gsebleve

README

gse-bleve

Use

package main

import (
	"fmt"
	"os"

	"github.com/blevesearch/bleve/v2"
	gse "github.com/vcaesar/gse-bleve"
)

func main() {
	opt := gse.Option{
		Index: "test.blv",
		Dicts: "emend, zh", Stop: "",
		Opt: "search-hmm", Trim: "trim"}

	index, err := gse.New(opt)
	if err != nil {
		fmt.Println("new mapping error is: ", err)
	}

	text := `他在命运的沉浮中随波逐流, 扮演着受害与加害者的双重角色`
	err = index.Index("1", text)
	index.Index("3", text+"沉浮")
	index.Index("4", `In view, a humble vaudevillian veteran cast vicariously as both victim and villain vicissitudes of fate.`)
	index.Index("2", `It's difficult to understand the sum of a person's life.`)
	if err != nil {
		fmt.Println("index error: ", err)
	}

	query := "命运的沉浮"
	req := bleve.NewSearchRequest(bleve.NewQueryStringQuery(query))
	req.Highlight = bleve.NewHighlight()
	res, err := index.Search(req)
	fmt.Println(res, err)

	os.RemoveAll("test.blv")
}

Documentation

Index

• Constants
• func New(opt Option) (bleve.Index, error)
• func NewMapping(opt Option) (*mapping.IndexMappingImpl, error)
• func NewMem(opt Option) (bleve.Index, error)
• type GseCut
  • func NewGse(dicts, stop, opt, trim string) (*GseCut, error)
  • func (c *GseCut) Cut(text string, opt string) []string
  • func (c *GseCut) Tokenize(text []byte) analysis.TokenStream
  • func (c *GseCut) Trim(s []string) []string
• type Option

Constants

const (
	TokenName = "gse"
)

Functions

func New

func New(opt Option) (bleve.Index, error)

New new bleve index

func NewMapping

func NewMapping(opt Option) (*mapping.IndexMappingImpl, error)

NewMapping new bleve index mapping

func NewMem

func NewMem(opt Option) (bleve.Index, error)

NewMem new bleve index only memory

Types

type GseCut

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

GseCut gse cut token structure

func NewGse

func NewGse(dicts, stop, opt, trim string) (*GseCut, error)

NewGseCut create a gse cut tokenizer

func (*GseCut) Cut

func (c *GseCut) Cut(text string, opt string) []string

Cut option the gse cut mode

func (*GseCut) Tokenize

func (c *GseCut) Tokenize(text []byte) analysis.TokenStream

Tokenize cut the text to bleve token stream

func (*GseCut) Trim

func (c *GseCut) Trim(s []string) []string

Trim trim the unused token string

type Option

type Option struct {
	Index                  string
	Dicts, Stop, Opt, Trim string
}

Option gse bleve option structure