duckdb 1.5.0.dev53__cp314-cp314-manylinux_2_26_x86_64.manylinux_2_28_x86_64.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.
- _duckdb-stubs/__init__.pyi +1443 -0
- _duckdb-stubs/_func.pyi +46 -0
- _duckdb-stubs/_sqltypes.pyi +75 -0
- _duckdb.cpython-314-x86_64-linux-gnu.so +0 -0
- adbc_driver_duckdb/__init__.py +50 -0
- adbc_driver_duckdb/dbapi.py +115 -0
- duckdb/__init__.py +381 -0
- duckdb/_dbapi_type_object.py +231 -0
- duckdb/_version.py +22 -0
- duckdb/bytes_io_wrapper.py +69 -0
- duckdb/experimental/__init__.py +3 -0
- duckdb/experimental/spark/LICENSE +260 -0
- duckdb/experimental/spark/__init__.py +6 -0
- duckdb/experimental/spark/_globals.py +77 -0
- duckdb/experimental/spark/_typing.py +46 -0
- duckdb/experimental/spark/conf.py +46 -0
- duckdb/experimental/spark/context.py +180 -0
- duckdb/experimental/spark/errors/__init__.py +70 -0
- duckdb/experimental/spark/errors/error_classes.py +918 -0
- duckdb/experimental/spark/errors/exceptions/__init__.py +16 -0
- duckdb/experimental/spark/errors/exceptions/base.py +168 -0
- duckdb/experimental/spark/errors/utils.py +111 -0
- duckdb/experimental/spark/exception.py +18 -0
- duckdb/experimental/spark/sql/__init__.py +7 -0
- duckdb/experimental/spark/sql/_typing.py +86 -0
- duckdb/experimental/spark/sql/catalog.py +79 -0
- duckdb/experimental/spark/sql/column.py +361 -0
- duckdb/experimental/spark/sql/conf.py +24 -0
- duckdb/experimental/spark/sql/dataframe.py +1389 -0
- duckdb/experimental/spark/sql/functions.py +6195 -0
- duckdb/experimental/spark/sql/group.py +424 -0
- duckdb/experimental/spark/sql/readwriter.py +435 -0
- duckdb/experimental/spark/sql/session.py +297 -0
- duckdb/experimental/spark/sql/streaming.py +36 -0
- duckdb/experimental/spark/sql/type_utils.py +107 -0
- duckdb/experimental/spark/sql/types.py +1239 -0
- duckdb/experimental/spark/sql/udf.py +37 -0
- duckdb/filesystem.py +33 -0
- duckdb/func/__init__.py +3 -0
- duckdb/functional/__init__.py +13 -0
- duckdb/polars_io.py +284 -0
- duckdb/py.typed +0 -0
- duckdb/query_graph/__main__.py +358 -0
- duckdb/sqltypes/__init__.py +63 -0
- duckdb/typing/__init__.py +71 -0
- duckdb/udf.py +24 -0
- duckdb/value/__init__.py +1 -0
- duckdb/value/constant/__init__.py +270 -0
- duckdb-1.5.0.dev53.dist-info/METADATA +87 -0
- duckdb-1.5.0.dev53.dist-info/RECORD +52 -0
- duckdb-1.5.0.dev53.dist-info/WHEEL +6 -0
- duckdb-1.5.0.dev53.dist-info/licenses/LICENSE +7 -0
|
@@ -0,0 +1,231 @@
|
|
|
1
|
+
"""DuckDB DB API 2.0 Type Objects Module.
|
|
2
|
+
|
|
3
|
+
This module provides DB API 2.0 compliant type objects for DuckDB, allowing applications
|
|
4
|
+
to check column types returned by queries against standard database API categories.
|
|
5
|
+
|
|
6
|
+
Example:
|
|
7
|
+
>>> import duckdb
|
|
8
|
+
>>>
|
|
9
|
+
>>> conn = duckdb.connect()
|
|
10
|
+
>>> cursor = conn.cursor()
|
|
11
|
+
>>> cursor.execute("SELECT 'hello' as text_col, 42 as num_col, CURRENT_DATE as date_col")
|
|
12
|
+
>>>
|
|
13
|
+
>>> # Check column types using DB API type objects
|
|
14
|
+
>>> for i, desc in enumerate(cursor.description):
|
|
15
|
+
>>> col_name, col_type = desc[0], desc[1]
|
|
16
|
+
>>> if col_type == duckdb.STRING:
|
|
17
|
+
>>> print(f"{col_name} is a string type")
|
|
18
|
+
>>> elif col_type == duckdb.NUMBER:
|
|
19
|
+
>>> print(f"{col_name} is a numeric type")
|
|
20
|
+
>>> elif col_type == duckdb.DATETIME:
|
|
21
|
+
>>> print(f"{col_name} is a date/time type")
|
|
22
|
+
|
|
23
|
+
See Also:
|
|
24
|
+
- PEP 249: https://peps.python.org/pep-0249/
|
|
25
|
+
- DuckDB Type System: https://duckdb.org/docs/sql/data_types/overview
|
|
26
|
+
"""
|
|
27
|
+
|
|
28
|
+
from duckdb import sqltypes
|
|
29
|
+
|
|
30
|
+
|
|
31
|
+
class DBAPITypeObject:
|
|
32
|
+
"""DB API 2.0 type object for categorizing database column types.
|
|
33
|
+
|
|
34
|
+
This class implements the type objects defined in PEP 249 (DB API 2.0).
|
|
35
|
+
It allows checking whether a specific DuckDB type belongs to a broader
|
|
36
|
+
category like STRING, NUMBER, DATETIME, etc.
|
|
37
|
+
|
|
38
|
+
The type object supports equality comparison with DuckDBPyType instances,
|
|
39
|
+
returning True if the type belongs to this category.
|
|
40
|
+
|
|
41
|
+
Args:
|
|
42
|
+
types: A list of DuckDBPyType instances that belong to this type category.
|
|
43
|
+
|
|
44
|
+
Example:
|
|
45
|
+
>>> string_types = DBAPITypeObject([sqltypes.VARCHAR, sqltypes.CHAR])
|
|
46
|
+
>>> result = sqltypes.VARCHAR == string_types # True
|
|
47
|
+
>>> result = sqltypes.INTEGER == string_types # False
|
|
48
|
+
|
|
49
|
+
Note:
|
|
50
|
+
This follows the DB API 2.0 specification where type objects are compared
|
|
51
|
+
using equality operators rather than isinstance() checks.
|
|
52
|
+
"""
|
|
53
|
+
|
|
54
|
+
def __init__(self, types: list[sqltypes.DuckDBPyType]) -> None:
|
|
55
|
+
"""Initialize a DB API type object.
|
|
56
|
+
|
|
57
|
+
Args:
|
|
58
|
+
types: List of DuckDB types that belong to this category.
|
|
59
|
+
"""
|
|
60
|
+
self.types = types
|
|
61
|
+
|
|
62
|
+
def __eq__(self, other: object) -> bool:
|
|
63
|
+
"""Check if a DuckDB type belongs to this type category.
|
|
64
|
+
|
|
65
|
+
This method implements the DB API 2.0 type checking mechanism.
|
|
66
|
+
It returns True if the other object is a DuckDBPyType that
|
|
67
|
+
is contained in this type category.
|
|
68
|
+
|
|
69
|
+
Args:
|
|
70
|
+
other: The object to compare, typically a DuckDBPyType instance.
|
|
71
|
+
|
|
72
|
+
Returns:
|
|
73
|
+
True if other is a DuckDBPyType in this category, False otherwise.
|
|
74
|
+
|
|
75
|
+
Example:
|
|
76
|
+
>>> NUMBER == sqltypes.INTEGER # True
|
|
77
|
+
>>> NUMBER == sqltypes.VARCHAR # False
|
|
78
|
+
"""
|
|
79
|
+
if isinstance(other, sqltypes.DuckDBPyType):
|
|
80
|
+
return other in self.types
|
|
81
|
+
return False
|
|
82
|
+
|
|
83
|
+
def __repr__(self) -> str:
|
|
84
|
+
"""Return a string representation of this type object.
|
|
85
|
+
|
|
86
|
+
Returns:
|
|
87
|
+
A string showing the type object and its contained DuckDB types.
|
|
88
|
+
|
|
89
|
+
Example:
|
|
90
|
+
>>> repr(STRING)
|
|
91
|
+
'<DBAPITypeObject [VARCHAR]>'
|
|
92
|
+
"""
|
|
93
|
+
return f"<DBAPITypeObject [{','.join(str(x) for x in self.types)}]>"
|
|
94
|
+
|
|
95
|
+
|
|
96
|
+
# Define the standard DB API 2.0 type objects for DuckDB
|
|
97
|
+
|
|
98
|
+
STRING = DBAPITypeObject([sqltypes.VARCHAR])
|
|
99
|
+
"""
|
|
100
|
+
STRING type object for text-based database columns.
|
|
101
|
+
|
|
102
|
+
This type object represents all string/text types in DuckDB. Currently includes:
|
|
103
|
+
- VARCHAR: Variable-length character strings
|
|
104
|
+
|
|
105
|
+
Use this to check if a column contains textual data that should be handled
|
|
106
|
+
as Python strings.
|
|
107
|
+
|
|
108
|
+
DB API 2.0 Reference:
|
|
109
|
+
https://peps.python.org/pep-0249/#string
|
|
110
|
+
|
|
111
|
+
Example:
|
|
112
|
+
>>> cursor.description[0][1] == STRING # Check if first column is text
|
|
113
|
+
"""
|
|
114
|
+
|
|
115
|
+
NUMBER = DBAPITypeObject(
|
|
116
|
+
[
|
|
117
|
+
sqltypes.TINYINT,
|
|
118
|
+
sqltypes.UTINYINT,
|
|
119
|
+
sqltypes.SMALLINT,
|
|
120
|
+
sqltypes.USMALLINT,
|
|
121
|
+
sqltypes.INTEGER,
|
|
122
|
+
sqltypes.UINTEGER,
|
|
123
|
+
sqltypes.BIGINT,
|
|
124
|
+
sqltypes.UBIGINT,
|
|
125
|
+
sqltypes.HUGEINT,
|
|
126
|
+
sqltypes.UHUGEINT,
|
|
127
|
+
sqltypes.DuckDBPyType("BIGNUM"),
|
|
128
|
+
sqltypes.DuckDBPyType("DECIMAL"),
|
|
129
|
+
sqltypes.FLOAT,
|
|
130
|
+
sqltypes.DOUBLE,
|
|
131
|
+
]
|
|
132
|
+
)
|
|
133
|
+
"""
|
|
134
|
+
NUMBER type object for numeric database columns.
|
|
135
|
+
|
|
136
|
+
This type object represents all numeric types in DuckDB, including:
|
|
137
|
+
|
|
138
|
+
Integer Types:
|
|
139
|
+
- TINYINT, UTINYINT: 8-bit signed/unsigned integers
|
|
140
|
+
- SMALLINT, USMALLINT: 16-bit signed/unsigned integers
|
|
141
|
+
- INTEGER, UINTEGER: 32-bit signed/unsigned integers
|
|
142
|
+
- BIGINT, UBIGINT: 64-bit signed/unsigned integers
|
|
143
|
+
- HUGEINT, UHUGEINT: 128-bit signed/unsigned integers
|
|
144
|
+
|
|
145
|
+
Decimal Types:
|
|
146
|
+
- BIGNUM: Arbitrary precision integers
|
|
147
|
+
- DECIMAL: Fixed-point decimal numbers
|
|
148
|
+
|
|
149
|
+
Floating Point Types:
|
|
150
|
+
- FLOAT: 32-bit floating point
|
|
151
|
+
- DOUBLE: 64-bit floating point
|
|
152
|
+
|
|
153
|
+
Use this to check if a column contains numeric data that should be handled
|
|
154
|
+
as Python int, float, or Decimal objects.
|
|
155
|
+
|
|
156
|
+
DB API 2.0 Reference:
|
|
157
|
+
https://peps.python.org/pep-0249/#number
|
|
158
|
+
|
|
159
|
+
Example:
|
|
160
|
+
>>> cursor.description[1][1] == NUMBER # Check if second column is numeric
|
|
161
|
+
"""
|
|
162
|
+
|
|
163
|
+
DATETIME = DBAPITypeObject(
|
|
164
|
+
[
|
|
165
|
+
sqltypes.DATE,
|
|
166
|
+
sqltypes.TIME,
|
|
167
|
+
sqltypes.TIME_TZ,
|
|
168
|
+
sqltypes.TIMESTAMP,
|
|
169
|
+
sqltypes.TIMESTAMP_TZ,
|
|
170
|
+
sqltypes.TIMESTAMP_NS,
|
|
171
|
+
sqltypes.TIMESTAMP_MS,
|
|
172
|
+
sqltypes.TIMESTAMP_S,
|
|
173
|
+
]
|
|
174
|
+
)
|
|
175
|
+
"""
|
|
176
|
+
DATETIME type object for date and time database columns.
|
|
177
|
+
|
|
178
|
+
This type object represents all date/time types in DuckDB, including:
|
|
179
|
+
|
|
180
|
+
Date Types:
|
|
181
|
+
- DATE: Calendar dates (year, month, day)
|
|
182
|
+
|
|
183
|
+
Time Types:
|
|
184
|
+
- TIME: Time of day without timezone
|
|
185
|
+
- TIME_TZ: Time of day with timezone
|
|
186
|
+
|
|
187
|
+
Timestamp Types:
|
|
188
|
+
- TIMESTAMP: Date and time without timezone (microsecond precision)
|
|
189
|
+
- TIMESTAMP_TZ: Date and time with timezone
|
|
190
|
+
- TIMESTAMP_NS: Nanosecond precision timestamps
|
|
191
|
+
- TIMESTAMP_MS: Millisecond precision timestamps
|
|
192
|
+
- TIMESTAMP_S: Second precision timestamps
|
|
193
|
+
|
|
194
|
+
Use this to check if a column contains temporal data that should be handled
|
|
195
|
+
as Python datetime, date, or time objects.
|
|
196
|
+
|
|
197
|
+
DB API 2.0 Reference:
|
|
198
|
+
https://peps.python.org/pep-0249/#datetime
|
|
199
|
+
|
|
200
|
+
Example:
|
|
201
|
+
>>> cursor.description[2][1] == DATETIME # Check if third column is date/time
|
|
202
|
+
"""
|
|
203
|
+
|
|
204
|
+
BINARY = DBAPITypeObject([sqltypes.BLOB])
|
|
205
|
+
"""
|
|
206
|
+
BINARY type object for binary data database columns.
|
|
207
|
+
|
|
208
|
+
This type object represents binary data types in DuckDB:
|
|
209
|
+
- BLOB: Binary Large Objects for storing arbitrary binary data
|
|
210
|
+
|
|
211
|
+
Use this to check if a column contains binary data that should be handled
|
|
212
|
+
as Python bytes objects.
|
|
213
|
+
|
|
214
|
+
DB API 2.0 Reference:
|
|
215
|
+
https://peps.python.org/pep-0249/#binary
|
|
216
|
+
|
|
217
|
+
Example:
|
|
218
|
+
>>> cursor.description[3][1] == BINARY # Check if fourth column is binary
|
|
219
|
+
"""
|
|
220
|
+
|
|
221
|
+
ROWID = None
|
|
222
|
+
"""
|
|
223
|
+
ROWID type object for row identifier columns.
|
|
224
|
+
|
|
225
|
+
DB API 2.0 Reference:
|
|
226
|
+
https://peps.python.org/pep-0249/#rowid
|
|
227
|
+
|
|
228
|
+
Note:
|
|
229
|
+
This will always be None for DuckDB connections. Applications should not
|
|
230
|
+
rely on ROWID functionality when using DuckDB.
|
|
231
|
+
"""
|
duckdb/_version.py
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
1
|
+
# ----------------------------------------------------------------------
|
|
2
|
+
# Version API
|
|
3
|
+
#
|
|
4
|
+
# We provide three symbols:
|
|
5
|
+
# - duckdb.__version__: The version of this package
|
|
6
|
+
# - duckdb.__duckdb_version__: The version of duckdb that is bundled
|
|
7
|
+
# - duckdb.version(): A human-readable version string containing both of the above
|
|
8
|
+
# ----------------------------------------------------------------------
|
|
9
|
+
from importlib.metadata import version as _dist_version
|
|
10
|
+
|
|
11
|
+
import _duckdb
|
|
12
|
+
|
|
13
|
+
__version__: str = _dist_version("duckdb")
|
|
14
|
+
"""Version of the DuckDB Python Package."""
|
|
15
|
+
|
|
16
|
+
__duckdb_version__: str = _duckdb.__version__
|
|
17
|
+
"""Version of DuckDB that is bundled."""
|
|
18
|
+
|
|
19
|
+
|
|
20
|
+
def version() -> str:
|
|
21
|
+
"""Human-friendly formatted version string of both the distribution package and the bundled DuckDB engine."""
|
|
22
|
+
return f"{__version__} (with duckdb {_duckdb.__version__})"
|
|
@@ -0,0 +1,69 @@
|
|
|
1
|
+
"""StringIO buffer wrapper.
|
|
2
|
+
|
|
3
|
+
BSD 3-Clause License
|
|
4
|
+
|
|
5
|
+
Copyright (c) 2008-2011, AQR Capital Management, LLC, Lambda Foundry, Inc. and PyData Development Team
|
|
6
|
+
All rights reserved.
|
|
7
|
+
|
|
8
|
+
Copyright (c) 2011-2022, Open source contributors.
|
|
9
|
+
|
|
10
|
+
Redistribution and use in source and binary forms, with or without
|
|
11
|
+
modification, are permitted provided that the following conditions are met:
|
|
12
|
+
|
|
13
|
+
* Redistributions of source code must retain the above copyright notice, this
|
|
14
|
+
list of conditions and the following disclaimer.
|
|
15
|
+
|
|
16
|
+
* Redistributions in binary form must reproduce the above copyright notice,
|
|
17
|
+
this list of conditions and the following disclaimer in the documentation
|
|
18
|
+
and/or other materials provided with the distribution.
|
|
19
|
+
|
|
20
|
+
* Neither the name of the copyright holder nor the names of its
|
|
21
|
+
contributors may be used to endorse or promote products derived from
|
|
22
|
+
this software without specific prior written permission.
|
|
23
|
+
|
|
24
|
+
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
|
25
|
+
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
26
|
+
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
|
|
27
|
+
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
|
|
28
|
+
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
|
29
|
+
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
|
|
30
|
+
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
|
|
31
|
+
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
|
|
32
|
+
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
|
33
|
+
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
|
34
|
+
"""
|
|
35
|
+
|
|
36
|
+
from io import StringIO, TextIOBase
|
|
37
|
+
from typing import Any, Union
|
|
38
|
+
|
|
39
|
+
|
|
40
|
+
class BytesIOWrapper:
|
|
41
|
+
"""Wrapper that wraps a StringIO buffer and reads bytes from it.
|
|
42
|
+
|
|
43
|
+
Created for compat with pyarrow read_csv.
|
|
44
|
+
"""
|
|
45
|
+
|
|
46
|
+
def __init__(self, buffer: Union[StringIO, TextIOBase], encoding: str = "utf-8") -> None: # noqa: D107
|
|
47
|
+
self.buffer = buffer
|
|
48
|
+
self.encoding = encoding
|
|
49
|
+
# Because a character can be represented by more than 1 byte,
|
|
50
|
+
# it is possible that reading will produce more bytes than n
|
|
51
|
+
# We store the extra bytes in this overflow variable, and append the
|
|
52
|
+
# overflow to the front of the bytestring the next time reading is performed
|
|
53
|
+
self.overflow = b""
|
|
54
|
+
|
|
55
|
+
def __getattr__(self, attr: str) -> Any: # noqa: D105, ANN401
|
|
56
|
+
return getattr(self.buffer, attr)
|
|
57
|
+
|
|
58
|
+
def read(self, n: Union[int, None] = -1) -> bytes: # noqa: D102
|
|
59
|
+
assert self.buffer is not None
|
|
60
|
+
bytestring = self.buffer.read(n).encode(self.encoding)
|
|
61
|
+
# When n=-1/n greater than remaining bytes: Read entire file/rest of file
|
|
62
|
+
combined_bytestring = self.overflow + bytestring
|
|
63
|
+
if n is None or n < 0 or n >= len(combined_bytestring):
|
|
64
|
+
self.overflow = b""
|
|
65
|
+
return combined_bytestring
|
|
66
|
+
else:
|
|
67
|
+
to_return = combined_bytestring[:n]
|
|
68
|
+
self.overflow = combined_bytestring[n:]
|
|
69
|
+
return to_return
|
|
@@ -0,0 +1,260 @@
|
|
|
1
|
+
Apache License
|
|
2
|
+
Version 2.0, January 2004
|
|
3
|
+
http://www.apache.org/licenses/
|
|
4
|
+
|
|
5
|
+
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
|
6
|
+
|
|
7
|
+
1. Definitions.
|
|
8
|
+
|
|
9
|
+
"License" shall mean the terms and conditions for use, reproduction,
|
|
10
|
+
and distribution as defined by Sections 1 through 9 of this document.
|
|
11
|
+
|
|
12
|
+
"Licensor" shall mean the copyright owner or entity authorized by
|
|
13
|
+
the copyright owner that is granting the License.
|
|
14
|
+
|
|
15
|
+
"Legal Entity" shall mean the union of the acting entity and all
|
|
16
|
+
other entities that control, are controlled by, or are under common
|
|
17
|
+
control with that entity. For the purposes of this definition,
|
|
18
|
+
"control" means (i) the power, direct or indirect, to cause the
|
|
19
|
+
direction or management of such entity, whether by contract or
|
|
20
|
+
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
|
21
|
+
outstanding shares, or (iii) beneficial ownership of such entity.
|
|
22
|
+
|
|
23
|
+
"You" (or "Your") shall mean an individual or Legal Entity
|
|
24
|
+
exercising permissions granted by this License.
|
|
25
|
+
|
|
26
|
+
"Source" form shall mean the preferred form for making modifications,
|
|
27
|
+
including but not limited to software source code, documentation
|
|
28
|
+
source, and configuration files.
|
|
29
|
+
|
|
30
|
+
"Object" form shall mean any form resulting from mechanical
|
|
31
|
+
transformation or translation of a Source form, including but
|
|
32
|
+
not limited to compiled object code, generated documentation,
|
|
33
|
+
and conversions to other media types.
|
|
34
|
+
|
|
35
|
+
"Work" shall mean the work of authorship, whether in Source or
|
|
36
|
+
Object form, made available under the License, as indicated by a
|
|
37
|
+
copyright notice that is included in or attached to the work
|
|
38
|
+
(an example is provided in the Appendix below).
|
|
39
|
+
|
|
40
|
+
"Derivative Works" shall mean any work, whether in Source or Object
|
|
41
|
+
form, that is based on (or derived from) the Work and for which the
|
|
42
|
+
editorial revisions, annotations, elaborations, or other modifications
|
|
43
|
+
represent, as a whole, an original work of authorship. For the purposes
|
|
44
|
+
of this License, Derivative Works shall not include works that remain
|
|
45
|
+
separable from, or merely link (or bind by name) to the interfaces of,
|
|
46
|
+
the Work and Derivative Works thereof.
|
|
47
|
+
|
|
48
|
+
"Contribution" shall mean any work of authorship, including
|
|
49
|
+
the original version of the Work and any modifications or additions
|
|
50
|
+
to that Work or Derivative Works thereof, that is intentionally
|
|
51
|
+
submitted to Licensor for inclusion in the Work by the copyright owner
|
|
52
|
+
or by an individual or Legal Entity authorized to submit on behalf of
|
|
53
|
+
the copyright owner. For the purposes of this definition, "submitted"
|
|
54
|
+
means any form of electronic, verbal, or written communication sent
|
|
55
|
+
to the Licensor or its representatives, including but not limited to
|
|
56
|
+
communication on electronic mailing lists, source code control systems,
|
|
57
|
+
and issue tracking systems that are managed by, or on behalf of, the
|
|
58
|
+
Licensor for the purpose of discussing and improving the Work, but
|
|
59
|
+
excluding communication that is conspicuously marked or otherwise
|
|
60
|
+
designated in writing by the copyright owner as "Not a Contribution."
|
|
61
|
+
|
|
62
|
+
"Contributor" shall mean Licensor and any individual or Legal Entity
|
|
63
|
+
on behalf of whom a Contribution has been received by Licensor and
|
|
64
|
+
subsequently incorporated within the Work.
|
|
65
|
+
|
|
66
|
+
2. Grant of Copyright License. Subject to the terms and conditions of
|
|
67
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
68
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
69
|
+
copyright license to reproduce, prepare Derivative Works of,
|
|
70
|
+
publicly display, publicly perform, sublicense, and distribute the
|
|
71
|
+
Work and such Derivative Works in Source or Object form.
|
|
72
|
+
|
|
73
|
+
3. Grant of Patent License. Subject to the terms and conditions of
|
|
74
|
+
this License, each Contributor hereby grants to You a perpetual,
|
|
75
|
+
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
|
76
|
+
(except as stated in this section) patent license to make, have made,
|
|
77
|
+
use, offer to sell, sell, import, and otherwise transfer the Work,
|
|
78
|
+
where such license applies only to those patent claims licensable
|
|
79
|
+
by such Contributor that are necessarily infringed by their
|
|
80
|
+
Contribution(s) alone or by combination of their Contribution(s)
|
|
81
|
+
with the Work to which such Contribution(s) was submitted. If You
|
|
82
|
+
institute patent litigation against any entity (including a
|
|
83
|
+
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
|
84
|
+
or a Contribution incorporated within the Work constitutes direct
|
|
85
|
+
or contributory patent infringement, then any patent licenses
|
|
86
|
+
granted to You under this License for that Work shall terminate
|
|
87
|
+
as of the date such litigation is filed.
|
|
88
|
+
|
|
89
|
+
4. Redistribution. You may reproduce and distribute copies of the
|
|
90
|
+
Work or Derivative Works thereof in any medium, with or without
|
|
91
|
+
modifications, and in Source or Object form, provided that You
|
|
92
|
+
meet the following conditions:
|
|
93
|
+
|
|
94
|
+
(a) You must give any other recipients of the Work or
|
|
95
|
+
Derivative Works a copy of this License; and
|
|
96
|
+
|
|
97
|
+
(b) You must cause any modified files to carry prominent notices
|
|
98
|
+
stating that You changed the files; and
|
|
99
|
+
|
|
100
|
+
(c) You must retain, in the Source form of any Derivative Works
|
|
101
|
+
that You distribute, all copyright, patent, trademark, and
|
|
102
|
+
attribution notices from the Source form of the Work,
|
|
103
|
+
excluding those notices that do not pertain to any part of
|
|
104
|
+
the Derivative Works; and
|
|
105
|
+
|
|
106
|
+
(d) If the Work includes a "NOTICE" text file as part of its
|
|
107
|
+
distribution, then any Derivative Works that You distribute must
|
|
108
|
+
include a readable copy of the attribution notices contained
|
|
109
|
+
within such NOTICE file, excluding those notices that do not
|
|
110
|
+
pertain to any part of the Derivative Works, in at least one
|
|
111
|
+
of the following places: within a NOTICE text file distributed
|
|
112
|
+
as part of the Derivative Works; within the Source form or
|
|
113
|
+
documentation, if provided along with the Derivative Works; or,
|
|
114
|
+
within a display generated by the Derivative Works, if and
|
|
115
|
+
wherever such third-party notices normally appear. The contents
|
|
116
|
+
of the NOTICE file are for informational purposes only and
|
|
117
|
+
do not modify the License. You may add Your own attribution
|
|
118
|
+
notices within Derivative Works that You distribute, alongside
|
|
119
|
+
or as an addendum to the NOTICE text from the Work, provided
|
|
120
|
+
that such additional attribution notices cannot be construed
|
|
121
|
+
as modifying the License.
|
|
122
|
+
|
|
123
|
+
You may add Your own copyright statement to Your modifications and
|
|
124
|
+
may provide additional or different license terms and conditions
|
|
125
|
+
for use, reproduction, or distribution of Your modifications, or
|
|
126
|
+
for any such Derivative Works as a whole, provided Your use,
|
|
127
|
+
reproduction, and distribution of the Work otherwise complies with
|
|
128
|
+
the conditions stated in this License.
|
|
129
|
+
|
|
130
|
+
5. Submission of Contributions. Unless You explicitly state otherwise,
|
|
131
|
+
any Contribution intentionally submitted for inclusion in the Work
|
|
132
|
+
by You to the Licensor shall be under the terms and conditions of
|
|
133
|
+
this License, without any additional terms or conditions.
|
|
134
|
+
Notwithstanding the above, nothing herein shall supersede or modify
|
|
135
|
+
the terms of any separate license agreement you may have executed
|
|
136
|
+
with Licensor regarding such Contributions.
|
|
137
|
+
|
|
138
|
+
6. Trademarks. This License does not grant permission to use the trade
|
|
139
|
+
names, trademarks, service marks, or product names of the Licensor,
|
|
140
|
+
except as required for reasonable and customary use in describing the
|
|
141
|
+
origin of the Work and reproducing the content of the NOTICE file.
|
|
142
|
+
|
|
143
|
+
7. Disclaimer of Warranty. Unless required by applicable law or
|
|
144
|
+
agreed to in writing, Licensor provides the Work (and each
|
|
145
|
+
Contributor provides its Contributions) on an "AS IS" BASIS,
|
|
146
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
|
147
|
+
implied, including, without limitation, any warranties or conditions
|
|
148
|
+
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
|
149
|
+
PARTICULAR PURPOSE. You are solely responsible for determining the
|
|
150
|
+
appropriateness of using or redistributing the Work and assume any
|
|
151
|
+
risks associated with Your exercise of permissions under this License.
|
|
152
|
+
|
|
153
|
+
8. Limitation of Liability. In no event and under no legal theory,
|
|
154
|
+
whether in tort (including negligence), contract, or otherwise,
|
|
155
|
+
unless required by applicable law (such as deliberate and grossly
|
|
156
|
+
negligent acts) or agreed to in writing, shall any Contributor be
|
|
157
|
+
liable to You for damages, including any direct, indirect, special,
|
|
158
|
+
incidental, or consequential damages of any character arising as a
|
|
159
|
+
result of this License or out of the use or inability to use the
|
|
160
|
+
Work (including but not limited to damages for loss of goodwill,
|
|
161
|
+
work stoppage, computer failure or malfunction, or any and all
|
|
162
|
+
other commercial damages or losses), even if such Contributor
|
|
163
|
+
has been advised of the possibility of such damages.
|
|
164
|
+
|
|
165
|
+
9. Accepting Warranty or Additional Liability. While redistributing
|
|
166
|
+
the Work or Derivative Works thereof, You may choose to offer,
|
|
167
|
+
and charge a fee for, acceptance of support, warranty, indemnity,
|
|
168
|
+
or other liability obligations and/or rights consistent with this
|
|
169
|
+
License. However, in accepting such obligations, You may act only
|
|
170
|
+
on Your own behalf and on Your sole responsibility, not on behalf
|
|
171
|
+
of any other Contributor, and only if You agree to indemnify,
|
|
172
|
+
defend, and hold each Contributor harmless for any liability
|
|
173
|
+
incurred by, or claims asserted against, such Contributor by reason
|
|
174
|
+
of your accepting any such warranty or additional liability.
|
|
175
|
+
|
|
176
|
+
END OF TERMS AND CONDITIONS
|
|
177
|
+
|
|
178
|
+
APPENDIX: How to apply the Apache License to your work.
|
|
179
|
+
|
|
180
|
+
To apply the Apache License to your work, attach the following
|
|
181
|
+
boilerplate notice, with the fields enclosed by brackets "[]"
|
|
182
|
+
replaced with your own identifying information. (Don't include
|
|
183
|
+
the brackets!) The text should be enclosed in the appropriate
|
|
184
|
+
comment syntax for the file format. We also recommend that a
|
|
185
|
+
file or class name and description of purpose be included on the
|
|
186
|
+
same "printed page" as the copyright notice for easier
|
|
187
|
+
identification within third-party archives.
|
|
188
|
+
|
|
189
|
+
Copyright [yyyy] [name of copyright owner]
|
|
190
|
+
|
|
191
|
+
Licensed under the Apache License, Version 2.0 (the "License");
|
|
192
|
+
you may not use this file except in compliance with the License.
|
|
193
|
+
You may obtain a copy of the License at
|
|
194
|
+
|
|
195
|
+
http://www.apache.org/licenses/LICENSE-2.0
|
|
196
|
+
|
|
197
|
+
Unless required by applicable law or agreed to in writing, software
|
|
198
|
+
distributed under the License is distributed on an "AS IS" BASIS,
|
|
199
|
+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
200
|
+
See the License for the specific language governing permissions and
|
|
201
|
+
limitations under the License.
|
|
202
|
+
|
|
203
|
+
|
|
204
|
+
------------------------------------------------------------------------------------
|
|
205
|
+
This product bundles various third-party components under other open source licenses.
|
|
206
|
+
This section summarizes those components and their licenses. See licenses/
|
|
207
|
+
for text of these licenses.
|
|
208
|
+
|
|
209
|
+
|
|
210
|
+
Apache Software Foundation License 2.0
|
|
211
|
+
--------------------------------------
|
|
212
|
+
|
|
213
|
+
common/network-common/src/main/java/org/apache/spark/network/util/LimitedInputStream.java
|
|
214
|
+
core/src/main/java/org/apache/spark/util/collection/TimSort.java
|
|
215
|
+
core/src/main/resources/org/apache/spark/ui/static/bootstrap*
|
|
216
|
+
core/src/main/resources/org/apache/spark/ui/static/vis*
|
|
217
|
+
docs/js/vendor/bootstrap.js
|
|
218
|
+
connector/spark-ganglia-lgpl/src/main/java/com/codahale/metrics/ganglia/GangliaReporter.java
|
|
219
|
+
|
|
220
|
+
|
|
221
|
+
Python Software Foundation License
|
|
222
|
+
----------------------------------
|
|
223
|
+
|
|
224
|
+
python/docs/source/_static/copybutton.js
|
|
225
|
+
|
|
226
|
+
BSD 3-Clause
|
|
227
|
+
------------
|
|
228
|
+
|
|
229
|
+
python/lib/py4j-*-src.zip
|
|
230
|
+
python/pyspark/cloudpickle/*.py
|
|
231
|
+
python/pyspark/join.py
|
|
232
|
+
core/src/main/resources/org/apache/spark/ui/static/d3.min.js
|
|
233
|
+
|
|
234
|
+
The CSS style for the navigation sidebar of the documentation was originally
|
|
235
|
+
submitted by Óscar Nájera for the scikit-learn project. The scikit-learn project
|
|
236
|
+
is distributed under the 3-Clause BSD license.
|
|
237
|
+
|
|
238
|
+
|
|
239
|
+
MIT License
|
|
240
|
+
-----------
|
|
241
|
+
|
|
242
|
+
core/src/main/resources/org/apache/spark/ui/static/dagre-d3.min.js
|
|
243
|
+
core/src/main/resources/org/apache/spark/ui/static/*dataTables*
|
|
244
|
+
core/src/main/resources/org/apache/spark/ui/static/graphlib-dot.min.js
|
|
245
|
+
core/src/main/resources/org/apache/spark/ui/static/jquery*
|
|
246
|
+
core/src/main/resources/org/apache/spark/ui/static/sorttable.js
|
|
247
|
+
docs/js/vendor/anchor.min.js
|
|
248
|
+
docs/js/vendor/jquery*
|
|
249
|
+
docs/js/vendor/modernizer*
|
|
250
|
+
|
|
251
|
+
|
|
252
|
+
Creative Commons CC0 1.0 Universal Public Domain Dedication
|
|
253
|
+
-----------------------------------------------------------
|
|
254
|
+
(see LICENSE-CC0.txt)
|
|
255
|
+
|
|
256
|
+
data/mllib/images/kittens/29.5.a_b_EGDP022204.jpg
|
|
257
|
+
data/mllib/images/kittens/54893.jpg
|
|
258
|
+
data/mllib/images/kittens/DP153539.jpg
|
|
259
|
+
data/mllib/images/kittens/DP802813.jpg
|
|
260
|
+
data/mllib/images/multi-channel/chr30.4.184.jpg
|
|
@@ -0,0 +1,6 @@
|
|
|
1
|
+
from .conf import SparkConf # noqa: D104
|
|
2
|
+
from .context import SparkContext
|
|
3
|
+
from .exception import ContributionsAcceptedError
|
|
4
|
+
from .sql import DataFrame, SparkSession
|
|
5
|
+
|
|
6
|
+
__all__ = ["ContributionsAcceptedError", "DataFrame", "SparkConf", "SparkContext", "SparkSession"]
|
|
@@ -0,0 +1,77 @@
|
|
|
1
|
+
#
|
|
2
|
+
# Licensed to the Apache Software Foundation (ASF) under one or more
|
|
3
|
+
# contributor license agreements. See the NOTICE file distributed with
|
|
4
|
+
# this work for additional information regarding copyright ownership.
|
|
5
|
+
# The ASF licenses this file to You under the Apache License, Version 2.0
|
|
6
|
+
# (the "License"); you may not use this file except in compliance with
|
|
7
|
+
# the License. You may obtain a copy of the License at
|
|
8
|
+
#
|
|
9
|
+
# http://www.apache.org/licenses/LICENSE-2.0
|
|
10
|
+
#
|
|
11
|
+
# Unless required by applicable law or agreed to in writing, software
|
|
12
|
+
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
13
|
+
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
14
|
+
# See the License for the specific language governing permissions and
|
|
15
|
+
# limitations under the License.
|
|
16
|
+
#
|
|
17
|
+
|
|
18
|
+
"""Module defining global singleton classes.
|
|
19
|
+
|
|
20
|
+
This module raises a RuntimeError if an attempt to reload it is made. In that
|
|
21
|
+
way the identities of the classes defined here are fixed and will remain so
|
|
22
|
+
even if duckdb spark itself is reloaded. In particular, a function like the following
|
|
23
|
+
will still work correctly after duckdb spark is reloaded:
|
|
24
|
+
|
|
25
|
+
def foo(arg=pyducdkb.spark._NoValue):
|
|
26
|
+
if arg is pyducdkb.spark._NoValue:
|
|
27
|
+
...
|
|
28
|
+
|
|
29
|
+
See gh-7844 for a discussion of the reload problem that motivated this module.
|
|
30
|
+
|
|
31
|
+
Note that this approach is taken after from NumPy.
|
|
32
|
+
"""
|
|
33
|
+
|
|
34
|
+
__ALL__ = ["_NoValue"]
|
|
35
|
+
|
|
36
|
+
|
|
37
|
+
# Disallow reloading this module so as to preserve the identities of the
|
|
38
|
+
# classes defined here.
|
|
39
|
+
if "_is_loaded" in globals():
|
|
40
|
+
msg = "Reloading duckdb.experimental.spark._globals is not allowed"
|
|
41
|
+
raise RuntimeError(msg)
|
|
42
|
+
_is_loaded = True
|
|
43
|
+
|
|
44
|
+
|
|
45
|
+
class _NoValueType:
|
|
46
|
+
"""Special keyword value.
|
|
47
|
+
|
|
48
|
+
The instance of this class may be used as the default value assigned to a
|
|
49
|
+
deprecated keyword in order to check if it has been given a user defined
|
|
50
|
+
value.
|
|
51
|
+
|
|
52
|
+
This class was copied from NumPy.
|
|
53
|
+
"""
|
|
54
|
+
|
|
55
|
+
__instance = None
|
|
56
|
+
|
|
57
|
+
def __new__(cls) -> "_NoValueType":
|
|
58
|
+
# ensure that only one instance exists
|
|
59
|
+
if not cls.__instance:
|
|
60
|
+
cls.__instance = super().__new__(cls)
|
|
61
|
+
return cls.__instance
|
|
62
|
+
|
|
63
|
+
# Make the _NoValue instance falsey
|
|
64
|
+
def __nonzero__(self) -> bool:
|
|
65
|
+
return False
|
|
66
|
+
|
|
67
|
+
__bool__ = __nonzero__
|
|
68
|
+
|
|
69
|
+
# needed for python 2 to preserve identity through a pickle
|
|
70
|
+
def __reduce__(self) -> tuple[type, tuple]:
|
|
71
|
+
return (self.__class__, ())
|
|
72
|
+
|
|
73
|
+
def __repr__(self) -> str:
|
|
74
|
+
return "<no value>"
|
|
75
|
+
|
|
76
|
+
|
|
77
|
+
_NoValue = _NoValueType()
|