case class Document(rawInput: String, firstNonAdjacent: Array[Int], lang: LanguageInfo) extends Product with Serializable
- firstNonAdjacent
for a given index 'i' it keeps a first index 'j' greater or equal 'i' -- such that isAdjacentSeparator (indexable ! j) == False -- eg. " a document " :: Document -- firstNonAdjacent = [1,1,3,3,4,5,6,7,8,9,10,12] -- Note that in this case 12 is the length of the vector, hence not a -- valid index inside the array, this is intentional.
- Alphabetic
- By Inheritance
- Document
- Serializable
- Product
- Equals
- AnyRef
- Any
- Hide All
- Show All
- Public
- Protected
Instance Constructors
- new Document(rawInput: String, firstNonAdjacent: Array[Int], lang: LanguageInfo)
- firstNonAdjacent
for a given index 'i' it keeps a first index 'j' greater or equal 'i' -- such that isAdjacentSeparator (indexable ! j) == False -- eg. " a document " :: Document -- firstNonAdjacent = [1,1,3,3,4,5,6,7,8,9,10,12] -- Note that in this case 12 is the length of the vector, hence not a -- valid index inside the array, this is intentional.
Value Members
- def !(i: Int): Char
- final def !=(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
- final def ##: Int
- Definition Classes
- AnyRef → Any
- final def ==(arg0: Any): Boolean
- Definition Classes
- AnyRef → Any
- def adjacentToken(node: Node): Option[TokenLabel]
- final def asInstanceOf[T0]: T0
- Definition Classes
- Any
- def clone(): AnyRef
- Attributes
- protected[java.lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.CloneNotSupportedException]) @native()
- def dependencyChildren: Map[Int, List[DependencyEdge]]
- def deps(token: TokenLabel): List[DependencyEdge]
- final def eq(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- def finalize(): Unit
- Attributes
- protected[java.lang]
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.Throwable])
- def findCoveredToken(start: Int, end: Int): Option[TokenLabel]
- def findToken(start: Int, end: Int): Option[TokenLabel]
- val firstNonAdjacent: Array[Int]
- final def getClass(): Class[_ <: AnyRef]
- Definition Classes
- AnyRef → Any
- Annotations
- @native()
- def indexOfToken(offset: Int): Int
- def isAdjacent(a: Int, b: Int): Boolean
True iff a is followed by whitespaces and b.
- def isChinese(c: Char): Boolean
摘自knowledge-base-langs,避免循环依赖
- final def isInstanceOf[T0]: Boolean
- Definition Classes
- Any
- def isPositionValid(position: Int)(node: Node): Boolean
- def isRangeValid(start: Int, end: Int): Boolean
As regexes are matched without whitespace delimitator, we need to check the reasonability of the match to actually be a word.
- val lang: LanguageInfo
- def length: Int
- final def ne(arg0: AnyRef): Boolean
- Definition Classes
- AnyRef
- final def notify(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
- final def notifyAll(): Unit
- Definition Classes
- AnyRef
- Annotations
- @native()
- def numTokens: Int
- def phrase(start: Int, end: Int): String
- def productElementNames: Iterator[String]
- Definition Classes
- Product
- val rawInput: String
- def stringFromPos(position: Int): (String, (Int, Int) => String, (Int, Int) => (Int, Int))
- def substring(range: Range): String
- def substring(node: Node): String
- def substring(s: Int, t: Int): String
- final def synchronized[T0](arg0: => T0): T0
- Definition Classes
- AnyRef
- def toString(): String
- Definition Classes
- Document → AnyRef → Any
- def token(i: Int): TokenLabel
- def tokens: Array[TokenLabel]
- val validSequenceHeads: Set[Int]
sequence优化,不是该起始点的均会被丢弃
- final def wait(): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- final def wait(arg0: Long, arg1: Int): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException])
- final def wait(arg0: Long): Unit
- Definition Classes
- AnyRef
- Annotations
- @throws(classOf[java.lang.InterruptedException]) @native()
- def word(i: Int): String