final class WordDelimiterFilter
extends org.apache.lucene.analysis.TokenFilter
Modifier and Type | Class and Description |
---|---|
(package private) class |
WordDelimiterFilter.WordDelimiterConcatenation
A WDF concatenated 'run'
|
Modifier and Type | Field and Description |
---|---|
private int |
accumPosInc |
static int |
ALPHA |
static int |
ALPHANUM |
static int |
CATENATE_ALL
Causes all subword parts to be catenated:
"wi-fi-4000" => "wifi4000"
|
static int |
CATENATE_NUMBERS
Causes maximum runs of word parts to be catenated:
"wi-fi" => "wifi"
|
static int |
CATENATE_WORDS
Causes maximum runs of word parts to be catenated:
"wi-fi" => "wifi"
|
private WordDelimiterFilter.WordDelimiterConcatenation |
concat |
private WordDelimiterFilter.WordDelimiterConcatenation |
concatAll |
static int |
DIGIT |
private int |
flags |
static int |
GENERATE_NUMBER_PARTS
Causes number subwords to be generated:
"500-42" => "500" "42"
|
static int |
GENERATE_WORD_PARTS
Causes parts of words to be generated:
"PowerShot" => "Power" "Shot"
|
private boolean |
hasIllegalOffsets |
private boolean |
hasOutputFollowingOriginal |
private boolean |
hasOutputToken |
private boolean |
hasSavedState |
private WordDelimiterIterator |
iterator |
private int |
lastConcatCount |
static int |
LOWER |
private org.apache.lucene.analysis.tokenattributes.OffsetAttribute |
offsetAttribute |
private org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute |
posIncAttribute |
static int |
PRESERVE_ORIGINAL
Causes original words are preserved and added to the subword list (Defaults to false)
"500-42" => "500" "42" "500-42"
|
(package private) org.apache.lucene.analysis.CharArraySet |
protWords
If not null is the set of tokens to protect from being delimited
|
private char[] |
savedBuffer |
private int |
savedEndOffset |
private int |
savedStartOffset |
private java.lang.String |
savedType |
static int |
SPLIT_ON_CASE_CHANGE
If not set, causes case changes to be ignored (subwords will only be generated
given SUBWORD_DELIM tokens)
|
static int |
SPLIT_ON_NUMERICS
If not set, causes numeric changes to be ignored (subwords will only be generated
given SUBWORD_DELIM tokens).
|
static int |
STEM_ENGLISH_POSSESSIVE
Causes trailing "'s" to be removed for each subword
"O'Neil's" => "O", "Neil"
|
static int |
SUBWORD_DELIM |
private org.apache.lucene.analysis.tokenattributes.CharTermAttribute |
termAttribute |
private org.apache.lucene.analysis.tokenattributes.TypeAttribute |
typeAttribute |
static int |
UPPER |
Constructor and Description |
---|
WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in,
byte[] charTypeTable,
int configurationFlags,
org.apache.lucene.analysis.CharArraySet protWords)
Creates a new WordDelimiterFilter
|
WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in,
byte[] charTypeTable,
int generateWordParts,
int generateNumberParts,
int catenateWords,
int catenateNumbers,
int catenateAll)
Deprecated.
|
WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in,
byte[] charTypeTable,
int generateWordParts,
int generateNumberParts,
int catenateWords,
int catenateNumbers,
int catenateAll,
int splitOnCaseChange,
int preserveOriginal)
Deprecated.
|
WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in,
byte[] charTypeTable,
int generateWordParts,
int generateNumberParts,
int catenateWords,
int catenateNumbers,
int catenateAll,
int splitOnCaseChange,
int preserveOriginal,
int splitOnNumerics,
org.apache.lucene.analysis.CharArraySet protWords)
Deprecated.
|
WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in,
byte[] charTypeTable,
int generateWordParts,
int generateNumberParts,
int catenateWords,
int catenateNumbers,
int catenateAll,
int splitOnCaseChange,
int preserveOriginal,
int splitOnNumerics,
int stemEnglishPossessive,
org.apache.lucene.analysis.CharArraySet protWords)
Deprecated.
|
WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in,
int configurationFlags,
org.apache.lucene.analysis.CharArraySet protWords)
Creates a new WordDelimiterFilter using
WordDelimiterIterator.DEFAULT_WORD_DELIM_TABLE
as its charTypeTable |
WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in,
int generateWordParts,
int generateNumberParts,
int catenateWords,
int catenateNumbers,
int catenateAll)
Deprecated.
|
WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in,
int generateWordParts,
int generateNumberParts,
int catenateWords,
int catenateNumbers,
int catenateAll,
int splitOnCaseChange,
int preserveOriginal)
Deprecated.
|
WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in,
int generateWordParts,
int generateNumberParts,
int catenateWords,
int catenateNumbers,
int catenateAll,
int splitOnCaseChange,
int preserveOriginal,
int splitOnNumerics,
org.apache.lucene.analysis.CharArraySet protWords)
Deprecated.
|
WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in,
int generateWordParts,
int generateNumberParts,
int catenateWords,
int catenateNumbers,
int catenateAll,
int splitOnCaseChange,
int preserveOriginal,
int splitOnNumerics,
int stemEnglishPossessive,
org.apache.lucene.analysis.CharArraySet protWords)
Deprecated.
|
Modifier and Type | Method and Description |
---|---|
private void |
concatenate(WordDelimiterFilter.WordDelimiterConcatenation concatenation)
Concatenates the saved buffer to the given WordDelimiterConcatenation
|
private boolean |
flushConcatenation(WordDelimiterFilter.WordDelimiterConcatenation concatenation)
Flushes the given WordDelimiterConcatenation by either writing its concat and then clearing, or just clearing.
|
private void |
generatePart(boolean isSingleWord)
Generates a word/number part, updating the appropriate attributes
|
private boolean |
has(int flag)
Determines whether the given flag is set
|
boolean |
incrementToken() |
(package private) static boolean |
isAlpha(int type)
Checks if the given word type includes
ALPHA |
(package private) static boolean |
isDigit(int type)
Checks if the given word type includes
DIGIT |
(package private) static boolean |
isSubwordDelim(int type)
Checks if the given word type includes
SUBWORD_DELIM |
(package private) static boolean |
isUpper(int type)
Checks if the given word type includes
UPPER |
private int |
position(boolean inject)
Get the position increment gap for a subword or concatenation
|
void |
reset() |
private void |
saveState()
Saves the existing attribute states
|
private boolean |
shouldConcatenate(int wordType)
Determines whether to concatenate a word or number if the current word is the given type
|
private boolean |
shouldGenerateParts(int wordType)
Determines whether a word/number part should be generated for a word of the given type
|
addAttribute, addAttributeImpl, captureState, clearAttributes, cloneAttributes, copyTo, equals, getAttribute, getAttributeClassesIterator, getAttributeFactory, getAttributeImplsIterator, hasAttribute, hasAttributes, hashCode, reflectAsString, reflectWith, restoreState, toString
public static final int LOWER
public static final int UPPER
public static final int DIGIT
public static final int SUBWORD_DELIM
public static final int ALPHA
public static final int ALPHANUM
public static final int GENERATE_WORD_PARTS
public static final int GENERATE_NUMBER_PARTS
public static final int CATENATE_WORDS
public static final int CATENATE_NUMBERS
public static final int CATENATE_ALL
public static final int PRESERVE_ORIGINAL
public static final int SPLIT_ON_CASE_CHANGE
public static final int SPLIT_ON_NUMERICS
public static final int STEM_ENGLISH_POSSESSIVE
final org.apache.lucene.analysis.CharArraySet protWords
private final int flags
private final org.apache.lucene.analysis.tokenattributes.CharTermAttribute termAttribute
private final org.apache.lucene.analysis.tokenattributes.OffsetAttribute offsetAttribute
private final org.apache.lucene.analysis.tokenattributes.PositionIncrementAttribute posIncAttribute
private final org.apache.lucene.analysis.tokenattributes.TypeAttribute typeAttribute
private final WordDelimiterIterator iterator
private final WordDelimiterFilter.WordDelimiterConcatenation concat
private int lastConcatCount
private final WordDelimiterFilter.WordDelimiterConcatenation concatAll
private int accumPosInc
private char[] savedBuffer
private int savedStartOffset
private int savedEndOffset
private java.lang.String savedType
private boolean hasSavedState
private boolean hasIllegalOffsets
private boolean hasOutputToken
private boolean hasOutputFollowingOriginal
public WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in, byte[] charTypeTable, int configurationFlags, org.apache.lucene.analysis.CharArraySet protWords)
in
- TokenStream to be filteredcharTypeTable
- table containing character typesconfigurationFlags
- Flags configuring the filterprotWords
- If not null is the set of tokens to protect from being delimitedpublic WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in, int configurationFlags, org.apache.lucene.analysis.CharArraySet protWords)
WordDelimiterIterator.DEFAULT_WORD_DELIM_TABLE
as its charTypeTablein
- TokenStream to be filteredconfigurationFlags
- Flags configuring the filterprotWords
- If not null is the set of tokens to protect from being delimited@Deprecated public WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in, byte[] charTypeTable, int generateWordParts, int generateNumberParts, int catenateWords, int catenateNumbers, int catenateAll, int splitOnCaseChange, int preserveOriginal, int splitOnNumerics, int stemEnglishPossessive, org.apache.lucene.analysis.CharArraySet protWords)
WordDelimiterFilter(TokenStream, byte[], int, CharArraySet)
in
- Token stream to be filtered.charTypeTable
- table containing character typesgenerateWordParts
- If 1, causes parts of words to be generated: "PowerShot" => "Power" "Shot"generateNumberParts
- If 1, causes number subwords to be generated: "500-42" => "500" "42"catenateWords
- 1, causes maximum runs of word parts to be catenated: "wi-fi" => "wifi"catenateNumbers
- If 1, causes maximum runs of number parts to be catenated: "500-42" => "50042"catenateAll
- If 1, causes all subword parts to be catenated: "wi-fi-4000" => "wifi4000"splitOnCaseChange
- 1, causes "PowerShot" to be two tokens; ("Power-Shot" remains two parts regards)preserveOriginal
- If 1, includes original words in subwords: "500-42" => "500" "42" "500-42"splitOnNumerics
- 1, causes "j2se" to be three tokens; "j" "2" "se"stemEnglishPossessive
- If 1, causes trailing "'s" to be removed for each subword: "O'Neil's" => "O", "Neil"protWords
- If not null is the set of tokens to protect from being delimited@Deprecated public WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in, byte[] charTypeTable, int generateWordParts, int generateNumberParts, int catenateWords, int catenateNumbers, int catenateAll, int splitOnCaseChange, int preserveOriginal, int splitOnNumerics, org.apache.lucene.analysis.CharArraySet protWords)
WordDelimiterFilter(TokenStream, byte[], int, int, int, int, int, int, int, int, int, CharArraySet)
instead.@Deprecated public WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in, byte[] charTypeTable, int generateWordParts, int generateNumberParts, int catenateWords, int catenateNumbers, int catenateAll, int splitOnCaseChange, int preserveOriginal)
WordDelimiterFilter(TokenStream, byte[], int, int, int, int, int, int, int, int, int, CharArraySet)
instead.@Deprecated public WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in, int generateWordParts, int generateNumberParts, int catenateWords, int catenateNumbers, int catenateAll, int splitOnCaseChange, int preserveOriginal, int splitOnNumerics, int stemEnglishPossessive, org.apache.lucene.analysis.CharArraySet protWords)
WordDelimiterFilter(TokenStream, int, CharArraySet)
in
- Token stream to be filtered.generateWordParts
- If 1, causes parts of words to be generated: "PowerShot", "Power-Shot" => "Power" "Shot"generateNumberParts
- If 1, causes number subwords to be generated: "500-42" => "500" "42"catenateWords
- 1, causes maximum runs of word parts to be catenated: "wi-fi" => "wifi"catenateNumbers
- If 1, causes maximum runs of number parts to be catenated: "500-42" => "50042"catenateAll
- If 1, causes all subword parts to be catenated: "wi-fi-4000" => "wifi4000"splitOnCaseChange
- 1, causes "PowerShot" to be two tokens; ("Power-Shot" remains two parts regards)preserveOriginal
- If 1, includes original words in subwords: "500-42" => "500" "42" "500-42"splitOnNumerics
- 1, causes "j2se" to be three tokens; "j" "2" "se"stemEnglishPossessive
- If 1, causes trailing "'s" to be removed for each subword: "O'Neil's" => "O", "Neil"protWords
- If not null is the set of tokens to protect from being delimited@Deprecated public WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in, int generateWordParts, int generateNumberParts, int catenateWords, int catenateNumbers, int catenateAll, int splitOnCaseChange, int preserveOriginal, int splitOnNumerics, org.apache.lucene.analysis.CharArraySet protWords)
WordDelimiterFilter(TokenStream, int, int, int, int, int, int, int, int, int, CharArraySet)
instead.@Deprecated public WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in, int generateWordParts, int generateNumberParts, int catenateWords, int catenateNumbers, int catenateAll, int splitOnCaseChange, int preserveOriginal)
WordDelimiterFilter(TokenStream, int, int, int, int, int, int, int, int, int, CharArraySet)
instead.@Deprecated public WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in, byte[] charTypeTable, int generateWordParts, int generateNumberParts, int catenateWords, int catenateNumbers, int catenateAll)
WordDelimiterFilter(TokenStream, int, int, int, int, int, int, int, int, int, CharArraySet)
instead.@Deprecated public WordDelimiterFilter(org.apache.lucene.analysis.TokenStream in, int generateWordParts, int generateNumberParts, int catenateWords, int catenateNumbers, int catenateAll)
WordDelimiterFilter(TokenStream, int, int, int, int, int, int, int, int, int, CharArraySet)
instead.public boolean incrementToken() throws java.io.IOException
incrementToken
in class org.apache.lucene.analysis.TokenStream
java.io.IOException
public void reset() throws java.io.IOException
reset
in class org.apache.lucene.analysis.TokenFilter
java.io.IOException
private void saveState()
private boolean flushConcatenation(WordDelimiterFilter.WordDelimiterConcatenation concatenation)
concatenation
- WordDelimiterConcatenation that will be flushedtrue
if the concatenation was written before it was cleared, false otherwiseprivate boolean shouldConcatenate(int wordType)
wordType
- Type of the current word used to determine if it should be concatenatedtrue
if concatenation should occur, false
otherwiseprivate boolean shouldGenerateParts(int wordType)
wordType
- Type of the word used to determine if a word/number part should be generatedtrue
if a word/number part should be generated, false
otherwiseprivate void concatenate(WordDelimiterFilter.WordDelimiterConcatenation concatenation)
concatenation
- WordDelimiterConcatenation to concatenate the buffer toprivate void generatePart(boolean isSingleWord)
isSingleWord
- true
if the generation is occurring from a single word, false
otherwiseprivate int position(boolean inject)
inject
- true if this token wants to be injectedstatic boolean isAlpha(int type)
ALPHA
type
- Word type to checktrue
if the type contains ALPHA, false
otherwisestatic boolean isDigit(int type)
DIGIT
type
- Word type to checktrue
if the type contains DIGIT, false
otherwisestatic boolean isSubwordDelim(int type)
SUBWORD_DELIM
type
- Word type to checktrue
if the type contains SUBWORD_DELIM, false
otherwisestatic boolean isUpper(int type)
UPPER
type
- Word type to checktrue
if the type contains UPPER, false
otherwiseprivate boolean has(int flag)
flag
- Flag to see if set