polytypo 1.20.1 → 1.21.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/polytypo/data/VERSION +1 -1
- data/lib/polytypo/data/fixtures/bg.json +12 -1
- data/lib/polytypo/data/fixtures/cs.json +12 -1
- data/lib/polytypo/data/fixtures/de-CH.json +12 -1
- data/lib/polytypo/data/fixtures/de-DE.json +12 -1
- data/lib/polytypo/data/fixtures/el.json +12 -1
- data/lib/polytypo/data/fixtures/en-GB.json +12 -1
- data/lib/polytypo/data/fixtures/en-US.json +403 -1
- data/lib/polytypo/data/fixtures/es.json +12 -1
- data/lib/polytypo/data/fixtures/fi.json +12 -1
- data/lib/polytypo/data/fixtures/fr-CA.json +12 -1
- data/lib/polytypo/data/fixtures/fr.json +12 -1
- data/lib/polytypo/data/fixtures/hr.json +12 -1
- data/lib/polytypo/data/fixtures/hu.json +12 -1
- data/lib/polytypo/data/fixtures/it.json +12 -1
- data/lib/polytypo/data/fixtures/locale-resolution.json +1 -1
- data/lib/polytypo/data/fixtures/lt.json +12 -1
- data/lib/polytypo/data/fixtures/nl.json +12 -1
- data/lib/polytypo/data/fixtures/pl.json +12 -1
- data/lib/polytypo/data/fixtures/pt-BR.json +12 -1
- data/lib/polytypo/data/fixtures/pt-PT.json +12 -1
- data/lib/polytypo/data/fixtures/ro.json +12 -1
- data/lib/polytypo/data/fixtures/ru.json +12 -1
- data/lib/polytypo/data/fixtures/sk.json +12 -1
- data/lib/polytypo/data/fixtures/sl.json +12 -1
- data/lib/polytypo/data/fixtures/sr.json +12 -1
- data/lib/polytypo/data/fixtures/sv.json +12 -1
- data/lib/polytypo/data/fixtures/tr.json +12 -1
- data/lib/polytypo/data/fixtures/uk.json +12 -1
- data/lib/polytypo/data/locales/bg.json +1 -0
- data/lib/polytypo/data/locales/cs.json +1 -0
- data/lib/polytypo/data/locales/de-CH.json +6 -0
- data/lib/polytypo/data/locales/de-DE.json +7 -0
- data/lib/polytypo/data/locales/el.json +1 -0
- data/lib/polytypo/data/locales/en-GB.json +7 -0
- data/lib/polytypo/data/locales/en-US.json +7 -0
- data/lib/polytypo/data/locales/es.json +1 -0
- data/lib/polytypo/data/locales/fi.json +1 -0
- data/lib/polytypo/data/locales/fr-CA.json +1 -0
- data/lib/polytypo/data/locales/fr.json +1 -0
- data/lib/polytypo/data/locales/hr.json +1 -0
- data/lib/polytypo/data/locales/hu.json +1 -0
- data/lib/polytypo/data/locales/it.json +1 -0
- data/lib/polytypo/data/locales/lt.json +1 -0
- data/lib/polytypo/data/locales/nl.json +1 -0
- data/lib/polytypo/data/locales/pl.json +1 -0
- data/lib/polytypo/data/locales/pt-BR.json +1 -0
- data/lib/polytypo/data/locales/pt-PT.json +1 -0
- data/lib/polytypo/data/locales/registry.json +1 -1
- data/lib/polytypo/data/locales/ro.json +1 -0
- data/lib/polytypo/data/locales/ru.json +1 -0
- data/lib/polytypo/data/locales/sk.json +1 -0
- data/lib/polytypo/data/locales/sl.json +1 -0
- data/lib/polytypo/data/locales/sr.json +1 -0
- data/lib/polytypo/data/locales/sv.json +1 -0
- data/lib/polytypo/data/locales/tr.json +1 -0
- data/lib/polytypo/data/locales/uk.json +1 -0
- data/lib/polytypo/data/rules/order.json +9 -1
- data/lib/polytypo/data/rules/pipeline-idempotency.md +23 -3
- data/lib/polytypo/data/rules/quote-punctuation.md +334 -0
- data/lib/polytypo/data/rules/quotes.md +9 -0
- data/lib/polytypo/data/schema/fixtures.schema.json +1 -0
- data/lib/polytypo/data/schema/locale.schema.json +12 -1
- data/lib/polytypo/engine/locale.rb +22 -1
- data/lib/polytypo/engine/pipeline.rb +1 -1
- data/lib/polytypo/engine/rules/quote_punctuation.rb +79 -0
- data/lib/polytypo/engine/rules.rb +1 -0
- data/lib/polytypo/version.rb +1 -1
- metadata +3 -1
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "fr",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -1089,6 +1089,17 @@
|
|
|
1089
1089
|
"in": "Écrire à foo@example.com ; oui\n",
|
|
1090
1090
|
"out": "Écrire à foo@example.com ; oui\n",
|
|
1091
1091
|
"note": "modes.md §3.7.3 terminator guard: it applies to http, https and www addresses only, so the space after an e-mail address converts as before."
|
|
1092
|
+
},
|
|
1093
|
+
{
|
|
1094
|
+
"id": "fr-quote-punctuation-none",
|
|
1095
|
+
"rule": "quote-punctuation",
|
|
1096
|
+
"mode": "text",
|
|
1097
|
+
"in": "alpha « beta », gamma",
|
|
1098
|
+
"out": "alpha « beta », gamma",
|
|
1099
|
+
"rules": {
|
|
1100
|
+
"quote-punctuation": true
|
|
1101
|
+
},
|
|
1102
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for fr, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
1092
1103
|
}
|
|
1093
1104
|
]
|
|
1094
1105
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "hr",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -248,6 +248,17 @@
|
|
|
248
248
|
"in": "To je McDonald's",
|
|
249
249
|
"out": "To je McDonald’s",
|
|
250
250
|
"note": "apostrophe rule, locale-neutral; 8.18 uses U+2019 for the elision mark as well."
|
|
251
|
+
},
|
|
252
|
+
{
|
|
253
|
+
"id": "hr-quote-punctuation-none",
|
|
254
|
+
"rule": "quote-punctuation",
|
|
255
|
+
"mode": "text",
|
|
256
|
+
"in": "alpha „beta”, gamma",
|
|
257
|
+
"out": "alpha „beta”, gamma",
|
|
258
|
+
"rules": {
|
|
259
|
+
"quote-punctuation": true
|
|
260
|
+
},
|
|
261
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for hr, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
251
262
|
}
|
|
252
263
|
]
|
|
253
264
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "hu",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -259,6 +259,17 @@
|
|
|
259
259
|
"in": "Ez a McDonald's",
|
|
260
260
|
"out": "Ez a McDonald’s",
|
|
261
261
|
"note": "apostrophe rule, locale-neutral."
|
|
262
|
+
},
|
|
263
|
+
{
|
|
264
|
+
"id": "hu-quote-punctuation-none",
|
|
265
|
+
"rule": "quote-punctuation",
|
|
266
|
+
"mode": "text",
|
|
267
|
+
"in": "alpha „beta”, gamma",
|
|
268
|
+
"out": "alpha „beta”, gamma",
|
|
269
|
+
"rules": {
|
|
270
|
+
"quote-punctuation": true
|
|
271
|
+
},
|
|
272
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for hu, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
262
273
|
}
|
|
263
274
|
]
|
|
264
275
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "it",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -172,6 +172,17 @@
|
|
|
172
172
|
"in": "Lui dice 'un'<em>idea</em> è buona.' Fine.",
|
|
173
173
|
"out": "Lui dice «un’<em>idea</em> è buona.» Fine.",
|
|
174
174
|
"note": "The entry un covers the feminine indefinite un' only; Crusca is categorical that the masculine un takes no apostrophe. The mechanism cannot tell the two apart, which is harmless here because it only ever declines a pairing."
|
|
175
|
+
},
|
|
176
|
+
{
|
|
177
|
+
"id": "it-quote-punctuation-none",
|
|
178
|
+
"rule": "quote-punctuation",
|
|
179
|
+
"mode": "text",
|
|
180
|
+
"in": "alpha «beta», gamma",
|
|
181
|
+
"out": "alpha «beta», gamma",
|
|
182
|
+
"rules": {
|
|
183
|
+
"quote-punctuation": true
|
|
184
|
+
},
|
|
185
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for it, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
175
186
|
}
|
|
176
187
|
]
|
|
177
188
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "lt",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -309,6 +309,17 @@
|
|
|
309
309
|
"in": "O'Brien atėjo.",
|
|
310
310
|
"out": "O’Brien atėjo.",
|
|
311
311
|
"note": "apostrophe.md: a straight apostrophe inside a foreign name becomes U+2019."
|
|
312
|
+
},
|
|
313
|
+
{
|
|
314
|
+
"id": "lt-quote-punctuation-none",
|
|
315
|
+
"rule": "quote-punctuation",
|
|
316
|
+
"mode": "text",
|
|
317
|
+
"in": "alpha „beta“, gamma",
|
|
318
|
+
"out": "alpha „beta“, gamma",
|
|
319
|
+
"rules": {
|
|
320
|
+
"quote-punctuation": true
|
|
321
|
+
},
|
|
322
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for lt, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
312
323
|
}
|
|
313
324
|
]
|
|
314
325
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "nl",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -132,6 +132,17 @@
|
|
|
132
132
|
"in": "Hij zegt 'ik kom <em>vroeg </em>'t is laat.' Klaar.",
|
|
133
133
|
"out": "Hij zegt “ik kom <em>vroeg </em>’t is laat.” Klaar.",
|
|
134
134
|
"note": "The same mechanism on the entry t ('t was), attested by the same Taalunie pair of pages."
|
|
135
|
+
},
|
|
136
|
+
{
|
|
137
|
+
"id": "nl-quote-punctuation-none",
|
|
138
|
+
"rule": "quote-punctuation",
|
|
139
|
+
"mode": "text",
|
|
140
|
+
"in": "alpha “beta”, gamma",
|
|
141
|
+
"out": "alpha “beta”, gamma",
|
|
142
|
+
"rules": {
|
|
143
|
+
"quote-punctuation": true
|
|
144
|
+
},
|
|
145
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for nl, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
135
146
|
}
|
|
136
147
|
]
|
|
137
148
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "pl",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -132,6 +132,17 @@
|
|
|
132
132
|
"in": "d'Artagnan",
|
|
133
133
|
"out": "d’Artagnan",
|
|
134
134
|
"note": "U+0027 staje się U+2019. Reguła nie czyta danych locale; przypadek ją dla polskiego poświadcza."
|
|
135
|
+
},
|
|
136
|
+
{
|
|
137
|
+
"id": "pl-quote-punctuation-none",
|
|
138
|
+
"rule": "quote-punctuation",
|
|
139
|
+
"mode": "text",
|
|
140
|
+
"in": "alpha „beta”, gamma",
|
|
141
|
+
"out": "alpha „beta”, gamma",
|
|
142
|
+
"rules": {
|
|
143
|
+
"quote-punctuation": true
|
|
144
|
+
},
|
|
145
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for pl, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
135
146
|
}
|
|
136
147
|
]
|
|
137
148
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "pt-BR",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -159,6 +159,17 @@
|
|
|
159
159
|
"in": "Ele diz 'd'<em>Os Lusíadas</em> é bom.' Fim.",
|
|
160
160
|
"out": "Ele diz “d’<em>Os Lusíadas</em> é bom.” Fim.",
|
|
161
161
|
"note": "Same input and same Base XVIII citation as pt-PT, different primary pair — pt-BR opens with U+201C where pt-PT opens with a guillemet. Pinned in both files so a runtime cannot pass one and fail the other."
|
|
162
|
+
},
|
|
163
|
+
{
|
|
164
|
+
"id": "pt-br-quote-punctuation-none",
|
|
165
|
+
"rule": "quote-punctuation",
|
|
166
|
+
"mode": "text",
|
|
167
|
+
"in": "alpha “beta”, gamma",
|
|
168
|
+
"out": "alpha “beta”, gamma",
|
|
169
|
+
"rules": {
|
|
170
|
+
"quote-punctuation": true
|
|
171
|
+
},
|
|
172
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for pt-BR, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
162
173
|
}
|
|
163
174
|
]
|
|
164
175
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "pt-PT",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -159,6 +159,17 @@
|
|
|
159
159
|
"in": "Ele diz 'd'<em>Os Lusíadas</em> é bom.' Fim.",
|
|
160
160
|
"out": "Ele diz «d’<em>Os Lusíadas</em> é bom.» Fim.",
|
|
161
161
|
"note": "quotes.md §3.2's span-boundary elision veto (spec 1.4.0), on Acordo Ortográfico Base XVIII 1.º a) — whose own examples are book titles, which is what makes this list load-bearing: a title set in emphasis rather than italics puts the span boundary immediately after the mark."
|
|
162
|
+
},
|
|
163
|
+
{
|
|
164
|
+
"id": "pt-pt-quote-punctuation-none",
|
|
165
|
+
"rule": "quote-punctuation",
|
|
166
|
+
"mode": "text",
|
|
167
|
+
"in": "alpha «beta», gamma",
|
|
168
|
+
"out": "alpha «beta», gamma",
|
|
169
|
+
"rules": {
|
|
170
|
+
"quote-punctuation": true
|
|
171
|
+
},
|
|
172
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for pt-PT, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
162
173
|
}
|
|
163
174
|
]
|
|
164
175
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "ro",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -229,6 +229,17 @@
|
|
|
229
229
|
"in": "A mers la McDonald's și înapoi",
|
|
230
230
|
"out": "A mers la McDonald’s și înapoi",
|
|
231
231
|
"note": "An apostrophe in a foreign name is written U+2019."
|
|
232
|
+
},
|
|
233
|
+
{
|
|
234
|
+
"id": "ro-quote-punctuation-none",
|
|
235
|
+
"rule": "quote-punctuation",
|
|
236
|
+
"mode": "text",
|
|
237
|
+
"in": "alpha „beta”, gamma",
|
|
238
|
+
"out": "alpha „beta”, gamma",
|
|
239
|
+
"rules": {
|
|
240
|
+
"quote-punctuation": true
|
|
241
|
+
},
|
|
242
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for ro, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
232
243
|
}
|
|
233
244
|
]
|
|
234
245
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "ru",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -737,6 +737,17 @@
|
|
|
737
737
|
"ranges": true
|
|
738
738
|
},
|
|
739
739
|
"note": "ranges.md §3.2a, via dashes.md §3.2 step 8 (spec 1.3.0): the same witness in the suffix direction and in an em-dash locale — the disturbed guard is the range's `after` rather than its `before`. Pinned separately because the two directions are separate code paths in every port. To be precise about \"before the amendment\": the drift is a property of the INTERMEDIATE state — ranges.md §3.2a's widened candidacy without T1's transparency — which never shipped. Under spec 1.2.0 this input was stable, because the token was not a range candidate at all."
|
|
740
|
+
},
|
|
741
|
+
{
|
|
742
|
+
"id": "ru-quote-punctuation-none",
|
|
743
|
+
"rule": "quote-punctuation",
|
|
744
|
+
"mode": "text",
|
|
745
|
+
"in": "alpha «beta», gamma",
|
|
746
|
+
"out": "alpha «beta», gamma",
|
|
747
|
+
"rules": {
|
|
748
|
+
"quote-punctuation": true
|
|
749
|
+
},
|
|
750
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for ru, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
740
751
|
}
|
|
741
752
|
]
|
|
742
753
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "sk",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -273,6 +273,17 @@
|
|
|
273
273
|
"in": "Išiel do McDonald's a späť",
|
|
274
274
|
"out": "Išiel do McDonald’s a späť",
|
|
275
275
|
"note": "Apostrof v cudzom mene sa píše ako U+2019."
|
|
276
|
+
},
|
|
277
|
+
{
|
|
278
|
+
"id": "sk-quote-punctuation-none",
|
|
279
|
+
"rule": "quote-punctuation",
|
|
280
|
+
"mode": "text",
|
|
281
|
+
"in": "alpha „beta“, gamma",
|
|
282
|
+
"out": "alpha „beta“, gamma",
|
|
283
|
+
"rules": {
|
|
284
|
+
"quote-punctuation": true
|
|
285
|
+
},
|
|
286
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for sk, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
276
287
|
}
|
|
277
288
|
]
|
|
278
289
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "sl",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -242,6 +242,17 @@
|
|
|
242
242
|
"in": "O'Brien je prišel.",
|
|
243
243
|
"out": "O’Brien je prišel.",
|
|
244
244
|
"note": "apostrophe.md: a straight apostrophe inside a foreign name becomes U+2019."
|
|
245
|
+
},
|
|
246
|
+
{
|
|
247
|
+
"id": "sl-quote-punctuation-none",
|
|
248
|
+
"rule": "quote-punctuation",
|
|
249
|
+
"mode": "text",
|
|
250
|
+
"in": "alpha »beta«, gamma",
|
|
251
|
+
"out": "alpha »beta«, gamma",
|
|
252
|
+
"rules": {
|
|
253
|
+
"quote-punctuation": true
|
|
254
|
+
},
|
|
255
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for sl, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
245
256
|
}
|
|
246
257
|
]
|
|
247
258
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "sr",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -202,6 +202,17 @@
|
|
|
202
202
|
"in": "То је McDonald's",
|
|
203
203
|
"out": "То је McDonald’s",
|
|
204
204
|
"note": "apostrophe rule, locale-neutral."
|
|
205
|
+
},
|
|
206
|
+
{
|
|
207
|
+
"id": "sr-quote-punctuation-none",
|
|
208
|
+
"rule": "quote-punctuation",
|
|
209
|
+
"mode": "text",
|
|
210
|
+
"in": "alpha „beta”, gamma",
|
|
211
|
+
"out": "alpha „beta”, gamma",
|
|
212
|
+
"rules": {
|
|
213
|
+
"quote-punctuation": true
|
|
214
|
+
},
|
|
215
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for sr, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
205
216
|
}
|
|
206
217
|
]
|
|
207
218
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "sv",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -1293,6 +1293,17 @@
|
|
|
1293
1293
|
"in": "tidningen l'\"Humanité\"",
|
|
1294
1294
|
"out": "tidningen l’”Humanité”",
|
|
1295
1295
|
"note": "apostrophe.md §3.3 cases 3 and 3a (spec 1.2.0): same as fi; U+201D is in CLOSEISH and the output is unchanged from spec 1.1.0."
|
|
1296
|
+
},
|
|
1297
|
+
{
|
|
1298
|
+
"id": "sv-quote-punctuation-none",
|
|
1299
|
+
"rule": "quote-punctuation",
|
|
1300
|
+
"mode": "text",
|
|
1301
|
+
"in": "alpha ”beta”, gamma",
|
|
1302
|
+
"out": "alpha ”beta”, gamma",
|
|
1303
|
+
"rules": {
|
|
1304
|
+
"quote-punctuation": true
|
|
1305
|
+
},
|
|
1306
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for sv, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
1296
1307
|
}
|
|
1297
1308
|
]
|
|
1298
1309
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "tr",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -245,6 +245,17 @@
|
|
|
245
245
|
"in": "Dedi: '<b>2</b>'nci kat.' Bitti.",
|
|
246
246
|
"out": "Dedi: “<b>2</b>’nci kat.” Bitti.",
|
|
247
247
|
"note": "Sayılara gelen sıra eki, TDK «Kesme İşareti» 4'ün kendi örneğinden («2'nci kat»). Aynı maddeden gelen «7,65'lik» ve «Atatürk'üm» de listededir; üçü de basılı örnekte kesme işaretinden sonraki dizinin TAMAMI olduğu ve çıplak bir sözcükle çakışmadığı için alınmıştır."
|
|
248
|
+
},
|
|
249
|
+
{
|
|
250
|
+
"id": "tr-quote-punctuation-none",
|
|
251
|
+
"rule": "quote-punctuation",
|
|
252
|
+
"mode": "text",
|
|
253
|
+
"in": "alpha “beta”, gamma",
|
|
254
|
+
"out": "alpha “beta”, gamma",
|
|
255
|
+
"rules": {
|
|
256
|
+
"quote-punctuation": true
|
|
257
|
+
},
|
|
258
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for tr, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
248
259
|
}
|
|
249
260
|
]
|
|
250
261
|
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.21.0",
|
|
3
3
|
"locale": "uk",
|
|
4
4
|
"cases": [
|
|
5
5
|
{
|
|
@@ -148,6 +148,17 @@
|
|
|
148
148
|
"in": "п'ять об'єктів",
|
|
149
149
|
"out": "п’ять об’єктів",
|
|
150
150
|
"note": "ВАЖЛИВИЙ ВИПАДОК для української, і перевірений на рушії, а не припущений: апостроф у «п'ять», «об'єкт» — частина орфографії слова, а не пунктуація, і правило apostrophe перетворює прямий U+0027 на U+2019 саме там, де він і має бути в друкованому тексті. Спершу цей випадок був написаний як no-op — рушій показав протилежне, і показав правильно."
|
|
151
|
+
},
|
|
152
|
+
{
|
|
153
|
+
"id": "uk-quote-punctuation-none",
|
|
154
|
+
"rule": "quote-punctuation",
|
|
155
|
+
"mode": "text",
|
|
156
|
+
"in": "alpha «beta», gamma",
|
|
157
|
+
"out": "alpha «beta», gamma",
|
|
158
|
+
"rules": {
|
|
159
|
+
"quote-punctuation": true
|
|
160
|
+
},
|
|
161
|
+
"note": "quote-punctuation.md §2, §6: quotes.punctuationPlacement is \"none\" for uk, so enabling the rule is a no-op; the input is already in the locale's own quotation marks."
|
|
151
162
|
}
|
|
152
163
|
]
|
|
153
164
|
}
|
|
@@ -12,6 +12,7 @@
|
|
|
12
12
|
"close": "›",
|
|
13
13
|
"innerSpace": "none"
|
|
14
14
|
},
|
|
15
|
+
"punctuationPlacement": "none",
|
|
15
16
|
"elisionIdioms": [],
|
|
16
17
|
"elisionClitics": {
|
|
17
18
|
"before": [],
|
|
@@ -76,6 +77,11 @@
|
|
|
76
77
|
"cite": "Schweizerische Bundeskanzlei, Schreibweisungen, Rz. 223 und 224: der Bindestrich wird als Ergänzungsstrich für einen eingesparten Wortteil verwendet („Papierproduktion und -handel“); mit dem geschützten Ergänzungsstrich wird verhindert, dass der Ergänzungsstrich am Zeilenende auf der oberen Zeile bleibt, während der zugehörige zweite Wortbestandteil auf die nächste Zeile rutscht",
|
|
77
78
|
"url": "https://www.bk.admin.ch/dam/de/sd-web/YVHazXZRkqKn/schreibweisungen.pdf",
|
|
78
79
|
"note": "Beleg dafür, dass die drei Listen leer bleiben. Das Deutsche kennt keine geschlossene Liste von Morphemen mit unteilbarem Bindestrich; die Trennung am Bindestrich ist zulässig (Rz. 269–271 behandeln nur sinnentstellende Trennungen). Der einzige belegte Fall eines geschützten Bindestrichs ist der Ergänzungsstrich (Rz. 224), und der ist offen: er betrifft jedes beliebige Zweitglied nach „und -“ und lässt sich als literale Wortliste nicht abbilden."
|
|
80
|
+
},
|
|
81
|
+
{
|
|
82
|
+
"rule": "quote-punctuation",
|
|
83
|
+
"cite": "No Swiss source for the placement of punctuation relative to the closing quotation mark was consulted; value left at the default",
|
|
84
|
+
"note": "quotes.punctuationPlacement is \"none\" because no convention has been verified for de-CH. That is the default and means the rule does nothing, not that a convention was found to depend on meaning. The German Amtliches Regelwerk (2024) is the source cited for de-DE; whether it is the right authority for Swiss usage was not established."
|
|
79
85
|
}
|
|
80
86
|
]
|
|
81
87
|
}
|
|
@@ -12,6 +12,7 @@
|
|
|
12
12
|
"close": "‘",
|
|
13
13
|
"innerSpace": "none"
|
|
14
14
|
},
|
|
15
|
+
"punctuationPlacement": "none",
|
|
15
16
|
"elisionIdioms": [],
|
|
16
17
|
"elisionClitics": {
|
|
17
18
|
"before": [],
|
|
@@ -80,6 +81,12 @@
|
|
|
80
81
|
"rule": "nbsp",
|
|
81
82
|
"cite": "Keine frei prüfbare Normquelle für „Nr.“ + Zahl: DIN 5008:2020-03 ist kostenpflichtig und wurde nicht gelesen; Duden und das Amtliche Regelwerk 2024 sprechen keine Abstandsregel aus. Vereinheitlicht nach vorherrschendem Gebrauch (Operatorentscheid, 18.09.2026)",
|
|
82
83
|
"note": "Diese Zeile ist ausdrücklich kein Beleg, sondern eine Festlegung, und wird als solche geführt. Geprüft und ergebnislos: Duden, Rechtschreibregeln „Abkürzungen“ (D 1–D 4, nur der Abkürzungspunkt); Duden, Sprachratgeber „Worttrennung am Zeilenende“; Amtliches Regelwerk 2024, Kapitel F (§§ 84–90, nur Worttrennung) und der Kasten „Sonderzeichen“ auf S. 153, der Typografie ausdrücklich den Konventionen bzw. den DIN-, ÖNORM- und SNV-Normen zuweist, also ausserhalb des Regelwerks. Entscheiden könnte nur DIN 5008:2020-03. Der Projektentscheid dazu: liegt eine Regel hinter einer Bezahlschranke, formuliert polytypo sie nach dem verbreitetsten Gebrauch und hält sie in allen Runtimes gleich — Einheitlichkeit geht hier vor Kanontreue, und die Festlegung wird offen als solche gekennzeichnet statt als Zitat ausgegeben. Der verbreitetste Gebrauch bindet „Nr.“ an die folgende Zahl; die Sekundärquellen, die DIN 5008 referieren, sagen dasselbe. Fällt die Schranke, tritt der Wortlaut der Norm an die Stelle dieser Zeile — auch wenn er ihr widerspricht."
|
|
84
|
+
},
|
|
85
|
+
{
|
|
86
|
+
"rule": "quote-punctuation",
|
|
87
|
+
"cite": "Rat für deutsche Rechtschreibung, Amtliches Regelwerk der deutschen Rechtschreibung (2024), §79 E1",
|
|
88
|
+
"url": "https://www.rechtschreibrat.com/DOX/RfdR_Amtliches-Regelwerk_2024.pdf",
|
|
89
|
+
"note": "Supports quotes.punctuationPlacement = \"none\". Verbatim: “Satzzeichen, die zu einer angeführten Einheit gehören, stehen vor dem schließenden Anführungszeichen; Satzzeichen, die zum Trägersatz gehören, stehen nach dem schließenden Anführungszeichen.” E1(2) puts a comma after the closing mark when a carrier sentence follows the quotation, but the placement of a full stop and of the other marks depends on whether they belong to the quotation, so the rule does nothing here. Consulted 2026-11-09."
|
|
83
90
|
}
|
|
84
91
|
]
|
|
85
92
|
}
|
|
@@ -12,6 +12,7 @@
|
|
|
12
12
|
"close": "”",
|
|
13
13
|
"innerSpace": "none"
|
|
14
14
|
},
|
|
15
|
+
"punctuationPlacement": "none",
|
|
15
16
|
"elisionIdioms": [],
|
|
16
17
|
"elisionClitics": {
|
|
17
18
|
"before": [],
|
|
@@ -120,6 +121,12 @@
|
|
|
120
121
|
"cite": "The Chicago Manual of Style, 7.16 “Possessive form of most nouns” (section number and title confirmed against the publisher's own chapter-7 table of contents; cited as 7.16–19 and 7.22 by the CMOS Q&A on the 18th-edition site). Verbatim, as reproduced by CMOS Shop Talk, “Section 7.16 in the Spotlight”, 12 May 2015: “The possessive of most singular nouns is formed by adding an apostrophe and an s.” Reconfirmed for the current edition by CMOS Shop Talk, 31 August 2021: “Chicago adds an apostrophe and an s to form the possessive of a singular noun, including singular nouns ending in s” (see CMOS 7.16)",
|
|
121
122
|
"url": "https://cmosshoptalk.com/2021/08/31/introducing-the-chicago-manual-of-style-for-perfectit/",
|
|
122
123
|
"note": "Supports quotes.elisionClitics.after = [\"s\"], identical to en-US. LABELLED GAP: en-GB rests on an American authority because no British one was reachable. New Hart's Rules: The Oxford Style Guide (ed. Anne Waddingham, OUP) is print and paywalled; ox.ac.uk's style guide returned HTTP 403, OUP's own free companion site for New Hart's Rules returned an empty body, and Oxford Reference is paywalled. Every British statement of the rule found was a third-party paraphrase and therefore not citable. The gap is narrow rather than papered over: the single point on which US and UK possessive practice actually diverges is whether a second s follows a sibilant (Dickens's, Chicago's preference per 7.16–19, versus Dickens', the alternative practice per 7.22), and that divergence cannot reach this entry, because the veto matches the maximal LETTER run to the RIGHT of the mark — Burns's fires on s, Burns' has no letter there and fires nothing. So the two locales take the identical entry not by assumption but because the two practices coincide wherever this field is consulted. Replace with New Hart's Rules if the book is obtained. Note also that en-GB's primary close is U+2019, so this is the locale where a wrong entry could collide with genuine quotation — a one-element list is the minimum that closes issue #53."
|
|
124
|
+
},
|
|
125
|
+
{
|
|
126
|
+
"rule": "quote-punctuation",
|
|
127
|
+
"cite": "University of Oxford Style Guide (2014; Michaelmas term 2014 edition), p. 16, “Using other punctuation with quotation marks”",
|
|
128
|
+
"url": "https://warwick.ac.uk/fac/sci/lifesci/research/der/workshop/university_of_oxford_style_guide.pdf",
|
|
129
|
+
"note": "Supports quotes.punctuationPlacement = \"none\". Verbatim: “If the quote would have required punctuation in its original form, place the punctuation inside the quotation marks.” and “Place any punctuation which does not belong to the quote outside the quotation marks (except closing punctuation if the end of the quote is also the end of the sentence).” Placement follows whether the mark belongs to the quoted material, which a scan of code points cannot decide, so the rule does nothing here rather than guess. This is a university house style, not a national norm, and the copy read is the 2014 edition at the URL above; the current edition on ox.ac.uk was not reachable. Consulted 2026-11-09."
|
|
123
130
|
}
|
|
124
131
|
]
|
|
125
132
|
}
|
|
@@ -12,6 +12,7 @@
|
|
|
12
12
|
"close": "’",
|
|
13
13
|
"innerSpace": "none"
|
|
14
14
|
},
|
|
15
|
+
"punctuationPlacement": "inside",
|
|
15
16
|
"elisionIdioms": [
|
|
16
17
|
{
|
|
17
18
|
"left": "rock",
|
|
@@ -138,6 +139,12 @@
|
|
|
138
139
|
"cite": "The Chicago Manual of Style, 7.16 “Possessive form of most nouns” (section number and title confirmed against the publisher's own chapter-7 table of contents; cited as 7.16–19 and 7.22 by the CMOS Q&A on the 18th-edition site). Verbatim, as reproduced by CMOS Shop Talk, “Section 7.16 in the Spotlight”, 12 May 2015: “The possessive of most singular nouns is formed by adding an apostrophe and an s.” Reconfirmed for the current edition by CMOS Shop Talk, 31 August 2021: “Chicago adds an apostrophe and an s to form the possessive of a singular noun, including singular nouns ending in s” (see CMOS 7.16)",
|
|
139
140
|
"url": "https://cmosshoptalk.com/2021/08/31/introducing-the-chicago-manual-of-style-for-perfectit/",
|
|
140
141
|
"note": "Supports the single entry quotes.elisionClitics.after = [\"s\"] — the possessive s, not the contraction enclitics. t, ll, re, ve, d and m are deliberately absent: nobody writes `won`'t, so they have no attested occurrence in the shape this veto is scoped to, whereas possessivising a set-off identifier (`x`'s printer) is everyday technical prose and is the shape reported in canonical issue #53. Chicago states the rule, not a code point; U+2019 follows from apostrophe.md §3.3, which is unchanged. Edition and section provenance is mixed deliberately and should not be tidied into a single number: the numbered paragraph itself is paywalled, the verbatim wording above is the 16th edition's (the 2015 post carries an editor's note saying so), and the 2021 post plus the 18th-edition Q&A are what establish that 7.16 is still the general rule. CMOS 7.22's alternative practice (Burns' rather than Burns's) does not affect this entry: the veto matches the maximal LETTER run to the RIGHT of the mark, so Burns's fires on s while Burns' has no letter there and fires nothing. CMOS 7.29 “Possessive with italicized or quoted terms” is a closer fit to the reported shape than 7.16 and would strengthen this citation, but its text is paywalled and was not read — only its title, from the table of contents."
|
|
142
|
+
},
|
|
143
|
+
{
|
|
144
|
+
"rule": "quote-punctuation",
|
|
145
|
+
"cite": "CMOS Shop Talk (the Chicago Manual of Style’s own blog), Russell Harper, “Commas and Periods with Quotation Marks”, 20 October 2020 (updated 20 January 2026), which cites Chicago Manual of Style 6.9–6.10",
|
|
146
|
+
"url": "https://cmosshoptalk.com/2020/10/20/commas-and-periods-with-quotation-marks/",
|
|
147
|
+
"note": "Supports quotes.punctuationPlacement = \"inside\". Verbatim: “In publications that follow Chicago style, commas and periods are placed before a closing quotation mark”; semicolons, colons, question marks, exclamation points and dashes “go after a closing quotation mark unless they belong to the quoted matter.” Only the comma and the full stop are positional, so only those two are moved (quote-punctuation.md §3); the others depend on whether they belong to the quotation, which no scan of code points can tell. The post also notes the convention is “no longer universally followed outside the United States”. The numbered paragraphs of the manual itself are behind a login and were not read; 6.9–6.10 are the numbers the post gives, and it names no edition; the current (18th) edition is inferred from the post’s update date, not stated by it. CMOS Shop Talk, “Section 7.75 in the Spotlight” (11 August 2015, 16th ed.), says punctuation that is not part of a quoted computer term stays outside the marks; whether that holds in the 18th edition was not checked, and the rule does not model it (accepted cost, quote-punctuation.md §6). Consulted 2026-11-09."
|
|
141
148
|
}
|
|
142
149
|
]
|
|
143
150
|
}
|