-
Notifications
You must be signed in to change notification settings - Fork 2.4k
/
black.py
3758 lines (3130 loc) · 122 KB
/
black.py
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
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
import asyncio
from asyncio.base_events import BaseEventLoop
from concurrent.futures import Executor, ProcessPoolExecutor
from datetime import datetime
from enum import Enum
from functools import lru_cache, partial, wraps
import io
import itertools
import logging
from multiprocessing import Manager, freeze_support
import os
from pathlib import Path
import pickle
import re
import signal
import sys
import tempfile
import tokenize
from typing import (
Any,
Callable,
Collection,
Dict,
Generator,
Generic,
Iterable,
Iterator,
List,
Optional,
Pattern,
Sequence,
Set,
Tuple,
TypeVar,
Union,
cast,
)
from appdirs import user_cache_dir
from attr import dataclass, evolve, Factory
import click
import toml
# lib2to3 fork
from blib2to3.pytree import Node, Leaf, type_repr
from blib2to3 import pygram, pytree
from blib2to3.pgen2 import driver, token
from blib2to3.pgen2.grammar import Grammar
from blib2to3.pgen2.parse import ParseError
__version__ = "19.3b0"
DEFAULT_LINE_LENGTH = 88
DEFAULT_EXCLUDES = (
r"/(\.eggs|\.git|\.hg|\.mypy_cache|\.nox|\.tox|\.venv|_build|buck-out|build|dist)/"
)
DEFAULT_INCLUDES = r"\.pyi?$"
CACHE_DIR = Path(user_cache_dir("black", version=__version__))
# types
FileContent = str
Encoding = str
NewLine = str
Depth = int
NodeType = int
LeafID = int
Priority = int
Index = int
LN = Union[Leaf, Node]
SplitFunc = Callable[["Line", bool], Iterator["Line"]]
Timestamp = float
FileSize = int
CacheInfo = Tuple[Timestamp, FileSize]
Cache = Dict[Path, CacheInfo]
out = partial(click.secho, bold=True, err=True)
err = partial(click.secho, fg="red", err=True)
pygram.initialize(CACHE_DIR)
syms = pygram.python_symbols
class NothingChanged(UserWarning):
"""Raised when reformatted code is the same as source."""
class CannotSplit(Exception):
"""A readable split that fits the allotted line length is impossible."""
class InvalidInput(ValueError):
"""Raised when input source code fails all parse attempts."""
class WriteBack(Enum):
NO = 0
YES = 1
DIFF = 2
CHECK = 3
@classmethod
def from_configuration(cls, *, check: bool, diff: bool) -> "WriteBack":
if check and not diff:
return cls.CHECK
return cls.DIFF if diff else cls.YES
class Changed(Enum):
NO = 0
CACHED = 1
YES = 2
class TargetVersion(Enum):
PY27 = 2
PY33 = 3
PY34 = 4
PY35 = 5
PY36 = 6
PY37 = 7
PY38 = 8
def is_python2(self) -> bool:
return self is TargetVersion.PY27
PY36_VERSIONS = {TargetVersion.PY36, TargetVersion.PY37, TargetVersion.PY38}
class Feature(Enum):
# All string literals are unicode
UNICODE_LITERALS = 1
F_STRINGS = 2
NUMERIC_UNDERSCORES = 3
TRAILING_COMMA = 4
VERSION_TO_FEATURES: Dict[TargetVersion, Set[Feature]] = {
TargetVersion.PY27: set(),
TargetVersion.PY33: {Feature.UNICODE_LITERALS},
TargetVersion.PY34: {Feature.UNICODE_LITERALS},
TargetVersion.PY35: {Feature.UNICODE_LITERALS, Feature.TRAILING_COMMA},
TargetVersion.PY36: {
Feature.UNICODE_LITERALS,
Feature.F_STRINGS,
Feature.NUMERIC_UNDERSCORES,
Feature.TRAILING_COMMA,
},
TargetVersion.PY37: {
Feature.UNICODE_LITERALS,
Feature.F_STRINGS,
Feature.NUMERIC_UNDERSCORES,
Feature.TRAILING_COMMA,
},
TargetVersion.PY38: {
Feature.UNICODE_LITERALS,
Feature.F_STRINGS,
Feature.NUMERIC_UNDERSCORES,
Feature.TRAILING_COMMA,
},
}
@dataclass
class FileMode:
target_versions: Set[TargetVersion] = Factory(set)
line_length: int = DEFAULT_LINE_LENGTH
string_normalization: bool = True
is_pyi: bool = False
def get_cache_key(self) -> str:
if self.target_versions:
version_str = ",".join(
str(version.value)
for version in sorted(self.target_versions, key=lambda v: v.value)
)
else:
version_str = "-"
parts = [
version_str,
str(self.line_length),
str(int(self.string_normalization)),
str(int(self.is_pyi)),
]
return ".".join(parts)
def supports_feature(target_versions: Set[TargetVersion], feature: Feature) -> bool:
return all(feature in VERSION_TO_FEATURES[version] for version in target_versions)
def read_pyproject_toml(
ctx: click.Context, param: click.Parameter, value: Union[str, int, bool, None]
) -> Optional[str]:
"""Inject Black configuration from "pyproject.toml" into defaults in `ctx`.
Returns the path to a successfully found and read configuration file, None
otherwise.
"""
assert not isinstance(value, (int, bool)), "Invalid parameter type passed"
if not value:
root = find_project_root(ctx.params.get("src", ()))
path = root / "pyproject.toml"
if path.is_file():
value = str(path)
else:
return None
try:
pyproject_toml = toml.load(value)
config = pyproject_toml.get("tool", {}).get("black", {})
except (toml.TomlDecodeError, OSError) as e:
raise click.FileError(
filename=value, hint=f"Error reading configuration file: {e}"
)
if not config:
return None
if ctx.default_map is None:
ctx.default_map = {}
ctx.default_map.update( # type: ignore # bad types in .pyi
{k.replace("--", "").replace("-", "_"): v for k, v in config.items()}
)
return value
@click.command(context_settings=dict(help_option_names=["-h", "--help"]))
@click.option(
"-l",
"--line-length",
type=int,
default=DEFAULT_LINE_LENGTH,
help="How many characters per line to allow.",
show_default=True,
)
@click.option(
"-t",
"--target-version",
type=click.Choice([v.name.lower() for v in TargetVersion]),
callback=lambda c, p, v: [TargetVersion[val.upper()] for val in v],
multiple=True,
help=(
"Python versions that should be supported by Black's output. [default: "
"per-file auto-detection]"
),
)
@click.option(
"--py36",
is_flag=True,
help=(
"Allow using Python 3.6-only syntax on all input files. This will put "
"trailing commas in function signatures and calls also after *args and "
"**kwargs. Deprecated; use --target-version instead. "
"[default: per-file auto-detection]"
),
)
@click.option(
"--pyi",
is_flag=True,
help=(
"Format all input files like typing stubs regardless of file extension "
"(useful when piping source on standard input)."
),
)
@click.option(
"-S",
"--skip-string-normalization",
is_flag=True,
help="Don't normalize string quotes or prefixes.",
)
@click.option(
"--check",
is_flag=True,
help=(
"Don't write the files back, just return the status. Return code 0 "
"means nothing would change. Return code 1 means some files would be "
"reformatted. Return code 123 means there was an internal error."
),
)
@click.option(
"--diff",
is_flag=True,
help="Don't write the files back, just output a diff for each file on stdout.",
)
@click.option(
"--fast/--safe",
is_flag=True,
help="If --fast given, skip temporary sanity checks. [default: --safe]",
)
@click.option(
"--include",
type=str,
default=DEFAULT_INCLUDES,
help=(
"A regular expression that matches files and directories that should be "
"included on recursive searches. An empty value means all files are "
"included regardless of the name. Use forward slashes for directories on "
"all platforms (Windows, too). Exclusions are calculated first, inclusions "
"later."
),
show_default=True,
)
@click.option(
"--exclude",
type=str,
default=DEFAULT_EXCLUDES,
help=(
"A regular expression that matches files and directories that should be "
"excluded on recursive searches. An empty value means no paths are excluded. "
"Use forward slashes for directories on all platforms (Windows, too). "
"Exclusions are calculated first, inclusions later."
),
show_default=True,
)
@click.option(
"-q",
"--quiet",
is_flag=True,
help=(
"Don't emit non-error messages to stderr. Errors are still emitted, "
"silence those with 2>/dev/null."
),
)
@click.option(
"-v",
"--verbose",
is_flag=True,
help=(
"Also emit messages to stderr about files that were not changed or were "
"ignored due to --exclude=."
),
)
@click.version_option(version=__version__)
@click.argument(
"src",
nargs=-1,
type=click.Path(
exists=True, file_okay=True, dir_okay=True, readable=True, allow_dash=True
),
is_eager=True,
)
@click.option(
"--config",
type=click.Path(
exists=False, file_okay=True, dir_okay=False, readable=True, allow_dash=False
),
is_eager=True,
callback=read_pyproject_toml,
help="Read configuration from PATH.",
)
@click.pass_context
def main(
ctx: click.Context,
line_length: int,
target_version: List[TargetVersion],
check: bool,
diff: bool,
fast: bool,
pyi: bool,
py36: bool,
skip_string_normalization: bool,
quiet: bool,
verbose: bool,
include: str,
exclude: str,
src: Tuple[str],
config: Optional[str],
) -> None:
"""The uncompromising code formatter."""
write_back = WriteBack.from_configuration(check=check, diff=diff)
if target_version:
if py36:
err(f"Cannot use both --target-version and --py36")
ctx.exit(2)
else:
versions = set(target_version)
elif py36:
err(
"--py36 is deprecated and will be removed in a future version. "
"Use --target-version py36 instead."
)
versions = PY36_VERSIONS
else:
# We'll autodetect later.
versions = set()
mode = FileMode(
target_versions=versions,
line_length=line_length,
is_pyi=pyi,
string_normalization=not skip_string_normalization,
)
if config and verbose:
out(f"Using configuration from {config}.", bold=False, fg="blue")
try:
include_regex = re_compile_maybe_verbose(include)
except re.error:
err(f"Invalid regular expression for include given: {include!r}")
ctx.exit(2)
try:
exclude_regex = re_compile_maybe_verbose(exclude)
except re.error:
err(f"Invalid regular expression for exclude given: {exclude!r}")
ctx.exit(2)
report = Report(check=check, quiet=quiet, verbose=verbose)
root = find_project_root(src)
sources: Set[Path] = set()
for s in src:
p = Path(s)
if p.is_dir():
sources.update(
gen_python_files_in_dir(p, root, include_regex, exclude_regex, report)
)
elif p.is_file() or s == "-":
# if a file was explicitly given, we don't care about its extension
sources.add(p)
else:
err(f"invalid path: {s}")
if len(sources) == 0:
if verbose or not quiet:
out("No paths given. Nothing to do 😴")
ctx.exit(0)
if len(sources) == 1:
reformat_one(
src=sources.pop(),
fast=fast,
write_back=write_back,
mode=mode,
report=report,
)
else:
loop = asyncio.get_event_loop()
executor = ProcessPoolExecutor(max_workers=os.cpu_count())
try:
loop.run_until_complete(
schedule_formatting(
sources=sources,
fast=fast,
write_back=write_back,
mode=mode,
report=report,
loop=loop,
executor=executor,
)
)
finally:
shutdown(loop)
if verbose or not quiet:
bang = "💥 💔 💥" if report.return_code else "✨ 🍰 ✨"
out(f"All done! {bang}")
click.secho(str(report), err=True)
ctx.exit(report.return_code)
def reformat_one(
src: Path, fast: bool, write_back: WriteBack, mode: FileMode, report: "Report"
) -> None:
"""Reformat a single file under `src` without spawning child processes.
If `quiet` is True, non-error messages are not output. `line_length`,
`write_back`, `fast` and `pyi` options are passed to
:func:`format_file_in_place` or :func:`format_stdin_to_stdout`.
"""
try:
changed = Changed.NO
if not src.is_file() and str(src) == "-":
if format_stdin_to_stdout(fast=fast, write_back=write_back, mode=mode):
changed = Changed.YES
else:
cache: Cache = {}
if write_back != WriteBack.DIFF:
cache = read_cache(mode)
res_src = src.resolve()
if res_src in cache and cache[res_src] == get_cache_info(res_src):
changed = Changed.CACHED
if changed is not Changed.CACHED and format_file_in_place(
src, fast=fast, write_back=write_back, mode=mode
):
changed = Changed.YES
if (write_back is WriteBack.YES and changed is not Changed.CACHED) or (
write_back is WriteBack.CHECK and changed is Changed.NO
):
write_cache(cache, [src], mode)
report.done(src, changed)
except Exception as exc:
report.failed(src, str(exc))
async def schedule_formatting(
sources: Set[Path],
fast: bool,
write_back: WriteBack,
mode: FileMode,
report: "Report",
loop: BaseEventLoop,
executor: Executor,
) -> None:
"""Run formatting of `sources` in parallel using the provided `executor`.
(Use ProcessPoolExecutors for actual parallelism.)
`line_length`, `write_back`, `fast`, and `pyi` options are passed to
:func:`format_file_in_place`.
"""
cache: Cache = {}
if write_back != WriteBack.DIFF:
cache = read_cache(mode)
sources, cached = filter_cached(cache, sources)
for src in sorted(cached):
report.done(src, Changed.CACHED)
if not sources:
return
cancelled = []
sources_to_cache = []
lock = None
if write_back == WriteBack.DIFF:
# For diff output, we need locks to ensure we don't interleave output
# from different processes.
manager = Manager()
lock = manager.Lock()
tasks = {
loop.run_in_executor(
executor, format_file_in_place, src, fast, mode, write_back, lock
): src
for src in sorted(sources)
}
pending: Iterable[asyncio.Task] = tasks.keys()
try:
loop.add_signal_handler(signal.SIGINT, cancel, pending)
loop.add_signal_handler(signal.SIGTERM, cancel, pending)
except NotImplementedError:
# There are no good alternatives for these on Windows.
pass
while pending:
done, _ = await asyncio.wait(pending, return_when=asyncio.FIRST_COMPLETED)
for task in done:
src = tasks.pop(task)
if task.cancelled():
cancelled.append(task)
elif task.exception():
report.failed(src, str(task.exception()))
else:
changed = Changed.YES if task.result() else Changed.NO
# If the file was written back or was successfully checked as
# well-formatted, store this information in the cache.
if write_back is WriteBack.YES or (
write_back is WriteBack.CHECK and changed is Changed.NO
):
sources_to_cache.append(src)
report.done(src, changed)
if cancelled:
await asyncio.gather(*cancelled, loop=loop, return_exceptions=True)
if sources_to_cache:
write_cache(cache, sources_to_cache, mode)
def format_file_in_place(
src: Path,
fast: bool,
mode: FileMode,
write_back: WriteBack = WriteBack.NO,
lock: Any = None, # multiprocessing.Manager().Lock() is some crazy proxy
) -> bool:
"""Format file under `src` path. Return True if changed.
If `write_back` is DIFF, write a diff to stdout. If it is YES, write reformatted
code to the file.
`line_length` and `fast` options are passed to :func:`format_file_contents`.
"""
if src.suffix == ".pyi":
mode = evolve(mode, is_pyi=True)
then = datetime.utcfromtimestamp(src.stat().st_mtime)
with open(src, "rb") as buf:
src_contents, encoding, newline = decode_bytes(buf.read())
try:
dst_contents = format_file_contents(src_contents, fast=fast, mode=mode)
except NothingChanged:
return False
if write_back == write_back.YES:
with open(src, "w", encoding=encoding, newline=newline) as f:
f.write(dst_contents)
elif write_back == write_back.DIFF:
now = datetime.utcnow()
src_name = f"{src}\t{then} +0000"
dst_name = f"{src}\t{now} +0000"
diff_contents = diff(src_contents, dst_contents, src_name, dst_name)
if lock:
lock.acquire()
try:
f = io.TextIOWrapper(
sys.stdout.buffer,
encoding=encoding,
newline=newline,
write_through=True,
)
f.write(diff_contents)
f.detach()
finally:
if lock:
lock.release()
return True
def format_stdin_to_stdout(
fast: bool, *, write_back: WriteBack = WriteBack.NO, mode: FileMode
) -> bool:
"""Format file on stdin. Return True if changed.
If `write_back` is YES, write reformatted code back to stdout. If it is DIFF,
write a diff to stdout. The `mode` argument is passed to
:func:`format_file_contents`.
"""
then = datetime.utcnow()
src, encoding, newline = decode_bytes(sys.stdin.buffer.read())
dst = src
try:
dst = format_file_contents(src, fast=fast, mode=mode)
return True
except NothingChanged:
return False
finally:
f = io.TextIOWrapper(
sys.stdout.buffer, encoding=encoding, newline=newline, write_through=True
)
if write_back == WriteBack.YES:
f.write(dst)
elif write_back == WriteBack.DIFF:
now = datetime.utcnow()
src_name = f"STDIN\t{then} +0000"
dst_name = f"STDOUT\t{now} +0000"
f.write(diff(src, dst, src_name, dst_name))
f.detach()
def format_file_contents(
src_contents: str, *, fast: bool, mode: FileMode
) -> FileContent:
"""Reformat contents a file and return new contents.
If `fast` is False, additionally confirm that the reformatted code is
valid by calling :func:`assert_equivalent` and :func:`assert_stable` on it.
`line_length` is passed to :func:`format_str`.
"""
if src_contents.strip() == "":
raise NothingChanged
dst_contents = format_str(src_contents, mode=mode)
if src_contents == dst_contents:
raise NothingChanged
if not fast:
assert_equivalent(src_contents, dst_contents)
assert_stable(src_contents, dst_contents, mode=mode)
return dst_contents
def format_str(src_contents: str, *, mode: FileMode) -> FileContent:
"""Reformat a string and return new contents.
`line_length` determines how many characters per line are allowed.
"""
src_node = lib2to3_parse(src_contents.lstrip(), mode.target_versions)
dst_contents = ""
future_imports = get_future_imports(src_node)
if mode.target_versions:
versions = mode.target_versions
else:
versions = detect_target_versions(src_node)
normalize_fmt_off(src_node)
lines = LineGenerator(
remove_u_prefix="unicode_literals" in future_imports
or supports_feature(versions, Feature.UNICODE_LITERALS),
is_pyi=mode.is_pyi,
normalize_strings=mode.string_normalization,
)
elt = EmptyLineTracker(is_pyi=mode.is_pyi)
empty_line = Line()
after = 0
for current_line in lines.visit(src_node):
for _ in range(after):
dst_contents += str(empty_line)
before, after = elt.maybe_empty_lines(current_line)
for _ in range(before):
dst_contents += str(empty_line)
for line in split_line(
current_line,
line_length=mode.line_length,
supports_trailing_commas=supports_feature(versions, Feature.TRAILING_COMMA),
):
dst_contents += str(line)
return dst_contents
def decode_bytes(src: bytes) -> Tuple[FileContent, Encoding, NewLine]:
"""Return a tuple of (decoded_contents, encoding, newline).
`newline` is either CRLF or LF but `decoded_contents` is decoded with
universal newlines (i.e. only contains LF).
"""
srcbuf = io.BytesIO(src)
encoding, lines = tokenize.detect_encoding(srcbuf.readline)
if not lines:
return "", encoding, "\n"
newline = "\r\n" if b"\r\n" == lines[0][-2:] else "\n"
srcbuf.seek(0)
with io.TextIOWrapper(srcbuf, encoding) as tiow:
return tiow.read(), encoding, newline
GRAMMARS = [
pygram.python_grammar_no_print_statement_no_exec_statement,
pygram.python_grammar_no_print_statement,
pygram.python_grammar,
]
def get_grammars(target_versions: Set[TargetVersion]) -> List[Grammar]:
if not target_versions:
return GRAMMARS
elif all(not version.is_python2() for version in target_versions):
# Python 2-compatible code, so don't try Python 3 grammar.
return [
pygram.python_grammar_no_print_statement_no_exec_statement,
pygram.python_grammar_no_print_statement,
]
else:
return [pygram.python_grammar]
def lib2to3_parse(src_txt: str, target_versions: Iterable[TargetVersion] = ()) -> Node:
"""Given a string with source, return the lib2to3 Node."""
if src_txt[-1:] != "\n":
src_txt += "\n"
for grammar in get_grammars(set(target_versions)):
drv = driver.Driver(grammar, pytree.convert)
try:
result = drv.parse_string(src_txt, True)
break
except ParseError as pe:
lineno, column = pe.context[1]
lines = src_txt.splitlines()
try:
faulty_line = lines[lineno - 1]
except IndexError:
faulty_line = "<line number missing in source>"
exc = InvalidInput(f"Cannot parse: {lineno}:{column}: {faulty_line}")
else:
raise exc from None
if isinstance(result, Leaf):
result = Node(syms.file_input, [result])
return result
def lib2to3_unparse(node: Node) -> str:
"""Given a lib2to3 node, return its string representation."""
code = str(node)
return code
T = TypeVar("T")
class Visitor(Generic[T]):
"""Basic lib2to3 visitor that yields things of type `T` on `visit()`."""
def visit(self, node: LN) -> Iterator[T]:
"""Main method to visit `node` and its children.
It tries to find a `visit_*()` method for the given `node.type`, like
`visit_simple_stmt` for Node objects or `visit_INDENT` for Leaf objects.
If no dedicated `visit_*()` method is found, chooses `visit_default()`
instead.
Then yields objects of type `T` from the selected visitor.
"""
if node.type < 256:
name = token.tok_name[node.type]
else:
name = type_repr(node.type)
yield from getattr(self, f"visit_{name}", self.visit_default)(node)
def visit_default(self, node: LN) -> Iterator[T]:
"""Default `visit_*()` implementation. Recurses to children of `node`."""
if isinstance(node, Node):
for child in node.children:
yield from self.visit(child)
@dataclass
class DebugVisitor(Visitor[T]):
tree_depth: int = 0
def visit_default(self, node: LN) -> Iterator[T]:
indent = " " * (2 * self.tree_depth)
if isinstance(node, Node):
_type = type_repr(node.type)
out(f"{indent}{_type}", fg="yellow")
self.tree_depth += 1
for child in node.children:
yield from self.visit(child)
self.tree_depth -= 1
out(f"{indent}/{_type}", fg="yellow", bold=False)
else:
_type = token.tok_name.get(node.type, str(node.type))
out(f"{indent}{_type}", fg="blue", nl=False)
if node.prefix:
# We don't have to handle prefixes for `Node` objects since
# that delegates to the first child anyway.
out(f" {node.prefix!r}", fg="green", bold=False, nl=False)
out(f" {node.value!r}", fg="blue", bold=False)
@classmethod
def show(cls, code: Union[str, Leaf, Node]) -> None:
"""Pretty-print the lib2to3 AST of a given string of `code`.
Convenience method for debugging.
"""
v: DebugVisitor[None] = DebugVisitor()
if isinstance(code, str):
code = lib2to3_parse(code)
list(v.visit(code))
WHITESPACE = {token.DEDENT, token.INDENT, token.NEWLINE}
STATEMENT = {
syms.if_stmt,
syms.while_stmt,
syms.for_stmt,
syms.try_stmt,
syms.except_clause,
syms.with_stmt,
syms.funcdef,
syms.classdef,
}
STANDALONE_COMMENT = 153
token.tok_name[STANDALONE_COMMENT] = "STANDALONE_COMMENT"
LOGIC_OPERATORS = {"and", "or"}
COMPARATORS = {
token.LESS,
token.GREATER,
token.EQEQUAL,
token.NOTEQUAL,
token.LESSEQUAL,
token.GREATEREQUAL,
}
MATH_OPERATORS = {
token.VBAR,
token.CIRCUMFLEX,
token.AMPER,
token.LEFTSHIFT,
token.RIGHTSHIFT,
token.PLUS,
token.MINUS,
token.STAR,
token.SLASH,
token.DOUBLESLASH,
token.PERCENT,
token.AT,
token.TILDE,
token.DOUBLESTAR,
}
STARS = {token.STAR, token.DOUBLESTAR}
VARARGS_PARENTS = {
syms.arglist,
syms.argument, # double star in arglist
syms.trailer, # single argument to call
syms.typedargslist,
syms.varargslist, # lambdas
}
UNPACKING_PARENTS = {
syms.atom, # single element of a list or set literal
syms.dictsetmaker,
syms.listmaker,
syms.testlist_gexp,
syms.testlist_star_expr,
}
TEST_DESCENDANTS = {
syms.test,
syms.lambdef,
syms.or_test,
syms.and_test,
syms.not_test,
syms.comparison,
syms.star_expr,
syms.expr,
syms.xor_expr,
syms.and_expr,
syms.shift_expr,
syms.arith_expr,
syms.trailer,
syms.term,
syms.power,
}
ASSIGNMENTS = {
"=",
"+=",
"-=",
"*=",
"@=",
"/=",
"%=",
"&=",
"|=",
"^=",
"<<=",
">>=",
"**=",
"//=",
}
COMPREHENSION_PRIORITY = 20
COMMA_PRIORITY = 18
TERNARY_PRIORITY = 16
LOGIC_PRIORITY = 14
STRING_PRIORITY = 12
COMPARATOR_PRIORITY = 10
MATH_PRIORITIES = {
token.VBAR: 9,
token.CIRCUMFLEX: 8,
token.AMPER: 7,
token.LEFTSHIFT: 6,
token.RIGHTSHIFT: 6,
token.PLUS: 5,
token.MINUS: 5,
token.STAR: 4,
token.SLASH: 4,
token.DOUBLESLASH: 4,
token.PERCENT: 4,
token.AT: 4,
token.TILDE: 3,
token.DOUBLESTAR: 2,
}
DOT_PRIORITY = 1
@dataclass
class BracketTracker:
"""Keeps track of brackets on a line."""
depth: int = 0
bracket_match: Dict[Tuple[Depth, NodeType], Leaf] = Factory(dict)
delimiters: Dict[LeafID, Priority] = Factory(dict)
previous: Optional[Leaf] = None
_for_loop_depths: List[int] = Factory(list)
_lambda_argument_depths: List[int] = Factory(list)
def mark(self, leaf: Leaf) -> None:
"""Mark `leaf` with bracket-related metadata. Keep track of delimiters.
All leaves receive an int `bracket_depth` field that stores how deep
within brackets a given leaf is. 0 means there are no enclosing brackets
that started on this line.
If a leaf is itself a closing bracket, it receives an `opening_bracket`
field that it forms a pair with. This is a one-directional link to
avoid reference cycles.
If a leaf is a delimiter (a token on which Black can split the line if
needed) and it's on depth 0, its `id()` is stored in the tracker's
`delimiters` field.
"""
if leaf.type == token.COMMENT:
return
self.maybe_decrement_after_for_loop_variable(leaf)
self.maybe_decrement_after_lambda_arguments(leaf)
if leaf.type in CLOSING_BRACKETS:
self.depth -= 1
opening_bracket = self.bracket_match.pop((self.depth, leaf.type))
leaf.opening_bracket = opening_bracket
leaf.bracket_depth = self.depth
if self.depth == 0:
delim = is_split_before_delimiter(leaf, self.previous)
if delim and self.previous is not None:
self.delimiters[id(self.previous)] = delim
else:
delim = is_split_after_delimiter(leaf, self.previous)
if delim:
self.delimiters[id(leaf)] = delim
if leaf.type in OPENING_BRACKETS:
self.bracket_match[self.depth, BRACKET[leaf.type]] = leaf
self.depth += 1
self.previous = leaf
self.maybe_increment_lambda_arguments(leaf)
self.maybe_increment_for_loop_variable(leaf)
def any_open_brackets(self) -> bool:
"""Return True if there is an yet unmatched open bracket on the line."""
return bool(self.bracket_match)