Skip to content

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

Word import: bullets and numbering from numbering.xml (#626)

aiongg7515dfeaf501
diff --git a/ROADMAP.md b/ROADMAP.md
index f826a3767..9caf72aae 100644
--- a/ROADMAP.md
+++ b/ROADMAP.md
@@ -129,6 +129,7 @@ list) · [roadmap.md](docs/roadmap.md) (milestones, plan) · [parity-checklist.m
Newest first.
+- **2026-10-12** · Placed Word documents keep their bullets and numbering (#626): `numbering.xml` levels become bullet or numbered paragraphs with Word's number formats, label text, start numbers, restarts and list indents, also when a paragraph style carries the list. No readiness percentage change.
- **2026-10-12** · Orderly native exit writes the latest recovery state after finalizing current quit approvals; incomplete or stale plans keep their documents, and Undo to the saved state clears stale recovery. Unavailable or failed recovery is reported. Cancelable macOS Dock Quit remains open (#544). No readiness percentage change.
- **2026-10-12** · Recovered documents keep a checkpoint until saved, closed or reverted, including a second crash before autosave. Restarted document IDs and explicit recovery folders preserve other snapshots; failed republishing retains the original. No readiness percentage change.
- **2026-10-12** · Book numbering and style updates prepare every chapter before saving. Only closed native chapters are changed; imported IDML remains a read-only style/PDF source. If a later disk write fails, the error names the completed chapters; the batch is not a whole-book transaction. No readiness percentage change.
diff --git a/crates/textimport/src/docx.rs b/crates/textimport/src/docx.rs
index 67a2b71a1..a51e9fe02 100644
--- a/crates/textimport/src/docx.rs
+++ b/crates/textimport/src/docx.rs
@@ -4,9 +4,10 @@ use std::collections::HashMap;
use std::io::Read;
use designcraft_doc::story::{BASIC_PARAGRAPH, NO_CHAR_STYLE};
-use designcraft_doc::{CharAttrs, CharFormat, ParaAttrs, ParaFormat, Story, StoryId, Table};
+use designcraft_doc::{CharAttrs, CharFormat, ListType, ParaAttrs, ParaFormat, Story, StoryId, Table};
use quick_xml::events::Event;
+use crate::docx_numbering::{ListPara, Numbering};
use crate::{ImportError, Imported, ImportedStyle};
/// A minimal element tree (local names, attributes by local name).
@@ -43,10 +44,10 @@ impl El {
.collect()
}
/// `<w:x w:val="…"/>` → the value; a bare `<w:b/>` counts as "on".
- fn val(&self, name: &str) -> Option<String> {
+ pub(crate) fn val(&self, name: &str) -> Option<String> {
self.child(name).map(|e| e.attr("val").unwrap_or("true").to_string())
}
- fn on(&self, name: &str) -> Option<bool> {
+ pub(crate) fn on(&self, name: &str) -> Option<bool> {
self.val(name).map(|v| !matches!(v.as_str(), "0" | "false" | "none"))
}
}
@@ -216,6 +217,12 @@ struct Ctx {
footnotes: HashMap<String, El>,
warnings: Vec<String>,
next_table: u64,
+ numbering: Numbering,
+ /// A paragraph style's list (`w:numPr` numId and ilvl, through `w:basedOn`), by style id.
+ style_lists: HashMap<String, (Option<String>, Option<String>)>,
+ /// The number the model's own list counter is at (it restarts after a paragraph that isn't
+ /// in a list), to tell where a numbered paragraph needs an explicit Start At.
+ model_counter: u32,
}
impl Ctx {
@@ -236,10 +243,20 @@ impl Ctx {
first = false;
let ppr = e.child("pPr");
let style = self.para_style(ppr);
- let attrs = para_attrs(ppr);
+ let mut attrs = para_attrs(ppr);
+ let list = self.list(ppr);
+ if let Some(l) = &list {
+ // The level's indents, unless the paragraph sets its own.
+ let direct = attrs;
+ attrs = l.attrs.clone();
+ attrs.merge(&direct);
+ }
let at = st.len();
st.format_paras(at..at, |f| *f = ParaFormat { style: style.clone(), para: attrs.clone(), ..Default::default() });
self.inline(e, st, allow_notes);
+ if let Some(n) = self.start_at(list.as_ref(), st.len() == at) {
+ st.format_paras(at..at, |f| f.para.start_at = Some(Some(n)));
+ }
}
"tbl" => {
let rows: Vec<Vec<String>> = e
@@ -271,6 +288,35 @@ impl Ctx {
}
}
+ /// The list a paragraph is in (its own `w:numPr`, else its style's), counting it.
+ fn list(&mut self, ppr: Option<&El>) -> Option<ListPara> {
+ let direct = ppr.and_then(|p| p.child("numPr"));
+ let style = ppr.and_then(|p| p.val("pStyle")).and_then(|id| self.style_lists.get(&id));
+ let num_id = direct.and_then(|n| n.val("numId")).or_else(|| style.and_then(|s| s.0.clone()))?;
+ let ilvl = direct.and_then(|n| n.val("ilvl")).or_else(|| style.and_then(|s| s.1.clone()));
+ // A level that isn't a small number is no list.
+ let ilvl = ilvl.map_or(Some(0), |l| l.trim().parse::<u32>().ok())?;
+ self.numbering.next(num_id.trim(), ilvl)
+ }
+
+ /// Start At for a paragraph, so that the model numbers it as Word does: only where the
+ /// model's counter (which follows the previous numbered paragraph, and restarts after one
+ /// that isn't in a list) would give a different number.
+ fn start_at(&mut self, list: Option<&ListPara>, empty: bool) -> Option<u32> {
+ let Some(l) = list else {
+ self.model_counter = 0;
+ return None;
+ };
+ // Bullets and empty paragraphs leave the counter alone (they show no number).
+ if l.attrs.list_type != Some(ListType::Numbers) || empty {
+ return None;
+ }
+ let want = l.number.max(1);
+ let next = self.model_counter.saturating_add(1);
+ self.model_counter = want;
+ (want != next).then_some(want)
+ }
+
/// Runs (and hyperlinks, fields' results) of a paragraph.
fn inline(&mut self, p: &El, st: &mut Story, allow_notes: bool) {
for e in p.els() {
@@ -302,7 +348,9 @@ impl Ctx {
"footnoteReference" if allow_notes => {
if let Some(note) = e.attr("id").and_then(|id| self.footnotes.get(id).cloned()) {
let mut ns = Story::new(StoryId(0));
+ let counter = std::mem::take(&mut self.model_counter);
self.blocks(&note, &mut ns, false);
+ self.model_counter = counter;
// Word puts the reference mark in the note text: we generate the number.
let len = st.len();
let id = st.insert_note(len, "", ParaFormat::default());
@@ -328,17 +376,63 @@ impl Ctx {
}
}
+/// Largest `word/numbering.xml` read.
+const NUMBERING_LIMIT: u64 = 16 * 1024 * 1024;
+/// Deepest `w:basedOn` chain followed (a cycle stops here too).
+const MAX_STYLE_DEPTH: usize = 32;
+
+/// Each paragraph style's list: the first `w:numId` and `w:ilvl` on its `w:basedOn` chain.
+fn style_lists(styles: &El) -> HashMap<String, (Option<String>, Option<String>)> {
+ let by_id: HashMap<&str, &El> = styles.els().filter(|s| s.name == "style").filter_map(|s| Some((s.attr("styleId")?, s))).collect();
+ let mut out = HashMap::new();
+ for (id, s) in &by_id {
+ let (mut num_id, mut ilvl) = (None, None);
+ let mut cur = Some(*s);
+ for _ in 0..MAX_STYLE_DEPTH {
+ let Some(c) = cur else { break };
+ if let Some(n) = c.child("pPr").and_then(|p| p.child("numPr")) {
+ num_id = num_id.or_else(|| n.val("numId"));
+ ilvl = ilvl.or_else(|| n.val("ilvl"));
+ }
+ if num_id.is_some() && ilvl.is_some() {
+ break;
+ }
+ cur = c.val("basedOn").and_then(|b| by_id.get(b.as_str()).copied());
+ }
+ if num_id.is_some() {
+ out.insert(id.to_string(), (num_id, ilvl));
+ }
+ }
+ out
+}
+
pub fn import(bytes: &[u8]) -> Result<Imported, ImportError> {
let mut zip = zip::ZipArchive::new(std::io::Cursor::new(bytes)).map_err(|e| ImportError::Corrupt(e.to_string()))?;
let doc = part(&mut zip, "word/document.xml")?.ok_or_else(|| ImportError::Corrupt("no word/document.xml (not a Word document)".into()))?;
let doc = parse(&doc)?;
// Styles.
- let mut ctx = Ctx { para_names: HashMap::new(), char_names: HashMap::new(), footnotes: HashMap::new(), warnings: vec![], next_table: 0 };
+ let mut ctx = Ctx {
+ para_names: HashMap::new(),
+ char_names: HashMap::new(),
+ footnotes: HashMap::new(),
+ warnings: vec![],
+ next_table: 0,
+ numbering: Numbering::default(),
+ style_lists: HashMap::new(),
+ model_counter: 0,
+ };
+ // Lists that can't be read leave plain paragraphs, not a failed import.
+ match part_capped(&mut zip, "word/numbering.xml", NUMBERING_LIMIT).and_then(|s| s.map(|s| parse(&s)).transpose()) {
+ Ok(Some(n)) => ctx.numbering = Numbering::parse(&n),
+ Ok(None) => {}
+ Err(_) => ctx.warnings.push("The Word file's list definitions could not be read: lists were imported as plain paragraphs.".into()),
+ }
let mut para_styles = Vec::new();
let mut char_styles = Vec::new();
if let Some(styles) = part(&mut zip, "word/styles.xml")?.map(|s| parse(&s)).transpose()? {
let ids: HashMap<String, String> =
styles.els().filter(|s| s.name == "style").filter_map(|s| Some((s.attr("styleId")?.to_string(), s.val("name")?))).collect();
+ ctx.style_lists = style_lists(&styles);
for s in styles.els().filter(|s| s.name == "style") {
let (Some(id), Some(name)) = (s.attr("styleId"), s.val("name")) else { continue };
let kind = s.attr("type").unwrap_or("paragraph");
@@ -404,9 +498,14 @@ mod tests {
use std::io::Write;
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 [("word/document.xml", document), ("word/styles.xml", styles), ("word/footnotes.xml", footnotes)] {
+ for &(n, c) in parts {
if c.is_empty() {
continue;
}
@@ -510,4 +609,187 @@ mod tests {
i.story.check().unwrap();
assert_eq!(i.story.text, "Kept text. MOVED HERE. Plain INSERTED\nEnd.");
}
+
+ /// 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 the model gives paragraph `i` when its number is `n`.
+ fn label(st: &Story, i: usize, n: u32) -> String {
+ let mut p = designcraft_doc::ParaProps::default();
+ p.apply(&st.paras[i].para);
+ match p.list_type {
+ ListType::Numbers => p.number_label(n),
+ ListType::Bullets => p.bullet_label(),
+ ListType::None => String::new(),
+ }
+ }
+
+ /// 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, 1), "•\t");
+ assert_eq!(st.paras[3].para.number_style, Some(designcraft_doc::NumberStyle::Arabic));
+ assert_eq!((label(&st, 3, 1), label(&st, 4, 2)), ("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). E's 2
+ // follows the model's counter (1 after D).
+ assert_eq!(start, [None, Some(Some(1)), None, Some(Some(1)), None, None, Some(Some(3)), Some(Some(1)), Some(Some(4))]);
+ assert_eq!(label(&st, 1, 1), "a) ");
+ assert_eq!(label(&st, 3, 1), "1.b.I\t");
+ assert_eq!(st.paras[1].para.left_indent, Some(72.0));
+ assert_eq!(st.paras[1].para.first_line_indent, Some(-18.0));
+ }
+
+ /// 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, 1), "•\t");
+ assert_eq!(label(&st, 1, 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), "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);
+ }
}
diff --git a/crates/textimport/src/docx_numbering.rs b/crates/textimport/src/docx_numbering.rs
new file mode 100644
index 000000000..31b855b09
--- /dev/null
+++ b/crates/textimport/src/docx_numbering.rs
@@ -0,0 +1,325 @@
+//! Word lists: `word/numbering.xml` and the `w:numPr` of paragraphs and paragraph styles.
+//!
+//! A `w:num` (numId) points at a `w:abstractNum`, whose `w:lvl` elements (levels 0–8) give
+//! each level's format, label text, start number, indents and the text after the label.
+//!
+//! Numbering follows Word's main rules, simplified:
+//! - Numbers count per level. A paragraph at level L restarts the levels below it (unless a
+//! level's `w:lvlRestart` says otherwise).
+//! - `num` instances of one abstractNum share their counters, so a list carries on across
+//! them and across paragraphs that aren't in a list. A `num` with a `w:startOverride` counts
+//! on its own, starting at the override.
+//! - Parent levels in a label (`%1.%2.`) are written as text: the model's labels number only
+//! the paragraph's own level.
+
+use std::collections::HashMap;
+
+use designcraft_doc::{ListType, NumberStyle, ParaAttrs};
+
+use crate::docx::El;
+
+/// Most `w:abstractNum` or `w:num` elements read; the rest are ignored.
+pub(crate) const MAX_DEFS: usize = 10_000;
+/// Word's list levels are 0–8.
+const LEVELS: usize = 9;
+/// Longest label text (`w:lvlText`) kept, in characters.
+const MAX_LVL_TEXT: usize = 64;
+
+#[derive(Clone, Copy, Debug, Default, PartialEq)]
+enum Format {
+ #[default]
+ Bullet,
+ /// No number: the label is the level text alone.
+ Nothing,
+ Number(NumberStyle),
+}
+
+#[derive(Clone, Copy, Debug, Default, PartialEq)]
+enum Suffix {
+ #[default]
+ Tab,
+ Space,
+ Nothing,
+}
+
+#[derive(Clone, Debug, Default)]
+struct Level {
+ format: Format,
+ text: String,
+ start: u32,
+ suffix: Suffix,
+ left: Option<f64>,
+ /// First-line indent in points (negative for a hanging indent).
+ first_line: Option<f64>,
+ /// `w:lvlRestart`: 0 = never restart, n = restart after level n (1-based) or a higher one.
+ restart: Option<u32>,
+ /// `w:isLgl`: parent levels in the label are written as decimal numbers.
+ legal: bool,
+ /// The font of the label (`w:rPr/w:rFonts`), which decides what a Symbol/Wingdings bullet is.
+ font: Option<String>,
+ picture: bool,
+}
+
+#[derive(Debug, Default)]
+struct Num {
+ abstract_id: String,
+ /// `w:lvlOverride` per level: a start override and/or a replacement level.
+ start_override: [Option<u32>; LEVELS],
+ level_override: [Option<Level>; LEVELS],
+}
+
+impl Num {
+ fn has_start_override(&self) -> bool {
+ self.start_override.iter().any(Option::is_some)
+ }
+}
+
+/// A list paragraph: the paragraph attributes that make it one, and its number in Word.
+#[derive(Clone, Debug, PartialEq)]
+pub(crate) struct ListPara {
+ pub(crate) attrs: ParaAttrs,
+ /// The paragraph's number at its level (also counted for bullets).
+ pub(crate) number: u32,
+}
+
+/// The lists of a Word document and the numbering state while its paragraphs are read in order.
+#[derive(Debug, Default)]
+pub(crate) struct Numbering {
+ abstracts: HashMap<String, [Option<Level>; LEVELS]>,
+ nums: HashMap<String, Num>,
+ /// Current number per level, per counter key (an abstractNum, or a `num` with overrides).
+ counters: HashMap<String, [Option<u32>; LEVELS]>,
+}
+
+fn level_index(e: &El) -> Option<usize> {
+ e.attr("ilvl").and_then(|v| v.trim().parse::<usize>().ok()).filter(|l| *l < LEVELS)
+}
+
+fn parse_u32(v: Option<String>) -> Option<u32> {
+ let v = v?;
+ let v = v.trim();
+ // Negative starts count from 0; numbers too large for a u32 are clamped.
+ match v.parse::<i64>() {
+ Ok(n) => Some(u32::try_from(n.max(0)).unwrap_or(u32::MAX)),
+ Err(_) => None,
+ }
+}
+
+fn number_style(fmt: &str) -> Format {
+ match fmt {
+ "bullet" => Format::Bullet,
+ "none" => Format::Nothing,
+ "decimalZero" => Format::Number(NumberStyle::ArabicLeadingZero),
+ "upperRoman" => Format::Number(NumberStyle::UpperRoman),
+ "lowerRoman" => Format::Number(NumberStyle::LowerRoman),
+ "upperLetter" => Format::Number(NumberStyle::UpperLetters),
+ "lowerLetter" => Format::Number(NumberStyle::LowerLetters),
+ "chicago" => Format::Number(NumberStyle::Symbols),
+ // decimal and every format the model has no style for (ordinal, cardinalText,
+ // decimalEnclosedCircle, the East Asian counting systems, …).
+ _ => Format::Number(NumberStyle::Arabic),
+ }
+}
+
+fn parse_level(e: &El) -> Level {
+ let tw = |v: Option<&str>| v.and_then(|v| v.trim().parse::<f64>().ok()).filter(|v| v.is_finite()).map(|v| v / 20.0);
+ let ind = e.child("pPr").and_then(|p| p.child("ind"));
+ Level {
+ format: e.val("numFmt").map_or(Format::Number(NumberStyle::Arabic), |f| number_style(&f)),
+ text: e.child("lvlText").and_then(|t| t.attr("val")).unwrap_or_default().chars().take(MAX_LVL_TEXT).collect(),
+ start: parse_u32(e.val("start")).unwrap_or(1),
+ suffix: match e.val("suff").as_deref() {
+ Some("space") => Suffix::Space,
+ Some("nothing") => Suffix::Nothing,
+ _ => Suffix::Tab,
+ },
+ left: ind.and_then(|i| tw(i.attr("left").or(i.attr("start")))),
+ first_line: ind.and_then(|i| tw(i.attr("firstLine")).or(tw(i.attr("hanging")).map(|h| -h))),
+ restart: parse_u32(e.val("lvlRestart")),
+ legal: e.on("isLgl") == Some(true),
+ font: e.child("rPr").and_then(|r| r.child("rFonts")).and_then(|f| f.attr("ascii").or(f.attr("hAnsi"))).map(str::to_string),
+ picture: e.child("lvlPicBulletId").is_some(),
+ }
+}
+
+/// The bullet Word shows for `text` in `font`. Symbol and Wingdings bullets are stored as
+/// private-use characters (U+F0xx) or as the font's own code points; the common ones become
+/// their Unicode look-alikes, unknown ones a plain bullet.
+fn bullet_char(text: &str, font: Option<&str>) -> String {
+ let font = font.unwrap_or_default().to_ascii_lowercase();
+ let symbol = font.contains("symbol");
+ let wingdings = font.contains("wingdings");
+ text.chars()
+ .map(|c| {
+ let code = u32::from(c);
+ let low = if (0xF000..=0xF0FF).contains(&code) { code - 0xF000 } else { code };
+ if wingdings {
+ return match low {
+ 0x6C => '●',
+ 0x6E => '■',
+ 0x71 => '❑',
+ 0x76 => '❖',
+ 0xA7 => '▪',
+ 0xD8 => '➢',
+ 0xFC => '✓',
+ _ => '•',
+ };
+ }
+ if symbol {
+ return match low {
+ 0x2D => '–',
+ 0x6F => '◦',
+ _ => '•',
+ };
+ }
+ match c {
+ // Word's second-level bullet is a Courier New "o".
+ 'o' => '◦',
+ '\u{E000}'..='\u{F8FF}' => '•',
+ c => c,
+ }
+ })
+ .filter(|c| *c != '\n' && *c != '\r')
+ .collect()
+}
+
+impl Numbering {
+ /// Read `numbering.xml`'s root (`w:numbering`).
+ pub(crate) fn parse(root: &El) -> Self {
+ let mut n = Numbering::default();
+ for e in root.els() {
+ match e.name.as_str() {
+ "abstractNum" if n.abstracts.len() < MAX_DEFS => {
+ let Some(id) = e.attr("abstractNumId") else { continue };
+ let mut levels: [Option<Level>; LEVELS] = Default::default();
+ for l in e.els().filter(|l| l.name == "lvl") {
+ if let Some(slot) = level_index(l).and_then(|i| levels.get_mut(i)) {
+ *slot = Some(parse_level(l));
+ }
+ }
+ n.abstracts.insert(id.to_string(), levels);
+ }
+ "num" if n.nums.len() < MAX_DEFS => {
+ let (Some(id), Some(abstract_id)) = (e.attr("numId"), e.val("abstractNumId")) else { continue };
+ let mut num = Num { abstract_id, ..Default::default() };
+ for o in e.els().filter(|o| o.name == "lvlOverride") {
+ let Some(i) = level_index(o) else { continue };
+ if let Some(slot) = num.start_override.get_mut(i) {
+ *slot = parse_u32(o.val("startOverride"));
+ }
+ if let (Some(slot), Some(l)) = (num.level_override.get_mut(i), o.child("lvl")) {
+ *slot = Some(parse_level(l));
+ }
+ }
+ n.nums.insert(id.to_string(), num);
+ }
+ _ => {}
+ }
+ }
+ n
+ }
+
+ /// The list formatting of the next paragraph with `w:numId` `num_id` at level `ilvl`, counting
+ /// it. `None` (a plain paragraph) for numId 0, an unknown list or level, or a level past 8.
+ pub(crate) fn next(&mut self, num_id: &str, ilvl: u32) -> Option<ListPara> {
+ let lv = usize::try_from(ilvl).ok().filter(|l| *l < LEVELS)?;
+ let num = self.nums.get(num_id)?;
+ let abs = self.abstracts.get(&num.abstract_id)?;
+ let level = |k: usize| num.level_override.get(k).and_then(Option::as_ref).or_else(|| abs.get(k).and_then(Option::as_ref));
+ let def = level(lv)?;
+ let own = num.has_start_override();
+ let key = if own { format!("n:{num_id}") } else { format!("a:{}", num.abstract_id) };
+ let start = |k: usize| {
+ let o = if own { num.start_override.get(k).copied().flatten() } else { None };
+ o.or_else(|| level(k).map(|l| l.start)).unwrap_or(1)
+ };
+ let counters = self.counters.entry(key).or_default();
+ let n = counters.get(lv).copied().flatten().map_or_else(|| start(lv), |v| v.saturating_add(1));
+ if let Some(c) = counters.get_mut(lv) {
+ *c = Some(n);
+ }
+ for (m, c) in counters.iter_mut().enumerate().skip(lv + 1) {
+ let restart = match level(m).and_then(|l| l.restart) {
+ None => true,
+ Some(0) => false,
+ Some(r) => ilvl < r,
+ };
+ if restart {
+ *c = None;
+ }
+ }
+ // Parent levels' current numbers, as text, for the label.
+ let parent = |k: usize| -> String {
+ let v = counters.get(k).copied().flatten().unwrap_or_else(|| start(k));
+ match level(k).map(|l| l.format) {
+ Some(Format::Number(s)) if !def.legal => s.format(v),
+ Some(Format::Number(_)) => v.to_string(),
+ _ => String::new(),
+ }
+ };
+ let label = |own_level: &str, escape: bool| -> String {
+ let mut out = String::new();
+ let mut it = def.text.chars().peekable();
+ while let Some(c) = it.next() {
+ if c == '%'
+ && let Some(k) = it.peek().and_then(|d| d.to_digit(10)).filter(|d| (1..=9).contains(d))
+ {
+ it.next();
+ let k = k as usize - 1;
+ if k == lv {
+ out.push_str(own_level);
+ } else {
+ let p = parent(k);
+ out.push_str(&if escape { p.replace('^', "^^") } else { p });
+ }
+ } else if escape && c == '^' {
+ out.push_str("^^");
+ } else if c != '\n' && c != '\r' {
+ out.push(c);
+ }
+ }
+ out
+ };
+ // The model's defaults: `^t` after a number, a literal tab after a bullet.
+ let (number_sep, bullet_sep) = match def.suffix {
+ Suffix::Tab => ("^t", "\t"),
+ Suffix::Space => (" ", " "),
+ Suffix::Nothing => ("", ""),
+ };
+ let mut a = ParaAttrs::default();
+ match def.format {
+ Format::Number(style) => {
+ a.list_type = Some(ListType::Numbers);
+ a.number_style = Some(style);
+ a.number_expression = Some(format!("{}{number_sep}", label("^#", true)));
+ }
+ Format::Bullet => {
+ a.list_type = Some(ListType::Bullets);
+ a.bullet_char = Some(if def.picture { "•".into() } else { bullet_char(&def.text, def.font.as_deref()) });
+ a.list_separator = Some(bullet_sep.into());
+ }
+ Format::Nothing => {
+ a.list_type = Some(ListType::Bullets);
+ a.bullet_char = Some(label("", false));
+ a.list_separator = Some(bullet_sep.into());
+ }
+ }
+ a.left_indent = def.left;
+ a.first_line_indent = def.first_line;
+ Some(ListPara { attrs: a, number: n })
+ }
+}
+
+#[cfg(test)]
+mod tests {
+ use super::*;
+
+ #[test]
+ fn symbol_and_wingdings_bullets_become_unicode() {
+ assert_eq!(bullet_char("\u{F0B7}", Some("Symbol")), "•");
+ assert_eq!(bullet_char("\u{F0A7}", Some("Wingdings")), "▪");
+ assert_eq!(bullet_char("o", Some("Courier New")), "◦");
+ assert_eq!(bullet_char("–", None), "–");
+ assert_eq!(bullet_char("\u{F076}", None), "•");
+ }
+}
diff --git a/crates/textimport/src/lib.rs b/crates/textimport/src/lib.rs
index 22f79c513..ba9cb92e3 100644
--- a/crates/textimport/src/lib.rs
+++ b/crates/textimport/src/lib.rs
@@ -1,6 +1,6 @@
//! Text import (File › Place of text files): plain text, Word documents (`.docx`) and RTF become
//! a frameless [`Story`] with paragraph and character styles, local bold/italic/underline/size,
-//! footnotes (Word) and tables (Word), ready to flow into text frames.
+//! footnotes, tables and bullets/numbering (Word), ready to flow into text frames.
//!
//! Word styles are imported by name (their font, size, bold/italic and space before/after become
//! the style definition, like InDesign's "Use Word styles" import option). RTF keeps bold,
@@ -9,6 +9,7 @@
#![forbid(unsafe_code)]
mod docx;
+mod docx_numbering;
pub mod export;
mod rtf;
pub mod tagged;
diff --git a/docs/file-format-parity.md b/docs/file-format-parity.md
index fc8fbc3a5..ae8f8c919 100644
--- a/docs/file-format-parity.md
+++ b/docs/file-format-parity.md
@@ -60,7 +60,7 @@ score below).
| EPS | `.eps` | ✓ (PostScript) | ~ preview only (no interpreter) | | <1% |
| SVG | `.svg` | ✓ | ✓ (usvg) | | <1% |
| HEIC | `.heic` | ✓ | ✗ | | <1% |
-| Word | `.docx` | ✓ styles, footnotes, tables, track changes, options | ✓ styles by name, footnotes, tables, tabs, breaks, moved text (#257), style mapping and conflicts | `.doc` not supported (InDesign reads it) | 2% |
+| Word | `.docx` | ✓ styles, footnotes, tables, track changes, options | ✓ styles by name, footnotes, tables, tabs, breaks, moved text (#257), bullets and numbering from `numbering.xml` (#626; parent levels in a label are fixed text), style mapping and conflicts | `.doc` not supported (InDesign reads it) | 2% |
| RTF | `.rtf` | ✓ | ✓ | | <1% |
| Excel | `.xlsx`, `.xls` | ✓ | ~ `.xlsx` first sheet's used range | no sheet/range options; `.xls` ✗ | <1% |
| Plain text, Markdown | `.txt`, `.md` | ✓ (txt) | ✓ | | <1% |