forked from astanin/python-tabulate
-
Notifications
You must be signed in to change notification settings - Fork 0
/
tabulate.py
executable file
·1790 lines (1526 loc) · 56.5 KB
/
tabulate.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
# -*- coding: utf-8 -*-
"""Pretty-print tabular data."""
from __future__ import print_function
from __future__ import unicode_literals
from collections import namedtuple
from platform import python_version_tuple
import re
import math
if python_version_tuple() >= ("3", "3", "0"):
from collections.abc import Iterable
else:
from collections import Iterable
if python_version_tuple()[0] < "3":
from itertools import izip_longest
from functools import partial
_none_type = type(None)
_bool_type = bool
_int_type = int
_long_type = long # noqa
_float_type = float
_text_type = unicode # noqa
_binary_type = str
def _is_file(f):
return hasattr(f, "read")
else:
from itertools import zip_longest as izip_longest
from functools import reduce, partial
_none_type = type(None)
_bool_type = bool
_int_type = int
_long_type = int
_float_type = float
_text_type = str
_binary_type = bytes
basestring = str
import io
def _is_file(f):
return isinstance(f, io.IOBase)
try:
import wcwidth # optional wide-character (CJK) support
except ImportError:
wcwidth = None
try:
from html import escape as htmlescape
except ImportError:
from cgi import escape as htmlescape
__all__ = ["tabulate", "tabulate_formats", "simple_separated_format"]
__version__ = "0.8.8"
# minimum extra space in headers
MIN_PADDING = 2
# Whether or not to preserve leading/trailing whitespace in data.
PRESERVE_WHITESPACE = False
_DEFAULT_FLOATFMT = "g"
_DEFAULT_MISSINGVAL = ""
# if True, enable wide-character (CJK) support
WIDE_CHARS_MODE = wcwidth is not None
Line = namedtuple("Line", ["begin", "hline", "sep", "end"])
DataRow = namedtuple("DataRow", ["begin", "sep", "end"])
# A table structure is suppposed to be:
#
# --- lineabove ---------
# headerrow
# --- linebelowheader ---
# datarow
# --- linebewteenrows ---
# ... (more datarows) ...
# --- linebewteenrows ---
# last datarow
# --- linebelow ---------
#
# TableFormat's line* elements can be
#
# - either None, if the element is not used,
# - or a Line tuple,
# - or a function: [col_widths], [col_alignments] -> string.
#
# TableFormat's *row elements can be
#
# - either None, if the element is not used,
# - or a DataRow tuple,
# - or a function: [cell_values], [col_widths], [col_alignments] -> string.
#
# padding (an integer) is the amount of white space around data values.
#
# with_header_hide:
#
# - either None, to display all table elements unconditionally,
# - or a list of elements not to be displayed if the table has column headers.
#
TableFormat = namedtuple(
"TableFormat",
[
"lineabove",
"linebelowheader",
"linebetweenrows",
"linebelow",
"headerrow",
"datarow",
"padding",
"with_header_hide",
],
)
def _pipe_segment_with_colons(align, colwidth):
"""Return a segment of a horizontal line with optional colons which
indicate column's alignment (as in `pipe` output format)."""
w = colwidth
if align in ["right", "decimal"]:
return ("-" * (w - 1)) + ":"
elif align == "center":
return ":" + ("-" * (w - 2)) + ":"
elif align == "left":
return ":" + ("-" * (w - 1))
else:
return "-" * w
def _pipe_line_with_colons(colwidths, colaligns):
"""Return a horizontal line with optional colons to indicate column's
alignment (as in `pipe` output format)."""
if not colaligns: # e.g. printing an empty data frame (github issue #15)
colaligns = [""] * len(colwidths)
segments = [_pipe_segment_with_colons(a, w) for a, w in zip(colaligns, colwidths)]
return "|" + "|".join(segments) + "|"
def _mediawiki_row_with_attrs(separator, cell_values, colwidths, colaligns):
alignment = {
"left": "",
"right": 'align="right"| ',
"center": 'align="center"| ',
"decimal": 'align="right"| ',
}
# hard-coded padding _around_ align attribute and value together
# rather than padding parameter which affects only the value
values_with_attrs = [
" " + alignment.get(a, "") + c + " " for c, a in zip(cell_values, colaligns)
]
colsep = separator * 2
return (separator + colsep.join(values_with_attrs)).rstrip()
def _textile_row_with_attrs(cell_values, colwidths, colaligns):
cell_values[0] += " "
alignment = {"left": "<.", "right": ">.", "center": "=.", "decimal": ">."}
values = (alignment.get(a, "") + v for a, v in zip(colaligns, cell_values))
return "|" + "|".join(values) + "|"
def _html_begin_table_without_header(colwidths_ignore, colaligns_ignore):
# this table header will be suppressed if there is a header row
return "<table>\n<tbody>"
def _html_row_with_attrs(celltag, unsafe, cell_values, colwidths, colaligns):
alignment = {
"left": "",
"right": ' style="text-align: right;"',
"center": ' style="text-align: center;"',
"decimal": ' style="text-align: right;"',
}
if unsafe:
values_with_attrs = [
"<{0}{1}>{2}</{0}>".format(celltag, alignment.get(a, ""), c)
for c, a in zip(cell_values, colaligns)
]
else:
values_with_attrs = [
"<{0}{1}>{2}</{0}>".format(celltag, alignment.get(a, ""), htmlescape(c))
for c, a in zip(cell_values, colaligns)
]
rowhtml = "<tr>{}</tr>".format("".join(values_with_attrs).rstrip())
if celltag == "th": # it's a header row, create a new table header
rowhtml = "<table>\n<thead>\n{}\n</thead>\n<tbody>".format(rowhtml)
return rowhtml
def _moin_row_with_attrs(celltag, cell_values, colwidths, colaligns, header=""):
alignment = {
"left": "",
"right": '<style="text-align: right;">',
"center": '<style="text-align: center;">',
"decimal": '<style="text-align: right;">',
}
values_with_attrs = [
"{0}{1} {2} ".format(celltag, alignment.get(a, ""), header + c + header)
for c, a in zip(cell_values, colaligns)
]
return "".join(values_with_attrs) + "||"
def _latex_line_begin_tabular(colwidths, colaligns, booktabs=False):
alignment = {"left": "l", "right": "r", "center": "c", "decimal": "r"}
tabular_columns_fmt = "".join([alignment.get(a, "l") for a in colaligns])
return "\n".join(
[
"\\begin{tabular}{" + tabular_columns_fmt + "}",
"\\toprule" if booktabs else "\\hline",
]
)
LATEX_ESCAPE_RULES = {
r"&": r"\&",
r"%": r"\%",
r"$": r"\$",
r"#": r"\#",
r"_": r"\_",
r"^": r"\^{}",
r"{": r"\{",
r"}": r"\}",
r"~": r"\textasciitilde{}",
"\\": r"\textbackslash{}",
r"<": r"\ensuremath{<}",
r">": r"\ensuremath{>}",
}
def _latex_row(cell_values, colwidths, colaligns, escrules=LATEX_ESCAPE_RULES):
def escape_char(c):
return escrules.get(c, c)
escaped_values = ["".join(map(escape_char, cell)) for cell in cell_values]
rowfmt = DataRow("", "&", "\\\\")
return _build_simple_row(escaped_values, rowfmt)
def _rst_escape_first_column(rows, headers):
def escape_empty(val):
if isinstance(val, (_text_type, _binary_type)) and not val.strip():
return ".."
else:
return val
new_headers = list(headers)
new_rows = []
if headers:
new_headers[0] = escape_empty(headers[0])
for row in rows:
new_row = list(row)
if new_row:
new_row[0] = escape_empty(row[0])
new_rows.append(new_row)
return new_rows, new_headers
_table_formats = {
"simple": TableFormat(
lineabove=Line("", "-", " ", ""),
linebelowheader=Line("", "-", " ", ""),
linebetweenrows=None,
linebelow=Line("", "-", " ", ""),
headerrow=DataRow("", " ", ""),
datarow=DataRow("", " ", ""),
padding=0,
with_header_hide=["lineabove", "linebelow"],
),
"plain": TableFormat(
lineabove=None,
linebelowheader=None,
linebetweenrows=None,
linebelow=None,
headerrow=DataRow("", " ", ""),
datarow=DataRow("", " ", ""),
padding=0,
with_header_hide=None,
),
"grid": TableFormat(
lineabove=Line("+", "-", "+", "+"),
linebelowheader=Line("+", "=", "+", "+"),
linebetweenrows=Line("+", "-", "+", "+"),
linebelow=Line("+", "-", "+", "+"),
headerrow=DataRow("|", "|", "|"),
datarow=DataRow("|", "|", "|"),
padding=1,
with_header_hide=None,
),
"fancy_grid": TableFormat(
lineabove=Line("╒", "═", "╤", "╕"),
linebelowheader=Line("╞", "═", "╪", "╡"),
linebetweenrows=Line("├", "─", "┼", "┤"),
linebelow=Line("╘", "═", "╧", "╛"),
headerrow=DataRow("│", "│", "│"),
datarow=DataRow("│", "│", "│"),
padding=1,
with_header_hide=None,
),
"github": TableFormat(
lineabove=Line("|", "-", "|", "|"),
linebelowheader=Line("|", "-", "|", "|"),
linebetweenrows=None,
linebelow=None,
headerrow=DataRow("|", "|", "|"),
datarow=DataRow("|", "|", "|"),
padding=1,
with_header_hide=["lineabove"],
),
"pipe": TableFormat(
lineabove=_pipe_line_with_colons,
linebelowheader=_pipe_line_with_colons,
linebetweenrows=None,
linebelow=None,
headerrow=DataRow("|", "|", "|"),
datarow=DataRow("|", "|", "|"),
padding=1,
with_header_hide=["lineabove"],
),
"orgtbl": TableFormat(
lineabove=None,
linebelowheader=Line("|", "-", "+", "|"),
linebetweenrows=None,
linebelow=None,
headerrow=DataRow("|", "|", "|"),
datarow=DataRow("|", "|", "|"),
padding=1,
with_header_hide=None,
),
"jira": TableFormat(
lineabove=None,
linebelowheader=None,
linebetweenrows=None,
linebelow=None,
headerrow=DataRow("||", "||", "||"),
datarow=DataRow("|", "|", "|"),
padding=1,
with_header_hide=None,
),
"presto": TableFormat(
lineabove=None,
linebelowheader=Line("", "-", "+", ""),
linebetweenrows=None,
linebelow=None,
headerrow=DataRow("", "|", ""),
datarow=DataRow("", "|", ""),
padding=1,
with_header_hide=None,
),
"pretty": TableFormat(
lineabove=Line("+", "-", "+", "+"),
linebelowheader=Line("+", "-", "+", "+"),
linebetweenrows=None,
linebelow=Line("+", "-", "+", "+"),
headerrow=DataRow("|", "|", "|"),
datarow=DataRow("|", "|", "|"),
padding=1,
with_header_hide=None,
),
"psql": TableFormat(
lineabove=Line("+", "-", "+", "+"),
linebelowheader=Line("|", "-", "+", "|"),
linebetweenrows=None,
linebelow=Line("+", "-", "+", "+"),
headerrow=DataRow("|", "|", "|"),
datarow=DataRow("|", "|", "|"),
padding=1,
with_header_hide=None,
),
"rst": TableFormat(
lineabove=Line("", "=", " ", ""),
linebelowheader=Line("", "=", " ", ""),
linebetweenrows=None,
linebelow=Line("", "=", " ", ""),
headerrow=DataRow("", " ", ""),
datarow=DataRow("", " ", ""),
padding=0,
with_header_hide=None,
),
"mediawiki": TableFormat(
lineabove=Line(
'{| class="wikitable" style="text-align: left;"',
"",
"",
"\n|+ <!-- caption -->\n|-",
),
linebelowheader=Line("|-", "", "", ""),
linebetweenrows=Line("|-", "", "", ""),
linebelow=Line("|}", "", "", ""),
headerrow=partial(_mediawiki_row_with_attrs, "!"),
datarow=partial(_mediawiki_row_with_attrs, "|"),
padding=0,
with_header_hide=None,
),
"moinmoin": TableFormat(
lineabove=None,
linebelowheader=None,
linebetweenrows=None,
linebelow=None,
headerrow=partial(_moin_row_with_attrs, "||", header="'''"),
datarow=partial(_moin_row_with_attrs, "||"),
padding=1,
with_header_hide=None,
),
"youtrack": TableFormat(
lineabove=None,
linebelowheader=None,
linebetweenrows=None,
linebelow=None,
headerrow=DataRow("|| ", " || ", " || "),
datarow=DataRow("| ", " | ", " |"),
padding=1,
with_header_hide=None,
),
"html": TableFormat(
lineabove=_html_begin_table_without_header,
linebelowheader="",
linebetweenrows=None,
linebelow=Line("</tbody>\n</table>", "", "", ""),
headerrow=partial(_html_row_with_attrs, "th", False),
datarow=partial(_html_row_with_attrs, "td", False),
padding=0,
with_header_hide=["lineabove"],
),
"unsafehtml": TableFormat(
lineabove=_html_begin_table_without_header,
linebelowheader="",
linebetweenrows=None,
linebelow=Line("</tbody>\n</table>", "", "", ""),
headerrow=partial(_html_row_with_attrs, "th", True),
datarow=partial(_html_row_with_attrs, "td", True),
padding=0,
with_header_hide=["lineabove"],
),
"latex": TableFormat(
lineabove=_latex_line_begin_tabular,
linebelowheader=Line("\\hline", "", "", ""),
linebetweenrows=None,
linebelow=Line("\\hline\n\\end{tabular}", "", "", ""),
headerrow=_latex_row,
datarow=_latex_row,
padding=1,
with_header_hide=None,
),
"latex_raw": TableFormat(
lineabove=_latex_line_begin_tabular,
linebelowheader=Line("\\hline", "", "", ""),
linebetweenrows=None,
linebelow=Line("\\hline\n\\end{tabular}", "", "", ""),
headerrow=partial(_latex_row, escrules={}),
datarow=partial(_latex_row, escrules={}),
padding=1,
with_header_hide=None,
),
"latex_booktabs": TableFormat(
lineabove=partial(_latex_line_begin_tabular, booktabs=True),
linebelowheader=Line("\\midrule", "", "", ""),
linebetweenrows=None,
linebelow=Line("\\bottomrule\n\\end{tabular}", "", "", ""),
headerrow=_latex_row,
datarow=_latex_row,
padding=1,
with_header_hide=None,
),
"tsv": TableFormat(
lineabove=None,
linebelowheader=None,
linebetweenrows=None,
linebelow=None,
headerrow=DataRow("", "\t", ""),
datarow=DataRow("", "\t", ""),
padding=0,
with_header_hide=None,
),
"textile": TableFormat(
lineabove=None,
linebelowheader=None,
linebetweenrows=None,
linebelow=None,
headerrow=DataRow("|_. ", "|_.", "|"),
datarow=_textile_row_with_attrs,
padding=1,
with_header_hide=None,
),
}
tabulate_formats = list(sorted(_table_formats.keys()))
# The table formats for which multiline cells will be folded into subsequent
# table rows. The key is the original format specified at the API. The value is
# the format that will be used to represent the original format.
multiline_formats = {
"plain": "plain",
"simple": "simple",
"grid": "grid",
"fancy_grid": "fancy_grid",
"pipe": "pipe",
"orgtbl": "orgtbl",
"jira": "jira",
"presto": "presto",
"pretty": "pretty",
"psql": "psql",
"rst": "rst",
}
# TODO: Add multiline support for the remaining table formats:
# - mediawiki: Replace \n with <br>
# - moinmoin: TBD
# - youtrack: TBD
# - html: Replace \n with <br>
# - latex*: Use "makecell" package: In header, replace X\nY with
# \thead{X\\Y} and in data row, replace X\nY with \makecell{X\\Y}
# - tsv: TBD
# - textile: Replace \n with <br/> (must be well-formed XML)
_multiline_codes = re.compile(r"\r|\n|\r\n")
_multiline_codes_bytes = re.compile(b"\r|\n|\r\n")
_invisible_codes = re.compile(
r"\x1b\[\d+[;\d]*m|\x1b\[\d*\;\d*\;\d*m"
) # ANSI color codes
_invisible_codes_bytes = re.compile(
b"\x1b\\[\\d+\\[;\\d]*m|\x1b\\[\\d*;\\d*;\\d*m"
) # ANSI color codes
def simple_separated_format(separator):
"""Construct a simple TableFormat with columns separated by a separator.
>>> tsv = simple_separated_format("\\t") ; \
tabulate([["foo", 1], ["spam", 23]], tablefmt=tsv) == 'foo \\t 1\\nspam\\t23'
True
"""
return TableFormat(
None,
None,
None,
None,
headerrow=DataRow("", separator, ""),
datarow=DataRow("", separator, ""),
padding=0,
with_header_hide=None,
)
def _isconvertible(conv, string):
try:
conv(string)
return True
except (ValueError, TypeError):
return False
def _isnumber(string):
"""
>>> _isnumber("123.45")
True
>>> _isnumber("123")
True
>>> _isnumber("spam")
False
>>> _isnumber("123e45678")
False
>>> _isnumber("inf")
True
"""
if not _isconvertible(float, string):
return False
elif isinstance(string, (_text_type, _binary_type)) and (
math.isinf(float(string)) or math.isnan(float(string))
):
return string.lower() in ["inf", "-inf", "nan"]
return True
def _isint(string, inttype=int):
"""
>>> _isint("123")
True
>>> _isint("123.45")
False
"""
return (
type(string) is inttype
or (isinstance(string, _binary_type) or isinstance(string, _text_type))
and _isconvertible(inttype, string)
)
def _isbool(string):
"""
>>> _isbool(True)
True
>>> _isbool("False")
True
>>> _isbool(1)
False
"""
return type(string) is _bool_type or (
isinstance(string, (_binary_type, _text_type)) and string in ("True", "False")
)
def _type(string, has_invisible=True, numparse=True):
"""The least generic type (type(None), int, float, str, unicode).
>>> _type(None) is type(None)
True
>>> _type("foo") is type("")
True
>>> _type("1") is type(1)
True
>>> _type('\x1b[31m42\x1b[0m') is type(42)
True
>>> _type('\x1b[31m42\x1b[0m') is type(42)
True
"""
if has_invisible and (
isinstance(string, _text_type) or isinstance(string, _binary_type)
):
string = _strip_invisible(string)
if string is None:
return _none_type
elif hasattr(string, "isoformat"): # datetime.datetime, date, and time
return _text_type
elif _isbool(string):
return _bool_type
elif _isint(string) and numparse:
return int
elif _isint(string, _long_type) and numparse:
return int
elif _isnumber(string) and numparse:
return float
elif isinstance(string, _binary_type):
return _binary_type
else:
return _text_type
def _afterpoint(string):
"""Symbols after a decimal point, -1 if the string lacks the decimal point.
>>> _afterpoint("123.45")
2
>>> _afterpoint("1001")
-1
>>> _afterpoint("eggs")
-1
>>> _afterpoint("123e45")
2
"""
if _isnumber(string):
if _isint(string):
return -1
else:
pos = string.rfind(".")
pos = string.lower().rfind("e") if pos < 0 else pos
if pos >= 0:
return len(string) - pos - 1
else:
return -1 # no point
else:
return -1 # not a number
def _padleft(width, s):
"""Flush right.
>>> _padleft(6, '\u044f\u0439\u0446\u0430') == ' \u044f\u0439\u0446\u0430'
True
"""
fmt = "{0:>%ds}" % width
return fmt.format(s)
def _padright(width, s):
"""Flush left.
>>> _padright(6, '\u044f\u0439\u0446\u0430') == '\u044f\u0439\u0446\u0430 '
True
"""
fmt = "{0:<%ds}" % width
return fmt.format(s)
def _padboth(width, s):
"""Center string.
>>> _padboth(6, '\u044f\u0439\u0446\u0430') == ' \u044f\u0439\u0446\u0430 '
True
"""
fmt = "{0:^%ds}" % width
return fmt.format(s)
def _padnone(ignore_width, s):
return s
def _strip_invisible(s):
"Remove invisible ANSI color codes."
if isinstance(s, _text_type):
return re.sub(_invisible_codes, "", s)
else: # a bytestring
return re.sub(_invisible_codes_bytes, "", s)
def _visible_width(s):
"""Visible width of a printed string. ANSI color codes are removed.
>>> _visible_width('\x1b[31mhello\x1b[0m'), _visible_width("world")
(5, 5)
"""
# optional wide-character support
if wcwidth is not None and WIDE_CHARS_MODE:
len_fn = wcwidth.wcswidth
else:
len_fn = len
if isinstance(s, _text_type) or isinstance(s, _binary_type):
return len_fn(_strip_invisible(s))
else:
return len_fn(_text_type(s))
def _is_multiline(s):
if isinstance(s, _text_type):
return bool(re.search(_multiline_codes, s))
else: # a bytestring
return bool(re.search(_multiline_codes_bytes, s))
def _multiline_width(multiline_s, line_width_fn=len):
"""Visible width of a potentially multiline content."""
return max(map(line_width_fn, re.split("[\r\n]", multiline_s)))
def _choose_width_fn(has_invisible, enable_widechars, is_multiline):
"""Return a function to calculate visible cell width."""
if has_invisible:
line_width_fn = _visible_width
elif enable_widechars: # optional wide-character support if available
line_width_fn = wcwidth.wcswidth
else:
line_width_fn = len
if is_multiline:
width_fn = lambda s: _multiline_width(s, line_width_fn) # noqa
else:
width_fn = line_width_fn
return width_fn
def _align_column_choose_padfn(strings, alignment, has_invisible):
if alignment == "right":
if not PRESERVE_WHITESPACE:
strings = [s.strip() for s in strings]
padfn = _padleft
elif alignment == "center":
if not PRESERVE_WHITESPACE:
strings = [s.strip() for s in strings]
padfn = _padboth
elif alignment == "decimal":
if has_invisible:
decimals = [_afterpoint(_strip_invisible(s)) for s in strings]
else:
decimals = [_afterpoint(s) for s in strings]
maxdecimals = max(decimals)
strings = [s + (maxdecimals - decs) * " " for s, decs in zip(strings, decimals)]
padfn = _padleft
elif not alignment:
padfn = _padnone
else:
if not PRESERVE_WHITESPACE:
strings = [s.strip() for s in strings]
padfn = _padright
return strings, padfn
def _align_column(
strings,
alignment,
minwidth=0,
has_invisible=True,
enable_widechars=False,
is_multiline=False,
):
"""[string] -> [padded_string]"""
strings, padfn = _align_column_choose_padfn(strings, alignment, has_invisible)
width_fn = _choose_width_fn(has_invisible, enable_widechars, is_multiline)
s_widths = list(map(width_fn, strings))
maxwidth = max(max(s_widths), minwidth)
# TODO: refactor column alignment in single-line and multiline modes
if is_multiline:
if not enable_widechars and not has_invisible:
padded_strings = [
"\n".join([padfn(maxwidth, s) for s in ms.splitlines()])
for ms in strings
]
else:
# enable wide-character width corrections
s_lens = [max((len(s) for s in re.split("[\r\n]", ms))) for ms in strings]
visible_widths = [maxwidth - (w - l) for w, l in zip(s_widths, s_lens)]
# wcswidth and _visible_width don't count invisible characters;
# padfn doesn't need to apply another correction
padded_strings = [
"\n".join([padfn(w, s) for s in (ms.splitlines() or ms)])
for ms, w in zip(strings, visible_widths)
]
else: # single-line cell values
if not enable_widechars and not has_invisible:
padded_strings = [padfn(maxwidth, s) for s in strings]
else:
# enable wide-character width corrections
s_lens = list(map(len, strings))
visible_widths = [maxwidth - (w - l) for w, l in zip(s_widths, s_lens)]
# wcswidth and _visible_width don't count invisible characters;
# padfn doesn't need to apply another correction
padded_strings = [padfn(w, s) for s, w in zip(strings, visible_widths)]
return padded_strings
def _more_generic(type1, type2):
types = {
_none_type: 0,
_bool_type: 1,
int: 2,
float: 3,
_binary_type: 4,
_text_type: 5,
}
invtypes = {
5: _text_type,
4: _binary_type,
3: float,
2: int,
1: _bool_type,
0: _none_type,
}
moregeneric = max(types.get(type1, 5), types.get(type2, 5))
return invtypes[moregeneric]
def _column_type(strings, has_invisible=True, numparse=True):
"""The least generic type all column values are convertible to.
>>> _column_type([True, False]) is _bool_type
True
>>> _column_type(["1", "2"]) is _int_type
True
>>> _column_type(["1", "2.3"]) is _float_type
True
>>> _column_type(["1", "2.3", "four"]) is _text_type
True
>>> _column_type(["four", '\u043f\u044f\u0442\u044c']) is _text_type
True
>>> _column_type([None, "brux"]) is _text_type
True
>>> _column_type([1, 2, None]) is _int_type
True
>>> import datetime as dt
>>> _column_type([dt.datetime(1991,2,19), dt.time(17,35)]) is _text_type
True
"""
types = [_type(s, has_invisible, numparse) for s in strings]
return reduce(_more_generic, types, _bool_type)
def _format(val, valtype, floatfmt, missingval="", has_invisible=True):
"""Format a value accoding to its type.
Unicode is supported:
>>> hrow = ['\u0431\u0443\u043a\u0432\u0430', '\u0446\u0438\u0444\u0440\u0430'] ; \
tbl = [['\u0430\u0437', 2], ['\u0431\u0443\u043a\u0438', 4]] ; \
good_result = '\\u0431\\u0443\\u043a\\u0432\\u0430 \\u0446\\u0438\\u0444\\u0440\\u0430\\n------- -------\\n\\u0430\\u0437 2\\n\\u0431\\u0443\\u043a\\u0438 4' ; \
tabulate(tbl, headers=hrow) == good_result
True
""" # noqa
if val is None:
return missingval
if valtype in [int, _text_type]:
return "{0}".format(val)
elif valtype is _binary_type:
try:
return _text_type(val, "ascii")
except TypeError:
return _text_type(val)
elif valtype is float:
is_a_colored_number = has_invisible and isinstance(
val, (_text_type, _binary_type)
)
if is_a_colored_number:
raw_val = _strip_invisible(val)
formatted_val = format(float(raw_val), floatfmt)
return val.replace(raw_val, formatted_val)
else:
return format(float(val), floatfmt)
else:
return "{0}".format(val)
def _align_header(
header, alignment, width, visible_width, is_multiline=False, width_fn=None
):
"Pad string header to width chars given known visible_width of the header."
if is_multiline:
header_lines = re.split(_multiline_codes, header)
padded_lines = [
_align_header(h, alignment, width, width_fn(h)) for h in header_lines
]
return "\n".join(padded_lines)
# else: not multiline
ninvisible = len(header) - visible_width
width += ninvisible
if alignment == "left":
return _padright(width, header)
elif alignment == "center":
return _padboth(width, header)
elif not alignment:
return "{0}".format(header)
else:
return _padleft(width, header)
def _prepend_row_index(rows, index):
"""Add a left-most index column."""
if index is None or index is False:
return rows
if len(index) != len(rows):
print("index=", index)
print("rows=", rows)
raise ValueError("index must be as long as the number of data rows")
rows = [[v] + list(row) for v, row in zip(index, rows)]
return rows
def _bool(val):
"A wrapper around standard bool() which doesn't throw on NumPy arrays"
try:
return bool(val)
except ValueError: # val is likely to be a numpy array with many elements
return False
def _normalize_tabular_data(tabular_data, headers, showindex="default"):
"""Transform a supported data type to a list of lists, and a list of headers.
Supported tabular data types:
* list-of-lists or another iterable of iterables
* list of named tuples (usually used with headers="keys")
* list of dicts (usually used with headers="keys")
* list of OrderedDicts (usually used with headers="keys")
* 2D NumPy arrays
* NumPy record arrays (usually used with headers="keys")
* dict of iterables (usually used with headers="keys")
* pandas.DataFrame (usually used with headers="keys")
The first row can be used as headers if headers="firstrow",
column indices can be used as headers if headers="keys".
If showindex="default", show row indices of the pandas.DataFrame.
If showindex="always", show row indices for all types of data.