Java AnalyzeRequest.text方法代码示例

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入方法依赖的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; //导入方法依赖的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; //导入方法依赖的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; //导入方法依赖的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; //导入方法依赖的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; //导入方法依赖的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; //导入方法依赖的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; //导入方法依赖的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; //导入方法依赖的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());
    }
}
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入方法依赖的package包/类
static void buildFromContent(XContentParser parser, AnalyzeRequest analyzeRequest)
        throws IOException {
    if (parser.nextToken() != XContentParser.Token.START_OBJECT) {
        throw new IllegalArgumentException("Malformed content, must start with an object");
    } else {
        XContentParser.Token token;
        String currentFieldName = null;
        while ((token = parser.nextToken()) != XContentParser.Token.END_OBJECT) {
            if (token == XContentParser.Token.FIELD_NAME) {
                currentFieldName = parser.currentName();
            } else if (Fields.TEXT.match(currentFieldName) && token == XContentParser.Token.VALUE_STRING) {
                analyzeRequest.text(parser.text());
            } else if (Fields.TEXT.match(currentFieldName) && token == XContentParser.Token.START_ARRAY) {
                List<String> texts = new ArrayList<>();
                while ((token = parser.nextToken()) != XContentParser.Token.END_ARRAY) {
                    if (token.isValue() == false) {
                        throw new IllegalArgumentException(currentFieldName + " array element should only contain text");
                    }
                    texts.add(parser.text());
                }
                analyzeRequest.text(texts.toArray(new String[texts.size()]));
            } else if (Fields.ANALYZER.match(currentFieldName) && token == XContentParser.Token.VALUE_STRING) {
                analyzeRequest.analyzer(parser.text());
            } else if (Fields.FIELD.match(currentFieldName) && token == XContentParser.Token.VALUE_STRING) {
                analyzeRequest.field(parser.text());
            } else if (Fields.TOKENIZER.match(currentFieldName)) {
                if (token == XContentParser.Token.VALUE_STRING) {
                    analyzeRequest.tokenizer(parser.text());
                } else if (token == XContentParser.Token.START_OBJECT) {
                    analyzeRequest.tokenizer(parser.map());
                } else {
                    throw new IllegalArgumentException(currentFieldName + " should be tokenizer's name or setting");
                }
            } else if (Fields.TOKEN_FILTERS.match(currentFieldName)
                    && token == XContentParser.Token.START_ARRAY) {
                while ((token = parser.nextToken()) != XContentParser.Token.END_ARRAY) {
                    if (token == XContentParser.Token.VALUE_STRING) {
                        analyzeRequest.addTokenFilter(parser.text());
                    } else if (token == XContentParser.Token.START_OBJECT) {
                        analyzeRequest.addTokenFilter(parser.map());
                    } else {
                        throw new IllegalArgumentException(currentFieldName
                                + " array element should contain filter's name or setting");
                    }
                }
            } else if (Fields.CHAR_FILTERS.match(currentFieldName)
                    && token == XContentParser.Token.START_ARRAY) {
                while ((token = parser.nextToken()) != XContentParser.Token.END_ARRAY) {
                    if (token == XContentParser.Token.VALUE_STRING) {
                        analyzeRequest.addCharFilter(parser.text());
                    } else if (token == XContentParser.Token.START_OBJECT) {
                        analyzeRequest.addCharFilter(parser.map());
                    } else {
                        throw new IllegalArgumentException(currentFieldName
                                + " array element should contain char filter's name or setting");
                    }
                }
            } else if (Fields.EXPLAIN.match(currentFieldName)) {
                if (parser.isBooleanValue()) {
                    analyzeRequest.explain(parser.booleanValue());
                } else {
                    throw new IllegalArgumentException(currentFieldName + " must be either 'true' or 'false'");
                }
            } else if (Fields.ATTRIBUTES.match(currentFieldName) && token == XContentParser.Token.START_ARRAY) {
                List<String> attributes = new ArrayList<>();
                while ((token = parser.nextToken()) != XContentParser.Token.END_ARRAY) {
                    if (token.isValue() == false) {
                        throw new IllegalArgumentException(currentFieldName + " array element should only contain attribute name");
                    }
                    attributes.add(parser.text());
                }
                analyzeRequest.attributes(attributes.toArray(new String[attributes.size()]));
            } else {
                throw new IllegalArgumentException("Unknown parameter ["
                        + currentFieldName + "] in request body or parameter is of the wrong type[" + token + "] ");
            }
        }
    }
}
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入方法依赖的package包/类
public void testWithIndexAnalyzers() throws IOException {

        AnalyzeRequest request = new AnalyzeRequest();
        request.analyzer("standard");
        request.text("the quick brown fox");
        request.analyzer("custom_analyzer");
        request.text("the qu1ck brown fox");
        AnalyzeResponse analyze = TransportAnalyzeAction.analyze(request, AllFieldMapper.NAME, null, indexAnalyzers, registry, environment);
        List<AnalyzeResponse.AnalyzeToken> tokens = analyze.getTokens();
        assertEquals(4, tokens.size());

        request.analyzer("whitespace");
        request.text("the qu1ck brown fox-dog");
        analyze = TransportAnalyzeAction.analyze(request, AllFieldMapper.NAME, null, indexAnalyzers, registry, environment);
        tokens = analyze.getTokens();
        assertEquals(4, tokens.size());

        request.analyzer("custom_analyzer");
        request.text("the qu1ck brown fox-dog");
        analyze = TransportAnalyzeAction.analyze(request, AllFieldMapper.NAME, null, indexAnalyzers, registry, environment);
        tokens = analyze.getTokens();
        assertEquals(5, tokens.size());

        request.analyzer(null);
        request.tokenizer("whitespace");
        request.addTokenFilter("lowercase");
        request.addTokenFilter("wordDelimiter");
        request.text("the qu1ck brown fox-dog");
        analyze = TransportAnalyzeAction.analyze(request, AllFieldMapper.NAME, null, indexAnalyzers, registry, environment);
        tokens = analyze.getTokens();
        assertEquals(5, tokens.size());
        assertEquals("the", tokens.get(0).getTerm());
        assertEquals("qu1ck", tokens.get(1).getTerm());
        assertEquals("brown", tokens.get(2).getTerm());
        assertEquals("fox", tokens.get(3).getTerm());
        assertEquals("dog", tokens.get(4).getTerm());

        request.analyzer(null);
        request.tokenizer("trigram");
        request.addTokenFilter("synonym");
        request.text("kimchy");
        analyze = TransportAnalyzeAction.analyze(request, AllFieldMapper.NAME, null, indexAnalyzers, registry, environment);
        tokens = analyze.getTokens();
        assertEquals(2, tokens.size());
        assertEquals("sha", tokens.get(0).getTerm());
        assertEquals("hay", tokens.get(1).getTerm());
    }
 

import org.elasticsearch.action.admin.indices.analyze.AnalyzeRequest; //导入方法依赖的package包/类
public static void buildFromContent(BytesReference content, AnalyzeRequest analyzeRequest, ParseFieldMatcher parseFieldMatcher) {
    try (XContentParser parser = XContentHelper.createParser(content)) {
        if (parser.nextToken() != XContentParser.Token.START_OBJECT) {
            throw new IllegalArgumentException("Malforrmed content, must start with an object");
        } else {
            XContentParser.Token token;
            String currentFieldName = null;
            while ((token = parser.nextToken()) != XContentParser.Token.END_OBJECT) {
                if (token == XContentParser.Token.FIELD_NAME) {
                    currentFieldName = parser.currentName();
                } else if (parseFieldMatcher.match(currentFieldName, Fields.TEXT) && token == XContentParser.Token.VALUE_STRING) {
                    analyzeRequest.text(parser.text());
                } else if (parseFieldMatcher.match(currentFieldName, Fields.TEXT) && token == XContentParser.Token.START_ARRAY) {
                    List<String> texts = new ArrayList<>();
                    while ((token = parser.nextToken()) != XContentParser.Token.END_ARRAY) {
                        if (token.isValue() == false) {
                            throw new IllegalArgumentException(currentFieldName + " array element should only contain text");
                        }
                        texts.add(parser.text());
                    }
                    analyzeRequest.text(texts.toArray(new String[texts.size()]));
                } else if (parseFieldMatcher.match(currentFieldName, Fields.ANALYZER) && token == XContentParser.Token.VALUE_STRING) {
                    analyzeRequest.analyzer(parser.text());
                } else if (parseFieldMatcher.match(currentFieldName, Fields.FIELD) && token == XContentParser.Token.VALUE_STRING) {
                    analyzeRequest.field(parser.text());
                } else if (parseFieldMatcher.match(currentFieldName, Fields.TOKENIZER) && token == XContentParser.Token.VALUE_STRING) {
                    analyzeRequest.tokenizer(parser.text());
                } else if (parseFieldMatcher.match(currentFieldName, Fields.TOKEN_FILTERS) && token == XContentParser.Token.START_ARRAY) {
                    List<String> filters = new ArrayList<>();
                    while ((token = parser.nextToken()) != XContentParser.Token.END_ARRAY) {
                        if (token.isValue() == false) {
                            throw new IllegalArgumentException(currentFieldName + " array element should only contain token filter's name");
                        }
                        filters.add(parser.text());
                    }
                    analyzeRequest.tokenFilters(filters.toArray(new String[filters.size()]));
                } else if (parseFieldMatcher.match(currentFieldName, Fields.CHAR_FILTERS) && token == XContentParser.Token.START_ARRAY) {
                    List<String> charFilters = new ArrayList<>();
                    while ((token = parser.nextToken()) != XContentParser.Token.END_ARRAY) {
                        if (token.isValue() == false) {
                            throw new IllegalArgumentException(currentFieldName + " array element should only contain char filter's name");
                        }
                        charFilters.add(parser.text());
                    }
                    analyzeRequest.charFilters(charFilters.toArray(new String[charFilters.size()]));
                } else if (parseFieldMatcher.match(currentFieldName, Fields.EXPLAIN)) {
                    if (parser.isBooleanValue()) {
                        analyzeRequest.explain(parser.booleanValue());
                    } else {
                        throw new IllegalArgumentException(currentFieldName + " must be either 'true' or 'false'");
                    }
                } else if (parseFieldMatcher.match(currentFieldName, Fields.ATTRIBUTES) && token == XContentParser.Token.START_ARRAY){
                    List<String> attributes = new ArrayList<>();
                    while ((token = parser.nextToken()) != XContentParser.Token.END_ARRAY) {
                        if (token.isValue() == false) {
                            throw new IllegalArgumentException(currentFieldName + " array element should only contain attribute name");
                        }
                        attributes.add(parser.text());
                    }
                    analyzeRequest.attributes(attributes.toArray(new String[attributes.size()]));
                } else {
                    throw new IllegalArgumentException("Unknown parameter [" + currentFieldName + "] in request body or parameter is of the wrong type[" + token + "] ");
                }
            }
        }
    } catch (IOException e) {
        throw new IllegalArgumentException("Failed to parse request body", e);
    }
}