Documentation
¶
Index ¶
- Constants
- Variables
- func Add(d *Document) error
- func Delete(u string) error
- func DetectLanguage(s string) (*lingua.Language, error)
- func DocumentCount() uint64
- func Extract(d *Document) error
- func Init(cfg *config.Config) error
- func Iterate(fn func(*Document))
- func Reindex(basePath string, rules *config.Rules, skipSensitiveChecks bool) error
- type Document
- type Extractor
- type Query
- type Results
Constants ¶
View Source
const UnknownLanguage = "unknown"
Variables ¶
View Source
var ErrNoExtractor = errors.New("no extractor found")
View Source
var (
ErrSensitiveContent = errors.New("document contains sensitive data")
)
View Source
var Languages = []lingua.Language{ lingua.Arabic, lingua.Bulgarian, lingua.Catalan, lingua.Czech, lingua.Danish, lingua.German, lingua.Greek, lingua.English, lingua.Spanish, lingua.Basque, lingua.Persian, lingua.Finnish, lingua.French, lingua.Irish, lingua.Hindi, lingua.Croatian, lingua.Hungarian, lingua.Armenian, lingua.Indonesian, lingua.Italian, lingua.Dutch, lingua.Polish, lingua.Portuguese, lingua.Romanian, lingua.Russian, lingua.Swedish, lingua.Turkish, }
View Source
var Version = 2
Functions ¶
func DocumentCount ¶ added in v0.6.0
func DocumentCount() uint64
Types ¶
type Document ¶
type Document struct {
URL string `json:"url"`
Domain string `json:"domain"`
HTML string `json:"html"`
Title string `json:"title"`
Text string `json:"text"`
Favicon string `json:"favicon"`
Score float64 `json:"score"`
Added int64 `json:"added"`
Language string `json:"language"`
// contains filtered or unexported fields
}
func (*Document) DownloadFavicon ¶
type Query ¶
Click to show internal directories.
Click to hide internal directories.