Example usage for org.apache.lucene.analysis.charfilter MappingCharFilterFactory MappingCharFilterFactory

Introduction

In this page you can find the example usage for org.apache.lucene.analysis.charfilter MappingCharFilterFactory MappingCharFilterFactory.

Prototype

public MappingCharFilterFactory(Map<String, String> args) 

Source Link

Document

Creates a new MappingCharFilterFactory

Usage

From source file:jp.co.atware.solr.analizers.cjk.CJKBigramFilterTest.java

License:Apache License

@BeforeClass
public static void setUp() throws Exception {
    Map<String, String> map = new HashMap<String, String>();
    map.put("mapping", "mapping.txt");
    charFilterFactory = new MappingCharFilterFactory(map);
    charFilterFactory.inform(new FilesystemResourceLoader(new File("src/test/resources/cjkbigramfilter")));
    tokenizerFactory = new CJKTokenizerFactory(new HashMap<String, String>());
    map = new HashMap<String, String>();
    map.put("outputUnigrams", "true");
    tokenFilterFactory = new CJKBigramFilterFactory(map);
}

---

From source file:org.apache.solr.search.PreAnalyzedQParserPlugin.java

License:Apache License

public void init(NamedList args) {
    // TODO Auto-generated method stub
    try {/*  w w  w  . j  a  v  a 2 s .c om*/
        // Initialize lemmatizer
        lemmatizer = LemmatizerFactory.createLemmatizer();

        // Initialize OpenNLP model and tokenizer
        modelsPath = args.get("modelsPath").toString();
        tokenModelIn = new FileInputStream(
                PreAnalyzedQParserPlugin.modelsPath + lang + File.separator + lang + "-token.bin");
        tokenModel = new TokenizerModel(tokenModelIn);
        tokenizer = new TokenizerME(tokenModel);
        tokenizerSimple = SimpleTokenizer.INSTANCE;
        tokenizerWS = WhitespaceTokenizer.INSTANCE;

        // Get Synonyms file path
        synonymsPath = args.get("synonymsPath").toString();

        // Initialize Synonyms Filter factory
        Map<String, String> argsSyn = new HashMap<String, String>();
        argsSyn.put("synonyms", synonymsPath);
        argsSyn.put("luceneMatchVersion", Version.LUCENE_46.toString());
        synFactory = new SynonymFilterFactory(argsSyn);
        synFactory.inform(new FilesystemResourceLoader());

        // Get Mapping Char file path
        mappingPath = args.get("mappingsPath").toString();

        lemmaLogPath = args.get("lemmaLogPath").toString();

        // Initialize Mapping Char Filter factory
        Map<String, String> argsCharFactory = new HashMap<String, String>();
        argsCharFactory.put("mapping", mappingPath);
        argsCharFactory.put("luceneMatchVersion", Version.LUCENE_46.toString());
        mapCharFactory = new MappingCharFilterFactory(argsCharFactory);
        mapCharFactory.inform(new FilesystemResourceLoader());

    } catch (LemmatizerException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    } catch (FileNotFoundException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    } catch (InvalidFormatException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    } catch (IOException e) {
        // TODO Auto-generated catch block
        e.printStackTrace();
    }
}

---