1// Copyright (c) 2014 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 zerowidthnonjoiner 16 17import ( 18 "regexp" 19 20 "github.com/blevesearch/bleve/analysis" 21 regexpCharFilter "github.com/blevesearch/bleve/analysis/char/regexp" 22 "github.com/blevesearch/bleve/registry" 23) 24 25const Name = "zero_width_spaces" 26 27var zeroWidthNonJoinerRegexp = regexp.MustCompile(`\x{200C}`) 28 29func CharFilterConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.CharFilter, error) { 30 replaceBytes := []byte(" ") 31 return regexpCharFilter.New(zeroWidthNonJoinerRegexp, replaceBytes), nil 32} 33 34func init() { 35 registry.RegisterCharFilter(Name, CharFilterConstructor) 36} 37