This file is indexed.

/usr/lib/python2.7/dist-packages/parse.py is in python-parse 1.6.6-0ubuntu1.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

   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
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
r'''Parse strings using a specification based on the Python format() syntax.

   ``parse()`` is the opposite of ``format()``

The module is set up to only export ``parse()``, ``search()`` and
``findall()`` when ``import *`` is used:

>>> from parse import *

From there it's a simple thing to parse a string:

>>> parse("It's {}, I love it!", "It's spam, I love it!")
<Result ('spam',) {}>
>>> _[0]
'spam'

Or to search a string for some pattern:

>>> search('Age: {:d}\n', 'Name: Rufus\nAge: 42\nColor: red\n')
<Result (42,) {}>

Or find all the occurrances of some pattern in a string:

>>> ''.join(r.fixed[0] for r in findall(">{}<", "<p>the <b>bold</b> text</p>"))
'the bold text'

If you're going to use the same pattern to match lots of strings you can
compile it once:

>>> from parse import compile
>>> p = compile("It's {}, I love it!")
>>> print(p)
<Parser "It's {}, I love it!">
>>> p.parse("It's spam, I love it!")
<Result ('spam',) {}>

("compile" is not exported for ``import *`` usage as it would override the
built-in ``compile()`` function)


Format Syntax
-------------

A basic version of the `Format String Syntax`_ is supported with anonymous
(fixed-position), named and formatted fields::

   {[field name]:[format spec]}

Field names must be a valid Python identifiers, including dotted names;
element indexes are supported (as they would make no sense.)

Numbered fields are also not supported: the result of parsing will include
the parsed fields in the order they are parsed.

The conversion of fields to types other than strings is done based on the
type in the format specification, which mirrors the ``format()`` behaviour.
There are no "!" field conversions like ``format()`` has.

Some simple parse() format string examples:

>>> parse("Bring me a {}", "Bring me a shrubbery")
<Result ('shrubbery',) {}>
>>> r = parse("The {} who say {}", "The knights who say Ni!")
>>> print(r)
<Result ('knights', 'Ni!') {}>
>>> print(r.fixed)
('knights', 'Ni!')
>>> r = parse("Bring out the holy {item}", "Bring out the holy hand grenade")
>>> print(r)
<Result () {'item': 'hand grenade'}>
>>> print(r.named)
{'item': 'hand grenade'}
>>> print(r['item'])
hand grenade

Dotted names are possible though the application must make additional sense of
the result:

>>> r = parse("Mmm, {food.type}, I love it!", "Mmm, spam, I love it!")
>>> print(r)
<Result () {'food.type': 'spam'}>
>>> print(r.named)
{'food.type': 'spam'}
>>> print(r['food.type'])
spam


Format Specification
--------------------

Most often a straight format-less ``{}`` will suffice where a more complex
format specification might have been used.

Most of `format()`'s `Format Specification Mini-Language`_ is supported:

   [[fill]align][0][width][.precision][type]

The differences between `parse()` and `format()` are:

- The align operators will cause spaces (or specified fill character) to be
  stripped from the parsed value. The width is not enforced; it just indicates
  there may be whitespace or "0"s to strip.
- Numeric parsing will automatically handle a "0b", "0o" or "0x" prefix.
  That is, the "#" format character is handled automatically by d, b, o
  and x formats. For "d" any will be accepted, but for the others the correct
  prefix must be present if at all.
- Numeric sign is handled automatically.
- The thousands separator is handled automatically if the "n" type is used.
- The types supported are a slightly different mix to the format() types.  Some
  format() types come directly over: "d", "n", "%", "f", "e", "b", "o" and "x".
  In addition some regular expression character group types "D", "w", "W", "s"
  and "S" are also available.
- The "e" and "g" types are case-insensitive so there is not need for
  the "E" or "G" types.

===== =========================================== ========
Type  Characters Matched                          Output
===== =========================================== ========
 w    Letters and underscore                      str
 W    Non-letter and underscore                   str
 s    Whitespace                                  str
 S    Non-whitespace                              str
 d    Digits (effectively integer numbers)        int
 D    Non-digit                                   str
 n    Numbers with thousands separators (, or .)  int
 %    Percentage (converted to value/100.0)       float
 f    Fixed-point numbers                         float
 e    Floating-point numbers with exponent        float
      e.g. 1.1e-10, NAN (all case insensitive)
 g    General number format (either d, f or e)    float
 b    Binary numbers                              int
 o    Octal numbers                               int
 x    Hexadecimal numbers (lower and upper case)  int
 ti   ISO 8601 format date/time                   datetime
      e.g. 1972-01-20T10:21:36Z ("T" and "Z"
      optional)
 te   RFC2822 e-mail format date/time             datetime
      e.g. Mon, 20 Jan 1972 10:21:36 +1000
 tg   Global (day/month) format date/time         datetime
      e.g. 20/1/1972 10:21:36 AM +1:00
 ta   US (month/day) format date/time             datetime
      e.g. 1/20/1972 10:21:36 PM +10:30
 tc   ctime() format date/time                    datetime
      e.g. Sun Sep 16 01:03:52 1973
 th   HTTP log format date/time                   datetime
      e.g. 21/Nov/2011:00:07:11 +0000
 ts   Linux system log format date/time           datetime
      e.g. Nov  9 03:37:44
 tt   Time                                        time
      e.g. 10:21:36 PM -5:30
===== =========================================== ========

Some examples of typed parsing with ``None`` returned if the typing
does not match:

>>> parse('Our {:d} {:w} are...', 'Our 3 weapons are...')
<Result (3, 'weapons') {}>
>>> parse('Our {:d} {:w} are...', 'Our three weapons are...')
>>> parse('Meet at {:tg}', 'Meet at 1/2/2011 11:00 PM')
<Result (datetime.datetime(2011, 2, 1, 23, 0),) {}>

And messing about with alignment:

>>> parse('with {:>} herring', 'with     a herring')
<Result ('a',) {}>
>>> parse('spam {:^} spam', 'spam    lovely     spam')
<Result ('lovely',) {}>

Note that the "center" alignment does not test to make sure the value is
centered - it just strips leading and trailing whitespace.

Some notes for the date and time types:

- the presence of the time part is optional (including ISO 8601, starting
  at the "T"). A full datetime object will always be returned; the time
  will be set to 00:00:00. You may also specify a time without seconds.
- when a seconds amount is present in the input fractions will be parsed
  to give microseconds.
- except in ISO 8601 the day and month digits may be 0-padded.
- the date separator for the tg and ta formats may be "-" or "/".
- named months (abbreviations or full names) may be used in the ta and tg
  formats in place of numeric months.
- as per RFC 2822 the e-mail format may omit the day (and comma), and the
  seconds but nothing else.
- hours greater than 12 will be happily accepted.
- the AM/PM are optional, and if PM is found then 12 hours will be added
  to the datetime object's hours amount - even if the hour is greater
  than 12 (for consistency.)
- in ISO 8601 the "Z" (UTC) timezone part may be a numeric offset
- timezones are specified as "+HH:MM" or "-HH:MM". The hour may be one or two
  digits (0-padded is OK.) Also, the ":" is optional.
- the timezone is optional in all except the e-mail format (it defaults to
  UTC.)
- named timezones are not handled yet.

Note: attempting to match too many datetime fields in a single parse() will
currently result in a resource allocation issue. A TooManyFields exception
will be raised in this instance. The current limit is about 15. It is hoped
that this limit will be removed one day.

.. _`Format String Syntax`:
  http://docs.python.org/library/string.html#format-string-syntax
.. _`Format Specification Mini-Language`:
  http://docs.python.org/library/string.html#format-specification-mini-language


Result Objects
--------------

The result of a ``parse()`` operation is either ``None`` (no match) or a
``Result`` instance.

The ``Result`` instance has three attributes:

fixed
   A tuple of the fixed-position, anonymous fields extracted from the input.
named
   A dictionary of the named fields extracted from the input.
spans
   A dictionary mapping the names and fixed position indices matched to a
   2-tuple slice range of where the match occurred in the input.
   The span does not include any stripped padding (alignment or width).


Custom Type Conversions
-----------------------

If you wish to have matched fields automatically converted to your own type you
may pass in a dictionary of type conversion information to ``parse()`` and
``compile()``.

The converter will be passed the field string matched. Whatever it returns
will be substituted in the ``Result`` instance for that field.

Your custom type conversions may override the builtin types if you supply one
with the same identifier.

>>> def shouty(string):
...    return string.upper()
...
>>> parse('{:shouty} world', 'hello world', dict(shouty=shouty))
<Result ('HELLO',) {}>

If the type converter has the optional ``pattern`` attribute, it is used as
regular expression for better pattern matching (instead of the default one).

>>> def parse_number(text):
...    return int(text)
>>> parse_number.pattern = r'\d+'
>>> parse('Answer: {number:Number}', 'Answer: 42', dict(Number=parse_number))
<Result () {'number': 42}>
>>> _ = parse('Answer: {:Number}', 'Answer: Alice', dict(Number=parse_number))
>>> assert _ is None, "MISMATCH"

You can also use the ``with_pattern(pattern)`` decorator to add this
information to a type converter function:

>>> from parse import with_pattern
>>> @with_pattern(r'\d+')
... def parse_number(text):
...    return int(text)
>>> parse('Answer: {number:Number}', 'Answer: 42', dict(Number=parse_number))
<Result () {'number': 42}>

A more complete example of a custom type might be:

>>> yesno_mapping = {
...     "yes":  True,   "no":    False,
...     "on":   True,   "off":   False,
...     "true": True,   "false": False,
... }
... @with_pattern(r"|".join(yesno_mapping))
... def parse_yesno(text):
...     return yesno_mapping[text.lower()]


----

**Version history (in brief)**:

- 1.6.6 parse Linux system log dates (thanks Alex Cowan)
- 1.6.5 handle precision in float format (thanks Levi Kilcher)
- 1.6.4 handle pipe "|" characters in parse string (thanks Martijn Pieters)
- 1.6.3 handle repeated instances of named fields, fix bug in PM time
  overflow
- 1.6.2 fix logging to use local, not root logger (thanks Necku)
- 1.6.1 be more flexible regarding matched ISO datetimes and timezones in
  general, fix bug in timezones without ":" and improve docs
- 1.6.0 add support for optional ``pattern`` attribute in user-defined types
  (thanks Jens Engel)
- 1.5.3 fix handling of question marks
- 1.5.2 fix type conversion error with dotted names (thanks Sebastian Thiel)
- 1.5.1 implement handling of named datetime fields
- 1.5 add handling of dotted field names (thanks Sebastian Thiel)
- 1.4.1 fix parsing of "0" in int conversion (thanks James Rowe)
- 1.4 add __getitem__ convenience access on Result.
- 1.3.3 fix Python 2.5 setup.py issue.
- 1.3.2 fix Python 3.2 setup.py issue.
- 1.3.1 fix a couple of Python 3.2 compatibility issues.
- 1.3 added search() and findall(); removed compile() from ``import *``
  export as it overwrites builtin.
- 1.2 added ability for custom and override type conversions to be
  provided; some cleanup
- 1.1.9 to keep things simpler number sign is handled automatically;
  significant robustification in the face of edge-case input.
- 1.1.8 allow "d" fields to have number base "0x" etc. prefixes;
  fix up some field type interactions after stress-testing the parser;
  implement "%" type.
- 1.1.7 Python 3 compatibility tweaks (2.5 to 2.7 and 3.2 are supported).
- 1.1.6 add "e" and "g" field types; removed redundant "h" and "X";
  removed need for explicit "#".
- 1.1.5 accept textual dates in more places; Result now holds match span
  positions.
- 1.1.4 fixes to some int type conversion; implemented "=" alignment; added
  date/time parsing with a variety of formats handled.
- 1.1.3 type conversion is automatic based on specified field types. Also added
  "f" and "n" types.
- 1.1.2 refactored, added compile() and limited ``from parse import *``
- 1.1.1 documentation improvements
- 1.1.0 implemented more of the `Format Specification Mini-Language`_
  and removed the restriction on mixing fixed-position and named fields
- 1.0.0 initial release

This code is copyright 2012-2013 Richard Jones <richard@python.org>
See the end of the source file for the license of use.
'''
__version__ = '1.6.6'

# yes, I now have two problems
import re
import sys
from datetime import datetime, time, tzinfo, timedelta
from functools import partial
import logging

__all__ = 'parse search findall with_pattern'.split()

log = logging.getLogger(__name__)


def with_pattern(pattern):
    """Attach a regular expression pattern matcher to a custom type converter
    function.

    This annotates the type converter with the :attr:`pattern` attribute.

    EXAMPLE:
        >>> import parse
        >>> @parse.with_pattern(r"\d+")
        ... def parse_number(text):
        ...     return int(text)

    is equivalent to:

        >>> def parse_number(text):
        ...     return int(text)
        >>> parse_number.pattern = r"\d+"

    :param pattern: regular expression pattern (as text)
    :return: wrapped function
    """
    def decorator(func):
        func.pattern = pattern
        return func
    return decorator


def int_convert(base):
    '''Convert a string to an integer.

    The string may start with a sign.

    It may be of a base other than 10.

    It may also have other non-numeric characters that we can ignore.
    '''
    CHARS = '0123456789abcdefghijklmnopqrstuvwxyz'

    def f(string, match, base=base):
        if string[0] == '-':
            sign = -1
        else:
            sign = 1

        if string[0] == '0' and len(string) > 1:
            if string[1] in 'bB':
                base = 2
            elif string[1] in 'oO':
                base = 8
            elif string[1] in 'xX':
                base = 16
            else:
                # just go with the base specifed
                pass

        chars = CHARS[:base]
        string = re.sub('[^%s]' % chars, '', string.lower())
        return sign * int(string, base)
    return f


def percentage(string, match):
    return float(string[:-1]) / 100.


class FixedTzOffset(tzinfo):
    """Fixed offset in minutes east from UTC.
    """
    ZERO = timedelta(0)

    def __init__(self, offset, name):
        self._offset = timedelta(minutes=offset)
        self._name = name

    def __repr__(self):
        return '<%s %s %s>' % (self.__class__.__name__, self._name,
            self._offset)

    def utcoffset(self, dt):
        return self._offset

    def tzname(self, dt):
        return self._name

    def dst(self, dt):
        return self.ZERO

    def __eq__(self, other):
        return self._name == other._name and self._offset == other._offset


MONTHS_MAP = dict(
    Jan=1, January=1,
    Feb=2, February=2,
    Mar=3, March=3,
    Apr=4, April=4,
    May=5,
    Jun=6, June=6,
    Jul=7, July=7,
    Aug=8, August=8,
    Sep=9, September=9,
    Oct=10, October=10,
    Nov=11, November=11,
    Dec=12, December=12
)
DAYS_PAT = '(Mon|Tue|Wed|Thu|Fri|Sat|Sun)'
MONTHS_PAT = '(Jan|Feb|Mar|Apr|May|Jun|Jul|Aug|Sep|Oct|Nov|Dec)'
ALL_MONTHS_PAT = '(%s)' % '|'.join(MONTHS_MAP)
TIME_PAT = r'(\d{1,2}:\d{1,2}(:\d{1,2}(\.\d+)?)?)'
AM_PAT = r'(\s+[AP]M)'
TZ_PAT = r'(\s+[-+]\d\d?:?\d\d)'


def date_convert(string, match, ymd=None, mdy=None, dmy=None,
        d_m_y=None, hms=None, am=None, tz=None, mm=None, dd=None):
    '''Convert the incoming string containing some date / time info into a
    datetime instance.
    '''
    groups = match.groups()
    time_only = False
    if mm and dd:
        y=datetime.today().year
        m=groups[mm]
        d=groups[dd]
    elif ymd is not None:
        y, m, d = re.split('[-/\s]', groups[ymd])
    elif mdy is not None:
        m, d, y = re.split('[-/\s]', groups[mdy])
    elif dmy is not None:
        d, m, y = re.split('[-/\s]', groups[dmy])
    elif d_m_y is not None:
        d, m, y = d_m_y
        d = groups[d]
        m = groups[m]
        y = groups[y]
    else:
        time_only = True

    H = M = S = u = 0
    if hms is not None and groups[hms]:
        t = groups[hms].split(':')
        if len(t) == 2:
            H, M = t
        else:
            H, M, S = t
            if '.' in S:
                S, u = S.split('.')
                u = int(float('.' + u) * 1000000)
            S = int(S)
        H = int(H)
        M = int(M)

    day_incr = False
    if am is not None:
        am = groups[am]
        if am and am.strip() == 'PM':
            H += 12
            if H > 23:
                day_incr = True
                H -= 24

    if tz is not None:
        tz = groups[tz]
    if tz == 'Z':
        tz = FixedTzOffset(0, 'UTC')
    elif tz:
        tz = tz.strip()
        if tz.isupper():
            # TODO use the awesome python TZ module?
            pass
        else:
            sign = tz[0]
            if ':' in tz:
                tzh, tzm = tz[1:].split(':')
            elif len(tz) == 4:  # 'snnn'
                tzh, tzm = tz[1], tz[2:4]
            else:
                tzh, tzm = tz[1:3], tz[3:5]
            offset = int(tzm) + int(tzh) * 60
            if sign == '-':
                offset = -offset
            tz = FixedTzOffset(offset, tz)

    if time_only:
        d = time(H, M, S, u, tzinfo=tz)
    else:
        y = int(y)
        if m.isdigit():
            m = int(m)
        else:
            m = MONTHS_MAP[m]
        d = int(d)
        d = datetime(y, m, d, H, M, S, u, tzinfo=tz)

    if day_incr:
        d = d + timedelta(days=1)

    return d


class TooManyFields(ValueError):
    pass


class RepeatedNameError(ValueError):
    pass


# note: {} are handled separately
# note: I don't use r'' here because Sublime Text 2 syntax highlight has a fit
REGEX_SAFETY = re.compile('([?\\\\.[\]()*+\^$!\|])')

# allowed field types
ALLOWED_TYPES = set(list('nbox%fegwWdDsS') +
    ['t' + c for c in 'ieahgcts'])


def extract_format(format, extra_types):
    '''Pull apart the format [[fill]align][0][width][.precision][type]
    '''
    fill = align = None
    if format[0] in '<>=^':
        align = format[0]
        format = format[1:]
    elif len(format) > 1 and format[1] in '<>=^':
        fill = format[0]
        align = format[1]
        format = format[2:]

    zero = False
    if format and format[0] == '0':
        zero = True
        format = format[1:]

    width = ''
    while format:
        if not format[0].isdigit():
            break
        width += format[0]
        format = format[1:]

    if format.startswith('.'):
        # Precision isn't needed but we need to capture it so that
        # the ValueError isn't raised.
        format = format[1:]  # drop the '.'
        precision = ''
        while format:
            if not format[0].isdigit():
                break
            precision += format[0]
            format = format[1:]

    # the rest is the type, if present
    type = format
    if type and type not in ALLOWED_TYPES and type not in extra_types:
        raise ValueError('type %r not recognised' % type)

    return locals()


PARSE_RE = re.compile(r'({{|}}|{}|{:[^}]+?}|{\w+?(?:\.\w+?)*}|'
    r'{\w+?(?:\.\w+?)*:[^}]+?})')


class Parser(object):
    '''Encapsulate a format string that may be used to parse other strings.
    '''
    def __init__(self, format, extra_types={}):
        # a mapping of a name as in {hello.world} to a regex-group compatible
        # name, like hello__world Its used to prevent the transformation of
        # name-to-group and group to name to fail subtly, such as in:
        # hello_.world-> hello___world->hello._world
        self._group_to_name_map = {}
        # also store the original field name to group name mapping to allow
        # multiple instances of a name in the format string
        self._name_to_group_map = {}
        # and to sanity check the repeated instances store away the first
        # field type specification for the named field
        self._name_types = {}

        self._format = format
        self._extra_types = extra_types
        self._fixed_fields = []
        self._named_fields = []
        self._group_index = 0
        self._type_conversions = {}
        self._expression = self._generate_expression()
        self.__search_re = None
        self.__match_re = None

        log.debug('format %r -> %r' % (format, self._expression))

    def __repr__(self):
        if len(self._format) > 20:
            return '<%s %r>' % (self.__class__.__name__,
                self._format[:17] + '...')
        return '<%s %r>' % (self.__class__.__name__, self._format)

    @property
    def _search_re(self):
        if self.__search_re is None:
            try:
                self.__search_re = re.compile(self._expression,
                    re.IGNORECASE | re.DOTALL)
            except AssertionError:
                # access error through sys to keep py3k and backward compat
                e = str(sys.exc_info()[1])
                if e.endswith('this version only supports 100 named groups'):
                    raise TooManyFields('sorry, you are attempting to parse '
                        'too many complex fields')
        return self.__search_re

    @property
    def _match_re(self):
        if self.__match_re is None:
            expression = '^%s$' % self._expression
            try:
                self.__match_re = re.compile(expression,
                    re.IGNORECASE | re.DOTALL)
            except AssertionError:
                # access error through sys to keep py3k and backward compat
                e = str(sys.exc_info()[1])
                if e.endswith('this version only supports 100 named groups'):
                    raise TooManyFields('sorry, you are attempting to parse '
                        'too many complex fields')
            except re.error:
                raise NotImplementedError("Group names (e.g. (?P<name>) can "
                    "cause failure, as they are not escaped properly: '%s'" %
                    expression)
        return self.__match_re

    def parse(self, string):
        '''Match my format to the string exactly.

        Return either a Result instance or None if there's no match.
        '''
        m = self._match_re.match(string)
        if m is None:
            return None

        return self._generate_result(m)

    def search(self, string, pos=0, endpos=None):
        '''Search the string for my format.

        Optionally start the search at "pos" character index and limit the
        search to a maximum index of endpos - equivalent to
        search(string[:endpos]).

        Return either a Result instance or None if there's no match.
        '''
        if endpos is None:
            endpos = len(string)
        m = self._search_re.search(string, pos, endpos)
        if m is None:
            return None

        return self._generate_result(m)

    def findall(self, string, pos=0, endpos=None, extra_types={}):
        '''Search "string" for the all occurrances of "format".

        Optionally start the search at "pos" character index and limit the
        search to a maximum index of endpos - equivalent to
        search(string[:endpos]).

        Returns an iterator that holds Result instances for each format match
        found.
        '''
        if endpos is None:
            endpos = len(string)
        return ResultIterator(self, string, pos, endpos)

    def _generate_result(self, m):
        # ok, figure the fixed fields we've pulled out and type convert them
        fixed_fields = list(m.groups())
        for n in self._fixed_fields:
            if n in self._type_conversions:
                fixed_fields[n] = self._type_conversions[n](fixed_fields[n], m)
        fixed_fields = tuple(fixed_fields[n] for n in self._fixed_fields)

        # grab the named fields, converting where requested
        groupdict = m.groupdict()
        named_fields = {}
        name_map = {}
        for k in self._named_fields:
            korig = self._group_to_name_map[k]
            name_map[korig] = k
            if k in self._type_conversions:
                named_fields[korig] = self._type_conversions[k](groupdict[k],
                    m)
            else:
                named_fields[korig] = groupdict[k]

        # now figure the match spans
        spans = dict((n, m.span(name_map[n])) for n in named_fields)
        spans.update((i, m.span(n + 1))
            for i, n in enumerate(self._fixed_fields))

        # and that's our result
        return Result(fixed_fields, named_fields, spans)

    def _regex_replace(self, match):
        return '\\' + match.group(1)

    def _generate_expression(self):
        # turn my _format attribute into the _expression attribute
        e = []
        for part in PARSE_RE.split(self._format):
            if not part:
                continue
            elif part == '{{':
                e.append(r'\{')
            elif part == '}}':
                e.append(r'\}')
            elif part[0] == '{':
                # this will be a braces-delimited field to handle
                e.append(self._handle_field(part))
            else:
                # just some text to match
                e.append(REGEX_SAFETY.sub(self._regex_replace, part))
        return ''.join(e)

    def _to_group_name(self, field):
        # return a version of field which can be used as capture group, even
        # though it might contain '.'
        group = field.replace('.', '_')

        # make sure we don't collide ("a.b" colliding with "a_b")
        n = 1
        while group in self._group_to_name_map:
            n += 1
            if '.' in field:
                group = field.replace('.', '_' * n)
            elif '_' in field:
                group = field.replace('_', '_' * n)
            else:
                raise KeyError('duplicated group name %r' % (field, ))

        # save off the mapping
        self._group_to_name_map[group] = field
        self._name_to_group_map[field] = group
        return group

    def _handle_field(self, field):
        # first: lose the braces
        field = field[1:-1]

        # now figure whether this is an anonymous or named field, and whether
        # there's any format specification
        format = ''
        if field and field[0].isalpha():
            if ':' in field:
                name, format = field.split(':')
            else:
                name = field
            if name in self._name_to_group_map:
                if self._name_types[name] != format:
                    raise RepeatedNameError('field type %r for field "%s" '
                        'does not match previous seen type %r' % (format,
                        name, self._name_types[name]))
                group = self._name_to_group_map[name]
                # match previously-seen value
                return '(?P=%s)' % group
            else:
                group = self._to_group_name(name)
                self._name_types[name] = format
            self._named_fields.append(group)
            # this will become a group, which must not contain dots
            wrap = '(?P<%s>%%s)' % group
        else:
            self._fixed_fields.append(self._group_index)
            wrap = '(%s)'
            if ':' in field:
                format = field[1:]
            group = self._group_index

        # simplest case: no type specifier ({} or {name})
        if not format:
            self._group_index += 1
            return wrap % '.+?'

        # decode the format specification
        format = extract_format(format, self._extra_types)

        # figure type conversions, if any
        type = format['type']
        is_numeric = type and type in 'n%fegdobh'
        if type in self._extra_types:
            type_converter = self._extra_types[type]
            s = getattr(type_converter, 'pattern', r'.+?')

            def f(string, m):
                return type_converter(string)
            self._type_conversions[group] = f
        elif type == 'n':
            s = '\d{1,3}([,.]\d{3})*'
            self._group_index += 1
            self._type_conversions[group] = int_convert(10)
        elif type == 'b':
            s = '(0[bB])?[01]+'
            self._type_conversions[group] = int_convert(2)
            self._group_index += 1
        elif type == 'o':
            s = '(0[oO])?[0-7]+'
            self._type_conversions[group] = int_convert(8)
            self._group_index += 1
        elif type == 'x':
            s = '(0[xX])?[0-9a-fA-F]+'
            self._type_conversions[group] = int_convert(16)
            self._group_index += 1
        elif type == '%':
            s = r'\d+(\.\d+)?%'
            self._group_index += 1
            self._type_conversions[group] = percentage
        elif type == 'f':
            s = r'\d+\.\d+'
            self._type_conversions[group] = lambda s, m: float(s)
        elif type == 'e':
            s = r'\d+\.\d+[eE][-+]?\d+|nan|NAN|[-+]?inf|[-+]?INF'
            self._type_conversions[group] = lambda s, m: float(s)
        elif type == 'g':
            s = r'\d+(\.\d+)?([eE][-+]?\d+)?|nan|NAN|[-+]?inf|[-+]?INF'
            self._group_index += 2
            self._type_conversions[group] = lambda s, m: float(s)
        elif type == 'd':
            s = r'\d+|0[xX][0-9a-fA-F]+|[0-9a-fA-F]+|0[bB][01]+|0[oO][0-7]+'
            self._type_conversions[group] = int_convert(10)
        elif type == 'ti':
            s = r'(\d{4}-\d\d-\d\d)((\s+|T)%s)?(Z|\s*[-+]\d\d:?\d\d)?' % \
                TIME_PAT
            n = self._group_index
            self._type_conversions[group] = partial(date_convert, ymd=n + 1,
                hms=n + 4, tz=n + 7)
            self._group_index += 7
        elif type == 'tg':
            s = r'(\d{1,2}[-/](\d{1,2}|%s)[-/]\d{4})(\s+%s)?%s?%s?' % (
                ALL_MONTHS_PAT, TIME_PAT, AM_PAT, TZ_PAT)
            n = self._group_index
            self._type_conversions[group] = partial(date_convert, dmy=n + 1,
                hms=n + 5, am=n + 8, tz=n + 9)
            self._group_index += 9
        elif type == 'ta':
            s = r'((\d{1,2}|%s)[-/]\d{1,2}[-/]\d{4})(\s+%s)?%s?%s?' % (
                ALL_MONTHS_PAT, TIME_PAT, AM_PAT, TZ_PAT)
            n = self._group_index
            self._type_conversions[group] = partial(date_convert, mdy=n + 1,
                hms=n + 5, am=n + 8, tz=n + 9)
            self._group_index += 9
        elif type == 'te':
            # this will allow microseconds through if they're present, but meh
            s = r'(%s,\s+)?(\d{1,2}\s+%s\s+\d{4})\s+%s%s' % (DAYS_PAT,
                MONTHS_PAT, TIME_PAT, TZ_PAT)
            n = self._group_index
            self._type_conversions[group] = partial(date_convert, dmy=n + 3,
                hms=n + 5, tz=n + 8)
            self._group_index += 8
        elif type == 'th':
            # slight flexibility here from the stock Apache format
            s = r'(\d{1,2}[-/]%s[-/]\d{4}):%s%s' % (MONTHS_PAT, TIME_PAT,
                TZ_PAT)
            n = self._group_index
            self._type_conversions[group] = partial(date_convert, dmy=n + 1,
                hms=n + 3, tz=n + 6)
            self._group_index += 6
        elif type == 'tc':
            s = r'(%s)\s+%s\s+(\d{1,2})\s+%s\s+(\d{4})' % (
                DAYS_PAT, MONTHS_PAT, TIME_PAT)
            n = self._group_index
            self._type_conversions[group] = partial(date_convert,
                d_m_y=(n + 4, n + 3, n + 8), hms=n + 5)
            self._group_index += 8
        elif type == 'tt':
            s = r'%s?%s?%s?' % (TIME_PAT, AM_PAT, TZ_PAT)
            n = self._group_index
            self._type_conversions[group] = partial(date_convert, hms=n + 1,
                am=n + 4, tz=n + 5)
            self._group_index += 5
        elif type == 'ts':
            s = r'%s(\s+)(\d+)(\s+)(\d{1,2}:\d{1,2}:\d{1,2})?' % (MONTHS_PAT)
            n = self._group_index
            self._type_conversions[group] = partial(date_convert, mm=n+1, dd=n+3,
                hms=n + 5)
            self._group_index += 5

        elif type:
            s = r'\%s+' % type
        else:
            s = '.+?'

        align = format['align']
        fill = format['fill']

        # handle some numeric-specific things like fill and sign
        if is_numeric:
            # prefix with something (align "=" trumps zero)
            if align == '=':
                # special case - align "=" acts like the zero above but with
                # configurable fill defaulting to "0"
                if not fill:
                    fill = '0'
                s = '%s*' % fill + s
            elif format['zero']:
                s = '0*' + s

            # allow numbers to be prefixed with a sign
            s = r'[-+ ]?' + s

        if not fill:
            fill = ' '

        # Place into a group now - this captures the value we want to keep.
        # Everything else from now is just padding to be stripped off
        if wrap:
            s = wrap % s
            self._group_index += 1

        if format['width']:
            # all we really care about is that if the format originally
            # specified a width then there will probably be padding - without
            # an explicit alignment that'll mean right alignment with spaces
            # padding
            if not align:
                align = '>'

        if fill in '.\+?*[](){}^$':
            fill = '\\' + fill

        # align "=" has been handled
        if align == '<':
            s = '%s%s*' % (s, fill)
        elif align == '>':
            s = '%s*%s' % (fill, s)
        elif align == '^':
            s = '%s*%s%s*' % (fill, s, fill)

        return s


class Result(object):
    '''The result of a parse() or search().

    Fixed results may be looked up using result[index]. Named results may be
    looked up using result['name'].
    '''
    def __init__(self, fixed, named, spans):
        self.fixed = fixed
        self.named = named
        self.spans = spans

    def __getitem__(self, item):
        if isinstance(item, int):
            return self.fixed[item]
        return self.named[item]

    def __repr__(self):
        return '<%s %r %r>' % (self.__class__.__name__, self.fixed,
            self.named)


class ResultIterator(object):
    '''The result of a findall() operation.

    Each element is a Result instance.
    '''
    def __init__(self, parser, string, pos, endpos):
        self.parser = parser
        self.string = string
        self.pos = pos
        self.endpos = endpos

    def __iter__(self):
        return self

    def __next__(self):
        m = self.parser._search_re.search(self.string, self.pos, self.endpos)
        if m is None:
            raise StopIteration()
        self.pos = m.end()
        return self.parser._generate_result(m)

    # pre-py3k compat
    next = __next__


def parse(format, string, extra_types={}):
    '''Using "format" attempt to pull values from "string".

    The format must match the string contents exactly. If the value
    you're looking for is instead just a part of the string use
    search().

    The return value will be an Result instance with two attributes:

     .fixed - tuple of fixed-position values from the string
     .named - dict of named values from the string

    If the format is invalid a ValueError will be raised.

    See the module documentation for the use of "extra_types".

    In the case there is no match parse() will return None.
    '''
    return Parser(format, extra_types=extra_types).parse(string)


def search(format, string, pos=0, endpos=None, extra_types={}):
    '''Search "string" for the first occurance of "format".

    The format may occur anywhere within the string. If
    instead you wish for the format to exactly match the string
    use parse().

    Optionally start the search at "pos" character index and limit the search
    to a maximum index of endpos - equivalent to search(string[:endpos]).

    The return value will be an Result instance with two attributes:

     .fixed - tuple of fixed-position values from the string
     .named - dict of named values from the string

    If the format is invalid a ValueError will be raised.

    See the module documentation for the use of "extra_types".

    In the case there is no match parse() will return None.
    '''
    return Parser(format, extra_types=extra_types).search(string, pos, endpos)


def findall(format, string, pos=0, endpos=None, extra_types={}):
    '''Search "string" for the all occurrances of "format".

    You will be returned an iterator that holds Result instances
    for each format match found.

    Optionally start the search at "pos" character index and limit the search
    to a maximum index of endpos - equivalent to search(string[:endpos]).

    Each Result instance has two attributes:

     .fixed - tuple of fixed-position values from the string
     .named - dict of named values from the string

    If the format is invalid a ValueError will be raised.

    See the module documentation for the use of "extra_types".
    '''
    return Parser(format, extra_types=extra_types).findall(string, pos, endpos)


def compile(format, extra_types={}):
    '''Create a Parser instance to parse "format".

    The resultant Parser has a method .parse(string) which
    behaves in the same manner as parse(format, string).

    Use this function if you intend to parse many strings
    with the same format.

    See the module documentation for the use of "extra_types".

    Returns a Parser instance.
    '''
    return Parser(format, extra_types=extra_types)


# Copyright (c) 2012-2013 Richard Jones <richard@python.org>
#
# Permission is hereby granted, free of charge, to any person obtaining a copy
# of this software and associated documentation files (the "Software"), to deal
# in the Software without restriction, including without limitation the rights
# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
# copies of the Software, and to permit persons to whom the Software is
# furnished to do so, subject to the following conditions:
#
#  The above copyright notice and this permission notice shall be included in
#  all copies or substantial portions of the Software.
#
# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
# SOFTWARE.

# vim: set filetype=python ts=4 sw=4 et si tw=75