Skip to main content

rust_docx/
lib.rs

1//! Native and WebAssembly-compatible Word document parsing, modeling, and serialization.
2
3pub mod chart;
4pub mod doc;
5pub mod emf;
6pub mod model;
7pub mod package;
8pub mod parse;
9pub mod revisions;
10pub mod review;
11pub mod serialize;
12pub mod source_graph;
13pub mod structured;
14pub mod table_grid;
15mod wmf;
16pub mod xml;
17mod xml_index;
18pub mod zip;
19
20pub use chart::{extract_chart_data, ChartCategory, ChartData, ChartPoint, ChartSeries};
21pub use doc::{is_doc_format, parse_doc};
22pub use model::*;
23pub use package::*;
24pub use parse::{build_doc_model, build_doc_model_with_options};
25pub use rust_office_art::ParseOptions;
26pub use review::{extract_document_review, DocumentReview, DocumentComment, CommentTarget};
27pub use revisions::{
28    DocumentRevision, ReviewedDocument, RevisionKind, RevisionProperties, RevisionScope,
29    WordProperty,
30};
31pub use source_graph::{document_source_graph, DocumentSourceGraph};
32pub use structured::{
33    extract_document_blocks, extract_document_blocks_with_options,
34    extract_document_blocks_with_revisions, BlockDetails, BlockType, DocumentBlock, DocumentWord,
35    ExtractDocumentBlocksOptions, ParagraphDetails, ParagraphInline, SourceRef, StructuredDocument,
36    TableCellDetails,
37};
38
39pub fn parse_document_blocks(bytes: &[u8]) -> Result<StructuredDocument, String> {
40    parse_document_blocks_with_options(bytes, ExtractDocumentBlocksOptions::default())
41}
42
43pub fn parse_document_blocks_with_options(
44    bytes: &[u8],
45    options: ExtractDocumentBlocksOptions,
46) -> Result<StructuredDocument, String> {
47    let package = parse_document_bytes(bytes)?;
48    Ok(extract_document_blocks_with_options(
49        &build_doc_model_with_options(
50            &package,
51            &ParseOptions {
52                include_3d_models: options.include_3d_models,
53            },
54        ),
55        options,
56    ))
57}
58
59/// Parse Word bytes and return current blocks together with their tracked revisions.
60pub fn parse_document_blocks_with_revisions(
61    bytes: &[u8],
62    options: ExtractDocumentBlocksOptions,
63) -> Result<ReviewedDocument, String> {
64    let package = parse_document_bytes(bytes)?;
65    Ok(extract_document_blocks_with_revisions(
66        &build_doc_model_with_options(
67            &package,
68            &ParseOptions {
69                include_3d_models: options.include_3d_models,
70            },
71        ),
72        options,
73    ))
74}
75
76pub use serialize::{
77    can_preserve_image_paint_source, model_to_document_xml, serialize_doc_model, serialize_docx,
78    try_serialize_doc_model, validate_image_paint_bounds,
79};
80pub use zip::{create_minimal_docx_package, package_to_bytes, parse_docx};
81
82/// Parses either a DOCX (OOXML zip) or a legacy Word 97-2003 binary `.doc`
83/// file, detected by magic bytes, into the same in-memory package shape.
84pub fn parse_document_bytes(bytes: &[u8]) -> Result<OoxmlPackage, String> {
85    if is_doc_format(bytes) {
86        parse_doc(bytes)
87    } else {
88        parse_docx(bytes)
89    }
90}