omlish 0.0.0.dev192__py3-none-any.whl → 0.0.0.dev194__py3-none-any.whl
Sign up to get free protection for your applications and to get access to all the features.
- omlish/.manifests.json +17 -3
- omlish/__about__.py +2 -2
- omlish/codecs/base.py +2 -0
- omlish/configs/__init__.py +0 -5
- omlish/configs/formats.py +247 -0
- omlish/configs/nginx.py +72 -0
- omlish/configs/processing/__init__.py +0 -0
- omlish/configs/{flattening.py → processing/flattening.py} +31 -33
- omlish/configs/processing/inheritance.py +58 -0
- omlish/configs/processing/matching.py +53 -0
- omlish/configs/processing/names.py +50 -0
- omlish/configs/processing/rewriting.py +141 -0
- omlish/configs/processing/strings.py +45 -0
- omlish/configs/types.py +9 -0
- omlish/formats/__init__.py +4 -0
- omlish/formats/ini/__init__.py +0 -0
- omlish/formats/ini/codec.py +26 -0
- omlish/formats/ini/sections.py +45 -0
- omlish/formats/toml/__init__.py +0 -0
- omlish/formats/{toml.py → toml/codec.py} +2 -2
- omlish/formats/toml/parser.py +827 -0
- omlish/formats/toml/writer.py +124 -0
- omlish/lang/__init__.py +4 -1
- omlish/lang/iterables.py +0 -7
- omlish/lite/configs.py +38 -0
- omlish/lite/types.py +9 -0
- omlish/text/glyphsplit.py +25 -10
- {omlish-0.0.0.dev192.dist-info → omlish-0.0.0.dev194.dist-info}/METADATA +1 -1
- {omlish-0.0.0.dev192.dist-info → omlish-0.0.0.dev194.dist-info}/RECORD +33 -17
- omlish/configs/strings.py +0 -96
- {omlish-0.0.0.dev192.dist-info → omlish-0.0.0.dev194.dist-info}/LICENSE +0 -0
- {omlish-0.0.0.dev192.dist-info → omlish-0.0.0.dev194.dist-info}/WHEEL +0 -0
- {omlish-0.0.0.dev192.dist-info → omlish-0.0.0.dev194.dist-info}/entry_points.txt +0 -0
- {omlish-0.0.0.dev192.dist-info → omlish-0.0.0.dev194.dist-info}/top_level.txt +0 -0
@@ -0,0 +1,827 @@
|
|
1
|
+
# ruff: noqa: UP006 UP007
|
2
|
+
# @omlish-lite
|
3
|
+
# SPDX-License-Identifier: MIT
|
4
|
+
# SPDX-FileCopyrightText: 2021 Taneli Hukkinen
|
5
|
+
# Licensed to PSF under a Contributor Agreement.
|
6
|
+
#
|
7
|
+
# PYTHON SOFTWARE FOUNDATION LICENSE VERSION 2
|
8
|
+
# --------------------------------------------
|
9
|
+
#
|
10
|
+
# 1. This LICENSE AGREEMENT is between the Python Software Foundation ("PSF"), and the Individual or Organization
|
11
|
+
# ("Licensee") accessing and otherwise using this software ("Python") in source or binary form and its associated
|
12
|
+
# documentation.
|
13
|
+
#
|
14
|
+
# 2. Subject to the terms and conditions of this License Agreement, PSF hereby grants Licensee a nonexclusive,
|
15
|
+
# royalty-free, world-wide license to reproduce, analyze, test, perform and/or display publicly, prepare derivative
|
16
|
+
# works, distribute, and otherwise use Python alone or in any derivative version, provided, however, that PSF's License
|
17
|
+
# Agreement and PSF's notice of copyright, i.e., "Copyright (c) 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009,
|
18
|
+
# 2010, 2011, 2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023 Python Software Foundation; All
|
19
|
+
# Rights Reserved" are retained in Python alone or in any derivative version prepared by Licensee.
|
20
|
+
#
|
21
|
+
# 3. In the event Licensee prepares a derivative work that is based on or incorporates Python or any part thereof, and
|
22
|
+
# wants to make the derivative work available to others as provided herein, then Licensee hereby agrees to include in
|
23
|
+
# any such work a brief summary of the changes made to Python.
|
24
|
+
#
|
25
|
+
# 4. PSF is making Python available to Licensee on an "AS IS" basis. PSF MAKES NO REPRESENTATIONS OR WARRANTIES,
|
26
|
+
# EXPRESS OR IMPLIED. BY WAY OF EXAMPLE, BUT NOT LIMITATION, PSF MAKES NO AND DISCLAIMS ANY REPRESENTATION OR WARRANTY
|
27
|
+
# OF MERCHANTABILITY OR FITNESS FOR ANY PARTICULAR PURPOSE OR THAT THE USE OF PYTHON WILL NOT INFRINGE ANY THIRD PARTY
|
28
|
+
# RIGHTS.
|
29
|
+
#
|
30
|
+
# 5. PSF SHALL NOT BE LIABLE TO LICENSEE OR ANY OTHER USERS OF PYTHON FOR ANY INCIDENTAL, SPECIAL, OR CONSEQUENTIAL
|
31
|
+
# DAMAGES OR LOSS AS A RESULT OF MODIFYING, DISTRIBUTING, OR OTHERWISE USING PYTHON, OR ANY DERIVATIVE THEREOF, EVEN IF
|
32
|
+
# ADVISED OF THE POSSIBILITY THEREOF.
|
33
|
+
#
|
34
|
+
# 6. This License Agreement will automatically terminate upon a material breach of its terms and conditions.
|
35
|
+
#
|
36
|
+
# 7. Nothing in this License Agreement shall be deemed to create any relationship of agency, partnership, or joint
|
37
|
+
# venture between PSF and Licensee. This License Agreement does not grant permission to use PSF trademarks or trade
|
38
|
+
# name in a trademark sense to endorse or promote products or services of Licensee, or any third party.
|
39
|
+
#
|
40
|
+
# 8. By copying, installing or otherwise using Python, Licensee agrees to be bound by the terms and conditions of this
|
41
|
+
# License Agreement.
|
42
|
+
#
|
43
|
+
# https://github.com/python/cpython/blob/9ce90206b7a4649600218cf0bd4826db79c9a312/Lib/tomllib/_parser.py
|
44
|
+
import datetime
|
45
|
+
import functools
|
46
|
+
import re
|
47
|
+
import string
|
48
|
+
import types
|
49
|
+
import typing as ta
|
50
|
+
|
51
|
+
|
52
|
+
TomlParseFloat = ta.Callable[[str], ta.Any]
|
53
|
+
TomlKey = ta.Tuple[str, ...]
|
54
|
+
TomlPos = int # ta.TypeAlias
|
55
|
+
|
56
|
+
|
57
|
+
##
|
58
|
+
|
59
|
+
|
60
|
+
_TOML_TIME_RE_STR = r'([01][0-9]|2[0-3]):([0-5][0-9]):([0-5][0-9])(?:\.([0-9]{1,6})[0-9]*)?'
|
61
|
+
|
62
|
+
TOML_RE_NUMBER = re.compile(
|
63
|
+
r"""
|
64
|
+
0
|
65
|
+
(?:
|
66
|
+
x[0-9A-Fa-f](?:_?[0-9A-Fa-f])* # hex
|
67
|
+
|
|
68
|
+
b[01](?:_?[01])* # bin
|
69
|
+
|
|
70
|
+
o[0-7](?:_?[0-7])* # oct
|
71
|
+
)
|
72
|
+
|
|
73
|
+
[+-]?(?:0|[1-9](?:_?[0-9])*) # dec, integer part
|
74
|
+
(?P<floatpart>
|
75
|
+
(?:\.[0-9](?:_?[0-9])*)? # optional fractional part
|
76
|
+
(?:[eE][+-]?[0-9](?:_?[0-9])*)? # optional exponent part
|
77
|
+
)
|
78
|
+
""",
|
79
|
+
flags=re.VERBOSE,
|
80
|
+
)
|
81
|
+
TOML_RE_LOCALTIME = re.compile(_TOML_TIME_RE_STR)
|
82
|
+
TOML_RE_DATETIME = re.compile(
|
83
|
+
rf"""
|
84
|
+
([0-9]{{4}})-(0[1-9]|1[0-2])-(0[1-9]|[12][0-9]|3[01]) # date, e.g. 1988-10-27
|
85
|
+
(?:
|
86
|
+
[Tt ]
|
87
|
+
{_TOML_TIME_RE_STR}
|
88
|
+
(?:([Zz])|([+-])([01][0-9]|2[0-3]):([0-5][0-9]))? # optional time offset
|
89
|
+
)?
|
90
|
+
""",
|
91
|
+
flags=re.VERBOSE,
|
92
|
+
)
|
93
|
+
|
94
|
+
|
95
|
+
def toml_match_to_datetime(match: re.Match) -> ta.Union[datetime.datetime, datetime.date]:
|
96
|
+
"""Convert a `RE_DATETIME` match to `datetime.datetime` or `datetime.date`.
|
97
|
+
|
98
|
+
Raises ValueError if the match does not correspond to a valid date or datetime.
|
99
|
+
"""
|
100
|
+
(
|
101
|
+
year_str,
|
102
|
+
month_str,
|
103
|
+
day_str,
|
104
|
+
hour_str,
|
105
|
+
minute_str,
|
106
|
+
sec_str,
|
107
|
+
micros_str,
|
108
|
+
zulu_time,
|
109
|
+
offset_sign_str,
|
110
|
+
offset_hour_str,
|
111
|
+
offset_minute_str,
|
112
|
+
) = match.groups()
|
113
|
+
year, month, day = int(year_str), int(month_str), int(day_str)
|
114
|
+
if hour_str is None:
|
115
|
+
return datetime.date(year, month, day)
|
116
|
+
hour, minute, sec = int(hour_str), int(minute_str), int(sec_str)
|
117
|
+
micros = int(micros_str.ljust(6, '0')) if micros_str else 0
|
118
|
+
if offset_sign_str:
|
119
|
+
tz: ta.Optional[datetime.tzinfo] = toml_cached_tz(
|
120
|
+
offset_hour_str, offset_minute_str, offset_sign_str,
|
121
|
+
)
|
122
|
+
elif zulu_time:
|
123
|
+
tz = datetime.UTC
|
124
|
+
else: # local date-time
|
125
|
+
tz = None
|
126
|
+
return datetime.datetime(year, month, day, hour, minute, sec, micros, tzinfo=tz)
|
127
|
+
|
128
|
+
|
129
|
+
@functools.lru_cache() # noqa
|
130
|
+
def toml_cached_tz(hour_str: str, minute_str: str, sign_str: str) -> datetime.timezone:
|
131
|
+
sign = 1 if sign_str == '+' else -1
|
132
|
+
return datetime.timezone(
|
133
|
+
datetime.timedelta(
|
134
|
+
hours=sign * int(hour_str),
|
135
|
+
minutes=sign * int(minute_str),
|
136
|
+
),
|
137
|
+
)
|
138
|
+
|
139
|
+
|
140
|
+
def toml_match_to_localtime(match: re.Match) -> datetime.time:
|
141
|
+
hour_str, minute_str, sec_str, micros_str = match.groups()
|
142
|
+
micros = int(micros_str.ljust(6, '0')) if micros_str else 0
|
143
|
+
return datetime.time(int(hour_str), int(minute_str), int(sec_str), micros)
|
144
|
+
|
145
|
+
|
146
|
+
def toml_match_to_number(match: re.Match, parse_float: TomlParseFloat) -> ta.Any:
|
147
|
+
if match.group('floatpart'):
|
148
|
+
return parse_float(match.group())
|
149
|
+
return int(match.group(), 0)
|
150
|
+
|
151
|
+
|
152
|
+
TOML_ASCII_CTRL = frozenset(chr(i) for i in range(32)) | frozenset(chr(127))
|
153
|
+
|
154
|
+
# Neither of these sets include quotation mark or backslash. They are currently handled as separate cases in the parser
|
155
|
+
# functions.
|
156
|
+
TOML_ILLEGAL_BASIC_STR_CHARS = TOML_ASCII_CTRL - frozenset('\t')
|
157
|
+
TOML_ILLEGAL_MULTILINE_BASIC_STR_CHARS = TOML_ASCII_CTRL - frozenset('\t\n')
|
158
|
+
|
159
|
+
TOML_ILLEGAL_LITERAL_STR_CHARS = TOML_ILLEGAL_BASIC_STR_CHARS
|
160
|
+
TOML_ILLEGAL_MULTILINE_LITERAL_STR_CHARS = TOML_ILLEGAL_MULTILINE_BASIC_STR_CHARS
|
161
|
+
|
162
|
+
TOML_ILLEGAL_COMMENT_CHARS = TOML_ILLEGAL_BASIC_STR_CHARS
|
163
|
+
|
164
|
+
TOML_WS = frozenset(' \t')
|
165
|
+
TOML_WS_AND_NEWLINE = TOML_WS | frozenset('\n')
|
166
|
+
TOML_BARE_KEY_CHARS = frozenset(string.ascii_letters + string.digits + '-_')
|
167
|
+
TOML_KEY_INITIAL_CHARS = TOML_BARE_KEY_CHARS | frozenset("\"'")
|
168
|
+
TOML_HEXDIGIT_CHARS = frozenset(string.hexdigits)
|
169
|
+
|
170
|
+
TOML_BASIC_STR_ESCAPE_REPLACEMENTS = types.MappingProxyType(
|
171
|
+
{
|
172
|
+
'\\b': '\u0008', # backspace
|
173
|
+
'\\t': '\u0009', # tab
|
174
|
+
'\\n': '\u000A', # linefeed
|
175
|
+
'\\f': '\u000C', # form feed
|
176
|
+
'\\r': '\u000D', # carriage return
|
177
|
+
'\\"': '\u0022', # quote
|
178
|
+
'\\\\': '\u005C', # backslash
|
179
|
+
},
|
180
|
+
)
|
181
|
+
|
182
|
+
|
183
|
+
class TomlDecodeError(ValueError):
|
184
|
+
"""An error raised if a document is not valid TOML."""
|
185
|
+
|
186
|
+
|
187
|
+
def toml_load(fp: ta.BinaryIO, /, *, parse_float: TomlParseFloat = float) -> ta.Dict[str, ta.Any]:
|
188
|
+
"""Parse TOML from a binary file object."""
|
189
|
+
b = fp.read()
|
190
|
+
try:
|
191
|
+
s = b.decode()
|
192
|
+
except AttributeError:
|
193
|
+
raise TypeError("File must be opened in binary mode, e.g. use `open('foo.toml', 'rb')`") from None
|
194
|
+
return toml_loads(s, parse_float=parse_float)
|
195
|
+
|
196
|
+
|
197
|
+
def toml_loads(s: str, /, *, parse_float: TomlParseFloat = float) -> ta.Dict[str, ta.Any]: # noqa: C901
|
198
|
+
"""Parse TOML from a string."""
|
199
|
+
|
200
|
+
# The spec allows converting "\r\n" to "\n", even in string literals. Let's do so to simplify parsing.
|
201
|
+
try:
|
202
|
+
src = s.replace('\r\n', '\n')
|
203
|
+
except (AttributeError, TypeError):
|
204
|
+
raise TypeError(f"Expected str object, not '{type(s).__qualname__}'") from None
|
205
|
+
pos = 0
|
206
|
+
out = TomlOutput(TomlNestedDict(), TomlFlags())
|
207
|
+
header: TomlKey = ()
|
208
|
+
parse_float = toml_make_safe_parse_float(parse_float)
|
209
|
+
|
210
|
+
# Parse one statement at a time (typically means one line in TOML source)
|
211
|
+
while True:
|
212
|
+
# 1. Skip line leading whitespace
|
213
|
+
pos = toml_skip_chars(src, pos, TOML_WS)
|
214
|
+
|
215
|
+
# 2. Parse rules. Expect one of the following:
|
216
|
+
# - end of file
|
217
|
+
# - end of line
|
218
|
+
# - comment
|
219
|
+
# - key/value pair
|
220
|
+
# - append dict to list (and move to its namespace)
|
221
|
+
# - create dict (and move to its namespace)
|
222
|
+
# Skip trailing whitespace when applicable.
|
223
|
+
try:
|
224
|
+
char = src[pos]
|
225
|
+
except IndexError:
|
226
|
+
break
|
227
|
+
if char == '\n':
|
228
|
+
pos += 1
|
229
|
+
continue
|
230
|
+
if char in TOML_KEY_INITIAL_CHARS:
|
231
|
+
pos = toml_key_value_rule(src, pos, out, header, parse_float)
|
232
|
+
pos = toml_skip_chars(src, pos, TOML_WS)
|
233
|
+
elif char == '[':
|
234
|
+
try:
|
235
|
+
second_char: ta.Optional[str] = src[pos + 1]
|
236
|
+
except IndexError:
|
237
|
+
second_char = None
|
238
|
+
out.flags.finalize_pending()
|
239
|
+
if second_char == '[':
|
240
|
+
pos, header = toml_create_list_rule(src, pos, out)
|
241
|
+
else:
|
242
|
+
pos, header = toml_create_dict_rule(src, pos, out)
|
243
|
+
pos = toml_skip_chars(src, pos, TOML_WS)
|
244
|
+
elif char != '#':
|
245
|
+
raise toml_suffixed_err(src, pos, 'Invalid statement')
|
246
|
+
|
247
|
+
# 3. Skip comment
|
248
|
+
pos = toml_skip_comment(src, pos)
|
249
|
+
|
250
|
+
# 4. Expect end of line or end of file
|
251
|
+
try:
|
252
|
+
char = src[pos]
|
253
|
+
except IndexError:
|
254
|
+
break
|
255
|
+
if char != '\n':
|
256
|
+
raise toml_suffixed_err(
|
257
|
+
src, pos, 'Expected newline or end of document after a statement',
|
258
|
+
)
|
259
|
+
pos += 1
|
260
|
+
|
261
|
+
return out.data.dict
|
262
|
+
|
263
|
+
|
264
|
+
class TomlFlags:
|
265
|
+
"""Flags that map to parsed keys/namespaces."""
|
266
|
+
|
267
|
+
# Marks an immutable namespace (inline array or inline table).
|
268
|
+
FROZEN = 0
|
269
|
+
# Marks a nest that has been explicitly created and can no longer be opened using the "[table]" syntax.
|
270
|
+
EXPLICIT_NEST = 1
|
271
|
+
|
272
|
+
def __init__(self) -> None:
|
273
|
+
self._flags: ta.Dict[str, dict] = {}
|
274
|
+
self._pending_flags: ta.Set[ta.Tuple[TomlKey, int]] = set()
|
275
|
+
|
276
|
+
def add_pending(self, key: TomlKey, flag: int) -> None:
|
277
|
+
self._pending_flags.add((key, flag))
|
278
|
+
|
279
|
+
def finalize_pending(self) -> None:
|
280
|
+
for key, flag in self._pending_flags:
|
281
|
+
self.set(key, flag, recursive=False)
|
282
|
+
self._pending_flags.clear()
|
283
|
+
|
284
|
+
def unset_all(self, key: TomlKey) -> None:
|
285
|
+
cont = self._flags
|
286
|
+
for k in key[:-1]:
|
287
|
+
if k not in cont:
|
288
|
+
return
|
289
|
+
cont = cont[k]['nested']
|
290
|
+
cont.pop(key[-1], None)
|
291
|
+
|
292
|
+
def set(self, key: TomlKey, flag: int, *, recursive: bool) -> None: # noqa: A003
|
293
|
+
cont = self._flags
|
294
|
+
key_parent, key_stem = key[:-1], key[-1]
|
295
|
+
for k in key_parent:
|
296
|
+
if k not in cont:
|
297
|
+
cont[k] = {'flags': set(), 'recursive_flags': set(), 'nested': {}}
|
298
|
+
cont = cont[k]['nested']
|
299
|
+
if key_stem not in cont:
|
300
|
+
cont[key_stem] = {'flags': set(), 'recursive_flags': set(), 'nested': {}}
|
301
|
+
cont[key_stem]['recursive_flags' if recursive else 'flags'].add(flag)
|
302
|
+
|
303
|
+
def is_(self, key: TomlKey, flag: int) -> bool:
|
304
|
+
if not key:
|
305
|
+
return False # document root has no flags
|
306
|
+
cont = self._flags
|
307
|
+
for k in key[:-1]:
|
308
|
+
if k not in cont:
|
309
|
+
return False
|
310
|
+
inner_cont = cont[k]
|
311
|
+
if flag in inner_cont['recursive_flags']:
|
312
|
+
return True
|
313
|
+
cont = inner_cont['nested']
|
314
|
+
key_stem = key[-1]
|
315
|
+
if key_stem in cont:
|
316
|
+
cont = cont[key_stem]
|
317
|
+
return flag in cont['flags'] or flag in cont['recursive_flags']
|
318
|
+
return False
|
319
|
+
|
320
|
+
|
321
|
+
class TomlNestedDict:
|
322
|
+
def __init__(self) -> None:
|
323
|
+
# The parsed content of the TOML document
|
324
|
+
self.dict: ta.Dict[str, ta.Any] = {}
|
325
|
+
|
326
|
+
def get_or_create_nest(
|
327
|
+
self,
|
328
|
+
key: TomlKey,
|
329
|
+
*,
|
330
|
+
access_lists: bool = True,
|
331
|
+
) -> dict:
|
332
|
+
cont: ta.Any = self.dict
|
333
|
+
for k in key:
|
334
|
+
if k not in cont:
|
335
|
+
cont[k] = {}
|
336
|
+
cont = cont[k]
|
337
|
+
if access_lists and isinstance(cont, list):
|
338
|
+
cont = cont[-1]
|
339
|
+
if not isinstance(cont, dict):
|
340
|
+
raise KeyError('There is no nest behind this key')
|
341
|
+
return cont
|
342
|
+
|
343
|
+
def append_nest_to_list(self, key: TomlKey) -> None:
|
344
|
+
cont = self.get_or_create_nest(key[:-1])
|
345
|
+
last_key = key[-1]
|
346
|
+
if last_key in cont:
|
347
|
+
list_ = cont[last_key]
|
348
|
+
if not isinstance(list_, list):
|
349
|
+
raise KeyError('An object other than list found behind this key')
|
350
|
+
list_.append({})
|
351
|
+
else:
|
352
|
+
cont[last_key] = [{}]
|
353
|
+
|
354
|
+
|
355
|
+
class TomlOutput(ta.NamedTuple):
|
356
|
+
data: TomlNestedDict
|
357
|
+
flags: TomlFlags
|
358
|
+
|
359
|
+
|
360
|
+
def toml_skip_chars(src: str, pos: TomlPos, chars: ta.Iterable[str]) -> TomlPos:
|
361
|
+
try:
|
362
|
+
while src[pos] in chars:
|
363
|
+
pos += 1
|
364
|
+
except IndexError:
|
365
|
+
pass
|
366
|
+
return pos
|
367
|
+
|
368
|
+
|
369
|
+
def toml_skip_until(
|
370
|
+
src: str,
|
371
|
+
pos: TomlPos,
|
372
|
+
expect: str,
|
373
|
+
*,
|
374
|
+
error_on: ta.FrozenSet[str],
|
375
|
+
error_on_eof: bool,
|
376
|
+
) -> TomlPos:
|
377
|
+
try:
|
378
|
+
new_pos = src.index(expect, pos)
|
379
|
+
except ValueError:
|
380
|
+
new_pos = len(src)
|
381
|
+
if error_on_eof:
|
382
|
+
raise toml_suffixed_err(src, new_pos, f'Expected {expect!r}') from None
|
383
|
+
|
384
|
+
if not error_on.isdisjoint(src[pos:new_pos]):
|
385
|
+
while src[pos] not in error_on:
|
386
|
+
pos += 1
|
387
|
+
raise toml_suffixed_err(src, pos, f'Found invalid character {src[pos]!r}')
|
388
|
+
return new_pos
|
389
|
+
|
390
|
+
|
391
|
+
def toml_skip_comment(src: str, pos: TomlPos) -> TomlPos:
|
392
|
+
try:
|
393
|
+
char: ta.Optional[str] = src[pos]
|
394
|
+
except IndexError:
|
395
|
+
char = None
|
396
|
+
if char == '#':
|
397
|
+
return toml_skip_until(
|
398
|
+
src, pos + 1, '\n', error_on=TOML_ILLEGAL_COMMENT_CHARS, error_on_eof=False,
|
399
|
+
)
|
400
|
+
return pos
|
401
|
+
|
402
|
+
|
403
|
+
def toml_skip_comments_and_array_ws(src: str, pos: TomlPos) -> TomlPos:
|
404
|
+
while True:
|
405
|
+
pos_before_skip = pos
|
406
|
+
pos = toml_skip_chars(src, pos, TOML_WS_AND_NEWLINE)
|
407
|
+
pos = toml_skip_comment(src, pos)
|
408
|
+
if pos == pos_before_skip:
|
409
|
+
return pos
|
410
|
+
|
411
|
+
|
412
|
+
def toml_create_dict_rule(src: str, pos: TomlPos, out: TomlOutput) -> ta.Tuple[TomlPos, TomlKey]:
|
413
|
+
pos += 1 # Skip "["
|
414
|
+
pos = toml_skip_chars(src, pos, TOML_WS)
|
415
|
+
pos, key = toml_parse_key(src, pos)
|
416
|
+
|
417
|
+
if out.flags.is_(key, TomlFlags.EXPLICIT_NEST) or out.flags.is_(key, TomlFlags.FROZEN):
|
418
|
+
raise toml_suffixed_err(src, pos, f'Cannot declare {key} twice')
|
419
|
+
out.flags.set(key, TomlFlags.EXPLICIT_NEST, recursive=False)
|
420
|
+
try:
|
421
|
+
out.data.get_or_create_nest(key)
|
422
|
+
except KeyError:
|
423
|
+
raise toml_suffixed_err(src, pos, 'Cannot overwrite a value') from None
|
424
|
+
|
425
|
+
if not src.startswith(']', pos):
|
426
|
+
raise toml_suffixed_err(src, pos, "Expected ']' at the end of a table declaration")
|
427
|
+
return pos + 1, key
|
428
|
+
|
429
|
+
|
430
|
+
def toml_create_list_rule(src: str, pos: TomlPos, out: TomlOutput) -> ta.Tuple[TomlPos, TomlKey]:
|
431
|
+
pos += 2 # Skip "[["
|
432
|
+
pos = toml_skip_chars(src, pos, TOML_WS)
|
433
|
+
pos, key = toml_parse_key(src, pos)
|
434
|
+
|
435
|
+
if out.flags.is_(key, TomlFlags.FROZEN):
|
436
|
+
raise toml_suffixed_err(src, pos, f'Cannot mutate immutable namespace {key}')
|
437
|
+
# Free the namespace now that it points to another empty list item...
|
438
|
+
out.flags.unset_all(key)
|
439
|
+
# ...but this key precisely is still prohibited from table declaration
|
440
|
+
out.flags.set(key, TomlFlags.EXPLICIT_NEST, recursive=False)
|
441
|
+
try:
|
442
|
+
out.data.append_nest_to_list(key)
|
443
|
+
except KeyError:
|
444
|
+
raise toml_suffixed_err(src, pos, 'Cannot overwrite a value') from None
|
445
|
+
|
446
|
+
if not src.startswith(']]', pos):
|
447
|
+
raise toml_suffixed_err(src, pos, "Expected ']]' at the end of an array declaration")
|
448
|
+
return pos + 2, key
|
449
|
+
|
450
|
+
|
451
|
+
def toml_key_value_rule(
|
452
|
+
src: str,
|
453
|
+
pos: TomlPos,
|
454
|
+
out: TomlOutput,
|
455
|
+
header: TomlKey,
|
456
|
+
parse_float: TomlParseFloat,
|
457
|
+
) -> TomlPos:
|
458
|
+
pos, key, value = toml_parse_key_value_pair(src, pos, parse_float)
|
459
|
+
key_parent, key_stem = key[:-1], key[-1]
|
460
|
+
abs_key_parent = header + key_parent
|
461
|
+
|
462
|
+
relative_path_cont_keys = (header + key[:i] for i in range(1, len(key)))
|
463
|
+
for cont_key in relative_path_cont_keys:
|
464
|
+
# Check that dotted key syntax does not redefine an existing table
|
465
|
+
if out.flags.is_(cont_key, TomlFlags.EXPLICIT_NEST):
|
466
|
+
raise toml_suffixed_err(src, pos, f'Cannot redefine namespace {cont_key}')
|
467
|
+
# Containers in the relative path can't be opened with the table syntax or dotted key/value syntax in following
|
468
|
+
# table sections.
|
469
|
+
out.flags.add_pending(cont_key, TomlFlags.EXPLICIT_NEST)
|
470
|
+
|
471
|
+
if out.flags.is_(abs_key_parent, TomlFlags.FROZEN):
|
472
|
+
raise toml_suffixed_err(
|
473
|
+
src,
|
474
|
+
pos,
|
475
|
+
f'Cannot mutate immutable namespace {abs_key_parent}',
|
476
|
+
)
|
477
|
+
|
478
|
+
try:
|
479
|
+
nest = out.data.get_or_create_nest(abs_key_parent)
|
480
|
+
except KeyError:
|
481
|
+
raise toml_suffixed_err(src, pos, 'Cannot overwrite a value') from None
|
482
|
+
if key_stem in nest:
|
483
|
+
raise toml_suffixed_err(src, pos, 'Cannot overwrite a value')
|
484
|
+
# Mark inline table and array namespaces recursively immutable
|
485
|
+
if isinstance(value, (dict, list)):
|
486
|
+
out.flags.set(header + key, TomlFlags.FROZEN, recursive=True)
|
487
|
+
nest[key_stem] = value
|
488
|
+
return pos
|
489
|
+
|
490
|
+
|
491
|
+
def toml_parse_key_value_pair(
|
492
|
+
src: str,
|
493
|
+
pos: TomlPos,
|
494
|
+
parse_float: TomlParseFloat,
|
495
|
+
) -> ta.Tuple[TomlPos, TomlKey, ta.Any]:
|
496
|
+
pos, key = toml_parse_key(src, pos)
|
497
|
+
try:
|
498
|
+
char: ta.Optional[str] = src[pos]
|
499
|
+
except IndexError:
|
500
|
+
char = None
|
501
|
+
if char != '=':
|
502
|
+
raise toml_suffixed_err(src, pos, "Expected '=' after a key in a key/value pair")
|
503
|
+
pos += 1
|
504
|
+
pos = toml_skip_chars(src, pos, TOML_WS)
|
505
|
+
pos, value = toml_parse_value(src, pos, parse_float)
|
506
|
+
return pos, key, value
|
507
|
+
|
508
|
+
|
509
|
+
def toml_parse_key(src: str, pos: TomlPos) -> ta.Tuple[TomlPos, TomlKey]:
|
510
|
+
pos, key_part = toml_parse_key_part(src, pos)
|
511
|
+
key: TomlKey = (key_part,)
|
512
|
+
pos = toml_skip_chars(src, pos, TOML_WS)
|
513
|
+
while True:
|
514
|
+
try:
|
515
|
+
char: ta.Optional[str] = src[pos]
|
516
|
+
except IndexError:
|
517
|
+
char = None
|
518
|
+
if char != '.':
|
519
|
+
return pos, key
|
520
|
+
pos += 1
|
521
|
+
pos = toml_skip_chars(src, pos, TOML_WS)
|
522
|
+
pos, key_part = toml_parse_key_part(src, pos)
|
523
|
+
key += (key_part,)
|
524
|
+
pos = toml_skip_chars(src, pos, TOML_WS)
|
525
|
+
|
526
|
+
|
527
|
+
def toml_parse_key_part(src: str, pos: TomlPos) -> ta.Tuple[TomlPos, str]:
|
528
|
+
try:
|
529
|
+
char: ta.Optional[str] = src[pos]
|
530
|
+
except IndexError:
|
531
|
+
char = None
|
532
|
+
if char in TOML_BARE_KEY_CHARS:
|
533
|
+
start_pos = pos
|
534
|
+
pos = toml_skip_chars(src, pos, TOML_BARE_KEY_CHARS)
|
535
|
+
return pos, src[start_pos:pos]
|
536
|
+
if char == "'":
|
537
|
+
return toml_parse_literal_str(src, pos)
|
538
|
+
if char == '"':
|
539
|
+
return toml_parse_one_line_basic_str(src, pos)
|
540
|
+
raise toml_suffixed_err(src, pos, 'Invalid initial character for a key part')
|
541
|
+
|
542
|
+
|
543
|
+
def toml_parse_one_line_basic_str(src: str, pos: TomlPos) -> ta.Tuple[TomlPos, str]:
|
544
|
+
pos += 1
|
545
|
+
return toml_parse_basic_str(src, pos, multiline=False)
|
546
|
+
|
547
|
+
|
548
|
+
def toml_parse_array(src: str, pos: TomlPos, parse_float: TomlParseFloat) -> ta.Tuple[TomlPos, list]:
|
549
|
+
pos += 1
|
550
|
+
array: list = []
|
551
|
+
|
552
|
+
pos = toml_skip_comments_and_array_ws(src, pos)
|
553
|
+
if src.startswith(']', pos):
|
554
|
+
return pos + 1, array
|
555
|
+
while True:
|
556
|
+
pos, val = toml_parse_value(src, pos, parse_float)
|
557
|
+
array.append(val)
|
558
|
+
pos = toml_skip_comments_and_array_ws(src, pos)
|
559
|
+
|
560
|
+
c = src[pos:pos + 1]
|
561
|
+
if c == ']':
|
562
|
+
return pos + 1, array
|
563
|
+
if c != ',':
|
564
|
+
raise toml_suffixed_err(src, pos, 'Unclosed array')
|
565
|
+
pos += 1
|
566
|
+
|
567
|
+
pos = toml_skip_comments_and_array_ws(src, pos)
|
568
|
+
if src.startswith(']', pos):
|
569
|
+
return pos + 1, array
|
570
|
+
|
571
|
+
|
572
|
+
def toml_parse_inline_table(src: str, pos: TomlPos, parse_float: TomlParseFloat) -> ta.Tuple[TomlPos, dict]:
|
573
|
+
pos += 1
|
574
|
+
nested_dict = TomlNestedDict()
|
575
|
+
flags = TomlFlags()
|
576
|
+
|
577
|
+
pos = toml_skip_chars(src, pos, TOML_WS)
|
578
|
+
if src.startswith('}', pos):
|
579
|
+
return pos + 1, nested_dict.dict
|
580
|
+
while True:
|
581
|
+
pos, key, value = toml_parse_key_value_pair(src, pos, parse_float)
|
582
|
+
key_parent, key_stem = key[:-1], key[-1]
|
583
|
+
if flags.is_(key, TomlFlags.FROZEN):
|
584
|
+
raise toml_suffixed_err(src, pos, f'Cannot mutate immutable namespace {key}')
|
585
|
+
try:
|
586
|
+
nest = nested_dict.get_or_create_nest(key_parent, access_lists=False)
|
587
|
+
except KeyError:
|
588
|
+
raise toml_suffixed_err(src, pos, 'Cannot overwrite a value') from None
|
589
|
+
if key_stem in nest:
|
590
|
+
raise toml_suffixed_err(src, pos, f'Duplicate inline table key {key_stem!r}')
|
591
|
+
nest[key_stem] = value
|
592
|
+
pos = toml_skip_chars(src, pos, TOML_WS)
|
593
|
+
c = src[pos:pos + 1]
|
594
|
+
if c == '}':
|
595
|
+
return pos + 1, nested_dict.dict
|
596
|
+
if c != ',':
|
597
|
+
raise toml_suffixed_err(src, pos, 'Unclosed inline table')
|
598
|
+
if isinstance(value, (dict, list)):
|
599
|
+
flags.set(key, TomlFlags.FROZEN, recursive=True)
|
600
|
+
pos += 1
|
601
|
+
pos = toml_skip_chars(src, pos, TOML_WS)
|
602
|
+
|
603
|
+
|
604
|
+
def toml_parse_basic_str_escape(
|
605
|
+
src: str,
|
606
|
+
pos: TomlPos,
|
607
|
+
*,
|
608
|
+
multiline: bool = False,
|
609
|
+
) -> ta.Tuple[TomlPos, str]:
|
610
|
+
escape_id = src[pos:pos + 2]
|
611
|
+
pos += 2
|
612
|
+
if multiline and escape_id in {'\\ ', '\\\t', '\\\n'}:
|
613
|
+
# Skip whitespace until next non-whitespace character or end of the doc. Error if non-whitespace is found before
|
614
|
+
# newline.
|
615
|
+
if escape_id != '\\\n':
|
616
|
+
pos = toml_skip_chars(src, pos, TOML_WS)
|
617
|
+
try:
|
618
|
+
char = src[pos]
|
619
|
+
except IndexError:
|
620
|
+
return pos, ''
|
621
|
+
if char != '\n':
|
622
|
+
raise toml_suffixed_err(src, pos, "Unescaped '\\' in a string")
|
623
|
+
pos += 1
|
624
|
+
pos = toml_skip_chars(src, pos, TOML_WS_AND_NEWLINE)
|
625
|
+
return pos, ''
|
626
|
+
if escape_id == '\\u':
|
627
|
+
return toml_parse_hex_char(src, pos, 4)
|
628
|
+
if escape_id == '\\U':
|
629
|
+
return toml_parse_hex_char(src, pos, 8)
|
630
|
+
try:
|
631
|
+
return pos, TOML_BASIC_STR_ESCAPE_REPLACEMENTS[escape_id]
|
632
|
+
except KeyError:
|
633
|
+
raise toml_suffixed_err(src, pos, "Unescaped '\\' in a string") from None
|
634
|
+
|
635
|
+
|
636
|
+
def toml_parse_basic_str_escape_multiline(src: str, pos: TomlPos) -> ta.Tuple[TomlPos, str]:
|
637
|
+
return toml_parse_basic_str_escape(src, pos, multiline=True)
|
638
|
+
|
639
|
+
|
640
|
+
def toml_parse_hex_char(src: str, pos: TomlPos, hex_len: int) -> ta.Tuple[TomlPos, str]:
|
641
|
+
hex_str = src[pos:pos + hex_len]
|
642
|
+
if len(hex_str) != hex_len or not TOML_HEXDIGIT_CHARS.issuperset(hex_str):
|
643
|
+
raise toml_suffixed_err(src, pos, 'Invalid hex value')
|
644
|
+
pos += hex_len
|
645
|
+
hex_int = int(hex_str, 16)
|
646
|
+
if not toml_is_unicode_scalar_value(hex_int):
|
647
|
+
raise toml_suffixed_err(src, pos, 'Escaped character is not a Unicode scalar value')
|
648
|
+
return pos, chr(hex_int)
|
649
|
+
|
650
|
+
|
651
|
+
def toml_parse_literal_str(src: str, pos: TomlPos) -> ta.Tuple[TomlPos, str]:
|
652
|
+
pos += 1 # Skip starting apostrophe
|
653
|
+
start_pos = pos
|
654
|
+
pos = toml_skip_until(
|
655
|
+
src, pos, "'", error_on=TOML_ILLEGAL_LITERAL_STR_CHARS, error_on_eof=True,
|
656
|
+
)
|
657
|
+
return pos + 1, src[start_pos:pos] # Skip ending apostrophe
|
658
|
+
|
659
|
+
|
660
|
+
def toml_parse_multiline_str(src: str, pos: TomlPos, *, literal: bool) -> ta.Tuple[TomlPos, str]:
|
661
|
+
pos += 3
|
662
|
+
if src.startswith('\n', pos):
|
663
|
+
pos += 1
|
664
|
+
|
665
|
+
if literal:
|
666
|
+
delim = "'"
|
667
|
+
end_pos = toml_skip_until(
|
668
|
+
src,
|
669
|
+
pos,
|
670
|
+
"'''",
|
671
|
+
error_on=TOML_ILLEGAL_MULTILINE_LITERAL_STR_CHARS,
|
672
|
+
error_on_eof=True,
|
673
|
+
)
|
674
|
+
result = src[pos:end_pos]
|
675
|
+
pos = end_pos + 3
|
676
|
+
else:
|
677
|
+
delim = '"'
|
678
|
+
pos, result = toml_parse_basic_str(src, pos, multiline=True)
|
679
|
+
|
680
|
+
# Add at maximum two extra apostrophes/quotes if the end sequence is 4 or 5 chars long instead of just 3.
|
681
|
+
if not src.startswith(delim, pos):
|
682
|
+
return pos, result
|
683
|
+
pos += 1
|
684
|
+
if not src.startswith(delim, pos):
|
685
|
+
return pos, result + delim
|
686
|
+
pos += 1
|
687
|
+
return pos, result + (delim * 2)
|
688
|
+
|
689
|
+
|
690
|
+
def toml_parse_basic_str(src: str, pos: TomlPos, *, multiline: bool) -> ta.Tuple[TomlPos, str]:
|
691
|
+
if multiline:
|
692
|
+
error_on = TOML_ILLEGAL_MULTILINE_BASIC_STR_CHARS
|
693
|
+
parse_escapes = toml_parse_basic_str_escape_multiline
|
694
|
+
else:
|
695
|
+
error_on = TOML_ILLEGAL_BASIC_STR_CHARS
|
696
|
+
parse_escapes = toml_parse_basic_str_escape
|
697
|
+
result = ''
|
698
|
+
start_pos = pos
|
699
|
+
while True:
|
700
|
+
try:
|
701
|
+
char = src[pos]
|
702
|
+
except IndexError:
|
703
|
+
raise toml_suffixed_err(src, pos, 'Unterminated string') from None
|
704
|
+
if char == '"':
|
705
|
+
if not multiline:
|
706
|
+
return pos + 1, result + src[start_pos:pos]
|
707
|
+
if src.startswith('"""', pos):
|
708
|
+
return pos + 3, result + src[start_pos:pos]
|
709
|
+
pos += 1
|
710
|
+
continue
|
711
|
+
if char == '\\':
|
712
|
+
result += src[start_pos:pos]
|
713
|
+
pos, parsed_escape = parse_escapes(src, pos)
|
714
|
+
result += parsed_escape
|
715
|
+
start_pos = pos
|
716
|
+
continue
|
717
|
+
if char in error_on:
|
718
|
+
raise toml_suffixed_err(src, pos, f'Illegal character {char!r}')
|
719
|
+
pos += 1
|
720
|
+
|
721
|
+
|
722
|
+
def toml_parse_value( # noqa: C901
|
723
|
+
src: str,
|
724
|
+
pos: TomlPos,
|
725
|
+
parse_float: TomlParseFloat,
|
726
|
+
) -> ta.Tuple[TomlPos, ta.Any]:
|
727
|
+
try:
|
728
|
+
char: ta.Optional[str] = src[pos]
|
729
|
+
except IndexError:
|
730
|
+
char = None
|
731
|
+
|
732
|
+
# IMPORTANT: order conditions based on speed of checking and likelihood
|
733
|
+
|
734
|
+
# Basic strings
|
735
|
+
if char == '"':
|
736
|
+
if src.startswith('"""', pos):
|
737
|
+
return toml_parse_multiline_str(src, pos, literal=False)
|
738
|
+
return toml_parse_one_line_basic_str(src, pos)
|
739
|
+
|
740
|
+
# Literal strings
|
741
|
+
if char == "'":
|
742
|
+
if src.startswith("'''", pos):
|
743
|
+
return toml_parse_multiline_str(src, pos, literal=True)
|
744
|
+
return toml_parse_literal_str(src, pos)
|
745
|
+
|
746
|
+
# Booleans
|
747
|
+
if char == 't':
|
748
|
+
if src.startswith('true', pos):
|
749
|
+
return pos + 4, True
|
750
|
+
if char == 'f':
|
751
|
+
if src.startswith('false', pos):
|
752
|
+
return pos + 5, False
|
753
|
+
|
754
|
+
# Arrays
|
755
|
+
if char == '[':
|
756
|
+
return toml_parse_array(src, pos, parse_float)
|
757
|
+
|
758
|
+
# Inline tables
|
759
|
+
if char == '{':
|
760
|
+
return toml_parse_inline_table(src, pos, parse_float)
|
761
|
+
|
762
|
+
# Dates and times
|
763
|
+
datetime_match = TOML_RE_DATETIME.match(src, pos)
|
764
|
+
if datetime_match:
|
765
|
+
try:
|
766
|
+
datetime_obj = toml_match_to_datetime(datetime_match)
|
767
|
+
except ValueError as e:
|
768
|
+
raise toml_suffixed_err(src, pos, 'Invalid date or datetime') from e
|
769
|
+
return datetime_match.end(), datetime_obj
|
770
|
+
localtime_match = TOML_RE_LOCALTIME.match(src, pos)
|
771
|
+
if localtime_match:
|
772
|
+
return localtime_match.end(), toml_match_to_localtime(localtime_match)
|
773
|
+
|
774
|
+
# Integers and "normal" floats. The regex will greedily match any type starting with a decimal char, so needs to be
|
775
|
+
# located after handling of dates and times.
|
776
|
+
number_match = TOML_RE_NUMBER.match(src, pos)
|
777
|
+
if number_match:
|
778
|
+
return number_match.end(), toml_match_to_number(number_match, parse_float)
|
779
|
+
|
780
|
+
# Special floats
|
781
|
+
first_three = src[pos:pos + 3]
|
782
|
+
if first_three in {'inf', 'nan'}:
|
783
|
+
return pos + 3, parse_float(first_three)
|
784
|
+
first_four = src[pos:pos + 4]
|
785
|
+
if first_four in {'-inf', '+inf', '-nan', '+nan'}:
|
786
|
+
return pos + 4, parse_float(first_four)
|
787
|
+
|
788
|
+
raise toml_suffixed_err(src, pos, 'Invalid value')
|
789
|
+
|
790
|
+
|
791
|
+
def toml_suffixed_err(src: str, pos: TomlPos, msg: str) -> TomlDecodeError:
|
792
|
+
"""Return a `TomlDecodeError` where error message is suffixed with coordinates in source."""
|
793
|
+
|
794
|
+
def coord_repr(src: str, pos: TomlPos) -> str:
|
795
|
+
if pos >= len(src):
|
796
|
+
return 'end of document'
|
797
|
+
line = src.count('\n', 0, pos) + 1
|
798
|
+
if line == 1:
|
799
|
+
column = pos + 1
|
800
|
+
else:
|
801
|
+
column = pos - src.rindex('\n', 0, pos)
|
802
|
+
return f'line {line}, column {column}'
|
803
|
+
|
804
|
+
return TomlDecodeError(f'{msg} (at {coord_repr(src, pos)})')
|
805
|
+
|
806
|
+
|
807
|
+
def toml_is_unicode_scalar_value(codepoint: int) -> bool:
|
808
|
+
return (0 <= codepoint <= 55295) or (57344 <= codepoint <= 1114111)
|
809
|
+
|
810
|
+
|
811
|
+
def toml_make_safe_parse_float(parse_float: TomlParseFloat) -> TomlParseFloat:
|
812
|
+
"""A decorator to make `parse_float` safe.
|
813
|
+
|
814
|
+
`parse_float` must not return dicts or lists, because these types would be mixed with parsed TOML tables and arrays,
|
815
|
+
thus confusing the parser. The returned decorated callable raises `ValueError` instead of returning illegal types.
|
816
|
+
"""
|
817
|
+
# The default `float` callable never returns illegal types. Optimize it.
|
818
|
+
if parse_float is float:
|
819
|
+
return float
|
820
|
+
|
821
|
+
def safe_parse_float(float_str: str) -> ta.Any:
|
822
|
+
float_value = parse_float(float_str)
|
823
|
+
if isinstance(float_value, (dict, list)):
|
824
|
+
raise ValueError('parse_float must not return dicts or lists') # noqa
|
825
|
+
return float_value
|
826
|
+
|
827
|
+
return safe_parse_float
|