db-dtypes 1.4.3__py3-none-any.whl

db_dtypes/__init__.py

@@ -0,0 +1,366 @@
+# Copyright 2021 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+"""
+Pandas Data Types for SQL systems (BigQuery, Spanner)
+"""
+
+import datetime
+import re
+from typing import Optional, Union
+import warnings
+
+import numpy
+import pandas
+import pandas.api.extensions
+from pandas.errors import OutOfBoundsDatetime
+import pyarrow
+import pyarrow.compute
+
+from db_dtypes import core
+from db_dtypes.json import JSONArray, JSONDtype, JSONArrowType  # noqa: F401
+
+from . import _versions_helpers
+
+date_dtype_name = "dbdate"
+time_dtype_name = "dbtime"
+_EPOCH = datetime.datetime(1970, 1, 1)
+_NPEPOCH = numpy.datetime64(_EPOCH)
+_NP_DTYPE = "datetime64[ns]"
+
+# Numpy converts datetime64 scalars to datetime.datetime only if microsecond or
+# smaller precision is used.
+#
+# TODO(https://github.com/googleapis/python-db-dtypes-pandas/issues/63): Keep
+# nanosecond precision when boxing scalars.
+_NP_BOX_DTYPE = "datetime64[us]"
+
+
+@pandas.api.extensions.register_extension_dtype
+class TimeDtype(core.BaseDatetimeDtype):
+    """
+    Extension dtype for time data.
+    """
+
+    name = time_dtype_name
+    type = datetime.time
+
+    def construct_array_type(self):
+        return TimeArray
+
+    @staticmethod
+    def __from_arrow__(
+        array: Union[pyarrow.Array, pyarrow.ChunkedArray]
+    ) -> "TimeArray":
+        """Convert to dbtime data from an Arrow array.
+
+        See:
+        https://pandas.pydata.org/pandas-docs/stable/development/extending.html#compatibility-with-apache-arrow
+        """
+        # We can't call combine_chunks on an empty array, so short-circuit the
+        # rest of the function logic for this special case.
+        if len(array) == 0:
+            return TimeArray(numpy.array([], dtype="datetime64[ns]"))
+
+        # We can't cast to timestamp("ns"), but time64("ns") has the same
+        # memory layout: 64-bit integers representing the number of nanoseconds
+        # since the datetime epoch (midnight 1970-01-01).
+        array = pyarrow.compute.cast(array, pyarrow.time64("ns"))
+
+        # ChunkedArray has no "view" method, so combine into an Array.
+        if isinstance(array, pyarrow.ChunkedArray):
+            array = array.combine_chunks()
+
+        array = array.view(pyarrow.timestamp("ns"))
+        np_array = array.to_numpy(zero_copy_only=False)
+        return TimeArray(np_array)
+
+
+class TimeArray(core.BaseDatetimeArray):
+    """
+    Pandas array type containing time data
+    """
+
+    # Data are stored as datetime64 values with a date of Jan 1, 1970
+
+    dtype = TimeDtype()
+
+    @classmethod
+    def _datetime(
+        cls,
+        scalar,
+        match_fn=re.compile(
+            r"\s*(?P<hours>\d+)"
+            r"(?::(?P<minutes>\d+)"
+            r"(?::(?P<seconds>\d+)"
+            r"(?:\.(?P<fraction>\d*))?)?)?\s*$"
+        ).match,
+    ) -> Optional[numpy.datetime64]:
+        if isinstance(scalar, numpy.datetime64):
+            return scalar
+
+        # Convert pyarrow values to datetime.time.
+        if isinstance(scalar, (pyarrow.Time32Scalar, pyarrow.Time64Scalar)):
+            scalar = (
+                scalar.cast(pyarrow.time64("ns"))
+                .cast(pyarrow.int64())
+                .cast(pyarrow.timestamp("ns"))
+                .as_py()
+            )
+
+        if pandas.isna(scalar):
+            return numpy.datetime64("NaT")
+        if isinstance(scalar, datetime.time):
+            return pandas.Timestamp(
+                year=1970,
+                month=1,
+                day=1,
+                hour=scalar.hour,
+                minute=scalar.minute,
+                second=scalar.second,
+                microsecond=scalar.microsecond,
+            ).to_datetime64()
+        elif isinstance(scalar, pandas.Timestamp):
+            return scalar.to_datetime64()
+        elif isinstance(scalar, str):
+            # iso string
+            parsed = match_fn(scalar)
+            if not parsed:
+                raise ValueError(f"Bad time string: {repr(scalar)}")
+
+            hour = parsed.group("hours")
+            minute = parsed.group("minutes")
+            second = parsed.group("seconds")
+            fraction = parsed.group("fraction")
+            nanosecond = int(fraction.ljust(9, "0")[:9]) if fraction else 0
+
+            return pandas.Timestamp(
+                year=1970,
+                month=1,
+                day=1,
+                hour=int(hour),
+                minute=int(minute) if minute else 0,
+                second=int(second) if second else 0,
+                microsecond=nanosecond // 1000,
+                nanosecond=nanosecond % 1000,
+            ).to_datetime64()
+        else:
+            raise TypeError("Invalid value type", scalar)
+
+    def _box_func(self, x):
+        if pandas.isna(x):
+            return pandas.NaT
+
+        try:
+            return x.astype(_NP_BOX_DTYPE).item().time()
+        except AttributeError:
+            x = numpy.datetime64(
+                x, "ns"
+            )  # Integers are stored with nanosecond precision.
+            return x.astype(_NP_BOX_DTYPE).item().time()
+
+    __return_deltas = {"timedelta", "timedelta64", "timedelta64[ns]", "<m8", _NP_DTYPE}
+
+    def astype(self, dtype, copy=True):
+        deltas = self._ndarray - _NPEPOCH
+        stype = str(dtype)
+        if stype in self.__return_deltas:
+            return deltas
+        elif stype.startswith("timedelta64[") or stype.startswith("<m8["):
+            return deltas.astype(dtype, copy=False)
+        else:
+            return super().astype(dtype, copy=copy)
+
+    def __arrow_array__(self, type=None):
+        """Convert to an Arrow array from dbtime data.
+
+        See:
+        https://pandas.pydata.org/pandas-docs/stable/development/extending.html#compatibility-with-apache-arrow
+        """
+        array = pyarrow.array(self._ndarray, type=pyarrow.timestamp("ns"))
+
+        # ChunkedArray has no "view" method, so combine into an Array.
+        array = (
+            array.combine_chunks() if isinstance(array, pyarrow.ChunkedArray) else array
+        )
+
+        # We can't cast to time64("ns"), but timestamp("ns") has the same
+        # memory layout: 64-bit integers representing the number of nanoseconds
+        # since the datetime epoch (midnight 1970-01-01).
+        array = array.view(pyarrow.time64("ns"))
+        return pyarrow.compute.cast(
+            array,
+            type if type is not None else pyarrow.time64("ns"),
+        )
+
+
+@pandas.api.extensions.register_extension_dtype
+class DateDtype(core.BaseDatetimeDtype):
+    """
+    Extension dtype for time data.
+    """
+
+    name = date_dtype_name
+    type = datetime.date
+
+    def construct_array_type(self):
+        return DateArray
+
+    @staticmethod
+    def __from_arrow__(
+        array: Union[pyarrow.Array, pyarrow.ChunkedArray]
+    ) -> "DateArray":
+        """Convert to dbdate data from an Arrow array.
+
+        See:
+        https://pandas.pydata.org/pandas-docs/stable/development/extending.html#compatibility-with-apache-arrow
+        """
+        array = pyarrow.compute.cast(array, pyarrow.timestamp("ns"))
+        np_array = array.to_numpy()
+        return DateArray(np_array)
+
+
+class DateArray(core.BaseDatetimeArray):
+    """
+    Pandas array type containing date data
+    """
+
+    # Data are stored as datetime64 values with a date of Jan 1, 1970
+
+    dtype = DateDtype()
+
+    @staticmethod
+    def _datetime(
+        scalar,
+        match_fn=re.compile(r"\s*(?P<year>\d+)-(?P<month>\d+)-(?P<day>\d+)\s*$").match,
+    ) -> Optional[numpy.datetime64]:
+        # Convert pyarrow values to datetime.date.
+        if isinstance(scalar, (pyarrow.Date32Scalar, pyarrow.Date64Scalar)):
+            scalar = scalar.as_py()
+
+        if pandas.isna(scalar):
+            return numpy.datetime64("NaT")
+        elif isinstance(scalar, numpy.datetime64):
+            dateObj = pandas.Timestamp(scalar)
+        elif isinstance(scalar, datetime.date):
+            dateObj = pandas.Timestamp(
+                year=scalar.year, month=scalar.month, day=scalar.day
+            )
+        elif isinstance(scalar, str):
+            match = match_fn(scalar)
+            if not match:
+                raise ValueError(f"Bad date string: {repr(scalar)}")
+            year = int(match.group("year"))
+            month = int(match.group("month"))
+            day = int(match.group("day"))
+
+            dateObj = pandas.Timestamp(
+                year=year,
+                month=month,
+                day=day,
+            )
+        else:
+            raise TypeError("Invalid value type", scalar)
+
+        # TODO(#64): Support larger ranges with other units.
+        if pandas.Timestamp.min < dateObj < pandas.Timestamp.max:
+            return dateObj.to_datetime64()
+        else:  # pragma: NO COVER
+            # TODO(#166): Include these lines in coverage when pandas 2.0 is released.
+            raise OutOfBoundsDatetime("Out of bounds", scalar)  # pragma: NO COVER
+
+    def _box_func(self, x):
+        if pandas.isna(x):
+            return pandas.NaT
+        try:
+            return x.astype(_NP_BOX_DTYPE).item().date()
+        except AttributeError:
+            x = numpy.datetime64(
+                x, "ns"
+            )  # Integers are stored with nanosecond precision.
+            return x.astype(_NP_BOX_DTYPE).item().date()
+
+    def astype(self, dtype, copy=True):
+        stype = str(dtype)
+        if stype.startswith("datetime"):
+            if stype == "datetime" or stype == "datetime64":
+                dtype = self._ndarray.dtype
+            return self._ndarray.astype(dtype, copy=copy)
+        elif stype.startswith("<M8"):
+            if stype == "<M8":
+                dtype = self._ndarray.dtype
+            return self._ndarray.astype(dtype, copy=copy)
+
+        return super().astype(dtype, copy=copy)
+
+    def __arrow_array__(self, type=None):
+        """Convert to an Arrow array from dbdate data.
+
+        See:
+        https://pandas.pydata.org/pandas-docs/stable/development/extending.html#compatibility-with-apache-arrow
+        """
+        array = pyarrow.array(self._ndarray, type=pyarrow.timestamp("ns"))
+        return pyarrow.compute.cast(
+            array,
+            type if type is not None else pyarrow.date32(),
+        )
+
+    def __add__(self, other):
+        if isinstance(other, pandas.DateOffset):
+            return self.astype("object") + other
+
+        if isinstance(other, TimeArray):
+            return (other._ndarray - _NPEPOCH) + self._ndarray
+
+        return super().__add__(other)
+
+    def __radd__(self, other):
+        return self.__add__(other)
+
+    def __sub__(self, other):
+        if isinstance(other, pandas.DateOffset):
+            return self.astype("object") - other
+
+        if isinstance(other, self.__class__):
+            return self._ndarray - other._ndarray
+
+        return super().__sub__(other)
+
+
+def _check_python_version():
+    """Checks the runtime Python version and issues a warning if needed."""
+    sys_major, sys_minor, sys_micro = _versions_helpers.extract_runtime_version()
+    if sys_major == 3 and sys_minor in (7, 8):
+        warnings.warn(
+            "The python-bigquery library as well as the python-db-dtypes-pandas library no "
+            "longer supports Python 3.7 and Python 3.8. "
+            f"Your Python version is {sys_major}.{sys_minor}.{sys_micro}. We "
+            "recommend that you update soon to ensure ongoing support. For "
+            "more details, see: [Google Cloud Client Libraries Supported Python Versions policy](https://cloud.google.com/python/docs/supported-python-versions)",
+            FutureWarning,
+            stacklevel=2,  # Point warning to the caller of __init__
+        )
+
+
+_check_python_version()
+
+__all__ = [
+    "__version__",
+    "DateArray",
+    "DateDtype",
+    "TimeArray",
+    "TimeDtype",
+    "JSONDtype",
+    "JSONArray",
+    "JSONArrowType",
+]

db_dtypes/_versions_helpers.py

@@ -0,0 +1,32 @@
+# Copyright 2024 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""Shared helper functions for verifying versions of installed modules."""
+
+
+import sys
+from typing import Tuple
+
+
+def extract_runtime_version() -> Tuple[int, int, int]:
+    # Retrieve the version information
+    version_info = sys.version_info
+
+    # Extract the major, minor, and micro components
+    major = version_info.major
+    minor = version_info.minor
+    micro = version_info.micro
+
+    # Display the version number in a clear format
+    return major, minor, micro

db_dtypes/core.py

@@ -0,0 +1,195 @@
+# Copyright 2021 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from typing import Optional
+
+import numpy
+import pandas
+import pandas.api.extensions
+from pandas.api.types import is_dtype_equal, is_list_like, is_scalar, pandas_dtype
+from pandas.core.arrays import _mixins
+
+from db_dtypes import pandas_backports
+
+pandas_release = pandas_backports.pandas_release
+
+
+class BaseDatetimeDtype(pandas.api.extensions.ExtensionDtype):
+    na_value = pandas.NaT
+    kind = "O"
+    names = None
+
+    @classmethod
+    def construct_from_string(cls, name: str):
+        if not isinstance(name, str):
+            raise TypeError(
+                f"'construct_from_string' expects a string, got {type(name)}"
+            )
+
+        if name != cls.name:
+            raise TypeError(f"Cannot construct a '{cls.__name__}' from 'another_type'")
+
+        return cls()
+
+
+class BaseDatetimeArray(pandas_backports.OpsMixin, _mixins.NDArrayBackedExtensionArray):
+    # scalar used to denote NA value inside our self._ndarray, e.g. -1 for
+    # Categorical, iNaT for Period. Outside of object dtype, self.isna() should
+    # be exactly locations in self._ndarray with _internal_fill_value. See:
+    # https://github.com/pandas-dev/pandas/blob/main/pandas/core/arrays/_mixins.py
+    _internal_fill_value = numpy.datetime64("NaT")
+
+    def __init__(self, values, dtype=None, copy: bool = False):
+        if not (
+            isinstance(values, numpy.ndarray) and values.dtype == numpy.dtype("<M8[ns]")
+        ):
+            values = self.__ndarray(values)
+        elif copy:
+            values = values.copy()
+
+        super().__init__(values=values, dtype=values.dtype)
+
+    @classmethod
+    def __ndarray(cls, scalars):
+        return numpy.array(
+            [cls._datetime(scalar) for scalar in scalars],
+            "M8[ns]",
+        )
+
+    @classmethod
+    def _from_sequence(cls, scalars, *, dtype=None, copy=False):
+        if dtype is not None:
+            assert dtype.__class__ is cls.dtype.__class__
+        return cls(cls.__ndarray(scalars))
+
+    _from_sequence_of_strings = _from_sequence
+
+    def astype(self, dtype, copy=True):
+        dtype = pandas_dtype(dtype)
+        if is_dtype_equal(dtype, self.dtype):
+            if not copy:
+                return self
+            else:
+                return self.copy()
+
+        return super().astype(dtype, copy=copy)
+
+    def _cmp_method(self, other, op):
+        """Compare array values, for use in OpsMixin."""
+
+        if is_scalar(other) and (
+            pandas.isna(other) or isinstance(other, self.dtype.type)
+        ):
+            other = type(self)([other])
+
+        if type(other) is not type(self):
+            return NotImplemented
+
+        oshape = getattr(other, "shape", None)
+        if oshape != self.shape and oshape != (1,) and self.shape != (1,):
+            raise TypeError(
+                "Can't compare arrays with different shapes", self.shape, oshape
+            )
+        return op(self._ndarray, other._ndarray)
+
+    def _from_factorized(self, unique, original):
+        return self.__class__(unique)
+
+    def isna(self):
+        return pandas.isna(self._ndarray)
+
+    def _validate_scalar(self, value):
+        """
+        Validate and convert a scalar value to datetime64[ns] for storage in
+        backing NumPy array.
+        """
+        return self._datetime(value)
+
+    def _validate_searchsorted_value(self, value):
+        """
+        Convert a value for use in searching for a value in the backing numpy array.
+
+        TODO: With pandas 2.0, this may be unnecessary. https://github.com/pandas-dev/pandas/pull/45544#issuecomment-1052809232
+        """
+        return self._validate_setitem_value(value)
+
+    def _validate_setitem_value(self, value):
+        """
+        Convert a value for use in setting a value in the backing numpy array.
+        """
+        if is_list_like(value):
+            _datetime = self._datetime
+            return [_datetime(v) for v in value]
+
+        return self._datetime(value)
+
+    def any(
+        self,
+        *,
+        axis: Optional[int] = None,
+        out=None,
+        keepdims: bool = False,
+        skipna: bool = True,
+    ):
+        pandas_backports.numpy_validate_any((), {"out": out, "keepdims": keepdims})
+        result = pandas_backports.nanany(self._ndarray, axis=axis, skipna=skipna)
+        return result
+
+    def all(
+        self,
+        *,
+        axis: Optional[int] = None,
+        out=None,
+        keepdims: bool = False,
+        skipna: bool = True,
+    ):
+        pandas_backports.numpy_validate_all((), {"out": out, "keepdims": keepdims})
+        result = pandas_backports.nanall(self._ndarray, axis=axis, skipna=skipna)
+        return result
+
+    def min(self, *, axis: Optional[int] = None, skipna: bool = True, **kwargs):
+        pandas_backports.numpy_validate_min((), kwargs)
+        result = pandas_backports.nanmin(
+            values=self._ndarray, axis=axis, mask=self.isna(), skipna=skipna
+        )
+        if axis is None or self.ndim == 1:
+            return self._box_func(result)
+        return self._from_backing_data(result)
+
+    def max(self, *, axis: Optional[int] = None, skipna: bool = True, **kwargs):
+        pandas_backports.numpy_validate_max((), kwargs)
+        result = pandas_backports.nanmax(
+            values=self._ndarray, axis=axis, mask=self.isna(), skipna=skipna
+        )
+        if axis is None or self.ndim == 1:
+            return self._box_func(result)
+        return self._from_backing_data(result)
+
+    def median(
+        self,
+        *,
+        axis: Optional[int] = None,
+        out=None,
+        overwrite_input: bool = False,
+        keepdims: bool = False,
+        skipna: bool = True,
+    ):
+        pandas_backports.numpy_validate_median(
+            (),
+            {"out": out, "overwrite_input": overwrite_input, "keepdims": keepdims},
+        )
+        result = pandas_backports.nanmedian(self._ndarray, axis=axis, skipna=skipna)
+        if axis is None or self.ndim == 1:
+            return self._box_func(result)
+        return self._from_backing_data(result)

db_dtypes/json.py

@@ -0,0 +1,281 @@
+# Copyright 2024 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import annotations
+
+import json
+
+import numpy as np
+import pandas as pd
+import pandas.arrays as arrays
+import pandas.core.dtypes.common as common
+import pandas.core.indexers as indexers
+import pyarrow as pa
+import pyarrow.compute
+
+
+@pd.api.extensions.register_extension_dtype
+class JSONDtype(pd.api.extensions.ExtensionDtype):
+    """Extension dtype for BigQuery JSON data."""
+
+    name = "dbjson"
+
+    @property
+    def na_value(self) -> pd.NA:
+        """Default NA value to use for this type."""
+        return pd.NA
+
+    @property
+    def type(self) -> type[str]:
+        """
+        Return the scalar type for the array elements.
+        The standard JSON data types can be one of `dict`, `list`, `str`, `int`, `float`,
+        `bool` and `None`. However, this method returns a `str` type to indicate its
+        storage type, because the union of multiple types are not supported well in pandas.
+        """
+        return str
+
+    @property
+    def pyarrow_dtype(self):
+        """Return the pyarrow data type used for storing data in the pyarrow array."""
+        return pa.string()
+
+    @property
+    def _is_numeric(self) -> bool:
+        return False
+
+    @property
+    def _is_boolean(self) -> bool:
+        return False
+
+    @classmethod
+    def construct_array_type(cls):
+        """Return the array type associated with this dtype."""
+        return JSONArray
+
+    def __from_arrow__(self, array: pa.Array | pa.ChunkedArray) -> JSONArray:
+        """Convert the pyarrow array to the extension array."""
+        return JSONArray(array)
+
+
+class JSONArray(arrays.ArrowExtensionArray):
+    """Extension array that handles BigQuery JSON data, leveraging a string-based
+    pyarrow array for storage. It enables seamless conversion to JSON objects when
+    accessing individual elements."""
+
+    _dtype = JSONDtype()
+
+    def __init__(self, values) -> None:
+        super().__init__(values)
+        self._dtype = JSONDtype()
+        if isinstance(values, pa.Array):
+            pa_data = pa.chunked_array([values])
+        elif isinstance(values, pa.ChunkedArray):
+            pa_data = values
+        else:
+            raise NotImplementedError(
+                f"Unsupported type '{type(values)}' for JSONArray"
+            )
+
+        # Ensures compatibility with pandas version 1.5.3
+        if hasattr(self, "_data"):
+            self._data = pa_data
+        elif hasattr(self, "_pa_array"):
+            self._pa_array = pa_data
+        else:
+            raise NotImplementedError(f"Unsupported pandas version: {pd.__version__}")
+
+    def __arrow_array__(self, type=None):
+        """Convert to an arrow array. This is required for pyarrow extension."""
+        return pa.array(self.pa_data, type=JSONArrowType())
+
+    @classmethod
+    def _box_pa(
+        cls, value, pa_type: pa.DataType | None = None
+    ) -> pa.Array | pa.ChunkedArray | pa.Scalar:
+        """Box value into a pyarrow Array, ChunkedArray or Scalar."""
+        assert pa_type is None or pa_type == cls._dtype.pyarrow_dtype
+
+        if isinstance(value, pa.Scalar) or not (
+            common.is_list_like(value) and not common.is_dict_like(value)
+        ):
+            return cls._box_pa_scalar(value)
+        return cls._box_pa_array(value)
+
+    @classmethod
+    def _box_pa_scalar(cls, value) -> pa.Scalar:
+        """Box value into a pyarrow Scalar."""
+        if pd.isna(value):
+            pa_scalar = pa.scalar(None, type=cls._dtype.pyarrow_dtype)
+        else:
+            value = JSONArray._serialize_json(value)
+            pa_scalar = pa.scalar(
+                value, type=cls._dtype.pyarrow_dtype, from_pandas=True
+            )
+
+        return pa_scalar
+
+    @classmethod
+    def _box_pa_array(cls, value, copy: bool = False) -> pa.Array | pa.ChunkedArray:
+        """Box value into a pyarrow Array or ChunkedArray."""
+        if isinstance(value, cls):
+            pa_array = value.pa_data
+        else:
+            value = [JSONArray._serialize_json(x) for x in value]
+            pa_array = pa.array(value, type=cls._dtype.pyarrow_dtype, from_pandas=True)
+        return pa_array
+
+    @classmethod
+    def _from_sequence(cls, scalars, *, dtype=None, copy=False):
+        """Construct a new ExtensionArray from a sequence of scalars."""
+        pa_array = cls._box_pa(scalars)
+        arr = cls(pa_array)
+        return arr
+
+    @staticmethod
+    def _serialize_json(value):
+        """A static method that converts a JSON value into a string representation."""
+        if not common.is_list_like(value) and pd.isna(value):
+            return value
+        else:
+            # `sort_keys=True` sorts dictionary keys before serialization, making
+            # JSON comparisons deterministic.
+            # `separators=(',', ':')` eliminate whitespace to get the most compact
+            # JSON representation.
+            return json.dumps(value, sort_keys=True, separators=(",", ":"))
+
+    @staticmethod
+    def _deserialize_json(value):
+        """A static method that converts a JSON string back into its original value."""
+        if not pd.isna(value):
+            return json.loads(value)
+        else:
+            return value
+
+    @property
+    def dtype(self) -> JSONDtype:
+        """An instance of JSONDtype"""
+        return self._dtype
+
+    @property
+    def pa_data(self):
+        """An instance of stored pa data"""
+        # Ensures compatibility with pandas version 1.5.3
+        if hasattr(self, "_data"):
+            return self._data
+        elif hasattr(self, "_pa_array"):
+            return self._pa_array
+        else:
+            raise NotImplementedError(f"Unsupported pandas version: {pd.__version__}")
+
+    def _cmp_method(self, other, op):
+        if op.__name__ == "eq":
+            result = pyarrow.compute.equal(self.pa_data, self._box_pa(other))
+        elif op.__name__ == "ne":
+            result = pyarrow.compute.not_equal(self.pa_data, self._box_pa(other))
+        else:
+            # Comparison is not a meaningful one. We don't want to support sorting by JSON columns.
+            raise TypeError(f"{op.__name__} not supported for JSONArray")
+        return arrays.ArrowExtensionArray(result)
+
+    def __getitem__(self, item):
+        """Select a subset of self."""
+        item = indexers.check_array_indexer(self, item)
+
+        if isinstance(item, np.ndarray):
+            if not len(item):
+                return type(self)(pa.chunked_array([], type=self.dtype.pyarrow_dtype))
+            elif item.dtype.kind in "iu":
+                return self.take(item)
+            else:
+                # `check_array_indexer` should verify that the assertion hold true.
+                assert item.dtype.kind == "b"
+                return type(self)(self.pa_data.filter(item))
+        elif isinstance(item, tuple):
+            item = indexers.unpack_tuple_and_ellipses(item)
+
+        if common.is_scalar(item) and not common.is_integer(item):
+            # e.g. "foo" or 2.5
+            # exception message copied from numpy
+            raise IndexError(
+                r"only integers, slices (`:`), ellipsis (`...`), numpy.newaxis "
+                r"(`None`) and integer or boolean arrays are valid indices"
+            )
+
+        value = self.pa_data[item]
+        if isinstance(value, pa.ChunkedArray):
+            return type(self)(value)
+        elif isinstance(value, pa.ExtensionScalar):
+            return value.as_py()
+        else:
+            scalar = JSONArray._deserialize_json(value.as_py())
+            if scalar is None:
+                return self._dtype.na_value
+            else:
+                return scalar
+
+    def __iter__(self):
+        """Iterate over elements of the array."""
+        for value in self.pa_data:
+            val = JSONArray._deserialize_json(value.as_py())
+            if val is None:
+                yield self._dtype.na_value
+            else:
+                yield val
+
+    def _reduce(
+        self, name: str, *, skipna: bool = True, keepdims: bool = False, **kwargs
+    ):
+        """Return a scalar result of performing the reduction operation."""
+        if name in ["min", "max"]:
+            raise TypeError("JSONArray does not support min/max reducntion.")
+        super()._reduce(name, skipna=skipna, keepdims=keepdims, **kwargs)
+
+    def __array__(self, dtype=None, copy: bool | None = None) -> np.ndarray:
+        """Correctly construct numpy arrays when passed to `np.asarray()`."""
+        pa_type = self.pa_data.type
+        data = self
+        if dtype is None:
+            empty = pa.array([], type=pa_type).to_numpy(zero_copy_only=False)
+            dtype = empty.dtype
+        result = np.empty(len(data), dtype=dtype)
+        mask = data.isna()
+        result[mask] = self._dtype.na_value
+        result[~mask] = data[~mask].pa_data.to_numpy()
+        return result
+
+
+class JSONArrowType(pa.ExtensionType):
+    """Arrow extension type for the `dbjson` Pandas extension type."""
+
+    def __init__(self) -> None:
+        super().__init__(pa.string(), "dbjson")
+
+    def __arrow_ext_serialize__(self) -> bytes:
+        return b""
+
+    @classmethod
+    def __arrow_ext_deserialize__(cls, storage_type, serialized) -> JSONArrowType:
+        return JSONArrowType()
+
+    def __hash__(self) -> int:
+        return hash(str(self))
+
+    def to_pandas_dtype(self):
+        return JSONDtype()
+
+
+# Register the type to be included in RecordBatches, sent over IPC and received in
+# another Python process.
+pa.register_extension_type(JSONArrowType())

db_dtypes/pandas_backports.py

@@ -0,0 +1,74 @@
+# Copyright 2021 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+"""
+Utilities to support older pandas versions.
+
+These backported versions are simpler and, in some cases, less featureful than
+the versions in the later versions of pandas.
+"""
+
+import packaging.version
+import pandas
+import pandas.compat.numpy.function
+
+pandas_release = packaging.version.parse(pandas.__version__).release
+
+# # Create aliases for private methods in case they move in a future version.
+nanall = pandas.core.nanops.nanall
+nanany = pandas.core.nanops.nanany
+nanmax = pandas.core.nanops.nanmax
+nanmin = pandas.core.nanops.nanmin
+numpy_validate_all = pandas.compat.numpy.function.validate_all
+numpy_validate_any = pandas.compat.numpy.function.validate_any
+numpy_validate_max = pandas.compat.numpy.function.validate_max
+numpy_validate_min = pandas.compat.numpy.function.validate_min
+
+nanmedian = pandas.core.nanops.nanmedian
+numpy_validate_median = pandas.compat.numpy.function.validate_median
+
+
+def import_default(module_name, force=False, default=None):
+    """
+    Provide an implementation for a class or function when it can't be imported
+
+    or when force is True.
+
+    This is used to replicate Pandas APIs that are missing or insufficient
+    (thus the force option) in early pandas versions.
+    """
+
+    if default is None:
+        return lambda func_or_class: import_default(module_name, force, func_or_class)
+
+    if force:
+        return default
+
+    name = default.__name__
+    try:
+        module = __import__(module_name, {}, {}, [name])
+    except ModuleNotFoundError:
+        return default
+
+    return getattr(module, name, default)
+
+
+# pandas.core.arraylike.OpsMixin is private, but the related public API
+# "ExtensionScalarOpsMixin" is not sufficient for adding dates to times.
+# It results in unsupported operand type(s) for +: 'datetime.time' and
+# 'datetime.date'
+@import_default("pandas.core.arraylike")
+class OpsMixin:
+    def _cmp_method(self, other, op):  # pragma: NO COVER
+        return NotImplemented

db_dtypes/version.py

@@ -0,0 +1,15 @@
+# Copyright 2021 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     https://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+__version__ = "1.4.3"  # pragma: NO COVER

db_dtypes-1.4.3.dist-info/AUTHORS

@@ -0,0 +1,9 @@
+# This is the list of db-dtypes's significant contributors.
+#
+# This does not necessarily list everyone who has contributed code,
+# especially since many employees of one corporation may be contributing.
+# To see the full list of contributors, see the revision history in
+# source control.
+Google LLC
+Jim Fulton
+Tim Swast (tswast)

db_dtypes-1.4.3.dist-info/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

db_dtypes-1.4.3.dist-info/METADATA

@@ -0,0 +1,93 @@
+Metadata-Version: 2.1
+Name: db-dtypes
+Version: 1.4.3
+Summary: Pandas Data Types for SQL systems (BigQuery, Spanner)
+Home-page: https://github.com/googleapis/python-db-dtypes-pandas
+Author: The db-dtypes Authors
+Author-email: googleapis-packages@google.com
+Keywords: sql,pandas
+Platform: Posix; MacOS X; Windows
+Classifier: Development Status :: 5 - Production/Stable
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Database :: Front-Ends
+Requires-Python: >=3.9
+Description-Content-Type: text/x-rst
+License-File: LICENSE
+License-File: AUTHORS
+Requires-Dist: numpy>=1.24.0
+Requires-Dist: packaging>=24.2.0
+Requires-Dist: pandas>=1.5.3
+Requires-Dist: pyarrow>=13.0.0
+
+Pandas Data Types for SQL systems (BigQuery, Spanner)
+=====================================================
+
+|ga| |pypi| |versions|
+
+`Pandas extension data types`_ for data from SQL systems such as `BigQuery`_.
+
+- `Library Documentation`_
+
+.. |ga| image:: https://img.shields.io/badge/support-GA-gold.svg
+   :target: https://github.com/googleapis/google-cloud-python/blob/main/README.rst#general-availability
+.. |pypi| image:: https://img.shields.io/pypi/v/db-dtypes.svg
+   :target: https://pypi.org/project/db-dtypes/
+.. |versions| image:: https://img.shields.io/pypi/pyversions/db-dtypes.svg
+   :target: https://pypi.org/project/db-dtypes/
+.. _Pandas extension data types: https://pandas.pydata.org/docs/development/extending.html#extension-types
+.. _BigQuery: https://cloud.google.com/bigquery/docs/
+.. _Library Documentation: https://googleapis.dev/python/db-dtypes/latest
+
+
+Installation
+------------
+
+Install this library in a `virtualenv`_ using pip. `virtualenv`_ is a tool to
+create isolated Python environments. The basic problem it addresses is one of
+dependencies and versions, and indirectly permissions.
+
+With `virtualenv`_, it's possible to install this library without needing system
+install permissions, and without clashing with the installed system
+dependencies.
+
+.. _`virtualenv`: https://virtualenv.pypa.io/en/latest/
+
+
+Supported Python Versions
+^^^^^^^^^^^^^^^^^^^^^^^^^
+Python >= 3.9
+
+Unsupported Python Versions
+^^^^^^^^^^^^^^^^^^^^^^^^^^^
+Python <= 3.8.
+
+
+Mac/Linux
+^^^^^^^^^
+
+.. code-block:: console
+
+    pip install virtualenv
+    virtualenv <your-env>
+    source <your-env>/bin/activate
+    <your-env>/bin/pip install db-dtypes
+
+
+Windows
+^^^^^^^
+
+.. code-block:: console
+
+    pip install virtualenv
+    virtualenv <your-env>
+    <your-env>\Scripts\activate
+    <your-env>\Scripts\pip.exe install db-dtypes

db_dtypes-1.4.3.dist-info/RECORD

@@ -0,0 +1,12 @@
+db_dtypes/__init__.py,sha256=Lq8VKd1X7hdaHIwYoLOWe4Hj3UT5PNgZaSIgx9nnUh4,12259
+db_dtypes/_versions_helpers.py,sha256=ChEUHNB1zLfn1RwAiuh3TyyATuq7rdSNAYW-DkKFphs,1050
+db_dtypes/core.py,sha256=p3rmWRqJ6ryWyMyyUVeH3btLO2xp5HjxjoGwD-zkkqU,6572
+db_dtypes/json.py,sha256=UMno-4dCC3ldOUNXTSRPFG7LHBV08h1Zk5BwZJBdVz8,10029
+db_dtypes/pandas_backports.py,sha256=ZIQsNY-Nz1gbAgMSu2034XTLk-ZEGKgmU4S71JShGps,2521
+db_dtypes/version.py,sha256=RGho-Ro8RZTtDee-enRlIndtWLt_3udMRn1zWdA3-9o,618
+db_dtypes-1.4.3.dist-info/AUTHORS,sha256=ZzwnqDCA5-5_W_beU6-64JXYg_8IyNUp7aHfvZHowmI,331
+db_dtypes-1.4.3.dist-info/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
+db_dtypes-1.4.3.dist-info/METADATA,sha256=waf9H7MnIJDqMFXu6U6sp0k52U5WFQ8SIeve3G4ZjH4,2970
+db_dtypes-1.4.3.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
+db_dtypes-1.4.3.dist-info/top_level.txt,sha256=Lzrj78HENTzHjW4Xb-xOlAuHlAgu4z8nG9NrXPqZKJk,10
+db_dtypes-1.4.3.dist-info/RECORD,,

db_dtypes-1.4.3.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (75.3.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

db_dtypes-1.4.3.dist-info/top_level.txt

@@ -0,0 +1 @@
+db_dtypes