Expand description
Native and WebAssembly-compatible Word document parsing, modeling, and serialization.
Re-exports§
pub use bundle::extract_document_assets;pub use bundle::extract_document_bundle;pub use bundle::parse_document_bundle;pub use bundle::DocumentBundle;pub use bundle::ExtractDocumentBundleOptions;pub use export::export_document;pub use export::ContentOverride;pub use export::ExportOptions;pub use export::ExportRequest;pub use export::ExportedDocument;pub use export::TableFormat;pub use revision_inlines::revision_inlines;pub use revision_inlines::InlineChange;pub use revision_inlines::RevisionInline;pub use chart::extract_chart_data;pub use doc::is_doc_format;pub use doc::parse_doc;pub use parse::build_doc_model;pub use parse::build_doc_model_with_options;pub use review::extract_document_review;pub use review::DocumentReview;pub use review::DocumentComment;pub use review::CommentTarget;pub use revisions::DocumentRevision;pub use revisions::ReviewedDocument;pub use revisions::RevisionKind;pub use revisions::RevisionProperties;pub use revisions::RevisionScope;pub use revisions::WordProperty;pub use source_graph::document_source_graph;pub use source_graph::DocumentSourceGraph;pub use structured::extract_document_blocks;pub use structured::extract_document_blocks_with_options;pub use structured::extract_document_blocks_with_revisions;pub use structured::BlockDetails;pub use structured::BlockType;pub use structured::DocumentBlock;pub use structured::DocumentWord;pub use structured::ExtractDocumentBlocksOptions;pub use structured::ParagraphDetails;pub use structured::ParagraphInline;pub use structured::SourceRef;pub use structured::StructuredDocument;pub use structured::TableCellDetails;pub use serialize::can_preserve_image_paint_source;pub use serialize::model_to_document_xml;pub use serialize::serialize_doc_model;pub use serialize::serialize_docx;pub use serialize::try_serialize_doc_model;pub use serialize::validate_image_paint_bounds;pub use zip::create_minimal_docx_package;pub use zip::package_to_bytes;pub use zip::parse_docx;pub use model::*;pub use package::*;
Modules§
- bundle
- Portable structured extraction with optional assets, charts, and tracked-change spans.
- chart
- doc
- Legacy Word 97-2003 binary
.docparser ([MS-DOC]). - emf
- EMF (Enhanced Metafile) to SVG conversion for the supported drawing record subset: window/viewport mapping, paths, solid brushes/pens, positioned Unicode text, solid raster-operation fills, saved device contexts, fill modes, clipping, and opaque bitmap transfers. Records outside the supported set abort the conversion so the caller can fall back to the unsupported-image placeholder instead of rendering something wrong.
- export
- HTML document export with selectable HTML, Markdown, or CSV tables.
- model
- package
- parse
- review
- revision_
inlines - Ordered inline spans annotated with tracked insertions and deletions.
- revisions
- serialize
- DOCX serialization.
- source_
graph - structured
- table_
grid - xml
- XML parsing utilities.
- zip
Structs§
- Chart
Category - A label at its stored hierarchy level, starting at zero for the leaf level.
- Chart
Data - Chart
Point - Source indices are zero-based. Values retain their original spelling and precision.
- Chart
Series - Parse
Options
Functions§
- parse_
document_ blocks - parse_
document_ blocks_ with_ options - parse_
document_ blocks_ with_ revisions - Parse Word bytes and return current blocks together with their tracked revisions.
- parse_
document_ bytes - Parses either a DOCX (OOXML zip) or a legacy Word 97-2003 binary
.docfile, detected by magic bytes, into the same in-memory package shape.