codegraph-java 0.1.0

package/dist/extraction/languages/rust.js

@@ -0,0 +1,169 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.rustExtractor = void 0;
+exports.rustImplTypeName = rustImplTypeName;
+const tree_sitter_helpers_1 = require("../tree-sitter-helpers");
+/**
+ * A Rust function's declared return type, normalized to the bare type a chained
+ * `Foo::new().bar()` could be called on (the #645/#608 mechanism). Reads the
+ * `return_type` field: `-> Self` yields the marker `self` (resolved to the impl's
+ * own type at resolution time, like PHP's `self`/`static`); a concrete `-> Foo` /
+ * `-> FooBuilder` its name; a reference (`&Foo`) is unwrapped; generics are reduced
+ * to the base type (`Vec<Foo>` → `Vec`); primitives / unit / tuple yield undefined.
+ * Stdlib types that aren't in the graph simply fail the later existence check.
+ */
+function extractRustReturnType(node, source) {
+    let rt = (0, tree_sitter_helpers_1.getChildByField)(node, 'return_type');
+    if (!rt)
+        return undefined;
+    if (rt.type === 'reference_type') {
+        rt =
+            rt.namedChildren.find((c) => c.type === 'type_identifier' ||
+                c.type === 'scoped_type_identifier' ||
+                c.type === 'generic_type') ?? rt;
+    }
+    if (!rt || rt.type === 'primitive_type' || rt.type === 'unit_type' || rt.type === 'tuple_type') {
+        return undefined;
+    }
+    const text = (0, tree_sitter_helpers_1.getNodeText)(rt, source).trim().replace(/<[^>]*>/g, '');
+    const last = text.split('::').pop()?.trim();
+    if (!last || !/^[A-Za-z_]\w*$/.test(last))
+        return undefined;
+    return last === 'Self' ? 'self' : last;
+}
+/**
+ * The implementing type's simple name for an `impl` block, read from the
+ * grammar's `type` field (#1588). Mirrored byte-for-byte by the native
+ * kernel's `impl_type_name` (codegraph-kernel/src/rustlang.rs) — change both.
+ *
+ * `impl<T> Source for BufSource<T>`, `impl<'a> Iterator for Parents<'a>`,
+ * `impl Trait for &Foo`, `impl Trait for m::Foo` all yield the implementing
+ * TYPE (`BufSource`, `Parents`, `Foo`, `Foo`). The previous rule took the last
+ * bare `type_identifier` child of the `impl_item`; once the implementing type
+ * carries parameters it parses as a `generic_type`, so the only bare
+ * identifier left was the TRAIT's — every parameterized impl's methods were
+ * qualified by the trait (`Source::read`), unaddressable by their type and
+ * colliding with the trait's own declaration.
+ *
+ * Shapes that name no single type (tuples, `dyn Trait`, pointers, primitives,
+ * function types…) yield undefined: no receiver, and the fn is extracted
+ * exactly as before.
+ */
+function rustImplTypeName(typeNode, source) {
+    if (!typeNode)
+        return undefined;
+    switch (typeNode.type) {
+        case 'type_identifier':
+        case 'identifier':
+            return (0, tree_sitter_helpers_1.getNodeText)(typeNode, source);
+        // `Foo<T>` — the `type` field is the bare (or scoped) name, never the args.
+        case 'generic_type':
+            return rustImplTypeName((0, tree_sitter_helpers_1.getChildByField)(typeNode, 'type'), source);
+        // `m::Foo` — the last segment is the type's name.
+        case 'scoped_type_identifier':
+        case 'scoped_identifier':
+            return rustImplTypeName((0, tree_sitter_helpers_1.getChildByField)(typeNode, 'name'), source);
+        // `&Foo` / `&'a mut Foo` — the referenced type.
+        case 'reference_type':
+            return rustImplTypeName((0, tree_sitter_helpers_1.getChildByField)(typeNode, 'type'), source);
+        default:
+            return undefined;
+    }
+}
+exports.rustExtractor = {
+    // `function_signature_item` is a trait method DECLARATION (`fn render(&self);`,
+    // no body). Extracting it makes a trait's method set first-class, which
+    // impl-navigation and trait-dispatch synthesis need (a struct's method set is
+    // matched against the trait's).
+    functionTypes: ['function_item', 'function_signature_item'],
+    classTypes: [], // Rust has impl blocks
+    methodTypes: ['function_item', 'function_signature_item'],
+    interfaceTypes: ['trait_item'],
+    structTypes: ['struct_item'],
+    // Unions share struct member syntax and impl attachment, but retain their
+    // distinct semantic kind in the graph.
+    unionTypes: ['union_item'],
+    enumTypes: ['enum_item'],
+    enumMemberTypes: ['enum_variant'],
+    typeAliasTypes: ['type_item'], // Rust type aliases
+    importTypes: ['use_declaration'],
+    callTypes: ['call_expression'],
+    variableTypes: ['let_declaration', 'const_item', 'static_item'],
+    interfaceKind: 'trait',
+    nameField: 'name',
+    bodyField: 'body',
+    paramsField: 'parameters',
+    returnField: 'return_type',
+    getReturnType: extractRustReturnType,
+    getSignature: (node, source) => {
+        const params = (0, tree_sitter_helpers_1.getChildByField)(node, 'parameters');
+        const returnType = (0, tree_sitter_helpers_1.getChildByField)(node, 'return_type');
+        if (!params)
+            return undefined;
+        let sig = (0, tree_sitter_helpers_1.getNodeText)(params, source);
+        if (returnType) {
+            sig += ' -> ' + (0, tree_sitter_helpers_1.getNodeText)(returnType, source);
+        }
+        return sig;
+    },
+    isAsync: (node) => {
+        for (let i = 0; i < node.childCount; i++) {
+            const child = node.child(i);
+            if (child?.type === 'async')
+                return true;
+        }
+        return false;
+    },
+    getVisibility: (node) => {
+        for (let i = 0; i < node.childCount; i++) {
+            const child = node.child(i);
+            if (child?.type === 'visibility_modifier') {
+                return child.text.includes('pub') ? 'public' : 'private';
+            }
+        }
+        return 'private'; // Rust defaults to private
+    },
+    getReceiverType: (node, source) => {
+        // Walk up the tree-sitter AST to find a parent impl_item
+        let parent = node.parent;
+        while (parent) {
+            if (parent.type === 'impl_item') {
+                // The grammar names the implementing type directly (the `type` field)
+                // for both `impl Type { … }` and `impl Trait for Type { … }` — see
+                // rustImplTypeName for why the old positional scan was wrong (#1588).
+                return rustImplTypeName((0, tree_sitter_helpers_1.getChildByField)(parent, 'type'), source);
+            }
+            parent = parent.parent;
+        }
+        return undefined;
+    },
+    extractImport: (node, source) => {
+        const importText = source.substring(node.startIndex, node.endIndex).trim();
+        // Helper to get the root crate/module from a scoped path
+        const getRootModule = (scopedNode) => {
+            const firstChild = scopedNode.namedChild(0);
+            if (!firstChild)
+                return source.substring(scopedNode.startIndex, scopedNode.endIndex);
+            if (firstChild.type === 'identifier' ||
+                firstChild.type === 'crate' ||
+                firstChild.type === 'super' ||
+                firstChild.type === 'self') {
+                return source.substring(firstChild.startIndex, firstChild.endIndex);
+            }
+            else if (firstChild.type === 'scoped_identifier') {
+                return getRootModule(firstChild);
+            }
+            return source.substring(firstChild.startIndex, firstChild.endIndex);
+        };
+        // Find the use argument (scoped_use_list or scoped_identifier)
+        const useArg = node.namedChildren.find((c) => c.type === 'scoped_use_list' ||
+            c.type === 'scoped_identifier' ||
+            c.type === 'use_list' ||
+            c.type === 'identifier');
+        if (useArg) {
+            return { moduleName: getRootModule(useArg), signature: importText };
+        }
+        return null;
+    },
+};
+//# sourceMappingURL=rust.js.map

package/dist/extraction/languages/rust.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"rust.js","sourceRoot":"","sources":["../../../src/extraction/languages/rust.ts"],"names":[],"mappings":";;;AAoDA,4CAmBC;AAtED,gEAAsE;AAGtE;;;;;;;;GAQG;AACH,SAAS,qBAAqB,CAAC,IAAgB,EAAE,MAAc;IAC7D,IAAI,EAAE,GAAG,IAAA,qCAAe,EAAC,IAAI,EAAE,aAAa,CAAC,CAAC;IAC9C,IAAI,CAAC,EAAE;QAAE,OAAO,SAAS,CAAC;IAC1B,IAAI,EAAE,CAAC,IAAI,KAAK,gBAAgB,EAAE,CAAC;QACjC,EAAE;YACA,EAAE,CAAC,aAAa,CAAC,IAAI,CACnB,CAAC,CAAa,EAAE,EAAE,CAChB,CAAC,CAAC,IAAI,KAAK,iBAAiB;gBAC5B,CAAC,CAAC,IAAI,KAAK,wBAAwB;gBACnC,CAAC,CAAC,IAAI,KAAK,cAAc,CAC5B,IAAI,EAAE,CAAC;IACZ,CAAC;IACD,IAAI,CAAC,EAAE,IAAI,EAAE,CAAC,IAAI,KAAK,gBAAgB,IAAI,EAAE,CAAC,IAAI,KAAK,WAAW,IAAI,EAAE,CAAC,IAAI,KAAK,YAAY,EAAE,CAAC;QAC/F,OAAO,SAAS,CAAC;IACnB,CAAC;IACD,MAAM,IAAI,GAAG,IAAA,iCAAW,EAAC,EAAE,EAAE,MAAM,CAAC,CAAC,IAAI,EAAE,CAAC,OAAO,CAAC,UAAU,EAAE,EAAE,CAAC,CAAC;IACpE,MAAM,IAAI,GAAG,IAAI,CAAC,KAAK,CAAC,IAAI,CAAC,CAAC,GAAG,EAAE,EAAE,IAAI,EAAE,CAAC;IAC5C,IAAI,CAAC,IAAI,IAAI,CAAC,gBAAgB,CAAC,IAAI,CAAC,IAAI,CAAC;QAAE,OAAO,SAAS,CAAC;IAC5D,OAAO,IAAI,KAAK,MAAM,CAAC,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,IAAI,CAAC;AACzC,CAAC;AAED;;;;;;;;;;;;;;;;;GAiBG;AACH,SAAgB,gBAAgB,CAAC,QAA2B,EAAE,MAAc;IAC1E,IAAI,CAAC,QAAQ;QAAE,OAAO,SAAS,CAAC;IAChC,QAAQ,QAAQ,CAAC,IAAI,EAAE,CAAC;QACtB,KAAK,iBAAiB,CAAC;QACvB,KAAK,YAAY;YACf,OAAO,IAAA,iCAAW,EAAC,QAAQ,EAAE,MAAM,CAAC,CAAC;QACvC,4EAA4E;QAC5E,KAAK,cAAc;YACjB,OAAO,gBAAgB,CAAC,IAAA,qCAAe,EAAC,QAAQ,EAAE,MAAM,CAAC,EAAE,MAAM,CAAC,CAAC;QACrE,kDAAkD;QAClD,KAAK,wBAAwB,CAAC;QAC9B,KAAK,mBAAmB;YACtB,OAAO,gBAAgB,CAAC,IAAA,qCAAe,EAAC,QAAQ,EAAE,MAAM,CAAC,EAAE,MAAM,CAAC,CAAC;QACrE,gDAAgD;QAChD,KAAK,gBAAgB;YACnB,OAAO,gBAAgB,CAAC,IAAA,qCAAe,EAAC,QAAQ,EAAE,MAAM,CAAC,EAAE,MAAM,CAAC,CAAC;QACrE;YACE,OAAO,SAAS,CAAC;IACrB,CAAC;AACH,CAAC;AAEY,QAAA,aAAa,GAAsB;IAC9C,gFAAgF;IAChF,wEAAwE;IACxE,8EAA8E;IAC9E,gCAAgC;IAChC,aAAa,EAAE,CAAC,eAAe,EAAE,yBAAyB,CAAC;IAC3D,UAAU,EAAE,EAAE,EAAE,uBAAuB;IACvC,WAAW,EAAE,CAAC,eAAe,EAAE,yBAAyB,CAAC;IACzD,cAAc,EAAE,CAAC,YAAY,CAAC;IAC9B,WAAW,EAAE,CAAC,aAAa,CAAC;IAC5B,0EAA0E;IAC1E,uCAAuC;IACvC,UAAU,EAAE,CAAC,YAAY,CAAC;IAC1B,SAAS,EAAE,CAAC,WAAW,CAAC;IACxB,eAAe,EAAE,CAAC,cAAc,CAAC;IACjC,cAAc,EAAE,CAAC,WAAW,CAAC,EAAE,oBAAoB;IACnD,WAAW,EAAE,CAAC,iBAAiB,CAAC;IAChC,SAAS,EAAE,CAAC,iBAAiB,CAAC;IAC9B,aAAa,EAAE,CAAC,iBAAiB,EAAE,YAAY,EAAE,aAAa,CAAC;IAC/D,aAAa,EAAE,OAAO;IACtB,SAAS,EAAE,MAAM;IACjB,SAAS,EAAE,MAAM;IACjB,WAAW,EAAE,YAAY;IACzB,WAAW,EAAE,aAAa;IAC1B,aAAa,EAAE,qBAAqB;IACpC,YAAY,EAAE,CAAC,IAAI,EAAE,MAAM,EAAE,EAAE;QAC7B,MAAM,MAAM,GAAG,IAAA,qCAAe,EAAC,IAAI,EAAE,YAAY,CAAC,CAAC;QACnD,MAAM,UAAU,GAAG,IAAA,qCAAe,EAAC,IAAI,EAAE,aAAa,CAAC,CAAC;QACxD,IAAI,CAAC,MAAM;YAAE,OAAO,SAAS,CAAC;QAC9B,IAAI,GAAG,GAAG,IAAA,iCAAW,EAAC,MAAM,EAAE,MAAM,CAAC,CAAC;QACtC,IAAI,UAAU,EAAE,CAAC;YACf,GAAG,IAAI,MAAM,GAAG,IAAA,iCAAW,EAAC,UAAU,EAAE,MAAM,CAAC,CAAC;QAClD,CAAC;QACD,OAAO,GAAG,CAAC;IACb,CAAC;IACD,OAAO,EAAE,CAAC,IAAI,EAAE,EAAE;QAChB,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,UAAU,EAAE,CAAC,EAAE,EAAE,CAAC;YACzC,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;YAC5B,IAAI,KAAK,EAAE,IAAI,KAAK,OAAO;gBAAE,OAAO,IAAI,CAAC;QAC3C,CAAC;QACD,OAAO,KAAK,CAAC;IACf,CAAC;IACD,aAAa,EAAE,CAAC,IAAI,EAAE,EAAE;QACtB,KAAK,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,IAAI,CAAC,UAAU,EAAE,CAAC,EAAE,EAAE,CAAC;YACzC,MAAM,KAAK,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;YAC5B,IAAI,KAAK,EAAE,IAAI,KAAK,qBAAqB,EAAE,CAAC;gBAC1C,OAAO,KAAK,CAAC,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC,QAAQ,CAAC,CAAC,CAAC,SAAS,CAAC;YAC3D,CAAC;QACH,CAAC;QACD,OAAO,SAAS,CAAC,CAAC,2BAA2B;IAC/C,CAAC;IACD,eAAe,EAAE,CAAC,IAAI,EAAE,MAAM,EAAE,EAAE;QAChC,yDAAyD;QACzD,IAAI,MAAM,GAAG,IAAI,CAAC,MAAM,CAAC;QACzB,OAAO,MAAM,EAAE,CAAC;YACd,IAAI,MAAM,CAAC,IAAI,KAAK,WAAW,EAAE,CAAC;gBAChC,sEAAsE;gBACtE,mEAAmE;gBACnE,sEAAsE;gBACtE,OAAO,gBAAgB,CAAC,IAAA,qCAAe,EAAC,MAAM,EAAE,MAAM,CAAC,EAAE,MAAM,CAAC,CAAC;YACnE,CAAC;YACD,MAAM,GAAG,MAAM,CAAC,MAAM,CAAC;QACzB,CAAC;QACD,OAAO,SAAS,CAAC;IACnB,CAAC;IAED,aAAa,EAAE,CAAC,IAAI,EAAE,MAAM,EAAE,EAAE;QAC9B,MAAM,UAAU,GAAG,MAAM,CAAC,SAAS,CAAC,IAAI,CAAC,UAAU,EAAE,IAAI,CAAC,QAAQ,CAAC,CAAC,IAAI,EAAE,CAAC;QAE3E,yDAAyD;QACzD,MAAM,aAAa,GAAG,CAAC,UAAsB,EAAU,EAAE;YACvD,MAAM,UAAU,GAAG,UAAU,CAAC,UAAU,CAAC,CAAC,CAAC,CAAC;YAC5C,IAAI,CAAC,UAAU;gBAAE,OAAO,MAAM,CAAC,SAAS,CAAC,UAAU,CAAC,UAAU,EAAE,UAAU,CAAC,QAAQ,CAAC,CAAC;YACrF,IAAI,UAAU,CAAC,IAAI,KAAK,YAAY;gBAChC,UAAU,CAAC,IAAI,KAAK,OAAO;gBAC3B,UAAU,CAAC,IAAI,KAAK,OAAO;gBAC3B,UAAU,CAAC,IAAI,KAAK,MAAM,EAAE,CAAC;gBAC/B,OAAO,MAAM,CAAC,SAAS,CAAC,UAAU,CAAC,UAAU,EAAE,UAAU,CAAC,QAAQ,CAAC,CAAC;YACtE,CAAC;iBAAM,IAAI,UAAU,CAAC,IAAI,KAAK,mBAAmB,EAAE,CAAC;gBACnD,OAAO,aAAa,CAAC,UAAU,CAAC,CAAC;YACnC,CAAC;YACD,OAAO,MAAM,CAAC,SAAS,CAAC,UAAU,CAAC,UAAU,EAAE,UAAU,CAAC,QAAQ,CAAC,CAAC;QACtE,CAAC,CAAC;QAEF,+DAA+D;QAC/D,MAAM,MAAM,GAAG,IAAI,CAAC,aAAa,CAAC,IAAI,CAAC,CAAC,CAAa,EAAE,EAAE,CACvD,CAAC,CAAC,IAAI,KAAK,iBAAiB;YAC5B,CAAC,CAAC,IAAI,KAAK,mBAAmB;YAC9B,CAAC,CAAC,IAAI,KAAK,UAAU;YACrB,CAAC,CAAC,IAAI,KAAK,YAAY,CACxB,CAAC;QAEF,IAAI,MAAM,EAAE,CAAC;YACX,OAAO,EAAE,UAAU,EAAE,aAAa,CAAC,MAAM,CAAC,EAAE,SAAS,EAAE,UAAU,EAAE,CAAC;QACtE,CAAC;QACD,OAAO,IAAI,CAAC;IACd,CAAC;CACF,CAAC"}

package/dist/extraction/parse-pool.d.ts

@@ -0,0 +1,167 @@
+/**
+ * Parse worker pool — runs tree-sitter parsing across N worker threads so a full
+ * `cg index` uses every core instead of pinning one.
+ *
+ * Why this exists: `ExtractionOrchestrator.indexAll()` already reads files in
+ * parallel, but it parsed them through a SINGLE worker thread, so on an
+ * N-core machine indexing a large repo used one core and left the rest idle
+ * (issue #1015, the parse-time half of #320). Spreading the parse calls across a
+ * pool of workers — each its own tree-sitter WASM heap — restores multi-core
+ * throughput. SQLite storage stays on the main thread (it isn't thread-safe), so
+ * only the CPU-bound parse step is parallelised; results are stored as they
+ * arrive, in whatever order they finish.
+ *
+ * Design mirrors {@link ../mcp/query-pool} (idle-list dispatch, lazy growth,
+ * throttled cold-starts, crash recovery), with parse-specific behaviour:
+ *   - per-worker recycle: WASM linear memory grows but never shrinks, so each
+ *     worker is torn down and replaced after `recycleInterval` parses to reclaim
+ *     its heap — the same reason the old single worker recycled.
+ *   - reject, don't retry: a parse that crashes or times out its worker REJECTS
+ *     (with a message the orchestrator's retry pass recognises) rather than being
+ *     silently requeued — the orchestrator owns the smarter two-stage retry
+ *     (fresh worker, then comment-stripped) on a clean WASM heap.
+ *   - a size-1 pool reproduces the old single-worker path exactly, which is the
+ *     conservative rollback: set `CODEGRAPH_PARSE_WORKERS=1`.
+ *
+ * Memory: peak scales with pool size (≈ size × a worker's pre-recycle heap), so
+ * the default is capped and the env var lets constrained machines dial it down.
+ */
+import type { Language, ExtractionResult } from '../types';
+/**
+ * Minimal worker surface the pool drives — satisfied by a real `worker_threads`
+ * Worker. Abstracted so tests can inject a fake worker and exercise the pool's
+ * queue / growth / recycle / crash-recovery logic without spawning threads or a
+ * built `dist/`.
+ */
+export interface ParsePoolWorker {
+    postMessage(msg: unknown): void;
+    terminate(): Promise<number> | void;
+    on(event: 'message', cb: (m: unknown) => void): void;
+    on(event: 'error', cb: (e: Error) => void): void;
+    on(event: 'exit', cb: (code: number) => void): void;
+}
+/** A single file to parse. `language` is resolved on the main thread (it holds
+ *  the project's codegraph.json extension overrides) and handed to the worker. */
+export interface ParseTask {
+    filePath: string;
+    content: string;
+    language: Language;
+    frameworkNames?: string[];
+}
+/**
+ * Resolve the pool size from the `CODEGRAPH_PARSE_WORKERS` override and the
+ * machine's core count.
+ *   - explicit `0` or `1` → 1 worker (the old single-worker path; the rollback).
+ *   - explicit `N` → N, clamped to [1, 16].
+ *   - unset / blank / non-numeric → `clamp(cores - 1, 1, 8)` (leave a core for
+ *     the main thread + UI; never zero — parsing always needs a worker).
+ */
+/**
+ * Resolve the base per-parse timeout from the `CODEGRAPH_PARSE_TIMEOUT_MS`
+ * override. Slow storage (HDD, network folders) can need a larger budget; a
+ * non-numeric / non-positive value falls back to the default (10s).
+ */
+export declare function resolveParseTimeoutMs(envVal: string | undefined): number;
+/**
+ * Per-file soft timeout. Size scaling helps legitimate large sources, but an
+ * uncapped linear budget gave data-only headers near the 1 MiB file limit a
+ * 4.5–5 minute hard-kill window (#1555). Explicit larger base overrides remain
+ * respected for slow storage.
+ */
+export declare function resolveParseBudgetMs(baseMs: number, contentLength: number): number;
+export declare function resolveParsePoolSize(envVal: string | undefined, cpuCount: number): number;
+export interface ParseWorkerPoolOptions {
+    /** Languages to load grammars for in every worker at spawn. */
+    languages: Language[];
+    /** Number of worker threads (≥1). Clamp the resolved value before passing. */
+    size: number;
+    /** Compiled `parse-worker.js` path. Required unless `createWorker` is given. */
+    workerScriptPath?: string;
+    /** Parses per worker before recycle. Default 250. */
+    recycleInterval?: number;
+    /** Base per-parse timeout (ms); scaled by file size per parse. Default 10s. */
+    parseTimeoutMs?: number;
+    /** Worker factory (tests inject a fake). Defaults to a real `worker_threads` Worker. */
+    createWorker?: () => ParsePoolWorker;
+    /** Optional verbose logger (the orchestrator's `[worker] …` logger). */
+    log?: (msg: string) => void;
+    /**
+     * Pre-read grammar WASM bytes keyed by language, forwarded to every worker's
+     * `load-grammars` message so a spawn/respawn loads grammars from memory
+     * instead of re-reading them from disk — on slow storage each respawn's
+     * grammar re-read otherwise amplifies the very I/O contention that caused
+     * the respawn (issue #1231). Best-effort: a missing language falls back to
+     * the worker's own disk read.
+     */
+    grammarBuffers?: Record<string, Uint8Array>;
+}
+export declare class ParseWorkerPool {
+    private idle;
+    private queue;
+    private inflight;
+    private workers;
+    private pending;
+    private parseCounts;
+    private nextId;
+    private totalCrashes;
+    private destroyed;
+    private readonly languages;
+    private readonly maxSize;
+    private readonly recycleInterval;
+    private readonly parseTimeoutMs;
+    private readonly createWorker;
+    private readonly log;
+    private readonly grammarBuffers?;
+    constructor(opts: ParseWorkerPoolOptions);
+    /**
+     * Spawn the whole pool up front. The default demand-driven growth avoids
+     * paying worker boot for small jobs, but a bulk index KNOWS every core will
+     * be needed — on a fast repo the one-by-one ramp-up otherwise consumes most
+     * of the parse phase (each worker boot is a fresh Node isolate + grammar
+     * load, ~hundreds of ms, and growth only triggers as queue pressure builds).
+     */
+    prewarm(): void;
+    /** Pool size cap (for logging). */
+    get size(): number;
+    /** Live worker count (for tests). */
+    get liveWorkers(): number;
+    /** False once the crash budget is exhausted (or after destroy). */
+    get healthy(): boolean;
+    /**
+     * Parse one file on the pool. Resolves with the extraction result, or REJECTS
+     * if the parse times out or its worker crashes — the caller records the error
+     * and (for worker-exit/OOM/timeout rejections) re-attempts in its retry pass.
+     */
+    requestParse(task: ParseTask): Promise<ExtractionResult>;
+    private spawnOne;
+    private onMessage;
+    /** A worker died (crash hook / OOM exit / spawn error). Reject its in-flight
+     *  parse so the caller's retry pass can re-attempt it, then respawn. */
+    private onWorkerGone;
+    /** Tear down a worker that has hit its recycle threshold and replace it. Not a
+     *  crash, so it doesn't count against the budget. */
+    private recycle;
+    private removeWorker;
+    private dispatch;
+    /**
+     * The base timer fired with no result processed yet. Do NOT kill or settle:
+     * the timer firing doesn't prove the parse is still running — after a long
+     * synchronous main-thread stretch Node services the timers phase before the
+     * poll phase, so an already-delivered `parse-result` is still queued behind
+     * this callback. Mark the job late (onMessage accepts a result that shows up)
+     * and arm the hard-kill backstop for workers that are genuinely hung.
+     */
+    private onTimeout;
+    /** No result after the full hard-kill window — the worker really is hung. */
+    private onHardTimeout;
+    private drain;
+    private settle;
+    /**
+     * Recycle every idle worker now (fresh WASM heaps). The orchestrator calls
+     * this before its retry pass so crash-on-memory files get the cleanest heap.
+     */
+    recycleAll(): void;
+    /** Terminate all workers and reject any outstanding parses. */
+    destroy(): Promise<void>;
+}
+//# sourceMappingURL=parse-pool.d.ts.map

package/dist/extraction/parse-pool.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"parse-pool.d.ts","sourceRoot":"","sources":["../../src/extraction/parse-pool.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;;;;;;;;;;;GA2BG;AAGH,OAAO,KAAK,EAAE,QAAQ,EAAE,gBAAgB,EAAE,MAAM,UAAU,CAAC;AAE3D;;;;;GAKG;AACH,MAAM,WAAW,eAAe;IAC9B,WAAW,CAAC,GAAG,EAAE,OAAO,GAAG,IAAI,CAAC;IAChC,SAAS,IAAI,OAAO,CAAC,MAAM,CAAC,GAAG,IAAI,CAAC;IACpC,EAAE,CAAC,KAAK,EAAE,SAAS,EAAE,EAAE,EAAE,CAAC,CAAC,EAAE,OAAO,KAAK,IAAI,GAAG,IAAI,CAAC;IACrD,EAAE,CAAC,KAAK,EAAE,OAAO,EAAE,EAAE,EAAE,CAAC,CAAC,EAAE,KAAK,KAAK,IAAI,GAAG,IAAI,CAAC;IACjD,EAAE,CAAC,KAAK,EAAE,MAAM,EAAE,EAAE,EAAE,CAAC,IAAI,EAAE,MAAM,KAAK,IAAI,GAAG,IAAI,CAAC;CACrD;AAED;kFACkF;AAClF,MAAM,WAAW,SAAS;IACxB,QAAQ,EAAE,MAAM,CAAC;IACjB,OAAO,EAAE,MAAM,CAAC;IAChB,QAAQ,EAAE,QAAQ,CAAC;IACnB,cAAc,CAAC,EAAE,MAAM,EAAE,CAAC;CAC3B;AAuCD;;;;;;;GAOG;AACH;;;;GAIG;AACH,wBAAgB,qBAAqB,CAAC,MAAM,EAAE,MAAM,GAAG,SAAS,GAAG,MAAM,CAMxE;AAED;;;;;GAKG;AACH,wBAAgB,oBAAoB,CAAC,MAAM,EAAE,MAAM,EAAE,aAAa,EAAE,MAAM,GAAG,MAAM,CAGlF;AAED,wBAAgB,oBAAoB,CAAC,MAAM,EAAE,MAAM,GAAG,SAAS,EAAE,QAAQ,EAAE,MAAM,GAAG,MAAM,CASzF;AAyBD,MAAM,WAAW,sBAAsB;IACrC,+DAA+D;IAC/D,SAAS,EAAE,QAAQ,EAAE,CAAC;IACtB,8EAA8E;IAC9E,IAAI,EAAE,MAAM,CAAC;IACb,gFAAgF;IAChF,gBAAgB,CAAC,EAAE,MAAM,CAAC;IAC1B,qDAAqD;IACrD,eAAe,CAAC,EAAE,MAAM,CAAC;IACzB,+EAA+E;IAC/E,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB,wFAAwF;IACxF,YAAY,CAAC,EAAE,MAAM,eAAe,CAAC;IACrC,wEAAwE;IACxE,GAAG,CAAC,EAAE,CAAC,GAAG,EAAE,MAAM,KAAK,IAAI,CAAC;IAC5B;;;;;;;OAOG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,UAAU,CAAC,CAAC;CAC7C;AAED,qBAAa,eAAe;IAC1B,OAAO,CAAC,IAAI,CAAyB;IACrC,OAAO,CAAC,KAAK,CAAkB;IAC/B,OAAO,CAAC,QAAQ,CAAwC;IACxD,OAAO,CAAC,OAAO,CAA8B;IAG7C,OAAO,CAAC,OAAO,CAA8B;IAC7C,OAAO,CAAC,WAAW,CAAsC;IACzD,OAAO,CAAC,MAAM,CAAK;IACnB,OAAO,CAAC,YAAY,CAAK;IACzB,OAAO,CAAC,SAAS,CAAS;IAE1B,OAAO,CAAC,QAAQ,CAAC,SAAS,CAAa;IACvC,OAAO,CAAC,QAAQ,CAAC,OAAO,CAAS;IACjC,OAAO,CAAC,QAAQ,CAAC,eAAe,CAAS;IACzC,OAAO,CAAC,QAAQ,CAAC,cAAc,CAAS;IACxC,OAAO,CAAC,QAAQ,CAAC,YAAY,CAAwB;IACrD,OAAO,CAAC,QAAQ,CAAC,GAAG,CAAwB;IAC5C,OAAO,CAAC,QAAQ,CAAC,cAAc,CAAC,CAA6B;gBAEjD,IAAI,EAAE,sBAAsB;IAwBxC;;;;;;OAMG;IACH,OAAO,IAAI,IAAI;IAQf,mCAAmC;IACnC,IAAI,IAAI,IAAI,MAAM,CAAyB;IAE3C,qCAAqC;IACrC,IAAI,WAAW,IAAI,MAAM,CAA8B;IAEvD,mEAAmE;IACnE,IAAI,OAAO,IAAI,OAAO,CAErB;IAED;;;;OAIG;IACH,YAAY,CAAC,IAAI,EAAE,SAAS,GAAG,OAAO,CAAC,gBAAgB,CAAC;IAQxD,OAAO,CAAC,QAAQ;IAqBhB,OAAO,CAAC,SAAS;IAwCjB;4EACwE;IACxE,OAAO,CAAC,YAAY;IAYpB;yDACqD;IACrD,OAAO,CAAC,OAAO;IAQf,OAAO,CAAC,YAAY;IAOpB,OAAO,CAAC,QAAQ;IAmBhB;;;;;;;OAOG;IACH,OAAO,CAAC,SAAS;IASjB,6EAA6E;IAC7E,OAAO,CAAC,aAAa;IAerB,OAAO,CAAC,KAAK;IA8Bb,OAAO,CAAC,MAAM;IASd;;;OAGG;IACH,UAAU,IAAI,IAAI;IAIlB,+DAA+D;IACzD,OAAO,IAAI,OAAO,CAAC,IAAI,CAAC;CAe/B"}