PyPI - duckdb - Versions diffs - 1.4.2.dev1__cp39-cp39-macosx_10_9_universal2.whl → 1.5.0.dev44__cp39-cp39-macosx_10_9_universal2.whl - Mend

duckdb 1.4.2.dev1__cp39-cp39-macosx_10_9_universal2.whl → 1.5.0.dev44__cp39-cp39-macosx_10_9_universal2.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.

This version of duckdb might be problematic. Click here for more details.

Files changed (57) hide show

_duckdb.cpython-39-darwin.so +0 -0
duckdb/__init__.py +435 -341
duckdb/__init__.pyi +713 -0
duckdb/bytes_io_wrapper.py +9 -12
duckdb/experimental/__init__.py +1 -2
duckdb/experimental/spark/__init__.py +4 -3
duckdb/experimental/spark/_globals.py +8 -8
duckdb/experimental/spark/_typing.py +9 -7
duckdb/experimental/spark/conf.py +15 -16
duckdb/experimental/spark/context.py +44 -60
duckdb/experimental/spark/errors/__init__.py +35 -33
duckdb/experimental/spark/errors/error_classes.py +1 -1
duckdb/experimental/spark/errors/exceptions/__init__.py +1 -1
duckdb/experimental/spark/errors/exceptions/base.py +88 -39
duckdb/experimental/spark/errors/utils.py +16 -11
duckdb/experimental/spark/exception.py +6 -9
duckdb/experimental/spark/sql/__init__.py +5 -5
duckdb/experimental/spark/sql/_typing.py +15 -8
duckdb/experimental/spark/sql/catalog.py +20 -21
duckdb/experimental/spark/sql/column.py +55 -48
duckdb/experimental/spark/sql/conf.py +8 -9
duckdb/experimental/spark/sql/dataframe.py +233 -185
duckdb/experimental/spark/sql/functions.py +1248 -1222
duckdb/experimental/spark/sql/group.py +52 -56
duckdb/experimental/spark/sql/readwriter.py +94 -80
duckdb/experimental/spark/sql/session.py +59 -64
duckdb/experimental/spark/sql/streaming.py +10 -9
duckdb/experimental/spark/sql/type_utils.py +65 -67
duckdb/experimental/spark/sql/types.py +345 -309
duckdb/experimental/spark/sql/udf.py +6 -6
duckdb/filesystem.py +16 -26
duckdb/functional/__init__.py +16 -12
duckdb/functional/__init__.pyi +31 -0
duckdb/polars_io.py +83 -130
duckdb/query_graph/__main__.py +96 -91
duckdb/typing/__init__.py +8 -18
duckdb/typing/__init__.pyi +36 -0
duckdb/udf.py +5 -10
duckdb/value/__init__.py +0 -1
duckdb/value/constant/__init__.py +60 -62
duckdb/value/constant/__init__.pyi +115 -0
duckdb-1.5.0.dev44.dist-info/METADATA +80 -0
duckdb-1.5.0.dev44.dist-info/RECORD +47 -0
_duckdb-stubs/__init__.pyi +0 -1443
_duckdb-stubs/_func.pyi +0 -46
_duckdb-stubs/_sqltypes.pyi +0 -75
adbc_driver_duckdb/__init__.py +0 -50
adbc_driver_duckdb/dbapi.py +0 -115
duckdb/_dbapi_type_object.py +0 -231
duckdb/_version.py +0 -22
duckdb/func/__init__.py +0 -3
duckdb/sqltypes/__init__.py +0 -63
duckdb-1.4.2.dev1.dist-info/METADATA +0 -326
duckdb-1.4.2.dev1.dist-info/RECORD +0 -52
/duckdb/{py.typed → value/__init__.pyi} +0 -0
{duckdb-1.4.2.dev1.dist-info → duckdb-1.5.0.dev44.dist-info}/WHEEL +0 -0
{duckdb-1.4.2.dev1.dist-info → duckdb-1.5.0.dev44.dist-info}/licenses/LICENSE +0 -0

duckdb/__init__.py CHANGED Viewed

@@ -1,381 +1,475 @@
-# ruff: noqa: F401
-"""The DuckDB Python Package.
+# Modules
+import duckdb.functional as functional
+import duckdb.typing as typing
+from _duckdb import __version__ as duckdb_version
+from importlib.metadata import version
-This module re-exports the DuckDB C++ extension (`_duckdb`) and provides DuckDB's public API.
+# duckdb.__version__ returns the version of the distribution package, i.e. the pypi version
+__version__ = version("duckdb")
-Note:
-- Some symbols exposed here are implementation details of DuckDB's C++ engine.
-- They are kept for backwards compatibility but are not considered stable API.
-- Future versions may move them into submodules with deprecation warnings.
-"""
+# version() is a more human friendly formatted version string of both the distribution package and the bundled duckdb
+def version():
+    return f"{__version__} (with duckdb {duckdb_version})"
+_exported_symbols = ['__version__', 'version']
+_exported_symbols.extend([
+    "typing",
+    "functional"
+])
+class DBAPITypeObject:
+    def __init__(self, types: list[typing.DuckDBPyType]) -> None:
+        self.types = types
+    def __eq__(self, other):
+        if isinstance(other, typing.DuckDBPyType):
+            return other in self.types
+        return False
+    def __repr__(self):
+        return f"<DBAPITypeObject [{','.join(str(x) for x in self.types)}]>"
+# Define the standard DBAPI sentinels
+STRING   = DBAPITypeObject([typing.VARCHAR])
+NUMBER   = DBAPITypeObject([
+    typing.TINYINT,
+    typing.UTINYINT,
+    typing.SMALLINT,
+    typing.USMALLINT,
+    typing.INTEGER,
+    typing.UINTEGER,
+    typing.BIGINT,
+    typing.UBIGINT,
+    typing.HUGEINT,
+    typing.UHUGEINT,
+    typing.DuckDBPyType("BIGNUM"),
+    typing.DuckDBPyType("DECIMAL"),
+    typing.FLOAT,
+    typing.DOUBLE
+])
+DATETIME = DBAPITypeObject([
+    typing.DATE,
+    typing.TIME,
+    typing.TIME_TZ,
+    typing.TIMESTAMP,
+    typing.TIMESTAMP_TZ,
+    typing.TIMESTAMP_NS,
+    typing.TIMESTAMP_MS,
+    typing.TIMESTAMP_S
+])
+BINARY   = DBAPITypeObject([typing.BLOB])
+ROWID    = None
+# Classes
 from _duckdb import (
-    BinderException,
-    CaseExpression,
-    CatalogException,
-    CoalesceOperator,
-    ColumnExpression,
-    ConnectionException,
-    ConstantExpression,
-    ConstraintException,
-    ConversionException,
-    CSVLineTerminator,
-    DatabaseError,
-    DataError,
-    DefaultExpression,
-    DependencyException,
-    DuckDBPyConnection,
     DuckDBPyRelation,
-    Error,
-    ExpectedResultType,
+    DuckDBPyConnection,
+    Statement,
     ExplainType,
+    StatementType,
+    ExpectedResultType,
+	CSVLineTerminator,
+    PythonExceptionHandling,
+    RenderMode,
     Expression,
-    FatalException,
+    ConstantExpression,
+    ColumnExpression,
+    DefaultExpression,
+    CoalesceOperator,
+    LambdaExpression,
+    StarExpression,
     FunctionExpression,
-    HTTPException,
+    CaseExpression,
+    SQLExpression
+)
+_exported_symbols.extend([
+    "DuckDBPyRelation",
+    "DuckDBPyConnection",
+    "ExplainType",
+    "PythonExceptionHandling",
+    "Expression",
+    "ConstantExpression",
+    "ColumnExpression",
+    "DefaultExpression",
+    "CoalesceOperator",
+    "LambdaExpression",
+    "StarExpression",
+    "FunctionExpression",
+    "CaseExpression",
+    "SQLExpression"
+])
+# These are overloaded twice, we define them inside of C++ so pybind can deal with it
+_exported_symbols.extend([
+    'df',
+    'arrow'
+])
+from _duckdb import (
+    df,
+    arrow
+)
+# NOTE: this section is generated by tools/pythonpkg/scripts/generate_connection_wrapper_methods.py.
+# Do not edit this section manually, your changes will be overwritten!
+# START OF CONNECTION WRAPPER
+from _duckdb import (
+	cursor,
+	register_filesystem,
+	unregister_filesystem,
+	list_filesystems,
+	filesystem_is_registered,
+	create_function,
+	remove_function,
+	sqltype,
+	dtype,
+	type,
+	array_type,
+	list_type,
+	union_type,
+	string_type,
+	enum_type,
+	decimal_type,
+	struct_type,
+	row_type,
+	map_type,
+	duplicate,
+	execute,
+	executemany,
+	close,
+	interrupt,
+	query_progress,
+	fetchone,
+	fetchmany,
+	fetchall,
+	fetchnumpy,
+	fetchdf,
+	fetch_df,
+	df,
+	fetch_df_chunk,
+	pl,
+	fetch_arrow_table,
+	arrow,
+	fetch_record_batch,
+	torch,
+	tf,
+	begin,
+	commit,
+	rollback,
+	checkpoint,
+	append,
+	register,
+	unregister,
+	table,
+	view,
+	values,
+	table_function,
+	read_json,
+	extract_statements,
+	sql,
+	query,
+	from_query,
+	read_csv,
+	from_csv_auto,
+	from_df,
+	from_arrow,
+	from_parquet,
+	read_parquet,
+	from_parquet,
+	read_parquet,
+	get_table_names,
+	install_extension,
+	load_extension,
+	project,
+	distinct,
+	write_csv,
+	aggregate,
+	alias,
+	filter,
+	limit,
+	order,
+	query_df,
+	description,
+	rowcount,
+)
+_exported_symbols.extend([
+	'cursor',
+	'register_filesystem',
+	'unregister_filesystem',
+	'list_filesystems',
+	'filesystem_is_registered',
+	'create_function',
+	'remove_function',
+	'sqltype',
+	'dtype',
+	'type',
+	'array_type',
+	'list_type',
+	'union_type',
+	'string_type',
+	'enum_type',
+	'decimal_type',
+	'struct_type',
+	'row_type',
+	'map_type',
+	'duplicate',
+	'execute',
+	'executemany',
+	'close',
+	'interrupt',
+	'query_progress',
+	'fetchone',
+	'fetchmany',
+	'fetchall',
+	'fetchnumpy',
+	'fetchdf',
+	'fetch_df',
+	'df',
+	'fetch_df_chunk',
+	'pl',
+	'fetch_arrow_table',
+	'arrow',
+	'fetch_record_batch',
+	'torch',
+	'tf',
+	'begin',
+	'commit',
+	'rollback',
+	'checkpoint',
+	'append',
+	'register',
+	'unregister',
+	'table',
+	'view',
+	'values',
+	'table_function',
+	'read_json',
+	'extract_statements',
+	'sql',
+	'query',
+	'from_query',
+	'read_csv',
+	'from_csv_auto',
+	'from_df',
+	'from_arrow',
+	'from_parquet',
+	'read_parquet',
+	'from_parquet',
+	'read_parquet',
+	'get_table_names',
+	'install_extension',
+	'load_extension',
+	'project',
+	'distinct',
+	'write_csv',
+	'aggregate',
+	'alias',
+	'filter',
+	'limit',
+	'order',
+	'query_df',
+	'description',
+	'rowcount',
+])
+# END OF CONNECTION WRAPPER
+# Enums
+from _duckdb import (
+    ANALYZE,
+    DEFAULT,
+    RETURN_NULL,
+    STANDARD,
+    COLUMNS,
+    ROWS
+)
+_exported_symbols.extend([
+    "ANALYZE",
+    "DEFAULT",
+    "RETURN_NULL",
+    "STANDARD"
+])
+# read-only properties
+from _duckdb import (
+    __standard_vector_size__,
+    __interactive__,
+    __jupyter__,
+    __formatted_python_version__,
+    apilevel,
+    comment,
+    identifier,
+    keyword,
+    numeric_const,
+    operator,
+    paramstyle,
+    string_const,
+    threadsafety,
+    token_type,
+    tokenize
+)
+_exported_symbols.extend([
+    "__standard_vector_size__",
+    "__interactive__",
+    "__jupyter__",
+    "__formatted_python_version__",
+    "apilevel",
+    "comment",
+    "identifier",
+    "keyword",
+    "numeric_const",
+    "operator",
+    "paramstyle",
+    "string_const",
+    "threadsafety",
+    "token_type",
+    "tokenize"
+])
+from _duckdb import (
+    connect,
+    default_connection,
+    set_default_connection,
+)
+_exported_symbols.extend([
+    "connect",
+    "default_connection",
+    "set_default_connection",
+])
+# Exceptions
+from _duckdb import (
+    Error,
+    DataError,
+    ConversionException,
+    OutOfRangeException,
+    TypeMismatchException,
+    FatalException,
     IntegrityError,
+    ConstraintException,
     InternalError,
     InternalException,
     InterruptException,
-    InvalidInputException,
-    InvalidTypeException,
-    IOException,
-    LambdaExpression,
-    NotImplementedException,
     NotSupportedError,
+    NotImplementedException,
     OperationalError,
+    ConnectionException,
+    IOException,
+    HTTPException,
     OutOfMemoryException,
-    OutOfRangeException,
-    ParserException,
+    SerializationException,
+    TransactionException,
     PermissionException,
     ProgrammingError,
-    PythonExceptionHandling,
-    RenderMode,
-    SequenceException,
-    SerializationException,
-    SQLExpression,
-    StarExpression,
-    Statement,
-    StatementType,
+    BinderException,
+    CatalogException,
+    InvalidInputException,
+    InvalidTypeException,
+    ParserException,
     SyntaxException,
-    TransactionException,
-    TypeMismatchException,
-    Warning,
-    __formatted_python_version__,
-    __git_revision__,
-    __interactive__,
-    __jupyter__,
-    __standard_vector_size__,
-    _clean_default_connection,
-    aggregate,
-    alias,
-    apilevel,
-    append,
-    array_type,
-    arrow,
-    begin,
-    checkpoint,
-    close,
-    commit,
-    connect,
-    create_function,
-    cursor,
-    decimal_type,
-    default_connection,
-    description,
-    df,
-    distinct,
-    dtype,
-    duplicate,
-    enum_type,
-    execute,
-    executemany,
-    extract_statements,
-    fetch_arrow_table,
-    fetch_df,
-    fetch_df_chunk,
-    fetch_record_batch,
-    fetchall,
-    fetchdf,
-    fetchmany,
-    fetchnumpy,
-    fetchone,
-    filesystem_is_registered,
-    filter,
-    from_arrow,
-    from_csv_auto,
-    from_df,
-    from_parquet,
-    from_query,
-    get_table_names,
-    install_extension,
-    interrupt,
-    limit,
-    list_filesystems,
-    list_type,
-    load_extension,
-    map_type,
-    order,
-    paramstyle,
-    pl,
-    project,
-    query,
-    query_df,
-    query_progress,
-    read_csv,
-    read_json,
-    read_parquet,
-    register,
-    register_filesystem,
-    remove_function,
-    rollback,
-    row_type,
-    rowcount,
-    set_default_connection,
-    sql,
-    sqltype,
-    string_type,
-    struct_type,
-    table,
-    table_function,
-    tf,
-    threadsafety,
-    token_type,
-    tokenize,
-    torch,
-    type,
-    union_type,
-    unregister,
-    unregister_filesystem,
-    values,
-    view,
-    write_csv,
+    SequenceException,
+    Warning
 )
+_exported_symbols.extend([
+    "Error",
+    "DataError",
+    "ConversionException",
+    "OutOfRangeException",
+    "TypeMismatchException",
+    "FatalException",
+    "IntegrityError",
+    "ConstraintException",
+    "InternalError",
+    "InternalException",
+    "InterruptException",
+    "NotSupportedError",
+    "NotImplementedException",
+    "OperationalError",
+    "ConnectionException",
+    "IOException",
+    "HTTPException",
+    "OutOfMemoryException",
+    "SerializationException",
+    "TransactionException",
+    "PermissionException",
+    "ProgrammingError",
+    "BinderException",
+    "CatalogException",
+    "InvalidInputException",
+    "InvalidTypeException",
+    "ParserException",
+    "SyntaxException",
+    "SequenceException",
+    "Warning"
+])
-from duckdb._dbapi_type_object import (
-    BINARY,
-    DATETIME,
-    NUMBER,
-    ROWID,
-    STRING,
-    DBAPITypeObject,
-)
-from duckdb._version import (
-    __duckdb_version__,
-    __version__,
-    version,
-)
+# Value
 from duckdb.value.constant import (
+    Value,
+    NullValue,
+    BooleanValue,
+    UnsignedBinaryValue,
+    UnsignedShortValue,
+    UnsignedIntegerValue,
+    UnsignedLongValue,
     BinaryValue,
+    ShortValue,
+    IntegerValue,
+    LongValue,
+    HugeIntegerValue,
+    FloatValue,
+    DoubleValue,
+    DecimalValue,
+    StringValue,
+    UUIDValue,
     BitValue,
     BlobValue,
-    BooleanValue,
     DateValue,
-    DecimalValue,
-    DoubleValue,
-    FloatValue,
-    HugeIntegerValue,
-    IntegerValue,
     IntervalValue,
-    ListValue,
-    LongValue,
-    MapValue,
-    NullValue,
-    ShortValue,
-    StringValue,
-    StructValue,
+    TimestampValue,
+    TimestampSecondValue,
     TimestampMilisecondValue,
     TimestampNanosecondValue,
-    TimestampSecondValue,
     TimestampTimeZoneValue,
-    TimestampValue,
-    TimeTimeZoneValue,
     TimeValue,
-    UnionType,
-    UnsignedBinaryValue,
-    UnsignedHugeIntegerValue,
-    UnsignedIntegerValue,
-    UnsignedLongValue,
-    UnsignedShortValue,
-    UUIDValue,
-    Value,
+    TimeTimeZoneValue,
 )
-__all__: list[str] = [
+_exported_symbols.extend([
+    "Value",
+    "NullValue",
+    "BooleanValue",
+    "UnsignedBinaryValue",
+    "UnsignedShortValue",
+    "UnsignedIntegerValue",
+    "UnsignedLongValue",
     "BinaryValue",
-    "BinderException",
+    "ShortValue",
+    "IntegerValue",
+    "LongValue",
+    "HugeIntegerValue",
+    "FloatValue",
+    "DoubleValue",
+    "DecimalValue",
+    "StringValue",
+    "UUIDValue",
     "BitValue",
     "BlobValue",
-    "BooleanValue",
-    "CSVLineTerminator",
-    "CaseExpression",
-    "CatalogException",
-    "CoalesceOperator",
-    "ColumnExpression",
-    "ConnectionException",
-    "ConstantExpression",
-    "ConstraintException",
-    "ConversionException",
-    "DataError",
-    "DatabaseError",
     "DateValue",
-    "DecimalValue",
-    "DefaultExpression",
-    "DependencyException",
-    "DoubleValue",
-    "DuckDBPyConnection",
-    "DuckDBPyRelation",
-    "Error",
-    "ExpectedResultType",
-    "ExplainType",
-    "Expression",
-    "FatalException",
-    "FloatValue",
-    "FunctionExpression",
-    "HTTPException",
-    "HugeIntegerValue",
-    "IOException",
-    "IntegerValue",
-    "IntegrityError",
-    "InternalError",
-    "InternalException",
-    "InterruptException",
     "IntervalValue",
-    "InvalidInputException",
-    "InvalidTypeException",
-    "LambdaExpression",
-    "ListValue",
-    "LongValue",
-    "MapValue",
-    "NotImplementedException",
-    "NotSupportedError",
-    "NullValue",
-    "OperationalError",
-    "OutOfMemoryException",
-    "OutOfRangeException",
-    "ParserException",
-    "PermissionException",
-    "ProgrammingError",
-    "PythonExceptionHandling",
-    "RenderMode",
-    "SQLExpression",
-    "SequenceException",
-    "SerializationException",
-    "ShortValue",
-    "StarExpression",
-    "Statement",
-    "StatementType",
-    "StringValue",
-    "StructValue",
-    "SyntaxException",
-    "TimeTimeZoneValue",
-    "TimeValue",
+    "TimestampValue",
+    "TimestampSecondValue",
     "TimestampMilisecondValue",
     "TimestampNanosecondValue",
-    "TimestampSecondValue",
     "TimestampTimeZoneValue",
-    "TimestampValue",
-    "TransactionException",
-    "TypeMismatchException",
-    "UUIDValue",
-    "UnionType",
-    "UnsignedBinaryValue",
-    "UnsignedHugeIntegerValue",
-    "UnsignedIntegerValue",
-    "UnsignedLongValue",
-    "UnsignedShortValue",
-    "Value",
-    "Warning",
-    "__formatted_python_version__",
-    "__git_revision__",
-    "__interactive__",
-    "__jupyter__",
-    "__standard_vector_size__",
-    "__version__",
-    "_clean_default_connection",
-    "aggregate",
-    "alias",
-    "apilevel",
-    "append",
-    "array_type",
-    "arrow",
-    "begin",
-    "checkpoint",
-    "close",
-    "commit",
-    "connect",
-    "create_function",
-    "cursor",
-    "decimal_type",
-    "default_connection",
-    "description",
-    "df",
-    "distinct",
-    "dtype",
-    "duplicate",
-    "enum_type",
-    "execute",
-    "executemany",
-    "extract_statements",
-    "fetch_arrow_table",
-    "fetch_df",
-    "fetch_df_chunk",
-    "fetch_record_batch",
-    "fetchall",
-    "fetchdf",
-    "fetchmany",
-    "fetchnumpy",
-    "fetchone",
-    "filesystem_is_registered",
-    "filter",
-    "from_arrow",
-    "from_csv_auto",
-    "from_df",
-    "from_parquet",
-    "from_query",
-    "get_table_names",
-    "install_extension",
-    "interrupt",
-    "limit",
-    "list_filesystems",
-    "list_type",
-    "load_extension",
-    "map_type",
-    "order",
-    "paramstyle",
-    "paramstyle",
-    "pl",
-    "project",
-    "query",
-    "query_df",
-    "query_progress",
-    "read_csv",
-    "read_json",
-    "read_parquet",
-    "register",
-    "register_filesystem",
-    "remove_function",
-    "rollback",
-    "row_type",
-    "rowcount",
-    "set_default_connection",
-    "sql",
-    "sqltype",
-    "string_type",
-    "struct_type",
-    "table",
-    "table_function",
-    "tf",
-    "threadsafety",
-    "threadsafety",
-    "token_type",
-    "tokenize",
-    "torch",
-    "type",
-    "union_type",
-    "unregister",
-    "unregister_filesystem",
-    "values",
-    "view",
-    "write_csv",
-]
+    "TimeValue",
+    "TimeTimeZoneValue",
+])
+__all__ = _exported_symbols