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

<taeDescription
   xmlns="http://uima.apache.org/resourceSpecifier"
    xmlns:xi="http://www.w3.org/2001/XInclude"
>
    <frameworkImplementation>org.apache.uima.cpp</frameworkImplementation>
    <primitive>true</primitive>
    <annotatorImplementationName>libtoknz</annotatorImplementationName>

    <analysisEngineMetaData>
        <name>UnicodeTokenizer</name>
        <description>This annotator extracts tokens from text based on their Unicdoe character properties and simple rules.</description>
        <version>1.0</version>
        <vendor>IBM Corporation</vendor>

        <configurationParameters defaultGroup="x-unspecified">
            <configurationGroup names="x-unspecified">
                <configurationParameter>
                    <name>TokenNumbersIncludeStopwords</name>
                    <description>If true token numbers are counted including stopwords</description>
                    <type>Boolean</type>
                    <multiValued>false</multiValued>
                    <mandatory>true</mandatory>
                </configurationParameter>

                <configurationParameter>
                    <name>UseRelativeTokenAndSentenceNumbers</name>
                    <description>If true token and sentence numbers are reset to 1 for each new sentence/paragraph</description>
                    <type>Boolean</type>
                    <multiValued>false</multiValued>
                    <mandatory>true</mandatory>
                </configurationParameter>

                <configurationParameter>
                    <name>IgnorePunctuationTokens</name>
                    <description>If true, punctuation tokens are ignored</description>
                    <type>Boolean</type>
                    <multiValued>false</multiValued>
                    <mandatory>true</mandatory>
                </configurationParameter>

            </configurationGroup>
        </configurationParameters>

        <configurationParameterSettings>
            <settingsForGroup name="x-unspecified">
                <nameValuePair>
                    <name>TokenNumbersIncludeStopwords</name>
                    <value>
                        <boolean>true</boolean>
                    </value>
                </nameValuePair>

                <nameValuePair>
                    <name>UseRelativeTokenAndSentenceNumbers</name>
                    <value>
                        <boolean>false</boolean>
                    </value>
                </nameValuePair>

                <nameValuePair>
                    <name>IgnorePunctuationTokens</name>
                    <value>
                        <boolean>false</boolean>
                    </value>
                </nameValuePair>

            </settingsForGroup>
        </configurationParameterSettings>

        <typeSystemDescription>
            <imports>
                <import location="tt_typesystem.xml"/>
            </imports>
 		<types>
                    <typeDescription>
                        <name>uima.tt.TokenAnnotation</name>
                        <description></description>
                        <supertypeName>uima.tt.LexicalAnnotation</supertypeName>
                        <features>
                            <featureDescription>
                                <name>stem</name>
                                <description></description>
                                <rangeTypeName>uima.cas.String</rangeTypeName>
                            </featureDescription>
                        </features>
                    </typeDescription>
                </types>
        </typeSystemDescription>

        <fsIndexes>
        </fsIndexes>

        <capabilities>
            <capability>
                <inputs>
                </inputs>

                <outputs>
                    <type>uima.tt.TokenAnnotation</type>
                    <type>uima.tt.SentenceAnnotation</type>
                    <type>uima.tt.ParagraphAnnotation</type>
                </outputs>

                <languagesSupported>
                    <language>af</language>
                    <language>be</language>
                    <language>bg</language>
                    <language>ca</language>
                    <language>cs</language>
                    <language>da</language>
                    <language>de</language>
                    <language>en</language>
                    <language>el</language>
                    <language>es</language>
                    <language>et</language>
                    <language>fi</language>
                    <language>fr</language>
                    <language>hr</language>
                    <language>hi</language>
                    <language>hu</language>
                    <language>is</language>
                    <language>it</language>
                    <language>lt</language>
                    <language>lv</language>
                    <language>mk</language>
                    <language>nl</language>
                    <language>nb</language>
                    <language>no</language>
                    <language>pl</language>
                    <language>pt</language>
                    <language>ro</language>
                    <language>ru</language>
                    <language>sh</language>
                    <language>sk</language>
                    <language>sl</language>
                    <language>sr</language>
                    <language>sq</language>
                    <language>sv</language>
                    <language>tr</language>
                    <language>uk</language>
                    <language>vi</language>
                </languagesSupported>
            </capability>
            <capability>
                <inputs>
                </inputs>
                <outputs>
                    <feature>uima.tt.TokenAnnotation:stem</feature>
                </outputs>
                <languagesSupported>
                    <language>en</language>
                </languagesSupported>
            </capability>
        </capabilities>

    </analysisEngineMetaData>
</taeDescription>