feat: migrate C to scope-based resolution (RFC #909 Ring 3)

gitnexus/src/core/ingestion/languages/c-cpp.ts

@@ -46,6 +46,15 @@ import { createCallExtractor } from '../call-extractors/generic.js';
 import { cCallConfig, cppCallConfig } from '../call-extractors/configs/c-cpp.js';
 import { createHeritageExtractor } from '../heritage-extractors/generic.js';
 import { stripUeMacros } from '../cpp-ue-preprocessor.js';
+import {
+  emitCScopeCaptures,
+  interpretCImport,
+  interpretCTypeBinding,
+  cArityCompatibility,
+  cBindingScopeFor,
+  cImportOwningScope,
+  cReceiverBinding,
+} from './c/index.js';
 
 const C_BUILT_INS: ReadonlySet<string> = new Set([
   'printf',
@@ -367,6 +376,16 @@ export const cProvider = defineLanguage({
   heritageExtractor: createHeritageExtractor(SupportedLanguages.C),
   labelOverride: cppLabelOverride,
   builtInNames: C_BUILT_INS,
+
+  // ── RFC #909 Ring 3: scope-based resolution hooks (RFC §5) ──────────
+  emitScopeCaptures: emitCScopeCaptures,
+  interpretImport: interpretCImport,
+  interpretTypeBinding: interpretCTypeBinding,
+  bindingScopeFor: cBindingScopeFor,
+  importOwningScope: cImportOwningScope,
+  receiverBinding: cReceiverBinding,
+  arityCompatibility: cArityCompatibility,
+  // mergeBindings + resolveImportTarget live on ScopeResolver (see c/scope-resolver.ts).
 });
 
 export const cppProvider = defineLanguage({

gitnexus/src/core/ingestion/languages/c/arity-metadata.ts

@@ -0,0 +1,102 @@
+import type { SyntaxNode } from '../../utils/ast-helpers.js';
+
+export interface CArityInfo {
+  parameterCount?: number;
+  requiredParameterCount?: number;
+  parameterTypes?: string[];
+}
+
+/**
+ * Compute declaration arity from a C function definition or declaration node.
+ */
+export function computeCDeclarationArity(node: SyntaxNode): CArityInfo {
+  // Find the function_declarator child (may be wrapped in pointer_declarator)
+  const funcDecl = findFuncDeclarator(node);
+  if (funcDecl === null) return {};
+
+  const paramList = funcDecl.childForFieldName('parameters');
+  if (paramList === null) return {};
+
+  const params: SyntaxNode[] = [];
+  for (let i = 0; i < paramList.childCount; i++) {
+    const child = paramList.child(i);
+    if (child === null) continue;
+    if (child.type === 'parameter_declaration' || child.type === 'variadic_parameter') {
+      params.push(child);
+    }
+  }
+
+  // K&R old-style declaration: `int foo()` has an empty parameter_list with
+  // no parameter_declaration or variadic_parameter children. Per C89/C99,
+  // this means the function accepts an unspecified number/types of arguments —
+  // NOT zero arguments. Return unknown arity to avoid false 'incompatible'.
+  // `int foo(void)` is the explicit zero-parameter form and is handled below.
+  if (params.length === 0) return {};
+
+  // (void) means zero parameters
+  if (params.length === 1 && params[0].type === 'parameter_declaration') {
+    const typeNode = params[0].childForFieldName('type');
+    const hasDeclarator = params[0].childForFieldName('declarator') !== null;
+    if (typeNode !== null && typeNode.text === 'void' && !hasDeclarator) {
+      return { parameterCount: 0, requiredParameterCount: 0, parameterTypes: [] };
+    }
+  }
+
+  const isVariadic = params.some((p) => p.type === 'variadic_parameter');
+  const nonVariadicCount = params.filter((p) => p.type !== 'variadic_parameter').length;
+
+  const types: string[] = [];
+  for (const p of params) {
+    if (p.type === 'variadic_parameter') {
+      types.push('...');
+    } else {
+      const typeNode = p.childForFieldName('type');
+      types.push(typeNode?.text ?? 'unknown');
+    }
+  }
+
+  return {
+    parameterCount: isVariadic ? undefined : nonVariadicCount,
+    requiredParameterCount: nonVariadicCount,
+    parameterTypes: types,
+  };
+}
+
+/**
+ * Compute call-site arity from a call_expression node.
+ */
+export function computeCCallArity(node: SyntaxNode): number {
+  const argList = node.childForFieldName('arguments');
+  if (argList === null) return 0;
+
+  let count = 0;
+  for (let i = 0; i < argList.childCount; i++) {
+    const child = argList.child(i);
+    if (child === null) continue;
+    // Skip punctuation (commas, parens)
+    if (child.type !== ',' && child.type !== '(' && child.type !== ')') {
+      count++;
+    }
+  }
+  return count;
+}
+
+function findFuncDeclarator(node: SyntaxNode): SyntaxNode | null {
+  // Direct child
+  let decl = node.childForFieldName('declarator');
+  if (decl === null) {
+    for (let i = 0; i < node.childCount; i++) {
+      const c = node.child(i);
+      if (c?.type === 'function_declarator') return c;
+    }
+    return null;
+  }
+  // Unwrap pointer_declarator
+  while (decl.type === 'pointer_declarator') {
+    const next = decl.childForFieldName('declarator');
+    if (next === null) break;
+    decl = next;
+  }
+  if (decl.type === 'function_declarator') return decl;
+  return null;
+}

gitnexus/src/core/ingestion/languages/c/arity.ts

@@ -0,0 +1,20 @@
+import type { Callsite, SymbolDefinition } from 'gitnexus-shared';
+
+/**
+ * C arity compatibility: no overloading. Variadic functions detected
+ * via '...' in parameterTypes. Otherwise exact match or unknown.
+ */
+export function cArityCompatibility(
+  def: SymbolDefinition,
+  callsite: Callsite,
+): 'compatible' | 'unknown' | 'incompatible' {
+  const max = def.parameterCount;
+  const min = def.requiredParameterCount;
+  if (max === undefined && min === undefined) return 'unknown';
+  if (!Number.isFinite(callsite.arity) || callsite.arity < 0) return 'unknown';
+
+  const variadic = def.parameterTypes?.some((t) => t === '...') ?? false;
+  if (min !== undefined && callsite.arity < min) return 'incompatible';
+  if (max !== undefined && callsite.arity > max && !variadic) return 'incompatible';
+  return 'compatible';
+}

gitnexus/src/core/ingestion/languages/c/captures.ts

@@ -0,0 +1,142 @@
+import type { Capture, CaptureMatch } from 'gitnexus-shared';
+import {
+  findNodeAtRange,
+  nodeToCapture,
+  syntheticCapture,
+  type SyntaxNode,
+} from '../../utils/ast-helpers.js';
+import { getCParser, getCScopeQuery } from './query.js';
+import { getTreeSitterBufferSize } from '../../constants.js';
+import { parseSourceSafe } from '../../../tree-sitter/safe-parse.js';
+import { splitCInclude } from './import-decomposer.js';
+import { computeCDeclarationArity, computeCCallArity } from './arity-metadata.js';
+import { markStaticName } from './static-linkage.js';
+
+export function emitCScopeCaptures(
+  sourceText: string,
+  filePath: string,
+  cachedTree?: unknown,
+): readonly CaptureMatch[] {
+  let tree = cachedTree as ReturnType<ReturnType<typeof getCParser>['parse']> | undefined;
+  if (tree === undefined) {
+    tree = parseSourceSafe(getCParser(), sourceText, undefined, {
+      bufferSize: getTreeSitterBufferSize(sourceText),
+    });
+  }
+
+  const rawMatches = getCScopeQuery().matches(tree.rootNode);
+  const out: CaptureMatch[] = [];
+
+  // Track ranges where typedef-struct/union was captured as @declaration.struct/union
+  // so we can suppress the duplicate @declaration.typedef match at the same range.
+  const structTypedefRanges = new Set<string>();
+
+  for (const m of rawMatches) {
+    const grouped: Record<string, Capture> = {};
+    for (const c of m.captures) {
+      const tag = '@' + c.name;
+      if (tag.startsWith('@_')) continue;
+      grouped[tag] = nodeToCapture(tag, c.node);
+    }
+    if (Object.keys(grouped).length === 0) continue;
+
+    // Handle #include statements
+    if (grouped['@import.statement'] !== undefined) {
+      const anchor = grouped['@import.statement']!;
+      const includeNode = findNodeAtRange(tree.rootNode, anchor.range, 'preproc_include');
+      if (includeNode !== null) {
+        const split = splitCInclude(includeNode);
+        if (split !== null) {
+          out.push(split);
+          continue;
+        }
+      }
+    }
+
+    // Track typedef-struct ranges to suppress duplicate typedef declarations
+    const structAnchor = grouped['@declaration.struct'] ?? grouped['@declaration.union'];
+    if (structAnchor !== undefined) {
+      const r = structAnchor.range;
+      structTypedefRanges.add(`${r.startLine}:${r.startCol}:${r.endLine}:${r.endCol}`);
+    }
+
+    // Suppress @declaration.typedef if the same range was already captured as struct/union
+    const typedefAnchor = grouped['@declaration.typedef'];
+    if (typedefAnchor !== undefined) {
+      const r = typedefAnchor.range;
+      const key = `${r.startLine}:${r.startCol}:${r.endLine}:${r.endCol}`;
+      if (structTypedefRanges.has(key)) continue;
+    }
+
+    // Enrich function declarations with arity metadata and detect static linkage
+    const declAnchor = grouped['@declaration.function'];
+    if (declAnchor !== undefined) {
+      const fnNode =
+        findNodeAtRange(tree.rootNode, declAnchor.range, 'function_definition') ??
+        findNodeAtRange(tree.rootNode, declAnchor.range, 'declaration');
+      if (fnNode !== null) {
+        const arity = computeCDeclarationArity(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),
+          );
+        }
+
+        // Detect static storage class (file-local linkage)
+        if (hasStaticStorageClass(fnNode)) {
+          const nameText = grouped['@declaration.name']?.text;
+          if (nameText !== undefined) {
+            markStaticName(filePath, nameText);
+          }
+        }
+      }
+    }
+
+    // Enrich call references with arity
+    const callAnchor = grouped['@reference.call.free'] ?? grouped['@reference.call.member'];
+    if (callAnchor !== undefined && grouped['@reference.arity'] === undefined) {
+      const callNode = findNodeAtRange(tree.rootNode, callAnchor.range, 'call_expression');
+      if (callNode !== null) {
+        grouped['@reference.arity'] = syntheticCapture(
+          '@reference.arity',
+          callNode,
+          String(computeCCallArity(callNode)),
+        );
+      }
+    }
+
+    out.push(grouped);
+  }
+
+  return out;
+}
+
+/**
+ * Check if a C function_definition or declaration has `static` storage class.
+ * Walks direct children for a `storage_class_specifier` node with text `static`.
+ */
+function hasStaticStorageClass(node: SyntaxNode): boolean {
+  for (let i = 0; i < node.childCount; i++) {
+    const child = node.child(i);
+    if (child !== null && child.type === 'storage_class_specifier' && child.text === 'static') {
+      return true;
+    }
+  }
+  return false;
+}

gitnexus/src/core/ingestion/languages/c/header-scan.ts

@@ -0,0 +1,58 @@
+import { readdirSync, type Dirent } from 'fs';
+import { join, relative } from 'path';
+
+/** C header extensions to scan for in the workspace. */
+const HEADER_EXTENSIONS = new Set(['.h']);
+
+/**
+ * Walk `repoPath` recursively and return relative paths of all `.h` files.
+ * Used by `loadResolutionConfig` so the C resolver can resolve `#include`
+ * targets that live in `.h` files (classified as C++ by language detection
+ * but importable from `.c` files).
+ */
+export function scanHeaderFiles(repoPath: string): ReadonlySet<string> {
+  const headers = new Set<string>();
+  walk(repoPath, repoPath, headers);
+  return headers;
+}
+
+function walk(dir: string, root: string, out: Set<string>): void {
+  let entries: Dirent[];
+  try {
+    entries = readdirSync(dir, { withFileTypes: true, encoding: 'utf8' });
+  } catch {
+    return; // permission denied, etc.
+  }
+  for (const entry of entries) {
+    const name = entry.name;
+    const full = join(dir, name);
+    if (entry.isDirectory()) {
+      // Skip common non-source directories and build output dirs.
+      // Build dirs (dist, build, out, target, _build, .next, cmake-build-*)
+      // may contain generated headers that shadow source headers.
+      if (
+        name === 'node_modules' ||
+        name === '.git' ||
+        name === 'vendor' ||
+        name === 'dist' ||
+        name === 'build' ||
+        name === 'out' ||
+        name === 'target' ||
+        name === '_build' ||
+        name === '.next' ||
+        name.startsWith('cmake-build')
+      ) {
+        continue;
+      }
+      walk(full, root, out);
+    } else if (entry.isFile()) {
+      const ext = name.slice(name.lastIndexOf('.'));
+      if (HEADER_EXTENSIONS.has(ext)) {
+        // Normalize to forward slashes for cross-platform consistency.
+        // path.relative() returns backslash-separated paths on Windows,
+        // but the scope-resolution pipeline uses forward slashes uniformly.
+        out.add(relative(root, full).replace(/\\/g, '/'));
+      }
+    }
+  }
+}