lucene/solr/contrib/langid/build.xml

<?xml version="1.0"?>

<!--
    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.
 -->

<project name="solr-langid" default="default">

  <description>
    Language Identifier contrib for extracting language from a document being indexed
  </description>

  <import file="../contrib-build.xml"/>

  <property name="test.model.dir" location="${tests.userdir}/langid/solr/collection1/conf"/>
  <property name="test.leipzig.folder.link" value="http://pcai056.informatik.uni-leipzig.de/downloads/corpora"/><!-- URL broken? -->
  <property name="test.build.models.dir" location="${build.dir}/build-test-models"/>
  <property name="test.build.models.data.dir" location="${test.build.models.dir}/data"/>
  <property name="test.build.models.sentences.dir" location="${test.build.models.dir}/train"/>
  <property name="test.opennlp.model" value="opennlp-langdetect.eng-swe-spa-rus-deu.bin"/>

  <path id="opennlp.jars">
    <fileset dir="lib" includes="opennlp*.jar"/>
  </path>
  
  <path id="classpath">
    <fileset dir="../extraction/lib" excludes="${common.classpath.excludes}"/>
    <fileset dir="lib" excludes="${common.classpath.excludes}"/>
    <path refid="solr.base.classpath"/>   
  </path>

  <!-- we don't actually need to compile this thing, we just want its libs -->
  <target name="resolve-extraction-libs">
    <ant dir="${common-solr.dir}/contrib/extraction" target="resolve" inheritAll="false">
      <propertyset refid="uptodate.and.compiled.properties"/>
    </ant>
  </target>

  <target name="compile-core" depends="resolve-extraction-libs,solr-contrib-build.compile-core"/>

  <!--
  Create test models using data for five languages from the Leipzig corpora.
  See https://opennlp.apache.org/docs/1.8.3/manual/opennlp.html#tools.langdetect.training.leipzig
  -->
  <target name="train-test-models" description="Train small test models for unit tests" depends="resolve">
    <download-leipzig language.code="eng"/> 
    <download-leipzig language.code="swe"/>
    <download-leipzig language.code="spa"/>
    <download-leipzig language.code="rus"/>
    <download-leipzig language.code="deu"/>

    <echo message="Train OpenNLP test model over data from the Leipzig corpora"/>
    <java classname="opennlp.tools.cmdline.CLI" classpathref="opennlp.jars" fork="true" failonerror="true">
      <arg value="LanguageDetectorTrainer.leipzig"/>

      <arg value="-model"/>
      <arg value="${test.model.dir}/${test.opennlp.model}"/>

      <arg value="-params"/>
      <arg value="${tests.userdir}/opennlp.langdetect.trainer.params.txt"/>

      <arg value="-sentencesDir"/> 
      <arg value="${test.build.models.sentences.dir}"/>
      
      <arg value="-sentencesPerSample"/>
      <arg value="3"/>  
      
      <arg value="-samplesPerLanguage"/>
      <arg value="10000"/>
    </java>
  </target>

  <macrodef name="download-leipzig">
    <attribute name="language.code"/>
    <attribute name="leipzig.tarball" default="@{language.code}_news_2007_30K.tar.gz"/>
    <sequential>
      <mkdir dir="${test.build.models.data.dir}"/>
      <get src="${test.leipzig.folder.link}/@{leipzig.tarball}" dest="${test.build.models.data.dir}"/>
      <untar compression="gzip" src="${test.build.models.data.dir}/@{leipzig.tarball}"
             dest="${test.build.models.sentences.dir}">
        <patternset>
          <include name="*-sentences.txt"/>
        </patternset>
      </untar>
    </sequential>
  </macrodef>

  <target name="regenerate" depends="train-test-models"/>
</project>