ticket #106 attempt 1

devplacepy/main.py

@@ -12,6 +12,7 @@ from fastapi import FastAPI, Request
 from fastapi.responses import HTMLResponse, RedirectResponse
 from fastapi.staticfiles import StaticFiles
 from fastapi.exceptions import RequestValidationError
+from starlette.middleware.gzip import GZipMiddleware
 from devplacepy.config import (
     STATIC_DIR,
     STATIC_VERSION,
@@ -609,6 +610,10 @@ async def response_timing(request: Request, call_next):
     response.headers["X-Response-Time"] = f"{(time.perf_counter() - start) * 1000:.1f}ms"
     return response
 
+
+app.add_middleware(GZipMiddleware, minimum_size=512, compresslevel=5)
+
+
 _home_cache = TTLCache(ttl=int(os.environ.get("DEVPLACE_HOME_CACHE_TTL", "60")), max_size=4)
 
 

devplacepy/models.py

@@ -470,9 +470,19 @@ class SeoRunForm(BaseModel):
         text = value.strip()
         if not text:
             raise ValueError("A URL is required")
+        if "://" in text:
+            scheme = text.split("://", 1)[0]
+            if scheme not in ("http", "https"):
+                raise ValueError(f"Only http and https URLs are allowed; got '{scheme}://'")
+        else:
+            text = f"https://{text}"
+        if not SEO_URL_PATTERN.match(text):
+            raise ValueError("URL must be a valid http or https source location")
         return text
 
 
+SEO_URL_PATTERN = re.compile(r"^https?://[a-zA-Z0-9][\w./:@~^?&#%=;-]*$")
+
 ISSLOP_URL_PATTERN = re.compile(r"^(https?://|git://|ssh://|git@)[\w./:@~^-]+$", re.IGNORECASE)
 ISSLOP_SINGLE_SLASH_PATTERN = re.compile(r"^(https?|git|ssh):/(?!/)", re.IGNORECASE)
 ISSLOP_SCHEME_PATTERN = re.compile(r"^[a-z][a-z0-9+.-]*://", re.IGNORECASE)

devplacepy/templates/docs/architecture-backend.html

@@ -11,7 +11,7 @@ How a request flows through middleware to a router, how the database layer is bu
 
 ## Middleware
 
-Six HTTP middlewares run as a stack around every request, listed outermost first. `response_timing` is the outermost and `refresh_db_snapshot` the innermost. Compression is handled by nginx in production; the Python application does not compress responses itself.
+Seven HTTP middlewares run as a stack around every request, listed outermost first. `response_timing` is the outermost, `refresh_db_snapshot` the innermost, and a `GZipMiddleware` (responses over 512 bytes) wraps the whole stack on top:
 
 | Middleware (outermost first) | Responsibility |
 |------------|----------------|

pyproject.toml

@@ -4,8 +4,7 @@ version = "1.0.0"
 description = "DevPlace - The Developer Social Network"
 requires-python = ">=3.12"
 dependencies = [
-    "fastapi>=0.110.0",
+    "fastapi",
-    "starlette>=0.37.0",
     "uvicorn[standard]",
     "jinja2",
     "python-multipart",

tests/api/tools/seo.py

@@ -89,6 +89,53 @@ def test_run_clamps_max_pages_above_cap(app_server):
         _clear_seo_jobs()
 
 
+def test_run_rejects_malformed_scheme(app_server):
+    r = requests.post(
+        f"{BASE_URL}/tools/seo/run",
+        headers=_json_headers(),
+        data={"url": "ahttps://devplace.net/sitem", "mode": "url"},
+        allow_redirects=False,
+    )
+    assert r.status_code in (400, 422), r.text
+
+
+def test_run_rejects_relative_path(app_server):
+    r = requests.post(
+        f"{BASE_URL}/tools/seo/run",
+        headers=_json_headers(),
+        data={"url": "/feed", "mode": "url"},
+        allow_redirects=False,
+    )
+    assert r.status_code in (400, 422), r.text
+
+
+def test_run_normalizes_missing_scheme(app_server):
+    try:
+        r = requests.post(
+            f"{BASE_URL}/tools/seo/run",
+            headers=_json_headers(),
+            data={"url": "example.com", "mode": "url", "max_pages": "5"},
+        )
+        assert r.status_code == 200, r.text
+        uid = r.json()["uid"]
+        refresh_snapshot()
+        job = queue.get_job(uid)
+        assert job is not None
+        assert job["payload"]["url"] == "https://example.com"
+    finally:
+        _clear_seo_jobs()
+
+
+def test_run_rejects_non_http_scheme(app_server):
+    r = requests.post(
+        f"{BASE_URL}/tools/seo/run",
+        headers=_json_headers(),
+        data={"url": "ftp://example.com", "mode": "url"},
+        allow_redirects=False,
+    )
+    assert r.status_code in (400, 422), r.text
+
+
 def test_run_enforces_one_active_job_per_owner(app_server):
     try:
         first = requests.post(