src/test/data/descriptors/SimpleTextMerger.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.
***************************************************************
-->

<analysisEngineDescription xmlns="http://uima.apache.org/resourceSpecifier">
    <frameworkImplementation>org.apache.uima.cpp</frameworkImplementation>
    <primitive>true</primitive>
    <annotatorImplementationName>libSimpleTextMerger</annotatorImplementationName>

    <analysisEngineMetaData>
        <name>Simple Text Merger</name>
        <description>Merges text documents into larger ones, producing a merged CAS.  Also copies
            selected annotation types to the merged CAS.  The input CAS requires an instance of
            the type uima.tt.SourceDocumentInformation (which is produced by SimpleTextSegmenter).
            Input CASes will be merged until a CAS is encountered whose SourceDocumentInformation FS has its
            lastSegment feature set to true.  At that point a merged CAS will be output which
            includes the content up to and including that CAS.  If additional CASes are then
            received, a second merged CAS will be built, including all content from that point until
            the next CAS with lastSegment = true, and so on.</description>
        <version>1.0</version>
        <vendor>The Apache Software Foundation</vendor>

        <configurationParameters>
            <configurationParameter>
                <name>AnnotationTypesToCopy</name>
                <description>
                    Names of annotation types to be copied from source CASes into the merged CAS.
                    Type uima.tt.SourceDocumentInformation will specifically be ignored.
                </description>
                <type>String</type>
                <multiValued>true</multiValued>
                <mandatory>true</mandatory>
            </configurationParameter>


            <configurationParameter>
                <name>OutputFrequency</name>
                <description>
                    How frequent this merger will output a new CAS. If no value or (0) is specified, it
                    will only ouput a CAS at the end.
                    For example: if there are a total of 5 inputs and OutputFrequency is set to 2, this merger will
                    produce 3 CASes: (1 + 2), (3 + 4), (5)
                </description>
                <type>Integer</type>
                <multiValued>false</multiValued>
                <mandatory>false</mandatory>
            </configurationParameter>
        </configurationParameters>
        <configurationParameterSettings>
            <nameValuePair>
                <name>AnnotationTypesToCopy</name>
                <value>
                    <array>
                        <string>uima.tt.TokenAnnotation</string>
                    </array>
                </value>
            </nameValuePair>
        </configurationParameterSettings>

        <typeSystemDescription>
            <imports>
                <import location="tt_typesystem.xml"/>
            </imports>
        </typeSystemDescription>

        <capabilities>
            <capability>
                <inputs>
                    <type>uima.tt.SourceDocumentInformation</type>
                    <feature>uima.tt.SourceDocumentInformation:lastSegment</feature>
                </inputs>
                <outputs/>
            </capability>
        </capabilities>

        <operationalProperties>
            <modifiesCas>false</modifiesCas>
            <multipleDeploymentAllowed>true</multipleDeploymentAllowed>
            <outputsNewCASes>true</outputsNewCASes>
        </operationalProperties>

    </analysisEngineMetaData>
</analysisEngineDescription>