polytypo 1.11.0 → 1.12.0

data/lib/polytypo/data/fixtures/hu.json

@@ -0,0 +1,264 @@
+{
+  "spec": "1.12.0",
+  "locale": "hu",
+  "cases": [
+    {
+      "id": "hu-quotes-primary",
+      "rule": "quotes",
+      "mode": "text",
+      "in": "Azt mondta: \"szia\" és elment.",
+      "out": "Azt mondta: „szia” és elment.",
+      "note": "AkH12 §240 j: the base form is „…” (U+201E, U+201D)."
+    },
+    {
+      "id": "hu-quotes-not-german",
+      "rule": "quotes",
+      "mode": "text",
+      "in": "„szia“",
+      "out": "„szia”",
+      "note": "U+201C as a closing mark is the German form; AkH12 §240 j closes with U+201D."
+    },
+    {
+      "id": "hu-quotes-nested",
+      "rule": "quotes",
+      "mode": "text",
+      "in": "\"Ő azt mondta 'jó' volt\"",
+      "out": "„Ő azt mondta »jó« volt”",
+      "note": "AkH12 §257: a quote inside a quote takes the lúdlábidézőjel »…« (opens with U+00BB, the reverse of ro)."
+    },
+    {
+      "id": "hu-quotes-nested-guillemets-kept",
+      "rule": "quotes",
+      "mode": "text",
+      "in": "„Ő azt mondta »jó« volt”",
+      "out": "„Ő azt mondta »jó« volt”",
+      "note": "Already typeset: both levels are left as they are."
+    },
+    {
+      "id": "hu-quotes-no-inner-space",
+      "rule": "quotes",
+      "mode": "text",
+      "in": "„ szia ”",
+      "out": "„szia”",
+      "note": "AkH12 §240 j: the marks attach to the words they enclose, no inner space."
+    },
+    {
+      "id": "hu-ellipsis-three-dots",
+      "rule": "ellipsis",
+      "mode": "text",
+      "in": "Várj... mi?",
+      "out": "Várj… mi?",
+      "note": "AkH12 §240 b: three dots, attached to the preceding word."
+    },
+    {
+      "id": "hu-ellipsis-not-abbreviated",
+      "rule": "ellipsis",
+      "mode": "text",
+      "in": "Tényleg?.. igen",
+      "out": "Tényleg?… igen",
+      "note": "abbreviatedAfterTerminal is false: `?..` is a typing slip, not an abbreviated ellipsis."
+    },
+    {
+      "id": "hu-dashes-parenthetical",
+      "rule": "dashes",
+      "mode": "text",
+      "in": "Holnap - ha esik - elmegyünk.",
+      "out": "Holnap – ha esik – elmegyünk.",
+      "note": "AkH12 §240 g, §252: en dash with a space on both sides."
+    },
+    {
+      "id": "hu-dashes-existing-em-dash",
+      "rule": "dashes",
+      "mode": "text",
+      "in": "Holnap — ha esik — elmegyünk.",
+      "out": "Holnap – ha esik – elmegyünk.",
+      "note": "An authored em dash becomes the locale's en dash."
+    },
+    {
+      "id": "hu-dashes-tight-compound-kept",
+      "rule": "dashes",
+      "mode": "text",
+      "in": "Budapest–Bécs és Osztrák–Magyar",
+      "out": "Budapest–Bécs és Osztrák–Magyar",
+      "note": "AkH12 §264 c: the tight en dash is already correct, no spaces are added."
+    },
+    {
+      "id": "hu-ranges-years-and-pages",
+      "rule": "ranges",
+      "mode": "text",
+      "in": "az 1983-1984. évi és az 1-4. osztályban",
+      "out": "az 1983⁠–⁠1984. évi és az 1⁠–⁠4. osztályban",
+      "note": "ranges.md §3: AkH12 §264 c attaches the en dash to its members (1983–1984. évi, az 1–4. osztályban); the word joiners are the spec's line-break guard.",
+      "rules": {
+        "ranges": true
+      }
+    },
+    {
+      "id": "hu-ranges-spaced-input-tightened",
+      "rule": "ranges",
+      "mode": "text",
+      "in": "1 - 4 oldal",
+      "out": "1⁠–⁠4 oldal",
+      "note": "ranges.md §3: en-tight takes the spaced form of a digit range to the tight one.",
+      "rules": {
+        "ranges": true
+      }
+    },
+    {
+      "id": "hu-ranges-en-dash-kept",
+      "rule": "ranges",
+      "mode": "text",
+      "in": "1914–1918 és Budapest–Bécs",
+      "out": "1914–1918 és Budapest–Bécs",
+      "note": "ranges.md §3: an authored tight en dash is the correct form and is kept.",
+      "rules": {
+        "ranges": true
+      }
+    },
+    {
+      "id": "hu-ranges-complex-spaced-kept",
+      "rule": "ranges",
+      "mode": "text",
+      "in": "2011. április 25. – 2012. május 13.",
+      "out": "2011. április 25. – 2012. május 13.",
+      "note": "ranges.md §3: AkH12 §264 c allows the spaced en dash for complex members; a '.' beside the space keeps it out of the range candidates.",
+      "rules": {
+        "ranges": true
+      }
+    },
+    {
+      "id": "hu-ranges-ordinal-shape-declined",
+      "rule": "ranges",
+      "mode": "text",
+      "in": "a 128-9. lapon",
+      "out": "a 128-9. lapon",
+      "note": "ranges.md §3.2: AkH12 §264 c prints «a 128–9. lapon», but the shape (3,1) is declined by G4, so a typed hyphen stays a hyphen. Accepted miss, as `2020-24` in en-US.",
+      "rules": {
+        "ranges": true
+      }
+    },
+    {
+      "id": "hu-ranges-word-hyphen-untouched",
+      "rule": "ranges",
+      "mode": "text",
+      "in": "Budapest-Bécs út",
+      "out": "Budapest-Bécs út",
+      "note": "ranges.md §3: words joined by a hyphen are not a digit range and are left alone.",
+      "rules": {
+        "ranges": true
+      }
+    },
+    {
+      "id": "hu-hyphen-noop",
+      "rule": "hyphen",
+      "mode": "text",
+      "in": "A MÁV-ot és a tűzzel-vassal",
+      "out": "A MÁV-ot és a tűzzel-vassal",
+      "note": "AkH12 §270 permits breaking at a hyphen; no list ships, nothing changes."
+    },
+    {
+      "id": "hu-nbsp-units",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "100 km, 1 kg, 10 kWh és 120 km/h",
+      "out": "100 km, 1 kg, 10 kWh és 120 km/h",
+      "note": "AkH12 §279 c: a space separates the unit from its number."
+    },
+    {
+      "id": "hu-nbsp-celsius",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "23 °C",
+      "out": "23 °C",
+      "note": "AkH12 §275: «23 °C» with a space."
+    },
+    {
+      "id": "hu-nbsp-percent-inert",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "48 % és 48%",
+      "out": "48 % és 48%",
+      "note": "AkH12 §275 prints 48% without a space, so % is not a unit here and nothing is bound."
+    },
+    {
+      "id": "hu-nbsp-single-letter-unit-inert",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "220 W és 5 s",
+      "out": "220 W és 5 s",
+      "note": "Single-letter symbols are excluded by decision, not by citation (AkH12 §279 c writes «220 W» with a space): `s` is a Hungarian conjunction."
+    },
+    {
+      "id": "hu-nbsp-forint-inert",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "2890 Ft",
+      "out": "2890 Ft",
+      "note": "Ft is attested only by example (§290) and ships unverified: nothing is bound."
+    },
+    {
+      "id": "hu-nbsp-abbreviations",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "Kr. e. 44-ben, Kr. u. 2. században, i. sz. 3. század",
+      "out": "Kr. e. 44-ben, Kr. u. 2. században, i. sz. 3. század",
+      "note": "AkH12 §277 a, §284: abbreviations written with an internal space; N4 binds it."
+    },
+    {
+      "id": "hu-nbsp-abbreviations-short",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "a. m. annyi mint, s. k. aláírás",
+      "out": "a. m. annyi mint, s. k. aláírás",
+      "note": "AkH12 §277 a: a. m. and s. k."
+    },
+    {
+      "id": "hu-nbsp-initials-unbound",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "Kossuth L. és L. Kossuth",
+      "out": "Kossuth L. és L. Kossuth",
+      "note": "initialBinding is none: AkH12 has no rule on initials."
+    },
+    {
+      "id": "hu-nbsp-no-space-before-question",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "Tényleg ? Igen !",
+      "out": "Tényleg? Igen!",
+      "note": "AkH12 §240 c: no space before ? and !, so nothing is put back."
+    },
+    {
+      "id": "hu-nbsp-paragraph-sign-inert",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "a 4. § szerint",
+      "out": "a 4. § szerint",
+      "note": "AkH12 §275 writes '4. §' with the number first; afterSymbols ships empty."
+    },
+    {
+      "id": "hu-spaces-brackets",
+      "rule": "spaces",
+      "mode": "text",
+      "in": "Szöveg ( rendes ) marad  .",
+      "out": "Szöveg (rendes) marad.",
+      "note": "spaces.md: brackets tighten, no space before the final stop."
+    },
+    {
+      "id": "hu-symbols-copyright",
+      "rule": "symbols",
+      "mode": "text",
+      "in": "Copyright (c) 2026",
+      "out": "Copyright © 2026",
+      "note": "symbols rule, locale-neutral."
+    },
+    {
+      "id": "hu-apostrophe-foreign-name",
+      "rule": "apostrophe",
+      "mode": "text",
+      "in": "Ez a McDonald's",
+      "out": "Ez a McDonald’s",
+      "note": "apostrophe rule, locale-neutral."
+    }
+  ]
+}

data/lib/polytypo/data/fixtures/it.json

@@ -1,5 +1,5 @@
 {
-  "spec": "1.11.0",
+  "spec": "1.12.0",
   "locale": "it",
   "cases": [
     {

data/lib/polytypo/data/fixtures/locale-resolution.json

@@ -1,5 +1,5 @@
 {
-  "spec": "1.11.0",
+  "spec": "1.12.0",
   "cases": [
     {
       "id": "exact-en-us",

data/lib/polytypo/data/fixtures/nl.json

@@ -1,5 +1,5 @@
 {
-  "spec": "1.11.0",
+  "spec": "1.12.0",
   "locale": "nl",
   "cases": [
     {

data/lib/polytypo/data/fixtures/pl.json

@@ -1,5 +1,5 @@
 {
-  "spec": "1.11.0",
+  "spec": "1.12.0",
   "locale": "pl",
   "cases": [
     {

data/lib/polytypo/data/fixtures/pt-BR.json

@@ -1,5 +1,5 @@
 {
-  "spec": "1.11.0",
+  "spec": "1.12.0",
   "locale": "pt-BR",
   "cases": [
     {

data/lib/polytypo/data/fixtures/pt-PT.json

@@ -1,5 +1,5 @@
 {
-  "spec": "1.11.0",
+  "spec": "1.12.0",
   "locale": "pt-PT",
   "cases": [
     {

data/lib/polytypo/data/fixtures/ro.json

@@ -0,0 +1,234 @@
+{
+  "spec": "1.12.0",
+  "locale": "ro",
+  "cases": [
+    {
+      "id": "ro-quotes-primary",
+      "rule": "quotes",
+      "mode": "text",
+      "in": "A spus \"salut\".",
+      "out": "A spus „salut”.",
+      "note": "quotes.primary = U+201E/U+201D (forma «99…99»): ÎOOP6 §III.1.2, «ghilimele românești „ ”»."
+    },
+    {
+      "id": "ro-quotes-not-german",
+      "rule": "quotes",
+      "mode": "text",
+      "in": "„salut“",
+      "out": "„salut”",
+      "note": "DISTINCTIVE CASE: input is the German/Czech pair with closing U+201C; output is the Romanian closing U+201D. The two differ by one glyph in print, hence a fixture of their own."
+    },
+    {
+      "id": "ro-quotes-nested",
+      "rule": "quotes",
+      "mode": "text",
+      "in": "\"Ea a zis 'bine' acolo\"",
+      "out": "„Ea a zis «bine» acolo”",
+      "note": "quotes.secondary = U+00AB/U+00BB, pointing inwards: ÎOOP6 gives guillemets the role of a quote inside a quote."
+    },
+    {
+      "id": "ro-quotes-nested-guillemets-kept",
+      "rule": "quotes",
+      "mode": "text",
+      "in": "„Ea a zis «bine» acolo”",
+      "out": "„Ea a zis «bine» acolo”",
+      "note": "An already typeset nested pair is a fixed point."
+    },
+    {
+      "id": "ro-quotes-no-inner-space",
+      "rule": "quotes",
+      "mode": "text",
+      "in": "„ salut ”",
+      "out": "„salut”",
+      "note": "innerSpace = none: ÎOOP6 «Între ghilimele și elementul pe care îl încadrează nu se lasă blanc.»"
+    },
+    {
+      "id": "ro-ellipsis-three-dots",
+      "rule": "ellipsis",
+      "mode": "text",
+      "in": "Stai... ce?",
+      "out": "Stai… ce?",
+      "note": "Three dots become the single character U+2026."
+    },
+    {
+      "id": "ro-ellipsis-not-abbreviated",
+      "rule": "ellipsis",
+      "mode": "text",
+      "in": "Serios?.. da",
+      "out": "Serios?… da",
+      "note": "abbreviatedAfterTerminal = false: no source attests the two-dot form after a terminal mark; medium confidence, see sources."
+    },
+    {
+      "id": "ro-dashes-parenthetical",
+      "rule": "dashes",
+      "mode": "text",
+      "in": "Nu avem încă - firește - rezultate.",
+      "out": "Nu avem încă – firește – rezultate.",
+      "note": "dash.parenthetical = en-spaced: ÎOOP6 «Înainte și după linia de pauză, blancul este obligatoriu»."
+    },
+    {
+      "id": "ro-dashes-existing-em-dash",
+      "rule": "dashes",
+      "mode": "text",
+      "in": "Nu avem încă — firește — rezultate.",
+      "out": "Nu avem încă – firește – rezultate.",
+      "note": "The sources name U+2013 (the Order's annex, En-Dash) and never U+2014, so an em dash is rewritten."
+    },
+    {
+      "id": "ro-ranges-hyphen-kept",
+      "rule": "ranges",
+      "mode": "text",
+      "in": "anii 2020-2021, perioada 1-13 mai",
+      "out": "anii 2020-2021, perioada 1-13 mai",
+      "note": "ranges.md §3: dash.range = none. ÎOOP6 and DOOM3 prefer the unspaced hyphen for ranges, which is the input form, so nothing is substituted.",
+      "rules": {
+        "ranges": true
+      }
+    },
+    {
+      "id": "ro-ranges-spaced-kept",
+      "rule": "ranges",
+      "mode": "text",
+      "in": "noaptea de 30 – 31 decembrie",
+      "out": "noaptea de 30 – 31 decembrie",
+      "note": "ranges.md §3: dash.range = none. The spaced en dash is the second form ÎOOP6 attests for dates (30 – 31 decembrie); none preserves it.",
+      "rules": {
+        "ranges": true
+      }
+    },
+    {
+      "id": "ro-ranges-en-dash-tight-kept",
+      "rule": "ranges",
+      "mode": "text",
+      "in": "perioada 1–31 ianuarie",
+      "out": "perioada 1–31 ianuarie",
+      "note": "ranges.md §3: dash.range = none. DOOM3 «Bara oblică» II.3 b attests the unspaced en dash as a third range form; none preserves it.",
+      "rules": {
+        "ranges": true
+      }
+    },
+    {
+      "id": "ro-ranges-spaced-hyphen-untouched",
+      "rule": "ranges",
+      "mode": "text",
+      "in": "paginile 1 - 22",
+      "out": "paginile 1 - 22",
+      "note": "ranges.md §3: dash.range = none. With range = none a spaced hyphen is left as authored.",
+      "rules": {
+        "ranges": true
+      }
+    },
+    {
+      "id": "ro-hyphen-noop",
+      "rule": "hyphen",
+      "mode": "text",
+      "in": "s-a dus și l-am văzut",
+      "out": "s-a dus și l-am văzut",
+      "note": "The hyphen lists are empty: DOOM3 5.1.5 gives a general recommendation, not a closed list of forms."
+    },
+    {
+      "id": "ro-nbsp-no-short-words",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "și la ea, o dată",
+      "out": "și la ea, o dată",
+      "note": "afterShortWords is empty: no source states a short-word rule."
+    },
+    {
+      "id": "ro-nbsp-before-number",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "conform art. 3 și nr. 5",
+      "out": "conform art. 3 și nr. 5",
+      "note": "beforeNumber: DOOM3 5.2 «nu art. // 3»; nr. is the same class."
+    },
+    {
+      "id": "ro-nbsp-units",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "10 km, 5 kg, 20 cm, 3 mm și 90 km/h",
+      "out": "10 km, 5 kg, 20 cm, 3 mm și 90 km/h",
+      "note": "beforeUnits: DOOM3 5.2 «nu 10 // km»; the other symbols follow BIPM."
+    },
+    {
+      "id": "ro-nbsp-celsius",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "19 °C",
+      "out": "19 °C",
+      "note": "°C: same class as the other unit symbols; BIPM leaves a single space before the unit."
+    },
+    {
+      "id": "ro-nbsp-percent-inert",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "50 % din preț",
+      "out": "50 % din preț",
+      "note": "% is not listed: it rests only on a non-normative guide, so it is not bound."
+    },
+    {
+      "id": "ro-nbsp-initial-single",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "I. Popescu",
+      "out": "I. Popescu",
+      "note": "initialBinding = single: DOOM3 5.2 «nu Ion // Popescu, I. // Popescu»."
+    },
+    {
+      "id": "ro-nbsp-initials-compact-unbound",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "I.L. Caragiale",
+      "out": "I.L. Caragiale",
+      "note": "ACCEPTED MISS: DOOM3 1.2.6 writes compound initials closed up (I.L.), and N7 (nbsp.md §3.9) does not treat the L. after a full stop as an initial, so the space before the surname stays breakable. A false negative, never a damaged text."
+    },
+    {
+      "id": "ro-nbsp-initial-sentence-boundary",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "în anul A. Apoi",
+      "out": "în anul A. Apoi",
+      "note": "ACCEPTED COST of initialBinding = single: a lone capital before a full stop is read as an initial even at a sentence boundary (nbsp.md §3.9), the price of binding «I. // Popescu»."
+    },
+    {
+      "id": "ro-nbsp-no-space-before-question",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "Serios?",
+      "out": "Serios?",
+      "note": "No no-break space before ? ! : ;."
+    },
+    {
+      "id": "ro-nbsp-abbreviation-inert",
+      "rule": "nbsp",
+      "mode": "text",
+      "in": "nr. crt. 4",
+      "out": "nr. crt. 4",
+      "note": "abbreviations is empty: no source forbids splitting a spaced abbreviation such as nr. crt."
+    },
+    {
+      "id": "ro-spaces-brackets-and-final-stop",
+      "rule": "spaces",
+      "mode": "text",
+      "in": "Text ( obișnuit ) rămâne  .",
+      "out": "Text (obișnuit) rămâne.",
+      "note": "The spaces rule is language-independent."
+    },
+    {
+      "id": "ro-symbols-copyright",
+      "rule": "symbols",
+      "mode": "text",
+      "in": "Copyright (c) 2026",
+      "out": "Copyright © 2026",
+      "note": "The symbols rule is language-independent."
+    },
+    {
+      "id": "ro-apostrophe-foreign-name",
+      "rule": "apostrophe",
+      "mode": "text",
+      "in": "A mers la McDonald's și înapoi",
+      "out": "A mers la McDonald’s și înapoi",
+      "note": "An apostrophe in a foreign name is written U+2019."
+    }
+  ]
+}

data/lib/polytypo/data/fixtures/ru.json

@@ -1,5 +1,5 @@
 {
-  "spec": "1.11.0",
+  "spec": "1.12.0",
   "locale": "ru",
   "cases": [
     {

data/lib/polytypo/data/fixtures/sk.json

@@ -1,5 +1,5 @@
 {
-  "spec": "1.11.0",
+  "spec": "1.12.0",
   "locale": "sk",
   "cases": [
     {

data/lib/polytypo/data/fixtures/sv.json

@@ -1,5 +1,5 @@
 {
-  "spec": "1.11.0",
+  "spec": "1.12.0",
   "locale": "sv",
   "cases": [
     {

data/lib/polytypo/data/fixtures/tr.json

@@ -1,5 +1,5 @@
 {
-  "spec": "1.11.0",
+  "spec": "1.12.0",
   "locale": "tr",
   "cases": [
     {

data/lib/polytypo/data/fixtures/uk.json

@@ -1,5 +1,5 @@
 {
-  "spec": "1.11.0",
+  "spec": "1.12.0",
   "locale": "uk",
   "cases": [
     {