Fix clone not working on urls with query parameters

Author: cyclotruc

src/gitingest/parse_query.py

@@ -3,7 +3,7 @@
 import string
 import uuid
 from typing import Any
-from urllib.parse import unquote
+from urllib.parse import unquote, urlparse
 
 from gitingest.exceptions import InvalidPatternError
 from gitingest.ignore_patterns import DEFAULT_IGNORE_PATTERNS
@@ -103,6 +103,10 @@ def _parse_url(url: str) -> dict[str, Any]:
     if not url.startswith(("https://", "http://")):
         url = "https://" + url
 
+    # Parse URL and reconstruct it without query parameters and fragments
+    parsed_url = urlparse(url)
+    url = f"{parsed_url.scheme}://{parsed_url.netloc}{parsed_url.path}"
+
     # Extract domain and path
     url_parts = url.split("/")
     domain = url_parts[2]

src/gitingest/tests/test_parse_query.py

@@ -153,3 +153,11 @@ def test_parse_query_uuid_uniqueness() -> None:
     result1 = parse_query(path, max_file_size=100, from_web=False)
     result2 = parse_query(path, max_file_size=100, from_web=False)
     assert result1["id"] != result2["id"]
+
+
+def test_parse_url_with_query_and_fragment() -> None:
+    url = "https://github.com/user/repo?arg=value#fragment"
+    result = _parse_url(url)
+    assert result["user_name"] == "user"
+    assert result["repo_name"] == "repo"
+    assert result["url"] == "https://github.com/user/repo"  # URL should be cleaned