1// Copyright (c) 2018 Couchbase, Inc. 2// 3// Licensed under the Apache License, Version 2.0 (the "License"); 4// you may not use this file except in compliance with the License. 5// You may obtain a copy of the License at 6// 7// http://www.apache.org/licenses/LICENSE-2.0 8// 9// Unless required by applicable law or agreed to in writing, software 10// distributed under the License is distributed on an "AS IS" BASIS, 11// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 12// See the License for the specific language governing permissions and 13// limitations under the License. 14 15package hu 16 17import ( 18 "github.com/blevesearch/bleve/analysis" 19 "github.com/blevesearch/bleve/registry" 20 21 "github.com/blevesearch/snowballstem" 22 "github.com/blevesearch/snowballstem/hungarian" 23) 24 25const SnowballStemmerName = "stemmer_hu_snowball" 26 27type HungarianStemmerFilter struct { 28} 29 30func NewHungarianStemmerFilter() *HungarianStemmerFilter { 31 return &HungarianStemmerFilter{} 32} 33 34func (s *HungarianStemmerFilter) Filter(input analysis.TokenStream) analysis.TokenStream { 35 for _, token := range input { 36 env := snowballstem.NewEnv(string(token.Term)) 37 hungarian.Stem(env) 38 token.Term = []byte(env.Current()) 39 } 40 return input 41} 42 43func HungarianStemmerFilterConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.TokenFilter, error) { 44 return NewHungarianStemmerFilter(), nil 45} 46 47func init() { 48 registry.RegisterTokenFilter(SnowballStemmerName, HungarianStemmerFilterConstructor) 49} 50