embulk-output-utf8parquet 1.0.1 → 1.0.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (44) hide show
  1. checksums.yaml +4 -4
  2. data/LICENSE.txt +21 -0
  3. data/build.gradle +91 -0
  4. data/build/classes/main/org/embulk/output/EmbulkWriteSupport$ParquetColumnVisitor.class +0 -0
  5. data/build/classes/main/org/embulk/output/EmbulkWriteSupport$SchemaConvertColumnVisitor.class +0 -0
  6. data/build/classes/main/org/embulk/output/EmbulkWriteSupport$SchemaConvertColumnVisitorWithUTF8.class +0 -0
  7. data/build/classes/main/org/embulk/output/EmbulkWriteSupport.class +0 -0
  8. data/build/classes/main/org/embulk/output/EmbulkWriterBuilder.class +0 -0
  9. data/build/classes/main/org/embulk/output/ParquetOutputPlugin$ParquetTransactionalPageOutput.class +0 -0
  10. data/build/classes/main/org/embulk/output/ParquetOutputPlugin$PluginTask.class +0 -0
  11. data/build/classes/main/org/embulk/output/ParquetOutputPlugin$TimestampColumnOption.class +0 -0
  12. data/build/classes/main/org/embulk/output/ParquetOutputPlugin.class +0 -0
  13. data/build/classes/test/org/embulk/output/ParquetOutputPluginTest.class +0 -0
  14. data/build/gemspec +19 -0
  15. data/build/libs/embulk-output-utf8parquet-1.0.0.jar +0 -0
  16. data/build/libs/embulk-output-utf8parquet-1.0.1.jar +0 -0
  17. data/build/reports/checkstyle/main.html +119 -0
  18. data/build/reports/checkstyle/main.xml +9 -0
  19. data/build/reports/checkstyle/test.html +99 -0
  20. data/build/reports/checkstyle/test.xml +5 -0
  21. data/build/reports/tests/test/classes/org.embulk.output.ParquetOutputPluginTest.html +106 -0
  22. data/build/reports/tests/test/css/base-style.css +179 -0
  23. data/build/reports/tests/test/css/style.css +84 -0
  24. data/build/reports/tests/test/index.html +132 -0
  25. data/build/reports/tests/test/js/report.js +194 -0
  26. data/build/reports/tests/test/packages/org.embulk.output.html +103 -0
  27. data/build/test-results/test/TEST-org.embulk.output.ParquetOutputPluginTest.xml +9 -0
  28. data/build/test-results/test/binary/output.bin +0 -0
  29. data/build/test-results/test/binary/output.bin.idx +0 -0
  30. data/build/test-results/test/binary/results.bin +0 -0
  31. data/build/tmp/jar/MANIFEST.MF +2 -0
  32. data/classpath/embulk-output-utf8parquet-1.0.2.jar +0 -0
  33. data/config/checkstyle/checkstyle.xml +128 -0
  34. data/config/checkstyle/default.xml +108 -0
  35. data/gradle/wrapper/gradle-wrapper.jar +0 -0
  36. data/gradle/wrapper/gradle-wrapper.properties +6 -0
  37. data/gradlew +164 -0
  38. data/gradlew.bat +90 -0
  39. data/lib/embulk/output/utf8parquet.rb +3 -0
  40. data/src/main/java/org/embulk/output/EmbulkWriteSupport.java +215 -0
  41. data/src/main/java/org/embulk/output/EmbulkWriterBuilder.java +37 -0
  42. data/src/main/java/org/embulk/output/ParquetOutputPlugin.java +236 -0
  43. data/src/test/java/org/embulk/output/ParquetOutputPluginTest.java +70 -0
  44. metadata +115 -73
@@ -0,0 +1,70 @@
1
+ package org.embulk.output;
2
+
3
+ import org.apache.hadoop.conf.Configuration;
4
+ import org.embulk.EmbulkTestRuntime;
5
+ import org.embulk.config.ConfigException;
6
+ import org.embulk.config.ConfigSource;
7
+ import org.embulk.spi.Exec;
8
+ import org.junit.Rule;
9
+ import org.junit.Test;
10
+
11
+ import java.lang.reflect.InvocationTargetException;
12
+ import java.lang.reflect.Method;
13
+ import java.util.Map;
14
+
15
+ import static org.junit.Assert.assertEquals;
16
+ import static org.junit.Assert.assertFalse;
17
+ import static org.junit.Assert.assertTrue;
18
+
19
+ public class ParquetOutputPluginTest
20
+ {
21
+ @Rule
22
+ public EmbulkTestRuntime runtime = new EmbulkTestRuntime();
23
+
24
+ @Test
25
+ public void checkDefaultValues()
26
+ {
27
+ ConfigSource config = Exec.newConfigSource()
28
+ .set("path_prefix", "test");
29
+
30
+ ParquetOutputPlugin.PluginTask task = config.loadConfig(ParquetOutputPlugin.PluginTask.class);
31
+ assertEquals(".parquet", task.getFileNameExtension());
32
+ assertEquals(".%03d", task.getSequenceFormat());
33
+ assertEquals(134217728, task.getBlockSize());
34
+ assertEquals(1048576, task.getPageSize());
35
+ assertEquals("UNCOMPRESSED", task.getCompressionCodec());
36
+ assertFalse(task.getOverwrite());
37
+ }
38
+
39
+ @Test(expected = ConfigException.class)
40
+ public void checkColumnsRequired()
41
+ {
42
+ ConfigSource config = Exec.newConfigSource();
43
+
44
+ config.loadConfig(ParquetOutputPlugin.PluginTask.class);
45
+ }
46
+
47
+ @Test
48
+ public void checkExtraConfigurations()
49
+ throws NoSuchMethodException, InvocationTargetException, IllegalAccessException
50
+ {
51
+ ConfigSource map = Exec.newConfigSource()
52
+ .set("foo", "bar");
53
+
54
+ ConfigSource config = Exec.newConfigSource()
55
+ .set("path_prefix", "test")
56
+ .setNested("extra_configurations", map);
57
+
58
+ ParquetOutputPlugin.PluginTask task = config.loadConfig(ParquetOutputPlugin.PluginTask.class);
59
+
60
+ Map<String, String> extra = task.getExtraConfigurations();
61
+ assertTrue(extra.containsKey("foo"));
62
+ assertEquals("bar", extra.get("foo"));
63
+
64
+ ParquetOutputPlugin plugin = new ParquetOutputPlugin();
65
+ Method method = ParquetOutputPlugin.class.getDeclaredMethod("createConfiguration", Map.class);
66
+ method.setAccessible(true);
67
+ Configuration conf = (Configuration) method.invoke(plugin, extra);
68
+ assertEquals("bar", conf.get("foo"));
69
+ }
70
+ }
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: embulk-output-utf8parquet
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.0.1
4
+ version: 1.0.2
5
5
  platform: ruby
6
6
  authors:
7
7
  - Angelos Alexopoulos
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2018-05-23 00:00:00.000000000 Z
11
+ date: 2018-05-28 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  requirement: !ruby/object:Gem::Requirement
@@ -49,94 +49,136 @@ files:
49
49
  - .idea/misc.xml
50
50
  - .idea/modules.xml
51
51
  - .idea/vcs.xml
52
+ - LICENSE.txt
52
53
  - README.md
53
- - embulk-output-utf8parquet.iml
54
- - classpath/jaxb-impl-2.2.3-1.jar
55
- - classpath/hadoop-aws-2.7.1.jar
56
- - classpath/hadoop-auth-2.7.1.jar
54
+ - build.gradle
55
+ - build/classes/main/org/embulk/output/EmbulkWriteSupport$ParquetColumnVisitor.class
56
+ - build/classes/main/org/embulk/output/EmbulkWriteSupport$SchemaConvertColumnVisitor.class
57
+ - build/classes/main/org/embulk/output/EmbulkWriteSupport$SchemaConvertColumnVisitorWithUTF8.class
58
+ - build/classes/main/org/embulk/output/EmbulkWriteSupport.class
59
+ - build/classes/main/org/embulk/output/EmbulkWriterBuilder.class
60
+ - build/classes/main/org/embulk/output/ParquetOutputPlugin$ParquetTransactionalPageOutput.class
61
+ - build/classes/main/org/embulk/output/ParquetOutputPlugin$PluginTask.class
62
+ - build/classes/main/org/embulk/output/ParquetOutputPlugin$TimestampColumnOption.class
63
+ - build/classes/main/org/embulk/output/ParquetOutputPlugin.class
64
+ - build/classes/test/org/embulk/output/ParquetOutputPluginTest.class
65
+ - build/gemspec
66
+ - build/libs/embulk-output-utf8parquet-1.0.0.jar
67
+ - build/libs/embulk-output-utf8parquet-1.0.1.jar
68
+ - build/reports/checkstyle/main.html
69
+ - build/reports/checkstyle/main.xml
70
+ - build/reports/checkstyle/test.html
71
+ - build/reports/checkstyle/test.xml
72
+ - build/reports/tests/test/classes/org.embulk.output.ParquetOutputPluginTest.html
73
+ - build/reports/tests/test/css/base-style.css
74
+ - build/reports/tests/test/css/style.css
75
+ - build/reports/tests/test/index.html
76
+ - build/reports/tests/test/js/report.js
77
+ - build/reports/tests/test/packages/org.embulk.output.html
78
+ - build/test-results/test/TEST-org.embulk.output.ParquetOutputPluginTest.xml
79
+ - build/test-results/test/binary/output.bin
80
+ - build/test-results/test/binary/output.bin.idx
81
+ - build/test-results/test/binary/results.bin
82
+ - build/tmp/jar/MANIFEST.MF
57
83
  - classpath/activation-1.1.jar
58
- - classpath/commons-configuration-1.6.jar
59
- - classpath/commons-beanutils-1.7.0.jar
60
- - classpath/hadoop-yarn-client-2.7.1.jar
61
- - classpath/xz-1.0.jar
62
- - classpath/commons-httpclient-3.1.jar
63
- - classpath/stax-api-1.0-2.jar
64
84
  - classpath/apacheds-i18n-2.0.0-M15.jar
65
- - classpath/joda-time-2.9.9.jar
66
- - classpath/httpclient-4.2.5.jar
67
- - classpath/jline-0.9.94.jar
68
- - classpath/jaxb-api-2.2.2.jar
69
- - classpath/hadoop-annotations-2.7.1.jar
70
- - classpath/hadoop-mapreduce-client-jobclient-2.7.1.jar
71
- - classpath/hadoop-hdfs-2.7.1.jar
72
- - classpath/jackson-jaxrs-1.9.13.jar
73
- - classpath/xercesImpl-2.9.1.jar
74
- - classpath/commons-logging-1.1.3.jar
75
- - classpath/hadoop-yarn-server-common-2.7.1.jar
76
- - classpath/curator-recipes-2.7.1.jar
77
- - classpath/hadoop-yarn-server-nodemanager-2.7.1.jar
78
- - classpath/jersey-json-1.9.jar
85
+ - classpath/apacheds-kerberos-codec-2.0.0-M15.jar
86
+ - classpath/api-asn1-api-1.0.0-M20.jar
87
+ - classpath/api-util-1.0.0-M20.jar
88
+ - classpath/asm-3.1.jar
79
89
  - classpath/avro-1.7.4.jar
80
- - classpath/log4j-1.2.17.jar
90
+ - classpath/aws-java-sdk-1.7.4.jar
91
+ - classpath/commons-beanutils-1.7.0.jar
81
92
  - classpath/commons-cli-1.2.jar
82
- - classpath/parquet-column-1.8.1.jar
83
- - classpath/xml-apis-1.3.04.jar
93
+ - classpath/commons-codec-1.6.jar
94
+ - classpath/commons-collections-3.2.1.jar
95
+ - classpath/commons-compress-1.4.1.jar
96
+ - classpath/commons-configuration-1.6.jar
84
97
  - classpath/commons-digester-1.8.jar
85
- - classpath/servlet-api-2.5.jar
86
- - classpath/parquet-format-2.3.0-incubating.jar
87
- - classpath/protobuf-java-2.5.0.jar
98
+ - classpath/commons-httpclient-3.1.jar
99
+ - classpath/commons-io-2.4.jar
100
+ - classpath/commons-lang-2.6.jar
101
+ - classpath/commons-logging-1.1.3.jar
102
+ - classpath/commons-math3-3.1.1.jar
103
+ - classpath/commons-net-3.1.jar
104
+ - classpath/curator-client-2.7.1.jar
105
+ - classpath/curator-framework-2.7.1.jar
106
+ - classpath/curator-recipes-2.7.1.jar
107
+ - classpath/embulk-output-utf8parquet-1.0.1.jar
108
+ - classpath/gson-2.2.4.jar
109
+ - classpath/hadoop-annotations-2.7.1.jar
110
+ - classpath/hadoop-auth-2.7.1.jar
111
+ - classpath/hadoop-aws-2.7.1.jar
112
+ - classpath/hadoop-client-2.7.1.jar
113
+ - classpath/hadoop-common-2.7.1.jar
114
+ - classpath/hadoop-hdfs-2.7.1.jar
115
+ - classpath/hadoop-mapreduce-client-app-2.7.1.jar
88
116
  - classpath/hadoop-mapreduce-client-common-2.7.1.jar
89
- - classpath/xmlenc-0.52.jar
90
- - classpath/jackson-xc-1.9.13.jar
91
- - classpath/jetty-util-6.1.26.jar
117
+ - classpath/hadoop-mapreduce-client-core-2.7.1.jar
118
+ - classpath/hadoop-mapreduce-client-jobclient-2.7.1.jar
92
119
  - classpath/hadoop-mapreduce-client-shuffle-2.7.1.jar
93
- - classpath/commons-compress-1.4.1.jar
120
+ - classpath/hadoop-yarn-api-2.7.1.jar
121
+ - classpath/hadoop-yarn-client-2.7.1.jar
94
122
  - classpath/hadoop-yarn-common-2.7.1.jar
95
- - classpath/commons-io-2.4.jar
96
- - classpath/hadoop-mapreduce-client-core-2.7.1.jar
123
+ - classpath/hadoop-yarn-server-common-2.7.1.jar
124
+ - classpath/hadoop-yarn-server-nodemanager-2.7.1.jar
125
+ - classpath/htrace-core-3.1.0-incubating.jar
126
+ - classpath/httpclient-4.2.5.jar
127
+ - classpath/httpcore-4.2.4.jar
97
128
  - classpath/jackson-core-asl-1.9.13.jar
98
- - classpath/jersey-core-1.9.jar
99
- - classpath/jsp-api-2.1.jar
100
- - classpath/commons-codec-1.6.jar
101
- - classpath/snappy-java-1.1.1.6.jar
102
- - classpath/jetty-6.1.26.jar
103
- - classpath/hadoop-yarn-api-2.7.1.jar
104
- - classpath/jersey-server-1.9.jar
129
+ - classpath/jackson-jaxrs-1.9.13.jar
130
+ - classpath/jackson-mapper-asl-1.9.13.jar
131
+ - classpath/jackson-xc-1.9.13.jar
105
132
  - classpath/java-xmlbuilder-0.4.jar
106
- - classpath/netty-3.7.0.Final.jar
107
- - classpath/hadoop-common-2.7.1.jar
133
+ - classpath/jaxb-api-2.2.2.jar
134
+ - classpath/jaxb-impl-2.2.3-1.jar
108
135
  - classpath/jersey-client-1.9.jar
136
+ - classpath/jersey-core-1.9.jar
109
137
  - classpath/jersey-guice-1.9.jar
110
- - classpath/paranamer-2.3.jar
111
- - classpath/zookeeper-3.4.6.jar
112
- - classpath/parquet-encoding-1.8.1.jar
113
- - classpath/jettison-1.1.jar
114
- - classpath/api-asn1-api-1.0.0-M20.jar
115
- - classpath/apacheds-kerberos-codec-2.0.0-M15.jar
116
- - classpath/parquet-hadoop-1.8.1.jar
117
- - classpath/commons-collections-3.2.1.jar
118
- - classpath/asm-3.1.jar
119
- - classpath/parquet-common-1.8.1.jar
120
- - classpath/hadoop-client-2.7.1.jar
121
- - classpath/embulk-output-utf8parquet-1.0.1.jar
122
- - classpath/api-util-1.0.0-M20.jar
123
- - classpath/curator-framework-2.7.1.jar
124
- - classpath/commons-net-3.1.jar
125
- - classpath/gson-2.2.4.jar
138
+ - classpath/jersey-json-1.9.jar
139
+ - classpath/jersey-server-1.9.jar
126
140
  - classpath/jets3t-0.9.0.jar
127
- - classpath/commons-lang-2.6.jar
128
- - classpath/parquet-jackson-1.8.1.jar
141
+ - classpath/jettison-1.1.jar
142
+ - classpath/jetty-6.1.26.jar
143
+ - classpath/jetty-util-6.1.26.jar
144
+ - classpath/jline-0.9.94.jar
145
+ - classpath/joda-time-2.9.9.jar
129
146
  - classpath/jsch-0.1.42.jar
147
+ - classpath/jsp-api-2.1.jar
148
+ - classpath/jsr305-3.0.0.jar
130
149
  - classpath/leveldbjni-all-1.8.jar
131
- - classpath/httpcore-4.2.4.jar
132
- - classpath/hadoop-mapreduce-client-app-2.7.1.jar
133
- - classpath/jackson-mapper-asl-1.9.13.jar
134
- - classpath/commons-math3-3.1.1.jar
150
+ - classpath/log4j-1.2.17.jar
151
+ - classpath/netty-3.7.0.Final.jar
135
152
  - classpath/netty-all-4.0.23.Final.jar
136
- - classpath/aws-java-sdk-1.7.4.jar
137
- - classpath/htrace-core-3.1.0-incubating.jar
138
- - classpath/jsr305-3.0.0.jar
139
- - classpath/curator-client-2.7.1.jar
153
+ - classpath/paranamer-2.3.jar
154
+ - classpath/parquet-column-1.8.1.jar
155
+ - classpath/parquet-common-1.8.1.jar
156
+ - classpath/parquet-encoding-1.8.1.jar
157
+ - classpath/parquet-format-2.3.0-incubating.jar
158
+ - classpath/parquet-hadoop-1.8.1.jar
159
+ - classpath/parquet-jackson-1.8.1.jar
160
+ - classpath/protobuf-java-2.5.0.jar
161
+ - classpath/servlet-api-2.5.jar
162
+ - classpath/snappy-java-1.1.1.6.jar
163
+ - classpath/stax-api-1.0-2.jar
164
+ - classpath/xercesImpl-2.9.1.jar
165
+ - classpath/xml-apis-1.3.04.jar
166
+ - classpath/xmlenc-0.52.jar
167
+ - classpath/xz-1.0.jar
168
+ - classpath/zookeeper-3.4.6.jar
169
+ - config/checkstyle/checkstyle.xml
170
+ - config/checkstyle/default.xml
171
+ - embulk-output-utf8parquet.iml
172
+ - gradle/wrapper/gradle-wrapper.jar
173
+ - gradle/wrapper/gradle-wrapper.properties
174
+ - gradlew
175
+ - gradlew.bat
176
+ - lib/embulk/output/utf8parquet.rb
177
+ - src/main/java/org/embulk/output/EmbulkWriteSupport.java
178
+ - src/main/java/org/embulk/output/EmbulkWriterBuilder.java
179
+ - src/main/java/org/embulk/output/ParquetOutputPlugin.java
180
+ - src/test/java/org/embulk/output/ParquetOutputPluginTest.java
181
+ - classpath/embulk-output-utf8parquet-1.0.2.jar
140
182
  homepage: https://github.com/alexopoulos7/embulk-output-utf8parquet
141
183
  licenses:
142
184
  - MIT