feat(django): support string-prefixed route literals and re_path()

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@pensar/surface",
-  "version": "0.2.1",
+  "version": "0.2.2",
   "description": "White-box endpoint discovery for source code repositories.",
   "license": "MIT",
   "type": "module",

scripts/fixtures/django-urls/blog/urls.py

@@ -0,0 +1,12 @@
+from django.urls import path, re_path
+from . import views
+
+# Mixes the idiomatic raw-string `r"..."` route form with plain-quoted routes
+# and an re_path() regex route, so the extractor is exercised against every
+# common Python string-literal style.
+urlpatterns = [
+    path(r"posts/", views.post_list),
+    path(r"posts/new/", views.post_create),
+    path("drafts/", views.draft_list),
+    re_path(r"^posts/(?P<pk>[0-9]+)/$", views.post_detail),
+]

scripts/fixtures/django-urls/blog/views.py

@@ -0,0 +1,6 @@
+from rest_framework.decorators import api_view
+
+
+@api_view(["GET", "POST"])
+def feed(request):
+    return None

scripts/fixtures/django-urls/blogsite/urls.py

@@ -0,0 +1,10 @@
+from django.contrib import admin
+from django.urls import path, include
+from . import views
+
+# Root URLconf: plain-quoted routes plus an include() into the blog app.
+urlpatterns = [
+    path("admin/", admin.site.urls),
+    path("", views.home),
+    path("blog/", include("blog.urls")),
+]

scripts/fixtures/django-urls/manage.py

@@ -0,0 +1 @@
+# Django project marker (used for framework detection only).

src/extractors/django.test.ts

@@ -0,0 +1,53 @@
+import { describe, expect, test } from "bun:test";
+import { resolve } from "path";
+import { django } from "./django.ts";
+import { createScanContext } from "../scan-context.ts";
+
+const FIXTURE = resolve(import.meta.dir, "../../scripts/fixtures/django-urls");
+
+function extract(fixturePath: string = FIXTURE) {
+  const ctx = createScanContext(fixturePath);
+  return django.extract(ctx);
+}
+
+describe("django url extraction", () => {
+  const endpoints = extract();
+  const byPath = (p: string) => endpoints.find((e) => e.path === p);
+
+  test('extracts routes declared with string-prefixed literals (r"...")', () => {
+    // blog.urls is mounted under "blog/" via include(), so routes are prefixed.
+    expect(byPath("/blog/posts")).toBeDefined();
+    expect(byPath("/blog/posts/new")).toBeDefined();
+  });
+
+  test("extracts plain-quoted routes", () => {
+    expect(byPath("/admin")).toBeDefined();
+    expect(byPath("/blog/drafts")).toBeDefined();
+  });
+
+  test("extracts re_path() regex routes", () => {
+    expect(endpoints.find((e) => e.handler === "post_detail")).toBeDefined();
+  });
+
+  test("applies include() prefix to mounted app routes", () => {
+    // Unprefixed it would be "/posts"; the include mounts blog.urls at /blog.
+    expect(byPath("/posts")).toBeUndefined();
+    expect(byPath("/blog/posts")).toBeDefined();
+  });
+
+  test("extracts @api_view endpoints with their methods", () => {
+    const feed = endpoints.filter((e) => e.handler === "feed");
+    expect(feed.map((e) => e.method).sort()).toEqual(["GET", "POST"]);
+  });
+
+  test("captures every path()/re_path() route declared (recall guard)", () => {
+    for (const p of [
+      "/admin",
+      "/blog/posts",
+      "/blog/posts/new",
+      "/blog/drafts",
+    ]) {
+      expect(byPath(p)).toBeDefined();
+    }
+  });
+});

src/extractors/django.ts

@@ -21,10 +21,14 @@ export const django: Extractor = {
       return name === "urls.py" || name === "routes.py";
     });
 
-    // Build prefix map from include() calls
+    // Build prefix map from include() calls.
+    // `[rRbBuUfF]*` allows Python string-literal prefixes (raw `r"..."`,
+    // f-strings, bytes, unicode) before the quote — these are common in
+    // urls.py and would otherwise be skipped. `(?:path|re_path)` covers both
+    // Django route helpers.
     const includePrefixes: Record<string, string> = {};
     const pathIncludeRe =
-      /path\s*\(\s*['"]([^'"]*)['"]\s*,\s*include\s*\(\s*['"]([^'"]+)['"]/g;
+      /(?:path|re_path)\s*\(\s*[rRbBuUfF]*['"]([^'"]*)['"]\s*,\s*include\s*\(\s*[rRbBuUfF]*['"]([^'"]+)['"]/g;
 
     for (const f of urlFiles) {
       const content = ctx.readFile(f);
@@ -35,7 +39,7 @@ export const django: Extractor = {
     }
 
     const directPathRe =
-      /path\s*\(\s*['"]([^'"]*)['"]\s*,\s*(?!include)(\w[\w.]*)/g;
+      /(?:path|re_path)\s*\(\s*[rRbBuUfF]*['"]([^'"]*)['"]\s*,\s*(?!include)(\w[\w.]*)/g;
     const apiViewRe =
       /@api_view\s*\(\s*\[([^\]]*)\]\s*\)(.*?)def\s+(\w+)\s*\(/gs;