Java AnalyzeRequest类代码示例

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入依赖的package包/类
public void testParseXContentForAnalyzeRequest() throws Exception {
    XContentParser content = createParser(XContentFactory.jsonBuilder()
        .startObject()
            .field("text", "THIS IS A TEST")
            .field("tokenizer", "keyword")
            .array("filter", "lowercase")
        .endObject());

    AnalyzeRequest analyzeRequest = new AnalyzeRequest("for test");

    RestAnalyzeAction.buildFromContent(content, analyzeRequest);

    assertThat(analyzeRequest.text().length, equalTo(1));
    assertThat(analyzeRequest.text(), equalTo(new String[]{"THIS IS A TEST"}));
    assertThat(analyzeRequest.tokenizer().name, equalTo("keyword"));
    assertThat(analyzeRequest.tokenFilters().size(), equalTo(1));
    for (AnalyzeRequest.NameOrDefinition filter : analyzeRequest.tokenFilters()) {
        assertThat(filter.name, equalTo("lowercase"));
    }
}
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入依赖的package包/类
@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());
    }
}
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入依赖的package包/类
@Override
public RestChannelConsumer prepareRequest(final RestRequest request, final NodeClient client) throws IOException {

    AnalyzeRequest analyzeRequest = new AnalyzeRequest(request.param("index"));

    try (XContentParser parser = request.contentOrSourceParamParser()) {
        buildFromContent(parser, analyzeRequest);
    } catch (IOException e) {
        throw new IllegalArgumentException("Failed to parse request body", e);
    }

    return channel -> client.admin().indices().analyze(analyzeRequest, new RestToXContentListener<>(channel));
}
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入依赖的package包/类
public void testParseXContentForAnalyzeRequestWithCustomFilters() throws Exception {
    XContentParser content = createParser(XContentFactory.jsonBuilder()
        .startObject()
            .field("text", "THIS IS A TEST")
            .field("tokenizer", "keyword")
            .startArray("filter")
                .value("lowercase")
                .startObject()
                    .field("type", "stop")
                    .array("stopwords", "foo", "buzz")
                .endObject()
            .endArray()
            .startArray("char_filter")
                .startObject()
                    .field("type", "mapping")
                    .array("mappings", "ph => f", "qu => q")
                .endObject()
            .endArray()
        .endObject());

    AnalyzeRequest analyzeRequest = new AnalyzeRequest("for test");

    RestAnalyzeAction.buildFromContent(content, analyzeRequest);

    assertThat(analyzeRequest.text().length, equalTo(1));
    assertThat(analyzeRequest.text(), equalTo(new String[]{"THIS IS A TEST"}));
    assertThat(analyzeRequest.tokenizer().name, equalTo("keyword"));
    assertThat(analyzeRequest.tokenFilters().size(), equalTo(2));
    assertThat(analyzeRequest.tokenFilters().get(0).name, equalTo("lowercase"));
    assertThat(analyzeRequest.tokenFilters().get(1).definition, notNullValue());
    assertThat(analyzeRequest.charFilters().size(), equalTo(1));
    assertThat(analyzeRequest.charFilters().get(0).definition, notNullValue());
}
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入依赖的package包/类
public void testParseXContentForAnalyzeRequestWithUnknownParamThrowsException() throws Exception {
    AnalyzeRequest analyzeRequest = new AnalyzeRequest("for test");
    XContentParser invalidContent = createParser(XContentFactory.jsonBuilder()
        .startObject()
            .field("text", "THIS IS A TEST")
            .field("unknown", "keyword")
        .endObject());
    IllegalArgumentException e = expectThrows(IllegalArgumentException.class,
            () -> RestAnalyzeAction.buildFromContent(invalidContent, analyzeRequest));
    assertThat(e.getMessage(), startsWith("Unknown parameter [unknown]"));
}
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入依赖的package包/类
public void testParseXContentForAnalyzeRequestWithInvalidStringExplainParamThrowsException() throws Exception {
    AnalyzeRequest analyzeRequest = new AnalyzeRequest("for test");
    XContentParser invalidExplain = createParser(XContentFactory.jsonBuilder()
        .startObject()
            .field("explain", "fals")
        .endObject());
    IllegalArgumentException e = expectThrows(IllegalArgumentException.class,
        () -> RestAnalyzeAction.buildFromContent(invalidExplain, analyzeRequest));
    assertThat(e.getMessage(), startsWith("explain must be either 'true' or 'false'"));
}
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入依赖的package包/类
public void testNoIndexAnalyzers() throws IOException {
    AnalyzeRequest request = new AnalyzeRequest();
    request.analyzer("standard");
    request.text("the quick brown fox");
    AnalyzeResponse analyze = TransportAnalyzeAction.analyze(request, AllFieldMapper.NAME, null, null, registry, environment);
    List<AnalyzeResponse.AnalyzeToken> tokens = analyze.getTokens();
    assertEquals(4, tokens.size());

    request.analyzer(null);
    request.tokenizer("whitespace");
    request.addTokenFilter("lowercase");
    request.addTokenFilter("word_delimiter");
    request.text("the qu1ck brown fox");
    analyze = TransportAnalyzeAction.analyze(request, AllFieldMapper.NAME, null, randomBoolean() ? indexAnalyzers : null, registry, environment);
    tokens = analyze.getTokens();
    assertEquals(6, tokens.size());
    assertEquals("qu", tokens.get(1).getTerm());
    assertEquals("1", tokens.get(2).getTerm());
    assertEquals("ck", tokens.get(3).getTerm());

    request.analyzer(null);
    request.tokenizer("whitespace");
    request.addCharFilter("html_strip");
    request.addTokenFilter("lowercase");
    request.addTokenFilter("word_delimiter");
    request.text("<p>the qu1ck brown fox</p>");
    analyze = TransportAnalyzeAction.analyze(request, AllFieldMapper.NAME, null, randomBoolean() ? indexAnalyzers : null, registry, environment);
    tokens = analyze.getTokens();
    assertEquals(6, tokens.size());
    assertEquals("the", tokens.get(0).getTerm());
    assertEquals("qu", tokens.get(1).getTerm());
    assertEquals("1", tokens.get(2).getTerm());
    assertEquals("ck", tokens.get(3).getTerm());
    assertEquals("brown", tokens.get(4).getTerm());
    assertEquals("fox", tokens.get(5).getTerm());
}
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入依赖的package包/类
public void testFillsAttributes() throws IOException {
    AnalyzeRequest request = new AnalyzeRequest();
    request.analyzer("standard");
    request.text("the 1 brown fox");
    AnalyzeResponse analyze = TransportAnalyzeAction.analyze(request, AllFieldMapper.NAME, null, null, registry, environment);
    List<AnalyzeResponse.AnalyzeToken> tokens = analyze.getTokens();
    assertEquals(4, tokens.size());
    assertEquals("the", tokens.get(0).getTerm());
    assertEquals(0, tokens.get(0).getStartOffset());
    assertEquals(3, tokens.get(0).getEndOffset());
    assertEquals(0, tokens.get(0).getPosition());
    assertEquals("<ALPHANUM>", tokens.get(0).getType());

    assertEquals("1", tokens.get(1).getTerm());
    assertEquals(4, tokens.get(1).getStartOffset());
    assertEquals(5, tokens.get(1).getEndOffset());
    assertEquals(1, tokens.get(1).getPosition());
    assertEquals("<NUM>", tokens.get(1).getType());

    assertEquals("brown", tokens.get(2).getTerm());
    assertEquals(6, tokens.get(2).getStartOffset());
    assertEquals(11, tokens.get(2).getEndOffset());
    assertEquals(2, tokens.get(2).getPosition());
    assertEquals("<ALPHANUM>", tokens.get(2).getType());

    assertEquals("fox", tokens.get(3).getTerm());
    assertEquals(12, tokens.get(3).getStartOffset());
    assertEquals(15, tokens.get(3).getEndOffset());
    assertEquals(3, tokens.get(3).getPosition());
    assertEquals("<ALPHANUM>", tokens.get(3).getType());
}
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入依赖的package包/类
public void testGetIndexAnalyserWithoutIndexAnalyzers() throws IOException {
    IllegalArgumentException e = expectThrows(IllegalArgumentException.class,
        () -> TransportAnalyzeAction.analyze(
            new AnalyzeRequest()
                .analyzer("custom_analyzer")
                .text("the qu1ck brown fox-dog"),
            AllFieldMapper.NAME, null, null, registry, environment));
    assertEquals(e.getMessage(), "failed to find global analyzer [custom_analyzer]");
}
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入依赖的package包/类
public void testNonPreBuildTokenFilter() throws IOException {
    AnalyzeRequest request = new AnalyzeRequest();
    request.tokenizer("whitespace");
    request.addTokenFilter("min_hash");
    request.text("the quick brown fox");
    AnalyzeResponse analyze = TransportAnalyzeAction.analyze(request, AllFieldMapper.NAME, null, indexAnalyzers, registry, environment);
    List<AnalyzeResponse.AnalyzeToken> tokens = analyze.getTokens();
    int default_hash_count = 1;
    int default_bucket_size = 512;
    int default_hash_set_size = 1;
    assertEquals(default_hash_count * default_bucket_size * default_hash_set_size, tokens.size());

}
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入依赖的package包/类
public void testAnalyze() {
    String analyzeShardAction = AnalyzeAction.NAME + "[s]";
    interceptTransportActions(analyzeShardAction);

    AnalyzeRequest analyzeRequest = new AnalyzeRequest(randomIndexOrAlias());
    analyzeRequest.text("text");
    internalCluster().coordOnlyNodeClient().admin().indices().analyze(analyzeRequest).actionGet();

    clearInterceptedActions();
    assertSameIndices(analyzeRequest, analyzeShardAction);
}
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入依赖的package包/类
@Override
public void handleRequest(final RestRequest request, final RestChannel channel, final Client client) {

    String[] texts = request.paramAsStringArrayOrEmptyIfAll("text");

    AnalyzeRequest analyzeRequest = new AnalyzeRequest(request.param("index"));
    analyzeRequest.text(texts);
    analyzeRequest.analyzer(request.param("analyzer"));
    analyzeRequest.field(request.param("field"));
    analyzeRequest.tokenizer(request.param("tokenizer"));
    analyzeRequest.tokenFilters(request.paramAsStringArray("filter", request.paramAsStringArray("token_filter",
        request.paramAsStringArray("token_filters", request.paramAsStringArray("filters", analyzeRequest.tokenFilters())))));
    analyzeRequest.charFilters(request.paramAsStringArray("char_filter", request.paramAsStringArray("char_filters", analyzeRequest.charFilters())));
    analyzeRequest.explain(request.paramAsBoolean("explain", false));
    analyzeRequest.attributes(request.paramAsStringArray("attributes", analyzeRequest.attributes()));

    if (RestActions.hasBodyContent(request)) {
        XContentType type = RestActions.guessBodyContentType(request);
        if (type == null) {
            if (texts == null || texts.length == 0) {
                texts = new String[]{ RestActions.getRestContent(request).toUtf8() };
                analyzeRequest.text(texts);
            }
        } else {
            // NOTE: if rest request with xcontent body has request parameters, the parameters does not override xcontent values
            buildFromContent(RestActions.getRestContent(request), analyzeRequest, parseFieldMatcher);
        }
    }

    client.admin().indices().analyze(analyzeRequest, new RestToXContentListener<AnalyzeResponse>(channel));
}
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入依赖的package包/类
@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());
    }
}
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入依赖的package包/类
@Test
public void testElasticsearchTemplateConnection() throws Exception {
    AnalyzeRequest analyzeRequest = new AnalyzeRequest();
    analyzeRequest.text("中华人民共和国");
    ActionFuture<AnalyzeResponse> analyzeResponseActionFuture =  elasticsearchTemplate.getClient().admin().indices().analyze(analyzeRequest);
    List<AnalyzeResponse.AnalyzeToken> analyzeTokens =  analyzeResponseActionFuture.actionGet().getTokens();
    for (AnalyzeResponse.AnalyzeToken analyzeToken  : analyzeTokens){
        System.out.println(analyzeToken.getTerm());
    }
}
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入依赖的package包/类
@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());
    }
}