Merge pull request 'Fix #106: Add URL format validation to SEO diagnostics job queue' (#125) from typosaurus/ticket-106 into master

Reviewed-on: #125

devplacepy/models.py

@@ -484,9 +484,19 @@ 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)

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(