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
|
from __future__ import unicode_literals
class AppTestReader(object):
spaceconfig = dict(usemodules=['_csv'])
def setup_class(cls):
w__read_test = cls.space.appexec([], r"""():
import _csv
def _read_test(input, expect, **kwargs):
reader = _csv.reader(input, **kwargs)
if expect == 'Error':
raises(_csv.Error, list, reader)
return
result = list(reader)
assert result == expect, 'result: %r\nexpect: %r' % (
result, expect)
return _read_test
""")
if type(w__read_test) is type(lambda:0):
w__read_test = staticmethod(w__read_test)
cls.w__read_test = w__read_test
def test_escaped_char_quotes(self):
import _csv
from io import StringIO
r = _csv.reader(StringIO('a\\\nb,c\n'), quoting=_csv.QUOTE_NONE, escapechar='\\')
assert next(r) == ['a\nb', 'c']
def test_simple_reader(self):
self._read_test(['foo:bar\n'], [['foo', 'bar']], delimiter=':')
def test_cannot_read_bytes(self):
import _csv
reader = _csv.reader([b'foo'])
raises(_csv.Error, next, reader)
def test_read_oddinputs(self):
self._read_test([], [])
self._read_test([''], [[]])
self._read_test(['"ab"c'], 'Error', strict = 1)
self._read_test(['"ab"c'], [['abc']], doublequote = 0)
def test_read_eol(self):
import csv
self._read_test(['a,b'], [['a','b']])
self._read_test(['a,b\n'], [['a','b']])
self._read_test(['a,b\r\n'], [['a','b']])
self._read_test(['a,b\r'], [['a','b']])
self._read_test(['a,b\rc,d'], 'Error')
self._read_test(['a,b\nc,d'], 'Error')
self._read_test(['a,b\r\nc,d'], 'Error')
errmsg = "with newline=''"
with raises(csv.Error) as info:
next(csv.reader(['a,b\rc,d']))
assert errmsg in str(info.value)
def test_read_escape(self):
self._read_test(['a,\\b,c'], [['a', 'b', 'c']], escapechar='\\')
self._read_test(['a,b\\,c'], [['a', 'b,c']], escapechar='\\')
self._read_test(['a,"b\\,c"'], [['a', 'b,c']], escapechar='\\')
self._read_test(['a,"b,\\c"'], [['a', 'b,c']], escapechar='\\')
self._read_test(['a,"b,c\\""'], [['a', 'b,c"']], escapechar='\\')
self._read_test(['a,"b,c"\\'], [['a', 'b,c\\']], escapechar='\\')
self._read_test(['a,\0b,c'], [['a', 'b', 'c']], escapechar='\0')
def test_read_quoting(self):
import _csv as csv
self._read_test(['1,",3,",5'], [['1', ',3,', '5']])
self._read_test(['1,",3,",5'], [['1', '"', '3', '"', '5']],
quotechar=None, escapechar='\\')
self._read_test(['1,",3,",5'], [['1', '"', '3', '"', '5']],
quoting=csv.QUOTE_NONE, escapechar='\\')
# will this fail where locale uses comma for decimals?
self._read_test([',3,"5",7.3, 9'], [['', 3, '5', 7.3, 9]],
quoting=csv.QUOTE_NONNUMERIC)
self._read_test(['"a\nb", 7'], [['a\nb', ' 7']])
raises(ValueError, self._read_test,
['abc,3'], [[]],
quoting=csv.QUOTE_NONNUMERIC)
self._read_test(['1,\0,3,\0,5'], [['1', ',3,', '5']], quotechar='\0')
def test_read_bigfield(self):
# This exercises the buffer realloc functionality and field size
# limits.
import _csv as csv
limit = csv.field_size_limit()
try:
size = 150
bigstring = 'X' * size
bigline = '%s,%s' % (bigstring, bigstring)
self._read_test([bigline], [[bigstring, bigstring]])
csv.field_size_limit(size)
self._read_test([bigline], [[bigstring, bigstring]])
assert csv.field_size_limit() == size
csv.field_size_limit(size-1)
self._read_test([bigline], 'Error')
raises(TypeError, csv.field_size_limit, None)
raises(TypeError, csv.field_size_limit, 1, None)
finally:
csv.field_size_limit(limit)
def test_read_linenum(self):
import _csv as csv
r = csv.reader(['line,1', 'line,2', 'line,3'])
assert r.line_num == 0
next(r)
assert r.line_num == 1
next(r)
assert r.line_num == 2
next(r)
assert r.line_num == 3
raises(StopIteration, "next(r)")
assert r.line_num == 3
def test_dubious_quote(self):
self._read_test(['12,12,1",'], [['12', '12', '1"', '']])
def test_read_eof(self):
self._read_test(['a,"'], [['a', '']])
self._read_test(['"a'], [['a']])
self._read_test(['^'], [['\n']], escapechar='^')
self._read_test(['a,"'], 'Error', strict=True)
self._read_test(['"a'], 'Error', strict=True)
self._read_test(['^'], 'Error', escapechar='^', strict=True)
def test_read_nul(self):
self._read_test(['\0'], [['\0']])
self._read_test(['a,\0b,c'], [['a', '\0b', 'c']])
self._read_test(['a,b\0,c'], [['a', 'b\0', 'c']])
self._read_test(['a,b\\\0,c'], [['a', 'b\0', 'c']], escapechar='\\')
self._read_test(['a,"\0b",c'], [['a', '\0b', 'c']])
def test_read_nul_delimiter(self):
self._read_test(['a\0b\0c'], [['a', 'b', 'c']], delimiter='\0')
|
