common/org.gnit.lucenekmp.analysis.miscellaneous/ASCIIFoldingFilter

ASCIIFoldingFilter

class ASCIIFoldingFilter(input: TokenStream, val isPreserveOriginal: Boolean = false) : TokenFilter

This class converts alphabetic, numeric, and symbolic Unicode characters which are not in the first 127 ASCII characters (the "Basic Latin" Unicode block) into their ASCII equivalents, if one exists.

Characters from the following Unicode blocks are converted; however, only those characters with reasonable ASCII alternatives are converted:

C1 Controls and Latin-1 Supplement: http://www.unicode.org/charts/PDF/U0080.pdf
Latin Extended-A: http://www.unicode.org/charts/PDF/U0100.pdf
Latin Extended-B: http://www.unicode.org/charts/PDF/U0180.pdf
Latin Extended Additional: http://www.unicode.org/charts/PDF/U1E00.pdf
Latin Extended-C: http://www.unicode.org/charts/PDF/U2C60.pdf
Latin Extended-D: http://www.unicode.org/charts/PDF/UA720.pdf
IPA Extensions: http://www.unicode.org/charts/PDF/U0250.pdf
Phonetic Extensions: http://www.unicode.org/charts/PDF/U1D00.pdf
Phonetic Extensions Supplement: http://www.unicode.org/charts/PDF/U1D80.pdf
General Punctuation: http://www.unicode.org/charts/PDF/U2000.pdf
Superscripts and Subscripts: http://www.unicode.org/charts/PDF/U2070.pdf
Enclosed Alphanumerics: http://www.unicode.org/charts/PDF/U2460.pdf
Dingbats: http://www.unicode.org/charts/PDF/U2700.pdf
Supplemental Punctuation: http://www.unicode.org/charts/PDF/U2E00.pdf
Alphabetic Presentation Forms: http://www.unicode.org/charts/PDF/UFB00.pdf
Halfwidth and Fullwidth Forms: http://www.unicode.org/charts/PDF/UFF00.pdf

See: http://en.wikipedia.org/wiki/Latin_characters_in_Unicode

For example, '' will be replaced by 'a'.

Constructors

ASCIIFoldingFilter

constructor(input: TokenStream, isPreserveOriginal: Boolean = false)

Types

Companion

object Companion

Properties

attributeClassesIterator

val attributeClassesIterator: Iterator<Any>

attributeFactory

val attributeFactory: AttributeFactory

attributeImplsIterator

val attributeImplsIterator: Iterator<AttributeImpl>

isPreserveOriginal

val isPreserveOriginal: Boolean

Does the filter preserve the original tokens?

Functions

addAttribute

fun <T : Attribute> addAttribute(attClass: KClass<T>): T

addAttributeImpl

fun addAttributeImpl(att: AttributeImpl)

captureState

fun captureState(): AttributeSource.State?

clearAttributes

fun clearAttributes()

cloneAttributes

fun cloneAttributes(): AttributeSource

open override fun close()

copyTo

fun copyTo(target: AttributeSource)

end

open override fun end()

endAttributes

fun endAttributes()

equals

open operator override fun equals(obj: Any?): Boolean

foldToASCII

fun foldToASCII(input: CharArray, length: Int)

Converts characters above ASCII to their ASCII equivalents. For example, accents are removed from accented characters.

getAttribute

fun <T : Attribute> getAttribute(attClass: KClass<T>): T?

hasAttribute

fun hasAttribute(attClass: KClass<out Attribute>): Boolean

hasAttributes

fun hasAttributes(): Boolean

hashCode

open override fun hashCode(): Int

incrementToken

open override fun incrementToken(): Boolean

reflectAsString

fun reflectAsString(prependAttClass: Boolean): String

reflectWith

fun reflectWith(reflector: AttributeReflector)

removeAllAttributes

fun removeAllAttributes()

reset

open override fun reset()

restoreState

fun restoreState(state: AttributeSource.State?)

toString

open override fun toString(): String

unwrap

open override fun unwrap(): TokenStream