swe_bench / lite / dev

Task input

[version 2.20.0] TypeError: 'NoneType' object is not subscriptable
After update from version 2.19.5 to 2.20.0 I got error for code like:

```python
from marshmallow import Schema, fields, validates


class Bar(Schema):
    value = fields.String()

    @validates('value')  # <- issue here
    def validate_value(self, value):
        pass


class Foo(Schema):
    bar = fields.Nested(Bar)


sch = Foo()

sch.validate({
    'bar': 'invalid',
})
```

```
Traceback (most recent call last):
  File "/_/bug_mschema.py", line 19, in <module>
    'bar': 'invalid',
  File "/_/env/lib/python3.7/site-packages/marshmallow/schema.py", line 628, in validate
    _, errors = self._do_load(data, many, partial=partial, postprocess=False)
  File "/_/env/lib/python3.7/site-packages/marshmallow/schema.py", line 670, in _do_load
    index_errors=self.opts.index_errors,
  File "/_/env/lib/python3.7/site-packages/marshmallow/marshalling.py", line 292, in deserialize
    index=(index if index_errors else None)
  File "/_/env/lib/python3.7/site-packages/marshmallow/marshalling.py", line 65, in call_and_store
    value = getter_func(data)
  File "/_/env/lib/python3.7/site-packages/marshmallow/marshalling.py", line 285, in <lambda>
    data
  File "/_/env/lib/python3.7/site-packages/marshmallow/fields.py", line 265, in deserialize
    output = self._deserialize(value, attr, data)
  File "/_/env/lib/python3.7/site-packages/marshmallow/fields.py", line 465, in _deserialize
    data, errors = self.schema.load(value)
  File "/_/env/lib/python3.7/site-packages/marshmallow/schema.py", line 588, in load
    result, errors = self._do_load(data, many, partial=partial, postprocess=True)
  File "/_/env/lib/python3.7/site-packages/marshmallow/schema.py", line 674, in _do_load
    self._invoke_field_validators(unmarshal, data=result, many=many)
  File "/_/env/lib/python3.7/site-packages/marshmallow/schema.py", line 894, in _invoke_field_validators
    value = data[field_obj.attribute or field_name]
TypeError: 'NoneType' object is not subscriptable
```

Fix tests

tests/test_marshalling.py::TestUnmarshaller::test_deserialize_wrong_nested_type_with_validates_method

Regression tests

tests/test_marshalling.py::test_missing_is_falsy
tests/test_marshalling.py::TestMarshaller::test_prefix
tests/test_marshalling.py::TestMarshaller::test_marshalling_generator
tests/test_marshalling.py::TestMarshaller::test_default_to_missing
tests/test_marshalling.py::TestMarshaller::test_serialize_fields_with_load_only_param
tests/test_marshalling.py::TestMarshaller::test_missing_data_are_skipped
tests/test_marshalling.py::TestMarshaller::test_serialize_with_load_only_doesnt_validate
tests/test_marshalling.py::TestMarshaller::test_serialize_fields_with_dump_to_param
tests/test_marshalling.py::TestMarshaller::test_serialize_fields_with_dump_to_and_prefix_params
tests/test_marshalling.py::TestMarshaller::test_stores_indices_of_errors_when_many_equals_true
tests/test_marshalling.py::TestMarshaller::test_doesnt_store_errors_when_index_errors_equals_false
tests/test_marshalling.py::TestUnmarshaller::test_extra_data_is_ignored
tests/test_marshalling.py::TestUnmarshaller::test_stores_errors
tests/test_marshalling.py::TestUnmarshaller::test_stores_indices_of_errors_when_many_equals_true
tests/test_marshalling.py::TestUnmarshaller::test_doesnt_store_errors_when_index_errors_equals_false
tests/test_marshalling.py::TestUnmarshaller::test_deserialize
tests/test_marshalling.py::TestUnmarshaller::test_extra_fields
tests/test_marshalling.py::TestUnmarshaller::test_deserialize_many
tests/test_marshalling.py::TestUnmarshaller::test_deserialize_stores_errors
tests/test_marshalling.py::TestUnmarshaller::test_deserialize_fields_with_attribute_param
tests/test_marshalling.py::TestUnmarshaller::test_deserialize_fields_with_load_from_param
tests/test_marshalling.py::TestUnmarshaller::test_deserialize_fields_with_dump_only_param
tests/test_marshalling.py::TestUnmarshaller::test_deserialize_wrong_type_root_data
tests/test_marshalling.py::TestUnmarshaller::test_deserialize_wrong_type_nested_data

Scorer detail

[anthropic-agent] Attempt 1: Anthropic call failed for full_file: Anthropic request failed: HTTPStatusError: Client error '429 Too Many Requests' for url 'https://api.anthropic.com/v1/messages'
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429. Response body: {"type":"error","error":{"type":"rate_limit_error","message":"This request would exceed your organization's rate limit of 30,000 input tokens per minute (org: 7cd50861-f334-4b49-afb7-3c1da9371b1a, model: claude-sonnet-4-5-20250929). For details, refer to: https://docs.claude.com/en/api/rate-limits. You can see the response headers for current usage. Please reduce the prompt length or the maximum t
[anthropic-agent] Attempt 2: Anthropic call failed for single_file_rewrite: Anthropic request failed: HTTPStatusError: Client error '429 Too Many Requests' for url 'https://api.anthropic.com/v1/messages'
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429. Response body: {"type":"error","error":{"type":"rate_limit_error","message":"This request would exceed your organization's rate limit of 30,000 input tokens per minute (org: 7cd50861-f334-4b49-afb7-3c1da9371b1a, model: claude-sonnet-4-5-20250929). For details, refer to: https://docs.claude.com/en/api/rate-limits. You can see the response headers for current usage. Please reduce the prompt length or the maximum t
[anthropic-agent] Attempt 3: Anthropic call failed for line_ranges: Anthropic request failed: HTTPStatusError: Client error '429 Too Many Requests' for url 'https://api.anthropic.com/v1/messages'
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429. Response body: {"type":"error","error":{"type":"rate_limit_error","message":"This request would exceed your organization's rate limit of 30,000 input tokens per minute (org: 7cd50861-f334-4b49-afb7-3c1da9371b1a, model: claude-sonnet-4-5-20250929). For details, refer to: https://docs.claude.com/en/api/rate-limits. You can see the response headers for current usage. Please reduce the prompt length or the maximum t
[anthropic-agent] Attempt 4: Anthropic call failed for search_replace: Anthropic request failed: HTTPStatusError: Client error '429 Too Many Requests' for url 'https://api.anthropic.com/v1/messages'
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429. Response body: {"type":"error","error":{"type":"rate_limit_error","message":"This request would exceed your organization's rate limit of 30,000 input tokens per minute (org: 7cd50861-f334-4b49-afb7-3c1da9371b1a, model: claude-sonnet-4-5-20250929). For details, refer to: https://docs.claude.com/en/api/rate-limits. You can see the response headers for current usage. Please reduce the prompt length or the maximum t

Patch text

{"output": "", "patch_text": "", "stdout": "[anthropic-agent] instance=marshmallow-code__marshmallow-1343\n[anthropic-agent] repo=marshmallow-code/marshmallow\n[anthropic-agent] sandbox=352292b2-54ef-4ad0-ada7-ba708c24814d\n[anthropic-agent] model=claude-sonnet-4-5-20250929\n[anthropic-agent] context_files=5\n[anthropic-agent] full_file_context=yes\n[anthropic-agent] edit_attempts=4", "stderr": "[anthropic-agent] Attempt 1: Anthropic call failed for full_file: Anthropic request failed: HTTPStatusError: Client error '429 Too Many Requests' for url 'https://api.anthropic.com/v1/messages'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429. Response body: {\"type\":\"error\",\"error\":{\"type\":\"rate_limit_error\",\"message\":\"This request would exceed your organization's rate limit of 30,000 input tokens per minute (org: 7cd50861-f334-4b49-afb7-3c1da9371b1a, model: claude-sonnet-4-5-20250929). For details, refer to: https://docs.claude.com/en/api/rate-limits. You can see the response headers for current usage. Please reduce the prompt length or the maximum t\n[anthropic-agent] Attempt 2: Anthropic call failed for single_file_rewrite: Anthropic request failed: HTTPStatusError: Client error '429 Too Many Requests' for url 'https://api.anthropic.com/v1/messages'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429. Response body: {\"type\":\"error\",\"error\":{\"type\":\"rate_limit_error\",\"message\":\"This request would exceed your organization's rate limit of 30,000 input tokens per minute (org: 7cd50861-f334-4b49-afb7-3c1da9371b1a, model: claude-sonnet-4-5-20250929). For details, refer to: https://docs.claude.com/en/api/rate-limits. You can see the response headers for current usage. Please reduce the prompt length or the maximum t\n[anthropic-agent] Attempt 3: Anthropic call failed for line_ranges: Anthropic request failed: HTTPStatusError: Client error '429 Too Many Requests' for url 'https://api.anthropic.com/v1/messages'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429. Response body: {\"type\":\"error\",\"error\":{\"type\":\"rate_limit_error\",\"message\":\"This request would exceed your organization's rate limit of 30,000 input tokens per minute (org: 7cd50861-f334-4b49-afb7-3c1da9371b1a, model: claude-sonnet-4-5-20250929). For details, refer to: https://docs.claude.com/en/api/rate-limits. You can see the response headers for current usage. Please reduce the prompt length or the maximum t\n[anthropic-agent] Attempt 4: Anthropic call failed for search_replace: Anthropic request failed: HTTPStatusError: Client error '429 Too Many Requests' for url 'https://api.anthropic.com/v1/messages'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429. Response body: {\"type\":\"error\",\"error\":{\"type\":\"rate_limit_error\",\"message\":\"This request would exceed your organization's rate limit of 30,000 input tokens per minute (org: 7cd50861-f334-4b49-afb7-3c1da9371b1a, model: claude-sonnet-4-5-20250929). For details, refer to: https://docs.claude.com/en/api/rate-limits. You can see the response headers for current usage. Please reduce the prompt length or the maximum t", "model_name": "claude-sonnet-4-5-20250929", "prompt_tokens": 0, "completion_tokens": 0, "reported_cost_usd": 0.0}

Stdout

[anthropic-agent] instance=marshmallow-code__marshmallow-1343
[anthropic-agent] repo=marshmallow-code/marshmallow
[anthropic-agent] sandbox=352292b2-54ef-4ad0-ada7-ba708c24814d
[anthropic-agent] model=claude-sonnet-4-5-20250929
[anthropic-agent] context_files=5
[anthropic-agent] full_file_context=yes
[anthropic-agent] edit_attempts=4

Stderr

[anthropic-agent] Attempt 1: Anthropic call failed for full_file: Anthropic request failed: HTTPStatusError: Client error '429 Too Many Requests' for url 'https://api.anthropic.com/v1/messages'
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429. Response body: {"type":"error","error":{"type":"rate_limit_error","message":"This request would exceed your organization's rate limit of 30,000 input tokens per minute (org: 7cd50861-f334-4b49-afb7-3c1da9371b1a, model: claude-sonnet-4-5-20250929). For details, refer to: https://docs.claude.com/en/api/rate-limits. You can see the response headers for current usage. Please reduce the prompt length or the maximum t
[anthropic-agent] Attempt 2: Anthropic call failed for single_file_rewrite: Anthropic request failed: HTTPStatusError: Client error '429 Too Many Requests' for url 'https://api.anthropic.com/v1/messages'
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429. Response body: {"type":"error","error":{"type":"rate_limit_error","message":"This request would exceed your organization's rate limit of 30,000 input tokens per minute (org: 7cd50861-f334-4b49-afb7-3c1da9371b1a, model: claude-sonnet-4-5-20250929). For details, refer to: https://docs.claude.com/en/api/rate-limits. You can see the response headers for current usage. Please reduce the prompt length or the maximum t
[anthropic-agent] Attempt 3: Anthropic call failed for line_ranges: Anthropic request failed: HTTPStatusError: Client error '429 Too Many Requests' for url 'https://api.anthropic.com/v1/messages'
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429. Response body: {"type":"error","error":{"type":"rate_limit_error","message":"This request would exceed your organization's rate limit of 30,000 input tokens per minute (org: 7cd50861-f334-4b49-afb7-3c1da9371b1a, model: claude-sonnet-4-5-20250929). For details, refer to: https://docs.claude.com/en/api/rate-limits. You can see the response headers for current usage. Please reduce the prompt length or the maximum t
[anthropic-agent] Attempt 4: Anthropic call failed for search_replace: Anthropic request failed: HTTPStatusError: Client error '429 Too Many Requests' for url 'https://api.anthropic.com/v1/messages'
For more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429. Response body: {"type":"error","error":{"type":"rate_limit_error","message":"This request would exceed your organization's rate limit of 30,000 input tokens per minute (org: 7cd50861-f334-4b49-afb7-3c1da9371b1a, model: claude-sonnet-4-5-20250929). For details, refer to: https://docs.claude.com/en/api/rate-limits. You can see the response headers for current usage. Please reduce the prompt length or the maximum t

Agent output

{"output": "", "patch_text": "", "stdout": "[anthropic-agent] instance=marshmallow-code__marshmallow-1343\n[anthropic-agent] repo=marshmallow-code/marshmallow\n[anthropic-agent] sandbox=352292b2-54ef-4ad0-ada7-ba708c24814d\n[anthropic-agent] model=claude-sonnet-4-5-20250929\n[anthropic-agent] context_files=5\n[anthropic-agent] full_file_context=yes\n[anthropic-agent] edit_attempts=4", "stderr": "[anthropic-agent] Attempt 1: Anthropic call failed for full_file: Anthropic request failed: HTTPStatusError: Client error '429 Too Many Requests' for url 'https://api.anthropic.com/v1/messages'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429. Response body: {\"type\":\"error\",\"error\":{\"type\":\"rate_limit_error\",\"message\":\"This request would exceed your organization's rate limit of 30,000 input tokens per minute (org: 7cd50861-f334-4b49-afb7-3c1da9371b1a, model: claude-sonnet-4-5-20250929). For details, refer to: https://docs.claude.com/en/api/rate-limits. You can see the response headers for current usage. Please reduce the prompt length or the maximum t\n[anthropic-agent] Attempt 2: Anthropic call failed for single_file_rewrite: Anthropic request failed: HTTPStatusError: Client error '429 Too Many Requests' for url 'https://api.anthropic.com/v1/messages'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429. Response body: {\"type\":\"error\",\"error\":{\"type\":\"rate_limit_error\",\"message\":\"This request would exceed your organization's rate limit of 30,000 input tokens per minute (org: 7cd50861-f334-4b49-afb7-3c1da9371b1a, model: claude-sonnet-4-5-20250929). For details, refer to: https://docs.claude.com/en/api/rate-limits. You can see the response headers for current usage. Please reduce the prompt length or the maximum t\n[anthropic-agent] Attempt 3: Anthropic call failed for line_ranges: Anthropic request failed: HTTPStatusError: Client error '429 Too Many Requests' for url 'https://api.anthropic.com/v1/messages'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429. Response body: {\"type\":\"error\",\"error\":{\"type\":\"rate_limit_error\",\"message\":\"This request would exceed your organization's rate limit of 30,000 input tokens per minute (org: 7cd50861-f334-4b49-afb7-3c1da9371b1a, model: claude-sonnet-4-5-20250929). For details, refer to: https://docs.claude.com/en/api/rate-limits. You can see the response headers for current usage. Please reduce the prompt length or the maximum t\n[anthropic-agent] Attempt 4: Anthropic call failed for search_replace: Anthropic request failed: HTTPStatusError: Client error '429 Too Many Requests' for url 'https://api.anthropic.com/v1/messages'\nFor more information check: https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/429. Response body: {\"type\":\"error\",\"error\":{\"type\":\"rate_limit_error\",\"message\":\"This request would exceed your organization's rate limit of 30,000 input tokens per minute (org: 7cd50861-f334-4b49-afb7-3c1da9371b1a, model: claude-sonnet-4-5-20250929). For details, refer to: https://docs.claude.com/en/api/rate-limits. You can see the response headers for current usage. Please reduce the prompt length or the maximum t", "model_name": "claude-sonnet-4-5-20250929", "prompt_tokens": 0, "completion_tokens": 0, "reported_cost_usd": 0.0}

Passing target tests

No fail-to-pass successes recorded yet.

Failing target tests

No fail-to-pass failures recorded yet.

Maintained regression tests

No pass-to-pass successes recorded yet.

Regressed tests

No regression failures recorded yet.

Harness output

No harness output captured yet.

Reference output

diff --git a/src/marshmallow/schema.py b/src/marshmallow/schema.py
--- a/src/marshmallow/schema.py
+++ b/src/marshmallow/schema.py
@@ -877,7 +877,7 @@ def _invoke_field_validators(self, unmarshal, data, many):
                 for idx, item in enumerate(data):
                     try:
                         value = item[field_obj.attribute or field_name]
-                    except KeyError:
+                    except (KeyError, TypeError):
                         pass
                     else:
                         validated_value = unmarshal.call_and_store(
@@ -892,7 +892,7 @@ def _invoke_field_validators(self, unmarshal, data, many):
             else:
                 try:
                     value = data[field_obj.attribute or field_name]
-                except KeyError:
+                except (KeyError, TypeError):
                     pass
                 else:
                     validated_value = unmarshal.call_and_store(

Task input

3.0: DateTime fields cannot be used as inner field for List or Tuple fields
Between releases 3.0.0rc8 and 3.0.0rc9, `DateTime` fields have started throwing an error when being instantiated as inner fields of container fields like `List` or `Tuple`. The snippet below works in <=3.0.0rc8 and throws the error below in >=3.0.0rc9 (and, worryingly, 3.0.0):

```python
from marshmallow import fields, Schema

class MySchema(Schema):
    times = fields.List(fields.DateTime())

s = MySchema()
```

Traceback:
```
Traceback (most recent call last):
  File "test-mm.py", line 8, in <module>
    s = MySchema()
  File "/Users/victor/.pyenv/versions/marshmallow/lib/python3.6/site-packages/marshmallow/schema.py", line 383, in __init__
    self.fields = self._init_fields()
  File "/Users/victor/.pyenv/versions/marshmallow/lib/python3.6/site-packages/marshmallow/schema.py", line 913, in _init_fields
    self._bind_field(field_name, field_obj)
  File "/Users/victor/.pyenv/versions/marshmallow/lib/python3.6/site-packages/marshmallow/schema.py", line 969, in _bind_field
    field_obj._bind_to_schema(field_name, self)
  File "/Users/victor/.pyenv/versions/marshmallow/lib/python3.6/site-packages/marshmallow/fields.py", line 636, in _bind_to_schema
    self.inner._bind_to_schema(field_name, self)
  File "/Users/victor/.pyenv/versions/marshmallow/lib/python3.6/site-packages/marshmallow/fields.py", line 1117, in _bind_to_schema
    or getattr(schema.opts, self.SCHEMA_OPTS_VAR_NAME)
AttributeError: 'List' object has no attribute 'opts'
```

It seems like it's treating the parent field as a Schema without checking that it is indeed a schema, so the `schema.opts` statement fails as fields don't have an `opts` attribute.

Fix tests

tests/test_fields.py::TestParentAndName::test_datetime_list_inner_format

Regression tests

tests/test_fields.py::test_field_aliases[Integer-Integer]
tests/test_fields.py::test_field_aliases[String-String]
tests/test_fields.py::test_field_aliases[Boolean-Boolean]
tests/test_fields.py::test_field_aliases[Url-Url]
tests/test_fields.py::TestField::test_repr
tests/test_fields.py::TestField::test_error_raised_if_uncallable_validator_passed
tests/test_fields.py::TestField::test_error_raised_if_missing_is_set_on_required_field
tests/test_fields.py::TestField::test_custom_field_receives_attr_and_obj
tests/test_fields.py::TestField::test_custom_field_receives_data_key_if_set
tests/test_fields.py::TestField::test_custom_field_follows_data_key_if_set
tests/test_fields.py::TestParentAndName::test_simple_field_parent_and_name
tests/test_fields.py::TestParentAndName::test_unbound_field_root_returns_none
tests/test_fields.py::TestParentAndName::test_list_field_inner_parent_and_name
tests/test_fields.py::TestParentAndName::test_tuple_field_inner_parent_and_name
tests/test_fields.py::TestParentAndName::test_mapping_field_inner_parent_and_name
tests/test_fields.py::TestParentAndName::test_simple_field_root
tests/test_fields.py::TestParentAndName::test_list_field_inner_root
tests/test_fields.py::TestParentAndName::test_tuple_field_inner_root
tests/test_fields.py::TestParentAndName::test_list_root_inheritance
tests/test_fields.py::TestParentAndName::test_dict_root_inheritance
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[String]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Integer]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Boolean]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Float]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Number]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[DateTime]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Time]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Date]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[TimeDelta]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Dict]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Url]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Email]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[UUID]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Decimal]
tests/test_fields.py::TestErrorMessages::test_default_error_messages_get_merged_with_parent_error_messages_cstm_msg
tests/test_fields.py::TestErrorMessages::test_default_error_messages_get_merged_with_parent_error_messages
tests/test_fields.py::TestErrorMessages::test_make_error[required-Missing
tests/test_fields.py::TestErrorMessages::test_make_error[null-Field
tests/test_fields.py::TestErrorMessages::test_make_error[custom-Custom
tests/test_fields.py::TestErrorMessages::test_make_error[validator_failed-Invalid
tests/test_fields.py::TestErrorMessages::test_fail[required-Missing
tests/test_fields.py::TestErrorMessages::test_fail[null-Field
tests/test_fields.py::TestErrorMessages::test_fail[custom-Custom
tests/test_fields.py::TestErrorMessages::test_fail[validator_failed-Invalid
tests/test_fields.py::TestErrorMessages::test_make_error_key_doesnt_exist
tests/test_fields.py::TestNestedField::test_nested_only_and_exclude_as_string[only]
tests/test_fields.py::TestNestedField::test_nested_only_and_exclude_as_string[exclude]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[None-exclude]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[None-include]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[None-raise]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[exclude-exclude]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[exclude-include]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[exclude-raise]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[include-exclude]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[include-include]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[include-raise]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[raise-exclude]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[raise-include]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[raise-raise]
tests/test_fields.py::TestListNested::test_list_nested_only_exclude_dump_only_load_only_propagated_to_nested[only]
tests/test_fields.py::TestListNested::test_list_nested_only_exclude_dump_only_load_only_propagated_to_nested[exclude]
tests/test_fields.py::TestListNested::test_list_nested_only_exclude_dump_only_load_only_propagated_to_nested[dump_only]
tests/test_fields.py::TestListNested::test_list_nested_only_exclude_dump_only_load_only_propagated_to_nested[load_only]
tests/test_fields.py::TestListNested::test_list_nested_only_and_exclude_merged_with_nested[only-expected0]
tests/test_fields.py::TestListNested::test_list_nested_only_and_exclude_merged_with_nested[exclude-expected1]
tests/test_fields.py::TestListNested::test_list_nested_partial_propagated_to_nested
tests/test_fields.py::TestTupleNested::test_tuple_nested_only_exclude_dump_only_load_only_propagated_to_nested[dump_only]
tests/test_fields.py::TestTupleNested::test_tuple_nested_only_exclude_dump_only_load_only_propagated_to_nested[load_only]
tests/test_fields.py::TestTupleNested::test_tuple_nested_partial_propagated_to_nested
tests/test_fields.py::TestDictNested::test_dict_nested_only_exclude_dump_only_load_only_propagated_to_nested[only]
tests/test_fields.py::TestDictNested::test_dict_nested_only_exclude_dump_only_load_only_propagated_to_nested[exclude]
tests/test_fields.py::TestDictNested::test_dict_nested_only_exclude_dump_only_load_only_propagated_to_nested[dump_only]
tests/test_fields.py::TestDictNested::test_dict_nested_only_exclude_dump_only_load_only_propagated_to_nested[load_only]
tests/test_fields.py::TestDictNested::test_dict_nested_only_and_exclude_merged_with_nested[only-expected0]
tests/test_fields.py::TestDictNested::test_dict_nested_only_and_exclude_merged_with_nested[exclude-expected1]
tests/test_fields.py::TestDictNested::test_dict_nested_partial_propagated_to_nested

Scorer detail

Not resolved by official SWE-bench grading. Fail-to-pass: 0%. Pass-to-pass: 0%.

Patch text

diff --git a/src/marshmallow/schema.py b/src/marshmallow/schema.py
index 520ffb44..3a1fe9fc 100644
--- a/src/marshmallow/schema.py
+++ b/src/marshmallow/schema.py
@@ -343,798 +343,4 @@ class BaseSchema(base.SchemaABC):
         - ``unknown``: Whether to exclude, include, or raise an error for unknown
             fields in the data. Use `EXCLUDE`, `INCLUDE` or `RAISE`.
         - ``register``: Whether to register the `Schema` with marshmallow's internal
-            class registry. Must be `True` if you intend to refer to this `Schema`
-            by class name in `Nested` fields. Only set this to `False` when memory
-            usage is critical. Defaults to `True`.
-        """
-
-        pass
-
-    def __init__(
-        self,
-        *,
-        only=None,
-        exclude=(),
-        many=False,
-        context=None,
-        load_only=(),
-        dump_only=(),
-        partial=False,
-        unknown=None
-    ):
-        # Raise error if only or exclude is passed as string, not list of strings
-        if only is not None and not is_collection(only):
-            raise StringNotCollectionError('"only" should be a list of strings')
-        if exclude is not None and not is_collection(exclude):
-            raise StringNotCollectionError('"exclude" should be a list of strings')
-        # copy declared fields from metaclass
-        self.declared_fields = copy.deepcopy(self._declared_fields)
-        self.many = many
-        self.only = only
-        self.exclude = set(self.opts.exclude) | set(exclude)
-        self.ordered = self.opts.ordered
-        self.load_only = set(load_only) or set(self.opts.load_only)
-        self.dump_only = set(dump_only) or set(self.opts.dump_only)
-        self.partial = partial
-        self.unknown = unknown or self.opts.unknown
-        self.context = context or {}
-        self._normalize_nested_options()
-        #: Dictionary mapping field_names -> :class:`Field` objects
-        self.fields = self._init_fields()
-        self.dump_fields, self.load_fields = self.dict_class(), self.dict_class()
-        for field_name, field_obj in self.fields.items():
-            if field_obj.load_only:
-                self.load_fields[field_name] = field_obj
-            elif field_obj.dump_only:
-                self.dump_fields[field_name] = field_obj
-            else:
-                self.load_fields[field_name] = field_obj
-                self.dump_fields[field_name] = field_obj
-        messages = {}
-        messages.update(self._default_error_messages)
-        for cls in reversed(self.__class__.__mro__):
-            messages.update(getattr(cls, "error_messages", {}))
-        messages.update(self.error_messages or {})
-        self.error_messages = messages
-
-    def __repr__(self):
-        return "<{ClassName}(many={self.many})>".format(
-            ClassName=self.__class__.__name__, self=self
-        )
-
-    @property
-    def dict_class(self):
-        return OrderedDict if self.ordered else dict
-
-    @property
-    def set_class(self):
-        return OrderedSet if self.ordered else set
-
-    @classmethod
-    def from_dict(
-        cls, fields: typing.Dict[str, ma_fields.Field], *, name: str = "GeneratedSchema"
-    ) -> typing.Type["Schema"]:
-        """Generate a `Schema` class given a dictionary of fields.
-
-        .. code-block:: python
-
-            from marshmallow import Schema, fields
-
-            PersonSchema = Schema.from_dict({"name": fields.Str()})
-            print(PersonSchema().load({"name": "David"}))  # => {'name': 'David'}
-
-        Generated schemas are not added to the class registry and therefore cannot
-        be referred to by name in `Nested` fields.
-
-        :param dict fields: Dictionary mapping field names to field instances.
-        :param str name: Optional name for the class, which will appear in
-            the ``repr`` for the class.
-
-        .. versionadded:: 3.0.0
-        """
-        attrs = fields.copy()
-        attrs["Meta"] = type(
-            "GeneratedMeta", (getattr(cls, "Meta", object),), {"register": False}
-        )
-        schema_cls = type(name, (cls,), attrs)
-        return schema_cls
-
-    ##### Override-able methods #####
-
-    def handle_error(self, error, data, *, many, **kwargs):
-        """Custom error handler function for the schema.
-
-        :param ValidationError error: The `ValidationError` raised during (de)serialization.
-        :param data: The original input data.
-        :param bool many: Value of ``many`` on dump or load.
-        :param bool partial: Value of ``partial`` on load.
-
-        .. versionadded:: 2.0.0
-
-        .. versionchanged:: 3.0.0rc9
-            Receives `many` and `partial` (on deserialization) as keyword arguments.
-        """
-        pass
-
-    def get_attribute(self, obj, attr, default):
-        """Defines how to pull values from an object to serialize.
-
-        .. versionadded:: 2.0.0
-
-        .. versionchanged:: 3.0.0a1
-            Changed position of ``obj`` and ``attr``.
-        """
-        return get_value(obj, attr, default)
-
-    ##### Serialization/Deserialization API #####
-
-    @staticmethod
-    def _call_and_store(getter_func, data, *, field_name, error_store, index=None):
-        """Call ``getter_func`` with ``data`` as its argument, and store any `ValidationErrors`.
-
-        :param callable getter_func: Function for getting the serialized/deserialized
-            value from ``data``.
-        :param data: The data passed to ``getter_func``.
-        :param str field_name: Field name.
-        :param int index: Index of the item being validated, if validating a collection,
-            otherwise `None`.
-        """
-        try:
-            value = getter_func(data)
-        except ValidationError as error:
-            error_store.store_error(error.messages, field_name, index=index)
-            # When a Nested field fails validation, the marshalled data is stored
-            # on the ValidationError's valid_data attribute
-            return error.valid_data or missing
-        return value
-
-    def _serialize(self, obj, *, many=False):
-        """Serialize ``obj``.
-
-        :param obj: The object(s) to serialize.
-        :param bool many: `True` if ``data`` should be serialized as a collection.
-        :return: A dictionary of the serialized data
-
-        .. versionchanged:: 1.0.0
-            Renamed from ``marshal``.
-        """
-        if many and obj is not None:
-            return [self._serialize(d, many=False) for d in obj]
-        ret = self.dict_class()
-        for attr_name, field_obj in self.dump_fields.items():
-            value = field_obj.serialize(attr_name, obj, accessor=self.get_attribute)
-            if value is missing:
-                continue
-            key = field_obj.data_key or attr_name
-            ret[key] = value
-        return ret
-
-    def dump(self, obj, *, many=None):
-        """Serialize an object to native Python data types according to this
-        Schema's fields.
-
-        :param obj: The object to serialize.
-        :param bool many: Whether to serialize `obj` as a collection. If `None`, the value
-            for `self.many` is used.
-        :return: A dict of serialized data
-        :rtype: dict
-
-        .. versionadded:: 1.0.0
-        .. versionchanged:: 3.0.0b7
-            This method returns the serialized data rather than a ``(data, errors)`` duple.
-            A :exc:`ValidationError <marshmallow.exceptions.ValidationError>` is raised
-            if ``obj`` is invalid.
-        .. versionchanged:: 3.0.0rc9
-            Validation no longer occurs upon serialization.
-        """
-        many = self.many if many is None else bool(many)
-        if many and is_iterable_but_not_string(obj):
-            obj = list(obj)
-
-        if self._has_processors(PRE_DUMP):
-            processed_obj = self._invoke_dump_processors(
-                PRE_DUMP, obj, many=many, original_data=obj
-            )
-        else:
-            processed_obj = obj
-
-        result = self._serialize(processed_obj, many=many)
-
-        if self._has_processors(POST_DUMP):
-            result = self._invoke_dump_processors(
-                POST_DUMP, result, many=many, original_data=obj
-            )
-
-        return result
-
-    def dumps(self, obj, *args, many=None, **kwargs):
-        """Same as :meth:`dump`, except return a JSON-encoded string.
-
-        :param obj: The object to serialize.
-        :param bool many: Whether to serialize `obj` as a collection. If `None`, the value
-            for `self.many` is used.
-        :return: A ``json`` string
-        :rtype: str
-
-        .. versionadded:: 1.0.0
-        .. versionchanged:: 3.0.0b7
-            This method returns the serialized data rather than a ``(data, errors)`` duple.
-            A :exc:`ValidationError <marshmallow.exceptions.ValidationError>` is raised
-            if ``obj`` is invalid.
-        """
-        serialized = self.dump(obj, many=many)
-        return self.opts.render_module.dumps(serialized, *args, **kwargs)
-
-    def _deserialize(
-        self, data, *, error_store, many=False, partial=False, unknown=RAISE, index=None
-    ):
-        """Deserialize ``data``.
-
-        :param dict data: The data to deserialize.
-        :param ErrorStore error_store: Structure to store errors.
-        :param bool many: `True` if ``data`` should be deserialized as a collection.
-        :param bool|tuple partial: Whether to ignore missing fields and not require
-            any fields declared. Propagates down to ``Nested`` fields as well. If
-            its value is an iterable, only missing fields listed in that iterable
-            will be ignored. Use dot delimiters to specify nested fields.
-        :param unknown: Whether to exclude, include, or raise an error for unknown
-            fields in the data. Use `EXCLUDE`, `INCLUDE` or `RAISE`.
-        :param int index: Index of the item being serialized (for storing errors) if
-            serializing a collection, otherwise `None`.
-        :return: A dictionary of the deserialized data.
-        """
-        index_errors = self.opts.index_errors
-        index = index if index_errors else None
-        if many:
-            if not is_collection(data):
-                error_store.store_error([self.error_messages["type"]], index=index)
-                ret = []
-            else:
-                ret = [
-                    self._deserialize(
-                        d,
-                        error_store=error_store,
-                        many=False,
-                        partial=partial,
-                        unknown=unknown,
-                        index=idx,
-                    )
-                    for idx, d in enumerate(data)
-                ]
-            return ret
-        ret = self.dict_class()
-        # Check data is a dict
-        if not isinstance(data, Mapping):
-            error_store.store_error([self.error_messages["type"]], index=index)
-        else:
-            partial_is_collection = is_collection(partial)
-            for attr_name, field_obj in self.load_fields.items():
-                field_name = field_obj.data_key or attr_name
-                raw_value = data.get(field_name, missing)
-                if raw_value is missing:
-                    # Ignore missing field if we're allowed to.
-                    if partial is True or (
-                        partial_is_collection and attr_name in partial
-                    ):
-                        continue
-                d_kwargs = {}
-                # Allow partial loading of nested schemas.
-                if partial_is_collection:
-                    prefix = field_name + "."
-                    len_prefix = len(prefix)
-                    sub_partial = [
-                        f[len_prefix:] for f in partial if f.startswith(prefix)
-                    ]
-                    d_kwargs["partial"] = sub_partial
-                else:
-                    d_kwargs["partial"] = partial
-                getter = lambda val: field_obj.deserialize(
-                    val, field_name, data, **d_kwargs
-                )
-                value = self._call_and_store(
-                    getter_func=getter,
-                    data=raw_value,
-                    field_name=field_name,
-                    error_store=error_store,
-                    index=index,
-                )
-                if value is not missing:
-                    key = field_obj.attribute or attr_name
-                    set_value(ret, key, value)
-            if unknown != EXCLUDE:
-                fields = {
-                    field_obj.data_key or field_name
-                    for field_name, field_obj in self.load_fields.items()
-                }
-                for key in set(data) - fields:
-                    value = data[key]
-                    if unknown == INCLUDE:
-                        set_value(ret, key, value)
-                    elif unknown == RAISE:
-                        error_store.store_error(
-                            [self.error_messages["unknown"]],
-                            key,
-                            (index if index_errors else None),
-                        )
-        return ret
-
-    def load(self, data, *, many=None, partial=None, unknown=None):
-        """Deserialize a data structure to an object defined by this Schema's fields.
-
-        :param dict data: The data to deserialize.
-        :param bool many: Whether to deserialize `data` as a collection. If `None`, the
-            value for `self.many` is used.
-        :param bool|tuple partial: Whether to ignore missing fields and not require
-            any fields declared. Propagates down to ``Nested`` fields as well. If
-            its value is an iterable, only missing fields listed in that iterable
-            will be ignored. Use dot delimiters to specify nested fields.
-        :param unknown: Whether to exclude, include, or raise an error for unknown
-            fields in the data. Use `EXCLUDE`, `INCLUDE` or `RAISE`.
-            If `None`, the value for `self.unknown` is used.
-        :return: A dict of deserialized data
-        :rtype: dict
-
-        .. versionadded:: 1.0.0
-        .. versionchanged:: 3.0.0b7
-            This method returns the deserialized data rather than a ``(data, errors)`` duple.
-            A :exc:`ValidationError <marshmallow.exceptions.ValidationError>` is raised
-            if invalid data are passed.
-        """
-        return self._do_load(
-            data, many=many, partial=partial, unknown=unknown, postprocess=True
-        )
-
-    def loads(self, json_data, *, many=None, partial=None, unknown=None, **kwargs):
-        """Same as :meth:`load`, except it takes a JSON string as input.
-
-        :param str json_data: A JSON string of the data to deserialize.
-        :param bool many: Whether to deserialize `obj` as a collection. If `None`, the
-            value for `self.many` is used.
-        :param bool|tuple partial: Whether to ignore missing fields and not require
-            any fields declared. Propagates down to ``Nested`` fields as well. If
-            its value is an iterable, only missing fields listed in that iterable
-            will be ignored. Use dot delimiters to specify nested fields.
-        :param unknown: Whether to exclude, include, or raise an error for unknown
-            fields in the data. Use `EXCLUDE`, `INCLUDE` or `RAISE`.
-            If `None`, the value for `self.unknown` is used.
-        :return: A dict of deserialized data
-        :rtype: dict
-
-        .. versionadded:: 1.0.0
-        .. versionchanged:: 3.0.0b7
-            This method returns the deserialized data rather than a ``(data, errors)`` duple.
-            A :exc:`ValidationError <marshmallow.exceptions.ValidationError>` is raised
-            if invalid data are passed.
-        """
-        data = self.opts.render_module.loads(json_data, **kwargs)
-        return self.load(data, many=many, partial=partial, unknown=unknown)
-
-    def _run_validator(
-        self,
-        validator_func,
-        output,
-        *,
-        original_data,
-        error_store,
-        many,
-        partial,
-        pass_original,
-        index=None
-    ):
-        try:
-            if pass_original:  # Pass original, raw data (before unmarshalling)
-                validator_func(output, original_data, partial=partial, many=many)
-            else:
-                validator_func(output, partial=partial, many=many)
-        except ValidationError as err:
-            error_store.store_error(err.messages, err.field_name, index=index)
-
-    def validate(self, data, *, many=None, partial=None):
-        """Validate `data` against the schema, returning a dictionary of
-        validation errors.
-
-        :param dict data: The data to validate.
-        :param bool many: Whether to validate `data` as a collection. If `None`, the
-            value for `self.many` is used.
-        :param bool|tuple partial: Whether to ignore missing fields and not require
-            any fields declared. Propagates down to ``Nested`` fields as well. If
-            its value is an iterable, only missing fields listed in that iterable
-            will be ignored. Use dot delimiters to specify nested fields.
-        :return: A dictionary of validation errors.
-        :rtype: dict
-
-        .. versionadded:: 1.1.0
-        """
-        try:
-            self._do_load(data, many=many, partial=partial, postprocess=False)
-        except ValidationError as exc:
-            return exc.messages
-        return {}
-
-    ##### Private Helpers #####
-
-    def _do_load(
-        self, data, *, many=None, partial=None, unknown=None, postprocess=True
-    ):
-        """Deserialize `data`, returning the deserialized result.
-
-        :param data: The data to deserialize.
-        :param bool many: Whether to deserialize `data` as a collection. If `None`, the
-            value for `self.many` is used.
-        :param bool|tuple partial: Whether to validate required fields. If its
-            value is an iterable, only fields listed in that iterable will be
-            ignored will be allowed missing. If `True`, all fields will be allowed missing.
-            If `None`, the value for `self.partial` is used.
-        :param unknown: Whether to exclude, include, or raise an error for unknown
-            fields in the data. Use `EXCLUDE`, `INCLUDE` or `RAISE`.
-            If `None`, the value for `self.unknown` is used.
-        :param bool postprocess: Whether to run post_load methods..
-        :return: A dict of deserialized data
-        :rtype: dict
-        """
-        error_store = ErrorStore()
-        errors = {}
-        many = self.many if many is None else bool(many)
-        unknown = unknown or self.unknown
-        if partial is None:
-            partial = self.partial
-        # Run preprocessors
-        if self._has_processors(PRE_LOAD):
-            try:
-                processed_data = self._invoke_load_processors(
-                    PRE_LOAD, data, many=many, original_data=data, partial=partial
-                )
-            except ValidationError as err:
-                errors = err.normalized_messages()
-                result = None
-        else:
-            processed_data = data
-        if not errors:
-            # Deserialize data
-            result = self._deserialize(
-                processed_data,
-                error_store=error_store,
-                many=many,
-                partial=partial,
-                unknown=unknown,
-            )
-            # Run field-level validation
-            self._invoke_field_validators(
-                error_store=error_store, data=result, many=many
-            )
-            # Run schema-level validation
-            if self._has_processors(VALIDATES_SCHEMA):
-                field_errors = bool(error_store.errors)
-                self._invoke_schema_validators(
-                    error_store=error_store,
-                    pass_many=True,
-                    data=result,
-                    original_data=data,
-                    many=many,
-                    partial=partial,
-                    field_errors=field_errors,
-                )
-                self._invoke_schema_validators(
-                    error_store=error_store,
-                    pass_many=False,
-                    data=result,
-                    original_data=data,
-                    many=many,
-                    partial=partial,
-                    field_errors=field_errors,
-                )
-            errors = error_store.errors
-            # Run post processors
-            if not errors and postprocess and self._has_processors(POST_LOAD):
-                try:
-                    result = self._invoke_load_processors(
-                        POST_LOAD,
-                        result,
-                        many=many,
-                        original_data=data,
-                        partial=partial,
-                    )
-                except ValidationError as err:
-                    errors = err.normalized_messages()
-        if errors:
-            exc = ValidationError(errors, data=data, valid_data=result)
-            self.handle_error(exc, data, many=many, partial=partial)
-            raise exc
-
-        return result
-
-    def _normalize_nested_options(self):
-        """Apply then flatten nested schema options"""
-        if self.only is not None:
-            # Apply the only option to nested fields.
-            self.__apply_nested_option("only", self.only, "intersection")
-            # Remove the child field names from the only option.
-            self.only = self.set_class([field.split(".", 1)[0] for field in self.only])
-        if self.exclude:
-            # Apply the exclude option to nested fields.
-            self.__apply_nested_option("exclude", self.exclude, "union")
-            # Remove the parent field names from the exclude option.
-            self.exclude = self.set_class(
-                [field for field in self.exclude if "." not in field]
-            )
-
-    def __apply_nested_option(self, option_name, field_names, set_operation):
-        """Apply nested options to nested fields"""
-        # Split nested field names on the first dot.
-        nested_fields = [name.split(".", 1) for name in field_names if "." in name]
-        # Partition the nested field names by parent field.
-        nested_options = defaultdict(list)
-        for parent, nested_names in nested_fields:
-            nested_options[parent].append(nested_names)
-        # Apply the nested field options.
-        for key, options in iter(nested_options.items()):
-            new_options = self.set_class(options)
-            original_options = getattr(self.declared_fields[key], option_name, ())
-            if original_options:
-                if set_operation == "union":
-                    new_options |= self.set_class(original_options)
-                if set_operation == "intersection":
-                    new_options &= self.set_class(original_options)
-            setattr(self.declared_fields[key], option_name, new_options)
-
-    def _init_fields(self):
-        """Update fields based on schema options."""
-        if self.opts.fields:
-            available_field_names = self.set_class(self.opts.fields)
-        else:
-            available_field_names = self.set_class(self.declared_fields.keys())
-            if self.opts.additional:
-                available_field_names |= self.set_class(self.opts.additional)
-
-        invalid_fields = self.set_class()
-
-        if self.only is not None:
-            # Return only fields specified in only option
-            field_names = self.set_class(self.only)
-
-            invalid_fields |= field_names - available_field_names
-        else:
-            field_names = available_field_names
-
-        # If "exclude" option or param is specified, remove those fields.
-        if self.exclude:
-            # Note that this isn't available_field_names, since we want to
-            # apply "only" for the actual calculation.
-            field_names = field_names - self.exclude
-            invalid_fields |= self.exclude - available_field_names
-
-        if invalid_fields:
-            message = "Invalid fields for {}: {}.".format(self, invalid_fields)
-            raise ValueError(message)
-
-        fields_dict = self.dict_class()
-        for field_name in field_names:
-            field_obj = self.declared_fields.get(field_name, ma_fields.Inferred())
-            self._bind_field(field_name, field_obj)
-            fields_dict[field_name] = field_obj
-
-        dump_data_keys = [
-            obj.data_key or name
-            for name, obj in fields_dict.items()
-            if not obj.load_only
-        ]
-        if len(dump_data_keys) != len(set(dump_data_keys)):
-            data_keys_duplicates = {
-                x for x in dump_data_keys if dump_data_keys.count(x) > 1
-            }
-            raise ValueError(
-                "The data_key argument for one or more fields collides "
-                "with another field's name or data_key argument. "
-                "Check the following field names and "
-                "data_key arguments: {}".format(list(data_keys_duplicates))
-            )
-
-        load_attributes = [
-            obj.attribute or name
-            for name, obj in fields_dict.items()
-            if not obj.dump_only
-        ]
-        if len(load_attributes) != len(set(load_attributes)):
-            attributes_duplicates = {
-                x for x in load_attributes if load_attributes.count(x) > 1
-            }
-            raise ValueError(
-                "The attribute argument for one or more fields collides "
-                "with another field's name or attribute argument. "
-                "Check the following field names and "
-                "attribute arguments: {}".format(list(attributes_duplicates))
-            )
-
-        return fields_dict
-
-    def on_bind_field(self, field_name, field_obj):
-        """Hook to modify a field when it is bound to the `Schema`.
-
-        No-op by default.
-        """
-        return None
-
-    def _bind_field(self, field_name, field_obj):
-        """Bind field to the schema, setting any necessary attributes on the
-        field (e.g. parent and name).
-
-        Also set field load_only and dump_only values if field_name was
-        specified in ``class Meta``.
-        """
-        try:
-            if field_name in self.load_only:
-                field_obj.load_only = True
-            if field_name in self.dump_only:
-                field_obj.dump_only = True
-            field_obj._bind_to_schema(field_name, self)
-            self.on_bind_field(field_name, field_obj)
-        except TypeError as error:
-            # field declared as a class, not an instance
-            if isinstance(field_obj, type) and issubclass(field_obj, base.FieldABC):
-                msg = (
-                    'Field for "{}" must be declared as a '
-                    "Field instance, not a class. "
-                    'Did you mean "fields.{}()"?'.format(field_name, field_obj.__name__)
-                )
-                raise TypeError(msg) from error
-
-    @lru_cache(maxsize=8)
-    def _has_processors(self, tag):
-        return self._hooks[(tag, True)] or self._hooks[(tag, False)]
-
-    def _invoke_dump_processors(self, tag, data, *, many, original_data=None):
-        # The pass_many post-dump processors may do things like add an envelope, so
-        # invoke those after invoking the non-pass_many processors which will expect
-        # to get a list of items.
-        data = self._invoke_processors(
-            tag, pass_many=False, data=data, many=many, original_data=original_data
-        )
-        data = self._invoke_processors(
-            tag, pass_many=True, data=data, many=many, original_data=original_data
-        )
-        return data
-
-    def _invoke_load_processors(self, tag, data, *, many, original_data, partial):
-        # This has to invert the order of the dump processors, so run the pass_many
-        # processors first.
-        data = self._invoke_processors(
-            tag,
-            pass_many=True,
-            data=data,
-            many=many,
-            original_data=original_data,
-            partial=partial,
-        )
-        data = self._invoke_processors(
-            tag,
-            pass_many=False,
-            data=data,
-            many=many,
-            original_data=original_data,
-            partial=partial,
-        )
-        return data
-
-    def _invoke_field_validators(self, *, error_store, data, many):
-        for attr_name in self._hooks[VALIDATES]:
-            validator = getattr(self, attr_name)
-            validator_kwargs = validator.__marshmallow_hook__[VALIDATES]
-            field_name = validator_kwargs["field_name"]
-
-            try:
-                field_obj = self.fields[field_name]
-            except KeyError as error:
-                if field_name in self.declared_fields:
-                    continue
-                raise ValueError(
-                    '"{}" field does not exist.'.format(field_name)
-                ) from error
-
-            if many:
-                for idx, item in enumerate(data):
-                    try:
-                        value = item[field_obj.attribute or field_name]
-                    except KeyError:
-                        pass
-                    else:
-                        validated_value = self._call_and_store(
-                            getter_func=validator,
-                            data=value,
-                            field_name=field_obj.data_key or field_name,
-                            error_store=error_store,
-                            index=(idx if self.opts.index_errors else None),
-                        )
-                        if validated_value is missing:
-                            data[idx].pop(field_name, None)
-            else:
-                try:
-                    value = data[field_obj.attribute or field_name]
-                except KeyError:
-                    pass
-                else:
-                    validated_value = self._call_and_store(
-                        getter_func=validator,
-                        data=value,
-                        field_name=field_obj.data_key or field_name,
-                        error_store=error_store,
-                    )
-                    if validated_value is missing:
-                        data.pop(field_name, None)
-
-    def _invoke_schema_validators(
-        self,
-        *,
-        error_store,
-        pass_many,
-        data,
-        original_data,
-        many,
-        partial,
-        field_errors=False
-    ):
-        for attr_name in self._hooks[(VALIDATES_SCHEMA, pass_many)]:
-            validator = getattr(self, attr_name)
-            validator_kwargs = validator.__marshmallow_hook__[
-                (VALIDATES_SCHEMA, pass_many)
-            ]
-            if field_errors and validator_kwargs["skip_on_field_errors"]:
-                continue
-            pass_original = validator_kwargs.get("pass_original", False)
-
-            if many and not pass_many:
-                for idx, (item, orig) in enumerate(zip(data, original_data)):
-                    self._run_validator(
-                        validator,
-                        item,
-                        original_data=orig,
-                        error_store=error_store,
-                        many=many,
-                        partial=partial,
-                        index=idx,
-                        pass_original=pass_original,
-                    )
-            else:
-                self._run_validator(
-                    validator,
-                    data,
-                    original_data=original_data,
-                    error_store=error_store,
-                    many=many,
-                    pass_original=pass_original,
-                    partial=partial,
-                )
-
-    def _invoke_processors(
-        self, tag, *, pass_many, data, many, original_data=None, **kwargs
-    ):
-        key = (tag, pass_many)
-        for attr_name in self._hooks[key]:
-            # This will be a bound method.
-            processor = getattr(self, attr_name)
-
-            processor_kwargs = processor.__marshmallow_hook__[key]
-            pass_original = processor_kwargs.get("pass_original", False)
-
-            if pass_many:
-                if pass_original:
-                    data = processor(data, original_data, many=many, **kwargs)
-                else:
-                    data = processor(data, many=many, **kwargs)
-            elif many:
-                if pass_original:
-                    data = [
-                        processor(item, original, many=many, **kwargs)
-                        for item, original in zip(data, original_data)
-                    ]
-                else:
-                    data = [processor(item, many=many, **kwargs) for item in data]
-            else:
-                if pass_original:
-                    data = processor(data, original_data, many=many, **kwargs)
-                else:
-                    data = processor(data, many=many, **kwargs)
-        return data
-
-
-class Schema(BaseSchema, metaclass=SchemaMeta):
-    __doc__ = BaseSchema.__doc__
+            class registry. Must be `True` if you intend to refer
\ No newline at end of file

Stdout

[anthropic-agent] instance=marshmallow-code__marshmallow-1359
[anthropic-agent] repo=marshmallow-code/marshmallow
[anthropic-agent] sandbox=0242536b-99a8-4cc1-bd48-a695fbd6f419
[anthropic-agent] model=claude-sonnet-4-5-20250929
[anthropic-agent] context_files=6
[anthropic-agent] full_file_context=yes
[anthropic-agent] edit_attempts=2

Stderr

[anthropic-agent] Attempt 1: File-rewrite plan contained no files.

Agent output

diff --git a/src/marshmallow/schema.py b/src/marshmallow/schema.py
index 520ffb44..3a1fe9fc 100644
--- a/src/marshmallow/schema.py
+++ b/src/marshmallow/schema.py
@@ -343,798 +343,4 @@ class BaseSchema(base.SchemaABC):
         - ``unknown``: Whether to exclude, include, or raise an error for unknown
             fields in the data. Use `EXCLUDE`, `INCLUDE` or `RAISE`.
         - ``register``: Whether to register the `Schema` with marshmallow's internal
-            class registry. Must be `True` if you intend to refer to this `Schema`
-            by class name in `Nested` fields. Only set this to `False` when memory
-            usage is critical. Defaults to `True`.
-        """
-
-        pass
-
-    def __init__(
-        self,
-        *,
-        only=None,
-        exclude=(),
-        many=False,
-        context=None,
-        load_only=(),
-        dump_only=(),
-        partial=False,
-        unknown=None
-    ):
-        # Raise error if only or exclude is passed as string, not list of strings
-        if only is not None and not is_collection(only):
-            raise StringNotCollectionError('"only" should be a list of strings')
-        if exclude is not None and not is_collection(exclude):
-            raise StringNotCollectionError('"exclude" should be a list of strings')
-        # copy declared fields from metaclass
-        self.declared_fields = copy.deepcopy(self._declared_fields)
-        self.many = many
-        self.only = only
-        self.exclude = set(self.opts.exclude) | set(exclude)
-        self.ordered = self.opts.ordered
-        self.load_only = set(load_only) or set(self.opts.load_only)
-        self.dump_only = set(dump_only) or set(self.opts.dump_only)
-        self.partial = partial
-        self.unknown = unknown or self.opts.unknown
-        self.context = context or {}
-        self._normalize_nested_options()
-        #: Dictionary mapping field_names -> :class:`Field` objects
-        self.fields = self._init_fields()
-        self.dump_fields, self.load_fields = self.dict_class(), self.dict_class()
-        for field_name, field_obj in self.fields.items():
-            if field_obj.load_only:
-                self.load_fields[field_name] = field_obj
-            elif field_obj.dump_only:
-                self.dump_fields[field_name] = field_obj
-            else:
-                self.load_fields[field_name] = field_obj
-                self.dump_fields[field_name] = field_obj
-        messages = {}
-        messages.update(self._default_error_messages)
-        for cls in reversed(self.__class__.__mro__):
-            messages.update(getattr(cls, "error_messages", {}))
-        messages.update(self.error_messages or {})
-        self.error_messages = messages
-
-    def __repr__(self):
-        return "<{ClassName}(many={self.many})>".format(
-            ClassName=self.__class__.__name__, self=self
-        )
-
-    @property
-    def dict_class(self):
-        return OrderedDict if self.ordered else dict
-
-    @property
-    def set_class(self):
-        return OrderedSet if self.ordered else set
-
-    @classmethod
-    def from_dict(
-        cls, fields: typing.Dict[str, ma_fields.Field], *, name: str = "GeneratedSchema"
-    ) -> typing.Type["Schema"]:
-        """Generate a `Schema` class given a dictionary of fields.
-
-        .. code-block:: python
-
-            from marshmallow import Schema, fields
-
-            PersonSchema = Schema.from_dict({"name": fields.Str()})
-            print(PersonSchema().load({"name": "David"}))  # => {'name': 'David'}
-
-        Generated schemas are not added to the class registry and therefore cannot
-        be referred to by name in `Nested` fields.
-
-        :param dict fields: Dictionary mapping field names to field instances.
-        :param str name: Optional name for the class, which will appear in
-            the ``repr`` for the class.
-
-        .. versionadded:: 3.0.0
-        """
-        attrs = fields.copy()
-        attrs["Meta"] = type(
-            "GeneratedMeta", (getattr(cls, "Meta", object),), {"register": False}
-        )
-        schema_cls = type(name, (cls,), attrs)
-        return schema_cls
-
-    ##### Override-able methods #####
-
-    def handle_error(self, error, data, *, many, **kwargs):
-        """Custom error handler function for the schema.
-
-        :param ValidationError error: The `ValidationError` raised during (de)serialization.
-        :param data: The original input data.
-        :param bool many: Value of ``many`` on dump or load.
-        :param bool partial: Value of ``partial`` on load.
-
-        .. versionadded:: 2.0.0
-
-        .. versionchanged:: 3.0.0rc9
-            Receives `many` and `partial` (on deserialization) as keyword arguments.
-        """
-        pass
-
-    def get_attribute(self, obj, attr, default):
-        """Defines how to pull values from an object to serialize.
-
-        .. versionadded:: 2.0.0
-
-        .. versionchanged:: 3.0.0a1
-            Changed position of ``obj`` and ``attr``.
-        """
-        return get_value(obj, attr, default)
-
-    ##### Serialization/Deserialization API #####
-
-    @staticmethod
-    def _call_and_store(getter_func, data, *, field_name, error_store, index=None):
-        """Call ``getter_func`` with ``data`` as its argument, and store any `ValidationErrors`.
-
-        :param callable getter_func: Function for getting the serialized/deserialized
-            value from ``data``.
-        :param data: The data passed to ``getter_func``.
-        :param str field_name: Field name.
-        :param int index: Index of the item being validated, if validating a collection,
-            otherwise `None`.
-        """
-        try:
-            value = getter_func(data)
-        except ValidationError as error:
-            error_store.store_error(error.messages, field_name, index=index)
-            # When a Nested field fails validation, the marshalled data is stored
-            # on the ValidationError's valid_data attribute
-            return error.valid_data or missing
-        return value
-
-    def _serialize(self, obj, *, many=False):
-        """Serialize ``obj``.
-
-        :param obj: The object(s) to serialize.
-        :param bool many: `True` if ``data`` should be serialized as a collection.
-        :return: A dictionary of the serialized data
-
-        .. versionchanged:: 1.0.0
-            Renamed from ``marshal``.
-        """
-        if many and obj is not None:
-            return [self._serialize(d, many=False) for d in obj]
-        ret = self.dict_class()
-        for attr_name, field_obj in self.dump_fields.items():
-            value = field_obj.serialize(attr_name, obj, accessor=self.get_attribute)
-            if value is missing:
-                continue
-            key = field_obj.data_key or attr_name
-            ret[key] = value
-        return ret
-
-    def dump(self, obj, *, many=None):
-        """Serialize an object to native Python data types according to this
-        Schema's fields.
-
-        :param obj: The object to serialize.
-        :param bool many: Whether to serialize `obj` as a collection. If `None`, the value
-            for `self.many` is used.
-        :return: A dict of serialized data
-        :rtype: dict
-
-        .. versionadded:: 1.0.0
-        .. versionchanged:: 3.0.0b7
-            This method returns the serialized data rather than a ``(data, errors)`` duple.
-            A :exc:`ValidationError <marshmallow.exceptions.ValidationError>` is raised
-            if ``obj`` is invalid.
-        .. versionchanged:: 3.0.0rc9
-            Validation no longer occurs upon serialization.
-        """
-        many = self.many if many is None else bool(many)
-        if many and is_iterable_but_not_string(obj):
-            obj = list(obj)
-
-        if self._has_processors(PRE_DUMP):
-            processed_obj = self._invoke_dump_processors(
-                PRE_DUMP, obj, many=many, original_data=obj
-            )
-        else:
-            processed_obj = obj
-
-        result = self._serialize(processed_obj, many=many)
-
-        if self._has_processors(POST_DUMP):
-            result = self._invoke_dump_processors(
-                POST_DUMP, result, many=many, original_data=obj
-            )
-
-        return result
-
-    def dumps(self, obj, *args, many=None, **kwargs):
-        """Same as :meth:`dump`, except return a JSON-encoded string.
-
-        :param obj: The object to serialize.
-        :param bool many: Whether to serialize `obj` as a collection. If `None`, the value
-            for `self.many` is used.
-        :return: A ``json`` string
-        :rtype: str
-
-        .. versionadded:: 1.0.0
-        .. versionchanged:: 3.0.0b7
-            This method returns the serialized data rather than a ``(data, errors)`` duple.
-            A :exc:`ValidationError <marshmallow.exceptions.ValidationError>` is raised
-            if ``obj`` is invalid.
-        """
-        serialized = self.dump(obj, many=many)
-        return self.opts.render_module.dumps(serialized, *args, **kwargs)
-
-    def _deserialize(
-        self, data, *, error_store, many=False, partial=False, unknown=RAISE, index=None
-    ):
-        """Deserialize ``data``.
-
-        :param dict data: The data to deserialize.
-        :param ErrorStore error_store: Structure to store errors.
-        :param bool many: `True` if ``data`` should be deserialized as a collection.
-        :param bool|tuple partial: Whether to ignore missing fields and not require
-            any fields declared. Propagates down to ``Nested`` fields as well. If
-            its value is an iterable, only missing fields listed in that iterable
-            will be ignored. Use dot delimiters to specify nested fields.
-        :param unknown: Whether to exclude, include, or raise an error for unknown
-            fields in the data. Use `EXCLUDE`, `INCLUDE` or `RAISE`.
-        :param int index: Index of the item being serialized (for storing errors) if
-            serializing a collection, otherwise `None`.
-        :return: A dictionary of the deserialized data.
-        """
-        index_errors = self.opts.index_errors
-        index = index if index_errors else None
-        if many:
-            if not is_collection(data):
-                error_store.store_error([self.error_messages["type"]], index=index)
-                ret = []
-            else:
-                ret = [
-                    self._deserialize(
-                        d,
-                        error_store=error_store,
-                        many=False,
-                        partial=partial,
-                        unknown=unknown,
-                        index=idx,
-                    )
-                    for idx, d in enumerate(data)
-                ]
-            return ret
-        ret = self.dict_class()
-        # Check data is a dict
-        if not isinstance(data, Mapping):
-            error_store.store_error([self.error_messages["type"]], index=index)
-        else:
-            partial_is_collection = is_collection(partial)
-            for attr_name, field_obj in self.load_fields.items():
-                field_name = field_obj.data_key or attr_name
-                raw_value = data.get(field_name, missing)
-                if raw_value is missing:
-                    # Ignore missing field if we're allowed to.
-                    if partial is True or (
-                        partial_is_collection and attr_name in partial
-                    ):
-                        continue
-                d_kwargs = {}
-                # Allow partial loading of nested schemas.
-                if partial_is_collection:
-                    prefix = field_name + "."
-                    len_prefix = len(prefix)
-                    sub_partial = [
-                        f[len_prefix:] for f in partial if f.startswith(prefix)
-                    ]
-                    d_kwargs["partial"] = sub_partial
-                else:
-                    d_kwargs["partial"] = partial
-                getter = lambda val: field_obj.deserialize(
-                    val, field_name, data, **d_kwargs
-                )
-                value = self._call_and_store(
-                    getter_func=getter,
-                    data=raw_value,
-                    field_name=field_name,
-                    error_store=error_store,
-                    index=index,
-                )
-                if value is not missing:
-                    key = field_obj.attribute or attr_name
-                    set_value(ret, key, value)
-            if unknown != EXCLUDE:
-                fields = {
-                    field_obj.data_key or field_name
-                    for field_name, field_obj in self.load_fields.items()
-                }
-                for key in set(data) - fields:
-                    value = data[key]
-                    if unknown == INCLUDE:
-                        set_value(ret, key, value)
-                    elif unknown == RAISE:
-                        error_store.store_error(
-                            [self.error_messages["unknown"]],
-                            key,
-                            (index if index_errors else None),
-                        )
-        return ret
-
-    def load(self, data, *, many=None, partial=None, unknown=None):
-        """Deserialize a data structure to an object defined by this Schema's fields.
-
-        :param dict data: The data to deserialize.
-        :param bool many: Whether to deserialize `data` as a collection. If `None`, the
-            value for `self.many` is used.
-        :param bool|tuple partial: Whether to ignore missing fields and not require
-            any fields declared. Propagates down to ``Nested`` fields as well. If
-            its value is an iterable, only missing fields listed in that iterable
-            will be ignored. Use dot delimiters to specify nested fields.
-        :param unknown: Whether to exclude, include, or raise an error for unknown
-            fields in the data. Use `EXCLUDE`, `INCLUDE` or `RAISE`.
-            If `None`, the value for `self.unknown` is used.
-        :return: A dict of deserialized data
-        :rtype: dict
-
-        .. versionadded:: 1.0.0
-        .. versionchanged:: 3.0.0b7
-            This method returns the deserialized data rather than a ``(data, errors)`` duple.
-            A :exc:`ValidationError <marshmallow.exceptions.ValidationError>` is raised
-            if invalid data are passed.
-        """
-        return self._do_load(
-            data, many=many, partial=partial, unknown=unknown, postprocess=True
-        )
-
-    def loads(self, json_data, *, many=None, partial=None, unknown=None, **kwargs):
-        """Same as :meth:`load`, except it takes a JSON string as input.
-
-        :param str json_data: A JSON string of the data to deserialize.
-        :param bool many: Whether to deserialize `obj` as a collection. If `None`, the
-            value for `self.many` is used.
-        :param bool|tuple partial: Whether to ignore missing fields and not require
-            any fields declared. Propagates down to ``Nested`` fields as well. If
-            its value is an iterable, only missing fields listed in that iterable
-            will be ignored. Use dot delimiters to specify nested fields.
-        :param unknown: Whether to exclude, include, or raise an error for unknown
-            fields in the data. Use `EXCLUDE`, `INCLUDE` or `RAISE`.
-            If `None`, the value for `self.unknown` is used.
-        :return: A dict of deserialized data
-        :rtype: dict
-
-        .. versionadded:: 1.0.0
-        .. versionchanged:: 3.0.0b7
-            This method returns the deserialized data rather than a ``(data, errors)`` duple.
-            A :exc:`ValidationError <marshmallow.exceptions.ValidationError>` is raised
-            if invalid data are passed.
-        """
-        data = self.opts.render_module.loads(json_data, **kwargs)
-        return self.load(data, many=many, partial=partial, unknown=unknown)
-
-    def _run_validator(
-        self,
-        validator_func,
-        output,
-        *,
-        original_data,
-        error_store,
-        many,
-        partial,
-        pass_original,
-        index=None
-    ):
-        try:
-            if pass_original:  # Pass original, raw data (before unmarshalling)
-                validator_func(output, original_data, partial=partial, many=many)
-            else:
-                validator_func(output, partial=partial, many=many)
-        except ValidationError as err:
-            error_store.store_error(err.messages, err.field_name, index=index)
-
-    def validate(self, data, *, many=None, partial=None):
-        """Validate `data` against the schema, returning a dictionary of
-        validation errors.
-
-        :param dict data: The data to validate.
-        :param bool many: Whether to validate `data` as a collection. If `None`, the
-            value for `self.many` is used.
-        :param bool|tuple partial: Whether to ignore missing fields and not require
-            any fields declared. Propagates down to ``Nested`` fields as well. If
-            its value is an iterable, only missing fields listed in that iterable
-            will be ignored. Use dot delimiters to specify nested fields.
-        :return: A dictionary of validation errors.
-        :rtype: dict
-
-        .. versionadded:: 1.1.0
-        """
-        try:
-            self._do_load(data, many=many, partial=partial, postprocess=False)
-        except ValidationError as exc:
-            return exc.messages
-        return {}
-
-    ##### Private Helpers #####
-
-    def _do_load(
-        self, data, *, many=None, partial=None, unknown=None, postprocess=True
-    ):
-        """Deserialize `data`, returning the deserialized result.
-
-        :param data: The data to deserialize.
-        :param bool many: Whether to deserialize `data` as a collection. If `None`, the
-            value for `self.many` is used.
-        :param bool|tuple partial: Whether to validate required fields. If its
-            value is an iterable, only fields listed in that iterable will be
-            ignored will be allowed missing. If `True`, all fields will be allowed missing.
-            If `None`, the value for `self.partial` is used.
-        :param unknown: Whether to exclude, include, or raise an error for unknown
-            fields in the data. Use `EXCLUDE`, `INCLUDE` or `RAISE`.
-            If `None`, the value for `self.unknown` is used.
-        :param bool postprocess: Whether to run post_load methods..
-        :return: A dict of deserialized data
-        :rtype: dict
-        """
-        error_store = ErrorStore()
-        errors = {}
-        many = self.many if many is None else bool(many)
-        unknown = unknown or self.unknown
-        if partial is None:
-            partial = self.partial
-        # Run preprocessors
-        if self._has_processors(PRE_LOAD):
-            try:
-                processed_data = self._invoke_load_processors(
-                    PRE_LOAD, data, many=many, original_data=data, partial=partial
-                )
-            except ValidationError as err:
-                errors = err.normalized_messages()
-                result = None
-        else:
-            processed_data = data
-        if not errors:
-            # Deserialize data
-            result = self._deserialize(
-                processed_data,
-                error_store=error_store,
-                many=many,
-                partial=partial,
-                unknown=unknown,
-            )
-            # Run field-level validation
-            self._invoke_field_validators(
-                error_store=error_store, data=result, many=many
-            )
-            # Run schema-level validation
-            if self._has_processors(VALIDATES_SCHEMA):
-                field_errors = bool(error_store.errors)
-                self._invoke_schema_validators(
-                    error_store=error_store,
-                    pass_many=True,
-                    data=result,
-                    original_data=data,
-                    many=many,
-                    partial=partial,
-                    field_errors=field_errors,
-                )
-                self._invoke_schema_validators(
-                    error_store=error_store,
-                    pass_many=False,
-                    data=result,
-                    original_data=data,
-                    many=many,
-                    partial=partial,
-                    field_errors=field_errors,
-                )
-            errors = error_store.errors
-            # Run post processors
-            if not errors and postprocess and self._has_processors(POST_LOAD):
-                try:
-                    result = self._invoke_load_processors(
-                        POST_LOAD,
-                        result,
-                        many=many,
-                        original_data=data,
-                        partial=partial,
-                    )
-                except ValidationError as err:
-                    errors = err.normalized_messages()
-        if errors:
-            exc = ValidationError(errors, data=data, valid_data=result)
-            self.handle_error(exc, data, many=many, partial=partial)
-            raise exc
-
-        return result
-
-    def _normalize_nested_options(self):
-        """Apply then flatten nested schema options"""
-        if self.only is not None:
-            # Apply the only option to nested fields.
-            self.__apply_nested_option("only", self.only, "intersection")
-            # Remove the child field names from the only option.
-            self.only = self.set_class([field.split(".", 1)[0] for field in self.only])
-        if self.exclude:
-            # Apply the exclude option to nested fields.
-            self.__apply_nested_option("exclude", self.exclude, "union")
-            # Remove the parent field names from the exclude option.
-            self.exclude = self.set_class(
-                [field for field in self.exclude if "." not in field]
-            )
-
-    def __apply_nested_option(self, option_name, field_names, set_operation):
-        """Apply nested options to nested fields"""
-        # Split nested field names on the first dot.
-        nested_fields = [name.split(".", 1) for name in field_names if "." in name]
-        # Partition the nested field names by parent field.
-        nested_options = defaultdict(list)
-        for parent, nested_names in nested_fields:
-            nested_options[parent].append(nested_names)
-        # Apply the nested field options.
-        for key, options in iter(nested_options.items()):
-            new_options = self.set_class(options)
-            original_options = getattr(self.declared_fields[key], option_name, ())
-            if original_options:
-                if set_operation == "union":
-                    new_options |= self.set_class(original_options)
-                if set_operation == "intersection":
-                    new_options &= self.set_class(original_options)
-            setattr(self.declared_fields[key], option_name, new_options)
-
-    def _init_fields(self):
-        """Update fields based on schema options."""
-        if self.opts.fields:
-            available_field_names = self.set_class(self.opts.fields)
-        else:
-            available_field_names = self.set_class(self.declared_fields.keys())
-            if self.opts.additional:
-                available_field_names |= self.set_class(self.opts.additional)
-
-        invalid_fields = self.set_class()
-
-        if self.only is not None:
-            # Return only fields specified in only option
-            field_names = self.set_class(self.only)
-
-            invalid_fields |= field_names - available_field_names
-        else:
-            field_names = available_field_names
-
-        # If "exclude" option or param is specified, remove those fields.
-        if self.exclude:
-            # Note that this isn't available_field_names, since we want to
-            # apply "only" for the actual calculation.
-            field_names = field_names - self.exclude
-            invalid_fields |= self.exclude - available_field_names
-
-        if invalid_fields:
-            message = "Invalid fields for {}: {}.".format(self, invalid_fields)
-            raise ValueError(message)
-
-        fields_dict = self.dict_class()
-        for field_name in field_names:
-            field_obj = self.declared_fields.get(field_name, ma_fields.Inferred())
-            self._bind_field(field_name, field_obj)
-            fields_dict[field_name] = field_obj
-
-        dump_data_keys = [
-            obj.data_key or name
-            for name, obj in fields_dict.items()
-            if not obj.load_only
-        ]
-        if len(dump_data_keys) != len(set(dump_data_keys)):
-            data_keys_duplicates = {
-                x for x in dump_data_keys if dump_data_keys.count(x) > 1
-            }
-            raise ValueError(
-                "The data_key argument for one or more fields collides "
-                "with another field's name or data_key argument. "
-                "Check the following field names and "
-                "data_key arguments: {}".format(list(data_keys_duplicates))
-            )
-
-        load_attributes = [
-            obj.attribute or name
-            for name, obj in fields_dict.items()
-            if not obj.dump_only
-        ]
-        if len(load_attributes) != len(set(load_attributes)):
-            attributes_duplicates = {
-                x for x in load_attributes if load_attributes.count(x) > 1
-            }
-            raise ValueError(
-                "The attribute argument for one or more fields collides "
-                "with another field's name or attribute argument. "
-                "Check the following field names and "
-                "attribute arguments: {}".format(list(attributes_duplicates))
-            )
-
-        return fields_dict
-
-    def on_bind_field(self, field_name, field_obj):
-        """Hook to modify a field when it is bound to the `Schema`.
-
-        No-op by default.
-        """
-        return None
-
-    def _bind_field(self, field_name, field_obj):
-        """Bind field to the schema, setting any necessary attributes on the
-        field (e.g. parent and name).
-
-        Also set field load_only and dump_only values if field_name was
-        specified in ``class Meta``.
-        """
-        try:
-            if field_name in self.load_only:
-                field_obj.load_only = True
-            if field_name in self.dump_only:
-                field_obj.dump_only = True
-            field_obj._bind_to_schema(field_name, self)
-            self.on_bind_field(field_name, field_obj)
-        except TypeError as error:
-            # field declared as a class, not an instance
-            if isinstance(field_obj, type) and issubclass(field_obj, base.FieldABC):
-                msg = (
-                    'Field for "{}" must be declared as a '
-                    "Field instance, not a class. "
-                    'Did you mean "fields.{}()"?'.format(field_name, field_obj.__name__)
-                )
-                raise TypeError(msg) from error
-
-    @lru_cache(maxsize=8)
-    def _has_processors(self, tag):
-        return self._hooks[(tag, True)] or self._hooks[(tag, False)]
-
-    def _invoke_dump_processors(self, tag, data, *, many, original_data=None):
-        # The pass_many post-dump processors may do things like add an envelope, so
-        # invoke those after invoking the non-pass_many processors which will expect
-        # to get a list of items.
-        data = self._invoke_processors(
-            tag, pass_many=False, data=data, many=many, original_data=original_data
-        )
-        data = self._invoke_processors(
-            tag, pass_many=True, data=data, many=many, original_data=original_data
-        )
-        return data
-
-    def _invoke_load_processors(self, tag, data, *, many, original_data, partial):
-        # This has to invert the order of the dump processors, so run the pass_many
-        # processors first.
-        data = self._invoke_processors(
-            tag,
-            pass_many=True,
-            data=data,
-            many=many,
-            original_data=original_data,
-            partial=partial,
-        )
-        data = self._invoke_processors(
-            tag,
-            pass_many=False,
-            data=data,
-            many=many,
-            original_data=original_data,
-            partial=partial,
-        )
-        return data
-
-    def _invoke_field_validators(self, *, error_store, data, many):
-        for attr_name in self._hooks[VALIDATES]:
-            validator = getattr(self, attr_name)
-            validator_kwargs = validator.__marshmallow_hook__[VALIDATES]
-            field_name = validator_kwargs["field_name"]
-
-            try:
-                field_obj = self.fields[field_name]
-            except KeyError as error:
-                if field_name in self.declared_fields:
-                    continue
-                raise ValueError(
-                    '"{}" field does not exist.'.format(field_name)
-                ) from error
-
-            if many:
-                for idx, item in enumerate(data):
-                    try:
-                        value = item[field_obj.attribute or field_name]
-                    except KeyError:
-                        pass
-                    else:
-                        validated_value = self._call_and_store(
-                            getter_func=validator,
-                            data=value,
-                            field_name=field_obj.data_key or field_name,
-                            error_store=error_store,
-                            index=(idx if self.opts.index_errors else None),
-                        )
-                        if validated_value is missing:
-                            data[idx].pop(field_name, None)
-            else:
-                try:
-                    value = data[field_obj.attribute or field_name]
-                except KeyError:
-                    pass
-                else:
-                    validated_value = self._call_and_store(
-                        getter_func=validator,
-                        data=value,
-                        field_name=field_obj.data_key or field_name,
-                        error_store=error_store,
-                    )
-                    if validated_value is missing:
-                        data.pop(field_name, None)
-
-    def _invoke_schema_validators(
-        self,
-        *,
-        error_store,
-        pass_many,
-        data,
-        original_data,
-        many,
-        partial,
-        field_errors=False
-    ):
-        for attr_name in self._hooks[(VALIDATES_SCHEMA, pass_many)]:
-            validator = getattr(self, attr_name)
-            validator_kwargs = validator.__marshmallow_hook__[
-                (VALIDATES_SCHEMA, pass_many)
-            ]
-            if field_errors and validator_kwargs["skip_on_field_errors"]:
-                continue
-            pass_original = validator_kwargs.get("pass_original", False)
-
-            if many and not pass_many:
-                for idx, (item, orig) in enumerate(zip(data, original_data)):
-                    self._run_validator(
-                        validator,
-                        item,
-                        original_data=orig,
-                        error_store=error_store,
-                        many=many,
-                        partial=partial,
-                        index=idx,
-                        pass_original=pass_original,
-                    )
-            else:
-                self._run_validator(
-                    validator,
-                    data,
-                    original_data=original_data,
-                    error_store=error_store,
-                    many=many,
-                    pass_original=pass_original,
-                    partial=partial,
-                )
-
-    def _invoke_processors(
-        self, tag, *, pass_many, data, many, original_data=None, **kwargs
-    ):
-        key = (tag, pass_many)
-        for attr_name in self._hooks[key]:
-            # This will be a bound method.
-            processor = getattr(self, attr_name)
-
-            processor_kwargs = processor.__marshmallow_hook__[key]
-            pass_original = processor_kwargs.get("pass_original", False)
-
-            if pass_many:
-                if pass_original:
-                    data = processor(data, original_data, many=many, **kwargs)
-                else:
-                    data = processor(data, many=many, **kwargs)
-            elif many:
-                if pass_original:
-                    data = [
-                        processor(item, original, many=many, **kwargs)
-                        for item, original in zip(data, original_data)
-                    ]
-                else:
-                    data = [processor(item, many=many, **kwargs) for item in data]
-            else:
-                if pass_original:
-                    data = processor(data, original_data, many=many, **kwargs)
-                else:
-                    data = processor(data, many=many, **kwargs)
-        return data
-
-
-class Schema(BaseSchema, metaclass=SchemaMeta):
-    __doc__ = BaseSchema.__doc__
+            class registry. Must be `True` if you intend to refer
\ No newline at end of file

Passing target tests

No fail-to-pass successes recorded yet.

Failing target tests

tests/test_fields.py::TestParentAndName::test_datetime_list_inner_format

Maintained regression tests

No pass-to-pass successes recorded yet.

Regressed tests

tests/test_fields.py::test_field_aliases[Integer-Integer]
tests/test_fields.py::test_field_aliases[String-String]
tests/test_fields.py::test_field_aliases[Boolean-Boolean]
tests/test_fields.py::test_field_aliases[Url-Url]
tests/test_fields.py::TestField::test_repr
tests/test_fields.py::TestField::test_error_raised_if_uncallable_validator_passed
tests/test_fields.py::TestField::test_error_raised_if_missing_is_set_on_required_field
tests/test_fields.py::TestField::test_custom_field_receives_attr_and_obj
tests/test_fields.py::TestField::test_custom_field_receives_data_key_if_set
tests/test_fields.py::TestField::test_custom_field_follows_data_key_if_set
tests/test_fields.py::TestParentAndName::test_simple_field_parent_and_name
tests/test_fields.py::TestParentAndName::test_unbound_field_root_returns_none
tests/test_fields.py::TestParentAndName::test_list_field_inner_parent_and_name
tests/test_fields.py::TestParentAndName::test_tuple_field_inner_parent_and_name
tests/test_fields.py::TestParentAndName::test_mapping_field_inner_parent_and_name
tests/test_fields.py::TestParentAndName::test_simple_field_root
tests/test_fields.py::TestParentAndName::test_list_field_inner_root
tests/test_fields.py::TestParentAndName::test_tuple_field_inner_root
tests/test_fields.py::TestParentAndName::test_list_root_inheritance
tests/test_fields.py::TestParentAndName::test_dict_root_inheritance
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[String]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Integer]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Boolean]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Float]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Number]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[DateTime]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Time]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Date]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[TimeDelta]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Dict]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Url]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Email]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[UUID]
tests/test_fields.py::TestMetadata::test_extra_metadata_may_be_added_to_field[Decimal]
tests/test_fields.py::TestErrorMessages::test_default_error_messages_get_merged_with_parent_error_messages_cstm_msg
tests/test_fields.py::TestErrorMessages::test_default_error_messages_get_merged_with_parent_error_messages
tests/test_fields.py::TestErrorMessages::test_make_error[required-Missing
tests/test_fields.py::TestErrorMessages::test_make_error[null-Field
tests/test_fields.py::TestErrorMessages::test_make_error[custom-Custom
tests/test_fields.py::TestErrorMessages::test_make_error[validator_failed-Invalid
tests/test_fields.py::TestErrorMessages::test_fail[required-Missing
tests/test_fields.py::TestErrorMessages::test_fail[null-Field
tests/test_fields.py::TestErrorMessages::test_fail[custom-Custom
tests/test_fields.py::TestErrorMessages::test_fail[validator_failed-Invalid
tests/test_fields.py::TestErrorMessages::test_make_error_key_doesnt_exist
tests/test_fields.py::TestNestedField::test_nested_only_and_exclude_as_string[only]
tests/test_fields.py::TestNestedField::test_nested_only_and_exclude_as_string[exclude]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[None-exclude]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[None-include]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[None-raise]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[exclude-exclude]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[exclude-include]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[exclude-raise]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[include-exclude]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[include-include]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[include-raise]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[raise-exclude]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[raise-include]
tests/test_fields.py::TestNestedField::test_nested_unknown_override[raise-raise]
tests/test_fields.py::TestListNested::test_list_nested_only_exclude_dump_only_load_only_propagated_to_nested[only]
tests/test_fields.py::TestListNested::test_list_nested_only_exclude_dump_only_load_only_propagated_to_nested[exclude]
tests/test_fields.py::TestListNested::test_list_nested_only_exclude_dump_only_load_only_propagated_to_nested[dump_only]
tests/test_fields.py::TestListNested::test_list_nested_only_exclude_dump_only_load_only_propagated_to_nested[load_only]
tests/test_fields.py::TestListNested::test_list_nested_only_and_exclude_merged_with_nested[only-expected0]
tests/test_fields.py::TestListNested::test_list_nested_only_and_exclude_merged_with_nested[exclude-expected1]
tests/test_fields.py::TestListNested::test_list_nested_partial_propagated_to_nested
tests/test_fields.py::TestTupleNested::test_tuple_nested_only_exclude_dump_only_load_only_propagated_to_nested[dump_only]
tests/test_fields.py::TestTupleNested::test_tuple_nested_only_exclude_dump_only_load_only_propagated_to_nested[load_only]
tests/test_fields.py::TestTupleNested::test_tuple_nested_partial_propagated_to_nested
tests/test_fields.py::TestDictNested::test_dict_nested_only_exclude_dump_only_load_only_propagated_to_nested[only]
tests/test_fields.py::TestDictNested::test_dict_nested_only_exclude_dump_only_load_only_propagated_to_nested[exclude]
tests/test_fields.py::TestDictNested::test_dict_nested_only_exclude_dump_only_load_only_propagated_to_nested[dump_only]
tests/test_fields.py::TestDictNested::test_dict_nested_only_exclude_dump_only_load_only_propagated_to_nested[load_only]
tests/test_fields.py::TestDictNested::test_dict_nested_only_and_exclude_merged_with_nested[only-expected0]
tests/test_fields.py::TestDictNested::test_dict_nested_only_and_exclude_merged_with_nested[exclude-expected1]
tests/test_fields.py::TestDictNested::test_dict_nested_partial_propagated_to_nested

Harness output

+ source /opt/miniconda3/bin/activate
++ _CONDA_ROOT=/opt/miniconda3
++ . /opt/miniconda3/etc/profile.d/conda.sh
+++ export CONDA_EXE=/opt/miniconda3/bin/conda
+++ CONDA_EXE=/opt/miniconda3/bin/conda
+++ export _CE_M=
+++ _CE_M=
+++ export _CE_CONDA=
+++ _CE_CONDA=
+++ export CONDA_PYTHON_EXE=/opt/miniconda3/bin/python
+++ CONDA_PYTHON_EXE=/opt/miniconda3/bin/python
+++ '[' -z x ']'
++ conda activate
++ local cmd=activate
++ case "$cmd" in
++ __conda_activate activate
++ '[' -n '' ']'
++ local ask_conda
+++ PS1=
+++ __conda_exe shell.posix activate
+++ /opt/miniconda3/bin/conda shell.posix activate
++ ask_conda='PS1='\''(base) '\''
export PATH='\''/opt/miniconda3/bin:/opt/miniconda3/condabin:/opt/miniconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin'\''
export CONDA_PREFIX='\''/opt/miniconda3'\''
export CONDA_SHLVL='\''2'\''
export CONDA_DEFAULT_ENV='\''base'\''
export CONDA_PROMPT_MODIFIER='\''(base) '\''
export CONDA_PREFIX_1='\''/opt/miniconda3/envs/testbed'\''
export CONDA_EXE='\''/opt/miniconda3/bin/conda'\''
export _CE_M='\'''\''
export _CE_CONDA='\'''\''
export CONDA_PYTHON_EXE='\''/opt/miniconda3/bin/python'\'''
++ eval 'PS1='\''(base) '\''
export PATH='\''/opt/miniconda3/bin:/opt/miniconda3/condabin:/opt/miniconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin'\''
export CONDA_PREFIX='\''/opt/miniconda3'\''
export CONDA_SHLVL='\''2'\''
export CONDA_DEFAULT_ENV='\''base'\''
export CONDA_PROMPT_MODIFIER='\''(base) '\''
export CONDA_PREFIX_1='\''/opt/miniconda3/envs/testbed'\''
export CONDA_EXE='\''/opt/miniconda3/bin/conda'\''
export _CE_M='\'''\''
export _CE_CONDA='\'''\''
export CONDA_PYTHON_EXE='\''/opt/miniconda3/bin/python'\'''
+++ PS1='(base) '
+++ export PATH=/opt/miniconda3/bin:/opt/miniconda3/condabin:/opt/miniconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
+++ PATH=/opt/miniconda3/bin:/opt/miniconda3/condabin:/opt/miniconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
+++ export CONDA_PREFIX=/opt/miniconda3
+++ CONDA_PREFIX=/opt/miniconda3
+++ export CONDA_SHLVL=2
+++ CONDA_SHLVL=2
+++ export CONDA_DEFAULT_ENV=base
+++ CONDA_DEFAULT_ENV=base
+++ export 'CONDA_PROMPT_MODIFIER=(base) '
+++ CONDA_PROMPT_MODIFIER='(base) '
+++ export CONDA_PREFIX_1=/opt/miniconda3/envs/testbed
+++ CONDA_PREFIX_1=/opt/miniconda3/envs/testbed
+++ export CONDA_EXE=/opt/miniconda3/bin/conda
+++ CONDA_EXE=/opt/miniconda3/bin/conda
+++ export _CE_M=
+++ _CE_M=
+++ export _CE_CONDA=
+++ _CE_CONDA=
+++ export CONDA_PYTHON_EXE=/opt/miniconda3/bin/python
+++ CONDA_PYTHON_EXE=/opt/miniconda3/bin/python
++ __conda_hashr
++ '[' -n '' ']'
++ '[' -n '' ']'
++ hash -r
+ conda activate testbed
+ local cmd=activate
+ case "$cmd" in
+ __conda_activate activate testbed
+ '[' -n '' ']'
+ local ask_conda
++ PS1='(base) '
++ __conda_exe shell.posix activate testbed
++ /opt/miniconda3/bin/conda shell.posix activate testbed
+ ask_conda='PS1='\''(testbed) '\''
export PATH='\''/opt/miniconda3/envs/testbed/bin:/opt/miniconda3/condabin:/opt/miniconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin'\''
export CONDA_PREFIX='\''/opt/miniconda3/envs/testbed'\''
export CONDA_SHLVL='\''3'\''
export CONDA_DEFAULT_ENV='\''testbed'\''
export CONDA_PROMPT_MODIFIER='\''(testbed) '\''
export CONDA_PREFIX_2='\''/opt/miniconda3'\''
export CONDA_EXE='\''/opt/miniconda3/bin/conda'\''
export _CE_M='\'''\''
export _CE_CONDA='\'''\''
export CONDA_PYTHON_EXE='\''/opt/miniconda3/bin/python'\'''
+ eval 'PS1='\''(testbed) '\''
export PATH='\''/opt/miniconda3/envs/testbed/bin:/opt/miniconda3/condabin:/opt/miniconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin'\''
export CONDA_PREFIX='\''/opt/miniconda3/envs/testbed'\''
export CONDA_SHLVL='\''3'\''
export CONDA_DEFAULT_ENV='\''testbed'\''
export CONDA_PROMPT_MODIFIER='\''(testbed) '\''
export CONDA_PREFIX_2='\''/opt/miniconda3'\''
export CONDA_EXE='\''/opt/miniconda3/bin/conda'\''
export _CE_M='\'''\''
export _CE_CONDA='\'''\''
export CONDA_PYTHON_EXE='\''/opt/miniconda3/bin/python'\'''
++ PS1='(testbed) '
++ export PATH=/opt/miniconda3/envs/testbed/bin:/opt/miniconda3/condabin:/opt/miniconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
++ PATH=/opt/miniconda3/envs/testbed/bin:/opt/miniconda3/condabin:/opt/miniconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
++ export CONDA_PREFIX=/opt/miniconda3/envs/testbed
++ CONDA_PREFIX=/opt/miniconda3/envs/testbed
++ export CONDA_SHLVL=3
++ CONDA_SHLVL=3
++ export CONDA_DEFAULT_ENV=testbed
++ CONDA_DEFAULT_ENV=testbed
++ export 'CONDA_PROMPT_MODIFIER=(testbed) '
++ CONDA_PROMPT_MODIFIER='(testbed) '
++ export CONDA_PREFIX_2=/opt/miniconda3
++ CONDA_PREFIX_2=/opt/miniconda3
++ export CONDA_EXE=/opt/miniconda3/bin/conda
++ CONDA_EXE=/opt/miniconda3/bin/conda
++ export _CE_M=
++ _CE_M=
++ export _CE_CONDA=
++ _CE_CONDA=
++ export CONDA_PYTHON_EXE=/opt/miniconda3/bin/python
++ CONDA_PYTHON_EXE=/opt/miniconda3/bin/python
+ __conda_hashr
+ '[' -n '' ']'
+ '[' -n '' ']'
+ hash -r
+ cd /testbed
+ git config --global --add safe.directory /testbed
+ cd /testbed
+ git status
On branch dev
Changes not staged for commit:
  (use "git add <file>..." to update what will be committed)
  (use "git restore <file>..." to discard changes in working directory)
	modified:   src/marshmallow/schema.py

no changes added to commit (use "git add" and/or "git commit -a")
+ git show
commit 8ad28316545371a1d1d7c2ad0b32d5f8ab206853
Author: SWE-bench <setup@swebench.config>
Date:   Tue May 6 23:07:21 2025 +0000

    SWE-bench
+ git -c core.fileMode=false diff b40a0f4e33823e6d0f341f7e8684e359a99060d1
diff --git a/src/marshmallow/schema.py b/src/marshmallow/schema.py
index 520ffb44..3a1fe9fc 100644
--- a/src/marshmallow/schema.py
+++ b/src/marshmallow/schema.py
@@ -343,798 +343,4 @@ class BaseSchema(base.SchemaABC):
         - ``unknown``: Whether to exclude, include, or raise an error for unknown
             fields in the data. Use `EXCLUDE`, `INCLUDE` or `RAISE`.
         - ``register``: Whether to register the `Schema` with marshmallow's internal
-            class registry. Must be `True` if you intend to refer to this `Schema`
-            by class name in `Nested` fields. Only set this to `False` when memory
-            usage is critical. Defaults to `True`.
-        """
-
-        pass
-
-    def __init__(
-        self,
-        *,
-        only=None,
-        exclude=(),
-        many=False,
-        context=None,
-        load_only=(),
-        dump_only=(),
-        partial=False,
-        unknown=None
-    ):
-        # Raise error if only or exclude is passed as string, not list of strings
-        if only is not None and not is_collection(only):
-            raise StringNotCollectionError('"only" should be a list of strings')
-        if exclude is not None and not is_collection(exclude):
-            raise StringNotCollectionError('"exclude" should be a list of strings')
-        # copy declared fields from metaclass
-        self.declared_fields = copy.deepcopy(self._declared_fields)
-        self.many = many
-        self.only = only
-        self.exclude = set(self.opts.exclude) | set(exclude)
-        self.ordered = self.opts.ordered
-        self.load_only = set(load_only) or set(self.opts.load_only)
-        self.dump_only = set(dump_only) or set(self.opts.dump_only)
-        self.partial = partial
-        self.unknown = unknown or self.opts.unknown
-        self.context = context or {}
-        self._normalize_nested_options()
-        #: Dictionary mapping field_names -> :class:`Field` objects
-        self.fields = self._init_fields()
-        self.dump_fields, self.load_fields = self.dict_class(), self.dict_class()
-        for field_name, field_obj in self.fields.items():
-            if field_obj.load_only:
-                self.load_fields[field_name] = field_obj
-            elif field_obj.dump_only:
-                self.dump_fields[field_name] = field_obj
-            else:
-                self.load_fields[field_name] = field_obj
-                self.dump_fields[field_name] = field_obj
-        messages = {}
-        messages.update(self._default_error_messages)
-        for cls in reversed(self.__class__.__mro__):
-            messages.update(getattr(cls, "error_messages", {}))
-        messages.update(self.error_messages or {})
-        self.error_messages = messages
-
-    def __repr__(self):
-        return "<{ClassName}(many={self.many})>".format(
-            ClassName=self.__class__.__name__, self=self
-        )
-
-    @property
-    def dict_class(self):
-        return OrderedDict if self.ordered else dict
-
-    @property
-    def set_class(self):
-        return OrderedSet if self.ordered else set
-
-    @classmethod
-    def from_dict(
-        cls, fields: typing.Dict[str, ma_fields.Field], *, name: str = "GeneratedSchema"
-    ) -> typing.Type["Schema"]:
-        """Generate a `Schema` class given a dictionary of fields.
-
-        .. code-block:: python
-
-            from marshmallow import Schema, fields
-
-            PersonSchema = Schema.from_dict({"name": fields.Str()})
-            print(PersonSchema().load({"name": "David"}))  # => {'name': 'David'}
-
-        Generated schemas are not added to the class registry and therefore cannot
-        be referred to by name in `Nested` fields.
-
-        :param dict fields: Dictionary mapping field names to field instances.
-        :param str name: Optional name for the class, which will appear in
-            the ``repr`` for the class.
-
-        .. versionadded:: 3.0.0
-        """
-        attrs = fields.copy()
-        attrs["Meta"] = type(
-            "GeneratedMeta", (getattr(cls, "Meta", object),), {"register": False}
-        )
-        schema_cls = type(name, (cls,), attrs)
-        return schema_cls
-
-    ##### Override-able methods #####
-
-    def handle_error(self, error, data, *, many, **kwargs):
-        """Custom error handler function for the schema.
-
-        :param ValidationError error: The `ValidationError` raised during (de)serialization.
-        :param data: The original input data.
-        :param bool many: Value of ``many`` on dump or load.
-        :param bool partial: Value of ``partial`` on load.
-
-        .. versionadded:: 2.0.0
-
-        .. versionchanged:: 3.0.0rc9
-            Receives `many` and `partial` (on deserialization) as keyword arguments.
-        """
-        pass
-
-    def get_attribute(self, obj, attr, default):
-        """Defines how to pull values from an object to serialize.
-
-        .. versionadded:: 2.0.0
-
-        .. versionchanged:: 3.0.0a1
-            Changed position of ``obj`` and ``attr``.
-        """
-        return get_value(obj, attr, default)
-
-    ##### Serialization/Deserialization API #####
-
-    @staticmethod
-    def _call_and_store(getter_func, data, *, field_name, error_store, index=None):
-        """Call ``getter_func`` with ``data`` as its argument, and store any `ValidationErrors`.
-
-        :param callable getter_func: Function for getting the serialized/deserialized
-            value from ``data``.
-        :param data: The data passed to ``getter_func``.
-        :param str field_name: Field name.
-        :param int index: Index of the item being validated, if validating a collection,
-            otherwise `None`.
-        """
-        try:
-            value = getter_func(data)
-        except ValidationError as error:
-            error_store.store_error(error.messages, field_name, index=index)
-            # When a Nested field fails validation, the marshalled data is stored
-            # on the ValidationError's valid_data attribute
-            return error.valid_data or missing
-        return value
-
-    def _serialize(self, obj, *, many=False):
-        """Serialize ``obj``.
-
-        :param obj: The object(s) to serialize.
-        :param bool many: `True` if ``data`` should be serialized as a collection.
-        :return: A dictionary of the serialized data
-
-        .. versionchanged:: 1.0.0
-            Renamed from ``marshal``.
-        """
-        if many and obj is not None:
-            return [self._serialize(d, many=False) for d in obj]
-        ret = self.dict_class()
-        for attr_name, field_obj in self.dump_fields.items():
-            value = field_obj.serialize(attr_name, obj, accessor=self.get_attribute)
-            if value is missing:
-                continue
-            key = field_obj.data_key or attr_name
-            ret[key] = value
-        return ret
-
-    def dump(self, obj, *, many=None):
-        """Serialize an object to native Python data types according to this
-        Schema's fields.
-
-        :param obj: The object to serialize.
-        :param bool many: Whether to serialize `obj` as a collection. If `None`, the value
-            for `self.many` is used.
-        :return: A dict of serialized data
-        :rtype: dict
-
-        .. versionadded:: 1.0.0
-        .. versionchanged:: 3.0.0b7
-            This method returns the serialized data rather than a ``(data, errors)`` duple.
-            A :exc:`ValidationError <marshmallow.exceptions.ValidationError>` is raised
-            if ``obj`` is invalid.
-        .. versionchanged:: 3.0.0rc9
-            Validation no longer occurs upon serialization.
-        """
-        many = self.many if many is None else bool(many)
-        if many and is_iterable_but_not_string(obj):
-            obj = list(obj)
-
-        if self._has_processors(PRE_DUMP):
-            processed_obj = self._invoke_dump_processors(
-                PRE_DUMP, obj, many=many, original_data=obj
-            )
-        else:
-            processed_obj = obj
-
-        result = self._serialize(processed_obj, many=many)
-
-        if self._has_processors(POST_DUMP):
-            result = self._invoke_dump_processors(
-                POST_DUMP, result, many=many, original_data=obj
-            )
-
-        return result
-
-    def dumps(self, obj, *args, many=None, **kwargs):
-        """Same as :meth:`dump`, except return a JSON-encoded string.
-
-        :param obj: The object to serialize.
-        :param bool many: Whether to serialize `obj` as a collection. If `None`, the value
-            for `self.many` is used.
-        :return: A ``json`` string
-        :rtype: str
-
-        .. versionadded:: 1.0.0
-        .. versionchanged:: 3.0.0b7
-            This method returns the serialized data rather than a ``(data, errors)`` duple.
-            A :exc:`ValidationError <marshmallow.exceptions.ValidationError>` is raised
-            if ``obj`` is invalid.
-        """
-        serialized = self.dump(obj, many=many)
-        return self.opts.render_module.dumps(serialized, *args, **kwargs)
-
-    def _deserialize(
-        self, data, *, error_store, many=False, partial=False, unknown=RAISE, index=None
-    ):
-        """Deserialize ``data``.
-
-        :param dict data: The data to deserialize.
-        :param ErrorStore error_store: Structure to store errors.
-        :param bool many: `True` if ``data`` should be deserialized as a collection.
-        :param bool|tuple partial: Whether to ignore missing fields and not require
-            any fields declared. Propagates down to ``Nested`` fields as well. If
-            its value is an iterable, only missing fields listed in that iterable
-            will be ignored. Use dot delimiters to specify nested fields.
-        :param unknown: Whether to exclude, include, or raise an error for unknown
-            fields in the data. Use `EXCLUDE`, `INCLUDE` or `RAISE`.
-        :param int index: Index of the item being serialized (for storing errors) if
-            serializing a collection, otherwise `None`.
-        :return: A dictionary of the deserialized data.
-        """
-        index_errors = self.opts.index_errors
-        index = index if index_errors else None
-        if many:
-            if not is_collection(data):
-                error_store.store_error([self.error_messages["type"]], index=index)
-                ret = []
-            else:
-                ret = [
-                    self._deserialize(
-                        d,
-                        error_store=error_store,
-                        many=False,
-                        partial=partial,
-                        unknown=unknown,
-                        index=idx,
-                    )
-                    for idx, d in enumerate(data)
-                ]
-            return ret
-        ret = self.dict_class()
-        # Check data is a dict
-        if not isinstance(data, Mapping):
-            error_store.store_error([self.error_messages["type"]], index=index)
-        else:
-            partial_is_collection = is_collection(partial)
-            for attr_name, field_obj in self.load_fields.items():
-                field_name = field_obj.data_key or attr_name
-                raw_value = data.get(field_name, missing)
-                if raw_value is missing:
-                    # Ignore missing field if we're allowed to.
-                    if partial is True or (
-                        partial_is_collection and attr_name in partial
-                    ):
-                        continue
-                d_kwargs = {}
-                # Allow partial loading of nested schemas.
-                if partial_is_collection:
-                    prefix = field_name + "."
-                    len_prefix = len(prefix)
-                    sub_partial = [
-                        f[len_prefix:] for f in partial if f.startswith(prefix)
-                    ]
-                    d_kwargs["partial"] = sub_partial
-                else:
-                    d_kwargs["partial"] = partial
-                getter = lambda val: field_obj.deserialize(
-                    val, field_name, data, **d_kwargs
-                )
-                value = self._call_and_store(
-                    getter_func=getter,
-                    data=raw_value,
-                    field_name=field_name,
-                    error_store=error_store,
-                    index=index,
-                )
-                if value is not missing:
-                    key = field_obj.attribute or attr_name
-                    set_value(ret, key, value)
-            if unknown != EXCLUDE:
-                fields = {
-                    field_obj.data_key or field_name
-                    for field_name, field_obj in self.load_fields.items()
-                }
-                for key in set(data) - fields:
-                    value = data[key]
-                    if unknown == INCLUDE:
-                        set_value(ret, key, value)
-                    elif unknown == RAISE:
-                        error_store.store_error(
-                            [self.error_messages["unknown"]],
-                            key,
-                            (index if index_errors else None),
-                        )
-        return ret
-
-    def load(self, data, *, many=None, partial=None, unknown=None):
-        """Deserialize a data structure to an object defined by this Schema's fields.
-
-        :param dict data: The data to deserialize.
-        :param bool many: Whether to deserialize `data` as a collection. If `None`, the
-            value for `self.many` is used.
-        :param bool|tuple partial: Whether to ignore missing fields and not require
-            any fields declared. Propagates down to ``Nested`` fields as well. If
-            its value is an iterable, only missing fields listed in that iterable
-            will be ignored. Use dot delimiters to specify nested fields.
-        :param unknown: Whether to exclude, include, or raise an error for unknown
-            fields in the data. Use `EXCLUDE`, `INCLUDE` or `RAISE`.
-            If `None`, the value for `self.unknown` is used.
-        :return: A dict of deserialized data
-        :rtype: dict
-
-        .. versionadded:: 1.0.0
-        .. versionchanged:: 3.0.0b7
-            This method returns the deserialized data rather than a ``(data, errors)`` duple.
-            A :exc:`ValidationError <marshmallow.exceptions.ValidationError>` is raised
-            if invalid data are passed.
-        """
-        return self._do_load(
-            data, many=many, partial=partial, unknown=unknown, postprocess=True
-        )
-
-    def loads(self, json_data, *, many=None, partial=None, unknown=None, **kwargs):
-        """Same as :meth:`load`, except it takes a JSON string as input.
-
-        :param str json_data: A JSON string of the data to deserialize.
-        :param bool many: Whether to deserialize `obj` as a collection. If `None`, the
-            value for `self.many` is used.
-        :param bool|tuple partial: Whether to ignore missing fields and not require
-            any fields declared. Propagates down to ``Nested`` fields as well. If
-            its value is an iterable, only missing fields listed in that iterable
-            will be ignored. Use dot delimiters to specify nested fields.
-        :param unknown: Whether to exclude, include, or raise an error for unknown
-            fields in the data. Use `EXCLUDE`, `INCLUDE` or `RAISE`.
-            If `None`, the value for `self.unknown` is used.
-        :return: A dict of deserialized data
-        :rtype: dict
-
-        .. versionadded:: 1.0.0
-        .. versionchanged:: 3.0.0b7
-            This method returns the deserialized data rather than a ``(data, errors)`` duple.
-            A :exc:`ValidationError <marshmallow.exceptions.ValidationError>` is raised
-            if invalid data are passed.
-        """
-        data = self.opts.render_module.loads(json_data, **kwargs)
-        return self.load(data, many=many, partial=partial, unknown=unknown)
-
-    def _run_validator(
-        self,
-        validator_func,
-        output,
-        *,
-        original_data,
-        error_store,
-        many,
-        partial,
-        pass_original,
-        index=None
-    ):
-        try:
-            if pass_original:  # Pass original, raw data (before unmarshalling)
-                validator_func(output, original_data, partial=partial, many=many)
-            else:
-                validator_func(output, partial=partial, many=many)
-        except ValidationError as err:
-            error_store.store_error(err.messages, err.field_name, index=index)
-
-    def validate(self, data, *, many=None, partial=None):
-        """Validate `data` against the schema, returning a dictionary of
-        validation errors.
-
-        :param dict data: The data to validate.
-        :param bool many: Whether to validate `data` as a collection. If `None`, the
-            value for `self.many` is used.
-        :param bool|tuple partial: Whether to ignore missing fields and not require
-            any fields declared. Propagates down to ``Nested`` fields as well. If
-            its value is an iterable, only missing fields listed in that iterable
-            will be ignored. Use dot delimiters to specify nested fields.
-        :return: A dictionary of validation errors.
-        :rtype: dict
-
-        .. versionadded:: 1.1.0
-        """
-        try:
-            self._do_load(data, many=many, partial=partial, postprocess=False)
-        except ValidationError as exc:
-            return exc.messages
-        return {}
-
-    ##### Private Helpers #####
-
-    def _do_load(
-        self, data, *, many=None, partial=None, unknown=None, postprocess=True
-    ):
-        """Deserialize `data`, returning the deserialized result.
-
-        :param data: The data to deserialize.
-        :param bool many: Whether to deserialize `data` as a collection. If `None`, the
-            value for `self.many` is used.
-        :param bool|tuple partial: Whether to validate required fields. If its
-            value is an iterable, only fields listed in that iterable will be
-            ignored will be allowed missing. If `True`, all fields will be allowed missing.
-            If `None`, the value for `self.partial` is used.
-        :param unknown: Whether to exclude, include, or raise an error for unknown
-            fields in the data. Use `EXCLUDE`, `INCLUDE` or `RAISE`.
-            If `None`, the value for `self.unknown` is used.
-        :param bool postprocess: Whether to run post_load methods..
-        :return: A dict of deserialized data
-        :rtype: dict
-        """
-        error_store = ErrorStore()
-        errors = {}
-        many = self.many if many is None else bool(many)
-        unknown = unknown or self.unknown
-        if partial is None:
-            partial = self.partial
-        # Run preprocessors
-        if self._has_processors(PRE_LOAD):
-            try:
-                processed_data = self._invoke_load_processors(
-                    PRE_LOAD, data, many=many, original_data=data, partial=partial
-                )
-            except ValidationError as err:
-                errors = err.normalized_messages()
-                result = None
-        else:
-            processed_data = data
-        if not errors:
-            # Deserialize data
-            result = self._deserialize(
-                processed_data,
-                error_store=error_store,
-                many=many,
-                partial=partial,
-                unknown=unknown,
-            )
-            # Run field-level validation
-            self._invoke_field_validators(
-                error_store=error_store, data=result, many=many
-            )
-            # Run schema-level validation
-            if self._has_processors(VALIDATES_SCHEMA):
-                field_errors = bool(error_store.errors)
-                self._invoke_schema_validators(
-                    error_store=error_store,
-                    pass_many=True,
-                    data=result,
-                    original_data=data,
-                    many=many,
-                    partial=partial,
-                    field_errors=field_errors,
-                )
-                self._invoke_schema_validators(
-                    error_store=error_store,
-                    pass_many=False,
-                    data=result,
-                    original_data=data,
-                    many=many,
-                    partial=partial,
-                    field_errors=field_errors,
-                )
-            errors = error_store.errors
-            # Run post processors
-            if not errors and postprocess and self._has_processors(POST_LOAD):
-                try:
-                    result = self._invoke_load_processors(
-                        POST_LOAD,
-                        result,
-                        many=many,
-                        original_data=data,
-                        partial=partial,
-                    )
-                except ValidationError as err:
-                    errors = err.normalized_messages()
-        if errors:
-            exc = ValidationError(errors, data=data, valid_data=result)
-            self.handle_error(exc, data, many=many, partial=partial)
-            raise exc
-
-        return result
-
-    def _normalize_nested_options(self):
-        """Apply then flatten nested schema options"""
-        if self.only is not None:
-            # Apply the only option to nested fields.
-            self.__apply_nested_option("only", self.only, "intersection")
-            # Remove the child field names from the only option.
-            self.only = self.set_class([field.split(".", 1)[0] for field in self.only])
-        if self.exclude:
-            # Apply the exclude option to nested fields.
-            self.__apply_nested_option("exclude", self.exclude, "union")
-            # Remove the parent field names from the exclude option.
-            self.exclude = self.set_class(
-                [field for field in self.exclude if "." not in field]
-            )
-
-    def __apply_nested_option(self, option_name, field_names, set_operation):
-        """Apply nested options to nested fields"""
-        # Split nested field names on the first dot.
-        nested_fields = [name.split(".", 1) for name in field_names if "." in name]
-        # Partition the nested field names by parent field.
-        nested_options = defaultdict(list)
-        for parent, nested_names in nested_fields:
-            nested_options[parent].append(nested_names)
-        # Apply the nested field options.
-        for key, options in iter(nested_options.items()):
-            new_options = self.set_class(options)
-            original_options = getattr(self.declared_fields[key], option_name, ())
-            if original_options:
-                if set_operation == "union":
-                    new_options |= self.set_class(original_options)
-                if set_operation == "intersection":
-                    new_options &= self.set_class(original_options)
-            setattr(self.declared_fields[key], option_name, new_options)
-
-    def _init_fields(self):
-        """Update fields based on schema options."""
-        if self.opts.fields:
-            available_field_names = self.set_class(self.opts.fields)
-        else:
-            available_field_names = self.set_class(self.declared_fields.keys())
-            if self.opts.additional:
-                available_field_names |= self.set_class(self.opts.additional)
-
-        invalid_fields = self.set_class()
-
-        if self.only is not None:
-            # Return only fields specified in only option
-            field_names = self.set_class(self.only)
-
-            invalid_fields |= field_names - available_field_names
-        else:
-            field_names = available_field_names
-
-        # If "exclude" option or param is specified, remove those fields.
-        if self.exclude:
-            # Note that this isn't available_field_names, since we want to
-            # apply "only" for the actual calculation.
-            field_names = field_names - self.exclude
-            invalid_fields |= self.exclude - available_field_names
-
-        if invalid_fields:
-            message = "Invalid fields for {}: {}.".format(self, invalid_fields)
-            raise ValueError(message)
-
-        fields_dict = self.dict_class()
-        for field_name in field_names:
-            field_obj = self.declared_fields.get(field_name, ma_fields.Inferred())
-            self._bind_field(field_name, field_obj)
-            fields_dict[field_name] = field_obj
-
-        dump_data_keys = [
-            obj.data_key or name
-            for name, obj in fields_dict.items()
-            if not obj.load_only
-        ]
-        if len(dump_data_keys) != len(set(dump_data_keys)):
-            data_keys_duplicates = {
-                x for x in dump_data_keys if dump_data_keys.count(x) > 1
-            }
-            raise ValueError(
-                "The data_key argument for one or more fields collides "
-                "with another field's name or data_key argument. "
-                "Check the following field names and "
-                "data_key arguments: {}".format(list(data_keys_duplicates))
-            )
-
-        load_attributes = [
-            obj.attribute or name
-            for name, obj in fields_dict.items()
-            if not obj.dump_only
-        ]
-        if len(load_attributes) != len(set(load_attributes)):
-            attributes_duplicates = {
-                x for x in load_attributes if load_attributes.count(x) > 1
-            }
-            raise ValueError(
-                "The attribute argument for one or more fields collides "
-                "with another field's name or attribute argument. "
-                "Check the following field names and "
-                "attribute arguments: {}".format(list(attributes_duplicates))
-            )
-
-        return fields_dict
-
-    def on_bind_field(self, field_name, field_obj):
-        """Hook to modify a field when it is bound to the `Schema`.
-
-        No-op by default.
-        """
-        return None
-
-    def _bind_field(self, field_name, field_obj):
-        """Bind field to the schema, setting any necessary attributes on the
-        field (e.g. parent and name).
-
-        Also set field load_only and dump_only values if field_name was
-        specified in ``class Meta``.
-        """
-        try:
-            if field_name in self.load_only:
-                field_obj.load_only = True
-            if field_name in self.dump_only:
-                field_obj.dump_only = True
-            field_obj._bind_to_schema(field_name, self)
-            self.on_bind_field(field_name, field_obj)
-        except TypeError as error:
-            # field declared as a class, not an instance
-            if isinstance(field_obj, type) and issubclass(field_obj, base.FieldABC):
-                msg = (
-                    'Field for "{}" must be declared as a '
-                    "Field instance, not a class. "
-                    'Did you mean "fields.{}()"?'.format(field_name, field_obj.__name__)
-                )
-                raise TypeError(msg) from error
-
-    @lru_cache(maxsize=8)
-    def _has_processors(self, tag):
-        return self._hooks[(tag, True)] or self._hooks[(tag, False)]
-
-    def _invoke_dump_processors(self, tag, data, *, many, original_data=None):
-        # The pass_many post-dump processors may do things like add an envelope, so
-        # invoke those after invoking the non-pass_many processors which will expect
-        # to get a list of items.
-        data = self._invoke_processors(
-            tag, pass_many=False, data=data, many=many, original_data=original_data
-        )
-        data = self._invoke_processors(
-            tag, pass_many=True, data=data, many=many, original_data=original_data
-        )
-        return data
-
-    def _invoke_load_processors(self, tag, data, *, many, original_data, partial):
-        # This has to invert the order of the dump processors, so run the pass_many
-        # processors first.
-        data = self._invoke_processors(
-            tag,
-            pass_many=True,
-            data=data,
-            many=many,
-            original_data=original_data,
-            partial=partial,
-        )
-        data = self._invoke_processors(
-            tag,
-            pass_many=False,
-            data=data,
-            many=many,
-            original_data=original_data,
-            partial=partial,
-        )
-        return data
-
-    def _invoke_field_validators(self, *, error_store, data, many):
-        for attr_name in self._hooks[VALIDATES]:
-            validator = getattr(self, attr_name)
-            validator_kwargs = validator.__marshmallow_hook__[VALIDATES]
-            field_name = validator_kwargs["field_name"]
-
-            try:
-                field_obj = self.fields[field_name]
-            except KeyError as error:
-                if field_name in self.declared_fields:
-                    continue
-                raise ValueError(
-                    '"{}" field does not exist.'.format(field_name)
-                ) from error
-
-            if many:
-                for idx, item in enumerate(data):
-                    try:
-                        value = item[field_obj.attribute or field_name]
-                    except KeyError:
-                        pass
-                    else:
-                        validated_value = self._call_and_store(
-                            getter_func=validator,
-                            data=value,
-                            field_name=field_obj.data_key or field_name,
-                            error_store=error_store,
-                            index=(idx if self.opts.index_errors else None),
-                        )
-                        if validated_value is missing:
-                            data[idx].pop(field_name, None)
-            else:
-                try:
-                    value = data[field_obj.attribute or field_name]
-                except KeyError:
-                    pass
-                else:
-                    validated_value = self._call_and_store(
-                        getter_func=validator,
-                        data=value,
-                        field_name=field_obj.data_key or field_name,
-                        error_store=error_store,
-                    )
-                    if validated_value is missing:
-                        data.pop(field_name, None)
-
-    def _invoke_schema_validators(
-        self,
-        *,
-        error_store,
-        pass_many,
-        data,
-        original_data,
-        many,
-        partial,
-        field_errors=False
-    ):
-        for attr_name in self._hooks[(VALIDATES_SCHEMA, pass_many)]:
-            validator = getattr(self, attr_name)
-            validator_kwargs = validator.__marshmallow_hook__[
-                (VALIDATES_SCHEMA, pass_many)
-            ]
-            if field_errors and validator_kwargs["skip_on_field_errors"]:
-                continue
-            pass_original = validator_kwargs.get("pass_original", False)
-
-            if many and not pass_many:
-                for idx, (item, orig) in enumerate(zip(data, original_data)):
-                    self._run_validator(
-                        validator,
-                        item,
-                        original_data=orig,
-                        error_store=error_store,
-                        many=many,
-                        partial=partial,
-                        index=idx,
-                        pass_original=pass_original,
-                    )
-            else:
-                self._run_validator(
-                    validator,
-                    data,
-                    original_data=original_data,
-                    error_store=error_store,
-                    many=many,
-                    pass_original=pass_original,
-                    partial=partial,
-                )
-
-    def _invoke_processors(
-        self, tag, *, pass_many, data, many, original_data=None, **kwargs
-    ):
-        key = (tag, pass_many)
-        for attr_name in self._hooks[key]:
-            # This will be a bound method.
-            processor = getattr(self, attr_name)
-
-            processor_kwargs = processor.__marshmallow_hook__[key]
-            pass_original = processor_kwargs.get("pass_original", False)
-
-            if pass_many:
-                if pass_original:
-                    data = processor(data, original_data, many=many, **kwargs)
-                else:
-                    data = processor(data, many=many, **kwargs)
-            elif many:
-                if pass_original:
-                    data = [
-                        processor(item, original, many=many, **kwargs)
-                        for item, original in zip(data, original_data)
-                    ]
-                else:
-                    data = [processor(item, many=many, **kwargs) for item in data]
-            else:
-                if pass_original:
-                    data = processor(data, original_data, many=many, **kwargs)
-                else:
-                    data = processor(data, many=many, **kwargs)
-        return data
-
-
-class Schema(BaseSchema, metaclass=SchemaMeta):
-    __doc__ = BaseSchema.__doc__
+            class registry. Must be `True` if you intend to refer
\ No newline at end of file
+ source /opt/miniconda3/bin/activate
++ _CONDA_ROOT=/opt/miniconda3
++ . /opt/miniconda3/etc/profile.d/conda.sh
+++ export CONDA_EXE=/opt/miniconda3/bin/conda
+++ CONDA_EXE=/opt/miniconda3/bin/conda
+++ export _CE_M=
+++ _CE_M=
+++ export _CE_CONDA=
+++ _CE_CONDA=
+++ export CONDA_PYTHON_EXE=/opt/miniconda3/bin/python
+++ CONDA_PYTHON_EXE=/opt/miniconda3/bin/python
+++ '[' -z x ']'
++ conda activate
++ local cmd=activate
++ case "$cmd" in
++ __conda_activate activate
++ '[' -n '' ']'
++ local ask_conda
+++ PS1='(testbed) '
+++ __conda_exe shell.posix activate
+++ /opt/miniconda3/bin/conda shell.posix activate
++ ask_conda='PS1='\''(base) '\''
export PATH='\''/opt/miniconda3/bin:/opt/miniconda3/condabin:/opt/miniconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin'\''
export CONDA_PREFIX='\''/opt/miniconda3'\''
export CONDA_SHLVL='\''4'\''
export CONDA_DEFAULT_ENV='\''base'\''
export CONDA_PROMPT_MODIFIER='\''(base) '\''
export CONDA_PREFIX_3='\''/opt/miniconda3/envs/testbed'\''
export CONDA_EXE='\''/opt/miniconda3/bin/conda'\''
export _CE_M='\'''\''
export _CE_CONDA='\'''\''
export CONDA_PYTHON_EXE='\''/opt/miniconda3/bin/python'\'''
++ eval 'PS1='\''(base) '\''
export PATH='\''/opt/miniconda3/bin:/opt/miniconda3/condabin:/opt/miniconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin'\''
export CONDA_PREFIX='\''/opt/miniconda3'\''
export CONDA_SHLVL='\''4'\''
export CONDA_DEFAULT_ENV='\''base'\''
export CONDA_PROMPT_MODIFIER='\''(base) '\''
export CONDA_PREFIX_3='\''/opt/miniconda3/envs/testbed'\''
export CONDA_EXE='\''/opt/miniconda3/bin/conda'\''
export _CE_M='\'''\''
export _CE_CONDA='\'''\''
export CONDA_PYTHON_EXE='\''/opt/miniconda3/bin/python'\'''
+++ PS1='(base) '
+++ export PATH=/opt/miniconda3/bin:/opt/miniconda3/condabin:/opt/miniconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
+++ PATH=/opt/miniconda3/bin:/opt/miniconda3/condabin:/opt/miniconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
+++ export CONDA_PREFIX=/opt/miniconda3
+++ CONDA_PREFIX=/opt/miniconda3
+++ export CONDA_SHLVL=4
+++ CONDA_SHLVL=4
+++ export CONDA_DEFAULT_ENV=base
+++ CONDA_DEFAULT_ENV=base
+++ export 'CONDA_PROMPT_MODIFIER=(base) '
+++ CONDA_PROMPT_MODIFIER='(base) '
+++ export CONDA_PREFIX_3=/opt/miniconda3/envs/testbed
+++ CONDA_PREFIX_3=/opt/miniconda3/envs/testbed
+++ export CONDA_EXE=/opt/miniconda3/bin/conda
+++ CONDA_EXE=/opt/miniconda3/bin/conda
+++ export _CE_M=
+++ _CE_M=
+++ export _CE_CONDA=
+++ _CE_CONDA=
+++ export CONDA_PYTHON_EXE=/opt/miniconda3/bin/python
+++ CONDA_PYTHON_EXE=/opt/miniconda3/bin/python
++ __conda_hashr
++ '[' -n '' ']'
++ '[' -n '' ']'
++ hash -r
+ conda activate testbed
+ local cmd=activate
+ case "$cmd" in
+ __conda_activate activate testbed
+ '[' -n '' ']'
+ local ask_conda
++ PS1='(base) '
++ __conda_exe shell.posix activate testbed
++ /opt/miniconda3/bin/conda shell.posix activate testbed
+ ask_conda='PS1='\''(testbed) '\''
export PATH='\''/opt/miniconda3/envs/testbed/bin:/opt/miniconda3/condabin:/opt/miniconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin'\''
export CONDA_PREFIX='\''/opt/miniconda3/envs/testbed'\''
export CONDA_SHLVL='\''5'\''
export CONDA_DEFAULT_ENV='\''testbed'\''
export CONDA_PROMPT_MODIFIER='\''(testbed) '\''
export CONDA_PREFIX_4='\''/opt/miniconda3'\''
export CONDA_EXE='\''/opt/miniconda3/bin/conda'\''
export _CE_M='\'''\''
export _CE_CONDA='\'''\''
export CONDA_PYTHON_EXE='\''/opt/miniconda3/bin/python'\'''
+ eval 'PS1='\''(testbed) '\''
export PATH='\''/opt/miniconda3/envs/testbed/bin:/opt/miniconda3/condabin:/opt/miniconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin'\''
export CONDA_PREFIX='\''/opt/miniconda3/envs/testbed'\''
export CONDA_SHLVL='\''5'\''
export CONDA_DEFAULT_ENV='\''testbed'\''
export CONDA_PROMPT_MODIFIER='\''(testbed) '\''
export CONDA_PREFIX_4='\''/opt/miniconda3'\''
export CONDA_EXE='\''/opt/miniconda3/bin/conda'\''
export _CE_M='\'''\''
export _CE_CONDA='\'''\''
export CONDA_PYTHON_EXE='\''/opt/miniconda3/bin/python'\'''
++ PS1='(testbed) '
++ export PATH=/opt/miniconda3/envs/testbed/bin:/opt/miniconda3/condabin:/opt/miniconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
++ PATH=/opt/miniconda3/envs/testbed/bin:/opt/miniconda3/condabin:/opt/miniconda3/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin
++ export CONDA_PREFIX=/opt/miniconda3/envs/testbed
++ CONDA_PREFIX=/opt/miniconda3/envs/testbed
++ export CONDA_SHLVL=5
++ CONDA_SHLVL=5
++ export CONDA_DEFAULT_ENV=testbed
++ CONDA_DEFAULT_ENV=testbed
++ export 'CONDA_PROMPT_MODIFIER=(testbed) '
++ CONDA_PROMPT_MODIFIER='(testbed) '
++ export CONDA_PREFIX_4=/opt/miniconda3
++ CONDA_PREFIX_4=/opt/miniconda3
++ export CONDA_EXE=/opt/miniconda3/bin/conda
++ CONDA_EXE=/opt/miniconda3/bin/conda
++ export _CE_M=
++ _CE_M=
++ export _CE_CONDA=
++ _CE_CONDA=
++ export CONDA_PYTHON_EXE=/opt/miniconda3/bin/python
++ CONDA_PYTHON_EXE=/opt/miniconda3/bin/python
+ __conda_hashr
+ '[' -n '' ']'
+ '[' -n '' ']'
+ hash -r
+ python -m pip install -e '.[dev]'
Obtaining file:///testbed
  Installing build dependencies: started
  Installing build dependencies: finished with status 'done'
  Checking if build backend supports build_editable: started
  Checking if build backend supports build_editable: finished with status 'done'
  Getting requirements to build editable: started
  Getting requirements to build editable: finished with status 'done'
  Preparing editable metadata (pyproject.toml): started
  Preparing editable metadata (pyproject.toml): finished with status 'done'
Requirement already satisfied: pytest in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from marshmallow==3.0.0) (8.3.5)
Requirement already satisfied: pytz in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from marshmallow==3.0.0) (2025.2)
Requirement already satisfied: simplejson in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from marshmallow==3.0.0) (3.20.1)
Requirement already satisfied: flake8==3.7.8 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from marshmallow==3.0.0) (3.7.8)
Requirement already satisfied: flake8-bugbear==19.8.0 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from marshmallow==3.0.0) (19.8.0)
Requirement already satisfied: pre-commit~=1.17 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from marshmallow==3.0.0) (1.21.0)
Requirement already satisfied: tox in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from marshmallow==3.0.0) (4.25.0)
Requirement already satisfied: entrypoints<0.4.0,>=0.3.0 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from flake8==3.7.8->marshmallow==3.0.0) (0.3)
Requirement already satisfied: pyflakes<2.2.0,>=2.1.0 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from flake8==3.7.8->marshmallow==3.0.0) (2.1.1)
Requirement already satisfied: pycodestyle<2.6.0,>=2.5.0 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from flake8==3.7.8->marshmallow==3.0.0) (2.5.0)
Requirement already satisfied: mccabe<0.7.0,>=0.6.0 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from flake8==3.7.8->marshmallow==3.0.0) (0.6.1)
Requirement already satisfied: attrs in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from flake8-bugbear==19.8.0->marshmallow==3.0.0) (25.3.0)
Requirement already satisfied: aspy.yaml in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from pre-commit~=1.17->marshmallow==3.0.0) (1.3.0)
Requirement already satisfied: cfgv>=2.0.0 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from pre-commit~=1.17->marshmallow==3.0.0) (3.4.0)
Requirement already satisfied: identify>=1.0.0 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from pre-commit~=1.17->marshmallow==3.0.0) (2.6.10)
Requirement already satisfied: nodeenv>=0.11.1 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from pre-commit~=1.17->marshmallow==3.0.0) (1.9.1)
Requirement already satisfied: pyyaml in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from pre-commit~=1.17->marshmallow==3.0.0) (6.0.2)
Requirement already satisfied: six in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from pre-commit~=1.17->marshmallow==3.0.0) (1.17.0)
Requirement already satisfied: toml in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from pre-commit~=1.17->marshmallow==3.0.0) (0.10.2)
Requirement already satisfied: virtualenv>=15.2 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from pre-commit~=1.17->marshmallow==3.0.0) (20.31.1)
Requirement already satisfied: distlib<1,>=0.3.7 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from virtualenv>=15.2->pre-commit~=1.17->marshmallow==3.0.0) (0.3.9)
Requirement already satisfied: filelock<4,>=3.12.2 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from virtualenv>=15.2->pre-commit~=1.17->marshmallow==3.0.0) (3.18.0)
Requirement already satisfied: platformdirs<5,>=3.9.1 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from virtualenv>=15.2->pre-commit~=1.17->marshmallow==3.0.0) (4.3.7)
Requirement already satisfied: exceptiongroup>=1.0.0rc8 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from pytest->marshmallow==3.0.0) (1.2.2)
Requirement already satisfied: iniconfig in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from pytest->marshmallow==3.0.0) (2.1.0)
Requirement already satisfied: packaging in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from pytest->marshmallow==3.0.0) (25.0)
Requirement already satisfied: pluggy<2,>=1.5 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from pytest->marshmallow==3.0.0) (1.5.0)
Requirement already satisfied: tomli>=1 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from pytest->marshmallow==3.0.0) (2.2.1)
Requirement already satisfied: cachetools>=5.5.1 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from tox->marshmallow==3.0.0) (5.5.2)
Requirement already satisfied: chardet>=5.2 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from tox->marshmallow==3.0.0) (5.2.0)
Requirement already satisfied: colorama>=0.4.6 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from tox->marshmallow==3.0.0) (0.4.6)
Requirement already satisfied: pyproject-api>=1.8 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from tox->marshmallow==3.0.0) (1.9.0)
Requirement already satisfied: typing-extensions>=4.12.2 in /opt/miniconda3/envs/testbed/lib/python3.9/site-packages (from tox->marshmallow==3.0.0) (4.15.0)
Building wheels for collected packages: marshmallow
  Building editable for marshmallow (pyproject.toml): started
  Building editable for marshmallow (pyproject.toml): finished with status 'done'
  Created wheel for marshmallow: filename=marshmallow-3.0.0-0.editable-py2.py3-none-any.whl size=4552 sha256=6f232cee560568a004706f4084f2775240351448673f6178fa3495f45d7a17e1
  Stored in directory: /tmp/pip-ephem-wheel-cache-itfxhjjx/wheels/7d/66/67/70d1ee2124ccf21d601c352e25cdca10f611f7c8b3f9ffb9e4
Successfully built marshmallow
Installing collected packages: marshmallow
  Attempting uninstall: marshmallow
    Found existing installation: marshmallow 3.0.0
    Uninstalling marshmallow-3.0.0:
      Successfully uninstalled marshmallow-3.0.0
Successfully installed marshmallow-3.0.0
WARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager, possibly rendering your system unusable. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv. Use the --root-user-action option if you know what you are doing and want to suppress this warning.
+ git checkout b40a0f4e33823e6d0f341f7e8684e359a99060d1 tests/test_fields.py
Updated 0 paths from 56ab4168
+ git apply -v -
Checking patch tests/test_fields.py...
Applied patch tests/test_fields.py cleanly.
+ : '>>>>> Start Test Output'
+ pytest -rA tests/test_fields.py
ImportError while loading conftest '/testbed/tests/conftest.py'.
tests/conftest.py:4: in <module>
    from tests.base import User, UserSchema, Blog
tests/base.py:9: in <module>
    from marshmallow import Schema, fields, post_load, validate, missing
src/marshmallow/__init__.py:1: in <module>
    from marshmallow.schema import Schema, SchemaOpts
E     File "/testbed/src/marshmallow/schema.py", line 346
E       class registry. Must be `True` if you intend to refer
E                                                            ^
E   SyntaxError: EOF while scanning triple-quoted string literal
+ : '>>>>> End Test Output'
+ git checkout b40a0f4e33823e6d0f341f7e8684e359a99060d1 tests/test_fields.py
Updated 1 path from 56ab4168

Reference output

diff --git a/src/marshmallow/fields.py b/src/marshmallow/fields.py
--- a/src/marshmallow/fields.py
+++ b/src/marshmallow/fields.py
@@ -1114,7 +1114,7 @@ def _bind_to_schema(self, field_name, schema):
         super()._bind_to_schema(field_name, schema)
         self.format = (
             self.format
-            or getattr(schema.opts, self.SCHEMA_OPTS_VAR_NAME)
+            or getattr(self.root.opts, self.SCHEMA_OPTS_VAR_NAME)
             or self.DEFAULT_FORMAT
         )