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
|
/*
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you under the Apache License, Version 2.0 (the
* "License"); you may not use this file except in compliance
* with the License. You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package org.apache.drill.exec.store.easy.text.compliant;
import static org.apache.drill.test.rowSet.RowSetUtilities.strArray;
import java.io.File;
import java.io.IOException;
import org.apache.drill.categories.RowSetTests;
import org.apache.drill.common.types.TypeProtos.MinorType;
import org.apache.drill.exec.record.metadata.SchemaBuilder;
import org.apache.drill.exec.record.metadata.TupleMetadata;
import org.apache.drill.test.rowSet.RowSet;
import org.apache.drill.test.rowSet.RowSetBuilder;
import org.apache.drill.test.rowSet.RowSetUtilities;
import org.junit.BeforeClass;
import org.junit.Test;
import org.junit.experimental.categories.Category;
// CSV reader now hosted on the row set framework
@Category(RowSetTests.class)
public class TestCsvIgnoreHeaders extends BaseCsvTest{
private static String withHeaders[] = {
"a,b,c",
"10,foo,bar",
"20,fred,wilma"
};
private static String raggedRows[] = {
"a,b,c",
"10,dino",
"20,foo,bar",
"30"
};
@BeforeClass
public static void setup() throws Exception {
BaseCsvTest.setup(true, false);
}
@Test
public void testColumns() throws IOException {
try {
enableV3(false);
doTestColumns();
enableV3(true);
doTestColumns();
} finally {
resetV3();
}
}
private void doTestColumns() throws IOException {
String fileName = "simple.csv";
buildFile(fileName, withHeaders);
String sql = "SELECT columns FROM `dfs.data`.`%s`";
RowSet actual = client.queryBuilder().sql(sql, fileName).rowSet();
TupleMetadata expectedSchema = new SchemaBuilder()
.addArray("columns", MinorType.VARCHAR)
.buildSchema();
RowSet expected = new RowSetBuilder(client.allocator(), expectedSchema)
.addSingleCol(strArray("10", "foo", "bar"))
.addSingleCol(strArray("20", "fred", "wilma"))
.build();
RowSetUtilities.verify(expected, actual);
}
@Test
public void testRaggedRows() throws IOException {
try {
enableV3(false);
doTestRaggedRows();
enableV3(true);
doTestRaggedRows();
} finally {
resetV3();
}
}
private void doTestRaggedRows() throws IOException {
String fileName = "ragged.csv";
TestCsvWithHeaders.buildFile(new File(testDir, fileName), raggedRows);
String sql = "SELECT columns FROM `dfs.data`.`%s`";
RowSet actual = client.queryBuilder().sql(sql, fileName).rowSet();
TupleMetadata expectedSchema = new SchemaBuilder()
.addArray("columns", MinorType.VARCHAR)
.buildSchema();
RowSet expected = new RowSetBuilder(client.allocator(), expectedSchema)
.addSingleCol(strArray("10", "dino"))
.addSingleCol(strArray("20", "foo", "bar"))
.addSingleCol(strArray("30"))
.build();
RowSetUtilities.verify(expected, actual);
}
}
|