embulk-filter-reverse_geocoding 0.1.0

data/example/config.yml

@@ -0,0 +1,30 @@
+in:
+  type: file
+  path_prefix: /Users/devlop/github/embulk-filter-reverse_geocoding/example/test.csv
+  parser:
+    charset: UTF-8
+    newline: CRLF
+    type: csv
+    delimiter: ','
+    quote: '"'
+    escape: '"'
+    trim_if_not_quoted: false
+    skip_header_lines: 1
+    columns:
+    - {name: status, type: string}
+    - {name: address, type: string}
+    - {name: lat, type: double}
+    - {name: lon, type: double}
+filters:
+  - type: column
+    drop_columns:
+      - {name: status}
+  - type: reverse_geocoding
+    target_lon: lon
+    target_lat: lat
+    level: 5
+    output_columns:
+      - {name: pref, type: string, out: pref}
+      - {name: city, type: string, out: city}
+      - {name: hash, type: string, out: hash}
+out: {type: stdout}

data/example/test.csv

@@ -0,0 +1,9 @@
+status,address,lat,lon
+OK,東京都,1,1
+OK,東京駅,35.681298,139.766247
+OK,金閣寺,35.03937,135.729243
+OK,首里城,26.217014,127.719521
+OK,札幌市時計台,43.062562,141.35365
+OK,東京都千代田区1−1−1,35.6721277,139.75891209999997
+OK,東京都港区六本木3-2-1 六本木グランドタワー,35.6641222,139.729426
+OK,ニューヨーク,40.712784,-74.005941

data/gradle/wrapper/gradle-wrapper.properties

@@ -0,0 +1,6 @@
+#Wed Jan 13 12:41:02 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-bin.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/reverse_geocoding.rb

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

data/src/main/java/org/embulk/filter/reverse_geocoding/GeoCodeMap.java

@@ -0,0 +1,80 @@
+package org.embulk.filter.reverse_geocoding;
+
+import ch.hsr.geohash.GeoHash;
+import com.google.common.base.Strings;
+import org.h2.tools.Csv;
+
+import java.net.URL;
+import java.sql.ResultSet;
+import java.sql.ResultSetMetaData;
+import java.sql.SQLException;
+import java.util.HashMap;
+
+public class GeoCodeMap
+{
+
+    static final String LEVEL5_CSV_PATH = "jpcities-master/geohash5.csv";
+    static final String LEVEL4_CSV_PATH = "jpcities-master/geohash4.csv";
+    static HashMap<String, String[]> GEOHASH_MAP;
+    //    GeoHash, 緯度, 経度, 都道府県, 支庁, 群もしくは市, 市町村, 行政区域コード
+    //    xpsj,43.154296875,140.80078125,北海道,後志支庁,余市郡,余市町,01408
+    static int IDX_HASH = 0;
+    static int IDX_LAT = 1;
+    static int IDX_LON = 2;
+    static int IDX_PREF = 3;
+    static int IDX_BRANCH = 4;
+    static int IDX_COUNTRY = 5;
+    static int IDX_CITY = 6;
+    static int IDX_CODE = 7;
+
+    public static String convert2Pref(double lat, double lon)
+    {
+        String hash = GeoHash.geoHashStringWithCharacterPrecision(lat, lon, 5);
+        String[] s = GEOHASH_MAP.get(hash);
+        //if null throw exception ? not japanese lat/lon exception
+        return s != null ? GEOHASH_MAP.get(hash)[IDX_PREF] : "";
+    }
+
+    public static String convert2City(double lat, double lon)
+    {
+        String hash = GeoHash.geoHashStringWithCharacterPrecision(lat, lon, 5);
+        //if null throw exception ? not japanese lat/lon exception
+        String[] s = GEOHASH_MAP.get(hash);
+        if (s == null) {
+            return "";
+        }
+
+        StringBuilder sb = new StringBuilder();
+
+        for (int i = IDX_PREF; i < IDX_CITY; i++) {
+            sb.append(s[i]);
+        }
+
+        return sb.toString();
+    }
+
+    public static String convert2GeoHash(double lat, double lon)
+    {
+        return GeoHash.geoHashStringWithCharacterPrecision(lat, lon, 5);
+    }
+
+    static {
+        GEOHASH_MAP = new HashMap<>();
+        URL url = GeoCodeMap.class.getClassLoader().getResource(LEVEL5_CSV_PATH);
+        try {
+            ResultSet rs = new Csv().read(url.toString(), null, null);
+            ResultSetMetaData meta = rs.getMetaData();
+            while (rs.next()) {
+                String[] tmp = new String[meta.getColumnCount()];
+                for (int i = 0; i < meta.getColumnCount(); i++) {
+                    tmp[i] = Strings.nullToEmpty(rs.getString(i + 1));
+                }
+                GEOHASH_MAP.put(rs.getString(1), tmp);
+            }
+            rs.close();
+        }
+        catch (SQLException e) {
+            throw new RuntimeException("geohash4.csv is not found!");
+        }
+    }
+}

data/src/main/java/org/embulk/filter/reverse_geocoding/ReverseGeoCodingFilterPlugin.java

@@ -0,0 +1,266 @@
+package org.embulk.filter.reverse_geocoding;
+
+import com.google.common.base.Optional;
+import com.google.common.collect.ImmutableList;
+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.Column;
+import org.embulk.spi.ColumnVisitor;
+import org.embulk.spi.Exec;
+import org.embulk.spi.FilterPlugin;
+import org.embulk.spi.Page;
+import org.embulk.spi.PageBuilder;
+import org.embulk.spi.PageOutput;
+import org.embulk.spi.PageReader;
+import org.embulk.spi.Schema;
+import org.embulk.spi.type.Type;
+import org.embulk.spi.type.Types;
+
+import java.util.HashMap;
+import java.util.List;
+import java.util.Map;
+
+import static org.embulk.filter.reverse_geocoding.ReverseGeoCodingFilterPlugin.OutputColumnTask.TYPE_CITY;
+import static org.embulk.filter.reverse_geocoding.ReverseGeoCodingFilterPlugin.OutputColumnTask.TYPE_HASH;
+import static org.embulk.filter.reverse_geocoding.ReverseGeoCodingFilterPlugin.OutputColumnTask.TYPE_PREF;
+
+public class ReverseGeoCodingFilterPlugin
+        implements FilterPlugin
+{
+    static Schema buildOutputSchema(PluginTask task, Schema inputSchema)
+    {
+        List<OutputColumnTask> outputColumns = task.getOutputColumns();
+        ImmutableList.Builder<Column> builder = ImmutableList.builder();
+        builder.addAll(inputSchema.getColumns());
+        int i = inputSchema.getColumnCount();
+
+        for (OutputColumnTask outputColumn : outputColumns) {
+            Column column = new Column(i++, outputColumn.getName(), outputColumn.getType());
+            builder.add(column);
+        }
+
+        return new Schema(builder.build());
+    }
+
+    static Map<String, OutputColumnTask> getTaskColumnMap(List<OutputColumnTask> outputColumnTasks)
+    {
+        Map<String, OutputColumnTask> m = new HashMap<>();
+        for (OutputColumnTask columnTask : outputColumnTasks) {
+            m.put(columnTask.getName(), columnTask);
+        }
+        return m;
+    }
+
+    static Map<String, Column> getOutputSchemaMap(Schema outputSchema)
+    {
+        Map<String, Column> m = new HashMap<>();
+        for (Column column : outputSchema.getColumns()) {
+            m.put(column.getName(), column);
+        }
+        return m;
+    }
+
+    @Override
+    public void transaction(ConfigSource config, Schema inputSchema,
+            FilterPlugin.Control control)
+    {
+        PluginTask task = config.loadConfig(PluginTask.class);
+        Schema outputSchema = buildOutputSchema(task, inputSchema);
+        control.run(task.dump(), outputSchema);
+    }
+
+    @Override
+    public PageOutput open(TaskSource taskSource, final Schema inputSchema,
+            final Schema outputSchema, final PageOutput output)
+    {
+
+        final PluginTask task = taskSource.loadTask(PluginTask.class);
+
+        final Map<String, Column> outputSchemaMap = getOutputSchemaMap(outputSchema);
+
+        return new PageOutput()
+        {
+            private PageReader reader = new PageReader(inputSchema);
+            private PageBuilder builder = new PageBuilder(
+                    Exec.getBufferAllocator(), outputSchema, output);
+            private ColumnVisitorImpl visitor = new ColumnVisitorImpl(builder);
+
+            @Override
+            public void add(Page page)
+            {
+                reader.setPage(page);
+
+                while (reader.nextRecord()) {
+                    double lon = 0d;
+                    double lat = 0d;
+
+                    // get lon / lat
+                    for (Column column : inputSchema.getColumns()) {
+                        String colName = column.getName();
+                        if (colName.equals(task.getTargetLon())) {
+                            lon = reader.getDouble(column);
+                        }
+                        else if (colName.equals(task.getTargetLat())) {
+                            lat = reader.getDouble(column);
+                        }
+                        column.visit(visitor);
+                    }
+
+                    for (OutputColumnTask outputColumnTask : task.getOutputColumns()) {
+                        String name = outputColumnTask.getName();
+                        String output = outputColumnTask.getOutput(); // pref/city
+
+                        int idx = outputSchemaMap.get(name).getIndex();
+                        Type type = outputColumnTask.getType();
+
+                        if (Types.STRING.equals(type)) {
+
+                            if (output.equals(TYPE_PREF)) {
+                                builder.setString(idx, GeoCodeMap.convert2Pref(lat, lon));
+                            }
+                            else if (output.equals(TYPE_CITY)) {
+                                builder.setString(idx, GeoCodeMap.convert2City(lat, lon));
+                            }
+                            else if (output.equals(TYPE_HASH)) {
+                                builder.setString(idx, GeoCodeMap.convert2GeoHash(lat, lon));
+                            }
+                        }
+                        else if (Types.DOUBLE.equals(type)) {
+//                            builder.setDouble(idx, GeoCodeMap.convert2LatLon(hash));
+                        }
+                    }
+
+                    //visitcolumns
+                    builder.addRecord();
+                }
+            }
+
+            @Override
+            public void finish()
+            {
+                builder.finish();
+            }
+
+            @Override
+            public void close()
+            {
+                builder.close();
+            }
+
+            class ColumnVisitorImpl
+                    implements ColumnVisitor
+            {
+                private final PageBuilder builder;
+
+                ColumnVisitorImpl(PageBuilder builder)
+                {
+                    this.builder = builder;
+                }
+
+                @Override
+                public void booleanColumn(Column outputColumn)
+                {
+                    if (reader.isNull(outputColumn)) {
+                        builder.setNull(outputColumn);
+                    }
+                    else {
+                        builder.setBoolean(outputColumn, reader.getBoolean(outputColumn));
+                    }
+                }
+
+                @Override
+                public void longColumn(Column outputColumn)
+                {
+                    if (reader.isNull(outputColumn)) {
+                        builder.setNull(outputColumn);
+                    }
+                    else {
+                        builder.setLong(outputColumn, reader.getLong(outputColumn));
+                    }
+                }
+
+                @Override
+                public void doubleColumn(Column outputColumn)
+                {
+                    if (reader.isNull(outputColumn)) {
+                        builder.setNull(outputColumn);
+                    }
+                    else {
+                        builder.setDouble(outputColumn, reader.getDouble(outputColumn));
+                    }
+                }
+
+                @Override
+                public void stringColumn(Column outputColumn)
+                {
+                    if (reader.isNull(outputColumn)) {
+                        builder.setNull(outputColumn);
+                    }
+                    else {
+                        builder.setString(outputColumn, reader.getString(outputColumn));
+                    }
+                }
+
+                @Override
+                public void timestampColumn(Column outputColumn)
+                {
+                    if (reader.isNull(outputColumn)) {
+                        builder.setNull(outputColumn);
+                    }
+                    else {
+                        builder.setTimestamp(outputColumn, reader.getTimestamp(outputColumn));
+                    }
+                }
+
+                @Override
+                public void jsonColumn(Column outputColumn)
+                {
+                    if (reader.isNull(outputColumn)) {
+                        builder.setNull(outputColumn);
+                    }
+                    else {
+                        builder.setJson(outputColumn, reader.getJson(outputColumn));
+                    }
+                }
+            }
+        };
+    }
+
+    public interface PluginTask
+            extends Task
+    {
+        @Config("target_lon")
+        public String getTargetLon();
+
+        @Config("target_lat")
+        public String getTargetLat();
+
+        @Config("level")
+        @ConfigDefault("5")
+        public Optional<String> getLevel();
+
+        @Config("output_columns")
+        public List<OutputColumnTask> getOutputColumns();
+    }
+
+    public interface OutputColumnTask
+            extends Task
+    {
+        String TYPE_PREF = "pref";
+        String TYPE_CITY = "city";
+        String TYPE_HASH = "hash";
+
+        @Config("name")
+        String getName();
+
+        @Config("type")
+        Type getType();
+
+        @Config("out")
+        @ConfigDefault("pref")
+        String getOutput();
+    }
+}