* docs: add framework extract wiring plan
* feat(resolution): replace extractNodes with extract() returning nodes and references
* feat(resolution): add getApplicableFrameworks helper for per-language dispatch
* feat(django): emit route nodes and route->view references in extract()
* feat(flask,fastapi): emit route nodes and route->handler references
* feat(express): emit route nodes and route->handler references
* feat(laravel): emit route nodes and route->handler references
* feat(rails): emit route nodes and route->handler references
* feat(spring): emit route nodes and route->handler references
* feat(go): emit route nodes and route->handler references
* feat(rust): emit route nodes and route->handler references
* feat(aspnet): emit route nodes and route->handler references
* feat(swift,vapor): emit route nodes and route->handler references
* chore(react,svelte): migrate resolvers to extract() interface
* feat(extraction): run framework extractors after tree-sitter parse
* docs: document framework route extraction
* feat(strip-comments): add per-language comment stripper for framework extractors
Replaces comment characters and string-literal contents with spaces (not
removal) so source offsets stay valid for downstream regex match index ->
line number conversion. Handles Python triple-quoted docstrings, Ruby
=begin/=end, Rust nested block comments, and the standard //, #, /* */
forms across the supported languages.
This is consumed by framework extract() methods in a follow-up commit so
that commented-out / docstring routing examples don't surface as phantom
route nodes in the graph.
* feat(frameworks): strip comments before regex extraction (prevents phantom routes)
Pipes the per-language stripCommentsForRegex helper into every framework
extract() that scans raw source: django/flask/fastapi (python.ts),
express, laravel, rails, spring, go, rust, aspnet, vapor, plus
swiftui/uikit struct extraction in swift.ts.
Without this, examples like:
# path('/admin/', AdminPanel.as_view())
""" path('/users/', UserListView.as_view()) """
urlpatterns = [path('/real/', RealView.as_view())]
produced 3 phantom route nodes. Now only the real one is extracted.
Each framework gets a regression test in __tests__/frameworks.test.ts
asserting that line-, block-, docstring- and (where relevant)
heredoc-style commented-out routes do not surface as nodes.
---------
Co-authored-by: Colby McHenry <me@colbymchenry.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
102 lines
4.2 KiB
TypeScript
102 lines
4.2 KiB
TypeScript
/**
|
|
* Parse Worker
|
|
*
|
|
* Runs tree-sitter parsing in a separate thread so the main thread
|
|
* stays unblocked and the UI animation renders smoothly.
|
|
*/
|
|
|
|
import { parentPort } from 'worker_threads';
|
|
import { extractFromSource } from './tree-sitter';
|
|
import { detectLanguage, loadGrammarsForLanguages, resetParser } from './grammars';
|
|
import type { Language, ExtractionResult } from '../types';
|
|
|
|
// Emscripten prints `Aborted()` (and a follow-up RuntimeError diag
|
|
// line) directly to stderr when WASM aborts — before the JS catch
|
|
// runs. Worker stderr is inherited by the parent, so each crash leaks
|
|
// a noise line to the user's terminal even though the JS layer
|
|
// already handles the failure cleanly. Filter these specific lines
|
|
// out at the source. Real diagnostic output (anything we log
|
|
// ourselves) goes through console.* / parentPort and is unaffected.
|
|
//
|
|
// Caveats deliberately accepted:
|
|
// - Per-call match: each `write()` call is matched in isolation.
|
|
// If Emscripten ever splits `Aborted(` across two write()s (it
|
|
// doesn't today — synchronous abort prints the whole line at
|
|
// once via libc puts) the first fragment would leak. Buffering
|
|
// across calls would add complexity for a hypothetical case.
|
|
// - Substring exactness: the prefix `Aborted(` is the literal
|
|
// Emscripten signature. Any user code that legitimately writes
|
|
// a stderr line starting with that prefix would also be filtered;
|
|
// in practice no real diagnostic does.
|
|
{
|
|
const realWrite = process.stderr.write.bind(process.stderr);
|
|
process.stderr.write = ((
|
|
chunk: string | Uint8Array,
|
|
encoding?: BufferEncoding | ((err?: Error | null) => void),
|
|
cb?: (err?: Error | null) => void
|
|
): boolean => {
|
|
const s = typeof chunk === 'string' ? chunk : Buffer.from(chunk).toString('utf-8');
|
|
if (
|
|
s.startsWith('Aborted(') ||
|
|
s.includes('Build with -sASSERTIONS for more info')
|
|
) {
|
|
// Honour the Writable stream contract: callbacks must always
|
|
// fire even when the write is suppressed, or upstream code
|
|
// waiting on the drain signal would hang. Both overload forms
|
|
// are handled (`(chunk, cb)` and `(chunk, encoding, cb)`).
|
|
if (typeof encoding === 'function') encoding();
|
|
else if (cb) cb();
|
|
return true;
|
|
}
|
|
return realWrite(chunk as never, encoding as never, cb as never);
|
|
}) as typeof process.stderr.write;
|
|
}
|
|
|
|
const PARSER_RESET_INTERVAL = 5000;
|
|
const parseCounts = new Map<Language, number>();
|
|
|
|
parentPort!.on('message', async (msg: { type: string; id?: number; filePath?: string; content?: string; languages?: Language[]; frameworkNames?: string[] }) => {
|
|
if (msg.type === 'load-grammars') {
|
|
await loadGrammarsForLanguages(msg.languages!);
|
|
parentPort!.postMessage({ type: 'grammars-loaded' });
|
|
} else if (msg.type === 'parse') {
|
|
const { id, filePath, content, frameworkNames } = msg;
|
|
try {
|
|
const language = detectLanguage(filePath!, content);
|
|
const result: ExtractionResult = extractFromSource(filePath!, content!, language, frameworkNames);
|
|
|
|
// Periodic parser reset to reclaim WASM heap memory
|
|
const count = (parseCounts.get(language) ?? 0) + 1;
|
|
parseCounts.set(language, count);
|
|
if (count % PARSER_RESET_INTERVAL === 0) {
|
|
resetParser(language);
|
|
}
|
|
|
|
parentPort!.postMessage({ type: 'parse-result', id, result });
|
|
} catch (err) {
|
|
const message = err instanceof Error ? err.message : String(err);
|
|
|
|
// WASM memory errors leave the module in a corrupted state — all
|
|
// subsequent parses would also fail (cascading failures). Crash the
|
|
// worker so the main thread spawns a fresh one with a clean heap.
|
|
if (message.includes('memory access out of bounds') || message.includes('out of memory')) {
|
|
process.exit(1);
|
|
}
|
|
|
|
parentPort!.postMessage({
|
|
type: 'parse-result',
|
|
id,
|
|
result: {
|
|
nodes: [],
|
|
edges: [],
|
|
unresolvedReferences: [],
|
|
errors: [{ message: `Parse worker error: ${message}`, filePath: filePath!, severity: 'error', code: 'parse_error' }],
|
|
durationMs: 0,
|
|
} satisfies ExtractionResult,
|
|
});
|
|
}
|
|
} else if (msg.type === 'shutdown') {
|
|
parentPort!.postMessage({ type: 'shutdown-ack' });
|
|
}
|
|
});
|