-
Notifications
You must be signed in to change notification settings - Fork 16
/
Copy pathDBInputFormat.java
272 lines (236 loc) · 9.79 KB
/
DBInputFormat.java
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
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
/**
Copyright 2010 BackType
Licensed 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 cascading.dbmigrate.hadoop;
import cascading.tuple.Tuple;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.WritableUtils;
import org.apache.hadoop.mapred.*;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.math.BigDecimal;
import java.math.BigInteger;
import java.sql.*;
import java.util.Map;
public class DBInputFormat implements InputFormat<LongWritable, TupleWrapper> {
private static final Logger LOG = LoggerFactory.getLogger(DBInputFormat.class);
public static class DBRecordReader implements RecordReader<LongWritable, TupleWrapper> {
private ResultSet results;
private Statement statement;
private Connection connection;
private DBInputSplit split;
private long pos = 0;
protected DBRecordReader(DBInputSplit split, JobConf job) throws IOException {
try {
this.split = split;
DBConfiguration conf = new DBConfiguration(job);
connection = conf.getConnection();
statement = connection
.createStatement(ResultSet.TYPE_FORWARD_ONLY, ResultSet.CONCUR_READ_ONLY);
//statement.setFetchSize(Integer.MIN_VALUE);
String query = getSelectQuery(conf, split);
LOG.info("Running query: " + query);
try {
results = statement.executeQuery(query);
} catch (SQLException exception) {
LOG.error("unable to execute select query: " + query, exception);
throw new IOException("unable to execute select query: " + query, exception);
}
} catch (SQLException e) {
throw new RuntimeException(e);
}
}
public static <T> String join(T[] arr, String sep) {
String ret = "";
for (int i = 0; i < arr.length; i++) {
ret = ret + arr[i];
if (i < arr.length - 1) {
ret = ret + sep;
}
}
return ret;
}
protected String getSelectQuery(DBConfiguration conf, DBInputSplit split) {
StringBuilder query = new StringBuilder();
query.append("SELECT ");
query.append(join(conf.getInputColumnNames(), ","));
query.append(" FROM ");
query.append(conf.getInputTableName());
query.append(" WHERE ");
query.append(split.primaryKeyColumn + ">=" + split.startId);
query.append(" AND ");
query.append(split.primaryKeyColumn + "<" + split.endId);
return query.toString();
}
public void close() throws IOException {
try {
results.close();
statement.close();
connection.close();
} catch (SQLException exception) {
throw new IOException("unable to commit and close", exception);
}
}
/** {@inheritDoc} */
public LongWritable createKey() {
return new LongWritable();
}
/** {@inheritDoc} */
public TupleWrapper createValue() {
return new TupleWrapper();
}
/** {@inheritDoc} */
public long getPos() throws IOException {
return pos;
}
/** {@inheritDoc} */
public float getProgress() throws IOException {
return (pos / (float) split.getLength());
}
/** {@inheritDoc} */
public boolean next(LongWritable key, TupleWrapper value) throws IOException {
try {
if (!results.next()) {
return false;
}
key.set(pos + split.startId);
value.tuple = new Tuple();
for (int i = 0; i < results.getMetaData().getColumnCount(); i++) {
Object o = results.getObject(i + 1);
if (o instanceof byte[]) {
o = new BytesWritable((byte[]) o);
} else if (o instanceof BigInteger) {
o = ((BigInteger) o).longValue();
} else if (o instanceof BigDecimal) {
o = ((BigDecimal) o).doubleValue();
}
try {
value.tuple.add(o);
} catch (Throwable t) {
LOG.info("WTF: " + o.toString() + o.getClass().toString());
throw new RuntimeException(t);
}
}
pos++;
} catch (SQLException exception) {
throw new IOException("unable to get next value", exception);
}
return true;
}
}
protected static class DBInputSplit implements InputSplit {
public long endId = 0;
public long startId = 0;
public String primaryKeyColumn;
public DBInputSplit() {
}
public DBInputSplit(long start, long end, String primaryKeyColumn) {
startId = start;
endId = end;
this.primaryKeyColumn = primaryKeyColumn;
}
public String[] getLocations() throws IOException {
return new String[]{};
}
public long getLength() throws IOException {
return endId - startId;
}
public void readFields(DataInput input) throws IOException {
startId = input.readLong();
endId = input.readLong();
primaryKeyColumn = WritableUtils.readString(input);
}
public void write(DataOutput output) throws IOException {
output.writeLong(startId);
output.writeLong(endId);
WritableUtils.writeString(output, primaryKeyColumn);
}
}
public RecordReader<LongWritable, TupleWrapper> getRecordReader(InputSplit split, JobConf job,
Reporter reporter) throws IOException {
return new DBRecordReader((DBInputSplit) split, job);
}
private long getMaxId(DBConfiguration conf, Connection conn, String tableName, String col) {
if (conf.getMaxId() != null) {
return conf.getMaxId();
}
try {
PreparedStatement s =
conn.prepareStatement("SELECT MAX(" + col + ") FROM " + tableName);
ResultSet rs = s.executeQuery();
rs.next();
long ret = rs.getLong(1);
rs.close();
s.close();
return ret;
} catch (SQLException e) {
throw new RuntimeException(e);
}
}
private long getMinId(DBConfiguration conf, Connection conn, String tableName, String col) {
if (conf.getMinId() != null) {
return conf.getMinId();
}
try {
PreparedStatement s =
conn.prepareStatement("SELECT MIN(" + col + ") FROM " + tableName);
ResultSet rs = s.executeQuery();
rs.next();
long ret = rs.getLong(1);
rs.close();
s.close();
return ret;
} catch (SQLException e) {
throw new RuntimeException(e);
}
}
public InputSplit[] getSplits(JobConf job, int ignored) throws IOException {
try {
DBConfiguration conf = new DBConfiguration(job);
int chunks = conf.getNumChunks();
Connection conn = conf.getConnection();
String primarykeycolumn = conf.getPrimaryKeyColumn();
long maxId = getMaxId(conf, conn, conf.getInputTableName(), conf.getPrimaryKeyColumn());
long minId = getMinId(conf, conn, conf.getInputTableName(), conf.getPrimaryKeyColumn());
long chunkSize = (maxId - minId + 1) / chunks + 1;
chunks = (int) ((maxId - minId + 1) / chunkSize) + 1;
InputSplit[] ret = new InputSplit[chunks];
long currId = minId;
for (int i = 0; i < chunks; i++) {
long start = currId;
currId += chunkSize;
ret[i] = new DBInputSplit(start, Math.min(currId, maxId + 1), primarykeycolumn);
}
conn.close();
return ret;
} catch (SQLException e) {
throw new RuntimeException(e);
}
}
public static void setInput(JobConf job, int numChunks, String databaseDriver, String username,
String pwd, String dburl, String tableName, String pkColumn, Long minId, Long maxId,
Map<String,String> driverProps,
String... columnNames) {
job.setInputFormat(DBInputFormat.class);
DBConfiguration dbConf = new DBConfiguration(job);
dbConf.configureDB(databaseDriver, dburl, username, pwd);
if (minId != null) {
dbConf.setMinId(minId.longValue());
}
if (maxId != null) {
dbConf.setMaxId(maxId.longValue());
}
if (driverProps != null) {
dbConf.setDriverProperties(driverProps);
}
dbConf.setInputTableName(tableName);
dbConf.setInputColumnNames(columnNames);
dbConf.setPrimaryKeyColumn(pkColumn);
dbConf.setNumChunks(numChunks);
}
}