embulk-output-elasticsearch 0.1.0

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.
checksums.yaml ADDED
@@ -0,0 +1,7 @@
1
+ ---
2
+ SHA1:
3
+ metadata.gz: 81f91426171815e966260af0bc33010a33d6751a
4
+ data.tar.gz: 714ef2ccf5d6482e71f456bf882248aace621d1e
5
+ SHA512:
6
+ metadata.gz: ce73b2bc564f308d70f5f2b33e4c7d52760c2a1afc07edd7f4be8b49b705a22ee2f1e8ed649961ef26ca5f7a57de1ff9ac925bee3f9564296da6b9728d44b5c3
7
+ data.tar.gz: f763815c3f63f6115a03c62c4e13c36e8ad7420118f80e9640704527cc986cebbf32311fea9e350150a2c28eed5403d8dff76324a16e273d532d43a878d35cc9
data/.gitignore ADDED
@@ -0,0 +1,7 @@
1
+ *~
2
+ *.iml
3
+ .idea
4
+ build/
5
+ /classpath/
6
+ /.gradle
7
+ /pkg/
data/README.md ADDED
@@ -0,0 +1,30 @@
1
+ # Elasticsearch output plugin for Embulk
2
+
3
+ ## Overview
4
+
5
+ * **Plugin type**: output
6
+ * **Rollback supported**: no
7
+ * **Resume supported**: no
8
+ * **Cleanup supported**: no
9
+
10
+ ## Configuration
11
+
12
+ - **cluster**: cluster name (string, default: 'elasticsearch')
13
+ - **index_name**: index name (string, required)
14
+ - **index_type**: index type (string, required)
15
+
16
+ ## Example
17
+
18
+ ```yaml
19
+ out:
20
+ type: elasticsearch
21
+ cluster: elasticsearch
22
+ index_name: embulk
23
+ index_type: embulk
24
+ ```
25
+
26
+ ## Build
27
+
28
+ ```
29
+ $ ./gradlew gem
30
+ ```
data/build.gradle ADDED
@@ -0,0 +1,66 @@
1
+ plugins {
2
+ id "com.jfrog.bintray" version "1.1"
3
+ id "com.github.jruby-gradle.base" version "0.1.5"
4
+ id "java"
5
+ }
6
+ import com.github.jrubygradle.JRubyExec
7
+ repositories {
8
+ mavenCentral()
9
+ jcenter()
10
+ mavenLocal()
11
+ }
12
+ configurations {
13
+ provided
14
+ }
15
+
16
+ version = "0.1.0"
17
+
18
+ dependencies {
19
+ compile "org.embulk:embulk-core:0.4.0"
20
+ provided "org.embulk:embulk-core:0.4.0"
21
+ compile 'org.elasticsearch:elasticsearch:1.4.2'
22
+ testCompile "junit:junit:4.+"
23
+ testCompile "org.mockito:mockito-core:1.+"
24
+ }
25
+
26
+ task classpath(type: Copy, dependsOn: ["jar"]) {
27
+ doFirst { file("classpath").deleteDir() }
28
+ from (configurations.runtime - configurations.provided + files(jar.archivePath))
29
+ into "classpath"
30
+ }
31
+ clean { delete 'classpath' }
32
+
33
+ //task copyDependencies(type:Copy) {
34
+ // new File("$buildDir/libs/dependencies").mkdirs()
35
+ // into "$buildDir/libs/dependencies" from configurations.runtime
36
+ //}
37
+
38
+ task gem(type: JRubyExec, dependsOn: ["build", "gemspec", "classpath"]) {
39
+ jrubyArgs "-rrubygems/gem_runner", "-eGem::GemRunner.new.run(ARGV)", "build"
40
+ script "build/gemspec"
41
+ doLast { ant.move(file: "${project.name}-${project.version}.gem", todir: "pkg") }
42
+ }
43
+
44
+ task gemspec << { file("build/gemspec").write($/
45
+ Gem::Specification.new do |spec|
46
+ spec.name = "${project.name}"
47
+ spec.version = "${project.version}"
48
+ spec.authors = ["Muga Nishizawa"]
49
+ spec.summary = %[Elasticsearch output plugin for Embulk]
50
+ spec.description = %[Elasticsearch output plugin is an Embulk plugin that loads records to Elasticsearch read by any input plugins. Search the input plugins by "embulk-input" keyword.]
51
+ spec.email = ["muga.nishizawa@gmail.com"]
52
+ spec.licenses = ["Apache 2.0"]
53
+ spec.homepage = "https://github.com/muga/embulk-output-elasticsearch"
54
+
55
+ spec.files = `git ls-files`.split("\n") + Dir["classpath/*.jar"]
56
+ spec.test_files = spec.files.grep(%r"^(test|spec)/")
57
+ spec.require_paths = ["lib"]
58
+ spec.executables = spec.files.grep(%r{^bin/}).map{ |f| File.basename(f) }
59
+ spec.has_rdoc = false
60
+
61
+ spec.add_development_dependency "bundler", [">= 1.0"]
62
+ spec.add_development_dependency "rake", [">= 10.0"]
63
+ spec.add_development_dependency "test-unit", ["~> 3.0.2"]
64
+ end
65
+ /$)
66
+ }
Binary file
@@ -0,0 +1,6 @@
1
+ #Thu Feb 05 00:05:43 PST 2015
2
+ distributionBase=GRADLE_USER_HOME
3
+ distributionPath=wrapper/dists
4
+ zipStoreBase=GRADLE_USER_HOME
5
+ zipStorePath=wrapper/dists
6
+ distributionUrl=https\://services.gradle.org/distributions/gradle-2.1-bin.zip
data/gradlew ADDED
@@ -0,0 +1,164 @@
1
+ #!/usr/bin/env bash
2
+
3
+ ##############################################################################
4
+ ##
5
+ ## Gradle start up script for UN*X
6
+ ##
7
+ ##############################################################################
8
+
9
+ # Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
10
+ DEFAULT_JVM_OPTS=""
11
+
12
+ APP_NAME="Gradle"
13
+ APP_BASE_NAME=`basename "$0"`
14
+
15
+ # Use the maximum available, or set MAX_FD != -1 to use that value.
16
+ MAX_FD="maximum"
17
+
18
+ warn ( ) {
19
+ echo "$*"
20
+ }
21
+
22
+ die ( ) {
23
+ echo
24
+ echo "$*"
25
+ echo
26
+ exit 1
27
+ }
28
+
29
+ # OS specific support (must be 'true' or 'false').
30
+ cygwin=false
31
+ msys=false
32
+ darwin=false
33
+ case "`uname`" in
34
+ CYGWIN* )
35
+ cygwin=true
36
+ ;;
37
+ Darwin* )
38
+ darwin=true
39
+ ;;
40
+ MINGW* )
41
+ msys=true
42
+ ;;
43
+ esac
44
+
45
+ # For Cygwin, ensure paths are in UNIX format before anything is touched.
46
+ if $cygwin ; then
47
+ [ -n "$JAVA_HOME" ] && JAVA_HOME=`cygpath --unix "$JAVA_HOME"`
48
+ fi
49
+
50
+ # Attempt to set APP_HOME
51
+ # Resolve links: $0 may be a link
52
+ PRG="$0"
53
+ # Need this for relative symlinks.
54
+ while [ -h "$PRG" ] ; do
55
+ ls=`ls -ld "$PRG"`
56
+ link=`expr "$ls" : '.*-> \(.*\)$'`
57
+ if expr "$link" : '/.*' > /dev/null; then
58
+ PRG="$link"
59
+ else
60
+ PRG=`dirname "$PRG"`"/$link"
61
+ fi
62
+ done
63
+ SAVED="`pwd`"
64
+ cd "`dirname \"$PRG\"`/" >&-
65
+ APP_HOME="`pwd -P`"
66
+ cd "$SAVED" >&-
67
+
68
+ CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
69
+
70
+ # Determine the Java command to use to start the JVM.
71
+ if [ -n "$JAVA_HOME" ] ; then
72
+ if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
73
+ # IBM's JDK on AIX uses strange locations for the executables
74
+ JAVACMD="$JAVA_HOME/jre/sh/java"
75
+ else
76
+ JAVACMD="$JAVA_HOME/bin/java"
77
+ fi
78
+ if [ ! -x "$JAVACMD" ] ; then
79
+ die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
80
+
81
+ Please set the JAVA_HOME variable in your environment to match the
82
+ location of your Java installation."
83
+ fi
84
+ else
85
+ JAVACMD="java"
86
+ which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
87
+
88
+ Please set the JAVA_HOME variable in your environment to match the
89
+ location of your Java installation."
90
+ fi
91
+
92
+ # Increase the maximum file descriptors if we can.
93
+ if [ "$cygwin" = "false" -a "$darwin" = "false" ] ; then
94
+ MAX_FD_LIMIT=`ulimit -H -n`
95
+ if [ $? -eq 0 ] ; then
96
+ if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
97
+ MAX_FD="$MAX_FD_LIMIT"
98
+ fi
99
+ ulimit -n $MAX_FD
100
+ if [ $? -ne 0 ] ; then
101
+ warn "Could not set maximum file descriptor limit: $MAX_FD"
102
+ fi
103
+ else
104
+ warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
105
+ fi
106
+ fi
107
+
108
+ # For Darwin, add options to specify how the application appears in the dock
109
+ if $darwin; then
110
+ GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
111
+ fi
112
+
113
+ # For Cygwin, switch paths to Windows format before running java
114
+ if $cygwin ; then
115
+ APP_HOME=`cygpath --path --mixed "$APP_HOME"`
116
+ CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
117
+
118
+ # We build the pattern for arguments to be converted via cygpath
119
+ ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
120
+ SEP=""
121
+ for dir in $ROOTDIRSRAW ; do
122
+ ROOTDIRS="$ROOTDIRS$SEP$dir"
123
+ SEP="|"
124
+ done
125
+ OURCYGPATTERN="(^($ROOTDIRS))"
126
+ # Add a user-defined pattern to the cygpath arguments
127
+ if [ "$GRADLE_CYGPATTERN" != "" ] ; then
128
+ OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
129
+ fi
130
+ # Now convert the arguments - kludge to limit ourselves to /bin/sh
131
+ i=0
132
+ for arg in "$@" ; do
133
+ CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
134
+ CHECK2=`echo "$arg"|egrep -c "^-"` ### Determine if an option
135
+
136
+ if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then ### Added a condition
137
+ eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
138
+ else
139
+ eval `echo args$i`="\"$arg\""
140
+ fi
141
+ i=$((i+1))
142
+ done
143
+ case $i in
144
+ (0) set -- ;;
145
+ (1) set -- "$args0" ;;
146
+ (2) set -- "$args0" "$args1" ;;
147
+ (3) set -- "$args0" "$args1" "$args2" ;;
148
+ (4) set -- "$args0" "$args1" "$args2" "$args3" ;;
149
+ (5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
150
+ (6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
151
+ (7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
152
+ (8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
153
+ (9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
154
+ esac
155
+ fi
156
+
157
+ # Split up the JVM_OPTS And GRADLE_OPTS values into an array, following the shell quoting and substitution rules
158
+ function splitJvmOpts() {
159
+ JVM_OPTS=("$@")
160
+ }
161
+ eval splitJvmOpts $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS
162
+ JVM_OPTS[${#JVM_OPTS[*]}]="-Dorg.gradle.appname=$APP_BASE_NAME"
163
+
164
+ exec "$JAVACMD" "${JVM_OPTS[@]}" -classpath "$CLASSPATH" org.gradle.wrapper.GradleWrapperMain "$@"
data/gradlew.bat ADDED
@@ -0,0 +1,90 @@
1
+ @if "%DEBUG%" == "" @echo off
2
+ @rem ##########################################################################
3
+ @rem
4
+ @rem Gradle startup script for Windows
5
+ @rem
6
+ @rem ##########################################################################
7
+
8
+ @rem Set local scope for the variables with windows NT shell
9
+ if "%OS%"=="Windows_NT" setlocal
10
+
11
+ @rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
12
+ set DEFAULT_JVM_OPTS=
13
+
14
+ set DIRNAME=%~dp0
15
+ if "%DIRNAME%" == "" set DIRNAME=.
16
+ set APP_BASE_NAME=%~n0
17
+ set APP_HOME=%DIRNAME%
18
+
19
+ @rem Find java.exe
20
+ if defined JAVA_HOME goto findJavaFromJavaHome
21
+
22
+ set JAVA_EXE=java.exe
23
+ %JAVA_EXE% -version >NUL 2>&1
24
+ if "%ERRORLEVEL%" == "0" goto init
25
+
26
+ echo.
27
+ echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
28
+ echo.
29
+ echo Please set the JAVA_HOME variable in your environment to match the
30
+ echo location of your Java installation.
31
+
32
+ goto fail
33
+
34
+ :findJavaFromJavaHome
35
+ set JAVA_HOME=%JAVA_HOME:"=%
36
+ set JAVA_EXE=%JAVA_HOME%/bin/java.exe
37
+
38
+ if exist "%JAVA_EXE%" goto init
39
+
40
+ echo.
41
+ echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME%
42
+ echo.
43
+ echo Please set the JAVA_HOME variable in your environment to match the
44
+ echo location of your Java installation.
45
+
46
+ goto fail
47
+
48
+ :init
49
+ @rem Get command-line arguments, handling Windowz variants
50
+
51
+ if not "%OS%" == "Windows_NT" goto win9xME_args
52
+ if "%@eval[2+2]" == "4" goto 4NT_args
53
+
54
+ :win9xME_args
55
+ @rem Slurp the command line arguments.
56
+ set CMD_LINE_ARGS=
57
+ set _SKIP=2
58
+
59
+ :win9xME_args_slurp
60
+ if "x%~1" == "x" goto execute
61
+
62
+ set CMD_LINE_ARGS=%*
63
+ goto execute
64
+
65
+ :4NT_args
66
+ @rem Get arguments from the 4NT Shell from JP Software
67
+ set CMD_LINE_ARGS=%$
68
+
69
+ :execute
70
+ @rem Setup the command line
71
+
72
+ set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
73
+
74
+ @rem Execute Gradle
75
+ "%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
76
+
77
+ :end
78
+ @rem End local scope for the variables with windows NT shell
79
+ if "%ERRORLEVEL%"=="0" goto mainEnd
80
+
81
+ :fail
82
+ rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
83
+ rem the _cmd.exe /c_ return code!
84
+ if not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
85
+ exit /b 1
86
+
87
+ :mainEnd
88
+ if "%OS%"=="Windows_NT" endlocal
89
+
90
+ :omega
data/settings.gradle ADDED
@@ -0,0 +1 @@
1
+ rootProject.name = 'embulk-output-elasticsearch'
@@ -0,0 +1,351 @@
1
+ package org.embulk.output;
2
+
3
+ import com.google.common.base.Optional;
4
+ import com.google.common.base.Throwables;
5
+ import com.google.inject.Inject;
6
+ import org.elasticsearch.action.bulk.BulkItemResponse;
7
+ import org.elasticsearch.action.bulk.BulkProcessor;
8
+ import org.elasticsearch.action.bulk.BulkRequest;
9
+ import org.elasticsearch.action.bulk.BulkResponse;
10
+ import org.elasticsearch.action.index.IndexRequest;
11
+ import org.elasticsearch.client.Client;
12
+ import org.elasticsearch.client.Requests;
13
+ import org.elasticsearch.common.settings.ImmutableSettings;
14
+ import org.elasticsearch.common.settings.Settings;
15
+ import org.elasticsearch.common.xcontent.XContentBuilder;
16
+ import org.elasticsearch.common.xcontent.XContentFactory;
17
+ import org.elasticsearch.node.Node;
18
+ import org.elasticsearch.node.NodeBuilder;
19
+ import org.embulk.config.CommitReport;
20
+ import org.embulk.config.Config;
21
+ import org.embulk.config.ConfigDefault;
22
+ import org.embulk.config.ConfigDiff;
23
+ import org.embulk.config.ConfigSource;
24
+ import org.embulk.config.Task;
25
+ import org.embulk.config.TaskSource;
26
+ import org.embulk.spi.Column;
27
+ import org.embulk.spi.Exec;
28
+ import org.embulk.spi.OutputPlugin;
29
+ import org.embulk.spi.Page;
30
+ import org.embulk.spi.PageReader;
31
+ import org.embulk.spi.Schema;
32
+ import org.embulk.spi.ColumnVisitor;
33
+ import org.embulk.spi.TransactionalPageOutput;
34
+ import org.slf4j.Logger;
35
+
36
+ import java.io.IOException;
37
+ import java.util.List;
38
+ import java.util.concurrent.TimeUnit;
39
+
40
+ public class ElasticsearchOutputPlugin
41
+ implements OutputPlugin
42
+ {
43
+ public interface RunnerTask
44
+ extends Task
45
+ {
46
+ @Config("cluster")
47
+ @ConfigDefault("elasticsearch")
48
+ public String getClusterName();
49
+
50
+ @Config("index_name")
51
+ @ConfigDefault("embulk")
52
+ public String getIndex();
53
+
54
+ @Config("index_type")
55
+ @ConfigDefault("embulk")
56
+ public String getIndexType();
57
+
58
+ @Config("doc_id")
59
+ @ConfigDefault("null")
60
+ public Optional<String> getDocId();
61
+
62
+ @Config("bulk_actions")
63
+ @ConfigDefault("1000")
64
+ public int getBulkActions();
65
+
66
+ @Config("concurrent_requests")
67
+ @ConfigDefault("5")
68
+ public int getConcurrentRequests();
69
+
70
+ }
71
+
72
+ private final Logger log;
73
+
74
+ @Inject
75
+ public ElasticsearchOutputPlugin()
76
+ {
77
+ log = Exec.getLogger(getClass());
78
+ }
79
+
80
+ @Override
81
+ public ConfigDiff transaction(ConfigSource config, Schema schema,
82
+ int processorCount, Control control)
83
+ {
84
+ final RunnerTask task = config.loadConfig(RunnerTask.class);
85
+
86
+ try (Node node = createNode(task)) {
87
+ try (Client client = createClient(task, node)) {
88
+ }
89
+ }
90
+
91
+ try {
92
+ control.run(task.dump());
93
+ } catch (Exception e) {
94
+ throw Throwables.propagate(e);
95
+ }
96
+
97
+ ConfigDiff nextConfig = Exec.newConfigDiff();
98
+ return nextConfig;
99
+ }
100
+
101
+ @Override
102
+ public ConfigDiff resume(TaskSource taskSource,
103
+ Schema schema, int processorCount,
104
+ OutputPlugin.Control control)
105
+ {
106
+ // TODO
107
+ return Exec.newConfigDiff();
108
+ }
109
+
110
+ @Override
111
+ public void cleanup(TaskSource taskSource,
112
+ Schema schema, int processorCount,
113
+ List<CommitReport> successCommitReports)
114
+ { }
115
+
116
+ private Node createNode(final RunnerTask task)
117
+ {
118
+ // @see http://www.elasticsearch.org/guide/en/elasticsearch/client/java-api/current/client.html
119
+ Settings settings = ImmutableSettings.settingsBuilder()
120
+ .classLoader(Settings.class.getClassLoader())
121
+ .build();
122
+ return NodeBuilder.nodeBuilder()
123
+ .clusterName(task.getClusterName())
124
+ .settings(settings)
125
+ .node();
126
+ }
127
+
128
+ private Client createClient(final RunnerTask task, final Node node)
129
+ {
130
+ return node.client();
131
+ }
132
+
133
+ private BulkProcessor newBulkProcessor(final RunnerTask task, final Client client)
134
+ {
135
+ return BulkProcessor.builder(client, new BulkProcessor.Listener() {
136
+ @Override
137
+ public void beforeBulk(long executionId, BulkRequest request)
138
+ {
139
+ log.info("Execute {} bulk actions", request.numberOfActions());
140
+ }
141
+
142
+ @Override
143
+ public void afterBulk(long executionId, BulkRequest request, BulkResponse response)
144
+ {
145
+ if (response.hasFailures()) {
146
+ long items = 0;
147
+ if (log.isDebugEnabled()) {
148
+ for (BulkItemResponse item : response.getItems()) {
149
+ if (item.isFailed()) {
150
+ items += 1;
151
+ log.debug(" Error for {}/{}/{} for {} operation: {}",
152
+ item.getIndex(), item.getType(), item.getId(),
153
+ item.getOpType(), item.getFailureMessage());
154
+ }
155
+ }
156
+ }
157
+ log.warn("{} bulk actions failed: {}", items, response.buildFailureMessage());
158
+ } else {
159
+ log.info("{} bulk actions succeeded", request.numberOfActions());
160
+ }
161
+ }
162
+
163
+ @Override
164
+ public void afterBulk(long executionId, BulkRequest request, Throwable failure)
165
+ {
166
+ log.warn("Got the error during bulk processing", failure);
167
+ }
168
+ }).setBulkActions(task.getBulkActions())
169
+ .setConcurrentRequests(task.getConcurrentRequests())
170
+ .build();
171
+ }
172
+
173
+ @Override
174
+ public TransactionalPageOutput open(TaskSource taskSource, Schema schema,
175
+ int processorIndex)
176
+ {
177
+ final RunnerTask task = taskSource.loadTask(RunnerTask.class);
178
+
179
+ Node node = createNode(task);
180
+ Client client = createClient(task, node);
181
+ BulkProcessor bulkProcessor = newBulkProcessor(task, client);
182
+ ElasticsearchPageOutput pageOutput = new ElasticsearchPageOutput(task, node, client, bulkProcessor);
183
+ pageOutput.open(schema);
184
+ return pageOutput;
185
+ }
186
+
187
+ static class ElasticsearchPageOutput implements TransactionalPageOutput
188
+ {
189
+ private Logger log;
190
+
191
+ private Node node;
192
+ private Client client;
193
+ private BulkProcessor bulkProcessor;
194
+
195
+ private PageReader pageReader;
196
+
197
+ private final String index;
198
+ private final String indexType;
199
+ private final String docId;
200
+
201
+ ElasticsearchPageOutput(RunnerTask task, Node node, Client client,
202
+ BulkProcessor bulkProcessor)
203
+ {
204
+ this.log = Exec.getLogger(getClass());
205
+
206
+ this.node = node;
207
+ this.client = client;
208
+ this.bulkProcessor = bulkProcessor;
209
+
210
+ this.index = task.getIndex();
211
+ this.indexType = task.getIndexType();
212
+ this.docId = task.getDocId().orNull();
213
+ }
214
+
215
+ void open(final Schema schema)
216
+ {
217
+ pageReader = new PageReader(schema);
218
+ }
219
+
220
+ @Override
221
+ public void add(Page page)
222
+ {
223
+ pageReader.setPage(page);
224
+
225
+ while (pageReader.nextRecord()) {
226
+ try {
227
+ final XContentBuilder contextBuilder = XContentFactory.jsonBuilder().startObject(); // TODO reusable??
228
+ pageReader.getSchema().visitColumns(new ColumnVisitor() {
229
+ @Override
230
+ public void booleanColumn(Column column) {
231
+ try {
232
+ contextBuilder.field(column.getName(), pageReader.getBoolean(column));
233
+ } catch (IOException e) {
234
+ try {
235
+ contextBuilder.nullField(column.getName());
236
+ } catch (IOException ex) {
237
+ throw Throwables.propagate(ex);
238
+ }
239
+ }
240
+ }
241
+
242
+ @Override
243
+ public void longColumn(Column column) {
244
+ try {
245
+ contextBuilder.field(column.getName(), pageReader.getLong(column));
246
+ } catch (IOException e) {
247
+ try {
248
+ contextBuilder.nullField(column.getName());
249
+ } catch (IOException ex) {
250
+ throw Throwables.propagate(ex);
251
+ }
252
+ }
253
+ }
254
+
255
+ @Override
256
+ public void doubleColumn(Column column) {
257
+ try {
258
+ contextBuilder.field(column.getName(), pageReader.getDouble(column));
259
+ } catch (IOException e) {
260
+ try {
261
+ contextBuilder.nullField(column.getName());
262
+ } catch (IOException ex) {
263
+ throw Throwables.propagate(ex);
264
+ }
265
+ }
266
+ }
267
+
268
+ @Override
269
+ public void stringColumn(Column column) {
270
+ try {
271
+ contextBuilder.field(column.getName(), pageReader.getString(column));
272
+ } catch (IOException e) {
273
+ try {
274
+ contextBuilder.nullField(column.getName());
275
+ } catch (IOException ex) {
276
+ throw Throwables.propagate(ex);
277
+ }
278
+ }
279
+ }
280
+
281
+ @Override
282
+ public void timestampColumn(Column column) {
283
+ // TODO
284
+ }
285
+ });
286
+
287
+ contextBuilder.endObject();
288
+ bulkProcessor.add(newIndexRequest().source(contextBuilder));
289
+
290
+ } catch (IOException e) {
291
+ Throwables.propagate(e); // TODO error handling
292
+ }
293
+ }
294
+ }
295
+
296
+ private IndexRequest newIndexRequest()
297
+ {
298
+ return Requests.indexRequest(index).type(indexType).id(docId);
299
+ }
300
+
301
+ @Override
302
+ public void finish()
303
+ {
304
+ try {
305
+ bulkProcessor.flush();
306
+ } finally {
307
+ close();
308
+ }
309
+ }
310
+
311
+ @Override
312
+ public void close()
313
+ {
314
+ if (bulkProcessor != null) {
315
+ try {
316
+ while (!bulkProcessor.awaitClose(3, TimeUnit.SECONDS)) {
317
+ log.debug("wait for closing the bulk processing..");
318
+ }
319
+ } catch (InterruptedException e) {
320
+ Thread.currentThread().interrupt();
321
+ }
322
+ bulkProcessor = null;
323
+ }
324
+
325
+ if (client != null) {
326
+ client.close(); // ElasticsearchException
327
+ client = null;
328
+ }
329
+
330
+ if (node != null) {
331
+ node.close();
332
+ node = null;
333
+ }
334
+ }
335
+
336
+ @Override
337
+ public void abort()
338
+ {
339
+ // TODO do nothing
340
+ }
341
+
342
+ @Override
343
+ public CommitReport commit()
344
+ {
345
+ CommitReport report = Exec.newCommitReport();
346
+ // TODO
347
+ return report;
348
+ }
349
+
350
+ }
351
+ }
@@ -0,0 +1,31 @@
1
+ package org.embulk.output;
2
+
3
+ import com.google.common.base.Preconditions;
4
+ import com.google.common.collect.ImmutableList;
5
+ import com.google.inject.Binder;
6
+ import com.google.inject.Module;
7
+ import org.embulk.config.ConfigSource;
8
+ import org.embulk.spi.Extension;
9
+ import org.embulk.spi.OutputPlugin;
10
+
11
+ import java.util.List;
12
+
13
+ import static org.embulk.plugin.InjectedPluginSource.registerPluginTo;
14
+
15
+ public class ElasticsearchOutputPluginModule
16
+ implements Extension, Module
17
+ {
18
+
19
+ @Override
20
+ public void configure(Binder binder)
21
+ {
22
+ Preconditions.checkNotNull(binder, "binder is null.");
23
+ registerPluginTo(binder, OutputPlugin.class, "elasticsearch", ElasticsearchOutputPlugin.class);
24
+ }
25
+
26
+ @Override
27
+ public List<Module> getModules(ConfigSource systemConfig)
28
+ {
29
+ return ImmutableList.<Module>of(this);
30
+ }
31
+ }
@@ -0,0 +1 @@
1
+ org.embulk.output.ElasticsearchOutputPluginModule
@@ -0,0 +1,5 @@
1
+ package org.embulk.output;
2
+
3
+ public class TestElasticsearchOutputPlugin
4
+ {
5
+ }
metadata ADDED
@@ -0,0 +1,113 @@
1
+ --- !ruby/object:Gem::Specification
2
+ name: embulk-output-elasticsearch
3
+ version: !ruby/object:Gem::Version
4
+ version: 0.1.0
5
+ platform: ruby
6
+ authors:
7
+ - Muga Nishizawa
8
+ autorequire:
9
+ bindir: bin
10
+ cert_chain: []
11
+ date: 2015-02-16 00:00:00.000000000 Z
12
+ dependencies:
13
+ - !ruby/object:Gem::Dependency
14
+ name: bundler
15
+ version_requirements: !ruby/object:Gem::Requirement
16
+ requirements:
17
+ - - '>='
18
+ - !ruby/object:Gem::Version
19
+ version: '1.0'
20
+ requirement: !ruby/object:Gem::Requirement
21
+ requirements:
22
+ - - '>='
23
+ - !ruby/object:Gem::Version
24
+ version: '1.0'
25
+ prerelease: false
26
+ type: :development
27
+ - !ruby/object:Gem::Dependency
28
+ name: rake
29
+ version_requirements: !ruby/object:Gem::Requirement
30
+ requirements:
31
+ - - '>='
32
+ - !ruby/object:Gem::Version
33
+ version: '10.0'
34
+ requirement: !ruby/object:Gem::Requirement
35
+ requirements:
36
+ - - '>='
37
+ - !ruby/object:Gem::Version
38
+ version: '10.0'
39
+ prerelease: false
40
+ type: :development
41
+ - !ruby/object:Gem::Dependency
42
+ name: test-unit
43
+ version_requirements: !ruby/object:Gem::Requirement
44
+ requirements:
45
+ - - ~>
46
+ - !ruby/object:Gem::Version
47
+ version: 3.0.2
48
+ requirement: !ruby/object:Gem::Requirement
49
+ requirements:
50
+ - - ~>
51
+ - !ruby/object:Gem::Version
52
+ version: 3.0.2
53
+ prerelease: false
54
+ type: :development
55
+ description: Elasticsearch output plugin is an Embulk plugin that loads records to Elasticsearch read by any input plugins. Search the input plugins by "embulk-input" keyword.
56
+ email:
57
+ - muga.nishizawa@gmail.com
58
+ executables: []
59
+ extensions: []
60
+ extra_rdoc_files: []
61
+ files:
62
+ - .gitignore
63
+ - README.md
64
+ - build.gradle
65
+ - gradle/wrapper/gradle-wrapper.jar
66
+ - gradle/wrapper/gradle-wrapper.properties
67
+ - gradlew
68
+ - gradlew.bat
69
+ - settings.gradle
70
+ - src/main/java/org/embulk/output/ElasticsearchOutputPlugin.java
71
+ - src/main/java/org/embulk/output/ElasticsearchOutputPluginModule.java
72
+ - src/main/resources/META-INF/services/org.embulk.spi.Extension
73
+ - src/test/java/org/embulk/output/TestElasticsearchOutputPlugin.java
74
+ - classpath/elasticsearch-1.4.2.jar
75
+ - classpath/embulk-output-elasticsearch-0.1.0.jar
76
+ - classpath/lucene-analyzers-common-4.10.2.jar
77
+ - classpath/lucene-core-4.10.2.jar
78
+ - classpath/lucene-grouping-4.10.2.jar
79
+ - classpath/lucene-highlighter-4.10.2.jar
80
+ - classpath/lucene-join-4.10.2.jar
81
+ - classpath/lucene-memory-4.10.2.jar
82
+ - classpath/lucene-misc-4.10.2.jar
83
+ - classpath/lucene-queries-4.10.2.jar
84
+ - classpath/lucene-queryparser-4.10.2.jar
85
+ - classpath/lucene-sandbox-4.10.2.jar
86
+ - classpath/lucene-spatial-4.10.2.jar
87
+ - classpath/lucene-suggest-4.10.2.jar
88
+ - classpath/spatial4j-0.4.1.jar
89
+ homepage: https://github.com/muga/embulk-output-elasticsearch
90
+ licenses:
91
+ - Apache 2.0
92
+ metadata: {}
93
+ post_install_message:
94
+ rdoc_options: []
95
+ require_paths:
96
+ - lib
97
+ required_ruby_version: !ruby/object:Gem::Requirement
98
+ requirements:
99
+ - - '>='
100
+ - !ruby/object:Gem::Version
101
+ version: '0'
102
+ required_rubygems_version: !ruby/object:Gem::Requirement
103
+ requirements:
104
+ - - '>='
105
+ - !ruby/object:Gem::Version
106
+ version: '0'
107
+ requirements: []
108
+ rubyforge_project:
109
+ rubygems_version: 2.1.9
110
+ signing_key:
111
+ specification_version: 4
112
+ summary: Elasticsearch output plugin for Embulk
113
+ test_files: []