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
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
|
/*
* Copyright (c) 2009 Concurrent, Inc.
*
* This work has been released into the public domain
* by the copyright holder. This applies worldwide.
*
* In case this is not legally possible:
* The copyright holder grants any entity the right
* to use this work for any purpose, without any
* conditions, unless such conditions are required by law.
*/
/**
* 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 parallelai.spyglass.jdbc.db;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.mapred.*;
import org.apache.hadoop.util.ReflectionUtils;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.DataInput;
import java.io.DataOutput;
import java.io.IOException;
import java.sql.*;
/**
* A InputFormat that reads input data from an SQL table. <p/> DBInputFormat emits LongWritables
* containing the record number as key and DBWritables as value. <p/> The SQL query, and input class
* can be using one of the two setInput methods.
*/
public class DBInputFormat<T extends DBWritable>
implements InputFormat<LongWritable, T>, JobConfigurable {
/** Field LOG */
private static final Logger LOG = LoggerFactory.getLogger(DBInputFormat.class);
/**
* A RecordReader that reads records from a SQL table. Emits LongWritables containing the record
* number as key and DBWritables as value.
*/
protected class DBRecordReader implements RecordReader<LongWritable, T> {
private ResultSet results;
private Statement statement;
private Class<T> inputClass;
private JobConf job;
private DBInputSplit split;
private long pos = 0;
/**
* @param split The InputSplit to read data for
* @throws SQLException
*/
protected DBRecordReader(DBInputSplit split, Class<T> inputClass, JobConf job)
throws SQLException, IOException {
this.inputClass = inputClass;
this.split = split;
this.job = job;
statement =
connection.createStatement(ResultSet.TYPE_FORWARD_ONLY, ResultSet.CONCUR_READ_ONLY);
//statement.setFetchSize(Integer.MIN_VALUE);
String query = getSelectQuery();
try {
LOG.info(query);
results = statement.executeQuery(query);
LOG.info("done executing select query");
} catch (SQLException exception) {
LOG.error("unable to execute select query: " + query, exception);
throw new IOException("unable to execute select query: " + query, exception);
}
}
/**
* Returns the query for selecting the records, subclasses can override this for custom
* behaviour.
*/
protected String getSelectQuery() {
LOG.info("Executing select query");
StringBuilder query = new StringBuilder();
if (dbConf.getInputQuery() == null) {
query.append("SELECT ");
for (int i = 0; i < fieldNames.length; i++) {
query.append(fieldNames[i]);
if (i != fieldNames.length - 1)
query.append(", ");
}
query.append(" FROM ").append(tableName);
query.append(" AS ").append(tableName); //in hsqldb this is necessary
if (conditions != null && conditions.length() > 0)
query.append(" WHERE (").append(conditions).append(")");
String orderBy = dbConf.getInputOrderBy();
if (orderBy != null && orderBy.length() > 0)
query.append(" ORDER BY ").append(orderBy);
}
else
query.append(dbConf.getInputQuery());
try {
// Only add limit and offset if you have multiple chunks
if(split.getChunks() > 1) {
query.append(" LIMIT ").append(split.getLength());
query.append(" OFFSET ").append(split.getStart());
}
} catch (IOException ex) {
//ignore, will not throw
}
return query.toString();
}
/** {@inheritDoc} */
public void close() throws IOException {
try {
connection.commit();
results.close();
statement.close();
} catch (SQLException exception) {
throw new IOException("unable to commit and close", exception);
}
}
/** {@inheritDoc} */
public LongWritable createKey() {
return new LongWritable();
}
/** {@inheritDoc} */
public T createValue() {
return ReflectionUtils.newInstance(inputClass, job);
}
/** {@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, T value) throws IOException {
try {
if (!results.next())
return false;
// Set the key field value as the output key value
key.set(pos + split.getStart());
value.readFields(results);
pos++;
} catch (SQLException exception) {
throw new IOException("unable to get next value", exception);
}
return true;
}
}
/** A Class that does nothing, implementing DBWritable */
public static class NullDBWritable implements DBWritable, Writable {
public void readFields(DataInput in) throws IOException {
}
public void readFields(ResultSet arg0) throws SQLException {
}
public void write(DataOutput out) throws IOException {
}
public void write(PreparedStatement arg0) throws SQLException {
}
}
/** A InputSplit that spans a set of rows */
protected static class DBInputSplit implements InputSplit {
private long end = 0;
private long start = 0;
private long chunks = 0;
/** Default Constructor */
public DBInputSplit() {
}
/**
* Convenience Constructor
*
* @param start the index of the first row to select
* @param end the index of the last row to select
*/
public DBInputSplit(long start, long end, long chunks) {
this.start = start;
this.end = end;
this.chunks = chunks;
LOG.info("creating DB input split with start: " + start + ", end: " + end + ", chunks: " + chunks);
}
/** {@inheritDoc} */
public String[] getLocations() throws IOException {
// TODO Add a layer to enable SQL "sharding" and support locality
return new String[]{};
}
/** @return The index of the first row to select */
public long getStart() {
return start;
}
/** @return The index of the last row to select */
public long getEnd() {
return end;
}
/** @return The total row count in this split */
public long getLength() throws IOException {
return end - start;
}
/** @return The total number of chucks accross all splits */
public long getChunks() {
return chunks;
}
/** {@inheritDoc} */
public void readFields(DataInput input) throws IOException {
start = input.readLong();
end = input.readLong();
chunks = input.readLong();
}
/** {@inheritDoc} */
public void write(DataOutput output) throws IOException {
output.writeLong(start);
output.writeLong(end);
output.writeLong(chunks);
}
}
protected DBConfiguration dbConf;
protected Connection connection;
protected String tableName;
protected String[] fieldNames;
protected String conditions;
protected long limit;
protected int maxConcurrentReads;
/** {@inheritDoc} */
public void configure(JobConf job) {
dbConf = new DBConfiguration(job);
tableName = dbConf.getInputTableName();
fieldNames = dbConf.getInputFieldNames();
conditions = dbConf.getInputConditions();
limit = dbConf.getInputLimit();
maxConcurrentReads = dbConf.getMaxConcurrentReadsNum();
try {
connection = dbConf.getConnection();
} catch (IOException exception) {
throw new RuntimeException("unable to create connection", exception.getCause());
}
configureConnection(connection);
}
protected void configureConnection(Connection connection) {
setTransactionIsolationLevel(connection);
setAutoCommit(connection);
}
protected void setAutoCommit(Connection connection) {
try {
connection.setAutoCommit(false);
} catch (Exception exception) {
throw new RuntimeException("unable to set auto commit", exception);
}
}
protected void setTransactionIsolationLevel(Connection connection) {
try {
connection.setTransactionIsolation(Connection.TRANSACTION_SERIALIZABLE);
} catch (SQLException exception) {
throw new RuntimeException("unable to configure transaction isolation level", exception);
}
}
/** {@inheritDoc} */
@SuppressWarnings("unchecked")
public RecordReader<LongWritable, T> getRecordReader(InputSplit split, JobConf job,
Reporter reporter) throws IOException {
Class inputClass = dbConf.getInputClass();
try {
return new DBRecordReader((DBInputSplit) split, inputClass, job);
} catch (SQLException exception) {
throw new IOException(exception.getMessage(), exception);
}
}
/** {@inheritDoc} */
public InputSplit[] getSplits(JobConf job, int chunks) throws IOException {
// use the configured value if avail
chunks = maxConcurrentReads == 0 ? chunks : maxConcurrentReads;
try {
Statement statement = connection.createStatement();
ResultSet results = statement.executeQuery(getCountQuery());
long count = 0;
while (results.next())
count += results.getLong(1);
if (limit != -1)
count = Math.min(limit, count);
long chunkSize = (count / chunks);
results.close();
statement.close();
InputSplit[] splits = new InputSplit[chunks];
// Split the rows into n-number of chunks and adjust the last chunk
// accordingly
for (int i = 0; i < chunks; i++) {
DBInputSplit split;
if (i + 1 == chunks)
split = new DBInputSplit(i * chunkSize, count, chunks);
else
split = new DBInputSplit(i * chunkSize, i * chunkSize + chunkSize, chunks);
splits[i] = split;
}
return splits;
} catch (SQLException e) {
throw new IOException(e.getMessage());
}
}
/**
* Returns the query for getting the total number of rows, subclasses can override this for
* custom behaviour.
*/
protected String getCountQuery() {
if (dbConf.getInputCountQuery() != null) { return dbConf.getInputCountQuery(); }
StringBuilder query = new StringBuilder();
query.append("SELECT COUNT(*) FROM " + tableName);
if (conditions != null && conditions.length() > 0)
query.append(" WHERE " + conditions);
return query.toString();
}
/**
* Initializes the map-part of the job with the appropriate input settings.
*
* @param job The job
* @param inputClass the class object implementing DBWritable, which is the Java object
* holding tuple fields.
* @param tableName The table to read data from
* @param conditions The condition which to select data with, eg. '(updated > 20070101 AND
* length > 0)'
* @param orderBy the fieldNames in the orderBy clause.
* @param limit
* @param fieldNames The field names in the table
* @param concurrentReads
*/
public static void setInput(JobConf job, Class<? extends DBWritable> inputClass,
String tableName, String conditions, String orderBy, long limit, int concurrentReads,
String... fieldNames) {
job.setInputFormat(DBInputFormat.class);
DBConfiguration dbConf = new DBConfiguration(job);
dbConf.setInputClass(inputClass);
dbConf.setInputTableName(tableName);
dbConf.setInputFieldNames(fieldNames);
dbConf.setInputConditions(conditions);
dbConf.setInputOrderBy(orderBy);
if (limit != -1)
dbConf.setInputLimit(limit);
dbConf.setMaxConcurrentReadsNum(concurrentReads);
}
/**
* Initializes the map-part of the job with the appropriate input settings.
*
* @param job The job
* @param inputClass the class object implementing DBWritable, which is the Java object
* holding tuple fields.
* @param selectQuery the input query to select fields. Example : "SELECT f1, f2, f3 FROM
* Mytable ORDER BY f1"
* @param countQuery the input query that returns the number of records in the table.
* Example : "SELECT COUNT(f1) FROM Mytable"
* @param concurrentReads
*/
public static void setInput(JobConf job, Class<? extends DBWritable> inputClass,
String selectQuery, String countQuery, long limit, int concurrentReads) {
job.setInputFormat(DBInputFormat.class);
DBConfiguration dbConf = new DBConfiguration(job);
dbConf.setInputClass(inputClass);
dbConf.setInputQuery(selectQuery);
dbConf.setInputCountQuery(countQuery);
if (limit != -1)
dbConf.setInputLimit(limit);
dbConf.setMaxConcurrentReadsNum(concurrentReads);
}
}
|