Skip to content

DesignCraft: An open-source page and layout design editor written by scratch in pure Rust

refactor(textimport): move the tests module of docx.rs to docx/tests.rs

aiongg53b3144ab528
diff --git a/crates/textimport/src/docx.rs b/crates/textimport/src/docx.rs
index 346e9601e..94085ca69 100644
--- a/crates/textimport/src/docx.rs
+++ b/crates/textimport/src/docx.rs
@@ -582,527 +582,4 @@ pub fn import(bytes: &[u8]) -> Result<Imported, ImportError> {
}
#[cfg(test)]
-mod tests {
- use super::*;
- use std::io::Write;
-
- #[test]
- fn cdata_text() {
- let el = parse("<a><t><![CDATA[x < y]]></t></a>").unwrap();
- assert_eq!(el.child("t").unwrap().text(), "x < y");
- }
-
- /// Issue #712: nesting past the budget is an error from the parser, not a stack overflow later.
- #[test]
- fn nesting_past_the_budget_is_refused() {
- let nested = |n: usize| format!("{}{}", "<w:p>".repeat(n), "</w:p>".repeat(n));
- let ok = parse(&nested(MAX_DEPTH)).expect("the budget itself parses");
- assert_eq!(ok.name, "p");
- let err = parse(&nested(MAX_DEPTH + 1)).expect_err("one level more is refused");
- assert!(err.to_string().contains("nested deeper"), "{err}");
- assert!(parse(&nested(100_000)).is_err());
- }
-
- #[test]
- fn table_adds_no_empty_paragraph() {
- let document = format!(
- r#"<w:document {W}><w:body>
- <w:p><w:r><w:t>Before</w:t></w:r></w:p>
- <w:tbl><w:tr><w:tc><w:p><w:r><w:t>A</w:t></w:r></w:p></w:tc></w:tr></w:tbl>
- <w:p><w:r><w:t>After</w:t></w:r></w:p>
- </w:body></w:document>"#
- );
- let st = import(&docx(&document, "", "")).unwrap().story;
- st.check().unwrap();
- let paras: Vec<&str> = st.para_ranges().into_iter().map(|r| &st.text[r]).collect();
- assert_eq!(paras.len(), 3, "{paras:?}");
- assert_eq!(paras[0], "Before");
- assert_eq!(paras[2], "After");
- }
-
- pub(crate) fn docx(document: &str, styles: &str, footnotes: &str) -> Vec<u8> {
- docx_parts(&[("word/document.xml", document), ("word/styles.xml", styles), ("word/footnotes.xml", footnotes)])
- }
-
- /// A zip of `(part name, XML)`; empty parts are left out.
- fn docx_parts(parts: &[(&str, &str)]) -> Vec<u8> {
- let mut w = zip::ZipWriter::new(std::io::Cursor::new(Vec::new()));
- let o = zip::write::SimpleFileOptions::default();
- for &(n, c) in parts {
- if c.is_empty() {
- continue;
- }
- w.start_file(n, o).unwrap();
- w.write_all(c.as_bytes()).unwrap();
- }
- w.finish().unwrap().into_inner()
- }
-
- const W: &str = r#"xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main""#;
-
- #[test]
- fn oversized_part_is_an_error_not_a_huge_read() {
- // A highly compressible part: 64 KiB of spaces inflates past a 4 KiB cap.
- let big = docx(&" ".repeat(64 * 1024), "", "");
- let mut zip = zip::ZipArchive::new(std::io::Cursor::new(big.as_slice())).unwrap();
- assert!(matches!(part_capped(&mut zip, "word/document.xml", 4096), Err(ImportError::Corrupt(_))));
- // At or under the cap reads fine; a missing part is `None`.
- assert_eq!(part_capped(&mut zip, "word/document.xml", 64 * 1024).unwrap().map(|s| s.len()), Some(64 * 1024));
- assert_eq!(part_capped(&mut zip, "word/missing.xml", 4096).unwrap(), None);
- }
-
- /// A DOCX can hold any number where a measure belongs: `1e300` twips became a 5e298 pt
- /// indent, and `w:sz` of `1e300` a 5e299 pt type size. Measures are clamped to the widest
- /// page and a size the engine cannot mean is dropped (#1593).
- #[test]
- fn a_measure_or_size_a_file_cannot_mean_is_bounded() {
- use designcraft_doc::attrs::MAX_MEASURE;
- let doc = format!(
- r#"<w:document {W}><w:body><w:p><w:pPr>
- <w:spacing w:before="1e300" w:after="-1e300"/><w:ind w:left="1e300" w:firstLine="-1e300"/>
- </w:pPr><w:r><w:rPr><w:sz w:val="1e300"/></w:rPr><w:t>big</w:t></w:r></w:p></w:body></w:document>"#
- );
- let i = import(&docx(&doc, "", "")).unwrap();
- let p = &i.story.paras[0].para;
- for (what, v) in
- [("space before", p.space_before), ("space after", p.space_after), ("left indent", p.left_indent), ("first line", p.first_line_indent)]
- {
- let v = v.expect("the value is kept, bounded");
- assert!(v.is_finite() && v.abs() <= MAX_MEASURE, "{what} is within the widest page: {v}");
- }
- let size = i.story.char_format_at(i.story.text.find("big").unwrap() + 1).over.size;
- assert_eq!(size, None, "a size the engine cannot mean is dropped, so the style's size stands");
- }
-
- #[test]
- fn imports_styles_runs_footnotes_and_tables() {
- let styles = format!(
- r#"<w:styles {W}>
- <w:style w:type="paragraph" 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:pPr><w:spacing w:before="240" w:after="120"/></w:pPr><w:rPr><w:b/><w:sz w:val="32"/></w:rPr></w:style>
- <w:style w:type="paragraph" w:styleId="Unused"><w:name w:val="Unused"/></w:style>
- <w:style w:type="character" w:styleId="Emph"><w:name w:val="Emphasis"/><w:rPr><w:i/></w:rPr></w:style>
- </w:styles>"#
- );
- let document = format!(
- r#"<w:document {W}><w:body>
- <w:p><w:pPr><w:pStyle w:val="Heading1"/></w:pPr><w:r><w:t>Title &amp; more</w:t></w:r></w:p>
- <w:p><w:r><w:t xml:space="preserve">Plain </w:t></w:r><w:r><w:rPr><w:b/></w:rPr><w:t>bold</w:t></w:r>
- <w:r><w:rPr><w:rStyle w:val="Emph"/></w:rPr><w:t> styled</w:t></w:r><w:r><w:tab/><w:t>x</w:t></w:r>
- <w:r><w:footnoteReference w:id="1"/></w:r></w:p>
- <w:tbl><w:tr><w:tc><w:p><w:r><w:t>A</w:t></w:r></w:p></w:tc><w:tc><w:p><w:r><w:t>B</w:t></w:r></w:p></w:tc></w:tr></w:tbl>
- <w:p><w:r><w:t>After</w:t></w:r></w:p>
- </w:body></w:document>"#
- );
- let notes = format!(
- r#"<w:footnotes {W}><w:footnote w:id="0"><w:p/></w:footnote>
- <w:footnote w:id="1"><w:p><w:r><w:t>The note.</w:t></w:r></w:p></w:footnote></w:footnotes>"#
- );
- let i = import(&docx(&document, &styles, &notes)).unwrap();
- let st = &i.story;
- st.check().unwrap();
- assert!(st.text.starts_with("Title & more\nPlain bold styled\tx"), "{:?}", st.text);
- assert!(st.text.ends_with("After"));
- assert_eq!(st.paras[0].style, "heading 1");
- assert_eq!(st.paras[1].style, "Normal");
- let at = st.text.find("bold").unwrap();
- assert_eq!(st.format_after(at).over.font_style.as_deref(), Some("Bold"));
- assert_eq!(st.format_after(st.text.find("styled").unwrap()).style, "Emphasis");
- assert_eq!(st.notes.len(), 1);
- assert_eq!(st.notes[0].text.text, "The note.");
- assert_eq!(st.tables.len(), 1);
- let names: Vec<&str> = i.para_styles.iter().map(|s| s.name.as_str()).collect();
- assert_eq!(names, ["Normal", "heading 1"], "unused styles are skipped");
- assert_eq!(i.para_styles[1].based_on.as_deref(), Some("Normal"));
- assert_eq!(i.para_styles[1].chars.size, Some(16.0));
- assert_eq!(i.para_styles[1].para.space_before, Some(12.0));
- assert_eq!(i.char_styles[0].chars.font_style.as_deref(), Some("Italic"));
- }
-
- /// A content control inside a paragraph (`w:sdt`) keeps its text, also around a hyperlink.
- #[test]
- fn inline_content_control_text_is_kept() {
- let document = format!(
- r#"<w:document {W}><w:body>
- <w:p><w:r><w:t xml:space="preserve">Date: </w:t></w:r><w:sdt><w:sdtPr><w:alias w:val="d"/></w:sdtPr><w:sdtContent><w:r><w:t>1 May 2026</w:t></w:r></w:sdtContent></w:sdt><w:r><w:t>.</w:t></w:r></w:p>
- <w:p><w:sdt><w:sdtContent><w:hyperlink><w:r><w:t>Link</w:t></w:r></w:hyperlink></w:sdtContent></w:sdt></w:p>
- </w:body></w:document>"#
- );
- let st = import(&docx(&document, "", "")).unwrap().story;
- st.check().unwrap();
- assert_eq!(st.text, "Date: 1 May 2026.\nLink");
- }
-
- /// `str::parse::<f64>` accepts "NaN"/"inf"; sizes, spacing and indents must ignore them.
- #[test]
- fn non_finite_sizes_spacing_and_indents_are_ignored() {
- let document = format!(
- r#"<w:document {W}><w:body>
- <w:p><w:pPr><w:spacing w:before="NaN" w:after="inf"/><w:ind w:left="-inf" w:right="NaN" w:firstLine="-inf"/></w:pPr>
- <w:r><w:rPr><w:sz w:val="NaN"/></w:rPr><w:t>a</w:t></w:r><w:r><w:rPr><w:sz w:val="inf"/></w:rPr><w:t>b</w:t></w:r></w:p>
- <w:p><w:pPr><w:ind w:hanging="inf"/></w:pPr><w:r><w:t>c</w:t></w:r></w:p>
- </w:body></w:document>"#
- );
- let st = import(&docx(&document, "", "")).unwrap().story;
- let fin = |v: Option<f64>| v.is_none_or(f64::is_finite);
- for p in &st.paras {
- let p = &p.para;
- assert!(fin(p.space_before) && fin(p.space_after), "{p:?}");
- assert!(fin(p.left_indent) && fin(p.right_indent) && fin(p.first_line_indent), "{p:?}");
- }
- for at in [0, 1] {
- assert!(fin(st.format_after(at).over.size), "{:?}", st.format_after(at).over.size);
- }
- }
-
- #[test]
- fn out_of_range_sizes_are_dropped() {
- let document = format!(
- r#"<w:document {W}><w:body>
- <w:p><w:r><w:rPr><w:sz w:val="0"/></w:rPr><w:t>a</w:t></w:r><w:r><w:rPr><w:sz w:val="99999999"/></w:rPr><w:t>b</w:t></w:r></w:p>
- </w:body></w:document>"#
- );
- let st = import(&docx(&document, "", "")).unwrap().story;
- for at in [0, 1] {
- assert_eq!(st.format_after(at).over.size, None, "run {at}");
- }
- }
-
- #[test]
- fn tracked_changes_import_as_accepted_including_moves() {
- // Regression (#256): text in a tracked move destination (`w:moveTo`) vanished on import.
- let document = format!(
- r#"<w:document {W}><w:body>
- <w:p><w:r><w:t xml:space="preserve">Kept text. </w:t></w:r>
- <w:moveTo w:id="1" w:author="A"><w:r><w:t xml:space="preserve">MOVED HERE.</w:t></w:r>
- <w:del w:id="5" w:author="A"><w:r><w:delText>MOVED THEN DELETED</w:delText></w:r></w:del></w:moveTo>
- <w:r><w:t xml:space="preserve"> Plain </w:t></w:r>
- <w:ins w:id="2" w:author="A"><w:r><w:t>INSERTED</w:t></w:r></w:ins>
- <w:del w:id="3" w:author="A"><w:r><w:delText>DELETED</w:delText></w:r></w:del></w:p>
- <w:p><w:moveFrom w:id="4" w:author="A"><w:r><w:t>MOVED HERE.</w:t></w:r></w:moveFrom><w:r><w:t>End.</w:t></w:r></w:p>
- </w:body></w:document>"#
- );
- let i = import(&docx(&document, "", "")).unwrap();
- i.story.check().unwrap();
- assert_eq!(i.story.text, "Kept text. MOVED HERE. Plain INSERTED\nEnd.");
- }
-
- /// A page break ends its paragraph: the text after it is a paragraph of its own (same style).
- #[test]
- fn page_break_ends_its_paragraph() {
- let styles = format!(r#"<w:styles {W}><w:style w:type="paragraph" w:styleId="H"><w:name w:val="Chapter"/></w:style></w:styles>"#);
- let document = format!(
- r#"<w:document {W}><w:body>
- <w:p><w:r><w:t>End of one</w:t></w:r><w:r><w:br w:type="page"/></w:r></w:p>
- <w:p><w:pPr><w:pStyle w:val="H"/></w:pPr><w:r><w:br w:type="page"/><w:t>Two</w:t><w:br w:type="column"/></w:r></w:p>
- </w:body></w:document>"#
- );
- let st = import(&docx(&document, &styles, "")).unwrap().story;
- st.check().unwrap();
- let (pb, cb) = (designcraft_doc::PAGE_BREAK, designcraft_doc::COLUMN_BREAK);
- assert_eq!(st.text, format!("End of one{pb}\n{pb}\nTwo{cb}\n"));
- let styles: Vec<&str> = st.paras.iter().map(|p| p.style.as_str()).collect();
- assert_eq!(styles, [BASIC_PARAGRAPH, "Chapter", "Chapter", "Chapter"]);
- }
-
- /// A paragraph in a Word list: `w:numPr` with `numId` and, unless `None`, `ilvl`.
- fn list_p(num_id: &str, ilvl: Option<&str>, text: &str) -> String {
- let ilvl = ilvl.map(|l| format!(r#"<w:ilvl w:val="{l}"/>"#)).unwrap_or_default();
- format!(r#"<w:p><w:pPr><w:numPr>{ilvl}<w:numId w:val="{num_id}"/></w:numPr></w:pPr><w:r><w:t>{text}</w:t></w:r></w:p>"#)
- }
-
- fn plain_p(text: &str) -> String {
- format!(r#"<w:p><w:r><w:t>{text}</w:t></w:r></w:p>"#)
- }
-
- fn lists_docx(numbering: &str, styles: &str, body: &[String]) -> Imported {
- let document = format!(r#"<w:document {W}><w:body>{}</w:body></w:document>"#, body.concat());
- let i = import(&docx_parts(&[("word/document.xml", &document), ("word/styles.xml", styles), ("word/numbering.xml", numbering)])).unwrap();
- i.story.check().unwrap();
- i
- }
-
- /// The label composition gives paragraph `i`: numbered paragraphs count per level on one
- /// counter that a paragraph outside a list restarts; bullets and empty paragraphs leave it.
- fn label(st: &Story, i: usize) -> String {
- let mut counter = designcraft_doc::ListCounter::default();
- let mut label = String::new();
- for (f, r) in st.paras.iter().zip(st.para_ranges()).take(i + 1) {
- let mut p = designcraft_doc::ParaProps::default();
- p.apply(&f.para);
- label = match p.list_type {
- _ if r.is_empty() => String::new(),
- ListType::Numbers => {
- counter.advance(&p);
- p.number_label_in(&counter)
- }
- ListType::Bullets => p.bullet_label(),
- ListType::None => {
- counter = designcraft_doc::ListCounter::default();
- String::new()
- }
- };
- }
- label
- }
-
- /// Regression (#626): pandoc's Markdown list example lost its bullets and numbers.
- #[test]
- fn bullets_and_numbers_from_numbering_xml() {
- let numbering = format!(
- r#"<w:numbering {W}>
- <w:abstractNum w:abstractNumId="990"><w:lvl w:ilvl="0"><w:start w:val="1"/><w:numFmt w:val="bullet"/><w:lvlText w:val="•"/>
- <w:pPr><w:ind w:left="480" w:hanging="480"/></w:pPr></w:lvl></w:abstractNum>
- <w:abstractNum w:abstractNumId="991"><w:lvl w:ilvl="0"><w:start w:val="1"/><w:numFmt w:val="decimal"/><w:lvlText w:val="%1."/>
- <w:pPr><w:ind w:left="480" w:hanging="480"/></w:pPr></w:lvl></w:abstractNum>
- <w:num w:numId="1000"><w:abstractNumId w:val="990"/></w:num>
- <w:num w:numId="1001"><w:abstractNumId w:val="991"/><w:lvlOverride w:ilvl="0"><w:startOverride w:val="1"/></w:lvlOverride></w:num>
- </w:numbering>"#
- );
- let body = [
- plain_p("Intro paragraph."),
- list_p("1000", Some("0"), "first item"),
- list_p("1000", Some("0"), "second item"),
- list_p("1001", Some("0"), "step one"),
- list_p("1001", Some("0"), "step two"),
- ];
- let st = lists_docx(&numbering, "", &body).story;
- let types: Vec<Option<ListType>> = st.paras.iter().map(|p| p.para.list_type).collect();
- assert_eq!(types, [None, Some(ListType::Bullets), Some(ListType::Bullets), Some(ListType::Numbers), Some(ListType::Numbers)]);
- assert_eq!(label(&st, 1), "•\t");
- assert_eq!(st.paras[3].para.number_style, Some(designcraft_doc::NumberStyle::Arabic));
- assert_eq!((label(&st, 3), label(&st, 4)), ("1.\t".to_string(), "2.\t".to_string()));
- // The model's own counter already starts at 1 and carries on: no Start At needed.
- assert_eq!((st.paras[3].para.start_at, st.paras[4].para.start_at), (None, None));
- assert_eq!((st.paras[1].para.left_indent, st.paras[1].para.first_line_indent), (Some(24.0), Some(-24.0)));
- }
-
- /// Level 1 inside level 0, parent numbers in a label, numbering that carries on past a plain
- /// paragraph, and a `num` with a start override restarting.
- #[test]
- fn nested_levels_and_restarts() {
- let numbering = format!(
- r#"<w:numbering {W}>
- <w:abstractNum w:abstractNumId="1">
- <w:lvl w:ilvl="0"><w:start w:val="1"/><w:numFmt w:val="decimal"/><w:lvlText w:val="%1."/></w:lvl>
- <w:lvl w:ilvl="1"><w:start w:val="1"/><w:numFmt w:val="lowerLetter"/><w:lvlText w:val="%2)"/><w:suff w:val="space"/>
- <w:pPr><w:ind w:left="1440" w:hanging="360"/></w:pPr></w:lvl>
- <w:lvl w:ilvl="2"><w:start w:val="1"/><w:numFmt w:val="upperRoman"/><w:lvlText w:val="%1.%2.%3"/></w:lvl>
- </w:abstractNum>
- <w:num w:numId="1"><w:abstractNumId w:val="1"/></w:num>
- <w:num w:numId="2"><w:abstractNumId w:val="1"/><w:lvlOverride w:ilvl="0"><w:startOverride w:val="1"/></w:lvlOverride></w:num>
- <w:num w:numId="3"><w:abstractNumId w:val="1"/></w:num>
- </w:numbering>"#
- );
- let body = [
- list_p("1", None, "A"),
- list_p("1", Some("1"), "B"),
- list_p("1", Some("1"), "C"),
- list_p("1", Some("2"), "D"),
- list_p("1", Some("0"), "E"),
- plain_p("Between"),
- list_p("1", Some("0"), "F"),
- list_p("2", Some("0"), "G"),
- list_p("3", Some("0"), "H"),
- ];
- let st = lists_docx(&numbering, "", &body).story;
- let start: Vec<Option<Option<u32>>> = st.paras.iter().map(|p| p.para.start_at).collect();
- // Word's numbers: 1, a, b, 1.b.I, 2, –, 3, 1 (own counter), 4 (shares numId 1's). The
- // model numbers each level on its own, so only the paragraphs after the plain one need
- // Start At.
- assert_eq!(start, [None, None, None, None, None, None, Some(Some(3)), Some(Some(1)), Some(Some(4))]);
- let levels: Vec<Option<u32>> = st.paras.iter().map(|p| p.para.list_level).collect();
- assert_eq!(levels, [Some(1), Some(2), Some(2), Some(3), Some(1), None, Some(1), Some(1), Some(1)]);
- assert_eq!(label(&st, 1), "a) ");
- // Parent numbers are the model's level references.
- assert_eq!(st.paras[3].para.number_expression.as_deref(), Some("^1.^2.^#^t"));
- assert_eq!(label(&st, 3), "1.b.I\t");
- let labels: Vec<String> = (0..st.paras.len()).map(|i| label(&st, i)).collect();
- assert_eq!(labels, ["1.\t", "a) ", "b) ", "1.b.I\t", "2.\t", "", "3.\t", "1.\t", "4.\t"]);
- assert_eq!(st.paras[1].para.left_indent, Some(72.0));
- assert_eq!(st.paras[1].para.first_line_indent, Some(-18.0));
- }
-
- /// Parent numbers the model's levels can't give are written as text: a list that starts at
- /// level 1 (level 0 never numbered), and a legal-style label (decimal parents).
- #[test]
- fn parent_numbers_the_model_lacks_are_text() {
- let numbering = format!(
- r#"<w:numbering {W}>
- <w:abstractNum w:abstractNumId="1">
- <w:lvl w:ilvl="0"><w:start w:val="1"/><w:numFmt w:val="upperRoman"/><w:lvlText w:val="%1."/></w:lvl>
- <w:lvl w:ilvl="1"><w:start w:val="1"/><w:numFmt w:val="decimal"/><w:lvlText w:val="%1.%2"/></w:lvl>
- <w:lvl w:ilvl="2"><w:start w:val="1"/><w:isLgl/><w:numFmt w:val="decimal"/><w:lvlText w:val="%1.%2.%3"/></w:lvl>
- </w:abstractNum>
- <w:num w:numId="1"><w:abstractNumId w:val="1"/></w:num>
- </w:numbering>"#
- );
- let body = [list_p("1", Some("1"), "A"), list_p("1", Some("0"), "B"), list_p("1", Some("1"), "C"), list_p("1", Some("2"), "D")];
- let st = lists_docx(&numbering, "", &body).story;
- let labels: Vec<String> = (0..st.paras.len()).map(|i| label(&st, i)).collect();
- assert_eq!(labels, ["I.1\t", "I.\t", "I.1\t", "1.1.1\t"]);
- assert_eq!(st.paras[0].para.number_expression.as_deref(), Some("I.^#^t"));
- assert_eq!(st.paras[2].para.number_expression.as_deref(), Some("^1.^#^t"));
- }
-
- /// A paragraph style's `w:numPr` (inherited through `w:basedOn`) makes its paragraphs a list;
- /// numId 0 on a paragraph takes it out of the list.
- #[test]
- fn style_lists_and_num_id_zero() {
- let numbering = format!(
- r#"<w:numbering {W}>
- <w:abstractNum w:abstractNumId="7">
- <w:lvl w:ilvl="0"><w:numFmt w:val="bullet"/><w:lvlText w:val="&#xF0B7;"/><w:rPr><w:rFonts w:ascii="Symbol" w:hAnsi="Symbol"/></w:rPr></w:lvl>
- <w:lvl w:ilvl="1"><w:numFmt w:val="bullet"/><w:lvlText w:val="o"/><w:rPr><w:rFonts w:ascii="Courier New"/></w:rPr></w:lvl>
- </w:abstractNum>
- <w:num w:numId="5"><w:abstractNumId w:val="7"/></w:num>
- </w:numbering>"#
- );
- let styles = format!(
- r#"<w:styles {W}>
- <w:style w:type="paragraph" w:styleId="ListBullet"><w:name w:val="List Bullet"/><w:pPr><w:numPr><w:numId w:val="5"/></w:numPr></w:pPr></w:style>
- <w:style w:type="paragraph" w:styleId="ListBullet2"><w:name w:val="List Bullet 2"/><w:basedOn w:val="ListBullet"/>
- <w:pPr><w:numPr><w:ilvl w:val="1"/></w:numPr></w:pPr></w:style>
- </w:styles>"#
- );
- let styled =
- |id: &str, extra: &str, text: &str| format!(r#"<w:p><w:pPr><w:pStyle w:val="{id}"/>{extra}</w:pPr><w:r><w:t>{text}</w:t></w:r></w:p>"#);
- let body = [
- styled("ListBullet", "", "one"),
- styled("ListBullet2", "", "two"),
- styled("ListBullet", r#"<w:numPr><w:ilvl w:val="0"/><w:numId w:val="0"/></w:numPr>"#, "not a list"),
- ];
- let st = lists_docx(&numbering, &styles, &body).story;
- assert_eq!(label(&st, 0), "•\t");
- assert_eq!(label(&st, 1), "◦\t");
- assert_eq!(st.paras[2].para.list_type, None);
- assert_eq!(st.paras[2].style, "List Bullet");
- }
-
- /// Hostile list definitions: missing abstractNums and levels, huge or negative levels and
- /// starts, a long label, a `w:basedOn` cycle. No panic; what can't be a list is plain.
- #[test]
- fn hostile_numbering_falls_back_to_plain_paragraphs() {
- let long = "x".repeat(10_000);
- let numbering = format!(
- r#"<w:numbering {W}>
- <w:abstractNum w:abstractNumId="1">
- <w:lvl w:ilvl="0"><w:start w:val="99999999999999"/><w:numFmt w:val="decimal"/><w:lvlText w:val="%1{long}%9%"/></w:lvl>
- <w:lvl w:ilvl="99999999999999"><w:numFmt w:val="decimal"/></w:lvl>
- <w:lvl w:ilvl="-1"><w:numFmt w:val="decimal"/></w:lvl>
- <w:lvl w:ilvl="3"><w:start w:val="-5"/><w:numFmt w:val="ordinalText"/><w:lvlText w:val="%4^"/><w:lvlRestart w:val="99"/></w:lvl>
- </w:abstractNum>
- <w:num w:numId="1"><w:abstractNumId w:val="1"/></w:num>
- <w:num w:numId="2"><w:abstractNumId w:val="404"/></w:num>
- <w:num w:numId="3"/>
- <w:num><w:abstractNumId w:val="1"/></w:num>
- </w:numbering>"#
- );
- let styles = format!(
- r#"<w:styles {W}>
- <w:style w:type="paragraph" w:styleId="A"><w:name w:val="A"/><w:basedOn w:val="B"/></w:style>
- <w:style w:type="paragraph" w:styleId="B"><w:name w:val="B"/><w:basedOn w:val="A"/></w:style>
- </w:styles>"#
- );
- let body = [
- list_p("2", None, "missing abstractNum"),
- list_p("3", None, "num without abstractNum"),
- list_p("404", None, "unknown numId"),
- list_p("1", Some("99999999999999"), "huge level"),
- list_p("1", Some("9"), "level 9"),
- list_p("1", Some("-1"), "negative level"),
- list_p("1", Some("1"), "undefined level"),
- r#"<w:p><w:pPr><w:pStyle w:val="A"/><w:numPr><w:ilvl w:val="0"/></w:numPr></w:pPr><w:r><w:t>cycle</w:t></w:r></w:p>"#.to_string(),
- list_p("1", None, "huge start"),
- list_p("1", Some("3"), "negative start"),
- ];
- let st = lists_docx(&numbering, &styles, &body).story;
- assert!(st.paras[..8].iter().all(|p| p.para.list_type.is_none()), "{:?}", st.paras);
- assert_eq!(st.paras[8].para.start_at, Some(Some(u32::MAX)));
- let expr = st.paras[8].para.number_expression.clone().unwrap_or_default();
- assert!(expr.starts_with("^#x") && expr.chars().count() < 80, "{expr}");
- // A start below 0 counts from 0, which the model shows as 1; `^` in a label is literal.
- assert_eq!(label(&st, 9), "1^\t");
- // Unreadable list definitions leave plain paragraphs and a warning, not a failed import.
- let document = format!(r#"<w:document {W}><w:body>{}</w:body></w:document>"#, list_p("1", None, "x"));
- let i = import(&docx_parts(&[("word/document.xml", &document), ("word/numbering.xml", "<w:numbering></w:num>")])).unwrap();
- assert_eq!(i.story.paras[0].para.list_type, None);
- assert_eq!(i.warnings.len(), 1);
- }
-
- #[test]
- fn an_element_with_many_attributes_parses_in_linear_time() {
- // RUSTSEC-2026-0194: before quick-xml 0.41 the duplicate-attribute check compared each name with every
- // earlier one on the element, so a crafted .docx/.xlsx with one huge tag hung the import (O(N²)).
- let attrs: String = (0..100_000).map(|i| format!(" w:a{i}=\"{i}\"")).collect();
- let xml = format!("<w:document><w:body><w:p{attrs}/></w:body></w:document>");
- let started = std::time::Instant::now();
- let doc = parse(&xml).unwrap();
- assert!(started.elapsed() < std::time::Duration::from_secs(5), "parse took {:?}", started.elapsed());
- let p = doc.child("body").and_then(|b| b.child("p")).unwrap();
- assert_eq!(p.attr("a0"), Some("0"));
- assert_eq!(p.attr("a99999"), Some("99999"));
- }
-
- #[test]
- fn table_cells_read_text_like_body_paragraphs() {
- // Regression (#721): cells took every text node, so deleted text, move sources and field
- // instructions showed up in the table.
- let para = r#"<w:p><w:r><w:t xml:space="preserve">kept </w:t></w:r>
- <w:del w:id="1" w:author="A"><w:r><w:delText>GONE</w:delText></w:r></w:del>
- <w:moveFrom w:id="2" w:author="A"><w:r><w:t>MOVED AWAY</w:t></w:r></w:moveFrom>
- <w:r><w:fldChar w:fldCharType="begin"/></w:r><w:r><w:instrText xml:space="preserve"> PAGE </w:instrText></w:r>
- <w:r><w:fldChar w:fldCharType="separate"/></w:r><w:r><w:t>7</w:t></w:r><w:r><w:fldChar w:fldCharType="end"/></w:r></w:p>"#;
- let document = format!(r#"<w:document {W}><w:body>{para}<w:tbl><w:tr><w:tc>{para}<w:p/></w:tc></w:tr></w:tbl></w:body></w:document>"#);
- let i = import(&docx(&document, "", "")).unwrap();
- assert!(i.story.text.starts_with("kept 7"), "{:?}", i.story.text);
- let cell = &i.story.tables.values().next().unwrap().cell(0, 0).unwrap().text;
- assert_eq!(cell.text, "kept 7\n");
- }
-
- #[test]
- fn normal_is_its_own_style_over_the_document_defaults() {
- // Regression (#722): text formatted only by Normal and the document defaults lost it.
- let styles = format!(
- r#"<w:styles {W}><w:docDefaults><w:rPrDefault><w:rPr><w:sz w:val="22"/></w:rPr></w:rPrDefault>
- <w:pPrDefault><w:pPr><w:spacing w:after="160"/></w:pPr></w:pPrDefault></w:docDefaults>
- <w:style w:type="paragraph" w:default="1" w:styleId="Normal"><w:name w:val="Normal"/><w:rPr><w:rFonts w:ascii="Georgia"/><w:sz w:val="26"/></w:rPr></w:style>
- <w:style w:type="paragraph" w:styleId="Quote"><w:name w:val="Quote"/><w:basedOn w:val="Normal"/><w:rPr><w:i/></w:rPr></w:style>
- </w:styles>"#
- );
- let document = format!(
- r#"<w:document {W}><w:body><w:p><w:r><w:t>Plain</w:t></w:r></w:p>
- <w:p><w:pPr><w:pStyle w:val="Quote"/></w:pPr><w:r><w:t>Quoted</w:t></w:r></w:p></w:body></w:document>"#
- );
- let i = import(&docx(&document, &styles, "")).unwrap();
- assert_eq!(i.story.paras[0].style, "Normal");
- let normal = i.para_styles.iter().find(|s| s.name == "Normal").unwrap();
- assert_eq!(normal.chars.size, Some(13.0), "Normal's size wins over the default");
- assert_eq!(normal.chars.font_family.as_deref(), Some("Georgia"));
- assert_eq!(normal.para.space_after, Some(8.0), "from the document defaults");
- let quote = i.para_styles.iter().find(|s| s.name == "Quote").unwrap();
- assert_eq!(quote.based_on.as_deref(), Some("Normal"));
- assert_eq!(quote.chars.size, None, "inherited from Normal, not copied");
- }
-
- /// `ST_OnOff` is a boolean plus the words `on` and `off`: an explicit `off` is off.
- #[test]
- fn off_valued_toggles_stay_off() {
- let document = format!(
- r#"<w:document {W}><w:body><w:p>
- <w:r><w:rPr><w:b w:val="off"/><w:i w:val="0"/><w:strike w:val="off"/><w:u w:val="off"/><w:caps w:val="off"/></w:rPr><w:t>plain</w:t></w:r>
- <w:r><w:rPr><w:b w:val="on"/></w:rPr><w:t>bold</w:t></w:r>
- </w:p></w:body></w:document>"#
- );
- let st = import(&docx(&document, "", "")).unwrap().story;
- st.check().unwrap();
- let plain = st.format_after(st.text.find("plain").unwrap()).clone().over;
- assert_eq!(plain.font_style.as_deref(), Some("Regular"), "an explicit `off` is not bold");
- assert_eq!(plain.strikethrough, Some(false));
- assert_eq!(plain.underline, Some(false));
- assert_eq!(plain.capitalization, None, "no all-caps");
- let on = st.format_after(st.text.find("bold").unwrap()).clone().over;
- assert_eq!(on.font_style.as_deref(), Some("Bold"), "`on` is still on");
- }
-}
+mod tests;
diff --git a/crates/textimport/src/docx/tests.rs b/crates/textimport/src/docx/tests.rs
new file mode 100644
index 000000000..c70ca851f
--- /dev/null
+++ b/crates/textimport/src/docx/tests.rs
@@ -0,0 +1,522 @@
+use super::*;
+use std::io::Write;
+
+#[test]
+fn cdata_text() {
+ let el = parse("<a><t><![CDATA[x < y]]></t></a>").unwrap();
+ assert_eq!(el.child("t").unwrap().text(), "x < y");
+}
+
+/// Issue #712: nesting past the budget is an error from the parser, not a stack overflow later.
+#[test]
+fn nesting_past_the_budget_is_refused() {
+ let nested = |n: usize| format!("{}{}", "<w:p>".repeat(n), "</w:p>".repeat(n));
+ let ok = parse(&nested(MAX_DEPTH)).expect("the budget itself parses");
+ assert_eq!(ok.name, "p");
+ let err = parse(&nested(MAX_DEPTH + 1)).expect_err("one level more is refused");
+ assert!(err.to_string().contains("nested deeper"), "{err}");
+ assert!(parse(&nested(100_000)).is_err());
+}
+
+#[test]
+fn table_adds_no_empty_paragraph() {
+ let document = format!(
+ r#"<w:document {W}><w:body>
+ <w:p><w:r><w:t>Before</w:t></w:r></w:p>
+ <w:tbl><w:tr><w:tc><w:p><w:r><w:t>A</w:t></w:r></w:p></w:tc></w:tr></w:tbl>
+ <w:p><w:r><w:t>After</w:t></w:r></w:p>
+ </w:body></w:document>"#
+ );
+ let st = import(&docx(&document, "", "")).unwrap().story;
+ st.check().unwrap();
+ let paras: Vec<&str> = st.para_ranges().into_iter().map(|r| &st.text[r]).collect();
+ assert_eq!(paras.len(), 3, "{paras:?}");
+ assert_eq!(paras[0], "Before");
+ assert_eq!(paras[2], "After");
+}
+
+pub(crate) fn docx(document: &str, styles: &str, footnotes: &str) -> Vec<u8> {
+ docx_parts(&[("word/document.xml", document), ("word/styles.xml", styles), ("word/footnotes.xml", footnotes)])
+}
+
+/// A zip of `(part name, XML)`; empty parts are left out.
+fn docx_parts(parts: &[(&str, &str)]) -> Vec<u8> {
+ let mut w = zip::ZipWriter::new(std::io::Cursor::new(Vec::new()));
+ let o = zip::write::SimpleFileOptions::default();
+ for &(n, c) in parts {
+ if c.is_empty() {
+ continue;
+ }
+ w.start_file(n, o).unwrap();
+ w.write_all(c.as_bytes()).unwrap();
+ }
+ w.finish().unwrap().into_inner()
+}
+
+const W: &str = r#"xmlns:w="http://schemas.openxmlformats.org/wordprocessingml/2006/main""#;
+
+#[test]
+fn oversized_part_is_an_error_not_a_huge_read() {
+ // A highly compressible part: 64 KiB of spaces inflates past a 4 KiB cap.
+ let big = docx(&" ".repeat(64 * 1024), "", "");
+ let mut zip = zip::ZipArchive::new(std::io::Cursor::new(big.as_slice())).unwrap();
+ assert!(matches!(part_capped(&mut zip, "word/document.xml", 4096), Err(ImportError::Corrupt(_))));
+ // At or under the cap reads fine; a missing part is `None`.
+ assert_eq!(part_capped(&mut zip, "word/document.xml", 64 * 1024).unwrap().map(|s| s.len()), Some(64 * 1024));
+ assert_eq!(part_capped(&mut zip, "word/missing.xml", 4096).unwrap(), None);
+}
+
+/// A DOCX can hold any number where a measure belongs: `1e300` twips became a 5e298 pt
+/// indent, and `w:sz` of `1e300` a 5e299 pt type size. Measures are clamped to the widest
+/// page and a size the engine cannot mean is dropped (#1593).
+#[test]
+fn a_measure_or_size_a_file_cannot_mean_is_bounded() {
+ use designcraft_doc::attrs::MAX_MEASURE;
+ let doc = format!(
+ r#"<w:document {W}><w:body><w:p><w:pPr>
+ <w:spacing w:before="1e300" w:after="-1e300"/><w:ind w:left="1e300" w:firstLine="-1e300"/>
+ </w:pPr><w:r><w:rPr><w:sz w:val="1e300"/></w:rPr><w:t>big</w:t></w:r></w:p></w:body></w:document>"#
+ );
+ let i = import(&docx(&doc, "", "")).unwrap();
+ let p = &i.story.paras[0].para;
+ for (what, v) in
+ [("space before", p.space_before), ("space after", p.space_after), ("left indent", p.left_indent), ("first line", p.first_line_indent)]
+ {
+ let v = v.expect("the value is kept, bounded");
+ assert!(v.is_finite() && v.abs() <= MAX_MEASURE, "{what} is within the widest page: {v}");
+ }
+ let size = i.story.char_format_at(i.story.text.find("big").unwrap() + 1).over.size;
+ assert_eq!(size, None, "a size the engine cannot mean is dropped, so the style's size stands");
+}
+
+#[test]
+fn imports_styles_runs_footnotes_and_tables() {
+ let styles = format!(
+ r#"<w:styles {W}>
+ <w:style w:type="paragraph" 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:pPr><w:spacing w:before="240" w:after="120"/></w:pPr><w:rPr><w:b/><w:sz w:val="32"/></w:rPr></w:style>
+ <w:style w:type="paragraph" w:styleId="Unused"><w:name w:val="Unused"/></w:style>
+ <w:style w:type="character" w:styleId="Emph"><w:name w:val="Emphasis"/><w:rPr><w:i/></w:rPr></w:style>
+ </w:styles>"#
+ );
+ let document = format!(
+ r#"<w:document {W}><w:body>
+ <w:p><w:pPr><w:pStyle w:val="Heading1"/></w:pPr><w:r><w:t>Title &amp; more</w:t></w:r></w:p>
+ <w:p><w:r><w:t xml:space="preserve">Plain </w:t></w:r><w:r><w:rPr><w:b/></w:rPr><w:t>bold</w:t></w:r>
+ <w:r><w:rPr><w:rStyle w:val="Emph"/></w:rPr><w:t> styled</w:t></w:r><w:r><w:tab/><w:t>x</w:t></w:r>
+ <w:r><w:footnoteReference w:id="1"/></w:r></w:p>
+ <w:tbl><w:tr><w:tc><w:p><w:r><w:t>A</w:t></w:r></w:p></w:tc><w:tc><w:p><w:r><w:t>B</w:t></w:r></w:p></w:tc></w:tr></w:tbl>
+ <w:p><w:r><w:t>After</w:t></w:r></w:p>
+ </w:body></w:document>"#
+ );
+ let notes = format!(
+ r#"<w:footnotes {W}><w:footnote w:id="0"><w:p/></w:footnote>
+ <w:footnote w:id="1"><w:p><w:r><w:t>The note.</w:t></w:r></w:p></w:footnote></w:footnotes>"#
+ );
+ let i = import(&docx(&document, &styles, &notes)).unwrap();
+ let st = &i.story;
+ st.check().unwrap();
+ assert!(st.text.starts_with("Title & more\nPlain bold styled\tx"), "{:?}", st.text);
+ assert!(st.text.ends_with("After"));
+ assert_eq!(st.paras[0].style, "heading 1");
+ assert_eq!(st.paras[1].style, "Normal");
+ let at = st.text.find("bold").unwrap();
+ assert_eq!(st.format_after(at).over.font_style.as_deref(), Some("Bold"));
+ assert_eq!(st.format_after(st.text.find("styled").unwrap()).style, "Emphasis");
+ assert_eq!(st.notes.len(), 1);
+ assert_eq!(st.notes[0].text.text, "The note.");
+ assert_eq!(st.tables.len(), 1);
+ let names: Vec<&str> = i.para_styles.iter().map(|s| s.name.as_str()).collect();
+ assert_eq!(names, ["Normal", "heading 1"], "unused styles are skipped");
+ assert_eq!(i.para_styles[1].based_on.as_deref(), Some("Normal"));
+ assert_eq!(i.para_styles[1].chars.size, Some(16.0));
+ assert_eq!(i.para_styles[1].para.space_before, Some(12.0));
+ assert_eq!(i.char_styles[0].chars.font_style.as_deref(), Some("Italic"));
+}
+
+/// A content control inside a paragraph (`w:sdt`) keeps its text, also around a hyperlink.
+#[test]
+fn inline_content_control_text_is_kept() {
+ let document = format!(
+ r#"<w:document {W}><w:body>
+ <w:p><w:r><w:t xml:space="preserve">Date: </w:t></w:r><w:sdt><w:sdtPr><w:alias w:val="d"/></w:sdtPr><w:sdtContent><w:r><w:t>1 May 2026</w:t></w:r></w:sdtContent></w:sdt><w:r><w:t>.</w:t></w:r></w:p>
+ <w:p><w:sdt><w:sdtContent><w:hyperlink><w:r><w:t>Link</w:t></w:r></w:hyperlink></w:sdtContent></w:sdt></w:p>
+ </w:body></w:document>"#
+ );
+ let st = import(&docx(&document, "", "")).unwrap().story;
+ st.check().unwrap();
+ assert_eq!(st.text, "Date: 1 May 2026.\nLink");
+}
+
+/// `str::parse::<f64>` accepts "NaN"/"inf"; sizes, spacing and indents must ignore them.
+#[test]
+fn non_finite_sizes_spacing_and_indents_are_ignored() {
+ let document = format!(
+ r#"<w:document {W}><w:body>
+ <w:p><w:pPr><w:spacing w:before="NaN" w:after="inf"/><w:ind w:left="-inf" w:right="NaN" w:firstLine="-inf"/></w:pPr>
+ <w:r><w:rPr><w:sz w:val="NaN"/></w:rPr><w:t>a</w:t></w:r><w:r><w:rPr><w:sz w:val="inf"/></w:rPr><w:t>b</w:t></w:r></w:p>
+ <w:p><w:pPr><w:ind w:hanging="inf"/></w:pPr><w:r><w:t>c</w:t></w:r></w:p>
+ </w:body></w:document>"#
+ );
+ let st = import(&docx(&document, "", "")).unwrap().story;
+ let fin = |v: Option<f64>| v.is_none_or(f64::is_finite);
+ for p in &st.paras {
+ let p = &p.para;
+ assert!(fin(p.space_before) && fin(p.space_after), "{p:?}");
+ assert!(fin(p.left_indent) && fin(p.right_indent) && fin(p.first_line_indent), "{p:?}");
+ }
+ for at in [0, 1] {
+ assert!(fin(st.format_after(at).over.size), "{:?}", st.format_after(at).over.size);
+ }
+}
+
+#[test]
+fn out_of_range_sizes_are_dropped() {
+ let document = format!(
+ r#"<w:document {W}><w:body>
+ <w:p><w:r><w:rPr><w:sz w:val="0"/></w:rPr><w:t>a</w:t></w:r><w:r><w:rPr><w:sz w:val="99999999"/></w:rPr><w:t>b</w:t></w:r></w:p>
+ </w:body></w:document>"#
+ );
+ let st = import(&docx(&document, "", "")).unwrap().story;
+ for at in [0, 1] {
+ assert_eq!(st.format_after(at).over.size, None, "run {at}");
+ }
+}
+
+#[test]
+fn tracked_changes_import_as_accepted_including_moves() {
+ // Regression (#256): text in a tracked move destination (`w:moveTo`) vanished on import.
+ let document = format!(
+ r#"<w:document {W}><w:body>
+ <w:p><w:r><w:t xml:space="preserve">Kept text. </w:t></w:r>
+ <w:moveTo w:id="1" w:author="A"><w:r><w:t xml:space="preserve">MOVED HERE.</w:t></w:r>
+ <w:del w:id="5" w:author="A"><w:r><w:delText>MOVED THEN DELETED</w:delText></w:r></w:del></w:moveTo>
+ <w:r><w:t xml:space="preserve"> Plain </w:t></w:r>
+ <w:ins w:id="2" w:author="A"><w:r><w:t>INSERTED</w:t></w:r></w:ins>
+ <w:del w:id="3" w:author="A"><w:r><w:delText>DELETED</w:delText></w:r></w:del></w:p>
+ <w:p><w:moveFrom w:id="4" w:author="A"><w:r><w:t>MOVED HERE.</w:t></w:r></w:moveFrom><w:r><w:t>End.</w:t></w:r></w:p>
+ </w:body></w:document>"#
+ );
+ let i = import(&docx(&document, "", "")).unwrap();
+ i.story.check().unwrap();
+ assert_eq!(i.story.text, "Kept text. MOVED HERE. Plain INSERTED\nEnd.");
+}
+
+/// A page break ends its paragraph: the text after it is a paragraph of its own (same style).
+#[test]
+fn page_break_ends_its_paragraph() {
+ let styles = format!(r#"<w:styles {W}><w:style w:type="paragraph" w:styleId="H"><w:name w:val="Chapter"/></w:style></w:styles>"#);
+ let document = format!(
+ r#"<w:document {W}><w:body>
+ <w:p><w:r><w:t>End of one</w:t></w:r><w:r><w:br w:type="page"/></w:r></w:p>
+ <w:p><w:pPr><w:pStyle w:val="H"/></w:pPr><w:r><w:br w:type="page"/><w:t>Two</w:t><w:br w:type="column"/></w:r></w:p>
+ </w:body></w:document>"#
+ );
+ let st = import(&docx(&document, &styles, "")).unwrap().story;
+ st.check().unwrap();
+ let (pb, cb) = (designcraft_doc::PAGE_BREAK, designcraft_doc::COLUMN_BREAK);
+ assert_eq!(st.text, format!("End of one{pb}\n{pb}\nTwo{cb}\n"));
+ let styles: Vec<&str> = st.paras.iter().map(|p| p.style.as_str()).collect();
+ assert_eq!(styles, [BASIC_PARAGRAPH, "Chapter", "Chapter", "Chapter"]);
+}
+
+/// A paragraph in a Word list: `w:numPr` with `numId` and, unless `None`, `ilvl`.
+fn list_p(num_id: &str, ilvl: Option<&str>, text: &str) -> String {
+ let ilvl = ilvl.map(|l| format!(r#"<w:ilvl w:val="{l}"/>"#)).unwrap_or_default();
+ format!(r#"<w:p><w:pPr><w:numPr>{ilvl}<w:numId w:val="{num_id}"/></w:numPr></w:pPr><w:r><w:t>{text}</w:t></w:r></w:p>"#)
+}
+
+fn plain_p(text: &str) -> String {
+ format!(r#"<w:p><w:r><w:t>{text}</w:t></w:r></w:p>"#)
+}
+
+fn lists_docx(numbering: &str, styles: &str, body: &[String]) -> Imported {
+ let document = format!(r#"<w:document {W}><w:body>{}</w:body></w:document>"#, body.concat());
+ let i = import(&docx_parts(&[("word/document.xml", &document), ("word/styles.xml", styles), ("word/numbering.xml", numbering)])).unwrap();
+ i.story.check().unwrap();
+ i
+}
+
+/// The label composition gives paragraph `i`: numbered paragraphs count per level on one
+/// counter that a paragraph outside a list restarts; bullets and empty paragraphs leave it.
+fn label(st: &Story, i: usize) -> String {
+ let mut counter = designcraft_doc::ListCounter::default();
+ let mut label = String::new();
+ for (f, r) in st.paras.iter().zip(st.para_ranges()).take(i + 1) {
+ let mut p = designcraft_doc::ParaProps::default();
+ p.apply(&f.para);
+ label = match p.list_type {
+ _ if r.is_empty() => String::new(),
+ ListType::Numbers => {
+ counter.advance(&p);
+ p.number_label_in(&counter)
+ }
+ ListType::Bullets => p.bullet_label(),
+ ListType::None => {
+ counter = designcraft_doc::ListCounter::default();
+ String::new()
+ }
+ };
+ }
+ label
+}
+
+/// Regression (#626): pandoc's Markdown list example lost its bullets and numbers.
+#[test]
+fn bullets_and_numbers_from_numbering_xml() {
+ let numbering = format!(
+ r#"<w:numbering {W}>
+ <w:abstractNum w:abstractNumId="990"><w:lvl w:ilvl="0"><w:start w:val="1"/><w:numFmt w:val="bullet"/><w:lvlText w:val="•"/>
+ <w:pPr><w:ind w:left="480" w:hanging="480"/></w:pPr></w:lvl></w:abstractNum>
+ <w:abstractNum w:abstractNumId="991"><w:lvl w:ilvl="0"><w:start w:val="1"/><w:numFmt w:val="decimal"/><w:lvlText w:val="%1."/>
+ <w:pPr><w:ind w:left="480" w:hanging="480"/></w:pPr></w:lvl></w:abstractNum>
+ <w:num w:numId="1000"><w:abstractNumId w:val="990"/></w:num>
+ <w:num w:numId="1001"><w:abstractNumId w:val="991"/><w:lvlOverride w:ilvl="0"><w:startOverride w:val="1"/></w:lvlOverride></w:num>
+ </w:numbering>"#
+ );
+ let body = [
+ plain_p("Intro paragraph."),
+ list_p("1000", Some("0"), "first item"),
+ list_p("1000", Some("0"), "second item"),
+ list_p("1001", Some("0"), "step one"),
+ list_p("1001", Some("0"), "step two"),
+ ];
+ let st = lists_docx(&numbering, "", &body).story;
+ let types: Vec<Option<ListType>> = st.paras.iter().map(|p| p.para.list_type).collect();
+ assert_eq!(types, [None, Some(ListType::Bullets), Some(ListType::Bullets), Some(ListType::Numbers), Some(ListType::Numbers)]);
+ assert_eq!(label(&st, 1), "•\t");
+ assert_eq!(st.paras[3].para.number_style, Some(designcraft_doc::NumberStyle::Arabic));
+ assert_eq!((label(&st, 3), label(&st, 4)), ("1.\t".to_string(), "2.\t".to_string()));
+ // The model's own counter already starts at 1 and carries on: no Start At needed.
+ assert_eq!((st.paras[3].para.start_at, st.paras[4].para.start_at), (None, None));
+ assert_eq!((st.paras[1].para.left_indent, st.paras[1].para.first_line_indent), (Some(24.0), Some(-24.0)));
+}
+
+/// Level 1 inside level 0, parent numbers in a label, numbering that carries on past a plain
+/// paragraph, and a `num` with a start override restarting.
+#[test]
+fn nested_levels_and_restarts() {
+ let numbering = format!(
+ r#"<w:numbering {W}>
+ <w:abstractNum w:abstractNumId="1">
+ <w:lvl w:ilvl="0"><w:start w:val="1"/><w:numFmt w:val="decimal"/><w:lvlText w:val="%1."/></w:lvl>
+ <w:lvl w:ilvl="1"><w:start w:val="1"/><w:numFmt w:val="lowerLetter"/><w:lvlText w:val="%2)"/><w:suff w:val="space"/>
+ <w:pPr><w:ind w:left="1440" w:hanging="360"/></w:pPr></w:lvl>
+ <w:lvl w:ilvl="2"><w:start w:val="1"/><w:numFmt w:val="upperRoman"/><w:lvlText w:val="%1.%2.%3"/></w:lvl>
+ </w:abstractNum>
+ <w:num w:numId="1"><w:abstractNumId w:val="1"/></w:num>
+ <w:num w:numId="2"><w:abstractNumId w:val="1"/><w:lvlOverride w:ilvl="0"><w:startOverride w:val="1"/></w:lvlOverride></w:num>
+ <w:num w:numId="3"><w:abstractNumId w:val="1"/></w:num>
+ </w:numbering>"#
+ );
+ let body = [
+ list_p("1", None, "A"),
+ list_p("1", Some("1"), "B"),
+ list_p("1", Some("1"), "C"),
+ list_p("1", Some("2"), "D"),
+ list_p("1", Some("0"), "E"),
+ plain_p("Between"),
+ list_p("1", Some("0"), "F"),
+ list_p("2", Some("0"), "G"),
+ list_p("3", Some("0"), "H"),
+ ];
+ let st = lists_docx(&numbering, "", &body).story;
+ let start: Vec<Option<Option<u32>>> = st.paras.iter().map(|p| p.para.start_at).collect();
+ // Word's numbers: 1, a, b, 1.b.I, 2, –, 3, 1 (own counter), 4 (shares numId 1's). The
+ // model numbers each level on its own, so only the paragraphs after the plain one need
+ // Start At.
+ assert_eq!(start, [None, None, None, None, None, None, Some(Some(3)), Some(Some(1)), Some(Some(4))]);
+ let levels: Vec<Option<u32>> = st.paras.iter().map(|p| p.para.list_level).collect();
+ assert_eq!(levels, [Some(1), Some(2), Some(2), Some(3), Some(1), None, Some(1), Some(1), Some(1)]);
+ assert_eq!(label(&st, 1), "a) ");
+ // Parent numbers are the model's level references.
+ assert_eq!(st.paras[3].para.number_expression.as_deref(), Some("^1.^2.^#^t"));
+ assert_eq!(label(&st, 3), "1.b.I\t");
+ let labels: Vec<String> = (0..st.paras.len()).map(|i| label(&st, i)).collect();
+ assert_eq!(labels, ["1.\t", "a) ", "b) ", "1.b.I\t", "2.\t", "", "3.\t", "1.\t", "4.\t"]);
+ assert_eq!(st.paras[1].para.left_indent, Some(72.0));
+ assert_eq!(st.paras[1].para.first_line_indent, Some(-18.0));
+}
+
+/// Parent numbers the model's levels can't give are written as text: a list that starts at
+/// level 1 (level 0 never numbered), and a legal-style label (decimal parents).
+#[test]
+fn parent_numbers_the_model_lacks_are_text() {
+ let numbering = format!(
+ r#"<w:numbering {W}>
+ <w:abstractNum w:abstractNumId="1">
+ <w:lvl w:ilvl="0"><w:start w:val="1"/><w:numFmt w:val="upperRoman"/><w:lvlText w:val="%1."/></w:lvl>
+ <w:lvl w:ilvl="1"><w:start w:val="1"/><w:numFmt w:val="decimal"/><w:lvlText w:val="%1.%2"/></w:lvl>
+ <w:lvl w:ilvl="2"><w:start w:val="1"/><w:isLgl/><w:numFmt w:val="decimal"/><w:lvlText w:val="%1.%2.%3"/></w:lvl>
+ </w:abstractNum>
+ <w:num w:numId="1"><w:abstractNumId w:val="1"/></w:num>
+ </w:numbering>"#
+ );
+ let body = [list_p("1", Some("1"), "A"), list_p("1", Some("0"), "B"), list_p("1", Some("1"), "C"), list_p("1", Some("2"), "D")];
+ let st = lists_docx(&numbering, "", &body).story;
+ let labels: Vec<String> = (0..st.paras.len()).map(|i| label(&st, i)).collect();
+ assert_eq!(labels, ["I.1\t", "I.\t", "I.1\t", "1.1.1\t"]);
+ assert_eq!(st.paras[0].para.number_expression.as_deref(), Some("I.^#^t"));
+ assert_eq!(st.paras[2].para.number_expression.as_deref(), Some("^1.^#^t"));
+}
+
+/// A paragraph style's `w:numPr` (inherited through `w:basedOn`) makes its paragraphs a list;
+/// numId 0 on a paragraph takes it out of the list.
+#[test]
+fn style_lists_and_num_id_zero() {
+ let numbering = format!(
+ r#"<w:numbering {W}>
+ <w:abstractNum w:abstractNumId="7">
+ <w:lvl w:ilvl="0"><w:numFmt w:val="bullet"/><w:lvlText w:val="&#xF0B7;"/><w:rPr><w:rFonts w:ascii="Symbol" w:hAnsi="Symbol"/></w:rPr></w:lvl>
+ <w:lvl w:ilvl="1"><w:numFmt w:val="bullet"/><w:lvlText w:val="o"/><w:rPr><w:rFonts w:ascii="Courier New"/></w:rPr></w:lvl>
+ </w:abstractNum>
+ <w:num w:numId="5"><w:abstractNumId w:val="7"/></w:num>
+ </w:numbering>"#
+ );
+ let styles = format!(
+ r#"<w:styles {W}>
+ <w:style w:type="paragraph" w:styleId="ListBullet"><w:name w:val="List Bullet"/><w:pPr><w:numPr><w:numId w:val="5"/></w:numPr></w:pPr></w:style>
+ <w:style w:type="paragraph" w:styleId="ListBullet2"><w:name w:val="List Bullet 2"/><w:basedOn w:val="ListBullet"/>
+ <w:pPr><w:numPr><w:ilvl w:val="1"/></w:numPr></w:pPr></w:style>
+ </w:styles>"#
+ );
+ let styled =
+ |id: &str, extra: &str, text: &str| format!(r#"<w:p><w:pPr><w:pStyle w:val="{id}"/>{extra}</w:pPr><w:r><w:t>{text}</w:t></w:r></w:p>"#);
+ let body = [
+ styled("ListBullet", "", "one"),
+ styled("ListBullet2", "", "two"),
+ styled("ListBullet", r#"<w:numPr><w:ilvl w:val="0"/><w:numId w:val="0"/></w:numPr>"#, "not a list"),
+ ];
+ let st = lists_docx(&numbering, &styles, &body).story;
+ assert_eq!(label(&st, 0), "•\t");
+ assert_eq!(label(&st, 1), "◦\t");
+ assert_eq!(st.paras[2].para.list_type, None);
+ assert_eq!(st.paras[2].style, "List Bullet");
+}
+
+/// Hostile list definitions: missing abstractNums and levels, huge or negative levels and
+/// starts, a long label, a `w:basedOn` cycle. No panic; what can't be a list is plain.
+#[test]
+fn hostile_numbering_falls_back_to_plain_paragraphs() {
+ let long = "x".repeat(10_000);
+ let numbering = format!(
+ r#"<w:numbering {W}>
+ <w:abstractNum w:abstractNumId="1">
+ <w:lvl w:ilvl="0"><w:start w:val="99999999999999"/><w:numFmt w:val="decimal"/><w:lvlText w:val="%1{long}%9%"/></w:lvl>
+ <w:lvl w:ilvl="99999999999999"><w:numFmt w:val="decimal"/></w:lvl>
+ <w:lvl w:ilvl="-1"><w:numFmt w:val="decimal"/></w:lvl>
+ <w:lvl w:ilvl="3"><w:start w:val="-5"/><w:numFmt w:val="ordinalText"/><w:lvlText w:val="%4^"/><w:lvlRestart w:val="99"/></w:lvl>
+ </w:abstractNum>
+ <w:num w:numId="1"><w:abstractNumId w:val="1"/></w:num>
+ <w:num w:numId="2"><w:abstractNumId w:val="404"/></w:num>
+ <w:num w:numId="3"/>
+ <w:num><w:abstractNumId w:val="1"/></w:num>
+ </w:numbering>"#
+ );
+ let styles = format!(
+ r#"<w:styles {W}>
+ <w:style w:type="paragraph" w:styleId="A"><w:name w:val="A"/><w:basedOn w:val="B"/></w:style>
+ <w:style w:type="paragraph" w:styleId="B"><w:name w:val="B"/><w:basedOn w:val="A"/></w:style>
+ </w:styles>"#
+ );
+ let body = [
+ list_p("2", None, "missing abstractNum"),
+ list_p("3", None, "num without abstractNum"),
+ list_p("404", None, "unknown numId"),
+ list_p("1", Some("99999999999999"), "huge level"),
+ list_p("1", Some("9"), "level 9"),
+ list_p("1", Some("-1"), "negative level"),
+ list_p("1", Some("1"), "undefined level"),
+ r#"<w:p><w:pPr><w:pStyle w:val="A"/><w:numPr><w:ilvl w:val="0"/></w:numPr></w:pPr><w:r><w:t>cycle</w:t></w:r></w:p>"#.to_string(),
+ list_p("1", None, "huge start"),
+ list_p("1", Some("3"), "negative start"),
+ ];
+ let st = lists_docx(&numbering, &styles, &body).story;
+ assert!(st.paras[..8].iter().all(|p| p.para.list_type.is_none()), "{:?}", st.paras);
+ assert_eq!(st.paras[8].para.start_at, Some(Some(u32::MAX)));
+ let expr = st.paras[8].para.number_expression.clone().unwrap_or_default();
+ assert!(expr.starts_with("^#x") && expr.chars().count() < 80, "{expr}");
+ // A start below 0 counts from 0, which the model shows as 1; `^` in a label is literal.
+ assert_eq!(label(&st, 9), "1^\t");
+ // Unreadable list definitions leave plain paragraphs and a warning, not a failed import.
+ let document = format!(r#"<w:document {W}><w:body>{}</w:body></w:document>"#, list_p("1", None, "x"));
+ let i = import(&docx_parts(&[("word/document.xml", &document), ("word/numbering.xml", "<w:numbering></w:num>")])).unwrap();
+ assert_eq!(i.story.paras[0].para.list_type, None);
+ assert_eq!(i.warnings.len(), 1);
+}
+
+#[test]
+fn an_element_with_many_attributes_parses_in_linear_time() {
+ // RUSTSEC-2026-0194: before quick-xml 0.41 the duplicate-attribute check compared each name with every
+ // earlier one on the element, so a crafted .docx/.xlsx with one huge tag hung the import (O(N²)).
+ let attrs: String = (0..100_000).map(|i| format!(" w:a{i}=\"{i}\"")).collect();
+ let xml = format!("<w:document><w:body><w:p{attrs}/></w:body></w:document>");
+ let started = std::time::Instant::now();
+ let doc = parse(&xml).unwrap();
+ assert!(started.elapsed() < std::time::Duration::from_secs(5), "parse took {:?}", started.elapsed());
+ let p = doc.child("body").and_then(|b| b.child("p")).unwrap();
+ assert_eq!(p.attr("a0"), Some("0"));
+ assert_eq!(p.attr("a99999"), Some("99999"));
+}
+
+#[test]
+fn table_cells_read_text_like_body_paragraphs() {
+ // Regression (#721): cells took every text node, so deleted text, move sources and field
+ // instructions showed up in the table.
+ let para = r#"<w:p><w:r><w:t xml:space="preserve">kept </w:t></w:r>
+ <w:del w:id="1" w:author="A"><w:r><w:delText>GONE</w:delText></w:r></w:del>
+ <w:moveFrom w:id="2" w:author="A"><w:r><w:t>MOVED AWAY</w:t></w:r></w:moveFrom>
+ <w:r><w:fldChar w:fldCharType="begin"/></w:r><w:r><w:instrText xml:space="preserve"> PAGE </w:instrText></w:r>
+ <w:r><w:fldChar w:fldCharType="separate"/></w:r><w:r><w:t>7</w:t></w:r><w:r><w:fldChar w:fldCharType="end"/></w:r></w:p>"#;
+ let document = format!(r#"<w:document {W}><w:body>{para}<w:tbl><w:tr><w:tc>{para}<w:p/></w:tc></w:tr></w:tbl></w:body></w:document>"#);
+ let i = import(&docx(&document, "", "")).unwrap();
+ assert!(i.story.text.starts_with("kept 7"), "{:?}", i.story.text);
+ let cell = &i.story.tables.values().next().unwrap().cell(0, 0).unwrap().text;
+ assert_eq!(cell.text, "kept 7\n");
+}
+
+#[test]
+fn normal_is_its_own_style_over_the_document_defaults() {
+ // Regression (#722): text formatted only by Normal and the document defaults lost it.
+ let styles = format!(
+ r#"<w:styles {W}><w:docDefaults><w:rPrDefault><w:rPr><w:sz w:val="22"/></w:rPr></w:rPrDefault>
+ <w:pPrDefault><w:pPr><w:spacing w:after="160"/></w:pPr></w:pPrDefault></w:docDefaults>
+ <w:style w:type="paragraph" w:default="1" w:styleId="Normal"><w:name w:val="Normal"/><w:rPr><w:rFonts w:ascii="Georgia"/><w:sz w:val="26"/></w:rPr></w:style>
+ <w:style w:type="paragraph" w:styleId="Quote"><w:name w:val="Quote"/><w:basedOn w:val="Normal"/><w:rPr><w:i/></w:rPr></w:style>
+ </w:styles>"#
+ );
+ let document = format!(
+ r#"<w:document {W}><w:body><w:p><w:r><w:t>Plain</w:t></w:r></w:p>
+ <w:p><w:pPr><w:pStyle w:val="Quote"/></w:pPr><w:r><w:t>Quoted</w:t></w:r></w:p></w:body></w:document>"#
+ );
+ let i = import(&docx(&document, &styles, "")).unwrap();
+ assert_eq!(i.story.paras[0].style, "Normal");
+ let normal = i.para_styles.iter().find(|s| s.name == "Normal").unwrap();
+ assert_eq!(normal.chars.size, Some(13.0), "Normal's size wins over the default");
+ assert_eq!(normal.chars.font_family.as_deref(), Some("Georgia"));
+ assert_eq!(normal.para.space_after, Some(8.0), "from the document defaults");
+ let quote = i.para_styles.iter().find(|s| s.name == "Quote").unwrap();
+ assert_eq!(quote.based_on.as_deref(), Some("Normal"));
+ assert_eq!(quote.chars.size, None, "inherited from Normal, not copied");
+}
+
+/// `ST_OnOff` is a boolean plus the words `on` and `off`: an explicit `off` is off.
+#[test]
+fn off_valued_toggles_stay_off() {
+ let document = format!(
+ r#"<w:document {W}><w:body><w:p>
+ <w:r><w:rPr><w:b w:val="off"/><w:i w:val="0"/><w:strike w:val="off"/><w:u w:val="off"/><w:caps w:val="off"/></w:rPr><w:t>plain</w:t></w:r>
+ <w:r><w:rPr><w:b w:val="on"/></w:rPr><w:t>bold</w:t></w:r>
+ </w:p></w:body></w:document>"#
+ );
+ let st = import(&docx(&document, "", "")).unwrap().story;
+ st.check().unwrap();
+ let plain = st.format_after(st.text.find("plain").unwrap()).clone().over;
+ assert_eq!(plain.font_style.as_deref(), Some("Regular"), "an explicit `off` is not bold");
+ assert_eq!(plain.strikethrough, Some(false));
+ assert_eq!(plain.underline, Some(false));
+ assert_eq!(plain.capitalization, None, "no all-caps");
+ let on = st.format_after(st.text.find("bold").unwrap()).clone().over;
+ assert_eq!(on.font_style.as_deref(), Some("Bold"), "`on` is still on");
+}