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
|
# name: test/sql/copy/csv/test_comment_midline.test
# description: Test that the comment option of csv reading works properly
# group: [csv]
statement ok
PRAGMA enable_verification
query II
from read_csv('{DATA_DIR}/csv/comments/14648.csv',
header=false,
sep=',',
null_padding=true,
comment='#',
ignore_errors=true
);
----
a b
a NULL
x y
query II
from read_csv('{DATA_DIR}/csv/comments/14648.csv',
header=false,
sep=',',
comment='#',
ignore_errors=true
);
----
a b
x y
statement error
from read_csv('{DATA_DIR}/csv/comments/14648.csv',
header=false,
sep=',',
comment='#'
);
----
Error when sniffing file "{DATA_DIR}/csv/comments/14648.csv".
# Not a comment
query III
FROM '{DATA_DIR}/csv/comments/14635.csv'
----
a #b c
# Ignore errors will have,
query III
FROM read_csv('{DATA_DIR}/csv/comments/14635.csv', ignore_errors = true, columns = {'header1': 'VARCHAR', 'header2': 'VARCHAR', 'header3': 'VARCHAR'}, quote = '', escape = '', delim =',');
----
a #b c
# If we only have midline comments, the comment must be explicitly given by the user
query I
FROM '{DATA_DIR}/csv/comments/only_midline.csv';
----
6;7
query II
FROM read_csv('{DATA_DIR}/csv/comments/only_midline.csv', comment = '#');
----
1 3
6 7
query II
FROM '{DATA_DIR}/csv/comments/mid_line.csv';
----
1 3
6 7
query II
FROM '{DATA_DIR}/csv/comments/mid_line_header.csv';
----
1 3
6 7
query II
FROM '{DATA_DIR}/csv/comments/mid_line_quote.csv';
----
1 3
6 7#test
query II
FROM '{DATA_DIR}/csv/comments/mid_line_null.csv';
----
1 3
6 NULL
query II
FROM '{DATA_DIR}/csv/comments/simple_mid_line.csv';
----
1 3
6 7
1 3
6 7
query II
FROM '{DATA_DIR}/csv/comments/midline_empty_space.csv';
----
1 3
6 7
query II
FROM read_csv('{DATA_DIR}/csv/comments/mid_line_invalid.csv', ignore_errors = true, delim = ';', comment = '#', auto_detect = false, columns= {'a':'integer', 'b':'integer'}, strict_mode=True);
----
1 3
6 7
8 9
# Lets try over a vector size
query II
FROM '{DATA_DIR}/csv/comments/midline_big.csv' limit 5;
----
1 3
6 7
1 3
6 7
1 3
# Check commented data-points are not in the data
query II
FROM '{DATA_DIR}/csv/comments/midline_big.csv' where a = 20
----
query I
SELECT count(*) FROM '{DATA_DIR}/csv/comments/midline_big.csv'
----
1448
# Lets try with a buffer limit
loop buffer_size 30 35
query II
FROM read_csv('{DATA_DIR}/csv/comments/simple_mid_line.csv', buffer_size = ${buffer_size}) limit 5;
----
1 3
6 7
1 3
6 7
endloop
|
