Files
wordcraft/crates/docx/tests/it/char_units.rs
T
Dylan M. Taylor 42a5df5f94 chore: cut over image codecs and zip to craft-libs (#6661)
* chore: cut over image codecs and zip to craft-libs, fix main test regressions

* tests: store ODS mimetype and use standard ODF namespaces in mailings test

* Remove unused quick-xml workspace dependency

* fix: use standard ODF namespaces in file_dialogs test and preserve trailing line in markdown import_on_with_lines

* fix(geom): use png_chunks for PNG dimensions and p.fits(budget) in decode_for_drawing
2026-11-14 14:51:35 -05:00

108 lines
6.7 KiB
Rust

//! Indents in character units (#534), common in Chinese documents: ECMA-376 Part 1 §17.3.1.12
//! `w:ind` `w:firstLineChars`, `w:hangingChars`, `w:leftChars` and `w:rightChars`, in hundredths
//! of a character. Fixtures are hand-written.
use wordcraft_doc::Document;
use wordcraft_doc::props::ParaProps;
fn zip(entries: &[(&str, &[u8])]) -> Vec<u8> {
let mut zw = craft_zip::Writer::new();
for (name, bytes) in entries {
zw.add(name, bytes, craft_zip::Compression::Deflated).unwrap();
}
zw.finish().unwrap()
}
/// A package whose body is `body`.
fn docx(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 doc = format!(
r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?><w:document xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:body>{body}</w:body></w:document>"#
);
zip(&[("_rels/.rels", root.as_bytes()), ("word/document.xml", doc.as_bytes())])
}
fn props(d: &Document) -> Vec<ParaProps> {
d.body.iter().filter_map(|b| b.as_para()).map(|p| p.props.clone()).collect()
}
#[test]
fn character_indents_read_and_round_trip() {
let body = r#"<w:p><w:pPr><w:ind w:firstLineChars="200" w:firstLine="420"/></w:pPr><w:r><w:t>一</w:t></w:r></w:p>
<w:p><w:pPr><w:ind w:leftChars="150" w:left="315" w:rightChars="50" w:right="105" w:hangingChars="100" w:hanging="210"/></w:pPr><w:r><w:t>二</w:t></w:r></w:p>
<w:p><w:pPr><w:ind w:firstLineChars="0" w:firstLine="240"/></w:pPr><w:r><w:t>三</w:t></w:r></w:p>
<w:p><w:pPr><w:ind w:firstLineChars="99999999" w:leftChars="junk"/></w:pPr><w:r><w:t>四</w:t></w:r></w:p>"#;
let d = wordcraft_docx::read(&docx(body)).unwrap();
let p = props(&d);
assert_eq!((p[0].indent_first_chars, p[0].indent_first), (Some(2.0), Some(21.0)));
assert_eq!((p[1].indent_left_chars, p[1].indent_right_chars, p[1].indent_first_chars), (Some(1.5), Some(0.5), Some(-1.0)));
// Zero cancels an inherited value; the points apply.
assert_eq!((p[2].indent_first_chars, p[2].indent_first), (Some(0.0), Some(12.0)));
// Hostile values are clamped or dropped.
assert_eq!((p[3].indent_first_chars, p[3].indent_left_chars), (Some(1584.0), None));
let _z_bytes = wordcraft_docx::write(&d).unwrap();
let mut z = craft_zip::Archive::open(&_z_bytes, craft_zip::Limits { max_entries: 10_000, max_total_bytes: 64 << 20 }).unwrap();
let xml = String::from_utf8(z.read("word/document.xml", 16 << 20).unwrap().unwrap()).unwrap();
for attr in [r#"w:firstLineChars="200""#, r#"w:leftChars="150""#, r#"w:rightChars="50""#, r#"w:hangingChars="100""#, r#"w:firstLineChars="0""#] {
assert!(xml.contains(attr), "{attr} missing: {xml}");
}
let again = props(&wordcraft_docx::read(&docx(&xml[xml.find("<w:body>").unwrap() + 8..xml.find("</w:body>").unwrap()])).unwrap());
assert_eq!(again[..3], p[..3]);
}
/// HTML-style automatic paragraph spacing (`w:beforeAutospacing`, `w:afterAutospacing`, ECMA-376
/// §17.3.1.33), common in text pasted from web pages: read, "0" switching an inherited one off,
/// and written back.
#[test]
fn automatic_spacing_reads_and_round_trips() {
let body = r#"<w:p><w:pPr><w:spacing w:before="100" w:beforeAutospacing="1" w:after="100" w:afterAutospacing="1"/></w:pPr><w:r><w:t>a</w:t></w:r></w:p>
<w:p><w:pPr><w:spacing w:before="0" w:beforeAutospacing="0" w:after="100" w:afterAutospacing="true"/></w:pPr><w:r><w:t>b</w:t></w:r></w:p>
<w:p><w:pPr><w:spacing w:after="100"/></w:pPr><w:r><w:t>c</w:t></w:r></w:p>"#;
let d = wordcraft_docx::read(&docx(body)).unwrap();
let p = props(&d);
assert_eq!((p[0].space_before_auto, p[0].space_after_auto, p[0].space_before), (Some(true), Some(true), Some(5.0)));
assert_eq!((p[1].space_before_auto, p[1].space_after_auto), (Some(false), Some(true)));
assert_eq!((p[2].space_before_auto, p[2].space_after_auto), (None, None));
let rp = d.styles.resolve_para(&p[0]);
assert_eq!((rp.space_before, rp.space_after, rp.before_auto), (14.0, 14.0, true), "automatic spacing is 14 pt");
assert_eq!(d.styles.resolve_para(&p[2]).space_after, 5.0);
let _z_bytes = wordcraft_docx::write(&d).unwrap();
let mut z = craft_zip::Archive::open(&_z_bytes, craft_zip::Limits { max_entries: 10_000, max_total_bytes: 64 << 20 }).unwrap();
let xml = String::from_utf8(z.read("word/document.xml", 16 << 20).unwrap().unwrap()).unwrap();
for attr in [r#"w:beforeAutospacing="1""#, r#"w:afterAutospacing="1""#, r#"w:beforeAutospacing="0""#] {
assert!(xml.contains(attr), "{attr} missing");
}
let again = wordcraft_docx::read(&wordcraft_docx::write(&d).unwrap()).unwrap();
assert_eq!(props(&again)[..3], p[..3]);
}
#[test]
fn adjust_right_indent_is_preserved() {
let body = r#"<w:p><w:pPr><w:adjustRightInd w:val="0"/><w:snapToGrid w:val="0"/><w:spacing w:after="120"/><w:ind w:right="120"/></w:pPr><w:r><w:t>false</w:t></w:r></w:p>
<w:p><w:pPr><w:adjustRightInd w:val="1"/></w:pPr><w:r><w:t>true</w:t></w:r></w:p>
<w:p><w:r><w:t>absent</w:t></w:r></w:p>"#;
let mut d = wordcraft_docx::read(&docx(body)).unwrap();
assert_eq!(props(&d).iter().map(|p| p.adjust_right_indent).collect::<Vec<_>>(), [Some(false), Some(true), None]);
for _ in 0..2 {
let out = wordcraft_docx::write(&d).unwrap();
let mut z = craft_zip::Archive::open(&out, craft_zip::Limits { max_entries: 10_000, max_total_bytes: 64 << 20 }).unwrap();
let xml = String::from_utf8(z.read("word/document.xml", 16 << 20).unwrap().unwrap()).unwrap();
assert!(xml.contains(r#"<w:adjustRightInd w:val="0""#), "explicit false was lost: {xml}");
assert!(xml.contains("<w:adjustRightInd/>"), "explicit true was lost: {xml}");
let tags = ["<w:adjustRightInd", "<w:snapToGrid", "<w:spacing", "<w:ind"];
let pprs = xml.split("<w:pPr>").skip(1).filter_map(|rest| rest.split("</w:pPr>").next()).collect::<Vec<_>>();
let first = pprs.first().expect("paragraph properties must be present");
for &tag in &tags {
assert!(first.contains(tag), "{tag} missing: {xml}");
}
for ppr in pprs {
let order = tags.iter().filter_map(|tag| ppr.find(*tag)).collect::<Vec<_>>();
assert!(order.windows(2).all(|pair| pair[0] < pair[1]), "paragraph properties are out of schema order: {xml}");
}
d = wordcraft_docx::read(&out).unwrap();
assert_eq!(props(&d).iter().map(|p| p.adjust_right_indent).collect::<Vec<_>>(), [Some(false), Some(true), None]);
}
}