0
0
bleve/analysis/tokenizers/whitespace_tokenizer/whitespace_tokenizer.go
Marty Schoch cb5ccd2b1d fix whitespace tokenizer
previously would fail to split ascii running into ideographic
2014-09-11 10:38:02 -04:00

31 lines
1.2 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 whitespace_tokenizer
import (
"regexp"
"github.com/blevesearch/bleve/analysis"
"github.com/blevesearch/bleve/analysis/tokenizers/regexp_tokenizer"
"github.com/blevesearch/bleve/registry"
)
const Name = "whitespace"
var whitespaceTokenizerRegexp = regexp.MustCompile(`\p{Han}|\p{Hangul}|\p{Hiragana}|\p{Katakana}|[^\p{Z}\p{P}\p{C}\p{Han}\p{Hangul}\p{Hiragana}\p{Katakana}]+`)
func TokenizerConstructor(config map[string]interface{}, cache *registry.Cache) (analysis.Tokenizer, error) {
return regexp_tokenizer.NewRegexpTokenizer(whitespaceTokenizerRegexp), nil
}
func init() {
registry.RegisterTokenizer(Name, TokenizerConstructor)
}