c526a38369
ultimately this is make it more convenient for us to wire up different elements of the analysis pipeline, without having to preload everything into memory before we need it separately the index layer now has a mechanism for storing internal key/value pairs. this is expected to be used to store the mapping, and possibly other pieces of data by the top layer, but not exposed to the user at the top.
148 lines
5.1 KiB
Go
148 lines
5.1 KiB
Go
// Copyright (c) 2014 Couchbase, Inc.
|
|
// Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file
|
|
// except in compliance with the License. You may obtain a copy of the License at
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
// Unless required by applicable law or agreed to in writing, software distributed under the
|
|
// License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,
|
|
// either express or implied. See the License for the specific language governing permissions
|
|
// and limitations under the License.
|
|
package hi
|
|
|
|
import (
|
|
"bytes"
|
|
"unicode/utf8"
|
|
|
|
"github.com/couchbaselabs/bleve/analysis"
|
|
"github.com/couchbaselabs/bleve/registry"
|
|
)
|
|
|
|
const StemmerName = "stemmer_hi"
|
|
|
|
type HindiStemmerFilter struct {
|
|
}
|
|
|
|
func NewHindiStemmerFilter() *HindiStemmerFilter {
|
|
return &HindiStemmerFilter{}
|
|
}
|
|
|
|
func (s *HindiStemmerFilter) Filter(input analysis.TokenStream) analysis.TokenStream {
|
|
rv := make(analysis.TokenStream, 0)
|
|
|
|
for _, token := range input {
|
|
// if not protected keyword, stem it
|
|
if !token.KeyWord {
|
|
stemmed := stem(token.Term)
|
|
token.Term = stemmed
|
|
}
|
|
rv = append(rv, token)
|
|
}
|
|
|
|
return rv
|
|
}
|
|
|
|
func stem(input []byte) []byte {
|
|
inputLen := utf8.RuneCount(input)
|
|
|
|
// 5
|
|
if inputLen > 6 &&
|
|
(bytes.HasSuffix(input, []byte("ाएंगी")) ||
|
|
bytes.HasSuffix(input, []byte("ाएंगे")) ||
|
|
bytes.HasSuffix(input, []byte("ाऊंगी")) ||
|
|
bytes.HasSuffix(input, []byte("ाऊंगा")) ||
|
|
bytes.HasSuffix(input, []byte("ाइयाँ")) ||
|
|
bytes.HasSuffix(input, []byte("ाइयों")) ||
|
|
bytes.HasSuffix(input, []byte("ाइयां"))) {
|
|
return analysis.TruncateRunes(input, 5)
|
|
}
|
|
|
|
// 4
|
|
if inputLen > 5 &&
|
|
(bytes.HasSuffix(input, []byte("ाएगी")) ||
|
|
bytes.HasSuffix(input, []byte("ाएगा")) ||
|
|
bytes.HasSuffix(input, []byte("ाओगी")) ||
|
|
bytes.HasSuffix(input, []byte("ाओगे")) ||
|
|
bytes.HasSuffix(input, []byte("एंगी")) ||
|
|
bytes.HasSuffix(input, []byte("ेंगी")) ||
|
|
bytes.HasSuffix(input, []byte("एंगे")) ||
|
|
bytes.HasSuffix(input, []byte("ेंगे")) ||
|
|
bytes.HasSuffix(input, []byte("ूंगी")) ||
|
|
bytes.HasSuffix(input, []byte("ूंगा")) ||
|
|
bytes.HasSuffix(input, []byte("ातीं")) ||
|
|
bytes.HasSuffix(input, []byte("नाओं")) ||
|
|
bytes.HasSuffix(input, []byte("नाएं")) ||
|
|
bytes.HasSuffix(input, []byte("ताओं")) ||
|
|
bytes.HasSuffix(input, []byte("ताएं")) ||
|
|
bytes.HasSuffix(input, []byte("ियाँ")) ||
|
|
bytes.HasSuffix(input, []byte("ियों")) ||
|
|
bytes.HasSuffix(input, []byte("ियां"))) {
|
|
return analysis.TruncateRunes(input, 4)
|
|
}
|
|
|
|
// 3
|
|
if inputLen > 4 &&
|
|
(bytes.HasSuffix(input, []byte("ाकर")) ||
|
|
bytes.HasSuffix(input, []byte("ाइए")) ||
|
|
bytes.HasSuffix(input, []byte("ाईं")) ||
|
|
bytes.HasSuffix(input, []byte("ाया")) ||
|
|
bytes.HasSuffix(input, []byte("ेगी")) ||
|
|
bytes.HasSuffix(input, []byte("ेगा")) ||
|
|
bytes.HasSuffix(input, []byte("ोगी")) ||
|
|
bytes.HasSuffix(input, []byte("ोगे")) ||
|
|
bytes.HasSuffix(input, []byte("ाने")) ||
|
|
bytes.HasSuffix(input, []byte("ाना")) ||
|
|
bytes.HasSuffix(input, []byte("ाते")) ||
|
|
bytes.HasSuffix(input, []byte("ाती")) ||
|
|
bytes.HasSuffix(input, []byte("ाता")) ||
|
|
bytes.HasSuffix(input, []byte("तीं")) ||
|
|
bytes.HasSuffix(input, []byte("ाओं")) ||
|
|
bytes.HasSuffix(input, []byte("ाएं")) ||
|
|
bytes.HasSuffix(input, []byte("ुओं")) ||
|
|
bytes.HasSuffix(input, []byte("ुएं")) ||
|
|
bytes.HasSuffix(input, []byte("ुआं"))) {
|
|
return analysis.TruncateRunes(input, 3)
|
|
}
|
|
|
|
// 2
|
|
if inputLen > 3 &&
|
|
(bytes.HasSuffix(input, []byte("कर")) ||
|
|
bytes.HasSuffix(input, []byte("ाओ")) ||
|
|
bytes.HasSuffix(input, []byte("िए")) ||
|
|
bytes.HasSuffix(input, []byte("ाई")) ||
|
|
bytes.HasSuffix(input, []byte("ाए")) ||
|
|
bytes.HasSuffix(input, []byte("ने")) ||
|
|
bytes.HasSuffix(input, []byte("नी")) ||
|
|
bytes.HasSuffix(input, []byte("ना")) ||
|
|
bytes.HasSuffix(input, []byte("ते")) ||
|
|
bytes.HasSuffix(input, []byte("ीं")) ||
|
|
bytes.HasSuffix(input, []byte("ती")) ||
|
|
bytes.HasSuffix(input, []byte("ता")) ||
|
|
bytes.HasSuffix(input, []byte("ाँ")) ||
|
|
bytes.HasSuffix(input, []byte("ां")) ||
|
|
bytes.HasSuffix(input, []byte("ों")) ||
|
|
bytes.HasSuffix(input, []byte("ें"))) {
|
|
return analysis.TruncateRunes(input, 2)
|
|
}
|
|
|
|
// 1
|
|
if inputLen > 2 &&
|
|
(bytes.HasSuffix(input, []byte("ो")) ||
|
|
bytes.HasSuffix(input, []byte("े")) ||
|
|
bytes.HasSuffix(input, []byte("ू")) ||
|
|
bytes.HasSuffix(input, []byte("ु")) ||
|
|
bytes.HasSuffix(input, []byte("ी")) ||
|
|
bytes.HasSuffix(input, []byte("ि")) ||
|
|
bytes.HasSuffix(input, []byte("ा"))) {
|
|
return analysis.TruncateRunes(input, 1)
|
|
}
|
|
|
|
return input
|
|
}
|
|
|
|
func StemmerFilterConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.TokenFilter, error) {
|
|
return NewHindiStemmerFilter(), nil
|
|
}
|
|
|
|
func init() {
|
|
registry.RegisterTokenFilter(StemmerName, StemmerFilterConstructor)
|
|
}
|