Codebase list pyexcel / master tests / test_multiple_sheets.py
master

Tree @master (Download .tar.gz)

test_multiple_sheets.py @masterraw · history · blame

  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
import os

import pyexcel as pe
from base import PyexcelMultipleSheetBase, clean_up_files, create_sample_file1
from _compact import OrderedDict

from nose.tools import raises


class TestXlsNXlsmMultipleSheets(PyexcelMultipleSheetBase):
    def setUp(self):
        self.testfile = "multiple1.xls"
        self.testfile2 = "multiple1.xlsm"
        self.content = _produce_ordered_dict()
        self._write_test_file(self.testfile)

    def tearDown(self):
        self._clean_up()


class TestCSVNXlsMultipleSheets:
    def setUp(self):
        self.testfile = "multiple1.csv"
        self.content = _produce_ordered_dict()
        pe.save_book_as(dest_file_name=self.testfile, bookdict=self.content)

    def test_read_multiple_csv_into_book(self):
        book = pe.load_book(self.testfile)
        assert book.sheet_names() == ["Sheet1", "Sheet2", "Sheet3"]
        book["Sheet1"].format(int)
        assert self.content["Sheet1"] == book["Sheet1"].to_array()
        book["Sheet2"].format(int)
        assert self.content["Sheet2"] == book["Sheet2"].to_array()
        book["Sheet3"].format(int)
        assert self.content["Sheet3"] == book["Sheet3"].to_array()

    def tearDown(self):
        if os.path.exists("multiple1__Sheet1__0.csv"):
            os.unlink("multiple1__Sheet1__0.csv")
        if os.path.exists("multiple1__Sheet2__1.csv"):
            os.unlink("multiple1__Sheet2__1.csv")
        if os.path.exists("multiple1__Sheet3__2.csv"):
            os.unlink("multiple1__Sheet3__2.csv")


class TestCSVzMultipleSheets:
    def setUp(self):
        self.testfile = "multiple1.csvz"
        self.content = _produce_ordered_dict()
        pe.save_book_as(dest_file_name=self.testfile, bookdict=self.content)

    def test_read_multiple_csv_into_book(self):
        book = pe.load_book(self.testfile)
        assert book.sheet_names() == ["Sheet1", "Sheet2", "Sheet3"]
        book["Sheet1"].format(int)
        assert self.content["Sheet1"] == book["Sheet1"].to_array()
        book["Sheet2"].format(int)
        assert self.content["Sheet2"] == book["Sheet2"].to_array()
        book["Sheet3"].format(int)
        assert self.content["Sheet3"] == book["Sheet3"].to_array()

    def tearDown(self):
        if os.path.exists("multiple1.csvz"):
            os.unlink("multiple1.csvz")


class TestSingleSheetReaderForMulitpleSheetBook:
    def setUp(self):
        self.testfile = "multiple1.xls"
        self.content = _produce_ordered_dict()
        pe.save_book_as(dest_file_name=self.testfile, bookdict=self.content)

    def test_non_default_sheet_as_single_sheet_reader(self):
        r = pe.get_sheet(file_name=self.testfile, sheet_name="Sheet1")
        data = r.array
        assert data == self.content["Sheet1"]
        r2 = pe.get_sheet(file_name=self.testfile, sheet_name="Sheet2")
        data = r2.array
        assert data == self.content["Sheet2"]
        r3 = pe.get_sheet(file_name=self.testfile, sheet_name="Sheet3")
        data = r3.array
        assert data == self.content["Sheet3"]

    def test_non_default_sheet_as_single_sheet_reader_series(self):
        r = pe.SeriesReader(self.testfile, "Sheet3")
        data = list(r.rows())
        assert data == self.content["Sheet3"][1:]

    def test_non_default_sheet_as_single_sheet_plain_reader(self):
        r = pe.load(self.testfile, "Sheet2")
        data = list(r.rows())
        assert data == self.content["Sheet2"]

    def tearDown(self):
        if os.path.exists(self.testfile):
            os.unlink(self.testfile)


class TestReader:
    def setUp(self):
        """
        Make a test csv file as:

        a,b,c,d
        e,f,g,h
        i,j,1.1,1
        """
        self.testfile = "testcsv.csv"
        create_sample_file1(self.testfile)

    def test_csv_book_reader(self):
        r = pe.BookReader(self.testfile)
        assert r.number_of_sheets() == 1
        assert r.sheet_names() == [self.testfile]

    def tearDown(self):
        if os.path.exists(self.testfile):
            os.unlink(self.testfile)


class TestCSVSingleSheet:
    def _write_test_file(self, filename, content):
        """
        Make a test file as:

        1,1,1,1
        2,2,2,2
        3,3,3,3
        """
        pe.save_book_as(dest_file_name=filename, bookdict=content)

    def setUp(self):
        self.testfile = "multiple1.csv"
        self.content = _produce_ordered_dict()
        self._write_test_file(self.testfile, self.content)

    def test_load_a_single_sheet(self):
        b1 = pe.load_book(self.testfile, sheet_name="Sheet1")
        b1["Sheet1"].format(int)
        assert len(b1.sheet_names()) == 1
        assert b1["Sheet1"].to_array() == self.content["Sheet1"]

    def test_load_a_single_sheet2(self):
        b1 = pe.load_book(self.testfile, sheet_index=1)
        b1["Sheet2"].format(int)
        assert len(b1.sheet_names()) == 1
        assert b1["Sheet2"].to_array() == self.content["Sheet2"]

    @raises(IndexError)
    def test_load_a_single_sheet3(self):
        pe.load_book(self.testfile, sheet_index=10000)

    @raises(ValueError)
    def test_load_a_single_sheet4(self):
        pe.load_book(self.testfile, sheet_name="Not exist")

    def tearDown(self):
        clean_up_files(
            [
                "multiple1__Sheet1__0.csv",
                "multiple1__Sheet2__1.csv",
                "multiple1__Sheet3__2.csv",
            ]
        )


class TestCSVZSingleSheet:
    def _write_test_file(self, filename, content):
        """
        Make a test file as:

        1,1,1,1
        2,2,2,2
        3,3,3,3
        """
        pe.save_book_as(dest_file_name=filename, bookdict=content)

    def setUp(self):
        self.testfile = "multiple1.csvz"
        self.content = _produce_ordered_dict()
        self._write_test_file(self.testfile, self.content)

    def test_load_a_single_sheet(self):
        b1 = pe.load_book(self.testfile, sheet_name="Sheet1")
        b1["Sheet1"].format(int)
        assert len(b1.sheet_names()) == 1
        assert b1["Sheet1"].to_array() == self.content["Sheet1"]

    def test_load_a_single_sheet2(self):
        b1 = pe.load_book(self.testfile, sheet_index=1)
        b1["Sheet2"].format(int)
        assert len(b1.sheet_names()) == 1
        assert b1["Sheet2"].to_array() == self.content["Sheet2"]

    @raises(IndexError)
    def test_load_a_single_sheet3(self):
        pe.load_book(self.testfile, sheet_index=10000)

    @raises(ValueError)
    def test_load_a_single_sheet4(self):
        pe.load_book(self.testfile, sheet_name="Not exist")

    def tearDown(self):
        clean_up_files([self.testfile])


class TestAddBooks:
    def _write_test_file(self, filename, content):
        """
        Make a test file as:

        1,1,1,1
        2,2,2,2
        3,3,3,3
        """
        pe.save_book_as(dest_file_name=filename, bookdict=content)

    def setUp(self):
        self.testfile = "multiple1.xlsm"
        self.testfile2 = "multiple1.xls"
        self.testfile3 = "multiple2.xlsx"
        self.content = _produce_ordered_dict()
        self._write_test_file(self.testfile, self.content)
        self._write_test_file(self.testfile2, self.content)
        self.test_single_sheet_file = "single.xls"
        self.content1 = {"Sheet1": [[1, 1, 1, 1], [2, 2, 2, 2], [3, 3, 3, 3]]}
        self._write_test_file(self.test_single_sheet_file, self.content1)

    @raises(KeyError)
    def test_delete_sheets(self):
        """Can delete by sheet name"""
        b1 = pe.load_book(self.testfile)
        assert len(b1.sheet_names()) == 3
        del b1["Sheet1"]
        assert len(b1.sheet_names()) == 2
        del b1["Sheet1"]  # bang, already deleted

    @raises(IndexError)
    def test_delete_sheets2(self):
        """Can delete by index"""
        b1 = pe.load_book(self.testfile)
        assert len(b1.sheet_names()) == 3
        del b1[2]
        del b1[1]
        assert len(b1.sheet_names()) == 1
        del b1[1]  # bang, already deleted

    @raises(TypeError)
    def test_delete_sheets3(self):
        """Test float in []"""
        b1 = pe.load_book(self.testfile)
        del b1[1.1]

    def test_delete_sheets4(self):
        """repetitively delete first sheet"""
        b1 = pe.load_book(self.testfile)
        del b1[0]
        assert len(b1.sheet_names()) == 2
        del b1[0]
        assert len(b1.sheet_names()) == 1
        del b1[0]
        assert len(b1.sheet_names()) == 0

    def test_add_book1(self):
        """
        test this scenario: book3 = book1 + book2
        """
        b1 = pe.BookReader(self.testfile)
        b2 = pe.BookReader(self.testfile2)
        b3 = b1 + b2
        content = b3.dict
        sheet_names = content.keys()
        assert len(sheet_names) == 6
        for name in sheet_names:
            if "Sheet3" in name:
                assert content[name] == self.content["Sheet3"]
            elif "Sheet2" in name:
                assert content[name] == self.content["Sheet2"]
            elif "Sheet1" in name:
                assert content[name] == self.content["Sheet1"]

    def test_add_book1_in_place(self):
        """
        test this scenario: book1 +=  book2
        """
        b1 = pe.BookReader(self.testfile)
        b2 = pe.BookReader(self.testfile2)
        b1 += b2
        content = b1.dict
        sheet_names = content.keys()
        assert len(sheet_names) == 6
        for name in sheet_names:
            if "Sheet3" in name:
                assert content[name] == self.content["Sheet3"]
            elif "Sheet2" in name:
                assert content[name] == self.content["Sheet2"]
            elif "Sheet1" in name:
                assert content[name] == self.content["Sheet1"]

    def test_add_book2(self):
        """
        test this scenario: book3 = book1 + sheet3
        """
        b1 = pe.BookReader(self.testfile)
        b2 = pe.BookReader(self.testfile2)
        b3 = b1 + b2["Sheet3"]
        content = b3.dict
        sheet_names = content.keys()
        assert len(sheet_names) == 4
        for name in sheet_names:
            if "Sheet3" in name:
                assert content[name] == self.content["Sheet3"]
            elif "Sheet2" in name:
                assert content[name] == self.content["Sheet2"]
            elif "Sheet1" in name:
                assert content[name] == self.content["Sheet1"]

    def test_add_book2_in_place(self):
        """
        test this scenario: book3 = book1 + sheet3
        """
        b1 = pe.BookReader(self.testfile)
        b2 = pe.BookReader(self.testfile2)
        b1 += b2["Sheet3"]
        content = b1.dict
        sheet_names = content.keys()
        assert len(sheet_names) == 4
        for name in sheet_names:
            if "Sheet3" in name:
                assert content[name] == self.content["Sheet3"]
            elif "Sheet2" in name:
                assert content[name] == self.content["Sheet2"]
            elif "Sheet1" in name:
                assert content[name] == self.content["Sheet1"]

    def test_add_book3(self):
        """
        test this scenario: book3 = sheet1 + sheet2
        """
        b1 = pe.BookReader(self.testfile)
        b2 = pe.BookReader(self.testfile2)
        b3 = b1["Sheet1"] + b2["Sheet3"]
        content = b3.dict
        sheet_names = content.keys()
        assert len(sheet_names) == 2
        assert content["Sheet3"] == self.content["Sheet3"]
        assert content["Sheet1"] == self.content["Sheet1"]

    def test_add_book4(self):
        """
        test this scenario: book3 = sheet1 + book
        """
        b1 = pe.BookReader(self.testfile)
        b2 = pe.BookReader(self.testfile2)
        b3 = b1["Sheet1"] + b2
        content = b3.dict
        sheet_names = content.keys()
        assert len(sheet_names) == 4
        for name in sheet_names:
            if "Sheet3" in name:
                assert content[name] == self.content["Sheet3"]
            elif "Sheet2" in name:
                assert content[name] == self.content["Sheet2"]
            elif "Sheet1" in name:
                assert content[name] == self.content["Sheet1"]

    def test_add_book4_2(self):
        """
        test this scenario: book3 = sheet1 + book

        use . notation
        """
        b1 = pe.BookReader(self.testfile)
        b2 = pe.BookReader(self.testfile2)
        b3 = b1.Sheet1 + b2
        content = b3.dict
        sheet_names = content.keys()
        assert len(sheet_names) == 4
        for name in sheet_names:
            if "Sheet3" in name:
                assert content[name] == self.content["Sheet3"]
            elif "Sheet2" in name:
                assert content[name] == self.content["Sheet2"]
            elif "Sheet1" in name:
                assert content[name] == self.content["Sheet1"]

    def test_add_book5(self):
        """
        test this scenario: book3 = single_sheet_book + book
        """
        b1 = pe.BookReader(self.test_single_sheet_file)
        b2 = pe.BookReader(self.testfile2)
        b3 = b1 + b2
        content = b3.dict
        sheet_names = content.keys()
        assert len(sheet_names) == 4
        for name in sheet_names:
            if "Sheet3" in name:
                assert content[name] == self.content["Sheet3"]
            elif "Sheet2" in name:
                assert content[name] == self.content["Sheet2"]
            elif "Sheet1" in name:
                assert content[name] == self.content["Sheet1"]
            elif "single.xls" in name:
                assert content[name] == self.content1["Sheet1"]

    def test_add_book6(self):
        """
        test this scenario: book3 = book + single_sheet_book
        """
        b1 = pe.BookReader(self.test_single_sheet_file)
        b2 = pe.BookReader(self.testfile2)
        b3 = b2 + b1
        content = b3.dict
        sheet_names = content.keys()
        assert len(sheet_names) == 4
        for name in sheet_names:
            if "Sheet3" in name:
                assert content[name] == self.content["Sheet3"]
            elif "Sheet2" in name:
                assert content[name] == self.content["Sheet2"]
            elif "Sheet1" in name:
                assert content[name] == self.content["Sheet1"]
            elif "single.xls" in name:
                assert content[name] == self.content1["Sheet1"]

    def test_add_sheet(self):
        """
        test this scenario: book3 = sheet1 + single_sheet_book
        """
        b1 = pe.BookReader(self.testfile)
        b2 = pe.BookReader(self.test_single_sheet_file)
        b3 = b1["Sheet1"] + b2
        content = b3.dict
        sheet_names = content.keys()
        assert len(sheet_names) == 2
        for name in sheet_names:
            if "Sheet1" in name:
                assert content[name] == self.content["Sheet1"]
            elif "single.xls" in name:
                assert content[name] == self.content1["Sheet1"]

    def test_add_sheet2(self):
        """
        test this scenario: book3 = sheet1 + single_sheet_book
        """
        b1 = pe.BookReader(self.testfile)
        b3 = b1["Sheet1"] + b1["Sheet1"]
        content = b3.dict
        sheet_names = content.keys()
        assert len(sheet_names) == 2
        for name in sheet_names:
            if "Sheet1" in name:
                assert content[name] == self.content["Sheet1"]

    @raises(TypeError)
    def test_add_book_error(self):
        """
        test this scenario: book3 = book + integer
        """
        b1 = pe.BookReader(self.testfile)
        b1 + 12  # bang, cannot add integer

    @raises(TypeError)
    def test_add_book_error2(self):
        b1 = pe.BookReader(self.testfile)
        b1 += 12  # bang cannot iadd integer

    @raises(TypeError)
    def test_add_sheet_error(self):
        """
        test this scenario: book3 = sheet1 + integer
        """
        b1 = pe.BookReader(self.testfile)
        b1["Sheet1"] + 12  # bang, cannot add integer

    @raises(TypeError)
    def test_add_sheet_error2(self):
        b1 = pe.BookReader(self.testfile)
        b1["Sheet1"] += 12  # bang, cannot iadd integer

    def tearDown(self):
        if os.path.exists(self.testfile):
            os.unlink(self.testfile)
        if os.path.exists(self.testfile2):
            os.unlink(self.testfile2)
        if os.path.exists(self.testfile3):
            os.unlink(self.testfile3)
        if os.path.exists(self.test_single_sheet_file):
            os.unlink(self.test_single_sheet_file)


class TestMergeCSVsIntoOne:
    def test_merging(self):
        # set up
        import pyexcel as pe

        data = [[1, 2, 3], [4, 5, 6], [7, 8, 9]]
        data2 = [["a", "b", "c"], ["d", "e", "f"], ["g", "h", "i"]]
        data3 = [[1.1, 2.2, 3.3], [4.4, 5.5, 6.6], [7.7, 8.8, 9.9]]
        pe.save_as(dest_file_name="1.csv", array=data)
        pe.save_as(dest_file_name="2.csv", array=data2)
        pe.save_as(dest_file_name="3.csv", array=data3)
        # execute
        merged = pe.Sheet()
        for file in ["1.csv", "2.csv", "3.csv"]:
            r = pe.get_sheet(file_name=file)
            merged.row += r
        merged.save_as("merged.csv")
        r = pe.get_sheet(file_name="merged.csv")
        actual = r.array
        result = [
            [1, 2, 3],
            [4, 5, 6],
            [7, 8, 9],
            [u"a", u"b", u"c"],
            [u"d", u"e", u"f"],
            [u"g", u"h", u"i"],
            [1.1, 2.2, 3.3],
            [4.4, 5.5, 6.6],
            [7.7, 8.8, 9.9],
        ]
        assert result == actual
        # verify
        os.unlink("1.csv")
        os.unlink("2.csv")
        os.unlink("3.csv")
        os.unlink("merged.csv")


def _produce_ordered_dict():
    data_dict = OrderedDict()
    data_dict.update({"Sheet1": [[1, 1, 1, 1], [2, 2, 2, 2], [3, 3, 3, 3]]})
    data_dict.update({"Sheet2": [[4, 4, 4, 4], [5, 5, 5, 5], [6, 6, 6, 6]]})
    data_dict.update(
        {"Sheet3": [[u"X", u"Y", u"Z"], [1, 4, 7], [2, 5, 8], [3, 6, 9]]}
    )
    return data_dict