summaryrefslogtreecommitdiffstats
path: root/Lib/cgi.py
blob: d4c55b73e11eaefa4b93f82f01436a940eaa66fb (plain)
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
#! /usr/local/bin/python

"""Support module for CGI (Common Gateway Interface) scripts.

This module defines a number of utilities for use by CGI scripts
written in Python.
"""

# XXX Perhaps there should be a slimmed version that doesn't contain
# all those backwards compatible and debugging classes and functions?

# History
# -------
# 
# Michael McLay started this module.  Steve Majewski changed the
# interface to SvFormContentDict and FormContentDict.  The multipart
# parsing was inspired by code submitted by Andreas Paepcke.  Guido van
# Rossum rewrote, reformatted and documented the module and is currently
# responsible for its maintenance.
# 

__version__ = "2.5"


# Imports
# =======

import string
import sys
import os
import urllib
import mimetools
import rfc822
import UserDict
from StringIO import StringIO


# Logging support
# ===============

logfile = ""            # Filename to log to, if not empty
logfp = None            # File object to log to, if not None

def initlog(*allargs):
    """Write a log message, if there is a log file.

    Even though this function is called initlog(), you should always
    use log(); log is a variable that is set either to initlog
    (initially), to dolog (once the log file has been opened), or to
    nolog (when logging is disabled).

    The first argument is a format string; the remaining arguments (if
    any) are arguments to the % operator, so e.g.
        log("%s: %s", "a", "b")
    will write "a: b" to the log file, followed by a newline.

    If the global logfp is not None, it should be a file object to
    which log data is written.

    If the global logfp is None, the global logfile may be a string
    giving a filename to open, in append mode.  This file should be
    world writable!!!  If the file can't be opened, logging is
    silently disabled (since there is no safe place where we could
    send an error message).

    """
    global logfp, log
    if logfile and not logfp:
        try:
            logfp = open(logfile, "a")
        except IOError:
            pass
    if not logfp:
        log = nolog
    else:
        log = dolog
    apply(log, allargs)

def dolog(fmt, *args):
    """Write a log message to the log file.  See initlog() for docs."""
    logfp.write(fmt%args + "\n")

def nolog(*allargs):
    """Dummy function, assigned to log when logging is disabled."""
    pass

log = initlog           # The current logging function


# Parsing functions
# =================

# Maximum input we will accept when REQUEST_METHOD is POST
# 0 ==> unlimited input
maxlen = 0

def parse(fp=None, environ=os.environ, keep_blank_values=0, strict_parsing=0):
    """Parse a query in the environment or from a file (default stdin)

        Arguments, all optional:

        fp              : file pointer; default: sys.stdin

        environ         : environment dictionary; default: os.environ

        keep_blank_values: flag indicating whether blank values in
            URL encoded forms should be treated as blank strings.  
            A true value indicates that blanks should be retained as 
            blank strings.  The default false value indicates that
            blank values are to be ignored and treated as if they were
            not included.

        strict_parsing: flag indicating what to do with parsing errors.
            If false (the default), errors are silently ignored.
            If true, errors raise a ValueError exception.
    """
    if not fp:
        fp = sys.stdin
    if not environ.has_key('REQUEST_METHOD'):
        environ['REQUEST_METHOD'] = 'GET'       # For testing stand-alone
    if environ['REQUEST_METHOD'] == 'POST':
        ctype, pdict = parse_header(environ['CONTENT_TYPE'])
        if ctype == 'multipart/form-data':
            return parse_multipart(fp, pdict)
        elif ctype == 'application/x-www-form-urlencoded':
            clength = string.atoi(environ['CONTENT_LENGTH'])
            if maxlen and clength > maxlen:
                raise ValueError, 'Maximum content length exceeded'
            qs = fp.read(clength)
        else:
            qs = ''                     # Unknown content-type
        if environ.has_key('QUERY_STRING'): 
            if qs: qs = qs + '&'
            qs = qs + environ['QUERY_STRING']
        elif sys.argv[1:]: 
            if qs: qs = qs + '&'
            qs = qs + sys.argv[1]
        environ['QUERY_STRING'] = qs    # XXX Shouldn't, really
    elif environ.has_key('QUERY_STRING'):
        qs = environ['QUERY_STRING']
    else:
        if sys.argv[1:]:
            qs = sys.argv[1]
        else:
            qs = ""
        environ['QUERY_STRING'] = qs    # XXX Shouldn't, really
    return parse_qs(qs, keep_blank_values, strict_parsing)


def parse_qs(qs, keep_blank_values=0, strict_parsing=0):
    """Parse a query given as a string argument.

        Arguments:

        qs: URL-encoded query string to be parsed

        keep_blank_values: flag indicating whether blank values in
            URL encoded queries should be treated as blank strings.  
            A true value indicates that blanks should be retained as 
            blank strings.  The default false value indicates that
            blank values are to be ignored and treated as if they were
            not included.

        strict_parsing: flag indicating what to do with parsing errors.
            If false (the default), errors are silently ignored.
            If true, errors raise a ValueError exception.
    """
    dict = {}
    for name, value in parse_qsl(qs, keep_blank_values, strict_parsing):
        if dict.has_key(name):
            dict[name].append(value)
        else:
            dict[name] = [value]
    return dict

def parse_qsl(qs, keep_blank_values=0, strict_parsing=0):
    """Parse a query given as a string argument.

    Arguments:

    qs: URL-encoded query string to be parsed

    keep_blank_values: flag indicating whether blank values in
        URL encoded queries should be treated as blank strings.  A
        true value indicates that blanks should be retained as blank
        strings.  The default false value indicates that blank values
        are to be ignored and treated as if they were  not included.

    strict_parsing: flag indicating what to do with parsing errors. If
        false (the default), errors are silently ignored. If true,
        errors raise a ValueError exception. 

    Returns a list, as G-d intended.
    """
    pairs = [s2 for s1 in qs.split('&') for s2 in s1.split(';')]
    r = []
    for name_value in pairs:
        nv = name_value.split('=', 1)
        if len(nv) != 2:
            if strict_parsing:
                raise ValueError, "bad query field: %s" % `name_value`
            continue
        if len(nv[1]) or keep_blank_values:
            name = urllib.unquote(string.replace(nv[0], '+', ' '))
            value = urllib.unquote(string.replace(nv[1], '+', ' '))
            r.append((name, value))

    return r


def parse_multipart(fp, pdict):
    """Parse multipart input.

    Arguments:
    fp   : input file
    pdict: dictionary containing other parameters of conten-type header

    Returns a dictionary just like parse_qs(): keys are the field names, each 
    value is a list of values for that field.  This is easy to use but not 
    much good if you are expecting megabytes to be uploaded -- in that case, 
    use the FieldStorage class instead which is much more flexible.  Note 
    that content-type is the raw, unparsed contents of the content-type 
    header.
    
    XXX This does not parse nested multipart parts -- use FieldStorage for 
    that.
    
    XXX This should really be subsumed by FieldStorage altogether -- no 
    point in having two implementations of the same parsing algorithm.

    """
    if pdict.has_key('boundary'):
        boundary = pdict['boundary']
    else:
        boundary = ""
    nextpart = "--" + boundary
    lastpart = "--" + boundary + "--"
    partdict = {}
    terminator = ""

    while terminator != lastpart:
        bytes = -1
        data = None
        if terminator:
            # At start of next part.  Read headers first.
            headers = mimetools.Message(fp)
            clength = headers.getheader('content-length')
            if clength:
                try:
                    bytes = string.atoi(clength)
                except string.atoi_error:
                    pass
            if bytes > 0:
                if maxlen and bytes > maxlen:
                    raise ValueError, 'Maximum content length exceeded'
                data = fp.read(bytes)
            else:
                data = ""
        # Read lines until end of part.
        lines = []
        while 1:
            line = fp.readline()
            if not line:
                terminator = lastpart # End outer loop
                break
            if line[:2] == "--":
                terminator = string.strip(line)
                if terminator in (nextpart, lastpart):
                    break
            lines.append(line)
        # Done with part.
        if data is None:
            continue
        if bytes < 0:
            if lines:
                # Strip final line terminator
                line = lines[-1]
                if line[-2:] == "\r\n":
                    line = line[:-2]
                elif line[-1:] == "\n":
                    line = line[:-1]
                lines[-1] = line
                data = string.joinfields(lines, "")
        line = headers['content-disposition']
        if not line:
            continue
        key, params = parse_header(line)
        if key != 'form-data':
            continue
        if params.has_key('name'):
            name = params['name']
        else:
            continue
        if partdict.has_key(name):
            partdict[name].append(data)
        else:
            partdict[name] = [data]

    return partdict


def parse_header(line):
    """Parse a Content-type like header.

    Return the main content-type and a dictionary of options.

    """
    plist = map(string.strip, string.splitfields(line, ';'))
    key = string.lower(plist[0])
    del plist[0]
    pdict = {}
    for p in plist:
        i = string.find(p, '=')
        if i >= 0:
            name = string.lower(string.strip(p[:i]))
            value = string.strip(p[i+1:])
            if len(value) >= 2 and value[0] == value[-1] == '"':
                value = value[1:-1]
            pdict[name] = value
    return key, pdict


# Classes for field storage
# =========================

class MiniFieldStorage:

    """Like FieldStorage, for use when no file uploads are possible."""

    # Dummy attributes
    filename = None
    list = None
    type = None
    file = None
    type_options = {}
    disposition = None
    disposition_options = {}
    headers = {}

    def __init__(self, name, value):
        """Constructor from field name and value."""
        self.name = name
        self.value = value
        # self.file = StringIO(value)

    def __repr__(self):
        """Return printable representation."""
        return "MiniFieldStorage(%s, %s)" % (`self.name`, `self.value`)


class FieldStorage:

    """Store a sequence of fields, reading multipart/form-data.

    This class provides naming, typing, files stored on disk, and
    more.  At the top level, it is accessible like a dictionary, whose
    keys are the field names.  (Note: None can occur as a field name.)
    The items are either a Python list (if there's multiple values) or
    another FieldStorage or MiniFieldStorage object.  If it's a single
    object, it has the following attributes:

    name: the field name, if specified; otherwise None

    filename: the filename, if specified; otherwise None; this is the
        client side filename, *not* the file name on which it is
        stored (that's a temporary file you don't deal with)

    value: the value as a *string*; for file uploads, this
        transparently reads the file every time you request the value

    file: the file(-like) object from which you can read the data;
        None if the data is stored a simple string

    type: the content-type, or None if not specified

    type_options: dictionary of options specified on the content-type
        line

    disposition: content-disposition, or None if not specified

    disposition_options: dictionary of corresponding options

    headers: a dictionary(-like) object (sometimes rfc822.Message or a
        subclass thereof) containing *all* headers

    The class is subclassable, mostly for the purpose of overriding
    the make_file() method, which is called internally to come up with
    a file open for reading and writing.  This makes it possible to
    override the default choice of storing all files in a temporary
    directory and unlinking them as soon as they have been opened.

    """

    def __init__(self, fp=None, headers=None, outerboundary="",
                 environ=os.environ, keep_blank_values=0, strict_parsing=0):
        """Constructor.  Read multipart/* until last part.

        Arguments, all optional:

        fp              : file pointer; default: sys.stdin
            (not used when the request method is GET)

        headers         : header dictionary-like object; default:
            taken from environ as per CGI spec

        outerboundary   : terminating multipart boundary
            (for internal use only)

        environ         : environment dictionary; default: os.environ

        keep_blank_values: flag indicating whether blank values in
            URL encoded forms should be treated as blank strings.  
            A true value indicates that blanks should be retained as 
            blank strings.  The default false value indicates that
            blank values are to be ignored and treated as if they were
            not included.

        strict_parsing: flag indicating what to do with parsing errors.
            If false (the default), errors are silently ignored.
            If true, errors raise a ValueError exception.

        """
        method = 'GET'
        self.keep_blank_values = keep_blank_values
        self.strict_parsing = strict_parsing
        if environ.has_key('REQUEST_METHOD'):
            method = string.upper(environ['REQUEST_METHOD'])
        if method == 'GET' or method == 'HEAD':
            if environ.has_key('QUERY_STRING'):
                qs = environ['QUERY_STRING']
            elif sys.argv[1:]:
                qs = sys.argv[1]
            else:
                qs = ""
            fp = StringIO(qs)
            if headers is None:
                headers = {'content-type':
                           "application/x-www-form-urlencoded"}
        if headers is None:
            headers = {}
            if method == 'POST':
                # Set default content-type for POST to what's traditional
                headers['content-type'] = "application/x-www-form-urlencoded"
            if environ.has_key('CONTENT_TYPE'):
                headers['content-type'] = environ['CONTENT_TYPE']
            if environ.has_key('CONTENT_LENGTH'):
                headers['content-length'] = environ['CONTENT_LENGTH']
        self.fp = fp or sys.stdin
        self.headers = headers
        self.outerboundary = outerboundary

        # Process content-disposition header
        cdisp, pdict = "", {}
        if self.headers.has_key('content-disposition'):
            cdisp, pdict = parse_header(self.headers['content-disposition'])
        self.disposition = cdisp
        self.disposition_options = pdict
        self.name = None
        if pdict.has_key('name'):
            self.name = pdict['name']
        self.filename = None
        if pdict.has_key('filename'):
            self.filename = pdict['filename']

        # Process content-type header
        #
        # Honor any existing content-type header.  But if there is no
        # content-type header, use some sensible defaults.  Assume
        # outerboundary is "" at the outer level, but something non-false
        # inside a multi-part.  The default for an inner part is text/plain,
        # but for an outer part it should be urlencoded.  This should catch
        # bogus clients which erroneously forget to include a content-type
        # header.
        #
        # See below for what we do if there does exist a content-type header,
        # but it happens to be something we don't understand.
        if self.headers.has_key('content-type'):
            ctype, pdict = parse_header(self.headers['content-type'])
        elif self.outerboundary or method != 'POST':
            ctype, pdict = "text/plain", {}
        else:
            ctype, pdict = 'application/x-www-form-urlencoded', {}
        self.type = ctype
        self.type_options = pdict
        self.innerboundary = ""
        if pdict.has_key('boundary'):
            self.innerboundary = pdict['boundary']
        clen = -1
        if self.headers.has_key('content-length'):
            try:
                clen = string.atoi(self.headers['content-length'])
            except:
                pass
            if maxlen and clen > maxlen:
                raise ValueError, 'Maximum content length exceeded'
        self.length = clen

        self.list = self.file = None
        self.done = 0
        if ctype == 'application/x-www-form-urlencoded':
            self.read_urlencoded()
        elif ctype[:10] == 'multipart/':
            self.read_multi(environ, keep_blank_values, strict_parsing)
        else:
            self.read_single()

    def __repr__(self):
        """Return a printable representation."""
        return "FieldStorage(%s, %s, %s)" % (
                `self.name`, `self.filename`, `self.value`)

    def __getattr__(self, name):
        if name != 'value':
            raise AttributeError, name
        if self.file:
            self.file.seek(0)
            value = self.file.read()
            self.file.seek(0)
        elif self.list is not None:
            value = self.list
        else:
            value = None
        return value

    def __getitem__(self, key):
        """Dictionary style indexing."""
        if self.list is None:
            raise TypeError, "not indexable"
        found = []
        for item in self.list:
            if item.name == key: found.append(item)
        if not found:
            raise KeyError, key
        if len(found) == 1:
            return found[0]
        else:
            return found

    def getvalue(self, key, default=None):
        """Dictionary style get() method, including 'value' lookup."""
        if self.has_key(key):
            value = self[key]
            if type(value) is type([]):
                return map(lambda v: v.value, value)
            else:
                return value.value
        else:
            return default

    def keys(self):
        """Dictionary style keys() method."""
        if self.list is None:
            raise TypeError, "not indexable"
        keys = []
        for item in self.list:
            if item.name not in keys: keys.append(item.name)
        return keys

    def has_key(self, key):
        """Dictionary style has_key() method."""
        if self.list is None:
            raise TypeError, "not indexable"
        for item in self.list:
            if item.name == key: return 1
        return 0

    def __len__(self):
        """Dictionary style len(x) support."""
        return len(self.keys())

    def read_urlencoded(self):
        """Internal: read data in query string format."""
        qs = self.fp.read(self.length)
        self.list = list = []
        for key, value in parse_qsl(qs, self.keep_blank_values,
                                    self.strict_parsing):
            list.append(MiniFieldStorage(key, value))
        self.skip_lines()

    FieldStorageClass = None

    def read_multi(self, environ, keep_blank_values, strict_parsing):
        """Internal: read a part that is itself multipart."""
        self.list = []
        klass = self.FieldStorageClass or self.__class__
        part = klass(self.fp, {}, self.innerboundary,
                     environ, keep_blank_values, strict_parsing)
        # Throw first part away
        while not part.done:
            headers = rfc822.Message(self.fp)
            part = klass(self.fp, headers, self.innerboundary,
                         environ, keep_blank_values, strict_parsing)
            self.list.append(part)
        self.skip_lines()

    def read_single(self):
        """Internal: read an atomic part."""
        if self.length >= 0:
            self.read_binary()
            self.skip_lines()
        else:
            self.read_lines()
        self.file.seek(0)

    bufsize = 8*1024            # I/O buffering size for copy to file

    def read_binary(self):
        """Internal: read binary data."""
        self.file = self.make_file('b')
        todo = self.length
        if todo >= 0:
            while todo > 0:
                data = self.fp.read(min(todo, self.bufsize))
                if not data:
                    self.done = -1
                    break
                self.file.write(data)
                todo = todo - len(data)

    def read_lines(self):
        """Internal: read lines until EOF or outerboundary."""
        self.file = self.make_file('')
        if self.outerboundary:
            self.read_lines_to_outerboundary()
        else:
            self.read_lines_to_eof()

    def read_lines_to_eof(self):
        """Internal: read lines until EOF."""
        while 1:
            line = self.fp.readline()
            if not line:
                self.done = -1
                break
            self.file.write(line)

    def read_lines_to_outerboundary(self):
        """Internal: read lines until outerboundary."""
        next = "--" + self.outerboundary
        last = next + "--"
        delim = ""
        while 1:
            line = self.fp.readline()
            if not line:
                self.done = -1
                break
            if line[:2] == "--":
                strippedline = string.strip(line)
                if strippedline == next:
                    break
                if strippedline == last:
                    self.done = 1
                    break
            odelim = delim
            if line[-2:] == "\r\n":
                delim = "\r\n"
                line = line[:-2]
            elif line[-1] == "\n":
                delim = "\n"
                line = line[:-1]
            else:
                delim = ""
            self.file.write(odelim + line)

    def skip_lines(self):
        """Internal: skip lines until outer boundary if defined."""
        if not self.outerboundary or self.done:
            return
        next = "--" + self.outerboundary
        last = next + "--"
        while 1:
            line = self.fp.readline()
            if not line:
                self.done = -1
                break
            if line[:2] == "--":
                strippedline = string.strip(line)
                if strippedline == next:
                    break
                if strippedline == last:
                    self.done = 1
                    break

    def make_file(self, binary=None):
        """Overridable: return a readable & writable file.

        The file will be used as follows:
        - data is written to it
        - seek(0)
        - data is read from it

        The 'binary' argument is unused -- the file is always opened
        in binary mode.

        This version opens a temporary file for reading and writing,
        and immediately deletes (unlinks) it.  The trick (on Unix!) is
        that the file can still be used, but it can't be opened by
        another process, and it will automatically be deleted when it
        is closed or when the current process terminates.

        If you want a more permanent file, you derive a class which
        overrides this method.  If you want a visible temporary file
        that is nevertheless automatically deleted when the script
        terminates, try defining a __del__ method in a derived class
        which unlinks the temporary files you have created.

        """
        import tempfile
        return tempfile.TemporaryFile("w+b")
        


# Backwards Compatibility Classes
# ===============================

class FormContentDict(UserDict.UserDict):
    """Form content as dictionary with a list of values per field.

    form = FormContentDict()

    form[key] -> [value, value, ...]
    form.has_key(key) -> Boolean
    form.keys() -> [key, key, ...]
    form.values() -> [[val, val, ...], [val, val, ...], ...]
    form.items() ->  [(key, [val, val, ...]), (key, [val, val, ...]), ...]
    form.dict == {key: [val, val, ...], ...}

    """
    def __init__(self, environ=os.environ):
        self.dict = self.data = parse(environ=environ)
        self.query_string = environ['QUERY_STRING']


class SvFormContentDict(FormContentDict):
    """Form content as dictionary expecting a single value per field.

    If you only expect a single value for each field, then form[key]
    will return that single value.  It will raise an IndexError if
    that expectation is not true.  If you expect a field to have
    possible multiple values, than you can use form.getlist(key) to
    get all of the values.  values() and items() are a compromise:
    they return single strings where there is a single value, and
    lists of strings otherwise.

    """
    def __getitem__(self, key):
        if len(self.dict[key]) > 1: 
            raise IndexError, 'expecting a single value' 
        return self.dict[key][0]
    def getlist(self, key):
        return self.dict[key]
    def values(self):
        result = []
        for value in self.dict.values():
            if len(value) == 1:
                result.append(value[0])
            else: result.append(value)
        return result
    def items(self):
        result = []
        for key, value in self.dict.items():
            if len(value) == 1:
                result.append((key, value[0]))
            else: result.append((key, value))
        return result


class InterpFormContentDict(SvFormContentDict):
    """This class is present for backwards compatibility only.""" 
    def __getitem__(self, key):
        v = SvFormContentDict.__getitem__(self, key)
        if v[0] in string.digits + '+-.':
            try: return string.atoi(v)
            except ValueError:
                try: return string.atof(v)
                except ValueError: pass
        return string.strip(v)
    def values(self):
        result = []
        for key in self.keys():
            try:
                result.append(self[key])
            except IndexError:
                result.append(self.dict[key])
        return result
    def items(self):
        result = []
        for key in self.keys():
            try:
                result.append((key, self[key]))
            except IndexError:
                result.append((key, self.dict[key]))
        return result


class FormContent(FormContentDict):
    """This class is present for backwards compatibility only.""" 
    def values(self, key):
        if self.dict.has_key(key) :return self.dict[key]
        else: return None
    def indexed_value(self, key, location):
        if self.dict.has_key(key):
            if len(self.dict[key]) > location:
                return self.dict[key][location]
            else: return None
        else: return None
    def value(self, key):
        if self.dict.has_key(key): return self.dict[key][0]
        else: return None
    def length(self, key):
        return len(self.dict[key])
    def stripped(self, key):
        if self.dict.has_key(key): return string.strip(self.dict[key][0])
        else: return None
    def pars(self):
        return self.dict


# Test/debug code
# ===============

def test(environ=os.environ):
    """Robust test CGI script, usable as main program.

    Write minimal HTTP headers and dump all information provided to
    the script in HTML form.

    """
    import traceback
    print "Content-type: text/html"
    print
    sys.stderr = sys.stdout
    try:
        form = FieldStorage()   # Replace with other classes to test those
        print_directory()
        print_arguments()
        print_form(form)
        print_environ(environ)
        print_environ_usage()
        def f():
            exec "testing print_exception() -- <I>italics?</I>"
        def g(f=f):
            f()
        print "<H3>What follows is a test, not an actual exception:</H3>"
        g()
    except:
        print_exception()

    print "<H1>Second try with a small maxlen...</H1>"

    global maxlen
    maxlen = 50
    try:
        form = FieldStorage()   # Replace with other classes to test those
        print_directory()
        print_arguments()
        print_form(form)
        print_environ(environ)
    except:
        print_exception()

def print_exception(type=None, value=None, tb=None, limit=None):
    if type is None:
        type, value, tb = sys.exc_info()
    import traceback
    print
    print "<H3>Traceback (innermost last):</H3>"
    list = traceback.format_tb(tb, limit) + \
           traceback.format_exception_only(type, value)
    print "<PRE>%s<B>%s</B></PRE>" % (
        escape(string.join(list[:-1], "")),
        escape(list[-1]),
        )
    del tb

def print_environ(environ=os.environ):
    """Dump the shell environment as HTML."""
    keys = environ.keys()
    keys.sort()
    print
    print "<H3>Shell Environment:</H3>"
    print "<DL>"
    for key in keys:
        print "<DT>", escape(key), "<DD>", escape(environ[key])
    print "</DL>" 
    print

def print_form(form):
    """Dump the contents of a form as HTML."""
    keys = form.keys()
    keys.sort()
    print
    print "<H3>Form Contents:</H3>"
    if not keys:
        print "<P>No form fields."
    print "<DL>"
    for key in keys:
        print "<DT>" + escape(key) + ":",
        value = form[key]
        print "<i>" + escape(`type(value)`) + "</i>"
        print "<DD>" + escape(`value`)
    print "</DL>"
    print

def print_directory():
    """Dump the current directory as HTML."""
    print
    print "<H3>Current Working Directory:</H3>"
    try:
        pwd = os.getcwd()
    except os.error, msg:
        print "os.error:", escape(str(msg))
    else:
        print escape(pwd)
    print

def print_arguments():
    print
    print "<H3>Command Line Arguments:</H3>"
    print
    print sys.argv
    print

def print_environ_usage():
    """Dump a list of environment variables used by CGI as HTML."""
    print """
<H3>These environment variables could have been set:</H3>
<UL>
<LI>AUTH_TYPE
<LI>CONTENT_LENGTH
<LI>CONTENT_TYPE
<LI>DATE_GMT
<LI>DATE_LOCAL
<LI>DOCUMENT_NAME
<LI>DOCUMENT_ROOT
<LI>DOCUMENT_URI
<LI>GATEWAY_INTERFACE
<LI>LAST_MODIFIED
<LI>PATH
<LI>PATH_INFO
<LI>PATH_TRANSLATED
<LI>QUERY_STRING
<LI>REMOTE_ADDR
<LI>REMOTE_HOST
<LI>REMOTE_IDENT
<LI>REMOTE_USER
<LI>REQUEST_METHOD
<LI>SCRIPT_NAME
<LI>SERVER_NAME
<LI>SERVER_PORT
<LI>SERVER_PROTOCOL
<LI>SERVER_ROOT
<LI>SERVER_SOFTWARE
</UL>
In addition, HTTP headers sent by the server may be passed in the
environment as well.  Here are some common variable names:
<UL>
<LI>HTTP_ACCEPT
<LI>HTTP_CONNECTION
<LI>HTTP_HOST
<LI>HTTP_PRAGMA
<LI>HTTP_REFERER
<LI>HTTP_USER_AGENT
</UL>
"""


# Utilities
# =========

def escape(s, quote=None):
    """Replace special characters '&', '<' and '>' by SGML entities."""
    s = string.replace(s, "&", "&amp;") # Must be done first!
    s = string.replace(s, "<", "&lt;")
    s = string.replace(s, ">", "&gt;",)
    if quote:
        s = string.replace(s, '"', "&quot;")
    return s


# Invoke mainline
# ===============

# Call test() when this file is run as a script (not imported as a module)
if __name__ == '__main__': 
    test()