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
| """
| Tests that work on both the Python and C engines but do not have a
| specific classification into the other test modules.
| """
| import csv
| from io import StringIO
|
| import pytest
|
| from pandas import DataFrame
| import pandas._testing as tm
|
| from pandas.io.parsers import TextParser
|
| xfail_pyarrow = pytest.mark.usefixtures("pyarrow_xfail")
|
|
| @xfail_pyarrow
| def test_read_data_list(all_parsers):
| parser = all_parsers
| kwargs = {"index_col": 0}
| data = "A,B,C\nfoo,1,2,3\nbar,4,5,6"
|
| data_list = [["A", "B", "C"], ["foo", "1", "2", "3"], ["bar", "4", "5", "6"]]
| expected = parser.read_csv(StringIO(data), **kwargs)
|
| with TextParser(data_list, chunksize=2, **kwargs) as parser:
| result = parser.read()
|
| tm.assert_frame_equal(result, expected)
|
|
| def test_reader_list(all_parsers):
| data = """index,A,B,C,D
| foo,2,3,4,5
| bar,7,8,9,10
| baz,12,13,14,15
| qux,12,13,14,15
| foo2,12,13,14,15
| bar2,12,13,14,15
| """
| parser = all_parsers
| kwargs = {"index_col": 0}
|
| lines = list(csv.reader(StringIO(data)))
| with TextParser(lines, chunksize=2, **kwargs) as reader:
| chunks = list(reader)
|
| expected = parser.read_csv(StringIO(data), **kwargs)
|
| tm.assert_frame_equal(chunks[0], expected[:2])
| tm.assert_frame_equal(chunks[1], expected[2:4])
| tm.assert_frame_equal(chunks[2], expected[4:])
|
|
| def test_reader_list_skiprows(all_parsers):
| data = """index,A,B,C,D
| foo,2,3,4,5
| bar,7,8,9,10
| baz,12,13,14,15
| qux,12,13,14,15
| foo2,12,13,14,15
| bar2,12,13,14,15
| """
| parser = all_parsers
| kwargs = {"index_col": 0}
|
| lines = list(csv.reader(StringIO(data)))
| with TextParser(lines, chunksize=2, skiprows=[1], **kwargs) as reader:
| chunks = list(reader)
|
| expected = parser.read_csv(StringIO(data), **kwargs)
|
| tm.assert_frame_equal(chunks[0], expected[1:3])
|
|
| def test_read_csv_parse_simple_list(all_parsers):
| parser = all_parsers
| data = """foo
| bar baz
| qux foo
| foo
| bar"""
|
| result = parser.read_csv(StringIO(data), header=None)
| expected = DataFrame(["foo", "bar baz", "qux foo", "foo", "bar"])
| tm.assert_frame_equal(result, expected)
|
|
