pxf/pxf-service/src/main/resources/pxf-profiles-default.xml

<?xml version="1.0" encoding="UTF-8"?>

<!--
Licensed to the Apache Software Foundation (ASF) under one
or more contributor license agreements.  See the NOTICE file
distributed with this work for additional information
regarding copyright ownership.  The ASF licenses this file
to you under the Apache License, Version 2.0 (the
"License"); you may not use this file except in compliance
with the License.  You may obtain a copy of the License at

  http://www.apache.org/licenses/LICENSE-2.0

Unless required by applicable law or agreed to in writing,
software distributed under the License is distributed on an
"AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
KIND, either express or implied.  See the License for the
specific language governing permissions and limitations
under the License.
-->

<!--
    PXF pre-packaged profiles definition file.
    It's not recommended to add new profiles here.
    For adding new custom profiles please edit pxf-profiles.xml
-->
<profiles>
    <profile>
        <name>HBase</name>
        <description>This profile is suitable for using when connecting to an HBase data store engine</description>
        <plugins>
            <fragmenter>org.apache.hawq.pxf.plugins.hbase.HBaseDataFragmenter</fragmenter>
            <accessor>org.apache.hawq.pxf.plugins.hbase.HBaseAccessor</accessor>
            <resolver>org.apache.hawq.pxf.plugins.hbase.HBaseResolver</resolver>
        </plugins>
    </profile>
    <profile>
        <name>Hive</name>
        <description>
            This profile is suitable for using when connecting to Hive.
            Supports GPDBWritable output format, as specified in FORMAT header parameter.
            It auto-detects actual file storage format and uses an optimized profile (HiveRC, HiveText, HiveORC) if applicable.
        </description>
        <plugins>
            <fragmenter>org.apache.hawq.pxf.plugins.hive.HiveDataFragmenter</fragmenter>
            <accessor>org.apache.hawq.pxf.plugins.hive.HiveAccessor</accessor>
            <resolver>org.apache.hawq.pxf.plugins.hive.HiveResolver</resolver>
            <metadata>org.apache.hawq.pxf.plugins.hive.HiveMetadataFetcher</metadata>
            <outputFormat>org.apache.hawq.pxf.service.io.GPDBWritable</outputFormat>
        </plugins>
    </profile>
    <profile>
        <name>HiveRC</name>
        <description>This profile is suitable only for Hive tables stored in RC files
            and serialized with either the ColumnarSerDe or the LazyBinaryColumnarSerDe.
            It is much faster than the general purpose Hive profile.
            DELIMITER parameter is mandatory.
            Supports both GPDBWritable and TEXT output formats, as specified in FORMAT header parameter.
            Primary optimized for TEXT output format.
        </description>
        <plugins>
            <fragmenter>org.apache.hawq.pxf.plugins.hive.HiveInputFormatFragmenter</fragmenter>
            <accessor>org.apache.hawq.pxf.plugins.hive.HiveRCFileAccessor</accessor>
            <resolver>org.apache.hawq.pxf.plugins.hive.HiveColumnarSerdeResolver</resolver>
            <metadata>org.apache.hawq.pxf.plugins.hive.HiveMetadataFetcher</metadata>
            <outputFormat>org.apache.hawq.pxf.service.io.Text</outputFormat>
        </plugins>
    </profile>
    <profile>
        <name>HiveText</name>
        <description>This profile is suitable only for Hive tables stored as Text files.
            It is much faster than the general purpose Hive profile.
            DELIMITER parameter is mandatory.
            Supports both GPDBWritable and TEXT output formats, as specified in FORMAT header parameter.
            Primary optimized for TEXT output format.
        </description>
        <plugins>
            <fragmenter>org.apache.hawq.pxf.plugins.hive.HiveInputFormatFragmenter</fragmenter>
            <accessor>org.apache.hawq.pxf.plugins.hive.HiveLineBreakAccessor</accessor>
            <resolver>org.apache.hawq.pxf.plugins.hive.HiveStringPassResolver</resolver>
            <metadata>org.apache.hawq.pxf.plugins.hive.HiveMetadataFetcher</metadata>
            <outputFormat>org.apache.hawq.pxf.service.io.Text</outputFormat>
        </plugins>
    </profile>
    <profile>
        <name>HiveORC</name>
        <description>This profile is suitable only for Hive tables stored in ORC files
            and serialized with either the ColumnarSerDe or the LazyBinaryColumnarSerDe.
            It is much faster than the general purpose Hive profile.
            Supports GPDBWritable output format, as specified in FORMAT header parameter.
        </description>
        <plugins>
            <fragmenter>org.apache.hawq.pxf.plugins.hive.HiveInputFormatFragmenter</fragmenter>
            <accessor>org.apache.hawq.pxf.plugins.hive.HiveORCAccessor</accessor>
            <resolver>org.apache.hawq.pxf.plugins.hive.HiveORCSerdeResolver</resolver>
            <metadata>org.apache.hawq.pxf.plugins.hive.HiveMetadataFetcher</metadata>
            <outputFormat>org.apache.hawq.pxf.service.io.GPDBWritable</outputFormat>
        </plugins>
    </profile>
    <profile>
        <name>HiveVectorizedORC</name>
        <description>This profile is same as HiveORC profile, but operates on batches of rows
            instead of one row at a time, leading to faster reading and resolution phases.
        </description>
        <plugins>
            <fragmenter>org.apache.hawq.pxf.plugins.hive.HiveInputFormatFragmenter</fragmenter>
            <accessor>org.apache.hawq.pxf.plugins.hive.HiveORCVectorizedAccessor</accessor>
            <resolver>org.apache.hawq.pxf.plugins.hive.HiveORCVectorizedResolver</resolver>
            <metadata>org.apache.hawq.pxf.plugins.hive.HiveMetadataFetcher</metadata>
            <outputFormat>org.apache.hawq.pxf.service.io.GPDBWritable</outputFormat>
        </plugins>
    </profile>
    <profile>
        <name>HdfsTextSimple</name>
        <description>This profile is suitable for using when reading delimited single line records from plain text files
            on HDFS
        </description>
        <plugins>
            <fragmenter>org.apache.hawq.pxf.plugins.hdfs.HdfsDataFragmenter</fragmenter>
            <accessor>org.apache.hawq.pxf.plugins.hdfs.LineBreakAccessor</accessor>
            <resolver>org.apache.hawq.pxf.plugins.hdfs.StringPassResolver</resolver>
        </plugins>
    </profile>
    <profile>
        <name>HdfsTextMulti</name>
        <description>This profile is suitable for using when reading delimited single or multi line records (with quoted
            linefeeds) from plain text files on HDFS. It is not splittable (non parallel) and slower than HdfsTextSimple.
        </description>
        <plugins>
            <fragmenter>org.apache.hawq.pxf.plugins.hdfs.HdfsDataFragmenter</fragmenter>
            <accessor>org.apache.hawq.pxf.plugins.hdfs.QuotedLineBreakAccessor</accessor>
            <resolver>org.apache.hawq.pxf.plugins.hdfs.StringPassResolver</resolver>
        </plugins>
    </profile>
    <profile>
        <name>Avro</name>
        <description>This profile is suitable for using when reading Avro files (i.e fileName.avro)</description>
        <plugins>
            <fragmenter>org.apache.hawq.pxf.plugins.hdfs.HdfsDataFragmenter</fragmenter>
            <accessor>org.apache.hawq.pxf.plugins.hdfs.AvroFileAccessor</accessor>
            <resolver>org.apache.hawq.pxf.plugins.hdfs.AvroResolver</resolver>
        </plugins>
    </profile>
    <profile>
        <name>SequenceWritable</name>
        <description>
            Profile for accessing Sequence files serialized with a custom Writable class
        </description>
        <plugins>
            <fragmenter>org.apache.hawq.pxf.plugins.hdfs.HdfsDataFragmenter</fragmenter>
            <accessor>org.apache.hawq.pxf.plugins.hdfs.SequenceFileAccessor</accessor>
            <resolver>org.apache.hawq.pxf.plugins.hdfs.WritableResolver</resolver>
        </plugins>
    </profile>
    <profile>
        <name>GemFireXD</name>
        <description>This profile is suitable for using when connecting to GemFireXD</description>
        <plugins>
            <fragmenter>org.apache.hawq.pxf.plugins.gemfirexd.GemFireXDFragmenter</fragmenter>
            <accessor>org.apache.hawq.pxf.plugins.gemfirexd.GemFireXDAccessor</accessor>
            <resolver>org.apache.hawq.pxf.plugins.gemfirexd.GemFireXDResolver</resolver>
        </plugins>
    </profile>
    <profile>
        <name>Json</name>
        <description>
            Access JSON data either as:
            * one JSON record per line (default)
            * or multiline JSON records with an IDENTIFIER parameter indicating a member name
              used to determine the encapsulating json object to return
        </description>
        <plugins>
            <fragmenter>org.apache.hawq.pxf.plugins.hdfs.HdfsDataFragmenter</fragmenter>
            <accessor>org.apache.hawq.pxf.plugins.json.JsonAccessor</accessor>
            <resolver>org.apache.hawq.pxf.plugins.json.JsonResolver</resolver>
        </plugins>
    </profile>
    <profile>
        <name>Jdbc</name>
        <description>A profile for reading and writing data via JDBC</description>
        <plugins>
            <fragmenter>org.apache.hawq.pxf.plugins.jdbc.JdbcPartitionFragmenter</fragmenter>
            <accessor>org.apache.hawq.pxf.plugins.jdbc.JdbcAccessor</accessor>
            <resolver>org.apache.hawq.pxf.plugins.jdbc.JdbcResolver</resolver>
        </plugins>
    </profile>
    <profile>
        <name>Parquet</name>
        <description>A profile for reading and writing Parquet data from HDFS</description>
        <plugins>
            <fragmenter>org.apache.hawq.pxf.plugins.hdfs.ParquetDataFragmenter</fragmenter>
            <accessor>org.apache.hawq.pxf.plugins.hdfs.ParquetFileAccessor</accessor>
            <resolver>org.apache.hawq.pxf.plugins.hdfs.ParquetResolver</resolver>
        </plugins>
    </profile>
    <profile>
        <name>Apache Ignite</name>
        <description>A profile to read and write data from/to Apache Ignite database</description>
        <plugins>
            <fragmenter>org.apache.hawq.pxf.plugins.ignite.IgnitePartitionFragmenter</fragmenter>
            <accessor>org.apache.hawq.pxf.plugins.ignite.IgniteAccessor</accessor>
            <resolver>org.apache.hawq.pxf.plugins.ignite.IgniteResolver</resolver>
        </plugins>
    </profile>
</profiles>