mirror of
https://github.com/storytold/craft-libs.git
synced 2026-11-12 10:03:51 +00:00
Dylan M. Taylor
e3e31693c7
* Add craft-wordmodel: WordCraft's document model without its editing code WordCraft's crates/doc (wordcraft-doc, at 07f97737) moved as it is, so the DOCX, RTF, ODT and other text-format crates can read into and write from one model. Module paths, type names and serde attributes are unchanged: an app that re-exports the crate keeps its native file format. Left in the app: range editing (edit.rs), IME text and equation editing. Not model, and already in craft-libs: code pages (craft-rtf), the ZIP entry-count check (craft-opc), the compound-file guard (craft-cfb). The paragraph walks moved to walk.rs and the unit helpers of wordcraft-geom to geom.rs. * craft-wordmodel: math_tree, the arguments of an equation node and a walk over its runs The DOCX reader and writer walk an equation's runs. The walk and the child accessors it uses were in WordCraft's equation editor (math_edit.rs), which stays in the app; they are structure, not editing. * craft-wordmodel: keep the document operations (edit.rs) with the model The DOCX and RTF readers use them: alternative-format chunks are merged into a document with adopt_blocks, and a reader formats ranges with format_range and inserts objects. They operate on the document, not on a view, so they belong beside it. The tests that drove them come back with them; the paragraph walks stay in walk.rs and edit re-exports them. base64 0.23, as WordCraft and craft-offcrypto use. * craft-docx: WordCraft's crates/docx as it is at wordcraft 07f97737 The source, unchanged, so the next commit shows only what the move changes. This commit does not build on its own (it still names wordcraft-doc and wordcraft-geom, and is not a workspace member yet). * craft-docx: on craft-wordmodel, craft-opc, craft-xml and craft-offcrypto - The package (zip reading, part names, relationships, content types, zip writing) is craft-opc's; the module keeps WordCraft's bookkeeping (passthrough keys, the embedded-part manifest) and its own Rel/Rels shape. - Parts are parsed with craft-xml's canonical names (the Strict drawing names and mc:Choice/@Requires through its hooks), then given the tree shape the reader was written against. - Encryption and Restrict Editing hashes are craft-offcrypto's; this crate maps its errors and the w:documentProtection attributes. - wordcraft-doc is craft-wordmodel; wordcraft-geom's helpers are its geom. Tests that covered what now lives in craft-opc and craft-offcrypto are left to those crates; the DIFAT regression is craft-cfb's. Test-only zip use follows zip 9's fallible names. The attribute-cap test times the read only.
58 lines
4.0 KiB
Rust
58 lines
4.0 KiB
Rust
//! #4696: Word's built-in heading styles have their outline level even when the file's
|
|
//! `styles.xml` doesn't write `w:outlineLvl` (some producers leave it out). Word for Windows,
|
|
//! opening such a file, reports `OutlineLevel` 1 and 2 for "heading 1" and "heading 2" (whatever
|
|
//! their style ids) and body text for a custom style.
|
|
use craft_wordmodel::Paragraph;
|
|
use std::io::Write;
|
|
|
|
const W: &str = "http://schemas.openxmlformats.org/wordprocessingml/2006/main";
|
|
|
|
fn package(styles: &str, body: &str) -> Vec<u8> {
|
|
let root = r#"<?xml version="1.0" encoding="UTF-8"?><Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument" Target="word/document.xml"/></Relationships>"#;
|
|
let rels = r#"<?xml version="1.0" encoding="UTF-8"?><Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships"><Relationship Id="rId1" Type="http://schemas.openxmlformats.org/officeDocument/2006/relationships/styles" Target="styles.xml"/></Relationships>"#;
|
|
let doc = format!(r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?><w:document xmlns:w="{W}"><w:body>{body}</w:body></w:document>"#);
|
|
let styles = format!(r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?><w:styles xmlns:w="{W}">{styles}</w:styles>"#);
|
|
let mut zw = zip::ZipWriter::new(std::io::Cursor::new(Vec::new()));
|
|
for (name, body) in
|
|
[("_rels/.rels", root), ("word/document.xml", doc.as_str()), ("word/_rels/document.xml.rels", rels), ("word/styles.xml", styles.as_str())]
|
|
{
|
|
zw.start_file(name, zip::write::SimpleFileOptions::default()).unwrap();
|
|
zw.write_all(body.as_bytes()).unwrap();
|
|
}
|
|
zw.finish().unwrap().into_inner()
|
|
}
|
|
|
|
fn para(style: &str, text: &str) -> String {
|
|
format!(r#"<w:p><w:pPr><w:pStyle w:val="{style}"/></w:pPr><w:r><w:t>{text}</w:t></w:r></w:p>"#)
|
|
}
|
|
|
|
fn levels(d: &craft_wordmodel::Document) -> Vec<Option<u8>> {
|
|
d.body.iter().filter_map(|b| b.as_para()).map(|p: &Paragraph| d.styles.resolve_para(&p.props).outline_level).collect()
|
|
}
|
|
|
|
#[test]
|
|
fn built_in_heading_styles_have_their_outline_level_without_outline_lvl() {
|
|
let styles = r#"<w:style w:type="paragraph" w:default="1" w:styleId="Normal"><w:name w:val="Normal"/></w:style>
|
|
<w:style w:type="paragraph" w:styleId="Heading1"><w:name w:val="heading 1"/><w:basedOn w:val="Normal"/></w:style>
|
|
<w:style w:type="paragraph" w:styleId="Titolo2"><w:name w:val="heading 2"/><w:basedOn w:val="Normal"/></w:style>
|
|
<w:style w:type="paragraph" w:styleId="Heading9"><w:name w:val="Heading 9"/></w:style>
|
|
<w:style w:type="paragraph" w:styleId="Below"><w:name w:val="Below heading 2"/><w:basedOn w:val="Titolo2"/></w:style>
|
|
<w:style w:type="paragraph" w:customStyle="1" w:styleId="MyHead"><w:name w:val="My heading 3"/><w:basedOn w:val="Normal"/></w:style>
|
|
<w:style w:type="paragraph" w:styleId="Heading10"><w:name w:val="heading 10"/></w:style>
|
|
<w:style w:type="paragraph" w:customStyle="on" w:styleId="Fake4"><w:name w:val="heading 4"/></w:style>
|
|
<w:style w:type="paragraph" w:styleId="Heading3"><w:name w:val="heading 3"/><w:pPr><w:outlineLvl w:val="5"/></w:pPr></w:style>"#;
|
|
let body = ["Heading1", "Titolo2", "Heading9", "Below", "MyHead", "Heading10", "Fake4", "Heading3", "Normal"]
|
|
.iter()
|
|
.map(|s| para(s, "x"))
|
|
.collect::<String>();
|
|
let d = craft_docx::read(&package(styles, &body)).unwrap();
|
|
// Heading 1, 2 and 9 by name; a style based on a heading inherits its level; a custom style,
|
|
// "heading 10", a custom style named "heading 4" (`w:customStyle="on"`) and Normal have none; a
|
|
// level the file gives is kept.
|
|
let want = vec![Some(0), Some(1), Some(8), Some(1), None, None, None, Some(5), None];
|
|
assert_eq!(levels(&d), want);
|
|
// The level survives a save and reopen.
|
|
let again = craft_docx::read(&craft_docx::write(&d).unwrap()).unwrap();
|
|
assert_eq!(levels(&again), want);
|
|
}
|