forked from pyexcel/pyexcel
-
Notifications
You must be signed in to change notification settings - Fork 0
/
test_reader.py
341 lines (273 loc) · 8.09 KB
/
test_reader.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
from nose.tools import eq_, raises
import pyexcel as p
from .base import (
PyexcelBase,
clean_up_files,
create_generic_file,
create_sample_file1
)
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)
@raises(IndexError)
def test_cell_value(self):
r = p.Reader(self.testfile)
value = r.cell_value(0, 1)
assert value == "b"
value = r.cell_value(100, 100)
def test_row_range(self):
r = p.Reader(self.testfile)
row_range = r.row_range()
assert len(row_range) == 3
def test_column_range(self):
r = p.Reader(self.testfile)
column_range = r.column_range()
assert len(column_range) == 4
@raises(ValueError)
def test_named_column_at(self):
r = p.SeriesReader(self.testfile)
data = r.named_column_at("a")
assert ["e", "i"] == data
r.named_column_at("A")
def test_get_item_operator(self):
r = p.Reader(self.testfile)
value = r[0, 1]
assert value == "b"
@raises(IndexError)
def test_row_at(self):
r = p.Reader(self.testfile)
value = r.row_at(2)
assert value == ["i", "j", 1.1, 1]
value = r.row_at(100) # bang
@raises(IndexError)
def test_column_at(self):
r = p.Reader(self.testfile)
value = r.column_at(1)
assert value == ["b", "f", "j"]
value = r.column_at(100) # bang
@raises(p.exceptions.FileTypeNotSupported)
def test_not_supported_file(self):
p.Reader("test.sylk")
@raises(IndexError)
def test_out_of_index(self):
r = p.Reader(self.testfile)
r.row[10000]
def test_contains(self):
r = p.Reader(self.testfile)
def f(row):
return row[0] == "a" and row[1] == "b"
assert r.contains(f) is True
def tearDown(self):
clean_up_files([self.testfile])
class TestCSVReader(PyexcelBase):
"""
Test CSV reader
"""
def setUp(self):
"""
Make a test csv file as:
1,1,1,1
2,2,2,2
3,3,3,3
"""
self.testfile = "testcsv.csv"
self._write_test_file(self.testfile)
def tearDown(self):
clean_up_files([self.testfile])
class TestCSVReader2:
def setUp(self):
"""
Make a test csv file as:
a,b,c,d
e,f,g,h
i,j,k,l
"""
self.testfile = "testcsv.csv"
create_sample_file1(self.testfile)
def test_data_types(self):
r = p.Reader(self.testfile)
result = ["a", "b", "c", "d", "e", "f", "g", "h", "i", "j", 1.1, 1]
actual = list(r.enumerate())
eq_(result, actual)
def tearDown(self):
clean_up_files([self.testfile])
class TestCSVReaderDialect:
def setUp(self):
"""
Make a test csv file as:
a,b,c,d
e,f,g,h
i,j,k,l
"""
self.testfile = "testcsv.csv"
table = []
for i in [0, 4, 8]:
array = [i + 1, i + 2, i + 3, i + 4]
table.append(array)
p.save_as(
dest_file_name=self.testfile, dest_delimiter=":", array=table
)
def test_delimiter(self):
with open(self.testfile, encoding='utf-8') as test_file:
content = "1:2:3:45:6:7:89:10:11:12"
expected = ""
for line in test_file:
line = line.rstrip()
expected += line
eq_(expected, content)
def test_read_delimiter(self):
r = p.Reader(self.testfile, delimiter=":")
content = list(r)
assert content == [[1, 2, 3, 4], [5, 6, 7, 8], [9, 10, 11, 12]]
def tearDown(self):
clean_up_files([self.testfile])
class TestXLSReader(PyexcelBase):
def setUp(self):
"""
Make a test csv file as:
1,1,1,1
2,2,2,2
3,3,3,3
"""
self.testfile = "test.xls"
self._write_test_file(self.testfile)
@raises(ValueError)
def test_wrong_sheet(self):
p.load(self.testfile, "Noexistent Sheet")
def tearDown(self):
clean_up_files([self.testfile])
class TestXLSXReader(PyexcelBase):
def setUp(self):
"""
Make a test csv file as:
1,1,1,1
2,2,2,2
3,3,3,3
"""
self.testfile = "test.xlsx"
self._write_test_file(self.testfile)
def tearDown(self):
clean_up_files([self.testfile])
class TestXLSMReader(PyexcelBase):
def setUp(self):
"""
Make a test csv file as:
1,1,1,1
2,2,2,2
3,3,3,3
"""
self.testfile = "test.xlsm"
self._write_test_file(self.testfile)
def tearDown(self):
clean_up_files([self.testfile])
class TestSeriesReader3:
def setUp(self):
self.testfile = "test.xlsx"
self.content = [
["X", "Y", "Z"],
[1, 11, 12],
[2, 21, 22],
[3, 31, 32],
[4, 41, 42],
[5, 51, 52],
]
create_generic_file(self.testfile, self.content)
def test_empty_series_reader(self):
# debug this further
s = p.Sheet() # seriesreader is gone since v0.0.7
assert s.name == "pyexcel sheet"
test_data = [
[1, 2, 3],
[4, 5, 6],
["Column 1", "Column 2", "Column 3"],
]
s.column += p.internal.sheets.transpose(test_data)
actual = s.array
assert test_data == actual
s.name_columns_by_row(2)
assert s.colnames == test_data[2]
def tearDown(self):
clean_up_files([self.testfile])
class TestSeriesReader4:
def setUp(self):
self.testfile = "test.xls"
self.content = [
["X", "Y", "Z"],
[1, 2, 3],
[1, 2, 3],
[1, 2, 3],
[1, 2, 3],
[1, 2, 3],
]
create_generic_file(self.testfile, self.content)
def test_content_is_read(self):
r = p.SeriesReader(self.testfile)
actual = list(r.rows())
assert self.content[1:] == actual
def test_headers(self):
r = p.SeriesReader(self.testfile)
actual = r.colnames
assert self.content[0] == actual
def test_named_column_at(self):
r = p.SeriesReader(self.testfile)
result = r.named_column_at("X")
actual = {"X": [1, 1, 1, 1, 1]}
eq_(result, actual["X"])
def test_get_item_operator(self):
"""
Series Reader will skip first row because it has column header
"""
r = p.SeriesReader(self.testfile)
value = r[0, 1]
assert value == 2
def tearDown(self):
clean_up_files([self.testfile])
class TestSeriesReader5:
def setUp(self):
self.testfile = "test.xls"
self.content = [
[1, 2, 3],
[1, 2, 3],
[1, 2, 3],
[1, 2, 3],
["X", "Y", "Z"],
[1, 2, 3],
]
create_generic_file(self.testfile, self.content)
def test_content_is_read(self):
r = p.SeriesReader(self.testfile, series=4)
actual = list(r.rows())
self.content.pop(4)
eq_(self.content, actual)
def test_headers(self):
r = p.SeriesReader(self.testfile, series=4)
actual = r.colnames
eq_(self.content[4], actual)
def test_named_column_at(self):
r = p.SeriesReader(self.testfile, series=4)
result = r.named_column_at("X")
actual = {"X": [1, 1, 1, 1, 1]}
eq_(result, actual["X"])
def test_get_item_operator(self):
r = p.SeriesReader(self.testfile, series=4)
value = r[0, 1]
assert value == 2
def tearDown(self):
clean_up_files([self.testfile])
def test_cell_value_boundary():
data = [[0, 1], [10, 11]]
sheet = p.Sheet(data)
value = sheet.cell_value(1, 1)
eq_(value, 11)
@raises(IndexError)
def test_cell_value_outside_boundary():
data = [[0, 1], [10, 11]]
sheet = p.Sheet(data)
sheet.cell_value(1, 2)