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
|
"""Defines parsing functions used by isort for parsing import definitions"""
from collections import OrderedDict, defaultdict, namedtuple
from io import StringIO
from itertools import chain
from typing import TYPE_CHECKING, Any, Dict, Generator, Iterator, List, NamedTuple, Optional, Tuple
from warnings import warn
from isort.format import format_natural
from isort.settings import DEFAULT_CONFIG, Config
from .comments import parse as parse_comments
from .finders import FindersManager
if TYPE_CHECKING:
from mypy_extensions import TypedDict
CommentsAboveDict = TypedDict(
"CommentsAboveDict", {"straight": Dict[str, Any], "from": Dict[str, Any]}
)
CommentsDict = TypedDict(
"CommentsDict",
{
"from": Dict[str, Any],
"straight": Dict[str, Any],
"nested": Dict[str, Any],
"above": CommentsAboveDict,
},
)
def _infer_line_separator(file_contents: str) -> str:
if "\r\n" in file_contents:
return "\r\n"
elif "\r" in file_contents:
return "\r"
else:
return "\n"
def _normalize_line(raw_line: str) -> Tuple[str, str]:
"""Normalizes import related statements in the provided line.
Returns (normalized_line: str, raw_line: str)
"""
line = raw_line.replace("from.import ", "from . import ")
line = raw_line.replace("from.cimport ", "from . cimport ")
line = line.replace("import*", "import *")
line = line.replace(" .import ", " . import ")
line = line.replace(" .cimport ", " . cimport ")
line = line.replace("\t", " ")
return (line, raw_line)
def import_type(line: str) -> Optional[str]:
"""If the current line is an import line it will return its type (from or straight)"""
if "isort:skip" in line or "isort: skip" in line or "NOQA" in line:
return None
elif line.startswith(("import ", "cimport ")):
return "straight"
elif line.startswith("from "):
return "from"
return None
def _strip_syntax(import_string: str) -> str:
import_string = import_string.replace("_import", "[[i]]")
for remove_syntax in ["\\", "(", ")", ","]:
import_string = import_string.replace(remove_syntax, " ")
import_list = import_string.split()
for key in ("from", "import", "cimport"):
if key in import_list:
import_list.remove(key)
import_string = " ".join(import_list)
import_string = import_string.replace("[[i]]", "_import")
return import_string.replace("{ ", "{|").replace(" }", "|}")
def skip_line(
line: str, in_quote: str, index: int, section_comments: List[str]
) -> Tuple[bool, str]:
"""Determine if a given line should be skipped.
Returns back a tuple containing:
(skip_line: bool,
in_quote: str,)
"""
skip_line = bool(in_quote)
if '"' in line or "'" in line:
char_index = 0
while char_index < len(line):
if line[char_index] == "\\":
char_index += 1
elif in_quote:
if line[char_index : char_index + len(in_quote)] == in_quote:
in_quote = ""
elif line[char_index] in ("'", '"'):
long_quote = line[char_index : char_index + 3]
if long_quote in ('"""', "'''"):
in_quote = long_quote
char_index += 2
else:
in_quote = line[char_index]
elif line[char_index] == "#":
break
char_index += 1
if ";" in line:
for part in (part.strip() for part in line.split(";")):
if part and not part.startswith("from ") and not part.startswith(("import ", "cimport ")):
skip_line = True
return (bool(skip_line or in_quote), in_quote)
class ParsedContent(NamedTuple):
in_lines: List[str]
lines_without_imports: List[str]
import_index: int
place_imports: Dict[str, List[str]]
import_placements: Dict[str, str]
as_map: Dict[str, List[str]]
imports: Dict[str, Dict[str, Any]]
categorized_comments: "CommentsDict"
change_count: int
original_line_count: int
line_separator: str
sections: Any
section_comments: List[str]
def file_contents(contents: str, config: Config = DEFAULT_CONFIG) -> ParsedContent:
"""Parses a python file taking out and categorizing imports."""
line_separator: str = config.line_ending or _infer_line_separator(contents)
in_lines = contents.split(line_separator)
out_lines = []
original_line_count = len(in_lines)
section_comments = [f"# {heading}" for heading in config.import_headings.values()]
finder = FindersManager(config=config)
line_count = len(in_lines)
place_imports: Dict[str, List[str]] = {}
import_placements: Dict[str, str] = {}
as_map: Dict[str, List[str]] = defaultdict(list)
imports: OrderedDict[str, Dict[str, Any]] = OrderedDict()
for section in chain(config.sections, config.forced_separate):
imports[section] = {"straight": OrderedDict(), "from": OrderedDict()}
categorized_comments: CommentsDict = {
"from": {},
"straight": {},
"nested": {},
"above": {"straight": {}, "from": {}},
}
index = 0
import_index = -1
in_quote = ""
while index < line_count:
line = in_lines[index]
index += 1
statement_index = index
(skipping_line, in_quote) = skip_line(
line, in_quote=in_quote, index=index, section_comments=section_comments
)
if line in section_comments and not skipping_line:
if import_index == -1:
import_index = index - 1
continue
if "isort:imports-" in line and line.startswith("#"):
section = line.split("isort:imports-")[-1].split()[0].upper()
place_imports[section] = []
import_placements[line] = section
elif "isort: imports-" in line and line.startswith("#"):
section = line.split("isort: imports-")[-1].split()[0].upper()
place_imports[section] = []
import_placements[line] = section
if skipping_line:
out_lines.append(line)
continue
for line in (
(line.strip() for line in line.split(";")) if ";" in line else (line,) # type: ignore
):
line, raw_line = _normalize_line(line)
type_of_import = import_type(line) or ""
if not type_of_import:
out_lines.append(raw_line)
continue
if import_index == -1:
import_index = index - 1
nested_comments = {}
import_string, comment = parse_comments(line)
comments = [comment] if comment else []
line_parts = [part for part in _strip_syntax(import_string).strip().split(" ") if part]
if (
type_of_import == "from"
and len(line_parts) == 2
and line_parts[1] != "*"
and comments
):
nested_comments[line_parts[-1]] = comments[0]
if "(" in line.split("#")[0] and index < line_count:
while not line.strip().endswith(")") and index < line_count:
line, new_comment = parse_comments(in_lines[index])
index += 1
if new_comment:
comments.append(new_comment)
stripped_line = _strip_syntax(line).strip()
if (
type_of_import == "from"
and stripped_line
and " " not in stripped_line
and new_comment
):
nested_comments[stripped_line] = comments[-1]
import_string += line_separator + line
else:
while line.strip().endswith("\\"):
line, new_comment = parse_comments(in_lines[index])
index += 1
if new_comment:
comments.append(new_comment)
# Still need to check for parentheses after an escaped line
if (
"(" in line.split("#")[0]
and ")" not in line.split("#")[0]
and index < line_count
):
stripped_line = _strip_syntax(line).strip()
if (
type_of_import == "from"
and stripped_line
and " " not in stripped_line
and new_comment
):
nested_comments[stripped_line] = comments[-1]
import_string += line_separator + line
while not line.strip().endswith(")") and index < line_count:
line, new_comment = parse_comments(in_lines[index])
index += 1
if new_comment:
comments.append(new_comment)
stripped_line = _strip_syntax(line).strip()
if (
type_of_import == "from"
and stripped_line
and " " not in stripped_line
and new_comment
):
nested_comments[stripped_line] = comments[-1]
import_string += line_separator + line
stripped_line = _strip_syntax(line).strip()
if (
type_of_import == "from"
and stripped_line
and " " not in stripped_line
and new_comment
):
nested_comments[stripped_line] = comments[-1]
if import_string.strip().endswith((" import", " cimport")) or line.strip().startswith(("import ", "cimport ")):
import_string += line_separator + line
else:
import_string = import_string.rstrip().rstrip("\\") + " " + line.lstrip()
if type_of_import == "from":
cimport: bool
import_string = import_string.replace("import(", "import (")
if " cimport " in import_string:
parts = import_string.split(" cimport ")
cimport = True
else:
parts = import_string.split(" import ")
cimport = False
from_import = parts[0].split(" ")
import_string = " cimport " if cimport else " import ".join(
[from_import[0] + " " + "".join(from_import[1:])] + parts[1:]
)
just_imports = [
item.replace("{|", "{ ").replace("|}", " }")
for item in _strip_syntax(import_string).split()
]
straight_import = True
if "as" in just_imports and (just_imports.index("as") + 1) < len(just_imports):
straight_import = False
while "as" in just_imports:
as_index = just_imports.index("as")
if type_of_import == "from":
module = just_imports[0] + "." + just_imports[as_index - 1]
as_map[module].append(just_imports[as_index + 1])
else:
module = just_imports[as_index - 1]
as_map[module].append(just_imports[as_index + 1])
if not config.combine_as_imports:
categorized_comments["straight"][module] = comments
comments = []
del just_imports[as_index : as_index + 2]
if type_of_import == "from":
import_from = just_imports.pop(0)
placed_module = finder.find(import_from)
if config.verbose:
print(f"from-type place_module for {import_from} returned {placed_module}")
if placed_module == "":
warn(
f"could not place module {import_from} of line {line} --"
" Do you need to define a default section?"
)
root = imports[placed_module][type_of_import] # type: ignore
for import_name in just_imports:
associated_comment = nested_comments.get(import_name)
if associated_comment:
categorized_comments["nested"].setdefault(import_from, {})[
import_name
] = associated_comment
comments.pop(comments.index(associated_comment))
if comments:
categorized_comments["from"].setdefault(import_from, []).extend(comments)
if len(out_lines) > max(import_index, 1) - 1:
last = out_lines and out_lines[-1].rstrip() or ""
while (
last.startswith("#")
and not last.endswith('"""')
and not last.endswith("'''")
and "isort:imports-" not in last
and "isort: imports-" not in last
):
categorized_comments["above"]["from"].setdefault(import_from, []).insert(
0, out_lines.pop(-1)
)
if len(out_lines) > max(import_index - 1, 1) - 1:
last = out_lines[-1].rstrip()
else:
last = ""
if statement_index - 1 == import_index:
import_index -= len(
categorized_comments["above"]["from"].get(import_from, [])
)
if import_from not in root:
root[import_from] = OrderedDict(
(module, straight_import) for module in just_imports
)
else:
root[import_from].update(
(module, straight_import | root[import_from].get(module, False))
for module in just_imports
)
else:
for module in just_imports:
if comments:
categorized_comments["straight"][module] = comments
comments = []
if len(out_lines) > max(import_index, +1, 1) - 1:
last = out_lines and out_lines[-1].rstrip() or ""
while (
last.startswith("#")
and not last.endswith('"""')
and not last.endswith("'''")
and "isort:imports-" not in last
and "isort: imports-" not in last
):
categorized_comments["above"]["straight"].setdefault(module, []).insert(
0, out_lines.pop(-1)
)
if len(out_lines) > 0 and len(out_lines):
last = out_lines[-1].rstrip()
else:
last = ""
if index - 1 == import_index:
import_index -= len(
categorized_comments["above"]["straight"].get(module, [])
)
placed_module = finder.find(module)
if config.verbose:
print(f"else-type place_module for {module} returned {placed_module}")
if placed_module == "":
warn(
f"could not place module {import_from} of line {line} --"
" Do you need to define a default section?"
)
straight_import |= imports[placed_module][type_of_import].get( # type: ignore
module, False
)
imports[placed_module][type_of_import][module] = straight_import # type: ignore
change_count = len(out_lines) - original_line_count
return ParsedContent(
in_lines=in_lines,
lines_without_imports=out_lines,
import_index=import_index,
place_imports=place_imports,
import_placements=import_placements,
as_map=as_map,
imports=imports,
categorized_comments=categorized_comments,
change_count=change_count,
original_line_count=original_line_count,
line_separator=line_separator,
sections=config.sections,
section_comments=section_comments,
)
|