Examples with TokenFilterFactory org.elasticsearch.index.analysis.TokenFilterFactory used on opensource projects

Example 1 with TokenFilterFactory

use of org.elasticsearch.index.analysis.TokenFilterFactory in project elasticsearch by elastic.

the class CommonGramsTokenFilterFactoryTests method testWithoutCommonWordsMatch.

public void testWithoutCommonWordsMatch() throws IOException {
    {
        Settings settings = Settings.builder().put("index.analysis.filter.common_grams_default.type", "common_grams").putArray("index.analysis.filter.common_grams_default.common_words", "chromosome", "protein").put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString()).build();
        ESTestCase.TestAnalysis analysis = AnalysisTestsHelper.createTestAnalysisFromSettings(settings);
        {
            TokenFilterFactory tokenFilter = analysis.tokenFilter.get("common_grams_default");
            String source = "the quick brown is a fox Or noT";
            String[] expected = new String[] { "the", "quick", "brown", "is", "a", "fox", "Or", "noT" };
            Tokenizer tokenizer = new WhitespaceTokenizer();
            tokenizer.setReader(new StringReader(source));
            assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
        }
    }
    {
        Settings settings = Settings.builder().put("index.analysis.filter.common_grams_default.type", "common_grams").put("index.analysis.filter.common_grams_default.query_mode", false).put(Environment.PATH_HOME_SETTING.getKey(), createTempDir().toString()).putArray("index.analysis.filter.common_grams_default.common_words", "chromosome", "protein").build();
        ESTestCase.TestAnalysis analysis = AnalysisTestsHelper.createTestAnalysisFromSettings(settings);
        {
            TokenFilterFactory tokenFilter = analysis.tokenFilter.get("common_grams_default");
            String source = "the quick brown is a fox Or noT";
            String[] expected = new String[] { "the", "quick", "brown", "is", "a", "fox", "Or", "noT" };
            Tokenizer tokenizer = new WhitespaceTokenizer();
            tokenizer.setReader(new StringReader(source));
            assertTokenStreamContents(tokenFilter.create(tokenizer), expected);
        }
    }
}

Example 2 with TokenFilterFactory

use of org.elasticsearch.index.analysis.TokenFilterFactory in project elasticsearch by elastic.

the class FragmentBuilderHelper method containsBrokenAnalysis.

private static boolean containsBrokenAnalysis(Analyzer analyzer) {
    // TODO maybe we need a getter on Namedanalyzer that tells if this uses broken Analysis
    if (analyzer instanceof NamedAnalyzer) {
        analyzer = ((NamedAnalyzer) analyzer).analyzer();
    }
    if (analyzer instanceof CustomAnalyzer) {
        final CustomAnalyzer a = (CustomAnalyzer) analyzer;
        TokenFilterFactory[] tokenFilters = a.tokenFilters();
        for (TokenFilterFactory tokenFilterFactory : tokenFilters) {
            if (tokenFilterFactory instanceof WordDelimiterTokenFilterFactory || tokenFilterFactory instanceof EdgeNGramTokenFilterFactory) {
                return true;
            }
        }
    }
    return false;
}

Example 3 with TokenFilterFactory

use of org.elasticsearch.index.analysis.TokenFilterFactory in project elasticsearch by elastic.

the class PhraseSuggestionBuilder method getShingleFilterFactory.

private static ShingleTokenFilterFactory.Factory getShingleFilterFactory(Analyzer analyzer) {
    if (analyzer instanceof NamedAnalyzer) {
        analyzer = ((NamedAnalyzer) analyzer).analyzer();
    }
    if (analyzer instanceof CustomAnalyzer) {
        final CustomAnalyzer a = (CustomAnalyzer) analyzer;
        final TokenFilterFactory[] tokenFilters = a.tokenFilters();
        for (TokenFilterFactory tokenFilterFactory : tokenFilters) {
            if (tokenFilterFactory instanceof ShingleTokenFilterFactory) {
                return ((ShingleTokenFilterFactory) tokenFilterFactory).getInnerFactory();
            } else if (tokenFilterFactory instanceof ShingleTokenFilterFactory.Factory) {
                return (ShingleTokenFilterFactory.Factory) tokenFilterFactory;
            }
        }
    }
    return null;
}

Example 4 with TokenFilterFactory

use of org.elasticsearch.index.analysis.TokenFilterFactory in project elasticsearch by elastic.

the class TransportAnalyzeAction method getTokenFilterFactories.

private static TokenFilterFactory[] getTokenFilterFactories(AnalyzeRequest request, IndexSettings indexSettings, AnalysisRegistry analysisRegistry, Environment environment, TokenFilterFactory[] tokenFilterFactories) throws IOException {
    if (request.tokenFilters() != null && request.tokenFilters().size() > 0) {
        tokenFilterFactories = new TokenFilterFactory[request.tokenFilters().size()];
        for (int i = 0; i < request.tokenFilters().size(); i++) {
            final AnalyzeRequest.NameOrDefinition tokenFilter = request.tokenFilters().get(i);
            // parse anonymous settings
            if (tokenFilter.definition != null) {
                Settings settings = getAnonymousSettings(tokenFilter.definition);
                String filterTypeName = settings.get("type");
                if (filterTypeName == null) {
                    throw new IllegalArgumentException("Missing [type] setting for anonymous token filter: " + tokenFilter.definition);
                }
                AnalysisModule.AnalysisProvider<TokenFilterFactory> tokenFilterFactoryFactory = analysisRegistry.getTokenFilterProvider(filterTypeName);
                if (tokenFilterFactoryFactory == null) {
                    throw new IllegalArgumentException("failed to find global token filter under [" + filterTypeName + "]");
                }
                // Need to set anonymous "name" of tokenfilter
                tokenFilterFactories[i] = tokenFilterFactoryFactory.get(getNaIndexSettings(settings), environment, "_anonymous_tokenfilter_[" + i + "]", settings);
            } else {
                AnalysisModule.AnalysisProvider<TokenFilterFactory> tokenFilterFactoryFactory;
                if (indexSettings == null) {
                    tokenFilterFactoryFactory = analysisRegistry.getTokenFilterProvider(tokenFilter.name);
                    if (tokenFilterFactoryFactory == null) {
                        throw new IllegalArgumentException("failed to find global token filter under [" + tokenFilter.name + "]");
                    }
                    tokenFilterFactories[i] = tokenFilterFactoryFactory.get(environment, tokenFilter.name);
                } else {
                    tokenFilterFactoryFactory = analysisRegistry.getTokenFilterProvider(tokenFilter.name, indexSettings);
                    if (tokenFilterFactoryFactory == null) {
                        throw new IllegalArgumentException("failed to find token filter under [" + tokenFilter.name + "]");
                    }
                    tokenFilterFactories[i] = tokenFilterFactoryFactory.get(indexSettings, environment, tokenFilter.name, AnalysisRegistry.getSettingsFromIndexSettings(indexSettings, AnalysisRegistry.INDEX_ANALYSIS_FILTER + "." + tokenFilter.name));
                }
            }
            if (tokenFilterFactories[i] == null) {
                throw new IllegalArgumentException("failed to find or create token filter under [" + tokenFilter.name + "]");
            }
        }
    }
    return tokenFilterFactories;
}

Example 5 with TokenFilterFactory

use of org.elasticsearch.index.analysis.TokenFilterFactory in project elasticsearch by elastic.

the class TransportAnalyzeAction method detailAnalyze.

private static DetailAnalyzeResponse detailAnalyze(AnalyzeRequest request, Analyzer analyzer, String field) {
    DetailAnalyzeResponse detailResponse;
    final Set<String> includeAttributes = new HashSet<>();
    if (request.attributes() != null) {
        for (String attribute : request.attributes()) {
            includeAttributes.add(attribute.toLowerCase(Locale.ROOT));
        }
    }
    CustomAnalyzer customAnalyzer = null;
    if (analyzer instanceof CustomAnalyzer) {
        customAnalyzer = (CustomAnalyzer) analyzer;
    } else if (analyzer instanceof NamedAnalyzer && ((NamedAnalyzer) analyzer).analyzer() instanceof CustomAnalyzer) {
        customAnalyzer = (CustomAnalyzer) ((NamedAnalyzer) analyzer).analyzer();
    }
    if (customAnalyzer != null) {
        // customAnalyzer = divide charfilter, tokenizer tokenfilters
        CharFilterFactory[] charFilterFactories = customAnalyzer.charFilters();
        TokenizerFactory tokenizerFactory = customAnalyzer.tokenizerFactory();
        TokenFilterFactory[] tokenFilterFactories = customAnalyzer.tokenFilters();
        String[][] charFiltersTexts = new String[charFilterFactories != null ? charFilterFactories.length : 0][request.text().length];
        TokenListCreator[] tokenFiltersTokenListCreator = new TokenListCreator[tokenFilterFactories != null ? tokenFilterFactories.length : 0];
        TokenListCreator tokenizerTokenListCreator = new TokenListCreator();
        for (int textIndex = 0; textIndex < request.text().length; textIndex++) {
            String charFilteredSource = request.text()[textIndex];
            Reader reader = new FastStringReader(charFilteredSource);
            if (charFilterFactories != null) {
                for (int charFilterIndex = 0; charFilterIndex < charFilterFactories.length; charFilterIndex++) {
                    reader = charFilterFactories[charFilterIndex].create(reader);
                    Reader readerForWriteOut = new FastStringReader(charFilteredSource);
                    readerForWriteOut = charFilterFactories[charFilterIndex].create(readerForWriteOut);
                    charFilteredSource = writeCharStream(readerForWriteOut);
                    charFiltersTexts[charFilterIndex][textIndex] = charFilteredSource;
                }
            }
            // analyzing only tokenizer
            Tokenizer tokenizer = tokenizerFactory.create();
            tokenizer.setReader(reader);
            tokenizerTokenListCreator.analyze(tokenizer, customAnalyzer, field, includeAttributes);
            // analyzing each tokenfilter
            if (tokenFilterFactories != null) {
                for (int tokenFilterIndex = 0; tokenFilterIndex < tokenFilterFactories.length; tokenFilterIndex++) {
                    if (tokenFiltersTokenListCreator[tokenFilterIndex] == null) {
                        tokenFiltersTokenListCreator[tokenFilterIndex] = new TokenListCreator();
                    }
                    TokenStream stream = createStackedTokenStream(request.text()[textIndex], charFilterFactories, tokenizerFactory, tokenFilterFactories, tokenFilterIndex + 1);
                    tokenFiltersTokenListCreator[tokenFilterIndex].analyze(stream, customAnalyzer, field, includeAttributes);
                }
            }
        }
        DetailAnalyzeResponse.CharFilteredText[] charFilteredLists = new DetailAnalyzeResponse.CharFilteredText[charFiltersTexts.length];
        if (charFilterFactories != null) {
            for (int charFilterIndex = 0; charFilterIndex < charFiltersTexts.length; charFilterIndex++) {
                charFilteredLists[charFilterIndex] = new DetailAnalyzeResponse.CharFilteredText(charFilterFactories[charFilterIndex].name(), charFiltersTexts[charFilterIndex]);
            }
        }
        DetailAnalyzeResponse.AnalyzeTokenList[] tokenFilterLists = new DetailAnalyzeResponse.AnalyzeTokenList[tokenFiltersTokenListCreator.length];
        if (tokenFilterFactories != null) {
            for (int tokenFilterIndex = 0; tokenFilterIndex < tokenFiltersTokenListCreator.length; tokenFilterIndex++) {
                tokenFilterLists[tokenFilterIndex] = new DetailAnalyzeResponse.AnalyzeTokenList(tokenFilterFactories[tokenFilterIndex].name(), tokenFiltersTokenListCreator[tokenFilterIndex].getArrayTokens());
            }
        }
        detailResponse = new DetailAnalyzeResponse(charFilteredLists, new DetailAnalyzeResponse.AnalyzeTokenList(tokenizerFactory.name(), tokenizerTokenListCreator.getArrayTokens()), tokenFilterLists);
    } else {
        String name;
        if (analyzer instanceof NamedAnalyzer) {
            name = ((NamedAnalyzer) analyzer).name();
        } else {
            name = analyzer.getClass().getName();
        }
        TokenListCreator tokenListCreator = new TokenListCreator();
        for (String text : request.text()) {
            tokenListCreator.analyze(analyzer.tokenStream(field, text), analyzer, field, includeAttributes);
        }
        detailResponse = new DetailAnalyzeResponse(new DetailAnalyzeResponse.AnalyzeTokenList(name, tokenListCreator.getArrayTokens()));
    }
    return detailResponse;
}