xml

Documentation

Index

• type Parser
  • func DefaultParser() *Parser
  • func (p *Parser) GetSupportedTypes() []string
  • func (p *Parser) Parse(ctx context.Context, content []byte, metadata map[string]any) (*core.Document, error)
  • func (p *Parser) ParseStream(ctx context.Context, r io.Reader, metadata map[string]any) (<-chan *core.Document, error)
  • func (p *Parser) SetChunkOverlap(overlap int)
  • func (p *Parser) SetChunkSize(size int)
  • func (p *Parser) SetPreserveComments(preserve bool)
  • func (p *Parser) Supports(contentType string) bool

Types

type Parser

type Parser struct {
	// contains filtered or unexported fields
}

Parser implements an XML parser using SAX-style parsing

func DefaultParser

func DefaultParser() *Parser

DefaultParser creates a new XML parser

func (*Parser) GetSupportedTypes

func (p *Parser) GetSupportedTypes() []string

GetSupportedTypes returns supported formats

func (*Parser) Parse

func (p *Parser) Parse(ctx context.Context, content []byte, metadata map[string]any) (*core.Document, error)

Parse implements the core.Parser interface

func (*Parser) ParseStream

func (p *Parser) ParseStream(ctx context.Context, r io.Reader, metadata map[string]any) (<-chan *core.Document, error)

ParseStream implements the core.Parser interface

func (*Parser) SetChunkOverlap

func (p *Parser) SetChunkOverlap(overlap int)

SetChunkOverlap sets the chunk overlap

func (*Parser) SetChunkSize

func (p *Parser) SetChunkSize(size int)

SetChunkSize sets the chunk size

func (*Parser) SetPreserveComments

func (p *Parser) SetPreserveComments(preserve bool)

SetPreserveComments sets whether to preserve XML comments

func (*Parser) Supports

func (p *Parser) Supports(contentType string) bool

Supports checks if the content type is supported