xberg

package

v0.3.0 Latest Latest Go to latest Published: Aug 31, 2026 License: MIT Imports: 12 Imported by: 0

Details

Valid go.mod file
Redistributable license
Tagged version
Stable version
Learn more about best practices

Repository

github.com/sungithubid/go-xberg-sdk

Links

Open Source Insights

Documentation ¶

Overview ¶

Package xberg implements Eino's document parser interface with the native Xberg extraction engine.

Index ¶

Constants
func WithChunking(config native.ChunkingConfig) einoparser.Option
func WithDocumentMode(mode DocumentMode) einoparser.Option
func WithFileConfig(config native.FileExtractionConfig) einoparser.Option
func WithFilename(filename string) einoparser.Option
func WithForceOCRPages(pages ...uint32) einoparser.Option
func WithMIMEType(mimeType string) einoparser.Option
func WithNativeFileConfig(apply func(*native.FileExtractionConfig)) einoparser.Option
func WithOCR(config native.OcrConfig) einoparser.Option
func WithOutputFormat(format native.OutputFormat) einoparser.Option
func WithPDF(config native.PdfConfig) einoparser.Option
func WithPDFPasswords(passwords ...string) einoparser.Option
func WithPages(config native.PageConfig) einoparser.Option
func WithTimeout(timeout time.Duration) einoparser.Option
type Config
type DocumentMode
type Parser
- func NewParser(ctx context.Context, config *Config) (*Parser, error)
- func (parser *Parser) Parse(ctx context.Context, reader io.Reader, options ...einoparser.Option) ([]*schema.Document, error)

Constants ¶

View Source

const (
	MetaKeyMIMEType          = "xberg_mime_type"
	MetaKeyDocumentIndex     = "xberg_document_index"
	MetaKeyDocumentCount     = "xberg_document_count"
	MetaKeyNativeMetadata    = "xberg_metadata"
	MetaKeyCounts            = "xberg_counts"
	MetaKeyExtractionMethod  = "xberg_extraction_method"
	MetaKeyDetectedLanguages = "xberg_detected_languages"
	MetaKeyTables            = "xberg_tables"
	MetaKeyWarnings          = "xberg_warnings"
	MetaKeyErrors            = "xberg_errors"
	MetaKeyPageNumber        = "xberg_page_number"
	MetaKeyPageBlank         = "xberg_page_blank"
	MetaKeySheetName         = "xberg_sheet_name"
	MetaKeySectionName       = "xberg_section_name"
	MetaKeySpeakerNotes      = "xberg_speaker_notes"
	MetaKeyImageIndices      = "xberg_image_indices"
	MetaKeyChunkIndex        = "xberg_chunk_index"
	MetaKeyTotalChunks       = "xberg_total_chunks"
	MetaKeyByteStart         = "xberg_byte_start"
	MetaKeyByteEnd           = "xberg_byte_end"
	MetaKeyFirstPage         = "xberg_first_page"
	MetaKeyLastPage          = "xberg_last_page"
	MetaKeyHeadingPath       = "xberg_heading_path"
	MetaKeyChunkType         = "xberg_chunk_type"
	MetaKeyElementType       = "xberg_element_type"
	MetaKeyElementMetadata   = "xberg_element_metadata"
)

Variables ¶

This section is empty.

Functions ¶

func WithChunking ¶

func WithChunking(config native.ChunkingConfig) einoparser.Option

func WithDocumentMode ¶

func WithDocumentMode(mode DocumentMode) einoparser.Option

func WithFileConfig ¶

func WithFileConfig(config native.FileExtractionConfig) einoparser.Option

func WithFilename ¶

func WithFilename(filename string) einoparser.Option

func WithForceOCRPages ¶

func WithForceOCRPages(pages ...uint32) einoparser.Option

func WithMIMEType ¶

func WithMIMEType(mimeType string) einoparser.Option

func WithNativeFileConfig ¶

func WithNativeFileConfig(apply func(*native.FileExtractionConfig)) einoparser.Option

WithNativeFileConfig is the escape hatch for Xberg features not covered by the convenience options in this package.

func WithOCR ¶

func WithOCR(config native.OcrConfig) einoparser.Option

func WithOutputFormat ¶

func WithOutputFormat(format native.OutputFormat) einoparser.Option

func WithPDF ¶

func WithPDF(config native.PdfConfig) einoparser.Option

func WithPDFPasswords ¶

func WithPDFPasswords(passwords ...string) einoparser.Option

func WithPages ¶

func WithPages(config native.PageConfig) einoparser.Option

func WithTimeout ¶

func WithTimeout(timeout time.Duration) einoparser.Option

Types ¶

type Config ¶

type Config struct {
	Core         core.Config
	DocumentMode DocumentMode
}

Config combines adapter-specific behavior with the reusable core extractor configuration. Native Xberg settings live in Core.Native.

type DocumentMode ¶

type DocumentMode string

const (
	DocumentModeDocument DocumentMode = "document"
	DocumentModePage     DocumentMode = "page"
	DocumentModeChunk    DocumentMode = "chunk"
	DocumentModeElement  DocumentMode = "element"
)

type Parser ¶

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

func NewParser ¶

func NewParser(ctx context.Context, config *Config) (*Parser, error)

func (*Parser) Parse ¶

func (parser *Parser) Parse(ctx context.Context, reader io.Reader, options ...einoparser.Option) ([]*schema.Document, error)

Source Files ¶

View all Source files

?	: This menu
/	: Search site
f or F	: Jump to
y or Y	: Canonical URL