Merge PR #3289: M15: fix Russian ё ordering and decomposed Cyrillic keys

ROADMAP.md: status line and revision history carry both sides.
docs/gaps.md, docs/localization-parity.md: status lines carry both sides.

crates/doc/src/collate.rs

@@ -150,6 +150,8 @@ const HU: &[Tailor] = &[
 const SV: &[Tailor] = &[t("å", 'z', 1), t("ä", 'z', 2), ts("æ", 'z', 2, 16), t("ö", 'z', 3), ts("ø", 'z', 3, 11)];
 const DA: &[Tailor] = &[t("æ", 'z', 1), ts("ä", 'z', 1, 4), t("ø", 'z', 2), ts("ö", 'z', 2, 4), t("å", 'z', 3)];
 const ES: &[Tailor] = &[t("ñ", 'n', 1)];
+// Russian ё shares е's primary weight; the diaeresis breaks ties (CLDR Russian standard).
+const RU: &[Tailor] = &[ts("ё", 'е', 0, 4)];
 const TR: &[Tailor] = &[t("ç", 'c', 1), t("ğ", 'g', 1), t("ı", 'h', 1), t("ö", 'o', 1), t("ş", 's', 1), t("ü", 'u', 1)];
 const HR: &[Tailor] =
     &[t("č", 'c', 1), t("ć", 'c', 2), t("dž", 'd', 1), t("đ", 'd', 2), t("lj", 'l', 1), t("nj", 'n', 1), t("š", 's', 1), t("ž", 'z', 1)];
@@ -184,6 +186,7 @@ fn tailoring(lang: Option<&str>) -> &'static [Tailor] {
         "sv" | "fi" => SV,
         "da" | "nb" | "nn" | "no" => DA,
         "es" | "gl" => ES,
+        "ru" => RU,
         "tr" | "az" => TR,
         "hr" | "bs" | "sr" => HR,
         "ro" => RO,
@@ -196,7 +199,7 @@ fn tailoring(lang: Option<&str>) -> &'static [Tailor] {
     }
 }
 
-/// A lowercase Latin letter followed by a combining mark, and the single letter Unicode
+/// A lowercase Latin or Russian letter followed by a combining mark, and the single letter Unicode
 /// composes them to (NFC; generated from the Unicode Character Database). Text pasted from
 /// decomposed sources (macOS file names: `z` + U+0307) collates like the composed letter.
 const COMPOSE: &[(char, char, char)] = &[
@@ -329,6 +332,8 @@ const COMPOSE: &[(char, char, char)] = &[
     ('z', '\u{302}', 'ẑ'),
     ('z', '\u{307}', 'ż'),
     ('z', '\u{30c}', 'ž'),
+    ('е', '\u{308}', 'ё'),
+    ('и', '\u{306}', 'й'),
 ];
 
 /// `s` lowercased, with each letter + combining mark that has a single-letter form composed.
@@ -476,6 +481,25 @@ mod tests {
         assert_eq!(sorted(&["Straße", "Strasse", "Strand"], "de"), ["Strand", "Strasse", "Straße"]);
     }
 
+    #[test]
+    fn russian_yo_sorts_with_e_instead_of_after_ya() {
+        for lang in ["ru", "ru-RU", "RU_ru"] {
+            assert_eq!(sorted(&["яблоко", "ёлка", "жук", "ель", "ёж", "еж"], lang), ["еж", "ёж", "ёлка", "ель", "жук", "яблоко"]);
+            assert_eq!(collate("ЁЛКА", "ёлка", Some(lang)), Ordering::Equal);
+            assert_eq!(heading_letter("Ёлка", Some(lang)).as_deref(), Some("Ё"));
+        }
+    }
+
+    #[test]
+    fn russian_decomposed_letters_match_their_composed_forms() {
+        for (composed, decomposed) in [("ёлка", "е\u{308}лка"), ("Ёлка", "Е\u{308}лка"), ("йод", "и\u{306}од"), ("Йод", "И\u{306}од")]
+        {
+            assert_eq!(collate(composed, decomposed, Some("ru-RU")), Ordering::Equal);
+            assert_eq!(heading_letter(composed, Some("ru")), heading_letter(decomposed, Some("ru")));
+        }
+        assert_eq!(sorted(&["к", "и\u{306}", "и"], "ru"), ["и", "и\u{306}", "к"]);
+    }
+
     #[test]
     fn spanish_n_tilde_after_n() {
         assert_eq!(sorted(&["oso", "ñu", "nube"], "es-ES"), ["nube", "ñu", "oso"]);

docs/gaps.md

@@ -1,6 +1,6 @@
 # Where WordCraft falls short of Word
 
-> **Last reviewed:** 2026-10-10 · **Last updated:** 2026-10-19 · **Change:** trivial (personal templates in File › New and Save as Word Template, #2852; previously trivial: #8: English dialects — en-GB, en-CA, en-AU… flag each other's spellings, #1281; previously trivial: #1: shape gradients and transparency, #1500; 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: clearing a no-match font query keeps the recent heading visible, #2068; previously trivial: line breaking: a slash opening a word travels whole to the next line, #2963; previously trivial: recipient list search and merged-only view, #1576; previously trivial: #2 impact restated: only ink rendering and OLE editing remain; previously trivial: #2 narrowed: native ink nested in groups and drawing canvases kept on save; previously trivial: opening a DOCX no longer copies its pictures; previously trivial: RTF export writes sections (gap 19); previously trivial: ODT export writes sections (gap 19); previously trivial: automatic Asian/Latin and Asian/number spacing laid out, #2358; previously trivial: hint-reliant CJK outlines; previously trivial: numbered headings, #1793; previously trivial: legacy outline, shadow, emboss and imprint text effects drawn, #2534; previously trivial: #8 narrowed: Indonesian proofing from the installed Hunspell dictionary, #498; previously trivial: glossary/building blocks closed; previously trivial: Split Cells and Convert Text to Table follow the Word check, #2592; previously trivial: Language dialog keeps inherited proofing language and no-proof choices (#2717); previously trivial: #29: a copied equation also goes in the MathML clipboard formats, #1297; previously trivial: #24: the Spike, Ctrl+F3 and Ctrl+Shift+F3; previously trivial: VML freeforms read and kept on save; previously trivial: consistent preferred cell widths; previously trivial: multi-paragraph field instructions no longer add blank lines; previously trivial: page-break-only list paragraphs hide their labels; previously trivial: floating-table overlap ignores empty line-break lines; previously trivial: copies keep their formatting on the clipboard as HTML, #1523; previously trivial: sample-text formulas on Enter, #1067; previously trivial: #29: copied equations as MathML, OMML open as #1297, #816; previously trivial: the Font list no longer keeps every previewed font in memory, #848; previously trivial: table column and row markers on the rulers, #700; previously trivial: table borders and the resize handle drag on the page, #217; previously trivial: formatting revisions landed, #41; previously trivial: Draw Table and Eraser landed, #303; previously minor: beta distance restated: ~15 points, ~150–230 h; previously: first version; every known shortfall from the 2026-10-10 re-measure, ranked) · **Target:** Microsoft Word (Microsoft 365) for Mac 16.113.4
+> **Last reviewed:** 2026-10-10 · **Last updated:** 2026-10-20 · **Change:** trivial (Russian sorting keeps ё with е and recognises decomposed ё/й; previously trivial: personal templates in File › New and Save as Word Template, #2852; previously trivial: #8: English dialects — en-GB, en-CA, en-AU… flag each other's spellings, #1281; previously trivial: #1: shape gradients and transparency, #1500; 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: clearing a no-match font query keeps the recent heading visible, #2068; previously trivial: line breaking: a slash opening a word travels whole to the next line, #2963; previously trivial: recipient list search and merged-only view, #1576; previously trivial: #2 impact restated: only ink rendering and OLE editing remain; previously trivial: #2 narrowed: native ink nested in groups and drawing canvases kept on save; previously trivial: opening a DOCX no longer copies its pictures; previously trivial: RTF export writes sections (gap 19); previously trivial: ODT export writes sections (gap 19); previously trivial: automatic Asian/Latin and Asian/number spacing laid out, #2358; previously trivial: hint-reliant CJK outlines; previously trivial: numbered headings, #1793; previously trivial: legacy outline, shadow, emboss and imprint text effects drawn, #2534; previously trivial: #8 narrowed: Indonesian proofing from the installed Hunspell dictionary, #498; previously trivial: glossary/building blocks closed; previously trivial: Split Cells and Convert Text to Table follow the Word check, #2592; previously trivial: Language dialog keeps inherited proofing language and no-proof choices (#2717); previously trivial: #29: a copied equation also goes in the MathML clipboard formats, #1297; previously trivial: #24: the Spike, Ctrl+F3 and Ctrl+Shift+F3; previously trivial: VML freeforms read and kept on save; previously trivial: consistent preferred cell widths; previously trivial: multi-paragraph field instructions no longer add blank lines; previously trivial: page-break-only list paragraphs hide their labels; previously trivial: floating-table overlap ignores empty line-break lines; previously trivial: copies keep their formatting on the clipboard as HTML, #1523; previously trivial: sample-text formulas on Enter, #1067; previously trivial: #29: copied equations as MathML, OMML open as #1297, #816; previously trivial: the Font list no longer keeps every previewed font in memory, #848; previously trivial: table column and row markers on the rulers, #700; previously trivial: table borders and the resize handle drag on the page, #217; previously trivial: formatting revisions landed, #41; previously trivial: Draw Table and Eraser landed, #303; previously minor: beta distance restated: ~15 points, ~150–230 h; previously: first version; every known shortfall from the 2026-10-10 re-measure, ranked) · **Target:** Microsoft Word (Microsoft 365) for Mac 16.113.4
 
 > **Printing update:** 2026-10-12 · direct desktop printing through craft-print; details below.
 
@@ -31,6 +31,8 @@ Legacy Word imports (#2445): interactive Save for `.doc`/`.dot` uses the existin
 
 Active footnote and endnote text stays readable while editing (#2545). This fixes a display-context defect; the broader fidelity, accessibility and readiness gates below are unchanged.
 
+Russian language-aware sorting now keeps ё with е instead of after я, with the diaeresis as a secondary difference. Composed and decomposed ё and й compare equally. Fixed synthetic collation tests cover order, case and index headings; this does not establish full Cyrillic or CLDR collation parity.
+
 ## Ranked
 
 | # | Gap | B | Evidence | Impact | Hours | Doc |
@@ -106,6 +108,7 @@ Footer page-table height and body wrapping are corrected. Other pagination gaps
 
 | Date | Change | Summary |
 |---|---|---|
+| 2026-10-20 | trivial | Russian sorting keeps ё with е and recognises decomposed ё/й; synthetic ordering, case and index-heading regressions; broader parity estimates unchanged |
 | 2026-10-19 | trivial | Restrict Editing: with Filling in forms enforced, inserting content controls, their Properties and Remove Content Control are refused, as in Word (it greys them out), so a form's fields stay as they are and only their content is filled in |
 | 2026-10-19 | trivial | Content controls: text typed over a placeholder takes the control's own run properties (`w:sdtPr/w:rPr`, ECMA-376 §17.5.2.27), as in Word, and the placeholder style is recognised by its built-in name "Placeholder Text" whatever its localized id (German Word: `Platzhaltertext`), so entries in forms from localized Word no longer stay grey |
 | 2026-10-18 | trivial | Font list starts at its first row after clearing a no-match query; recent heading remains visible (#2068) |

docs/localization-parity.md

@@ -1,6 +1,6 @@
 # Localization parity with Microsoft Word
 
-> **Last reviewed:** 2026-10-10 · **Last updated:** 2026-10-16 · **Change:** minor (English dialects: en-GB, en-CA, en-AU and the other British-spelling Englishes proof their own spellings and flag the other dialect's, #1281, #1045; previously minor: how to install the Hunspell dictionaries on Windows, macOS and Linux: `docs/spelling-dictionaries.md`; previously minor: Read Aloud speaks each sentence in its own language, #1843; previously minor: Indonesian proofing: id-ID spelling from the installed Hunspell dictionary, dictionary-driven suggestions, generic checks with Indonesian messages, #498; previously trivial: print-area strings translated in every catalog; previously trivial: Italian: the interface audit checks the Italian catalog, `Privacy Settings` wording; previously trivial: Italian grammar: `po'`, `qual è`, `È`, `un`/`un'` rules; more elisions and truncations in spelling; previously trivial: Czech interface catalog completed, 2,447 entries; previously trivial: interface audit runs in CI again: size labels translated, 20 strings in every catalog, Read Aloud error race fixed, #1128; previously trivial: Review › Language reaches every language again — Set Proofing Language… and Set As Default, #860; previously minor: Italian proofing: it-IT spelling from the installed Hunspell dictionary, accent-first suggestions, conservative grammar with Italian messages; previously minor: Portuguese proofing; previously trivial: Turkish interface catalog completed, 2,325 entries, #774; previously minor: Hungarian interface added; previously trivial: sorting and table numbers follow the text's language, #836, #837; previously minor: Polish interface; Polish proofing — spelling, grammar, hyphenation — and a proofing language per run; previously minor: Turkish interface added; previously major: first version; catalogs measured from `crates/ui-egui/src/i18n`, Word's languages from its bundle listing) · **Target:** Microsoft Word (Microsoft 365) for Mac 16.113.4
+> **Last reviewed:** 2026-10-10 · **Last updated:** 2026-10-20 · **Change:** trivial (Russian sorting keeps ё with е and recognises decomposed ё/й; previously minor: English dialects: en-GB, en-CA, en-AU and the other British-spelling Englishes proof their own spellings and flag the other dialect's, #1281, #1045; previously minor: how to install the Hunspell dictionaries on Windows, macOS and Linux: `docs/spelling-dictionaries.md`; previously minor: Read Aloud speaks each sentence in its own language, #1843; previously minor: Indonesian proofing: id-ID spelling from the installed Hunspell dictionary, dictionary-driven suggestions, generic checks with Indonesian messages, #498; previously trivial: print-area strings translated in every catalog; previously trivial: Italian: the interface audit checks the Italian catalog, `Privacy Settings` wording; previously trivial: Italian grammar: `po'`, `qual è`, `È`, `un`/`un'` rules; more elisions and truncations in spelling; previously trivial: Czech interface catalog completed, 2,447 entries; previously trivial: interface audit runs in CI again: size labels translated, 20 strings in every catalog, Read Aloud error race fixed, #1128; previously trivial: Review › Language reaches every language again — Set Proofing Language… and Set As Default, #860; previously minor: Italian proofing: it-IT spelling from the installed Hunspell dictionary, accent-first suggestions, conservative grammar with Italian messages; previously minor: Portuguese proofing; previously trivial: Turkish interface catalog completed, 2,325 entries, #774; previously minor: Hungarian interface added; previously trivial: sorting and table numbers follow the text's language, #836, #837; previously minor: Polish interface; Polish proofing — spelling, grammar, hyphenation — and a proofing language per run; previously minor: Turkish interface added; previously major: first version; catalogs measured from `crates/ui-egui/src/i18n`, Word's languages from its bundle listing) · **Target:** Microsoft Word (Microsoft 365) for Mac 16.113.4
 
 Interface languages, script support and proofing per language. How translation works (catalog
 format, adding a language, clean-room rule): `crates/ui-egui/src/i18n/mod.rs`.
@@ -151,6 +151,8 @@ Polish, `1.250,50` in German, `1,250.50` in English) and write formula results w
 separator (`crates/doc/src/locale_number.rs`). Interface lists (styles, fonts) still sort by code
 point.
 
+Russian (`ru`) sorting keeps ё with е (a secondary diaeresis difference), before ж. Composed and decomposed ё and й have the same keys and index headings; the stored text is unchanged. Tests cover Russian locale aliases, case, representative words and these two canonical pairs. This is a narrow Cyrillic correction, not full Unicode normalization or CLDR collation. Ordering reference: [Unicode CLDR Russian collation chart](https://unicode.org/cldr/charts/42/collation/ru.html).
+
 ## Region conventions (#838)
 
 As in Word, a new blank document takes its paper from the system **region**, not the interface
@@ -198,6 +200,7 @@ WordCraft keeps 2,54 cm).
 
 | Date | Change | Summary |
 |---|---|---|
+| 2026-10-20 | trivial | Russian sorting keeps ё with е and recognises decomposed ё/й; synthetic ordering, case and index-heading regressions; broader parity estimates unchanged |
 | 2026-10-14 | trivial | The sentence-capital rule (English, Polish, Croatian, Italian, Turkish, Portuguese) skips the first word of a list item (#1741) |
 | 2026-10-16 | minor | Indonesian proofing (#498): id-ID spelling from the installed Hunspell `id_ID` dictionary (not bundled), Czech's dictionary-driven suggestions, repeated-word (hyphenated reduplication offered) and spacing checks with Indonesian messages; Review › Language, the status bar, Set Proofing Language and File › Options › Proofing list Indonesian; estimates unchanged |
 | 2026-10-16 | trivial | Read Aloud picks a voice for the sentence's language (run tag, else script) when the default voice doesn't speak it, reads Windows text as UTF-8 |