LangBundle

Abstract Value Members

abstract def stopwords: Set[String]

Language specific stopwords

Concrete Value Members

final def !=(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def !=(arg0: Any): Boolean

Definition Classes
Any
final def ##(): Int

Definition Classes
AnyRef → Any
final def ==(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def ==(arg0: Any): Boolean

Definition Classes
Any
final def asInstanceOf[T0]: T0

Definition Classes
Any
def clone(): AnyRef

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( ... )
final def eq(arg0: AnyRef): Boolean

Definition Classes
AnyRef
def equals(arg0: Any): Boolean

Definition Classes
AnyRef → Any
def finalize(): Unit

Attributes
protected[java.lang]
Definition Classes
AnyRef
Annotations
@throws( classOf[java.lang.Throwable] )
final def getClass(): Class[_]

Definition Classes
AnyRef → Any
def hashCode(): Int

Definition Classes
AnyRef → Any
def isContentTerm(term: String): Boolean

Whether the string is probably a linguistic term with meaning
def isHashtag(term: String): Boolean

Whether the string can could be a social media hashtag
final def isInstanceOf[T0]: Boolean

Definition Classes
Any
def isMention(term: String): Boolean

Whether the string could be a social media @-mention
final def ne(arg0: AnyRef): Boolean

Definition Classes
AnyRef
final def notify(): Unit

Definition Classes
AnyRef
final def notifyAll(): Unit

Definition Classes
AnyRef
final def synchronized[T0](arg0: ⇒ T0): T0

Definition Classes
AnyRef
def termBigrams(tokens: Seq[String]): Set[String]

Extract the set of term-only bigrams from the token sequence
Extract the set of term-only bigrams from the token sequence
For example from the text "this is the winning team" only the bigram "winning team" would be extracted
tokens
the token sequence to extract n-grams from
def termBigrams(text: String): Set[String]

Extract the set of term-only bigrams from the text
Extract the set of term-only bigrams from the text
For example from the text "this is the winning team" only the bigram "winning team" would be extracted
text
the text to extract n-grams from
def termNgrams(tokens: Seq[String], min: Int, max: Int): Set[String]

Extract the set of term-only n-grams from the token sequence
Extract the set of term-only n-grams from the token sequence
For example from the text "this is the winning team" only the bigram "winning team" would be extracted
tokens
the token sequence to extract n-grams from
min
the minimum length of extracted n-grams
max
the maximum length of extracted n-grams
def termNgrams(text: String, min: Int, max: Int): Set[String]

Extract the set of term-only n-grams from the text
Extract the set of term-only n-grams from the text
For example from the text "this is the winning team" only the bigram "winning team" would be extracted
text
the text to extract n-grams from
min
the minimum length of extracted n-grams
max
the maximum length of extracted n-grams
def termTrigrams(tokens: Seq[String]): Set[String]

Extract the set of term-only bigrams from the text
Extract the set of term-only bigrams from the text
For example from the text "this is red sox nation" only the trigram "red sox nation" would be extracted
tokens
the token sequence to extract n-grams from
def termTrigrams(text: String): Set[String]

Extract the set of term-only bigrams from the text
Extract the set of term-only bigrams from the text
For example from the text "this is red sox nation" only the trigram "red sox nation" would be extracted
text
the text to extract n-grams from
def terms(tokens: Seq[String]): Set[String]

Extract terms from the sequence of tokens
def terms(text: String): Set[String]

Tokenize the string and extract the set of terms
def termsPlus(tokens: Seq[String]): Set[String]

Extract terms plus hashtags, emoji, @-mentions from the token sequence
def termsPlus(text: String): Set[String]

Tokenize the string and extract terms plus hashtags, emoji, @-mentions
def toString(): String

Definition Classes
AnyRef → Any
def tokens(text: String): Vector[String]

Parse text into an array of String
Parse text into an array of String
text
text to tokenize
final def wait(): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long, arg1: Int): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )
final def wait(arg0: Long): Unit

Definition Classes
AnyRef
Annotations
@throws( ... )

trait LangBundle extends AnyRef

Abstract Value Members

abstract def stopwords: Set[String]

Concrete Value Members

final def !=(arg0: AnyRef): Boolean

final def !=(arg0: Any): Boolean

final def ##(): Int

final def ==(arg0: AnyRef): Boolean

final def ==(arg0: Any): Boolean

final def asInstanceOf[T0]: T0

def clone(): AnyRef

final def eq(arg0: AnyRef): Boolean

def equals(arg0: Any): Boolean

def finalize(): Unit

final def getClass(): Class[_]

def hashCode(): Int

def isContentTerm(term: String): Boolean

def isHashtag(term: String): Boolean

final def isInstanceOf[T0]: Boolean

def isMention(term: String): Boolean

final def ne(arg0: AnyRef): Boolean

final def notify(): Unit

final def notifyAll(): Unit

final def synchronized[T0](arg0: ⇒ T0): T0

def termBigrams(tokens: Seq[String]): Set[String]

def termBigrams(text: String): Set[String]

def termNgrams(tokens: Seq[String], min: Int, max: Int): Set[String]

def termNgrams(text: String, min: Int, max: Int): Set[String]

def termTrigrams(tokens: Seq[String]): Set[String]

def termTrigrams(text: String): Set[String]

def terms(tokens: Seq[String]): Set[String]

def terms(text: String): Set[String]

def termsPlus(tokens: Seq[String]): Set[String]

def termsPlus(text: String): Set[String]

def toString(): String

def tokens(text: String): Vector[String]

final def wait(): Unit

final def wait(arg0: Long, arg1: Int): Unit

final def wait(arg0: Long): Unit

Inherited from AnyRef

Inherited from Any

Ungrouped