embulk-input-clickhouse 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.
Binary file
@@ -0,0 +1,6 @@
1
+ #Tue Oct 02 20:27:31 JST 2018
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-4.1-all.zip
data/gradlew ADDED
@@ -0,0 +1,172 @@
1
+ #!/usr/bin/env sh
2
+
3
+ ##############################################################################
4
+ ##
5
+ ## Gradle start up script for UN*X
6
+ ##
7
+ ##############################################################################
8
+
9
+ # Attempt to set APP_HOME
10
+ # Resolve links: $0 may be a link
11
+ PRG="$0"
12
+ # Need this for relative symlinks.
13
+ while [ -h "$PRG" ] ; do
14
+ ls=`ls -ld "$PRG"`
15
+ link=`expr "$ls" : '.*-> \(.*\)$'`
16
+ if expr "$link" : '/.*' > /dev/null; then
17
+ PRG="$link"
18
+ else
19
+ PRG=`dirname "$PRG"`"/$link"
20
+ fi
21
+ done
22
+ SAVED="`pwd`"
23
+ cd "`dirname \"$PRG\"`/" >/dev/null
24
+ APP_HOME="`pwd -P`"
25
+ cd "$SAVED" >/dev/null
26
+
27
+ APP_NAME="Gradle"
28
+ APP_BASE_NAME=`basename "$0"`
29
+
30
+ # Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
31
+ DEFAULT_JVM_OPTS=""
32
+
33
+ # Use the maximum available, or set MAX_FD != -1 to use that value.
34
+ MAX_FD="maximum"
35
+
36
+ warn () {
37
+ echo "$*"
38
+ }
39
+
40
+ die () {
41
+ echo
42
+ echo "$*"
43
+ echo
44
+ exit 1
45
+ }
46
+
47
+ # OS specific support (must be 'true' or 'false').
48
+ cygwin=false
49
+ msys=false
50
+ darwin=false
51
+ nonstop=false
52
+ case "`uname`" in
53
+ CYGWIN* )
54
+ cygwin=true
55
+ ;;
56
+ Darwin* )
57
+ darwin=true
58
+ ;;
59
+ MINGW* )
60
+ msys=true
61
+ ;;
62
+ NONSTOP* )
63
+ nonstop=true
64
+ ;;
65
+ esac
66
+
67
+ CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
68
+
69
+ # Determine the Java command to use to start the JVM.
70
+ if [ -n "$JAVA_HOME" ] ; then
71
+ if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
72
+ # IBM's JDK on AIX uses strange locations for the executables
73
+ JAVACMD="$JAVA_HOME/jre/sh/java"
74
+ else
75
+ JAVACMD="$JAVA_HOME/bin/java"
76
+ fi
77
+ if [ ! -x "$JAVACMD" ] ; then
78
+ die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
79
+
80
+ Please set the JAVA_HOME variable in your environment to match the
81
+ location of your Java installation."
82
+ fi
83
+ else
84
+ JAVACMD="java"
85
+ which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
86
+
87
+ Please set the JAVA_HOME variable in your environment to match the
88
+ location of your Java installation."
89
+ fi
90
+
91
+ # Increase the maximum file descriptors if we can.
92
+ if [ "$cygwin" = "false" -a "$darwin" = "false" -a "$nonstop" = "false" ] ; then
93
+ MAX_FD_LIMIT=`ulimit -H -n`
94
+ if [ $? -eq 0 ] ; then
95
+ if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
96
+ MAX_FD="$MAX_FD_LIMIT"
97
+ fi
98
+ ulimit -n $MAX_FD
99
+ if [ $? -ne 0 ] ; then
100
+ warn "Could not set maximum file descriptor limit: $MAX_FD"
101
+ fi
102
+ else
103
+ warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
104
+ fi
105
+ fi
106
+
107
+ # For Darwin, add options to specify how the application appears in the dock
108
+ if $darwin; then
109
+ GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
110
+ fi
111
+
112
+ # For Cygwin, switch paths to Windows format before running java
113
+ if $cygwin ; then
114
+ APP_HOME=`cygpath --path --mixed "$APP_HOME"`
115
+ CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
116
+ JAVACMD=`cygpath --unix "$JAVACMD"`
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
+ # Escape application args
158
+ save () {
159
+ for i do printf %s\\n "$i" | sed "s/'/'\\\\''/g;1s/^/'/;\$s/\$/' \\\\/" ; done
160
+ echo " "
161
+ }
162
+ APP_ARGS=$(save "$@")
163
+
164
+ # Collect all arguments for the java command, following the shell quoting and substitution rules
165
+ eval set -- $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS "\"-Dorg.gradle.appname=$APP_BASE_NAME\"" -classpath "\"$CLASSPATH\"" org.gradle.wrapper.GradleWrapperMain "$APP_ARGS"
166
+
167
+ # by default we should be in the correct project dir, but when run from Finder on Mac, the cwd is wrong
168
+ if [ "$(uname)" = "Darwin" ] && [ "$HOME" = "$PWD" ]; then
169
+ cd "$(dirname "$0")"
170
+ fi
171
+
172
+ exec "$JAVACMD" "$@"
data/gradlew.bat ADDED
@@ -0,0 +1,84 @@
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
+ set DIRNAME=%~dp0
12
+ if "%DIRNAME%" == "" set DIRNAME=.
13
+ set APP_BASE_NAME=%~n0
14
+ set APP_HOME=%DIRNAME%
15
+
16
+ @rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
17
+ set DEFAULT_JVM_OPTS=
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 Windows variants
50
+
51
+ if not "%OS%" == "Windows_NT" goto win9xME_args
52
+
53
+ :win9xME_args
54
+ @rem Slurp the command line arguments.
55
+ set CMD_LINE_ARGS=
56
+ set _SKIP=2
57
+
58
+ :win9xME_args_slurp
59
+ if "x%~1" == "x" goto execute
60
+
61
+ set CMD_LINE_ARGS=%*
62
+
63
+ :execute
64
+ @rem Setup the command line
65
+
66
+ set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
67
+
68
+ @rem Execute Gradle
69
+ "%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
70
+
71
+ :end
72
+ @rem End local scope for the variables with windows NT shell
73
+ if "%ERRORLEVEL%"=="0" goto mainEnd
74
+
75
+ :fail
76
+ rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
77
+ rem the _cmd.exe /c_ return code!
78
+ if not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
79
+ exit /b 1
80
+
81
+ :mainEnd
82
+ if "%OS%"=="Windows_NT" endlocal
83
+
84
+ :omega
@@ -0,0 +1,3 @@
1
+ Embulk::JavaPlugin.register_input(
2
+ "clickhouse", "org.embulk.input.clickhouse.ClickhouseInputPlugin",
3
+ File.expand_path('../../../../classpath', __FILE__))
@@ -0,0 +1,40 @@
1
+ package org.embulk.input.clickhouse;
2
+
3
+ import org.embulk.input.clickhouse.getter.ArrayColumnGetter;
4
+ import org.embulk.input.clickhouse.getter.BigIntegerColumnGetter;
5
+ import org.embulk.input.clickhouse.getter.TupleColumnGetter;
6
+ import org.embulk.input.jdbc.AbstractJdbcInputPlugin;
7
+ import org.embulk.input.jdbc.JdbcColumn;
8
+ import org.embulk.input.jdbc.JdbcColumnOption;
9
+ import org.embulk.input.jdbc.JdbcInputConnection;
10
+ import org.embulk.input.jdbc.getter.ColumnGetter;
11
+ import org.embulk.input.jdbc.getter.ColumnGetterFactory;
12
+ import org.embulk.spi.PageBuilder;
13
+ import org.joda.time.DateTimeZone;
14
+
15
+ public class ClickHouseColumnGetterFactory extends ColumnGetterFactory
16
+ {
17
+
18
+ public ClickHouseColumnGetterFactory(PageBuilder to, DateTimeZone defaultTimeZone)
19
+ {
20
+ super(to, defaultTimeZone);
21
+ }
22
+
23
+ @Override
24
+ public ColumnGetter newColumnGetter(JdbcInputConnection con, AbstractJdbcInputPlugin.PluginTask task, JdbcColumn column, JdbcColumnOption option)
25
+ {
26
+ if (column.getTypeName().toLowerCase().equals("uint64")) {
27
+ return new BigIntegerColumnGetter(to, getToType(option), column.getTypeName());
28
+ }
29
+
30
+ if (column.getSqlType() == java.sql.Types.ARRAY) {
31
+ return new ArrayColumnGetter(to, getToType(option));
32
+ }
33
+
34
+ if (column.getTypeName().startsWith("Tuple")) {
35
+ return new TupleColumnGetter(to, getToType(option));
36
+ }
37
+
38
+ return super.newColumnGetter(con, task, column, option);
39
+ }
40
+ }
@@ -0,0 +1,15 @@
1
+ package org.embulk.input.clickhouse;
2
+
3
+ import org.embulk.input.jdbc.JdbcInputConnection;
4
+
5
+ import java.sql.Connection;
6
+ import java.sql.SQLException;
7
+
8
+ public class ClickHouseInputConnection extends JdbcInputConnection
9
+ {
10
+ public ClickHouseInputConnection(Connection connection, String schemaName)
11
+ throws SQLException
12
+ {
13
+ super(connection, schemaName);
14
+ }
15
+ }
@@ -0,0 +1,184 @@
1
+ package org.embulk.input.clickhouse;
2
+
3
+ import com.google.common.base.Optional;
4
+
5
+ import org.embulk.config.Config;
6
+ import org.embulk.config.ConfigDefault;
7
+ import org.embulk.config.ConfigDiff;
8
+ import org.embulk.config.ConfigSource;
9
+ import org.embulk.config.TaskReport;
10
+ import org.embulk.config.TaskSource;
11
+ import org.embulk.input.jdbc.AbstractJdbcInputPlugin;
12
+ import org.embulk.input.jdbc.JdbcInputConnection;
13
+ import org.embulk.input.jdbc.getter.ColumnGetterFactory;
14
+ import org.embulk.spi.InputPlugin;
15
+ import org.embulk.spi.PageBuilder;
16
+ import org.embulk.spi.PageOutput;
17
+ import org.embulk.spi.Schema;
18
+ import org.joda.time.DateTimeZone;
19
+
20
+ import java.sql.Connection;
21
+ import java.sql.DriverManager;
22
+ import java.sql.SQLException;
23
+ import java.util.List;
24
+ import java.util.Properties;
25
+
26
+ import ru.yandex.clickhouse.settings.ClickHouseConnectionSettings;
27
+
28
+ public class ClickhouseInputPlugin extends AbstractJdbcInputPlugin
29
+ {
30
+ public interface ClickHousePluginTask
31
+ extends AbstractJdbcInputPlugin.PluginTask
32
+ {
33
+ @Config("driver_path")
34
+ @ConfigDefault("null")
35
+ public Optional<String> getDriverPath();
36
+
37
+ @Config("host")
38
+ public String getHost();
39
+
40
+ @Config("port")
41
+ @ConfigDefault("8123")
42
+ public int getPort();
43
+
44
+ @Config("user")
45
+ @ConfigDefault("null")
46
+ public Optional<String> getUser();
47
+
48
+ @Config("password")
49
+ @ConfigDefault("null")
50
+ public Optional<String> getPassword();
51
+
52
+ @Config("database")
53
+ public String getDatabase();
54
+
55
+ @Config("buffer_size")
56
+ @ConfigDefault("65536")
57
+ public Optional<Integer> getBufferSize();
58
+
59
+ @Config("apache_buffer_size")
60
+ @ConfigDefault("65536")
61
+ public Optional<Integer> getApacheBufferSize();
62
+
63
+ @Config("connect_timeout")
64
+ @ConfigDefault("30000")
65
+ public int getConnectTimeout();
66
+
67
+ @Config("socket_timeout")
68
+ @ConfigDefault("10000")
69
+ public int getSocketTimeout();
70
+
71
+ /**
72
+ * Timeout for data transfer. socketTimeout + dataTransferTimeout is sent to ClickHouse as max_execution_time.
73
+ * ClickHouse rejects request execution if its time exceeds max_execution_time
74
+ */
75
+ @Config("data_transfer_timeout")
76
+ @ConfigDefault("10000")
77
+ public Optional<Integer> getDataTransferTimeout();
78
+
79
+ @Config("keep_alive_timeout")
80
+ @ConfigDefault("30000")
81
+ public Optional<Integer> getKeepAliveTimeout();
82
+ }
83
+
84
+ @Override
85
+ protected Class<? extends AbstractJdbcInputPlugin.PluginTask> getTaskClass()
86
+ {
87
+ return ClickHousePluginTask.class;
88
+ }
89
+
90
+ @Override
91
+ protected JdbcInputConnection newConnection(AbstractJdbcInputPlugin.PluginTask task) throws SQLException
92
+ {
93
+ final String driverClass = "ru.yandex.clickhouse.ClickHouseDriver";
94
+
95
+ ClickHousePluginTask t = (ClickHousePluginTask) task;
96
+
97
+ loadDriver(driverClass, t.getDriverPath());
98
+
99
+ Properties props = new Properties();
100
+ if (t.getUser().isPresent()) {
101
+ props.setProperty("user", t.getUser().get());
102
+ }
103
+ if (t.getPassword().isPresent()) {
104
+ props.setProperty("password", t.getPassword().get());
105
+ }
106
+
107
+ // ClickHouse Connection Options
108
+ if (t.getApacheBufferSize().isPresent()) {
109
+ props.setProperty(ClickHouseConnectionSettings.APACHE_BUFFER_SIZE.getKey(), String.valueOf(t.getApacheBufferSize().get())); // byte?
110
+ }
111
+ if (t.getBufferSize().isPresent()) {
112
+ props.setProperty(ClickHouseConnectionSettings.BUFFER_SIZE.getKey(), String.valueOf(t.getBufferSize().get())); // byte?
113
+ }
114
+ if (t.getDataTransferTimeout().isPresent()) {
115
+ props.setProperty(ClickHouseConnectionSettings.DATA_TRANSFER_TIMEOUT.getKey(), String.valueOf(t.getDataTransferTimeout().get())); // seconds
116
+ }
117
+ if (t.getKeepAliveTimeout().isPresent()) {
118
+ props.setProperty(ClickHouseConnectionSettings.KEEP_ALIVE_TIMEOUT.getKey(), String.valueOf(t.getKeepAliveTimeout().get())); // seconds
119
+ }
120
+
121
+ props.setProperty(ClickHouseConnectionSettings.SOCKET_TIMEOUT.getKey(), String.valueOf(t.getSocketTimeout())); // seconds
122
+ props.setProperty(ClickHouseConnectionSettings.CONNECTION_TIMEOUT.getKey(), String.valueOf(t.getConnectTimeout())); // seconds
123
+ props.putAll(t.getOptions());
124
+
125
+ final String url = String.format("jdbc:clickhouse://%s:%d/%s", t.getHost(), t.getPort(), t.getDatabase());
126
+
127
+ logConnectionProperties(url, props);
128
+
129
+ Connection con = DriverManager.getConnection(url, props);
130
+ try {
131
+ ClickHouseInputConnection c = new ClickHouseInputConnection(con, null);
132
+ con = null;
133
+ return c;
134
+ }
135
+ finally {
136
+ if (con != null) {
137
+ con.close();
138
+ }
139
+ }
140
+ }
141
+
142
+ @Override
143
+ protected ColumnGetterFactory newColumnGetterFactory(PageBuilder pageBuilder, DateTimeZone dateTimeZone)
144
+ {
145
+ return new ClickHouseColumnGetterFactory(pageBuilder, dateTimeZone);
146
+ }
147
+
148
+ @Override
149
+ public ConfigDiff transaction(ConfigSource config, InputPlugin.Control control)
150
+ {
151
+ // TBD
152
+ return super.transaction(config, control);
153
+ }
154
+
155
+ @Override
156
+ public ConfigDiff resume(TaskSource taskSource, Schema schema, int taskCount, InputPlugin.Control control)
157
+ {
158
+ // TBD
159
+ return super.resume(taskSource, schema, taskCount, control);
160
+ }
161
+
162
+ @Override
163
+ public void cleanup(TaskSource taskSource, Schema schema, int taskCount, List<TaskReport> successTaskReports)
164
+ {
165
+ //TBD
166
+ super.cleanup(taskSource, schema, taskCount, successTaskReports);
167
+ }
168
+
169
+ @Override
170
+ public TaskReport run(TaskSource taskSource, Schema schema, int taskIndex, PageOutput output)
171
+ {
172
+ PluginTask task = taskSource.loadTask(PluginTask.class);
173
+
174
+ //TBD
175
+ return super.run(taskSource, schema, taskIndex, output);
176
+ }
177
+
178
+ @Override
179
+ public ConfigDiff guess(ConfigSource config)
180
+ {
181
+ //TBD
182
+ return super.guess(config);
183
+ }
184
+ }