diff --git a/crates/formats/src/odt/body.rs b/crates/formats/src/odt/body.rs index c5c6c563c9..18db5d5cc1 100644 --- a/crates/formats/src/odt/body.rs +++ b/crates/formats/src/odt/body.rs @@ -30,6 +30,9 @@ pub(super) struct Body<'a> { pub(super) entries: &'a [String], /// The paragraph before had a page break after it: the next one starts a page. break_next: bool, + /// A ruby being read: its base text, ruby text, which of them the text goes to (`true`: + /// the ruby), and the base's formatting. + ruby: Option<(String, String, Option, Fmt)>, /// The form controls of `office:forms`, placed where a `draw:control` names them. forms: super::forms::FormsReader, pub(super) manifest: Option<&'a HashMap>, @@ -128,6 +131,7 @@ impl<'a> Body<'a> { entries: &[], forms: Default::default(), break_next: false, + ruby: None, manifest: None, containers: vec![Vec::new()], fmt: Vec::new(), @@ -216,6 +220,38 @@ impl<'a> Body<'a> { Ev::End(q) if self.forms.end(&q) => {} Ev::Start(q, a) if q == "draw:control" => self.place_control(&a), Ev::End(q) if q == "draw:control" => {} + // Ruby (ODF 1.3 §6.4): its base and ruby text, read on their own. + Ev::Start(q, _) if q == "text:ruby" && self.para.is_some() && self.field.is_none() => { + self.ruby = Some((String::new(), String::new(), None, self.cur_fmt())); + } + Ev::Start(q, _) if self.ruby.is_some() && matches!(q.as_str(), "text:ruby-base" | "text:ruby-text") => { + if let Some(r) = &mut self.ruby { + r.2 = Some(q == "text:ruby-text"); + } + } + Ev::End(q) if self.ruby.is_some() && matches!(q.as_str(), "text:ruby-base" | "text:ruby-text") => { + if let Some(r) = &mut self.ruby { + r.2 = None; + } + } + Ev::End(q) if q == "text:ruby" && self.ruby.is_some() => { + if let Some((base, ruby, _, fmt)) = self.ruby.take() { + let (base, ruby) = (base.trim().to_string(), ruby.trim().to_string()); + match (base.is_empty(), ruby.is_empty()) { + (false, false) => self.push_inline(Inline::Ruby { base, ruby, fmt }), + // A guide over nothing, or reading nothing: its text. + (false, true) | (true, false) => self.push_inline(Inline::Text(if base.is_empty() { ruby } else { base }, fmt)), + (true, true) => {} + } + } + } + Ev::Text(t) if self.ruby.is_some() => { + if let Some((base, ruby, Some(in_ruby), _)) = &mut self.ruby { + let s = if *in_ruby { ruby } else { base }; + let room = MAX_FIELD_RESULT.saturating_sub(s.len()); + s.extend(t.chars().take(room)); + } + } Ev::Start(q, a) => { if self.depth < MAX_XML_DEPTH { self.start(&q, &a); diff --git a/crates/formats/src/odt/tests.rs b/crates/formats/src/odt/tests.rs index dc1f7fbbc7..120935cee2 100644 --- a/crates/formats/src/odt/tests.rs +++ b/crates/formats/src/odt/tests.rs @@ -848,8 +848,8 @@ fn tracked_changes_round_trip_through_export() { #[test] fn an_inserted_ruby_keeps_its_tracked_insertion() { - // ODF has no ruby: its base text is written as text, and the insertion on the ruby must - // still be a change range around that text, not plain untracked text. + // A ruby inside a tracked insertion is written as its base text, so that it stays inside + // the change range rather than becoming plain untracked text. use wordcraft_doc::RevisionKind::Insert; let props = wordcraft_doc::props::CharProps::default(); let mut p = wordcraft_doc::Paragraph::with_text("before ", props.clone()); diff --git a/crates/formats/src/odt/tests_more.rs b/crates/formats/src/odt/tests_more.rs index 643088b83f..490c6d7738 100644 --- a/crates/formats/src/odt/tests_more.rs +++ b/crates/formats/src/odt/tests_more.rs @@ -29,6 +29,7 @@ mod para_borders; mod polygons; mod rotation; mod rtl; +mod ruby; mod settings; mod shapes; mod spacing; diff --git a/crates/formats/src/odt/tests_more/ruby.rs b/crates/formats/src/odt/tests_more/ruby.rs new file mode 100644 index 0000000000..3910139b2b --- /dev/null +++ b/crates/formats/src/odt/tests_more/ruby.rs @@ -0,0 +1,46 @@ +//! Ruby (ODF 1.3 §6.4 `text:ruby`: a base text with ruby text over it, furigana or pinyin) read as +//! WordCraft's Phonetic Guide and written back as ODF ruby. + +use crate::odt::tests::{NS_T, content_of, package}; +use crate::odt::{export, import}; +use wordcraft_doc::para::InlineObject; + +fn open(p: &str) -> wordcraft_doc::Document { + let content = format!( + r#"{p}"# + ); + import(&package(&content, None)).unwrap() +} + +/// Each ruby: (base, ruby text), and the paragraph's text. +fn rubies(d: &wordcraft_doc::Document) -> (Vec<(String, String)>, String) { + let p = d.body.iter().find_map(|b| b.as_para()).unwrap(); + let r = p + .objects + .iter() + .filter_map(|o| if let InlineObject::Ruby { base, ruby, .. } = o { Some((base.clone(), ruby.clone())) } else { None }) + .collect(); + (r, p.text.replace(wordcraft_doc::para::OBJ, "[R]")) +} + +#[test] +fn ruby_is_read_as_a_phonetic_guide_and_written_back() { + let d = open( + r#"Ruby: 漢字かんじ after."#, + ); + assert_eq!(rubies(&d), (vec![("漢字".to_string(), "かんじ".to_string())], "Ruby: [R] after.".to_string())); + let c = content_of(&export(&d).unwrap()); + assert!(c.contains("漢字かんじ"), "{c}"); + assert!(c.contains(r#"style:family="ruby">漢字!"#); + assert_eq!(rubies(&d), (Vec::new(), "漢字!".to_string())); + let d = open( + r#"基本きほん"#, + ); + assert_eq!(rubies(&d).0, vec![("基本".to_string(), "きほん".to_string())]); +} diff --git a/crates/formats/src/odt/writer.rs b/crates/formats/src/odt/writer.rs index b8363241c3..2688f7db0f 100644 --- a/crates/formats/src/odt/writer.rs +++ b/crates/formats/src/odt/writer.rs @@ -159,6 +159,8 @@ pub(super) struct Writer { /// kept objects' folders with their media types, for the manifest. pub(super) object_names: usize, pub(super) object_dirs: Vec<(String, String)>, + /// Ruby was written: its automatic ruby style is. + ruby_used: bool, /// Form controls written (`form:*` elements for `office:forms`), and whether this writer's /// text may hold them (the body's; not headers and footers). pub(super) forms: Vec, @@ -294,8 +296,6 @@ impl Writer { fn plain_inlines(&mut self, inl: &[Inline], out: &mut String) { let mut prev_space = true; - // ODF has no ruby: its base text goes through the text path below. - let inl = model::ruby_as_text(inl); let last = inl.len().saturating_sub(1); for (idx, i) in inl.iter().enumerate() { match i { @@ -420,8 +420,25 @@ impl Writer { prev_space = result.ends_with(' '); } }, - // Read as its base text by `ruby_as_text` above. - Inline::Ruby { .. } => {} + // Inside a tracked change: its base text, which the text path marks as changed. + Inline::Ruby { base, fmt, .. } if fmt.ins.is_some() || fmt.del.is_some() => { + self.plain_inlines(&[Inline::Text(base.clone(), fmt.clone())], out); + prev_space = false; + } + // Ruby (§6.4): the base text in its formatting, the ruby text over it. + Inline::Ruby { base, ruby, fmt } => { + self.ruby_used = true; + let base_xml = match self.text_style(&Fmt { link: None, ..fmt.clone() }) { + Some(n) => format!("{}", x(base)), + None => x(base), + }; + out.push_str(&format!( + "{base_xml}{}", + self.prefix, + x(ruby) + )); + prev_space = false; + } Inline::Equation { linear, display } => { self.formula(linear, *display, out); prev_space = false; @@ -748,6 +765,12 @@ impl Writer { )); } } + if self.ruby_used { + s.push_str(&format!( + "", + self.prefix + )); + } for (i, props) in self.row_styles.iter().enumerate() { s.push_str(&format!( "", diff --git a/docs/file-format-parity.md b/docs/file-format-parity.md index 2960ca18f3..4673126140 100644 --- a/docs/file-format-parity.md +++ b/docs/file-format-parity.md @@ -1,6 +1,6 @@ # File-format parity with Microsoft Word -> **Last reviewed:** 2026-10-11 · **Last updated:** 2026-11-01 · **Change:** trivial (ODT page breaks after a paragraph, kept lines, widow control, hyphenation, table alignment and width and row heights); previously trivial (in-line drawings raised or lowered by their run's position; ODT in-line frames keep their place on the baseline; leading's space after the last line; text box borders shown by LibreOffice); previously trivial (ODT form controls opened and saved as content controls); previously trivial (password-protected ODT opened and saved); previously trivial (ODT headers and footers keep their shapes, text boxes, charts and embedded objects on save); previously trivial (ODT embedded spreadsheets and OLE objects kept whole instead of lost; flat ODT sub-documents valid `office:document`s); previously trivial (ODT charts in drawing groups drawn on open); previously trivial (ODT charts opened and saved as editable charts; flat ODT sub-documents no longer end the body); previously trivial (ODT leading read as an at-least spacing); previously trivial (ODT tracked formatting changes; changed regions named by `xml:id`); previously trivial (ODT drop caps; tab stops no longer drop a paragraph's background); previously trivial (flat ODT `.fodt` opened and saved; ODT fidelity re-estimated at ~80%); previously trivial (ODT page settings; a footnote no longer takes a footer's text); previously trivial (ODT dates in their formats, sequences, chapters and references); previously trivial (ODT bookmarks over text); previously trivial (ODT tables of contents and indexes; ODT fidelity re-estimated); previously trivial (ODT polygons, polylines and paths); previously trivial (ODT arrowheads, dashes and gradients); previously trivial (ODT groups of shapes and pictures); previously trivial (ODT rotated and mirrored shapes and pictures); previously trivial (ODT drawing shapes read and written); previously trivial (ODT text box frames keep their line, fill, padding and fit); previously trivial (ODT Asian and complex-script fonts); previously trivial (ODT right-to-left paragraphs); previously trivial (ODT text boxes kept); previously trivial (ODT unnumbered headings detached from the outline); previously trivial (ODT contextual spacing and layout settings); previously trivial (ODT custom character styles kept); previously trivial (ODT list level positions); previously trivial (ODT custom paragraph styles kept); previously trivial (ODT equations written as formula objects); previously trivial (ODT numbered headings written as headings); previously trivial (ODT floating pictures); previously trivial (ODT paragraph borders and background); previously trivial (ODT heading numbering); previously trivial (ODT font-face names); previously trivial (ODT table cell borders and padding); previously trivial (ODT heading, title, quote and preformatted styles keep their look); previously trivial (ODT tab stops read and written); previously trivial (ODT character formatting read and written); previously trivial (ODT lists keep their number formats, bullets and identity); previously trivial (ODT comments read and written); previously trivial (ODT footnotes and endnotes read and written); previously trivial (ODT headers, footers and text fields written; fields read); previously trivial (ODT paragraph spacing, indents and line spacing read and written); previously trivial (a paragraph naming an undefined style is formatted as Normal, as in Word, #5077); previously trivial (a hyperlinked TOC writes its page numbers as `PAGEREF _Toc… \h` fields, as Word does, #5097); previously trivial (HTML import ends the empty comments and at once, #5040); previously trivial (chart and SmartArt text the font lacks is drawn in a fallback face, so Chinese labels no longer show boxes, #4720); previously trivial (bibliography sources keep a corporate author (`b:Corporate`): read, written, cited and listed whole, #4848); previously trivial (custom-property bookmark-link preservation, #4767); previously trivial (note conversion preserves content with an ordered reference/run walk, #4750); previously trivial (DOCX comment-ID save lookups); previously trivial (built-in heading styles have their outline level without `w:outlineLvl`, #4696); previously trivial (DOCX comment ranges inside footnotes and endnotes are kept on read, #4548); previously trivial (RTF import and export keep Windows and Enhanced Metafile pictures (`\wmetafile`, `\emfblip`), #4259); previously trivial (#4658 bounds nested Markdown reference-label work); previously trivial (HTML import keeps preformatted lines with CR or CRLF input newlines, #4810); previously trivial (DOCX parts stored under another casing keep their embedded fonts through a save, and a private save of a kept glossary escapes the attribute values it rewrites; previously trivial: the `.doc` reader logs what its copy budget leaves out, once a kind per document; importers bound hostile expansion: font names, links, ODS repeats, LaTeX wrappers, Markdown delimiters, #3692/#3713; previously trivial: repeated DOCX style IDs: save/reopen regression; previously trivial: Markdown code spans keep line-broken text literal, #3738; previously trivial: Arabic list labels: `arabicAlpha` and `arabicAbjad` draw the 28 Arabic letters (alphabetical and abjad order), doubling past the last letter; Hebrew, Hindi, Thai and Vietnamese still show decimal (`doc::section::tests::arabic_letters_count_in_both_orders`); previously trivial: localized TOC style ids read as the TOC styles, and a TOC in columns keeps its layout through Update Table, #3889; previously trivial: cu20we: outline caps; previously trivial: a relationship the markup names without the prefix is read as it wrote: an unqualified `id` on an element that carries a relationship names that relationship, and the writer keeps the attribute with the id the new package holds the part under; an ordinary `id` — a VML shape's, a drawing's — names no part; previously trivial: the reader takes the relationship ids the markup refers to from the relationship attributes of the main document it has already parsed, so a document with many relationships opens in the time its part takes, #3411; previously trivial: a table cell span from a `.json` file stays within 63 columns through Insert Column and Merge Cells, #3637; previously trivial: the file commands that change the document are checked on a protected document, the protection of a protected document needs an explicit stop, the session author can't change through `file.setAuthor` under protection (the CLI's `--author` uses the same protection check), and the post-check compares the settings and the metadata; previously trivial: a document with many content controls saves in the time the controls take, #13; previously trivial: `majorBidi`/`minorBidi` theme fonts follow the settings' theme font language, as measured in Word; previously trivial: Word signature lines are kept on save, still signable; previously trivial: Times New Roman keeps Liberation Serif under the roman-font rule; previously trivial: shape gradients and transparency, #1500; previously trivial: a folder that keeps no Unix modes, such as a NAS share mounted by GVFS, still takes a save, #3003; previously trivial: a text frame in the paragraph defaults frames nothing, #2360; previously trivial: table style band sizes written, a style without them unbanded as in Word, #3415; previously trivial: HTML export writes ruby (furigana, phonetic guides) and HTML import reads it back, #1681; previously trivial: RTF import decodes the East Asian multibyte code pages, #1653; previously trivial: PDF export: lam-alef drawn as two glyphs at one x extracts in reading order, #2310; previously trivial: native .json stores pictures and kept parts as base64, #586 follow-up; previously trivial: ODT headers and footers read from each master page, #863; previously trivial: RTF import compares heading and code formatting with the file's stylesheet; previously trivial: text typed into a content control takes the control's formatting; localized placeholder styles recognised; previously trivial: forms protection keeps its content controls: no inserting, Properties or Remove Content Control; previously trivial: Word XML and web pages saved as `.doc` open by what they hold, #2853; previously trivial: a VML shape in a header cell is always placed on the page, user-checked in Word for Mac, #1775; previously trivial: `w:sym` characters keep their symbol font when the text's font changes and are written back as `w:sym`, #2036; previously trivial: RTF export writes sections (gap 19); previously trivial: ODT export writes sections (gap 19); previously trivial: two lines in one and horizontal in vertical (`w:eastAsianLayout`) kept on save; previously trivial: PDF outline targets follow leading page breaks; previously trivial: positional tabs `w:ptab` read and kept on save, #2367; previously trivial: DOCX: mixed right-to-left runs split and marked `w:rtl` with their language, #1543; previously trivial: `w:doNotTrackMoves` round-trips and turns move tracking off; previously trivial: legacy outline, shadow, emboss and imprint text effects drawn, #2534; previously trivial: DOCX glossary documents (building blocks) read, kept and written; previously trivial: cached field results keep their visible run formatting; previously trivial: cached REF results retain hyperlink destinations; previously trivial: CLI conversions can explicitly refresh fields; previously trivial: a copied equation also goes in the clipboard's MathML formats, #1297; previously trivial: a pasted HTML `
` is an indented paragraph, not the Quote style, #1270); previously trivial: every table style part round-trips, #714; previously trivial: VML freeforms read and kept on save; previously trivial: multi-paragraph field instructions no longer add blank lines; previously trivial: `flowChartOr` draws its circle and cross spokes, as in Word; previously trivial: RTF: Mac OS Roman and DOS text, #1653; previously trivial: VML text boxes keep their internal margins, fit to their text and vertical alignment; hidden drawings not shown; previously trivial: PDF export draws horizontal and vertical lines inside groups, #1474; previously trivial: symbol-font text exported as Unicode, #776; previously trivial: text-box margins, Resize shape to fit text and freeforms in groups, #743; previously trivial: formatted paste from the system clipboard's HTML and RTF, #687; previously trivial: independent complex-script formatting inheritance and round-trip regression tests; previously trivial: import/export fixes for TXT, RTF, ODT, HTML and LaTeX, #433–#440; previously major: first version; every format Word reads or writes, measured from the readers and writers on origin/main) · **Target:** Microsoft Word (Microsoft 365) for Mac 16.113.4, plus Word for Windows' extra formats +> **Last reviewed:** 2026-10-11 · **Last updated:** 2026-11-01 · **Change:** trivial (ODT ruby read and written); previously trivial (ODT page breaks after a paragraph, kept lines, widow control, hyphenation, table alignment and width and row heights); previously trivial (in-line drawings raised or lowered by their run's position; ODT in-line frames keep their place on the baseline; leading's space after the last line; text box borders shown by LibreOffice); previously trivial (ODT form controls opened and saved as content controls); previously trivial (password-protected ODT opened and saved); previously trivial (ODT headers and footers keep their shapes, text boxes, charts and embedded objects on save); previously trivial (ODT embedded spreadsheets and OLE objects kept whole instead of lost; flat ODT sub-documents valid `office:document`s); previously trivial (ODT charts in drawing groups drawn on open); previously trivial (ODT charts opened and saved as editable charts; flat ODT sub-documents no longer end the body); previously trivial (ODT leading read as an at-least spacing); previously trivial (ODT tracked formatting changes; changed regions named by `xml:id`); previously trivial (ODT drop caps; tab stops no longer drop a paragraph's background); previously trivial (flat ODT `.fodt` opened and saved; ODT fidelity re-estimated at ~80%); previously trivial (ODT page settings; a footnote no longer takes a footer's text); previously trivial (ODT dates in their formats, sequences, chapters and references); previously trivial (ODT bookmarks over text); previously trivial (ODT tables of contents and indexes; ODT fidelity re-estimated); previously trivial (ODT polygons, polylines and paths); previously trivial (ODT arrowheads, dashes and gradients); previously trivial (ODT groups of shapes and pictures); previously trivial (ODT rotated and mirrored shapes and pictures); previously trivial (ODT drawing shapes read and written); previously trivial (ODT text box frames keep their line, fill, padding and fit); previously trivial (ODT Asian and complex-script fonts); previously trivial (ODT right-to-left paragraphs); previously trivial (ODT text boxes kept); previously trivial (ODT unnumbered headings detached from the outline); previously trivial (ODT contextual spacing and layout settings); previously trivial (ODT custom character styles kept); previously trivial (ODT list level positions); previously trivial (ODT custom paragraph styles kept); previously trivial (ODT equations written as formula objects); previously trivial (ODT numbered headings written as headings); previously trivial (ODT floating pictures); previously trivial (ODT paragraph borders and background); previously trivial (ODT heading numbering); previously trivial (ODT font-face names); previously trivial (ODT table cell borders and padding); previously trivial (ODT heading, title, quote and preformatted styles keep their look); previously trivial (ODT tab stops read and written); previously trivial (ODT character formatting read and written); previously trivial (ODT lists keep their number formats, bullets and identity); previously trivial (ODT comments read and written); previously trivial (ODT footnotes and endnotes read and written); previously trivial (ODT headers, footers and text fields written; fields read); previously trivial (ODT paragraph spacing, indents and line spacing read and written); previously trivial (a paragraph naming an undefined style is formatted as Normal, as in Word, #5077); previously trivial (a hyperlinked TOC writes its page numbers as `PAGEREF _Toc… \h` fields, as Word does, #5097); previously trivial (HTML import ends the empty comments and at once, #5040); previously trivial (chart and SmartArt text the font lacks is drawn in a fallback face, so Chinese labels no longer show boxes, #4720); previously trivial (bibliography sources keep a corporate author (`b:Corporate`): read, written, cited and listed whole, #4848); previously trivial (custom-property bookmark-link preservation, #4767); previously trivial (note conversion preserves content with an ordered reference/run walk, #4750); previously trivial (DOCX comment-ID save lookups); previously trivial (built-in heading styles have their outline level without `w:outlineLvl`, #4696); previously trivial (DOCX comment ranges inside footnotes and endnotes are kept on read, #4548); previously trivial (RTF import and export keep Windows and Enhanced Metafile pictures (`\wmetafile`, `\emfblip`), #4259); previously trivial (#4658 bounds nested Markdown reference-label work); previously trivial (HTML import keeps preformatted lines with CR or CRLF input newlines, #4810); previously trivial (DOCX parts stored under another casing keep their embedded fonts through a save, and a private save of a kept glossary escapes the attribute values it rewrites; previously trivial: the `.doc` reader logs what its copy budget leaves out, once a kind per document; importers bound hostile expansion: font names, links, ODS repeats, LaTeX wrappers, Markdown delimiters, #3692/#3713; previously trivial: repeated DOCX style IDs: save/reopen regression; previously trivial: Markdown code spans keep line-broken text literal, #3738; previously trivial: Arabic list labels: `arabicAlpha` and `arabicAbjad` draw the 28 Arabic letters (alphabetical and abjad order), doubling past the last letter; Hebrew, Hindi, Thai and Vietnamese still show decimal (`doc::section::tests::arabic_letters_count_in_both_orders`); previously trivial: localized TOC style ids read as the TOC styles, and a TOC in columns keeps its layout through Update Table, #3889; previously trivial: cu20we: outline caps; previously trivial: a relationship the markup names without the prefix is read as it wrote: an unqualified `id` on an element that carries a relationship names that relationship, and the writer keeps the attribute with the id the new package holds the part under; an ordinary `id` — a VML shape's, a drawing's — names no part; previously trivial: the reader takes the relationship ids the markup refers to from the relationship attributes of the main document it has already parsed, so a document with many relationships opens in the time its part takes, #3411; previously trivial: a table cell span from a `.json` file stays within 63 columns through Insert Column and Merge Cells, #3637; previously trivial: the file commands that change the document are checked on a protected document, the protection of a protected document needs an explicit stop, the session author can't change through `file.setAuthor` under protection (the CLI's `--author` uses the same protection check), and the post-check compares the settings and the metadata; previously trivial: a document with many content controls saves in the time the controls take, #13; previously trivial: `majorBidi`/`minorBidi` theme fonts follow the settings' theme font language, as measured in Word; previously trivial: Word signature lines are kept on save, still signable; previously trivial: Times New Roman keeps Liberation Serif under the roman-font rule; previously trivial: shape gradients and transparency, #1500; previously trivial: a folder that keeps no Unix modes, such as a NAS share mounted by GVFS, still takes a save, #3003; previously trivial: a text frame in the paragraph defaults frames nothing, #2360; previously trivial: table style band sizes written, a style without them unbanded as in Word, #3415; previously trivial: HTML export writes ruby (furigana, phonetic guides) and HTML import reads it back, #1681; previously trivial: RTF import decodes the East Asian multibyte code pages, #1653; previously trivial: PDF export: lam-alef drawn as two glyphs at one x extracts in reading order, #2310; previously trivial: native .json stores pictures and kept parts as base64, #586 follow-up; previously trivial: ODT headers and footers read from each master page, #863; previously trivial: RTF import compares heading and code formatting with the file's stylesheet; previously trivial: text typed into a content control takes the control's formatting; localized placeholder styles recognised; previously trivial: forms protection keeps its content controls: no inserting, Properties or Remove Content Control; previously trivial: Word XML and web pages saved as `.doc` open by what they hold, #2853; previously trivial: a VML shape in a header cell is always placed on the page, user-checked in Word for Mac, #1775; previously trivial: `w:sym` characters keep their symbol font when the text's font changes and are written back as `w:sym`, #2036; previously trivial: RTF export writes sections (gap 19); previously trivial: ODT export writes sections (gap 19); previously trivial: two lines in one and horizontal in vertical (`w:eastAsianLayout`) kept on save; previously trivial: PDF outline targets follow leading page breaks; previously trivial: positional tabs `w:ptab` read and kept on save, #2367; previously trivial: DOCX: mixed right-to-left runs split and marked `w:rtl` with their language, #1543; previously trivial: `w:doNotTrackMoves` round-trips and turns move tracking off; previously trivial: legacy outline, shadow, emboss and imprint text effects drawn, #2534; previously trivial: DOCX glossary documents (building blocks) read, kept and written; previously trivial: cached field results keep their visible run formatting; previously trivial: cached REF results retain hyperlink destinations; previously trivial: CLI conversions can explicitly refresh fields; previously trivial: a copied equation also goes in the clipboard's MathML formats, #1297; previously trivial: a pasted HTML `
` is an indented paragraph, not the Quote style, #1270); previously trivial: every table style part round-trips, #714; previously trivial: VML freeforms read and kept on save; previously trivial: multi-paragraph field instructions no longer add blank lines; previously trivial: `flowChartOr` draws its circle and cross spokes, as in Word; previously trivial: RTF: Mac OS Roman and DOS text, #1653; previously trivial: VML text boxes keep their internal margins, fit to their text and vertical alignment; hidden drawings not shown; previously trivial: PDF export draws horizontal and vertical lines inside groups, #1474; previously trivial: symbol-font text exported as Unicode, #776; previously trivial: text-box margins, Resize shape to fit text and freeforms in groups, #743; previously trivial: formatted paste from the system clipboard's HTML and RTF, #687; previously trivial: independent complex-script formatting inheritance and round-trip regression tests; previously trivial: import/export fixes for TXT, RTF, ODT, HTML and LaTeX, #433–#440; previously major: first version; every format Word reads or writes, measured from the readers and writers on origin/main) · **Target:** Microsoft Word (Microsoft 365) for Mac 16.113.4, plus Word for Windows' extra formats Every format Word opens or saves, what WordCraft does with it, and how it's tested. Fidelity is the share of a typical real-world file's content and formatting that survives (read: shows correctly; @@ -57,7 +57,7 @@ Weights are the share of a Word user's file traffic (estimate). Read/write: ✅ | PDF export | 8% | W | — | ✅ | ~80% | 6–10 | `crates/pdf/src/tests.rs` | krilla: embedded subsets, selectable text incl. field results (#133); Hebrew and Arabic copy and search as whole words (right-to-left glyphs written in visual order, #1383, also with fonts that draw lam-alef as two glyphs at one x, #2310); All Caps and Small Caps text extracts as the capitals shown, as from Word's PDFs, and never changes the case of other text (#1473), links, outline, tagging. Outline destinations follow leading page breaks to the heading text. Fonts it can't subset become outlines (#132). Print Markup (#589): comments in balloons beside each page (scaled to its paper) and tracked changes; HTML/Markdown/text copies end with a comment list. Horizontal and vertical lines inside groups are drawn (#1474). No PDF/A option, no "best for printing/online" choice | | PDF open (PDF Reflow, Word for Windows) | 1% | R | ❌ | — | 0% | 30–50 | — | Converting a PDF into an editable document. A sibling app (PdfCraft) may supply the parser | | `.rtf` Rich Text Format | 3% | R/W | 🟡 | 🟡 | ~50% | 10–15 | `crates/formats/src/tests.rs` | ~1,500 lines: text, character/paragraph formatting, styles, lists, tables, pictures (`\shppict`, #154; Windows and Enhanced Metafiles, `\wmetafile` and `\emfblip`, read and written, #4259), fields, bookmarks. 8-bit text in the document's code page (`\ansicpg`) or the current font's (`\fcharset`, `\cpg`): Cyrillic, Central European, Greek, Turkish, Hebrew, Arabic, Baltic, Vietnamese, Thai (was Windows-1252 only), Mac OS Roman (`\mac`, `\fcharset77`) and DOS code pages (`\pc` 437, `\pca` 850, `\cpg` 437/737/850/852/857/866, `\fcharset254`) (#1653). East Asian multibyte code pages decoded as runs: 932 Shift-JIS (`\fcharset128`, Japanese), 936 GBK (134, Simplified Chinese), 949 UHC/windows-949 (129, Korean) and 950 Big5 (136, Traditional Chinese) through `\ansicpg`, `\cpg` or the font's charset, escaped or raw, a lead byte and its trail byte together; invalid sequences read as U+FFFD, and a run that starts `EF BB BF` is text, not a BOM (#1653). Pasted from the system clipboard where the platform offers it (Windows, Wayland) when there is no HTML (#687). Tracked insertions and deletions read and written (`\revtbl`, `\revised`/`\deleted`, authors, `\revdttm` dates), so Accept/Reject All work after opening or a round trip; tracked paragraph marks (`\par` inside `\revised`/`\deleted` groups, including a `\sect` inside a deletion) and character and paragraph formatting revisions (`\crauth`/`\crdate` with `\oldcprops`, `\prauth`/`\prdate` with `\oldpprops`) read and written; section and table formatting revisions (`\oldsprops`, `\oldtprops`) not yet. Sections on import (#1378): each `\sect` ends a section with its own page size and orientation, margins, header/footer distance, columns, break type, page-number restart, start and format, title page and headers/footers (those it leaves out link to the previous); export writes every section too (break type, page size and orientation, margins, header/footer distance, columns, page numbering, title page; not headers/footers). Thin: comments, notes, RTL | -| `.odt` OpenDocument Text (and flat `.fodt`) | 2% | R/W | 🟡 | 🟡 | ~82% | 30–50 | `crates/formats/src/tests.rs`, `crates/formats/src/odt/tests.rs` and one file per feature in `crates/formats/src/odt/tests_more/`, `crates/engine/tests/it/odt_sections.rs`, `odt_toc.rs`, `odt_fields.rs`, `odt_charts.rs`, `odt_objects.rs`, `odt_password.rs`, `odt_forms.rs`; checked against LibreOffice's own documents (round trips compared page by page) and the ODF 1.3 schema | How text flows: a page break after a paragraph (`fo:break-after`, a page break before the next paragraph as Word has it), lines kept together (`fo:keep-together`), widow and orphan control (`fo:widows`/`fo:orphans`: on with any line count, off with none; the counts themselves aren't kept) and hyphenation (`fo:hyphenate`, a paragraph's in ODF and the document's in WordCraft: a document with a hyphenated paragraph hyphenates, its other paragraphs opting out) are read and written; a table's alignment and width (`table:align`, `style:rel-width`, or `style:width` for an aligned table) and its rows' heights (`style:row-height` exact, `style:min-row-height` at least) are read and written. Form controls (`office:forms` controls placed by `draw:control`, ODF 1.3 §13) open as content controls — text fields and text areas as plain text controls, check boxes as check boxes, radio buttons as check boxes with round symbols, list boxes as drop-down lists, combo boxes as combo boxes, date fields as date controls, each with its value, entries and selection, its name as the control's tag and a label as its title — and content controls of those kinds in the body are written back as form controls LibreOffice shows with their values (in headers and footers, as their text); buttons, images, hidden and other controls aren't read, and a control's size and look aren't kept. Password-protected ODT (ODF 1.3 Part 2 §3.4) opens with its password — AES-256-CBC with a SHA-256 or SHA-1 start key and PBKDF2, as LibreOffice writes it; the old Blowfish encryption is refused with a message saying so — and a document opened with a password, or saved with one (Save with password), is written encrypted the way LibreOffice encrypts (every file but the `mimetype` and manifest; each with its own salt and initialisation vector; SHA-256 checksums), which LibreOffice opens with the password. Flat OpenDocument text (`.fodt`: the whole document in one `office:document`, pictures inline as base64 `office:binary-data`, formulas inline) is opened and saved as a package is, both validating against the schema. Tables of contents and other indexes (`text:table-of-content`, `text:illustration-index`/`text:table-index`, `text:alphabetical-index`, `text:bibliography`) open as Word's `TOC` (levels from the source's `text:outline-level`; `\c` with the caption name for a table of figures), `INDEX` and `BIBLIOGRAPHY` fields — in the title paragraph when the index has one, as WordCraft inserts a table, else around the entries — so References › Update Table regenerates them; LibreOffice's Contents 1–10, Contents Heading and Figure Index 1 styles are WordCraft's TOC 1–9, TOC Heading and Table of Figures; WordCraft's tables are written back as ODF indexes with their source and entry templates (LibreOffice updates them), entries' links in the Index Link style; user and object indexes are read as their paragraphs; index marks (`text:alphabetical-index-mark`, Word's `XE`) are not read. Custom character styles (a common text style other than LibreOffice's link, note-mark and list-label styles kept as a character style with its name, parent and own formatting, its text in it; written back as common text styles), custom paragraph styles (a common style other than Standard, the kinds' and the note texts' kept as a document style with its name, parent and own formatting, its paragraphs in it rather than given its formatting directly; written back as common styles, named so LibreOffice keeps them), paragraph borders (each side's line and padding) and background, heading numbering (`text:outline-style`: each level's format, prefix, suffix, levels shown and start number the headings through their styles, as Word's numbered headings, and are written back), styles (the file's own Heading 1–6, Title, Quotations and Preformatted Text definitions give those styles' look on open — font, size, percent sizes included, bold, colour, spacing, alignment, keep with next — and saving writes the document's own style definitions rather than fixed ones), tab stops (left, centre, right, decimal; dot, hyphen, underline and middle-dot leaders; LibreOffice's indent-relative positions converted, and a `settings.xml` written saying positions run from the margin) and the default tab interval, character formatting (underline styles and colour, double strike, caps, small caps, hidden text kept hidden, letter spacing, scale, raised and lowered text, outline, shadow, emboss, engrave, language, Asian and complex-script fonts, complex-script size, weight and posture and both script languages (per run and as document defaults), a monospaced font by its own name, a `style:font-name` read as the family its `style:font-face` declares, and the default style's pair kerning) both ways, lists (#87; each `text:list` a list of its own unless it continues one by `text:continue-numbering` or `text:continue-list`, an item's `text:start-value` restarting from it; each level's number format — 1, i, I, a, A, none —, prefix, suffix, levels shown, start value, bullet character, indent, hanging and number alignment read from its list style and written back), floating pictures (a frame anchored to a paragraph, character or page: wrap — square on both sides, left, right or the larger side, top and bottom, behind or in front of text —, horizontal and vertical alignment or offset and what it is relative to, distances from the text, read into the picture's placement and written back in a graphic style), tables (cell borders — width, style, colour, an edge LibreOffice gives one cell shared by both — and cell padding read and written, each shared edge written once so lines don't double, a table without lines written without), pictures, page breaks (#86), paragraph spacing, indents and line spacing (proportional, fixed, at least; leading read as an at-least spacing of a 12 pt line and the leading, which puts the extra space above each line as LibreOffice draws it, and as that much more space after the paragraph, where LibreOffice leaves it after the last line) both ways, with the default and Standard styles' spacing as the document defaults (ODT's are none, not Word's 8 pt after and 1.15 lines), headers and footers of each master page (every, left and first page) read on open and written on save, with the header and footer distances converted between Word's page-edge measures and ODF's header bands (#863), text fields (page number and count, date, time, title, subject, author, file name, word and character counts, bookmark references as `REF`/`PAGEREF`, to bookmarks kept over the text they mark — `text:bookmark-start`…`-end`, in a paragraph or across several — so a reference updates to that text) read as fields and written back as ODF fields; dates and times in their date style (`number:date-style`/`time-style` ↔ Word's `\@` picture, both ways), sequences numbering figures and tables (`text:sequence` ↔ `SEQ` with its number format, declared on save; a bookmark over the caption's label and number, which references to it show), chapter fields (`text:chapter` ↔ `STYLEREF "Heading n"`, by name or number), reference marks (as bookmarks) and references to them and to sequences (`text:reference-ref`, `text:sequence-ref` ↔ `REF`/`PAGEREF`); fixed dates and fields without a Word equivalent (variables — `text:variable-set`/`-get`, `text:user-field-get`; WordCraft has no document variables to update them from —, references to a caption's text) read as their text, and Word fields ODF lacks written as their result, keep with next (#2813), an embedded formula object (`draw:object`) is read from its own `content.xml`'s MathML, same as HTML (#3099); charts (a `draw:object` whose sub-document is an `office:chart`: column, bar, stacked, line, area, pie, doughnut and scatter charts; categories, series names and values — gaps included — from the chart's own table through their cell range addresses, title, legend position, data labels) open as WordCraft charts (in a drawing group too), drawn in the theme's colours and edited with Chart Design's commands, and every WordCraft chart is written back as an ODF chart object shaped like LibreOffice's (its data table, each series in its accent colour, slices clockwise from the top), in line or floating, inline in a flat document; a chart WordCraft can't edit as it is (3D, percent-stacked, stacked lines or areas, radar, stock or bubble charts, mixed plot types, a second value axis, one with no series) keeps its replacement picture, and fonts and axis scaling aren't kept; other embedded objects (`draw:object` sub-documents such as spreadsheets, drawings and presentations, and `draw:object-ole` OLE files) are kept whole — their files, media type and replacement picture — and saved back as the same objects, which LibreOffice opens as before; WordCraft shows one by its replacement picture, or, when that is in LibreOffice's own metafile format, by a placeholder of its size it draws itself (ruled for a spreadsheet), and doesn't edit or draw its contents; DOCX and other formats get the picture alone; in a flat document each object goes inline with its replacement picture — a sub-document as an `office:document` of its media type, its styles and settings with it, an OLE file as base64 — and is taken apart into its files again on opening; export writes each equation as a formula object of its own (MathML, with its linear text as an annotation), its frame sized from the equation's structure and centred on the line, so LibreOffice shows and edits it, page size, orientation and margins (#810), page number format (the page style's, and a page number field's own as `PAGE \* Arabic`/`roman`/…), page colour, page borders (ODF's at the margin with the text inside their padding ↔ WordCraft's measured from the page edge), footnote and endnote numbering (`text:notes-configuration`: format, first number, restart, page foot or document end) and line numbering (`text:linenumbering-configuration`, on unless it says otherwise: every how many lines, distance, restart on each page), sections: one per master-page change on a paragraph or table (next page, with its own page size, orientation, margins, columns and page-numbering restart) and per columned `text:section` (continuous, with its columns and separator line) (#1379); export writes them back: a master page and page layout per new-page section (size, orientation, margins, columns, page-numbering restart on the first paragraph or table), a `text:section` with its columns per continuous section whose columns differ from the page's (one column included), a list cut by a section break goes on numbering. Limits: a continuous section's page-numbering restart isn't written (ODF applies it only with a master page); a continuous section with the page's columns merges into the section before it on reopening; even and odd page starts are written as plain new pages; a tracked deletion of a section break is lost; an empty last section is dropped; tracked insertions and deletions with author and date, inserted and deleted paragraph marks and text inserted then deleted included (ODF change tracking; format changes (`text:format-change`) as formatting revisions with their author and date — ODF records no old formatting, so the old is the text's own — and WordCraft's formatting revisions written as format changes; regions named by `xml:id` as ODF 1.3 requires; pictures and tables inside a tracked deletion are dropped). footnotes and endnotes (`text:note`) read into note stories as Word's (Footnote Text style, the note's own mark first, a custom mark kept) and written back with their citations; notes inside notes and in deleted text left out; comments (`office:annotation` with `office:annotation-end` ranges, author, date, initials, LibreOffice's resolved state and reply threads, `loext:resolved`/`loext:parent-name`) read and written, a comment whose end never comes covering nothing; comments in notes and in deleted text left out; text boxes (`draw:text-box` in a frame) open as WordCraft text boxes with their text, in line or floating, and are written back, keeping the frame's line (colour and width), fill, padding (through the frame's graphic style and its parents, LibreOffice's Frame style included) and a frame without a height growing to its text (`fo:min-height`), which WordCraft lays out floating as well as in line. Right-to-left paragraphs (`style:writing-mode` `rl-tb`) read and written. Drop caps (`style:drop-cap`: lines and distance; WordCraft drops one letter, so a longer drop cap opens as its first letter) read and written. Drawing shapes (`draw:rect`, `draw:ellipse`, `draw:line`, and `draw:custom-shape` of a predefined geometry by its `draw:type`: rounded rectangle, triangles, diamond, the four block arrows, star, heart, flowchart or; LibreOffice's names and the `ooxml-` preset names) open as WordCraft shapes with their size, placement (in line or floating, as frames are), fill, line (colour and width; LibreOffice's default blue line and fill where the styles say nothing), text and a line's direction, and are written back, a custom shape by its type alone, which LibreOffice rebuilds the geometry from; a geometry WordCraft has no shape for opens as a rectangle; shapes and pictures turned by `draw:transform` (rotate, translate and scale; anticlockwise about the corner in the file, clockwise about the centre in WordCraft) and custom shapes mirrored (`draw:mirror-horizontal`/`-vertical`) keep their turn and mirroring both ways, in line or floating, a turned line by its turned ends; groups (`draw:g`) of shapes, text boxes and pictures open as one WordCraft group anchored and wrapped as the group is, its members placed (and turned) as they are in it, groups in it flattened into it, and are written back as a group; a frame, shape or group whose styles state no wrap has text on both sides, as LibreOffice wraps it (§20.400 states no default), and `biggest` wraps on the larger side; arrowheads (`draw:marker-start`/`-end`, written with WordCraft's own triangle marker), dashes (`draw:stroke-dash`: up to two kinds of dash and a space, in line widths or lengths, matched to WordCraft's named dashes; a pattern with more kinds is written as its first two) and gradient fills (`draw:gradient`: linear and axial along their angle, radial, ellipsoid, square and rectangular out from their centre, border and intensity; more than two colours written as the first and last) are read and written, a line's direction (and so its arrowheads' ends) kept from its two ends; polygons, polylines, paths (SVG path data: moves, lines, cubic and quadratic curves, smooth ones and elliptical arcs, absolute and relative, curves followed in short straight steps) and regular polygons (stars too) open as WordCraft freeforms in their view box, circles as ellipses, and freeforms (ink too) are written as `draw:path`; connectors, captions and measures are left out, a custom shape whose type WordCraft has no shape for opens as a rectangle; an in-line frame or shape stands on the baseline, is centred on it or hangs from it as its `style:vertical-pos` relative to the baseline says (`top`, `middle`, `bottom`, or its top `svg:y` from it with `from-top`), read as its run's raise or lowering (Word's `w:position`, which WordCraft now applies to in-line pictures and shapes too) and written back as `from-top`; placement relative to the character or line stays on the baseline; a text box's frame derives from LibreOffice's Frame style, so LibreOffice draws its border | +| `.odt` OpenDocument Text (and flat `.fodt`) | 2% | R/W | 🟡 | 🟡 | ~82% | 30–50 | `crates/formats/src/tests.rs`, `crates/formats/src/odt/tests.rs` and one file per feature in `crates/formats/src/odt/tests_more/`, `crates/engine/tests/it/odt_sections.rs`, `odt_toc.rs`, `odt_fields.rs`, `odt_charts.rs`, `odt_objects.rs`, `odt_password.rs`, `odt_forms.rs`; checked against LibreOffice's own documents (round trips compared page by page) and the ODF 1.3 schema | Ruby (`text:ruby`, §6.4: a base text with ruby text over it) is read as WordCraft's Phonetic Guide and written back as ODF ruby above its base, centred (one inside a tracked change is written as its base text, which the change marks); its own position and alignment aren't kept. Emphasis marks (`style:text-emphasize`), character borders (LibreOffice's `loext:border`) and rotated text (`style:text-rotation-angle`) aren't read. How text flows: a page break after a paragraph (`fo:break-after`, a page break before the next paragraph as Word has it), lines kept together (`fo:keep-together`), widow and orphan control (`fo:widows`/`fo:orphans`: on with any line count, off with none; the counts themselves aren't kept) and hyphenation (`fo:hyphenate`, a paragraph's in ODF and the document's in WordCraft: a document with a hyphenated paragraph hyphenates, its other paragraphs opting out) are read and written; a table's alignment and width (`table:align`, `style:rel-width`, or `style:width` for an aligned table) and its rows' heights (`style:row-height` exact, `style:min-row-height` at least) are read and written. Form controls (`office:forms` controls placed by `draw:control`, ODF 1.3 §13) open as content controls — text fields and text areas as plain text controls, check boxes as check boxes, radio buttons as check boxes with round symbols, list boxes as drop-down lists, combo boxes as combo boxes, date fields as date controls, each with its value, entries and selection, its name as the control's tag and a label as its title — and content controls of those kinds in the body are written back as form controls LibreOffice shows with their values (in headers and footers, as their text); buttons, images, hidden and other controls aren't read, and a control's size and look aren't kept. Password-protected ODT (ODF 1.3 Part 2 §3.4) opens with its password — AES-256-CBC with a SHA-256 or SHA-1 start key and PBKDF2, as LibreOffice writes it; the old Blowfish encryption is refused with a message saying so — and a document opened with a password, or saved with one (Save with password), is written encrypted the way LibreOffice encrypts (every file but the `mimetype` and manifest; each with its own salt and initialisation vector; SHA-256 checksums), which LibreOffice opens with the password. Flat OpenDocument text (`.fodt`: the whole document in one `office:document`, pictures inline as base64 `office:binary-data`, formulas inline) is opened and saved as a package is, both validating against the schema. Tables of contents and other indexes (`text:table-of-content`, `text:illustration-index`/`text:table-index`, `text:alphabetical-index`, `text:bibliography`) open as Word's `TOC` (levels from the source's `text:outline-level`; `\c` with the caption name for a table of figures), `INDEX` and `BIBLIOGRAPHY` fields — in the title paragraph when the index has one, as WordCraft inserts a table, else around the entries — so References › Update Table regenerates them; LibreOffice's Contents 1–10, Contents Heading and Figure Index 1 styles are WordCraft's TOC 1–9, TOC Heading and Table of Figures; WordCraft's tables are written back as ODF indexes with their source and entry templates (LibreOffice updates them), entries' links in the Index Link style; user and object indexes are read as their paragraphs; index marks (`text:alphabetical-index-mark`, Word's `XE`) are not read. Custom character styles (a common text style other than LibreOffice's link, note-mark and list-label styles kept as a character style with its name, parent and own formatting, its text in it; written back as common text styles), custom paragraph styles (a common style other than Standard, the kinds' and the note texts' kept as a document style with its name, parent and own formatting, its paragraphs in it rather than given its formatting directly; written back as common styles, named so LibreOffice keeps them), paragraph borders (each side's line and padding) and background, heading numbering (`text:outline-style`: each level's format, prefix, suffix, levels shown and start number the headings through their styles, as Word's numbered headings, and are written back), styles (the file's own Heading 1–6, Title, Quotations and Preformatted Text definitions give those styles' look on open — font, size, percent sizes included, bold, colour, spacing, alignment, keep with next — and saving writes the document's own style definitions rather than fixed ones), tab stops (left, centre, right, decimal; dot, hyphen, underline and middle-dot leaders; LibreOffice's indent-relative positions converted, and a `settings.xml` written saying positions run from the margin) and the default tab interval, character formatting (underline styles and colour, double strike, caps, small caps, hidden text kept hidden, letter spacing, scale, raised and lowered text, outline, shadow, emboss, engrave, language, Asian and complex-script fonts, complex-script size, weight and posture and both script languages (per run and as document defaults), a monospaced font by its own name, a `style:font-name` read as the family its `style:font-face` declares, and the default style's pair kerning) both ways, lists (#87; each `text:list` a list of its own unless it continues one by `text:continue-numbering` or `text:continue-list`, an item's `text:start-value` restarting from it; each level's number format — 1, i, I, a, A, none —, prefix, suffix, levels shown, start value, bullet character, indent, hanging and number alignment read from its list style and written back), floating pictures (a frame anchored to a paragraph, character or page: wrap — square on both sides, left, right or the larger side, top and bottom, behind or in front of text —, horizontal and vertical alignment or offset and what it is relative to, distances from the text, read into the picture's placement and written back in a graphic style), tables (cell borders — width, style, colour, an edge LibreOffice gives one cell shared by both — and cell padding read and written, each shared edge written once so lines don't double, a table without lines written without), pictures, page breaks (#86), paragraph spacing, indents and line spacing (proportional, fixed, at least; leading read as an at-least spacing of a 12 pt line and the leading, which puts the extra space above each line as LibreOffice draws it, and as that much more space after the paragraph, where LibreOffice leaves it after the last line) both ways, with the default and Standard styles' spacing as the document defaults (ODT's are none, not Word's 8 pt after and 1.15 lines), headers and footers of each master page (every, left and first page) read on open and written on save, with the header and footer distances converted between Word's page-edge measures and ODF's header bands (#863), text fields (page number and count, date, time, title, subject, author, file name, word and character counts, bookmark references as `REF`/`PAGEREF`, to bookmarks kept over the text they mark — `text:bookmark-start`…`-end`, in a paragraph or across several — so a reference updates to that text) read as fields and written back as ODF fields; dates and times in their date style (`number:date-style`/`time-style` ↔ Word's `\@` picture, both ways), sequences numbering figures and tables (`text:sequence` ↔ `SEQ` with its number format, declared on save; a bookmark over the caption's label and number, which references to it show), chapter fields (`text:chapter` ↔ `STYLEREF "Heading n"`, by name or number), reference marks (as bookmarks) and references to them and to sequences (`text:reference-ref`, `text:sequence-ref` ↔ `REF`/`PAGEREF`); fixed dates and fields without a Word equivalent (variables — `text:variable-set`/`-get`, `text:user-field-get`; WordCraft has no document variables to update them from —, references to a caption's text) read as their text, and Word fields ODF lacks written as their result, keep with next (#2813), an embedded formula object (`draw:object`) is read from its own `content.xml`'s MathML, same as HTML (#3099); charts (a `draw:object` whose sub-document is an `office:chart`: column, bar, stacked, line, area, pie, doughnut and scatter charts; categories, series names and values — gaps included — from the chart's own table through their cell range addresses, title, legend position, data labels) open as WordCraft charts (in a drawing group too), drawn in the theme's colours and edited with Chart Design's commands, and every WordCraft chart is written back as an ODF chart object shaped like LibreOffice's (its data table, each series in its accent colour, slices clockwise from the top), in line or floating, inline in a flat document; a chart WordCraft can't edit as it is (3D, percent-stacked, stacked lines or areas, radar, stock or bubble charts, mixed plot types, a second value axis, one with no series) keeps its replacement picture, and fonts and axis scaling aren't kept; other embedded objects (`draw:object` sub-documents such as spreadsheets, drawings and presentations, and `draw:object-ole` OLE files) are kept whole — their files, media type and replacement picture — and saved back as the same objects, which LibreOffice opens as before; WordCraft shows one by its replacement picture, or, when that is in LibreOffice's own metafile format, by a placeholder of its size it draws itself (ruled for a spreadsheet), and doesn't edit or draw its contents; DOCX and other formats get the picture alone; in a flat document each object goes inline with its replacement picture — a sub-document as an `office:document` of its media type, its styles and settings with it, an OLE file as base64 — and is taken apart into its files again on opening; export writes each equation as a formula object of its own (MathML, with its linear text as an annotation), its frame sized from the equation's structure and centred on the line, so LibreOffice shows and edits it, page size, orientation and margins (#810), page number format (the page style's, and a page number field's own as `PAGE \* Arabic`/`roman`/…), page colour, page borders (ODF's at the margin with the text inside their padding ↔ WordCraft's measured from the page edge), footnote and endnote numbering (`text:notes-configuration`: format, first number, restart, page foot or document end) and line numbering (`text:linenumbering-configuration`, on unless it says otherwise: every how many lines, distance, restart on each page), sections: one per master-page change on a paragraph or table (next page, with its own page size, orientation, margins, columns and page-numbering restart) and per columned `text:section` (continuous, with its columns and separator line) (#1379); export writes them back: a master page and page layout per new-page section (size, orientation, margins, columns, page-numbering restart on the first paragraph or table), a `text:section` with its columns per continuous section whose columns differ from the page's (one column included), a list cut by a section break goes on numbering. Limits: a continuous section's page-numbering restart isn't written (ODF applies it only with a master page); a continuous section with the page's columns merges into the section before it on reopening; even and odd page starts are written as plain new pages; a tracked deletion of a section break is lost; an empty last section is dropped; tracked insertions and deletions with author and date, inserted and deleted paragraph marks and text inserted then deleted included (ODF change tracking; format changes (`text:format-change`) as formatting revisions with their author and date — ODF records no old formatting, so the old is the text's own — and WordCraft's formatting revisions written as format changes; regions named by `xml:id` as ODF 1.3 requires; pictures and tables inside a tracked deletion are dropped). footnotes and endnotes (`text:note`) read into note stories as Word's (Footnote Text style, the note's own mark first, a custom mark kept) and written back with their citations; notes inside notes and in deleted text left out; comments (`office:annotation` with `office:annotation-end` ranges, author, date, initials, LibreOffice's resolved state and reply threads, `loext:resolved`/`loext:parent-name`) read and written, a comment whose end never comes covering nothing; comments in notes and in deleted text left out; text boxes (`draw:text-box` in a frame) open as WordCraft text boxes with their text, in line or floating, and are written back, keeping the frame's line (colour and width), fill, padding (through the frame's graphic style and its parents, LibreOffice's Frame style included) and a frame without a height growing to its text (`fo:min-height`), which WordCraft lays out floating as well as in line. Right-to-left paragraphs (`style:writing-mode` `rl-tb`) read and written. Drop caps (`style:drop-cap`: lines and distance; WordCraft drops one letter, so a longer drop cap opens as its first letter) read and written. Drawing shapes (`draw:rect`, `draw:ellipse`, `draw:line`, and `draw:custom-shape` of a predefined geometry by its `draw:type`: rounded rectangle, triangles, diamond, the four block arrows, star, heart, flowchart or; LibreOffice's names and the `ooxml-` preset names) open as WordCraft shapes with their size, placement (in line or floating, as frames are), fill, line (colour and width; LibreOffice's default blue line and fill where the styles say nothing), text and a line's direction, and are written back, a custom shape by its type alone, which LibreOffice rebuilds the geometry from; a geometry WordCraft has no shape for opens as a rectangle; shapes and pictures turned by `draw:transform` (rotate, translate and scale; anticlockwise about the corner in the file, clockwise about the centre in WordCraft) and custom shapes mirrored (`draw:mirror-horizontal`/`-vertical`) keep their turn and mirroring both ways, in line or floating, a turned line by its turned ends; groups (`draw:g`) of shapes, text boxes and pictures open as one WordCraft group anchored and wrapped as the group is, its members placed (and turned) as they are in it, groups in it flattened into it, and are written back as a group; a frame, shape or group whose styles state no wrap has text on both sides, as LibreOffice wraps it (§20.400 states no default), and `biggest` wraps on the larger side; arrowheads (`draw:marker-start`/`-end`, written with WordCraft's own triangle marker), dashes (`draw:stroke-dash`: up to two kinds of dash and a space, in line widths or lengths, matched to WordCraft's named dashes; a pattern with more kinds is written as its first two) and gradient fills (`draw:gradient`: linear and axial along their angle, radial, ellipsoid, square and rectangular out from their centre, border and intensity; more than two colours written as the first and last) are read and written, a line's direction (and so its arrowheads' ends) kept from its two ends; polygons, polylines, paths (SVG path data: moves, lines, cubic and quadratic curves, smooth ones and elliptical arcs, absolute and relative, curves followed in short straight steps) and regular polygons (stars too) open as WordCraft freeforms in their view box, circles as ellipses, and freeforms (ink too) are written as `draw:path`; connectors, captions and measures are left out, a custom shape whose type WordCraft has no shape for opens as a rectangle; an in-line frame or shape stands on the baseline, is centred on it or hangs from it as its `style:vertical-pos` relative to the baseline says (`top`, `middle`, `bottom`, or its top `svg:y` from it with `from-top`), read as its run's raise or lowering (Word's `w:position`, which WordCraft now applies to in-line pictures and shapes too) and written back as `from-top`; placement relative to the character or line stays on the baseline; a text box's frame derives from LibreOffice's Frame style, so LibreOffice draws its border | | `.txt` Plain text | 2% | R/W | ✅ | ✅ | ~95% | 1–2 | unit tests | Encoding detection. Files with other extensions (`.m3u`/`.m3u8` playlists, logs, config files, no extension) open as text when they are text, Word and RTF files by their signature; binary files are refused (#569). A Word or RTF extension that contradicts the content also opens by signature, as in Word: RTF saved as `.doc` (hh.ru résumés, accounting exports), a `.docx` renamed `.doc`, a Word 97-2003 file renamed `.docx`; a Word XML Document (Word 2003 XML or Flat OPC) or a web page (``, ``) under a `.doc`, `.docx` or `.rtf` name opens as what it is (#2853, `tests::word_xml_and_web_pages_saved_as_doc_open_by_content`). Word's encoding choice dialog and line-ending options missing; such files save only through Save As | | `.htm/.html` Web Page and Web Page, Filtered | 1% | R/W | 🟡 | 🟡 | ~60% | 6–10 | `crates/formats/src/tests.rs` | Tables (#102), relative pictures embedded (#113), missing `` tolerated (#154); the empty comments `` and `` end at once instead of swallowing the rest of the page (#5040). Header cells (``) bold unless their CSS says otherwise; `text-align` on a cell, or inherited from its row, row group or table, aligns the cell's paragraphs (#1381). HTML gives no page size, so it opens on the region's paper (A4 or Letter), as Markdown and plain text do; `@page` isn't read (#1381). No Word "Web Page" (with `_files` folder) round-trip. The same reader takes HTML from the system clipboard: Paste keeps another program's formatting (a Word document, a web page; Windows' "HTML Format" header understood), Merge Formatting keeps its emphasis (#687). A pasted `
` (LibreOffice's paragraph indented on both sides) becomes a Normal paragraph indented by the page's `blockquote` margins, else 0.5 in each side; opening an .html file keeps it as the Quote style (#1270). Equations are written as MathML (with the linear format as a UnicodeMath annotation) and read back from MathML: our annotation, else the presentation elements, else a TeX annotation (#816). A copy of one equation alone also goes in the clipboard's MathML formats (Windows "MathML" and "MathML Presentation", macOS `public.mathml.presentation` and `public.mathml`; W3C MathML 3 §6.2.4), which Microsoft documents Word reading first when it pastes math (#1297; the paste into Word is not yet verified); Ruby (furigana, phonetic guides) is written as `basereading` in the base text's formatting and read back from ``/``/`` (`` fallback parentheses dropped; malformed markup keeps its text), so docx/doc → HTML → doc keeps the annotation; HTML states no alignment, size or raise, so the Phonetic Guide's defaults apply (#1681) CRLF and lone CR input newlines normalize before tokenization, preserving preformatted lines and leaving decoded character references separate (#4810). | | `.mht/.mhtml` Single File Web Page | <1% | R/W | ❌ | ❌ | 0% | 3–5 | — | | @@ -279,6 +279,7 @@ Custom document properties retain their bookmark link targets through DOCX saves | Date | Change | Summary | |---|---|---| +| 2026-11-01 | trivial | ODT: ruby (`text:ruby`) was read as its base and ruby text run together and written as plain text; it is read as a Phonetic Guide and written back as ODF ruby, which LibreOffice shows over its base (`odt::tests_more::ruby`) | | 2026-11-01 | trivial | ODT: a page break after a paragraph (lost, so a two-page document saved as one page), lines kept together, widow and orphan control, hyphenation (the document hyphenates when a paragraph does), a table's alignment and width and its rows' heights are read and written; a LibreOffice document with them round-trips at 573 px instead of 4 407 and keeps its pages (`odt::tests_more::flow_breaks`) | | 2026-11-01 | trivial | Layout: an in-line picture, shape or chart moves with its run's raise or lowering (Word's `w:position`), the line growing to hold it. ODT: an in-line frame centred on or hanging from the baseline keeps that place (read as that lowering, written back as `from-top`) instead of standing on the baseline; leading's extra space after the last line is kept; a text box's frame derives from the Frame style, without which LibreOffice ignored its border. LibreOffice round trips: shapes 13 864 → 1 273 px, spacing 2 973 → 706 px, text box 736 → 0 px (`layout::tests::an_inline_picture_moves_with_its_runs_position`, `odt::tests_more::floats::an_inline_frame_keeps_its_place_on_the_baseline`, `odt::tests_more::text_boxes::a_text_box_frame_derives_from_the_frame_style`) | | 2026-11-01 | trivial | ODT: form controls (`office:forms`, `draw:control`) — text fields, text areas, check boxes, radio buttons, list and combo boxes, date fields — were dropped with their values; they open as content controls (which save to DOCX as Word's) and are written back as form controls LibreOffice shows (`odt::tests_more::forms`, `odt_forms.rs`) |