jieba

Documentation

Index

• Constants
• type HmmSeg
• type Keyword
  • func (kw *Keyword) String() string
• type ModeStyle
• type SegToken
  • func (st *SegToken) String() string
• type Segment
  • func (seg *Segment) ToString(sentence []rune) string
• type SegmentHandler
  • func MewSegmentHandler(dictRootPath string) (*SegmentHandler, error)
  • func (h *SegmentHandler) SegParagraph(s string, mode ModeStyle) []*SegToken
• type Tfidf
  • func NewTfidf(rootPath string, segHandler *SegmentHandler) (Tfidf, error)
• type Trie

Constants

const (
	BaseDictName    = "dict.txt"
	UserDictDirName = "user"
	BaseProbName    = "prob_emit.txt"
)

Types

type HmmSeg

type HmmSeg interface {
	Cut(statement []rune) []string
}

type Keyword

type Keyword struct {
	Word       string
	TfidfValue float64
}

func (*Keyword) String

func (kw *Keyword) String() string

type ModeStyle

type ModeStyle int

const ModeIndex ModeStyle = 1

const ModeSearch ModeStyle = 0

type SegToken

type SegToken struct {
	Word  string
	Start int
	End   int
}

func (*SegToken) String

func (st *SegToken) String() string

type Segment

type Segment struct {
	Start int
	End   int
}

func (*Segment) ToString

func (seg *Segment) ToString(sentence []rune) string

type SegmentHandler

type SegmentHandler struct {
	// contains filtered or unexported fields
}

func MewSegmentHandler

func MewSegmentHandler(dictRootPath string) (*SegmentHandler, error)

func (*SegmentHandler) SegParagraph

func (h *SegmentHandler) SegParagraph(s string, mode ModeStyle) []*SegToken

type Tfidf

type Tfidf interface {
	TopN(input []rune, n int) []*Keyword
	TopNByString(input string, n int) []*Keyword
}

func NewTfidf

func NewTfidf(rootPath string, segHandler *SegmentHandler) (Tfidf, error)

type Trie

type Trie interface {
	Match(sentence []rune) []*Segment
	ExistShortWord(word string) bool
}