embulk-filter-timestamp_hs 0.1.0

data/gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,6 @@
+#Wed Mar 02 22:27:43 JST 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/timestamp_hs.rb

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

data/performance/config_hs.yml

@@ -0,0 +1,21 @@
+in:
+  type: file
+  path_prefix: dummy
+  parser:
+    type: csv
+    columns:
+    - {name: timestamp, type: string}
+
+filters:
+  - type: timestamp_hs
+    column_options:
+      timestamp: {format: 'yyyy-MM-dd hh:mm:ss.SSS'}
+
+out:
+  type: file
+  path_prefix: out
+  file_ext: csv
+  formatter:
+    type: csv
+    column_options:
+      timestamp: {format: '%Y-%m-%d %H:%M:%S.%L'}

data/performance/config_std.yml

@@ -0,0 +1,16 @@
+in:
+  type: file
+  path_prefix: dummy
+  parser:
+    type: csv
+    columns:
+    - {name: timestamp, type: timestamp, format: '%Y-%m-%d %H:%M:%S.%L'}
+
+out:
+  type: file
+  path_prefix: out
+  file_ext: csv
+  formatter:
+    type: csv
+    column_options:
+      timestamp: {format: '%Y-%m-%d %H:%M:%S.%L'}

data/performance/generate_test_file.rb

@@ -0,0 +1,5 @@
+File::open('dummy.log', 'w') { |f|
+  (1..1000000).each {
+    f.puts(Time.now.strftime('%Y-%m-%d %H:%M:%S.%L'))
+  }
+}

data/src/main/java/org/embulk/filter/timestamp_hs/TimestampHsFilterPlugin.java

@@ -0,0 +1,210 @@
+package org.embulk.filter.timestamp_hs;
+
+import org.embulk.config.Config;
+import org.embulk.config.ConfigDefault;
+import org.embulk.config.ConfigSource;
+import org.embulk.config.Task;
+import org.embulk.config.TaskSource;
+import org.embulk.spi.*;
+import org.embulk.spi.time.Timestamp;
+import org.embulk.spi.time.TimestampFormatter;
+import org.embulk.spi.type.Types;
+import org.joda.time.DateTimeZone;
+import org.msgpack.value.Value;
+import org.slf4j.Logger;
+
+import java.text.ParseException;
+import java.text.SimpleDateFormat;
+import java.util.HashMap;
+import java.util.Map;
+
+
+public class TimestampHsFilterPlugin implements FilterPlugin {
+
+    public interface PluginTask extends Task {
+
+        @Config("default_timezone")
+        @ConfigDefault("\"UTC\"")
+        DateTimeZone getDefaultTimezone();
+
+        @Config("default_timestamp_format")
+        @ConfigDefault("\"yyyy-MM-dd hh:mm:ss\"")
+        String getDefaultTimestampFormat();
+
+        @Config("column_options")
+        Map<String, TimestampColumnOption> getColumnOptions();
+    }
+
+    public interface TimestampColumnOption
+            extends Task, TimestampFormatter.TimestampColumnOption {
+    }
+
+    private final Logger log;
+
+    public TimestampHsFilterPlugin() {
+        this.log = Exec.getLogger(TimestampHsFilterPlugin.class);
+    }
+
+    @Override
+    public void transaction(ConfigSource config,
+                            Schema inputSchema,
+                            FilterPlugin.Control control) {
+        PluginTask task = config.loadConfig(PluginTask.class);
+
+        // Validate column names.
+        for (String columnName : task.getColumnOptions().keySet()) {
+            inputSchema.lookupColumn(columnName);
+        }
+
+        Map<String, TimestampColumnOption> options = task.getColumnOptions();
+        Schema.Builder builder = Schema.builder();
+
+        // Convert type "string" to "timestamp".
+        for (Column column : inputSchema.getColumns()) {
+            if (options.containsKey(column.getName())) {
+                if (column.getType().equals(Types.STRING)) {
+                    builder.add(column.getName(), Types.TIMESTAMP);
+                } else {
+                    log.warn(String.format(
+                            "Can not convert to timestamp because '%s' is not string.",
+                            column.getName()));
+                    builder.add(column.getName(), column.getType());
+                }
+            } else {
+                builder.add(column.getName(), column.getType());
+            }
+        }
+
+        control.run(task.dump(), builder.build());
+    }
+
+    @Override
+    public PageOutput open(final TaskSource taskSource,
+                           final Schema inputSchema,
+                           final Schema outputSchema,
+                           final PageOutput output) {
+
+        PluginTask task = taskSource.loadTask(PluginTask.class);
+
+        final Map<String, SimpleDateFormat> timestampParsers
+                = generateTimestampParsers(task);
+
+        return new PageOutput() {
+            private PageReader reader = new PageReader(inputSchema);
+
+            private PageBuilder builder = new PageBuilder(
+                    Exec.getBufferAllocator(),
+                    outputSchema,
+                    output);
+
+            @Override
+            public void add(Page page) {
+                reader.setPage(page);
+                while (reader.nextRecord()) {
+                    setValues();
+                    builder.addRecord();
+                }
+            }
+
+            private void setValues() {
+                for (Column inputColumn : inputSchema.getColumns()) {
+                    setValue(inputColumn);
+                }
+            }
+
+            private void setValue(Column inputColumn) {
+                if (reader.isNull(inputColumn)) {
+                    builder.setNull(inputColumn);
+                    return;
+                }
+
+                if (timestampParsers.containsKey(inputColumn.getName())
+                        && inputColumn.getType().equals(Types.STRING)) {
+                    setTimestampFromString(inputColumn);
+                } else {
+                    setNonConvertedValue(inputColumn);
+                }
+            }
+
+            private void setNonConvertedValue(Column inputColumn) {
+                if (Types.STRING.equals(inputColumn.getType())) {
+                    final String value = reader.getString(inputColumn);
+                    builder.setString(inputColumn, value);
+                } else if (Types.BOOLEAN.equals(inputColumn.getType())) {
+                    final boolean value = reader.getBoolean(inputColumn);
+                    builder.setBoolean(inputColumn, value);
+                } else if (Types.DOUBLE.equals(inputColumn.getType())) {
+                    final double value = reader.getDouble(inputColumn);
+                    builder.setDouble(inputColumn, value);
+                } else if (Types.LONG.equals(inputColumn.getType())) {
+                    final long value = reader.getLong(inputColumn);
+                    builder.setLong(inputColumn, value);
+                } else if (Types.TIMESTAMP.equals(inputColumn.getType())) {
+                    final Timestamp value = reader.getTimestamp(inputColumn);
+                    builder.setTimestamp(inputColumn, value);
+                } else if (Types.JSON.equals(inputColumn.getType())) {
+                    final Value value = reader.getJson(inputColumn);
+                    builder.setJson(inputColumn, value);
+                } else {
+                    throw new DataException("Unexpected type:" + inputColumn.getType());
+                }
+            }
+
+            private void setTimestampFromString(Column inputColumn) {
+                String inputText = reader.getString(inputColumn);
+
+                try {
+                    SimpleDateFormat parser = timestampParsers.get(
+                            inputColumn.getName());
+
+                    Timestamp timestamp = Timestamp.ofEpochMilli(
+                            parser.parse(inputText).getTime());
+
+                    builder.setTimestamp(inputColumn, timestamp);
+
+                } catch (ParseException e) {
+                    log.warn(String.format(
+                            "Could not convert string to timestamp: '%s'",
+                            inputText));
+                    builder.setNull(inputColumn);
+                }
+            }
+
+            @Override
+            public void finish() {
+                builder.finish();
+            }
+
+            @Override
+            public void close() {
+                builder.close();
+            }
+        };
+    }
+
+    private Map<String, SimpleDateFormat> generateTimestampParsers(PluginTask task) {
+        Map<String, TimestampColumnOption> options = task.getColumnOptions();
+        Map<String, SimpleDateFormat> timestampParsers = new HashMap<>();
+
+        for (Map.Entry<String, TimestampColumnOption> entry : options.entrySet()) {
+            TimestampColumnOption option = entry.getValue();
+
+            String format;
+            DateTimeZone timezone;
+            if (option == null) {
+                format = task.getDefaultTimestampFormat();
+                timezone = task.getDefaultTimezone();
+            } else {
+                format = option.getFormat().or(task.getDefaultTimestampFormat());
+                timezone = option.getTimeZone().or(task.getDefaultTimezone());
+            }
+
+            SimpleDateFormat sdf = new SimpleDateFormat(format);
+            sdf.setTimeZone(timezone.toTimeZone());
+
+            timestampParsers.put(entry.getKey(), sdf);
+        }
+
+        return timestampParsers;
+    }
+}