sevenhill/QSfera
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

enhancement: improve content extraction stop word cleaning (#7553)

Browse Source 
* enhancement: improve content extraction stop word cleaning

* fix: cleanup documentation

Co-authored-by: Martin <github@diemattels.at>

* fix: failing tika stop word unit tests

---------

Co-authored-by: Martin <github@diemattels.at>
This commit is contained in:
Florian Schade
2023-10-23 13:40:37 +02:00
committed by GitHub
co-authored by Martin
parent e24fce483a
commit cdd2100b4b
8 changed files with 98 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
services/search/pkg/config/content.go
+2 -1
View File
@@ -9,5 +9,6 @@ type Extractor struct {
// ExtractorTika configures the Tika extractor
type ExtractorTika struct {
TikaURL string `yaml:"tika_url" env:"SEARCH_EXTRACTOR_TIKA_TIKA_URL" desc:"URL of the tika server."`
TikaURL string `yaml:"tika_url" env:"SEARCH_EXTRACTOR_TIKA_TIKA_URL" desc:"URL of the tika server."`
CleanStopWords bool `yaml:"clean_stop_words" env:"SEARCH_EXTRACTOR_TIKA_CLEAN_STOP_WORDS" desc:"Defines if stop words should be cleaned or not. See the documentation for more details."`
}