embulk-output-elasticsearch5 0.1.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/.gitignore +7 -0
- data/CHANGELOG.md +51 -0
- data/README.md +117 -0
- data/build.gradle +110 -0
- data/config/checkstyle/checkstyle.xml +130 -0
- data/config/checkstyle/default.xml +110 -0
- data/gradle/wrapper/gradle-wrapper.jar +0 -0
- data/gradle/wrapper/gradle-wrapper.properties +6 -0
- data/gradle/wrapper/wrapper/gradle-wrapper.jar +0 -0
- data/gradle/wrapper/wrapper/gradle-wrapper.properties +6 -0
- data/gradlew +160 -0
- data/gradlew.bat +90 -0
- data/lib/embulk/output/elasticsearch5.rb +3 -0
- data/settings.gradle +1 -0
- data/src/main/java/org/embulk/output/elasticsearch/ElasticsearchOutputPlugin.java +630 -0
- data/src/test/java/org/embulk/output/elasticsearch/TestElasticsearchOutputPlugin.java +482 -0
- data/src/test/resources/sample_01.csv +5 -0
- metadata +153 -0
Binary file
|
Binary file
|
data/gradlew
ADDED
@@ -0,0 +1,160 @@
|
|
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
|
+
# Attempt to set APP_HOME
|
46
|
+
# Resolve links: $0 may be a link
|
47
|
+
PRG="$0"
|
48
|
+
# Need this for relative symlinks.
|
49
|
+
while [ -h "$PRG" ] ; do
|
50
|
+
ls=`ls -ld "$PRG"`
|
51
|
+
link=`expr "$ls" : '.*-> \(.*\)$'`
|
52
|
+
if expr "$link" : '/.*' > /dev/null; then
|
53
|
+
PRG="$link"
|
54
|
+
else
|
55
|
+
PRG=`dirname "$PRG"`"/$link"
|
56
|
+
fi
|
57
|
+
done
|
58
|
+
SAVED="`pwd`"
|
59
|
+
cd "`dirname \"$PRG\"`/" >/dev/null
|
60
|
+
APP_HOME="`pwd -P`"
|
61
|
+
cd "$SAVED" >/dev/null
|
62
|
+
|
63
|
+
CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
|
64
|
+
|
65
|
+
# Determine the Java command to use to start the JVM.
|
66
|
+
if [ -n "$JAVA_HOME" ] ; then
|
67
|
+
if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
|
68
|
+
# IBM's JDK on AIX uses strange locations for the executables
|
69
|
+
JAVACMD="$JAVA_HOME/jre/sh/java"
|
70
|
+
else
|
71
|
+
JAVACMD="$JAVA_HOME/bin/java"
|
72
|
+
fi
|
73
|
+
if [ ! -x "$JAVACMD" ] ; then
|
74
|
+
die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
|
75
|
+
|
76
|
+
Please set the JAVA_HOME variable in your environment to match the
|
77
|
+
location of your Java installation."
|
78
|
+
fi
|
79
|
+
else
|
80
|
+
JAVACMD="java"
|
81
|
+
which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
|
82
|
+
|
83
|
+
Please set the JAVA_HOME variable in your environment to match the
|
84
|
+
location of your Java installation."
|
85
|
+
fi
|
86
|
+
|
87
|
+
# Increase the maximum file descriptors if we can.
|
88
|
+
if [ "$cygwin" = "false" -a "$darwin" = "false" ] ; then
|
89
|
+
MAX_FD_LIMIT=`ulimit -H -n`
|
90
|
+
if [ $? -eq 0 ] ; then
|
91
|
+
if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
|
92
|
+
MAX_FD="$MAX_FD_LIMIT"
|
93
|
+
fi
|
94
|
+
ulimit -n $MAX_FD
|
95
|
+
if [ $? -ne 0 ] ; then
|
96
|
+
warn "Could not set maximum file descriptor limit: $MAX_FD"
|
97
|
+
fi
|
98
|
+
else
|
99
|
+
warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
|
100
|
+
fi
|
101
|
+
fi
|
102
|
+
|
103
|
+
# For Darwin, add options to specify how the application appears in the dock
|
104
|
+
if $darwin; then
|
105
|
+
GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
|
106
|
+
fi
|
107
|
+
|
108
|
+
# For Cygwin, switch paths to Windows format before running java
|
109
|
+
if $cygwin ; then
|
110
|
+
APP_HOME=`cygpath --path --mixed "$APP_HOME"`
|
111
|
+
CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
|
112
|
+
JAVACMD=`cygpath --unix "$JAVACMD"`
|
113
|
+
|
114
|
+
# We build the pattern for arguments to be converted via cygpath
|
115
|
+
ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
|
116
|
+
SEP=""
|
117
|
+
for dir in $ROOTDIRSRAW ; do
|
118
|
+
ROOTDIRS="$ROOTDIRS$SEP$dir"
|
119
|
+
SEP="|"
|
120
|
+
done
|
121
|
+
OURCYGPATTERN="(^($ROOTDIRS))"
|
122
|
+
# Add a user-defined pattern to the cygpath arguments
|
123
|
+
if [ "$GRADLE_CYGPATTERN" != "" ] ; then
|
124
|
+
OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
|
125
|
+
fi
|
126
|
+
# Now convert the arguments - kludge to limit ourselves to /bin/sh
|
127
|
+
i=0
|
128
|
+
for arg in "$@" ; do
|
129
|
+
CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
|
130
|
+
CHECK2=`echo "$arg"|egrep -c "^-"` ### Determine if an option
|
131
|
+
|
132
|
+
if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then ### Added a condition
|
133
|
+
eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
|
134
|
+
else
|
135
|
+
eval `echo args$i`="\"$arg\""
|
136
|
+
fi
|
137
|
+
i=$((i+1))
|
138
|
+
done
|
139
|
+
case $i in
|
140
|
+
(0) set -- ;;
|
141
|
+
(1) set -- "$args0" ;;
|
142
|
+
(2) set -- "$args0" "$args1" ;;
|
143
|
+
(3) set -- "$args0" "$args1" "$args2" ;;
|
144
|
+
(4) set -- "$args0" "$args1" "$args2" "$args3" ;;
|
145
|
+
(5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
|
146
|
+
(6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
|
147
|
+
(7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
|
148
|
+
(8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
|
149
|
+
(9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
|
150
|
+
esac
|
151
|
+
fi
|
152
|
+
|
153
|
+
# Split up the JVM_OPTS And GRADLE_OPTS values into an array, following the shell quoting and substitution rules
|
154
|
+
function splitJvmOpts() {
|
155
|
+
JVM_OPTS=("$@")
|
156
|
+
}
|
157
|
+
eval splitJvmOpts $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS
|
158
|
+
JVM_OPTS[${#JVM_OPTS[*]}]="-Dorg.gradle.appname=$APP_BASE_NAME"
|
159
|
+
|
160
|
+
exec "$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-elasticsearch5'
|
@@ -0,0 +1,630 @@
|
|
1
|
+
package org.embulk.output.elasticsearch;
|
2
|
+
|
3
|
+
import com.carrotsearch.hppc.cursors.ObjectObjectCursor;
|
4
|
+
import com.fasterxml.jackson.annotation.JsonCreator;
|
5
|
+
import com.fasterxml.jackson.annotation.JsonValue;
|
6
|
+
import com.google.common.base.Optional;
|
7
|
+
import com.google.common.base.Throwables;
|
8
|
+
import com.google.inject.Inject;
|
9
|
+
import org.elasticsearch.action.admin.cluster.state.ClusterStateRequest;
|
10
|
+
import org.elasticsearch.action.admin.indices.alias.get.GetAliasesRequest;
|
11
|
+
import org.elasticsearch.action.admin.indices.delete.DeleteIndexRequest;
|
12
|
+
import org.elasticsearch.action.bulk.BulkItemResponse;
|
13
|
+
import org.elasticsearch.action.bulk.BulkProcessor;
|
14
|
+
import org.elasticsearch.action.bulk.BulkRequest;
|
15
|
+
import org.elasticsearch.action.bulk.BulkResponse;
|
16
|
+
import org.elasticsearch.action.index.IndexRequest;
|
17
|
+
import org.elasticsearch.client.Client;
|
18
|
+
import org.elasticsearch.client.Requests;
|
19
|
+
import org.elasticsearch.client.transport.NoNodeAvailableException;
|
20
|
+
import org.elasticsearch.client.transport.TransportClient;
|
21
|
+
import org.elasticsearch.cluster.metadata.AliasMetaData;
|
22
|
+
import org.elasticsearch.cluster.metadata.AliasOrIndex;
|
23
|
+
import org.elasticsearch.common.collect.ImmutableOpenMap;
|
24
|
+
import org.elasticsearch.common.settings.Settings;
|
25
|
+
import org.elasticsearch.common.transport.InetSocketTransportAddress;
|
26
|
+
import org.elasticsearch.common.unit.ByteSizeValue;
|
27
|
+
import org.elasticsearch.common.xcontent.XContentBuilder;
|
28
|
+
import org.elasticsearch.common.xcontent.XContentFactory;
|
29
|
+
import org.elasticsearch.index.IndexNotFoundException;
|
30
|
+
import org.elasticsearch.indices.InvalidAliasNameException;
|
31
|
+
import org.elasticsearch.transport.client.PreBuiltTransportClient;
|
32
|
+
import org.embulk.config.Config;
|
33
|
+
import org.embulk.config.ConfigDefault;
|
34
|
+
import org.embulk.config.ConfigDiff;
|
35
|
+
import org.embulk.config.ConfigException;
|
36
|
+
import org.embulk.config.ConfigSource;
|
37
|
+
import org.embulk.config.Task;
|
38
|
+
import org.embulk.config.TaskReport;
|
39
|
+
import org.embulk.config.TaskSource;
|
40
|
+
import org.embulk.config.UserDataException;
|
41
|
+
import org.embulk.spi.Column;
|
42
|
+
import org.embulk.spi.ColumnVisitor;
|
43
|
+
import org.embulk.spi.Exec;
|
44
|
+
import org.embulk.spi.OutputPlugin;
|
45
|
+
import org.embulk.spi.Page;
|
46
|
+
import org.embulk.spi.PageReader;
|
47
|
+
import org.embulk.spi.Schema;
|
48
|
+
import org.embulk.spi.TransactionalPageOutput;
|
49
|
+
import org.embulk.spi.time.Timestamp;
|
50
|
+
import org.embulk.spi.type.Types;
|
51
|
+
import org.slf4j.Logger;
|
52
|
+
|
53
|
+
import java.io.IOException;
|
54
|
+
import java.net.InetAddress;
|
55
|
+
import java.net.UnknownHostException;
|
56
|
+
import java.text.SimpleDateFormat;
|
57
|
+
import java.util.ArrayList;
|
58
|
+
import java.util.Date;
|
59
|
+
import java.util.List;
|
60
|
+
import java.util.Locale;
|
61
|
+
import java.util.concurrent.TimeUnit;
|
62
|
+
|
63
|
+
public class ElasticsearchOutputPlugin
|
64
|
+
implements OutputPlugin
|
65
|
+
{
|
66
|
+
public interface NodeAddressTask
|
67
|
+
extends Task
|
68
|
+
{
|
69
|
+
@Config("host")
|
70
|
+
public String getHost();
|
71
|
+
|
72
|
+
@Config("port")
|
73
|
+
@ConfigDefault("9300")
|
74
|
+
public int getPort();
|
75
|
+
}
|
76
|
+
|
77
|
+
public interface PluginTask
|
78
|
+
extends Task
|
79
|
+
{
|
80
|
+
@Config("mode")
|
81
|
+
@ConfigDefault("\"insert\"")
|
82
|
+
public Mode getMode();
|
83
|
+
|
84
|
+
@Config("nodes")
|
85
|
+
public List<NodeAddressTask> getNodes();
|
86
|
+
|
87
|
+
@Config("cluster_name")
|
88
|
+
@ConfigDefault("\"elasticsearch\"")
|
89
|
+
public String getClusterName();
|
90
|
+
|
91
|
+
@Config("index")
|
92
|
+
public String getIndex();
|
93
|
+
public void setIndex(String indexName);
|
94
|
+
|
95
|
+
@Config("pipeline")
|
96
|
+
public Optional<String> getPipeline();
|
97
|
+
|
98
|
+
@Config("alias")
|
99
|
+
@ConfigDefault("null")
|
100
|
+
public Optional<String> getAlias();
|
101
|
+
public void setAlias(Optional<String> aliasName);
|
102
|
+
|
103
|
+
@Config("index_type")
|
104
|
+
public String getType();
|
105
|
+
|
106
|
+
@Config("id")
|
107
|
+
@ConfigDefault("null")
|
108
|
+
public Optional<String> getId();
|
109
|
+
|
110
|
+
@Config("bulk_actions")
|
111
|
+
@ConfigDefault("1000")
|
112
|
+
public int getBulkActions();
|
113
|
+
|
114
|
+
@Config("bulk_size")
|
115
|
+
@ConfigDefault("5242880")
|
116
|
+
public long getBulkSize();
|
117
|
+
|
118
|
+
@Config("concurrent_requests")
|
119
|
+
@ConfigDefault("5")
|
120
|
+
public int getConcurrentRequests();
|
121
|
+
}
|
122
|
+
|
123
|
+
private final Logger log;
|
124
|
+
|
125
|
+
@Inject
|
126
|
+
public ElasticsearchOutputPlugin()
|
127
|
+
{
|
128
|
+
log = Exec.getLogger(getClass());
|
129
|
+
}
|
130
|
+
|
131
|
+
@Override
|
132
|
+
public ConfigDiff transaction(ConfigSource config, Schema schema,
|
133
|
+
int processorCount, Control control)
|
134
|
+
{
|
135
|
+
final PluginTask task = config.loadConfig(PluginTask.class);
|
136
|
+
|
137
|
+
// confirm that a client can be initialized
|
138
|
+
try (Client client = createClient(task)) {
|
139
|
+
log.info(String.format("Executing plugin with '%s' mode.", task.getMode()));
|
140
|
+
if (task.getMode().equals(Mode.REPLACE)) {
|
141
|
+
task.setAlias(Optional.of(task.getIndex()));
|
142
|
+
task.setIndex(generateNewIndexName(task.getIndex()));
|
143
|
+
if (isExistsIndex(task.getAlias().orNull(), client) && !isAlias(task.getAlias().orNull(), client)) {
|
144
|
+
throw new ConfigException(String.format("Invalid alias name [%s], an index exists with the same name as the alias", task.getAlias().orNull()));
|
145
|
+
}
|
146
|
+
}
|
147
|
+
log.info(String.format("Inserting data into index[%s]", task.getIndex()));
|
148
|
+
control.run(task.dump());
|
149
|
+
|
150
|
+
if (task.getMode().equals(Mode.REPLACE)) {
|
151
|
+
try {
|
152
|
+
reAssignAlias(task.getAlias().orNull(), task.getIndex(), client);
|
153
|
+
}
|
154
|
+
catch (IndexNotFoundException | InvalidAliasNameException e) {
|
155
|
+
throw new ConfigException(e);
|
156
|
+
}
|
157
|
+
catch (NoNodeAvailableException e) {
|
158
|
+
throw new ConnectionException(e);
|
159
|
+
}
|
160
|
+
}
|
161
|
+
} catch (Exception e) {
|
162
|
+
throw Throwables.propagate(e);
|
163
|
+
}
|
164
|
+
|
165
|
+
ConfigDiff nextConfig = Exec.newConfigDiff();
|
166
|
+
return nextConfig;
|
167
|
+
}
|
168
|
+
|
169
|
+
@Override
|
170
|
+
public ConfigDiff resume(TaskSource taskSource,
|
171
|
+
Schema schema, int processorCount,
|
172
|
+
OutputPlugin.Control control)
|
173
|
+
{
|
174
|
+
// TODO
|
175
|
+
return Exec.newConfigDiff();
|
176
|
+
}
|
177
|
+
|
178
|
+
@Override
|
179
|
+
public void cleanup(TaskSource taskSource,
|
180
|
+
Schema schema, int processorCount,
|
181
|
+
List<TaskReport> successTaskReports)
|
182
|
+
{}
|
183
|
+
|
184
|
+
private Client createClient(final PluginTask task)
|
185
|
+
{
|
186
|
+
// @see http://www.elasticsearch.org/guide/en/elasticsearch/client/java-api/current/client.html
|
187
|
+
Settings settings = Settings.builder()
|
188
|
+
.put("cluster.name", task.getClusterName())
|
189
|
+
.build();
|
190
|
+
TransportClient client = new PreBuiltTransportClient(settings);
|
191
|
+
List<NodeAddressTask> nodes = task.getNodes();
|
192
|
+
for (NodeAddressTask node : nodes) {
|
193
|
+
try {
|
194
|
+
client.addTransportAddress(new InetSocketTransportAddress(InetAddress.getByName(node.getHost()), node.getPort()));
|
195
|
+
}
|
196
|
+
catch (UnknownHostException | NoNodeAvailableException e) {
|
197
|
+
throw new ConnectionException(e);
|
198
|
+
}
|
199
|
+
}
|
200
|
+
return client;
|
201
|
+
}
|
202
|
+
|
203
|
+
private BulkProcessor newBulkProcessor(final PluginTask task, final Client client)
|
204
|
+
{
|
205
|
+
return BulkProcessor.builder(client, new BulkProcessor.Listener() {
|
206
|
+
@Override
|
207
|
+
public void beforeBulk(long executionId, BulkRequest request)
|
208
|
+
{
|
209
|
+
log.info("Execute {} bulk actions", request.numberOfActions());
|
210
|
+
}
|
211
|
+
|
212
|
+
@Override
|
213
|
+
public void afterBulk(long executionId, BulkRequest request, BulkResponse response)
|
214
|
+
{
|
215
|
+
if (response.hasFailures()) {
|
216
|
+
long items = 0;
|
217
|
+
if (log.isDebugEnabled()) {
|
218
|
+
for (BulkItemResponse item : response.getItems()) {
|
219
|
+
if (item.isFailed()) {
|
220
|
+
items += 1;
|
221
|
+
log.debug(" Error for {}/{}/{} for {} operation: {}",
|
222
|
+
item.getIndex(), item.getType(), item.getId(),
|
223
|
+
item.getOpType(), item.getFailureMessage());
|
224
|
+
}
|
225
|
+
}
|
226
|
+
}
|
227
|
+
log.warn("{} bulk actions failed: {}", items, response.buildFailureMessage());
|
228
|
+
}
|
229
|
+
else {
|
230
|
+
log.info("{} bulk actions succeeded", request.numberOfActions());
|
231
|
+
}
|
232
|
+
}
|
233
|
+
|
234
|
+
@Override
|
235
|
+
public void afterBulk(long executionId, BulkRequest request, Throwable failure)
|
236
|
+
{
|
237
|
+
if (failure.getClass() == NoNodeAvailableException.class) {
|
238
|
+
log.error("Got the error during bulk processing", failure);
|
239
|
+
throw new ConnectionException(failure);
|
240
|
+
}
|
241
|
+
else {
|
242
|
+
log.warn("Got the error during bulk processing", failure);
|
243
|
+
}
|
244
|
+
}
|
245
|
+
}).setBulkActions(task.getBulkActions())
|
246
|
+
.setBulkSize(new ByteSizeValue(task.getBulkSize()))
|
247
|
+
.setConcurrentRequests(task.getConcurrentRequests())
|
248
|
+
.build();
|
249
|
+
}
|
250
|
+
|
251
|
+
@Override
|
252
|
+
public TransactionalPageOutput open(TaskSource taskSource, Schema schema,
|
253
|
+
int processorIndex)
|
254
|
+
{
|
255
|
+
final PluginTask task = taskSource.loadTask(PluginTask.class);
|
256
|
+
Client client = createClient(task);
|
257
|
+
BulkProcessor bulkProcessor = newBulkProcessor(task, client);
|
258
|
+
ElasticsearchPageOutput pageOutput = new ElasticsearchPageOutput(task, client, bulkProcessor);
|
259
|
+
pageOutput.open(schema);
|
260
|
+
return pageOutput;
|
261
|
+
}
|
262
|
+
|
263
|
+
public static class ElasticsearchPageOutput implements TransactionalPageOutput
|
264
|
+
{
|
265
|
+
private Logger log;
|
266
|
+
|
267
|
+
private Client client;
|
268
|
+
private BulkProcessor bulkProcessor;
|
269
|
+
|
270
|
+
private PageReader pageReader;
|
271
|
+
private Column idColumn;
|
272
|
+
|
273
|
+
private final String index;
|
274
|
+
private final String type;
|
275
|
+
private final String id;
|
276
|
+
private final String pipeline;
|
277
|
+
|
278
|
+
public ElasticsearchPageOutput(PluginTask task, Client client, BulkProcessor bulkProcessor)
|
279
|
+
{
|
280
|
+
this.log = Exec.getLogger(getClass());
|
281
|
+
|
282
|
+
this.client = client;
|
283
|
+
this.bulkProcessor = bulkProcessor;
|
284
|
+
|
285
|
+
this.index = task.getIndex();
|
286
|
+
this.type = task.getType();
|
287
|
+
this.id = task.getId().orNull();
|
288
|
+
this.pipeline = task.getPipeline().orNull();
|
289
|
+
}
|
290
|
+
|
291
|
+
void open(final Schema schema)
|
292
|
+
{
|
293
|
+
pageReader = new PageReader(schema);
|
294
|
+
idColumn = (id == null) ? null : schema.lookupColumn(id);
|
295
|
+
}
|
296
|
+
|
297
|
+
@Override
|
298
|
+
public void add(Page page)
|
299
|
+
{
|
300
|
+
pageReader.setPage(page);
|
301
|
+
|
302
|
+
while (pageReader.nextRecord()) {
|
303
|
+
try {
|
304
|
+
final XContentBuilder contextBuilder = XContentFactory.jsonBuilder().startObject(); // TODO reusable??
|
305
|
+
pageReader.getSchema().visitColumns(new ColumnVisitor() {
|
306
|
+
@Override
|
307
|
+
public void booleanColumn(Column column)
|
308
|
+
{
|
309
|
+
try {
|
310
|
+
if (pageReader.isNull(column)) {
|
311
|
+
contextBuilder.nullField(column.getName());
|
312
|
+
}
|
313
|
+
else {
|
314
|
+
contextBuilder.field(column.getName(), pageReader.getBoolean(column));
|
315
|
+
}
|
316
|
+
}
|
317
|
+
catch (IOException e) {
|
318
|
+
try {
|
319
|
+
contextBuilder.nullField(column.getName());
|
320
|
+
}
|
321
|
+
catch (IOException ex) {
|
322
|
+
throw Throwables.propagate(ex);
|
323
|
+
}
|
324
|
+
}
|
325
|
+
}
|
326
|
+
|
327
|
+
@Override
|
328
|
+
public void longColumn(Column column)
|
329
|
+
{
|
330
|
+
try {
|
331
|
+
if (pageReader.isNull(column)) {
|
332
|
+
contextBuilder.nullField(column.getName());
|
333
|
+
}
|
334
|
+
else {
|
335
|
+
contextBuilder.field(column.getName(), pageReader.getLong(column));
|
336
|
+
}
|
337
|
+
}
|
338
|
+
catch (IOException e) {
|
339
|
+
try {
|
340
|
+
contextBuilder.nullField(column.getName());
|
341
|
+
}
|
342
|
+
catch (IOException ex) {
|
343
|
+
throw Throwables.propagate(ex);
|
344
|
+
}
|
345
|
+
}
|
346
|
+
}
|
347
|
+
|
348
|
+
@Override
|
349
|
+
public void doubleColumn(Column column)
|
350
|
+
{
|
351
|
+
try {
|
352
|
+
if (pageReader.isNull(column)) {
|
353
|
+
contextBuilder.nullField(column.getName());
|
354
|
+
}
|
355
|
+
else {
|
356
|
+
contextBuilder.field(column.getName(), pageReader.getDouble(column));
|
357
|
+
}
|
358
|
+
}
|
359
|
+
catch (IOException e) {
|
360
|
+
try {
|
361
|
+
contextBuilder.nullField(column.getName());
|
362
|
+
}
|
363
|
+
catch (IOException ex) {
|
364
|
+
throw Throwables.propagate(ex);
|
365
|
+
}
|
366
|
+
}
|
367
|
+
}
|
368
|
+
|
369
|
+
@Override
|
370
|
+
public void stringColumn(Column column)
|
371
|
+
{
|
372
|
+
try {
|
373
|
+
if (pageReader.isNull(column)) {
|
374
|
+
contextBuilder.nullField(column.getName());
|
375
|
+
}
|
376
|
+
else {
|
377
|
+
contextBuilder.field(column.getName(), pageReader.getString(column));
|
378
|
+
}
|
379
|
+
}
|
380
|
+
catch (IOException e) {
|
381
|
+
try {
|
382
|
+
contextBuilder.nullField(column.getName());
|
383
|
+
}
|
384
|
+
catch (IOException ex) {
|
385
|
+
throw Throwables.propagate(ex);
|
386
|
+
}
|
387
|
+
}
|
388
|
+
}
|
389
|
+
|
390
|
+
@Override
|
391
|
+
public void jsonColumn(Column column)
|
392
|
+
{
|
393
|
+
try {
|
394
|
+
if (pageReader.isNull(column)) {
|
395
|
+
contextBuilder.nullField(column.getName());
|
396
|
+
}
|
397
|
+
else {
|
398
|
+
contextBuilder.field(column.getName(), pageReader.getJson(column).toJson());
|
399
|
+
}
|
400
|
+
}
|
401
|
+
catch (IOException e) {
|
402
|
+
try {
|
403
|
+
contextBuilder.nullField(column.getName());
|
404
|
+
}
|
405
|
+
catch (IOException ex) {
|
406
|
+
throw Throwables.propagate(ex);
|
407
|
+
}
|
408
|
+
}
|
409
|
+
}
|
410
|
+
|
411
|
+
@Override
|
412
|
+
public void timestampColumn(Column column)
|
413
|
+
{
|
414
|
+
try {
|
415
|
+
if (pageReader.isNull(column)) {
|
416
|
+
contextBuilder.nullField(column.getName());
|
417
|
+
}
|
418
|
+
else {
|
419
|
+
contextBuilder.field(column.getName(), new Date(pageReader.getTimestamp(column).toEpochMilli()));
|
420
|
+
}
|
421
|
+
}
|
422
|
+
catch (IOException e) {
|
423
|
+
try {
|
424
|
+
contextBuilder.nullField(column.getName());
|
425
|
+
}
|
426
|
+
catch (IOException ex) {
|
427
|
+
throw Throwables.propagate(ex);
|
428
|
+
}
|
429
|
+
}
|
430
|
+
}
|
431
|
+
});
|
432
|
+
|
433
|
+
contextBuilder.endObject();
|
434
|
+
bulkProcessor.add(newIndexRequest(getIdValue(idColumn)).source(contextBuilder));
|
435
|
+
}
|
436
|
+
catch (ConnectionException | IOException e) {
|
437
|
+
Throwables.propagate(e); // TODO error handling
|
438
|
+
}
|
439
|
+
}
|
440
|
+
}
|
441
|
+
|
442
|
+
/**
|
443
|
+
* @param inputColumn
|
444
|
+
* @return
|
445
|
+
*/
|
446
|
+
private String getIdValue(Column inputColumn)
|
447
|
+
{
|
448
|
+
if (inputColumn == null) {
|
449
|
+
return null;
|
450
|
+
}
|
451
|
+
if (pageReader.isNull(inputColumn)) {
|
452
|
+
return null;
|
453
|
+
}
|
454
|
+
String idValue = null;
|
455
|
+
if (Types.STRING.equals(inputColumn.getType())) {
|
456
|
+
idValue = pageReader.getString(inputColumn);
|
457
|
+
}
|
458
|
+
else if (Types.BOOLEAN.equals(inputColumn.getType())) {
|
459
|
+
idValue = pageReader.getBoolean(inputColumn) + "";
|
460
|
+
}
|
461
|
+
else if (Types.DOUBLE.equals(inputColumn.getType())) {
|
462
|
+
idValue = pageReader.getDouble(inputColumn) + "";
|
463
|
+
}
|
464
|
+
else if (Types.LONG.equals(inputColumn.getType())) {
|
465
|
+
idValue = pageReader.getLong(inputColumn) + "";
|
466
|
+
}
|
467
|
+
else if (Types.JSON.equals(inputColumn.getType())) {
|
468
|
+
idValue = pageReader.getJson(inputColumn).toJson();
|
469
|
+
}
|
470
|
+
else if (Types.TIMESTAMP.equals(inputColumn.getType())) {
|
471
|
+
idValue = pageReader.getTimestamp(inputColumn).toString();
|
472
|
+
}
|
473
|
+
else {
|
474
|
+
idValue = null;
|
475
|
+
}
|
476
|
+
return idValue;
|
477
|
+
}
|
478
|
+
|
479
|
+
private IndexRequest newIndexRequest(String idValue)
|
480
|
+
{
|
481
|
+
return Requests.indexRequest(index).type(type).id(idValue).setPipeline(pipeline);
|
482
|
+
}
|
483
|
+
|
484
|
+
@Override
|
485
|
+
public void finish()
|
486
|
+
{
|
487
|
+
try {
|
488
|
+
bulkProcessor.flush();
|
489
|
+
}
|
490
|
+
finally {
|
491
|
+
close();
|
492
|
+
}
|
493
|
+
}
|
494
|
+
|
495
|
+
@Override
|
496
|
+
public void close()
|
497
|
+
{
|
498
|
+
if (bulkProcessor != null) {
|
499
|
+
try {
|
500
|
+
while (!bulkProcessor.awaitClose(3, TimeUnit.SECONDS)) {
|
501
|
+
log.debug("wait for closing the bulk processing..");
|
502
|
+
}
|
503
|
+
}
|
504
|
+
catch (InterruptedException e) {
|
505
|
+
Thread.currentThread().interrupt();
|
506
|
+
}
|
507
|
+
bulkProcessor = null;
|
508
|
+
}
|
509
|
+
|
510
|
+
if (client != null) {
|
511
|
+
client.close(); // ElasticsearchException
|
512
|
+
client = null;
|
513
|
+
}
|
514
|
+
}
|
515
|
+
|
516
|
+
@Override
|
517
|
+
public void abort()
|
518
|
+
{
|
519
|
+
// TODO do nothing
|
520
|
+
}
|
521
|
+
|
522
|
+
@Override
|
523
|
+
public TaskReport commit()
|
524
|
+
{
|
525
|
+
TaskReport report = Exec.newTaskReport();
|
526
|
+
// TODO
|
527
|
+
return report;
|
528
|
+
}
|
529
|
+
}
|
530
|
+
|
531
|
+
public enum Mode
|
532
|
+
{
|
533
|
+
INSERT,
|
534
|
+
REPLACE;
|
535
|
+
|
536
|
+
@JsonValue
|
537
|
+
@Override
|
538
|
+
public String toString()
|
539
|
+
{
|
540
|
+
return name().toLowerCase(Locale.ENGLISH);
|
541
|
+
}
|
542
|
+
|
543
|
+
@JsonCreator
|
544
|
+
public static Mode fromString(String value)
|
545
|
+
{
|
546
|
+
switch (value) {
|
547
|
+
case "insert":
|
548
|
+
return INSERT;
|
549
|
+
case "replace":
|
550
|
+
return REPLACE;
|
551
|
+
default:
|
552
|
+
throw new ConfigException(String.format("Unknown mode '%s'. Supported modes are insert, truncate_insert, replace", value));
|
553
|
+
}
|
554
|
+
}
|
555
|
+
}
|
556
|
+
|
557
|
+
private void reAssignAlias(String aliasName, String newIndexName, Client client)
|
558
|
+
throws IndexNotFoundException, InvalidAliasNameException
|
559
|
+
{
|
560
|
+
if (!isExistsAlias(aliasName, client)) {
|
561
|
+
client.admin().indices().prepareAliases()
|
562
|
+
.addAlias(newIndexName, aliasName)
|
563
|
+
.execute().actionGet();
|
564
|
+
log.info(String.format("Assigned alias[%s] to index[%s]", aliasName, newIndexName));
|
565
|
+
}
|
566
|
+
else {
|
567
|
+
List<String> oldIndices = getIndexByAlias(aliasName, client);
|
568
|
+
client.admin().indices().prepareAliases()
|
569
|
+
.removeAlias(oldIndices.toArray(new String[oldIndices.size()]), aliasName)
|
570
|
+
.addAlias(newIndexName, aliasName)
|
571
|
+
.execute().actionGet();
|
572
|
+
log.info(String.format("Reassigned alias[%s] from index%s to index[%s]", aliasName, oldIndices, newIndexName));
|
573
|
+
for (String index : oldIndices) {
|
574
|
+
deleteIndex(index, client);
|
575
|
+
}
|
576
|
+
}
|
577
|
+
}
|
578
|
+
|
579
|
+
private void deleteIndex(String indexName, Client client)
|
580
|
+
{
|
581
|
+
client.admin().indices().delete(new DeleteIndexRequest(indexName)).actionGet();
|
582
|
+
log.info(String.format("Deleted Index [%s]", indexName));
|
583
|
+
}
|
584
|
+
|
585
|
+
private List<String> getIndexByAlias(String aliasName, Client client)
|
586
|
+
{
|
587
|
+
ImmutableOpenMap<String, List<AliasMetaData>> map = client.admin().indices().getAliases(new GetAliasesRequest(aliasName))
|
588
|
+
.actionGet().getAliases();
|
589
|
+
List<String> indices = new ArrayList<>();
|
590
|
+
for (ObjectObjectCursor<String, List<AliasMetaData>> c : map) {
|
591
|
+
indices.add(c.key);
|
592
|
+
}
|
593
|
+
|
594
|
+
return indices;
|
595
|
+
}
|
596
|
+
|
597
|
+
private boolean isExistsAlias(String aliasName, Client client)
|
598
|
+
{
|
599
|
+
return client.admin().cluster().state(new ClusterStateRequest()).actionGet().getState().getMetaData().hasAlias(aliasName);
|
600
|
+
}
|
601
|
+
|
602
|
+
private boolean isExistsIndex(String indexName, Client client)
|
603
|
+
{
|
604
|
+
return client.admin().cluster().state(new ClusterStateRequest()).actionGet().getState().getMetaData().hasIndex(indexName);
|
605
|
+
}
|
606
|
+
|
607
|
+
private boolean isAlias(String aliasName, Client client)
|
608
|
+
{
|
609
|
+
AliasOrIndex aliasOrIndex = client.admin().cluster().state(new ClusterStateRequest()).actionGet().getState().getMetaData().getAliasAndIndexLookup().get(aliasName);
|
610
|
+
return aliasOrIndex != null && aliasOrIndex.isAlias();
|
611
|
+
}
|
612
|
+
|
613
|
+
public String generateNewIndexName(String indexName)
|
614
|
+
{
|
615
|
+
Timestamp time = Exec.getTransactionTime();
|
616
|
+
return indexName + new SimpleDateFormat("_yyyyMMdd-HHmmss").format(time.toEpochMilli());
|
617
|
+
}
|
618
|
+
|
619
|
+
public class ConnectionException extends RuntimeException implements UserDataException
|
620
|
+
{
|
621
|
+
protected ConnectionException()
|
622
|
+
{
|
623
|
+
}
|
624
|
+
|
625
|
+
public ConnectionException(Throwable cause)
|
626
|
+
{
|
627
|
+
super(cause);
|
628
|
+
}
|
629
|
+
}
|
630
|
+
}
|