Java Code Examples for org.elasticsearch.action.admin.indices.analyze.AnalyzeResponse#AnalyzeToken

@Test
public void testTokenizer() throws Exception {
    AnalyzeRequest analyzeRequest = new AnalyzeRequest();
    analyzeRequest.text("My œsophagus caused a débâcle");
    /**
     * whitespace （空白字符）分词器按空白字符 —— 空格、tabs、换行符等等进行简单拆分
     * letter 分词器 ，采用另外一种策略，按照任何非字符进行拆分
     * standard 分词器使用 Unicode 文本分割算法
     */
    analyzeRequest.addTokenFilter("standard");
    analyzeRequest.addCharFilter("asciifolding");
    ActionFuture<AnalyzeResponse> analyzeResponseActionFuture =  client.admin().indices().analyze(analyzeRequest);
    List<AnalyzeResponse.AnalyzeToken> analyzeTokens =  analyzeResponseActionFuture.actionGet().getTokens();
    for (AnalyzeResponse.AnalyzeToken analyzeToken : analyzeTokens){
        System.out.println(analyzeToken.getTerm());
    }
}
 

/**
 * analyze the given text using the provided analyzer, return an ngram
 * @param text
 * @param analyzer
 * @return
 */
public Ngram analyze(String text, String analyzer){
    List<AnalyzeResponse.AnalyzeToken> tokens = client.admin().indices().prepareAnalyze(indexName,text).setAnalyzer(analyzer).get().getTokens();

    Ngram ngram = new Ngram();
    StringBuilder sb = new StringBuilder();
    for (int i=0;i<tokens.size();i++)
    {
        AnalyzeResponse.AnalyzeToken token = tokens.get(i);
        sb.append(token.getTerm());
        if (i!=tokens.size()-1){
            sb.append(" ");
        }
    }
    ngram.setNgram(sb.toString());
    return ngram;

}
 

/**
 * ik分词测试
 * @Author lihaodong
 * @Description
 * @Date 20:09 2018/12/21
 * @Param []
 * @return java.lang.String
 **/
public static String ik() {
    StringBuilder stringBuilder = new StringBuilder();
    AnalyzeRequest analyzeRequest = new AnalyzeRequest("entity")
            .text("书名")
            .analyzer("standard");  //ik_smart  ik_max_word  standard
    List<AnalyzeResponse.AnalyzeToken> tokens = client.admin().indices()
            .analyze(analyzeRequest)
            .actionGet()
            .getTokens();
    for (AnalyzeResponse.AnalyzeToken token : tokens) {
        stringBuilder.append(token.getTerm() + "\\r\\n");
    }
    return stringBuilder.toString();
}
 

public static void anylyze() throws Exception{
    AnalyzeRequest request = new AnalyzeRequest();
    request.text("ReadMe.txt Screenshots,ReadMe.txt Screenshots,1.jpg COVER.jpg Screenshots,4.jpg Screenshots,2.jpg Screenshots,3.jpg FIFA.Street.2012 - RELOADED.rar");
    request.analyzer("ik_max_word");

    AnalyzeResponse response = client.indices().analyze(request, RequestOptions.DEFAULT);
    List<AnalyzeResponse.AnalyzeToken> tokens =
            response.getTokens();
    for(AnalyzeResponse.AnalyzeToken to:tokens){
        System.out.println(to.getTerm());
    }
    System.out.println(response.getTokens().get(0).getAttributes());
}
 

@Test
public void testClientConnection() throws Exception {
    AnalyzeRequest analyzeRequest = new AnalyzeRequest();
    analyzeRequest.text("美女");
    ActionFuture<AnalyzeResponse> analyzeResponseActionFuture = client.admin().indices().analyze(analyzeRequest);
    List<AnalyzeResponse.AnalyzeToken> analyzeTokens =  analyzeResponseActionFuture.actionGet().getTokens();
    for (AnalyzeResponse.AnalyzeToken analyzeToken  : analyzeTokens){
        System.out.println(analyzeToken.getTerm());
    }
}
 

@Test
public void testClientConnection() throws Exception {
    AnalyzeRequest analyzeRequest = new AnalyzeRequest();
    analyzeRequest.text("中华人民共和国");
    ActionFuture<AnalyzeResponse> analyzeResponseActionFuture = client.admin().indices().analyze(analyzeRequest);
    List<AnalyzeResponse.AnalyzeToken> analyzeTokens =  analyzeResponseActionFuture.actionGet().getTokens();
    for (AnalyzeResponse.AnalyzeToken analyzeToken  : analyzeTokens){
        System.out.println(analyzeToken.getTerm());
    }
}
 

private static void showAnaylzerText(IndicesAdminClient indicesAdminClient,String analyzerName, String text) {
    AnalyzeResponse analyzeResponse = indicesAdminClient.analyze(new AnalyzeRequest(INDEX_NAME).analyzer(analyzerName).text(text)).actionGet();
    List<AnalyzeResponse.AnalyzeToken> token=analyzeResponse.getTokens();
    for (AnalyzeResponse.AnalyzeToken analyzeToken : token) {
        log.info(analyzerName+": {}",analyzeToken.getTerm());
    }

}
 

@Test
public void testPassthrough() {
    List<AnalyzeResponse.AnalyzeToken> tokens = analyzeURL("http://foo.com:9200/foo.bar baz bat.blah", "url_host_passthrough");
    assertThat(tokens, hasSize(4));
    assertThat(tokens.get(0).getTerm(), equalTo("foo.com"));
    assertThat(tokens.get(1).getTerm(), equalTo("com"));
    assertThat(tokens.get(2).getTerm(), equalTo("baz"));
    assertThat(tokens.get(3).getTerm(), equalTo("bat.blah"));
}
 

@Test
public void testAnalyze() {
    assertTokensContain(URLTokenizerTest.TEST_HTTP_URL, "tokenizer_url_protocol", "http");
    assertTokensContain(URLTokenizerTest.TEST_HTTPS_URL, "tokenizer_url_protocol", "https");

    assertTokensContain(URLTokenizerTest.TEST_HTTP_URL, "tokenizer_url_host", "www.foo.bar.com", "foo.bar.com", "bar.com", "com");
    List<AnalyzeResponse.AnalyzeToken> hostTokens = assertTokensContain(URLTokenizerTest.TEST_HTTP_URL, "tokenizer_url_host_single", "www.foo.bar.com");
    assertThat(hostTokens, hasSize(1));

    assertTokensContain(URLTokenizerTest.TEST_HTTP_URL, "tokenizer_url_all", "www.foo.bar.com:9200", "http://www.foo.bar.com");

    assertTokensContain(URLTokenizerTest.TEST_HTTP_URL, "tokenizer_url_protocol_and_host", "http", "www.foo.bar.com", "foo.bar.com", "bar.com", "com");

    assertTokensContain("foo.bar.com/baz.html/query?a=1", "tokenizer_url_all_malformed", "foo.bar.com", "/baz.html/query");
}
 

private List<AnalyzeResponse.AnalyzeToken> assertTokensContain(String url, String analyzer, String... expected) {
    List<AnalyzeResponse.AnalyzeToken> tokens = analyzeURL(url, analyzer);
    for (String e : expected) {
        assertThat(tokens, hasItem(Matchers.<AnalyzeResponse.AnalyzeToken>hasProperty("term", equalTo(e))));
    }
    return tokens;
}
 

/**
 * analyze the given text using the provided analyzer, return an ngram
 * @param text
 * @param analyzer
 * @return
 */
public List<String> analyzeString(String text, String analyzer){
    List<AnalyzeResponse.AnalyzeToken> tokens = client.admin().indices().prepareAnalyze(indexName,text).setAnalyzer(analyzer).get().getTokens();
    List<String> list = new ArrayList<>();
    for (int i=0;i<tokens.size();i++)
    {
        AnalyzeResponse.AnalyzeToken token = tokens.get(i);
        list.add(token.getTerm());

    }
    return list;

}
 

@Test
public void testEmptyString() {
    List<AnalyzeResponse.AnalyzeToken> tokens = analyzeURL("", "url_protocol");
    assertThat("no tokens", tokens, hasSize(0));
}
 

private void assertURLAnalyzesTo(String url, String analyzer, String expected) {
    List<AnalyzeResponse.AnalyzeToken> tokens = analyzeURL(url, analyzer);
    assertThat("a URL part was parsed", tokens, hasSize(1));
    assertEquals("term value", expected, tokens.get(0).getTerm());
}
 

@Test
public void testAnalyzeWhole() throws Exception {
    List<AnalyzeResponse.AnalyzeToken> tokens = analyzeURL("http://foo.bar.com", "tokenizer_url_all_malformed");
    assertThat(tokens, notNullValue());
    assertThat(tokens, hasSize(7));
}
 

protected List<AnalyzeResponse.AnalyzeToken> analyzeURL(String url, String analyzer) {
    return client().admin().indices().prepareAnalyze(INDEX, url).setAnalyzer(analyzer).get().getTokens();
}