Repository navigation
Expand file tree
/
Copy pathutil.py
More file actions
726 lines (557 loc) · 17.1 KB
/
Copy pathutil.py
File metadata and controls
726 lines (557 loc) · 17.1 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
"""Ibis utility functions."""
from __future__ import annotations
import base64
import collections
import collections.abc
import contextlib
import functools
import importlib.metadata
import itertools
import operator
import os
import re
import sys
import tempfile
import textwrap
import types
import uuid
import warnings
from types import ModuleType
from typing import TYPE_CHECKING, Any, Callable, Generic, TypeVar
from uuid import uuid4
import toolz
from ibis.common.typing import Coercible
if TYPE_CHECKING:
from collections.abc import Iterable, Iterator, Sequence
from pathlib import Path
import ibis.expr.types as ir
T = TypeVar("T", covariant=True)
S = TypeVar("S", bound=T, covariant=True)
U = TypeVar("U", covariant=True)
K = TypeVar("K")
V = TypeVar("V")
VERTICAL_ELLIPSIS = "⋮"
HORIZONTAL_ELLIPSIS = "…"
def guid() -> str:
"""Return a uuid4 hexadecimal value."""
return uuid4().hex
def indent(text: str, spaces: int) -> str:
"""Apply an indentation using the given spaces into the given text.
Parameters
----------
text
Text to indent
spaces
Number of leading spaces per line
Returns
-------
str
Indented text
"""
prefix = " " * spaces
return textwrap.indent(text, prefix=prefix)
def is_one_of(values: Sequence[T], t: type[U]) -> Iterator[bool]:
"""Check if the type of each value is the same of the given type.
Parameters
----------
values
Input values
t
Type to check against
Returns
-------
tuple
"""
return (isinstance(x, t) for x in values)
any_of = toolz.compose(any, is_one_of)
all_of = toolz.compose(all, is_one_of)
def promote_list(val: V | Iterable[V]) -> list[V]:
"""Ensure that the value is a list.
Parameters
----------
val
Value to promote
Returns
-------
list
"""
if isinstance(val, list):
return val
elif isinstance(val, dict):
return [val]
elif is_iterable(val):
return list(val)
elif val is None:
return []
else:
return [val]
def promote_tuple(val: V | Iterable[V]) -> tuple[V]:
"""Ensure that the value is a tuple.
Parameters
----------
val
Value to promote
Returns
-------
tuple
"""
if isinstance(val, tuple):
return val
elif is_iterable(val):
return tuple(val)
elif val is None:
return ()
else:
return (val,)
def is_function(v: Any) -> bool:
"""Check if the given object is a function.
Returns
-------
bool
Whether `v` is a function
"""
return isinstance(v, (types.FunctionType, types.LambdaType))
def log(msg: str) -> None:
"""Log `msg` using `options.verbose_log` if set, otherwise `print`."""
from ibis.config import options
if options.verbose:
(options.verbose_log or print)(msg)
def is_iterable(o: Any) -> bool:
"""Return whether `o` is iterable and not a :class:`str` or :class:`bytes`.
Parameters
----------
o : object
Any python object
Returns
-------
bool
Examples
--------
>>> is_iterable("1")
False
>>> is_iterable(b"1")
False
>>> is_iterable(iter("1"))
True
>>> is_iterable(i for i in range(1))
True
>>> is_iterable(1)
False
>>> is_iterable([])
True
"""
if isinstance(o, (str, bytes)):
return False
try:
iter(o)
except TypeError:
return False
else:
return True
def convert_unit(value, unit, to, floor: bool = True):
"""Convert a value between different units.
Convert `value`, is assumed to be in units of `unit`, to units of `to`.
If `floor` is true, then use floor division on `value` if necessary.
Parameters
----------
value
Number or numeric ibis expression
unit
Unit of `value`
to
Unit to convert to
floor
Whether or not to use floor division on `value` if necessary.
Returns
-------
Union[numbers.Integral, ibis.expr.types.NumericValue]
Integer converted unit
Examples
--------
>>> one_second = 1000
>>> x = convert_unit(one_second, "ms", "s")
>>> x
1
>>> one_second = 1
>>> x = convert_unit(one_second, "s", "ms")
>>> x
1000
>>> x = convert_unit(one_second, "s", "s")
>>> x
1
>>> x = convert_unit(one_second, "s", "M")
Traceback (most recent call last):
...
ValueError: Cannot convert to or from unit ... to unit ...
"""
# Don't do anything if from and to units are equivalent
if unit == to:
return value
units = ("W", "D", "h", "m", "s", "ms", "us", "ns")
factors = (7, 24, 60, 60, 1000, 1000, 1000)
monthly_units = ("Y", "Q", "M")
monthly_factors = (4, 3)
try:
i, j = units.index(unit), units.index(to)
except ValueError:
try:
i, j = monthly_units.index(unit), monthly_units.index(to)
factors = monthly_factors
except ValueError:
raise ValueError(
f"Cannot convert interval value from unit {unit} to unit {to}"
)
factor = functools.reduce(operator.mul, factors[min(i, j) : max(i, j)], 1)
assert factor > 1
if i < j:
op = operator.mul
else:
assert i > j
op = operator.floordiv if floor else operator.truediv
try:
return op(value.to_expr(), factor).op()
except AttributeError:
return op(value, factor)
# taken from the itertools documentation
def consume(iterator: Iterator[T], n: int | None = None) -> None:
"""Advance `iterator` n-steps ahead. If `n` is `None`, consume entirely."""
# Use functions that consume iterators at C speed.
if n is None:
# feed the entire iterator into a zero-length deque
collections.deque(iterator, maxlen=0)
else:
# advance to the empty slice starting at position n
next(itertools.islice(iterator, n, n), None)
def flatten_iterable(iterable):
"""Recursively flatten the iterable `iterable`."""
if not is_iterable(iterable):
raise TypeError("flatten is only defined for non-str iterables")
for item in iterable:
if is_iterable(item):
yield from flatten_iterable(item)
else:
yield item
def deprecated_msg(name, *, instead, as_of="", removed_in=""):
msg = f"`{name}` is deprecated"
msgs = []
if as_of:
msgs.append(f"as of v{as_of}")
if removed_in:
msgs.append(f"removed in v{removed_in}")
if msgs:
msg += f" {', '.join(msgs)}"
msg += f"; {instead}"
return msg
def warn_deprecated(name, *, instead, as_of="", removed_in="", stacklevel=1):
"""Warn about deprecated usage.
The message includes a stacktrace and what to do instead.
"""
msg = deprecated_msg(name, instead=instead, as_of=as_of, removed_in=removed_in)
warnings.warn(msg, FutureWarning, stacklevel=stacklevel + 1)
def append_admonition(
func: Callable, *, msg: str, body: str = "", kind: str = "warning"
) -> str:
"""Append a `kind` admonition with `msg` to `func`'s docstring."""
if docstr := func.__doc__:
preamble, *rest = docstr.split("\n\n", maxsplit=1)
# count leading spaces and add them to the deprecation warning so the
# docstring parses correctly
leading_spaces = " " * sum(
1 for _ in itertools.takewhile(str.isspace, rest[0] if rest else [])
)
lines = [f"::: {{.callout-{kind}}}", f"## {msg}", ":::"]
admonition_doc = textwrap.indent("\n".join(lines), leading_spaces)
if body:
rest = [indent(body, spaces=len(leading_spaces) + 4), *rest]
docstr = "\n\n".join([preamble, admonition_doc, *rest])
else:
lines = [f"::: {{.callout-{kind}}}", f"## {msg}", ":::"]
admonition_doc = "\n".join(lines)
if body:
admonition_doc += f"\n\n{indent(body, spaces=4)}"
docstr = admonition_doc
return docstr
def deprecated(*, instead: str, as_of: str = "", removed_in: str = ""):
"""Decorate to warn of deprecated usage and what to do instead."""
def decorator(func):
msg = deprecated_msg(
func.__qualname__, instead=instead, as_of=as_of, removed_in=removed_in
)
func.__doc__ = append_admonition(func, msg=f"DEPRECATED: {msg}")
@functools.wraps(func)
def wrapper(*args, **kwargs):
warn_deprecated(
func.__qualname__,
instead=instead,
as_of=as_of,
removed_in=removed_in,
stacklevel=2,
)
return func(*args, **kwargs)
return wrapper
return decorator
def backend_sensitive(
*,
msg: str = "This operation differs between backends.",
why: str = "",
):
"""Indicate that an API may be sensitive to a backend."""
def wrapper(func):
func.__doc__ = append_admonition(func, msg=msg, body=why, kind="info")
return func
return wrapper
def experimental(func):
"""Decorate a callable to add warning about API instability in docstring."""
func.__doc__ = append_admonition(
func, msg="This API is experimental and subject to change."
)
return func
@functools.cache
def backend_entry_points() -> list[importlib.metadata.EntryPoint]:
"""Get the list of installed `ibis.backend` entrypoints."""
if sys.version_info < (3, 10):
eps = importlib.metadata.entry_points()["ibis.backends"]
else:
eps = importlib.metadata.entry_points(group="ibis.backends")
return sorted(eps)
_common_package_aliases = {
"pa": "pyarrow",
"pd": "pandas",
"np": "numpy",
"sk": "sklearn",
"sp": "scipy",
"tf": "tensorflow",
}
def unalias_package(name: str) -> str:
return _common_package_aliases.get(name, name)
def import_object(qualname: str) -> Any:
"""Attempt to import an object given its full qualname.
Examples
--------
>>> ex = import_object("ibis.examples")
Is the same as
>>> from ibis import examples as ex
"""
mod_name, name = qualname.rsplit(".", 1)
mod = importlib.import_module(mod_name)
try:
return getattr(mod, name)
except AttributeError:
raise ImportError(f"cannot import name {name!r} from {mod_name!r}") from None
def normalize_filename(source: str | Path) -> str:
source = str(source)
for prefix in (
"parquet",
"csv",
"csv.gz",
"txt",
"txt.gz",
"tsv",
"tsv.gz",
"file",
):
source = source.removeprefix(f"{prefix}://")
def _absolufy_paths(name):
if re.search(r"^(?:.+)://", name) is None:
return os.path.abspath(name)
return name
source = _absolufy_paths(source)
return source
def normalize_filenames(source_list):
# Promote to list
source_list = promote_list(source_list)
return list(map(normalize_filename, source_list))
def gen_name(namespace: str) -> str:
"""Create a unique identifier."""
uid = base64.b32encode(uuid.uuid4().bytes).decode().rstrip("=").lower()
return f"ibis_{namespace}_{uid}"
def slice_to_limit_offset(
what: slice, count: ir.IntegerScalar
) -> tuple[int | ir.IntegerScalar, int | ir.IntegerScalar]:
"""Convert a Python [`slice`](slice) to a `limit`, `offset` pair.
Parameters
----------
what
The slice to convert
count
The total number of rows in the table as an expression
Returns
-------
tuple[int | ir.IntegerScalar, int | ir.IntegerScalar]
The offset and limit to use in a `Table.limit` call
Examples
--------
>>> import ibis
>>> t = ibis.table(dict(a="int", b="string"), name="t")
First 10 rows
>>> count = t.count()
>>> what = slice(0, 10)
>>> limit, offset = slice_to_limit_offset(what, count)
>>> limit
10
>>> offset
0
Last 10 rows
>>> what = slice(-10, None)
>>> limit, offset = slice_to_limit_offset(what, count)
>>> limit
10
>>> offset
r0 := UnboundTable: t
a int64
b string
<BLANKLINE>
Add(CountStar(t), -10): CountStar(r0) + -10
From 5th row to 10th row
>>> what = slice(5, 10)
>>> limit, offset = slice_to_limit_offset(what, count)
>>> limit, offset
(5, 5)
"""
if (step := what.step) is not None and step != 1:
raise ValueError("Slice step can only be 1")
import ibis
start = what.start
stop = what.stop
if start is None or start >= 0:
offset = start or 0
if stop is None:
limit = None
elif stop == 0:
limit = 0
elif stop < 0:
limit = count + (stop - offset)
else: # stop > 0
limit = max(stop - offset, 0)
else: # start < 0
offset = count + start
if stop is None:
limit = -start
elif stop == 0:
limit = offset = 0
elif stop < 0:
limit = max(stop - start, 0)
if limit == 0:
offset = 0
else: # stop > 0
limit = ibis.greatest((stop - start) - count, 0)
return limit, offset
class Namespace:
"""Convenience class for creating patterns for various types from a module.
Useful to reduce boilerplate when creating patterns for various types from
a module.
Parameters
----------
factory
The pattern to construct with the looked up types.
module
The module object or name to look up the types.
"""
__slots__ = ("_factory", "_module")
_factory: Callable
_module: ModuleType
def __init__(self, factory, module):
if isinstance(module, str):
module = sys.modules[module]
self._module = module
self._factory = factory
def __getattr__(self, name: str):
obj = getattr(self._module, name)
return self._factory(obj)
class PseudoHashable(Coercible, Generic[V]):
"""A wrapper that provides a best effort precomputed hash."""
__slots__ = ("hash", "obj")
obj: V
def __init__(self, obj: V):
if isinstance(obj, collections.abc.Hashable):
raise TypeError(f"Cannot wrap a hashable object: {obj!r}")
elif isinstance(obj, collections.abc.Sequence):
hashable_obj = tuple(obj)
elif isinstance(obj, collections.abc.Mapping):
hashable_obj = tuple(obj.items())
elif isinstance(obj, collections.abc.Set):
hashable_obj = frozenset(obj)
else:
hashable_obj = id(obj)
self.obj = obj
self.hash = hash((type(obj), hashable_obj))
@classmethod
def __coerce__(cls, value: V) -> PseudoHashable[V]:
if isinstance(value, cls):
return value
return cls(value)
def __hash__(self):
return self.hash
def __eq__(self, other):
if isinstance(other, PseudoHashable):
return self.obj == other.obj
else:
return NotImplemented
def __ne__(self, other):
if isinstance(other, PseudoHashable):
return self.obj != other.obj
else:
return NotImplemented
def chunks(n: int, *, chunk_size: int) -> Iterator[tuple[int, int]]:
"""Return an iterator of chunk start and end indices.
Parameters
----------
n
The total number of elements.
chunk_size
The size of each chunk.
Returns
-------
int
THE start and end indices of each chunk.
Examples
--------
>>> list(chunks(10, chunk_size=3))
[(0, 3), (3, 6), (6, 9), (9, 10)]
>>> list(chunks(10, chunk_size=4))
[(0, 4), (4, 8), (8, 10)]
"""
return ((start, min(start + chunk_size, n)) for start in range(0, n, chunk_size))
def get_subclasses(obj: type[T]) -> Iterator[type[S]]:
"""Recursively compute all subclasses of `obj`.
::: {.callout-note}
## The resulting iterator does **not** include the input type object.
:::
Parameters
----------
obj
Any type object
Examples
--------
>>> class Base: ...
>>> class Subclass1(Base): ...
>>> class Subclass2(Base): ...
>>> class TransitiveSubclass(Subclass2): ...
Everything inherits `Base` (directly or transitively)
>>> list(get_subclasses(Base))
[<class 'ibis.util.Subclass1'>, <class 'ibis.util.Subclass2'>, <class 'ibis.util.TransitiveSubclass'>]
Nothing inherits from `Subclass1`
>>> list(get_subclasses(Subclass1))
[]
Only `TransitiveSubclass` inherits from `Subclass2`
>>> list(get_subclasses(Subclass2))
[<class 'ibis.util.TransitiveSubclass'>]
Nothing inherits from `TransitiveSubclass`
>>> list(get_subclasses(TransitiveSubclass))
[]
"""
for child_class in obj.__subclasses__():
yield child_class
yield from get_subclasses(child_class)
if sys.version_info[:2] < (3, 10):
@contextlib.contextmanager
def mktempd():
tmpdir = tempfile.TemporaryDirectory()
try:
yield tmpdir.name
finally:
with contextlib.suppress(Exception):
tmpdir.cleanup()
else:
def mktempd():
return tempfile.TemporaryDirectory(ignore_cleanup_errors=True)