Resolve merge conflicts with main
- extraction/index.ts: use picomatch with static import (replacing dynamic require) and keep normalizePath for other call sites - utils.ts: keep normalizePath from main, take PR's PID-based FileLock
This commit is contained in:
+190
-23
@@ -9,8 +9,10 @@ import * as fs from 'fs';
|
||||
import * as path from 'path';
|
||||
import * as os from 'os';
|
||||
import { CodeGraph } from '../src';
|
||||
import { extractFromSource } from '../src/extraction';
|
||||
import { extractFromSource, scanDirectory, shouldIncludeFile } from '../src/extraction';
|
||||
import { detectLanguage, isLanguageSupported, getSupportedLanguages } from '../src/extraction/grammars';
|
||||
import { normalizePath } from '../src/utils';
|
||||
import { DEFAULT_CONFIG } from '../src/types';
|
||||
|
||||
// Create a temporary directory for each test
|
||||
function createTempDir(): string {
|
||||
@@ -127,14 +129,19 @@ export function processPayment(amount: number): Promise<Receipt> {
|
||||
`;
|
||||
const result = extractFromSource('payment.ts', code);
|
||||
|
||||
expect(result.nodes).toHaveLength(1);
|
||||
expect(result.nodes[0]).toMatchObject({
|
||||
// File node + function node
|
||||
const fileNode = result.nodes.find((n) => n.kind === 'file');
|
||||
expect(fileNode).toBeDefined();
|
||||
expect(fileNode?.name).toBe('payment.ts');
|
||||
|
||||
const funcNode = result.nodes.find((n) => n.kind === 'function');
|
||||
expect(funcNode).toMatchObject({
|
||||
kind: 'function',
|
||||
name: 'processPayment',
|
||||
language: 'typescript',
|
||||
isExported: true,
|
||||
});
|
||||
expect(result.nodes[0]?.signature).toContain('amount: number');
|
||||
expect(funcNode?.signature).toContain('amount: number');
|
||||
});
|
||||
|
||||
it('should extract class declarations', () => {
|
||||
@@ -175,8 +182,11 @@ export interface User {
|
||||
`;
|
||||
const result = extractFromSource('types.ts', code);
|
||||
|
||||
expect(result.nodes).toHaveLength(1);
|
||||
expect(result.nodes[0]).toMatchObject({
|
||||
const fileNode = result.nodes.find((n) => n.kind === 'file');
|
||||
expect(fileNode).toBeDefined();
|
||||
|
||||
const ifaceNode = result.nodes.find((n) => n.kind === 'interface');
|
||||
expect(ifaceNode).toMatchObject({
|
||||
kind: 'interface',
|
||||
name: 'User',
|
||||
isExported: true,
|
||||
@@ -207,8 +217,9 @@ export const useAuth = (): AuthContextValue => {
|
||||
`;
|
||||
const result = extractFromSource('hooks.ts', code);
|
||||
|
||||
expect(result.nodes).toHaveLength(1);
|
||||
expect(result.nodes[0]).toMatchObject({
|
||||
const funcNode = result.nodes.find((n) => n.kind === 'function' && n.name === 'useAuth');
|
||||
expect(funcNode).toBeDefined();
|
||||
expect(funcNode).toMatchObject({
|
||||
kind: 'function',
|
||||
name: 'useAuth',
|
||||
isExported: true,
|
||||
@@ -223,8 +234,9 @@ export const processData = function(input: string): string {
|
||||
`;
|
||||
const result = extractFromSource('utils.ts', code);
|
||||
|
||||
expect(result.nodes).toHaveLength(1);
|
||||
expect(result.nodes[0]).toMatchObject({
|
||||
const funcNode = result.nodes.find((n) => n.kind === 'function' && n.name === 'processData');
|
||||
expect(funcNode).toBeDefined();
|
||||
expect(funcNode).toMatchObject({
|
||||
kind: 'function',
|
||||
name: 'processData',
|
||||
isExported: true,
|
||||
@@ -286,8 +298,9 @@ export const fetchData = async () => {
|
||||
`;
|
||||
const result = extractFromSource('api.js', code);
|
||||
|
||||
expect(result.nodes).toHaveLength(1);
|
||||
expect(result.nodes[0]).toMatchObject({
|
||||
const funcNode = result.nodes.find((n) => n.kind === 'function' && n.name === 'fetchData');
|
||||
expect(funcNode).toBeDefined();
|
||||
expect(funcNode).toMatchObject({
|
||||
kind: 'function',
|
||||
name: 'fetchData',
|
||||
isExported: true,
|
||||
@@ -306,8 +319,8 @@ export type AuthContextValue = {
|
||||
`;
|
||||
const result = extractFromSource('types.ts', code);
|
||||
|
||||
expect(result.nodes).toHaveLength(1);
|
||||
expect(result.nodes[0]).toMatchObject({
|
||||
const typeNode = result.nodes.find((n) => n.kind === 'type_alias');
|
||||
expect(typeNode).toMatchObject({
|
||||
kind: 'type_alias',
|
||||
name: 'AuthContextValue',
|
||||
isExported: true,
|
||||
@@ -323,8 +336,8 @@ type InternalState = {
|
||||
`;
|
||||
const result = extractFromSource('internal.ts', code);
|
||||
|
||||
expect(result.nodes).toHaveLength(1);
|
||||
expect(result.nodes[0]).toMatchObject({
|
||||
const typeNode = result.nodes.find((n) => n.kind === 'type_alias');
|
||||
expect(typeNode).toMatchObject({
|
||||
kind: 'type_alias',
|
||||
name: 'InternalState',
|
||||
isExported: false,
|
||||
@@ -415,7 +428,7 @@ export const useAuth = () => {
|
||||
expect(varNodes).toHaveLength(0);
|
||||
});
|
||||
|
||||
it('should not extract non-exported const as exported variable', () => {
|
||||
it('should extract non-exported const as non-exported variable', () => {
|
||||
const code = `
|
||||
const internalConfig = {
|
||||
debug: true,
|
||||
@@ -423,10 +436,10 @@ const internalConfig = {
|
||||
`;
|
||||
const result = extractFromSource('internal.ts', code);
|
||||
|
||||
// Non-exported const should NOT create a variable node
|
||||
// (only export_statement triggers extractExportedVariables)
|
||||
const varNodes = result.nodes.filter((n) => n.kind === 'variable' && n.name === 'internalConfig');
|
||||
expect(varNodes).toHaveLength(0);
|
||||
// Non-exported const at file level should be extracted as a constant (not exported)
|
||||
const varNodes = result.nodes.filter((n) => (n.kind === 'variable' || n.kind === 'constant') && n.name === 'internalConfig');
|
||||
expect(varNodes).toHaveLength(1);
|
||||
expect(varNodes[0]?.isExported).toBeFalsy();
|
||||
});
|
||||
|
||||
it('should extract Zod schema exports', () => {
|
||||
@@ -463,6 +476,54 @@ export const authMachine = createMachine({
|
||||
});
|
||||
});
|
||||
|
||||
describe('File Node Extraction', () => {
|
||||
it('should create a file-kind node for each parsed file', () => {
|
||||
const code = `
|
||||
export function greet(name: string): string {
|
||||
return "Hello " + name;
|
||||
}
|
||||
`;
|
||||
const result = extractFromSource('greeter.ts', code);
|
||||
|
||||
const fileNode = result.nodes.find((n) => n.kind === 'file');
|
||||
expect(fileNode).toBeDefined();
|
||||
expect(fileNode?.name).toBe('greeter.ts');
|
||||
expect(fileNode?.filePath).toBe('greeter.ts');
|
||||
expect(fileNode?.language).toBe('typescript');
|
||||
expect(fileNode?.startLine).toBe(1);
|
||||
});
|
||||
|
||||
it('should create file nodes for Python files', () => {
|
||||
const code = `
|
||||
def main():
|
||||
pass
|
||||
`;
|
||||
const result = extractFromSource('main.py', code);
|
||||
|
||||
const fileNode = result.nodes.find((n) => n.kind === 'file');
|
||||
expect(fileNode).toBeDefined();
|
||||
expect(fileNode?.name).toBe('main.py');
|
||||
expect(fileNode?.language).toBe('python');
|
||||
});
|
||||
|
||||
it('should create containment edges from file node to top-level declarations', () => {
|
||||
const code = `
|
||||
export function foo() {}
|
||||
export function bar() {}
|
||||
`;
|
||||
const result = extractFromSource('fns.ts', code);
|
||||
|
||||
const fileNode = result.nodes.find((n) => n.kind === 'file');
|
||||
expect(fileNode).toBeDefined();
|
||||
|
||||
// There should be contains edges from the file node to each function
|
||||
const containsEdges = result.edges.filter(
|
||||
(e) => e.source === fileNode?.id && e.kind === 'contains'
|
||||
);
|
||||
expect(containsEdges.length).toBeGreaterThanOrEqual(2);
|
||||
});
|
||||
});
|
||||
|
||||
describe('Python Extraction', () => {
|
||||
it('should extract function definitions', () => {
|
||||
const code = `
|
||||
@@ -473,8 +534,11 @@ def calculate_total(items: list, tax_rate: float) -> float:
|
||||
`;
|
||||
const result = extractFromSource('calc.py', code);
|
||||
|
||||
expect(result.nodes).toHaveLength(1);
|
||||
expect(result.nodes[0]).toMatchObject({
|
||||
const fileNode = result.nodes.find((n) => n.kind === 'file');
|
||||
expect(fileNode).toBeDefined();
|
||||
|
||||
const funcNode = result.nodes.find((n) => n.kind === 'function');
|
||||
expect(funcNode).toMatchObject({
|
||||
kind: 'function',
|
||||
name: 'calculate_total',
|
||||
language: 'python',
|
||||
@@ -1880,3 +1944,106 @@ export function multiply(a: number, b: number): number {
|
||||
cg.close();
|
||||
});
|
||||
});
|
||||
|
||||
describe('Path Normalization', () => {
|
||||
it('should convert backslashes to forward slashes', () => {
|
||||
expect(normalizePath('gui\\node_modules\\foo')).toBe('gui/node_modules/foo');
|
||||
expect(normalizePath('src\\components\\Button.tsx')).toBe('src/components/Button.tsx');
|
||||
});
|
||||
|
||||
it('should leave forward-slash paths unchanged', () => {
|
||||
expect(normalizePath('src/components/Button.tsx')).toBe('src/components/Button.tsx');
|
||||
});
|
||||
|
||||
it('should handle empty string', () => {
|
||||
expect(normalizePath('')).toBe('');
|
||||
});
|
||||
});
|
||||
|
||||
describe('Directory Exclusion', () => {
|
||||
let tempDir: string;
|
||||
|
||||
beforeEach(() => {
|
||||
tempDir = createTempDir();
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
cleanupTempDir(tempDir);
|
||||
});
|
||||
|
||||
it('should exclude node_modules directories', () => {
|
||||
// Create structure: src/index.ts + node_modules/pkg/index.js
|
||||
const srcDir = path.join(tempDir, 'src');
|
||||
const nmDir = path.join(tempDir, 'node_modules', 'pkg');
|
||||
fs.mkdirSync(srcDir, { recursive: true });
|
||||
fs.mkdirSync(nmDir, { recursive: true });
|
||||
fs.writeFileSync(path.join(srcDir, 'index.ts'), 'export const x = 1;');
|
||||
fs.writeFileSync(path.join(nmDir, 'index.js'), 'module.exports = {};');
|
||||
|
||||
const config = { ...DEFAULT_CONFIG, rootDir: tempDir };
|
||||
const files = scanDirectory(tempDir, config);
|
||||
|
||||
expect(files).toContain('src/index.ts');
|
||||
expect(files.every((f) => !f.includes('node_modules'))).toBe(true);
|
||||
});
|
||||
|
||||
it('should exclude nested node_modules directories', () => {
|
||||
// Create structure: packages/app/node_modules/pkg/index.js
|
||||
const srcDir = path.join(tempDir, 'packages', 'app', 'src');
|
||||
const nmDir = path.join(tempDir, 'packages', 'app', 'node_modules', 'pkg');
|
||||
fs.mkdirSync(srcDir, { recursive: true });
|
||||
fs.mkdirSync(nmDir, { recursive: true });
|
||||
fs.writeFileSync(path.join(srcDir, 'index.ts'), 'export const x = 1;');
|
||||
fs.writeFileSync(path.join(nmDir, 'index.js'), 'module.exports = {};');
|
||||
|
||||
const config = { ...DEFAULT_CONFIG, rootDir: tempDir };
|
||||
const files = scanDirectory(tempDir, config);
|
||||
|
||||
expect(files).toContain('packages/app/src/index.ts');
|
||||
expect(files.every((f) => !f.includes('node_modules'))).toBe(true);
|
||||
});
|
||||
|
||||
it('should exclude .git directories', () => {
|
||||
const srcDir = path.join(tempDir, 'src');
|
||||
const gitDir = path.join(tempDir, '.git', 'objects');
|
||||
fs.mkdirSync(srcDir, { recursive: true });
|
||||
fs.mkdirSync(gitDir, { recursive: true });
|
||||
fs.writeFileSync(path.join(srcDir, 'index.ts'), 'export const x = 1;');
|
||||
fs.writeFileSync(path.join(gitDir, 'pack.ts'), 'export const y = 2;');
|
||||
|
||||
const config = { ...DEFAULT_CONFIG, rootDir: tempDir };
|
||||
const files = scanDirectory(tempDir, config);
|
||||
|
||||
expect(files).toContain('src/index.ts');
|
||||
expect(files.every((f) => !f.includes('.git'))).toBe(true);
|
||||
});
|
||||
|
||||
it('should return forward-slash paths on all platforms', () => {
|
||||
const srcDir = path.join(tempDir, 'src', 'components');
|
||||
fs.mkdirSync(srcDir, { recursive: true });
|
||||
fs.writeFileSync(path.join(srcDir, 'Button.tsx'), 'export function Button() {}');
|
||||
|
||||
const config = { ...DEFAULT_CONFIG, rootDir: tempDir };
|
||||
const files = scanDirectory(tempDir, config);
|
||||
|
||||
expect(files.length).toBe(1);
|
||||
expect(files[0]).toBe('src/components/Button.tsx');
|
||||
expect(files[0]).not.toContain('\\');
|
||||
});
|
||||
|
||||
it('should respect .codegraphignore marker', () => {
|
||||
const srcDir = path.join(tempDir, 'src');
|
||||
const vendorDir = path.join(tempDir, 'vendor');
|
||||
fs.mkdirSync(srcDir, { recursive: true });
|
||||
fs.mkdirSync(vendorDir, { recursive: true });
|
||||
fs.writeFileSync(path.join(srcDir, 'index.ts'), 'export const x = 1;');
|
||||
fs.writeFileSync(path.join(vendorDir, 'lib.ts'), 'export const y = 2;');
|
||||
fs.writeFileSync(path.join(vendorDir, '.codegraphignore'), '');
|
||||
|
||||
const config = { ...DEFAULT_CONFIG, rootDir: tempDir };
|
||||
const files = scanDirectory(tempDir, config);
|
||||
|
||||
expect(files).toContain('src/index.ts');
|
||||
expect(files.every((f) => !f.includes('vendor'))).toBe(true);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -0,0 +1,135 @@
|
||||
/**
|
||||
* Search Query Utilities Tests
|
||||
*
|
||||
* Tests multi-signal scoring, kind bonuses, and path relevance.
|
||||
*/
|
||||
|
||||
import { describe, it, expect } from 'vitest';
|
||||
import {
|
||||
extractSearchTerms,
|
||||
scorePathRelevance,
|
||||
kindBonus,
|
||||
STOP_WORDS,
|
||||
} from '../src/search/query-utils';
|
||||
|
||||
describe('Search Query Utilities', () => {
|
||||
describe('extractSearchTerms', () => {
|
||||
it('should extract meaningful terms from a query', () => {
|
||||
const terms = extractSearchTerms('find the login handler');
|
||||
expect(terms).toContain('login');
|
||||
expect(terms).toContain('handler');
|
||||
// 'find' and 'the' are stop words
|
||||
expect(terms).not.toContain('find');
|
||||
expect(terms).not.toContain('the');
|
||||
});
|
||||
|
||||
it('should filter stop words', () => {
|
||||
const terms = extractSearchTerms('how does the authentication work');
|
||||
expect(terms).not.toContain('how');
|
||||
expect(terms).not.toContain('does');
|
||||
expect(terms).not.toContain('the');
|
||||
expect(terms).toContain('authentication');
|
||||
expect(terms).toContain('work');
|
||||
});
|
||||
|
||||
it('should handle camelCase by lowercasing', () => {
|
||||
const terms = extractSearchTerms('UserService');
|
||||
expect(terms).toContain('userservice');
|
||||
});
|
||||
|
||||
it('should strip punctuation', () => {
|
||||
const terms = extractSearchTerms('payment.process()');
|
||||
expect(terms).toContain('payment');
|
||||
expect(terms).toContain('process');
|
||||
});
|
||||
|
||||
it('should return empty for all stop words', () => {
|
||||
const terms = extractSearchTerms('how do I get the');
|
||||
expect(terms).toHaveLength(0);
|
||||
});
|
||||
|
||||
it('should filter single-character terms', () => {
|
||||
const terms = extractSearchTerms('a b c auth');
|
||||
expect(terms).toEqual(['auth']);
|
||||
});
|
||||
});
|
||||
|
||||
describe('scorePathRelevance', () => {
|
||||
it('should score filename matches highest', () => {
|
||||
const score = scorePathRelevance('src/auth/login.ts', 'login');
|
||||
expect(score).toBeGreaterThanOrEqual(10);
|
||||
});
|
||||
|
||||
it('should score directory matches', () => {
|
||||
const score = scorePathRelevance('src/auth/index.ts', 'auth');
|
||||
expect(score).toBeGreaterThanOrEqual(5);
|
||||
});
|
||||
|
||||
it('should return 0 for unrelated paths', () => {
|
||||
const score = scorePathRelevance('src/utils/format.ts', 'payment');
|
||||
expect(score).toBe(0);
|
||||
});
|
||||
|
||||
it('should accumulate scores for multiple matching terms', () => {
|
||||
const score = scorePathRelevance('src/auth/login.ts', 'auth login');
|
||||
// Both 'auth' (dir match) and 'login' (filename match)
|
||||
expect(score).toBeGreaterThanOrEqual(15);
|
||||
});
|
||||
|
||||
it('should return 0 for empty query terms', () => {
|
||||
const score = scorePathRelevance('src/auth/login.ts', 'the a an');
|
||||
expect(score).toBe(0);
|
||||
});
|
||||
});
|
||||
|
||||
describe('kindBonus', () => {
|
||||
it('should give functions and methods highest bonus', () => {
|
||||
expect(kindBonus('function')).toBe(10);
|
||||
expect(kindBonus('method')).toBe(10);
|
||||
});
|
||||
|
||||
it('should rank functions > classes > variables > imports', () => {
|
||||
expect(kindBonus('function')).toBeGreaterThan(kindBonus('class'));
|
||||
expect(kindBonus('class')).toBeGreaterThan(kindBonus('variable'));
|
||||
expect(kindBonus('variable')).toBeGreaterThan(kindBonus('import'));
|
||||
});
|
||||
|
||||
it('should give routes high priority', () => {
|
||||
expect(kindBonus('route')).toBeGreaterThanOrEqual(9);
|
||||
});
|
||||
|
||||
it('should give components high priority', () => {
|
||||
expect(kindBonus('component')).toBeGreaterThanOrEqual(8);
|
||||
});
|
||||
|
||||
it('should return 0 for parameter and file kinds', () => {
|
||||
expect(kindBonus('parameter')).toBe(0);
|
||||
expect(kindBonus('file')).toBe(0);
|
||||
});
|
||||
|
||||
it('should return 0 for unknown kinds', () => {
|
||||
expect(kindBonus('unknown_kind' as any)).toBe(0);
|
||||
});
|
||||
});
|
||||
|
||||
describe('STOP_WORDS', () => {
|
||||
it('should contain common English stop words', () => {
|
||||
expect(STOP_WORDS.has('the')).toBe(true);
|
||||
expect(STOP_WORDS.has('and')).toBe(true);
|
||||
expect(STOP_WORDS.has('or')).toBe(true);
|
||||
});
|
||||
|
||||
it('should contain action verbs used in queries', () => {
|
||||
expect(STOP_WORDS.has('find')).toBe(true);
|
||||
expect(STOP_WORDS.has('show')).toBe(true);
|
||||
expect(STOP_WORDS.has('get')).toBe(true);
|
||||
expect(STOP_WORDS.has('list')).toBe(true);
|
||||
});
|
||||
|
||||
it('should not contain technical terms', () => {
|
||||
expect(STOP_WORDS.has('function')).toBe(false);
|
||||
expect(STOP_WORDS.has('class')).toBe(false);
|
||||
expect(STOP_WORDS.has('auth')).toBe(false);
|
||||
});
|
||||
});
|
||||
});
|
||||
@@ -8,6 +8,7 @@ import * as fs from 'fs';
|
||||
import * as path from 'path';
|
||||
import picomatch from 'picomatch';
|
||||
import { CodeGraphConfig, DEFAULT_CONFIG, Language, NodeKind } from './types';
|
||||
import { normalizePath } from './utils';
|
||||
|
||||
/**
|
||||
* Configuration filename
|
||||
@@ -269,6 +270,9 @@ export function addCustomPattern(
|
||||
* Check if a file path matches the include/exclude patterns
|
||||
*/
|
||||
export function shouldIncludeFile(filePath: string, config: CodeGraphConfig): boolean {
|
||||
// Normalize to forward slashes so Windows backslash paths match glob patterns
|
||||
filePath = normalizePath(filePath);
|
||||
|
||||
// Simple glob matching (for now, just check if any pattern matches)
|
||||
// A full implementation would use a proper glob library
|
||||
|
||||
|
||||
+13
-1
@@ -18,6 +18,7 @@ import {
|
||||
SearchResult,
|
||||
} from '../types';
|
||||
import { safeJsonParse } from '../utils';
|
||||
import { kindBonus, scorePathRelevance } from '../search/query-utils';
|
||||
|
||||
/**
|
||||
* Database row types (snake_case from SQLite)
|
||||
@@ -451,6 +452,15 @@ export class QueryBuilder {
|
||||
results = this.searchNodesLike(query, { kinds, languages, limit, offset });
|
||||
}
|
||||
|
||||
// Apply multi-signal scoring
|
||||
if (results.length > 0 && query) {
|
||||
results = results.map(r => ({
|
||||
...r,
|
||||
score: r.score + kindBonus(r.node.kind) + scorePathRelevance(r.node.filePath, query),
|
||||
}));
|
||||
results.sort((a, b) => b.score - a.score);
|
||||
}
|
||||
|
||||
return results;
|
||||
}
|
||||
|
||||
@@ -463,9 +473,11 @@ export class QueryBuilder {
|
||||
// Add prefix wildcard for better matching (e.g., "auth" matches "AuthService", "authenticate")
|
||||
// Escape special FTS5 characters and add prefix wildcard
|
||||
const ftsQuery = query
|
||||
.replace(/['"*()]/g, '') // Remove special chars
|
||||
.replace(/['"*():^]/g, '') // Remove FTS5 special chars
|
||||
.split(/\s+/)
|
||||
.filter(term => term.length > 0)
|
||||
// Strip FTS5 boolean operators to prevent query manipulation
|
||||
.filter(term => !/^(AND|OR|NOT|NEAR)$/i.test(term))
|
||||
.map(term => `"${term}"*`) // Prefix match each term
|
||||
.join(' OR ');
|
||||
|
||||
|
||||
+147
-33
@@ -8,6 +8,7 @@ import * as fs from 'fs';
|
||||
import * as fsp from 'fs/promises';
|
||||
import * as path from 'path';
|
||||
import * as crypto from 'crypto';
|
||||
import { execFileSync } from 'child_process';
|
||||
import {
|
||||
Language,
|
||||
FileRecord,
|
||||
@@ -18,9 +19,16 @@ import {
|
||||
import { QueryBuilder } from '../db/queries';
|
||||
import { extractFromSource } from './tree-sitter';
|
||||
import { detectLanguage, isLanguageSupported } from './grammars';
|
||||
import { logDebug } from '../errors';
|
||||
import { logDebug, logWarn } from '../errors';
|
||||
import { captureException } from '../sentry';
|
||||
import { validatePathWithinRoot } from '../utils';
|
||||
import { validatePathWithinRoot, normalizePath } from '../utils';
|
||||
import picomatch from 'picomatch';
|
||||
|
||||
/**
|
||||
* Number of files to read in parallel during indexing.
|
||||
* File reads are I/O-bound; batching overlaps I/O wait with CPU parse work.
|
||||
*/
|
||||
const FILE_IO_BATCH_SIZE = 10;
|
||||
|
||||
/**
|
||||
* Progress callback for indexing operations
|
||||
@@ -68,7 +76,7 @@ export function hashContent(content: string): string {
|
||||
* Check if a path matches any glob pattern (simplified)
|
||||
*/
|
||||
function matchesGlob(filePath: string, pattern: string): boolean {
|
||||
const picomatch = require('picomatch');
|
||||
filePath = normalizePath(filePath);
|
||||
return picomatch.isMatch(filePath, pattern, { dot: true });
|
||||
}
|
||||
|
||||
@@ -96,6 +104,31 @@ export function shouldIncludeFile(
|
||||
return false;
|
||||
}
|
||||
|
||||
/**
|
||||
* Get directories ignored by .gitignore using git ls-files.
|
||||
* Returns a Set of normalized relative directory paths (forward slashes, no trailing slash).
|
||||
* Gracefully returns empty Set on any failure.
|
||||
*/
|
||||
function getGitIgnoredDirectories(rootDir: string): Set<string> {
|
||||
try {
|
||||
const output = execFileSync(
|
||||
'git',
|
||||
['ls-files', '-oi', '--exclude-standard', '--directory'],
|
||||
{ cwd: rootDir, encoding: 'utf-8', timeout: 10000, stdio: ['pipe', 'pipe', 'pipe'] }
|
||||
);
|
||||
const dirs = new Set<string>();
|
||||
for (const line of output.split('\n')) {
|
||||
const trimmed = line.trim();
|
||||
if (trimmed.endsWith('/')) {
|
||||
dirs.add(normalizePath(trimmed.slice(0, -1)));
|
||||
}
|
||||
}
|
||||
return dirs;
|
||||
} catch {
|
||||
return new Set<string>();
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* Marker file name that indicates a directory (and all children) should be skipped
|
||||
*/
|
||||
@@ -111,22 +144,26 @@ export function scanDirectory(
|
||||
): string[] {
|
||||
const files: string[] = [];
|
||||
let count = 0;
|
||||
const visitedRealPaths = new Set<string>(); // Symlink cycle detection
|
||||
// Track visited real paths to detect symlink cycles
|
||||
const visitedDirs = new Set<string>();
|
||||
const gitIgnoredDirs = getGitIgnoredDirectories(rootDir);
|
||||
|
||||
function walk(dir: string): void {
|
||||
// Symlink cycle detection: resolve real path and skip if already visited
|
||||
// Resolve real path to detect symlink cycles
|
||||
let realDir: string;
|
||||
try {
|
||||
const realDir = fs.realpathSync(dir);
|
||||
if (visitedRealPaths.has(realDir)) {
|
||||
logDebug('Skipping directory to prevent symlink cycle', { dir, realDir });
|
||||
return;
|
||||
}
|
||||
visitedRealPaths.add(realDir);
|
||||
realDir = fs.realpathSync(dir);
|
||||
} catch {
|
||||
// If realpath fails, skip this directory
|
||||
logDebug('Skipping unresolvable directory', { dir });
|
||||
return;
|
||||
}
|
||||
|
||||
if (visitedDirs.has(realDir)) {
|
||||
logDebug('Skipping already-visited directory (symlink cycle)', { dir, realDir });
|
||||
return;
|
||||
}
|
||||
visitedDirs.add(realDir);
|
||||
|
||||
// Check for .codegraphignore marker file - skip entire directory tree if present
|
||||
const ignoreMarker = path.join(dir, CODEGRAPH_IGNORE_MARKER);
|
||||
if (fs.existsSync(ignoreMarker)) {
|
||||
@@ -145,7 +182,7 @@ export function scanDirectory(
|
||||
|
||||
for (const entry of entries) {
|
||||
const fullPath = path.join(dir, entry.name);
|
||||
const relativePath = path.relative(rootDir, fullPath);
|
||||
const relativePath = normalizePath(path.relative(rootDir, fullPath));
|
||||
|
||||
// Follow symlinked directories, but skip symlinked files to non-project targets
|
||||
if (entry.isSymbolicLink()) {
|
||||
@@ -153,6 +190,10 @@ export function scanDirectory(
|
||||
const realTarget = fs.realpathSync(fullPath);
|
||||
const stat = fs.statSync(realTarget);
|
||||
if (stat.isDirectory()) {
|
||||
// Check gitignore first (fast O(1) lookup)
|
||||
if (gitIgnoredDirs.has(relativePath)) {
|
||||
continue;
|
||||
}
|
||||
// Check exclusion, then recurse (cycle detection handles the rest)
|
||||
const dirPattern = relativePath + '/';
|
||||
let excluded = false;
|
||||
@@ -181,6 +222,10 @@ export function scanDirectory(
|
||||
}
|
||||
|
||||
if (entry.isDirectory()) {
|
||||
// Check gitignore first (fast O(1) lookup)
|
||||
if (gitIgnoredDirs.has(relativePath)) {
|
||||
continue;
|
||||
}
|
||||
// Check if directory should be excluded
|
||||
const dirPattern = relativePath + '/';
|
||||
let excluded = false;
|
||||
@@ -265,10 +310,11 @@ export class ExtractionOrchestrator {
|
||||
};
|
||||
}
|
||||
|
||||
// Phase 2: Parse files
|
||||
// Phase 2: Parse files (read in parallel batches, parse/store sequentially)
|
||||
const total = files.length;
|
||||
let processed = 0;
|
||||
|
||||
for (let i = 0; i < files.length; i++) {
|
||||
for (let i = 0; i < files.length; i += FILE_IO_BATCH_SIZE) {
|
||||
if (signal?.aborted) {
|
||||
return {
|
||||
success: false,
|
||||
@@ -281,26 +327,69 @@ export class ExtractionOrchestrator {
|
||||
};
|
||||
}
|
||||
|
||||
const filePath = files[i]!;
|
||||
onProgress?.({
|
||||
phase: 'parsing',
|
||||
current: i + 1,
|
||||
total,
|
||||
currentFile: filePath,
|
||||
});
|
||||
const batch = files.slice(i, i + FILE_IO_BATCH_SIZE);
|
||||
|
||||
const result = await this.indexFile(filePath);
|
||||
// Read files in parallel (with path validation before any I/O)
|
||||
const fileContents = await Promise.all(
|
||||
batch.map(async (fp) => {
|
||||
try {
|
||||
const fullPath = validatePathWithinRoot(this.rootDir, fp);
|
||||
if (!fullPath) {
|
||||
logWarn('Path traversal blocked in batch reader', { filePath: fp });
|
||||
return { filePath: fp, content: null as string | null, stats: null as fs.Stats | null, error: new Error('Path traversal blocked') };
|
||||
}
|
||||
const content = await fsp.readFile(fullPath, 'utf-8');
|
||||
const stats = await fsp.stat(fullPath);
|
||||
return { filePath: fp, content, stats, error: null as Error | null };
|
||||
} catch (err) {
|
||||
return { filePath: fp, content: null as string | null, stats: null as fs.Stats | null, error: err as Error };
|
||||
}
|
||||
})
|
||||
);
|
||||
|
||||
if (result.errors.length > 0) {
|
||||
errors.push(...result.errors);
|
||||
}
|
||||
// Parse and store sequentially
|
||||
for (const { filePath, content, stats, error } of fileContents) {
|
||||
if (signal?.aborted) {
|
||||
return {
|
||||
success: false,
|
||||
filesIndexed,
|
||||
filesSkipped,
|
||||
nodesCreated: totalNodes,
|
||||
edgesCreated: totalEdges,
|
||||
errors: [{ message: 'Aborted', severity: 'error' }, ...errors],
|
||||
durationMs: Date.now() - startTime,
|
||||
};
|
||||
}
|
||||
|
||||
if (result.nodes.length > 0) {
|
||||
filesIndexed++;
|
||||
totalNodes += result.nodes.length;
|
||||
totalEdges += result.edges.length;
|
||||
} else if (result.errors.length === 0) {
|
||||
filesSkipped++;
|
||||
processed++;
|
||||
onProgress?.({
|
||||
phase: 'parsing',
|
||||
current: processed,
|
||||
total,
|
||||
currentFile: filePath,
|
||||
});
|
||||
|
||||
if (error || content === null || stats === null) {
|
||||
errors.push({
|
||||
message: `Failed to read file: ${error instanceof Error ? error.message : String(error)}`,
|
||||
severity: 'error',
|
||||
});
|
||||
continue;
|
||||
}
|
||||
|
||||
const result = await this.indexFileWithContent(filePath, content, stats);
|
||||
|
||||
if (result.errors.length > 0) {
|
||||
errors.push(...result.errors);
|
||||
}
|
||||
|
||||
if (result.nodes.length > 0) {
|
||||
filesIndexed++;
|
||||
totalNodes += result.nodes.length;
|
||||
totalEdges += result.edges.length;
|
||||
} else if (result.errors.length === 0) {
|
||||
filesSkipped++;
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -378,7 +467,7 @@ export class ExtractionOrchestrator {
|
||||
};
|
||||
}
|
||||
|
||||
// Check file exists and is readable
|
||||
// Read file content and stats
|
||||
let content: string;
|
||||
let stats: fs.Stats;
|
||||
try {
|
||||
@@ -400,6 +489,31 @@ export class ExtractionOrchestrator {
|
||||
};
|
||||
}
|
||||
|
||||
return this.indexFileWithContent(relativePath, content, stats);
|
||||
}
|
||||
|
||||
/**
|
||||
* Index a single file with pre-read content and stats.
|
||||
* Used by the parallel batch reader to avoid redundant file I/O.
|
||||
*/
|
||||
async indexFileWithContent(
|
||||
relativePath: string,
|
||||
content: string,
|
||||
stats: fs.Stats
|
||||
): Promise<ExtractionResult> {
|
||||
// Prevent path traversal
|
||||
const fullPath = validatePathWithinRoot(this.rootDir, relativePath);
|
||||
if (!fullPath) {
|
||||
logWarn('Path traversal blocked in indexFileWithContent', { relativePath });
|
||||
return {
|
||||
nodes: [],
|
||||
edges: [],
|
||||
unresolvedReferences: [],
|
||||
errors: [{ message: 'Path traversal blocked', severity: 'error' }],
|
||||
durationMs: 0,
|
||||
};
|
||||
}
|
||||
|
||||
// Check file size
|
||||
if (stats.size > this.config.maxFileSize) {
|
||||
return {
|
||||
|
||||
@@ -6,6 +6,7 @@
|
||||
|
||||
import { SyntaxNode, Tree } from 'tree-sitter';
|
||||
import * as crypto from 'crypto';
|
||||
import * as path from 'path';
|
||||
import {
|
||||
Language,
|
||||
Node,
|
||||
@@ -875,7 +876,28 @@ export class TreeSitterExtractor {
|
||||
|
||||
try {
|
||||
this.tree = parser.parse(this.source);
|
||||
|
||||
// Create file node representing the source file
|
||||
const fileNode: Node = {
|
||||
id: `file:${this.filePath}`,
|
||||
kind: 'file',
|
||||
name: path.basename(this.filePath),
|
||||
qualifiedName: this.filePath,
|
||||
filePath: this.filePath,
|
||||
language: this.language,
|
||||
startLine: 1,
|
||||
endLine: this.source.split('\n').length,
|
||||
startColumn: 0,
|
||||
endColumn: 0,
|
||||
isExported: false,
|
||||
updatedAt: Date.now(),
|
||||
};
|
||||
this.nodes.push(fileNode);
|
||||
|
||||
// Push file node onto stack so top-level declarations get contains edges
|
||||
this.nodeStack.push(fileNode.id);
|
||||
this.visitNode(this.tree.rootNode);
|
||||
this.nodeStack.pop();
|
||||
} catch (error) {
|
||||
captureException(error, { operation: 'tree-sitter-parse', filePath: this.filePath, language: this.language });
|
||||
this.errors.push({
|
||||
@@ -905,7 +927,7 @@ export class TreeSitterExtractor {
|
||||
// Check for function declarations
|
||||
// For Python/Ruby, function_definition inside a class should be treated as method
|
||||
if (this.extractor.functionTypes.includes(nodeType)) {
|
||||
if (this.nodeStack.length > 0 && this.extractor.methodTypes.includes(nodeType)) {
|
||||
if (this.isInsideClassLikeNode() && this.extractor.methodTypes.includes(nodeType)) {
|
||||
// Inside a class - treat as method
|
||||
this.extractMethod(node);
|
||||
skipChildren = true; // extractMethod visits children via visitFunctionBody
|
||||
@@ -958,7 +980,7 @@ export class TreeSitterExtractor {
|
||||
}
|
||||
// Check for variable declarations (const, let, var, etc.)
|
||||
// Only extract top-level variables (not inside functions/methods)
|
||||
else if (this.extractor.variableTypes.includes(nodeType) && this.nodeStack.length === 0) {
|
||||
else if (this.extractor.variableTypes.includes(nodeType) && !this.isInsideClassLikeNode()) {
|
||||
this.extractVariable(node);
|
||||
skipChildren = true; // extractVariable handles children
|
||||
}
|
||||
@@ -1060,6 +1082,25 @@ export class TreeSitterExtractor {
|
||||
return false;
|
||||
}
|
||||
|
||||
/**
|
||||
* Check if the current node stack indicates we are inside a class-like node
|
||||
* (class, struct, interface, trait). File nodes do not count as class-like.
|
||||
*/
|
||||
private isInsideClassLikeNode(): boolean {
|
||||
if (this.nodeStack.length === 0) return false;
|
||||
const parentId = this.nodeStack[this.nodeStack.length - 1];
|
||||
if (!parentId) return false;
|
||||
const parentNode = this.nodes.find((n) => n.id === parentId);
|
||||
if (!parentNode) return false;
|
||||
return (
|
||||
parentNode.kind === 'class' ||
|
||||
parentNode.kind === 'struct' ||
|
||||
parentNode.kind === 'interface' ||
|
||||
parentNode.kind === 'trait' ||
|
||||
parentNode.kind === 'enum'
|
||||
);
|
||||
}
|
||||
|
||||
/**
|
||||
* Extract a function
|
||||
*/
|
||||
@@ -1160,10 +1201,10 @@ export class TreeSitterExtractor {
|
||||
private extractMethod(node: SyntaxNode): void {
|
||||
if (!this.extractor) return;
|
||||
|
||||
// For most languages, only extract as method if inside a class
|
||||
// For most languages, only extract as method if inside a class-like node
|
||||
// But Go methods are top-level with a receiver, so always treat them as methods
|
||||
if (this.nodeStack.length === 0 && this.language !== 'go') {
|
||||
// Top-level and not Go, treat as function
|
||||
if (!this.isInsideClassLikeNode() && this.language !== 'go') {
|
||||
// Not inside a class-like node and not Go, treat as function
|
||||
this.extractFunction(node);
|
||||
return;
|
||||
}
|
||||
|
||||
@@ -0,0 +1,89 @@
|
||||
/**
|
||||
* Search Query Utilities
|
||||
*
|
||||
* Shared module for search term extraction and scoring.
|
||||
*/
|
||||
|
||||
import * as path from 'path';
|
||||
import { Node } from '../types';
|
||||
|
||||
/**
|
||||
* Common stop words to filter from search queries
|
||||
*/
|
||||
export const STOP_WORDS = new Set([
|
||||
'the', 'a', 'an', 'and', 'or', 'but', 'in', 'on', 'at', 'to', 'for',
|
||||
'of', 'with', 'by', 'from', 'is', 'it', 'that', 'this', 'are', 'was',
|
||||
'be', 'has', 'had', 'have', 'do', 'does', 'did', 'will', 'would', 'could',
|
||||
'should', 'may', 'might', 'can', 'shall', 'not', 'no', 'all', 'each',
|
||||
'every', 'how', 'what', 'where', 'when', 'who', 'which', 'why',
|
||||
'i', 'me', 'my', 'we', 'our', 'you', 'your', 'he', 'she', 'they',
|
||||
'find', 'show', 'get', 'list', 'give', 'tell',
|
||||
]);
|
||||
|
||||
/**
|
||||
* Extract meaningful search terms from a natural language query
|
||||
*/
|
||||
export function extractSearchTerms(query: string): string[] {
|
||||
return query
|
||||
.toLowerCase()
|
||||
.replace(/[^\w\s-]/g, ' ')
|
||||
.split(/\s+/)
|
||||
.filter(term => term.length > 1 && !STOP_WORDS.has(term));
|
||||
}
|
||||
|
||||
/**
|
||||
* Score path relevance to a query
|
||||
* Higher score = more relevant path
|
||||
*/
|
||||
export function scorePathRelevance(filePath: string, query: string): number {
|
||||
const terms = extractSearchTerms(query);
|
||||
if (terms.length === 0) return 0;
|
||||
|
||||
const pathLower = filePath.toLowerCase();
|
||||
const fileName = path.basename(filePath).toLowerCase();
|
||||
const dirName = path.dirname(filePath).toLowerCase();
|
||||
let score = 0;
|
||||
|
||||
for (const term of terms) {
|
||||
// Exact filename match (strongest)
|
||||
if (fileName.includes(term)) score += 10;
|
||||
// Directory match
|
||||
if (dirName.includes(term)) score += 5;
|
||||
// General path match
|
||||
else if (pathLower.includes(term)) score += 3;
|
||||
}
|
||||
|
||||
return score;
|
||||
}
|
||||
|
||||
/**
|
||||
* Kind-based bonus for search ranking
|
||||
* Functions and classes are typically more relevant than variables/imports
|
||||
*/
|
||||
export function kindBonus(kind: Node['kind']): number {
|
||||
const bonuses: Record<string, number> = {
|
||||
function: 10,
|
||||
method: 10,
|
||||
class: 8,
|
||||
interface: 7,
|
||||
type_alias: 6,
|
||||
struct: 6,
|
||||
trait: 6,
|
||||
enum: 5,
|
||||
component: 8,
|
||||
route: 9,
|
||||
module: 4,
|
||||
property: 3,
|
||||
field: 3,
|
||||
variable: 2,
|
||||
constant: 3,
|
||||
import: 1,
|
||||
export: 1,
|
||||
parameter: 0,
|
||||
namespace: 4,
|
||||
file: 0,
|
||||
protocol: 6,
|
||||
enum_member: 3,
|
||||
};
|
||||
return bonuses[kind] ?? 0;
|
||||
}
|
||||
@@ -166,6 +166,14 @@ export function clamp(value: number, min: number, max: number): number {
|
||||
return Math.max(min, Math.min(max, value));
|
||||
}
|
||||
|
||||
/**
|
||||
* Normalize a file path to use forward slashes.
|
||||
* Fixes Windows backslash paths so glob matching works consistently.
|
||||
*/
|
||||
export function normalizePath(filePath: string): string {
|
||||
return filePath.replace(/\\/g, '/');
|
||||
}
|
||||
|
||||
/**
|
||||
* Cross-process file lock using a lock file with PID tracking.
|
||||
*
|
||||
|
||||
Reference in New Issue
Block a user