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 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039
|
"""Python module which parses and emits TOML.
Released under the MIT license.
"""
import re
import io
import datetime
from os import linesep
import sys
__version__ = "0.9.6"
_spec_ = "0.4.0"
class TomlDecodeError(Exception):
"""Base toml Exception / Error."""
pass
class TomlTz(datetime.tzinfo):
def __init__(self, toml_offset):
if toml_offset == "Z":
self._raw_offset = "+00:00"
else:
self._raw_offset = toml_offset
self._sign = -1 if self._raw_offset[0] == '-' else 1
self._hours = int(self._raw_offset[1:3])
self._minutes = int(self._raw_offset[4:6])
def tzname(self, dt):
return "UTC" + self._raw_offset
def utcoffset(self, dt):
return self._sign * datetime.timedelta(hours=self._hours,
minutes=self._minutes)
def dst(self, dt):
return datetime.timedelta(0)
class InlineTableDict(object):
"""Sentinel subclass of dict for inline tables."""
def _get_empty_inline_table(_dict):
class DynamicInlineTableDict(_dict, InlineTableDict):
"""Concrete sentinel subclass for inline tables.
It is a subclass of _dict which is passed in dynamically at load time
It is also a subclass of InlineTableDict
"""
return DynamicInlineTableDict()
try:
_range = xrange
except NameError:
unicode = str
_range = range
basestring = str
unichr = chr
try:
FNFError = FileNotFoundError
except NameError:
FNFError = IOError
def load(f, _dict=dict):
"""Parses named file or files as toml and returns a dictionary
Args:
f: Path to the file to open, array of files to read into single dict
or a file descriptor
_dict: (optional) Specifies the class of the returned toml dictionary
Returns:
Parsed toml file represented as a dictionary
Raises:
TypeError -- When f is invalid type
TomlDecodeError: Error while decoding toml
IOError / FileNotFoundError -- When an array with no valid (existing)
(Python 2 / Python 3) file paths is passed
"""
if isinstance(f, basestring):
with io.open(f, encoding='utf-8') as ffile:
return loads(ffile.read(), _dict)
elif isinstance(f, list):
from os import path as op
from warnings import warn
if not [path for path in f if op.exists(path)]:
error_msg = "Load expects a list to contain filenames only."
error_msg += linesep
error_msg += ("The list needs to contain the path of at least one "
"existing file.")
raise FNFError(error_msg)
d = _dict()
for l in f:
if op.exists(l):
d.update(load(l))
else:
warn("Non-existent filename in list with at least one valid "
"filename")
return d
else:
try:
return loads(f.read(), _dict)
except AttributeError:
raise TypeError("You can only load a file descriptor, filename or "
"list")
_groupname_re = re.compile(r'^[A-Za-z0-9_-]+$')
def loads(s, _dict=dict):
"""Parses string as toml
Args:
s: String to be parsed
_dict: (optional) Specifies the class of the returned toml dictionary
Returns:
Parsed toml file represented as a dictionary
Raises:
TypeError: When a non-string is passed
TomlDecodeError: Error while decoding toml
"""
implicitgroups = []
retval = _dict()
currentlevel = retval
if not isinstance(s, basestring):
raise TypeError("Expecting something like a string")
if not isinstance(s, unicode):
s = s.decode('utf8')
sl = list(s)
openarr = 0
openstring = False
openstrchar = ""
multilinestr = False
arrayoftables = False
beginline = True
keygroup = False
keyname = 0
for i, item in enumerate(sl):
if item == '\r' and sl[i + 1] == '\n':
sl[i] = ' '
continue
if keyname:
if item == '\n':
raise TomlDecodeError("Key name found without value."
" Reached end of line.")
if openstring:
if item == openstrchar:
keyname = 2
openstring = False
openstrchar = ""
continue
elif keyname == 1:
if item.isspace():
keyname = 2
continue
elif item.isalnum() or item == '_' or item == '-':
continue
elif keyname == 2 and item.isspace():
continue
if item == '=':
keyname = 0
else:
raise TomlDecodeError("Found invalid character in key name: '" +
item + "'. Try quoting the key name.")
if item == "'" and openstrchar != '"':
k = 1
try:
while sl[i - k] == "'":
k += 1
if k == 3:
break
except IndexError:
pass
if k == 3:
multilinestr = not multilinestr
openstring = multilinestr
else:
openstring = not openstring
if openstring:
openstrchar = "'"
else:
openstrchar = ""
if item == '"' and openstrchar != "'":
oddbackslash = False
k = 1
tripquote = False
try:
while sl[i - k] == '"':
k += 1
if k == 3:
tripquote = True
break
if k == 1 or (k == 3 and tripquote):
while sl[i - k] == '\\':
oddbackslash = not oddbackslash
k += 1
except IndexError:
pass
if not oddbackslash:
if tripquote:
multilinestr = not multilinestr
openstring = multilinestr
else:
openstring = not openstring
if openstring:
openstrchar = '"'
else:
openstrchar = ""
if item == '#' and (not openstring and not keygroup and
not arrayoftables):
j = i
try:
while sl[j] != '\n':
sl[j] = ' '
j += 1
except IndexError:
break
if item == '[' and (not openstring and not keygroup and
not arrayoftables):
if beginline:
if len(sl) > i + 1 and sl[i + 1] == '[':
arrayoftables = True
else:
keygroup = True
else:
openarr += 1
if item == ']' and not openstring:
if keygroup:
keygroup = False
elif arrayoftables:
if sl[i - 1] == ']':
arrayoftables = False
else:
openarr -= 1
if item == '\n':
if openstring or multilinestr:
if not multilinestr:
raise TomlDecodeError("Unbalanced quotes")
if ((sl[i - 1] == "'" or sl[i - 1] == '"') and (
sl[i - 2] == sl[i - 1])):
sl[i] = sl[i - 1]
if sl[i - 3] == sl[i - 1]:
sl[i - 3] = ' '
elif openarr:
sl[i] = ' '
else:
beginline = True
elif beginline and sl[i] != ' ' and sl[i] != '\t':
beginline = False
if not keygroup and not arrayoftables:
if sl[i] == '=':
raise TomlDecodeError("Found empty keyname. ")
keyname = 1
s = ''.join(sl)
s = s.split('\n')
multikey = None
multilinestr = ""
multibackslash = False
for line in s:
if not multilinestr or multibackslash or '\n' not in multilinestr:
line = line.strip()
if line == "" and (not multikey or multibackslash):
continue
if multikey:
if multibackslash:
multilinestr += line
else:
multilinestr += line
multibackslash = False
if len(line) > 2 and (line[-1] == multilinestr[0] and
line[-2] == multilinestr[0] and
line[-3] == multilinestr[0]):
try:
value, vtype = _load_value(multilinestr, _dict)
except ValueError as err:
raise TomlDecodeError(str(err))
currentlevel[multikey] = value
multikey = None
multilinestr = ""
else:
k = len(multilinestr) - 1
while k > -1 and multilinestr[k] == '\\':
multibackslash = not multibackslash
k -= 1
if multibackslash:
multilinestr = multilinestr[:-1]
else:
multilinestr += "\n"
continue
if line[0] == '[':
arrayoftables = False
if len(line) == 1:
raise TomlDecodeError("Opening key group bracket on line by "
"itself.")
if line[1] == '[':
arrayoftables = True
line = line[2:]
splitstr = ']]'
else:
line = line[1:]
splitstr = ']'
i = 1
quotesplits = _get_split_on_quotes(line)
quoted = False
for quotesplit in quotesplits:
if not quoted and splitstr in quotesplit:
break
i += quotesplit.count(splitstr)
quoted = not quoted
line = line.split(splitstr, i)
if len(line) < i + 1 or line[-1].strip() != "":
raise TomlDecodeError("Key group not on a line by itself.")
groups = splitstr.join(line[:-1]).split('.')
i = 0
while i < len(groups):
groups[i] = groups[i].strip()
if len(groups[i]) > 0 and (groups[i][0] == '"' or
groups[i][0] == "'"):
groupstr = groups[i]
j = i + 1
while not groupstr[0] == groupstr[-1]:
j += 1
if j > len(groups) + 2:
raise TomlDecodeError("Invalid group name '" +
groupstr + "' Something " +
"went wrong.")
groupstr = '.'.join(groups[i:j]).strip()
groups[i] = groupstr[1:-1]
groups[i + 1:j] = []
else:
if not _groupname_re.match(groups[i]):
raise TomlDecodeError("Invalid group name '" +
groups[i] + "'. Try quoting it.")
i += 1
currentlevel = retval
for i in _range(len(groups)):
group = groups[i]
if group == "":
raise TomlDecodeError("Can't have a keygroup with an empty "
"name")
try:
currentlevel[group]
if i == len(groups) - 1:
if group in implicitgroups:
implicitgroups.remove(group)
if arrayoftables:
raise TomlDecodeError("An implicitly defined "
"table can't be an array")
elif arrayoftables:
currentlevel[group].append(_dict())
else:
raise TomlDecodeError("What? " + group +
" already exists?" +
str(currentlevel))
except TypeError:
currentlevel = currentlevel[-1]
try:
currentlevel[group]
except KeyError:
currentlevel[group] = _dict()
if i == len(groups) - 1 and arrayoftables:
currentlevel[group] = [_dict()]
except KeyError:
if i != len(groups) - 1:
implicitgroups.append(group)
currentlevel[group] = _dict()
if i == len(groups) - 1 and arrayoftables:
currentlevel[group] = [_dict()]
currentlevel = currentlevel[group]
if arrayoftables:
try:
currentlevel = currentlevel[-1]
except KeyError:
pass
elif line[0] == "{":
if line[-1] != "}":
raise TomlDecodeError("Line breaks are not allowed in inline"
"objects")
try:
_load_inline_object(line, currentlevel, _dict, multikey,
multibackslash)
except ValueError as err:
raise TomlDecodeError(str(err))
elif "=" in line:
try:
ret = _load_line(line, currentlevel, _dict, multikey,
multibackslash)
except ValueError as err:
raise TomlDecodeError(str(err))
if ret is not None:
multikey, multilinestr, multibackslash = ret
return retval
def _load_inline_object(line, currentlevel, _dict, multikey=False,
multibackslash=False):
candidate_groups = line[1:-1].split(",")
groups = []
if len(candidate_groups) == 1 and not candidate_groups[0].strip():
candidate_groups.pop()
while len(candidate_groups) > 0:
candidate_group = candidate_groups.pop(0)
try:
_, value = candidate_group.split('=', 1)
except ValueError:
raise ValueError("Invalid inline table encountered")
value = value.strip()
if ((value[0] == value[-1] and value[0] in ('"', "'")) or (
value[0] in '-0123456789' or
value in ('true', 'false') or
(value[0] == "[" and value[-1] == "]") or
(value[0] == '{' and value[-1] == '}'))):
groups.append(candidate_group)
elif len(candidate_groups) > 0:
candidate_groups[0] = candidate_group + "," + candidate_groups[0]
else:
raise ValueError("Invalid inline table value encountered")
for group in groups:
status = _load_line(group, currentlevel, _dict, multikey,
multibackslash)
if status is not None:
break
# Matches a TOML number, which allows underscores for readability
_number_with_underscores = re.compile('([0-9])(_([0-9]))*')
def _strictly_valid_num(n):
n = n.strip()
if not n:
return False
if n[0] == '_':
return False
if n[-1] == '_':
return False
if "_." in n or "._" in n:
return False
if len(n) == 1:
return True
if n[0] == '0' and n[1] != '.':
return False
if n[0] == '+' or n[0] == '-':
n = n[1:]
if n[0] == '0' and n[1] != '.':
return False
if '__' in n:
return False
return True
def _get_split_on_quotes(line):
doublequotesplits = line.split('"')
quoted = False
quotesplits = []
if len(doublequotesplits) > 1 and "'" in doublequotesplits[0]:
singlequotesplits = doublequotesplits[0].split("'")
doublequotesplits = doublequotesplits[1:]
while len(singlequotesplits) % 2 == 0 and len(doublequotesplits):
singlequotesplits[-1] += '"' + doublequotesplits[0]
doublequotesplits = doublequotesplits[1:]
if "'" in singlequotesplits[-1]:
singlequotesplits = (singlequotesplits[:-1] +
singlequotesplits[-1].split("'"))
quotesplits += singlequotesplits
for doublequotesplit in doublequotesplits:
if quoted:
quotesplits.append(doublequotesplit)
else:
quotesplits += doublequotesplit.split("'")
quoted = not quoted
return quotesplits
def _load_line(line, currentlevel, _dict, multikey, multibackslash):
i = 1
quotesplits = _get_split_on_quotes(line)
quoted = False
for quotesplit in quotesplits:
if not quoted and '=' in quotesplit:
break
i += quotesplit.count('=')
quoted = not quoted
pair = line.split('=', i)
strictly_valid = _strictly_valid_num(pair[-1])
if _number_with_underscores.match(pair[-1]):
pair[-1] = pair[-1].replace('_', '')
while len(pair[-1]) and (pair[-1][0] != ' ' and pair[-1][0] != '\t' and
pair[-1][0] != "'" and pair[-1][0] != '"' and
pair[-1][0] != '[' and pair[-1][0] != '{' and
pair[-1] != 'true' and pair[-1] != 'false'):
try:
float(pair[-1])
break
except ValueError:
pass
if _load_date(pair[-1]) is not None:
break
i += 1
prev_val = pair[-1]
pair = line.split('=', i)
if prev_val == pair[-1]:
raise ValueError("Invalid date or number")
if strictly_valid:
strictly_valid = _strictly_valid_num(pair[-1])
pair = ['='.join(pair[:-1]).strip(), pair[-1].strip()]
if (pair[0][0] == '"' or pair[0][0] == "'") and \
(pair[0][-1] == '"' or pair[0][-1] == "'"):
pair[0] = pair[0][1:-1]
if len(pair[1]) > 2 and ((pair[1][0] == '"' or pair[1][0] == "'") and
pair[1][1] == pair[1][0] and
pair[1][2] == pair[1][0] and
not (len(pair[1]) > 5 and
pair[1][-1] == pair[1][0] and
pair[1][-2] == pair[1][0] and
pair[1][-3] == pair[1][0])):
k = len(pair[1]) - 1
while k > -1 and pair[1][k] == '\\':
multibackslash = not multibackslash
k -= 1
if multibackslash:
multilinestr = pair[1][:-1]
else:
multilinestr = pair[1] + "\n"
multikey = pair[0]
else:
value, vtype = _load_value(pair[1], _dict, strictly_valid)
try:
currentlevel[pair[0]]
raise ValueError("Duplicate keys!")
except KeyError:
if multikey:
return multikey, multilinestr, multibackslash
else:
currentlevel[pair[0]] = value
def _load_date(val):
microsecond = 0
tz = None
try:
if len(val) > 19:
if val[19] == '.':
if val[-1].upper() == 'Z':
subsecondval = val[20:-1]
tzval = "Z"
else:
subsecondvalandtz = val[20:]
if '+' in subsecondvalandtz:
splitpoint = subsecondvalandtz.index('+')
subsecondval = subsecondvalandtz[:splitpoint]
tzval = subsecondvalandtz[splitpoint:]
elif '-' in subsecondvalandtz:
splitpoint = subsecondvalandtz.index('-')
subsecondval = subsecondvalandtz[:splitpoint]
tzval = subsecondvalandtz[splitpoint:]
tz = TomlTz(tzval)
microsecond = int(int(subsecondval) *
(10 ** (6 - len(subsecondval))))
else:
tz = TomlTz(val[19:])
except ValueError:
tz = None
if "-" not in val[1:]:
return None
try:
d = datetime.datetime(
int(val[:4]), int(val[5:7]),
int(val[8:10]), int(val[11:13]),
int(val[14:16]), int(val[17:19]), microsecond, tz)
except ValueError:
return None
return d
def _load_unicode_escapes(v, hexbytes, prefix):
skip = False
i = len(v) - 1
while i > -1 and v[i] == '\\':
skip = not skip
i -= 1
for hx in hexbytes:
if skip:
skip = False
i = len(hx) - 1
while i > -1 and hx[i] == '\\':
skip = not skip
i -= 1
v += prefix
v += hx
continue
hxb = ""
i = 0
hxblen = 4
if prefix == "\\U":
hxblen = 8
hxb = ''.join(hx[i:i + hxblen]).lower()
if hxb.strip('0123456789abcdef'):
raise ValueError("Invalid escape sequence: " + hxb)
if hxb[0] == "d" and hxb[1].strip('01234567'):
raise ValueError("Invalid escape sequence: " + hxb +
". Only scalar unicode points are allowed.")
v += unichr(int(hxb, 16))
v += unicode(hx[len(hxb):])
return v
# Unescape TOML string values.
# content after the \
_escapes = ['0', 'b', 'f', 'n', 'r', 't', '"']
# What it should be replaced by
_escapedchars = ['\0', '\b', '\f', '\n', '\r', '\t', '\"']
# Used for substitution
_escape_to_escapedchars = dict(zip(_escapes, _escapedchars))
def _unescape(v):
"""Unescape characters in a TOML string."""
i = 0
backslash = False
while i < len(v):
if backslash:
backslash = False
if v[i] in _escapes:
v = v[:i - 1] + _escape_to_escapedchars[v[i]] + v[i + 1:]
elif v[i] == '\\':
v = v[:i - 1] + v[i:]
elif v[i] == 'u' or v[i] == 'U':
i += 1
else:
raise ValueError("Reserved escape sequence used")
continue
elif v[i] == '\\':
backslash = True
i += 1
return v
def _load_value(v, _dict, strictly_valid=True):
if not v:
raise ValueError("Empty value is invalid")
if v == 'true':
return (True, "bool")
elif v == 'false':
return (False, "bool")
elif v[0] == '"':
testv = v[1:].split('"')
triplequote = False
triplequotecount = 0
if len(testv) > 1 and testv[0] == '' and testv[1] == '':
testv = testv[2:]
triplequote = True
closed = False
for tv in testv:
if tv == '':
if triplequote:
triplequotecount += 1
else:
closed = True
else:
oddbackslash = False
try:
i = -1
j = tv[i]
while j == '\\':
oddbackslash = not oddbackslash
i -= 1
j = tv[i]
except IndexError:
pass
if not oddbackslash:
if closed:
raise ValueError("Stuff after closed string. WTF?")
else:
if not triplequote or triplequotecount > 1:
closed = True
else:
triplequotecount = 0
escapeseqs = v.split('\\')[1:]
backslash = False
for i in escapeseqs:
if i == '':
backslash = not backslash
else:
if i[0] not in _escapes and (i[0] != 'u' and i[0] != 'U' and
not backslash):
raise ValueError("Reserved escape sequence used")
if backslash:
backslash = False
for prefix in ["\\u", "\\U"]:
if prefix in v:
hexbytes = v.split(prefix)
v = _load_unicode_escapes(hexbytes[0], hexbytes[1:], prefix)
v = _unescape(v)
if len(v) > 1 and v[1] == '"' and (len(v) < 3 or v[1] == v[2]):
v = v[2:-2]
return (v[1:-1], "str")
elif v[0] == "'":
if v[1] == "'" and (len(v) < 3 or v[1] == v[2]):
v = v[2:-2]
return (v[1:-1], "str")
elif v[0] == '[':
return (_load_array(v, _dict), "array")
elif v[0] == '{':
inline_object = _get_empty_inline_table(_dict)
_load_inline_object(v, inline_object, _dict)
return (inline_object, "inline_object")
else:
parsed_date = _load_date(v)
if parsed_date is not None:
return (parsed_date, "date")
if not strictly_valid:
raise ValueError("Weirdness with leading zeroes or "
"underscores in your number.")
itype = "int"
neg = False
if v[0] == '-':
neg = True
v = v[1:]
elif v[0] == '+':
v = v[1:]
v = v.replace('_', '')
if '.' in v or 'e' in v or 'E' in v:
if '.' in v and v.split('.', 1)[1] == '':
raise ValueError("This float is missing digits after "
"the point")
if v[0] not in '0123456789':
raise ValueError("This float doesn't have a leading digit")
v = float(v)
itype = "float"
else:
v = int(v)
if neg:
return (0 - v, itype)
return (v, itype)
def _bounded_string(s):
if len(s) == 0:
return True
if s[-1] != s[0]:
return False
i = -2
backslash = False
while len(s) + i > 0:
if s[i] == "\\":
backslash = not backslash
i -= 1
else:
break
return not backslash
def _load_array(a, _dict):
atype = None
retval = []
a = a.strip()
if '[' not in a[1:-1] or "" != a[1:-1].split('[')[0].strip():
strarray = False
tmpa = a[1:-1].strip()
if tmpa != '' and (tmpa[0] == '"' or tmpa[0] == "'"):
strarray = True
if not a[1:-1].strip().startswith('{'):
a = a[1:-1].split(',')
else:
# a is an inline object, we must find the matching parenthesis
# to define groups
new_a = []
start_group_index = 1
end_group_index = 2
in_str = False
while end_group_index < len(a[1:]):
if a[end_group_index] == '"' or a[end_group_index] == "'":
if in_str:
backslash_index = end_group_index - 1
while (backslash_index > -1 and
a[backslash_index] == '\\'):
in_str = not in_str
backslash_index -= 1
in_str = not in_str
if in_str or a[end_group_index] != '}':
end_group_index += 1
continue
# Increase end_group_index by 1 to get the closing bracket
end_group_index += 1
new_a.append(a[start_group_index:end_group_index])
# The next start index is at least after the closing bracket, a
# closing bracket can be followed by a comma since we are in
# an array.
start_group_index = end_group_index + 1
while (start_group_index < len(a[1:]) and
a[start_group_index] != '{'):
start_group_index += 1
end_group_index = start_group_index + 1
a = new_a
b = 0
if strarray:
while b < len(a) - 1:
ab = a[b].strip()
while (not _bounded_string(ab) or
(len(ab) > 2 and
ab[0] == ab[1] == ab[2] and
ab[-2] != ab[0] and
ab[-3] != ab[0])):
a[b] = a[b] + ',' + a[b + 1]
ab = a[b].strip()
if b < len(a) - 2:
a = a[:b + 1] + a[b + 2:]
else:
a = a[:b + 1]
b += 1
else:
al = list(a[1:-1])
a = []
openarr = 0
j = 0
for i in _range(len(al)):
if al[i] == '[':
openarr += 1
elif al[i] == ']':
openarr -= 1
elif al[i] == ',' and not openarr:
a.append(''.join(al[j:i]))
j = i + 1
a.append(''.join(al[j:]))
for i in _range(len(a)):
a[i] = a[i].strip()
if a[i] != '':
nval, ntype = _load_value(a[i], _dict)
if atype:
if ntype != atype:
raise ValueError("Not a homogeneous array")
else:
atype = ntype
retval.append(nval)
return retval
def dump(o, f):
"""Writes out dict as toml to a file
Args:
o: Object to dump into toml
f: File descriptor where the toml should be stored
Returns:
String containing the toml corresponding to dictionary
Raises:
TypeError: When anything other than file descriptor is passed
"""
if not f.write:
raise TypeError("You can only dump an object to a file descriptor")
d = dumps(o)
f.write(d)
return d
def dumps(o, preserve=False):
"""Stringifies input dict as toml
Args:
o: Object to dump into toml
preserve: Boolean parameter. If true, preserve inline tables.
Returns:
String containing the toml corresponding to dict
"""
retval = ""
addtoretval, sections = _dump_sections(o, "")
retval += addtoretval
while sections != {}:
newsections = {}
for section in sections:
addtoretval, addtosections = _dump_sections(sections[section],
section, preserve)
if addtoretval or (not addtoretval and not addtosections):
if retval and retval[-2:] != "\n\n":
retval += "\n"
retval += "[" + section + "]\n"
if addtoretval:
retval += addtoretval
for s in addtosections:
newsections[section + "." + s] = addtosections[s]
sections = newsections
return retval
def _dump_sections(o, sup, preserve=False):
retstr = ""
if sup != "" and sup[-1] != ".":
sup += '.'
retdict = o.__class__()
arraystr = ""
for section in o:
section = unicode(section)
qsection = section
if not re.match(r'^[A-Za-z0-9_-]+$', section):
if '"' in section:
qsection = "'" + section + "'"
else:
qsection = '"' + section + '"'
if not isinstance(o[section], dict):
arrayoftables = False
if isinstance(o[section], list):
for a in o[section]:
if isinstance(a, dict):
arrayoftables = True
if arrayoftables:
for a in o[section]:
arraytabstr = "\n"
arraystr += "[[" + sup + qsection + "]]\n"
s, d = _dump_sections(a, sup + qsection)
if s:
if s[0] == "[":
arraytabstr += s
else:
arraystr += s
while d != {}:
newd = {}
for dsec in d:
s1, d1 = _dump_sections(d[dsec], sup + qsection +
"." + dsec)
if s1:
arraytabstr += ("[" + sup + qsection + "." +
dsec + "]\n")
arraytabstr += s1
for s1 in d1:
newd[dsec + "." + s1] = d1[s1]
d = newd
arraystr += arraytabstr
else:
if o[section] is not None:
retstr += (qsection + " = " +
unicode(_dump_value(o[section])) + '\n')
elif preserve and isinstance(o[section], InlineTableDict):
retstr += (qsection + " = " + _dump_inline_table(o[section]))
else:
retdict[qsection] = o[section]
retstr += arraystr
return (retstr, retdict)
def _dump_inline_table(section):
"""Preserve inline table in its compact syntax instead of expanding
into subsection.
https://github.com/toml-lang/toml#user-content-inline-table
"""
retval = ""
if isinstance(section, dict):
val_list = []
for k, v in section.items():
val = _dump_inline_table(v)
val_list.append(k + " = " + val)
retval += "{ " + ", ".join(val_list) + " }\n"
return retval
else:
return unicode(_dump_value(section))
def _dump_value(v):
dump_funcs = {
str: _dump_str,
unicode: _dump_str,
list: _dump_list,
int: lambda v: v,
bool: lambda v: unicode(v).lower(),
float: _dump_float,
datetime.datetime: lambda v: v.isoformat().replace('+00:00', 'Z'),
}
# Lookup function corresponding to v's type
dump_fn = dump_funcs.get(type(v))
if dump_fn is None and hasattr(v, '__iter__'):
dump_fn = dump_funcs[list]
# Evaluate function (if it exists) else return v
return dump_fn(v) if dump_fn is not None else dump_funcs[str](v)
def _dump_str(v):
if sys.version_info < (3,) and hasattr(v, 'decode') and isinstance(v, str):
v = v.decode('utf-8')
v = "%r" % v
if v[0] == 'u':
v = v[1:]
singlequote = v.startswith("'")
if singlequote or v.startswith('"'):
v = v[1:-1]
if singlequote:
v = v.replace("\\'", "'")
v = v.replace('"', '\\"')
v = v.split("\\x")
while len(v) > 1:
i = -1
if not v[0]:
v = v[1:]
v[0] = v[0].replace("\\\\", "\\")
# No, I don't know why != works and == breaks
joinx = v[0][i] != "\\"
while v[0][:i] and v[0][i] == "\\":
joinx = not joinx
i -= 1
if joinx:
joiner = "x"
else:
joiner = "u00"
v = [v[0] + joiner + v[1]] + v[2:]
return unicode('"' + v[0] + '"')
def _dump_list(v):
retval = "["
for u in v:
retval += " " + unicode(_dump_value(u)) + ","
retval += "]"
return retval
def _dump_float(v):
return "{0:.16}".format(v).replace("e+0", "e+").replace("e-0", "e-")
|