You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

52 lines
1.5 KiB

  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. package standard
  15. import (
  16. "github.com/blevesearch/bleve/analysis"
  17. "github.com/blevesearch/bleve/analysis/lang/en"
  18. "github.com/blevesearch/bleve/analysis/token/lowercase"
  19. "github.com/blevesearch/bleve/analysis/tokenizer/unicode"
  20. "github.com/blevesearch/bleve/registry"
  21. )
  22. const Name = "standard"
  23. func AnalyzerConstructor(config map[string]interface{}, cache *registry.Cache) (*analysis.Analyzer, error) {
  24. tokenizer, err := cache.TokenizerNamed(unicode.Name)
  25. if err != nil {
  26. return nil, err
  27. }
  28. toLowerFilter, err := cache.TokenFilterNamed(lowercase.Name)
  29. if err != nil {
  30. return nil, err
  31. }
  32. stopEnFilter, err := cache.TokenFilterNamed(en.StopName)
  33. if err != nil {
  34. return nil, err
  35. }
  36. rv := analysis.Analyzer{
  37. Tokenizer: tokenizer,
  38. TokenFilters: []analysis.TokenFilter{
  39. toLowerFilter,
  40. stopEnFilter,
  41. },
  42. }
  43. return &rv, nil
  44. }
  45. func init() {
  46. registry.RegisterAnalyzer(Name, AnalyzerConstructor)
  47. }