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
|
import json
import sys
from unittest.mock import patch
import agate
from csvkit.utilities.csvstat import CSVStat, launch_new_instance
from tests.utils import ColumnsTests, CSVKitTestCase, EmptyFileTests, NamesTests
class TestCSVStat(CSVKitTestCase, ColumnsTests, EmptyFileTests, NamesTests):
Utility = CSVStat
def test_launch_new_instance(self):
with patch.object(sys, 'argv', [self.Utility.__name__.lower(), 'examples/dummy.csv']):
launch_new_instance()
def test_options(self):
self.assertError(
launch_new_instance,
['--min', '--max'],
'Only one operation argument may be specified (--mean, --median, etc).',
)
def test_format_options(self):
for option in ('csv', 'json', 'count'):
with self.subTest(option=option):
self.assertError(
launch_new_instance,
['--min', f'--{option}'],
f'You may not specify --{option} and an operation (--mean, --median, etc) at the same time.',
)
def test_runs(self):
# Test that csvstat doesn't error on UTF-8 input.
self.get_output(['examples/test_utf8.csv'])
def test_encoding(self):
# Test that csvstat doesn't error on Latin-1 input.
self.get_output(['-e', 'latin1', 'examples/test_latin1.csv'])
def test_columns(self):
output = self.get_output(['-c', '2', 'examples/testxls_converted.csv'])
self.assertNotIn('1. "text"', output)
self.assertIn('2. "date"', output)
def test_linenumbers(self):
output = self.get_output(['-c', '2', '--linenumbers', 'examples/dummy.csv'])
self.assertNotIn('1. "a"', output)
self.assertIn('2. "b"', output)
def test_no_header_row(self):
output = self.get_output(['-c', '2', '--no-header-row', 'examples/no_header_row.csv'])
self.assertNotIn('1. "a"', output)
self.assertIn('2. "b"', output)
def test_count_only(self):
output = self.get_output(['--count', 'examples/realdata/ks_1033_data.csv'])
self.assertEqual(output, '1575\n')
def test_unique(self):
output = self.get_output(['-c', 'county', 'examples/realdata/ks_1033_data.csv'])
self.assertRegex(output, r'Unique values:\s+73')
def test_max_length(self):
output = self.get_output(['-c', 'county', 'examples/realdata/ks_1033_data.csv'])
self.assertRegex(output, r'Longest value:\s+12')
def test_freq_list(self):
output = self.get_output(['examples/realdata/ks_1033_data.csv'])
self.assertIn('WYANDOTTE (123x)', output)
self.assertIn('SALINE (59x)', output)
self.assertNotIn('MIAMI (56x)', output)
def test_freq(self):
output = self.get_output(['examples/realdata/ks_1033_data.csv', '--freq'])
self.assertIn(' 1. state: { "KS": 1575 }', output)
def test_freq_count(self):
output = self.get_output(['examples/realdata/ks_1033_data.csv', '--freq-count', '1'])
self.assertIn('WYANDOTTE (123x)', output)
self.assertNotIn('FINNEY (103x)', output)
self.assertNotIn('MIAMI (56x)', output)
def test_csv(self):
output = self.get_output_as_io(['--csv', 'examples/realdata/ks_1033_data.csv'])
reader = agate.csv.reader(output)
header = next(reader)
self.assertEqual(header[1], 'column_name')
self.assertEqual(header[5], 'unique')
row = next(reader)
self.assertEqual(row[1], 'state')
self.assertEqual(row[2], 'Text')
self.assertEqual(row[6], '')
self.assertEqual(row[12], '2')
def test_csv_columns(self):
output = self.get_output_as_io(['--csv', '-c', '4', 'examples/realdata/ks_1033_data.csv'])
reader = agate.csv.reader(output)
header = next(reader)
self.assertEqual(header[1], 'column_name')
self.assertEqual(header[5], 'unique')
row = next(reader)
self.assertEqual(row[1], 'nsn')
self.assertEqual(row[2], 'Text')
self.assertEqual(row[6], '')
self.assertEqual(row[12], '16')
def test_json(self):
output = self.get_output_as_io(['--json', 'examples/realdata/ks_1033_data.csv'])
data = json.load(output)
header = list(data[0])
self.assertEqual(header[1], 'column_name')
self.assertEqual(header[5], 'unique')
row = list(data[0].values())
self.assertEqual(row[1], 'state')
self.assertEqual(row[2], 'Text')
self.assertNotIn('min', data[0])
self.assertEqual(row[-2], 2.0)
def test_json_columns(self):
output = self.get_output_as_io(['--json', '-c', '4', 'examples/realdata/ks_1033_data.csv'])
data = json.load(output)
header = list(data[0])
self.assertEqual(header[1], 'column_name')
self.assertEqual(header[5], 'unique')
row = list(data[0].values())
self.assertEqual(row[1], 'nsn')
self.assertEqual(row[2], 'Text')
self.assertNotIn('min', data[0])
self.assertEqual(row[-2], 16.0)
def test_decimal_format(self):
# Disable locale-specific LC_NUMERIC grouping separator test
# output = self.get_output(['-c', 'TOTAL', '--mean', 'examples/realdata/FY09_EDU_Recipients_by_State.csv'])
# self.assertEqual(output, '9,748.346\n')
output = self.get_output([
'-c', 'TOTAL', '--mean', '--no-grouping-separator', 'examples/realdata/FY09_EDU_Recipients_by_State.csv',
])
self.assertEqual(output, '9748.346\n')
output = self.get_output([
'-c', 'TOTAL', '--mean', '--decimal-format', '%.2f', 'examples/realdata/FY09_EDU_Recipients_by_State.csv',
])
# Modify test to run under LC_ALL=C.UTF-8
self.assertEqual(output, '9748.35\n')
|
