Merge remote-tracking branch 'refs/remotes/upstream/main' into validate-base64

Author: josh-newman

.github/workflows/ci.yml

@@ -467,7 +467,9 @@ jobs:
           python-version: '3.11'
           architecture: ${{ matrix.python-architecture || 'x64' }}
 
-      - run: pip install -U twine 'ruff==0.1.3' typing_extensions
+      - run: pip install -U twine 'ruff==0.1.3'
+      # TODO: remove manual override for typing_extensions once a version newer than 4.12.1 is released
+      - run: pip install -U git+https://github.com/python/typing_extensions@main
 
       # generate self-schema now, so we don't have to do so inside docker in maturin build
       - run: python generate_self_schema.py
@@ -530,7 +532,9 @@ jobs:
         with:
           components: llvm-tools
 
-      - run: pip install -U 'ruff==0.1.3' typing_extensions
+      - run: pip install -U 'ruff==0.1.3'
+      # TODO: remove manual override for typing_extensions once a version newer than 4.12.1 is released
+      - run: pip install -U git+https://github.com/python/typing_extensions@main
 
       # generate self-schema now, so we don't have to do so inside docker in maturin build
       - run: python generate_self_schema.py
@@ -659,10 +663,8 @@ jobs:
             fi
           run: |
             set -x
-            # typing-extensions isn't automatically installed because of `--no-index --no-deps`
             python3 -m venv venv
             source venv/bin/activate
-            python3 -m pip install -U pip typing-extensions
             python3 -m pip install -r tests/requirements.txt
             python3 -m pip install pydantic-core --no-index --no-deps --find-links dist --force-reinstall
             python3 -m pytest --ignore=tests/test_docstrings.py
@@ -693,7 +695,6 @@ jobs:
           merge-multiple: true
           path: dist
 
-      - run: pip install typing-extensions
       - run: pip install -r tests/requirements.txt
       - run: pip install pydantic-core --no-index --no-deps --find-links dist --force-reinstall
       - run: pytest --ignore=tests/test_docstrings.py

Cargo.lock

@@ -1,6 +1,6 @@
 [package]
 name = "pydantic-core"
-version = "2.18.3"
+version = "2.19.0"
 edition = "2021"
 license = "MIT"
 homepage = "https://github.com/pydantic/pydantic-core"
@@ -24,7 +24,7 @@ include = [
     "!tests/.pytest_cache",
     "!*.so",
 ]
-rust-version = "1.76"
+rust-version = "1.75"
 
 [dependencies]
 pyo3 = { version = "0.21.2", features = ["generate-import-lib", "num-bigint"] }
@@ -33,7 +33,7 @@ strum = { version = "0.25.0", features = ["derive"] }
 strum_macros = "0.26.1"
 serde_json = {version = "1.0.116", features = ["arbitrary_precision", "preserve_order"]}
 enum_dispatch = "0.3.13"
-serde = { version = "1.0.197", features = ["derive"] }
+serde = { version = "1.0.203", features = ["derive"] }
 speedate = "0.14.0"
 smallvec = "1.13.2"
 ahash = "0.8.10"
@@ -43,8 +43,8 @@ idna = "0.5.0"
 base64 = "0.21.7"
 num-bigint = "0.4.4"
 python3-dll-a = "0.2.7"
-uuid = "1.7.0"
-jiter = { version = "0.2.1", features = ["python"] }
+uuid = "1.8.0"
+jiter = { version = "0.4.1", features = ["python"] }
 
 [lib]
 name = "_pydantic_core"

Cargo.toml

@@ -10,10 +10,11 @@
 import decimal
 import importlib.util
 import re
+import sys
 from collections.abc import Callable
 from datetime import date, datetime, time, timedelta
 from pathlib import Path
-from typing import TYPE_CHECKING, Any, Dict, ForwardRef, List, Set, Type, Union
+from typing import TYPE_CHECKING, Any, Dict, ForwardRef, List, Pattern, Set, Type, Union
 
 from typing_extensions import TypedDict, get_args, get_origin, is_typeddict
 
@@ -46,7 +47,7 @@
 schema_ref_validator = {'type': 'definition-ref', 'schema_ref': 'root-schema'}
 
 
-def get_schema(obj: Any, definitions: dict[str, core_schema.CoreSchema]) -> core_schema.CoreSchema:
+def get_schema(obj: Any, definitions: dict[str, core_schema.CoreSchema]) -> core_schema.CoreSchema:  # noqa: C901
     if isinstance(obj, str):
         return {'type': obj}
     elif obj in (datetime, timedelta, date, time, bool, int, float, str, decimal.Decimal):
@@ -81,6 +82,9 @@ def get_schema(obj: Any, definitions: dict[str, core_schema.CoreSchema]) -> core
     elif issubclass(origin, Type):
         # can't really use 'is-instance' since this is used for the class_ parameter of 'is-instance' validators
         return {'type': 'any'}
+    elif origin in (Pattern, re.Pattern):
+        # can't really use 'is-instance' easily with Pattern, so we use `any` as a placeholder for now
+        return {'type': 'any'}
     else:
         # debug(obj)
         raise TypeError(f'Unknown type: {obj!r}')
@@ -189,16 +193,12 @@ def all_literal_values(type_: type[core_schema.Literal]) -> list[any]:
 
 
 def eval_forward_ref(type_: Any) -> Any:
-    try:
-        try:
-            # Python 3.12+
-            return type_._evaluate(core_schema.__dict__, None, type_params=set(), recursive_guard=set())
-        except TypeError:
-            # Python 3.9+
-            return type_._evaluate(core_schema.__dict__, None, set())
-    except TypeError:
-        # for Python 3.8
+    if sys.version_info < (3, 9):
         return type_._evaluate(core_schema.__dict__, None)
+    elif sys.version_info < (3, 12, 4):
+        return type_._evaluate(core_schema.__dict__, None, recursive_guard=set())
+    else:
+        return type_._evaluate(core_schema.__dict__, None, type_params=set(), recursive_guard=set())
 
 
 def main() -> None:

generate_self_schema.py

@@ -89,7 +89,7 @@ class SchemaValidator:
         *,
         strict: bool | None = None,
         from_attributes: bool | None = None,
-        context: dict[str, Any] | None = None,
+        context: Any | None = None,
         self_instance: Any | None = None,
     ) -> Any:
         """
@@ -119,7 +119,7 @@ class SchemaValidator:
         *,
         strict: bool | None = None,
         from_attributes: bool | None = None,
-        context: dict[str, Any] | None = None,
+        context: Any | None = None,
         self_instance: Any | None = None,
     ) -> bool:
         """
@@ -136,7 +136,7 @@ class SchemaValidator:
         input: str | bytes | bytearray,
         *,
         strict: bool | None = None,
-        context: dict[str, Any] | None = None,
+        context: Any | None = None,
         self_instance: Any | None = None,
     ) -> Any:
         """
@@ -163,9 +163,7 @@ class SchemaValidator:
         Returns:
             The validated Python object.
         """
-    def validate_strings(
-        self, input: _StringInput, *, strict: bool | None = None, context: dict[str, Any] | None = None
-    ) -> Any:
+    def validate_strings(self, input: _StringInput, *, strict: bool | None = None, context: Any | None = None) -> Any:
         """
         Validate a string against the schema and return the validated Python object.
 
@@ -194,7 +192,7 @@ class SchemaValidator:
         *,
         strict: bool | None = None,
         from_attributes: bool | None = None,
-        context: dict[str, Any] | None = None,
+        context: Any | None = None,
     ) -> dict[str, Any] | tuple[dict[str, Any], dict[str, Any] | None, set[str]]:
         """
         Validate an assignment to a field on a model.
@@ -267,7 +265,7 @@ class SchemaSerializer:
         warnings: bool | Literal['none', 'warn', 'error'] = True,
         fallback: Callable[[Any], Any] | None = None,
         serialize_as_any: bool = False,
-        context: dict[str, Any] | None = None,
+        context: Any | None = None,
     ) -> Any:
         """
         Serialize/marshal a Python object to a Python object including transforming and filtering data.
@@ -313,7 +311,7 @@ class SchemaSerializer:
         warnings: bool | Literal['none', 'warn', 'error'] = True,
         fallback: Callable[[Any], Any] | None = None,
         serialize_as_any: bool = False,
-        context: dict[str, Any] | None = None,
+        context: Any | None = None,
     ) -> bytes:
         """
         Serialize a Python object to JSON including transforming and filtering data.
@@ -355,11 +353,11 @@ def to_json(
     round_trip: bool = False,
     timedelta_mode: Literal['iso8601', 'float'] = 'iso8601',
     bytes_mode: Literal['utf8', 'base64'] = 'utf8',
-    inf_nan_mode: Literal['null', 'constants'] = 'constants',
+    inf_nan_mode: Literal['null', 'constants', 'strings'] = 'constants',
     serialize_unknown: bool = False,
     fallback: Callable[[Any], Any] | None = None,
     serialize_as_any: bool = False,
-    context: dict[str, Any] | None = None,
+    context: Any | None = None,
 ) -> bytes:
     """
     Serialize a Python object to JSON including transforming and filtering data.
@@ -376,7 +374,7 @@ def to_json(
         round_trip: Whether to enable serialization and validation round-trip support.
         timedelta_mode: How to serialize `timedelta` objects, either `'iso8601'` or `'float'`.
         bytes_mode: How to serialize `bytes` objects, either `'utf8'` or `'base64'`.
-        inf_nan_mode: How to serialize `Infinity`, `-Infinity` and `NaN` values, either `'null'` or `'constants'`.
+        inf_nan_mode: How to serialize `Infinity`, `-Infinity` and `NaN` values, either `'null'`, `'constants'`, or `'strings'`.
         serialize_unknown: Attempt to serialize unknown types, `str(value)` will be used, if that fails
             `"<Unserializable {value_type} object>"` will be used.
         fallback: A function to call when an unknown value is encountered,
@@ -430,11 +428,11 @@ def to_jsonable_python(
     round_trip: bool = False,
     timedelta_mode: Literal['iso8601', 'float'] = 'iso8601',
     bytes_mode: Literal['utf8', 'base64'] = 'utf8',
-    inf_nan_mode: Literal['null', 'constants'] = 'constants',
+    inf_nan_mode: Literal['null', 'constants', 'strings'] = 'constants',
     serialize_unknown: bool = False,
     fallback: Callable[[Any], Any] | None = None,
     serialize_as_any: bool = False,
-    context: dict[str, Any] | None = None,
+    context: Any | None = None,
 ) -> Any:
     """
     Serialize/marshal a Python object to a JSON-serializable Python object including transforming and filtering data.
@@ -451,7 +449,7 @@ def to_jsonable_python(
         round_trip: Whether to enable serialization and validation round-trip support.
         timedelta_mode: How to serialize `timedelta` objects, either `'iso8601'` or `'float'`.
         bytes_mode: How to serialize `bytes` objects, either `'utf8'` or `'base64'`.
-        inf_nan_mode: How to serialize `Infinity`, `-Infinity` and `NaN` values, either `'null'` or `'constants'`.
+        inf_nan_mode: How to serialize `Infinity`, `-Infinity` and `NaN` values, either `'null'`, `'constants'`, or `'strings'`.
         serialize_unknown: Attempt to serialize unknown types, `str(value)` will be used, if that fails
             `"<Unserializable {value_type} object>"` will be used.
         fallback: A function to call when an unknown value is encountered,