Versions in this module Expand all Collapse all v0 v0.1.5 Aug 15, 2026 v0.1.4 Aug 10, 2026 v0.1.3 Aug 7, 2026 v0.1.2 Jun 20, 2026 v0.1.1 Apr 19, 2026 v0.1.0 Apr 19, 2026 Changes in this version + const ElementTypeAdmonition + const ElementTypeCodeBlock + const ElementTypeHeader + const ElementTypeImage + const ElementTypeList + const ElementTypeParagraph + const ElementTypeTable + func ApplyLinksToBlocks(blocks []extractor.TextBlock, links []types.Link) []extractor.TextBlock + func CleanMathContent(text string) string + func CreateONNXConfig(cfg *Config) *onnx.Config + func DetectHorizontalSeparators(graphics []types.VectorGraphic, pageWidth float64) []float64 + func DetectVerticalSeparators(graphics []types.VectorGraphic, pageHeight float64) []float64 + func FindTableCellsFromLines(hLines, vLines []Line, blocks []extractor.TextBlock) [][]TableCell + func IsLikelyEquation(blocks []extractor.TextBlock) bool + func SortBlocks(blocks []extractor.TextBlock) []extractor.TextBlock + type Analyzer struct + ColumnGapThreshold float64 + Config *Config + Exclusion ExclusionZone + HeaderSizeRatio float64 + Rules []Rule + func NewAnalyzer() *Analyzer + func NewAnalyzerWithConfig(config *Config) *Analyzer + func (a *Analyzer) Analyze(content *extractor.PageContent) []Element + func (a *Analyzer) CleanFragmentedMath(elements []Element) []Element + func (a *Analyzer) CleanMathSymbols(elements []Element) []Element + func (a *Analyzer) FilterPageNumbers(elements []Element) []Element + func (a *Analyzer) FilterRepeatedPageHeaders(elements []Element) []Element + func (a *Analyzer) MergeCodeBlocks(elements []Element) []Element + func (a *Analyzer) MergeDropCaps(elements []Element) []Element + func (a *Analyzer) MergeElements(elements []Element) []Element + func (a *Analyzer) MergeListContinuations(elements []Element) []Element + func (a *Analyzer) MergeParagraphLines(elements []Element) []Element + func (a *Analyzer) MergeSameLinkElements(elements []Element) []Element + func (a *Analyzer) MergeTableRows(elements []Element) []Element + func (a *Analyzer) NormalizeHeaderLevels(elements []Element) []Element + func (a *Analyzer) RemoveTableOfContentsRange(elements []Element) []Element + type AnalyzerWithONNX struct + func NewAnalyzerWithONNX(config *Config, detector LayoutDetector) *AnalyzerWithONNX + func (a *AnalyzerWithONNX) AnalyzeWithImage(content *extractor.PageContent, pageImage image.Image) []Element + type Config struct + ColumnGapThreshold float64 + EnableONNX bool + EquationScoreThreshold int + H1Ratio float64 + H2Ratio float64 + H3Ratio float64 + H4Ratio float64 + H5Ratio float64 + H6Ratio float64 + HeaderSizeRatio float64 + IndentThreshold float64 + LineHeightMultiplier float64 + MinImageSize float64 + MinONNXConfidence float64 + ONNXConfThreshold float64 + ONNXInputSize int + ONNXModelPath string + ONNXNMSThreshold float64 + ONNXRuntimePath string + ONNXStride int + ONNXUseCoreML bool + SentenceGapMultiplier float64 + TableMinColumns int + TableMinSpaces int + WideGapMultiple float64 + WordGapMultiplier float64 + func ConfigForAcademicPapers() *Config + func ConfigForScannedDocuments() *Config + func ConfigForTechnicalDocs() *Config + func DefaultConfig() *Config + type Element = types.Element + func ProcessLinks(elements []Element, links []types.Link) []Element + type ElementType = types.ElementType + type ExclusionZone struct + Bottom float64 + Top float64 + type GridRegion struct + Height float64 + HorizontalLines []float64 + VerticalLines []float64 + Width float64 + X float64 + Y float64 + func MergeRectanglesIntoCells(graphics []types.VectorGraphic) []GridRegion + type LayoutDetector interface + Close func() error + DetectLayout func(pageImage image.Image, pageWidth, pageHeight float64) (*types.PageDetections, error) + IsAvailable func() bool + type Line struct + IsHorizontal bool + IsVertical bool + Length float64 + X1 float64 + X2 float64 + Y1 float64 + Y2 float64 + type Rule struct + Condition func(text string, fontSize, bodyFontSize float64) bool + Name string + Type ElementType + type TableCell struct + Col int + ColSpan int + Content string + Height float64 + IsHeader bool + Row int + RowSpan int + Width float64 + X float64 + Y float64 + type TableDetector struct + ColumnTolerance float64 + GapThreshold float64 + MinColumns int + MinConfidence float64 + MinRows int + RowTolerance float64 + func NewTableDetector() *TableDetector + func (td *TableDetector) DetectTables(blocks []extractor.TextBlock, graphics []types.VectorGraphic) ([]TableStructure, map[int]bool) + type TableStructure struct + Cells [][]TableCell + Confidence float64 + HasHeader bool + Height float64 + NumCols int + NumRows int + Width float64 + X float64 + Y float64 + func DetectTableFromGraphics(graphics []types.VectorGraphic, textBlocks []extractor.TextBlock) *TableStructure + func (ts *TableStructure) ToMarkdown() string
Go to main page