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

Introduction

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

Prototype

DataType BinaryType

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

Click Source Link

Document

Gets the BinaryType object.

Usage

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 w  w .  j  av a  2 s.  co  m
    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;
    }// w w  w  . j a  v a 2s . c o m
    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;//from  w w  w  .j  av a2s .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 w ww .j a  va2 s .  c  om*/

    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.splicemachine.db.iapi.types.HBaseRowLocation.java

License:Open Source License

@Override
public StructField getStructField(String columnName) {
    return DataTypes.createStructField(columnName, DataTypes.BinaryType, 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);// w w  w  . j  ava 2s  .  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.
 *///from  ww  w.j a  va2s.  c  om
@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:fire.workflowengine.FireSchema.java

License:Apache License

public StructType getSparkSQLStructType() {

    List<StructField> fields = new ArrayList<StructField>();

    int idx = 0;/*from w  ww. j  av  a 2s . c  o m*/
    for (String fieldName : columnNames) {
        DataType dataType = null;

        if (columnTypes[idx] == Schema.Type.INT) {
            dataType = DataTypes.IntegerType;
        } else if (columnTypes[idx] == Schema.Type.DOUBLE) {
            dataType = DataTypes.DoubleType;
        } else if (columnTypes[idx] == Schema.Type.STRING) {
            dataType = DataTypes.StringType;
        } else if (columnTypes[idx] == Schema.Type.BYTES) {
            dataType = DataTypes.BinaryType;
        }

        fields.add(DataTypes.createStructField(fieldName, dataType, true)); // name, datatype, nullable

        idx++;
    }

    StructType structType = DataTypes.createStructType(fields);

    return structType;
}

---

From source file:org.icgc.dcc.release.job.export.util.SchemaGenerator.java

License:Open Source License

private static DataType parseDataType(String dataTypeString) {
    switch (dataTypeString) {
    case "StringType":
        return DataTypes.StringType;
    case "BinaryType":
        return DataTypes.BinaryType;
    case "BooleanType":
        return DataTypes.BooleanType;
    case "DateType":
        return DataTypes.DateType;
    case "TimestampType":
        return DataTypes.TimestampType;
    case "CalendarIntervalType":
        return DataTypes.CalendarIntervalType;
    case "DoubleType":
        return DataTypes.DoubleType;
    case "ByteType":
        return DataTypes.ByteType;
    case "IntegerType":
        return DataTypes.IntegerType;
    case "LongType":
        return DataTypes.LongType;
    case "ShortType":
        return DataTypes.ShortType;
    case "NullType":
        return DataTypes.NullType;
    default:/*  www . j av a2 s .  c  om*/
        throw new IllegalArgumentException(format("Unknown datatype %s", dataTypeString));
    }
}

---

From source file:org.wso2.carbon.analytics.engine.utils.AnalyzerEngineUtils.java

License:Open Source License

public static DataType stringToDataType(String strType) {
    switch (strType.toLowerCase(Locale.ENGLISH)) {
    case AnalyzerEngineConstants.INTEGER_TYPE:
        return DataTypes.IntegerType;
    case AnalyzerEngineConstants.INT_TYPE:
        return DataTypes.IntegerType;
    case AnalyzerEngineConstants.FLOAT_TYPE:
        return DataTypes.FloatType;
    case AnalyzerEngineConstants.DOUBLE_TYPE:
        return DataTypes.DoubleType;
    case AnalyzerEngineConstants.LONG_TYPE:
        return DataTypes.LongType;
    case AnalyzerEngineConstants.BOOLEAN_TYPE:
        return DataTypes.BooleanType;
    case AnalyzerEngineConstants.STRING_TYPE:
        return DataTypes.StringType;
    case AnalyzerEngineConstants.BINARY_TYPE:
        return DataTypes.BinaryType;
    case AnalyzerEngineConstants.FACET_TYPE:
        return DataTypes.StringType;
    default:/*from  w  w  w.  j  a v a2  s  . c om*/
        throw new RuntimeException("Invalid DataType: " + strType);
    }
}

---

• «
• 1
• 2
• »