-
-
Notifications
You must be signed in to change notification settings - Fork 18.4k
/
Copy path_openpyxl.py
594 lines (500 loc) · 17.9 KB
/
_openpyxl.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
from __future__ import annotations
import mmap
from typing import (
TYPE_CHECKING,
Any,
)
import numpy as np
from pandas._typing import (
FilePathOrBuffer,
Scalar,
StorageOptions,
)
from pandas.compat._optional import import_optional_dependency
from pandas.io.excel._base import (
BaseExcelReader,
ExcelWriter,
)
from pandas.io.excel._util import (
combine_kwargs,
validate_freeze_panes,
)
if TYPE_CHECKING:
from openpyxl.descriptors.serialisable import Serialisable
class OpenpyxlWriter(ExcelWriter):
engine = "openpyxl"
supported_extensions = (".xlsx", ".xlsm")
def __init__(
self,
path,
engine=None,
date_format=None,
datetime_format=None,
mode: str = "w",
storage_options: StorageOptions = None,
if_sheet_exists: str | None = None,
engine_kwargs: dict[str, Any] | None = None,
**kwargs,
):
# Use the openpyxl module as the Excel writer.
from openpyxl.workbook import Workbook
engine_kwargs = combine_kwargs(engine_kwargs, kwargs)
super().__init__(
path,
mode=mode,
storage_options=storage_options,
if_sheet_exists=if_sheet_exists,
engine_kwargs=engine_kwargs,
)
# ExcelWriter replaced "a" by "r+" to allow us to first read the excel file from
# the file and later write to it
if "r+" in self.mode: # Load from existing workbook
from openpyxl import load_workbook
self.book = load_workbook(self.handles.handle)
self.handles.handle.seek(0)
self.sheets = {name: self.book[name] for name in self.book.sheetnames}
else:
# Create workbook object with default optimized_write=True.
self.book = Workbook()
if self.book.worksheets:
self.book.remove(self.book.worksheets[0])
def save(self):
"""
Save workbook to disk.
"""
self.book.save(self.handles.handle)
if "r+" in self.mode and not isinstance(self.handles.handle, mmap.mmap):
# truncate file to the written content
self.handles.handle.truncate()
@classmethod
def _convert_to_style_kwargs(cls, style_dict: dict) -> dict[str, Serialisable]:
"""
Convert a style_dict to a set of kwargs suitable for initializing
or updating-on-copy an openpyxl v2 style object.
Parameters
----------
style_dict : dict
A dict with zero or more of the following keys (or their synonyms).
'font'
'fill'
'border' ('borders')
'alignment'
'number_format'
'protection'
Returns
-------
style_kwargs : dict
A dict with the same, normalized keys as ``style_dict`` but each
value has been replaced with a native openpyxl style object of the
appropriate class.
"""
_style_key_map = {"borders": "border"}
style_kwargs: dict[str, Serialisable] = {}
for k, v in style_dict.items():
if k in _style_key_map:
k = _style_key_map[k]
_conv_to_x = getattr(cls, f"_convert_to_{k}", lambda x: None)
new_v = _conv_to_x(v)
if new_v:
style_kwargs[k] = new_v
return style_kwargs
@classmethod
def _convert_to_color(cls, color_spec):
"""
Convert ``color_spec`` to an openpyxl v2 Color object.
Parameters
----------
color_spec : str, dict
A 32-bit ARGB hex string, or a dict with zero or more of the
following keys.
'rgb'
'indexed'
'auto'
'theme'
'tint'
'index'
'type'
Returns
-------
color : openpyxl.styles.Color
"""
from openpyxl.styles import Color
if isinstance(color_spec, str):
return Color(color_spec)
else:
return Color(**color_spec)
@classmethod
def _convert_to_font(cls, font_dict):
"""
Convert ``font_dict`` to an openpyxl v2 Font object.
Parameters
----------
font_dict : dict
A dict with zero or more of the following keys (or their synonyms).
'name'
'size' ('sz')
'bold' ('b')
'italic' ('i')
'underline' ('u')
'strikethrough' ('strike')
'color'
'vertAlign' ('vertalign')
'charset'
'scheme'
'family'
'outline'
'shadow'
'condense'
Returns
-------
font : openpyxl.styles.Font
"""
from openpyxl.styles import Font
_font_key_map = {
"sz": "size",
"b": "bold",
"i": "italic",
"u": "underline",
"strike": "strikethrough",
"vertalign": "vertAlign",
}
font_kwargs = {}
for k, v in font_dict.items():
if k in _font_key_map:
k = _font_key_map[k]
if k == "color":
v = cls._convert_to_color(v)
font_kwargs[k] = v
return Font(**font_kwargs)
@classmethod
def _convert_to_stop(cls, stop_seq):
"""
Convert ``stop_seq`` to a list of openpyxl v2 Color objects,
suitable for initializing the ``GradientFill`` ``stop`` parameter.
Parameters
----------
stop_seq : iterable
An iterable that yields objects suitable for consumption by
``_convert_to_color``.
Returns
-------
stop : list of openpyxl.styles.Color
"""
return map(cls._convert_to_color, stop_seq)
@classmethod
def _convert_to_fill(cls, fill_dict):
"""
Convert ``fill_dict`` to an openpyxl v2 Fill object.
Parameters
----------
fill_dict : dict
A dict with one or more of the following keys (or their synonyms),
'fill_type' ('patternType', 'patterntype')
'start_color' ('fgColor', 'fgcolor')
'end_color' ('bgColor', 'bgcolor')
or one or more of the following keys (or their synonyms).
'type' ('fill_type')
'degree'
'left'
'right'
'top'
'bottom'
'stop'
Returns
-------
fill : openpyxl.styles.Fill
"""
from openpyxl.styles import (
GradientFill,
PatternFill,
)
_pattern_fill_key_map = {
"patternType": "fill_type",
"patterntype": "fill_type",
"fgColor": "start_color",
"fgcolor": "start_color",
"bgColor": "end_color",
"bgcolor": "end_color",
}
_gradient_fill_key_map = {"fill_type": "type"}
pfill_kwargs = {}
gfill_kwargs = {}
for k, v in fill_dict.items():
pk = gk = None
if k in _pattern_fill_key_map:
pk = _pattern_fill_key_map[k]
if k in _gradient_fill_key_map:
gk = _gradient_fill_key_map[k]
if pk in ["start_color", "end_color"]:
v = cls._convert_to_color(v)
if gk == "stop":
v = cls._convert_to_stop(v)
if pk:
pfill_kwargs[pk] = v
elif gk:
gfill_kwargs[gk] = v
else:
pfill_kwargs[k] = v
gfill_kwargs[k] = v
try:
return PatternFill(**pfill_kwargs)
except TypeError:
return GradientFill(**gfill_kwargs)
@classmethod
def _convert_to_side(cls, side_spec):
"""
Convert ``side_spec`` to an openpyxl v2 Side object.
Parameters
----------
side_spec : str, dict
A string specifying the border style, or a dict with zero or more
of the following keys (or their synonyms).
'style' ('border_style')
'color'
Returns
-------
side : openpyxl.styles.Side
"""
from openpyxl.styles import Side
_side_key_map = {"border_style": "style"}
if isinstance(side_spec, str):
return Side(style=side_spec)
side_kwargs = {}
for k, v in side_spec.items():
if k in _side_key_map:
k = _side_key_map[k]
if k == "color":
v = cls._convert_to_color(v)
side_kwargs[k] = v
return Side(**side_kwargs)
@classmethod
def _convert_to_border(cls, border_dict):
"""
Convert ``border_dict`` to an openpyxl v2 Border object.
Parameters
----------
border_dict : dict
A dict with zero or more of the following keys (or their synonyms).
'left'
'right'
'top'
'bottom'
'diagonal'
'diagonal_direction'
'vertical'
'horizontal'
'diagonalUp' ('diagonalup')
'diagonalDown' ('diagonaldown')
'outline'
Returns
-------
border : openpyxl.styles.Border
"""
from openpyxl.styles import Border
_border_key_map = {"diagonalup": "diagonalUp", "diagonaldown": "diagonalDown"}
border_kwargs = {}
for k, v in border_dict.items():
if k in _border_key_map:
k = _border_key_map[k]
if k == "color":
v = cls._convert_to_color(v)
if k in ["left", "right", "top", "bottom", "diagonal"]:
v = cls._convert_to_side(v)
border_kwargs[k] = v
return Border(**border_kwargs)
@classmethod
def _convert_to_alignment(cls, alignment_dict):
"""
Convert ``alignment_dict`` to an openpyxl v2 Alignment object.
Parameters
----------
alignment_dict : dict
A dict with zero or more of the following keys (or their synonyms).
'horizontal'
'vertical'
'text_rotation'
'wrap_text'
'shrink_to_fit'
'indent'
Returns
-------
alignment : openpyxl.styles.Alignment
"""
from openpyxl.styles import Alignment
return Alignment(**alignment_dict)
@classmethod
def _convert_to_number_format(cls, number_format_dict):
"""
Convert ``number_format_dict`` to an openpyxl v2.1.0 number format
initializer.
Parameters
----------
number_format_dict : dict
A dict with zero or more of the following keys.
'format_code' : str
Returns
-------
number_format : str
"""
return number_format_dict["format_code"]
@classmethod
def _convert_to_protection(cls, protection_dict):
"""
Convert ``protection_dict`` to an openpyxl v2 Protection object.
Parameters
----------
protection_dict : dict
A dict with zero or more of the following keys.
'locked'
'hidden'
Returns
-------
"""
from openpyxl.styles import Protection
return Protection(**protection_dict)
def write_cells(
self, cells, sheet_name=None, startrow=0, startcol=0, freeze_panes=None
):
# Write the frame cells using openpyxl.
sheet_name = self._get_sheet_name(sheet_name)
_style_cache: dict[str, dict[str, Serialisable]] = {}
if sheet_name in self.sheets and self.if_sheet_exists != "new":
if "r+" in self.mode:
if self.if_sheet_exists == "replace":
old_wks = self.sheets[sheet_name]
target_index = self.book.index(old_wks)
del self.book[sheet_name]
wks = self.book.create_sheet(sheet_name, target_index)
self.sheets[sheet_name] = wks
elif self.if_sheet_exists == "error":
raise ValueError(
f"Sheet '{sheet_name}' already exists and "
f"if_sheet_exists is set to 'error'."
)
else:
raise ValueError(
f"'{self.if_sheet_exists}' is not valid for if_sheet_exists. "
"Valid options are 'error', 'new' and 'replace'."
)
else:
wks = self.sheets[sheet_name]
else:
wks = self.book.create_sheet()
wks.title = sheet_name
self.sheets[sheet_name] = wks
if validate_freeze_panes(freeze_panes):
wks.freeze_panes = wks.cell(
row=freeze_panes[0] + 1, column=freeze_panes[1] + 1
)
for cell in cells:
xcell = wks.cell(
row=startrow + cell.row + 1, column=startcol + cell.col + 1
)
xcell.value, fmt = self._value_with_fmt(cell.val)
if fmt:
xcell.number_format = fmt
style_kwargs: dict[str, Serialisable] | None = {}
if cell.style:
key = str(cell.style)
style_kwargs = _style_cache.get(key)
if style_kwargs is None:
style_kwargs = self._convert_to_style_kwargs(cell.style)
_style_cache[key] = style_kwargs
if style_kwargs:
for k, v in style_kwargs.items():
setattr(xcell, k, v)
if cell.mergestart is not None and cell.mergeend is not None:
wks.merge_cells(
start_row=startrow + cell.row + 1,
start_column=startcol + cell.col + 1,
end_column=startcol + cell.mergeend + 1,
end_row=startrow + cell.mergestart + 1,
)
# When cells are merged only the top-left cell is preserved
# The behaviour of the other cells in a merged range is
# undefined
if style_kwargs:
first_row = startrow + cell.row + 1
last_row = startrow + cell.mergestart + 1
first_col = startcol + cell.col + 1
last_col = startcol + cell.mergeend + 1
for row in range(first_row, last_row + 1):
for col in range(first_col, last_col + 1):
if row == first_row and col == first_col:
# Ignore first cell. It is already handled.
continue
xcell = wks.cell(column=col, row=row)
for k, v in style_kwargs.items():
setattr(xcell, k, v)
class OpenpyxlReader(BaseExcelReader):
def __init__(
self,
filepath_or_buffer: FilePathOrBuffer,
storage_options: StorageOptions = None,
) -> None:
"""
Reader using openpyxl engine.
Parameters
----------
filepath_or_buffer : str, path object or Workbook
Object to be parsed.
storage_options : dict, optional
passed to fsspec for appropriate URLs (see ``_get_filepath_or_buffer``)
"""
import_optional_dependency("openpyxl")
super().__init__(filepath_or_buffer, storage_options=storage_options)
@property
def _workbook_class(self):
from openpyxl import Workbook
return Workbook
def load_workbook(self, filepath_or_buffer: FilePathOrBuffer):
from openpyxl import load_workbook
return load_workbook(
filepath_or_buffer, read_only=True, data_only=True, keep_links=False
)
@property
def sheet_names(self) -> list[str]:
return [sheet.title for sheet in self.book.worksheets]
def get_sheet_by_name(self, name: str):
self.raise_if_bad_sheet_by_name(name)
return self.book[name]
def get_sheet_by_index(self, index: int):
self.raise_if_bad_sheet_by_index(index)
return self.book.worksheets[index]
def _convert_cell(self, cell, convert_float: bool) -> Scalar:
from openpyxl.cell.cell import (
TYPE_ERROR,
TYPE_NUMERIC,
)
if cell.value is None:
return "" # compat with xlrd
elif cell.data_type == TYPE_ERROR:
return np.nan
elif not convert_float and cell.data_type == TYPE_NUMERIC:
return float(cell.value)
return cell.value
def get_sheet_data(self, sheet, convert_float: bool) -> list[list[Scalar]]:
if self.book.read_only:
sheet.reset_dimensions()
data: list[list[Scalar]] = []
last_row_with_data = -1
for row_number, row in enumerate(sheet.rows):
converted_row = [self._convert_cell(cell, convert_float) for cell in row]
while converted_row and converted_row[-1] == "":
# trim trailing empty elements
converted_row.pop()
if converted_row:
last_row_with_data = row_number
data.append(converted_row)
# Trim trailing empty rows
data = data[: last_row_with_data + 1]
if len(data) > 0:
# extend rows to max width
max_width = max(len(data_row) for data_row in data)
if min(len(data_row) for data_row in data) < max_width:
empty_cell: list[Scalar] = [""]
data = [
data_row + (max_width - len(data_row)) * empty_cell
for data_row in data
]
return data