embulk-filter-calcite 0.1.0

data/gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,6 @@
+#Wed Nov 02 10:15:26 ICT 2016
+distributionBase=GRADLE_USER_HOME
+distributionPath=wrapper/dists
+zipStoreBase=GRADLE_USER_HOME
+zipStorePath=wrapper/dists
+distributionUrl=https\://services.gradle.org/distributions/gradle-2.10-all.zip

data/gradlew

@@ -0,0 +1,160 @@
+#!/usr/bin/env bash
+
+##############################################################################
+##
+##  Gradle start up script for UN*X
+##
+##############################################################################
+
+# Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+DEFAULT_JVM_OPTS=""
+
+APP_NAME="Gradle"
+APP_BASE_NAME=`basename "$0"`
+
+# Use the maximum available, or set MAX_FD != -1 to use that value.
+MAX_FD="maximum"
+
+warn ( ) {
+    echo "$*"
+}
+
+die ( ) {
+    echo
+    echo "$*"
+    echo
+    exit 1
+}
+
+# OS specific support (must be 'true' or 'false').
+cygwin=false
+msys=false
+darwin=false
+case "`uname`" in
+  CYGWIN* )
+    cygwin=true
+    ;;
+  Darwin* )
+    darwin=true
+    ;;
+  MINGW* )
+    msys=true
+    ;;
+esac
+
+# Attempt to set APP_HOME
+# Resolve links: $0 may be a link
+PRG="$0"
+# Need this for relative symlinks.
+while [ -h "$PRG" ] ; do
+    ls=`ls -ld "$PRG"`
+    link=`expr "$ls" : '.*-> \(.*\)$'`
+    if expr "$link" : '/.*' > /dev/null; then
+        PRG="$link"
+    else
+        PRG=`dirname "$PRG"`"/$link"
+    fi
+done
+SAVED="`pwd`"
+cd "`dirname \"$PRG\"`/" >/dev/null
+APP_HOME="`pwd -P`"
+cd "$SAVED" >/dev/null
+
+CLASSPATH=$APP_HOME/gradle/wrapper/gradle-wrapper.jar
+
+# Determine the Java command to use to start the JVM.
+if [ -n "$JAVA_HOME" ] ; then
+    if [ -x "$JAVA_HOME/jre/sh/java" ] ; then
+        # IBM's JDK on AIX uses strange locations for the executables
+        JAVACMD="$JAVA_HOME/jre/sh/java"
+    else
+        JAVACMD="$JAVA_HOME/bin/java"
+    fi
+    if [ ! -x "$JAVACMD" ] ; then
+        die "ERROR: JAVA_HOME is set to an invalid directory: $JAVA_HOME
+
+Please set the JAVA_HOME variable in your environment to match the
+location of your Java installation."
+    fi
+else
+    JAVACMD="java"
+    which java >/dev/null 2>&1 || die "ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
+
+Please set the JAVA_HOME variable in your environment to match the
+location of your Java installation."
+fi
+
+# Increase the maximum file descriptors if we can.
+if [ "$cygwin" = "false" -a "$darwin" = "false" ] ; then
+    MAX_FD_LIMIT=`ulimit -H -n`
+    if [ $? -eq 0 ] ; then
+        if [ "$MAX_FD" = "maximum" -o "$MAX_FD" = "max" ] ; then
+            MAX_FD="$MAX_FD_LIMIT"
+        fi
+        ulimit -n $MAX_FD
+        if [ $? -ne 0 ] ; then
+            warn "Could not set maximum file descriptor limit: $MAX_FD"
+        fi
+    else
+        warn "Could not query maximum file descriptor limit: $MAX_FD_LIMIT"
+    fi
+fi
+
+# For Darwin, add options to specify how the application appears in the dock
+if $darwin; then
+    GRADLE_OPTS="$GRADLE_OPTS \"-Xdock:name=$APP_NAME\" \"-Xdock:icon=$APP_HOME/media/gradle.icns\""
+fi
+
+# For Cygwin, switch paths to Windows format before running java
+if $cygwin ; then
+    APP_HOME=`cygpath --path --mixed "$APP_HOME"`
+    CLASSPATH=`cygpath --path --mixed "$CLASSPATH"`
+    JAVACMD=`cygpath --unix "$JAVACMD"`
+
+    # We build the pattern for arguments to be converted via cygpath
+    ROOTDIRSRAW=`find -L / -maxdepth 1 -mindepth 1 -type d 2>/dev/null`
+    SEP=""
+    for dir in $ROOTDIRSRAW ; do
+        ROOTDIRS="$ROOTDIRS$SEP$dir"
+        SEP="|"
+    done
+    OURCYGPATTERN="(^($ROOTDIRS))"
+    # Add a user-defined pattern to the cygpath arguments
+    if [ "$GRADLE_CYGPATTERN" != "" ] ; then
+        OURCYGPATTERN="$OURCYGPATTERN|($GRADLE_CYGPATTERN)"
+    fi
+    # Now convert the arguments - kludge to limit ourselves to /bin/sh
+    i=0
+    for arg in "$@" ; do
+        CHECK=`echo "$arg"|egrep -c "$OURCYGPATTERN" -`
+        CHECK2=`echo "$arg"|egrep -c "^-"`                                 ### Determine if an option
+
+        if [ $CHECK -ne 0 ] && [ $CHECK2 -eq 0 ] ; then                    ### Added a condition
+            eval `echo args$i`=`cygpath --path --ignore --mixed "$arg"`
+        else
+            eval `echo args$i`="\"$arg\""
+        fi
+        i=$((i+1))
+    done
+    case $i in
+        (0) set -- ;;
+        (1) set -- "$args0" ;;
+        (2) set -- "$args0" "$args1" ;;
+        (3) set -- "$args0" "$args1" "$args2" ;;
+        (4) set -- "$args0" "$args1" "$args2" "$args3" ;;
+        (5) set -- "$args0" "$args1" "$args2" "$args3" "$args4" ;;
+        (6) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" ;;
+        (7) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" ;;
+        (8) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" ;;
+        (9) set -- "$args0" "$args1" "$args2" "$args3" "$args4" "$args5" "$args6" "$args7" "$args8" ;;
+    esac
+fi
+
+# Split up the JVM_OPTS And GRADLE_OPTS values into an array, following the shell quoting and substitution rules
+function splitJvmOpts() {
+    JVM_OPTS=("$@")
+}
+eval splitJvmOpts $DEFAULT_JVM_OPTS $JAVA_OPTS $GRADLE_OPTS
+JVM_OPTS[${#JVM_OPTS[*]}]="-Dorg.gradle.appname=$APP_BASE_NAME"
+
+exec "$JAVACMD" "${JVM_OPTS[@]}" -classpath "$CLASSPATH" org.gradle.wrapper.GradleWrapperMain "$@"

data/gradlew.bat

@@ -0,0 +1,90 @@
+@if "%DEBUG%" == "" @echo off
+@rem ##########################################################################
+@rem
+@rem  Gradle startup script for Windows
+@rem
+@rem ##########################################################################
+
+@rem Set local scope for the variables with windows NT shell
+if "%OS%"=="Windows_NT" setlocal
+
+@rem Add default JVM options here. You can also use JAVA_OPTS and GRADLE_OPTS to pass JVM options to this script.
+set DEFAULT_JVM_OPTS=
+
+set DIRNAME=%~dp0
+if "%DIRNAME%" == "" set DIRNAME=.
+set APP_BASE_NAME=%~n0
+set APP_HOME=%DIRNAME%
+
+@rem Find java.exe
+if defined JAVA_HOME goto findJavaFromJavaHome
+
+set JAVA_EXE=java.exe
+%JAVA_EXE% -version >NUL 2>&1
+if "%ERRORLEVEL%" == "0" goto init
+
+echo.
+echo ERROR: JAVA_HOME is not set and no 'java' command could be found in your PATH.
+echo.
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of your Java installation.
+
+goto fail
+
+:findJavaFromJavaHome
+set JAVA_HOME=%JAVA_HOME:"=%
+set JAVA_EXE=%JAVA_HOME%/bin/java.exe
+
+if exist "%JAVA_EXE%" goto init
+
+echo.
+echo ERROR: JAVA_HOME is set to an invalid directory: %JAVA_HOME%
+echo.
+echo Please set the JAVA_HOME variable in your environment to match the
+echo location of your Java installation.
+
+goto fail
+
+:init
+@rem Get command-line arguments, handling Windowz variants
+
+if not "%OS%" == "Windows_NT" goto win9xME_args
+if "%@eval[2+2]" == "4" goto 4NT_args
+
+:win9xME_args
+@rem Slurp the command line arguments.
+set CMD_LINE_ARGS=
+set _SKIP=2
+
+:win9xME_args_slurp
+if "x%~1" == "x" goto execute
+
+set CMD_LINE_ARGS=%*
+goto execute
+
+:4NT_args
+@rem Get arguments from the 4NT Shell from JP Software
+set CMD_LINE_ARGS=%$
+
+:execute
+@rem Setup the command line
+
+set CLASSPATH=%APP_HOME%\gradle\wrapper\gradle-wrapper.jar
+
+@rem Execute Gradle
+"%JAVA_EXE%" %DEFAULT_JVM_OPTS% %JAVA_OPTS% %GRADLE_OPTS% "-Dorg.gradle.appname=%APP_BASE_NAME%" -classpath "%CLASSPATH%" org.gradle.wrapper.GradleWrapperMain %CMD_LINE_ARGS%
+
+:end
+@rem End local scope for the variables with windows NT shell
+if "%ERRORLEVEL%"=="0" goto mainEnd
+
+:fail
+rem Set variable GRADLE_EXIT_CONSOLE if you need the _script_ return code instead of
+rem the _cmd.exe /c_ return code!
+if  not "" == "%GRADLE_EXIT_CONSOLE%" exit 1
+exit /b 1
+
+:mainEnd
+if "%OS%"=="Windows_NT" endlocal
+
+:omega

data/lib/embulk/filter/calcite.rb

@@ -0,0 +1,3 @@
+Embulk::JavaPlugin.register_filter(
+  "calcite", "org.embulk.filter.calcite.CalciteFilterPlugin",
+  File.expand_path('../../../../classpath', __FILE__))

data/src/main/java/org/embulk/filter/calcite/CalciteFilterPlugin.java

@@ -0,0 +1,309 @@
+package org.embulk.filter.calcite;
+
+import com.google.common.base.Optional;
+import com.google.common.base.Throwables;
+import com.google.common.collect.ImmutableList;
+import com.google.common.collect.ImmutableMap;
+import com.google.inject.Inject;
+import org.apache.calcite.jdbc.Driver;
+import org.embulk.config.Config;
+import org.embulk.config.ConfigDefault;
+import org.embulk.config.ConfigException;
+import org.embulk.config.ConfigInject;
+import org.embulk.config.ConfigSource;
+import org.embulk.config.Task;
+import org.embulk.config.TaskSource;
+import org.embulk.filter.calcite.adapter.page.PageSchema;
+import org.embulk.filter.calcite.adapter.page.PageSchemaFactory;
+import org.embulk.filter.calcite.adapter.page.PageTable;
+import org.embulk.filter.calcite.getter.FilterColumnGetterFactory;
+import org.embulk.input.jdbc.JdbcColumn;
+import org.embulk.input.jdbc.JdbcColumnOption;
+import org.embulk.input.jdbc.JdbcSchema;
+import org.embulk.input.jdbc.getter.ColumnGetter;
+import org.embulk.input.jdbc.getter.ColumnGetterFactory;
+import org.embulk.spi.BufferAllocator;
+import org.embulk.spi.FilterPlugin;
+import org.embulk.spi.Page;
+import org.embulk.spi.PageBuilder;
+import org.embulk.spi.PageOutput;
+import org.embulk.spi.Schema;
+import org.joda.time.DateTimeZone;
+import org.slf4j.Logger;
+
+import java.sql.Connection;
+import java.sql.ResultSet;
+import java.sql.ResultSetMetaData;
+import java.sql.SQLException;
+import java.sql.Statement;
+import java.util.List;
+import java.util.Map;
+import java.util.Properties;
+
+import static java.lang.String.format;
+import static java.lang.Thread.currentThread;
+import static java.util.Locale.ENGLISH;
+import static org.embulk.spi.Exec.getLogger;
+import static org.embulk.spi.Exec.getModelManager;
+import static org.embulk.spi.Exec.newConfigSource;
+
+public class CalciteFilterPlugin
+        implements FilterPlugin
+{
+    public interface PluginTask
+            extends Task
+    {
+        @Config("query")
+        public String getQuery();
+
+        @Config("default_timezone")
+        @ConfigDefault("\"UTC\"")
+        public DateTimeZone getDefaultTimeZone();
+
+        public JdbcSchema getQuerySchema();
+        public void setQuerySchema(JdbcSchema querySchema);
+
+        // TODO support jdbc Url properties
+        // TODO support column_options: option
+        // TODO support options: option
+
+        @ConfigInject
+        public BufferAllocator getBufferAllocator();
+    }
+
+    private final Logger log;
+
+    @Inject
+    public CalciteFilterPlugin()
+    {
+        this.log = getLogger(getClass());
+    }
+
+    @Override
+    public void transaction(ConfigSource config, Schema inputSchema, FilterPlugin.Control control)
+    {
+        PluginTask task = config.loadConfig(PluginTask.class);
+        Properties props = System.getProperties(); // TODO should be configured as config option
+
+        // Set input schema in PageSchema
+        PageSchema.schema = inputSchema;
+
+        // Set page converter as TLS variable in PageTable
+        PageTable.pageConverter.set(newPageConverter(task, inputSchema));
+        try {
+            JdbcSchema querySchema;
+            try (Connection conn = newConnection(props)) { // SQLException thrown by conn.close()
+                querySchema = getQuerySchema(task, conn);
+                task.setQuerySchema(querySchema);
+            }
+            catch (SQLException e) {
+                throw Throwables.propagate(e);
+            }
+
+            control.run(task.dump(), buildOutputSchema(task, querySchema));
+        }
+        finally {
+            PageTable.pageConverter.remove();
+        }
+    }
+
+    private PageConverter newPageConverter(PluginTask task, Schema inputSchema)
+    {
+        return new PageConverter(inputSchema, task.getDefaultTimeZone().toTimeZone());
+    }
+
+    private Connection newConnection(Properties props)
+    {
+        String jdbcUrl = buildJdbcUrl();
+        try {
+            // Relax case-sensitive
+            // @see https://calcite.apache.org/docs/adapter.html#jdbc-connect-string-parameters
+            props.setProperty("caseSensitive", "false");
+            return new Driver().connect(jdbcUrl, props);
+        }
+        catch (SQLException e) {
+            String message = format(ENGLISH, "Cannot create connections by Jdbc URL: %s", jdbcUrl);
+            throw new IllegalStateException(message, e);
+        }
+    }
+
+    private String buildJdbcUrl()
+    {
+        // build a json model to apply Page storage adaptor
+        // @see https://github.com/apache/calcite/blob/master/example/csv/src/test/resources/model.json
+        ImmutableMap.Builder<String, Object> map = ImmutableMap.builder();
+        map.put("version", "1.0");
+        map.put("defaultSchema", "page");
+        map.put("schemas", ImmutableList.<Map<String, String>>of(
+                ImmutableMap.of(
+                        "name", "page",
+                        "type", "custom",
+                        "factory", PageSchemaFactory.class.getName()
+                )
+        ));
+        String jsonModel = getModelManager().writeObject(map.build());
+
+        // build Jdbc URL
+        String jdbcUrl = format(ENGLISH, "jdbc:calcite:model=inline:%s", jsonModel);
+        log.info(format(ENGLISH, "Generated Jdbc URL: %s", jdbcUrl));
+        return jdbcUrl;
+    }
+
+    private JdbcSchema getQuerySchema(PluginTask task, Connection conn)
+            throws SQLException
+    {
+        try (Statement stat = conn.createStatement(); // SQLException thrown by conn.close()
+                ResultSet result = executeQuery(stat, task.getQuery())) { // SQLException thrown by rs.close()
+            return getQuerySchema(result.getMetaData());
+        }
+    }
+
+    private ResultSet executeQuery(Statement stat, String query)
+    {
+        // This is a workaround to avoid NPE caused by commons-compiler v2.7.6
+        ClassLoader cl = currentThread().getContextClassLoader();
+        currentThread().setContextClassLoader(getClass().getClassLoader());
+        try {
+            return stat.executeQuery(query);
+        }
+        catch (SQLException e) {
+            throw new ConfigException("Cannot execute a query: " + query, e);
+        }
+        finally {
+            currentThread().setContextClassLoader(cl);
+        }
+    }
+
+    private JdbcSchema getQuerySchema(ResultSetMetaData metadata)
+            throws SQLException
+    {
+        ImmutableList.Builder<JdbcColumn> columns = ImmutableList.builder();
+        for (int i = 0; i < metadata.getColumnCount(); i++) {
+            int index = i + 1; // JDBC column index begins from 1
+            columns.add(new JdbcColumn(
+                    metadata.getColumnLabel(index),
+                    metadata.getColumnTypeName(index),
+                    metadata.getColumnType(index),
+                    metadata.getPrecision(index),
+                    metadata.getScale(index)));
+        }
+        return new JdbcSchema(columns.build());
+    }
+
+    private Schema buildOutputSchema(PluginTask task, JdbcSchema querySchema)
+    {
+        ColumnGetterFactory factory = newColumnGetterFactory(task, Optional.<PageBuilder>absent());
+        List<ColumnGetter> getters = newColumnGetters(factory, querySchema);
+
+        Schema.Builder schema = Schema.builder();
+        for (int i = 0; i < querySchema.getColumns().size(); i++) {
+            schema.add(querySchema.getColumn(i).getName(), getters.get(i).getToType());
+        }
+        return schema.build();
+    }
+
+    private ColumnGetterFactory newColumnGetterFactory(PluginTask task, Optional<PageBuilder> pageBuilder)
+    {
+        if (pageBuilder.isPresent()) {
+            return new FilterColumnGetterFactory(pageBuilder.get(), task.getDefaultTimeZone());
+        }
+        else {
+            return new FilterColumnGetterFactory(null, task.getDefaultTimeZone());
+        }
+    }
+
+    private List<ColumnGetter> newColumnGetters(ColumnGetterFactory factory, JdbcSchema querySchema)
+    {
+        ImmutableList.Builder<ColumnGetter> getters = ImmutableList.builder();
+        for (JdbcColumn column : querySchema.getColumns()) {
+            getters.add(factory.newColumnGetter(null, null, column, newJdbcColumnOption()));
+        }
+        return getters.build();
+    }
+
+    private JdbcColumnOption newJdbcColumnOption()
+    {
+        // TODO need to improve for supporting column_options: option
+        return newConfigSource().loadConfig(JdbcColumnOption.class);
+    }
+
+    @Override
+    public PageOutput open(TaskSource taskSource, Schema inputSchema, Schema outputSchema, PageOutput output)
+    {
+        PluginTask task = taskSource.loadTask(PluginTask.class);
+
+        // Set input schema in PageSchema for various types of executor plugins
+        PageSchema.schema = inputSchema;
+
+        PageBuilder pageBuilder = new PageBuilder(task.getBufferAllocator(), outputSchema, output);
+        PageConverter pageConverter = newPageConverter(task, inputSchema);
+        ColumnGetterFactory factory = newColumnGetterFactory(task, Optional.of(pageBuilder));
+        List<ColumnGetter> getters = newColumnGetters(factory, task.getQuerySchema());
+        Properties props = System.getProperties(); // TODO should be configured as config option
+        return new FilterPageOutput(outputSchema, task.getQuery(), pageBuilder, pageConverter, getters, props);
+    }
+
+    private class FilterPageOutput
+            implements PageOutput
+    {
+        private final Schema outputSchema;
+        private final String query;
+        private final PageBuilder pageBuilder;
+        private final PageConverter pageConverter;
+        private final List<ColumnGetter> getters;
+        private final Properties props;
+
+        private FilterPageOutput(Schema outputSchema, String query, PageBuilder pageBuilder, PageConverter pageConverter,
+                List<ColumnGetter> getters, Properties props)
+        {
+            this.outputSchema = outputSchema;
+            this.query = query;
+            this.pageBuilder = pageBuilder;
+            this.pageConverter = pageConverter;
+            this.getters = getters;
+            this.props = props;
+        }
+
+        @Override
+        public void add(Page page)
+        {
+            // Set page converter as TLS variable in PageTable
+            PageTable.pageConverter.set(pageConverter);
+
+            // Set page as TLS variable in PageTable
+            PageTable.page.set(page);
+
+            try (Connection conn = newConnection(props);
+                    Statement stat = conn.createStatement();
+                    ResultSet result = executeQuery(stat, query)) {
+
+                while (result.next()) {
+                    for (int i = 0; i < getters.size(); i++) {
+                        int index = i + 1; // JDBC column index begins from 1
+                        getters.get(i).getAndSet(result, index, outputSchema.getColumn(i));
+                    }
+                    pageBuilder.addRecord();
+                }
+            }
+            catch (SQLException e) {
+                throw Throwables.propagate(e); // TODO better exception handling? error messages?
+            }
+            finally {
+                PageTable.pageConverter.remove();
+                PageTable.page.remove();
+            }
+        }
+
+        @Override
+        public void finish()
+        {
+            pageBuilder.finish();
+        }
+
+        @Override
+        public void close()
+        {
+            pageBuilder.close();
+        }
+    }
+}