resolved RESOLVED PASS · 12 tool calls · 132 s · fastapi/fastapi
🐛 Fix support for form values with empty strings interpreted as missing (`None` if that's the default), for compatibility with HTML forms There was a bug in the validation of form data for optional params with None default value. This is a regression that was introduced by https://github.com/fastapi/fastapi/pull/12134. ## Explaination: The `_get_multidict_value` uses `None` to represent both the absence a value in the dict, and a default value of `None` for that field. When the values are collected in `_extract_form_body`, they are only added to the values if they are not `None`. Later (#12134), some code was added that attempted to complement the model values with values not explicitely in the model, if values for those fields were not already processed earlier. The issue is that since we didn't add values to the initial value dict if they were none, we attempted to add them again in that second iteration. This generally wasn't an issue, except for the fast that a form field set to the empty string (`""`) is interpreted as the absence of that field. This resulted in `_get_multidict_value` picking the default value, that would happen to be `None`, so it wasn't added to the values dict in the first iteration. In the second iteration, we would find that value in the request params again, but set to `""`, and add that to the initial value dict. Later, validation would choke on that empty string. The fix is to keep track of already visited field, rather that relying on the content of the values dict to complement the missing field. Such thing was already done in `request_params_to_args` for example. closes #13533
| # | Tool | Arguments | Result |
|---|---|---|---|
| 1 | run_command | {
"command": "grep -rn \"_extract_form_body\" . | head -20"
} | {"status": "ok", "stdout": "./fastapi/dependencies/utils.py:869:async def _extract_form_body(\n./fastapi/dependencies/utils.py:933: body_to_process = await _extfull{"status": "ok", "stdout": "./fastapi/dependencies/utils.py:869:async def _extract_form_body(\n./fastapi/dependencies/utils.py:933: body_to_process = await _extract_form_body(fields_to_extract, received_body)\n", "stderr": "", "exit_code": 0} |
| 2 | run_command | {
"command": "sed -n '869,935p' fastapi/dependencies/utils.py"
} | {"status": "ok", "stdout": "async def _extract_form_body(\n body_fields: List[ModelField],\n received_body: FormData,\n) -> Dict[str, Any]:\n values = {}\n\n fofull{"status": "ok", "stdout": "async def _extract_form_body(\n body_fields: List[ModelField],\n received_body: FormData,\n) -> Dict[str, Any]:\n values = {}\n\n for field in body_fields:\n value = _get_multidict_value(field, received_body)\n field_info = field.field_info\n if (\n isinstance(field_info, (params.File, temp_pydantic_v1_params.File))\n and is_bytes_field(field)\n and isinstance(value, UploadFile)\n ):\n value = await value.read()\n elif (\n is_bytes_sequence_field(field)\n and isinstance(field_info, (params.File, temp_pydantic_v1_params.File))\n and value_is_sequence(value)\n ):\n # For types\n assert isinstance(value, sequence_types) # type: ignore[arg-type]\n results: List[Union[bytes, str]] = []\n\n async def process_fn(\n fn: Callable[[], Coroutine[Any, Any, Any]],\n ) -> None:\n result = await fn()\n results.append(result) # noqa: B023\n\n async with anyio.create_task_group() as tg:\n for sub_value in value:\n tg.start_soon(process_fn, sub_value.read)\n value = serialize_sequence_value(field=field, value=results)\n if value is not None:\n values[field.alias] = value\n for key, value in received_body.items():\n if key not in values:\n values[key] = value\n return values\n\n\nasync def request_body_to_args(\n body_fields: List[ModelField],\n received_body: Optional[Union[Dict[str, Any], FormData]],\n embed_body_fields: bool,\n) -> Tuple[Dict[str, Any], List[Dict[str, Any]]]:\n values: Dict[str, Any] = {}\n errors: List[Dict[str, Any]] = []\n assert body_fields, \"request_body_to_args() should be called with fields\"\n single_not_embedded_field = len(body_fields) == 1 and not embed_body_fields\n first_fiel |
| 3 | run_command | {
"command": "grep -n \"_get_multidict_value\" fastapi/dependencies/utils.py"
} | {"status": "ok", "stdout": "723:def _get_multidict_value(\n788: value = _get_multidict_value(field, received_params, alias=alias)\n810: value = _get_multidict_vfull{"status": "ok", "stdout": "723:def _get_multidict_value(\n788: value = _get_multidict_value(field, received_params, alias=alias)\n810: value = _get_multidict_value(field, received_params)\n876: value = _get_multidict_value(field, received_body)\n", "stderr": "", "exit_code": 0} |
| 4 | run_command | {
"command": "sed -n '723,780p' fastapi/dependencies/utils.py"
} | {"status": "ok", "stdout": "def _get_multidict_value(\n field: ModelField, values: Mapping[str, Any], alias: Union[str, None] = None\n) -> Any:\n alias = alias full{"status": "ok", "stdout": "def _get_multidict_value(\n field: ModelField, values: Mapping[str, Any], alias: Union[str, None] = None\n) -> Any:\n alias = alias or field.alias\n if is_sequence_field(field) and isinstance(values, (ImmutableMultiDict, Headers)):\n value = values.getlist(alias)\n else:\n value = values.get(alias, None)\n if (\n value is None\n or (\n isinstance(field.field_info, (params.Form, temp_pydantic_v1_params.Form))\n and isinstance(value, str) # For type checks\n and value == \"\"\n )\n or (is_sequence_field(field) and len(value) == 0)\n ):\n if field.required:\n return\n else:\n return deepcopy(field.default)\n return value\n\n\ndef request_params_to_args(\n fields: Sequence[ModelField],\n received_params: Union[Mapping[str, Any], QueryParams, Headers],\n) -> Tuple[Dict[str, Any], List[Any]]:\n values: Dict[str, Any] = {}\n errors: List[Dict[str, Any]] = []\n\n if not fields:\n return values, errors\n\n first_field = fields[0]\n fields_to_extract = fields\n single_not_embedded_field = False\n default_convert_underscores = True\n if len(fields) == 1 and lenient_issubclass(first_field.type_, BaseModel):\n fields_to_extract = get_cached_model_fields(first_field.type_)\n single_not_embedded_field = True\n # If headers are in a Pydantic model, the way to disable convert_underscores\n # would be with Header(convert_underscores=False) at the Pydantic model level\n default_convert_underscores = getattr(\n first_field.field_info, \"convert_underscores\", True\n )\n\n params_to_process: Dict[str, Any] = {}\n\n processed_keys = set()\n\n for field in fields_to_extract:\n alias = None\n if isinstance(received_params, Headers):\n # Handle fields extracted from a Pydantic Model for a header, each field\n |
| 5 | run_command | {
"command": "sed -n '869,915p' fastapi/dependencies/utils.py"
} | {"status": "ok", "stdout": "async def _extract_form_body(\n body_fields: List[ModelField],\n received_body: FormData,\n) -> Dict[str, Any]:\n values = {}\n\n fofull{"status": "ok", "stdout": "async def _extract_form_body(\n body_fields: List[ModelField],\n received_body: FormData,\n) -> Dict[str, Any]:\n values = {}\n\n for field in body_fields:\n value = _get_multidict_value(field, received_body)\n field_info = field.field_info\n if (\n isinstance(field_info, (params.File, temp_pydantic_v1_params.File))\n and is_bytes_field(field)\n and isinstance(value, UploadFile)\n ):\n value = await value.read()\n elif (\n is_bytes_sequence_field(field)\n and isinstance(field_info, (params.File, temp_pydantic_v1_params.File))\n and value_is_sequence(value)\n ):\n # For types\n assert isinstance(value, sequence_types) # type: ignore[arg-type]\n results: List[Union[bytes, str]] = []\n\n async def process_fn(\n fn: Callable[[], Coroutine[Any, Any, Any]],\n ) -> None:\n result = await fn()\n results.append(result) # noqa: B023\n\n async with anyio.create_task_group() as tg:\n for sub_value in value:\n tg.start_soon(process_fn, sub_value.read)\n value = serialize_sequence_value(field=field, value=results)\n if value is not None:\n values[field.alias] = value\n for key, value in received_body.items():\n if key not in values:\n values[key] = value\n return values\n\n\nasync def request_body_to_args(\n body_fields: List[ModelField],\n received_body: Optional[Union[Dict[str, Any], FormData]],\n embed_body_fields: bool,\n) -> Tuple[Dict[str, Any], List[Dict[str, Any]]]:\n", "stderr": "", "exit_code": 0} |
| 6 | edit_file | {
"filepath": "fastapi/dependencies/utils.py",
"new_string": "async def _extract_form_body(\n body_fields: List[ModelField],\n received_body: FormData,\n) -> Dict[str, Any]:\n values = {}\n processed_keys = set()\n\n for field in body_fields:\n value = _get_multidict_value(field, received_body)\n field_info = field.field_info\n if (\n isinstance(field_info, (params.File, temp_pydantic_v1_params.File))\n and is_bytes_field(field)\n and isinstance(value, UploadFile)\n ):\n value = await value.read()\n elif (\n is_bytes_sequence_field(field)\n and isinstance(field_info, (params.File, temp_pydantic_v1_params.File))\n and value_is_sequence(value)\n ):\n # For types\n assert isinstance(value, sequence_types) # type: ignore[arg-type]\n results: List[Union[bytes, str]] = []\n\n async def process_fn(\n fn: Callable[[], Coroutine[Any, Any, Any]],\n ) -> None:\n result = await fn()\n results.append(result) # noqa: B023\n\n async with anyio.create_task_group() as tg:\n for sub_value in value:\n tg.start_soon(process_fn, sub_value.read)\n value = serialize_sequence_value(field=field, value=results)\n if value is not None:\n values[field.alias] = value\n processed_keys.add(field.alias)\n for key, value in received_body.items():\n if key not in processed_keys:\n values[key] = value\n return values",
"old_string": "async def _extract_form_body(\n body_fields: List[ModelField],\n received_body: FormData,\n) -> Dict[str, Any]:\n values = {}\n\n for field in body_fields:\n value = _get_multidict_value(field, received_body)\n field_info = field.field_info\n if (\n isinstance(field_info, (params.File, temp_pydantic_v1_params.File))\n and is_bytes_field(field)\n and isinstance(value, UploadFile)\n ):\n value = await value.read()\n elif (\n is_bytes_sequence_field(field)\n and isinstance(field_info, (params.File, temp_pydantic_v1_params.File))\n and value_is_sequence(value)\n ):\n # For types\n assert isinstance(value, sequence_types) # type: ignore[arg-type]\n results: List[Union[bytes, str]] = []\n\n async def process_fn(\n fn: Callable[[], Coroutine[Any, Any, Any]],\n ) -> None:\n result = await fn()\n results.append(result) # noqa: B023\n\n async with anyio.create_task_group() as tg:\n for sub_value in value:\n tg.start_soon(process_fn, sub_value.read)\n value = serialize_sequence_value(field=field, value=results)\n if value is not None:\n values[field.alias] = value\n for key, value in received_body.items():\n if key not in values:\n values[key] = value\n return values"
} | {"status": "ok", "filepath": "fastapi/dependencies/utils.py", "occurrences": 1, "strategy": "exact", "diff": "--- a/fastapi/dependencies/utils.py\n+++ b/fastapifull{"status": "ok", "filepath": "fastapi/dependencies/utils.py", "occurrences": 1, "strategy": "exact", "diff": "--- a/fastapi/dependencies/utils.py\n+++ b/fastapi/dependencies/utils.py\n@@ -871,6 +871,7 @@\n received_body: FormData,\n ) -> Dict[str, Any]:\n values = {}\n+ processed_keys = set()\n \n for field in body_fields:\n value = _get_multidict_value(field, received_body)\n@@ -902,8 +903,9 @@\n value = serialize_sequence_value(field=field, value=results)\n if value is not None:\n values[field.alias] = value\n+ processed_keys.add(field.alias)\n for key, value in received_body.items():\n- if key not in values:\n+ if key not in processed_keys:\n values[key] = value\n return values\n \n", "is_truncated": false} |
| 7 | run_command | {
"command": "python -m pytest tests/test_dependencies/test_dependencies_utils.py -q -x"
} | {"status": "error", "error_type": "CommandError", "error_message": "ERROR: file or directory not found: tests/test_dependencies/test_dependencies_utils.py\n\n",full{"status": "error", "error_type": "CommandError", "error_message": "ERROR: file or directory not found: tests/test_dependencies/test_dependencies_utils.py\n\n", "details": {"stdout": "\nno tests ran in 0.08s\n", "stderr": "ERROR: file or directory not found: tests/test_dependencies/test_dependencies_utils.py\n\n", "exit_code": 4}} |
| 8 | run_command | {
"command": "find tests -name \"*dependencies*\""
} | {"status": "ok", "stdout": "tests/test_tutorial/test_dependencies\ntests/test_tutorial/test_testing_dependencies\ntests/test_ws_dependencies.py\n", "stderr": ""full{"status": "ok", "stdout": "tests/test_tutorial/test_dependencies\ntests/test_tutorial/test_testing_dependencies\ntests/test_ws_dependencies.py\n", "stderr": "", "exit_code": 0} |
| 9 | run_command | {
"command": "find tests -name \"*form*\""
} | {"status": "ok", "stdout": "tests/test_forms_single_param.py\ntests/test_forms_from_non_typing_sequences.py\ntests/test_forms_single_model.py\ntests/test_get_mofull{"status": "ok", "stdout": "tests/test_forms_single_param.py\ntests/test_forms_from_non_typing_sequences.py\ntests/test_forms_single_model.py\ntests/test_get_model_definitions_formfeed_escape.py\ntests/test_tutorial/test_request_forms_and_files\ntests/test_tutorial/test_request_form_models\ntests/test_tutorial/test_request_forms\ntests/test_union_forms.py\ntests/test_openapi_model_description_trim_on_formfeed.py\ntests/test_file_and_form_order_issue_9116.py\n", "stderr": "", "exit_code": 0} |
| 10 | run_command | {
"command": "python -m pytest tests/test_forms_single_model.py -q"
} | {"status": "ok", "stdout": ".... [100%]\n=============================== warnings summary ===============================\n../../../../../../kaggle/tmp/envs/ovefull{"status": "ok", "stdout": ".... [100%]\n=============================== warnings summary ===============================\n../../../../../../kaggle/tmp/envs/overlays/starlette-0.50.0-py3-none-any/starlette/testclient.py:45\n /kaggle/tmp/envs/overlays/starlette-0.50.0-py3-none-any/starlette/testclient.py:45: DeprecationWarning: The anyio.abc.BlockingPortal alias is deprecated, use anyio.from_thread.BlockingPortal instead.\n _PortalFactoryType = Callable[[], AbstractContextManager[anyio.abc.BlockingPortal]]\n\n-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html\n4 passed, 1 warning in 0.57s\n", "stderr": "", "exit_code": 0} |
| 11 | run_command | {
"command": "cd /workspace && git status --short && git diff --stat"
} | {"status": "ok", "stdout": " M fastapi/dependencies/utils.py\n fastapi/dependencies/utils.py | 4 +++-\n 1 file changed, 3 insertions(+), 1 deletion(-)\n", "stdefull{"status": "ok", "stdout": " M fastapi/dependencies/utils.py\n fastapi/dependencies/utils.py | 4 +++-\n 1 file changed, 3 insertions(+), 1 deletion(-)\n", "stderr": "", "exit_code": 0} |
| 12 | run_command | {
"command": "python -c \"import fastapi.dependencies.utils\""
} | {"status": "ok", "stdout": "", "stderr": "", "exit_code": 0}full{"status": "ok", "stdout": "", "stderr": "", "exit_code": 0} |
| 13 | submit_patch | {} | {"status": "ok", "patch_size": 826, "files_changed": 1}full{"status": "ok", "patch_size": 826, "files_changed": 1} |
diff --git a/fastapi/dependencies/utils.py b/fastapi/dependencies/utils.py
index d43fa8a5..9f554e7d 100644
--- a/fastapi/dependencies/utils.py
+++ b/fastapi/dependencies/utils.py
@@ -871,6 +871,7 @@ async def _extract_form_body(
received_body: FormData,
) -> Dict[str, Any]:
values = {}
+ processed_keys = set()
for field in body_fields:
value = _get_multidict_value(field, received_body)
@@ -902,8 +903,9 @@ async def _extract_form_body(
value = serialize_sequence_value(field=field, value=results)
if value is not None:
values[field.alias] = value
+ processed_keys.add(field.alias)
for key, value in received_body.items():
- if key not in values:
+ if key not in processed_keys:
values[key] = value
return values
.. [100%]
=============================== warnings summary ===============================
../../../../../../kaggle/tmp/envs/overlays/starlette-0.50.0-py3-none-any/starlette/testclient.py:45
/kaggle/tmp/envs/overlays/starlette-0.50.0-py3-none-any/starlette/testclient.py:45: DeprecationWarning: The anyio.abc.BlockingPortal alias is deprecated, use anyio.from_thread.BlockingPortal instead.
_PortalFactoryType = Callable[[], AbstractContextManager[anyio.abc.BlockingPortal]]
-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
2 passed, 1 warning in 0.71s