordCacheHit();
|
||||
}
|
||||
|
||||
const rawMatches = getPhpScopeQuery().matches(tree.rootNode);
|
||||
const out: CaptureMatch[] = [];
|
||||
|
||||
// Pre-scan: collect anchor node IDs of property_declaration nodes already
|
||||
// matched by the typed @declaration.property pattern (query.ts ~lines 95–98).
|
||||
// The untyped @declaration.variable catch-all (query.ts ~lines 101–103) is
|
||||
// intentionally loose — it has no `type:` constraint, so tree-sitter also
|
||||
// matches it against typed property declarations and emits a second capture
|
||||
// for the same property_declaration anchor. Graph-level def-id collision
|
||||
// currently masks the duplicate at the node-emit layer, but the catch-all
|
||||
// capture still flows through scope-binding / name-keyed registries with a
|
||||
// `$`-prefixed name that the typed branch's `$`-strip never normalizes —
|
||||
// a known vector for receiver-binding lookup pollution. The two patterns
|
||||
// produce separate rawMatches entries with separate `grouped` maps, so the
|
||||
// dedup has to be cross-match: build the set here, then skip
|
||||
// @declaration.variable matches whose anchor is in it (loop below).
|
||||
const typedPropertyAnchorIds = new Set<number>();
|
||||
for (const m of rawMatches) {
|
||||
for (const c of m.captures) {
|
||||
if (c.name === 'declaration.property') {
|
||||
typedPropertyAnchorIds.add(c.node.id);
|
||||
break;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
for (const m of rawMatches) {
|
||||
// Group captures by their tag name. Tree-sitter strips the leading
|
||||
// `@`; we put it back so the central extractor's prefix lookups work.
|
||||
const grouped: Record<string, Capture> = {};
|
||||
for (const c of m.captures) {
|
||||
const tag = '@' + c.name;
|
||||
grouped[tag] = nodeToCapture(tag, c.node);
|
||||
}
|
||||
if (Object.keys(grouped).length === 0) continue;
|
||||
|
||||
// Cross-match dedup for the typed-property double-match described above:
|
||||
// skip @declaration.variable matches whose anchor was already captured as
|
||||
// @declaration.property in an earlier match.
|
||||
if (grouped['@declaration.variable'] !== undefined) {
|
||||
const varCap = m.captures.find((c) => c.name === 'declaration.variable');
|
||||
if (varCap !== undefined && typedPropertyAnchorIds.has(varCap.node.id)) continue;
|
||||
}
|
||||
|
||||
// Normalize PHP property declarations: strip leading `$` from
|
||||
// `@declaration.name` for @declaration.property matches. PHP stores
|
||||
// field names WITHOUT the `$` sigil in the graph so that member access
|
||||
// lookups like `$user->address` can find the property named `address`
|
||||
// (not `$address`). `@type-binding.annotation` already strips `$` in
|
||||
// `interpretPhpTypeBinding`; this mirrors that for the declaration side.
|
||||
//
|
||||
// Only applies to `@declaration.property` — typed class properties and
|
||||
// constructor-promoted parameters. Untyped `@declaration.variable` keeps
|
||||
// its `$` prefix (those defs are Variable type and not in the field
|
||||
// registry, so their name doesn't affect member lookup).
|
||||
if (
|
||||
grouped['@declaration.property'] !== undefined &&
|
||||
grouped['@declaration.name'] !== undefined
|
||||
) {
|
||||
const nameCap = grouped['@declaration.name'];
|
||||
if (nameCap.text.startsWith('$')) {
|
||||
grouped['@declaration.name'] = { ...nameCap, text: nameCap.text.slice(1) };
|
||||
}
|
||||
}
|
||||
|
||||
// Normalize PHP receiver expressions so the compound-receiver resolver
|
||||
// can walk chains expressed with `->` (PHP) as if they used `.` (the
|
||||
// resolver's canonical separator). Without this, `$user->address->save()`
|
||||
// has receiver text `$user->address` — the resolver sees no `.` separator,
|
||||
// treats it as a bare identifier, and cannot walk field types.
|
||||
//
|
||||
// Transformation applied to `@reference.receiver` captures:
|
||||
// 1. Replace `->` with `.` ($user->address → $user.address)
|
||||
// 2. Strip leading `$` from each segment ($user.address → user.address)
|
||||
// 3. Strip trailing `?` on null-safe receivers ($user? → user)
|
||||
//
|
||||
// This is a PHP-local normalization — no shared pipeline code is changed.
|
||||
if (grouped['@reference.receiver'] !== undefined) {
|
||||
const recvCap = grouped['@reference.receiver']!;
|
||||
const normalized = normalizePhpReceiver(recvCap.text);
|
||||
if (normalized !== recvCap.text) {
|
||||
grouped['@reference.receiver'] = { ...recvCap, text: normalized };
|
||||
}
|
||||
}
|
||||
|
||||
// Normalize static property write: strip leading `$` from `@reference.name`
|
||||
// so `User::$count` resolves to property `count` (stored without `$` in graph).
|
||||
if (grouped['@reference.write.static'] !== undefined) {
|
||||
const nameCap = grouped['@reference.name'];
|
||||
if (nameCap !== undefined && nameCap.text.startsWith('$')) {
|
||||
grouped['@reference.name'] = {
|
||||
...nameCap,
|
||||
text: nameCap.text.slice(1),
|
||||
};
|
||||
}
|
||||
// Re-tag as @reference.write.member so downstream passes see a uniform write kind.
|
||||
grouped['@reference.write.member'] = grouped['@reference.write.static']!;
|
||||
delete grouped['@reference.write.static'];
|
||||
}
|
||||
|
||||
// Decompose each `namespace_use_declaration` so `interpretPhpImport`
|
||||
// sees the kind/source/name/alias markers it consumes.
|
||||
if (grouped['@import.statement'] !== undefined) {
|
||||
const stmtCapture = grouped['@import.statement'];
|
||||
const stmtNode = findNodeAtRange(
|
||||
tree.rootNode,
|
||||
stmtCapture.range,
|
||||
'namespace_use_declaration',
|
||||
);
|
||||
if (stmtNode !== null) {
|
||||
const decomposed = splitNamespaceUseDeclaration(stmtNode);
|
||||
if (decomposed.length > 0) {
|
||||
for (const d of decomposed) out.push(d);
|
||||
continue;
|
||||
}
|
||||
}
|
||||
// Defensive fallback: emit the raw match.
|
||||
out.push(grouped);
|
||||
continue;
|
||||
}
|
||||
|
||||
// Synthesize `$this` / `parent` receiver type-bindings on every
|
||||
// non-static method-like. Mirrors C#'s `this` / `base` synthesis.
|
||||
if (grouped['@scope.function'] !== undefined) {
|
||||
out.push(grouped);
|
||||
const anchor = grouped['@scope.function']!;
|
||||
const fnNode = findFunctionNode(tree.rootNode, anchor.range);
|
||||
if (fnNode !== null) {
|
||||
for (const synth of synthesizePhpReceiverBinding(fnNode)) {
|
||||
out.push(synth);
|
||||
}
|
||||
// Synthesize PHPDoc @param and @return type bindings for this fn.
|
||||
for (const synth of synthesizePhpDocBindings(fnNode)) {
|
||||
out.push(synth);
|
||||
}
|
||||
// Synthesize foreach loop variable bindings inside this fn body.
|
||||
for (const synth of synthesizeForeachBindings(fnNode)) {
|
||||
out.push(synth);
|
||||
}
|
||||
}
|
||||
continue;
|
||||
}
|
||||
|
||||
// Synthesize arity metadata on function-like declarations so the
|
||||
// registry can narrow overloads.
|
||||
const declTag = FUNCTION_DECL_TAGS.find((t) => grouped[t] !== undefined);
|
||||
if (declTag !== undefined) {
|
||||
const anchor = grouped[declTag]!;
|
||||
const fnNode = findFunctionNode(tree.rootNode, anchor.range);
|
||||
if (fnNode !== null) {
|
||||
const arity = computePhpArityMetadata(fnNode);
|
||||
if (arity.parameterCount !== undefined) {
|
||||
grouped['@declaration.parameter-count'] = syntheticCapture(
|
||||
'@declaration.parameter-count',
|
||||
fnNode,
|
||||
String(arity.parameterCount),
|
||||
);
|
||||
}
|
||||
if (arity.requiredParameterCount !== undefined) {
|
||||
grouped['@declaration.required-parameter-count'] = syntheticCapture(
|
||||
'@declaration.required-parameter-count',
|
||||
fnNode,
|
||||
String(arity.requiredParameterCount),
|
||||
);
|
||||
}
|
||||
if (arity.parameterTypes !== undefined) {
|
||||
grouped['@declaration.parameter-types'] = syntheticCapture(
|
||||
'@declaration.parameter-types',
|
||||
fnNode,
|
||||
JSON.stringify(arity.parameterTypes),
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Synthesize `@reference.arity` on every call site so the registry's
|
||||
// arity filter can narrow overloads. Count the `argument` children of
|
||||
// the backing `arguments` node. Mirrors C#'s pattern (csharp/captures.ts
|
||||
// lines 149-186). PHP needs this for arity-based dispatch (Cluster H).
|
||||
const callTag = (
|
||||
['@reference.call.free', '@reference.call.member', '@reference.call.constructor'] as const
|
||||
).find((t) => grouped[t] !== undefined);
|
||||
if (callTag !== undefined && grouped['@reference.arity'] === undefined) {
|
||||
const anchor = grouped[callTag]!;
|
||||
const callNode =
|
||||
findNodeAtRange(tree.rootNode, anchor.range, 'function_call_expression') ??
|
||||
findNodeAtRange(tree.rootNode, anchor.range, 'member_call_expression') ??
|
||||
findNodeAtRange(tree.rootNode, anchor.range, 'nullsafe_member_call_expression') ??
|
||||
findNodeAtRange(tree.rootNode, anchor.range, 'scoped_call_expression') ??
|
||||
findNodeAtRange(tree.rootNode, anchor.range, 'object_creation_expression');
|
||||
if (callNode !== null) {
|
||||
const argList = callNode.childForFieldName('arguments');
|
||||
const args: SyntaxNode[] = [];
|
||||
if (argList !== null) {
|
||||
for (let i = 0; i < argList.namedChildCount; i++) {
|
||||
const child = argList.namedChild(i);
|
||||
if (child !== null && child.type === 'argument') args.push(child);
|
||||
}
|
||||
}
|
||||
grouped['@reference.arity'] = syntheticCapture(
|
||||
'@reference.arity',
|
||||
callNode,
|
||||
String(args.length),
|
||||
);
|
||||
// Infer argument types from literal nodes for type-based narrowing.
|
||||
// Non-literal arguments emit empty string ("unknown" = any-match).
|
||||
const argTypes = args.map((arg) => inferPhpArgType(arg));
|
||||
grouped['@reference.parameter-types'] = syntheticCapture(
|
||||
'@reference.parameter-types',
|
||||
callNode,
|
||||
JSON.stringify(argTypes),
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
out.push(grouped);
|
||||
}
|
||||
|
||||
return out;
|
||||
}
|
||||
|
||||
/** Find the first PHP function-like node at the given range. */
|
||||
function findFunctionNode(rootNode: SyntaxNode, range: Capture['range']): SyntaxNode | null {
|
||||
for (const nodeType of FUNCTION_NODE_TYPES) {
|
||||
const n = findNodeAtRange(rootNode, range, nodeType);
|
||||
if (n !== null) return n as SyntaxNode;
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
// ─── PHP receiver normalization ──────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Normalize a PHP receiver expression so the language-agnostic
|
||||
* compound-receiver resolver (which splits on `.`) can walk field-type chains.
|
||||
*
|
||||
* The compound-receiver resolver:
|
||||
* - splits on `.` to get chain segments
|
||||
* - looks up the first segment in `typeBindings` (keyed with `$` for variables)
|
||||
* - walks subsequent segments as field names (stored without `$` in the graph)
|
||||
*
|
||||
* Transformation:
|
||||
* 1. Replace `->` and `?->` with `.` so the resolver's splitter works
|
||||
* 2. Strip any bare `?` fragment left by null-safe chain ends
|
||||
* 3. Strip `$` from all segments EXCEPT the first (which is a variable
|
||||
* and must keep `$` for typeBindings lookup — e.g. `$user → User`)
|
||||
*
|
||||
* Examples:
|
||||
* `$user` → `$user` (bare variable — unchanged)
|
||||
* `$user->address` → `$user.address`
|
||||
* `$user->address->city` → `$user.address.city`
|
||||
* `$user?` → `$user` (null-safe trailing `?` stripped)
|
||||
* `$this` → `$this` (receiverBinding uses `$this`)
|
||||
* `parent` → `parent` (super-receiver check)
|
||||
*/
|
||||
function normalizePhpReceiver(raw: string): string {
|
||||
// Keep `$this`, `parent`, and `self` as-is.
|
||||
if (raw === '$this' || raw === 'parent' || raw === 'self') return raw;
|
||||
|
||||
// Replace `?->` (null-safe) and plain `->` with `.`.
|
||||
let text = raw.replace(/\?->/g, '.').replace(/->/g, '.');
|
||||
// Strip a trailing `?` (null-safe fragment on the last object node).
|
||||
text = text.replace(/\?$/, '');
|
||||
// Collapse any doubled dots from `?->` where `?` was on its own.
|
||||
text = text.replace(/\.{2,}/g, '.');
|
||||
// Strip trailing dot.
|
||||
text = text.replace(/\.$/, '');
|
||||
|
||||
// Split on `.` and strip `$` from all segments EXCEPT the first.
|
||||
// The first segment is a PHP variable (typeBinding key includes `$`).
|
||||
// Subsequent segments are property/method names (stored without `$`).
|
||||
const segments = text.split('.');
|
||||
for (let i = 1; i < segments.length; i++) {
|
||||
const s = segments[i];
|
||||
if (s !== undefined && s.startsWith('$')) segments[i] = s.slice(1);
|
||||
}
|
||||
return segments.join('.');
|
||||
}
|
||||
|
||||
// ─── PHP argument type inference ─────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Infer the PHP type of a call argument from its literal shape.
|
||||
* Returns an empty string for non-literals (treated as "unknown" = any-match).
|
||||
* Mirrors C#'s `inferArgType` helper.
|
||||
*/
|
||||
function inferPhpArgType(argNode: SyntaxNode): string {
|
||||
// argument node wraps the actual expression
|
||||
const expr = argNode.firstNamedChild ?? argNode;
|
||||
switch (expr.type) {
|
||||
case 'integer':
|
||||
return 'int';
|
||||
case 'float':
|
||||
return 'float';
|
||||
case 'string':
|
||||
case 'encapsed_string':
|
||||
case 'heredoc':
|
||||
case 'nowdoc':
|
||||
return 'string';
|
||||
case 'boolean':
|
||||
case 'true':
|
||||
case 'false':
|
||||
return 'bool';
|
||||
case 'null':
|
||||
return 'null';
|
||||
default:
|
||||
return '';
|
||||
}
|
||||
}
|
||||
|
||||
// ─── PHPDoc synthesis ─────────────────────────────────────────────────────────
|
||||
|
||||
/** PHP 8+ attribute_list nodes that appear between PHPDoc and method. */
|
||||
const SKIP_SIBLING_TYPES = new Set(['attribute_list', 'attribute', 'comment']);
|
||||
|
||||
/** Regex for PHPDoc @param: standard `@param Type $name` */
|
||||
const PHPDOC_PARAM_RE = /@param\s+(\S+)\s+\$(\w+)/g;
|
||||
/** Regex for PHPDoc @param: alternate `@param $name Type` */
|
||||
const PHPDOC_PARAM_ALT_RE = /@param\s+\$(\w+)\s+(\S+)/g;
|
||||
/** Regex for PHPDoc @return: `@return Type` */
|
||||
const PHPDOC_RETURN_RE = /@return\s+(\S+)/;
|
||||
|
||||
/**
|
||||
* Normalize a PHP type string to a simple class name for binding purposes.
|
||||
* Returns null for primitives or uninformative types.
|
||||
* Mirrors `normalizePhpType` in `interpret.ts` but operates on raw PHPDoc strings.
|
||||
*/
|
||||
function normalizePhpDocType(raw: string): string | null {
|
||||
let type = raw.trim();
|
||||
// Strip nullable prefix
|
||||
if (type.startsWith('?')) type = type.slice(1).trim();
|
||||
// Strip array suffix: User[] → User
|
||||
if (type.endsWith('[]')) type = type.slice(0, -2).trim();
|
||||
// Strip union with null/false/void
|
||||
if (type.includes('|')) {
|
||||
const parts = type
|
||||
.split('|')
|
||||
.map((p) => p.trim())
|
||||
.filter((p) => p !== 'null' && p !== 'false' && p !== 'void' && p !== 'mixed' && p !== '');
|
||||
if (parts.length !== 1) return null;
|
||||
type = parts[0];
|
||||
}
|
||||
// Strip intersection: take first part
|
||||
if (type.includes('&')) {
|
||||
const first = type.split('&')[0].trim();
|
||||
if (first === '') return null;
|
||||
type = first;
|
||||
}
|
||||
// Strip generic wrapper: Collection<User> → User
|
||||
const genericMatch = type.match(/^\w[\w\\]*\s*<([^,<>]+)>$/);
|
||||
if (genericMatch) {
|
||||
type = genericMatch[1].trim();
|
||||
// Strip array suffix again inside generic
|
||||
if (type.endsWith('[]')) type = type.slice(0, -2).trim();
|
||||
}
|
||||
// Strip namespace qualifier: \App\Models\User → User
|
||||
if (type.includes('\\')) {
|
||||
const segs = type.split('\\').filter(Boolean);
|
||||
type = segs[segs.length - 1] ?? type;
|
||||
}
|
||||
// Reject primitives
|
||||
if (PHP_PRIMITIVES.has(type.toLowerCase())) return null;
|
||||
// Must be a simple identifier
|
||||
if (!/^\w+$/.test(type)) return null;
|
||||
return type;
|
||||
}
|
||||
|
||||
const PHP_PRIMITIVES = new Set([
|
||||
'int',
|
||||
'integer',
|
||||
'float',
|
||||
'double',
|
||||
'string',
|
||||
'bool',
|
||||
'boolean',
|
||||
'array',
|
||||
'object',
|
||||
'callable',
|
||||
'iterable',
|
||||
'null',
|
||||
'void',
|
||||
'never',
|
||||
'mixed',
|
||||
'false',
|
||||
'true',
|
||||
'self',
|
||||
'static',
|
||||
'parent',
|
||||
]);
|
||||
|
||||
/**
|
||||
* Collect comment text from siblings immediately before `fnNode`.
|
||||
* Skips PHP 8+ attribute_list nodes.
|
||||
*/
|
||||
function collectPrecedingComments(fnNode: SyntaxNode): string {
|
||||
const texts: string[] = [];
|
||||
let sibling = fnNode.previousSibling;
|
||||
while (sibling !== null) {
|
||||
if (sibling.type === 'comment') {
|
||||
texts.unshift(sibling.text);
|
||||
} else if (sibling.isNamed && !SKIP_SIBLING_TYPES.has(sibling.type)) {
|
||||
break;
|
||||
}
|
||||
sibling = sibling.previousSibling;
|
||||
}
|
||||
return texts.join('\n');
|
||||
}
|
||||
|
||||
/**
|
||||
* Synthesize PHPDoc @param and @return type-binding captures for a
|
||||
* method_declaration or function_definition node.
|
||||
*
|
||||
* PHPDoc @param Type $name → `@type-binding.parameter` match (anchored at fn body/return_type).
|
||||
* PHPDoc @return Type → `@type-binding.return` match (anchored at fn name).
|
||||
*/
|
||||
function synthesizePhpDocBindings(fnNode: SyntaxNode): CaptureMatch[] {
|
||||
if (fnNode.type !== 'method_declaration' && fnNode.type !== 'function_definition') return [];
|
||||
|
||||
const commentBlock = collectPrecedingComments(fnNode);
|
||||
if (commentBlock === '') return [];
|
||||
|
||||
const out: CaptureMatch[] = [];
|
||||
|
||||
// Anchor for parameter type-bindings: the function body (or return_type as fallback).
|
||||
// The binding must be inside the function scope so it's visible to body statements.
|
||||
const bodyNode = fnNode.childForFieldName('body');
|
||||
const anchorNode = bodyNode ?? fnNode;
|
||||
|
||||
// ── @param annotations ────────────────────────────────────────────────────
|
||||
PHPDOC_PARAM_RE.lastIndex = 0;
|
||||
let m: RegExpExecArray | null;
|
||||
const seenParams = new Set<string>();
|
||||
|
||||
while ((m = PHPDOC_PARAM_RE.exec(commentBlock)) !== null) {
|
||||
const rawType = m[1];
|
||||
const paramName = '$' + m[2];
|
||||
const typeName = normalizePhpDocType(rawType);
|
||||
if (typeName === null) continue;
|
||||
seenParams.add(paramName);
|
||||
out.push({
|
||||
'@type-binding.parameter': nodeToCapture('@type-binding.parameter', anchorNode),
|
||||
'@type-binding.name': syntheticCapture('@type-binding.name', anchorNode, paramName),
|
||||
'@type-binding.type': syntheticCapture('@type-binding.type', anchorNode, typeName),
|
||||
});
|
||||
}
|
||||
|
||||
// Also check alternate PHPDoc order: @param $name Type
|
||||
PHPDOC_PARAM_ALT_RE.lastIndex = 0;
|
||||
while ((m = PHPDOC_PARAM_ALT_RE.exec(commentBlock)) !== null) {
|
||||
const paramName = '$' + m[1];
|
||||
if (seenParams.has(paramName)) continue; // standard format takes priority
|
||||
const rawType = m[2];
|
||||
const typeName = normalizePhpDocType(rawType);
|
||||
if (typeName === null) continue;
|
||||
out.push({
|
||||
'@type-binding.parameter': nodeToCapture('@type-binding.parameter', anchorNode),
|
||||
'@type-binding.name': syntheticCapture('@type-binding.name', anchorNode, paramName),
|
||||
'@type-binding.type': syntheticCapture('@type-binding.type', anchorNode, typeName),
|
||||
});
|
||||
}
|
||||
|
||||
// ── @return annotation ────────────────────────────────────────────────────
|
||||
const returnMatch = PHPDOC_RETURN_RE.exec(commentBlock);
|
||||
if (returnMatch !== null) {
|
||||
const rawType = returnMatch[1];
|
||||
const typeName = normalizePhpDocType(rawType);
|
||||
if (typeName !== null) {
|
||||
// @return bindings must be anchored at the method name and hoisted to Module scope
|
||||
// by phpBindingScopeFor (which checks for @type-binding.return presence).
|
||||
// Use the function_definition/method_declaration node itself as the anchor — it
|
||||
// coincides with the innermost scope's range, so auto-hoist kicks in.
|
||||
const nameNode = fnNode.childForFieldName('name') ?? fnNode;
|
||||
out.push({
|
||||
'@type-binding.return': nodeToCapture('@type-binding.return', fnNode),
|
||||
'@type-binding.name': syntheticCapture('@type-binding.name', nameNode, nameNode.text),
|
||||
'@type-binding.type': syntheticCapture('@type-binding.type', nameNode, typeName),
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
return out;
|
||||
}
|
||||
|
||||
// ─── Foreach synthesis ───────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Walk all `foreach_statement` nodes inside `fnNode` and synthesize
|
||||
* `@type-binding.alias` captures binding the loop variable to the
|
||||
* element type of the iterable.
|
||||
*
|
||||
* Supports:
|
||||
* - `foreach ($users as $user)` — simple iterable variable
|
||||
* - `foreach ($users as $k => $user)` — key→value pair
|
||||
* - `foreach ($this->users as $user)` — member access iterable
|
||||
* - `foreach (getUsers() as $user)` — NOT yet supported (needs return type)
|
||||
*
|
||||
* The element type is resolved by:
|
||||
* 1. Looking up the iterable name in PHPDoc @param bindings already
|
||||
* collected for this function (passed via typeBindingsByName).
|
||||
* 2. Direct resolution when iterable's env type IS the element type
|
||||
* (because PHPDoc normalizes `User[]` → `User` already).
|
||||
*/
|
||||
function synthesizeForeachBindings(fnNode: SyntaxNode): CaptureMatch[] {
|
||||
if (
|
||||
fnNode.type !== 'method_declaration' &&
|
||||
fnNode.type !== 'function_definition' &&
|
||||
fnNode.type !== 'anonymous_function' &&
|
||||
fnNode.type !== 'arrow_function'
|
||||
) {
|
||||
return [];
|
||||
}
|
||||
|
||||
const out: CaptureMatch[] = [];
|
||||
|
||||
// Build a mini type map from the function's PHPDoc @param annotations.
|
||||
// This is re-parsed here (not cached from synthesizePhpDocBindings) for simplicity;
|
||||
// the cost is negligible given the small comment sizes.
|
||||
const commentBlock = collectPrecedingComments(fnNode);
|
||||
const paramTypeMap = buildParamTypeMap(commentBlock);
|
||||
|
||||
// Walk the function body for foreach_statement nodes.
|
||||
const bodyNode = fnNode.childForFieldName('body');
|
||||
if (bodyNode === null) return [];
|
||||
collectForeachBindings(bodyNode, fnNode, paramTypeMap, out);
|
||||
|
||||
return out;
|
||||
}
|
||||
|
||||
/** Build a map of `$paramName → elementTypeName` from PHPDoc @param in a comment block. */
|
||||
function buildParamTypeMap(commentBlock: string): Map<string, string> {
|
||||
const map = new Map<string, string>();
|
||||
if (commentBlock === '') return map;
|
||||
|
||||
PHPDOC_PARAM_RE.lastIndex = 0;
|
||||
let m: RegExpExecArray | null;
|
||||
while ((m = PHPDOC_PARAM_RE.exec(commentBlock)) !== null) {
|
||||
const rawType = m[1];
|
||||
const paramName = '$' + m[2];
|
||||
const typeName = normalizePhpDocType(rawType);
|
||||
if (typeName !== null) map.set(paramName, typeName);
|
||||
}
|
||||
PHPDOC_PARAM_ALT_RE.lastIndex = 0;
|
||||
while ((m = PHPDOC_PARAM_ALT_RE.exec(commentBlock)) !== null) {
|
||||
const paramName = '$' + m[1];
|
||||
if (map.has(paramName)) continue;
|
||||
const rawType = m[2];
|
||||
const typeName = normalizePhpDocType(rawType);
|
||||
if (typeName !== null) map.set(paramName, typeName);
|
||||
}
|
||||
return map;
|
||||
}
|
||||
|
||||
/**
|
||||
* Walk a subtree and collect foreach_statement bindings.
|
||||
* Recursively descends into all child nodes.
|
||||
*/
|
||||
function collectForeachBindings(
|
||||
node: SyntaxNode,
|
||||
fnNode: SyntaxNode,
|
||||
paramTypeMap: Map<string, string>,
|
||||
out: CaptureMatch[],
|
||||
): void {
|
||||
if (node.type === 'foreach_statement') {
|
||||
const synth = synthesizeSingleForeach(node, fnNode, paramTypeMap);
|
||||
if (synth !== null) out.push(synth);
|
||||
}
|
||||
for (let i = 0; i < node.childCount; i++) {
|
||||
const child = node.child(i);
|
||||
if (child !== null) {
|
||||
collectForeachBindings(child, fnNode, paramTypeMap, out);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Synthesize a single `@type-binding.alias` match for a `foreach_statement`.
|
||||
*
|
||||
* AST structure for foreach_statement (tree-sitter-php):
|
||||
* foreach ( <iterable> as <value_or_pair> ) <body>
|
||||
* Named children (excluding body): first = iterable, second = value or pair.
|
||||
*/
|
||||
function synthesizeSingleForeach(
|
||||
foreachNode: SyntaxNode,
|
||||
fnNode: SyntaxNode,
|
||||
paramTypeMap: Map<string, string>,
|
||||
): CaptureMatch | null {
|
||||
// Collect non-body named children: [iterable, value_or_pair]
|
||||
const bodyNode = foreachNode.childForFieldName('body');
|
||||
const children: SyntaxNode[] = [];
|
||||
for (let i = 0; i < foreachNode.namedChildCount; i++) {
|
||||
const child = foreachNode.namedChild(i);
|
||||
if (child !== null && child !== bodyNode) children.push(child);
|
||||
}
|
||||
if (children.length < 2) return null;
|
||||
|
||||
const iterableNode = children[0];
|
||||
const valueOrPair = children[1];
|
||||
|
||||
// Determine the loop variable node
|
||||
let loopVarNode: SyntaxNode;
|
||||
if (valueOrPair.type === 'pair') {
|
||||
// $key => $value — use the last named child of the pair
|
||||
const lastChild = valueOrPair.namedChild(valueOrPair.namedChildCount - 1);
|
||||
if (lastChild === null) return null;
|
||||
loopVarNode =
|
||||
lastChild.type === 'by_ref' ? (lastChild.firstNamedChild ?? lastChild) : lastChild;
|
||||
} else {
|
||||
loopVarNode =
|
||||
valueOrPair.type === 'by_ref' ? (valueOrPair.firstNamedChild ?? valueOrPair) : valueOrPair;
|
||||
}
|
||||
|
||||
// Loop variable must be a variable_name
|
||||
if (loopVarNode.type !== 'variable_name') return null;
|
||||
const loopVarName = loopVarNode.text; // e.g. '$user'
|
||||
|
||||
// Resolve the element type from the iterable
|
||||
let elementType: string | null = null;
|
||||
|
||||
if (iterableNode.type === 'variable_name') {
|
||||
// foreach ($users as $user) — look up $users in param map
|
||||
const iterableName = iterableNode.text; // e.g. '$users'
|
||||
elementType = paramTypeMap.get(iterableName) ?? null;
|
||||
} else if (iterableNode.type === 'member_access_expression') {
|
||||
// foreach ($this->users as $user) — property name is the field
|
||||
const propNameNode = iterableNode.childForFieldName('name');
|
||||
if (propNameNode !== null) {
|
||||
// Property stored with $ prefix in paramTypeMap (rare for $this->prop patterns)
|
||||
// Try both with and without $ prefix
|
||||
const propKey = '$' + propNameNode.text;
|
||||
elementType = paramTypeMap.get(propKey) ?? null;
|
||||
if (elementType === null) {
|
||||
// Try to find the property type from the enclosing class
|
||||
elementType = findClassPropertyElementType(iterableNode, fnNode);
|
||||
}
|
||||
}
|
||||
} else if (iterableNode.type === 'function_call_expression') {
|
||||
// foreach (getUsers() as $user) — use the function name as a type alias.
|
||||
// The function's @return annotation produces a @type-binding.return binding
|
||||
// in the Module scope (e.g. getUsers → User). The scope-extractor's
|
||||
// followChainedRef will resolve $user → getUsers → User.
|
||||
const funcNode = iterableNode.childForFieldName('function');
|
||||
if (funcNode !== null && funcNode.type === 'name') {
|
||||
elementType = funcNode.text; // e.g. 'getUsers' — chain will be resolved later
|
||||
}
|
||||
} else if (iterableNode.type === 'member_call_expression') {
|
||||
// foreach ($this->getUsers() as $user) — use the method name as a type alias.
|
||||
const methodNameNode = iterableNode.childForFieldName('name');
|
||||
if (methodNameNode !== null) {
|
||||
elementType = methodNameNode.text; // e.g. 'getUsers'
|
||||
}
|
||||
}
|
||||
|
||||
if (elementType === null) return null;
|
||||
|
||||
// Anchor the binding inside the foreach body so it's scoped to the loop.
|
||||
const anchorNode = bodyNode ?? foreachNode;
|
||||
|
||||
return {
|
||||
'@type-binding.alias': nodeToCapture('@type-binding.alias', anchorNode),
|
||||
'@type-binding.name': syntheticCapture('@type-binding.name', anchorNode, loopVarName),
|
||||
'@type-binding.type': syntheticCapture('@type-binding.type', anchorNode, elementType),
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Try to find the element type for `$this->property` member access by walking
|
||||
* up from the foreach to the enclosing class and scanning the property declaration.
|
||||
*/
|
||||
function findClassPropertyElementType(
|
||||
memberAccessNode: SyntaxNode,
|
||||
fnNode: SyntaxNode,
|
||||
): string | null {
|
||||
const propNameNode = memberAccessNode.childForFieldName('name');
|
||||
if (propNameNode === null) return null;
|
||||
const propName = propNameNode.text;
|
||||
|
||||
// Walk up from fnNode to find the enclosing class declaration
|
||||
let cur: SyntaxNode | null = fnNode.parent;
|
||||
while (cur !== null) {
|
||||
if (cur.type === 'class_declaration' || cur.type === 'trait_declaration') {
|
||||
break;
|
||||
}
|
||||
cur = cur.parent;
|
||||
}
|
||||
if (cur === null) return null;
|
||||
|
||||
// Find the property_declaration with matching variable_name '$propName'
|
||||
const declList = cur.childForFieldName('body');
|
||||
if (declList === null) return null;
|
||||
|
||||
for (let i = 0; i < declList.namedChildCount; i++) {
|
||||
const child = declList.namedChild(i);
|
||||
if (child === null || child.type !== 'property_declaration') continue;
|
||||
for (let j = 0; j < child.namedChildCount; j++) {
|
||||
const elem = child.namedChild(j);
|
||||
if (elem === null || elem.type !== 'property_element') continue;
|
||||
const varNameNode = elem.firstNamedChild;
|
||||
if (varNameNode === null || varNameNode.text !== '$' + propName) continue;
|
||||
// Found the property — get its element type from @var PHPDoc or native type
|
||||
return extractPropertyElementType(child);
|
||||
}
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
/** Regex for PHPDoc @var: `@var Type` */
|
||||
const PHPDOC_VAR_RE = /@var\s+(\S+)/;
|
||||
|
||||
/**
|
||||
* Extract element type from a property_declaration node:
|
||||
* 1. PHPDoc @var annotation on a preceding comment sibling
|
||||
* 2. PHP 7.4+ native type field (non-array)
|
||||
*/
|
||||
function extractPropertyElementType(propDecl: SyntaxNode): string | null {
|
||||
// Strategy 1: PHPDoc @var on a preceding comment sibling
|
||||
let sibling = propDecl.previousSibling;
|
||||
while (sibling !== null) {
|
||||
if (sibling.type === 'comment') {
|
||||
const m = PHPDOC_VAR_RE.exec(sibling.text);
|
||||
if (m !== null) return normalizePhpDocType(m[1]);
|
||||
} else if (sibling.isNamed && !SKIP_SIBLING_TYPES.has(sibling.type)) {
|
||||
break;
|
||||
}
|
||||
sibling = sibling.previousSibling;
|
||||
}
|
||||
// Strategy 2: native type field — skip generic 'array'
|
||||
const typeNode = propDecl.childForFieldName('type');
|
||||
if (typeNode === null) return null;
|
||||
const typeName = typeNode.text.trim();
|
||||
if (typeName === 'array' || typeName === '') return null;
|
||||
return normalizePhpDocType(typeName);
|
||||
}
|
||||
304
gitnexus/src/core/ingestion/languages/php/import-decomposer.ts
Normal file
304
gitnexus/src/core/ingestion/languages/php/import-decomposer.ts
Normal file
|
|
@ -0,0 +1,304 @@
|
|||
/**
|
||||
* Decompose a PHP `namespace_use_declaration` into one or more
|
||||
* `CaptureMatch` objects carrying the synthesized markers
|
||||
* `@import.kind` / `@import.source` / `@import.name` / `@import.alias`
|
||||
* that `interpretPhpImport` consumes.
|
||||
*
|
||||
* PHP import forms handled:
|
||||
*
|
||||
* use Foo\Bar; → namespace, localName=Bar
|
||||
* use Foo\Bar as Baz; → alias, localName=Baz
|
||||
* use function Foo\bar; → function, localName=bar
|
||||
* use const Foo\BAR; → const, localName=BAR
|
||||
* use Foo\{A, B as C}; → grouped: one match per clause
|
||||
* use function Foo\{f, g as h}; → grouped function variants
|
||||
* use const Foo\{X, Y as Z}; → grouped const variants
|
||||
*
|
||||
* Unlike C#'s decomposer this is 1:N — each grouped use_declaration
|
||||
* fans out to one CaptureMatch per inner clause.
|
||||
*/
|
||||
|
||||
import type { Capture, CaptureMatch } from 'gitnexus-shared';
|
||||
import { nodeToCapture, syntheticCapture, type SyntaxNode } from '../../utils/ast-helpers.js';
|
||||
|
||||
export type PhpImportKind = 'namespace' | 'alias' | 'function' | 'const';
|
||||
|
||||
interface PhpImportSpec {
|
||||
readonly kind: PhpImportKind;
|
||||
/** Full backslash-separated path (backslashes intact): `Foo\Bar\Baz`. */
|
||||
readonly source: string;
|
||||
/** Local binding name — last source segment for plain imports, the
|
||||
* alias identifier for aliased imports. */
|
||||
readonly name: string;
|
||||
/** Present iff kind === 'alias'. */
|
||||
readonly alias?: string;
|
||||
/** Anchor node for synthesized captures (range-wise). */
|
||||
readonly atNode: SyntaxNode;
|
||||
}
|
||||
|
||||
/**
|
||||
* Decompose a `namespace_use_declaration` node into one `CaptureMatch`
|
||||
* per logical import. Returns `[]` when the node is unrecognized or
|
||||
* carries no resolvable clauses.
|
||||
*/
|
||||
export function splitNamespaceUseDeclaration(stmtNode: SyntaxNode): CaptureMatch[] {
|
||||
if (stmtNode.type !== 'namespace_use_declaration') return [];
|
||||
|
||||
// Detect qualifier keyword: `use function` / `use const`
|
||||
// tree-sitter-php uses a `use_type` or `function`/`const` keyword
|
||||
// child to distinguish them. We scan the raw text before the first
|
||||
// backslash-path child.
|
||||
const qualifier = detectQualifier(stmtNode);
|
||||
|
||||
// Grouped use: `use Foo\{A, B as C}` — find namespace_use_group child.
|
||||
const groupNode = findNamedChild(stmtNode, 'namespace_use_group');
|
||||
if (groupNode !== null) {
|
||||
return decomposeGrouped(stmtNode, groupNode, qualifier);
|
||||
}
|
||||
|
||||
// Single use clause (possibly aliased).
|
||||
const spec = parseSingleUseClause(stmtNode, qualifier);
|
||||
if (spec === null) return [];
|
||||
return [buildImportMatch(stmtNode, spec)];
|
||||
}
|
||||
|
||||
// ── Qualifier detection ────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Return the qualifier keyword appearing after `use`:
|
||||
* `'function'`, `'const'`, or `null` for plain namespace use.
|
||||
*
|
||||
* tree-sitter-php emits the qualifier as a `name` node with text
|
||||
* "function" or "const" (not a keyword token in recent grammars),
|
||||
* or as a dedicated `use_type` node. We inspect the node's raw text
|
||||
* to be grammar-version-agnostic.
|
||||
*/
|
||||
function detectQualifier(node: SyntaxNode): PhpImportKind {
|
||||
const raw = node.text;
|
||||
// Match `use function` or `use const` at the start (after optional whitespace)
|
||||
if (/^\s*use\s+function\s/i.test(raw)) return 'function';
|
||||
if (/^\s*use\s+const\s/i.test(raw)) return 'const';
|
||||
return 'namespace';
|
||||
}
|
||||
|
||||
// ── Single clause parsing ──────────────────────────────────────────────────
|
||||
|
||||
function parseSingleUseClause(node: SyntaxNode, qualifier: PhpImportKind): PhpImportSpec | null {
|
||||
// A plain `namespace_use_declaration` has one or more
|
||||
// `namespace_use_clause` named children (each clause is one import,
|
||||
// comma-separated for multiple). For the single case there is one.
|
||||
const clause = findNamedChild(node, 'namespace_use_clause');
|
||||
if (clause !== null) return parseUseClause(clause, qualifier);
|
||||
|
||||
// Older grammar versions may put the qualified_name directly under
|
||||
// the declaration node. Check for a qualified_name or name child.
|
||||
const qualName = findNamedChild(node, 'qualified_name') ?? findNamedChild(node, 'name');
|
||||
if (qualName === null) return null;
|
||||
const source = qualName.text.trim();
|
||||
if (source === '') return null;
|
||||
return {
|
||||
kind: qualifier,
|
||||
source,
|
||||
name: lastSegment(source),
|
||||
atNode: node,
|
||||
};
|
||||
}
|
||||
|
||||
function parseUseClause(clause: SyntaxNode, qualifier: PhpImportKind): PhpImportSpec | null {
|
||||
// namespace_use_clause:
|
||||
// qualified_name (or name)
|
||||
// optional: alias_clause → "as" name (some grammar versions)
|
||||
// optional: bare name node (tree-sitter-php ≥ 0.22 emits the
|
||||
// alias as a sibling `name` node
|
||||
// directly, not inside alias_clause)
|
||||
const qualName = findNamedChild(clause, 'qualified_name') ?? findNamedChild(clause, 'name');
|
||||
if (qualName === null) return null;
|
||||
const source = qualName.text.trim();
|
||||
if (source === '') return null;
|
||||
|
||||
// Strategy 1: explicit alias_clause wrapper (older grammar versions).
|
||||
const aliasClause = findNamedChild(clause, 'alias_clause');
|
||||
if (aliasClause !== null) {
|
||||
// alias_clause: "as" name
|
||||
const aliasName = findNamedChild(aliasClause, 'name') ?? aliasClause.firstNamedChild;
|
||||
const alias = aliasName?.text.trim() ?? '';
|
||||
if (alias === '') return null;
|
||||
return {
|
||||
kind: 'alias',
|
||||
source,
|
||||
name: alias,
|
||||
alias,
|
||||
atNode: clause,
|
||||
};
|
||||
}
|
||||
|
||||
// Strategy 2: bare sibling `name` node after the qualified_name.
|
||||
// tree-sitter-php (≥ 0.22) emits `use Foo\Bar as Baz` as:
|
||||
// namespace_use_clause
|
||||
// qualified_name "Foo\Bar"
|
||||
// name "Baz" ← alias, no alias_clause wrapper
|
||||
// Detect by: clause has ≥2 named children AND the last named child is
|
||||
// a `name` node that differs from the qualName node.
|
||||
if (clause.namedChildCount >= 2) {
|
||||
const lastChild = clause.namedChild(clause.namedChildCount - 1);
|
||||
if (lastChild !== null && lastChild !== qualName && lastChild.type === 'name') {
|
||||
const alias = lastChild.text.trim();
|
||||
if (alias !== '') {
|
||||
return {
|
||||
kind: 'alias',
|
||||
source,
|
||||
name: alias,
|
||||
alias,
|
||||
atNode: clause,
|
||||
};
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return {
|
||||
kind: qualifier,
|
||||
source,
|
||||
name: lastSegment(source),
|
||||
atNode: clause,
|
||||
};
|
||||
}
|
||||
|
||||
// ── Grouped use decomposition ──────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Decompose `use Foo\Bar\{A, B as C, function f, const X}` into one
|
||||
* `CaptureMatch` per inner clause.
|
||||
*
|
||||
* The leading prefix (`Foo\Bar`) is prepended to each inner path.
|
||||
* Inner clauses can override the qualifier with their own `function` /
|
||||
* `const` keyword inside the group.
|
||||
*/
|
||||
function decomposeGrouped(
|
||||
stmtNode: SyntaxNode,
|
||||
groupNode: SyntaxNode,
|
||||
outerQualifier: PhpImportKind,
|
||||
): CaptureMatch[] {
|
||||
// The prefix is the qualified_name that precedes the `{...}` group.
|
||||
const prefixNode = findNamedChild(stmtNode, 'qualified_name') ?? findNamedChild(stmtNode, 'name');
|
||||
const prefix = prefixNode?.text.trim() ?? '';
|
||||
|
||||
const out: CaptureMatch[] = [];
|
||||
|
||||
for (let i = 0; i < groupNode.namedChildCount; i++) {
|
||||
const child = groupNode.namedChild(i);
|
||||
if (child === null) continue;
|
||||
|
||||
// Each child in a group may be:
|
||||
// namespace_use_clause — plain or aliased
|
||||
// namespace_use_type — `function` or `const` qualifier inside group
|
||||
// We detect an inline qualifier by checking the raw text of the clause.
|
||||
if (child.type !== 'namespace_use_clause') continue;
|
||||
|
||||
const innerQualifier = detectInnerQualifier(child) ?? outerQualifier;
|
||||
const spec = parseInnerClause(child, prefix, innerQualifier);
|
||||
if (spec !== null) {
|
||||
out.push(buildImportMatch(stmtNode, spec));
|
||||
}
|
||||
}
|
||||
|
||||
return out;
|
||||
}
|
||||
|
||||
/**
|
||||
* Detect an inline qualifier keyword inside a grouped clause.
|
||||
* e.g. `use Foo\{function bar, const BAZ}` — each clause may start with
|
||||
* `function` or `const`.
|
||||
*/
|
||||
function detectInnerQualifier(clause: SyntaxNode): PhpImportKind | null {
|
||||
const raw = clause.text.trim();
|
||||
if (/^function\s/i.test(raw)) return 'function';
|
||||
if (/^const\s/i.test(raw)) return 'const';
|
||||
return null;
|
||||
}
|
||||
|
||||
function parseInnerClause(
|
||||
clause: SyntaxNode,
|
||||
prefix: string,
|
||||
qualifier: PhpImportKind,
|
||||
): PhpImportSpec | null {
|
||||
const qualName = findNamedChild(clause, 'qualified_name') ?? findNamedChild(clause, 'name');
|
||||
if (qualName === null) return null;
|
||||
|
||||
// Strip inline `function` / `const` text prefix if present in the text.
|
||||
let innerPath = qualName.text.trim();
|
||||
innerPath = innerPath.replace(/^(?:function|const)\s+/i, '').trim();
|
||||
if (innerPath === '') return null;
|
||||
|
||||
const source = prefix !== '' ? `${prefix}\\${innerPath}` : innerPath;
|
||||
|
||||
// Strategy 1: explicit alias_clause wrapper (older grammar versions).
|
||||
const aliasClause = findNamedChild(clause, 'alias_clause');
|
||||
if (aliasClause !== null) {
|
||||
const aliasName = findNamedChild(aliasClause, 'name') ?? aliasClause.firstNamedChild;
|
||||
const alias = aliasName?.text.trim() ?? '';
|
||||
if (alias === '') return null;
|
||||
return {
|
||||
kind: 'alias',
|
||||
source,
|
||||
name: alias,
|
||||
alias,
|
||||
atNode: clause,
|
||||
};
|
||||
}
|
||||
|
||||
// Strategy 2: bare sibling `name` node after the qualified_name (tree-sitter-php ≥ 0.22).
|
||||
if (clause.namedChildCount >= 2) {
|
||||
const lastChild = clause.namedChild(clause.namedChildCount - 1);
|
||||
if (lastChild !== null && lastChild !== qualName && lastChild.type === 'name') {
|
||||
const alias = lastChild.text.trim();
|
||||
if (alias !== '') {
|
||||
return {
|
||||
kind: 'alias',
|
||||
source,
|
||||
name: alias,
|
||||
alias,
|
||||
atNode: clause,
|
||||
};
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return {
|
||||
kind: qualifier,
|
||||
source,
|
||||
name: lastSegment(innerPath),
|
||||
atNode: clause,
|
||||
};
|
||||
}
|
||||
|
||||
// ── CaptureMatch builder ───────────────────────────────────────────────────
|
||||
|
||||
function buildImportMatch(stmtNode: SyntaxNode, spec: PhpImportSpec): CaptureMatch {
|
||||
const m: Record<string, Capture> = {
|
||||
'@import.statement': nodeToCapture('@import.statement', stmtNode),
|
||||
'@import.kind': syntheticCapture('@import.kind', spec.atNode, spec.kind),
|
||||
'@import.source': syntheticCapture('@import.source', spec.atNode, spec.source),
|
||||
'@import.name': syntheticCapture('@import.name', spec.atNode, spec.name),
|
||||
};
|
||||
if (spec.alias !== undefined) {
|
||||
m['@import.alias'] = syntheticCapture('@import.alias', spec.atNode, spec.alias);
|
||||
}
|
||||
return m;
|
||||
}
|
||||
|
||||
// ── Helpers ────────────────────────────────────────────────────────────────
|
||||
|
||||
/** Last backslash-separated segment: `Foo\Bar\Baz` → `Baz`. */
|
||||
function lastSegment(path: string): string {
|
||||
const parts = path.split('\\').filter(Boolean);
|
||||
return parts[parts.length - 1] ?? path;
|
||||
}
|
||||
|
||||
/** Find the first named child with a given node type. */
|
||||
function findNamedChild(node: SyntaxNode, type: string): SyntaxNode | null {
|
||||
for (let i = 0; i < node.namedChildCount; i++) {
|
||||
const child = node.namedChild(i);
|
||||
if (child !== null && child.type === type) return child;
|
||||
}
|
||||
return null;
|
||||
}
|
||||
140
gitnexus/src/core/ingestion/languages/php/import-target.ts
Normal file
140
gitnexus/src/core/ingestion/languages/php/import-target.ts
Normal file
|
|
@ -0,0 +1,140 @@
|
|||
/**
|
||||
* Adapter from `(ParsedImport, WorkspaceIndex)` → concrete file path.
|
||||
*
|
||||
* Delegates to the existing `resolvePhpImportInternal` (PSR-4 via
|
||||
* composer.json + suffix matching fallback). The `WorkspaceIndex` is
|
||||
* opaque at this layer; consumers wire a `PhpResolveContext` shape
|
||||
* carrying `fromFile` + `allFilePaths`.
|
||||
*
|
||||
* `loadPhpComposerConfig` is the `ScopeResolver.loadResolutionConfig`
|
||||
* implementation — it loads `composer.json` once per workspace pass and
|
||||
* threads the parsed config into every subsequent `resolveImportTarget`
|
||||
* call via the opaque `resolutionConfig` parameter.
|
||||
*
|
||||
* Returning `null` lets the finalize algorithm mark the edge as
|
||||
* `linkStatus: 'unresolved'`.
|
||||
*/
|
||||
|
||||
import type { ParsedImport, WorkspaceIndex } from 'gitnexus-shared';
|
||||
import { resolvePhpImportInternal } from '../../import-resolvers/php.js';
|
||||
import type { ComposerConfig } from '../../language-config.js';
|
||||
import { readFileSync } from 'node:fs';
|
||||
import { join } from 'node:path';
|
||||
|
||||
export interface PhpResolveContext {
|
||||
readonly fromFile: string;
|
||||
readonly allFilePaths: ReadonlySet<string>;
|
||||
}
|
||||
|
||||
// ─── loadResolutionConfig ──────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Load and parse `composer.json` from the repo root. Returns a
|
||||
* `ComposerConfig` object (PSR-4 namespace → directory mappings) or
|
||||
* `null` when no `composer.json` is present or it cannot be parsed.
|
||||
*
|
||||
* The result is threaded into each `resolvePhpImportInternal` call as
|
||||
* the `composerConfig` argument.
|
||||
*/
|
||||
export function loadPhpComposerConfig(repoPath: string): ComposerConfig | null {
|
||||
try {
|
||||
const composerPath = join(repoPath, 'composer.json');
|
||||
const raw = readFileSync(composerPath, 'utf8');
|
||||
const parsed = JSON.parse(raw) as unknown;
|
||||
if (typeof parsed !== 'object' || parsed === null) return null;
|
||||
|
||||
const composer = parsed as Record<string, unknown>;
|
||||
const autoload = composer['autoload'] as Record<string, unknown> | undefined;
|
||||
if (autoload === undefined) return null;
|
||||
|
||||
const psr4Raw = (autoload['psr-4'] ?? {}) as Record<string, string | string[]>;
|
||||
const psr4 = new Map<string, string>();
|
||||
|
||||
for (const [ns, dirs] of Object.entries(psr4Raw)) {
|
||||
// namespace prefix ends with `\` — keep as-is; resolver strips it
|
||||
const normalizedNs = ns.replace(/\\$/, '');
|
||||
const dir = Array.isArray(dirs) ? dirs[0] : dirs;
|
||||
if (typeof dir === 'string') {
|
||||
// Normalize directory path (strip trailing slash)
|
||||
const normalizedDir = dir.replace(/\/+$/, '');
|
||||
psr4.set(normalizedNs, normalizedDir);
|
||||
}
|
||||
}
|
||||
|
||||
return { psr4 };
|
||||
} catch {
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
// ─── resolvePhpImportTarget ────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* LanguageProvider-shaped adapter: `(ParsedImport, WorkspaceIndex) → string | null`.
|
||||
*
|
||||
* The `WorkspaceIndex` is `unknown` in the shared contract. The scope-resolution
|
||||
* orchestrator hands us a `PhpResolveContext`-shaped object; narrow structurally
|
||||
* rather than via a cast chain so unexpected shapes return `null` cleanly.
|
||||
*/
|
||||
export function resolvePhpImportTarget(
|
||||
parsedImport: ParsedImport,
|
||||
workspaceIndex: WorkspaceIndex,
|
||||
): string | null {
|
||||
const ctx = workspaceIndex as PhpResolveContext | undefined;
|
||||
if (
|
||||
ctx === undefined ||
|
||||
typeof (ctx as { fromFile?: unknown }).fromFile !== 'string' ||
|
||||
!((ctx as { allFilePaths?: unknown }).allFilePaths instanceof Set)
|
||||
) {
|
||||
return null;
|
||||
}
|
||||
if (parsedImport.kind === 'dynamic-unresolved') return null;
|
||||
if (parsedImport.targetRaw === null || parsedImport.targetRaw === '') return null;
|
||||
|
||||
const allFiles = ctx.allFilePaths as Set<string>;
|
||||
const normalizedFileList = [...allFiles].map((f) => f.replace(/\\/g, '/'));
|
||||
const allFileList = [...allFiles];
|
||||
|
||||
return resolvePhpImportInternal(
|
||||
parsedImport.targetRaw,
|
||||
null, // composerConfig not available through LanguageProvider path
|
||||
allFiles,
|
||||
normalizedFileList,
|
||||
allFileList,
|
||||
undefined,
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* ScopeResolver-shaped adapter: `(targetRaw, fromFile, allFilePaths, resolutionConfig?) → string | null`.
|
||||
*
|
||||
* Used inside `scope-resolver.ts`. Accepts the optional `resolutionConfig`
|
||||
* (a `ComposerConfig | null` loaded once per workspace by
|
||||
* `loadPhpComposerConfig`) and threads it into `resolvePhpImportInternal`.
|
||||
*/
|
||||
export function resolvePhpImportTargetInternal(
|
||||
targetRaw: string,
|
||||
_fromFile: string,
|
||||
allFilePaths: ReadonlySet<string>,
|
||||
resolutionConfig?: unknown,
|
||||
): string | null {
|
||||
if (targetRaw === '') return null;
|
||||
|
||||
const composerConfig =
|
||||
resolutionConfig !== undefined && resolutionConfig !== null
|
||||
? (resolutionConfig as ComposerConfig)
|
||||
: null;
|
||||
|
||||
const allFiles = allFilePaths as Set<string>;
|
||||
const normalizedFileList = [...allFiles].map((f) => f.replace(/\\/g, '/'));
|
||||
const allFileList = [...allFiles];
|
||||
|
||||
return resolvePhpImportInternal(
|
||||
targetRaw,
|
||||
composerConfig,
|
||||
allFiles,
|
||||
normalizedFileList,
|
||||
allFileList,
|
||||
undefined,
|
||||
);
|
||||
}
|
||||
73
gitnexus/src/core/ingestion/languages/php/index.ts
Normal file
73
gitnexus/src/core/ingestion/languages/php/index.ts
Normal file
|
|
@ -0,0 +1,73 @@
|
|||
/**
|
||||
* PHP scope-resolution hooks (RFC #909 Ring 3 LANG-php, #938).
|
||||
*
|
||||
* Public API barrel. Consumers should import from this file rather than
|
||||
* the individual modules.
|
||||
*
|
||||
* Module layout (each file is a single concern):
|
||||
*
|
||||
* - `query.ts` — tree-sitter query + lazy parser/query singletons
|
||||
* - `captures.ts` — `emitPhpScopeCaptures` orchestrator
|
||||
* - `import-decomposer.ts` — each `namespace_use_declaration` → ParsedImport captures
|
||||
* - `interpret.ts` — capture-match → `ParsedImport` / `ParsedTypeBinding`
|
||||
* - `simple-hooks.ts` — small/no-op hooks made explicit
|
||||
* - `receiver-binding.ts` — synthesize `$this` / `parent` type-bindings on
|
||||
* instance-method entry
|
||||
* - `merge-bindings.ts` — PHP `use` precedence (local > import > wildcard)
|
||||
* - `arity.ts` — PHP arity compatibility (variadic, defaults)
|
||||
* - `arity-metadata.ts` — synthesize arity metadata from declarations
|
||||
* - `import-target.ts` — `(ParsedImport, WorkspaceIndex) → file path` adapter
|
||||
* wrapping `resolvePhpImportInternal` (PSR-4 + composer.json)
|
||||
* - `scope-resolver.ts` — `ScopeResolver` registered in `SCOPE_RESOLVERS`
|
||||
* - `cache-stats.ts` — PROF_SCOPE_RESOLUTION cache hit/miss counters
|
||||
*
|
||||
* ## Known limitations
|
||||
*
|
||||
* The PHP registry-primary path intentionally does NOT resolve the following.
|
||||
* Each is a conscious trade-off at migration time.
|
||||
*
|
||||
* 1. **Trait `$this` → using-class binding** — for methods defined in a
|
||||
* trait, `$this` is synthesized as a binding to the trait itself.
|
||||
* Resolving `$this` to the actual using-class type requires cross-file
|
||||
* analysis of all `use TraitName;` declarations in class bodies.
|
||||
* Deferred to a follow-up; trait method resolution falls back to the
|
||||
* trait scope.
|
||||
*
|
||||
* 2. **Anonymous classes** — `new class extends Foo { }` have no stable
|
||||
* class name and are skipped by receiver-binding synthesis. The class
|
||||
* body is still scoped; member lookups inside it will fall back to
|
||||
* free-call resolution.
|
||||
*
|
||||
* 3. **Dynamic property/method access** — `$obj->{$name}()` and
|
||||
* `$$varName` are not followed. The dynamic receiver is ignored and
|
||||
* the call falls through to the shared free-call resolver.
|
||||
*
|
||||
* 4. **Magic methods** — `__get`, `__set`, `__call`, `__callStatic` are
|
||||
* not modeled as virtual dispatch; they appear as regular method
|
||||
* declarations in the graph but calls that would route through them
|
||||
* at runtime are not distinguished.
|
||||
*
|
||||
* 5. **Laravel facade magic** — `App::make(...)`, `Cache::get(...)` etc.
|
||||
* resolve statically to the Facade class rather than the underlying
|
||||
* bound implementation. Deferred to a Laravel-specific plugin.
|
||||
*
|
||||
* 6. **Intersection types in parameters** — `T&U $param` takes the first
|
||||
* named part (`T`). This matches the legacy type-extractor's behavior.
|
||||
*
|
||||
* Shadow-harness corpus parity is the authoritative signal for which of
|
||||
* these matter in practice. The CI parity gate blocks any PR that regresses
|
||||
* either the legacy or registry-primary run of
|
||||
* `test/integration/resolvers/php.test.ts`.
|
||||
*/
|
||||
|
||||
export { emitPhpScopeCaptures } from './captures.js';
|
||||
export { getPhpCaptureCacheStats, resetPhpCaptureCacheStats } from './cache-stats.js';
|
||||
export { interpretPhpImport, interpretPhpTypeBinding } from './interpret.js';
|
||||
export { phpMergeBindings } from './merge-bindings.js';
|
||||
export { phpArityCompatibility } from './arity.js';
|
||||
export { resolvePhpImportTarget, type PhpResolveContext } from './import-target.js';
|
||||
export { phpBindingScopeFor, phpImportOwningScope, phpReceiverBinding } from './simple-hooks.js';
|
||||
// NOTE: phpScopeResolver is intentionally NOT re-exported from this barrel.
|
||||
// Importing it here would create a circular dependency:
|
||||
// php.ts → php/index.js → php/scope-resolver.js → ../php.js
|
||||
// Registry and other consumers must import directly from './php/scope-resolver.js'.
|
||||
250
gitnexus/src/core/ingestion/languages/php/interpret.ts
Normal file
250
gitnexus/src/core/ingestion/languages/php/interpret.ts
Normal file
|
|
@ -0,0 +1,250 @@
|
|||
/**
|
||||
* Capture-match → semantic-shape interpreters for PHP.
|
||||
*
|
||||
* - `interpretPhpImport` → `ParsedImport`
|
||||
* - `interpretPhpTypeBinding` → `ParsedTypeBinding`
|
||||
*
|
||||
* Import matches arrive pre-decomposed by `emitPhpScopeCaptures` (one
|
||||
* CaptureMatch per logical import, with synthesized `@import.kind /
|
||||
* source / name / alias` markers). Type-binding matches arrive from
|
||||
* the raw query captures — each `@type-binding.*` anchor carries
|
||||
* `@type-binding.name` + `@type-binding.type`.
|
||||
*/
|
||||
|
||||
import type { CaptureMatch, ParsedImport, ParsedTypeBinding, TypeRef } from 'gitnexus-shared';
|
||||
|
||||
// ─── interpretImport ──────────────────────────────────────────────────────
|
||||
|
||||
export function interpretPhpImport(captures: CaptureMatch): ParsedImport | null {
|
||||
const kindCap = captures['@import.kind'];
|
||||
const sourceCap = captures['@import.source'];
|
||||
const nameCap = captures['@import.name'];
|
||||
const aliasCap = captures['@import.alias'];
|
||||
|
||||
const kind = kindCap?.text;
|
||||
if (kind === undefined || sourceCap === undefined) return null;
|
||||
|
||||
const source = sourceCap.text.trim();
|
||||
if (source === '') return null;
|
||||
|
||||
switch (kind) {
|
||||
case 'namespace': {
|
||||
// `use Foo\Bar;` — PHP `use` is a NAMED import (binds the class
|
||||
// `Bar`, not the namespace `Foo`). This differs from C# `using`,
|
||||
// which is a true namespace import. Producing 'named' here makes
|
||||
// `new Bar()` resolve to the imported class def.
|
||||
const localName = nameCap?.text.trim() ?? lastSegment(source);
|
||||
return {
|
||||
kind: 'named',
|
||||
localName,
|
||||
importedName: localName,
|
||||
targetRaw: source,
|
||||
};
|
||||
}
|
||||
case 'alias': {
|
||||
// `use Foo\Bar as Baz;`
|
||||
if (aliasCap === undefined) return null;
|
||||
const alias = aliasCap.text.trim();
|
||||
if (alias === '') return null;
|
||||
const importedName = lastSegment(source);
|
||||
return {
|
||||
kind: 'alias',
|
||||
localName: alias,
|
||||
importedName,
|
||||
alias,
|
||||
targetRaw: source,
|
||||
};
|
||||
}
|
||||
case 'function': {
|
||||
// `use function Foo\bar;` — treat as named import; importedName is
|
||||
// the function name (last segment). targetRaw is the full path.
|
||||
const localName = nameCap?.text.trim() ?? lastSegment(source);
|
||||
return {
|
||||
kind: 'named',
|
||||
localName,
|
||||
importedName: localName,
|
||||
targetRaw: source,
|
||||
};
|
||||
}
|
||||
case 'const': {
|
||||
// `use const Foo\BAR;` — same shape as function.
|
||||
const localName = nameCap?.text.trim() ?? lastSegment(source);
|
||||
return {
|
||||
kind: 'named',
|
||||
localName,
|
||||
importedName: localName,
|
||||
targetRaw: source,
|
||||
};
|
||||
}
|
||||
default:
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
// ─── interpretTypeBinding ─────────────────────────────────────────────────
|
||||
|
||||
export function interpretPhpTypeBinding(captures: CaptureMatch): ParsedTypeBinding | null {
|
||||
const nameCap = captures['@type-binding.name'];
|
||||
const typeCap = captures['@type-binding.type'];
|
||||
if (nameCap === undefined || typeCap === undefined) return null;
|
||||
|
||||
// Determine source from anchor captures. Order: most-specific first.
|
||||
let source: TypeRef['source'] = 'parameter-annotation';
|
||||
if (captures['@type-binding.self'] !== undefined) source = 'self';
|
||||
else if (captures['@type-binding.constructor'] !== undefined) source = 'constructor-inferred';
|
||||
else if (captures['@type-binding.annotation'] !== undefined) source = 'annotation';
|
||||
else if (captures['@type-binding.alias'] !== undefined) source = 'assignment-inferred';
|
||||
else if (captures['@type-binding.return'] !== undefined) source = 'return-annotation';
|
||||
|
||||
let rawType: string | null;
|
||||
|
||||
if (source === 'assignment-inferred') {
|
||||
// `@type-binding.alias` captures cover several assignment RHS shapes:
|
||||
// - `$alias = $u` → rawType = '$u' (variable alias)
|
||||
// - `$u = getUser()` → rawType = 'getUser' (callable alias)
|
||||
// - `$u = new User()` → rawType = 'User' (constructor — via @type-binding.constructor; handled below)
|
||||
// - `$role = UserRole::Viewer` → rawType = 'UserRole' (enum/class constant)
|
||||
//
|
||||
// For variable aliases (`$u`), `normalizePhpType` returns null because
|
||||
// `$` is not a word character. We must preserve the raw `$`-prefixed name
|
||||
// so `followChainedRef` can walk the chain `$alias → $u → User`.
|
||||
// For callable/class names, `normalizePhpType` strips qualifiers correctly.
|
||||
const rawText = typeCap.text.trim();
|
||||
if (rawText.startsWith('$')) {
|
||||
// Variable alias: keep as-is for chain-following.
|
||||
rawType = rawText;
|
||||
} else {
|
||||
rawType = normalizePhpType(rawText);
|
||||
}
|
||||
} else {
|
||||
// All other sources: strip PHP type decoration to get the simple class name:
|
||||
// ?User → User (nullable prefix)
|
||||
// User|null → User (union with null/false/void)
|
||||
// User&Loggable → User (intersection — take first meaningful)
|
||||
// Collection<User> → User (PHPDoc generic wrapper)
|
||||
// User[] → User (array suffix)
|
||||
// \App\Models\User → User (backslash qualifier)
|
||||
rawType = normalizePhpType(typeCap.text.trim());
|
||||
}
|
||||
|
||||
if (rawType === null) return null;
|
||||
|
||||
// PHP variable names include the `$` sigil (e.g. `$user`). Most
|
||||
// bindings keep it because they are looked up via the variable
|
||||
// (`$user->method()` finds binding `$user`). Property field bindings
|
||||
// are different: `$user->address` looks up `address` (no sigil) on
|
||||
// the User class. Property declarations carry source `'annotation'`,
|
||||
// so we strip the leading `$` for that source only.
|
||||
let boundName = nameCap.text.trim();
|
||||
if (source === 'annotation' && boundName.startsWith('$')) {
|
||||
boundName = boundName.slice(1);
|
||||
}
|
||||
|
||||
return { boundName, rawTypeName: rawType, source };
|
||||
}
|
||||
|
||||
// ─── Type normalization ───────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Normalize a PHP type string to a simple class identifier, or `null`
|
||||
* when the type is uninformative (primitive, void, mixed, self, etc.).
|
||||
*
|
||||
* Rules applied in order:
|
||||
* 1. Strip nullable prefix `?`
|
||||
* 2. Split on `|` (union) — keep only if exactly one non-null part
|
||||
* 3. Take first part of `&` intersection
|
||||
* 4. Strip array suffix `[]`
|
||||
* 5. Strip generic wrapper `Collection<User>` → `User`
|
||||
* 6. Canonicalize leading backslash off: `\App\Models\User` → `App\Models\User`
|
||||
* 7. Reject PHP primitive / pseudo types
|
||||
*
|
||||
* The qualified form is preserved on `TypeRef.rawName` so downstream PHP
|
||||
* receiver resolution can distinguish `\App\Other\User` from a same-simple-name
|
||||
* `User` reachable via `use`. Without this, fully-qualified type hints collapse
|
||||
* to ambiguous simple names and resolve against the caller's scope chain
|
||||
* instead of the explicit target the source named (Codex PR #1497 review,
|
||||
* finding 1).
|
||||
*/
|
||||
export function normalizePhpType(raw: string): string | null {
|
||||
// 1. Strip nullable prefix
|
||||
let type = raw.startsWith('?') ? raw.slice(1).trim() : raw;
|
||||
|
||||
// 2. Union type — keep only if one non-null/false/void part remains
|
||||
if (type.includes('|')) {
|
||||
const parts = type
|
||||
.split('|')
|
||||
.map((p) => p.trim())
|
||||
.filter((p) => p !== 'null' && p !== 'false' && p !== 'void' && p !== 'mixed' && p !== '');
|
||||
if (parts.length !== 1) return null;
|
||||
type = parts[0];
|
||||
}
|
||||
|
||||
// 3. Intersection type — take the first part
|
||||
if (type.includes('&')) {
|
||||
const first = type.split('&')[0].trim();
|
||||
if (first === '') return null;
|
||||
type = first;
|
||||
}
|
||||
|
||||
// 4. Strip array suffix
|
||||
if (type.endsWith('[]')) type = type.slice(0, -2).trim();
|
||||
|
||||
// 5. Strip single-arg generic wrapper: Collection<User> → User
|
||||
// Qualified inner types (Collection<\App\Models\User>) survive — the
|
||||
// capture group preserves whatever the writer named.
|
||||
const genericMatch = type.match(/^\w[\w\\]*\s*<([^,<>]+)>$/);
|
||||
if (genericMatch) {
|
||||
type = genericMatch[1].trim();
|
||||
}
|
||||
|
||||
// 6. Canonicalize leading backslash off — keep the qualified path intact.
|
||||
// `\App\Models\User` → `App\Models\User`. `App\Models\User` → unchanged.
|
||||
// Unqualified `User` stays as `User`. The qualified form is the lookup
|
||||
// key into the workspace QualifiedNameIndex (PHP defs are indexed by
|
||||
// namespace-joined qualifiedName); the leading-backslash distinction in
|
||||
// source is only an "absolute path" anchor, not part of the canonical key.
|
||||
if (type.startsWith('\\')) type = type.replace(/^\\+/, '');
|
||||
|
||||
// 7. Reject primitives / pseudo-types
|
||||
if (isPrimitiveOrPseudo(type)) return null;
|
||||
|
||||
// Must be a (possibly qualified) PHP identifier — segments of word chars
|
||||
// separated by single backslashes. Empty segments (consecutive backslashes,
|
||||
// trailing backslash) are rejected.
|
||||
if (!/^\w+(?:\\\w+)*$/.test(type)) return null;
|
||||
|
||||
return type;
|
||||
}
|
||||
|
||||
const PHP_PRIMITIVE_TYPES = new Set([
|
||||
'int',
|
||||
'integer',
|
||||
'float',
|
||||
'double',
|
||||
'string',
|
||||
'bool',
|
||||
'boolean',
|
||||
'array',
|
||||
'object',
|
||||
'callable',
|
||||
'iterable',
|
||||
'null',
|
||||
'void',
|
||||
'never',
|
||||
'mixed',
|
||||
'false',
|
||||
'true',
|
||||
'self',
|
||||
'static',
|
||||
'parent',
|
||||
]);
|
||||
|
||||
function isPrimitiveOrPseudo(type: string): boolean {
|
||||
return PHP_PRIMITIVE_TYPES.has(type.toLowerCase());
|
||||
}
|
||||
|
||||
/** Last backslash-separated segment: `Foo\Bar\Baz` → `Baz`. */
|
||||
function lastSegment(path: string): string {
|
||||
const parts = path.split('\\').filter(Boolean);
|
||||
return parts[parts.length - 1] ?? path;
|
||||
}
|
||||
51
gitnexus/src/core/ingestion/languages/php/merge-bindings.ts
Normal file
51
gitnexus/src/core/ingestion/languages/php/merge-bindings.ts
Normal file
|
|
@ -0,0 +1,51 @@
|
|||
/**
|
||||
* PHP shadowing precedence for the `mergeBindings` hook.
|
||||
*
|
||||
* Tier ranking (lower wins in shadowing):
|
||||
*
|
||||
* - 0: `local` — a class member, method, local variable, or parameter
|
||||
* declared in this scope.
|
||||
* - 1: `import` / `namespace` / `reexport` — `use Foo\Bar;`,
|
||||
* `use Foo\Bar as Baz;`, `use function`, `use const`.
|
||||
* All use-statement flavors that introduce a name sit at this tier.
|
||||
* - 2: `wildcard` — grouped uses / wildcard imports (deferred; mapped
|
||||
* here for completeness).
|
||||
*
|
||||
* Within a surviving tier we de-dup by `DefId`, last-write-wins so a
|
||||
* `use` re-declared further down the file cleanly replaces the earlier
|
||||
* binding.
|
||||
*/
|
||||
|
||||
import type { BindingRef } from 'gitnexus-shared';
|
||||
|
||||
const TIER_LOCAL = 0;
|
||||
const TIER_IMPORT = 1;
|
||||
const TIER_WILDCARD = 2;
|
||||
const TIER_UNKNOWN = 3;
|
||||
|
||||
function tierOf(b: BindingRef): number {
|
||||
switch (b.origin) {
|
||||
case 'local':
|
||||
return TIER_LOCAL;
|
||||
case 'reexport':
|
||||
case 'import':
|
||||
case 'namespace':
|
||||
return TIER_IMPORT;
|
||||
case 'wildcard':
|
||||
return TIER_WILDCARD;
|
||||
default:
|
||||
return TIER_UNKNOWN;
|
||||
}
|
||||
}
|
||||
|
||||
export function phpMergeBindings(bindings: readonly BindingRef[]): readonly BindingRef[] {
|
||||
if (bindings.length === 0) return bindings;
|
||||
|
||||
let bestTier = Number.POSITIVE_INFINITY;
|
||||
for (const b of bindings) bestTier = Math.min(bestTier, tierOf(b));
|
||||
const survivors = bindings.filter((b) => tierOf(b) === bestTier);
|
||||
|
||||
const seen = new Map<string, BindingRef>();
|
||||
for (const b of survivors) seen.set(b.def.nodeId, b);
|
||||
return [...seen.values()];
|
||||
}
|
||||
335
gitnexus/src/core/ingestion/languages/php/namespace-siblings.ts
Normal file
335
gitnexus/src/core/ingestion/languages/php/namespace-siblings.ts
Normal file
|
|
@ -0,0 +1,335 @@
|
|||
/**
|
||||
* PHP same-namespace cross-file visibility.
|
||||
*
|
||||
* In PHP, every class declared in `namespace Foo\Bar` is visible to all
|
||||
* other files in the same namespace WITHOUT an explicit `use` statement.
|
||||
* Without this pass, `Service.php` (namespace `App\Services`) can't see
|
||||
* `User` declared in `Models.php` (namespace `App\Models`) unless
|
||||
* `UserService.php` has an explicit `use App\Models\User` statement.
|
||||
*
|
||||
* More importantly, A.php (namespace `App\Models`) can return `Greeting`
|
||||
* (same namespace `App\Models`) without importing it, and the compound-
|
||||
* receiver resolver needs to find `Greeting` as a class binding in the
|
||||
* scope chain.
|
||||
*
|
||||
* Implementation mirrors C#'s `namespace-siblings.ts`:
|
||||
* 1. Extract the declared namespace from each PHP file's source.
|
||||
* 2. Group class-like defs by namespace.
|
||||
* 3. Inject sibling class defs into each file's Module scope's
|
||||
* `bindingAugmentations` with `origin: 'namespace'`.
|
||||
* 4. Also mirror return-type bindings from same-namespace siblings
|
||||
* so cross-file chain-follow finds return types without explicit imports.
|
||||
*
|
||||
* Uses the PHP tree-sitter parser (via the lazy singleton in `query.ts`)
|
||||
* to extract namespace declarations — same AST that `extractParsedFile`
|
||||
* already parsed, reused via `treeCache` to avoid double-parsing.
|
||||
*/
|
||||
|
||||
import type { BindingRef, ParsedFile, Scope, ScopeId, SymbolDefinition } from 'gitnexus-shared';
|
||||
import type { ScopeResolutionIndexes } from '../../model/scope-resolution-indexes.js';
|
||||
import { getPhpParser } from './query.js';
|
||||
import { getTreeSitterBufferSize } from '../../constants.js';
|
||||
import { parseSourceSafe } from '../../../tree-sitter/safe-parse.js';
|
||||
|
||||
// ─── PHP file structure extraction ──────────────────────────────────────────
|
||||
|
||||
interface PhpFileStructure {
|
||||
/** The declared namespace (backslash-separated), or '' for global namespace. */
|
||||
readonly namespace: string;
|
||||
}
|
||||
|
||||
type PhpTree = ReturnType<ReturnType<typeof getPhpParser>['parse']>;
|
||||
|
||||
/**
|
||||
* Extract the declared namespace from a PHP file's source.
|
||||
* Uses the cached AST tree when available to avoid re-parsing.
|
||||
*/
|
||||
function extractPhpFileStructure(content: string, cachedTree: unknown): PhpFileStructure {
|
||||
const tree =
|
||||
(cachedTree as PhpTree | undefined) ??
|
||||
parseSourceSafe(getPhpParser(), content, undefined, {
|
||||
bufferSize: getTreeSitterBufferSize(content),
|
||||
});
|
||||
|
||||
// Walk top-level nodes looking for namespace_definition.
|
||||
// PHP files have at most one namespace declaration (PSR-4 convention).
|
||||
// `namespace_definition` has a `name:` field of type `namespace_name`.
|
||||
const root = tree.rootNode;
|
||||
for (let i = 0; i < root.namedChildCount; i++) {
|
||||
const child = root.namedChild(i);
|
||||
if (child === null) continue;
|
||||
if (child.type === 'namespace_definition') {
|
||||
const nameNode = child.childForFieldName('name');
|
||||
if (nameNode !== null) {
|
||||
return { namespace: nameNode.text };
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return { namespace: '' };
|
||||
}
|
||||
|
||||
// ─── Augmentation bucket helper ─────────────────────────────────────────────
|
||||
|
||||
function getAugmentationBucket(
|
||||
augmentations: Map<ScopeId, Map<string, BindingRef[]>>,
|
||||
scopeId: ScopeId,
|
||||
name: string,
|
||||
): BindingRef[] {
|
||||
let scopeBindings = augmentations.get(scopeId);
|
||||
if (scopeBindings === undefined) {
|
||||
scopeBindings = new Map<string, BindingRef[]>();
|
||||
augmentations.set(scopeId, scopeBindings);
|
||||
}
|
||||
let bucket = scopeBindings.get(name);
|
||||
if (bucket === undefined) {
|
||||
bucket = [];
|
||||
scopeBindings.set(name, bucket);
|
||||
}
|
||||
return bucket;
|
||||
}
|
||||
|
||||
function isClassLikeDef(def: SymbolDefinition): boolean {
|
||||
return (
|
||||
def.type === 'Class' ||
|
||||
def.type === 'Interface' ||
|
||||
def.type === 'Struct' ||
|
||||
def.type === 'Enum' ||
|
||||
def.type === 'Trait'
|
||||
);
|
||||
}
|
||||
|
||||
// ─── Public entry point ──────────────────────────────────────────────────────
|
||||
|
||||
export interface PhpSiblingInputs {
|
||||
readonly fileContents: ReadonlyMap<string, string>;
|
||||
readonly treeCache?: { get(filePath: string): unknown };
|
||||
}
|
||||
|
||||
/**
|
||||
* Side-channel cache populated by `populatePhpNamespaceSiblings` so that
|
||||
* later visibility-check hooks (e.g., `isCallableVisibleFromCaller`) can
|
||||
* look up a file's PHP namespace without re-parsing. Cleared at the start
|
||||
* of every populate run so stale entries don't leak across resolutions.
|
||||
*/
|
||||
const namespaceByFilePath = new Map<string, string>();
|
||||
|
||||
/**
|
||||
* Read the cached PHP namespace for a given filePath. Returns `''` (global)
|
||||
* when the file has no namespace_definition or hasn't been processed yet.
|
||||
* Callers should only consult this AFTER either `populatePhpClassQualifiedNames`
|
||||
* or `populatePhpNamespaceSiblings` has run for the current resolution.
|
||||
*/
|
||||
export function getPhpNamespaceForFile(filePath: string): string {
|
||||
return namespaceByFilePath.get(filePath) ?? '';
|
||||
}
|
||||
|
||||
/**
|
||||
* Inject same-namespace class defs and return-type bindings into each
|
||||
* PHP file's Module scope's `bindingAugmentations`. This makes classes
|
||||
* in the same PHP namespace visible to each other without explicit `use`
|
||||
* statements, mirroring PHP's actual runtime behavior.
|
||||
*
|
||||
* Uses `origin: 'namespace'` so `phpMergeBindings` tiers it below
|
||||
* explicit `use` imports (`origin: 'import'`) and local declarations.
|
||||
*/
|
||||
export function populatePhpNamespaceSiblings(
|
||||
parsedFiles: readonly ParsedFile[],
|
||||
indexes: ScopeResolutionIndexes,
|
||||
inputs: PhpSiblingInputs,
|
||||
): void {
|
||||
// Step 1: extract namespace structure for each file. Also seed the
|
||||
// side-channel cache used by visibility-check hooks downstream.
|
||||
namespaceByFilePath.clear();
|
||||
const structureByFile = new Map<string, PhpFileStructure>();
|
||||
for (const parsed of parsedFiles) {
|
||||
const content = inputs.fileContents.get(parsed.filePath);
|
||||
if (content === undefined) continue;
|
||||
const cachedTree = inputs.treeCache?.get(parsed.filePath);
|
||||
const struct = extractPhpFileStructure(content, cachedTree);
|
||||
structureByFile.set(parsed.filePath, struct);
|
||||
namespaceByFilePath.set(parsed.filePath, struct.namespace);
|
||||
}
|
||||
|
||||
// Step 2: group class-like defs and module scopes by namespace.
|
||||
interface NamespaceBucket {
|
||||
readonly scopes: { filePath: string; scopeId: ScopeId; scope: Scope }[];
|
||||
readonly classDefs: SymbolDefinition[];
|
||||
}
|
||||
const buckets = new Map<string, NamespaceBucket>();
|
||||
const getBucket = (ns: string): NamespaceBucket => {
|
||||
let b = buckets.get(ns);
|
||||
if (b === undefined) {
|
||||
b = { scopes: [], classDefs: [] };
|
||||
buckets.set(ns, b);
|
||||
}
|
||||
return b;
|
||||
};
|
||||
|
||||
for (const parsed of parsedFiles) {
|
||||
const struct = structureByFile.get(parsed.filePath);
|
||||
if (struct === undefined) continue;
|
||||
const ns = struct.namespace;
|
||||
const bucket = getBucket(ns);
|
||||
|
||||
// Register the file's module scope in the bucket.
|
||||
const moduleScope = parsed.scopes.find((s) => s.kind === 'Module');
|
||||
if (moduleScope !== undefined) {
|
||||
bucket.scopes.push({
|
||||
filePath: parsed.filePath,
|
||||
scopeId: moduleScope.id,
|
||||
scope: moduleScope,
|
||||
});
|
||||
}
|
||||
|
||||
// Collect class-like defs declared at the top-level of this file
|
||||
// (defs in Class or Module scopes, excluding nested inner classes).
|
||||
for (const scope of parsed.scopes) {
|
||||
if (scope.kind !== 'Class') continue;
|
||||
// Only top-level class scopes (parent is Module or Namespace scope).
|
||||
if (scope.parent === null) continue;
|
||||
const parentScope = parsed.scopes.find((s) => s.id === scope.parent);
|
||||
if (
|
||||
parentScope === undefined ||
|
||||
(parentScope.kind !== 'Module' && parentScope.kind !== 'Namespace')
|
||||
) {
|
||||
continue;
|
||||
}
|
||||
for (const def of scope.ownedDefs) {
|
||||
if (isClassLikeDef(def)) {
|
||||
bucket.classDefs.push(def);
|
||||
break; // one class-like per scope
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
const augmentations = indexes.bindingAugmentations as Map<ScopeId, Map<string, BindingRef[]>>;
|
||||
|
||||
// Step 3: For each namespace bucket, inject sibling class bindings
|
||||
// into every file's Module scope (that is NOT the declaring file).
|
||||
for (const [, bucket] of buckets) {
|
||||
// Build name → def map (simple name of qualifiedName).
|
||||
const defsByName = new Map<string, SymbolDefinition[]>();
|
||||
for (const def of bucket.classDefs) {
|
||||
const q = def.qualifiedName ?? '';
|
||||
const simpleName = q.includes('.')
|
||||
? q.slice(q.lastIndexOf('.') + 1)
|
||||
: q.includes('\\')
|
||||
? q.slice(q.lastIndexOf('\\') + 1)
|
||||
: q;
|
||||
if (simpleName === '') continue;
|
||||
const arr = defsByName.get(simpleName) ?? [];
|
||||
arr.push(def);
|
||||
defsByName.set(simpleName, arr);
|
||||
}
|
||||
|
||||
for (const { filePath, scopeId, scope } of bucket.scopes) {
|
||||
for (const [name, defs] of defsByName) {
|
||||
// Skip if already locally declared (origin: 'local' wins).
|
||||
const local = scope.bindings.get(name);
|
||||
if (local !== undefined && local.some((b) => b.origin === 'local')) continue;
|
||||
|
||||
for (const def of defs) {
|
||||
if (def.filePath === filePath) continue; // don't self-inject
|
||||
const arr = getAugmentationBucket(augmentations, scopeId, name);
|
||||
if (arr.some((b) => b.def.nodeId === def.nodeId)) continue;
|
||||
arr.push({ def, origin: 'namespace' });
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Step 3b: Inject fully-qualified-name bindings into every PHP file's
|
||||
// Module scope. PHP `\App\Models\User` (leading-backslash FQN) and
|
||||
// `App\Models\User` (already-qualified relative) on a parameter or
|
||||
// typed receiver must resolve to the exact namespace-qualified class
|
||||
// regardless of which simple-name `User` the caller's `use` imports
|
||||
// shadowed. The shared `findClassBindingInScope` scope-chain walk
|
||||
// consumes these augmentations via `lookupBindingsAt`, so adding the
|
||||
// qualified key on every file's module scope routes FQN-receivers to
|
||||
// the right def. Codex PR #1497 review, finding 1.
|
||||
//
|
||||
// Cost: O(PHP files × class-like defs in the workspace) augmentation
|
||||
// entries. Bounded and acceptable in practice — typical PHP projects
|
||||
// have hundreds of files and classes, not tens of thousands.
|
||||
for (const parsed of parsedFiles) {
|
||||
const moduleScope = parsed.scopes.find((s) => s.kind === 'Module');
|
||||
if (moduleScope === undefined) continue;
|
||||
const moduleScopeId = moduleScope.id;
|
||||
|
||||
for (const [ns, bucket] of buckets) {
|
||||
if (ns === '') continue; // global-namespace classes have no qualified form to register
|
||||
for (const def of bucket.classDefs) {
|
||||
const q = def.qualifiedName ?? '';
|
||||
const simpleName = q.includes('\\') ? q.slice(q.lastIndexOf('\\') + 1) : q;
|
||||
if (simpleName === '') continue;
|
||||
const fqn = `${ns}\\${simpleName}`;
|
||||
const arr = getAugmentationBucket(augmentations, moduleScopeId, fqn);
|
||||
if (arr.some((b) => b.def.nodeId === def.nodeId)) continue;
|
||||
arr.push({ def, origin: 'namespace' });
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Step 4: Mirror return-type bindings from same-namespace sibling files.
|
||||
// This enables chain-follow like `$c->greet()->save()` where `greet()`
|
||||
// returns `Greeting` (declared in A.php, same namespace) and `Greeting`
|
||||
// isn't imported in the calling file. Without this, the compound-receiver
|
||||
// resolver can't resolve `Greeting` as a class binding in the importer's
|
||||
// scope chain.
|
||||
//
|
||||
// Additionally, mirror from files that are imported via `use` (different
|
||||
// namespace) so return types from dependencies are chain-followable too.
|
||||
for (const parsed of parsedFiles) {
|
||||
const moduleScope = parsed.scopes.find((s) => s.kind === 'Module');
|
||||
if (moduleScope === undefined) continue;
|
||||
const moduleTypeBindings = moduleScope.typeBindings as Map<
|
||||
string,
|
||||
import('gitnexus-shared').TypeRef
|
||||
>;
|
||||
|
||||
const struct = structureByFile.get(parsed.filePath);
|
||||
const ownNs = struct?.namespace ?? '';
|
||||
|
||||
// Collect namespaces accessible from this file:
|
||||
// 1. Own namespace (same-ns siblings)
|
||||
// 2. Namespaces of directly imported files (via parsedImports → targetRaw → PSR-4 namespace)
|
||||
const accessibleFiles = new Set<string>();
|
||||
|
||||
// Same-namespace siblings.
|
||||
const sameBucket = buckets.get(ownNs);
|
||||
if (sameBucket !== undefined) {
|
||||
for (const { filePath } of sameBucket.scopes) {
|
||||
if (filePath !== parsed.filePath) accessibleFiles.add(filePath);
|
||||
}
|
||||
}
|
||||
|
||||
// Files directly imported by this file (finalized import edges).
|
||||
const ownModuleScopeBindings = indexes.bindings.get(moduleScope.id);
|
||||
if (ownModuleScopeBindings !== undefined) {
|
||||
for (const [, refs] of ownModuleScopeBindings) {
|
||||
for (const ref of refs) {
|
||||
if (ref.origin === 'import' || ref.origin === 'namespace') {
|
||||
const importFilePath = ref.def.filePath;
|
||||
if (importFilePath !== parsed.filePath) {
|
||||
accessibleFiles.add(importFilePath);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Mirror return-type bindings from accessible files.
|
||||
for (const srcFilePath of accessibleFiles) {
|
||||
const srcParsed = parsedFiles.find((p) => p.filePath === srcFilePath);
|
||||
if (srcParsed === undefined) continue;
|
||||
const srcModuleScope = srcParsed.scopes.find((s) => s.kind === 'Module');
|
||||
if (srcModuleScope === undefined) continue;
|
||||
for (const [boundName, typeRef] of srcModuleScope.typeBindings) {
|
||||
if (moduleTypeBindings.has(boundName)) continue;
|
||||
moduleTypeBindings.set(boundName, typeRef);
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
332
gitnexus/src/core/ingestion/languages/php/query.ts
Normal file
332
gitnexus/src/core/ingestion/languages/php/query.ts
Normal file
|
|
@ -0,0 +1,332 @@
|
|||
/**
|
||||
* Tree-sitter query for PHP scope captures (RFC #909 Ring 3 LANG-php).
|
||||
*
|
||||
* Captures the structural skeleton the generic scope-resolution pipeline
|
||||
* consumes: scopes (program/namespace/class/function), declarations
|
||||
* (class-likes, method-likes, properties, variables), imports
|
||||
* (namespace_use_declaration), type bindings (parameter annotations,
|
||||
* property types, constructor-inferred locals, return types), and
|
||||
* references (call sites, member writes).
|
||||
*
|
||||
* PHP specifics that shape this query:
|
||||
*
|
||||
* - `namespace_use_declaration` is an import only at top level / inside
|
||||
* namespace blocks. Class-body `use_declaration` (trait-use) is a
|
||||
* different node type and is NOT captured here.
|
||||
*
|
||||
* - `object_creation_expression` has `name` and `qualified_name` as
|
||||
* direct children (no wrapping node).
|
||||
*
|
||||
* - `method_declaration` exposes a `return_type:` named field containing
|
||||
* a `type` node, which may be `named_type`, `optional_type`, etc.
|
||||
*
|
||||
* - `property_element` has a `name:` field of type `variable_name`.
|
||||
*
|
||||
* - `variable_name` nodes always include the `$` sigil in their text.
|
||||
*
|
||||
* Exposes lazy `Parser` and `Query` singletons so callers don't pay
|
||||
* tree-sitter init cost per file.
|
||||
*/
|
||||
|
||||
import Parser from 'tree-sitter';
|
||||
import Php from 'tree-sitter-php';
|
||||
|
||||
// tree-sitter-php exports `{ php, php_only, html }` in recent versions, or the
|
||||
// language directly in older versions.
|
||||
//
|
||||
// IMPORTANT: must match the grammar used by the central parse phase
|
||||
// (`src/core/tree-sitter/parser-loader.ts` line: `[SupportedLanguages.PHP]: PHP.php_only`).
|
||||
// Using a different grammar variant causes tree-sitter to throw when running
|
||||
// a query built against grammar A on a tree parsed by grammar B — this error
|
||||
// is swallowed by `scope-extractor-bridge.ts`, producing silent empty results.
|
||||
const Php_typed = Php as unknown as { php_only?: unknown; php?: unknown };
|
||||
const PHP_LANG = Php_typed.php_only ?? Php_typed.php ?? Php;
|
||||
|
||||
const PHP_SCOPE_QUERY = `
|
||||
;; ── Scopes ────────────────────────────────────────────────────────────────
|
||||
|
||||
(program) @scope.module
|
||||
|
||||
;; Both block-scoped and statement-scoped namespace declarations.
|
||||
(namespace_definition) @scope.namespace
|
||||
|
||||
(class_declaration) @scope.class
|
||||
(interface_declaration) @scope.class
|
||||
(trait_declaration) @scope.class
|
||||
(enum_declaration) @scope.class
|
||||
|
||||
(method_declaration) @scope.function
|
||||
(function_definition) @scope.function
|
||||
(anonymous_function) @scope.function
|
||||
(arrow_function) @scope.function
|
||||
|
||||
;; ── Declarations — types ──────────────────────────────────────────────────
|
||||
|
||||
(class_declaration
|
||||
name: (name) @declaration.name) @declaration.class
|
||||
|
||||
(interface_declaration
|
||||
name: (name) @declaration.name) @declaration.interface
|
||||
|
||||
(trait_declaration
|
||||
name: (name) @declaration.name) @declaration.trait
|
||||
|
||||
(enum_declaration
|
||||
name: (name) @declaration.name) @declaration.enum
|
||||
|
||||
;; ── Declarations — methods / functions / constructors ─────────────────────
|
||||
|
||||
(method_declaration
|
||||
name: (name) @declaration.name) @declaration.method
|
||||
|
||||
(function_definition
|
||||
name: (name) @declaration.name) @declaration.function
|
||||
|
||||
;; ── Declarations — properties ─────────────────────────────────────────────
|
||||
|
||||
;; PHP 7.4+ typed property: private UserRepo $repo;
|
||||
;; property_element has name: (variable_name) field.
|
||||
;; Emits BOTH a declaration (so SemanticModel registers the property) AND a type-binding.
|
||||
(property_declaration
|
||||
type: (_) @type-binding.type
|
||||
(property_element
|
||||
name: (variable_name) @type-binding.name)) @type-binding.annotation
|
||||
|
||||
(property_declaration
|
||||
type: (_)
|
||||
(property_element
|
||||
name: (variable_name) @declaration.name)) @declaration.property
|
||||
|
||||
;; Untyped property: public $id; — capture as plain declaration.
|
||||
(property_declaration
|
||||
(property_element
|
||||
name: (variable_name) @declaration.name)) @declaration.variable
|
||||
|
||||
;; ── Imports — namespace_use_declaration ───────────────────────────────────
|
||||
;;
|
||||
;; Captures ALL forms: plain, alias, function/const qualifiers, and grouped.
|
||||
;; The import-decomposer in captures.ts fans out grouped uses.
|
||||
;;
|
||||
;; NOTE: class-body use_declaration = trait-use, NOT an import.
|
||||
;; Only namespace_use_declaration (top-level / namespace scope) is an import.
|
||||
|
||||
(namespace_use_declaration) @import.statement
|
||||
|
||||
;; ── Type bindings — parameters ────────────────────────────────────────────
|
||||
|
||||
;; simple_parameter with a type hint: function f(User $u)
|
||||
;; type field is a 'type' supertype (named_type, optional_type, union_type, etc.)
|
||||
(simple_parameter
|
||||
type: (_) @type-binding.type
|
||||
name: (variable_name) @type-binding.name) @type-binding.parameter
|
||||
|
||||
;; property_promotion_parameter: function __construct(private User $u)
|
||||
;; Emits type-binding so the constructor body can resolve $u as the typed param.
|
||||
(property_promotion_parameter
|
||||
type: (_) @type-binding.type
|
||||
name: (variable_name) @type-binding.name) @type-binding.parameter
|
||||
|
||||
;; Also emit a @type-binding.annotation for the promoted parameter so that
|
||||
;; phpBindingScopeFor can hoist it to the Class scope (stripping the $ sigil).
|
||||
;; This enables compound-receiver resolution: $user->address->save() resolves
|
||||
;; address → Address via the Class scope's typeBindings.
|
||||
;; The @type-binding.parameter above stays for constructor-body resolution ($address).
|
||||
(property_promotion_parameter
|
||||
type: (_) @type-binding.type
|
||||
name: (variable_name) @type-binding.name) @type-binding.annotation
|
||||
|
||||
;; Also emit a @declaration.property so SemanticModel registers the promoted
|
||||
;; parameter as a class-owned property (enabling $obj->propName lookups).
|
||||
(property_promotion_parameter
|
||||
name: (variable_name) @declaration.name) @declaration.property
|
||||
|
||||
;; ── Type bindings — local assignment: $u = new User() ─────────────────────
|
||||
|
||||
;; new ClassName() — name is a direct child of object_creation_expression
|
||||
(assignment_expression
|
||||
left: (variable_name) @type-binding.name
|
||||
right: (object_creation_expression
|
||||
(name) @type-binding.type)) @type-binding.constructor
|
||||
|
||||
;; new Foo\Bar\ClassName() — qualified_name wraps name
|
||||
(assignment_expression
|
||||
left: (variable_name) @type-binding.name
|
||||
right: (object_creation_expression
|
||||
(qualified_name
|
||||
(name) @type-binding.type))) @type-binding.constructor
|
||||
|
||||
;; ── Type bindings — $alias = $u (identifier alias) ───────────────────────
|
||||
|
||||
(assignment_expression
|
||||
left: (variable_name) @type-binding.name
|
||||
right: (variable_name) @type-binding.type) @type-binding.alias
|
||||
|
||||
;; ── Type bindings — $u = factory() (free call return alias) ──────────────
|
||||
|
||||
(assignment_expression
|
||||
left: (variable_name) @type-binding.name
|
||||
right: (function_call_expression
|
||||
function: (name) @type-binding.type)) @type-binding.alias
|
||||
|
||||
;; ── Type bindings — $u = $svc->getUser() (method call return alias) ───────
|
||||
|
||||
(assignment_expression
|
||||
left: (variable_name) @type-binding.name
|
||||
right: (member_call_expression
|
||||
name: (name) @type-binding.type)) @type-binding.alias
|
||||
|
||||
;; ── Type bindings — method return type ───────────────────────────────────
|
||||
|
||||
;; method_declaration exposes return_type: field (type node supertype).
|
||||
;; named_type wraps the class name: function getUser(): User
|
||||
(method_declaration
|
||||
name: (name) @type-binding.name
|
||||
return_type: (named_type
|
||||
(name) @type-binding.type)) @type-binding.return
|
||||
|
||||
;; nullable return type via optional_type: function getUser(): ?User
|
||||
(method_declaration
|
||||
name: (name) @type-binding.name
|
||||
return_type: (optional_type
|
||||
(named_type
|
||||
(name) @type-binding.type))) @type-binding.return
|
||||
|
||||
;; function_definition (top-level or namespace-level) return type: User
|
||||
;; Enables cross-file return-type propagation for free functions.
|
||||
(function_definition
|
||||
name: (name) @type-binding.name
|
||||
return_type: (named_type
|
||||
(name) @type-binding.type)) @type-binding.return
|
||||
|
||||
;; nullable return type for function_definition: ?User
|
||||
(function_definition
|
||||
name: (name) @type-binding.name
|
||||
return_type: (optional_type
|
||||
(named_type
|
||||
(name) @type-binding.type))) @type-binding.return
|
||||
|
||||
;; ── References — free calls: foo() ───────────────────────────────────────
|
||||
|
||||
(function_call_expression
|
||||
function: (name) @reference.name) @reference.call.free
|
||||
|
||||
;; ── References — member calls: $obj->method() ────────────────────────────
|
||||
;;
|
||||
;; SAFETY-INVARIANT (Finding 1 of PR #1497 adversarial review): the name:
|
||||
;; field is constrained to (name), NOT (_) — tree-sitter-php emits
|
||||
;; variable_name nodes for dynamic method names ($obj->$method(),
|
||||
;; $obj->{$method}()). Keeping the pattern at (name) is what suppresses
|
||||
;; capture of those dynamic shapes. The resolver is structural-only and
|
||||
;; cannot infer the bound method name from runtime values; relaxing this
|
||||
;; pattern to (_) would silently emit zero-confidence false-positive
|
||||
;; edges. Regression: test/fixtures/lang-resolution/php-dynamic-calls/.
|
||||
|
||||
(member_call_expression
|
||||
object: (_) @reference.receiver
|
||||
name: (name) @reference.name) @reference.call.member
|
||||
|
||||
;; ── References — null-safe member calls: $obj?->method() (PHP 8+) ─────────
|
||||
|
||||
(nullsafe_member_call_expression
|
||||
object: (_) @reference.receiver
|
||||
name: (name) @reference.name) @reference.call.member
|
||||
|
||||
;; ── References — static calls: X::method() ───────────────────────────────
|
||||
;;
|
||||
;; Same SAFETY-INVARIANT as member_call_expression above: name: (name)
|
||||
;; deliberately excludes variable_name so Class::$method() and
|
||||
;; $className::$method() shapes do not capture. The receiver field uses
|
||||
;; (_) because static dispatch on a variable receiver
|
||||
;; ($className::method()) IS captured — but resolution falls through
|
||||
;; harmlessly when $className has no class type binding. See
|
||||
;; php-dynamic-calls/ regression suite.
|
||||
|
||||
(scoped_call_expression
|
||||
scope: (_) @reference.receiver
|
||||
name: (name) @reference.name) @reference.call.member
|
||||
|
||||
;; ── Type bindings — $x = X::Constant or $x = X::CASE (enum case) ─────────
|
||||
;; Binds the variable to the class name X so member calls on $x dispatch
|
||||
;; to X's methods (e.g. UserRole::Viewer → label()).
|
||||
;;
|
||||
;; tree-sitter-php emits class_constant_access_expression with two name
|
||||
;; children: [0]=class/enum name, [1]=constant/case name. The dot-anchor
|
||||
;; before (name) matches only the FIRST name child (the class).
|
||||
|
||||
(assignment_expression
|
||||
left: (variable_name) @type-binding.name
|
||||
right: (class_constant_access_expression
|
||||
. (name) @type-binding.type)) @type-binding.alias
|
||||
|
||||
(assignment_expression
|
||||
left: (variable_name) @type-binding.name
|
||||
right: (class_constant_access_expression
|
||||
(qualified_name
|
||||
(name) @type-binding.type))) @type-binding.alias
|
||||
|
||||
;; ── Type bindings — $x = SomeClass::staticFactory() ──────────────────────
|
||||
;; Binds $x to the type returned by the static factory method, anchored on
|
||||
;; the method name (chain-follow resolves the actual return type later).
|
||||
|
||||
(assignment_expression
|
||||
left: (variable_name) @type-binding.name
|
||||
right: (scoped_call_expression
|
||||
name: (name) @type-binding.type)) @type-binding.alias
|
||||
|
||||
;; ── Type bindings — null-safe member-call result: $x = $a?->getY() ───────
|
||||
|
||||
(assignment_expression
|
||||
left: (variable_name) @type-binding.name
|
||||
right: (nullsafe_member_call_expression
|
||||
name: (name) @type-binding.type)) @type-binding.alias
|
||||
|
||||
;; ── References — constructor calls: new User() ───────────────────────────
|
||||
|
||||
(object_creation_expression
|
||||
(name) @reference.name) @reference.call.constructor
|
||||
|
||||
(object_creation_expression
|
||||
(qualified_name
|
||||
(name) @reference.name)) @reference.call.constructor
|
||||
|
||||
;; ── References — member writes: $obj->prop = $x ──────────────────────────
|
||||
|
||||
(assignment_expression
|
||||
left: (member_access_expression
|
||||
object: (_) @reference.receiver
|
||||
name: (name) @reference.name)) @reference.write.member
|
||||
|
||||
;; ── References — static property writes: User::$count = $x ──────────────
|
||||
;; Uses @reference.write.static anchor so captures.ts can strip the leading
|
||||
;; $ from the variable_name capture (static props are stored without $ in graph).
|
||||
;;
|
||||
;; SAFETY-INVARIANT (Finding 2 of PR #1497 adversarial review): no
|
||||
;; read-access property capture exists in this query — dynamic property
|
||||
;; reads ($obj->$prop, $obj->{$prop}) produce no captures, which is the
|
||||
;; desired behavior for a structural-only resolver. Adding a read pattern
|
||||
;; in the future MUST keep name: (name) (not (_)) to preserve the
|
||||
;; suppression. Regression: php-dynamic-calls/ fixture dynamicPropertyRead.
|
||||
|
||||
(assignment_expression
|
||||
left: (scoped_property_access_expression
|
||||
scope: (_) @reference.receiver
|
||||
name: (variable_name) @reference.name)) @reference.write.static
|
||||
`;
|
||||
|
||||
let _parser: Parser | null = null;
|
||||
let _query: Parser.Query | null = null;
|
||||
|
||||
export function getPhpParser(): Parser {
|
||||
if (_parser === null) {
|
||||
_parser = new Parser();
|
||||
_parser.setLanguage(PHP_LANG as Parameters<Parser['setLanguage']>[0]);
|
||||
}
|
||||
return _parser;
|
||||
}
|
||||
|
||||
export function getPhpScopeQuery(): Parser.Query {
|
||||
if (_query === null) {
|
||||
_query = new Parser.Query(PHP_LANG as Parameters<Parser['setLanguage']>[0], PHP_SCOPE_QUERY);
|
||||
}
|
||||
return _query;
|
||||
}
|
||||
136
gitnexus/src/core/ingestion/languages/php/receiver-binding.ts
Normal file
136
gitnexus/src/core/ingestion/languages/php/receiver-binding.ts
Normal file
|
|
@ -0,0 +1,136 @@
|
|||
/**
|
||||
* Synthesize `@type-binding.self` captures for PHP instance methods —
|
||||
* one for `$this` (always on non-static methods inside a type
|
||||
* declaration) and optionally one for `parent` (only on class methods
|
||||
* when the enclosing class has an explicit `base_clause`).
|
||||
*
|
||||
* Mirrors `languages/csharp/receiver-binding.ts` in structure. PHP's
|
||||
* grammar doesn't give us a clean `.scm` pattern for "implicit receiver
|
||||
* on every instance method inside an enclosing type" because `$this` is
|
||||
* not a parameter — it's an implicit receiver. Synthesis in code is the
|
||||
* same approach C# uses for `this` / `base`.
|
||||
*
|
||||
* ## Known limitations
|
||||
*
|
||||
* - **Trait `$this`**: for methods defined in a trait, `$this` is
|
||||
* synthesized as a binding to the trait itself. The actual using-class
|
||||
* type is not known at single-file parse time. V1 limitation —
|
||||
* documented in `index.ts`.
|
||||
* - **Anonymous classes**: skipped (no stable enclosing class name).
|
||||
*/
|
||||
|
||||
import type { Capture, CaptureMatch } from 'gitnexus-shared';
|
||||
import { nodeToCapture, syntheticCapture, type SyntaxNode } from '../../utils/ast-helpers.js';
|
||||
|
||||
const TYPE_DECL_NODE_TYPES = new Set([
|
||||
'class_declaration',
|
||||
'interface_declaration',
|
||||
'trait_declaration',
|
||||
'enum_declaration',
|
||||
]);
|
||||
|
||||
const FUNCTION_NODE_TYPES = new Set([
|
||||
'method_declaration',
|
||||
'function_definition',
|
||||
'anonymous_function',
|
||||
'arrow_function',
|
||||
]);
|
||||
|
||||
/** Walk up to find the enclosing type declaration. */
|
||||
function findEnclosingTypeDeclaration(node: SyntaxNode): SyntaxNode | null {
|
||||
let cur: SyntaxNode | null = node.parent;
|
||||
while (cur !== null) {
|
||||
if (TYPE_DECL_NODE_TYPES.has(cur.type)) return cur;
|
||||
cur = cur.parent;
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
function typeName(typeNode: SyntaxNode): string | null {
|
||||
return typeNode.childForFieldName('name')?.text ?? null;
|
||||
}
|
||||
|
||||
/**
|
||||
* Return the base class name from a `base_clause` child of the class node.
|
||||
* `base_clause` contains a `qualified_name` or `name` child.
|
||||
*/
|
||||
function baseClauseText(typeNode: SyntaxNode): string | null {
|
||||
for (let i = 0; i < typeNode.namedChildCount; i++) {
|
||||
const child = typeNode.namedChild(i);
|
||||
if (child === null || child.type !== 'base_clause') continue;
|
||||
const nameNode = child.firstNamedChild;
|
||||
if (nameNode === null) return null;
|
||||
// Take last segment of qualified name (e.g. \App\Models\BaseModel → BaseModel)
|
||||
const text = nameNode.text.trim();
|
||||
const segments = text.split('\\').filter(Boolean);
|
||||
return segments[segments.length - 1] ?? text;
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
/** Check whether this method has a `static_modifier` child. */
|
||||
function isStaticMethod(fnNode: SyntaxNode): boolean {
|
||||
for (let i = 0; i < fnNode.namedChildCount; i++) {
|
||||
const child = fnNode.namedChild(i);
|
||||
if (child !== null && child.type === 'static_modifier') return true;
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
/**
|
||||
* Build zero, one, or two `@type-binding.self` matches for `fnNode`:
|
||||
*
|
||||
* - Returns `[]` if the function is free (no enclosing type), static,
|
||||
* or the enclosing type has no resolvable name.
|
||||
* - Returns one match (`$this`) for non-static methods inside a
|
||||
* class / trait / interface / enum body.
|
||||
* - Returns two matches (`$this` + `parent`) only when the function
|
||||
* lives in a `class_declaration` that has an explicit `base_clause`.
|
||||
*
|
||||
* The caller is responsible for guaranteeing
|
||||
* `FUNCTION_NODE_TYPES.has(fnNode.type)`.
|
||||
*/
|
||||
export function synthesizePhpReceiverBinding(fnNode: SyntaxNode): CaptureMatch[] {
|
||||
if (!FUNCTION_NODE_TYPES.has(fnNode.type)) return [];
|
||||
if (isStaticMethod(fnNode)) return [];
|
||||
|
||||
const enclosingType = findEnclosingTypeDeclaration(fnNode);
|
||||
if (enclosingType === null) return [];
|
||||
|
||||
// Anonymous class — skip (no stable name).
|
||||
if (enclosingType.type === 'anonymous_class_declaration') return [];
|
||||
|
||||
const enclosingName = typeName(enclosingType);
|
||||
if (enclosingName === null) return [];
|
||||
|
||||
// Anchor the synthesized captures to the method body (compound_statement)
|
||||
// so they land inside the function scope, not at the class scope.
|
||||
// For interface/abstract methods that have no body, skip.
|
||||
const bodyNode =
|
||||
fnNode.childForFieldName('body') ??
|
||||
// arrow_function: body is the expression after `=>`
|
||||
fnNode.childForFieldName('return_value');
|
||||
if (bodyNode === null) return [];
|
||||
|
||||
const out: CaptureMatch[] = [];
|
||||
out.push(buildReceiverMatch(bodyNode, '$this', enclosingName));
|
||||
|
||||
// `parent` applies only to class methods with an explicit base_clause.
|
||||
if (enclosingType.type === 'class_declaration') {
|
||||
const baseText = baseClauseText(enclosingType);
|
||||
if (baseText !== null) {
|
||||
out.push(buildReceiverMatch(bodyNode, 'parent', baseText));
|
||||
}
|
||||
}
|
||||
|
||||
return out;
|
||||
}
|
||||
|
||||
function buildReceiverMatch(anchorNode: SyntaxNode, name: string, typeText: string): CaptureMatch {
|
||||
const m: Record<string, Capture> = {
|
||||
'@type-binding.self': nodeToCapture('@type-binding.self', anchorNode),
|
||||
'@type-binding.name': syntheticCapture('@type-binding.name', anchorNode, name),
|
||||
'@type-binding.type': syntheticCapture('@type-binding.type', anchorNode, typeText),
|
||||
};
|
||||
return m;
|
||||
}
|
||||
421
gitnexus/src/core/ingestion/languages/php/scope-resolver.ts
Normal file
421
gitnexus/src/core/ingestion/languages/php/scope-resolver.ts
Normal file
|
|
@ -0,0 +1,421 @@
|
|||
/**
|
||||
* PHP `ScopeResolver` registered in `SCOPE_RESOLVERS` and consumed by
|
||||
* the generic `runScopeResolution` orchestrator (RFC #909 Ring 3 LANG-php).
|
||||
*
|
||||
* Third migration after Python and C#. See `pythonScopeResolver` for the
|
||||
* canonical shape.
|
||||
*
|
||||
* ## Circular-import avoidance
|
||||
*
|
||||
* The old PR had `php/scope-resolver.ts` importing `phpProvider` from
|
||||
* `../php.js` while `php.ts` imported `phpScopeResolver` from `./php/index.js`
|
||||
* — undefined at module load. The canonical fix (mirroring C#):
|
||||
*
|
||||
* - `scope-resolver.ts` imports `phpProvider` from `../php.js` ✓
|
||||
* - `php.ts` imports individual hook FUNCTIONS from `./php/index.js` ✗
|
||||
*
|
||||
* Node's ESM handles the cycle correctly because `phpProvider` is a named
|
||||
* export that is live-binding — by the time `phpScopeResolver` is first
|
||||
* read (lazily, at resolution time), `phpProvider` is fully initialized.
|
||||
*/
|
||||
|
||||
import type { ParsedFile } from 'gitnexus-shared';
|
||||
import { SupportedLanguages } from 'gitnexus-shared';
|
||||
import { buildMro, defaultLinearize } from '../../scope-resolution/passes/mro.js';
|
||||
import {
|
||||
findReceiverTypeBinding,
|
||||
populateClassOwnedMembers,
|
||||
} from '../../scope-resolution/scope/walkers.js';
|
||||
import type { ScopeResolver } from '../../scope-resolution/contract/scope-resolver.js';
|
||||
import type { KnowledgeGraph } from '../../../graph/types.js';
|
||||
import type { GraphNodeLookup } from '../../scope-resolution/graph-bridge/node-lookup.js';
|
||||
import {
|
||||
resolveCallerGraphId,
|
||||
resolveDefGraphId,
|
||||
} from '../../scope-resolution/graph-bridge/ids.js';
|
||||
import { narrowOverloadCandidates } from '../../scope-resolution/passes/overload-narrowing.js';
|
||||
import type { SemanticModel } from '../../model/semantic-model.js';
|
||||
import type { ScopeResolutionIndexes } from '../../model/scope-resolution-indexes.js';
|
||||
import type { SymbolDefinition } from 'gitnexus-shared';
|
||||
import { phpProvider } from '../php.js';
|
||||
import { phpArityCompatibility, phpMergeBindings } from './index.js';
|
||||
import { resolvePhpImportTargetInternal, loadPhpComposerConfig } from './import-target.js';
|
||||
import { populatePhpNamespaceSiblings, getPhpNamespaceForFile } from './namespace-siblings.js';
|
||||
|
||||
/**
|
||||
* PHP MRO builder — extends the generic EXTENDS-only MRO with trait-use
|
||||
* relationships encoded as IMPLEMENTS edges.
|
||||
*
|
||||
* PHP trait-use (`use TraitName;` inside a class body) is recorded in the
|
||||
* graph as an IMPLEMENTS edge from the using class to the Trait node. The
|
||||
* generic `buildMro` only walks EXTENDS edges, so trait methods are invisible
|
||||
* to the MRO-based dispatch index. This variant:
|
||||
*
|
||||
* 1. Runs the generic `buildMro` (EXTENDS edges, Class defs only).
|
||||
* 2. Indexes Trait defs from `parsedFiles` alongside Class defs.
|
||||
* 3. Walks IMPLEMENTS edges; for each edge whose target resolves to a
|
||||
* Trait DefId, prepends that Trait DefId to the source class's MRO.
|
||||
*
|
||||
* Trait methods are searched BEFORE parent-class methods (PHP semantics:
|
||||
* a trait method shadows the parent-class method but is overridden by the
|
||||
* using class's own methods).
|
||||
*/
|
||||
/**
|
||||
* PHP free-call visibility check for `pickUniqueGlobalCallable`. Returns
|
||||
* true when the candidate function is reachable from the caller's PHP
|
||||
* namespace context, false when the cross-namespace bridge would be a
|
||||
* false positive (e.g., `\App\Utils\format` is not visible from `\App`
|
||||
* without an explicit `use function App\Utils\format;`).
|
||||
*
|
||||
* Rules (PHP semantics):
|
||||
* 1. Same-namespace candidates are always visible.
|
||||
* 2. Global-namespace candidates (no namespace prefix) are visible from
|
||||
* every caller — PHP's global fallback for functions/constants.
|
||||
* 3. Candidates in a different namespace are visible only when the
|
||||
* caller has a `use function` import that matches the candidate's
|
||||
* fully-qualified name.
|
||||
*/
|
||||
function phpIsCallableVisibleFromCaller(ctx: {
|
||||
callerParsed: ParsedFile;
|
||||
candidate: SymbolDefinition;
|
||||
}): boolean {
|
||||
const { callerParsed, candidate } = ctx;
|
||||
const callerNs = getPhpNamespaceForFile(callerParsed.filePath);
|
||||
const candNs = getPhpNamespaceForFile(candidate.filePath);
|
||||
|
||||
// Global-namespace candidate: PHP falls back to global for functions
|
||||
// and constants when the local namespace doesn't define them.
|
||||
if (candNs === '') return true;
|
||||
|
||||
// Same-namespace: caller can see the candidate without an explicit use.
|
||||
if (candNs === callerNs) return true;
|
||||
|
||||
// Cross-namespace: require an explicit `use function` import in the
|
||||
// caller's parsedImports that matches the candidate's fully-qualified
|
||||
// name. interpret.ts maps `use function Foo\bar` to a named import with
|
||||
// localName = 'bar' and targetRaw = 'Foo\\bar'.
|
||||
const candQualified =
|
||||
candidate.qualifiedName === undefined
|
||||
? ''
|
||||
: candNs !== '' && !candidate.qualifiedName.includes('\\')
|
||||
? `${candNs}\\${candidate.qualifiedName}`
|
||||
: candidate.qualifiedName;
|
||||
if (candQualified === '') return false;
|
||||
return callerParsed.parsedImports.some(
|
||||
(imp) =>
|
||||
imp.kind === 'named' &&
|
||||
imp.targetRaw.replace(/^\\+/, '') === candQualified.replace(/^\\+/, ''),
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Compute the EXTENDS-only ancestor chain for every class — no trait
|
||||
* augmentation. PHP semantics: `parent::method()` walks this view so
|
||||
* that `parent::` resolves to the parent class's method, even when a
|
||||
* composed trait shadows the same name.
|
||||
*
|
||||
* Returns the same shape as `buildPhpMro` so callers can swap views
|
||||
* without changing dispatch logic. Just `buildMro` + `defaultLinearize`
|
||||
* — no trait IMPLEMENTS edge walk.
|
||||
*/
|
||||
function buildPhpExtendsOnlyMro(
|
||||
graph: KnowledgeGraph,
|
||||
parsedFiles: readonly ParsedFile[],
|
||||
nodeLookup: GraphNodeLookup,
|
||||
): Map<string, string[]> {
|
||||
return buildMro(graph, parsedFiles, nodeLookup, defaultLinearize);
|
||||
}
|
||||
|
||||
function buildPhpMro(
|
||||
graph: KnowledgeGraph,
|
||||
parsedFiles: readonly ParsedFile[],
|
||||
nodeLookup: GraphNodeLookup,
|
||||
): Map<string, string[]> {
|
||||
// Step 1: run generic MRO (Class-only, EXTENDS-only).
|
||||
const mro = buildMro(graph, parsedFiles, nodeLookup, defaultLinearize);
|
||||
|
||||
// Step 2: build a graphId → defId map for ALL class-like defs including Traits.
|
||||
// After the `isLinkableLabel` fix, Trait nodes are now indexed in nodeLookup.
|
||||
const defIdByGraphId = new Map<string, string>();
|
||||
for (const parsed of parsedFiles) {
|
||||
for (const def of parsed.localDefs) {
|
||||
if (def.type !== 'Class' && def.type !== 'Trait') continue;
|
||||
const graphId = resolveDefGraphId(parsed.filePath, def, nodeLookup);
|
||||
if (graphId !== undefined) defIdByGraphId.set(graphId, def.nodeId);
|
||||
}
|
||||
}
|
||||
|
||||
// Step 2b: build a Set of Trait defIds for O(1) trait-vs-interface checks.
|
||||
const traitDefIds = new Set<string>();
|
||||
for (const parsed of parsedFiles) {
|
||||
for (const def of parsed.localDefs) {
|
||||
if (def.type === 'Trait') traitDefIds.add(def.nodeId);
|
||||
}
|
||||
}
|
||||
|
||||
// Step 3: collect direct trait-use edges (IMPLEMENTS where target is a Trait).
|
||||
// Maps class/trait defId → [traitDefId, ...] for direct `use TraitName;`.
|
||||
const directTraitUse = new Map<string, string[]>();
|
||||
for (const rel of graph.iterRelationshipsByType('IMPLEMENTS')) {
|
||||
const sourceDefId = defIdByGraphId.get(rel.sourceId);
|
||||
if (sourceDefId === undefined) continue;
|
||||
const targetDefId = defIdByGraphId.get(rel.targetId);
|
||||
if (targetDefId === undefined) continue;
|
||||
if (!traitDefIds.has(targetDefId)) continue;
|
||||
|
||||
let list = directTraitUse.get(sourceDefId);
|
||||
if (list === undefined) {
|
||||
list = [];
|
||||
directTraitUse.set(sourceDefId, list);
|
||||
}
|
||||
if (!list.includes(targetDefId)) list.push(targetDefId);
|
||||
}
|
||||
|
||||
// Step 4: augment every class's MRO by prepending the traits used by
|
||||
// any class in its ancestor chain (transitively closed). PHP semantics:
|
||||
// a trait used by a parent class is also visible on the child, and a
|
||||
// trait-using-trait chain is flattened to a single ancestor set.
|
||||
//
|
||||
// For each class, walk its (already-computed) EXTENDS-based MRO and
|
||||
// collect all transitively-used traits via BFS — `trait A { use B; }
|
||||
// trait B { use C; } class X { use A; }` must include C in X's MRO.
|
||||
// Prepend them before the EXTENDS ancestors so the method dispatch
|
||||
// index finds trait methods before falling back to the parent class
|
||||
// hierarchy.
|
||||
for (const [classDefId, extendsMro] of mro) {
|
||||
const ancestorChain = [classDefId, ...extendsMro];
|
||||
const seeds: string[] = [];
|
||||
for (const ancestorId of ancestorChain) {
|
||||
for (const traitId of directTraitUse.get(ancestorId) ?? []) {
|
||||
seeds.push(traitId);
|
||||
}
|
||||
}
|
||||
const allTraits = collectTransitiveTraits(seeds, directTraitUse);
|
||||
|
||||
if (allTraits.length > 0) {
|
||||
// Prepend traits before EXTENDS ancestors: own class's traits first,
|
||||
// then parent traits (in ancestor order). This ensures trait methods
|
||||
// are found before falling back to the inheritance chain.
|
||||
mro.set(classDefId, [...allTraits, ...extendsMro]);
|
||||
}
|
||||
}
|
||||
|
||||
// Step 5: also insert Trait-only entries for classes that use traits
|
||||
// directly but have no EXTENDS parents (not in `mro` yet).
|
||||
for (const [classDefId, traits] of directTraitUse) {
|
||||
if (!mro.has(classDefId) && !traitDefIds.has(classDefId)) {
|
||||
// Class with no EXTENDS but with trait-use — add to MRO map.
|
||||
const allTraits = collectTransitiveTraits([...traits], directTraitUse);
|
||||
mro.set(classDefId, allTraits);
|
||||
}
|
||||
}
|
||||
|
||||
return mro;
|
||||
}
|
||||
|
||||
/**
|
||||
* Collect the transitive closure of traits reachable from the seed set.
|
||||
* BFS over `directTraitUse` until fixpoint. The `seen` set guards against
|
||||
* cycles (invalid PHP but defensively handled) and prevents duplicate
|
||||
* entries when multiple seeds converge on the same trait. Insertion order
|
||||
* is preserved — first-seen wins for MRO ordering.
|
||||
*/
|
||||
function collectTransitiveTraits(
|
||||
seeds: readonly string[],
|
||||
directTraitUse: ReadonlyMap<string, readonly string[]>,
|
||||
): string[] {
|
||||
const out: string[] = [];
|
||||
const seen = new Set<string>();
|
||||
const queue: string[] = [...seeds];
|
||||
while (queue.length > 0) {
|
||||
const t = queue.shift()!;
|
||||
if (seen.has(t)) continue;
|
||||
seen.add(t);
|
||||
out.push(t);
|
||||
for (const next of directTraitUse.get(t) ?? []) {
|
||||
if (!seen.has(next)) queue.push(next);
|
||||
}
|
||||
}
|
||||
return out;
|
||||
}
|
||||
|
||||
/**
|
||||
* Emit CALLS edges for PHP member-call sites whose receiver has no type
|
||||
* binding (e.g. `mixed`-typed parameters, untyped variables).
|
||||
*
|
||||
* PHP is dynamically typed: a parameter declared as `mixed` (or with no
|
||||
* type hint) cannot be resolved by the generic receiver-bound pass, which
|
||||
* requires a `TypeRef` in scope. This hook does a workspace-wide method
|
||||
* name lookup: when exactly one def in the workspace matches the called
|
||||
* method name, emit the CALLS edge.
|
||||
*
|
||||
* Only fires for sites that are NOT already in `handledSites` and whose
|
||||
* receiver has no type binding in the scope chain. Unique-name-match
|
||||
* constraint avoids false positives for common method names.
|
||||
*/
|
||||
function phpEmitUnresolvedReceiverEdges(
|
||||
graph: KnowledgeGraph,
|
||||
scopes: ScopeResolutionIndexes,
|
||||
parsedFiles: readonly ParsedFile[],
|
||||
nodeLookup: GraphNodeLookup,
|
||||
handledSites: Set<string>,
|
||||
model: SemanticModel,
|
||||
): number {
|
||||
let emitted = 0;
|
||||
const seen = new Set<string>();
|
||||
|
||||
for (const parsed of parsedFiles) {
|
||||
for (const site of parsed.referenceSites) {
|
||||
if (site.kind !== 'call') continue;
|
||||
if (site.explicitReceiver === undefined) continue;
|
||||
|
||||
const siteKey = `${parsed.filePath}:${site.atRange.startLine}:${site.atRange.startCol}`;
|
||||
if (handledSites.has(siteKey)) continue;
|
||||
|
||||
// Only proceed when the receiver has NO type binding — it's unresolvable
|
||||
// by the generic pass. This is the `mixed` / unannotated case.
|
||||
const typeRef = findReceiverTypeBinding(site.inScope, site.explicitReceiver.name, scopes);
|
||||
if (typeRef !== undefined) continue;
|
||||
|
||||
// Workspace-wide lookup: collect all methods matching the called name.
|
||||
// Filter out defs with no qualifiedName (legacy parse stubs without full
|
||||
// metadata) and deduplicate by nodeId so reconcileOwnership double-registration
|
||||
// doesn't inflate the count.
|
||||
const allCandidates = model.methods.lookupMethodByName(site.name);
|
||||
const seen2 = new Set<string>();
|
||||
const candidates = allCandidates.filter((c) => {
|
||||
if (c.qualifiedName === undefined) return false;
|
||||
if (seen2.has(c.nodeId)) return false;
|
||||
seen2.add(c.nodeId);
|
||||
return true;
|
||||
});
|
||||
if (candidates.length !== 1) continue; // ambiguous or missing — skip
|
||||
|
||||
const fnDef = candidates[0];
|
||||
if (fnDef === undefined) continue;
|
||||
|
||||
// Apply arity narrowing — a unique method name match is not enough
|
||||
// when arity says the call is definitively incompatible (e.g., PHP
|
||||
// f(int $req, ...$rest) called with zero args). This prevents the
|
||||
// fallback from emitting edges that the receiver-bound pass already
|
||||
// rejected for arity reasons.
|
||||
if (narrowOverloadCandidates([fnDef], site.arity, site.argumentTypes).length === 0) {
|
||||
continue;
|
||||
}
|
||||
|
||||
// Tighten the fallback further with an EXACT-required-arity gate
|
||||
// (Finding 8 / U4): the first-stage `narrowOverloadCandidates`
|
||||
// accepts any argCount in `min..max` (or `>= min` when variadic),
|
||||
// which over-emits 0.6-confidence edges for common method names
|
||||
// whose only workspace candidate has optional / defaulted params.
|
||||
// For the fallback path only, require argCount === required for
|
||||
// fixed-arity candidates. Variadic candidates keep the relaxed
|
||||
// `argCount >= required` semantics (already enforced by the first-
|
||||
// stage check, so no extra work here).
|
||||
const min = fnDef.requiredParameterCount;
|
||||
const hasVarArgs =
|
||||
fnDef.parameterTypes !== undefined &&
|
||||
fnDef.parameterTypes.some((t) => t === '...' || t.startsWith('...'));
|
||||
if (
|
||||
min !== undefined &&
|
||||
Number.isFinite(site.arity) &&
|
||||
site.arity >= 0 &&
|
||||
!hasVarArgs &&
|
||||
site.arity !== min
|
||||
) {
|
||||
continue;
|
||||
}
|
||||
|
||||
const callerGraphId = resolveCallerGraphId(site.inScope, scopes, nodeLookup);
|
||||
if (callerGraphId === undefined) continue;
|
||||
const tgtGraphId = resolveDefGraphId(fnDef.filePath, fnDef, nodeLookup);
|
||||
if (tgtGraphId === undefined) continue;
|
||||
|
||||
handledSites.add(siteKey);
|
||||
const relId = `rel:CALLS:${callerGraphId}->${tgtGraphId}`;
|
||||
if (seen.has(relId)) continue;
|
||||
seen.add(relId);
|
||||
graph.addRelationship({
|
||||
id: relId,
|
||||
sourceId: callerGraphId,
|
||||
targetId: tgtGraphId,
|
||||
type: 'CALLS',
|
||||
confidence: 0.6,
|
||||
reason: 'php-unresolved-receiver-fallback',
|
||||
});
|
||||
emitted++;
|
||||
}
|
||||
}
|
||||
return emitted;
|
||||
}
|
||||
|
||||
const phpScopeResolver: ScopeResolver = {
|
||||
language: SupportedLanguages.PHP,
|
||||
languageProvider: phpProvider,
|
||||
importEdgeReason: 'php-scope: use',
|
||||
|
||||
resolveImportTarget: (targetRaw, fromFile, allFilePaths, resolutionConfig) =>
|
||||
resolvePhpImportTargetInternal(targetRaw, fromFile, allFilePaths, resolutionConfig),
|
||||
|
||||
loadResolutionConfig: (repoPath) => loadPhpComposerConfig(repoPath),
|
||||
|
||||
// PHP LEGB-like precedence: local > import/namespace/reexport > wildcard.
|
||||
// The per-scope id is unused by phpMergeBindings (tier ordering computed
|
||||
// purely from BindingRef.origin), so we don't synthesize a Scope.
|
||||
mergeBindings: (existing, incoming) => [...phpMergeBindings([...existing, ...incoming])],
|
||||
|
||||
// Adapter: phpArityCompatibility uses (def, callsite); the contract is (callsite, def).
|
||||
arityCompatibility: (callsite, def) => phpArityCompatibility(def, callsite),
|
||||
|
||||
buildMro: (graph, parsedFiles, nodeLookup) => buildPhpMro(graph, parsedFiles, nodeLookup),
|
||||
|
||||
// PHP-specific: parent::method() must walk inheritance only, skipping
|
||||
// composed traits. See buildPhpExtendsOnlyMro and the super-branch use
|
||||
// in `passes/receiver-bound-calls.ts`.
|
||||
buildExtendsOnlyMro: (graph, parsedFiles, nodeLookup) =>
|
||||
buildPhpExtendsOnlyMro(graph, parsedFiles, nodeLookup),
|
||||
|
||||
// PHP free-call visibility: cross-namespace candidates are blocked
|
||||
// unless explicitly `use function`-imported by the caller. Prevents
|
||||
// false-positive CALLS edges between unrelated namespaces sharing a
|
||||
// function name. Same-namespace and global-namespace candidates pass
|
||||
// unchanged.
|
||||
isCallableVisibleFromCaller: phpIsCallableVisibleFromCaller,
|
||||
|
||||
populateOwners: (parsed: ParsedFile) => populateClassOwnedMembers(parsed),
|
||||
|
||||
// PHP same-namespace cross-file visibility — classes in the same
|
||||
// PHP namespace are visible without explicit `use` statements.
|
||||
// Mirrors C#'s `populateNamespaceSiblings`.
|
||||
populateNamespaceSiblings: populatePhpNamespaceSiblings,
|
||||
|
||||
// PHP uses `parent` for super-class dispatch (not `super()`).
|
||||
isSuperReceiver: (text) => text.trim() === 'parent',
|
||||
|
||||
// PHP is dynamically typed — field-fallback heuristic on so that
|
||||
// method calls on `mixed`-typed receivers (no annotation) fall back
|
||||
// to a workspace-wide name search rather than silently dropping the edge.
|
||||
fieldFallbackOnMethodLookup: true,
|
||||
|
||||
// PHP: allow free-call fallback to unique workspace-wide callable when
|
||||
// lexical/import bindings miss. Needed for two cases:
|
||||
// 1. `use function` imports where PSR-4 directory resolution is
|
||||
// non-deterministic (multiple .php files in same namespace dir).
|
||||
// 2. Unimported free calls within the same namespace (same-namespace
|
||||
// visibility without an explicit use statement, e.g. test fixtures).
|
||||
allowGlobalFreeCallFallback: true,
|
||||
|
||||
// Return-type propagation on — PHP method signatures are authoritative
|
||||
// enough for cross-file chain-follow.
|
||||
propagatesReturnTypesAcrossImports: true,
|
||||
|
||||
// PHP hoists method return-type bindings to the Module scope so
|
||||
// `propagateImportedReturnTypes` can pick them up across files.
|
||||
hoistTypeBindingsToModule: true,
|
||||
|
||||
// PHP recovers member calls on `mixed`/untyped receivers via a
|
||||
// workspace-wide unique-method-name lookup, mirroring the legacy DAG.
|
||||
emitUnresolvedReceiverEdges: phpEmitUnresolvedReceiverEdges,
|
||||
};
|
||||
|
||||
export { phpScopeResolver };
|
||||
134
gitnexus/src/core/ingestion/languages/php/simple-hooks.ts
Normal file
134
gitnexus/src/core/ingestion/languages/php/simple-hooks.ts
Normal file
|
|
@ -0,0 +1,134 @@
|
|||
/**
|
||||
* Trivial / no-op-ish hooks for the PHP provider. Made explicit so
|
||||
* reviewers don't have to re-derive the analysis from "absence == default".
|
||||
*/
|
||||
|
||||
import type {
|
||||
CaptureMatch,
|
||||
ParsedImport,
|
||||
Scope,
|
||||
ScopeId,
|
||||
ScopeTree,
|
||||
TypeRef,
|
||||
} from 'gitnexus-shared';
|
||||
|
||||
// ─── bindingScopeFor ──────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* PHP method return-type bindings (`@type-binding.return`) must hoist
|
||||
* to the enclosing Module scope so `propagateImportedReturnTypes` can
|
||||
* mirror them across files. Without this hoist, the return binding gets
|
||||
* stuck at the Class scope and is invisible to the cross-file propagation
|
||||
* pass that reads only `sourceModule.typeBindings`.
|
||||
*
|
||||
* All other bindings delegate to the default "innermost scope" rule.
|
||||
*/
|
||||
export function phpBindingScopeFor(
|
||||
decl: CaptureMatch,
|
||||
innermost: Scope,
|
||||
tree: ScopeTree,
|
||||
): ScopeId | null {
|
||||
if (decl['@type-binding.return'] !== undefined) {
|
||||
let cur: Scope | undefined = innermost;
|
||||
while (cur !== undefined && cur.kind !== 'Module') {
|
||||
const parentId: ScopeId | null = cur.parent ?? null;
|
||||
if (parentId === null) break;
|
||||
cur = tree.getScope(parentId);
|
||||
}
|
||||
if (cur !== undefined && cur.kind === 'Module') return cur.id;
|
||||
}
|
||||
|
||||
// Constructor-promoted properties (`function __construct(public User $u)`)
|
||||
// are declared inside the constructor's Function scope in the AST, but they
|
||||
// are class-owned fields. Hoist the @declaration.property binding to the
|
||||
// enclosing Class scope so `populateClassOwnedMembers` assigns the correct
|
||||
// ownerId and `findOwnedMember` can resolve `$obj->u`.
|
||||
if (decl['@declaration.property'] !== undefined && innermost.kind === 'Function') {
|
||||
let cur: Scope | undefined = innermost;
|
||||
while (cur !== undefined && cur.kind !== 'Class') {
|
||||
const parentId: ScopeId | null = cur.parent ?? null;
|
||||
if (parentId === null) break;
|
||||
cur = tree.getScope(parentId);
|
||||
}
|
||||
if (cur !== undefined && cur.kind === 'Class') return cur.id;
|
||||
}
|
||||
|
||||
// Constructor-promoted property TYPE BINDING (`function __construct(public Address $address)`)
|
||||
// produces both a @type-binding.parameter (stays in Function scope for `$address` lookups
|
||||
// inside the constructor body) AND a @type-binding.annotation (query.ts). The annotation
|
||||
// capture is emitted so this hoist branch can place `address → Address` in the CLASS scope.
|
||||
//
|
||||
// The compound-receiver resolver (`resolveCompoundReceiverClass`) reads typeBindings from
|
||||
// the class scope: `cs.typeBindings.get('address')`. Without hoisting, `$user->address->save()`
|
||||
// fails to resolve `address` because the type binding is in the constructor's Function scope.
|
||||
//
|
||||
// `@type-binding.annotation` for a promoted param appears with innermost = Function scope
|
||||
// (the constructor). Regular typed class properties (`private Address $addr;`) have their
|
||||
// annotation already in the Class scope, so this branch only fires for promoted params.
|
||||
if (decl['@type-binding.annotation'] !== undefined && innermost.kind === 'Function') {
|
||||
let cur: Scope | undefined = innermost;
|
||||
while (cur !== undefined && cur.kind !== 'Class') {
|
||||
const parentId: ScopeId | null = cur.parent ?? null;
|
||||
if (parentId === null) break;
|
||||
cur = tree.getScope(parentId);
|
||||
}
|
||||
if (cur !== undefined && cur.kind === 'Class') return cur.id;
|
||||
}
|
||||
|
||||
return null;
|
||||
}
|
||||
|
||||
// ─── importOwningScope ────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Determine which scope owns a `use` import declaration.
|
||||
*
|
||||
* - `use` inside `namespace Foo { }` → attach to that Namespace scope.
|
||||
* - Top-level `use` (no enclosing namespace) → innermost (Module).
|
||||
* - `use TraitName;` inside a class body → this is a trait-use
|
||||
* (heritage), NOT a namespace import. The grammar emits
|
||||
* `use_declaration` for trait-use (distinct from
|
||||
* `namespace_use_declaration`). Our query only captures
|
||||
* `namespace_use_declaration`, so trait-use never reaches this hook
|
||||
* in practice. Returning `null` here is a safety fallback.
|
||||
*/
|
||||
export function phpImportOwningScope(
|
||||
_imp: ParsedImport,
|
||||
innermost: Scope,
|
||||
_tree: ScopeTree,
|
||||
): ScopeId | null {
|
||||
// Namespace-scoped or module-scoped imports attach to the innermost scope
|
||||
// (either Namespace or Module). Class-scoped imports should not occur for
|
||||
// namespace_use_declaration; if they do, attach to the class scope.
|
||||
if (
|
||||
innermost.kind === 'Namespace' ||
|
||||
innermost.kind === 'Module' ||
|
||||
innermost.kind === 'Class' ||
|
||||
innermost.kind === 'Function'
|
||||
) {
|
||||
return innermost.id;
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
// ─── receiverBinding ──────────────────────────────────────────────────────
|
||||
|
||||
/**
|
||||
* Look up `$this` or `parent` in the function scope's type bindings.
|
||||
*
|
||||
* Both are synthesized as `@type-binding.self` captures during capture
|
||||
* emission (`receiver-binding.ts`) — `$this` for every non-static
|
||||
* method inside a class/trait/interface/enum body, `parent` additionally
|
||||
* for class methods with an explicit `base_clause`.
|
||||
*
|
||||
* Returns `null` for:
|
||||
* - static methods (no `$this` synthesized)
|
||||
* - free functions (no enclosing class)
|
||||
* - non-Function scopes
|
||||
*/
|
||||
export function phpReceiverBinding(functionScope: Scope): TypeRef | null {
|
||||
if (functionScope.kind !== 'Function') return null;
|
||||
return (
|
||||
functionScope.typeBindings.get('$this') ?? functionScope.typeBindings.get('parent') ?? null
|
||||
);
|
||||
}
|
||||
|
|
@ -82,6 +82,88 @@ export interface WorkerExtractedData {
|
|||
// Worker-based parallel parsing
|
||||
// ============================================================================
|
||||
|
||||
/**
|
||||
* Merge a list of `ParseWorkerResult`s into the running graph + symbol
|
||||
* table state and produce the chunk-aggregated `WorkerExtractedData`.
|
||||
*
|
||||
* Extracted from `processParsingWithWorkers` so the same merge logic can
|
||||
* be applied to both freshly-parsed worker output AND cached worker
|
||||
* output replayed during incremental analyze. Idempotent on the
|
||||
* accumulator fields (push-only); idempotent on graph if the caller
|
||||
* starts from a clean graph (otherwise duplicate `addNode` calls are
|
||||
* silently no-op'd by `KnowledgeGraph`).
|
||||
*/
|
||||
export const mergeChunkResults = (
|
||||
graph: KnowledgeGraph,
|
||||
symbolTable: SymbolTableWriter,
|
||||
chunkResults: readonly ParseWorkerResult[],
|
||||
): WorkerExtractedData => {
|
||||
const allImports: ExtractedImport[] = [];
|
||||
const allCalls: ExtractedCall[] = [];
|
||||
const allAssignments: ExtractedAssignment[] = [];
|
||||
const allHeritage: ExtractedHeritage[] = [];
|
||||
const allRoutes: ExtractedRoute[] = [];
|
||||
const allFetchCalls: ExtractedFetchCall[] = [];
|
||||
const allDecoratorRoutes: ExtractedDecoratorRoute[] = [];
|
||||
const allToolDefs: ExtractedToolDef[] = [];
|
||||
const allORMQueries: ExtractedORMQuery[] = [];
|
||||
const allConstructorBindings: FileConstructorBindings[] = [];
|
||||
const fileScopeBindingsByFile: FileScopeBindings[] = [];
|
||||
const allParsedFiles: ParsedFile[] = [];
|
||||
|
||||
for (const result of chunkResults) {
|
||||
for (const node of result.nodes) {
|
||||
graph.addNode({
|
||||
id: node.id,
|
||||
label: node.label as NodeLabel,
|
||||
properties: node.properties,
|
||||
});
|
||||
}
|
||||
for (const rel of result.relationships) {
|
||||
graph.addRelationship(rel);
|
||||
}
|
||||
for (const sym of result.symbols) {
|
||||
symbolTable.add(sym.filePath, sym.name, sym.nodeId, sym.type, {
|
||||
parameterCount: sym.parameterCount,
|
||||
requiredParameterCount: sym.requiredParameterCount,
|
||||
parameterTypes: sym.parameterTypes,
|
||||
returnType: sym.returnType,
|
||||
declaredType: sym.declaredType,
|
||||
ownerId: sym.ownerId,
|
||||
qualifiedName: sym.qualifiedName,
|
||||
});
|
||||
}
|
||||
for (const item of result.imports) allImports.push(item);
|
||||
for (const item of result.calls) allCalls.push(item);
|
||||
for (const item of result.assignments) allAssignments.push(item);
|
||||
for (const item of result.heritage) allHeritage.push(item);
|
||||
for (const item of result.routes) allRoutes.push(item);
|
||||
for (const item of result.fetchCalls) allFetchCalls.push(item);
|
||||
for (const item of result.decoratorRoutes) allDecoratorRoutes.push(item);
|
||||
for (const item of result.toolDefs) allToolDefs.push(item);
|
||||
if (result.ormQueries) for (const item of result.ormQueries) allORMQueries.push(item);
|
||||
for (const item of result.constructorBindings) allConstructorBindings.push(item);
|
||||
if (result.fileScopeBindings)
|
||||
for (const item of result.fileScopeBindings) fileScopeBindingsByFile.push(item);
|
||||
if (result.parsedFiles) for (const item of result.parsedFiles) allParsedFiles.push(item);
|
||||
}
|
||||
|
||||
return {
|
||||
imports: allImports,
|
||||
calls: allCalls,
|
||||
assignments: allAssignments,
|
||||
heritage: allHeritage,
|
||||
routes: allRoutes,
|
||||
fetchCalls: allFetchCalls,
|
||||
decoratorRoutes: allDecoratorRoutes,
|
||||
toolDefs: allToolDefs,
|
||||
ormQueries: allORMQueries,
|
||||
constructorBindings: allConstructorBindings,
|
||||
fileScopeBindings: fileScopeBindingsByFile,
|
||||
parsedFiles: allParsedFiles,
|
||||
};
|
||||
};
|
||||
|
||||
const processParsingWithWorkers = async (
|
||||
graph: KnowledgeGraph,
|
||||
files: { path: string; content: string }[],
|
||||
|
|
@ -89,6 +171,14 @@ const processParsingWithWorkers = async (
|
|||
astCache: ASTCache,
|
||||
workerPool: WorkerPool,
|
||||
onFileProgress?: FileProgressCallback,
|
||||
/**
|
||||
* When provided, populated with the raw worker results before merging.
|
||||
* Used by the incremental-indexing parse cache to capture the per-chunk
|
||||
* worker output for caching across runs. The mutation happens in-place
|
||||
* so the caller (parse-impl) can keep a reference. See
|
||||
* `gitnexus/src/storage/parse-cache.ts`.
|
||||
*/
|
||||
outRawResults?: ParseWorkerResult[],
|
||||
): Promise<WorkerExtractedData> => {
|
||||
// Filter to parseable files only
|
||||
const parseableFiles: ParseWorkerInput[] = [];
|
||||
|
|
@ -123,63 +213,16 @@ const processParsingWithWorkers = async (
|
|||
},
|
||||
);
|
||||
|
||||
// Merge results from all workers into graph and symbol table
|
||||
const allImports: ExtractedImport[] = [];
|
||||
const allCalls: ExtractedCall[] = [];
|
||||
const allAssignments: ExtractedAssignment[] = [];
|
||||
const allHeritage: ExtractedHeritage[] = [];
|
||||
const allRoutes: ExtractedRoute[] = [];
|
||||
const allFetchCalls: ExtractedFetchCall[] = [];
|
||||
const allDecoratorRoutes: ExtractedDecoratorRoute[] = [];
|
||||
const allToolDefs: ExtractedToolDef[] = [];
|
||||
const allORMQueries: ExtractedORMQuery[] = [];
|
||||
const allConstructorBindings: FileConstructorBindings[] = [];
|
||||
const fileScopeBindingsByFile: FileScopeBindings[] = [];
|
||||
const allParsedFiles: ParsedFile[] = [];
|
||||
for (const result of chunkResults) {
|
||||
for (const node of result.nodes) {
|
||||
graph.addNode({
|
||||
id: node.id,
|
||||
label: node.label as NodeLabel,
|
||||
properties: node.properties,
|
||||
});
|
||||
}
|
||||
|
||||
for (const rel of result.relationships) {
|
||||
graph.addRelationship(rel);
|
||||
}
|
||||
|
||||
for (const sym of result.symbols) {
|
||||
symbolTable.add(sym.filePath, sym.name, sym.nodeId, sym.type, {
|
||||
parameterCount: sym.parameterCount,
|
||||
requiredParameterCount: sym.requiredParameterCount,
|
||||
parameterTypes: sym.parameterTypes,
|
||||
returnType: sym.returnType,
|
||||
declaredType: sym.declaredType,
|
||||
ownerId: sym.ownerId,
|
||||
qualifiedName: sym.qualifiedName,
|
||||
});
|
||||
}
|
||||
|
||||
for (const item of result.imports) allImports.push(item);
|
||||
for (const item of result.calls) allCalls.push(item);
|
||||
for (const item of result.assignments) allAssignments.push(item);
|
||||
for (const item of result.heritage) allHeritage.push(item);
|
||||
for (const item of result.routes) allRoutes.push(item);
|
||||
for (const item of result.fetchCalls) allFetchCalls.push(item);
|
||||
for (const item of result.decoratorRoutes) allDecoratorRoutes.push(item);
|
||||
for (const item of result.toolDefs) allToolDefs.push(item);
|
||||
if (result.ormQueries) for (const item of result.ormQueries) allORMQueries.push(item);
|
||||
for (const item of result.constructorBindings) allConstructorBindings.push(item);
|
||||
if (result.fileScopeBindings)
|
||||
for (const item of result.fileScopeBindings) fileScopeBindingsByFile.push(item);
|
||||
// RFC #909 Ring 2: aggregate per-file scope artifacts. Tolerant of
|
||||
// workers that don't emit the field yet (older worker builds or
|
||||
// partial rollouts), since the additive contract means undefined =
|
||||
// "this worker produced no ParsedFiles for this chunk".
|
||||
if (result.parsedFiles) for (const item of result.parsedFiles) allParsedFiles.push(item);
|
||||
// Capture the raw chunk results for the incremental parse cache before
|
||||
// merging — the cache stores the unmerged worker output so a future run
|
||||
// can re-merge them into a fresh graph state.
|
||||
if (outRawResults) {
|
||||
for (const r of chunkResults) outRawResults.push(r);
|
||||
}
|
||||
|
||||
// Merge results from all workers into graph and symbol table.
|
||||
const merged = mergeChunkResults(graph, symbolTable, chunkResults);
|
||||
|
||||
// Merge and log skipped languages from workers
|
||||
const skippedLanguages = new Map<string, number>();
|
||||
for (const result of chunkResults) {
|
||||
|
|
@ -196,20 +239,7 @@ const processParsingWithWorkers = async (
|
|||
|
||||
// Final progress
|
||||
onFileProgress?.(total, total, 'done');
|
||||
return {
|
||||
imports: allImports,
|
||||
calls: allCalls,
|
||||
assignments: allAssignments,
|
||||
heritage: allHeritage,
|
||||
routes: allRoutes,
|
||||
fetchCalls: allFetchCalls,
|
||||
decoratorRoutes: allDecoratorRoutes,
|
||||
toolDefs: allToolDefs,
|
||||
ormQueries: allORMQueries,
|
||||
constructorBindings: allConstructorBindings,
|
||||
fileScopeBindings: fileScopeBindingsByFile,
|
||||
parsedFiles: allParsedFiles,
|
||||
};
|
||||
return merged;
|
||||
};
|
||||
|
||||
// ============================================================================
|
||||
|
|
@ -732,6 +762,14 @@ export const processParsing = async (
|
|||
scopeTreeCache: ASTCache | undefined,
|
||||
onFileProgress?: FileProgressCallback,
|
||||
workerPool?: WorkerPool,
|
||||
/**
|
||||
* Optional out-parameter for the incremental parse cache. When
|
||||
* provided AND the worker-pool path runs successfully, populated
|
||||
* with the raw `ParseWorkerResult[]` from the workers (pre-merge).
|
||||
* Stays empty for the sequential fallback path (no per-chunk
|
||||
* artifact to cache there). See `gitnexus/src/storage/parse-cache.ts`.
|
||||
*/
|
||||
outRawResults?: ParseWorkerResult[],
|
||||
): Promise<WorkerExtractedData | null> => {
|
||||
let lastProgress = 0;
|
||||
const reportProgress: FileProgressCallback | undefined = onFileProgress
|
||||
|
|
@ -759,6 +797,7 @@ export const processParsing = async (
|
|||
astCache,
|
||||
workerPool,
|
||||
reportProgress,
|
||||
outRawResults,
|
||||
);
|
||||
} catch (err) {
|
||||
const message = err instanceof Error ? err.message : String(err);
|
||||
|
|
|
|||
|
|
@ -17,7 +17,10 @@ import {
|
|||
enrichExportedTypeMap,
|
||||
type BindingEntry,
|
||||
} from '../binding-accumulator.js';
|
||||
import { processParsing } from '../parsing-processor.js';
|
||||
import { processParsing, mergeChunkResults } from '../parsing-processor.js';
|
||||
import { fileContentHash, computeChunkHash } from '../../../storage/parse-cache.js';
|
||||
import type { ParseWorkerResult } from '../workers/parse-worker.js';
|
||||
import type { WorkerExtractedData } from '../parsing-processor.js';
|
||||
import {
|
||||
processImports,
|
||||
processImportsFromExtracted,
|
||||
|
|
@ -72,8 +75,21 @@ import { extractORMQueriesInline } from './orm-extraction.js';
|
|||
import { logger } from '../../logger.js';
|
||||
// ── Constants ──────────────────────────────────────────────────────────────
|
||||
|
||||
/** Max bytes of source content to load per parse chunk. */
|
||||
const CHUNK_BYTE_BUDGET = 20 * 1024 * 1024; // 20MB
|
||||
/** Max bytes of source content to load per parse chunk.
|
||||
*
|
||||
* Memory bound for the worker pool dispatch + a granularity knob for
|
||||
* the parse cache. A single file change invalidates only its enclosing
|
||||
* chunk, so smaller budgets → finer-grained invalidation.
|
||||
*
|
||||
* Override via GITNEXUS_CHUNK_BYTE_BUDGET (bytes) — the default of 2MB
|
||||
* gives a useful invalidation floor (~1/N chunks on a multi-MB repo)
|
||||
* while keeping worker dispatch overhead under 5% on cold runs.
|
||||
*/
|
||||
const CHUNK_BYTE_BUDGET = (() => {
|
||||
const env = Number(process.env.GITNEXUS_CHUNK_BYTE_BUDGET);
|
||||
if (Number.isFinite(env) && env > 0) return env;
|
||||
return 2 * 1024 * 1024;
|
||||
})();
|
||||
|
||||
// ── Main parse + resolve function ──────────────────────────────────────────
|
||||
|
||||
|
|
@ -119,6 +135,11 @@ export async function runChunkedParseAndResolve(
|
|||
* source. See plan
|
||||
* docs/plans/2026-04-20-002-perf-parse-heritage-mro-plan.md (Unit 4). */
|
||||
scopeTreeCache: ASTCache;
|
||||
/** Worker-produced ParsedFile artifacts aggregated across chunks.
|
||||
* Threaded into scope-resolution as a re-extract cache so the warm-
|
||||
* cache analyze run can skip the dominant `extractParsedFile` cost
|
||||
* (otherwise ~58s on a 1000-file repo). */
|
||||
parsedFiles: import('gitnexus-shared').ParsedFile[];
|
||||
}> {
|
||||
const ctx = createResolutionContext();
|
||||
const symbolTable = ctx.model.symbols;
|
||||
|
|
@ -142,6 +163,15 @@ export async function runChunkedParseAndResolve(
|
|||
);
|
||||
}
|
||||
|
||||
// Sort parseableScanned alphabetically for stable chunk membership
|
||||
// across runs (Finding 4). Without this, filesystem-scan order can
|
||||
// shift between runs (notably on macOS APFS where directory entry
|
||||
// order can change after modifications) — different files in the
|
||||
// same chunk → different chunk hash → cache miss even when no file
|
||||
// content changed. The cache also becomes platform-specific: a
|
||||
// Linux-built cache misses on macOS for the same repo.
|
||||
parseableScanned.sort((a, b) => (a.path < b.path ? -1 : a.path > b.path ? 1 : 0));
|
||||
|
||||
const totalParseable = parseableScanned.length;
|
||||
|
||||
if (totalParseable === 0) {
|
||||
|
|
@ -271,6 +301,20 @@ export async function runChunkedParseAndResolve(
|
|||
const deferredWorkerHeritage: ExtractedHeritage[] = [];
|
||||
const deferredConstructorBindings: FileConstructorBindings[] = [];
|
||||
const deferredAssignments: ExtractedAssignment[] = [];
|
||||
// Aggregated per-file ParsedFile artifacts produced by workers' calls
|
||||
// to `extractParsedFile`. Threaded through to the scope-resolution
|
||||
// phase so it can SKIP its own re-extraction on cache hits — this is
|
||||
// the second-half of the parse-cache speedup since scope-resolution's
|
||||
// re-parse otherwise dominates the warm-cache wall-clock time.
|
||||
const allParsedFiles: import('gitnexus-shared').ParsedFile[] = [];
|
||||
|
||||
// Incremental parse cache (Option B): chunk-level content-addressed.
|
||||
// When the chunk's (filePath, content-hash) signature matches a prior
|
||||
// run's, replay the cached ParseWorkerResult[] instead of dispatching
|
||||
// to workers. See gitnexus/src/storage/parse-cache.ts.
|
||||
const parseCache = options?.parseCache;
|
||||
let chunkCacheHits = 0;
|
||||
let chunkCacheMisses = 0;
|
||||
|
||||
try {
|
||||
for (let chunkIdx = 0; chunkIdx < numChunks; chunkIdx++) {
|
||||
|
|
@ -281,29 +325,89 @@ export async function runChunkedParseAndResolve(
|
|||
.filter((p) => chunkContents.has(p))
|
||||
.map((p) => ({ path: p, content: chunkContents.get(p)! }));
|
||||
|
||||
const chunkWorkerData = await processParsing(
|
||||
graph,
|
||||
chunkFiles,
|
||||
symbolTable,
|
||||
astCache,
|
||||
scopeTreeCache,
|
||||
(current, _total, filePath) => {
|
||||
const globalCurrent = filesParsedSoFar + current;
|
||||
const parsingProgress = 20 + (globalCurrent / totalParseable) * 62;
|
||||
onProgress({
|
||||
phase: 'parsing',
|
||||
percent: Math.round(parsingProgress),
|
||||
message: `Parsing chunk ${chunkIdx + 1}/${numChunks}...`,
|
||||
detail: filePath,
|
||||
stats: {
|
||||
filesProcessed: globalCurrent,
|
||||
totalFiles: totalParseable,
|
||||
nodesCreated: graph.nodeCount,
|
||||
},
|
||||
});
|
||||
},
|
||||
workerPool,
|
||||
);
|
||||
// Compute the chunk's content-hash signature (if cache available).
|
||||
let chunkHash: string | null = null;
|
||||
if (parseCache) {
|
||||
const entries = chunkFiles.map((f) => ({
|
||||
filePath: f.path,
|
||||
contentHash: fileContentHash(f.content),
|
||||
}));
|
||||
chunkHash = computeChunkHash(entries);
|
||||
}
|
||||
|
||||
let chunkWorkerData: WorkerExtractedData | null;
|
||||
const cachedRaw = chunkHash ? parseCache!.entries.get(chunkHash) : undefined;
|
||||
|
||||
// Track every chunk hash we touched so the orchestrator can
|
||||
// prune stale entries (chunks whose composition no longer
|
||||
// corresponds to a live chunk in the current scan) before saving.
|
||||
if (parseCache && chunkHash) parseCache.usedKeys.add(chunkHash);
|
||||
|
||||
if (cachedRaw && cachedRaw.length > 0) {
|
||||
// Cache hit: replay the cached worker output through the same
|
||||
// merge logic the live worker path uses.
|
||||
chunkCacheHits++;
|
||||
chunkWorkerData = mergeChunkResults(graph, symbolTable, cachedRaw);
|
||||
if (isDev) {
|
||||
logger.info(
|
||||
`📦 parse-cache HIT: chunk ${chunkIdx + 1}/${numChunks} (${chunkFiles.length} files, ${chunkHash!.slice(0, 8)})`,
|
||||
);
|
||||
}
|
||||
// Progress update so UI advances even on a cache hit.
|
||||
const cachedFiles = chunkFiles.length;
|
||||
onProgress({
|
||||
phase: 'parsing',
|
||||
percent: Math.round(20 + ((filesParsedSoFar + cachedFiles) / totalParseable) * 62),
|
||||
message: `Parsing chunk ${chunkIdx + 1}/${numChunks} (cache)...`,
|
||||
stats: {
|
||||
filesProcessed: filesParsedSoFar + cachedFiles,
|
||||
totalFiles: totalParseable,
|
||||
nodesCreated: graph.nodeCount,
|
||||
},
|
||||
});
|
||||
} else {
|
||||
// Cache miss: dispatch to workers, capture the raw results, store
|
||||
// them under the chunk hash for the next run.
|
||||
chunkCacheMisses++;
|
||||
const rawResults: ParseWorkerResult[] = [];
|
||||
chunkWorkerData = await processParsing(
|
||||
graph,
|
||||
chunkFiles,
|
||||
symbolTable,
|
||||
astCache,
|
||||
scopeTreeCache,
|
||||
(current, _total, filePath) => {
|
||||
const globalCurrent = filesParsedSoFar + current;
|
||||
const parsingProgress = 20 + (globalCurrent / totalParseable) * 62;
|
||||
onProgress({
|
||||
phase: 'parsing',
|
||||
percent: Math.round(parsingProgress),
|
||||
message: `Parsing chunk ${chunkIdx + 1}/${numChunks}...`,
|
||||
detail: filePath,
|
||||
stats: {
|
||||
filesProcessed: globalCurrent,
|
||||
totalFiles: totalParseable,
|
||||
nodesCreated: graph.nodeCount,
|
||||
},
|
||||
});
|
||||
},
|
||||
workerPool,
|
||||
// Capture raw results only when we have a cache to write to —
|
||||
// otherwise we'd retain extra arrays for nothing.
|
||||
parseCache && chunkHash ? rawResults : undefined,
|
||||
);
|
||||
// Persist the raw results for this chunk hash. Sequential path
|
||||
// doesn't populate rawResults (it writes directly to graph), so
|
||||
// small repos without worker pool simply don't cache. That's fine.
|
||||
if (parseCache && chunkHash && rawResults.length > 0) {
|
||||
parseCache.entries.set(chunkHash, rawResults);
|
||||
if (isDev) {
|
||||
logger.info(
|
||||
`📦 parse-cache MISS+store: chunk ${chunkIdx + 1}/${numChunks} (${chunkFiles.length} files, ${chunkHash.slice(0, 8)})`,
|
||||
);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
const chunkBasePercent = 20 + (filesParsedSoFar / totalParseable) * 62;
|
||||
|
||||
|
|
@ -349,6 +453,12 @@ export async function runChunkedParseAndResolve(
|
|||
for (const item of chunkWorkerData.heritage) deferredWorkerHeritage.push(item);
|
||||
for (const item of chunkWorkerData.constructorBindings)
|
||||
deferredConstructorBindings.push(item);
|
||||
// Aggregate worker-produced ParsedFile artifacts so scope-
|
||||
// resolution can use them as a re-extraction cache (skips its
|
||||
// own tree-sitter re-parse on warm runs).
|
||||
if (chunkWorkerData.parsedFiles?.length) {
|
||||
for (const item of chunkWorkerData.parsedFiles) allParsedFiles.push(item);
|
||||
}
|
||||
if (chunkWorkerData.assignments?.length) {
|
||||
for (const item of chunkWorkerData.assignments) deferredAssignments.push(item);
|
||||
}
|
||||
|
|
@ -422,6 +532,12 @@ export async function runChunkedParseAndResolve(
|
|||
astCache.clear();
|
||||
}
|
||||
|
||||
if (isDev && parseCache && (chunkCacheHits > 0 || chunkCacheMisses > 0)) {
|
||||
logger.info(
|
||||
`📦 parse-cache summary: ${chunkCacheHits} chunk hit(s), ${chunkCacheMisses} miss(es) across ${numChunks} chunk(s)`,
|
||||
);
|
||||
}
|
||||
|
||||
const fullWorkerHeritageMap =
|
||||
deferredWorkerHeritage.length > 0
|
||||
? buildHeritageMap(deferredWorkerHeritage, ctx, getHeritageStrategyForLanguage)
|
||||
|
|
@ -621,5 +737,12 @@ export async function runChunkedParseAndResolve(
|
|||
// chunk-local `astCache` above is intentionally NOT exposed
|
||||
// because parse-impl clears it between chunks.
|
||||
scopeTreeCache,
|
||||
// Per-file ParsedFile artifacts produced by workers' calls to
|
||||
// `extractParsedFile`. Empty when only the sequential path ran
|
||||
// (sequential doesn't go through the worker, and extracts ParsedFile
|
||||
// inline rather than emitting it). Consumed by scope-resolution as
|
||||
// a re-extraction cache: when the file's ParsedFile is here,
|
||||
// scope-resolution skips its own `extractParsedFile` call.
|
||||
parsedFiles: allParsedFiles,
|
||||
};
|
||||
}
|
||||
|
|
|
|||
|
|
@ -20,6 +20,7 @@ import type { PipelinePhase, PipelineContext, PhaseResult } from './types.js';
|
|||
import { getPhaseOutput } from './types.js';
|
||||
import type { StructureOutput } from './structure.js';
|
||||
import type { BindingAccumulator } from '../binding-accumulator.js';
|
||||
import type { ParsedFile } from 'gitnexus-shared';
|
||||
import type {
|
||||
ExtractedFetchCall,
|
||||
ExtractedRoute,
|
||||
|
|
@ -81,6 +82,19 @@ export interface ParseOutput {
|
|||
* `scopeTreeCache.clear()` after its extract loop finishes.
|
||||
*/
|
||||
readonly scopeTreeCache: ASTCache;
|
||||
/**
|
||||
* Per-file `ParsedFile` artifacts produced by workers' calls to
|
||||
* `extractParsedFile`. Threaded through to `scopeResolutionPhase`
|
||||
* as a re-extraction cache: when a file's ParsedFile is present here,
|
||||
* scope-resolution can skip its own `extractParsedFile` (which would
|
||||
* otherwise re-parse the file with tree-sitter on the main thread,
|
||||
* costing ~58s on a 1000-file repo).
|
||||
*
|
||||
* Empty for files that went through the sequential parse fallback —
|
||||
* sequential doesn't emit ParsedFile artifacts; scope-resolution
|
||||
* falls back to a fresh extract for those.
|
||||
*/
|
||||
readonly parsedFiles: readonly ParsedFile[];
|
||||
}
|
||||
|
||||
export const parsePhase: PipelinePhase<ParseOutput> = {
|
||||
|
|
|
|||
|
|
@ -55,6 +55,19 @@ export interface PipelineOptions {
|
|||
minFiles?: number;
|
||||
minBytes?: number;
|
||||
};
|
||||
/**
|
||||
* Incremental-indexing parse cache. When provided:
|
||||
* - The parse phase looks up each chunk's content hash in
|
||||
* `parseCache.entries`. On hit, it replays the cached
|
||||
* `ParseWorkerResult[]` instead of dispatching to workers.
|
||||
* - On miss, it runs the workers as today and stores the new
|
||||
* results in `parseCache.entries` keyed by chunk hash.
|
||||
* The caller (`run-analyze.ts`) is responsible for loading the cache
|
||||
* before the pipeline runs and persisting it after. Cache survives
|
||||
* `--force` because keys are content-addressed.
|
||||
* See `gitnexus/src/storage/parse-cache.ts`.
|
||||
*/
|
||||
parseCache?: import('../../storage/parse-cache.js').ParseCache;
|
||||
}
|
||||
|
||||
// ── Phase registry ─────────────────────────────────────────────────────────
|
||||
|
|
|
|||
|
|
@ -72,6 +72,7 @@ export const MIGRATED_LANGUAGES: ReadonlySet<SupportedLanguages> = new Set<Suppo
|
|||
SupportedLanguages.TypeScript,
|
||||
SupportedLanguages.Go,
|
||||
SupportedLanguages.C,
|
||||
SupportedLanguages.PHP,
|
||||
]);
|
||||
|
||||
/**
|
||||
|
|
|
|||
|
|
@ -386,6 +386,26 @@ export interface ScopeResolver {
|
|||
nodeLookup: GraphNodeLookup,
|
||||
): Map<string /* DefId */, string[] /* ancestor DefIds */>;
|
||||
|
||||
/**
|
||||
* Optional parallel MRO that EXCLUDES mixin-like augmentation (e.g., PHP
|
||||
* traits). Returns the inheritance-only ancestor chain — the same kind
|
||||
* of map as `buildMro` but built only from inheritance edges (EXTENDS).
|
||||
*
|
||||
* Used by the shared super-branch dispatch in `receiver-bound-calls`
|
||||
* so that `parent::method()` walks the inheritance chain only, not the
|
||||
* trait-augmented one. PHP semantics: `parent::` explicitly bypasses
|
||||
* traits, even when a composed trait shadows a same-named parent method.
|
||||
*
|
||||
* Languages without mixin-like semantics leave this undefined — callers
|
||||
* fall back to `buildMro`/`mroFor`, which for those languages is already
|
||||
* the inheritance chain.
|
||||
*/
|
||||
readonly buildExtendsOnlyMro?: (
|
||||
graph: KnowledgeGraph,
|
||||
parsedFiles: readonly ParsedFile[],
|
||||
nodeLookup: GraphNodeLookup,
|
||||
) => Map<string /* DefId */, string[] /* ancestor DefIds */>;
|
||||
|
||||
/**
|
||||
* Mutate `parsed.localDefs[i].ownerId` to point at the structural
|
||||
* owner. Python's rule: methods (Function defs whose parent scope
|
||||
|
|
@ -484,6 +504,26 @@ export interface ScopeResolver {
|
|||
*/
|
||||
readonly isFileLocalDef?: (def: SymbolDefinition) => boolean;
|
||||
|
||||
/**
|
||||
* Optional predicate to gate free-call fallback emission by caller-side
|
||||
* visibility. When provided, `pickUniqueGlobalCallable` rejects candidates
|
||||
* the caller cannot legally reach — e.g., a PHP function in a different
|
||||
* namespace with no `use function` import, which PHP runtime would treat
|
||||
* as `Call to undefined function`. Returning `false` blocks the candidate;
|
||||
* returning `true` allows it; undefined-default keeps current behavior
|
||||
* (no visibility filtering, equivalent to "all candidates visible").
|
||||
*
|
||||
* The hook receives the caller's `ParsedFile` (so it can consult
|
||||
* `parsedImports`, `moduleScope`, etc.) and the candidate `SymbolDefinition`.
|
||||
* The predicate must be pure: same inputs → same answer.
|
||||
*
|
||||
* Languages without namespace-scoped function resolution leave this undefined.
|
||||
*/
|
||||
readonly isCallableVisibleFromCaller?: (ctx: {
|
||||
readonly callerParsed: ParsedFile;
|
||||
readonly candidate: SymbolDefinition;
|
||||
}) => boolean;
|
||||
|
||||
/**
|
||||
* Optional post-finalize hook to inject cross-file bindings that
|
||||
* aren't modeled via explicit imports. Runs after
|
||||
|
|
@ -576,4 +616,32 @@ export interface ScopeResolver {
|
|||
readonly treeCache?: { get(filePath: string): unknown };
|
||||
},
|
||||
) => void;
|
||||
|
||||
/**
|
||||
* Optional post-resolution pass: emit CALLS edges for member-call sites
|
||||
* whose receiver cannot be typed by the scope chain (no `TypeRef`).
|
||||
* Dynamically-typed languages with untyped/`mixed`/`Any` parameters use
|
||||
* this hook to recover the call edge via workspace-wide method-name
|
||||
* lookup, mirroring what their legacy resolvers did.
|
||||
*
|
||||
* Runs AFTER `emitReceiverBoundCalls` and BEFORE `emitFreeCallFallback`.
|
||||
* Implementations MUST:
|
||||
* - Skip sites already in `handledSites` (Invariant I2).
|
||||
* - Add resolved site keys to `handledSites` before returning.
|
||||
* - Stay narrow: a unique workspace-wide match is the safe baseline.
|
||||
* Multi-candidate fallbacks should narrow by arity / argument types
|
||||
* before emitting to keep false-positive rate bounded.
|
||||
*
|
||||
* Returns the number of edges emitted (for telemetry).
|
||||
*
|
||||
* Default: undefined (no unresolved-receiver fallback).
|
||||
*/
|
||||
readonly emitUnresolvedReceiverEdges?: (
|
||||
graph: KnowledgeGraph,
|
||||
scopes: ScopeResolutionIndexes,
|
||||
parsedFiles: readonly ParsedFile[],
|
||||
nodeLookup: GraphNodeLookup,
|
||||
handledSites: Set<string>,
|
||||
model: SemanticModel,
|
||||
) => number;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -22,8 +22,9 @@ const EMPTY_DEFS: readonly string[] = Object.freeze([]);
|
|||
|
||||
export function buildPopulatedMethodDispatch(
|
||||
mroByDefId: ReadonlyMap<string, readonly string[]>,
|
||||
extendsOnlyMroByDefId?: ReadonlyMap<string, readonly string[]>,
|
||||
): MethodDispatchIndex {
|
||||
return {
|
||||
const base: MethodDispatchIndex = {
|
||||
mroByOwnerDefId: mroByDefId,
|
||||
implsByInterfaceDefId: new Map(),
|
||||
mroFor(ownerDefId) {
|
||||
|
|
@ -33,4 +34,14 @@ export function buildPopulatedMethodDispatch(
|
|||
return EMPTY_DEFS;
|
||||
},
|
||||
};
|
||||
if (extendsOnlyMroByDefId !== undefined) {
|
||||
return {
|
||||
...base,
|
||||
extendsOnlyMroByOwnerDefId: extendsOnlyMroByDefId,
|
||||
extendsOnlyMroFor(ownerDefId) {
|
||||
return extendsOnlyMroByDefId.get(ownerDefId) ?? EMPTY_DEFS;
|
||||
},
|
||||
};
|
||||
}
|
||||
return base;
|
||||
}
|
||||
|
|
|
|||
|
|
@ -117,6 +117,11 @@ export function isLinkableLabel(label: NodeLabel): boolean {
|
|||
label === 'Interface' ||
|
||||
label === 'Struct' ||
|
||||
label === 'Enum' ||
|
||||
// Trait nodes are linkable so MRO builders can bridge PHP/Rust trait
|
||||
// defs between scope-resolution DefIds and the graph's node ids.
|
||||
// IMPLEMENTS edges from classes to traits are otherwise invisible to
|
||||
// the scope-resolution MRO pass.
|
||||
label === 'Trait' ||
|
||||
// Variable / Property are linkable too — receiver-bound write/read
|
||||
// ACCESSES edges target field nodes (e.g. `user.name = "x"` →
|
||||
// ACCESSES edge to User's `name` Variable/Property node).
|
||||
|
|
|
|||
|
|
@ -39,6 +39,10 @@ export function emitFreeCallFallback(
|
|||
options: {
|
||||
readonly allowGlobalFallback?: boolean;
|
||||
readonly isFileLocalDef?: (def: SymbolDefinition) => boolean;
|
||||
readonly isCallableVisibleFromCaller?: (ctx: {
|
||||
readonly callerParsed: ParsedFile;
|
||||
readonly candidate: SymbolDefinition;
|
||||
}) => boolean;
|
||||
} = {},
|
||||
): number {
|
||||
let emitted = 0;
|
||||
|
|
@ -82,6 +86,11 @@ export function emitFreeCallFallback(
|
|||
scopes,
|
||||
parsed.filePath,
|
||||
options.isFileLocalDef,
|
||||
site.arity,
|
||||
options.isCallableVisibleFromCaller !== undefined
|
||||
? (candidate) =>
|
||||
options.isCallableVisibleFromCaller!({ callerParsed: parsed, candidate })
|
||||
: undefined,
|
||||
);
|
||||
}
|
||||
if (fnDef === undefined) continue;
|
||||
|
|
@ -118,6 +127,8 @@ function pickUniqueGlobalCallable(
|
|||
scopes: ScopeResolutionIndexes,
|
||||
callerFilePath: string,
|
||||
isFileLocalDef?: (def: SymbolDefinition) => boolean,
|
||||
callArity?: number,
|
||||
isCallerVisible?: (candidate: SymbolDefinition) => boolean,
|
||||
): SymbolDefinition | undefined {
|
||||
const scopeDefs: SymbolDefinition[] = [];
|
||||
const scopeSeen = new Set<string>();
|
||||
|
|
@ -130,6 +141,13 @@ function pickUniqueGlobalCallable(
|
|||
if (isFileLocalDef !== undefined && def.filePath !== callerFilePath && isFileLocalDef(def)) {
|
||||
continue;
|
||||
}
|
||||
// Caller-side visibility filter (e.g., PHP namespace + use-function
|
||||
// import gating). When defined, blocks candidates the caller cannot
|
||||
// legally reach. Languages without namespace-scoped function resolution
|
||||
// leave this undefined → no filtering.
|
||||
if (isCallerVisible !== undefined && !isCallerVisible(def)) {
|
||||
continue;
|
||||
}
|
||||
const key = logicalCallableKey(def);
|
||||
if (scopeSeen.has(key)) continue;
|
||||
scopeSeen.add(key);
|
||||
|
|
@ -137,6 +155,15 @@ function pickUniqueGlobalCallable(
|
|||
}
|
||||
if (scopeDefs.length === 1) return scopeDefs[0];
|
||||
|
||||
// When multiple scope-index candidates exist, attempt arity narrowing
|
||||
// before falling back to the semantic-model lookup. This handles
|
||||
// registry-primary languages where the model is not populated for the
|
||||
// migrated language's files (call-processor skips them).
|
||||
if (scopeDefs.length > 1 && callArity !== undefined) {
|
||||
const arityMatch = narrowByArity(scopeDefs, callArity);
|
||||
if (arityMatch !== undefined) return arityMatch;
|
||||
}
|
||||
|
||||
const defs: SymbolDefinition[] = [];
|
||||
const seen = new Set<string>();
|
||||
const push = (pool: readonly SymbolDefinition[]): void => {
|
||||
|
|
@ -147,6 +174,10 @@ function pickUniqueGlobalCallable(
|
|||
if (isFileLocalDef !== undefined && def.filePath !== callerFilePath && isFileLocalDef(def)) {
|
||||
continue;
|
||||
}
|
||||
// Same caller-visibility filter applied to the model-side pool.
|
||||
if (isCallerVisible !== undefined && !isCallerVisible(def)) {
|
||||
continue;
|
||||
}
|
||||
const key = logicalCallableKey(def);
|
||||
if (seen.has(key)) continue;
|
||||
seen.add(key);
|
||||
|
|
@ -157,7 +188,35 @@ function pickUniqueGlobalCallable(
|
|||
push(model.symbols.lookupCallableByName(name));
|
||||
push(model.methods.lookupMethodByName(name));
|
||||
|
||||
return defs.length === 1 ? defs[0] : undefined;
|
||||
if (defs.length === 1) return defs[0];
|
||||
|
||||
// When multiple candidates exist and the call site has a known arity,
|
||||
// narrow by parameter count.
|
||||
if (defs.length > 1 && callArity !== undefined) {
|
||||
const arityMatch = narrowByArity(defs, callArity);
|
||||
if (arityMatch !== undefined) return arityMatch;
|
||||
}
|
||||
|
||||
return undefined;
|
||||
}
|
||||
|
||||
/**
|
||||
* Narrow a list of callable candidates by call-site arity.
|
||||
* A def is compatible when `requiredParameterCount <= arity <= parameterCount`.
|
||||
* Defs with `parameterCount === undefined` (variadic/unknown) are always kept.
|
||||
* Returns the single compatible def, or `undefined` when zero or multiple match.
|
||||
*/
|
||||
function narrowByArity(
|
||||
defs: readonly SymbolDefinition[],
|
||||
callArity: number,
|
||||
): SymbolDefinition | undefined {
|
||||
const compatible = defs.filter((d) => {
|
||||
const total = d.parameterCount;
|
||||
if (total === undefined) return true; // unknown arity — keep
|
||||
const required = d.requiredParameterCount ?? total;
|
||||
return required <= callArity && callArity <= total;
|
||||
});
|
||||
return compatible.length === 1 ? compatible[0] : undefined;
|
||||
}
|
||||
|
||||
function logicalCallableKey(def: SymbolDefinition): string {
|
||||
|
|
@ -189,10 +248,18 @@ function pickConstructorOrClass(
|
|||
|
||||
/** Walk up from the call-site scope to the enclosing class scope,
|
||||
* pick a method member by name with overload narrowing on arity +
|
||||
* argument types. Returns undefined if there's no enclosing class
|
||||
* or no matching method. Used for implicit-this calls inside a
|
||||
* class body where multiple overloads share the call name. */
|
||||
function pickImplicitThisOverload(
|
||||
* argument types. Returns undefined if there's no enclosing class,
|
||||
* no matching method, OR narrowing leaves multiple compatible
|
||||
* candidates — in the multi-candidate case, picking
|
||||
* `candidates[0]` would emit a high-confidence CALLS edge whose
|
||||
* target depends on registration order rather than a defensible
|
||||
* resolution. Mirrors `pickUniqueGlobalCallable`'s uniqueness check
|
||||
* in the same file (Codex PR #1497 review, finding 2).
|
||||
*
|
||||
* Exported for unit testing — language-agnostic logic, exercised
|
||||
* via synthetic stubs in `pick-implicit-this-overload.test.ts`. The
|
||||
* production call site is `applyFreeCallFallback` immediately above. */
|
||||
export function pickImplicitThisOverload(
|
||||
site: {
|
||||
readonly inScope: ScopeId;
|
||||
readonly name: string;
|
||||
|
|
@ -225,6 +292,11 @@ function pickImplicitThisOverload(
|
|||
if (overloads.length === 0) return undefined;
|
||||
if (overloads.length === 1) return overloads[0];
|
||||
|
||||
// Narrow on arity + argument types. Require a UNIQUE survivor —
|
||||
// ambiguous narrowing (multiple compatible candidates with no
|
||||
// disambiguating signal) leaves the call unresolved rather than
|
||||
// routing to an arbitrary first overload by registration order.
|
||||
const candidates = narrowOverloadCandidates(overloads, site.arity, site.argumentTypes);
|
||||
if (candidates.length !== 1) return undefined;
|
||||
return candidates[0];
|
||||
}
|
||||
|
|
|
|||
|
|
@ -13,9 +13,13 @@
|
|||
* 2. Exact-required-match wins over variadic. Variadic is detected
|
||||
* via a `parameterTypes` entry equal to `'params'` or starting
|
||||
* with `'params '` (C# `params` / variadic marker).
|
||||
* 3. If the arity filter empties the set, fall back to the full
|
||||
* overload list rather than returning nothing — the caller still
|
||||
* needs a best-effort candidate.
|
||||
* 3. If the arity filter empties the set AND any candidate had
|
||||
* unknown bounds (both `parameterCount` and `requiredParameterCount`
|
||||
* undefined), fall back to the full overload list — the empty
|
||||
* result may be due to missing metadata rather than a real mismatch.
|
||||
* If EVERY rejected candidate had definite arity bounds, trust the
|
||||
* filter and return empty — the call is genuinely arity-incompatible
|
||||
* (e.g., PHP `f(int $req, ...$rest)` called with zero args).
|
||||
* 4. If `argTypes` is present, filter further by per-slot type
|
||||
* equality. An empty string in `argTypes[i]` means "unknown" and
|
||||
* counts as a match. Mismatches disqualify. A non-empty typed
|
||||
|
|
@ -39,6 +43,16 @@ export function narrowOverloadCandidates(
|
|||
const max = d.parameterCount;
|
||||
const min = d.requiredParameterCount;
|
||||
if (max !== undefined && argCount > max) {
|
||||
// Variadic marker check is C#-specific (the 'params' keyword).
|
||||
// Other languages use their own marker — PHP uses '...' (see
|
||||
// `languages/php/arity-metadata.ts:46`), Python uses '*args'-
|
||||
// shaped metadata that lives outside `parameterTypes` entirely.
|
||||
// This branch is dead code for those languages because they
|
||||
// set `parameterCount = undefined` for variadic functions,
|
||||
// which keeps `max` undefined and skips this check entirely.
|
||||
// Adding new variadic markers here changes behavior for those
|
||||
// other languages too — don't extend without auditing each
|
||||
// adapter's `arity-metadata.ts`. Finding 9 of PR #1497.
|
||||
const variadic =
|
||||
d.parameterTypes !== undefined &&
|
||||
d.parameterTypes.some((t) => t === 'params' || t.startsWith('params '));
|
||||
|
|
@ -48,8 +62,16 @@ export function narrowOverloadCandidates(
|
|||
return true;
|
||||
});
|
||||
|
||||
// When the arity filter empties the set, only fall back to the full
|
||||
// overload list if some candidate had unknown bounds — otherwise the
|
||||
// empty result is authoritative (every candidate definitively failed
|
||||
// arity, e.g., PHP variadic with required-prefix called with too few
|
||||
// args).
|
||||
const anyUnknownBounds = overloads.some(
|
||||
(d) => d.parameterCount === undefined && d.requiredParameterCount === undefined,
|
||||
);
|
||||
const candidates: readonly SymbolDefinition[] =
|
||||
arityMatches.length > 0 ? arityMatches : overloads;
|
||||
arityMatches.length > 0 ? arityMatches : anyUnknownBounds ? overloads : [];
|
||||
|
||||
if (argTypes !== undefined && argTypes.length > 0) {
|
||||
const typed = candidates.filter((d) => {
|
||||
|
|
|
|||
|
|
@ -165,7 +165,16 @@ export function emitReceiverBoundCalls(
|
|||
if (provider.isSuperReceiver(receiverName)) {
|
||||
const enclosingClass = findEnclosingClassDef(site.inScope, scopes);
|
||||
if (enclosingClass !== undefined) {
|
||||
const ancestors = scopes.methodDispatch.mroFor(enclosingClass.nodeId);
|
||||
// For super-receiver dispatch (`parent::`, `base.`, `super()`),
|
||||
// walk the inheritance-only ancestor chain when the language
|
||||
// exposes it. PHP's `parent::` semantically bypasses composed
|
||||
// traits; other languages without mixin augmentation have no
|
||||
// `extendsOnlyMroFor` and fall back to `mroFor`.
|
||||
const extendsOnly = scopes.methodDispatch.extendsOnlyMroFor;
|
||||
const ancestors =
|
||||
extendsOnly !== undefined
|
||||
? extendsOnly(enclosingClass.nodeId)
|
||||
: scopes.methodDispatch.mroFor(enclosingClass.nodeId);
|
||||
let memberDef: SymbolDefinition | undefined;
|
||||
for (const ownerId of ancestors) {
|
||||
memberDef = findOwnedMember(ownerId, memberName, model);
|
||||
|
|
@ -283,7 +292,21 @@ export function emitReceiverBoundCalls(
|
|||
let memberDef: SymbolDefinition | undefined;
|
||||
for (const ownerId of chain) {
|
||||
memberDef = findOwnedMember(ownerId, memberName, model);
|
||||
if (memberDef !== undefined) break;
|
||||
if (memberDef !== undefined) {
|
||||
// The MRO chain is most-derived-first ([classDef, ...ancestors]).
|
||||
// If the most-derived definition is arity-incompatible with the
|
||||
// call site, PHP throws ArgumentCountError at runtime — it does
|
||||
// NOT silently dispatch to an ancestor. Terminate the chain walk
|
||||
// so no edge is emitted, rather than falling through to an
|
||||
// arity-compatible ancestor (which would be a false positive).
|
||||
if (
|
||||
narrowOverloadCandidates([memberDef], site.arity, site.argumentTypes).length === 0
|
||||
) {
|
||||
memberDef = undefined;
|
||||
break;
|
||||
}
|
||||
break;
|
||||
}
|
||||
}
|
||||
if (memberDef !== undefined) {
|
||||
const reason =
|
||||
|
|
|
|||
|
|
@ -93,13 +93,25 @@ export const scopeResolutionPhase: PipelinePhase<ScopeResolutionOutput> = {
|
|||
// Worker-mode parses leave the cache empty for those files; they
|
||||
// also fall back to a fresh parse — no correctness impact.
|
||||
const parseOutput = getPhaseOutput<ParseOutput>(deps, 'parse');
|
||||
const { scopeTreeCache, resolutionContext } = parseOutput;
|
||||
const { scopeTreeCache, resolutionContext, parsedFiles: workerParsedFiles } = parseOutput;
|
||||
// SemanticModel populated during `parse`: scope-resolution consumes
|
||||
// TypeRegistry / MethodRegistry / SymbolTable lookups instead of
|
||||
// rebuilding parallel indexes. See ARCHITECTURE.md § "Semantic-model
|
||||
// source of truth".
|
||||
const model = resolutionContext.model;
|
||||
|
||||
// Build a per-file lookup of ParsedFile artifacts the workers (or
|
||||
// sequential extracts) already produced. Threading this into
|
||||
// `runScopeResolution` lets the per-language extract loop short-
|
||||
// circuit `extractParsedFile` — the dominant cost on the warm-cache
|
||||
// path, since workers can't return tree-sitter Trees across the
|
||||
// MessageChannel and scope-resolution would otherwise re-parse
|
||||
// every file from scratch on the main thread.
|
||||
const preExtractedByPath = new Map<string, import('gitnexus-shared').ParsedFile>();
|
||||
for (const pf of workerParsedFiles) {
|
||||
preExtractedByPath.set(pf.filePath, pf);
|
||||
}
|
||||
|
||||
let totalFiles = 0;
|
||||
let totalImports = 0;
|
||||
let totalRefs = 0;
|
||||
|
|
@ -143,6 +155,7 @@ export const scopeResolutionPhase: PipelinePhase<ScopeResolutionOutput> = {
|
|||
files,
|
||||
treeCache: scopeTreeCache,
|
||||
resolutionConfig,
|
||||
preExtractedParsedFiles: preExtractedByPath,
|
||||
onWarn: (msg) => {
|
||||
if (isSemanticModelValidatorEnabled()) {
|
||||
logger.warn(`[scope-resolution:${lang}] ${msg}`);
|
||||
|
|
|
|||
|
|
@ -15,7 +15,9 @@ import { pythonScopeResolver } from '../../languages/python/scope-resolver.js';
|
|||
import { csharpScopeResolver } from '../../languages/csharp/scope-resolver.js';
|
||||
import { typescriptScopeResolver } from '../../languages/typescript/scope-resolver.js';
|
||||
import { goScopeResolver } from '../../languages/go/scope-resolver.js';
|
||||
import { javaScopeResolver } from '../../languages/java/scope-resolver.js';
|
||||
import { cScopeResolver } from '../../languages/c/scope-resolver.js';
|
||||
import { phpScopeResolver } from '../../languages/php/scope-resolver.js';
|
||||
|
||||
/** Map of `SupportedLanguages` → `ScopeResolver`. The phase iterates
|
||||
* this map intersected with `MIGRATED_LANGUAGES` (the per-language
|
||||
|
|
@ -29,5 +31,7 @@ export const SCOPE_RESOLVERS: ReadonlyMap<SupportedLanguages, ScopeResolver> = n
|
|||
[SupportedLanguages.CSharp, csharpScopeResolver],
|
||||
[SupportedLanguages.TypeScript, typescriptScopeResolver],
|
||||
[SupportedLanguages.Go, goScopeResolver],
|
||||
[SupportedLanguages.Java, javaScopeResolver],
|
||||
[SupportedLanguages.C, cScopeResolver],
|
||||
[SupportedLanguages.PHP, phpScopeResolver],
|
||||
]);
|
||||
|
|
|
|||
|
|
@ -72,6 +72,22 @@ interface RunScopeResolutionInput {
|
|||
* provider doesn't supply a config loader.
|
||||
*/
|
||||
readonly resolutionConfig?: unknown;
|
||||
/**
|
||||
* Pre-extracted ParsedFile artifacts keyed by file path. When a
|
||||
* file is present here, the extract loop reuses it directly and
|
||||
* skips `extractParsedFile` (which would re-parse the file with
|
||||
* tree-sitter on the main thread). Only files matching the
|
||||
* provider's language are honored — the loop verifies this
|
||||
* implicitly by language filter at the call-site (scopeResolution
|
||||
* phase).
|
||||
*
|
||||
* Worker-mode parses produce these ParsedFile artifacts as a side
|
||||
* effect of `extractParsedFile` running inside the worker; threading
|
||||
* them here is what lets the warm-cache analyze run skip the ~58s
|
||||
* scope-resolution re-parse loop on a multi-thousand-file repo.
|
||||
* Cache miss is safe — falls back to fresh extract.
|
||||
*/
|
||||
readonly preExtractedParsedFiles?: ReadonlyMap<string, ParsedFile>;
|
||||
}
|
||||
|
||||
interface RunScopeResolutionStats {
|
||||
|
|
@ -104,22 +120,37 @@ export function runScopeResolution(
|
|||
const parsedFiles: ParsedFile[] = [];
|
||||
let filesSkipped = 0;
|
||||
const treeCache = input.treeCache;
|
||||
const preExtracted = input.preExtractedParsedFiles;
|
||||
let preExtractedHits = 0;
|
||||
for (const file of files) {
|
||||
const cachedTree = treeCache?.get(file.path);
|
||||
const parsed = extractParsedFile(
|
||||
provider.languageProvider,
|
||||
file.content,
|
||||
file.path,
|
||||
onWarn,
|
||||
cachedTree,
|
||||
);
|
||||
let parsed: ParsedFile | undefined;
|
||||
// Fast path: a worker (during the parse phase) already produced a
|
||||
// ParsedFile for this file via `extractParsedFile`. Reuse it
|
||||
// directly — skips a tree-sitter re-parse on the main thread.
|
||||
if (preExtracted !== undefined) {
|
||||
parsed = preExtracted.get(file.path);
|
||||
if (parsed !== undefined) preExtractedHits++;
|
||||
}
|
||||
if (parsed === undefined) {
|
||||
filesSkipped++;
|
||||
continue;
|
||||
const cachedTree = treeCache?.get(file.path);
|
||||
parsed = extractParsedFile(
|
||||
provider.languageProvider,
|
||||
file.content,
|
||||
file.path,
|
||||
onWarn,
|
||||
cachedTree,
|
||||
);
|
||||
if (parsed === undefined) {
|
||||
filesSkipped++;
|
||||
continue;
|
||||
}
|
||||
}
|
||||
provider.populateOwners(parsed);
|
||||
parsedFiles.push(parsed);
|
||||
}
|
||||
if (PROF && preExtracted !== undefined) {
|
||||
logger.warn(`[scope-resolution prof] pre-extracted hits: ${preExtractedHits}/${files.length}`);
|
||||
}
|
||||
provider.populateWorkspaceOwners?.(parsedFiles, { fileContents: getFileContents() });
|
||||
|
||||
// Reconcile scope-resolution's ownership view into the SemanticModel.
|
||||
|
|
@ -153,6 +184,7 @@ export function runScopeResolution(
|
|||
const allFilePaths = new Set(parsedFiles.map((f) => f.filePath));
|
||||
const nodeLookup = buildGraphNodeLookup(graph);
|
||||
const mroByClassDefId = provider.buildMro(graph, parsedFiles, nodeLookup);
|
||||
const extendsOnlyMroByClassDefId = provider.buildExtendsOnlyMro?.(graph, parsedFiles, nodeLookup);
|
||||
|
||||
const resolutionConfig = input.resolutionConfig;
|
||||
const finalized = finalizeScopeModel(parsedFiles, {
|
||||
|
|
@ -174,7 +206,7 @@ export function runScopeResolution(
|
|||
// the type system.
|
||||
const indexes = {
|
||||
...finalized,
|
||||
methodDispatch: buildPopulatedMethodDispatch(mroByClassDefId),
|
||||
methodDispatch: buildPopulatedMethodDispatch(mroByClassDefId, extendsOnlyMroByClassDefId),
|
||||
};
|
||||
|
||||
// Build the workspace resolution index ONCE — scope-valued lookups
|
||||
|
|
@ -252,6 +284,17 @@ export function runScopeResolution(
|
|||
workspaceIndex,
|
||||
readonlyModel,
|
||||
);
|
||||
const unresolvedReceiverExtras =
|
||||
provider.emitUnresolvedReceiverEdges !== undefined
|
||||
? provider.emitUnresolvedReceiverEdges(
|
||||
graph,
|
||||
indexes,
|
||||
parsedFiles,
|
||||
nodeLookup,
|
||||
handledSites,
|
||||
readonlyModel,
|
||||
)
|
||||
: 0;
|
||||
const freeCallExtras = emitFreeCallFallback(
|
||||
graph,
|
||||
indexes,
|
||||
|
|
@ -264,6 +307,7 @@ export function runScopeResolution(
|
|||
{
|
||||
allowGlobalFallback: provider.allowGlobalFreeCallFallback === true,
|
||||
isFileLocalDef: provider.isFileLocalDef,
|
||||
isCallableVisibleFromCaller: provider.isCallableVisibleFromCaller,
|
||||
},
|
||||
);
|
||||
const { emitted, skipped } = emitReferencesViaLookup(
|
||||
|
|
@ -299,7 +343,7 @@ export function runScopeResolution(
|
|||
filesSkipped,
|
||||
importsEmitted,
|
||||
resolve: resolveStats,
|
||||
referenceEdgesEmitted: emitted + receiverExtras + freeCallExtras,
|
||||
referenceEdgesEmitted: emitted + receiverExtras + unresolvedReceiverExtras + freeCallExtras,
|
||||
referenceSkipped: skipped,
|
||||
};
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1020,6 +1020,16 @@ export const PHP_QUERIES = `
|
|||
(use_declaration
|
||||
[(name) (qualified_name)] @heritage.trait))) @heritage
|
||||
|
||||
; ── Heritage: trait uses another trait (transitive trait composition) ────────
|
||||
; PHP allows a trait body to contain "use OtherTrait;". The trait-uses-trait
|
||||
; IMPLEMENTS edge is required by buildPhpMro to compute the full transitive
|
||||
; trait closure (depth 3+ chains).
|
||||
(trait_declaration
|
||||
name: (name) @heritage.class
|
||||
body: (declaration_list
|
||||
(use_declaration
|
||||
[(name) (qualified_name)] @heritage.trait))) @heritage
|
||||
|
||||
; PHP HTTP consumers: file_get_contents('/path'), curl_init('/path')
|
||||
(function_call_expression
|
||||
function: (name) @_php_http (#match? @_php_http "^(file_get_contents|curl_init)$")
|
||||
|
|
|
|||
|
|
@ -218,6 +218,65 @@ const runWithSessionLock = async <T>(operation: () => Promise<T>): Promise<T> =>
|
|||
|
||||
const normalizeCopyPath = (filePath: string): string => filePath.replace(/\\/g, '/');
|
||||
|
||||
const closeQueryResult = async (result: lbug.QueryResult): Promise<void> => {
|
||||
try {
|
||||
await result.close();
|
||||
} catch {
|
||||
// Best-effort cleanup only.
|
||||
}
|
||||
};
|
||||
|
||||
const drainQueryResult = async (
|
||||
queryResult: lbug.QueryResult | lbug.QueryResult[],
|
||||
): Promise<void> => {
|
||||
const results = Array.isArray(queryResult) ? queryResult : [queryResult];
|
||||
let firstError: unknown;
|
||||
let hasError = false;
|
||||
for (const result of results) {
|
||||
try {
|
||||
await result.getAll();
|
||||
} catch (err) {
|
||||
if (!hasError) {
|
||||
firstError = err;
|
||||
hasError = true;
|
||||
}
|
||||
} finally {
|
||||
await closeQueryResult(result);
|
||||
}
|
||||
}
|
||||
if (hasError) throw firstError;
|
||||
};
|
||||
|
||||
const readQueryRows = async (
|
||||
queryResult: lbug.QueryResult | lbug.QueryResult[],
|
||||
): Promise<any[]> => {
|
||||
const results = Array.isArray(queryResult) ? queryResult : [queryResult];
|
||||
let rows: any[] = [];
|
||||
let firstError: unknown;
|
||||
let hasError = false;
|
||||
for (let i = 0; i < results.length; i++) {
|
||||
const result = results[i];
|
||||
try {
|
||||
const resultRows = await result.getAll();
|
||||
if (i === 0) rows = resultRows;
|
||||
} catch (err) {
|
||||
if (!hasError) {
|
||||
firstError = err;
|
||||
hasError = true;
|
||||
}
|
||||
} finally {
|
||||
await closeQueryResult(result);
|
||||
}
|
||||
}
|
||||
if (hasError) throw firstError;
|
||||
return rows;
|
||||
};
|
||||
|
||||
const queryAndDrain = async (targetConn: lbug.Connection, cypher: string): Promise<void> => {
|
||||
const queryResult = await targetConn.query(cypher);
|
||||
await drainQueryResult(queryResult);
|
||||
};
|
||||
|
||||
export const initLbug = async (dbPath: string) => {
|
||||
return runWithSessionLock(() => ensureLbugInitialized(dbPath));
|
||||
};
|
||||
|
|
@ -319,7 +378,7 @@ const doInitLbug = async (dbPath: string) => {
|
|||
|
||||
for (const schemaQuery of SCHEMA_QUERIES) {
|
||||
try {
|
||||
await conn.query(schemaQuery);
|
||||
await queryAndDrain(conn, schemaQuery);
|
||||
} catch (err) {
|
||||
const msg = err instanceof Error ? err.message : String(err);
|
||||
// Suppression list:
|
||||
|
|
@ -384,14 +443,14 @@ export const loadGraphToLbug = async (
|
|||
const copyQuery = getCopyQuery(table, normalizedPath);
|
||||
|
||||
try {
|
||||
await conn.query(copyQuery);
|
||||
await queryAndDrain(conn, copyQuery);
|
||||
} catch (err) {
|
||||
try {
|
||||
const retryQuery = copyQuery.replace(
|
||||
'auto_detect=false)',
|
||||
'auto_detect=false, IGNORE_ERRORS=true)',
|
||||
);
|
||||
await conn.query(retryQuery);
|
||||
await queryAndDrain(conn, retryQuery);
|
||||
} catch (retryErr) {
|
||||
const retryMsg = retryErr instanceof Error ? retryErr.message : String(retryErr);
|
||||
throw new Error(`COPY failed for ${table}: ${retryMsg.slice(0, 200)}`);
|
||||
|
|
@ -433,14 +492,14 @@ export const loadGraphToLbug = async (
|
|||
}
|
||||
|
||||
try {
|
||||
await conn.query(copyQuery);
|
||||
await queryAndDrain(conn, copyQuery);
|
||||
} catch (err) {
|
||||
try {
|
||||
const retryQuery = copyQuery.replace(
|
||||
'auto_detect=false)',
|
||||
'auto_detect=false, IGNORE_ERRORS=true)',
|
||||
);
|
||||
await conn.query(retryQuery);
|
||||
await queryAndDrain(conn, retryQuery);
|
||||
} catch (retryErr) {
|
||||
const retryMsg = retryErr instanceof Error ? retryErr.message : String(retryErr);
|
||||
warnings.push(`${fromLabel}->${toLabel} (${rows} edges): ${retryMsg.slice(0, 80)}`);
|
||||
|
|
@ -562,11 +621,14 @@ const fallbackRelationshipInserts = async (
|
|||
|
||||
const esc = (s: string) =>
|
||||
s.replace(/'/g, "''").replace(/\\/g, '\\\\').replace(/\n/g, '\\n').replace(/\r/g, '\\r');
|
||||
await conn.query(`
|
||||
await queryAndDrain(
|
||||
conn,
|
||||
`
|
||||
MATCH (a:${escapeLabel(fromLabel)} {id: '${esc(fromId)}' }),
|
||||
(b:${escapeLabel(toLabel)} {id: '${esc(toId)}' })
|
||||
CREATE (a)-[:${REL_TABLE_NAME} {type: '${esc(relType)}', confidence: ${confidence}, reason: '${esc(reason)}', step: ${step}}]->(b)
|
||||
`);
|
||||
`,
|
||||
);
|
||||
} catch {
|
||||
// skip
|
||||
}
|
||||
|
|
@ -679,14 +741,14 @@ export const insertNodeToLbug = async (
|
|||
if (targetDbPath) {
|
||||
const tempHandle = await openLbugConnection(lbug, targetDbPath);
|
||||
try {
|
||||
await tempHandle.conn.query(query);
|
||||
await queryAndDrain(tempHandle.conn, query);
|
||||
return true;
|
||||
} finally {
|
||||
await closeLbugConnection(tempHandle);
|
||||
}
|
||||
} else if (conn) {
|
||||
// Use existing persistent connection (when called from analyze)
|
||||
await conn.query(query);
|
||||
await queryAndDrain(conn, query);
|
||||
return true;
|
||||
}
|
||||
|
||||
|
|
@ -757,7 +819,7 @@ export const batchInsertNodesToLbug = async (
|
|||
query = `MERGE (n:${t} {id: ${escapeValue(properties.id)}}) SET n.name = ${escapeValue(properties.name)}, n.filePath = ${escapeValue(properties.filePath)}, n.startLine = ${properties.startLine || 0}, n.endLine = ${properties.endLine || 0}, n.content = ${escapeValue(properties.content || '')}${descPart}`;
|
||||
}
|
||||
|
||||
await tempConn.query(query);
|
||||
await queryAndDrain(tempConn, query);
|
||||
inserted++;
|
||||
} catch (e: any) {
|
||||
// Don't console.error here - it corrupts MCP JSON-RPC on stderr
|
||||
|
|
@ -777,11 +839,7 @@ export const executeQuery = async (cypher: string): Promise<any[]> => {
|
|||
}
|
||||
|
||||
const queryResult = await conn.query(cypher);
|
||||
// LadybugDB uses getAll() instead of hasNext()/getNext()
|
||||
// Query returns QueryResult for single queries, QueryResult[] for multi-statement
|
||||
const result = Array.isArray(queryResult) ? queryResult[0] : queryResult;
|
||||
const rows = await result.getAll();
|
||||
return rows;
|
||||
return await readQueryRows(queryResult);
|
||||
};
|
||||
|
||||
export const streamQuery = async (
|
||||
|
|
@ -793,8 +851,10 @@ export const streamQuery = async (
|
|||
}
|
||||
|
||||
const queryResult = await conn.query(cypher);
|
||||
const result = Array.isArray(queryResult) ? queryResult[0] : queryResult;
|
||||
const results = Array.isArray(queryResult) ? queryResult : [queryResult];
|
||||
const result = results[0];
|
||||
let rowCount = 0;
|
||||
let streamError: unknown;
|
||||
|
||||
try {
|
||||
while (await result.hasNext()) {
|
||||
|
|
@ -803,11 +863,14 @@ export const streamQuery = async (
|
|||
rowCount++;
|
||||
}
|
||||
return rowCount;
|
||||
} catch (err) {
|
||||
streamError = err;
|
||||
throw err;
|
||||
} finally {
|
||||
try {
|
||||
await result.close();
|
||||
} catch {
|
||||
// Best-effort cleanup only.
|
||||
await drainQueryResult(results);
|
||||
} catch (err) {
|
||||
if (streamError === undefined) throw err;
|
||||
}
|
||||
}
|
||||
};
|
||||
|
|
@ -829,8 +892,7 @@ export const executePrepared = async (
|
|||
throw new Error(`Prepare failed: ${errMsg}`);
|
||||
}
|
||||
const queryResult = await conn.execute(stmt, params);
|
||||
const result = Array.isArray(queryResult) ? queryResult[0] : queryResult;
|
||||
return await result.getAll();
|
||||
return await readQueryRows(queryResult);
|
||||
};
|
||||
|
||||
export const executeWithReusedStatement = async (
|
||||
|
|
@ -852,7 +914,7 @@ export const executeWithReusedStatement = async (
|
|||
}
|
||||
try {
|
||||
for (const params of subBatch) {
|
||||
await conn.execute(stmt, params);
|
||||
await drainQueryResult(await conn.execute(stmt, params));
|
||||
}
|
||||
} catch (e) {
|
||||
const msg = e instanceof Error ? e.message : String(e);
|
||||
|
|
@ -874,8 +936,7 @@ export const getLbugStats = async (): Promise<{ nodes: number; edges: number }>
|
|||
const queryResult = await conn.query(
|
||||
`MATCH (n:${escapeTableName(tableName)}) RETURN count(n) AS cnt`,
|
||||
);
|
||||
const nodeResult = Array.isArray(queryResult) ? queryResult[0] : queryResult;
|
||||
const nodeRows = await nodeResult.getAll();
|
||||
const nodeRows = await readQueryRows(queryResult);
|
||||
if (nodeRows.length > 0) {
|
||||
totalNodes += Number(nodeRows[0]?.cnt ?? nodeRows[0]?.[0] ?? 0);
|
||||
}
|
||||
|
|
@ -889,8 +950,7 @@ export const getLbugStats = async (): Promise<{ nodes: number; edges: number }>
|
|||
const queryResult = await conn.query(
|
||||
`MATCH ()-[r:${REL_TABLE_NAME}]->() RETURN count(r) AS cnt`,
|
||||
);
|
||||
const edgeResult = Array.isArray(queryResult) ? queryResult[0] : queryResult;
|
||||
const edgeRows = await edgeResult.getAll();
|
||||
const edgeRows = await readQueryRows(queryResult);
|
||||
if (edgeRows.length > 0) {
|
||||
totalEdges = Number(edgeRows[0]?.cnt ?? edgeRows[0]?.[0] ?? 0);
|
||||
}
|
||||
|
|
@ -926,8 +986,7 @@ export const loadCachedEmbeddings = async (): Promise<{
|
|||
const check = await conn.query(
|
||||
`MATCH (e:${EMBEDDING_TABLE_NAME}) RETURN e.nodeId AS nodeId, e.chunkIndex AS chunkIndex LIMIT 1`,
|
||||
);
|
||||
const checkResult = Array.isArray(check) ? check[0] : check;
|
||||
await checkResult.getAll();
|
||||
await readQueryRows(check);
|
||||
} catch {
|
||||
return { embeddingNodeIds: new Set(), embeddings: [] };
|
||||
}
|
||||
|
|
@ -951,8 +1010,7 @@ export const loadCachedEmbeddings = async (): Promise<{
|
|||
throw err;
|
||||
}
|
||||
}
|
||||
const result = Array.isArray(rows) ? rows[0] : rows;
|
||||
for (const row of await result.getAll()) {
|
||||
for (const row of await readQueryRows(rows)) {
|
||||
const nodeId = String(row.nodeId ?? row[0] ?? '');
|
||||
if (!nodeId) continue;
|
||||
embeddingNodeIds.add(nodeId);
|
||||
|
|
@ -1060,7 +1118,8 @@ export const fetchExistingEmbeddingHashes = async (
|
|||
export const flushWAL = async (): Promise<void> => {
|
||||
if (!conn) return;
|
||||
try {
|
||||
await conn.query('CHECKPOINT');
|
||||
const checkpointResult = await conn.query('CHECKPOINT');
|
||||
await drainQueryResult(checkpointResult);
|
||||
} catch {
|
||||
/* ignore — older LadybugDB or schemaless DB may not accept it */
|
||||
}
|
||||
|
|
@ -1170,13 +1229,13 @@ export const deleteNodesForFile = async (
|
|||
const countResult = await targetConn!.query(
|
||||
`MATCH (n:${tn}) WHERE n.filePath = '${escapedPath}' RETURN count(n) AS cnt`,
|
||||
);
|
||||
const result = Array.isArray(countResult) ? countResult[0] : countResult;
|
||||
const rows = await result.getAll();
|
||||
const rows = await readQueryRows(countResult);
|
||||
const count = Number(rows[0]?.cnt ?? rows[0]?.[0] ?? 0);
|
||||
|
||||
if (count > 0) {
|
||||
// Delete nodes (and implicitly their relationships via DETACH)
|
||||
await targetConn!.query(
|
||||
await queryAndDrain(
|
||||
targetConn!,
|
||||
`MATCH (n:${tn}) WHERE n.filePath = '${escapedPath}' DETACH DELETE n`,
|
||||
);
|
||||
deletedNodes += count;
|
||||
|
|
@ -1188,7 +1247,8 @@ export const deleteNodesForFile = async (
|
|||
|
||||
// Also delete any embeddings for nodes in this file
|
||||
try {
|
||||
await targetConn!.query(
|
||||
await queryAndDrain(
|
||||
targetConn!,
|
||||
`MATCH (e:${EMBEDDING_TABLE_NAME}) WHERE e.nodeId STARTS WITH '${escapedPath}' DELETE e`,
|
||||
);
|
||||
} catch {
|
||||
|
|
@ -1204,6 +1264,77 @@ export const deleteNodesForFile = async (
|
|||
|
||||
export const getEmbeddingTableName = (): string => EMBEDDING_TABLE_NAME;
|
||||
|
||||
/**
|
||||
* Return the distinct repo-relative paths of files that import
|
||||
* `targetFilePath` according to the IMPORTS edges currently in the
|
||||
* DB. Used by the incremental writeback path to expand the
|
||||
* "files-to-rewrite" set so that files importing a changed file get
|
||||
* their edges (which may have been refined by cross-file resolution)
|
||||
* re-emitted, rather than left stale in the DB.
|
||||
*
|
||||
* The DB query reads the *previous* run's state — pre-pipeline, before
|
||||
* any nodes are deleted — so the returned importers are "files that
|
||||
* USED TO import the target". That's the right set to invalidate:
|
||||
* those are the files whose edges in the DB might no longer match
|
||||
* what cross-file resolution produces given the changed file's new
|
||||
* exports.
|
||||
*/
|
||||
export const queryImporters = async (targetFilePath: string): Promise<string[]> => {
|
||||
if (!conn) {
|
||||
throw new Error('LadybugDB not initialized. Call initLbug first.');
|
||||
}
|
||||
const escaped = targetFilePath.replace(/'/g, "''");
|
||||
const cypher = `
|
||||
MATCH (a)-[r:${REL_TABLE_NAME}]->(b)
|
||||
WHERE r.type = 'IMPORTS' AND b.filePath = '${escaped}'
|
||||
RETURN DISTINCT a.filePath AS importer
|
||||
`;
|
||||
try {
|
||||
const queryResult = await conn.query(cypher);
|
||||
const result = Array.isArray(queryResult) ? queryResult[0] : queryResult;
|
||||
const rows = await result.getAll();
|
||||
const out: string[] = [];
|
||||
for (const row of rows) {
|
||||
const v = (row as { importer?: unknown }).importer;
|
||||
if (typeof v === 'string' && v.length > 0) out.push(v);
|
||||
}
|
||||
return out;
|
||||
} catch {
|
||||
return [];
|
||||
}
|
||||
};
|
||||
|
||||
/**
|
||||
* Drop every Community and Process node (and their MEMBER_OF /
|
||||
* STEP_IN_PROCESS edges via DETACH DELETE). Used at the start of an
|
||||
* incremental run so the communities and processes phases regenerate
|
||||
* them from scratch on the merged graph — required for the
|
||||
* "Leiden runs on the FULL graph" correctness invariant.
|
||||
*/
|
||||
export const deleteAllCommunitiesAndProcesses = async (): Promise<{
|
||||
nodesDeleted: number;
|
||||
}> => {
|
||||
if (!conn) {
|
||||
throw new Error('LadybugDB not initialized. Call initLbug first.');
|
||||
}
|
||||
let nodesDeleted = 0;
|
||||
for (const label of ['Community', 'Process']) {
|
||||
try {
|
||||
const countResult = await conn.query(`MATCH (n:${label}) RETURN count(n) AS cnt`);
|
||||
const result = Array.isArray(countResult) ? countResult[0] : countResult;
|
||||
const rows = await result.getAll();
|
||||
const count = Number(rows[0]?.cnt ?? rows[0]?.[0] ?? 0);
|
||||
if (count > 0) {
|
||||
await conn.query(`MATCH (n:${label}) DETACH DELETE n`);
|
||||
nodesDeleted += count;
|
||||
}
|
||||
} catch {
|
||||
// Table may not exist yet on a freshly-initialized DB — fine.
|
||||
}
|
||||
}
|
||||
return { nodesDeleted };
|
||||
};
|
||||
|
||||
// ============================================================================
|
||||
// Full-Text Search (FTS) Functions
|
||||
// ============================================================================
|
||||
|
|
@ -1232,7 +1363,7 @@ export const loadFTSExtension = async (
|
|||
throw new Error('LadybugDB not initialized. Call initLbug first.');
|
||||
}
|
||||
|
||||
const loaded = await extensionManager.ensure((sql) => c.query(sql), 'fts', 'FTS', opts);
|
||||
const loaded = await extensionManager.ensure((sql) => queryAndDrain(c, sql), 'fts', 'FTS', opts);
|
||||
if (loaded && useModuleState) ftsLoaded = true;
|
||||
return loaded;
|
||||
};
|
||||
|
|
@ -1262,7 +1393,12 @@ export const loadVectorExtension = async (
|
|||
throw new Error('LadybugDB not initialized. Call initLbug first.');
|
||||
}
|
||||
|
||||
const loaded = await extensionManager.ensure((sql) => c.query(sql), 'VECTOR', 'VECTOR', opts);
|
||||
const loaded = await extensionManager.ensure(
|
||||
(sql) => queryAndDrain(c, sql),
|
||||
'VECTOR',
|
||||
'VECTOR',
|
||||
opts,
|
||||
);
|
||||
if (loaded && useModuleState) vectorExtensionLoaded = true;
|
||||
return loaded;
|
||||
};
|
||||
|
|
@ -1294,7 +1430,7 @@ export const createFTSIndex = async (
|
|||
const query = `CALL CREATE_FTS_INDEX('${tableName}', '${indexName}', [${propList}], stemmer := '${stemmer}')`;
|
||||
|
||||
try {
|
||||
await conn.query(query);
|
||||
await queryAndDrain(conn, query);
|
||||
ensuredFTSIndexes.add(key);
|
||||
} catch (e: any) {
|
||||
if (e.message?.includes('already exists')) {
|
||||
|
|
@ -1378,8 +1514,7 @@ export const queryFTS = async (
|
|||
|
||||
try {
|
||||
const queryResult = await conn.query(cypher);
|
||||
const result = Array.isArray(queryResult) ? queryResult[0] : queryResult;
|
||||
const rows = await result.getAll();
|
||||
const rows = await readQueryRows(queryResult);
|
||||
|
||||
return rows.map((row: any) => {
|
||||
const node = row.node || row[0] || {};
|
||||
|
|
@ -1410,7 +1545,7 @@ export const dropFTSIndex = async (tableName: string, indexName: string): Promis
|
|||
}
|
||||
|
||||
try {
|
||||
await conn.query(`CALL DROP_FTS_INDEX('${tableName}', '${indexName}')`);
|
||||
await queryAndDrain(conn, `CALL DROP_FTS_INDEX('${tableName}', '${indexName}')`);
|
||||
} catch {
|
||||
// Index may not exist
|
||||
} finally {
|
||||
|
|
|
|||
|
|
@ -11,6 +11,7 @@
|
|||
|
||||
import path from 'path';
|
||||
import fs from 'fs/promises';
|
||||
import { execFileSync } from 'child_process';
|
||||
import { runPipelineFromRepo } from './ingestion/pipeline.js';
|
||||
import {
|
||||
initLbug,
|
||||
|
|
@ -20,6 +21,9 @@ import {
|
|||
executeWithReusedStatement,
|
||||
closeLbug,
|
||||
loadCachedEmbeddings,
|
||||
deleteNodesForFile,
|
||||
deleteAllCommunitiesAndProcesses,
|
||||
queryImporters,
|
||||
} from './lbug/lbug-adapter.js';
|
||||
import { createSearchFTSIndexes } from './search/fts-indexes.js';
|
||||
import {
|
||||
|
|
@ -29,7 +33,15 @@ import {
|
|||
ensureGitNexusIgnored,
|
||||
registerRepo,
|
||||
cleanupOldKuzuFiles,
|
||||
INCREMENTAL_SCHEMA_VERSION,
|
||||
} from '../storage/repo-manager.js';
|
||||
import { computeFileHashes, diffFileHashes } from '../storage/file-hash.js';
|
||||
import {
|
||||
extractChangedSubgraph,
|
||||
computeEffectiveWriteSet,
|
||||
} from './incremental/subgraph-extract.js';
|
||||
import { shadowCandidatesFor } from './incremental/shadow-candidates.js';
|
||||
import { loadParseCache, saveParseCache, pruneCache } from '../storage/parse-cache.js';
|
||||
import {
|
||||
getCurrentCommit,
|
||||
getRemoteUrl,
|
||||
|
|
@ -178,23 +190,81 @@ export async function runFullAnalysis(
|
|||
const currentCommit = repoHasGit ? getCurrentCommit(repoPath) : '';
|
||||
const existingMeta = await loadMeta(storagePath);
|
||||
|
||||
// ── Crash recovery: dirty flag forces full rebuild ────────────────
|
||||
// If the previous incremental run set incrementalInProgress and didn't
|
||||
// clear it, the on-disk index may be in a half-state. Cheapest path
|
||||
// back to a known-good index is to wipe + rebuild from scratch.
|
||||
if (existingMeta?.incrementalInProgress) {
|
||||
log(
|
||||
'Previous incremental run did not complete cleanly (incrementalInProgress flag set); ' +
|
||||
'forcing full rebuild to restore a known-good index.',
|
||||
);
|
||||
options = { ...options, force: true };
|
||||
// Reload meta after clearing the flag in-memory; we still want fileHashes
|
||||
// for the post-rebuild meta carry-over, but force=true ensures the
|
||||
// rebuild path executes.
|
||||
}
|
||||
|
||||
// ── Early-return: already up to date ──────────────────────────────
|
||||
if (existingMeta && !options.force && existingMeta.lastCommit === currentCommit) {
|
||||
// Non-git folders have currentCommit = '' — always rebuild since we can't detect changes
|
||||
if (currentCommit !== '') {
|
||||
await ensureGitNexusIgnored(repoPath);
|
||||
return {
|
||||
// `resolveRepoIdentityRoot` collapses worktree roots to the
|
||||
// canonical repo basename (#1259) but leaves arbitrary subdirs
|
||||
// and `--skip-git` paths unchanged (#1232/#1233 intent preserved).
|
||||
repoName:
|
||||
options.registryName ??
|
||||
getInferredRepoName(repoPath) ??
|
||||
path.basename(resolveRepoIdentityRoot(repoPath)),
|
||||
repoPath,
|
||||
stats: existingMeta.stats ?? {},
|
||||
alreadyUpToDate: true,
|
||||
};
|
||||
// For git repos, even if HEAD matches lastCommit, the working tree
|
||||
// may have uncommitted changes. Only short-circuit when the working
|
||||
// tree is also clean — otherwise fall through to the incremental
|
||||
// path which will hash-diff and update only changed files.
|
||||
//
|
||||
// We exclude paths that GitNexus itself writes during analyze:
|
||||
// .gitnexus/ — db / parse cache / meta.json
|
||||
// .claude/, .cursor/ — auto-generated agent skill files
|
||||
// AGENTS.md, CLAUDE.md — auto-updated stats blocks
|
||||
// Counting them as dirty would perpetually defeat the up-to-date
|
||||
// fast path because the previous analyze just wrote them
|
||||
// (regression vs PR #1233 behavior).
|
||||
const dirty = (() => {
|
||||
try {
|
||||
const out = execFileSync(
|
||||
'git',
|
||||
[
|
||||
'status',
|
||||
'--porcelain',
|
||||
'--',
|
||||
'.',
|
||||
':(exclude).gitnexus',
|
||||
':(exclude).gitnexus/**',
|
||||
':(exclude).claude',
|
||||
':(exclude).claude/**',
|
||||
':(exclude).cursor',
|
||||
':(exclude).cursor/**',
|
||||
':(exclude)AGENTS.md',
|
||||
':(exclude)CLAUDE.md',
|
||||
],
|
||||
{
|
||||
cwd: repoPath,
|
||||
stdio: ['ignore', 'pipe', 'ignore'],
|
||||
encoding: 'utf8',
|
||||
},
|
||||
);
|
||||
return out.trim().length > 0;
|
||||
} catch {
|
||||
return true; // conservative on git failure
|
||||
}
|
||||
})();
|
||||
if (!dirty) {
|
||||
await ensureGitNexusIgnored(repoPath);
|
||||
return {
|
||||
// `resolveRepoIdentityRoot` collapses worktree roots to the
|
||||
// canonical repo basename (#1259) but leaves arbitrary subdirs
|
||||
// and `--skip-git` paths unchanged (#1232/#1233 intent preserved).
|
||||
repoName:
|
||||
options.registryName ??
|
||||
getInferredRepoName(repoPath) ??
|
||||
path.basename(resolveRepoIdentityRoot(repoPath)),
|
||||
repoPath,
|
||||
stats: existingMeta.stats ?? {},
|
||||
alreadyUpToDate: true,
|
||||
};
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -243,6 +313,14 @@ export async function runFullAnalysis(
|
|||
);
|
||||
}
|
||||
|
||||
// We *always* load the embedding cache when one is requested (regardless
|
||||
// of the predicted `willTryIncremental`). The post-pipeline branch may
|
||||
// disagree with the prediction (e.g. when the pipeline produces zero
|
||||
// File nodes, `isIncremental` flips false and the full-rebuild path
|
||||
// wipes the DB) — loading unconditionally is cheap insurance against
|
||||
// silently dropping embeddings on a mispredicted run. The re-insert
|
||||
// step gates itself on the actual `isIncremental` value to avoid
|
||||
// PK-conflicts when the incremental writeback path keeps the rows.
|
||||
if (shouldLoadCache && existingMeta) {
|
||||
try {
|
||||
progress('embeddings', 0, 'Caching embeddings...');
|
||||
|
|
@ -270,24 +348,89 @@ export async function runFullAnalysis(
|
|||
}
|
||||
}
|
||||
|
||||
// ── Load incremental parse cache ──────────────────────────────────
|
||||
// Content-addressed: safe to reuse across `--force` runs (chunks whose
|
||||
// file contents haven't changed produce identical worker output).
|
||||
// Loaded into a single ParseCache object that the pipeline mutates
|
||||
// in-place (cache hits leave entries unchanged; misses add new ones).
|
||||
const parseCache = await loadParseCache(storagePath);
|
||||
|
||||
// ── Phase 1: Full Pipeline (0–60%) ────────────────────────────────
|
||||
const pipelineResult = await runPipelineFromRepo(repoPath, (p) => {
|
||||
const phaseLabel = PHASE_LABELS[p.phase] || p.phase;
|
||||
const scaled = Math.round(p.percent * 0.6);
|
||||
const message = p.detail ? `${p.message || phaseLabel} (${p.detail})` : p.message || phaseLabel;
|
||||
progress(p.phase, scaled, message);
|
||||
});
|
||||
const pipelineResult = await runPipelineFromRepo(
|
||||
repoPath,
|
||||
(p) => {
|
||||
const phaseLabel = PHASE_LABELS[p.phase] || p.phase;
|
||||
const scaled = Math.round(p.percent * 0.6);
|
||||
const message = p.detail
|
||||
? `${p.message || phaseLabel} (${p.detail})`
|
||||
: p.message || phaseLabel;
|
||||
progress(p.phase, scaled, message);
|
||||
},
|
||||
{ parseCache },
|
||||
);
|
||||
|
||||
// ── Phase 2: LadybugDB (60–85%) ──────────────────────────────────
|
||||
progress('lbug', 60, 'Loading into LadybugDB...');
|
||||
|
||||
await closeLbug();
|
||||
const lbugFiles = [lbugPath, `${lbugPath}.wal`, `${lbugPath}.lock`];
|
||||
for (const f of lbugFiles) {
|
||||
try {
|
||||
await fs.rm(f, { recursive: true, force: true });
|
||||
} catch {
|
||||
/* swallow */
|
||||
// Compute current per-file content hashes from the pipeline's File nodes.
|
||||
// Used both to drive the incremental DB writeback (when eligible) and to
|
||||
// populate meta.json.fileHashes for the next run.
|
||||
const allFilePaths: string[] = [];
|
||||
pipelineResult.graph.forEachNode((n) => {
|
||||
if (n.label === 'File') {
|
||||
const fp = n.properties?.filePath as string | undefined;
|
||||
if (fp) allFilePaths.push(fp);
|
||||
}
|
||||
});
|
||||
const newFileHashes = await computeFileHashes(repoPath, allFilePaths);
|
||||
|
||||
// Decide incremental vs full at THIS point (post-pipeline, pre-DB).
|
||||
// All eligibility conditions are checked here against the actual
|
||||
// pipeline output — no separate pre-pipeline prediction to desync from
|
||||
// (Bugbot review on PR #1479: a prediction that flipped post-pipeline
|
||||
// could skip the embedding cache load and then take the full-rebuild
|
||||
// path, silently losing embeddings).
|
||||
const isIncremental =
|
||||
!options.force &&
|
||||
!!existingMeta &&
|
||||
existingMeta.schemaVersion === INCREMENTAL_SCHEMA_VERSION &&
|
||||
!!existingMeta.fileHashes &&
|
||||
Object.keys(existingMeta.fileHashes).length > 0 &&
|
||||
repoHasGit &&
|
||||
allFilePaths.length > 0;
|
||||
|
||||
const hashDiff = isIncremental
|
||||
? diffFileHashes(newFileHashes, existingMeta!.fileHashes)
|
||||
: undefined;
|
||||
|
||||
if (isIncremental && hashDiff) {
|
||||
log(
|
||||
`Incremental: changed=${hashDiff.changed.length}, ` +
|
||||
`added=${hashDiff.added.length}, ` +
|
||||
`deleted=${hashDiff.deleted.length} ` +
|
||||
`(skipping wipe + ${
|
||||
allFilePaths.length - hashDiff.toWrite.length
|
||||
} unchanged file rows preserved)`,
|
||||
);
|
||||
// Set the dirty flag BEFORE any destructive DB mutation. Cleared on
|
||||
// success at the meta-save step.
|
||||
await saveMeta(storagePath, {
|
||||
...existingMeta!,
|
||||
incrementalInProgress: {
|
||||
startedAt: Date.now(),
|
||||
toWriteCount: hashDiff.toWrite.length,
|
||||
},
|
||||
});
|
||||
} else {
|
||||
// Full rebuild path: wipe DB files first.
|
||||
await closeLbug();
|
||||
const lbugFiles = [lbugPath, `${lbugPath}.wal`, `${lbugPath}.lock`];
|
||||
for (const f of lbugFiles) {
|
||||
try {
|
||||
await fs.rm(f, { recursive: true, force: true });
|
||||
} catch {
|
||||
/* swallow */
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
|
@ -298,11 +441,145 @@ export async function runFullAnalysis(
|
|||
// must be released to avoid blocking subsequent invocations.
|
||||
|
||||
let lbugMsgCount = 0;
|
||||
await loadGraphToLbug(pipelineResult.graph, pipelineResult.repoPath, storagePath, (msg) => {
|
||||
lbugMsgCount++;
|
||||
const pct = Math.min(84, 60 + Math.round((lbugMsgCount / (lbugMsgCount + 10)) * 24));
|
||||
progress('lbug', pct, msg);
|
||||
});
|
||||
if (isIncremental && hashDiff) {
|
||||
// ── Incremental DB writeback ───────────────────────────────────
|
||||
// 0. Expand the writable set with transitive importers of
|
||||
// changed/deleted files (bounded BFS).
|
||||
//
|
||||
// Reason (Bugbot/Claude review on PR #1479): when a barrel /
|
||||
// re-export file C changes, cross-file resolution may update
|
||||
// CALLS edges between two unchanged files A and B (A imports
|
||||
// from C, C re-exports something from B). Those refined edges
|
||||
// live in `ctx.graph` but would be excluded from the subgraph
|
||||
// if neither endpoint is in the changed set. To catch this,
|
||||
// files that imported (directly OR transitively, through
|
||||
// other unchanged intermediaries) any changed file get pulled
|
||||
// into the writable set so their rows are deleted + rewritten
|
||||
// against the refined edges.
|
||||
//
|
||||
// BFS bound: MAX_IMPORTER_BFS_DEPTH. Practically sized to
|
||||
// catch nested barrel chains (e.g. `index.ts → submodule/index.ts
|
||||
// → submodule/impl.ts`) without ballooning into a near-full-
|
||||
// rebuild on monorepos with deep re-export pyramids. Beyond
|
||||
// this depth, the "incremental ≡ full-rebuild" invariant is
|
||||
// self-acknowledged as best-effort; `--force` remains the
|
||||
// escape hatch documented in GUARDRAILS.md.
|
||||
//
|
||||
// `queryImporters` reads `IMPORTS` from the pre-pipeline DB
|
||||
// state, so the result is "files that USED TO import the
|
||||
// target" — exactly the set whose previously-stored edges may
|
||||
// no longer match what cross-file resolution produces this run.
|
||||
const MAX_IMPORTER_BFS_DEPTH = 4;
|
||||
const writableFiles = new Set<string>(hashDiff.toWrite);
|
||||
const directlyChangedCount = writableFiles.size;
|
||||
|
||||
// Shadow-seed: for ADDED files, queryImporters returns 0 (the new
|
||||
// file has no IMPORTS rows in the pre-pipeline DB yet). But pre-
|
||||
// existing unchanged files may have IMPORTS edges whose module-
|
||||
// resolution claim the newcomer can steal under standard JS/TS
|
||||
// resolution (Bugbot review on PR #1479). For each added file we
|
||||
// derive the shadow candidates and, if the candidate was a known
|
||||
// file in the prior meta, seed it into the BFS frontier so its
|
||||
// importers — surfaced via queryImporters — get their CALLS edges
|
||||
// re-resolved against the new file. See shadow-candidates.ts for
|
||||
// the full pattern catalogue.
|
||||
const priorFileSet = new Set<string>(
|
||||
existingMeta?.fileHashes ? Object.keys(existingMeta.fileHashes) : [],
|
||||
);
|
||||
const shadowSeed: string[] = [];
|
||||
for (const added of hashDiff.added) {
|
||||
for (const cand of shadowCandidatesFor(added)) {
|
||||
if (priorFileSet.has(cand) && !writableFiles.has(cand)) {
|
||||
shadowSeed.push(cand);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
{
|
||||
let frontier: string[] = [...hashDiff.toWrite, ...hashDiff.deleted, ...shadowSeed];
|
||||
for (let depth = 0; depth < MAX_IMPORTER_BFS_DEPTH && frontier.length > 0; depth++) {
|
||||
const nextFrontier: string[] = [];
|
||||
for (const f of frontier) {
|
||||
try {
|
||||
const importers = await queryImporters(f);
|
||||
for (const i of importers) {
|
||||
if (!writableFiles.has(i)) {
|
||||
writableFiles.add(i);
|
||||
nextFrontier.push(i);
|
||||
}
|
||||
}
|
||||
} catch {
|
||||
/* per-file importer query failure → skip; correctness degrades on
|
||||
that branch, but DB stays writable. */
|
||||
}
|
||||
}
|
||||
frontier = nextFrontier;
|
||||
}
|
||||
}
|
||||
const importerExpansion = writableFiles.size - directlyChangedCount;
|
||||
if (importerExpansion > 0) {
|
||||
log(
|
||||
`Incremental: +${importerExpansion} importer(s) added to writable set ` +
|
||||
`(BFS depth ≤ ${MAX_IMPORTER_BFS_DEPTH}` +
|
||||
(shadowSeed.length > 0 ? `, ${shadowSeed.length} shadow-seed(s)` : '') +
|
||||
`)`,
|
||||
);
|
||||
}
|
||||
|
||||
// 1. Compute the EFFECTIVE write-set (Finding 1). Two layers,
|
||||
// composed:
|
||||
// (a) `writableFiles` — toWrite ∪ transitive importers of
|
||||
// changed/deleted files (the bounded BFS above, reading
|
||||
// IMPORTS from the pre-pipeline DB).
|
||||
// (b) `computeEffectiveWriteSet` — walks the NEW graph's
|
||||
// edges and pulls in any unchanged-side file that sits
|
||||
// on a writable-boundary-crossing edge (catches refined
|
||||
// cross-file CALLS edges that the pre-run DB couldn't
|
||||
// predict, e.g. a barrel re-export shifting `foo` from
|
||||
// B to D).
|
||||
// The composed set is the input to BOTH deleteNodesForFile
|
||||
// and extractChangedSubgraph — asymmetry between the two would
|
||||
// leave stale rows or PK-conflict at COPY time.
|
||||
const effectiveWriteSet = computeEffectiveWriteSet(pipelineResult.graph, writableFiles);
|
||||
// Deduped: deleted entries may already appear via importer-BFS
|
||||
// expansion (queryImporters can return a now-deleted path), which
|
||||
// would otherwise call deleteNodesForFile twice for the same file
|
||||
// (Bugbot LOW finding on PR #1479).
|
||||
const filesToDelete = [...new Set([...effectiveWriteSet, ...hashDiff.deleted])];
|
||||
for (let i = 0; i < filesToDelete.length; i++) {
|
||||
const f = filesToDelete[i];
|
||||
try {
|
||||
await deleteNodesForFile(f);
|
||||
} catch {
|
||||
/* file may not have rows (e.g. an unparseable file) — fine */
|
||||
}
|
||||
if (i % 20 === 0) {
|
||||
progress('lbug', 62, `Removing rows for changed files (${i}/${filesToDelete.length})...`);
|
||||
}
|
||||
}
|
||||
// 2. Drop graph-wide nodes (Community, Process). They'll be re-inserted
|
||||
// from the fresh pipeline output below. Required for the
|
||||
// "Leiden runs on the FULL graph" correctness invariant.
|
||||
await deleteAllCommunitiesAndProcesses();
|
||||
|
||||
// 3. Extract the changed subgraph from the FULL ctx.graph and write
|
||||
// only that. Unchanged-file rows in the DB stay untouched. Pass
|
||||
// the SAME effectiveWriteSet so the subgraph and the deletes
|
||||
// cover identical files (asymmetry would silently corrupt).
|
||||
const subgraph = extractChangedSubgraph(pipelineResult.graph, effectiveWriteSet);
|
||||
await loadGraphToLbug(subgraph, pipelineResult.repoPath, storagePath, (msg) => {
|
||||
lbugMsgCount++;
|
||||
const pct = Math.min(84, 65 + Math.round((lbugMsgCount / (lbugMsgCount + 10)) * 19));
|
||||
progress('lbug', pct, msg);
|
||||
});
|
||||
} else {
|
||||
// ── Full rebuild ───────────────────────────────────────────────
|
||||
await loadGraphToLbug(pipelineResult.graph, pipelineResult.repoPath, storagePath, (msg) => {
|
||||
lbugMsgCount++;
|
||||
const pct = Math.min(84, 60 + Math.round((lbugMsgCount / (lbugMsgCount + 10)) * 24));
|
||||
progress('lbug', pct, msg);
|
||||
});
|
||||
}
|
||||
|
||||
// ── Phase 3: FTS (85–90%) ─────────────────────────────────────────
|
||||
progress('fts', 85, 'Creating search indexes...');
|
||||
|
|
@ -310,6 +587,19 @@ export async function runFullAnalysis(
|
|||
progress('fts', 90, 'Search indexes ready');
|
||||
|
||||
// ── Phase 3.5: Re-insert cached embeddings ────────────────────────
|
||||
// Runs on BOTH the full-rebuild path and the incremental path:
|
||||
// - Full rebuild: DB was wiped, every cached row needs to come back.
|
||||
// - Incremental: changed-file rows were just deleted by
|
||||
// deleteNodesForFile (which cascades to their
|
||||
// embedding rows) — so their cached vectors need
|
||||
// to come back too. Unchanged-file rows still
|
||||
// exist; re-inserting their cached vectors would
|
||||
// PK-conflict, but the per-batch try/catch below
|
||||
// silently ignores those (matches the existing
|
||||
// "some may fail if node was removed, that's
|
||||
// fine" semantics). Bugbot review on PR #1479
|
||||
// flagged that gating this on `!isIncremental`
|
||||
// silently lost changed-file embeddings.
|
||||
if (cachedEmbeddings.length > 0) {
|
||||
const cachedDims = cachedEmbeddings[0].embedding.length;
|
||||
const { EMBEDDING_DIMS } = await import('./lbug/schema.js');
|
||||
|
|
@ -456,6 +746,12 @@ export async function runFullAnalysis(
|
|||
const effectiveSemanticMode =
|
||||
semanticMode ??
|
||||
(runtimeCapabilities.semanticMode === 'vector-index' ? 'vector-index' : 'exact-scan');
|
||||
|
||||
// Convert the post-run file-hash map to the on-disk Record<string,string>
|
||||
// shape consumed by RepoMeta.fileHashes.
|
||||
const newFileHashesRecord: Record<string, string> = {};
|
||||
for (const [k, v] of newFileHashes) newFileHashesRecord[k] = v;
|
||||
|
||||
const meta = {
|
||||
repoPath,
|
||||
lastCommit: currentCommit,
|
||||
|
|
@ -485,8 +781,33 @@ export async function runFullAnalysis(
|
|||
reason: runtimeCapabilities.reason,
|
||||
},
|
||||
},
|
||||
// Incremental-indexing fields. Populated for git repos so the next
|
||||
// analyze run can take the incremental DB-writeback path. Setting
|
||||
// incrementalInProgress to undefined explicitly clears any prior
|
||||
// dirty flag (full and incremental success paths converge here).
|
||||
schemaVersion: hasGitDir(repoPath) ? INCREMENTAL_SCHEMA_VERSION : undefined,
|
||||
fileHashes: hasGitDir(repoPath) ? newFileHashesRecord : undefined,
|
||||
incrementalInProgress: undefined as { startedAt: number; toWriteCount: number } | undefined,
|
||||
};
|
||||
await saveMeta(storagePath, meta);
|
||||
|
||||
// Persist the incremental parse cache for the next run. Wraps in
|
||||
// try/catch so a cache-write failure never breaks an otherwise
|
||||
// successful indexing run. Prune stale chunk-hash entries first so
|
||||
// the cache file size stays bounded across runs (chunks whose
|
||||
// composition no longer matches anything in the current scan are
|
||||
// dead weight; the parse phase populates `usedKeys` as it processes
|
||||
// chunks).
|
||||
try {
|
||||
const pruned = pruneCache(parseCache, parseCache.usedKeys);
|
||||
if (pruned > 0) {
|
||||
log(`Parse cache: pruned ${pruned} stale chunk entries`);
|
||||
}
|
||||
await saveParseCache(storagePath, parseCache);
|
||||
} catch (e) {
|
||||
log(`Warning: could not save parse cache (${(e as Error).message}); continuing.`);
|
||||
}
|
||||
|
||||
// Forward the --name alias and the registry-collision bypass bit.
|
||||
// `allowDuplicateName` is its own concern — independent from the
|
||||
// pipeline `force` above. The CLI maps it from
|
||||
|
|
|
|||
104
gitnexus/src/storage/file-hash.ts
Normal file
104
gitnexus/src/storage/file-hash.ts
Normal file
|
|
@ -0,0 +1,104 @@
|
|||
/**
|
||||
* Per-file content hashing for incremental DB writeback.
|
||||
*
|
||||
* On every analyze run we compute SHA-256 of every file's content and
|
||||
* store the map in meta.json. The next run compares disk against the
|
||||
* stored map and produces:
|
||||
* - `changed` — content differs (re-emit DB rows for this file)
|
||||
* - `added` — file is new on disk (insert DB rows)
|
||||
* - `deleted` — file was in last meta but no longer on disk (drop rows)
|
||||
*
|
||||
* The pipeline still parses every file (correctness invariant: cross-file
|
||||
* resolution needs full data). What this enables is a SELECTIVE DB
|
||||
* writeback: instead of wipe-and-reload of the whole graph (~50s of CSV
|
||||
* COPY on a 25K-node repo), we only delete-and-rewrite rows for the
|
||||
* changed/added/deleted set.
|
||||
*
|
||||
* See docs/superpowers/specs/2026-05-10-incremental-indexing-design.md
|
||||
* (Option B revision).
|
||||
*/
|
||||
|
||||
import { createHash } from 'crypto';
|
||||
import fs from 'fs/promises';
|
||||
import path from 'path';
|
||||
|
||||
/**
|
||||
* Compute SHA-256 of a single file. Returns null when the file can't be
|
||||
* read — caller treats that as "no signature, assume changed".
|
||||
*/
|
||||
export const computeFileHash = async (absPath: string): Promise<string | null> => {
|
||||
try {
|
||||
const buf = await fs.readFile(absPath);
|
||||
return createHash('sha256').update(buf).digest('hex');
|
||||
} catch {
|
||||
return null;
|
||||
}
|
||||
};
|
||||
|
||||
/**
|
||||
* Compute SHA-256 hashes for many files in parallel batches. Files that
|
||||
* fail to read are omitted from the result map.
|
||||
*/
|
||||
export const computeFileHashes = async (
|
||||
repoPath: string,
|
||||
relPaths: readonly string[],
|
||||
): Promise<Map<string, string>> => {
|
||||
const out = new Map<string, string>();
|
||||
const BATCH = 100;
|
||||
for (let i = 0; i < relPaths.length; i += BATCH) {
|
||||
const batch = relPaths.slice(i, i + BATCH);
|
||||
const results = await Promise.all(
|
||||
batch.map(async (rel) => {
|
||||
const h = await computeFileHash(path.join(repoPath, rel));
|
||||
return h ? ([rel, h] as const) : null;
|
||||
}),
|
||||
);
|
||||
for (const r of results) if (r) out.set(r[0], r[1]);
|
||||
}
|
||||
return out;
|
||||
};
|
||||
|
||||
/** Result of comparing the current on-disk hashes against stored ones. */
|
||||
export interface FileHashDiff {
|
||||
/** Files whose content hash differs from stored. */
|
||||
changed: string[];
|
||||
/** Files in the current scan that weren't in the stored map. */
|
||||
added: string[];
|
||||
/** Files in the stored map that aren't in the current scan. */
|
||||
deleted: string[];
|
||||
/** All files whose DB rows must be replaced (changed ∪ added). */
|
||||
toWrite: string[];
|
||||
}
|
||||
|
||||
/**
|
||||
* Diff a current hash map against a previously stored one.
|
||||
*
|
||||
* Sorted output so two runs produce identical diff arrays for the same
|
||||
* changes — useful for stable logging / equivalence checks.
|
||||
*/
|
||||
export const diffFileHashes = (
|
||||
current: ReadonlyMap<string, string>,
|
||||
stored: Readonly<Record<string, string>> | undefined,
|
||||
): FileHashDiff => {
|
||||
const storedMap = new Map<string, string>(stored ? Object.entries(stored) : []);
|
||||
const changed: string[] = [];
|
||||
const added: string[] = [];
|
||||
for (const [p, h] of current) {
|
||||
const prev = storedMap.get(p);
|
||||
if (prev === undefined) added.push(p);
|
||||
else if (prev !== h) changed.push(p);
|
||||
}
|
||||
const deleted: string[] = [];
|
||||
for (const p of storedMap.keys()) {
|
||||
if (!current.has(p)) deleted.push(p);
|
||||
}
|
||||
changed.sort();
|
||||
added.sort();
|
||||
deleted.sort();
|
||||
return {
|
||||
changed,
|
||||
added,
|
||||
deleted,
|
||||
toWrite: [...changed, ...added].sort(),
|
||||
};
|
||||
};
|
||||
213
gitnexus/src/storage/parse-cache.ts
Normal file
213
gitnexus/src/storage/parse-cache.ts
Normal file
|
|
@ -0,0 +1,213 @@
|
|||
/**
|
||||
* Chunk-level content-addressed parse cache.
|
||||
*
|
||||
* The pipeline always parses every file (correctness invariant: cross-file
|
||||
* resolution and downstream phases need full graph data). What this cache
|
||||
* does is skip the tree-sitter worker dispatch when a chunk's contents
|
||||
* haven't changed since the last run.
|
||||
*
|
||||
* Granularity: chunk-level. The parse phase chunks files into ~20MB byte
|
||||
* budgets. The cache key is `sha256(joined(filePath:contentHash for each
|
||||
* file in the chunk, sorted))`. A change to a single file invalidates only
|
||||
* that file's chunk — typically 1 of ~50 chunks on a 1000-file repo.
|
||||
*
|
||||
* Why not per-file:
|
||||
* - Workers process sub-batches and emit aggregated `ParseWorkerResult`s.
|
||||
* Splitting back to per-file would require reworking the worker contract.
|
||||
* - Chunk-level invalidation gives a useful speedup floor (98% on a single
|
||||
* 1-of-50 invalidated chunk) without touching the worker.
|
||||
*
|
||||
* Survives `--force` because it's content-addressed: the same bytes always
|
||||
* produce the same key. `--force` only matters for the LadybugDB writeback;
|
||||
* the cache itself is always safe to reuse.
|
||||
*/
|
||||
|
||||
import { createHash } from 'crypto';
|
||||
import { createRequire } from 'module';
|
||||
import fs from 'fs/promises';
|
||||
import path from 'path';
|
||||
import { fileURLToPath } from 'url';
|
||||
import type { ParseWorkerResult } from '../core/ingestion/workers/parse-worker.js';
|
||||
|
||||
/**
|
||||
* Cache version composed of:
|
||||
* - A schema bump knob (`SCHEMA_BUMP`) for hand-controlled invalidation
|
||||
* when ParseWorkerResult shape or upstream parse semantics change.
|
||||
* - The current `gitnexus` npm package version, read at module load.
|
||||
* Any release that ships an updated tree-sitter grammar or revised
|
||||
* extractor logic implies a version bump in package.json, which
|
||||
* automatically invalidates the on-disk cache. Without this, a user
|
||||
* running `npm i -g gitnexus@latest` after a parser-affecting
|
||||
* release would silently replay pre-upgrade ParseWorkerResults
|
||||
* against the new graph schema (Bugbot/Claude review on #1479).
|
||||
*
|
||||
* On version mismatch, `loadParseCache` returns an empty cache and the
|
||||
* next save overwrites the on-disk file with the new version baked in.
|
||||
*/
|
||||
const SCHEMA_BUMP = 1;
|
||||
const GITNEXUS_PKG_VERSION = (() => {
|
||||
try {
|
||||
// package.json sits at gitnexus/package.json — two levels up from
|
||||
// gitnexus/src/storage/parse-cache.ts (or its dist/ equivalent).
|
||||
const here = path.dirname(fileURLToPath(import.meta.url));
|
||||
const candidates = [
|
||||
path.join(here, '..', '..', 'package.json'), // src/storage → gitnexus/
|
||||
path.join(here, '..', '..', '..', 'package.json'), // dist/storage → gitnexus/
|
||||
];
|
||||
const requireCJS = createRequire(import.meta.url);
|
||||
for (const c of candidates) {
|
||||
try {
|
||||
const pkg = requireCJS(c);
|
||||
if (typeof pkg?.version === 'string') return pkg.version;
|
||||
} catch {
|
||||
/* try next candidate */
|
||||
}
|
||||
}
|
||||
} catch {
|
||||
/* fall through to fallback */
|
||||
}
|
||||
return '0.0.0-unknown';
|
||||
})();
|
||||
export const PARSE_CACHE_VERSION = `${SCHEMA_BUMP}+${GITNEXUS_PKG_VERSION}`;
|
||||
|
||||
const CACHE_FILENAME = 'parse-cache.json';
|
||||
|
||||
/** On-disk shape. */
|
||||
interface ParseCacheFile {
|
||||
version: string;
|
||||
/** key = chunk hash (hex) → cached chunk result list. */
|
||||
entries: Record<string, ParseWorkerResult[]>;
|
||||
}
|
||||
|
||||
/** Runtime view: keyed Map for fast lookup; mutated in place during a run. */
|
||||
export interface ParseCache {
|
||||
version: string;
|
||||
entries: Map<string, ParseWorkerResult[]>;
|
||||
/**
|
||||
* Hashes referenced (hit OR miss-and-stored) by the current run.
|
||||
* The parse phase populates this as it processes chunks; the orchestrator
|
||||
* uses it as input to `pruneCache` before saving so entries that no
|
||||
* longer correspond to any chunk in the current scan are discarded.
|
||||
* Transient — never serialized to disk.
|
||||
*/
|
||||
usedKeys: Set<string>;
|
||||
}
|
||||
|
||||
/** SHA-256 hex of a single string or buffer. */
|
||||
const sha256Hex = (input: Buffer | string): string =>
|
||||
createHash('sha256')
|
||||
.update(typeof input === 'string' ? Buffer.from(input) : input)
|
||||
.digest('hex');
|
||||
|
||||
/** Stable hash of a single file's contents — used by callers to compose a chunk hash. */
|
||||
export const fileContentHash = (content: Buffer | string): string => sha256Hex(content);
|
||||
|
||||
/**
|
||||
* Compute the canonical cache key for a chunk's contents.
|
||||
*
|
||||
* `entries` is the list of (filePath, file content hash) for every file
|
||||
* in the chunk. We sort by filePath before hashing so chunks composed of
|
||||
* the same files in different order produce the same key.
|
||||
*/
|
||||
export const computeChunkHash = (
|
||||
entries: Array<{ filePath: string; contentHash: string }>,
|
||||
): string => {
|
||||
const sorted = [...entries].sort((a, b) => (a.filePath < b.filePath ? -1 : 1));
|
||||
const joined = sorted.map((e) => `${e.filePath}:${e.contentHash}`).join('\n');
|
||||
return sha256Hex(joined);
|
||||
};
|
||||
|
||||
/**
|
||||
* JSON replacer that round-trips Map/Set instances through plain JSON.
|
||||
*
|
||||
* `ParseWorkerResult.parsedFiles[*].scopes[*].typeBindings` is a
|
||||
* `ReadonlyMap<string, TypeRef>`; without this transform it serializes
|
||||
* to `{}` and downstream code that iterates / `.get()`s on it crashes
|
||||
* with "is not iterable". Applied symmetrically by `mapReviver` on
|
||||
* load so the in-memory shape stays Map-typed.
|
||||
*/
|
||||
const MAP_TAG = '__$mapEntries$__';
|
||||
const SET_TAG = '__$setValues$__';
|
||||
|
||||
const mapReplacer = (_key: string, value: unknown): unknown => {
|
||||
if (value instanceof Map) return { [MAP_TAG]: Array.from(value.entries()) };
|
||||
if (value instanceof Set) return { [SET_TAG]: Array.from(value.values()) };
|
||||
return value;
|
||||
};
|
||||
|
||||
const mapReviver = (_key: string, value: unknown): unknown => {
|
||||
if (value && typeof value === 'object') {
|
||||
const v = value as Record<string, unknown>;
|
||||
if (Array.isArray(v[MAP_TAG])) return new Map(v[MAP_TAG] as [unknown, unknown][]);
|
||||
if (Array.isArray(v[SET_TAG])) return new Set(v[SET_TAG] as unknown[]);
|
||||
}
|
||||
return value;
|
||||
};
|
||||
|
||||
/**
|
||||
* Load the parse cache. Returns an empty cache on any failure (missing
|
||||
* file, corrupt JSON, version mismatch). Never throws on a normal load.
|
||||
*/
|
||||
export const loadParseCache = async (storagePath: string): Promise<ParseCache> => {
|
||||
const cachePath = path.join(storagePath, CACHE_FILENAME);
|
||||
try {
|
||||
const raw = await fs.readFile(cachePath, 'utf-8');
|
||||
const data = JSON.parse(raw, mapReviver) as ParseCacheFile;
|
||||
if (
|
||||
typeof data !== 'object' ||
|
||||
data === null ||
|
||||
data.version !== PARSE_CACHE_VERSION ||
|
||||
typeof data.entries !== 'object' ||
|
||||
data.entries === null
|
||||
) {
|
||||
return emptyCache();
|
||||
}
|
||||
const entries = new Map<string, ParseWorkerResult[]>();
|
||||
for (const [k, v] of Object.entries(data.entries)) {
|
||||
if (Array.isArray(v)) entries.set(k, v as ParseWorkerResult[]);
|
||||
}
|
||||
return { version: PARSE_CACHE_VERSION, entries, usedKeys: new Set<string>() };
|
||||
} catch {
|
||||
return emptyCache();
|
||||
}
|
||||
};
|
||||
|
||||
/**
|
||||
* Persist the cache to disk atomically (write-and-rename) so a crash
|
||||
* mid-write doesn't leave a corrupt file.
|
||||
*/
|
||||
export const saveParseCache = async (storagePath: string, cache: ParseCache): Promise<void> => {
|
||||
await fs.mkdir(storagePath, { recursive: true });
|
||||
const cachePath = path.join(storagePath, CACHE_FILENAME);
|
||||
const tmpPath = `${cachePath}.tmp`;
|
||||
const out: ParseCacheFile = {
|
||||
version: cache.version,
|
||||
entries: Object.fromEntries(cache.entries),
|
||||
};
|
||||
// Compact JSON; this file can be tens of MB on a large repo and pretty-
|
||||
// printing roughly doubles size for no value.
|
||||
await fs.writeFile(tmpPath, JSON.stringify(out, mapReplacer), 'utf-8');
|
||||
await fs.rename(tmpPath, cachePath);
|
||||
};
|
||||
|
||||
/**
|
||||
* Drop entries whose hashes are not in `usedHashes`. Called at the end
|
||||
* of a run so chunks that no longer correspond to any current chunk
|
||||
* don't keep their stale entries forever.
|
||||
*/
|
||||
export const pruneCache = (cache: ParseCache, usedHashes: ReadonlySet<string>): number => {
|
||||
let removed = 0;
|
||||
for (const k of cache.entries.keys()) {
|
||||
if (!usedHashes.has(k)) {
|
||||
cache.entries.delete(k);
|
||||
removed++;
|
||||
}
|
||||
}
|
||||
return removed;
|
||||
};
|
||||
|
||||
const emptyCache = (): ParseCache => ({
|
||||
version: PARSE_CACHE_VERSION,
|
||||
entries: new Map<string, ParseWorkerResult[]>(),
|
||||
usedKeys: new Set<string>(),
|
||||
});
|
||||
|
|
@ -71,8 +71,40 @@ export interface RepoMeta {
|
|||
processes?: number;
|
||||
embeddings?: number;
|
||||
};
|
||||
/**
|
||||
* Bumped whenever incremental-indexing invariants change in an
|
||||
* incompatible way (delete-and-rewrite logic, subgraph extraction,
|
||||
* graph-wide node handling). On mismatch, runFullAnalysis forces a
|
||||
* full rebuild rather than risk an inconsistent incremental update.
|
||||
*/
|
||||
schemaVersion?: number;
|
||||
/**
|
||||
* SHA-256 of every file's content at the time of the last successful
|
||||
* indexing run. The next run computes current hashes and diffs against
|
||||
* this map to determine which files' DB rows must be replaced.
|
||||
* Map keys are repo-relative paths.
|
||||
*/
|
||||
fileHashes?: Record<string, string>;
|
||||
/**
|
||||
* Crash-recovery dirty flag. Written to meta.json BEFORE any
|
||||
* destructive DB mutation in an incremental run; cleared on success
|
||||
* by overwriting meta.json. If a run crashes between, the next run
|
||||
* sees the flag and forces a full rebuild — the cheapest path back
|
||||
* to a known-good index.
|
||||
*/
|
||||
incrementalInProgress?: {
|
||||
/** When the incremental run started (epoch ms). */
|
||||
startedAt: number;
|
||||
/** Number of files in the writable set, for diagnostic logs. */
|
||||
toWriteCount: number;
|
||||
};
|
||||
}
|
||||
|
||||
/**
|
||||
* Bumped whenever incremental-indexing invariants change incompatibly.
|
||||
*/
|
||||
export const INCREMENTAL_SCHEMA_VERSION = 1;
|
||||
|
||||
export interface IndexedRepo {
|
||||
repoPath: string;
|
||||
storagePath: string;
|
||||
|
|
@ -186,12 +218,23 @@ export const loadMeta = async (storagePath: string): Promise<RepoMeta | null> =>
|
|||
};
|
||||
|
||||
/**
|
||||
* Save metadata to storage
|
||||
* Save metadata to storage.
|
||||
*
|
||||
* Atomic via tmp-file + rename (matches `saveParseCache`'s pattern). The
|
||||
* `incrementalInProgress` dirty flag travels through this file — a crash
|
||||
* mid-write would leave a corrupt `meta.json` that the next run's
|
||||
* `loadMeta` would silently treat as "no prior index", losing the dirty
|
||||
* flag and skipping the recovery full-rebuild. Write-and-rename rules
|
||||
* that out: the rename is atomic on POSIX and on Windows (`fs.rename`
|
||||
* on `node:fs/promises` uses `MoveFileEx(REPLACE_EXISTING)`), so either
|
||||
* the old or the new file is observed at every moment.
|
||||
*/
|
||||
export const saveMeta = async (storagePath: string, meta: RepoMeta): Promise<void> => {
|
||||
await fs.mkdir(storagePath, { recursive: true });
|
||||
const metaPath = path.join(storagePath, 'meta.json');
|
||||
await fs.writeFile(metaPath, JSON.stringify(meta, null, 2), 'utf-8');
|
||||
const tmpPath = `${metaPath}.tmp`;
|
||||
await fs.writeFile(tmpPath, JSON.stringify(meta, null, 2), 'utf-8');
|
||||
await fs.rename(tmpPath, metaPath);
|
||||
};
|
||||
|
||||
/**
|
||||
|
|
|
|||
|
|
@ -1,10 +1,25 @@
|
|||
package com.example.app;
|
||||
|
||||
import com.example.util.Logger;
|
||||
import com.example.util.Formatter;
|
||||
|
||||
public class Main {
|
||||
public void run() {
|
||||
Logger logger = new Logger();
|
||||
logger.record("hello", "world", "test");
|
||||
|
||||
Formatter fmt = new Formatter();
|
||||
// 2-arg call: satisfies fixed prefix (level) + 1 vararg
|
||||
fmt.format(1, "hello");
|
||||
// 3-arg call: satisfies fixed prefix (level) + 2 varargs
|
||||
fmt.format(2, "hello", "world");
|
||||
}
|
||||
|
||||
public void badCall() {
|
||||
Formatter fmt = new Formatter();
|
||||
// 0-arg call: does NOT satisfy the required fixed prefix (int level)
|
||||
// This should be rejected by arity — no CALLS edge to format
|
||||
fmt.format();
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,8 @@
|
|||
package com.example.util;
|
||||
|
||||
public class Formatter {
|
||||
/** Varargs with a required fixed prefix — 0-arg calls should be rejected. */
|
||||
public void format(int level, String... args) {
|
||||
for (String a : args) System.out.println(level + ": " + a);
|
||||
}
|
||||
}
|
||||
10
gitnexus/test/fixtures/lang-resolution/java-wildcard-import/com/example/app/Main.java
vendored
Normal file
10
gitnexus/test/fixtures/lang-resolution/java-wildcard-import/com/example/app/Main.java
vendored
Normal file
|
|
@ -0,0 +1,10 @@
|
|||
package com.example.app;
|
||||
|
||||
import com.example.models.*;
|
||||
|
||||
public class Main {
|
||||
public void run() {
|
||||
User user = new User();
|
||||
user.save();
|
||||
}
|
||||
}
|
||||
7
gitnexus/test/fixtures/lang-resolution/java-wildcard-import/com/example/models/Order.java
vendored
Normal file
7
gitnexus/test/fixtures/lang-resolution/java-wildcard-import/com/example/models/Order.java
vendored
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
package com.example.models;
|
||||
|
||||
public class Order {
|
||||
public void submit() {
|
||||
System.out.println("submitting order");
|
||||
}
|
||||
}
|
||||
7
gitnexus/test/fixtures/lang-resolution/java-wildcard-import/com/example/models/User.java
vendored
Normal file
7
gitnexus/test/fixtures/lang-resolution/java-wildcard-import/com/example/models/User.java
vendored
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
package com.example.models;
|
||||
|
||||
public class User {
|
||||
public void save() {
|
||||
System.out.println("saving user");
|
||||
}
|
||||
}
|
||||
|
|
@ -2,10 +2,13 @@
|
|||
|
||||
namespace App\Services;
|
||||
|
||||
use function App\Utils\OneArg\log;
|
||||
use function App\Utils\ZeroArg\log as zero_log;
|
||||
use function App\Utils\OneArg\write_audit;
|
||||
use function App\Utils\ZeroArg\write_audit as zero_write_audit;
|
||||
|
||||
function create_user(): string
|
||||
{
|
||||
// Two visible write_audit candidates (different arities). Arity narrowing
|
||||
// must pick the 1-arg OneArg version. This validates that visibility +
|
||||
// arity together correctly disambiguate.
|
||||
return write_audit('hello');
|
||||
}
|
||||
|
|
|
|||
113
gitnexus/test/fixtures/lang-resolution/php-dynamic-calls/app/Services/Dynamic.php
vendored
Normal file
113
gitnexus/test/fixtures/lang-resolution/php-dynamic-calls/app/Services/Dynamic.php
vendored
Normal file
|
|
@ -0,0 +1,113 @@
|
|||
<?php
|
||||
|
||||
namespace App\Services;
|
||||
|
||||
/**
|
||||
* Exercises every dynamic PHP call/access shape that the tree-sitter
|
||||
* grammar should NOT capture as a resolvable reference. The negative
|
||||
* regression suite asserts zero CALLS edges from `Dynamic::*` to any
|
||||
* `Targets::*` method whose name only appears in dynamic position.
|
||||
*
|
||||
* Findings 1-7 of the adversarial review of PR #1497 confirmed via
|
||||
* grammar inspection that these patterns produce zero captures; this
|
||||
* fixture + test pair locks that invariant in regression coverage so
|
||||
* a future query.ts edit cannot silently break it.
|
||||
*/
|
||||
class Dynamic
|
||||
{
|
||||
public function memberCallDynamicName(Targets $obj): void
|
||||
{
|
||||
// $obj->$method() — dynamic method name via variable_name node.
|
||||
// Query pattern requires `name: (name)` so this is not captured.
|
||||
$method = 'dynamicProcess';
|
||||
$obj->$method();
|
||||
}
|
||||
|
||||
public function memberCallBraceDynamicName(Targets $obj): void
|
||||
{
|
||||
// $obj->{$method}() — brace-syntax variant of the above.
|
||||
$method = 'dynamicBrace';
|
||||
$obj->{$method}();
|
||||
}
|
||||
|
||||
public function scopedCallDynamicMethodName(): void
|
||||
{
|
||||
// ClassName::$method() — dynamic method name on static dispatch.
|
||||
$method = 'dynamicHandle';
|
||||
Targets::$method();
|
||||
}
|
||||
|
||||
public function scopedCallVariableClassNameStaticMethod($className): void
|
||||
{
|
||||
// $className::method() — class-name is an untyped parameter (no
|
||||
// type hint, no string-literal assignment that could be picked up
|
||||
// by a future type-binding heuristic). Receiver IS captured but
|
||||
// resolution falls through because $className has no class type
|
||||
// binding in scope. The unresolved-receiver fallback also doesn't
|
||||
// fire because `dynamicStaticMethod` is unique workspace-wide AND
|
||||
// exact-arity narrowing in U4 would still match — meaning the
|
||||
// ONLY thing keeping the edge count at zero today is the absence
|
||||
// of any type binding for the receiver.
|
||||
$className::dynamicStaticMethod();
|
||||
}
|
||||
|
||||
public function scopedCallDynamicClassAndMethodName(): void
|
||||
{
|
||||
// $className::$method() — both dynamic.
|
||||
$className = 'App\\Services\\Targets';
|
||||
$method = 'dynamicScopedDynName';
|
||||
$className::$method();
|
||||
}
|
||||
|
||||
public function callUserFuncVariableCallable($callable): void
|
||||
{
|
||||
// call_user_func($callable, ...) — resolver is structural-only
|
||||
// and never inspects argument values to infer the callable.
|
||||
// The literal `call_user_func` itself is an unresolved built-in.
|
||||
call_user_func($callable);
|
||||
}
|
||||
|
||||
public function callUserFuncArrayVariable($callable, $args): void
|
||||
{
|
||||
// call_user_func_array($callable, $args) — unknown-arity variant.
|
||||
call_user_func_array($callable, $args);
|
||||
}
|
||||
|
||||
public function callUserFuncStringCallable(): void
|
||||
{
|
||||
// 'Class::method' string-callable form — argument is a string
|
||||
// literal, never reaches the function: child of function_call_expression.
|
||||
call_user_func('App\\Services\\Targets::dynamicCallableMethod');
|
||||
}
|
||||
|
||||
public function callUserFuncArrayObjectCallable(Targets $obj): void
|
||||
{
|
||||
// [$obj, 'method'] array-callable form — array is an argument
|
||||
// value, not the function: child.
|
||||
call_user_func([$obj, 'dynamicArrayCallableMethod']);
|
||||
}
|
||||
|
||||
public function callUserFuncArrayClassNameCallable(): void
|
||||
{
|
||||
// ['Class', 'method'] array-callable with class-name string.
|
||||
call_user_func(['App\\Services\\Targets', 'dynamicArrayClassCallableMethod']);
|
||||
}
|
||||
|
||||
public function dynamicPropertyRead(Targets $obj): string
|
||||
{
|
||||
// $obj->$prop — dynamic property read. No read-access property
|
||||
// capture pattern exists in query.ts at all (Finding 2).
|
||||
$prop = 'dynamicProp';
|
||||
return $obj->$prop;
|
||||
}
|
||||
|
||||
public function sanityStaticCall(Targets $obj): void
|
||||
{
|
||||
// The fixture's deliberate sanity-check call. THIS one DOES emit
|
||||
// a CALLS edge — if the assertion that this edge exists ever
|
||||
// fails, the test infra is broken, not the dynamic-dispatch
|
||||
// suppression. Without this, every zero-edge assertion above
|
||||
// would pass even if the pipeline never emitted any edges at all.
|
||||
$obj->sanityStaticallyNamedTarget();
|
||||
}
|
||||
}
|
||||
16
gitnexus/test/fixtures/lang-resolution/php-dynamic-calls/app/Services/OtherTargets.php
vendored
Normal file
16
gitnexus/test/fixtures/lang-resolution/php-dynamic-calls/app/Services/OtherTargets.php
vendored
Normal file
|
|
@ -0,0 +1,16 @@
|
|||
<?php
|
||||
|
||||
namespace App\Services;
|
||||
|
||||
/**
|
||||
* Second attractor class. Its purpose is to provide a NON-UNIQUE
|
||||
* workspace-wide name for `dynamicStaticMethod`, so that the
|
||||
* phpEmitUnresolvedReceiverEdges 0.6-confidence fallback cannot fire
|
||||
* for the `$className::dynamicStaticMethod()` site in Dynamic.php.
|
||||
* That isolates the dynamic-receiver test from the U4 concern
|
||||
* (Finding 8 — unresolved-receiver fallback tightening).
|
||||
*/
|
||||
class OtherTargets
|
||||
{
|
||||
public static function dynamicStaticMethod(): void {}
|
||||
}
|
||||
36
gitnexus/test/fixtures/lang-resolution/php-dynamic-calls/app/Services/Targets.php
vendored
Normal file
36
gitnexus/test/fixtures/lang-resolution/php-dynamic-calls/app/Services/Targets.php
vendored
Normal file
|
|
@ -0,0 +1,36 @@
|
|||
<?php
|
||||
|
||||
namespace App\Services;
|
||||
|
||||
/**
|
||||
* Attractors: every method name here is unique workspace-wide so that if
|
||||
* the dynamic-dispatch suppression in the query / resolver layer ever
|
||||
* regresses, the false-positive CALLS edges would surface against these
|
||||
* targets.
|
||||
*/
|
||||
class Targets
|
||||
{
|
||||
public function dynamicProcess(): void {}
|
||||
|
||||
public function dynamicHandle(): void {}
|
||||
|
||||
public function dynamicBrace(): void {}
|
||||
|
||||
public static function dynamicStaticMethod(): void {}
|
||||
|
||||
public static function dynamicScopedDynName(): void {}
|
||||
|
||||
public function dynamicCallableMethod(): void {}
|
||||
|
||||
public function dynamicArrayCallableMethod(): void {}
|
||||
|
||||
public function dynamicArrayClassCallableMethod(): void {}
|
||||
|
||||
public string $dynamicProp = '';
|
||||
|
||||
/**
|
||||
* Sanity-check target: the fixture's one non-dynamic call DOES reach
|
||||
* this method, proving the test infra emits CALLS edges normally.
|
||||
*/
|
||||
public function sanityStaticallyNamedTarget(): void {}
|
||||
}
|
||||
5
gitnexus/test/fixtures/lang-resolution/php-dynamic-calls/composer.json
vendored
Normal file
5
gitnexus/test/fixtures/lang-resolution/php-dynamic-calls/composer.json
vendored
Normal file
|
|
@ -0,0 +1,5 @@
|
|||
{
|
||||
"autoload": {
|
||||
"psr-4": { "App\\": "app/" }
|
||||
}
|
||||
}
|
||||
8
gitnexus/test/fixtures/lang-resolution/php-fqn-cross-namespace/app/Models/User.php
vendored
Normal file
8
gitnexus/test/fixtures/lang-resolution/php-fqn-cross-namespace/app/Models/User.php
vendored
Normal file
|
|
@ -0,0 +1,8 @@
|
|||
<?php
|
||||
namespace App\Models;
|
||||
|
||||
class User {
|
||||
public function record(): string {
|
||||
return 'App\\Models\\User::record';
|
||||
}
|
||||
}
|
||||
8
gitnexus/test/fixtures/lang-resolution/php-fqn-cross-namespace/app/Other/User.php
vendored
Normal file
8
gitnexus/test/fixtures/lang-resolution/php-fqn-cross-namespace/app/Other/User.php
vendored
Normal file
|
|
@ -0,0 +1,8 @@
|
|||
<?php
|
||||
namespace App\Other;
|
||||
|
||||
class User {
|
||||
public function record(): string {
|
||||
return 'App\\Other\\User::record';
|
||||
}
|
||||
}
|
||||
25
gitnexus/test/fixtures/lang-resolution/php-fqn-cross-namespace/app/Services/Service.php
vendored
Normal file
25
gitnexus/test/fixtures/lang-resolution/php-fqn-cross-namespace/app/Services/Service.php
vendored
Normal file
|
|
@ -0,0 +1,25 @@
|
|||
<?php
|
||||
namespace App\Services;
|
||||
|
||||
use App\Models\User;
|
||||
|
||||
// Two `User` classes exist in the workspace: App\Models\User and App\Other\User.
|
||||
// The `use App\Models\User` import binds the simple name `User` to App\Models\User.
|
||||
//
|
||||
// The `save` method uses a fully-qualified type hint `\App\Other\User` — PHP
|
||||
// runtime semantics: the leading backslash means "absolute namespace path",
|
||||
// so this parameter is always App\Other\User, even though the simple `User`
|
||||
// elsewhere in this file is App\Models\User.
|
||||
//
|
||||
// CALLS edges from `$u->record()` MUST resolve to app/Other/User.php::record,
|
||||
// NOT app/Models/User.php::record. The `saveLocal` method exercises the
|
||||
// simple-name path as a control — `User` here is the imported App\Models\User.
|
||||
class Service {
|
||||
public function save(\App\Other\User $u): void {
|
||||
$u->record();
|
||||
}
|
||||
|
||||
public function saveLocal(User $u): void {
|
||||
$u->record();
|
||||
}
|
||||
}
|
||||
7
gitnexus/test/fixtures/lang-resolution/php-fqn-cross-namespace/composer.json
vendored
Normal file
7
gitnexus/test/fixtures/lang-resolution/php-fqn-cross-namespace/composer.json
vendored
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
{
|
||||
"autoload": {
|
||||
"psr-4": {
|
||||
"App\\": "app/"
|
||||
}
|
||||
}
|
||||
}
|
||||
10
gitnexus/test/fixtures/lang-resolution/php-mro-arity-mismatch/app/Models/ChildModel.php
vendored
Normal file
10
gitnexus/test/fixtures/lang-resolution/php-mro-arity-mismatch/app/Models/ChildModel.php
vendored
Normal file
|
|
@ -0,0 +1,10 @@
|
|||
<?php
|
||||
|
||||
namespace App\Models;
|
||||
|
||||
class ChildModel extends ParentModel
|
||||
{
|
||||
public function method(int $a, int $b): bool { return true; }
|
||||
|
||||
public function compat(int $a): bool { return true; }
|
||||
}
|
||||
8
gitnexus/test/fixtures/lang-resolution/php-mro-arity-mismatch/app/Models/Orphan.php
vendored
Normal file
8
gitnexus/test/fixtures/lang-resolution/php-mro-arity-mismatch/app/Models/Orphan.php
vendored
Normal file
|
|
@ -0,0 +1,8 @@
|
|||
<?php
|
||||
|
||||
namespace App\Models;
|
||||
|
||||
class Orphan
|
||||
{
|
||||
public function method(int $a, int $b): bool { return true; }
|
||||
}
|
||||
10
gitnexus/test/fixtures/lang-resolution/php-mro-arity-mismatch/app/Models/ParentModel.php
vendored
Normal file
10
gitnexus/test/fixtures/lang-resolution/php-mro-arity-mismatch/app/Models/ParentModel.php
vendored
Normal file
|
|
@ -0,0 +1,10 @@
|
|||
<?php
|
||||
|
||||
namespace App\Models;
|
||||
|
||||
class ParentModel
|
||||
{
|
||||
public function method(int $a): bool { return true; }
|
||||
|
||||
public function compat(int $a): bool { return true; }
|
||||
}
|
||||
42
gitnexus/test/fixtures/lang-resolution/php-mro-arity-mismatch/app/Services/Caller.php
vendored
Normal file
42
gitnexus/test/fixtures/lang-resolution/php-mro-arity-mismatch/app/Services/Caller.php
vendored
Normal file
|
|
@ -0,0 +1,42 @@
|
|||
<?php
|
||||
|
||||
namespace App\Services;
|
||||
|
||||
use App\Models\ChildModel;
|
||||
use App\Models\Orphan;
|
||||
|
||||
class Caller
|
||||
{
|
||||
public function callIncompatible(): void
|
||||
{
|
||||
// ChildModel::method takes 2 args; ParentModel::method takes 1.
|
||||
// Class-name receiver -> hits Case 2 (findClassBindingInScope) in
|
||||
// receiver-bound-calls.ts.
|
||||
// Pre-fix bug: MRO walk emits a false CALLS edge to ParentModel::method
|
||||
// because Case 2 used `continue` on arity mismatch and fell through.
|
||||
// Post-fix: zero edges (PHP throws ArgumentCountError at runtime).
|
||||
ChildModel::method(1);
|
||||
}
|
||||
|
||||
public function callCompatible(): void
|
||||
{
|
||||
// Happy path: ChildModel::compat takes 1 arg; matches call site.
|
||||
ChildModel::compat(1);
|
||||
}
|
||||
|
||||
public function callNoParent(): void
|
||||
{
|
||||
// Orphan::method takes 2 args; called with 1; no parent class exists.
|
||||
// Pre-fix: same Case 2 bug — the loop exhausts with memberDef cleared,
|
||||
// BUT with `continue` the loop simply ends after one iteration since
|
||||
// the chain has only one entry; no edge would have been emitted here
|
||||
// even pre-fix. Post-fix: same — zero edges. Documents the boundary.
|
||||
Orphan::method(1);
|
||||
}
|
||||
|
||||
public function callMostDerivedHappy(): void
|
||||
{
|
||||
// Happy path: ChildModel::method takes 2 args; matches call site.
|
||||
ChildModel::method(1, 2);
|
||||
}
|
||||
}
|
||||
5
gitnexus/test/fixtures/lang-resolution/php-mro-arity-mismatch/composer.json
vendored
Normal file
5
gitnexus/test/fixtures/lang-resolution/php-mro-arity-mismatch/composer.json
vendored
Normal file
|
|
@ -0,0 +1,5 @@
|
|||
{
|
||||
"autoload": {
|
||||
"psr-4": { "App\\": "app/" }
|
||||
}
|
||||
}
|
||||
8
gitnexus/test/fixtures/lang-resolution/php-namespace-fallback-isolation/composer.json
vendored
Normal file
8
gitnexus/test/fixtures/lang-resolution/php-namespace-fallback-isolation/composer.json
vendored
Normal file
|
|
@ -0,0 +1,8 @@
|
|||
{
|
||||
"autoload": {
|
||||
"psr-4": {
|
||||
"App\\": "src/App/",
|
||||
"Vendor\\": "src/Vendor/"
|
||||
}
|
||||
}
|
||||
}
|
||||
19
gitnexus/test/fixtures/lang-resolution/php-namespace-fallback-isolation/src/App/Caller.php
vendored
Normal file
19
gitnexus/test/fixtures/lang-resolution/php-namespace-fallback-isolation/src/App/Caller.php
vendored
Normal file
|
|
@ -0,0 +1,19 @@
|
|||
<?php
|
||||
namespace App;
|
||||
|
||||
use function Vendor\Utils\format as vendorFormat;
|
||||
|
||||
class Caller {
|
||||
public function callNoImport(): string {
|
||||
// No use function for `format`. Caller is in \App, candidates live
|
||||
// in \App\Utils and \Vendor\Utils. PHP runtime: Call to undefined
|
||||
// function App\format. Resolver must emit NO edge.
|
||||
return format('x');
|
||||
}
|
||||
|
||||
public function callImported(): string {
|
||||
// Imported via `use function Vendor\Utils\format as vendorFormat`.
|
||||
// Resolver must emit an edge to Vendor\Utils\format.
|
||||
return vendorFormat('x', 80);
|
||||
}
|
||||
}
|
||||
10
gitnexus/test/fixtures/lang-resolution/php-namespace-fallback-isolation/src/App/Utils/Caller.php
vendored
Normal file
10
gitnexus/test/fixtures/lang-resolution/php-namespace-fallback-isolation/src/App/Utils/Caller.php
vendored
Normal file
|
|
@ -0,0 +1,10 @@
|
|||
<?php
|
||||
namespace App\Utils;
|
||||
|
||||
class Caller {
|
||||
public function callSameNamespace(): string {
|
||||
// Caller is in \App\Utils, calls `format('x')`. Same-namespace
|
||||
// resolution: emit edge to \App\Utils\format.
|
||||
return format('x');
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
<?php
|
||||
namespace App\Utils;
|
||||
|
||||
function format(string $s): string {
|
||||
return $s;
|
||||
}
|
||||
|
|
@ -0,0 +1,6 @@
|
|||
<?php
|
||||
namespace Vendor\Utils;
|
||||
|
||||
function format(string $s, int $width): string {
|
||||
return str_pad($s, $width);
|
||||
}
|
||||
8
gitnexus/test/fixtures/lang-resolution/php-parent-vs-trait/app/Auditable.php
vendored
Normal file
8
gitnexus/test/fixtures/lang-resolution/php-parent-vs-trait/app/Auditable.php
vendored
Normal file
|
|
@ -0,0 +1,8 @@
|
|||
<?php
|
||||
namespace App;
|
||||
|
||||
trait Auditable {
|
||||
public function record(): string {
|
||||
return 'trait';
|
||||
}
|
||||
}
|
||||
8
gitnexus/test/fixtures/lang-resolution/php-parent-vs-trait/app/Base.php
vendored
Normal file
8
gitnexus/test/fixtures/lang-resolution/php-parent-vs-trait/app/Base.php
vendored
Normal file
|
|
@ -0,0 +1,8 @@
|
|||
<?php
|
||||
namespace App;
|
||||
|
||||
class Base {
|
||||
public function record(): string {
|
||||
return 'base';
|
||||
}
|
||||
}
|
||||
14
gitnexus/test/fixtures/lang-resolution/php-parent-vs-trait/app/Child.php
vendored
Normal file
14
gitnexus/test/fixtures/lang-resolution/php-parent-vs-trait/app/Child.php
vendored
Normal file
|
|
@ -0,0 +1,14 @@
|
|||
<?php
|
||||
namespace App;
|
||||
|
||||
class Child extends Base {
|
||||
use Auditable;
|
||||
|
||||
public function callViaParent(): string {
|
||||
return parent::record();
|
||||
}
|
||||
|
||||
public function callViaThis(): string {
|
||||
return $this->record();
|
||||
}
|
||||
}
|
||||
7
gitnexus/test/fixtures/lang-resolution/php-parent-vs-trait/composer.json
vendored
Normal file
7
gitnexus/test/fixtures/lang-resolution/php-parent-vs-trait/composer.json
vendored
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
{
|
||||
"autoload": {
|
||||
"psr-4": {
|
||||
"App\\": "app/"
|
||||
}
|
||||
}
|
||||
}
|
||||
20
gitnexus/test/fixtures/lang-resolution/php-transitive-traits/app/Models/Consumer.php
vendored
Normal file
20
gitnexus/test/fixtures/lang-resolution/php-transitive-traits/app/Models/Consumer.php
vendored
Normal file
|
|
@ -0,0 +1,20 @@
|
|||
<?php
|
||||
namespace App\Models;
|
||||
|
||||
use App\Traits\TraitA;
|
||||
|
||||
class Consumer {
|
||||
use TraitA;
|
||||
|
||||
public function callDepthOne(): string {
|
||||
return $this->aMethod();
|
||||
}
|
||||
|
||||
public function callDepthTwo(): string {
|
||||
return $this->bMethod();
|
||||
}
|
||||
|
||||
public function callDepthThree(): string {
|
||||
return $this->deepMethod();
|
||||
}
|
||||
}
|
||||
10
gitnexus/test/fixtures/lang-resolution/php-transitive-traits/app/Traits/TraitA.php
vendored
Normal file
10
gitnexus/test/fixtures/lang-resolution/php-transitive-traits/app/Traits/TraitA.php
vendored
Normal file
|
|
@ -0,0 +1,10 @@
|
|||
<?php
|
||||
namespace App\Traits;
|
||||
|
||||
trait TraitA {
|
||||
use TraitB;
|
||||
|
||||
public function aMethod(): string {
|
||||
return 'from A';
|
||||
}
|
||||
}
|
||||
10
gitnexus/test/fixtures/lang-resolution/php-transitive-traits/app/Traits/TraitB.php
vendored
Normal file
10
gitnexus/test/fixtures/lang-resolution/php-transitive-traits/app/Traits/TraitB.php
vendored
Normal file
|
|
@ -0,0 +1,10 @@
|
|||
<?php
|
||||
namespace App\Traits;
|
||||
|
||||
trait TraitB {
|
||||
use TraitC;
|
||||
|
||||
public function bMethod(): string {
|
||||
return 'from B';
|
||||
}
|
||||
}
|
||||
8
gitnexus/test/fixtures/lang-resolution/php-transitive-traits/app/Traits/TraitC.php
vendored
Normal file
8
gitnexus/test/fixtures/lang-resolution/php-transitive-traits/app/Traits/TraitC.php
vendored
Normal file
|
|
@ -0,0 +1,8 @@
|
|||
<?php
|
||||
namespace App\Traits;
|
||||
|
||||
trait TraitC {
|
||||
public function deepMethod(): string {
|
||||
return 'from C';
|
||||
}
|
||||
}
|
||||
7
gitnexus/test/fixtures/lang-resolution/php-transitive-traits/composer.json
vendored
Normal file
7
gitnexus/test/fixtures/lang-resolution/php-transitive-traits/composer.json
vendored
Normal file
|
|
@ -0,0 +1,7 @@
|
|||
{
|
||||
"autoload": {
|
||||
"psr-4": {
|
||||
"App\\": "app/"
|
||||
}
|
||||
}
|
||||
}
|
||||
8
gitnexus/test/fixtures/lang-resolution/php-typed-property-dedup/app/Models/UserRepo.php
vendored
Normal file
8
gitnexus/test/fixtures/lang-resolution/php-typed-property-dedup/app/Models/UserRepo.php
vendored
Normal file
|
|
@ -0,0 +1,8 @@
|
|||
<?php
|
||||
|
||||
namespace App\Models;
|
||||
|
||||
class UserRepo
|
||||
{
|
||||
public function save(): void {}
|
||||
}
|
||||
23
gitnexus/test/fixtures/lang-resolution/php-typed-property-dedup/app/Services/Mixed.php
vendored
Normal file
23
gitnexus/test/fixtures/lang-resolution/php-typed-property-dedup/app/Services/Mixed.php
vendored
Normal file
|
|
@ -0,0 +1,23 @@
|
|||
<?php
|
||||
|
||||
namespace App\Services;
|
||||
|
||||
use App\Models\UserRepo;
|
||||
|
||||
class Mixed
|
||||
{
|
||||
// Typed property: must emit exactly one Property def named `repo`,
|
||||
// zero stray Variable defs.
|
||||
private UserRepo $repo;
|
||||
|
||||
// Untyped property: must emit exactly one (legitimate) catch-all def
|
||||
// for `$id`, and zero Property defs for it.
|
||||
public $id;
|
||||
|
||||
// Constructor-promoted typed parameter: tree-sitter routes these
|
||||
// through the same `property_element` shape, so the dedup must also
|
||||
// suppress the stray Variable here.
|
||||
public function __construct(private UserRepo $promotedRepo)
|
||||
{
|
||||
}
|
||||
}
|
||||
5
gitnexus/test/fixtures/lang-resolution/php-typed-property-dedup/composer.json
vendored
Normal file
5
gitnexus/test/fixtures/lang-resolution/php-typed-property-dedup/composer.json
vendored
Normal file
|
|
@ -0,0 +1,5 @@
|
|||
{
|
||||
"autoload": {
|
||||
"psr-4": { "App\\": "app/" }
|
||||
}
|
||||
}
|
||||
26
gitnexus/test/fixtures/lang-resolution/php-unresolved-receiver-arity/app/Models/Handler.php
vendored
Normal file
26
gitnexus/test/fixtures/lang-resolution/php-unresolved-receiver-arity/app/Models/Handler.php
vendored
Normal file
|
|
@ -0,0 +1,26 @@
|
|||
<?php
|
||||
|
||||
namespace App\Models;
|
||||
|
||||
/**
|
||||
* Single workspace-unique candidate for each fallback-method name so the
|
||||
* unresolved-receiver fallback in phpEmitUnresolvedReceiverEdges fires
|
||||
* for untyped receivers. The names are deliberately chosen to NOT collide
|
||||
* with other fixtures so cross-fixture test interference cannot occur.
|
||||
*
|
||||
* Method-arity matrix:
|
||||
* - happyPath(): min=0, max=0
|
||||
* - withDefault(string $a, int $b = 0): min=1, max=2
|
||||
* - variadicLog(string $level, ...$args): min=1, max=undefined, hasVarArgs
|
||||
* - variadicLogTwoRequired(string $a, string $b, ...$rest): min=2, max=undefined, hasVarArgs
|
||||
*/
|
||||
class Handler
|
||||
{
|
||||
public function happyPath(): void {}
|
||||
|
||||
public function withDefault(string $a, int $b = 0): void {}
|
||||
|
||||
public function variadicLog(string $level, ...$args): void {}
|
||||
|
||||
public function variadicLogTwoRequired(string $a, string $b, ...$rest): void {}
|
||||
}
|
||||
58
gitnexus/test/fixtures/lang-resolution/php-unresolved-receiver-arity/app/Services/Caller.php
vendored
Normal file
58
gitnexus/test/fixtures/lang-resolution/php-unresolved-receiver-arity/app/Services/Caller.php
vendored
Normal file
|
|
@ -0,0 +1,58 @@
|
|||
<?php
|
||||
|
||||
namespace App\Services;
|
||||
|
||||
/**
|
||||
* Each method's receiver is an untyped parameter so the high-confidence
|
||||
* receiver-bound passes drop the site, leaving it for
|
||||
* phpEmitUnresolvedReceiverEdges (the 0.6-confidence fallback).
|
||||
*
|
||||
* The fallback's gate is EXACT-required-arity post-fix:
|
||||
* - call argCount === fnDef.requiredParameterCount → edge emitted
|
||||
* - call argCount !== required, non-variadic → NO edge (post-fix; pre-fix may have emitted)
|
||||
* - variadic candidate, argCount >= required → edge emitted
|
||||
* - variadic candidate, argCount < required → NO edge
|
||||
*/
|
||||
class Caller
|
||||
{
|
||||
public function callHappyPath($h): void
|
||||
{
|
||||
// happyPath(): min=0. argCount=0 → exact match. Edge.
|
||||
$h->happyPath();
|
||||
}
|
||||
|
||||
public function callDefaultExactRequired($h): void
|
||||
{
|
||||
// withDefault($a, $b=0): min=1. argCount=1 === min → exact match. Edge.
|
||||
$h->withDefault('a');
|
||||
}
|
||||
|
||||
public function callDefaultBeyondRequired($h): void
|
||||
{
|
||||
// withDefault($a, $b=0): min=1, max=2. argCount=2 > min.
|
||||
// Pre-fix: first-stage narrow accepts (2 <= 2), edge emitted.
|
||||
// Post-fix: exact-required gate rejects (2 !== 1), no edge.
|
||||
$h->withDefault('a', 99);
|
||||
}
|
||||
|
||||
public function callVariadicAtRequired($h): void
|
||||
{
|
||||
// variadicLog($level, ...$args): min=1, hasVarArgs.
|
||||
// argCount=1 === min → edge emitted (variadic relaxed path).
|
||||
$h->variadicLog('info');
|
||||
}
|
||||
|
||||
public function callVariadicBeyondRequired($h): void
|
||||
{
|
||||
// variadicLog($level, ...$args): min=1, hasVarArgs.
|
||||
// argCount=2 > min, variadic → edge emitted.
|
||||
$h->variadicLog('info', 'arg1');
|
||||
}
|
||||
|
||||
public function callVariadicBelowRequired($h): void
|
||||
{
|
||||
// variadicLogTwoRequired($a, $b, ...$rest): min=2, hasVarArgs.
|
||||
// argCount=1 < min → no edge (first-stage rejects). Both pre/post-fix.
|
||||
$h->variadicLogTwoRequired('only-one');
|
||||
}
|
||||
}
|
||||
Some files were not shown because too many files have changed in this diff Show more
Loading…
Add table
Reference in a new issue