cocoindex 0.2.3__cp311-abi3-macosx_10_12_x86_64.whl

cocoindex/tests/test_typing.py

@@ -0,0 +1,429 @@
+import dataclasses
+import datetime
+import uuid
+from collections.abc import Mapping, Sequence
+from typing import Annotated, Any, Literal, NamedTuple, get_args, get_origin
+
+import numpy as np
+import pytest
+from numpy.typing import NDArray
+
+from cocoindex.typing import (
+    AnalyzedBasicType,
+    AnalyzedDictType,
+    AnalyzedListType,
+    AnalyzedStructType,
+    AnalyzedUnknownType,
+    AnalyzedTypeInfo,
+    TypeAttr,
+    TypeKind,
+    Vector,
+    VectorInfo,
+    analyze_type_info,
+    encode_enriched_type,
+)
+
+
+@dataclasses.dataclass
+class SimpleDataclass:
+    name: str
+    value: int
+
+
+class SimpleNamedTuple(NamedTuple):
+    name: str
+    value: Any
+
+
+def test_ndarray_float32_no_dim() -> None:
+    typ = NDArray[np.float32]
+    result = analyze_type_info(typ)
+    assert isinstance(result.variant, AnalyzedListType)
+    assert result.variant.vector_info is None
+    assert result.variant.elem_type == np.float32
+    assert result.nullable is False
+    assert get_origin(result.core_type) == np.ndarray
+    assert get_args(result.core_type)[1] == np.dtype[np.float32]
+
+
+def test_vector_float32_no_dim() -> None:
+    typ = Vector[np.float32]
+    result = analyze_type_info(typ)
+    assert isinstance(result.variant, AnalyzedListType)
+    assert result.variant.vector_info == VectorInfo(dim=None)
+    assert result.variant.elem_type == np.float32
+    assert result.nullable is False
+    assert get_origin(result.core_type) == np.ndarray
+    assert get_args(result.core_type)[1] == np.dtype[np.float32]
+
+
+def test_ndarray_float64_with_dim() -> None:
+    typ = Annotated[NDArray[np.float64], VectorInfo(dim=128)]
+    result = analyze_type_info(typ)
+    assert isinstance(result.variant, AnalyzedListType)
+    assert result.variant.vector_info == VectorInfo(dim=128)
+    assert result.variant.elem_type == np.float64
+    assert result.nullable is False
+    assert get_origin(result.core_type) == np.ndarray
+    assert get_args(result.core_type)[1] == np.dtype[np.float64]
+
+
+def test_vector_float32_with_dim() -> None:
+    typ = Vector[np.float32, Literal[384]]
+    result = analyze_type_info(typ)
+    assert isinstance(result.variant, AnalyzedListType)
+    assert result.variant.vector_info == VectorInfo(dim=384)
+    assert result.variant.elem_type == np.float32
+    assert result.nullable is False
+    assert get_origin(result.core_type) == np.ndarray
+    assert get_args(result.core_type)[1] == np.dtype[np.float32]
+
+
+def test_ndarray_int64_no_dim() -> None:
+    typ = NDArray[np.int64]
+    result = analyze_type_info(typ)
+    assert isinstance(result.variant, AnalyzedListType)
+    assert result.variant.vector_info is None
+    assert result.variant.elem_type == np.int64
+    assert result.nullable is False
+    assert get_origin(result.core_type) == np.ndarray
+    assert get_args(result.core_type)[1] == np.dtype[np.int64]
+
+
+def test_nullable_ndarray() -> None:
+    typ = NDArray[np.float32] | None
+    result = analyze_type_info(typ)
+    assert isinstance(result.variant, AnalyzedListType)
+    assert result.variant.vector_info is None
+    assert result.variant.elem_type == np.float32
+    assert result.nullable is True
+    assert get_origin(result.core_type) == np.ndarray
+    assert get_args(result.core_type)[1] == np.dtype[np.float32]
+
+
+def test_scalar_numpy_types() -> None:
+    for np_type, expected_kind in [
+        (np.int64, "Int64"),
+        (np.float32, "Float32"),
+        (np.float64, "Float64"),
+    ]:
+        type_info = analyze_type_info(np_type)
+        assert isinstance(type_info.variant, AnalyzedBasicType)
+        assert type_info.variant.kind == expected_kind, (
+            f"Expected {expected_kind} for {np_type}, got {type_info.variant.kind}"
+        )
+        assert type_info.core_type == np_type, (
+            f"Expected {np_type}, got {type_info.core_type}"
+        )
+
+
+def test_vector_str() -> None:
+    typ = Vector[str]
+    result = analyze_type_info(typ)
+    assert isinstance(result.variant, AnalyzedListType)
+    assert result.variant.elem_type is str
+    assert result.variant.vector_info == VectorInfo(dim=None)
+
+
+def test_non_numpy_vector() -> None:
+    typ = Vector[float, Literal[3]]
+    result = analyze_type_info(typ)
+    assert isinstance(result.variant, AnalyzedListType)
+    assert result.variant.elem_type is float
+    assert result.variant.vector_info == VectorInfo(dim=3)
+
+
+def test_list_of_primitives() -> None:
+    typ = list[str]
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=list[str],
+        base_type=list,
+        variant=AnalyzedListType(elem_type=str, vector_info=None),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_list_of_structs() -> None:
+    typ = list[SimpleDataclass]
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=list[SimpleDataclass],
+        base_type=list,
+        variant=AnalyzedListType(elem_type=SimpleDataclass, vector_info=None),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_sequence_of_int() -> None:
+    typ = Sequence[int]
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=Sequence[int],
+        base_type=Sequence,
+        variant=AnalyzedListType(elem_type=int, vector_info=None),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_list_with_vector_info() -> None:
+    typ = Annotated[list[int], VectorInfo(dim=5)]
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=list[int],
+        base_type=list,
+        variant=AnalyzedListType(elem_type=int, vector_info=VectorInfo(dim=5)),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_dict_str_int() -> None:
+    typ = dict[str, int]
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=dict[str, int],
+        base_type=dict,
+        variant=AnalyzedDictType(key_type=str, value_type=int),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_mapping_str_dataclass() -> None:
+    typ = Mapping[str, SimpleDataclass]
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=Mapping[str, SimpleDataclass],
+        base_type=Mapping,
+        variant=AnalyzedDictType(key_type=str, value_type=SimpleDataclass),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_dataclass() -> None:
+    typ = SimpleDataclass
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=SimpleDataclass,
+        base_type=SimpleDataclass,
+        variant=AnalyzedStructType(struct_type=SimpleDataclass),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_named_tuple() -> None:
+    typ = SimpleNamedTuple
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=SimpleNamedTuple,
+        base_type=SimpleNamedTuple,
+        variant=AnalyzedStructType(struct_type=SimpleNamedTuple),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_str() -> None:
+    typ = str
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=str,
+        base_type=str,
+        variant=AnalyzedBasicType(kind="Str"),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_bool() -> None:
+    typ = bool
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=bool,
+        base_type=bool,
+        variant=AnalyzedBasicType(kind="Bool"),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_bytes() -> None:
+    typ = bytes
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=bytes,
+        base_type=bytes,
+        variant=AnalyzedBasicType(kind="Bytes"),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_uuid() -> None:
+    typ = uuid.UUID
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=uuid.UUID,
+        base_type=uuid.UUID,
+        variant=AnalyzedBasicType(kind="Uuid"),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_date() -> None:
+    typ = datetime.date
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=datetime.date,
+        base_type=datetime.date,
+        variant=AnalyzedBasicType(kind="Date"),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_time() -> None:
+    typ = datetime.time
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=datetime.time,
+        base_type=datetime.time,
+        variant=AnalyzedBasicType(kind="Time"),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_timedelta() -> None:
+    typ = datetime.timedelta
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=datetime.timedelta,
+        base_type=datetime.timedelta,
+        variant=AnalyzedBasicType(kind="TimeDelta"),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_float() -> None:
+    typ = float
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=float,
+        base_type=float,
+        variant=AnalyzedBasicType(kind="Float64"),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_int() -> None:
+    typ = int
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=int,
+        base_type=int,
+        variant=AnalyzedBasicType(kind="Int64"),
+        attrs=None,
+        nullable=False,
+    )
+
+
+def test_type_with_attributes() -> None:
+    typ = Annotated[str, TypeAttr("key", "value")]
+    result = analyze_type_info(typ)
+    assert result == AnalyzedTypeInfo(
+        core_type=str,
+        base_type=str,
+        variant=AnalyzedBasicType(kind="Str"),
+        attrs={"key": "value"},
+        nullable=False,
+    )
+
+
+def test_encode_enriched_type_none() -> None:
+    typ = None
+    result = encode_enriched_type(typ)
+    assert result is None
+
+
+def test_encode_enriched_type_struct() -> None:
+    typ = SimpleDataclass
+    result = encode_enriched_type(typ)
+    assert result["type"]["kind"] == "Struct"
+    assert len(result["type"]["fields"]) == 2
+    assert result["type"]["fields"][0]["name"] == "name"
+    assert result["type"]["fields"][0]["type"]["kind"] == "Str"
+    assert result["type"]["fields"][1]["name"] == "value"
+    assert result["type"]["fields"][1]["type"]["kind"] == "Int64"
+
+
+def test_encode_enriched_type_vector() -> None:
+    typ = NDArray[np.float32]
+    result = encode_enriched_type(typ)
+    assert result["type"]["kind"] == "Vector"
+    assert result["type"]["element_type"]["kind"] == "Float32"
+    assert result["type"]["dimension"] is None
+
+
+def test_encode_enriched_type_ltable() -> None:
+    typ = list[SimpleDataclass]
+    result = encode_enriched_type(typ)
+    assert result["type"]["kind"] == "LTable"
+    assert "fields" in result["type"]["row"]
+    assert len(result["type"]["row"]["fields"]) == 2
+
+
+def test_encode_enriched_type_with_attrs() -> None:
+    typ = Annotated[str, TypeAttr("key", "value")]
+    result = encode_enriched_type(typ)
+    assert result["type"]["kind"] == "Str"
+    assert result["attrs"] == {"key": "value"}
+
+
+def test_encode_enriched_type_nullable() -> None:
+    typ = str | None
+    result = encode_enriched_type(typ)
+    assert result["type"]["kind"] == "Str"
+    assert result["nullable"] is True
+
+
+def test_encode_scalar_numpy_types_schema() -> None:
+    for np_type, expected_kind in [
+        (np.int64, "Int64"),
+        (np.float32, "Float32"),
+        (np.float64, "Float64"),
+    ]:
+        schema = encode_enriched_type(np_type)
+        assert schema["type"]["kind"] == expected_kind, (
+            f"Expected {expected_kind} for {np_type}, got {schema['type']['kind']}"
+        )
+        assert not schema.get("nullable", False)
+
+
+def test_annotated_struct_with_type_kind() -> None:
+    typ = Annotated[SimpleDataclass, TypeKind("Vector")]
+    result = analyze_type_info(typ)
+    assert isinstance(result.variant, AnalyzedBasicType)
+    assert result.variant.kind == "Vector"
+
+
+def test_annotated_list_with_type_kind() -> None:
+    typ = Annotated[list[int], TypeKind("Struct")]
+    result = analyze_type_info(typ)
+    assert isinstance(result.variant, AnalyzedBasicType)
+    assert result.variant.kind == "Struct"
+
+
+def test_unknown_type() -> None:
+    typ = set
+    result = analyze_type_info(typ)
+    assert isinstance(result.variant, AnalyzedUnknownType)

cocoindex/tests/test_validation.py

@@ -0,0 +1,134 @@
+"""Tests for naming validation functionality."""
+
+import pytest
+from cocoindex.validation import (
+    validate_field_name,
+    validate_flow_name,
+    validate_full_flow_name,
+    validate_app_namespace_name,
+    validate_target_name,
+    NamingError,
+    validate_identifier_name,
+)
+
+
+class TestValidateIdentifierName:
+    """Test the core validation function."""
+
+    def test_valid_names(self) -> None:
+        """Test that valid names pass validation."""
+        valid_names = [
+            "field1",
+            "field_name",
+            "_private",
+            "a",
+            "field123",
+            "FIELD_NAME",
+            "MyField",
+            "field_123_test",
+        ]
+
+        for name in valid_names:
+            result = validate_identifier_name(name)
+            assert result is None, f"Valid name '{name}' failed validation: {result}"
+
+    def test_valid_names_with_dots(self) -> None:
+        """Test that valid names with dots pass validation when allowed."""
+        valid_names = ["app.flow", "my_app.my_flow", "namespace.sub.flow", "a.b.c.d"]
+
+        for name in valid_names:
+            result = validate_identifier_name(name, allow_dots=True)
+            assert result is None, (
+                f"Valid dotted name '{name}' failed validation: {result}"
+            )
+
+    def test_invalid_starting_characters(self) -> None:
+        """Test names with invalid starting characters."""
+        invalid_names = [
+            "123field",  # starts with digit
+            ".field",  # starts with dot
+            "-field",  # starts with dash
+            " field",  # starts with space
+        ]
+
+        for name in invalid_names:
+            result = validate_identifier_name(name)
+            assert result is not None, (
+                f"Invalid name '{name}' should have failed validation"
+            )
+
+    def test_double_underscore_restriction(self) -> None:
+        """Test double underscore restriction."""
+        invalid_names = ["__reserved", "__internal", "__test"]
+
+        for name in invalid_names:
+            result = validate_identifier_name(name)
+            assert result is not None
+            assert "double underscores" in result.lower()
+
+    def test_length_restriction(self) -> None:
+        """Test maximum length restriction."""
+        long_name = "a" * 65
+        result = validate_identifier_name(long_name, max_length=64)
+        assert result is not None
+        assert "maximum length" in result.lower()
+
+
+class TestSpecificValidators:
+    """Test the specific validation functions."""
+
+    def test_valid_field_names(self) -> None:
+        """Test valid field names."""
+        valid_names = ["field1", "field_name", "_private", "FIELD"]
+        for name in valid_names:
+            validate_field_name(name)  # Should not raise
+
+    def test_invalid_field_names(self) -> None:
+        """Test invalid field names raise NamingError."""
+        invalid_names = ["123field", "field-name", "__reserved", "a" * 65]
+
+        for name in invalid_names:
+            with pytest.raises(NamingError):
+                validate_field_name(name)
+
+    def test_flow_validation(self) -> None:
+        """Test flow name validation."""
+        # Valid flow names
+        validate_flow_name("MyFlow")
+        validate_flow_name("my_flow_123")
+
+        # Invalid flow names
+        with pytest.raises(NamingError):
+            validate_flow_name("123flow")
+
+        with pytest.raises(NamingError):
+            validate_flow_name("__reserved_flow")
+
+    def test_full_flow_name_allows_dots(self) -> None:
+        """Test that full flow names allow dots."""
+        validate_full_flow_name("app.my_flow")
+        validate_full_flow_name("namespace.subnamespace.flow")
+
+        # But still reject invalid patterns
+        with pytest.raises(NamingError):
+            validate_full_flow_name("123.invalid")
+
+    def test_target_validation(self) -> None:
+        """Test target name validation."""
+        validate_target_name("my_target")
+        validate_target_name("output_table")
+
+        with pytest.raises(NamingError):
+            validate_target_name("123target")
+
+    def test_app_namespace_validation(self) -> None:
+        """Test app namespace validation."""
+        validate_app_namespace_name("myapp")
+        validate_app_namespace_name("my_app_123")
+
+        # Should not allow dots in app namespace
+        with pytest.raises(NamingError):
+            validate_app_namespace_name("my.app")
+
+        with pytest.raises(NamingError):
+            validate_app_namespace_name("123app")