mirror of
https://github.com/abhigyanpatwari/GitNexus.git
synced 2026-09-07 08:26:11 +00:00
7376e92063
* fix: consolidate C/C++/C#/Rust language support from 6 overlapping PRs Merges fixes from PRs #163, #170, #178, #216, #227, #234 into a single coherent changeset with shared modules and deduplication. Phase 0 — Pre-merge consolidation: - Extract isNodeExported to shared export-detection.ts module - Extract TREE_SITTER_BUFFER_SIZE to shared constants.ts with adaptive sizing - Consolidate FUNCTION_NODE_TYPES, extractFunctionName, isBuiltInOrNoise from duplicated call-processor.ts and parse-worker.ts into shared utils.ts - Add query compilation smoke tests for all 12 languages Language fixes: - fix(c/cpp): isExported checks static linkage instead of returning false - fix(c/cpp): .h files parsed as C++ (tree-sitter-cpp is superset of C) - fix(c/cpp): expanded entry point patterns (~30 new for C, ~18 for C++) - fix(cpp): add typedef, union, macro, prototype, inline method queries - fix(c#): isExported scans sibling modifiers instead of parent walk - fix(c#): heritage queries use correct base_list AST structure - fix(c#): add framework detection, import resolution, entry point scoring - fix(rust): isExported scans sibling visibility_modifier in declaration - fix(builtins): remove open/read/write/close (real C POSIX syscalls) - fix(buffer): adaptive bufferSize (2x fileSize, 512KB-32MB range) - feat(ts/js): add call_expression query patterns for const assignments Deduplication: - call-processor.ts: -226 lines (uses shared utils) - parse-worker.ts: -320 lines (uses shared utils) - parsing-processor.ts: -156 lines (uses shared export-detection) * perf: fix review findings — hoist Sets, deduplicate DEFINITION_CAPTURE_KEYS - Hoist CSHARP_DECL_TYPES and RUST_DECL_TYPES to module-level constants in export-detection.ts (was allocating new Set on every isNodeExported call) - Extract DEFINITION_CAPTURE_KEYS and getDefinitionNodeFromCaptures to shared utils.ts (was duplicated in parsing-processor.ts and parse-worker.ts) - Pre-compute merged entry point patterns to avoid per-call array spread in calculateEntryPointScore * test: add C, C++, and Tree-sitter buffer size tests * fix: C/C++/Rust review findings + comprehensive test coverage (+72 tests) Source fixes: - Add Rust built-in noise (unwrap, clone, into, collect, panic, etc.) - C++ anonymous namespace → internal linkage (not exported) - Replace .text regex with storage_class_specifier child scan (perf) - Raise file skip threshold from 512KB to 32MB (TREE_SITTER_MAX_BUFFER) - Export TREE_SITTER_MAX_BUFFER from constants.ts - Add C++ double pointer query patterns to CPP_QUERIES - Add C#: record_struct, record_class, file_scoped_namespace to decl types - Add Rust: union_item to visibility scanning set Tests (214 → 286): - ingestion-utils: +24 (Rust/C# noise, pointer/ref/destructor extraction, buffer) - parsing: +36 (real AST C/C++ static/namespace, Rust/C#/Java/PHP/Swift edge cases) - tree-sitter-languages: +12 (query accuracy for C/C++/C#/Rust captures)
61 lines
2.4 KiB
TypeScript
61 lines
2.4 KiB
TypeScript
import { describe, it, expect, beforeAll } from 'vitest';
|
|
import { loadParser, loadLanguage, isLanguageAvailable } from '../../src/core/tree-sitter/parser-loader.js';
|
|
import { LANGUAGE_QUERIES } from '../../src/core/ingestion/tree-sitter-queries.js';
|
|
import { SupportedLanguages } from '../../src/config/supported-languages.js';
|
|
import Parser from 'tree-sitter';
|
|
|
|
/**
|
|
* Smoke test: verify that every LANGUAGE_QUERIES entry compiles against
|
|
* its tree-sitter grammar without throwing. A silent Query compilation
|
|
* failure is the #1 cause of "0 nodes extracted for language X" bugs.
|
|
*/
|
|
describe('Query compilation smoke tests', () => {
|
|
let parser: Parser;
|
|
|
|
beforeAll(async () => {
|
|
parser = await loadParser();
|
|
});
|
|
|
|
const languageFiles: Record<string, string> = {
|
|
[SupportedLanguages.TypeScript]: 'test.ts',
|
|
[SupportedLanguages.JavaScript]: 'test.js',
|
|
[SupportedLanguages.Python]: 'test.py',
|
|
[SupportedLanguages.Java]: 'Test.java',
|
|
[SupportedLanguages.C]: 'test.c',
|
|
[SupportedLanguages.CPlusPlus]: 'test.cpp',
|
|
[SupportedLanguages.CSharp]: 'Test.cs',
|
|
[SupportedLanguages.Go]: 'test.go',
|
|
[SupportedLanguages.Rust]: 'test.rs',
|
|
[SupportedLanguages.PHP]: 'test.php',
|
|
[SupportedLanguages.Kotlin]: 'Test.kt',
|
|
[SupportedLanguages.Swift]: 'test.swift',
|
|
};
|
|
|
|
// Known query compilation failures — remove from this set as PRs fix them
|
|
const knownFailures = new Set<string>([]);
|
|
|
|
for (const [lang, filename] of Object.entries(languageFiles)) {
|
|
const testFn = knownFailures.has(lang) ? it.fails : it;
|
|
|
|
testFn(`compiles query for ${lang}`, async () => {
|
|
if (!isLanguageAvailable(lang as SupportedLanguages)) {
|
|
return; // parser binary not available in this environment
|
|
}
|
|
|
|
await loadLanguage(lang as SupportedLanguages, filename);
|
|
const queryStr = LANGUAGE_QUERIES[lang as SupportedLanguages];
|
|
expect(queryStr).toBeTruthy();
|
|
|
|
const grammar = parser.getLanguage();
|
|
// This is the line that silently fails in production when queries
|
|
// use node types that don't exist in the grammar.
|
|
const query = new Parser.Query(grammar, queryStr);
|
|
expect(query).toBeDefined();
|
|
|
|
// Verify it can actually run against a minimal tree
|
|
const tree = parser.parse('');
|
|
const matches = query.matches(tree.rootNode);
|
|
expect(Array.isArray(matches)).toBe(true);
|
|
});
|
|
}
|
|
});
|