feat: wire up framework route extraction (#89)

* 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>
This commit is contained in:
timomeara
2026-05-07 22:03:33 -05:00
committed by GitHub
co-authored by Colby McHenry Claude Opus 4.7
parent 5ab81746e8
commit 74327814ee
23 changed files with 3080 additions and 719 deletions
+52 -20
View File
@@ -23,6 +23,10 @@ import { LiquidExtractor } from './liquid-extractor';
import { SvelteExtractor } from './svelte-extractor';
import { DfmExtractor } from './dfm-extractor';
import { VueExtractor } from './vue-extractor';
import {
getAllFrameworkResolvers,
getApplicableFrameworks,
} from '../resolution/frameworks';
// Re-export for backward compatibility
export { generateNodeId } from './tree-sitter-helpers';
@@ -2474,43 +2478,71 @@ export class TreeSitterExtractor {
/**
* Extract nodes and edges from source code
* Extract nodes and edges from source code.
*
* If `frameworkNames` is provided, framework-specific extractors matching
* those names and the file's language are run after the tree-sitter pass.
* Their nodes/references/errors are merged into the returned result.
*/
export function extractFromSource(
filePath: string,
source: string,
language?: Language
language?: Language,
frameworkNames?: string[]
): ExtractionResult {
const detectedLanguage = language || detectLanguage(filePath, source);
const fileExtension = path.extname(filePath).toLowerCase();
let result: ExtractionResult;
// Use custom extractor for Svelte
if (detectedLanguage === 'svelte') {
const extractor = new SvelteExtractor(filePath, source);
return extractor.extract();
}
// Use custom extractor for Vue
if (detectedLanguage === 'vue') {
result = extractor.extract();
} else if (detectedLanguage === 'vue') {
// Use custom extractor for Vue
const extractor = new VueExtractor(filePath, source);
return extractor.extract();
}
// Use custom extractor for Liquid
if (detectedLanguage === 'liquid') {
result = extractor.extract();
} else if (detectedLanguage === 'liquid') {
// Use custom extractor for Liquid
const extractor = new LiquidExtractor(filePath, source);
return extractor.extract();
}
// Use custom extractor for DFM/FMX form files
if (
result = extractor.extract();
} else if (
detectedLanguage === 'pascal' &&
(fileExtension === '.dfm' || fileExtension === '.fmx')
) {
// Use custom extractor for DFM/FMX form files
const extractor = new DfmExtractor(filePath, source);
return extractor.extract();
result = extractor.extract();
} else {
const extractor = new TreeSitterExtractor(filePath, source, detectedLanguage);
result = extractor.extract();
}
const extractor = new TreeSitterExtractor(filePath, source, detectedLanguage);
return extractor.extract();
// Framework-specific extraction (routes, middleware, etc.)
if (frameworkNames && frameworkNames.length > 0) {
const allResolvers = getAllFrameworkResolvers();
const applicable = getApplicableFrameworks(
allResolvers.filter((r) => frameworkNames.includes(r.name)),
detectedLanguage
);
for (const fw of applicable) {
if (!fw.extract) continue;
try {
const fwResult = fw.extract(filePath, source);
result.nodes.push(...fwResult.nodes);
result.unresolvedReferences.push(...fwResult.references);
} catch (err) {
result.errors.push({
message: `Framework extractor '${fw.name}' failed: ${
err instanceof Error ? err.message : String(err)
}`,
filePath,
severity: 'warning',
});
}
}
}
return result;
}