Example usage for org.apache.spark.sql.types DataTypes LongType

List of usage examples for org.apache.spark.sql.types DataTypes LongType

  1. HOME
  2. Java
  3. org.apache.spark
  4. org.apache.spark.sql.types.*
  5. DataTypes
  6. LongType

Introduction

In this page you can find the example usage for org.apache.spark.sql.types DataTypes LongType.

Prototype

DataType LongType

To view the source code for org.apache.spark.sql.types DataTypes LongType.

Click Source Link

Document

Gets the LongType object.

Usage

From source file:com.alpine.plugin.samples.ver1_0.JavaCountPlugin.CountPluginSparkJob.java

License:Open Source License

public DataFrame transform(OperatorParameters params, DataFrame inputDataFrame, SparkRuntimeUtils sparkUtils,
        OperatorListener listener) {/*from  w w w  .j  av a  2 s.  c  o  m*/
    String groupByVar = params.getTabularDatasetSelectedColumn(GroupByParamKey)._2();
    listener.notifyMessage("Starting the DataFrame Transformation");
    DataFrame selectedData = inputDataFrame.select(groupByVar);
    DataFrame df = selectedData.groupBy(groupByVar).count();

    //customize the output schema
    List<StructField> fields = new ArrayList<StructField>();
    fields.add(DataTypes.createStructField(groupByVar, DataTypes.StringType, true));
    fields.add(DataTypes.createStructField("GroupCount", DataTypes.LongType, true));
    StructType dfSchema = DataTypes.createStructType(fields);
    return inputDataFrame.sqlContext().createDataFrame(df.rdd(), dfSchema);
}

From source file:com.bosscs.spark.commons.utils.CellsUtils.java

License:Apache License

private static DataType getDataType(Object value) {
    Class cls = value.getClass();
    DataType dataType;/*  w ww.j  ava2 s  .  c  om*/
    if (cls.equals(String.class)) {
        dataType = DataTypes.StringType;
    } else if (cls.equals(Byte[].class)) {
        dataType = DataTypes.BinaryType;
    } else if (cls.equals(Boolean.class)) {
        dataType = DataTypes.BooleanType;
    } else if (cls.equals(Timestamp.class)) {
        dataType = DataTypes.TimestampType;
    } else if (cls.equals(Double.class)) {
        dataType = DataTypes.DoubleType;
    } else if (cls.equals(Float.class)) {
        dataType = DataTypes.FloatType;
    } else if (cls.equals(Byte.class)) {
        dataType = DataTypes.ByteType;
    } else if (cls.equals(Integer.class)) {
        dataType = DataTypes.IntegerType;
    } else if (cls.equals(Long.class)) {
        dataType = DataTypes.LongType;
    } else if (cls.equals(Short.class)) {
        dataType = DataTypes.ShortType;
    } else if (value instanceof List) {
        List listValue = (List) value;
        if (listValue.isEmpty()) {
            dataType = DataTypes.createArrayType(DataTypes.StringType);
        } else {
            dataType = DataTypes.createArrayType(getDataType(listValue.get(0)));
        }
    } else if (value instanceof Map) {
        Map mapValue = (Map) value;
        if (mapValue.isEmpty()) {
            dataType = DataTypes.createMapType(DataTypes.StringType, DataTypes.StringType);
        } else {
            Map.Entry entry = (Map.Entry) mapValue.entrySet().iterator().next();
            dataType = DataTypes.createMapType(getDataType(entry.getKey()), getDataType(entry.getValue()));
        }
    } else {
        dataType = DataTypes.StringType;
    }
    return dataType;
}

From source file:com.estonteco.spark.frames.conf.factory.creator.impl.AbstractDataFrameCreator.java

protected Object cast(String value, DataType dataType) {
    if (value == null || dataType == null) {
        return null;
    }//from ww  w  .  j  a  v  a2s.com
    if (dataType == DataTypes.StringType) {
        return value;
    }
    if (dataType == DataTypes.BooleanType) {
        return Boolean.valueOf(value);
    }
    if (dataType == DataTypes.ByteType) {
        return Byte.valueOf(value);
    }
    if (dataType == DataTypes.DateType) {
        try {
            return DateUtils.fromJavaDate(Date.valueOf(value));
        } catch (IllegalArgumentException ex) {
            ex.printStackTrace();
            return null;
        }
    }
    if (dataType == DataTypes.DoubleType) {
        return Double.valueOf(value);
    }
    if (dataType == DataTypes.FloatType) {
        return Float.valueOf(value);
    }
    if (dataType == DataTypes.LongType) {
        return Long.valueOf(value);
    }
    if (dataType == DataTypes.ShortType) {
        return Short.valueOf(value);
    }
    if (dataType == DataTypes.TimestampType) {
        // Throw away extra if more than 9 decimal places
        int periodIdx = value.indexOf(".");
        String str = value;
        if (periodIdx != -1 && str.length() - periodIdx > 9) {
            str = str.substring(0, periodIdx + 10);
        }
        try {
            return java.sql.Timestamp.valueOf(str);
        } catch (IllegalArgumentException ex) {
            ex.printStackTrace();
            return null;
        }
    }
    if (dataType == DataTypes.BinaryType) {
        return value.getBytes();
    }
    return null;
}

From source file:com.getcake.sparkjdbc.SparkJDBCServer.java

License:Apache License

private String loadSingleFileWithMeta(String registerTableName, String fullPathTableName, String metaFileName)
        throws IOException {
    DataFrame dynamicDataFrame;/*w  ww. jav  a  2 s  . c o m*/
    long startTime, firstStartTime;
    float durSeconds, durMinutes;
    String respMsg;

    startTime = System.currentTimeMillis();
    firstStartTime = startTime;
    try {
        dynamicDataFrame = hiveContext.table(registerTableName);
        respMsg = "table " + registerTableName + " at " + fullPathTableName + " was already loaded";
        log(respMsg);
        return respMsg;
    } catch (Throwable exc) {
        // hiveContext.table does not declare that it throws NoSuchTableException, so cannot use it in catch clause and
        // have to check for it explicitly
        if (exc instanceof NoSuchTableException) {
            respMsg = "table " + registerTableName + " at " + fullPathTableName
                    + " was not loaded => load it next";
            log(respMsg);
        } else {
            throw exc;
        }
    }

    FileInputStream propFileInputStream;
    propFileInputStream = new FileInputStream(metaFileName);
    properties = new Properties();
    properties.load(propFileInputStream);

    Stream<Entry<Object, Object>> stream = properties.entrySet().stream();
    Map<String, String> options = stream.collect(Collectors.toMap(entry -> String.valueOf(entry.getKey()),
            entry -> String.valueOf(entry.getValue())));

    int numColumns = Integer.parseInt(properties.getProperty("numColumns"));
    StructField structFields[] = new StructField[numColumns];
    String colName, colType;
    StructField structField;

    for (int i = 1; i <= numColumns; i++) {
        colName = properties.getProperty("col" + i + ".name");
        colType = properties.getProperty("col" + i + ".type");
        switch (colType) {
        case "TimeStamp":
            structField = DataTypes.createStructField(colName, DataTypes.TimestampType, true);
            break;

        case "Date":
            structField = DataTypes.createStructField(colName, DataTypes.DateType, true);
            break;

        case "Float":
            structField = DataTypes.createStructField(colName, DataTypes.FloatType, true);
            break;

        case "Integer":
            structField = DataTypes.createStructField(colName, DataTypes.IntegerType, true);
            break;

        case "Long":
            structField = DataTypes.createStructField(colName, DataTypes.LongType, true);
            break;

        case "Short":
            structField = DataTypes.createStructField(colName, DataTypes.ShortType, true);
            break;

        case "Double":
            structField = DataTypes.createStructField(colName, DataTypes.DoubleType, true);
            break;

        case "Boolean":
            structField = DataTypes.createStructField(colName, DataTypes.BooleanType, true);
            break;

        case "Binary":
            structField = DataTypes.createStructField(colName, DataTypes.BinaryType, true);
            break;

        case "Byte":
            structField = DataTypes.createStructField(colName, DataTypes.ByteType, true);
            break;

        case "Null":
            structField = DataTypes.createStructField(colName, DataTypes.NullType, true);
            break;

        default:
            structField = DataTypes.createStructField(colName, DataTypes.StringType, true);
        }

        structFields[i - 1] = structField;
    }

    // dynamicDataFrame = hiveContext.read().format("com.databricks.spark.csv").
    //   option("header", Boolean.toString(headerInCSVFileFlag)).option("inferSchema", Boolean.toString(inferSchemaFlag)).load(fullPathTableName);
    // Map<String, String> options = new HashMap<>(properties);
    options.put("path", "file:///" + fullPathTableName);
    // options.put("header", "false");
    // options.put("delimiter", ",");

    // DataType dataType = new DataType ();
    /*
    StructField structField1 = DataTypes.createStructField("LogType", DataTypes.StringType, false);
    StructField structField2 = DataTypes.createStructField("EntryTime", DataTypes.TimestampType, false);
    StructField structField3 = DataTypes.createStructField("Code_Class", DataTypes.StringType, false);
    StructField structField4 = DataTypes.createStructField("Code_Method", DataTypes.StringType, false);
    StructField structField5 = DataTypes.createStructField("Log_Message", DataTypes.StringType, false);
    structFields[0] = structField1;
    structFields[1] = structField2;
    structFields[2] = structField3;
    structFields[3] = structField4;
    structFields[4] = structField5;
    */

    StructType schema = new StructType(structFields);

    dynamicDataFrame = hiveContext.load("com.databricks.spark.csv", schema, options);

    durSeconds = (float) (System.currentTimeMillis() - startTime) / 1000F;
    durMinutes = durSeconds / 60F;
    log("loaded table " + fullPathTableName + " in seconds: " + durSeconds + " / in minutes: " + durMinutes);

    schema = dynamicDataFrame.schema();
    structFields = schema.fields();
    for (StructField structFieldLocal : structFields) {
        DataType dataType = structFieldLocal.dataType();
        logger.debug(structFieldLocal.name() + " - dataType: " + dataType.typeName());
    }

    startTime = System.currentTimeMillis();
    dynamicDataFrame.cache();
    durSeconds = (float) (System.currentTimeMillis() - startTime) / 1000F;
    durMinutes = durSeconds / 60F;
    log("cache table " + fullPathTableName + " in seconds: " + durSeconds + " / in minutes: " + durMinutes);

    startTime = System.currentTimeMillis();
    dynamicDataFrame.registerTempTable(registerTableName);

    durSeconds = (float) (System.currentTimeMillis() - startTime) / 1000F;
    durMinutes = durSeconds / 60F;
    log("registerTempTable table " + registerTableName + " in seconds: " + durSeconds + " / in minutes: "
            + durMinutes);

    durSeconds = (float) (System.currentTimeMillis() - firstStartTime) / 1000F;
    durMinutes = durSeconds / 60F;
    respMsg = "Completed loading table " + fullPathTableName + " in seconds: " + durSeconds + " / in minutes: "
            + durMinutes;
    log(respMsg);
    return respMsg;
}

From source file:com.getcake.sparkjdbc.SparkJDBCServer.java

License:Apache License

private String loadFilesWithMeta(String registerTableName, String fullPathTableName, String metaFileName,
        String fileListName) throws IOException {
    DataFrame combinedDynamicDataFrame = null, dynamicDataFrame = null;
    long startTime, firstStartTime;
    float durSeconds, durMinutes;
    String respMsg;//from   www.  j a  va  2 s .  c  o  m

    startTime = System.currentTimeMillis();
    firstStartTime = startTime;
    try {
        combinedDynamicDataFrame = hiveContext.table(registerTableName);
        respMsg = "table " + registerTableName + " at " + fullPathTableName + " was already loaded";
        log(respMsg);
        return respMsg;
    } catch (Throwable exc) {
        // hiveContext.table does not declare that it throws NoSuchTableException, so cannot use it in catch clause and
        // have to check for it explicitly
        if (exc instanceof NoSuchTableException) {
            respMsg = "table " + registerTableName + " at " + fullPathTableName
                    + " was not loaded => load it next";
            log(respMsg);
        } else {
            throw exc;
        }
    }

    FileInputStream propFileInputStream;
    propFileInputStream = new FileInputStream(metaFileName);
    properties = new Properties();
    properties.load(propFileInputStream);

    Stream<Entry<Object, Object>> stream = properties.entrySet().stream();
    Map<String, String> options = stream.collect(Collectors.toMap(entry -> String.valueOf(entry.getKey()),
            entry -> String.valueOf(entry.getValue())));

    int numColumns = Integer.parseInt(properties.getProperty("numColumns"));
    StructField structFields[] = new StructField[numColumns];
    String colName, colType;
    StructField structField;

    // structField = DataTypes.createStructField("File_Source", DataTypes.StringType, true);
    // structFields[0] = structField;

    for (int i = 1; i <= numColumns; i++) {
        colName = properties.getProperty("col" + i + ".name");
        colType = properties.getProperty("col" + i + ".type");
        switch (colType) {
        case "TimeStamp":
            structField = DataTypes.createStructField(colName, DataTypes.TimestampType, true);
            break;

        case "Date":
            structField = DataTypes.createStructField(colName, DataTypes.DateType, true);
            break;

        case "Float":
            structField = DataTypes.createStructField(colName, DataTypes.FloatType, true);
            break;

        case "Integer":
            structField = DataTypes.createStructField(colName, DataTypes.IntegerType, true);
            break;

        case "Long":
            structField = DataTypes.createStructField(colName, DataTypes.LongType, true);
            break;

        case "Short":
            structField = DataTypes.createStructField(colName, DataTypes.ShortType, true);
            break;

        case "Double":
            structField = DataTypes.createStructField(colName, DataTypes.DoubleType, true);
            break;

        case "Boolean":
            structField = DataTypes.createStructField(colName, DataTypes.BooleanType, true);
            break;

        case "Binary":
            structField = DataTypes.createStructField(colName, DataTypes.BinaryType, true);
            break;

        case "Byte":
            structField = DataTypes.createStructField(colName, DataTypes.ByteType, true);
            break;

        case "Null":
            structField = DataTypes.createStructField(colName, DataTypes.NullType, true);
            break;

        default:
            structField = DataTypes.createStructField(colName, DataTypes.StringType, true);
        }

        structFields[i - 1] = structField;
    }

    StructType schema = new StructType(structFields);

    List<String> fileLlist = new ArrayList<>();
    try (BufferedReader br = Files.newBufferedReader(Paths.get(fileListName))) {

        //br returns as stream and convert it into a List
        fileLlist = br.lines().collect(Collectors.toList());

    } catch (IOException e) {
        e.printStackTrace();
    }

    for (String file : fileLlist) {
        options.put("path", "file:///" + file);
        dynamicDataFrame = hiveContext.load("com.databricks.spark.csv", schema, options);
        if (combinedDynamicDataFrame == null) {
            combinedDynamicDataFrame = dynamicDataFrame;
        } else {
            combinedDynamicDataFrame = combinedDynamicDataFrame.unionAll(dynamicDataFrame);
        }
    }

    durSeconds = (float) (System.currentTimeMillis() - startTime) / 1000F;
    durMinutes = durSeconds / 60F;
    log("loaded table " + fullPathTableName + " in seconds: " + durSeconds + " / in minutes: " + durMinutes);

    schema = combinedDynamicDataFrame.schema();
    structFields = schema.fields();
    for (StructField structFieldLocal : structFields) {
        DataType dataType = structFieldLocal.dataType();
        logger.debug(structFieldLocal.name() + " - dataType: " + dataType.typeName());
    }

    startTime = System.currentTimeMillis();
    combinedDynamicDataFrame.cache();
    durSeconds = (float) (System.currentTimeMillis() - startTime) / 1000F;
    durMinutes = durSeconds / 60F;
    log("cache table " + fullPathTableName + " in seconds: " + durSeconds + " / in minutes: " + durMinutes);

    startTime = System.currentTimeMillis();
    combinedDynamicDataFrame.registerTempTable(registerTableName);

    durSeconds = (float) (System.currentTimeMillis() - startTime) / 1000F;
    durMinutes = durSeconds / 60F;
    log("registerTempTable table " + registerTableName + " in seconds: " + durSeconds + " / in minutes: "
            + durMinutes);

    durSeconds = (float) (System.currentTimeMillis() - firstStartTime) / 1000F;
    durMinutes = durSeconds / 60F;
    respMsg = "Completed loading table " + fullPathTableName + " in seconds: " + durSeconds + " / in minutes: "
            + durMinutes;
    log(respMsg);
    return respMsg;
}

From source file:com.github.sadikovi.riff.tree.expression.LongExpression.java

License:Open Source License

@Override
public DataType dataType() {
    return DataTypes.LongType;
}

From source file:com.splicemachine.db.iapi.types.SQLLongint.java

License:Apache License

@Override
public StructField getStructField(String columnName) {
    return DataTypes.createStructField(columnName, DataTypes.LongType, true);
}

From source file:com.splicemachine.derby.stream.spark.SparkHBaseBulkImport.java

License:Open Source License

private StructType createSchema() {
    List<StructField> fields = new ArrayList<>();
    StructField field = DataTypes.createStructField("conglomerateId", DataTypes.LongType, true);
    fields.add(field);//from   w  w  w.  j ava2s.c o  m

    field = DataTypes.createStructField("key", DataTypes.StringType, true);
    fields.add(field);

    field = DataTypes.createStructField("value", DataTypes.BinaryType, true);
    fields.add(field);

    StructType schema = DataTypes.createStructType(fields);

    return schema;
}

From source file:com.thinkbiganalytics.spark.metadata.SqlTransformStage.java

License:Apache License

/**
 * Gets the Spark SQL data type for the specified JDBC data type.
 *///w  w  w. ja  va 2s.c  o m
@Nonnull
@SuppressWarnings("squid:S1479")
private DataType getCatalystType(final int sqlType, final int precision, final int scale,
        final boolean signed) {
    switch (sqlType) {
    case Types.BINARY:
    case Types.BLOB:
    case Types.LONGVARBINARY:
    case Types.VARBINARY:
        return DataTypes.BinaryType;

    case Types.BIT:
    case Types.BOOLEAN:
        return DataTypes.BooleanType;

    case Types.DATE:
        return DataTypes.DateType;

    case Types.DECIMAL:
    case Types.NUMERIC:
        if (precision != 0 || scale != 0) {
            return new DecimalType(precision, scale);
        } else {
            return DecimalType.SYSTEM_DEFAULT();
        }

    case Types.DOUBLE:
    case Types.REAL:
        return DataTypes.DoubleType;

    case Types.FLOAT:
        return DataTypes.FloatType;

    case Types.SMALLINT:
    case Types.TINYINT:
        return DataTypes.IntegerType;

    case Types.INTEGER:
        return signed ? DataTypes.IntegerType : DataTypes.LongType;

    case Types.ROWID:
        return DataTypes.LongType;

    case Types.BIGINT:
        return signed ? DataTypes.LongType : new DecimalType(20, 0);

    case Types.CHAR:
    case Types.CLOB:
    case Types.LONGNVARCHAR:
    case Types.LONGVARCHAR:
    case Types.NCHAR:
    case Types.NCLOB:
    case Types.NVARCHAR:
    case Types.REF:
    case Types.SQLXML:
    case Types.STRUCT:
    case Types.VARCHAR:
        return DataTypes.StringType;

    case Types.TIME:
    case Types.TIMESTAMP:
        return DataTypes.TimestampType;

    default:
        log.debug("Unsupported SQL type: {}", sqlType);
        return DataTypes.StringType;
    }
}

From source file:gaffer.accumulostore.operation.spark.handler.AccumuloStoreRelation.java

License:Apache License

private static DataType getType(final String className) {
    switch (className) {
    case "java.lang.String":
        return DataTypes.StringType;
    case "java.lang.Integer":
        return DataTypes.IntegerType;
    case "java.lang.Long":
        return DataTypes.LongType;
    case "java.lang.Boolean":
        return DataTypes.BooleanType;
    case "java.lang.Double":
        return DataTypes.DoubleType;
    case "java.lang.Float":
        return DataTypes.FloatType;
    case "java.lang.Byte":
        return DataTypes.ByteType;
    case "java.lang.Short":
        return DataTypes.ShortType;
    default:/*from   w  ww. j  av  a2s .  c o  m*/
        return null;
    }
}