forked from apache/hudi
-
Notifications
You must be signed in to change notification settings - Fork 1
/
HoodieJavaGenerateApp.java
195 lines (167 loc) · 8.48 KB
/
HoodieJavaGenerateApp.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
/*
* 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.
*/
import org.apache.hudi.DataSourceWriteOptions;
import org.apache.hudi.HoodieDataSourceHelpers;
import org.apache.hudi.common.model.HoodieRecord;
import org.apache.hudi.common.model.HoodieTableType;
import org.apache.hudi.common.table.timeline.HoodieActiveTimeline;
import org.apache.hudi.common.testutils.HoodieTestDataGenerator;
import org.apache.hudi.config.HoodieWriteConfig;
import org.apache.hudi.hive.MultiPartKeysValueExtractor;
import org.apache.hudi.hive.NonPartitionedExtractor;
import org.apache.hudi.hive.SlashEncodedDayPartitionValueExtractor;
import org.apache.hudi.keygen.NonpartitionedKeyGenerator;
import org.apache.hudi.keygen.SimpleKeyGenerator;
import com.beust.jcommander.JCommander;
import com.beust.jcommander.Parameter;
import org.apache.hadoop.fs.FileSystem;
import org.apache.log4j.LogManager;
import org.apache.log4j.Logger;
import org.apache.spark.api.java.JavaSparkContext;
import org.apache.spark.sql.DataFrameWriter;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.Row;
import org.apache.spark.sql.SparkSession;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import static org.apache.hudi.common.testutils.RawTripTestPayload.recordsToStrings;
public class HoodieJavaGenerateApp {
@Parameter(names = {"--table-path", "-p"}, description = "Path for Hoodie sample table")
private String tablePath = "file:///tmp/hoodie/sample-table";
@Parameter(names = {"--table-name", "-n"}, description = "Table name for Hoodie sample table")
private String tableName = "hoodie_test";
@Parameter(names = {"--table-type", "-t"}, description = "One of COPY_ON_WRITE or MERGE_ON_READ")
private String tableType = HoodieTableType.COPY_ON_WRITE.name();
@Parameter(names = {"--hive-sync", "-hs"}, description = "Enable syncing to hive")
private Boolean enableHiveSync = false;
@Parameter(names = {"--hive-db", "-hd"}, description = "Hive database")
private String hiveDB = "default";
@Parameter(names = {"--hive-table", "-ht"}, description = "Hive table")
private String hiveTable = "hoodie_sample_test";
@Parameter(names = {"--hive-user", "-hu"}, description = "Hive username")
private String hiveUser = "hive";
@Parameter(names = {"--hive-password", "-hp"}, description = "Hive password")
private String hivePass = "hive";
@Parameter(names = {"--hive-url", "-hl"}, description = "Hive JDBC URL")
private String hiveJdbcUrl = "jdbc:hive2://localhost:10000";
@Parameter(names = {"--non-partitioned", "-np"}, description = "Use non-partitioned Table")
private Boolean nonPartitionedTable = false;
@Parameter(names = {"--use-multi-partition-keys", "-mp"}, description = "Use Multiple Partition Keys")
private Boolean useMultiPartitionKeys = false;
@Parameter(names = {"--commit-type", "-ct"}, description = "How may commits will run")
private String commitType = "overwrite";
@Parameter(names = {"--help", "-h"}, help = true)
public Boolean help = false;
private static final Logger LOG = LogManager.getLogger(HoodieJavaGenerateApp.class);
public static void main(String[] args) throws Exception {
HoodieJavaGenerateApp cli = new HoodieJavaGenerateApp();
JCommander cmd = new JCommander(cli, null, args);
if (cli.help) {
cmd.usage();
System.exit(1);
}
try (SparkSession spark = cli.getOrCreateSparkSession()) {
cli.insert(spark);
}
}
private SparkSession getOrCreateSparkSession() {
// Spark session setup..
SparkSession spark = SparkSession.builder().appName("Hoodie Spark APP")
.config("spark.serializer", "org.apache.spark.serializer.KryoSerializer").master("local[1]").getOrCreate();
spark.sparkContext().setLogLevel("WARN");
return spark;
}
private HoodieTestDataGenerator getDataGenerate() {
// Generator of some records to be loaded in.
if (nonPartitionedTable) {
// All data goes to base-path
return new HoodieTestDataGenerator(new String[]{""});
} else {
return new HoodieTestDataGenerator();
}
}
/**
* Setup configs for syncing to hive.
*/
private DataFrameWriter<Row> updateHiveSyncConfig(DataFrameWriter<Row> writer) {
if (enableHiveSync) {
LOG.info("Enabling Hive sync to " + hiveJdbcUrl);
writer = writer.option(DataSourceWriteOptions.HIVE_TABLE().key(), hiveTable)
.option(DataSourceWriteOptions.HIVE_DATABASE().key(), hiveDB)
.option(DataSourceWriteOptions.HIVE_URL().key(), hiveJdbcUrl)
.option(DataSourceWriteOptions.HIVE_USER().key(), hiveUser)
.option(DataSourceWriteOptions.HIVE_PASS().key(), hivePass)
.option(DataSourceWriteOptions.HIVE_SYNC_ENABLED().key(), "true");
if (nonPartitionedTable) {
writer = writer
.option(DataSourceWriteOptions.HIVE_PARTITION_EXTRACTOR_CLASS().key(),
NonPartitionedExtractor.class.getCanonicalName())
.option(DataSourceWriteOptions.PARTITIONPATH_FIELD().key(), "");
} else if (useMultiPartitionKeys) {
writer = writer.option(DataSourceWriteOptions.HIVE_PARTITION_FIELDS().key(), "year,month,day").option(
DataSourceWriteOptions.HIVE_PARTITION_EXTRACTOR_CLASS().key(),
MultiPartKeysValueExtractor.class.getCanonicalName());
} else {
writer = writer.option(DataSourceWriteOptions.HIVE_PARTITION_FIELDS().key(), "dateStr").option(
DataSourceWriteOptions.HIVE_PARTITION_EXTRACTOR_CLASS().key(),
SlashEncodedDayPartitionValueExtractor.class.getCanonicalName());
}
}
return writer;
}
private void insert(SparkSession spark) throws IOException {
HoodieTestDataGenerator dataGen = getDataGenerate();
JavaSparkContext jssc = new JavaSparkContext(spark.sparkContext());
// Generate some input..
String instantTime = HoodieActiveTimeline.createNewInstantTime();
List<HoodieRecord> recordsSoFar = new ArrayList<>(dataGen.generateInserts(instantTime/* ignore */, 100));
List<String> records1 = recordsToStrings(recordsSoFar);
Dataset<Row> inputDF1 = spark.read().json(jssc.parallelize(records1, 2));
// Save as hoodie dataset (copy on write)
// specify the hoodie source
DataFrameWriter<Row> writer = inputDF1.write().format("org.apache.hudi")
// any hoodie client config can be passed like this
.option("hoodie.insert.shuffle.parallelism", "2")
// full list in HoodieWriteConfig & its package
.option("hoodie.upsert.shuffle.parallelism", "2")
// Hoodie Table Type
.option(DataSourceWriteOptions.TABLE_TYPE().key(), tableType)
// insert
.option(DataSourceWriteOptions.OPERATION().key(), DataSourceWriteOptions.INSERT_OPERATION_OPT_VAL())
// This is the record key
.option(DataSourceWriteOptions.RECORDKEY_FIELD().key(), "_row_key")
// this is the partition to place it into
.option(DataSourceWriteOptions.PARTITIONPATH_FIELD().key(), "partition")
// use to combine duplicate records in input/with disk val
.option(DataSourceWriteOptions.PRECOMBINE_FIELD().key(), "timestamp")
// Used by hive sync and queries
.option(HoodieWriteConfig.TBL_NAME.key(), tableName)
// Add Key Extractor
.option(DataSourceWriteOptions.KEYGENERATOR_CLASS_NAME().key(),
nonPartitionedTable ? NonpartitionedKeyGenerator.class.getCanonicalName()
: SimpleKeyGenerator.class.getCanonicalName())
.mode(commitType);
updateHiveSyncConfig(writer);
// new dataset if needed
writer.save(tablePath); // ultimately where the dataset will be placed
FileSystem fs = FileSystem.get(jssc.hadoopConfiguration());
String commitInstantTime1 = HoodieDataSourceHelpers.latestCommit(fs, tablePath);
LOG.info("Commit at instant time :" + commitInstantTime1);
}
}