mirror of
https://github.com/opencloud-eu/opencloud.git
synced 2026-01-24 05:51:33 -05:00
cdd2100b4b
* 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>
15 lines
883 B
Go
15 lines
883 B
Go
package config
|
|
|
|
// Extractor defines which extractor to use
|
|
type Extractor struct {
|
|
Type string `yaml:"type" env:"SEARCH_EXTRACTOR_TYPE" desc:"Defines the content extraction engine. Defaults to 'basic'. Supported values are: 'basic' and 'tika'."`
|
|
CS3AllowInsecure bool `yaml:"cs3_allow_insecure" env:"OCIS_INSECURE;SEARCH_EXTRACTOR_CS3SOURCE_INSECURE" desc:"Ignore untrusted SSL certificates when connecting to the CS3 source."`
|
|
Tika ExtractorTika `yaml:"tika"`
|
|
}
|
|
|
|
// 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."`
|
|
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."`
|
|
}
|