converters

README

Package cloudeng.io/glean/crawlindex/converters

import cloudeng.io/glean/crawlindex/converters

Constants

GleanDocumentType, GleanUserType

GleanDocumentType = content.Type("glean/document")
GleanUserType = content.Type("glean/user")

Functions

Func CreateDocumentRegistry

func CreateDocumentRegistry(converters ...Document) (*content.Registry[Document], error)

Func CreateUserRegistry

func CreateUserRegistry(converters ...User) (*content.Registry[User], error)

Func IgnoreContentType

func IgnoreContentType(ctype content.Type) error

Func IsIgnoreContentType

func IsIgnoreContentType(err error) bool

Types

Type Document

type Document interface {
	Type() content.Type
	Convert(ctx context.Context, datasource string, cfg config.Conversion, ctype content.Type, data []byte) (gleansdk.DocumentDefinition, error)
}

Functions

func NewHTML() Document

NewHTML returns a new install of HTML.

Type HTML

type HTML struct{}

HTML represents an html to glean document converter.

Methods

func (cnv *HTML) Convert(_ context.Context, datasource string, cfg config.Conversion, ctype content.Type, data []byte) (gleansdk.DocumentDefinition, error)

func (cnv *HTML) Type() content.Type

Type User

type User interface {
	Type() content.Type
	Convert(ctx context.Context, datasource string, cfg config.Conversion, ctype content.Type, data []byte) (gleansdk.DatasourceUserDefinition, error)
}

Documentation

Index

• Constants
• func CreateDocumentRegistry(converters ...Document) (*content.Registry[Document], error)
• func CreateUserRegistry(converters ...User) (*content.Registry[User], error)
• func IgnoreContentType(ctype content.Type) error
• func IsIgnoreContentType(err error) bool
• type Document
  • func NewHTML() Document
• type HTML
  • func (cnv *HTML) Convert(_ context.Context, datasource string, cfg config.Conversion, ...) (gleansdk.DocumentDefinition, error)
  • func (cnv *HTML) Type() content.Type
• type User

Constants

const (
	GleanDocumentType = content.Type("glean/document")
	GleanUserType     = content.Type("glean/user")
)

Functions

func CreateDocumentRegistry

func CreateDocumentRegistry(converters ...Document) (*content.Registry[Document], error)

func CreateUserRegistry

func CreateUserRegistry(converters ...User) (*content.Registry[User], error)

func IgnoreContentType

func IgnoreContentType(ctype content.Type) error

func IsIgnoreContentType

func IsIgnoreContentType(err error) bool

Types

type Document

type Document interface {
	Type() content.Type
	Convert(ctx context.Context, datasource string, cfg config.Conversion, ctype content.Type, data []byte) (gleansdk.DocumentDefinition, error)
}

func NewHTML

func NewHTML() Document

NewHTML returns a new install of HTML.

type HTML

type HTML struct{}

HTML represents an html to glean document converter.

func (*HTML) Convert

func (cnv *HTML) Convert(_ context.Context, datasource string, cfg config.Conversion, ctype content.Type, data []byte) (gleansdk.DocumentDefinition, error)

func (*HTML) Type

func (cnv *HTML) Type() content.Type

type User

type User interface {
	Type() content.Type
	Convert(ctx context.Context, datasource string, cfg config.Conversion, ctype content.Type, data []byte) (gleansdk.DatasourceUserDefinition, error)
}