pptx

Documentation

Overview

Package pptx provides PPTX (Office Open XML Presentation) document parsing.

Package pptx provides PPTX (Office Open XML Presentation) document parsing.

Index

• type ExtractOptions
• type Paragraph
• type Reader
  • func Open(filename string) (*Reader, error)
  • func (r *Reader) Close() error
  • func (r *Reader) Document() (*model.Document, error)
  • func (r *Reader) Markdown() (string, error)
  • func (r *Reader) MarkdownWithOptions(opts ExtractOptions) (string, error)
  • func (r *Reader) MarkdownWithRAGOptions(extractOpts ExtractOptions, mdOpts rag.MarkdownOptions) (string, error)
  • func (r *Reader) Metadata() model.Metadata
  • func (r *Reader) PageCount() (int, error)
  • func (r *Reader) Slide(index int) (*Slide, error)
  • func (r *Reader) SlideCount() int
  • func (r *Reader) Text() (string, error)
  • func (r *Reader) TextWithOptions(opts ExtractOptions) (string, error)
• type Run
• type Slide
  • func (s *Slide) GetMarkdown() string
  • func (s *Slide) GetText() string
• type Table
  • func (t *Table) ToMarkdown() string
• type TableCell
• type TextBlock

Types

type ExtractOptions

type ExtractOptions struct {
	IncludeNotes   bool  // Include speaker notes
	IncludeTitles  bool  // Include slide titles (default: true)
	SlideNumbers   []int // Which slides to include (0-indexed, empty = all)
	ExcludeHeaders bool  // Exclude header placeholders
	ExcludeFooters bool  // Exclude footer placeholders (footer, date, slide number)
}

ExtractOptions holds options for text extraction.

type Paragraph

type Paragraph struct {
	Text       string
	Level      int    // Bullet/indent level (0 = top level)
	IsBullet   bool   // Has bullet point
	IsNumbered bool   // Is numbered list
	BulletChar string // Bullet character (if custom)
	Alignment  string // l, ctr, r, just
	Runs       []Run  // Text runs with formatting
}

Paragraph represents a paragraph within a text block.

type Reader

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

Reader provides access to PPTX document content.

func Open

func Open(filename string) (*Reader, error)

Open opens a PPTX file for reading.

func (*Reader) Close

func (r *Reader) Close() error

Close releases resources associated with the Reader.

func (*Reader) Document

func (r *Reader) Document() (*model.Document, error)

Document returns a model.Document representation of the PPTX content.

func (*Reader) Markdown

func (r *Reader) Markdown() (string, error)

Markdown returns the presentation content as Markdown.

func (*Reader) MarkdownWithOptions

func (r *Reader) MarkdownWithOptions(opts ExtractOptions) (string, error)

MarkdownWithOptions returns presentation content as Markdown with options.

func (*Reader) MarkdownWithRAGOptions

func (r *Reader) MarkdownWithRAGOptions(extractOpts ExtractOptions, mdOpts rag.MarkdownOptions) (string, error)

MarkdownWithRAGOptions returns presentation content as Markdown with RAG options.

func (*Reader) Metadata

func (r *Reader) Metadata() model.Metadata

Metadata returns document metadata.

func (*Reader) PageCount

func (r *Reader) PageCount() (int, error)

PageCount returns the number of slides (alias for SlideCount).

func (*Reader) Slide

func (r *Reader) Slide(index int) (*Slide, error)

Slide returns the slide at the given index (0-indexed).

func (*Reader) SlideCount

func (r *Reader) SlideCount() int

SlideCount returns the number of slides.

func (*Reader) Text

func (r *Reader) Text() (string, error)

Text extracts and returns all text content from the presentation.

func (*Reader) TextWithOptions

func (r *Reader) TextWithOptions(opts ExtractOptions) (string, error)

TextWithOptions extracts text content with the specified options.

type Run

type Run struct {
	Text     string
	Bold     bool
	Italic   bool
	FontSize int // In hundredths of a point
}

Run represents a text run with consistent formatting.

type Slide

type Slide struct {
	Index   int         // 0-indexed slide number
	Title   string      // Slide title (from title placeholder)
	Content []TextBlock // Text content in reading order
	Tables  []Table     // Tables on the slide
	Notes   string      // Speaker notes
}

Slide represents a parsed slide.

func (*Slide) GetMarkdown

func (s *Slide) GetMarkdown() string

GetMarkdown returns the slide content as markdown.

func (*Slide) GetText

func (s *Slide) GetText() string

GetText returns all text from the slide as a single string.

type Table

type Table struct {
	Rows    [][]TableCell
	Columns int
	X, Y    int // Position in EMUs
	Width   int // Width in EMUs
	Height  int // Height in EMUs
}

Table represents a table on a slide.

func (*Table) ToMarkdown

func (t *Table) ToMarkdown() string

ToMarkdown converts a table to markdown format.

type TableCell

type TableCell struct {
	Text     string
	RowSpan  int
	ColSpan  int
	IsMerged bool // Part of a merged cell (not the origin)
}

TableCell represents a cell in a table.

type TextBlock

type TextBlock struct {
	Text        string
	Paragraphs  []Paragraph
	IsTitle     bool   // Is this the slide title?
	IsSubtitle  bool   // Is this a subtitle?
	Placeholder string // Placeholder type (title, body, etc.)
	X, Y        int    // Position in EMUs
	Width       int    // Width in EMUs
	Height      int    // Height in EMUs
}

TextBlock represents a block of text on a slide.