Java Code Examples for org.elasticsearch.index.analysis.Analysis#getWordSet()

public AbstractCompoundWordTokenFilterFactory(Index index, Settings indexSettings, Environment env, @Assisted String name, @Assisted Settings settings) {
    super(index, indexSettings, name, settings);

    minWordSize = settings.getAsInt("min_word_size", CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE);
    minSubwordSize = settings.getAsInt("min_subword_size", CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE);
    maxSubwordSize = settings.getAsInt("max_subword_size", CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE);
    onlyLongestMatch = settings.getAsBoolean("only_longest_match", false);
    wordList = Analysis.getWordSet(env, settings, "word_list");
    if (wordList == null) {
        throw new IllegalArgumentException("word_list must be provided for [" + name + "], either as a path to a file, or directly");
    }
}
 

public WordDelimiterTokenFilterFactory(IndexSettings indexSettings, Environment env,
        String name, Settings settings) {
    super(indexSettings, name, settings);

    // Sample Format for the type table:
    // $ => DIGIT
    // % => DIGIT
    // . => DIGIT
    // \u002C => DIGIT
    // \u200D => ALPHANUM
    List<String> charTypeTableValues = Analysis.getWordList(env, settings, "type_table");
    if (charTypeTableValues == null) {
        this.charTypeTable = WordDelimiterIterator.DEFAULT_WORD_DELIM_TABLE;
    } else {
        this.charTypeTable = parseTypes(charTypeTableValues);
    }
    int flags = 0;
    // If set, causes parts of words to be generated: "PowerShot" => "Power" "Shot"
    flags |= getFlag(GENERATE_WORD_PARTS, settings, "generate_word_parts", true);
    // If set, causes number subwords to be generated: "500-42" => "500" "42"
    flags |= getFlag(GENERATE_NUMBER_PARTS, settings, "generate_number_parts", true);
    // 1, causes maximum runs of word parts to be catenated: "wi-fi" => "wifi"
    flags |= getFlag(CATENATE_WORDS, settings, "catenate_words", false);
    // If set, causes maximum runs of number parts to be catenated: "500-42" => "50042"
    flags |= getFlag(CATENATE_NUMBERS, settings, "catenate_numbers", false);
    // If set, causes all subword parts to be catenated: "wi-fi-4000" => "wifi4000"
    flags |= getFlag(CATENATE_ALL, settings, "catenate_all", false);
    // 1, causes "PowerShot" to be two tokens; ("Power-Shot" remains two parts regards)
    flags |= getFlag(SPLIT_ON_CASE_CHANGE, settings, "split_on_case_change", true);
    // If set, includes original words in subwords: "500-42" => "500" "42" "500-42"
    flags |= getFlag(PRESERVE_ORIGINAL, settings, "preserve_original", false);
    // 1, causes "j2se" to be three tokens; "j" "2" "se"
    flags |= getFlag(SPLIT_ON_NUMERICS, settings, "split_on_numerics", true);
    // If set, causes trailing "'s" to be removed for each subword: "O'Neil's" => "O", "Neil"
    flags |= getFlag(STEM_ENGLISH_POSSESSIVE, settings, "stem_english_possessive", true);
    // If not null is the set of tokens to protect from being delimited
    Set<?> protectedWords = Analysis.getWordSet(env, settings, "protected_words");
    this.protoWords = protectedWords == null ? null : CharArraySet.copy(protectedWords);
    this.flags = flags;
}
 

protected AbstractCompoundWordTokenFilterFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, name, settings);

    minWordSize = settings.getAsInt("min_word_size", CompoundWordTokenFilterBase.DEFAULT_MIN_WORD_SIZE);
    minSubwordSize = settings.getAsInt("min_subword_size", CompoundWordTokenFilterBase.DEFAULT_MIN_SUBWORD_SIZE);
    maxSubwordSize = settings.getAsInt("max_subword_size", CompoundWordTokenFilterBase.DEFAULT_MAX_SUBWORD_SIZE);
    onlyLongestMatch = settings.getAsBoolean("only_longest_match", false);
    wordList = Analysis.getWordSet(env, settings, "word_list");
    if (wordList == null) {
        throw new IllegalArgumentException("word_list must be provided for [" + name + "], either as a path to a file, or directly");
    }
}
 

public WordDelimiterGraphTokenFilterFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, name, settings);

    // Sample Format for the type table:
    // $ => DIGIT
    // % => DIGIT
    // . => DIGIT
    // \u002C => DIGIT
    // \u200D => ALPHANUM
    List<String> charTypeTableValues = Analysis.getWordList(env, settings, "type_table");
    if (charTypeTableValues == null) {
        this.charTypeTable = WordDelimiterIterator.DEFAULT_WORD_DELIM_TABLE;
    } else {
        this.charTypeTable = parseTypes(charTypeTableValues);
    }
    int flags = 0;
    // If set, causes parts of words to be generated: "PowerShot" => "Power" "Shot"
    flags |= getFlag(GENERATE_WORD_PARTS, settings, "generate_word_parts", true);
    // If set, causes number subwords to be generated: "500-42" => "500" "42"
    flags |= getFlag(GENERATE_NUMBER_PARTS, settings, "generate_number_parts", true);
    // 1, causes maximum runs of word parts to be catenated: "wi-fi" => "wifi"
    flags |= getFlag(CATENATE_WORDS, settings, "catenate_words", false);
    // If set, causes maximum runs of number parts to be catenated: "500-42" => "50042"
    flags |= getFlag(CATENATE_NUMBERS, settings, "catenate_numbers", false);
    // If set, causes all subword parts to be catenated: "wi-fi-4000" => "wifi4000"
    flags |= getFlag(CATENATE_ALL, settings, "catenate_all", false);
    // 1, causes "PowerShot" to be two tokens; ("Power-Shot" remains two parts regards)
    flags |= getFlag(SPLIT_ON_CASE_CHANGE, settings, "split_on_case_change", true);
    // If set, includes original words in subwords: "500-42" => "500" "42" "500-42"
    flags |= getFlag(PRESERVE_ORIGINAL, settings, "preserve_original", false);
    // 1, causes "j2se" to be three tokens; "j" "2" "se"
    flags |= getFlag(SPLIT_ON_NUMERICS, settings, "split_on_numerics", true);
    // If set, causes trailing "'s" to be removed for each subword: "O'Neil's" => "O", "Neil"
    flags |= getFlag(STEM_ENGLISH_POSSESSIVE, settings, "stem_english_possessive", true);
    // If not null is the set of tokens to protect from being delimited
    Set<?> protectedWords = Analysis.getWordSet(env, settings, "protected_words");
    this.protoWords = protectedWords == null ? null : CharArraySet.copy(protectedWords);
    this.flags = flags;
    this.adjustOffsets = settings.getAsBoolean("adjust_offsets", true);
}
 

KeepWordFilterFactory(IndexSettings indexSettings, Environment env, String name, Settings settings) {
    super(indexSettings, name, settings);

    final List<String> arrayKeepWords = settings.getAsList(KEEP_WORDS_KEY, null);
    final String keepWordsPath = settings.get(KEEP_WORDS_PATH_KEY, null);
    if ((arrayKeepWords == null && keepWordsPath == null) || (arrayKeepWords != null && keepWordsPath != null)) {
        // we don't allow both or none
        throw new IllegalArgumentException("keep requires either `" + KEEP_WORDS_KEY + "` or `"
                + KEEP_WORDS_PATH_KEY + "` to be configured");
    }
    if (settings.get(ENABLE_POS_INC_KEY) != null) {
        throw new IllegalArgumentException(ENABLE_POS_INC_KEY + " is not supported anymore. Please fix your analysis chain");
    }
    this.keepWords = Analysis.getWordSet(env, settings, KEEP_WORDS_KEY);
}