在GATE中使用TermRaider插件

Question

我想在GATE中使用TermRaider特性。有没有人可以发布一些示例代码来加载和使用java类中的资源。我尝试过跟随，但失败了。

 Gate.getCreoleRegister().registerDirectories(new URL("file:///D:/misc_workspace/gate-7.1-build4485-SRC/plugins/TermRaider"));

    ProcessingResource termRaider = (ProcessingResource) Factory.
    createResource("gate.termraider.TermRaiderEnglish",Factory.newFeatureMap());

Exception:
gate.termraider.TermRaiderEnglish cannot be cast to gate.ProcessingResource

有没有人能建议我该怎么做。

Answer 1

Groovy不是一个单独的PR，它是一个完整的应用程序(实际上是一个TermRaider ScriptableController)。TermraiderEnglish资源只是一个钩子，用于使应用程序出现在GATE Developer GUI的"ready-made applications“菜单中。

在嵌入式代码中，您可以使用PersistenceManager加载应用程序

File termRaiderPlugin = new File(Gate.getPluginsHome(), "TermRaider");
File gappFile = new File(new File(termRaiderPlugin, "applications"),
            "termraider-eng.gapp");
CorpusController trApp = (CorpusController)PersistenceManager.loadObjectFromFile(
    gappFile);

当您在语料库上运行应用程序时，它将创建三个“术语库”LR的新实例，其中包含有关新发现的术语的信息。这个普通的应用程序实际上是为图形用户界面而不是嵌入式使用而设计的，所以它不会存储对这些新LR的引用-您必须询问CreoleRegister才能找到它们。您可能更喜欢制作自己的应用程序副本，并调整控制脚本以将术语库实例存储为(比方说) Corpus上的特性，方法是添加如下内容

corpus.features.tfidfTermbank = termbank0
corpus.features.annotationTermbank = termbank1
corpus.features.hyponymyTermbank = termbank2

添加到控制脚本的末尾。然后你可以通过corpus.getFeatures().get("tfidfTermbank")等在你的Java代码中访问它们。

因为这些Termbank类本身就是TermRaider插件的一部分，所以您可能希望将gate-termraider.jar添加到主应用程序类路径中，而不是通过GateClassLoader加载它。

Answer 2

import gate.Corpus;
import gate.CorpusController;
import gate.Document;
import gate.Factory;
import gate.FeatureMap;
import gate.Gate;
import gate.termraider.bank.AbstractTermbank;
import gate.termraider.output.CsvGenerator;
import gate.util.GateException;
import gate.util.Out;
import gate.util.persistence.PersistenceManager;

import java.io.File;
import java.io.IOException;
import java.net.URL;
import java.net.URLDecoder;


public class termraider {
    public static void main(String[] args) throws IOException, GateException {

        // initialise the GATE library
        Out.prln("Initialising GATE...");
        Gate.init();

        // Initialize GATE
        File gateHome = Gate.getGateHome();
        Out.prln("...GATE initialised");

        //Load TermRaider plugin
        File termRaiderPlugin = new File(Gate.getPluginsHome(), "TermRaider");
        File gappFile = new File(new File(termRaiderPlugin, "applications"),
                   "termraider-eng.gapp");
        CorpusController trApp = (CorpusController)PersistenceManager.loadObjectFromFile(gappFile);
        System.out.println("TermRaider loaded successfully!!!");


    //Loading txt files from a folder path
        Corpus corpus = (Corpus) Factory.createResource("gate.corpora.CorpusImpl");
        //String dirname = "Desktop/Gate_corpus/About Us/New Folder";
        String dirname = "Desktop/GermanHPFCompetition/termRaider";
        File f1 = new File(dirname);
        String s[] = f1.list();
        for (int i=0; i < s.length; i++) {
            String path = dirname + "/" + s[i];
            path = URLDecoder.decode(path, "utf-8");
            path = new File(path).getPath();
            URL u=new URL("file:\\\\\\"+path);

          FeatureMap params = Factory.newFeatureMap();
          params.put("sourceUrl", u);
          params.put("preserveOriginalContent", new Boolean(true));
          params.put("collectRepositioningInfo", new Boolean(true));
          //Out.prln("Creating doc for " + u);
          Document doc = (Document)
          Factory.createResource("gate.corpora.DocumentImpl", params);
          corpus.add(doc);
        } // for each file in the folder

        //running TermRaider plugin with the corpus
        trApp.init();
        trApp.setCorpus(corpus);
        trApp.execute();
        Corpus output_corpus = (Corpus) Factory.createResource("gate.corpora.CorpusImpl");
        output_corpus=trApp.getCorpus();
        System.out.println("TermRaider executed successfully!!!");

        //Creating csv files as output
        AbstractTermbank tb1 = (AbstractTermbank) output_corpus.getFeatures().get("tfidfTermbank");
        AbstractTermbank tb2 = (AbstractTermbank) output_corpus.getFeatures().get("hyponymyTermbank");
        AbstractTermbank tb3 = (AbstractTermbank) output_corpus.getFeatures().get("annotationTermbank");

        System.out.println(tb1);
        System.out.println(tb2);
        System.out.println(tb3);

        CsvGenerator generator = new CsvGenerator();
        File outputFile1 = new File("Desktop/GermanHPFCompetition/termRaider/tfidfTermbank.csv");
        File outputFile2 = new File("Desktop/GermanHPFCompetition/termRaider/hyponymyTermbank.csv");
        File outputFile3 = new File("Desktop/GermanHPFCompeti`enter code here`tion/termRaider/annotationTermbank.csv");
        double threshold1 = 0;
        double threshold2 = 0;
        double threshold3 = 0;
        generator.generateAndSaveCsv(tb1, threshold1, outputFile1);
        generator.generateAndSaveCsv(tb2, threshold2, outputFile2);
        generator.generateAndSaveCsv(tb3, threshold3, outputFile3);
        System.out.println("CSV files created!!!");

    }//end of main

}//end of class