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 regexp
16
17import (
18	"bytes"
19	"fmt"
20	"regexp"
21
22	"github.com/blevesearch/bleve/analysis"
23	"github.com/blevesearch/bleve/registry"
24)
25
26const Name = "regexp"
27
28type CharFilter struct {
29	r           *regexp.Regexp
30	replacement []byte
31}
32
33func New(r *regexp.Regexp, replacement []byte) *CharFilter {
34	return &CharFilter{
35		r:           r,
36		replacement: replacement,
37	}
38}
39
40func (s *CharFilter) Filter(input []byte) []byte {
41	return s.r.ReplaceAllFunc(input, func(in []byte) []byte { return bytes.Repeat(s.replacement, len(in)) })
42}
43
44func CharFilterConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.CharFilter, error) {
45	regexpStr, ok := config["regexp"].(string)
46	if !ok {
47		return nil, fmt.Errorf("must specify regexp")
48	}
49	r, err := regexp.Compile(regexpStr)
50	if err != nil {
51		return nil, fmt.Errorf("unable to build regexp char filter: %v", err)
52	}
53	replaceBytes := []byte(" ")
54	replaceStr, ok := config["replace"].(string)
55	if ok {
56		replaceBytes = []byte(replaceStr)
57	}
58	return New(r, replaceBytes), nil
59}
60
61func init() {
62	registry.RegisterCharFilter(Name, CharFilterConstructor)
63}
64