/
importXLSX.py
451 lines (382 loc) · 12.6 KB
/
importXLSX.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
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# importXLSX.py
#
# This library imports an Excel-XLSX-file into FreeCAD.
#
# Copyright (C) 2016 Ulrich Brammer <ulrich1a@users.sourceforge.net>
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Lesser General Public
# License as published by the Free Software Foundation; either
# version 2.1 of the License, or (at your option) any later version.
#
# This library is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# Lesser General Public License for more details.
#
# You should have received a copy of the GNU Lesser General Public
# License along with this library; if not, write to the Free Software
# Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston,
# MA 02110-1301 USA
from __future__ import print_function
__title__="FreeCAD Spreadsheet Workbench - XLSX importer"
__author__ = "Ulrich Brammer <ulrich1a@users.sourceforge.net>"
__url__ = ["http://www.freecadweb.org"]
'''
This library imports an Excel-XLSX-file into FreeCAD.
It uses a minimal parser, in order to translate the IF-function into
the different FreeCAD version.
The other function-names are translated by search and replace.
Version 1.0:
- Imports tables defined inside Excel-document
- Set alias definitions
- Translate formulas known by FreeCAD. (see funcDic + IF)
- set cross table references
- strings are imported
- references to cells with strings are working
known issues:
- units are not imported
- string support is minimal, as it is so in FreeCAD
'''
import zipfile
import xml.dom.minidom
import FreeCAD as App
try: import FreeCADGui
except ValueError: gui = False
else: gui = True
if open.__module__ == '__builtin__':
pythonopen = open
funcDic = {
'ABS(':'abs(',
'ACOS(':'acos(',
'ASIN(':'asin(',
'ATAN(':'atan(',
'ATAN2(':'atan2(',
'COS(':'cos(',
'COSH(':'cosh(',
'EXP(':'exp(',
'LOG(':'log(',
'LOG10(':'log10(',
'MOD(':'mod(',
'POWER(':'pow(',
'SIN(':'sin(',
'SINH(':'sinh(',
'SQRT(':'sqrt(',
'TAN(':'tan(',
'TANH(':'tanh(',
'AVERAGE(':'average(',
'COUNT(':'count(',
'MAX(':'max(',
'MIN(':'min(',
'STDEVA(':'stddev(',
'SUM(':'sum(',
'PI()':'pi'
}
# The treeToken structure is used in the tokenizer functions isKey and
# getNextToken.
# treeToken defines a search tree for tokens with length of 1 to 3 characters
treeToken = {
'(':None,
'I':'branchI',
'=':None,
'<':'branchLower',
'>':'branchHigher',
')':None,
# '"':None,
# ';':None,
' ':None,
',':None,
'!':None
}
branchI = {'F':'branchF'}
branchF = {'(':None}
branchLower ={
'>':None,
'=':None
}
branchHigher = {'=':None}
# Needed to get a reference from a string to a dict
treeDict = {
'branchI':branchI,
'branchF':branchF,
'branchLower':branchLower,
'branchHigher':branchHigher
}
# The tokenDic is used in parseExpr.
# The tokenDic contains the following information:
# levelchange: -1: tree down, 0, +1: tree up
# replacement token
# special token list
tokenDic = {
'(' :( 1, '(', None),
'IF(':( 1, '(', None),
'=' :( 0 ,'==', None),
'<>' :( 0 ,'!=', None),
'>=' :( 0 ,'>=', None),
'<=' :( 0 ,'<=', None),
'<' :( 0 ,'<', None),
'>' :( 0 ,'>', None),
# ';' :( 0 ,';', ['?',':']),
',' :( 0 ,',', ['?',':']),
')' :(-1 ,')', None),
'!' :( 0 ,'.', None) #Connector to cells on other Sheets
# '"' :( 2 ,'', None)
}
class exprNode(object):
''' This defines a tree class for expression parsing'''
def __init__(self, parent, state):
self.state = state #see comment: State machine for expression parsing
self.parent = parent # Parent tree node
self.result = ''
class FormulaTranslator(object):
''' This class tranlates a cell-formula from Excel to FreeCAD.'''
def __init__(self):
self.theTList = ['=']
def translateForm(self, actExpr):
self.getNextToken(actExpr)
#print "tokenList: ", self.theTList
self.resultTree = exprNode(None, 5)
self.resultTree.result = self.resultTree.result + self.theTList[0]
self.parseExpr(self.theTList, 1, self.resultTree)
#print 'parseResult: ', self.resultTree.result
return self.replaceFunc(self.resultTree.result)
def replaceFunc(self, cellFormula):
for funcKey in funcDic:
if funcKey in cellFormula:
cellFormula = cellFormula.replace(funcKey, funcDic[funcKey])
return cellFormula
def getNextToken(self, theExpr):
#print 'next Token theExpr: ', theExpr
#print 'actTList: ', self.theTList
tokenComplete = False
keyToken = False
if len(theExpr)>0:
theTok = theExpr[0]
theExpr = theExpr[1:]
if theTok in treeToken:
keyToken = True
branch = treeToken[theTok]
while branch:
#print branch, ' theExpr[0]: ',theExpr[0]
if theExpr[0] in treeDict[branch]:
branch = treeDict[branch][theExpr[0]]
theTok = theTok + theExpr[0]
theExpr = theExpr[1:]
else:
branch= None
tokenComplete = True
self.theTList.append(theTok)
self.getNextToken(theExpr)
else:
if len(theExpr)>0:
while (not tokenComplete):
if not self.isKey(theExpr):
theTok = theTok + theExpr[0]
theExpr = theExpr[1:]
if len(theExpr) == 0:
tokenComplete = True
else:
tokenComplete = True
self.theTList.append(theTok)
self.getNextToken(theExpr)
def isKey(self, theExpr):
#print 'look up: ', theExpr
keyToken = False
lenExpr = len(theExpr)
if theExpr[0] in treeToken:
branch = treeToken[theExpr[0]]
if branch == None:
keyToken = True
else:
#print 'There is a branch. look up: ', theExpr[1]
if (lenExpr > 1) and (theExpr[1] in treeDict[branch]):
branch = treeDict[branch][theExpr[0]]
if branch == None:
keyToken = True
else:
if (lenExpr > 2) and (theExpr[2] in treeDict[branch]):
keyToken = True
else:
keyToken = True
return keyToken
# State machine for expression parsing
# 0 in ifsubexpression
# 1 in conditional
# 2 in truecase
# 3 in falsecase
# 4 in subexpression
# 5 toplevel '='
def parseExpr(self, tokenList, index, theTree):
token = tokenList[index]
#print 'state: ', theTree.state, ' ', token
nextIdx = index + 1
if token in tokenDic:
lChange, newToken, specialList = tokenDic[token]
else:
lChange = 0
newToken = token
specialList = None
if lChange == 1:
theTree.result = theTree.result + newToken
if token == '(':
state = 4
else:
state = 1
newNode = exprNode(theTree, state)
self.parseExpr(tokenList, nextIdx, newNode)
else:
if lChange == 0:
if theTree.state > 2:
theTree.result = theTree.result + newToken
else:
if (theTree.state == 1):
if specialList:
theTree.result = theTree.result + specialList[0]
theTree.state = 2
else:
theTree.result = theTree.result + newToken
else:
if (theTree.state == 2):
if specialList:
theTree.result = theTree.result + specialList[1]
theTree.state = 3
else:
theTree.result = theTree.result + newToken
if nextIdx < len(tokenList):
self.parseExpr(tokenList, nextIdx, theTree)
else:
theTree.parent.result = theTree.parent.result + theTree.result + newToken
if nextIdx < len(tokenList):
self.parseExpr(tokenList, nextIdx, theTree.parent)
# End of Formula Translator
def getText(nodelist):
rc = []
for node in nodelist:
if node.nodeType == node.TEXT_NODE:
rc.append(node.data)
return ''.join(rc)
def handleWorkSheet(theDom, actSheet, strList):
rows = theDom.getElementsByTagName("row")
for row in rows:
handleCells(row.getElementsByTagName("c"), actSheet, strList)
def handleCells(cellList, actCellSheet, sList):
for cell in cellList:
cellAtts = cell.attributes
refRef = cellAtts.getNamedItem("r")
ref = getText(refRef.childNodes)
refType = cellAtts.getNamedItem("t")
if refType:
cellType = getText(refType.childNodes)
else:
cellType = 'n' # fix me some cells dont have t and s attributes
#print "reference: ", ref, ' Cell type: ', cellType
formulaRef = cell.getElementsByTagName("f")
if len(formulaRef)==1:
theFormula = getText(formulaRef[0].childNodes)
#print "theFormula: ", theFormula
fTrans = FormulaTranslator()
actCellSheet.set(ref, fTrans.translateForm(theFormula))
else:
valueRef = cell.getElementsByTagName("v")[0]
if valueRef:
theValue = getText(valueRef.childNodes)
#print "theValue: ", theValue
if cellType == 'n':
actCellSheet.set(ref, theValue)
if cellType == 's':
actCellSheet.set(ref, (sList[int(theValue)]).encode('utf8'))
def handleWorkBook(theBook, sheetDict, Doc):
theSheets = theBook.getElementsByTagName("sheet")
#print "theSheets: ", theSheets
for sheet in theSheets:
sheetAtts = sheet.attributes
nameRef = sheetAtts.getNamedItem("name")
sheetName = getText(nameRef.childNodes)
#print "table name: ", sheetName
idRef = sheetAtts.getNamedItem("sheetId")
sheetFile = "sheet" + getText(idRef.childNodes) + '.xml'
#print "sheetFile: ", sheetFile
# add FreeCAD-spreadsheet
sheetDict[sheetName] = (Doc.addObject('Spreadsheet::Sheet', sheetName), sheetFile)
theAliases = theBook.getElementsByTagName("definedName")
for theAlias in theAliases:
aliAtts = theAlias.attributes
nameRef = aliAtts.getNamedItem("name")
aliasName = getText(nameRef.childNodes)
#print "aliasName: ", aliasName
aliasRef = getText(theAlias.childNodes)
if '$' in aliasRef:
refList = aliasRef.split('!$')
adressList = refList[1].split('$')
#print "aliasRef: ", aliasRef
#print 'Sheet Name: ', refList[0]
#print 'Adress: ', adressList[0] + adressList[1]
actSheet, sheetFile = sheetDict[refList[0]]
actSheet.setAlias(adressList[0]+adressList[1], aliasName.encode('utf8'))
def handleStrings(theStr, sList):
print('process Strings: ')
stringElements = theStr.getElementsByTagName('t')
for sElem in stringElements:
print('string: ', getText(sElem.childNodes))
sList.append(getText(sElem.childNodes))
def open(nameXLSX):
if len(nameXLSX) > 0:
z=zipfile.ZipFile(nameXLSX)
theDoc = App.newDocument()
sheetDict = dict()
stringList = []
theBookFile=z.open('xl/workbook.xml')
theBook = xml.dom.minidom.parse(theBookFile)
handleWorkBook(theBook, sheetDict, theDoc)
theBook.unlink()
if 'xl/sharedStrings.xml' in z.namelist():
theStringFile=z.open('xl/sharedStrings.xml')
theStrings = xml.dom.minidom.parse(theStringFile)
handleStrings(theStrings, stringList)
theStrings.unlink()
for sheetSpec in sheetDict:
#print "sheetSpec: ", sheetSpec
theSheet, sheetFile = sheetDict[sheetSpec]
f=z.open('xl/worksheets/' + sheetFile)
myDom = xml.dom.minidom.parse(f)
handleWorkSheet(myDom, theSheet, stringList)
myDom.unlink()
z.close()
# This is needed more than once, otherwise some references are not calculated!
theDoc.recompute()
theDoc.recompute()
theDoc.recompute()
return theDoc
def insert(nameXLSX,docname):
try:
theDoc=App.getDocument(docname)
except NameError:
theDoc=App.newDocument(docname)
App.ActiveDocument = theDoc
sheetDict = dict()
stringList = []
z=zipfile.ZipFile(nameXLSX)
theBookFile=z.open('xl/workbook.xml')
theBook = xml.dom.minidom.parse(theBookFile)
handleWorkBook(theBook, sheetDict, theDoc)
theBook.unlink()
if 'xl/sharedStrings.xml' in z.namelist():
theStringFile=z.open('xl/sharedStrings.xml')
theStrings = xml.dom.minidom.parse(theStringFile)
handleStrings(theStrings, stringList)
theStrings.unlink()
for sheetSpec in sheetDict:
#print "sheetSpec: ", sheetSpec
theSheet, sheetFile = sheetDict[sheetSpec]
f=z.open('xl/worksheets/' + sheetFile)
myDom = xml.dom.minidom.parse(f)
handleWorkSheet(myDom, theSheet, stringList)
myDom.unlink()
z.close()
# This is needed more than once, otherwise some references are not calculated!
theDoc.recompute()
theDoc.recompute()
theDoc.recompute()