-
Notifications
You must be signed in to change notification settings - Fork 0
/
DSV.py
executable file
·1084 lines (940 loc) · 44.8 KB
/
DSV.py
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
"""
DSV.py - Cliff Wells, 2002
Import/export DSV (delimiter separated values, a generalization of CSV).
Basic use:
from DSV import DSV
data = file.read()
qualifier = DSV.guessTextQualifier(data) # optional
data = DSV.organizeIntoLines(data, textQualifier = qualifier)
delimiter = DSV.guessDelimiter(data) # optional
data = DSV.importDSV(data, delimiter = delimiter, textQualifier = qualifier)
hasHeader = DSV.guessHeaders(data) # optional
If you know the delimiters, qualifiers, etc, you may skip the optional
'guessing' steps as they rely on heuristics anyway (although they seem
to work well, there is no guarantee they are correct). What they are
best used for is to make a good guess regarding the data structure and then
let the user confirm it.
As such there is a 'wizard' to aid in this process (use this in lieu of
the above code - requires wxPython):
from DSV import DSV
dlg = DSV.ImportWizardDialog(parent, -1, 'DSV Import Wizard', filename)
dlg.ShowModal()
headers, data = dlg.ImportData() # may also return None
dlg.Destroy()
The dlg.ImportData() method may also take a function as an optional argument
specifying what it should do about malformed rows. See the example at the bottom
of this file. A few common functions are provided in this file (padRow, skipRow,
useRow).
Requires Python 2.0 or later
Wizards tested with wxPython 2.2.5/NT 4.0, 2.3.2/Win2000 and Linux/GTK (RedHat 7, 8, 9)
"""
__version__ = '1.4.1'
"""
Bugs/Caveats:
- Although I've tested this stuff on varied data, I'm sure there are cases
that I haven't seen that will choke any one of these routines (or at least
return invalid data). This is beta code!
- guessTextQualifier() algorithm is limited to quotes (double or single).
- Surprising feature: Hitting <enter> on wxSpinCtrl causes seg
fault under Linux/GTK (not Win32). Strangely, pressing <tab> seems ok.
Therefore, I had to use wxSpinButton. Also, spurious spin events get
generated for both of these controls (e.g. when calling wxBeginBusyCursor)
- Keyboard navigation needs to be implemented on wizards
- There may be issues with cr/lf translation, although I haven't yet seen any.
Why another CSV tool?:
- Because I needed a more flexible CSV importer, one that could accept different
delimiters (not just commas or tabs), one that could make an intelligent guess
regarding file structure (for user convenience), be compatible with the files
output by MS Excel, and finally, be easily integrated with a wizard. All of the
modules I have seen prior to this fell short on one count or another.
- It seemed interesting.
To do:
- Better guessTextQualifier() algorithm. In the perfect world I envision, I can
use any character as a text qualifier, not just quotes.
- Finish wizards and move them into separate module.
- Better guessHeaders() algorithm, although this is difficult.
- Optimize maps() - try to eliminate lambda when possible
- Optimize memory usage. Presently the entire file is loaded and then saved as
a list. A better approach might be to analyze a smaller part of the file and
then return an iterator to step through it.
"""
# Changelog
# 1.4.1:
# - Several small enhancements, requested by Danny Adair:
# - pass record (line) number to errorHandler (importDSV)
# WARNING: this is an incompatible but trivial change. User-defined
# error handlers must accomodate the new argument in their signature.
# See the demo at the bottom of this file for an example.
# - optional newline specifier for exportDSV
# - optional stripping of whitespace from data (importDSV)
# - optional start, end arguments for importing portions of a file (importDSV)
#
# 1.4:
# - Fixed small bug in demo (forgotten Destroy()) that caused a hang
# when Cancel was pressed.
# - Removed extraneous guessHeaders() call in wizard. I can only say,
# "what the??" and remember to profile. This was a huge time waster.
#
# 1.3.9
# - Fixed real problem on Win32 in that wxProgressDialog must reach max
# value in order to close.
#
# 1.3.8
# - Change demo to use wxApp rather than wxPySimpleApp as it seemed
# to have problems on Win32 (per Kevin Altis)
#
# 1.37
# - Fix for font issue under GTK2 (thanks to Ahmad Baitalmal)
# - Added some space below the Ok/Cancel buttons.
#
# 1.36
# - Bugfix submitted by "nobody" ;) on SF
#
# 1.3.4 to 1.3.5:
# - Nigel Hathaway finds yet another bug (or two). Can't seem to make him
# use something else, so they had to be fixed. It's especially difficult
# to ignore him since he provided the fix. Very annoying.
# - Problem with odd quote/delimiter combinations (SF bug #620284)
# - Losing empty fields at beginning/end (#619771)
# - Whitespace stripped from around string (#620115)
#
# 1.3.3 to 1.3.4(a):
# - Fixed bug in exportDSV that failed to quote data containing delimiter
# thanks to nhathaway@users.sourceforge.net
#
# 1.3 to 1.3.1:
# - Test for presence of wxPython (since it's not required except for wizard)
# - Changed "from wxPython.wx import *" to "from wxPython import wx"
# - Changed sample csv file (darkwave.csv) to demonstrate embedded quotes
import sys
# import pre as re # sre was broken, appears okay now. Try this if there are problems.
import re
import copy
import exceptions
import string
# RedHat 8.0 (or rather GTK2?) sets LANG = en_us.UTF-8 and apparently some
# older apps (including wxGTK) can't handle this. The fix is to set LANG=C
# before running the app. Thanks to Ahmad Baitalmal for supplying this info.
import os
os.putenv('LANG', 'C')
try:
from wxPython import wx, grid
except ImportError:
wx = None
class InvalidDelimiter(exceptions.StandardError): pass
class InvalidTextQualifier(exceptions.StandardError): pass
class InvalidData(exceptions.StandardError): pass
class InvalidNumberOfColumns(exceptions.StandardError): pass
# ------------------------------------------------------------------------------
def guessTextQualifier(input):
"""
PROTOTYPE:
guessTextQualifier(input)
DESCRIPTION:
tries to guess if the text qualifier (a character delimiting ambiguous data)
is a single or double-quote (or None)
ARGUMENTS:
- input is raw data as a string
RETURNS:
single character or None
"""
# Algorithm: looks for text enclosed between two identical quotes (the probable
# qualifier) which are preceded and followed by the same character (the
# probable delimiter), for example:
# ,'some text',
# The quote with the most wins.
data = input[:16 * 1024] # limit sample to 16k
regexp = re.compile('(?:(?:^|\n)(?P<b_quote>["\']).*?(?P=b_quote))|'
'(?:(?P<delim>.)(?P<quote>["\']).*?(?P=quote)(?=(?P=delim)|\n))|'
'(?:(?P<e_quote>["\']).*?(?P=e_quote)$)', re.M | re.S)
matches = filter(lambda i: reduce(lambda a, b: a + b, i), regexp.findall(data))
if not matches: return None
quotes = {}
for q in ('b_quote', 'quote', 'e_quote'):
n = regexp.groupindex[q] - 1
for m in matches:
key = m[n]
if key:
quotes[key] = quotes.get(key, 0) + 1
return reduce(lambda a, b, quotes = quotes:
(quotes[a] > quotes[b]) and a or b, quotes.keys())
# ------------------------------------------------------------------------------
def guessDelimiter(input, textQualifier = '"'):
"""
PROTOTYPE:
guessDelimiter(input, textQualifier = '\"')
DESCRIPTION:
Tries to guess the delimiter.
ARGUMENTS:
- input is raw data as string
- textQualifier is a character used to delimit ambiguous data
RETURNS:
single character or None
"""
# Algorithm: the delimiter /should/ occur the same number of times on each
# row. However, due to malformed data, it may not. We don't want an all or
# nothing approach, so we allow for small variations in the number.
# 1) build a table of the frequency of each character on every line.
# 2) build a table of freqencies of this frequency (meta-frequency?), e.g.
# "x occurred 5 times in 10 rows, 6 times in 1000 rows, 7 times in 2 rows"
# 3) use the mode of the meta-frequency to decide what the frequency /should/
# be for that character
# 4) find out how often the character actually meets that goal
# 5) the character that best meets its goal is the delimiter
# For performance reasons, the data is evaluated in chunks, so it can try
# and evaluate the smallest portion of the data possible, evaluating additional
# chunks as necessary.
if type(input) != type([]): return None
if len(input) < 2: return None
if textQualifier:
# eliminate text inside textQualifiers
regexp = re.compile('%s(.*?)%s' % (textQualifier, textQualifier), re.S)
subCode = compile("regexp.sub('', line)", '', 'eval')
else:
subCode = compile("line", '', 'eval')
ascii = [chr(c) for c in range(127)] # 7-bit ASCII
# build frequency tables
chunkLength = min(10, len(input))
iteration = 0
charFrequency = {}
modes = {}
delims = {}
start, end = 0, min(chunkLength, len(input))
while start < len(input):
iteration += 1
for line in input[start:end]:
l = eval(subCode)
for char in ascii:
metafrequency = charFrequency.get(char, {})
freq = l.strip().count(char) # must count even if frequency is 0
metafrequency[freq] = metafrequency.get(freq, 0) + 1 # value is the mode
charFrequency[char] = metafrequency
for char in charFrequency.keys():
items = charFrequency[char].items()
if len(items) == 1 and items[0][0] == 0: continue
# get the mode of the frequencies
if len(items) > 1:
modes[char] = reduce(lambda a, b: a[1] > b[1] and a or b, items)
# adjust the mode - subtract the sum of all other frequencies
items.remove(modes[char])
modes[char] = (modes[char][0], modes[char][1]
- reduce(lambda a, b: (0, a[1] + b[1]), items)[1])
else:
modes[char] = items[0]
# build a list of possible delimiters
modeList = modes.items()
total = float(chunkLength * iteration)
consistency = 1.0 # (rows of consistent data) / (number of rows) = 100%
threshold = 0.9 # minimum consistency threshold
while len(delims) == 0 and consistency >= threshold:
for k, v in modeList:
if v[0] > 0 and v[1] > 0:
if (v[1]/total) >= consistency:
delims[k] = v
consistency -= 0.01
if len(delims) == 1:
return delims.keys()[0]
# analyze another chunkLength lines
start = end
end += chunkLength
if not delims: return None
# if there's more than one candidate, look at quoted data for clues.
# while any character may be quoted, any delimiter that occurs as a
# part of the data /must/ be quoted.
if len(delims) > 1 and textQualifier is not None:
regexp = re.compile('%s(.*?)%s' % (textQualifier, textQualifier), re.S)
for line in input:
inQuotes = "".join(regexp.findall(line))
for d in delims.keys():
if not d in inQuotes:
del delims[d]
if len(delims) == 1:
return delims.keys()[0]
# if there's *still* more than one, fall back to a 'preferred' list
if len(delims) > 1:
for d in ['\t', ',', ';', ' ', ':']:
if d in delims.keys():
return d
# finally, just return the first damn character in the list
return delims.keys()[0]
# ------------------------------------------------------------------------------
def modeOfLengths(input):
"""
PROTOTYPE:
modeOfLengths(input)
DESCRIPTION:
Finds the mode (most frequently occurring value) of the lengths of the lines.
ARGUMENTS:
- input is list of lists of data
RETURNS:
mode as integer
"""
freq = {}
for row in input:
l = len(row)
freq[l] = freq.get(l, 0) + 1
return reduce(lambda a, b, freq = freq: (freq[a] > freq[b]) and a or b, freq.keys())
# ------------------------------------------------------------------------------
def guessHeaders(input, columns = 0):
"""
PROTOTYPE:
guessHeaders(input, columns = 0)
DESCRIPTION:
Decides whether row 0 is a header row
ARGUMENTS:
- input is a list of lists of data (as returned by importDSV)
- columns is either the expected number of columns in each row or 0
RETURNS:
- true if data has header row
"""
# Algorithm: creates a dictionary of types of data in each column. If any column
# is of a single type (say, integers), *except* for the first row, then the first
# row is presumed to be labels. If the type can't be determined, it is assumed to
# be a string in which case the length of the string is the determining factor: if
# all of the rows except for the first are the same length, it's a header.
# Finally, a 'vote' is taken at the end for each column, adding or subtracting from
# the likelihood of the first row being a header.
if type(input) != type([]): raise InvalidData, "list expected."
if len(input) < 2: return 0
if not columns:
columns = modeOfLengths(input)
columnTypes = {}
for i in range(columns): columnTypes[i] = None
for row in input[1:]:
if len(row) != columns:
continue # skip rows that have irregular number of columns
for col in columnTypes.keys():
try:
try:
# is it a built-in type (besides string)?
thisType = type(eval(row[col]))
except OverflowError:
# a long int?
thisType = type(eval(row[col] + 'L'))
thisType = type(0) # treat long ints as int
except:
# fallback to length of string
thisType = len(row[col])
if thisType != columnTypes[col]:
if columnTypes[col] is None: # add new column type
columnTypes[col] = thisType
else: # type is inconsistent, remove column from consideration
del columnTypes[col]
# finally, compare results against first row and vote on whether it's a header
hasHeader = 0
for col, colType in columnTypes.items():
if type(colType) == type(0): # it's a length
if len(input[0][col]) != colType:
hasHeader += 1
else:
hasHeader -= 1
else: # attempt typecast
try:
eval("%s(%s)" % (colType.__name__, input[0][col]))
except:
hasHeader += 1
else:
hasHeader -= 1
return hasHeader > 0
# ------------------------------------------------------------------------------
def organizeIntoLines(input, textQualifier = '"', limit = None):
"""
PROTOTYPE:
organizeIntoLines(input, textQualifier = '\"', limit = None)
DESCRIPTION:
Takes raw data (as from file.read()) and organizes it into lines.
Newlines that occur within text qualifiers are treated as normal
characters, not line delimiters.
ARGUMENTS:
- input is raw data as a string
- textQualifier is a character used to delimit ambiguous data
- limit is a integer specifying the maximum number of lines to organize
RETURNS:
list of strings
"""
# Algorithm: there should be an even number of text qualifiers on every line.
# If there isn't, that means that the newline at the end of the line must occur
# within qualifiers and doesn't really indicate the end of a record.
data = input.split('\n')
line = 0
while 1:
try:
while data[line].count(textQualifier) % 2: # while odd number
data[line] = data[line] + '\n' + data[line + 1] # add the next line
del data[line + 1] # delete the next line
line += 1
if limit and line > limit:
del data[limit:] # kill any lines that weren't processed
break
except:
break
# filter out empty lines
# data = filter(lambda i: "".join(i), data)
data = filter(string.join, data)
return data
# ------------------------------------------------------------------------------
# some common error handlers to pass to importDSV
# others might do things like log errors to a file.
# oldrow is the unparsed data, newrow is the parsed data
def padRow(linenumber, oldrow, newrow, columns, maxColumns):
"pads all rows to the same length with empty strings"
difference = maxColumns - len(newrow)
return newrow + ([''] * difference)
def skipRow(linenumber, oldrow, newrow, columns, maxColumns):
"skips any inconsistent rows"
return None
def useRow(linenumber, oldrow, newrow, columns, maxColumns):
"returns row unchanged"
return newrow
# ------------------------------------------------------------------------------
def importDSV(input, delimiter = ',', textQualifier = '"', columns = 0,
updateFunction = None, errorHandler = None,
startline = 0, endline = None, stripall = 0):
"""
PROTOTYPE:
importDSV(input, delimiter = ',', textQualifier = '\"', columns = 0,
updateFunction = None, errorHandler = None)
DESCRIPTION:
parses lines of data in CSV format
ARGUMENTS:
- input is a list of strings (built by organizeIntoLines)
- delimiter is the character used to delimit columns
- textQualifier is the character used to delimit ambiguous data
- columns is the expected number of columns in each row or 0
- updateFunction is a callback function called once per record (could be
used for updating progress bars). Its prototype is
updateFunction(percentDone)
- percentDone is an integer between 0 and 100
- errorHandler is a callback invoked whenever a row has an unexpected number
of columns. Its prototype is
errorHandler(linenumber, oldrow, newrow, columns, maxColumns)
where
- linenumber is where the error occurred in the file
- oldrow is the unparsed data
- newrow is the parsed data
- columns is the expected length of a row
- maxColumns is the longest row in the data
- startline, endline specify how much of the file to parse
- stripall causes all data (EVEN QUOTED data) to be mercilessly stripped of whitespace
RETURNS:
list of lists of data
"""
if type(input) != type([]):
raise InvalidData, "expected list of lists of strings"
if type(delimiter) != type('') or not delimiter:
raise InvalidDelimiter, `delimiter`
## if textQualifier:
## # fieldRex=re.compile('(?:(?:[,]|^)"(.*?)"(?=[,]|$))|(?:(?:[,]|^)([^",]*?)(?=[,]|$))')
## fieldRex = re.compile('(?:(?:[%s]|^)%s(.*?)%s(?=[%s]|$))|(?:(?:[%s]|^)([^%s%s]*?)(?=[%s]|$))'
## % (delimiter, textQualifier, textQualifier, delimiter,
## delimiter, textQualifier, delimiter, delimiter),
## re.S)
## else:
## fieldRex = re.compile('(?:[%s]|^)([^%s]*?)(?=[%s]|$)'
## % (delimiter, delimiter, delimiter), re.S)
if startline is not None: # 1.4.1
input = input[startline:]
if endline is not None:
input = input[:endline]
percent = 0.0
lineno = 0.0
newdata = []
maxColumns = 0
## for line in input:
## line = line.strip()
## record = fieldRex.findall(line)
## print record
## if textQualifier:
## record = [(i[0] or i[1]) for i in record]
## if textQualifier:
## record = [c.replace(textQualifier * 2, textQualifier) for c in record]
## newdata.append(record)
# This code was submitted by Nigel to replace the code commented out above.
# It addresses several issues with embedded quotes and delimiters. It seems that
# while off to a good start, regular expressions won't be able to handle certain
# situations. i.e. '''"Say ""hello"", World", ""''' would seem to be a problem as
# an embedded delimiter follows an embedded quote which throws off the re search.
for line in input:
if textQualifier:
record = []
inquotes = 0
for s in line.split(delimiter):
odd = s.count(textQualifier) % 2
if inquotes:
accu += delimiter + s.replace(textQualifier * 2, delimiter).\
replace(textQualifier, '').replace(delimiter, textQualifier)
if odd:
record.append(accu)
inquotes = 0
else:
# 1.3.6 bugfix: deal with case where s = "" to denote an empty string
if s.count(textQualifier): # discard whitespace outside of textQualifiers when they are used
s = s.strip()
# fix new problem with ""
if s == textQualifier * 2:
s = ""
accu = s.replace(textQualifier * 2, delimiter).\
replace(textQualifier, '').replace(delimiter, textQualifier)
if odd:
inquotes = 1
else:
record.append(accu)
else:
#record = map(lambda x: x.strip(), line.split(delimiter))
record = map(string.strip, line.split(delimiter))
if stripall: # 1.4.1
record = map(string.strip, record)
newdata.append(record)
# (end of replacement code)
if updateFunction is not None:
lineno = lineno + 1.0
newpercent = int((lineno / len(input)) * 100)
if percent != newpercent:
percent = newpercent
if not updateFunction(percent):
return None
if not columns:
columns = modeOfLengths(newdata)
maxColumns = max([len(line) for line in newdata])
# consistency check
for record in xrange(len(newdata)):
length = len(newdata[record])
difference = length - columns
if difference:
if errorHandler is None:
raise InvalidNumberOfColumns, "Expected %d, got %d" % (columns, length)
else:
newdata[record] = errorHandler(record, input[record], newdata[record], columns, maxColumns)
# remove null values from data
# newdata = filter(lambda i: i, newdata)
newdata = filter(None, newdata)
return newdata
# ------------------------------------------------------------------------------
def exportDSV(input, delimiter = ',', textQualifier = '"', quoteall = 0, newline = '\n'):
"""
PROTOTYPE:
exportDSV(input, delimiter = ',', textQualifier = '\"', quoteall = 0)
DESCRIPTION:
Exports to DSV (delimiter-separated values) format.
ARGUMENTS:
- input is list of lists of data (as returned by importDSV)
- delimiter is character used to delimit columns
- textQualifier is character used to delimit ambiguous data
- quoteall is boolean specifying whether to quote all data or only data
that requires it
RETURNS:
data as string
"""
if not delimiter or type(delimiter) != type(''): raise InvalidDelimiter
if not textQualifier or type(delimiter) != type(''): raise InvalidTextQualifier
# double-up all text qualifiers in data (i.e. can't becomes can''t)
data = map(lambda i, q = textQualifier:
map(lambda j, q = q: str(j).replace(q, q * 2), i),
input)
if quoteall: # quote every data value
data = map(lambda i, q = textQualifier:
map(lambda j, q = q: q + j + q, i),
data)
else: # quote only the values that contain qualifiers, delimiters or newlines
data = map(lambda i, q = textQualifier, d = delimiter:
map(lambda j, q = q, d = d: ((j.find(q) != -1 or j.find(d) != -1
or j.find('\n') != -1)
and (q + j + q)) or j, i), data)
# assemble each line with delimiters
data = [delimiter.join(line) for line in data]
# assemble all lines together, separated by newlines
data = newline.join(data)
return data
if wx is not None:
# ------------------------------------------------------------------------------
class ImportWizardPanel_Delimiters(wx.wxPanel):
"""
CLASS(SUPERCLASS):
ImportWizardPanel_Delimiters(wx.wxPanel)
DESCRIPTION:
A wx.wxPanel that provides a basic interface for validating and changing the
parameters for importing a delimited text file. Similar to MS Excel's
CSV import wizard. Can be used in a series of wizards or embedded in an
application.
PROTOTYPE:
ImportWizardPanel_Delimiters(parent, id, file, data, isValidCallback = None,
pos = wx.wxDefaultPosition, size = wx.wxDefaultSize,
style = wx.wxTAB_TRAVERSAL, name = 'ImportWizardPanel')
ARGUMENTS:
- parent is the parent window
- id is the id of this wizard panel
- file is the name of the file being imported
- data is the raw data to be parsed
- isValidCallback is a callback function that accepts a single boolean argument
If the argument is true, the wizard is in a valid state (all the settings are
acceptable), if the argument is false, trying to import will likely cause an
exception.
METHODS:
- GetDelimiters()
returns list of characters used as delimiters
- GetTextQualifiers()
returns character used as text qualifier or None
- GetHasHeaders()
returns true if first row is header
"""
def __init__(self, parent, id, file, data, isValidCallback = None,
pos = wx.wxDefaultPosition, size = wx.wxDefaultSize,
style = wx.wxTAB_TRAVERSAL, name = "ImportWizardPanel"):
wx.wxPanel.__init__(self, parent, id, pos, size, style, name)
self.SetAutoLayout(wx.true)
mainSizer = wx.wxFlexGridSizer(3, 1)
self.SetSizer(mainSizer)
mainSizer.AddGrowableCol(0)
self.initialized = wx.false
self.data = data
self.isValidCallback = isValidCallback
self.Validate = (isValidCallback and self.Validate) or self.BuildPreview
dlg = wx.wxProgressDialog("Import Wizard",
"Analyzing %s... Please wait." % file,
3,
parent,
wx.wxPD_APP_MODAL | wx.wxPD_AUTO_HIDE)
textQualifier = guessTextQualifier(data)
dlg.Update(1)
newdata = organizeIntoLines(data, textQualifier = textQualifier, limit = 100)
dlg.Update(2)
delimiter = guessDelimiter(newdata, textQualifier = textQualifier)
dlg.Update(3)
dlg.Destroy()
# -------------
msg = ("This screen lets you set the delimiters your data contains.\n"
"You can see how your data is affected in the preview below.")
message1 = wx.wxStaticText(self, -1, msg)
# -------------
delimiterBox = wx.wxBoxSizer(wx.wxHORIZONTAL)
delimStaticBox = wx.wxStaticBox(self, -1, "Delimiters")
delimStaticSizer = wx.wxStaticBoxSizer(delimStaticBox, wx.wxVERTICAL)
delimGridSizer = wx.wxFlexGridSizer(2, 3)
delims = {
'Tab': '\t',
'Semicolon': ';',
'Comma': ',',
'Space': ' ',
}
self.delimChecks = {}
for label, value in delims.items():
self.delimChecks[value] = wx.wxCheckBox(self, -1, label)
delimGridSizer.Add(self.delimChecks[value], 0, wx.wxALL, 3)
wx.EVT_CHECKBOX(self, self.delimChecks[value].GetId(), self.Validate)
otherSizer = wx.wxBoxSizer(wx.wxHORIZONTAL)
self.delimChecks['Other'] = wx.wxCheckBox(self, -1, 'Other:')
wx.EVT_CHECKBOX(self, self.delimChecks['Other'].GetId(), self.Validate)
self.otherDelim = wx.wxTextCtrl(self, -1, size = (20, -1))
wx.EVT_TEXT(self, self.otherDelim.GetId(), self.OnCustomDelim)
if self.delimChecks.has_key(delimiter):
self.delimChecks[delimiter].SetValue(wx.true)
elif delimiter is not None:
self.delimChecks['Other'].SetValue(wx.true)
self.otherDelim.SetValue(delimiter)
otherSizer.AddMany([
(self.delimChecks['Other'], 0, wx.wxALL, 3),
(self.otherDelim, 0, wx.wxALIGN_CENTER),
])
delimGridSizer.Add(otherSizer)
delimStaticSizer.Add(delimGridSizer, 1, wx.wxEXPAND)
delimOtherSizer = wx.wxBoxSizer(wx.wxVERTICAL)
self.consecutiveDelimsAs1 = wx.wxCheckBox(self, -1, "Treat consecutive delimiters as one")
self.consecutiveDelimsAs1.Enable(wx.false)
tqSizer = wx.wxBoxSizer(wx.wxHORIZONTAL)
self.textQualifierChoice = wx.wxChoice(self, -1, choices = ['"', "'", "{None}"])
wx.EVT_CHOICE(self, self.textQualifierChoice.GetId(), self.BuildPreview)
if textQualifier is not None:
self.textQualifierChoice.SetStringSelection(textQualifier)
else:
self.textQualifierChoice.SetStringSelection('{None}')
tqSizer.AddMany([
(wx.wxStaticText(self, -1, "Text qualifier:"), 0, wx.wxALIGN_RIGHT | wx.wxALIGN_CENTER_VERTICAL),
(self.textQualifierChoice, 0, wx.wxALL | wx.wxALIGN_LEFT | wx.wxALIGN_CENTER_VERTICAL, 5),
])
delimOtherSizer.AddMany([
(self.consecutiveDelimsAs1, 1, wx.wxEXPAND | wx.wxALL, 5),
(tqSizer, 1, wx.wxALL | wx.wxALIGN_CENTER, 5),
])
delimiterBox.AddMany([
(delimStaticSizer, 0, wx.wxALIGN_CENTER),
(delimOtherSizer, 0, wx.wxALIGN_CENTER),
])
delimStaticBox.Fit()
# -------------
self.displayRows = 6
previewSettingsBox = wx.wxBoxSizer(wx.wxHORIZONTAL)
self.hasHeaderRow = wx.wxCheckBox(self, -1, "First row is header")
wx.EVT_CHECKBOX(self, self.hasHeaderRow.GetId(), self.BuildPreview)
if wx.wxPlatform in ('__WX.WXGTK__', '__WX.WXMSW__'):
# wx.wxSpinCtrl causes seg fault under GTK when <enter> is hit in text - use wx.wxSpinButton instead
self.previewRowsText = wx.wxTextCtrl(self, -1, str(self.displayRows),
size = (30, -1), style = wx.wxTE_PROCESS_ENTER)
h = self.previewRowsText.GetSize().height
self.previewRows = wx.wxSpinButton(self, -1, size = (-1, h), style = wx.wxSP_VERTICAL)
self.previewRows.SetRange(self.displayRows, 100)
self.previewRows.SetValue(self.displayRows)
wx.EVT_SPIN(self, self.previewRows.GetId(), self.OnSpinPreviewRows)
wx.EVT_TEXT_ENTER(self, self.previewRowsText.GetId(), self.OnTextPreviewRows)
else:
self.previewRows = wx.wxSpinCtrl(self, -1, str(self.displayRows),
min = self.displayRows, max = 100, size = (50, -1))
wx.EVT_SPINCTRL(self, self.previewRows.GetId(), self.BuildPreview)
previewSettingsBox.AddMany([
(self.hasHeaderRow, 1, wx.wxALL | wx.wxEXPAND, 5),
(wx.wxStaticText(self, -1, "Preview"), 0, wx.wxWEST | wx.wxALIGN_RIGHT | wx.wxALIGN_CENTER_VERTICAL, 10),
])
if wx.wxPlatform in ('__WX.WXGTK__', '__WX.WXMSW__'):
previewSettingsBox.Add(self.previewRowsText, 0, wx.wxALIGN_CENTER | wx.wxALL, 3)
previewSettingsBox.AddMany([
(self.previewRows, 0, wx.wxALIGN_CENTER | wx.wxALL, 3),
(wx.wxStaticText(self, -1, "rows"), 0, wx.wxALIGN_RIGHT | wx.wxALIGN_CENTER_VERTICAL),
])
# -------------
if delimiter is not None:
previewData = importDSV(newdata[:self.displayRows],
textQualifier = textQualifier,
delimiter = delimiter,
errorHandler = padRow)
hasHeaders = guessHeaders(previewData)
self.hasHeaderRow.SetValue(hasHeaders)
cols = len(previewData[0])
else:
previewData = []
hasHeaders = 0
cols = 1
previewStaticBox = wx.wxStaticBox(self, -1, "Data Preview")
previewStaticSizer = wx.wxStaticBoxSizer(previewStaticBox, wx.wxVERTICAL)
self.preview = grid.wxGrid(self, -1)
self.preview.CreateGrid(self.displayRows, cols)
self.preview.SetDefaultRowSize(self.preview.GetCharHeight() + 4, wx.true)
self.preview.EnableEditing(wx.false)
self.preview.SetColLabelSize(0)
self.preview.SetRowLabelSize(0)
self.preview.SetMargins(1, 0)
self.initialized = wx.true
self.BuildPreview()
rowheight = self.preview.GetRowSize(0) + 2
self.preview.SetSize((-1, rowheight * self.displayRows))
previewStaticSizer.Add(self.preview, 0, wx.wxALL | wx.wxEXPAND, 5)
# -------------
mainSizer.AddMany([
(message1, 0, wx.wxALL, 5),
(delimiterBox, 0, wx.wxALL, 5),
(previewSettingsBox, 0, wx.wxALL, 5),
(previewStaticSizer, 0, wx.wxALL | wx.wxEXPAND, 5),
])
self.Layout()
self.Fit()
def OnSpinPreviewRows(self, event):
self.previewRowsText.SetValue(str(event.GetPosition()))
self.BuildPreview()
def OnTextPreviewRows(self, event):
try: v = int(self.previewRowsText.GetValue())
except: v = self.displayRows
v = max(self.displayRows, v)
v = min(v, 100)
self.previewRowsText.SetValue(str(v))
self.previewRows.SetValue(v)
self.BuildPreview()
def Validate(self, event = None):
hasDelimiter = reduce(lambda a, b: a + b, [cb.GetValue() for cb in self.delimChecks.values()])
if hasDelimiter == 1 and self.delimChecks['Other'].GetValue():
hasDelimiter = self.otherDelim.GetValue() != ""
self.BuildPreview()
self.isValidCallback(hasDelimiter)
def BuildPreview(self, event = None):
if not self.initialized:
return # got triggered before initialization was completed
if wx.wxPlatform != '__WX.WXGTK__':
wx.wxBeginBusyCursor() # causes a spurious spin event under GTK
wx.wxYield() # allow controls to update first, in case of slow preview
self.preview.BeginBatch()
self.preview.DeleteCols(0, self.preview.GetNumberCols())
self.preview.DeleteRows(0, self.preview.GetNumberRows())
self.preview.ClearGrid()
textQualifier = self.textQualifierChoice.GetStringSelection()
if textQualifier == '{None}': textQualifier = None
other = self.otherDelim.GetValue()
delimiter = map(lambda i, other = other: i[0] != 'Other' and i[0] or other,
filter(lambda i: i[1].GetValue(), self.delimChecks.items()))
delimiter = "".join(delimiter)
rows = self.previewRows.GetValue()
newdata = organizeIntoLines(self.data, textQualifier, limit = rows)
try:
previewData = importDSV(newdata[:rows],
textQualifier = textQualifier,
delimiter = delimiter,
errorHandler = padRow)
except InvalidDelimiter, e:
previewData = map(lambda i: [i], newdata[:rows])
rows = min(rows, len(previewData))
hasHeaders = self.hasHeaderRow.GetValue()
self.preview.AppendRows(rows - hasHeaders)
cols = max([len(row) for row in previewData])
self.preview.AppendCols(cols)
if hasHeaders:
self.preview.SetColLabelSize(self.preview.GetRowSize(0))
for col in range(cols):
try: self.preview.SetColLabelValue(col, str(previewData[0][col]))
except: self.preview.SetColLabelValue(col, "")
# self.preview.AutoSizeColumns(wx.true) # size columns to headers
else:
self.preview.SetColLabelSize(0)
for row in range(hasHeaders, rows):
for col in range(cols):
try: self.preview.SetCellValue(row - hasHeaders, col, str(previewData[row][col]))
except: pass
# if not hasHeaders:
self.preview.AutoSizeColumns(wx.true) # size columns to data
rowheight = self.preview.GetRowSize(0)
self.preview.SetRowSize(0, rowheight)
self.preview.EndBatch()
if wx.wxPlatform != '__WX.WXGTK__':
wx.wxEndBusyCursor()
self.delimiters = delimiter
self.textQualifier = textQualifier
self.hasHeaders = hasHeaders
def OnCustomDelim(self, event = None):
self.delimChecks['Other'].SetValue(len(self.otherDelim.GetValue()))
self.Validate()
def GetDelimiters(self):
return self.delimiters
def GetTextQualifier(self):
return self.textQualifier
def GetHasHeaders(self):
return self.hasHeaders
# ------------------------------------------------------------------------------
class ImportWizardDialog(wx.wxDialog):
"""
CLASS(SUPERCLASS):
ImportWizardDialog(wx.wxDialog)
DESCRIPTION:
A dialog allowing the user to preview and change the options for importing
a file.
PROTOTYPE:
ImportWizardDialog(parent, id, title, file,
pos = wx.wxDefaultPosition, size = wx.wxDefaultSize,
style = wx.wxDEFAULT_DIALOG_STYLE, name = 'ImportWizardDialog')
ARGUMENTS:
- parent: the parent window
- id: the id of this window
- title: the title of this dialog
- file: the file to import
METHODS:
- GetImportInfo()
returns a tuple (delimiters, text qualifiers, has headers)
- ImportData(errorHandler = skipRow)
returns (headers, data), headers may be None
errorHandler is a callback function that instructs the method on what
to do with irregular rows. The default skipRow function simply discards
the bad row (see importDSV() above).
"""
def __init__(self, parent, id, title, file,
pos = wx.wxDefaultPosition, size = wx.wxDefaultSize,
style = wx.wxDEFAULT_DIALOG_STYLE, name = "ImportWizardDialog"):
wx.wxDialog.__init__(self, parent, id, title, pos, size, style, name)
self.SetAutoLayout(wx.true)
self.file = file
f = open(file, 'r')
self.data = f.read()
f.close()
sizer = wx.wxBoxSizer(wx.wxVERTICAL)
self.delimPanel = ImportWizardPanel_Delimiters(self, -1, file, self.data, self.ValidState)
buttonBox = self.ButtonBox()
sizer.AddMany([
(self.delimPanel, 0, wx.wxALL, 5),
(buttonBox, 0, wx.wxSOUTH | wx.wxALIGN_CENTER_HORIZONTAL | wx.wxALIGN_TOP, 0),
])
self.SetSizer(sizer)
self.Layout()
sizer.Fit(self.delimPanel)
self.Fit()
self.Centre()
def ButtonBox(self):
panel = wx.wxPanel(self, -1)
panel.SetAutoLayout(wx.true)
sizer = wx.wxBoxSizer(wx.wxHORIZONTAL)
panel.SetSizer(sizer)
self.ok = wx.wxButton(panel, wx.wxID_OK, "Ok")
cancel = wx.wxButton(panel, wx.wxID_CANCEL, "Cancel")
sizer.AddMany([
(self.ok, 0, wx.wxALIGN_TOP | wx.wxEAST | wx.wxSOUTH, 10),
(cancel, 0, wx.wxALIGN_TOP | wx.wxWEST | wx.wxSOUTH, 10),
])
panel.Layout()
panel.Fit()
return panel
def GetImportInfo(self):
return (self.delimPanel.GetDelimiters(),
self.delimPanel.GetTextQualifier(),
self.delimPanel.GetHasHeaders())