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
co-authored by
Colby McHenry
Claude Opus 4.7
Colby McHenry
Claude Opus 4.7
parent
5ab81746e8
commit
74327814ee
+190
-207
@@ -5,173 +5,62 @@
|
||||
*/
|
||||
|
||||
import { Node } from '../../types';
|
||||
import { FrameworkResolver, UnresolvedRef, ResolvedRef, ResolutionContext } from '../types';
|
||||
import { FrameworkResolver, UnresolvedRef, ResolutionContext, FrameworkExtractionResult } from '../types';
|
||||
import { stripCommentsForRegex } from '../strip-comments';
|
||||
|
||||
export const djangoResolver: FrameworkResolver = {
|
||||
name: 'django',
|
||||
languages: ['python'],
|
||||
|
||||
detect(context: ResolutionContext): boolean {
|
||||
// Check for Django in requirements.txt or setup.py
|
||||
detect(context) {
|
||||
const requirements = context.readFile('requirements.txt');
|
||||
if (requirements && requirements.includes('django')) {
|
||||
return true;
|
||||
}
|
||||
|
||||
if (requirements && requirements.toLowerCase().includes('django')) return true;
|
||||
const setup = context.readFile('setup.py');
|
||||
if (setup && setup.includes('django')) {
|
||||
return true;
|
||||
}
|
||||
|
||||
if (setup && setup.toLowerCase().includes('django')) return true;
|
||||
const pyproject = context.readFile('pyproject.toml');
|
||||
if (pyproject && pyproject.includes('django')) {
|
||||
return true;
|
||||
}
|
||||
|
||||
// Check for manage.py (Django signature)
|
||||
if (pyproject && pyproject.toLowerCase().includes('django')) return true;
|
||||
return context.fileExists('manage.py');
|
||||
},
|
||||
|
||||
resolve(ref: UnresolvedRef, context: ResolutionContext): ResolvedRef | null {
|
||||
// Pattern 1: Model references
|
||||
resolve(ref, context) {
|
||||
if (ref.referenceName.endsWith('Model') || /^[A-Z][a-z]+$/.test(ref.referenceName)) {
|
||||
const result = resolveByNameAndKind(ref.referenceName, CLASS_KINDS, MODEL_DIRS, context);
|
||||
if (result) {
|
||||
return {
|
||||
original: ref,
|
||||
targetNodeId: result,
|
||||
confidence: 0.8,
|
||||
resolvedBy: 'framework',
|
||||
};
|
||||
}
|
||||
if (result) return { original: ref, targetNodeId: result, confidence: 0.8, resolvedBy: 'framework' };
|
||||
}
|
||||
|
||||
// Pattern 2: View references
|
||||
if (ref.referenceName.endsWith('View') || ref.referenceName.endsWith('ViewSet')) {
|
||||
const result = resolveByNameAndKind(ref.referenceName, VIEW_KINDS, VIEW_DIRS, context);
|
||||
if (result) {
|
||||
return {
|
||||
original: ref,
|
||||
targetNodeId: result,
|
||||
confidence: 0.8,
|
||||
resolvedBy: 'framework',
|
||||
};
|
||||
}
|
||||
if (result) return { original: ref, targetNodeId: result, confidence: 0.8, resolvedBy: 'framework' };
|
||||
}
|
||||
|
||||
// Pattern 3: Form references
|
||||
if (ref.referenceName.endsWith('Form')) {
|
||||
const result = resolveByNameAndKind(ref.referenceName, CLASS_KINDS, FORM_DIRS, context);
|
||||
if (result) {
|
||||
return {
|
||||
original: ref,
|
||||
targetNodeId: result,
|
||||
confidence: 0.8,
|
||||
resolvedBy: 'framework',
|
||||
};
|
||||
}
|
||||
if (result) return { original: ref, targetNodeId: result, confidence: 0.8, resolvedBy: 'framework' };
|
||||
}
|
||||
|
||||
return null;
|
||||
},
|
||||
|
||||
extractNodes(filePath: string, content: string): Node[] {
|
||||
extract(filePath, content) {
|
||||
if (!filePath.endsWith('.py')) return { nodes: [], references: [] };
|
||||
|
||||
const nodes: Node[] = [];
|
||||
const references: UnresolvedRef[] = [];
|
||||
const now = Date.now();
|
||||
const safe = stripCommentsForRegex(content, 'python');
|
||||
|
||||
// Extract URL patterns
|
||||
// path('route/', view, name='name')
|
||||
const urlPatterns = [
|
||||
/path\s*\(\s*['"]([^'"]+)['"],\s*(\w+)/g,
|
||||
/url\s*\(\s*r?['"]([^'"]+)['"],\s*(\w+)/g,
|
||||
];
|
||||
// path('url', handler, name=...) / re_path(r'...', handler) / url(r'...', handler)
|
||||
// Capture groups: 1=function name, 2=url string, 3=handler expr
|
||||
// Handler expr may contain one balanced () pair (e.g. View.as_view(), include('x.y'))
|
||||
const routeRegex = /\b(path|re_path|url)\s*\(\s*r?['"]([^'"]+)['"]\s*,\s*([\w.]+(?:\s*\([^)]*\))?)/g;
|
||||
|
||||
for (const pattern of urlPatterns) {
|
||||
let match;
|
||||
while ((match = pattern.exec(content)) !== null) {
|
||||
const [, urlPath] = match;
|
||||
const line = content.slice(0, match.index).split('\n').length;
|
||||
let match: RegExpExecArray | null;
|
||||
while ((match = routeRegex.exec(safe)) !== null) {
|
||||
const [, _fn, urlPath, handlerExpr] = match;
|
||||
const line = safe.slice(0, match.index).split('\n').length;
|
||||
|
||||
nodes.push({
|
||||
id: `route:${filePath}:${urlPath}:${line}`,
|
||||
kind: 'route',
|
||||
name: urlPath!,
|
||||
qualifiedName: `${filePath}::route:${urlPath}`,
|
||||
filePath,
|
||||
startLine: line,
|
||||
endLine: line,
|
||||
startColumn: 0,
|
||||
endColumn: match[0].length,
|
||||
language: 'python',
|
||||
updatedAt: now,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
return nodes;
|
||||
},
|
||||
};
|
||||
|
||||
export const flaskResolver: FrameworkResolver = {
|
||||
name: 'flask',
|
||||
|
||||
detect(context: ResolutionContext): boolean {
|
||||
const requirements = context.readFile('requirements.txt');
|
||||
if (requirements && (requirements.includes('flask') || requirements.includes('Flask'))) {
|
||||
return true;
|
||||
}
|
||||
|
||||
const pyproject = context.readFile('pyproject.toml');
|
||||
if (pyproject && pyproject.includes('flask')) {
|
||||
return true;
|
||||
}
|
||||
|
||||
// Check for Flask app pattern in common files
|
||||
const appFiles = ['app.py', 'application.py', 'main.py', '__init__.py'];
|
||||
for (const file of appFiles) {
|
||||
const content = context.readFile(file);
|
||||
if (content && content.includes('Flask(__name__)')) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
return false;
|
||||
},
|
||||
|
||||
resolve(ref: UnresolvedRef, context: ResolutionContext): ResolvedRef | null {
|
||||
// Pattern 1: Blueprint references
|
||||
if (ref.referenceName.endsWith('_bp') || ref.referenceName.endsWith('_blueprint')) {
|
||||
const result = resolveByNameAndKind(ref.referenceName, VARIABLE_KINDS, [], context);
|
||||
if (result) {
|
||||
return {
|
||||
original: ref,
|
||||
targetNodeId: result,
|
||||
confidence: 0.8,
|
||||
resolvedBy: 'framework',
|
||||
};
|
||||
}
|
||||
}
|
||||
|
||||
return null;
|
||||
},
|
||||
|
||||
extractNodes(filePath: string, content: string): Node[] {
|
||||
const nodes: Node[] = [];
|
||||
const now = Date.now();
|
||||
|
||||
// Extract Flask route decorators
|
||||
// @app.route('/path') or @blueprint.route('/path')
|
||||
const routePattern = /@(\w+)\.route\s*\(\s*['"]([^'"]+)['"]/g;
|
||||
|
||||
let match;
|
||||
while ((match = routePattern.exec(content)) !== null) {
|
||||
const [, _appOrBp, routePath] = match;
|
||||
const line = content.slice(0, match.index).split('\n').length;
|
||||
|
||||
nodes.push({
|
||||
id: `route:${filePath}:${routePath}:${line}`,
|
||||
const routeNode: Node = {
|
||||
id: `route:${filePath}:${line}:${urlPath}`,
|
||||
kind: 'route',
|
||||
name: `${routePath}`,
|
||||
qualifiedName: `${filePath}::route:${routePath}`,
|
||||
name: urlPath!,
|
||||
qualifiedName: `${filePath}::route:${urlPath}`,
|
||||
filePath,
|
||||
startLine: line,
|
||||
endLine: line,
|
||||
@@ -179,101 +68,195 @@ export const flaskResolver: FrameworkResolver = {
|
||||
endColumn: match[0].length,
|
||||
language: 'python',
|
||||
updatedAt: now,
|
||||
});
|
||||
};
|
||||
nodes.push(routeNode);
|
||||
|
||||
const handler = handlerExpr!.trim();
|
||||
const target = resolveHandlerName(handler);
|
||||
if (target) {
|
||||
references.push({
|
||||
fromNodeId: routeNode.id,
|
||||
referenceName: target.name,
|
||||
referenceKind: target.kind,
|
||||
line,
|
||||
column: 0,
|
||||
filePath,
|
||||
language: 'python',
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
return nodes;
|
||||
return { nodes, references };
|
||||
},
|
||||
};
|
||||
|
||||
/**
|
||||
* Parse a Django URL handler expression and return the symbol/module to link.
|
||||
* Returns null for shapes we can't confidently link (e.g. lambdas).
|
||||
*/
|
||||
function resolveHandlerName(expr: string): { name: string; kind: 'references' | 'imports' } | null {
|
||||
// include('module.path')
|
||||
const includeMatch = expr.match(/^include\s*\(\s*['"]([^'"]+)['"]/);
|
||||
if (includeMatch) return { name: includeMatch[1]!, kind: 'imports' };
|
||||
|
||||
// Strip trailing .as_view(...) or .as_view()
|
||||
let head = expr.replace(/\.as_view\s*\([^)]*\)\s*$/, '');
|
||||
// Drop any other trailing method call
|
||||
head = head.replace(/\.\w+\s*\([^)]*\)\s*$/, '');
|
||||
|
||||
const dotted = head.split('.').filter(Boolean);
|
||||
if (dotted.length === 0) return null;
|
||||
const last = dotted[dotted.length - 1]!;
|
||||
if (!/^[A-Za-z_][A-Za-z0-9_]*$/.test(last)) return null;
|
||||
|
||||
return { name: last, kind: 'references' };
|
||||
}
|
||||
|
||||
export const flaskResolver: FrameworkResolver = {
|
||||
name: 'flask',
|
||||
languages: ['python'],
|
||||
|
||||
detect(context) {
|
||||
const requirements = context.readFile('requirements.txt');
|
||||
if (requirements && /\bflask\b/i.test(requirements)) return true;
|
||||
const pyproject = context.readFile('pyproject.toml');
|
||||
if (pyproject && /\bflask\b/i.test(pyproject)) return true;
|
||||
for (const file of ['app.py', 'application.py', 'main.py', '__init__.py']) {
|
||||
const content = context.readFile(file);
|
||||
if (content && content.includes('Flask(__name__)')) return true;
|
||||
}
|
||||
return false;
|
||||
},
|
||||
|
||||
resolve(ref, context) {
|
||||
if (ref.referenceName.endsWith('_bp') || ref.referenceName.endsWith('_blueprint')) {
|
||||
const result = resolveByNameAndKind(ref.referenceName, VARIABLE_KINDS, [], context);
|
||||
if (result) return { original: ref, targetNodeId: result, confidence: 0.8, resolvedBy: 'framework' };
|
||||
}
|
||||
return null;
|
||||
},
|
||||
|
||||
extract(filePath, content) {
|
||||
if (!filePath.endsWith('.py')) return { nodes: [], references: [] };
|
||||
return extractDecoratorRoutes(filePath, stripCommentsForRegex(content, 'python'), {
|
||||
// Flask: @x.route('/path', methods=[...])
|
||||
decoratorRegex: /@(\w+)\.route\s*\(\s*['"]([^'"]+)['"](?:\s*,\s*methods\s*=\s*\[([^\]]+)\])?\s*\)\s*\n\s*(?:async\s+)?def\s+(\w+)/g,
|
||||
defaultMethod: 'GET',
|
||||
methodFromGroup: 3,
|
||||
pathGroup: 2,
|
||||
handlerGroup: 4,
|
||||
language: 'python',
|
||||
});
|
||||
},
|
||||
};
|
||||
|
||||
export const fastapiResolver: FrameworkResolver = {
|
||||
name: 'fastapi',
|
||||
languages: ['python'],
|
||||
|
||||
detect(context: ResolutionContext): boolean {
|
||||
detect(context) {
|
||||
const requirements = context.readFile('requirements.txt');
|
||||
if (requirements && requirements.includes('fastapi')) {
|
||||
return true;
|
||||
}
|
||||
|
||||
if (requirements && /\bfastapi\b/i.test(requirements)) return true;
|
||||
const pyproject = context.readFile('pyproject.toml');
|
||||
if (pyproject && pyproject.includes('fastapi')) {
|
||||
return true;
|
||||
}
|
||||
|
||||
// Check for FastAPI app pattern
|
||||
const appFiles = ['app.py', 'main.py', 'api.py'];
|
||||
for (const file of appFiles) {
|
||||
if (pyproject && /\bfastapi\b/i.test(pyproject)) return true;
|
||||
for (const file of ['app.py', 'main.py', 'api.py']) {
|
||||
const content = context.readFile(file);
|
||||
if (content && content.includes('FastAPI()')) {
|
||||
return true;
|
||||
}
|
||||
if (content && content.includes('FastAPI(')) return true;
|
||||
}
|
||||
|
||||
return false;
|
||||
},
|
||||
|
||||
resolve(ref: UnresolvedRef, context: ResolutionContext): ResolvedRef | null {
|
||||
// Pattern 1: Router references
|
||||
resolve(ref, context) {
|
||||
if (ref.referenceName.endsWith('_router') || ref.referenceName === 'router') {
|
||||
const result = resolveByNameAndKind(ref.referenceName, VARIABLE_KINDS, ROUTER_DIRS, context);
|
||||
if (result) {
|
||||
return {
|
||||
original: ref,
|
||||
targetNodeId: result,
|
||||
confidence: 0.8,
|
||||
resolvedBy: 'framework',
|
||||
};
|
||||
}
|
||||
if (result) return { original: ref, targetNodeId: result, confidence: 0.8, resolvedBy: 'framework' };
|
||||
}
|
||||
|
||||
// Pattern 2: Dependency references
|
||||
if (ref.referenceName.startsWith('get_') || ref.referenceName.startsWith('Depends')) {
|
||||
const result = resolveByNameAndKind(ref.referenceName, FUNCTION_KINDS, DEP_DIRS, context);
|
||||
if (result) {
|
||||
return {
|
||||
original: ref,
|
||||
targetNodeId: result,
|
||||
confidence: 0.75,
|
||||
resolvedBy: 'framework',
|
||||
};
|
||||
}
|
||||
if (result) return { original: ref, targetNodeId: result, confidence: 0.75, resolvedBy: 'framework' };
|
||||
}
|
||||
|
||||
return null;
|
||||
},
|
||||
|
||||
extractNodes(filePath: string, content: string): Node[] {
|
||||
const nodes: Node[] = [];
|
||||
const now = Date.now();
|
||||
|
||||
// Extract FastAPI route decorators
|
||||
// @app.get('/path') or @router.post('/path')
|
||||
const routePattern = /@(\w+)\.(get|post|put|patch|delete|options|head)\s*\(\s*['"]([^'"]+)['"]/g;
|
||||
|
||||
let match;
|
||||
while ((match = routePattern.exec(content)) !== null) {
|
||||
const [, _appOrRouter, method, routePath] = match;
|
||||
const line = content.slice(0, match.index).split('\n').length;
|
||||
|
||||
nodes.push({
|
||||
id: `route:${filePath}:${method!.toUpperCase()}:${routePath}:${line}`,
|
||||
kind: 'route',
|
||||
name: `${method!.toUpperCase()} ${routePath}`,
|
||||
qualifiedName: `${filePath}::${method!.toUpperCase()}:${routePath}`,
|
||||
filePath,
|
||||
startLine: line,
|
||||
endLine: line,
|
||||
startColumn: 0,
|
||||
endColumn: match[0].length,
|
||||
language: 'python',
|
||||
updatedAt: now,
|
||||
});
|
||||
}
|
||||
|
||||
return nodes;
|
||||
extract(filePath, content) {
|
||||
if (!filePath.endsWith('.py')) return { nodes: [], references: [] };
|
||||
return extractDecoratorRoutes(filePath, stripCommentsForRegex(content, 'python'), {
|
||||
// FastAPI: @x.METHOD('/path') -> handler on the next def line
|
||||
decoratorRegex: /@(\w+)\.(get|post|put|patch|delete|options|head)\s*\(\s*['"]([^'"]+)['"]/g,
|
||||
defaultMethod: '',
|
||||
methodGroup: 2,
|
||||
pathGroup: 3,
|
||||
findHandler: true,
|
||||
language: 'python',
|
||||
});
|
||||
},
|
||||
};
|
||||
|
||||
interface DecoratorRouteOpts {
|
||||
decoratorRegex: RegExp;
|
||||
defaultMethod: string;
|
||||
methodGroup?: number;
|
||||
methodFromGroup?: number; // methods=[...] list
|
||||
pathGroup: number;
|
||||
handlerGroup?: number;
|
||||
findHandler?: boolean;
|
||||
language: 'python';
|
||||
}
|
||||
|
||||
function extractDecoratorRoutes(filePath: string, content: string, opts: DecoratorRouteOpts): FrameworkExtractionResult {
|
||||
const nodes: Node[] = [];
|
||||
const references: UnresolvedRef[] = [];
|
||||
const now = Date.now();
|
||||
let match: RegExpExecArray | null;
|
||||
while ((match = opts.decoratorRegex.exec(content)) !== null) {
|
||||
const routePath = match[opts.pathGroup];
|
||||
let method = opts.defaultMethod;
|
||||
if (opts.methodGroup && match[opts.methodGroup]) {
|
||||
method = match[opts.methodGroup]!.toUpperCase();
|
||||
} else if (opts.methodFromGroup && match[opts.methodFromGroup]) {
|
||||
const m = match[opts.methodFromGroup]!.match(/['"]([A-Z]+)['"]/i);
|
||||
if (m) method = m[1]!.toUpperCase();
|
||||
}
|
||||
const line = content.slice(0, match.index).split('\n').length;
|
||||
const name = method ? `${method} ${routePath}` : routePath!;
|
||||
const routeNode: Node = {
|
||||
id: `route:${filePath}:${line}:${method}:${routePath}`,
|
||||
kind: 'route',
|
||||
name,
|
||||
qualifiedName: `${filePath}::${method}:${routePath}`,
|
||||
filePath,
|
||||
startLine: line,
|
||||
endLine: line,
|
||||
startColumn: 0,
|
||||
endColumn: match[0].length,
|
||||
language: opts.language,
|
||||
updatedAt: now,
|
||||
};
|
||||
nodes.push(routeNode);
|
||||
|
||||
let handlerName: string | undefined;
|
||||
if (opts.handlerGroup && match[opts.handlerGroup]) {
|
||||
handlerName = match[opts.handlerGroup];
|
||||
} else if (opts.findHandler) {
|
||||
const tail = content.slice(match.index + match[0].length);
|
||||
const defMatch = tail.match(/\n\s*(?:async\s+)?def\s+(\w+)/);
|
||||
if (defMatch) handlerName = defMatch[1];
|
||||
}
|
||||
if (handlerName) {
|
||||
references.push({
|
||||
fromNodeId: routeNode.id,
|
||||
referenceName: handlerName,
|
||||
referenceKind: 'references',
|
||||
line,
|
||||
column: 0,
|
||||
filePath,
|
||||
language: 'python',
|
||||
});
|
||||
}
|
||||
}
|
||||
return { nodes, references };
|
||||
}
|
||||
|
||||
// Directory patterns
|
||||
const MODEL_DIRS = ['models', 'app/models', 'src/models'];
|
||||
const VIEW_DIRS = ['views', 'app/views', 'src/views', 'api/views'];
|
||||
|
||||
Reference in New Issue
Block a user