mirror of
https://github.com/storytold/wordcraft.git
synced 2026-10-24 02:17:24 -06:00
aiongg
c795e3cd41
* CI: line-table debug info for dev builds, none for dependencies * CI: one integration-test binary per crate * CI: nextest with doctests, test build without examples, one wasm check * CI: the interface audit reports missing catalog entries instead of failing * Docs: the interface audit, not CI as a whole, passes with missing catalog entries
345 lines
24 KiB
Rust
345 lines
24 KiB
Rust
//! What a save keeps from a Word file beyond the document model (settings: `settings_merge.rs`):
|
|
//! package parts WordCraft doesn't write (carried verbatim),
|
|
//! comment durable ids and UTC dates, localized default styles, latent styles, list identities
|
|
//! and extended properties. Hand-written fixtures (from the spec), no files produced by Word.
|
|
|
|
use std::collections::BTreeMap;
|
|
use std::io::{Read, Write};
|
|
|
|
const W: &str = "http://schemas.openxmlformats.org/wordprocessingml/2006/main";
|
|
const R_NS: &str = "http://schemas.openxmlformats.org/officeDocument/2006/relationships";
|
|
const REL: &str = "http://schemas.openxmlformats.org/officeDocument/2006/relationships";
|
|
|
|
fn zip(entries: &[(&str, Vec<u8>)]) -> Vec<u8> {
|
|
let mut zw = zip::ZipWriter::new(std::io::Cursor::new(Vec::new()));
|
|
for (name, bytes) in entries {
|
|
zw.start_file(*name, zip::write::SimpleFileOptions::default()).unwrap();
|
|
zw.write_all(bytes).unwrap();
|
|
}
|
|
zw.finish().unwrap().into_inner()
|
|
}
|
|
|
|
fn unzip(bytes: &[u8]) -> BTreeMap<String, Vec<u8>> {
|
|
let mut z = zip::ZipArchive::new(std::io::Cursor::new(bytes)).unwrap();
|
|
let mut out = BTreeMap::new();
|
|
for i in 0..z.len() {
|
|
let mut f = z.by_index(i).unwrap();
|
|
let mut b = Vec::new();
|
|
f.read_to_end(&mut b).unwrap();
|
|
assert!(out.insert(f.name().to_string(), b).is_none(), "duplicate part {}", f.name());
|
|
}
|
|
out
|
|
}
|
|
|
|
fn text(files: &BTreeMap<String, Vec<u8>>, name: &str) -> String {
|
|
String::from_utf8(files.get(name).unwrap_or_else(|| panic!("no {name} in {:?}", files.keys())).clone()).unwrap()
|
|
}
|
|
|
|
fn rels(list: &[(&str, &str, &str)]) -> Vec<u8> {
|
|
let mut s =
|
|
String::from(r#"<?xml version="1.0" encoding="UTF-8"?><Relationships xmlns="http://schemas.openxmlformats.org/package/2006/relationships">"#);
|
|
for (id, ty, target) in list {
|
|
s.push_str(&format!(r#"<Relationship Id="{id}" Type="{ty}" Target="{target}"/>"#));
|
|
}
|
|
s.push_str("</Relationships>");
|
|
s.into_bytes()
|
|
}
|
|
|
|
/// A package: `body`, document relationships, root relationships after the main document's,
|
|
/// and extra parts.
|
|
fn package(body: &str, doc_rels: &[(&str, &str, &str)], root_rels: &[(&str, &str, &str)], extra: &[(&str, &str)]) -> Vec<u8> {
|
|
let doc = format!(
|
|
r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?><w:document xmlns:w="{W}" xmlns:r="{R_NS}" xmlns:w14="http://schemas.microsoft.com/office/word/2010/wordml"><w:body>{body}</w:body></w:document>"#
|
|
);
|
|
let mut root = vec![("rIdMain", "http://schemas.openxmlformats.org/officeDocument/2006/relationships/officeDocument", "word/document.xml")];
|
|
root.extend_from_slice(root_rels);
|
|
let mut entries: Vec<(&str, Vec<u8>)> =
|
|
vec![("_rels/.rels", rels(&root)), ("word/document.xml", doc.into_bytes()), ("word/_rels/document.xml.rels", rels(doc_rels))];
|
|
for (p, c) in extra {
|
|
entries.push((p, c.as_bytes().to_vec()));
|
|
}
|
|
zip(&entries)
|
|
}
|
|
|
|
fn save(doc: &wordcraft_doc::Document) -> BTreeMap<String, Vec<u8>> {
|
|
unzip(&wordcraft_docx::write(doc).expect("write"))
|
|
}
|
|
|
|
const SETTINGS: &str = r#"<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
|
<w:settings xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships" xmlns:m="http://schemas.openxmlformats.org/officeDocument/2006/math" xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006" xmlns:w14="http://schemas.microsoft.com/office/word/2010/wordml" xmlns:w15="http://schemas.microsoft.com/office/word/2012/wordml" mc:Ignorable="w14 w15"><w:zoom w:percent="120"/><w:removePersonalInformation/><w:removeDateAndTime/><w:proofState w:spelling="clean" w:grammar="clean"/><w:mailMerge><w:mainDocumentType w:val="formLetters"/><w:dataSource r:id="rId9"/></w:mailMerge><w:trackRevisions/><w:defaultTabStop w:val="708"/><w:hyphenationZone w:val="425"/><w:characterSpacingControl w:val="doNotCompress"/><w:compat><w:compatSetting w:name="compatibilityMode" w:uri="http://schemas.microsoft.com/office/word" w:val="15"/><w:compatSetting w:name="overrideTableStyleFontSizeAndJustification" w:uri="http://schemas.microsoft.com/office/word" w:val="1"/><w:compatSetting w:name="enableOpenTypeFeatures" w:uri="http://schemas.microsoft.com/office/word" w:val="1"/></w:compat><w:docVars><w:docVar w:name="ClauseSet" w:val="B"/></w:docVars><w:rsids><w:rsidRoot w:val="00A1B2C3"/><w:rsid w:val="00A1B2C3"/></w:rsids><m:mathPr><m:mathFont m:val="Cambria Math"/><m:smallFrac m:val="0"/></m:mathPr><w:themeFontLang w:val="pl-PL"/><w:decimalSymbol w:val=","/><w:listSeparator w:val=";"/><w14:docId w14:val="1A2B3C4D"/></w:settings>"#;
|
|
|
|
fn pos(s: &str, needle: &str) -> usize {
|
|
s.find(needle).unwrap_or_else(|| panic!("{needle} missing from {s}"))
|
|
}
|
|
|
|
const CT: &str = r#"<?xml version="1.0" encoding="UTF-8"?><Types xmlns="http://schemas.openxmlformats.org/package/2006/content-types"><Default Extension="rels" ContentType="application/vnd.openxmlformats-package.relationships+xml"/><Default Extension="xml" ContentType="application/xml"/><Default Extension="jpeg" ContentType="image/jpeg"/><Override PartName="/word/document.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.document.main+xml"/><Override PartName="/word/webSettings.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.webSettings+xml"/><Override PartName="/word/stylesWithEffects.xml" ContentType="application/vnd.ms-word.stylesWithEffects+xml"/><Override PartName="/word/people.xml" ContentType="application/vnd.openxmlformats-officedocument.wordprocessingml.people+xml"/><Override PartName="/word/webextensions/taskpanes.xml" ContentType="application/vnd.ms-office.webextensiontaskpanes+xml"/><Override PartName="/word/webextensions/webextension1.xml" ContentType="application/vnd.ms-office.webextension+xml"/><Override PartName="/word/unknownPart.xml" ContentType="application/x-unknown+xml"/></Types>"#;
|
|
|
|
#[test]
|
|
fn unmodelled_parts_are_carried_with_relationships_and_content_types() {
|
|
let web = r#"<w:webSettings xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:optimizeForBrowser/><w:allowPNG/></w:webSettings>"#;
|
|
let swe =
|
|
r#"<w:styles xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:style w:type="paragraph" w:styleId="X"/></w:styles>"#;
|
|
let people = r#"<w15:people xmlns:w15="http://schemas.microsoft.com/office/word/2012/wordml"><w15:person w15:author="Ann"><w15:presenceInfo w15:providerId="None" w15:userId="Ann"/></w15:person></w15:people>"#;
|
|
let panes = r#"<wetp:taskpanes xmlns:wetp="http://schemas.microsoft.com/office/webextensions/taskpanes/2010/11" xmlns:r="http://schemas.openxmlformats.org/officeDocument/2006/relationships"><wetp:taskpane dockstate="right" visibility="0" width="350" row="1"><wetp:webextensionref r:id="rId1"/></wetp:taskpane></wetp:taskpanes>"#;
|
|
let ext = r#"<we:webextension xmlns:we="http://schemas.microsoft.com/office/webextensions/webextension/2010/11" id="{00000000-0000-0000-0000-000000000001}"><we:reference id="wa0" version="1.0.0.0" store="en-US" storeType="OMEX"/></we:webextension>"#;
|
|
let unknown = r#"<x:thing xmlns:x="urn:example:future"/>"#;
|
|
let thumb = "\u{ff}\u{d8}\u{ff}JPEG";
|
|
let panes_rels =
|
|
String::from_utf8(rels(&[("rId1", "http://schemas.microsoft.com/office/2011/relationships/webextension", "webextension1.xml")])).unwrap();
|
|
let bytes = package(
|
|
r#"<w:p><w:r><w:t>Body</w:t></w:r></w:p>"#,
|
|
&[
|
|
("rId1", &format!("{REL}/webSettings"), "webSettings.xml"),
|
|
("rId2", "http://schemas.microsoft.com/office/2007/relationships/stylesWithEffects", "stylesWithEffects.xml"),
|
|
("rId3", "http://schemas.microsoft.com/office/2011/relationships/people", "people.xml"),
|
|
("rId4", "urn:example:future-relationship", "unknownPart.xml"),
|
|
],
|
|
&[
|
|
("rIdT", "http://schemas.openxmlformats.org/package/2006/relationships/metadata/thumbnail", "docProps/thumbnail.jpeg"),
|
|
("rIdW", "http://schemas.microsoft.com/office/2011/relationships/webextensiontaskpanes", "word/webextensions/taskpanes.xml"),
|
|
],
|
|
&[
|
|
("[Content_Types].xml", CT),
|
|
("word/webSettings.xml", web),
|
|
("word/stylesWithEffects.xml", swe),
|
|
("word/people.xml", people),
|
|
("word/unknownPart.xml", unknown),
|
|
("docProps/thumbnail.jpeg", thumb),
|
|
("word/webextensions/taskpanes.xml", panes),
|
|
("word/webextensions/_rels/taskpanes.xml.rels", &panes_rels),
|
|
("word/webextensions/webextension1.xml", ext),
|
|
],
|
|
);
|
|
let doc = wordcraft_docx::read(&bytes).unwrap();
|
|
let files = save(&doc);
|
|
let input = unzip(&bytes);
|
|
for part in [
|
|
"word/webSettings.xml",
|
|
"word/stylesWithEffects.xml",
|
|
"word/people.xml",
|
|
"word/unknownPart.xml",
|
|
"docProps/thumbnail.jpeg",
|
|
"word/webextensions/taskpanes.xml",
|
|
"word/webextensions/webextension1.xml",
|
|
] {
|
|
assert_eq!(files.get(part), input.get(part), "{part} not carried verbatim");
|
|
}
|
|
let doc_rels = text(&files, "word/_rels/document.xml.rels");
|
|
for ty in ["/webSettings\"", "/stylesWithEffects\"", "/people\"", "urn:example:future-relationship"] {
|
|
assert_eq!(doc_rels.matches(ty).count(), 1, "{ty}: {doc_rels}");
|
|
}
|
|
let root_rels = text(&files, "_rels/.rels");
|
|
assert!(root_rels.contains(r#"Target="docProps/thumbnail.jpeg""#) && root_rels.contains("webextensiontaskpanes"), "{root_rels}");
|
|
assert!(text(&files, "word/webextensions/_rels/taskpanes.xml.rels").contains("webextension1.xml"));
|
|
let ct = text(&files, "[Content_Types].xml");
|
|
for (part, ty) in [
|
|
("/word/webSettings.xml", "webSettings+xml"),
|
|
("/word/stylesWithEffects.xml", "stylesWithEffects+xml"),
|
|
("/word/people.xml", "people+xml"),
|
|
("/word/webextensions/taskpanes.xml", "webextensiontaskpanes+xml"),
|
|
("/docProps/thumbnail.jpeg", "image/jpeg"),
|
|
] {
|
|
let entry = ct.split("<Override ").find(|o| o.contains(&format!(r#"PartName="{part}""#))).unwrap_or_else(|| panic!("{part}: {ct}"));
|
|
assert!(entry.contains(ty), "{part}: {entry}");
|
|
}
|
|
// Saved again: the same parts, still once each (`unzip` rejects duplicates).
|
|
let again = save(&wordcraft_docx::read(&wordcraft_docx::write(&doc).unwrap()).unwrap());
|
|
assert_eq!(again.get("word/webSettings.xml"), input.get("word/webSettings.xml"));
|
|
assert_eq!(text(&again, "word/_rels/document.xml.rels").matches("/webSettings\"").count(), 1);
|
|
}
|
|
|
|
#[test]
|
|
fn parts_the_writer_owns_or_the_body_refers_to_are_not_carried() {
|
|
// A second styles part, and an unknown part the body refers to by id: neither is carried
|
|
// (the first would contradict the written styles, the second's element isn't kept).
|
|
let bytes = package(
|
|
r#"<w:p><w:r><w:t>Body</w:t></w:r><w:customThing r:id="rId8"/></w:p>"#,
|
|
&[("rId7", &format!("{REL}/styles"), "other-styles.xml"), ("rId8", "urn:example:referenced", "referenced.xml")],
|
|
&[],
|
|
&[
|
|
("word/other-styles.xml", r#"<w:styles xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"/>"#),
|
|
("word/referenced.xml", "<x/>"),
|
|
],
|
|
);
|
|
let files = save(&wordcraft_docx::read(&bytes).unwrap());
|
|
assert!(!files.contains_key("word/other-styles.xml") && !files.contains_key("word/referenced.xml"), "{:?}", files.keys());
|
|
assert_eq!(text(&files, "word/_rels/document.xml.rels").matches("/styles\"").count(), 1);
|
|
}
|
|
|
|
fn comments_package(with_ids: bool) -> Vec<u8> {
|
|
let comments = r#"<w:comments xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main" xmlns:w14="http://schemas.microsoft.com/office/word/2010/wordml"><w:comment w:id="0" w:author="Ann" w:date="2026-01-02T10:00:00" w:initials="A"><w:p w14:paraId="11111111"><w:r><w:t>First</w:t></w:r></w:p></w:comment><w:comment w:id="1" w:author="Ben" w:date="2026-01-03T11:00:00" w:initials="B"><w:p w14:paraId="22222222"><w:r><w:t>Reply</w:t></w:r></w:p></w:comment></w:comments>"#;
|
|
let ex = r#"<w15:commentsEx xmlns:w15="http://schemas.microsoft.com/office/word/2012/wordml"><w15:commentEx w15:paraId="11111111" w15:done="0"/><w15:commentEx w15:paraId="22222222" w15:paraIdParent="11111111" w15:done="0"/></w15:commentsEx>"#;
|
|
let ids = r#"<w16cid:commentsIds xmlns:w16cid="http://schemas.microsoft.com/office/word/2016/wordml/cid"><w16cid:commentId w16cid:paraId="11111111" w16cid:durableId="5A1B2C3D"/><w16cid:commentId w16cid:paraId="22222222" w16cid:durableId="0F00BA12"/></w16cid:commentsIds>"#;
|
|
let cex = r#"<w16cex:commentsExtensible xmlns:w16cex="http://schemas.microsoft.com/office/word/2018/wordml/cex"><w16cex:commentExtensible w16cex:durableId="5A1B2C3D" w16cex:dateUtc="2026-01-02T09:00:00Z"/><w16cex:commentExtensible w16cex:durableId="0F00BA12" w16cex:dateUtc="2026-01-03T10:00:00Z"/></w16cex:commentsExtensible>"#;
|
|
let body = r#"<w:p><w:commentRangeStart w:id="0"/><w:commentRangeStart w:id="1"/><w:r><w:t>Text</w:t></w:r><w:commentRangeEnd w:id="0"/><w:r><w:rPr><w:rStyle w:val="Odwoaniedokomentarza"/></w:rPr><w:commentReference w:id="0"/></w:r><w:commentRangeEnd w:id="1"/><w:r><w:rPr><w:rStyle w:val="Odwoaniedokomentarza"/></w:rPr><w:commentReference w:id="1"/></w:r></w:p>"#;
|
|
let styles = r#"<w:styles xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:style w:type="paragraph" w:default="1" w:styleId="Normalny"><w:name w:val="Normal"/></w:style><w:style w:type="character" w:default="1" w:styleId="Domylnaczcionkaakapitu"><w:name w:val="Default Paragraph Font"/></w:style><w:style w:type="character" w:styleId="Odwoaniedokomentarza"><w:name w:val="annotation reference"/><w:basedOn w:val="Domylnaczcionkaakapitu"/><w:rPr><w:sz w:val="16"/></w:rPr></w:style></w:styles>"#;
|
|
let mut doc_rels = vec![
|
|
("rId1", format!("{REL}/comments"), "comments.xml"),
|
|
("rId2", "http://schemas.microsoft.com/office/2011/relationships/commentsExtended".to_string(), "commentsExtended.xml"),
|
|
("rId5", format!("{REL}/styles"), "styles.xml"),
|
|
];
|
|
let mut extra = vec![("word/comments.xml", comments), ("word/commentsExtended.xml", ex), ("word/styles.xml", styles)];
|
|
if with_ids {
|
|
doc_rels.push(("rId3", "http://schemas.microsoft.com/office/2016/09/relationships/commentsIds".into(), "commentsIds.xml"));
|
|
doc_rels.push(("rId4", "http://schemas.microsoft.com/office/2018/08/relationships/commentsExtensible".into(), "commentsExtensible.xml"));
|
|
extra.push(("word/commentsIds.xml", ids));
|
|
extra.push(("word/commentsExtensible.xml", cex));
|
|
}
|
|
let doc_rels: Vec<(&str, &str, &str)> = doc_rels.iter().map(|(a, b, c)| (*a, b.as_str(), *c)).collect();
|
|
package(body, &doc_rels, &[], &extra)
|
|
}
|
|
|
|
/// (paragraph id → durable id) from commentsIds, and (durable id → UTC date) from
|
|
/// commentsExtensible, as written.
|
|
fn written_ids(files: &BTreeMap<String, Vec<u8>>) -> (Vec<(String, String)>, Vec<(String, String)>) {
|
|
let attr = |el: &str, name: &str| -> Option<String> { el.split(&format!("{name}=\"")).nth(1)?.split('"').next().map(str::to_string) };
|
|
let ids = text(files, "word/commentsIds.xml")
|
|
.split("<w16cid:commentId ")
|
|
.skip(1)
|
|
.filter_map(|e| Some((attr(e, "w16cid:paraId")?, attr(e, "w16cid:durableId")?)))
|
|
.collect();
|
|
let dates = text(files, "word/commentsExtensible.xml")
|
|
.split("<w16cex:commentExtensible ")
|
|
.skip(1)
|
|
.filter_map(|e| Some((attr(e, "w16cex:durableId")?, attr(e, "w16cex:dateUtc").unwrap_or_default())))
|
|
.collect();
|
|
(ids, dates)
|
|
}
|
|
|
|
#[test]
|
|
fn comment_durable_ids_and_utc_dates_survive_and_match_the_written_paragraph_ids() {
|
|
let doc = wordcraft_docx::read(&comments_package(true)).unwrap();
|
|
let c: Vec<_> = doc.comments.values().collect();
|
|
assert_eq!(c[0].durable_id.as_deref(), Some("5A1B2C3D"));
|
|
assert_eq!(c[1].date_utc.as_deref(), Some("2026-01-03T10:00:00Z"));
|
|
let files = save(&doc);
|
|
let (ids, dates) = written_ids(&files);
|
|
assert_eq!(ids.iter().map(|(_, d)| d.as_str()).collect::<Vec<_>>(), ["5A1B2C3D", "0F00BA12"]);
|
|
// Each paragraph id is the one the comment's paragraph got in comments.xml.
|
|
let comments = text(&files, "word/comments.xml");
|
|
for (pid, _) in &ids {
|
|
assert!(comments.contains(&format!(r#"w14:paraId="{pid}""#)), "{pid}: {comments}");
|
|
}
|
|
assert_eq!(dates, [("5A1B2C3D".into(), "2026-01-02T09:00:00Z".into()), ("0F00BA12".into(), "2026-01-03T10:00:00Z".into())]);
|
|
let rels = text(&files, "word/_rels/document.xml.rels");
|
|
assert!(rels.contains("relationships/commentsIds") && rels.contains("relationships/commentsExtensible"), "{rels}");
|
|
// Read back: the same durable ids and dates.
|
|
let back = wordcraft_docx::read(&wordcraft_docx::write(&doc).unwrap()).unwrap();
|
|
assert_eq!(
|
|
back.comments.values().map(|c| c.durable_id.clone()).collect::<Vec<_>>(),
|
|
doc.comments.values().map(|c| c.durable_id.clone()).collect::<Vec<_>>()
|
|
);
|
|
assert_eq!(
|
|
back.comments.values().map(|c| c.date_utc.clone()).collect::<Vec<_>>(),
|
|
doc.comments.values().map(|c| c.date_utc.clone()).collect::<Vec<_>>()
|
|
);
|
|
}
|
|
|
|
#[test]
|
|
fn comments_without_durable_ids_get_unique_ones() {
|
|
let doc = wordcraft_docx::read(&comments_package(false)).unwrap();
|
|
let (ids, dates) = written_ids(&save(&doc));
|
|
assert_eq!(ids.len(), 2);
|
|
assert_ne!(ids[0].1, ids[1].1);
|
|
for (_, d) in &ids {
|
|
let v = u32::from_str_radix(d, 16).unwrap();
|
|
assert!(v != 0 && v < 0x7FFF_FFFF, "{d}");
|
|
}
|
|
// Local dates without a zone aren't passed off as UTC.
|
|
assert!(dates.iter().all(|(_, utc)| utc.is_empty()), "{dates:?}");
|
|
}
|
|
|
|
#[test]
|
|
fn comment_references_use_the_documents_annotation_reference_style() {
|
|
let files = save(&wordcraft_docx::read(&comments_package(true)).unwrap());
|
|
let body = text(&files, "word/document.xml");
|
|
assert!(body.contains(r#"<w:rStyle w:val="Odwoaniedokomentarza"/>"#), "{body}");
|
|
assert!(!body.contains(r#"w:val="CommentReference""#), "{body}");
|
|
// A document without that style keeps the English id.
|
|
let mut doc = wordcraft_doc::Document::new();
|
|
doc.styles.styles.retain(|s| !s.name.eq_ignore_ascii_case("annotation reference"));
|
|
let rebuilt = wordcraft_docx::read(&comments_package(true)).unwrap();
|
|
doc.body = rebuilt.body.clone();
|
|
doc.parts = rebuilt.parts.clone();
|
|
doc.comments = rebuilt.comments.clone();
|
|
assert!(text(&save(&doc), "word/document.xml").contains(r#"w:val="CommentReference""#));
|
|
}
|
|
|
|
#[test]
|
|
fn localized_default_styles_keep_their_default_flag() {
|
|
let styles = r#"<w:styles xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:latentStyles w:defLockedState="0" w:defUIPriority="99" w:defSemiHidden="0" w:defUnhideWhenUsed="0" w:defQFormat="0" w:count="376"><w:lsdException w:name="Normal" w:uiPriority="0" w:qFormat="1"/><w:lsdException w:name="heading 1" w:uiPriority="9" w:qFormat="1"/></w:latentStyles><w:style w:type="paragraph" w:default="1" w:styleId="Normalny"><w:name w:val="Normal"/></w:style><w:style w:type="character" w:default="1" w:styleId="Domylnaczcionkaakapitu"><w:name w:val="Default Paragraph Font"/></w:style><w:style w:type="table" w:default="1" w:styleId="Standardowy"><w:name w:val="Normal Table"/></w:style><w:style w:type="numbering" w:default="1" w:styleId="Bezlisty"><w:name w:val="No List"/></w:style></w:styles>"#;
|
|
let bytes =
|
|
package("<w:p><w:r><w:t>x</w:t></w:r></w:p>", &[("rId1", &format!("{REL}/styles"), "styles.xml")], &[], &[("word/styles.xml", styles)]);
|
|
let doc = wordcraft_docx::read(&bytes).unwrap();
|
|
let s = text(&save(&doc), "word/styles.xml");
|
|
for id in ["Domylnaczcionkaakapitu", "Standardowy", "Bezlisty"] {
|
|
assert!(s.contains(&format!(r#"w:default="1" w:styleId="{id}""#)) || s.contains(&format!(r#"w:styleId="{id}" w:default="1""#)), "{id}: {s}");
|
|
}
|
|
assert_eq!(s.matches(r#"w:default="1""#).count(), 4, "{s}");
|
|
// Latent styles come back as they were, before the styles.
|
|
assert!(s.contains(r#"<w:lsdException w:name="heading 1" w:uiPriority="9" w:qFormat="1"/>"#), "{s}");
|
|
assert!(pos(&s, "<w:latentStyles") < pos(&s, "<w:style "), "{s}");
|
|
// A new document still flags the English defaults.
|
|
let fresh = text(&save(&wordcraft_doc::Document::new()), "word/styles.xml");
|
|
assert!(fresh.contains(r#"w:styleId="Normal" w:default="1""#) || fresh.contains(r#"w:default="1" w:styleId="Normal""#), "{fresh}");
|
|
}
|
|
|
|
#[test]
|
|
fn list_identities_survive_and_a_copied_definition_gets_none() {
|
|
let numbering = r#"<w:numbering xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main"><w:abstractNum w:abstractNumId="0"><w:nsid w:val="1F2E3D4C"/><w:multiLevelType w:val="hybridMultilevel"/><w:tmpl w:val="0415000F"/><w:lvl w:ilvl="0"><w:start w:val="1"/><w:numFmt w:val="decimal"/><w:lvlText w:val="%1."/></w:lvl></w:abstractNum><w:num w:numId="1"><w:abstractNumId w:val="0"/></w:num></w:numbering>"#;
|
|
let bytes = package(
|
|
r#"<w:p><w:pPr><w:numPr><w:ilvl w:val="0"/><w:numId w:val="1"/></w:numPr></w:pPr><w:r><w:t>x</w:t></w:r></w:p>"#,
|
|
&[("rId1", &format!("{REL}/numbering"), "numbering.xml")],
|
|
&[],
|
|
&[("word/numbering.xml", numbering)],
|
|
);
|
|
let mut doc = wordcraft_docx::read(&bytes).unwrap();
|
|
let n = text(&save(&doc), "word/numbering.xml");
|
|
assert!(n.contains(r#"<w:nsid w:val="1F2E3D4C"/><w:multiLevelType w:val="hybridMultilevel"/><w:tmpl w:val="0415000F"/>"#), "{n}");
|
|
// A copy of the definition (as the engine makes when restarting a list) doesn't reuse the nsid.
|
|
let mut copy = doc.numbering.abstracts[0].clone();
|
|
copy.id = 7;
|
|
doc.numbering.abstracts.push(copy);
|
|
let n = text(&save(&doc), "word/numbering.xml");
|
|
assert_eq!(n.matches("1F2E3D4C").count(), 1, "{n}");
|
|
}
|
|
|
|
#[test]
|
|
fn extended_properties_are_kept_without_words_counts_and_personal_ones_follow_the_privacy_setting() {
|
|
let app = r#"<Properties xmlns="http://schemas.openxmlformats.org/officeDocument/2006/extended-properties" xmlns:vt="http://schemas.openxmlformats.org/officeDocument/2006/docPropsVTypes"><Template>Normal.dotm</Template><TotalTime>42</TotalTime><Pages>107</Pages><Words>40000</Words><Characters>250000</Characters><Application>Microsoft Office Word</Application><DocSecurity>0</DocSecurity><Lines>2000</Lines><Paragraphs>1700</Paragraphs><ScaleCrop>false</ScaleCrop><Manager>M</Manager><Company>Firma</Company><LinksUpToDate>false</LinksUpToDate><CharactersWithSpaces>290000</CharactersWithSpaces><SharedDoc>false</SharedDoc><HyperlinkBase>https://example.com/</HyperlinkBase><HyperlinksChanged>false</HyperlinksChanged><AppVersion>16.0000</AppVersion></Properties>"#;
|
|
let make = |settings: &str| {
|
|
let mut entries = vec![("docProps/app.xml", app)];
|
|
let mut doc_rels = vec![];
|
|
let s;
|
|
if !settings.is_empty() {
|
|
s = settings.to_string();
|
|
entries.push(("word/settings.xml", s.as_str()));
|
|
doc_rels.push(("rId1", format!("{REL}/settings"), "settings.xml"));
|
|
}
|
|
let doc_rels: Vec<(&str, &str, &str)> = doc_rels.iter().map(|(a, b, c)| (*a, b.as_str(), *c)).collect();
|
|
let b = package(
|
|
"<w:p><w:r><w:t>x</w:t></w:r></w:p>",
|
|
&doc_rels,
|
|
&[("rIdA", "http://schemas.openxmlformats.org/officeDocument/2006/relationships/extended-properties", "docProps/app.xml")],
|
|
&entries,
|
|
);
|
|
text(&save(&wordcraft_docx::read(&b).unwrap()), "docProps/app.xml")
|
|
};
|
|
let a = make("");
|
|
for kept in [
|
|
"<Template>Normal.dotm</Template>",
|
|
"<Company>Firma</Company>",
|
|
"<Manager>M</Manager>",
|
|
"<HyperlinkBase>https://example.com/</HyperlinkBase>",
|
|
] {
|
|
assert!(a.contains(kept), "{kept}: {a}");
|
|
}
|
|
for gone in ["Pages", "Characters", "Lines", "TotalTime", "AppVersion", "Microsoft Office Word", "40000"] {
|
|
assert!(!a.contains(gone), "{gone}: {a}");
|
|
}
|
|
assert!(a.contains("<Application>WordCraft</Application>"));
|
|
let private = make(SETTINGS);
|
|
assert!(!private.contains("Company") && !private.contains("Manager"), "{private}");
|
|
assert!(private.contains("<Template>Normal.dotm</Template>"));
|
|
}
|