| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"arabicNormalization" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final char | 
ALEF | 
1575 | 
public static final char | 
ALEF_HAMZA_ABOVE | 
1571 | 
public static final char | 
ALEF_HAMZA_BELOW | 
1573 | 
public static final char | 
ALEF_MADDA | 
1570 | 
public static final char | 
DAMMA | 
1615 | 
public static final char | 
DAMMATAN | 
1612 | 
public static final char | 
DOTLESS_YEH | 
1609 | 
public static final char | 
FATHA | 
1614 | 
public static final char | 
FATHATAN | 
1611 | 
public static final char | 
HEH | 
1607 | 
public static final char | 
KASRA | 
1616 | 
public static final char | 
KASRATAN | 
1613 | 
public static final char | 
SHADDA | 
1617 | 
public static final char | 
SUKUN | 
1618 | 
public static final char | 
TATWEEL | 
1600 | 
public static final char | 
TEH_MARBUTA | 
1577 | 
public static final char | 
YEH | 
1610 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"arabicStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final char | 
ALEF | 
1575 | 
public static final char | 
BEH | 
1576 | 
public static final char | 
FEH | 
1601 | 
public static final char | 
HEH | 
1607 | 
public static final char | 
KAF | 
1603 | 
public static final char | 
LAM | 
1604 | 
public static final char | 
NOON | 
1606 | 
public static final char | 
TEH | 
1578 | 
public static final char | 
TEH_MARBUTA | 
1577 | 
public static final char | 
WAW | 
1608 | 
public static final char | 
YEH | 
1610 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"bulgarianStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"bengaliNormalization" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"bengaliStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final char | 
DEFAULT_DELIMITER | 
124 | 
public static final String | 
DELIMITER_ATTR | 
"delimiter" | 
public static final String | 
NAME | 
"delimitedBoost" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"brazilianStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"htmlStrip" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"mapping" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DOUBLE_TYPE | 
"<DOUBLE>" | 
public static final int | 
HAN | 
1 | 
public static final int | 
HANGUL | 
8 | 
public static final int | 
HIRAGANA | 
2 | 
public static final int | 
KATAKANA | 
4 | 
public static final String | 
SINGLE_TYPE | 
"<SINGLE>" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"cjkBigram" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"cjkWidth" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"soraniNormalization" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"soraniStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
GRAM_TYPE | 
"gram" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"commonGrams" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"commonGramsQuery" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
DEFAULT_MAX_SUBWORD_SIZE | 
15 | 
public static final int | 
DEFAULT_MIN_SUBWORD_SIZE | 
2 | 
public static final int | 
DEFAULT_MIN_WORD_SIZE | 
5 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"dictionaryCompoundWord" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"hyphenationCompoundWord" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
protected static final int | 
BLOCK_SIZE | 
2048 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"decimalDigit" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"flattenGraph" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
DEFAULT_BUFFER_SIZE | 
256 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"keyword" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"letter" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"lowercase" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
FORMAT_SNOWBALL | 
"snowball" | 
public static final String | 
FORMAT_WORDSET | 
"wordset" | 
public static final String | 
NAME | 
"stop" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"type" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"uppercase" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"whitespace" | 
public static final String | 
RULE_JAVA | 
"java" | 
public static final String | 
RULE_UNICODE | 
"unicode" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"czechStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"danish_stop.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"german_stop.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"germanLightStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"germanMinimalStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"germanNormalization" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"germanStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"greekLowercase" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"greekStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"englishMinimalStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"englishPossessive" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"kStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"porterStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"spanish_stop.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"spanishLightStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"spanishMinimalStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
public static final String | 
STOPWORDS_COMMENT | 
"#" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"persian" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"persianNormalization" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final char | 
FARSI_YEH | 
1740 | 
public static final char | 
HAMZA_ABOVE | 
1620 | 
public static final char | 
HEH | 
1607 | 
public static final char | 
HEH_GOAL | 
1729 | 
public static final char | 
HEH_YEH | 
1728 | 
public static final char | 
KAF | 
1603 | 
public static final char | 
KEHEH | 
1705 | 
public static final char | 
YEH | 
1610 | 
public static final char | 
YEH_BARREE | 
1746 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"finnish_stop.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"finnishLightStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"french_stop.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"frenchLightStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"frenchMinimalStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"irishLowercase" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"galicianMinimalStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"galicianStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"hindiNormalization" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"hindiStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"hungarian_stop.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"hungarianLightStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"hunspellStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"indonesianStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"indicNormalization" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"italian_stop.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"italianLightStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"latvianStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
DEFAULT_BUCKET_COUNT | 
512 | 
public static final int | 
DEFAULT_HASH_COUNT | 
1 | 
public static final int | 
DEFAULT_HASH_SET_SIZE | 
1 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"minHash" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"asciiFolding" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
DEFAULT_MAX_TOKEN_LENGTH | 
2147483647 | 
public static final int | 
DEFAULT_MAX_WORD_COUNT | 
2147483647 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
FORCE_FIRST_LETTER | 
"forceFirstLetter" | 
public static final String | 
KEEP | 
"keep" | 
public static final String | 
KEEP_IGNORE_CASE | 
"keepIgnoreCase" | 
public static final String | 
MAX_TOKEN_LENGTH | 
"maxTokenLength" | 
public static final String | 
MAX_WORD_COUNT | 
"maxWordCount" | 
public static final String | 
MIN_WORD_LENGTH | 
"minWordLength" | 
public static final String | 
NAME | 
"capitalization" | 
public static final String | 
OK_PREFIX | 
"okPrefix" | 
public static final String | 
ONLY_FIRST_WORD | 
"onlyFirstWord" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
MAX_KEY | 
"max" | 
public static final String | 
MIN_KEY | 
"min" | 
public static final String | 
NAME | 
"codepointCount" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
DEFAULT_MAX_GRAPH_EXPANSIONS | 
10000 | 
public static final boolean | 
DEFAULT_PRESERVE_POSITION_INCREMENTS | 
true | 
public static final boolean | 
DEFAULT_PRESERVE_SEP | 
true | 
public static final int | 
SEP_LABEL | 
31 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"concatenateGraph" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"conditional" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DATE_TYPE | 
"date" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DATE_PATTERN | 
"datePattern" | 
public static final String | 
LOCALE | 
"locale" | 
public static final String | 
NAME | 
"dateRecognizer" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final char | 
DEFAULT_DELIMITER | 
124 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DELIMITER_ATTR | 
"delimiter" | 
public static final String | 
NAME | 
"delimitedTermFrequency" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
DEFAULT_MAX_OUTPUT_TOKEN_SIZE | 
1024 | 
public static final char | 
DEFAULT_SEPARATOR | 
32 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
MAX_OUTPUT_TOKEN_SIZE_KEY | 
"maxOutputTokenSize" | 
public static final String | 
NAME | 
"fingerprint" | 
public static final String | 
SEPARATOR_KEY | 
"separator" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"fixBrokenOffsets" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"hyphenatedWords" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"keepWord" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"keywordMarker" | 
public static final String | 
PATTERN | 
"pattern" | 
public static final String | 
PROTECTED_TOKENS | 
"protected" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"keywordRepeat" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
MAX_KEY | 
"max" | 
public static final String | 
MIN_KEY | 
"min" | 
public static final String | 
NAME | 
"length" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
CONSUME_ALL_TOKENS_KEY | 
"consumeAllTokens" | 
public static final String | 
MAX_TOKEN_COUNT_KEY | 
"maxTokenCount" | 
public static final String | 
NAME | 
"limitTokenCount" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
CONSUME_ALL_TOKENS_KEY | 
"consumeAllTokens" | 
public static final String | 
MAX_START_OFFSET | 
"maxStartOffset" | 
public static final String | 
NAME | 
"limitTokenOffset" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
CONSUME_ALL_TOKENS_KEY | 
"consumeAllTokens" | 
public static final String | 
MAX_TOKEN_POSITION_KEY | 
"maxTokenPosition" | 
public static final String | 
NAME | 
"limitTokenPosition" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final char | 
FILTER_ARG_SEPARATOR | 
46 | 
public static final char | 
FILTER_NAME_ID_SEPARATOR | 
45 | 
public static final String | 
NAME | 
"protectedTerm" | 
public static final String | 
PROTECTED_TERMS | 
"protected" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"removeDuplicates" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"scandinavianFolding" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"scandinavianNormalization" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"stemmerOverride" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"trim" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"truncate" | 
public static final String | 
PREFIX_LENGTH_KEY | 
"prefixLength" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"typeAsSynonym" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
ALPHA | 
3 | 
public static final int | 
ALPHANUM | 
7 | 
public static final int | 
CATENATE_ALL | 
16 | 
public static final int | 
CATENATE_NUMBERS | 
8 | 
public static final int | 
CATENATE_WORDS | 
4 | 
public static final int | 
DIGIT | 
4 | 
public static final int | 
GENERATE_NUMBER_PARTS | 
2 | 
public static final int | 
GENERATE_WORD_PARTS | 
1 | 
public static final int | 
IGNORE_KEYWORDS | 
512 | 
public static final int | 
LOWER | 
1 | 
public static final int | 
PRESERVE_ORIGINAL | 
32 | 
public static final int | 
SPLIT_ON_CASE_CHANGE | 
64 | 
public static final int | 
SPLIT_ON_NUMERICS | 
128 | 
public static final int | 
STEM_ENGLISH_POSSESSIVE | 
256 | 
public static final int | 
SUBWORD_DELIM | 
8 | 
public static final int | 
UPPER | 
2 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"wordDelimiter" | 
public static final String | 
PROTECTED_TOKENS | 
"protected" | 
public static final String | 
TYPES | 
"types" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
CATENATE_ALL | 
16 | 
public static final int | 
CATENATE_NUMBERS | 
8 | 
public static final int | 
CATENATE_WORDS | 
4 | 
public static final int | 
GENERATE_NUMBER_PARTS | 
2 | 
public static final int | 
GENERATE_WORD_PARTS | 
1 | 
public static final int | 
IGNORE_KEYWORDS | 
512 | 
public static final int | 
PRESERVE_ORIGINAL | 
32 | 
public static final int | 
SPLIT_ON_CASE_CHANGE | 
64 | 
public static final int | 
SPLIT_ON_NUMERICS | 
128 | 
public static final int | 
STEM_ENGLISH_POSSESSIVE | 
256 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"wordDelimiterGraph" | 
public static final String | 
OFFSETS | 
"adjustOffsets" | 
public static final String | 
PROTECTED_TOKENS | 
"protected" | 
public static final String | 
TYPES | 
"types" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
ALPHA | 
3 | 
public static final int | 
ALPHANUM | 
7 | 
public static final int | 
DONE | 
-1 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"edgeNGram" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final boolean | 
DEFAULT_PRESERVE_ORIGINAL | 
false | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
DEFAULT_MAX_GRAM_SIZE | 
1 | 
public static final int | 
DEFAULT_MIN_GRAM_SIZE | 
1 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"edgeNGram" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"nGram" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final boolean | 
DEFAULT_PRESERVE_ORIGINAL | 
false | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
DEFAULT_MAX_NGRAM_SIZE | 
2 | 
public static final int | 
DEFAULT_MIN_NGRAM_SIZE | 
1 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"nGram" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"dutch_stop.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"norwegian_stop.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"norwegianLightStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
BOKMAAL | 
1 | 
public static final int | 
NYNORSK | 
2 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"norwegianMinimalStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final char | 
DEFAULT_DELIMITER | 
47 | 
public static final int | 
DEFAULT_SKIP | 
0 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"pathHierarchy" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final char | 
DEFAULT_DELIMITER | 
47 | 
public static final int | 
DEFAULT_SKIP | 
0 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"patternCaptureGroup" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"patternReplace" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"patternReplace" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
GROUP | 
"group" | 
public static final String | 
NAME | 
"pattern" | 
public static final String | 
PATTERN | 
"pattern" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"simplePatternSplit" | 
public static final String | 
PATTERN | 
"pattern" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"simplePattern" | 
public static final String | 
PATTERN | 
"pattern" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final char | 
DEFAULT_DELIMITER | 
124 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DELIMITER_ATTR | 
"delimiter" | 
public static final String | 
ENCODER_ATTR | 
"encoder" | 
public static final String | 
NAME | 
"delimitedPayload" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"numericPayload" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"tokenOffsetPayload" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"typeAsPayload" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"portuguese_stop.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"portugueseLightStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"portugueseMinimalStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"portugueseStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final float | 
defaultMaxDocFreqPercent | 
0.4000000059604645f | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final char | 
INFORMATION_SEPARATOR_MARKER | 
31 | 
public static final char | 
PUA_EC00_MARKER | 
60416 | 
public static final char | 
RTL_DIRECTION_MARKER | 
8207 | 
public static final char | 
START_OF_HEADING_MARKER | 
1 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"reverseString" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"russian_stop.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"russianLightStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"fixedShingle" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_FILLER_TOKEN | 
"_" | 
public static final int | 
DEFAULT_MAX_SHINGLE_SIZE | 
2 | 
public static final int | 
DEFAULT_MIN_SHINGLE_SIZE | 
2 | 
public static final String | 
DEFAULT_TOKEN_SEPARATOR | 
" " | 
public static final String | 
DEFAULT_TOKEN_TYPE | 
"shingle" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"shingle" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"snowballPorter" | 
public static final String | 
PROTECTED_TOKENS | 
"protected" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"serbianNormalization" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
DEFAULT_MAX_TOKEN_LENGTH | 
255 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"classic" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
ACRONYM | 
2 | 
public static final int | 
ACRONYM_DEP | 
8 | 
public static final int | 
ALPHANUM | 
0 | 
public static final int | 
APOSTROPHE | 
1 | 
public static final int | 
CJ | 
7 | 
public static final int | 
COMPANY | 
3 | 
public static final int | 
EMAIL | 
4 | 
public static final int | 
HOST | 
5 | 
public static final int | 
NUM | 
6 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"classic" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"standard" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
DEFAULT_MAX_TOKEN_LENGTH | 
255 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
ALPHANUM | 
0 | 
public static final int | 
EMAIL | 
8 | 
public static final int | 
EMOJI | 
9 | 
public static final int | 
HANGUL | 
6 | 
public static final int | 
HIRAGANA | 
4 | 
public static final int | 
IDEOGRAPHIC | 
3 | 
public static final int | 
KATAKANA | 
5 | 
public static final int | 
MAX_TOKEN_LENGTH_LIMIT | 
1048576 | 
public static final int | 
NUM | 
1 | 
public static final int | 
SOUTHEAST_ASIAN | 
2 | 
public static final int | 
URL | 
7 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"uax29UrlEmail" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
AVOID_BAD_URL | 
2 | 
public static final int | 
EMAIL_TYPE | 
8 | 
public static final int | 
EMOJI_TYPE | 
9 | 
public static final int | 
HANGUL_TYPE | 
6 | 
public static final int | 
HIRAGANA_TYPE | 
4 | 
public static final int | 
IDEOGRAPHIC_TYPE | 
3 | 
public static final int | 
KATAKANA_TYPE | 
5 | 
public static final int | 
NUMERIC_TYPE | 
1 | 
public static final int | 
SOUTH_EAST_ASIAN_TYPE | 
2 | 
public static final int | 
URL_TYPE | 
7 | 
public static final int | 
WORD_TYPE | 
0 | 
public static final int | 
YYEOF | 
-1 | 
public static final int | 
YYINITIAL | 
0 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"swedish_stop.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"swedishLightStem" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
TYPE_SYNONYM | 
"SYNONYM" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"synonym" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
TYPE_SYNONYM | 
"SYNONYM" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"synonymGraph" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final char | 
WORD_SEPARATOR | 
0 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"thai" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"apostrophe" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
DEFAULT_STOPWORD_FILE | 
"stopwords.txt" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"turkishLowercase" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
LUCENE_MATCH_VERSION_PARAM | 
"luceneMatchVersion" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
DEFAULT_MAX_WORD_LEN | 
255 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"elision" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
protected static final int | 
BUFFERMAX | 
1024 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
UNICODE_VERSION | 
"11.0.0.0" | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final int | 
ACRONYM_ID | 
2 | 
public static final int | 
ALPHANUM_ID | 
0 | 
public static final int | 
APOSTROPHE_ID | 
1 | 
public static final String | 
BOLD | 
"b" | 
public static final int | 
BOLD_ID | 
12 | 
public static final String | 
BOLD_ITALICS | 
"bi" | 
public static final int | 
BOLD_ITALICS_ID | 
14 | 
public static final int | 
BOTH | 
2 | 
public static final String | 
CATEGORY | 
"c" | 
public static final int | 
CATEGORY_ID | 
11 | 
public static final String | 
CITATION | 
"ci" | 
public static final int | 
CITATION_ID | 
10 | 
public static final int | 
CJ_ID | 
7 | 
public static final int | 
COMPANY_ID | 
3 | 
public static final int | 
EMAIL_ID | 
4 | 
public static final String | 
EXTERNAL_LINK | 
"el" | 
public static final int | 
EXTERNAL_LINK_ID | 
9 | 
public static final String | 
EXTERNAL_LINK_URL | 
"elu" | 
public static final int | 
EXTERNAL_LINK_URL_ID | 
17 | 
public static final String | 
HEADING | 
"h" | 
public static final int | 
HEADING_ID | 
15 | 
public static final int | 
HOST_ID | 
5 | 
public static final String | 
INTERNAL_LINK | 
"il" | 
public static final int | 
INTERNAL_LINK_ID | 
8 | 
public static final String | 
ITALICS | 
"i" | 
public static final int | 
ITALICS_ID | 
13 | 
public static final int | 
NUM_ID | 
6 | 
public static final String | 
SUB_HEADING | 
"sh" | 
public static final int | 
SUB_HEADING_ID | 
16 | 
public static final int | 
TOKENS_ONLY | 
0 | 
public static final int | 
UNTOKENIZED_ONLY | 
1 | 
public static final int | 
UNTOKENIZED_TOKEN_FLAG | 
1 | 
| Modifier and Type | Constant Field | Value | 
|---|---|---|
public static final String | 
NAME | 
"wikipedia" | 
public static final String | 
TOKEN_OUTPUT | 
"tokenOutput" | 
public static final String | 
UNTOKENIZED_TYPES | 
"untokenizedTypes" | 
Copyright © 2000-2020 Apache Software Foundation. All Rights Reserved.