polytypo 1.26.0 → 1.27.0
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 +1 -1
- data/lib/polytypo/data/fixtures/cs.json +1 -1
- data/lib/polytypo/data/fixtures/da.json +1 -1
- data/lib/polytypo/data/fixtures/de-CH.json +1 -1
- data/lib/polytypo/data/fixtures/de-DE.json +1 -1
- data/lib/polytypo/data/fixtures/el.json +1 -1
- data/lib/polytypo/data/fixtures/en-GB.json +1 -1
- data/lib/polytypo/data/fixtures/en-US.json +1 -1
- data/lib/polytypo/data/fixtures/es.json +1 -1
- data/lib/polytypo/data/fixtures/et.json +1 -1
- data/lib/polytypo/data/fixtures/fi.json +1 -1
- data/lib/polytypo/data/fixtures/fr-CA.json +1 -1
- data/lib/polytypo/data/fixtures/fr.json +1 -1
- data/lib/polytypo/data/fixtures/hr.json +1 -1
- data/lib/polytypo/data/fixtures/hu.json +1 -1
- data/lib/polytypo/data/fixtures/it.json +1 -1
- data/lib/polytypo/data/fixtures/locale-resolution.json +22 -4
- data/lib/polytypo/data/fixtures/lt.json +1 -1
- data/lib/polytypo/data/fixtures/lv.json +1 -1
- data/lib/polytypo/data/fixtures/nb.json +315 -0
- data/lib/polytypo/data/fixtures/nl.json +1 -1
- data/lib/polytypo/data/fixtures/pl.json +1 -1
- data/lib/polytypo/data/fixtures/pt-BR.json +1 -1
- data/lib/polytypo/data/fixtures/pt-PT.json +1 -1
- data/lib/polytypo/data/fixtures/ro.json +1 -1
- data/lib/polytypo/data/fixtures/ru.json +1 -1
- data/lib/polytypo/data/fixtures/sk.json +1 -1
- data/lib/polytypo/data/fixtures/sl.json +1 -1
- data/lib/polytypo/data/fixtures/sr.json +1 -1
- data/lib/polytypo/data/fixtures/sv.json +1 -1
- data/lib/polytypo/data/fixtures/tr.json +1 -1
- data/lib/polytypo/data/fixtures/uk.json +1 -1
- data/lib/polytypo/data/locales/nb.json +85 -0
- data/lib/polytypo/data/locales/registry.json +5 -3
- data/lib/polytypo/data/rules/locale-resolution.md +2 -2
- data/lib/polytypo/data/rules/order.json +1 -1
- data/lib/polytypo/version.rb +1 -1
- metadata +3 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: ef4d0c5b5f293055fd48d033c9b046d72155af1d8fdc9497564be447d4a66734
|
|
4
|
+
data.tar.gz: c28d5edfdfb62e7250a7d2d6afde0a21b2800c95e27bf170274e9247459cee5e
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: a0301c699a9eb013b831074efe6fe3279bf880fe09d2a9d27de2ffc9d400498892f7a36a6d08b4093c2cec925b7eab161b071901d705276750fac181403fc156
|
|
7
|
+
data.tar.gz: c30adcce6313ae82384dcd78f9a2e535055473e61acf72814d0d4d83791ab6104f0a5d4202847b552fec4c12c7729547962cf982eab4b24e7c2e48753eb0a339
|
data/lib/polytypo/data/VERSION
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
1.
|
|
1
|
+
1.27.0
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.27.0",
|
|
3
3
|
"cases": [
|
|
4
4
|
{
|
|
5
5
|
"id": "exact-en-us",
|
|
@@ -146,10 +146,10 @@
|
|
|
146
146
|
"throws": "POLYTYPO_UNKNOWN_LOCALE"
|
|
147
147
|
},
|
|
148
148
|
{
|
|
149
|
-
"id": "unknown-
|
|
150
|
-
"tag": "
|
|
149
|
+
"id": "unknown-nn-no",
|
|
150
|
+
"tag": "nn-NO",
|
|
151
151
|
"throws": "POLYTYPO_UNKNOWN_LOCALE",
|
|
152
|
-
"note": "section 4:
|
|
152
|
+
"note": "section 4: nn (Nynorsk) must not resolve to the nearest locale nb"
|
|
153
153
|
},
|
|
154
154
|
{
|
|
155
155
|
"id": "unknown-ja",
|
|
@@ -306,6 +306,24 @@
|
|
|
306
306
|
"tag": "da-DK",
|
|
307
307
|
"resolves": "da",
|
|
308
308
|
"note": "section 3.4 step 3a: the region strip reaches da, which needs no registry alias."
|
|
309
|
+
},
|
|
310
|
+
{
|
|
311
|
+
"id": "strip-nb-no",
|
|
312
|
+
"tag": "nb-NO",
|
|
313
|
+
"resolves": "nb",
|
|
314
|
+
"note": "section 3.4 step 3a: the region strip reaches nb, which needs no registry alias."
|
|
315
|
+
},
|
|
316
|
+
{
|
|
317
|
+
"id": "alias-no",
|
|
318
|
+
"tag": "no",
|
|
319
|
+
"resolves": "nb",
|
|
320
|
+
"note": "section 3.4 step 2: the registry alias no maps to nb."
|
|
321
|
+
},
|
|
322
|
+
{
|
|
323
|
+
"id": "alias-no-no",
|
|
324
|
+
"tag": "no-NO",
|
|
325
|
+
"resolves": "nb",
|
|
326
|
+
"note": "section 3.4 step 3b: the strip lands on the alias key no, so the alias is followed."
|
|
309
327
|
}
|
|
310
328
|
]
|
|
311
329
|
}
|
|
@@ -0,0 +1,315 @@
|
|
|
1
|
+
{
|
|
2
|
+
"spec": "1.27.0",
|
|
3
|
+
"locale": "nb",
|
|
4
|
+
"cases": [
|
|
5
|
+
{
|
|
6
|
+
"id": "nb-quotes-primary",
|
|
7
|
+
"rule": "quotes",
|
|
8
|
+
"mode": "text",
|
|
9
|
+
"in": "Han sa: \"Jeg er trøtt.\" og gikk.",
|
|
10
|
+
"out": "Han sa: «Jeg er trøtt.» og gikk.",
|
|
11
|
+
"note": "Språkrådet, «Hermeteikn»: «…» is the pinned primary form; the full stop of a quotation that is a sentence stays inside."
|
|
12
|
+
},
|
|
13
|
+
{
|
|
14
|
+
"id": "nb-quotes-nested-secondary",
|
|
15
|
+
"rule": "quotes",
|
|
16
|
+
"mode": "text",
|
|
17
|
+
"in": "Han sa: \"Hun sa 'ja' til meg\" og gikk.",
|
|
18
|
+
"out": "Han sa: «Hun sa ‘ja’ til meg» og gikk.",
|
|
19
|
+
"note": "Språkrådet, «Sitat i sitat»: a quotation inside a quotation takes single marks; ‘…’ is the pin among the three permitted single forms."
|
|
20
|
+
},
|
|
21
|
+
{
|
|
22
|
+
"id": "nb-quotes-nested-at-end",
|
|
23
|
+
"rule": "quotes",
|
|
24
|
+
"mode": "text",
|
|
25
|
+
"in": "Han sa: \"Hun sa 'ja'\" og gikk.",
|
|
26
|
+
"out": "Han sa: «Hun sa ‘ja’» og gikk.",
|
|
27
|
+
"note": "Språkrådet, «Sitat i sitat»: a nest that ends against the outer closer is still paired."
|
|
28
|
+
},
|
|
29
|
+
{
|
|
30
|
+
"id": "nb-quotes-already-typeset",
|
|
31
|
+
"rule": "quotes",
|
|
32
|
+
"mode": "text",
|
|
33
|
+
"in": "Han sa «ja» og gikk.",
|
|
34
|
+
"out": "Han sa «ja» og gikk.",
|
|
35
|
+
"note": "Språkrådet, «Hermeteikn»: text already carrying «…» is a fixed point."
|
|
36
|
+
},
|
|
37
|
+
{
|
|
38
|
+
"id": "nb-quotes-already-typeset-nested",
|
|
39
|
+
"rule": "quotes",
|
|
40
|
+
"mode": "text",
|
|
41
|
+
"in": "Han sa «hun sa ‘ja’ til meg» og gikk.",
|
|
42
|
+
"out": "Han sa «hun sa ‘ja’ til meg» og gikk.",
|
|
43
|
+
"note": "Språkrådet, «Sitat i sitat»: already-typeset nesting is a fixed point."
|
|
44
|
+
},
|
|
45
|
+
{
|
|
46
|
+
"id": "nb-quotes-double-curly-input",
|
|
47
|
+
"rule": "quotes",
|
|
48
|
+
"mode": "text",
|
|
49
|
+
"in": "Han sa “ja” og gikk.",
|
|
50
|
+
"out": "Han sa «ja» og gikk.",
|
|
51
|
+
"note": "Språkrådet, «Hermeteikn»: “…” is an equally correct form; the pin normalises it to «…»."
|
|
52
|
+
},
|
|
53
|
+
{
|
|
54
|
+
"id": "nb-quotes-low-high-input",
|
|
55
|
+
"rule": "quotes",
|
|
56
|
+
"mode": "text",
|
|
57
|
+
"in": "Han sa „ja“ og gikk.",
|
|
58
|
+
"out": "Han sa «ja» og gikk.",
|
|
59
|
+
"note": "Språkrådet, «Hermeteikn»: „…“ (also „…”) was common in print until about 1900 and is less common now; it is normalised to the pinned pair."
|
|
60
|
+
},
|
|
61
|
+
{
|
|
62
|
+
"id": "nb-quotes-danish-guillemets-input",
|
|
63
|
+
"rule": "quotes",
|
|
64
|
+
"mode": "text",
|
|
65
|
+
"in": "Han sa »ja« og gikk.",
|
|
66
|
+
"out": "Han sa «ja» og gikk.",
|
|
67
|
+
"note": "Språkrådet, «Hermeteikn»: the reversed pair »…« is not a Norwegian form in the pages read; it is normalised to «…»."
|
|
68
|
+
},
|
|
69
|
+
{
|
|
70
|
+
"id": "nb-quotes-no-inner-space",
|
|
71
|
+
"rule": "quotes",
|
|
72
|
+
"mode": "text",
|
|
73
|
+
"in": "Han sa: \" ja \" og gikk.",
|
|
74
|
+
"out": "Han sa: «ja» og gikk.",
|
|
75
|
+
"note": "Språkrådet, «Hermeteikn»: no example carries a space inside the marks (innerSpace none)."
|
|
76
|
+
},
|
|
77
|
+
{
|
|
78
|
+
"id": "nb-quotes-question-inside",
|
|
79
|
+
"rule": "quotes",
|
|
80
|
+
"mode": "text",
|
|
81
|
+
"in": "\"Hva?\" spurte han.",
|
|
82
|
+
"out": "«Hva?» spurte han.",
|
|
83
|
+
"note": "Språkrådet, «Hermeteikn»: a question mark that belongs to the quotation stays before the closing mark."
|
|
84
|
+
},
|
|
85
|
+
{
|
|
86
|
+
"id": "nb-ellipsis-three-dots",
|
|
87
|
+
"rule": "ellipsis",
|
|
88
|
+
"mode": "text",
|
|
89
|
+
"in": "Vent... og så.",
|
|
90
|
+
"out": "Vent… og så.",
|
|
91
|
+
"note": "Språkrådet, «Mellomrom», shows both three full stops («så ...») and the single character («Svarte f…!») without ruling between them; conversion to U+2026 is the engine's ellipsis rule (ellipsis.md), not a Språkrådet norm."
|
|
92
|
+
},
|
|
93
|
+
{
|
|
94
|
+
"id": "nb-ellipsis-before-question",
|
|
95
|
+
"rule": "ellipsis",
|
|
96
|
+
"mode": "text",
|
|
97
|
+
"in": "Er det nå...?",
|
|
98
|
+
"out": "Er det nå…?",
|
|
99
|
+
"note": "Språkrådet, «Mellomrom»: «eller ...?» puts the terminal mark after the dots; abbreviatedAfterTerminal is false."
|
|
100
|
+
},
|
|
101
|
+
{
|
|
102
|
+
"id": "nb-ellipsis-before-exclamation",
|
|
103
|
+
"rule": "ellipsis",
|
|
104
|
+
"mode": "text",
|
|
105
|
+
"in": "Hva nå...!",
|
|
106
|
+
"out": "Hva nå…!",
|
|
107
|
+
"note": "Språkrådet, «Mellomrom»: «Svarte f…!»: the terminal mark follows the dots."
|
|
108
|
+
},
|
|
109
|
+
{
|
|
110
|
+
"id": "nb-dashes-parenthetical",
|
|
111
|
+
"rule": "dashes",
|
|
112
|
+
"mode": "text",
|
|
113
|
+
"in": "Nå - ikke minst - går vi.",
|
|
114
|
+
"out": "Nå – ikke minst – går vi.",
|
|
115
|
+
"note": "Språkrådet, «Tankestrek»: «med ett mellomrom på begge sider»; the short dash U+2013."
|
|
116
|
+
},
|
|
117
|
+
{
|
|
118
|
+
"id": "nb-dashes-em-input",
|
|
119
|
+
"rule": "dashes",
|
|
120
|
+
"mode": "text",
|
|
121
|
+
"in": "Nå — ikke minst — går vi.",
|
|
122
|
+
"out": "Nå – ikke minst – går vi.",
|
|
123
|
+
"note": "Språkrådet, «Tankestrek»: «Vi bruker kort tankestrek (–), ikke lang (—)»; an em dash is normalised to the en dash."
|
|
124
|
+
},
|
|
125
|
+
{
|
|
126
|
+
"id": "nb-dashes-existing-en",
|
|
127
|
+
"rule": "dashes",
|
|
128
|
+
"mode": "text",
|
|
129
|
+
"in": "Nå – ikke minst – går vi.",
|
|
130
|
+
"out": "Nå – ikke minst – går vi.",
|
|
131
|
+
"note": "Språkrådet, «Tankestrek»: the spaced en dash is a fixed point."
|
|
132
|
+
},
|
|
133
|
+
{
|
|
134
|
+
"id": "nb-ranges-hyphen-converted",
|
|
135
|
+
"rule": "ranges",
|
|
136
|
+
"rules": {
|
|
137
|
+
"ranges": true
|
|
138
|
+
},
|
|
139
|
+
"mode": "text",
|
|
140
|
+
"in": "kapitlene 2-10",
|
|
141
|
+
"out": "kapitlene 2–10",
|
|
142
|
+
"note": "Språkrådet, «Tankestrek»: «kapitlene 2–10»: the range takes the en dash with no spaces; ranges.md §3.3.1 binds the dash with word joiners when a hyphen-typed range is converted."
|
|
143
|
+
},
|
|
144
|
+
{
|
|
145
|
+
"id": "nb-ranges-opening-hours",
|
|
146
|
+
"rule": "ranges",
|
|
147
|
+
"rules": {
|
|
148
|
+
"ranges": true
|
|
149
|
+
},
|
|
150
|
+
"mode": "text",
|
|
151
|
+
"in": "åpent 9-19",
|
|
152
|
+
"out": "åpent 9–19",
|
|
153
|
+
"note": "Språkrådet, «Mellomrom»: «opningstid: 9–19»; ranges.md §3.2 G4's one-digit against two-digit branch admits it."
|
|
154
|
+
},
|
|
155
|
+
{
|
|
156
|
+
"id": "nb-ranges-authored-unbound",
|
|
157
|
+
"rule": "ranges",
|
|
158
|
+
"rules": {
|
|
159
|
+
"ranges": true
|
|
160
|
+
},
|
|
161
|
+
"mode": "text",
|
|
162
|
+
"in": "kapitlene 2–10",
|
|
163
|
+
"out": "kapitlene 2–10",
|
|
164
|
+
"note": "Språkrådet, «Tankestrek»: an authored en-dash range is already correct and stays unbound; ranges.md §3.3.1 never makes an edit whose entire content is invisible."
|
|
165
|
+
},
|
|
166
|
+
{
|
|
167
|
+
"id": "nb-ranges-date-words-untouched",
|
|
168
|
+
"rule": "ranges",
|
|
169
|
+
"rules": {
|
|
170
|
+
"ranges": true
|
|
171
|
+
},
|
|
172
|
+
"mode": "text",
|
|
173
|
+
"in": "1. mai–10. september",
|
|
174
|
+
"out": "1. mai–10. september",
|
|
175
|
+
"note": "Språkrådet, «Tankestrek»: «1. mai–10. september»; the dash is not digit-flanked and is left as typed (ranges.md §3)."
|
|
176
|
+
},
|
|
177
|
+
{
|
|
178
|
+
"id": "nb-ranges-abbreviated-year-declined",
|
|
179
|
+
"rule": "ranges",
|
|
180
|
+
"rules": {
|
|
181
|
+
"ranges": true
|
|
182
|
+
},
|
|
183
|
+
"mode": "text",
|
|
184
|
+
"in": "årene 1349-54",
|
|
185
|
+
"out": "årene 1349-54",
|
|
186
|
+
"note": "Språkrådet, «Tankestrek»: the source writes «1349–54» with an abbreviated second member; ranges.md §3.2 G4 declines a four-and-two digit pair, a recorded miss."
|
|
187
|
+
},
|
|
188
|
+
{
|
|
189
|
+
"id": "nb-ranges-word-hyphen-untouched",
|
|
190
|
+
"rule": "ranges",
|
|
191
|
+
"rules": {
|
|
192
|
+
"ranges": true
|
|
193
|
+
},
|
|
194
|
+
"mode": "text",
|
|
195
|
+
"in": "e-post og EU-motstander",
|
|
196
|
+
"out": "e-post og EU-motstander",
|
|
197
|
+
"note": "Språkrådet, «Bindestrek»: a hyphen between letters is a compound hyphen and is untouched (ranges.md §3)."
|
|
198
|
+
},
|
|
199
|
+
{
|
|
200
|
+
"id": "nb-hyphen-noop",
|
|
201
|
+
"rule": "hyphen",
|
|
202
|
+
"mode": "text",
|
|
203
|
+
"in": "e-post og 50-årsdag og A4-format",
|
|
204
|
+
"out": "e-post og 50-årsdag og A4-format",
|
|
205
|
+
"note": "Språkrådet, «Bindestrek»: the hyphen is written in these compounds; the lists are empty, so nothing is bound."
|
|
206
|
+
},
|
|
207
|
+
{
|
|
208
|
+
"id": "nb-nbsp-spaced-units",
|
|
209
|
+
"rule": "nbsp",
|
|
210
|
+
"mode": "text",
|
|
211
|
+
"in": "Prisen er 25 % og 10 kr og 3 km og 5 kg og 7 cm og 38 °C",
|
|
212
|
+
"out": "Prisen er 25 % og 10 kr og 3 km og 5 kg og 7 cm og 38 °C",
|
|
213
|
+
"note": "Språkrådet, «Mellomrom»: «Det skal vere mellomrom mellom tal og (forkorta) nemningar» (10 kr, 5,68 kg, 10 %, +5 °C); «Prosentteikn og mellomrom»: a hard space is welcome."
|
|
214
|
+
},
|
|
215
|
+
{
|
|
216
|
+
"id": "nb-nbsp-spaced-unit-inserted",
|
|
217
|
+
"rule": "nbsp",
|
|
218
|
+
"mode": "text",
|
|
219
|
+
"in": "Prisen 25% og 10kr her",
|
|
220
|
+
"out": "Prisen 25 % og 10 kr her",
|
|
221
|
+
"note": "Språkrådet, «Mellomrom»: a missing space between the number and % or kr is supplied, as a no-break space."
|
|
222
|
+
},
|
|
223
|
+
{
|
|
224
|
+
"id": "nb-nbsp-spaced-unit-inserted-metric",
|
|
225
|
+
"rule": "nbsp",
|
|
226
|
+
"mode": "text",
|
|
227
|
+
"in": "Det er 3km og 5kg og 7cm og 38°C",
|
|
228
|
+
"out": "Det er 3 km og 5 kg og 7 cm og 38 °C",
|
|
229
|
+
"note": "Språkrådet, «Mellomrom»: the general rule for abbreviated designations, with °C exemplified."
|
|
230
|
+
},
|
|
231
|
+
{
|
|
232
|
+
"id": "nb-nbsp-kr-with-full-stop",
|
|
233
|
+
"rule": "nbsp",
|
|
234
|
+
"mode": "text",
|
|
235
|
+
"in": "Det koster 15 kr. i dag",
|
|
236
|
+
"out": "Det koster 15 kr. i dag",
|
|
237
|
+
"note": "Språkrådet, «Kronebeløp: rekkjefølgje, komma og strek»: «Etter kr skal det ikkje stå punktum, bortsett frå til slutt i setningar»; the engine accepts a full stop after kr (nbsp.md §3.7) and does not remove it, so the space is bound and the full stop stays."
|
|
238
|
+
},
|
|
239
|
+
{
|
|
240
|
+
"id": "nb-nbsp-single-letter-unit-inert",
|
|
241
|
+
"rule": "nbsp",
|
|
242
|
+
"mode": "text",
|
|
243
|
+
"in": "Det er 5 m og 3 g og 10 min",
|
|
244
|
+
"out": "Det er 5 m og 3 g og 10 min",
|
|
245
|
+
"note": "nbsp.md §3.7: single-letter and common-word units are not listed; min is also a Norwegian word."
|
|
246
|
+
},
|
|
247
|
+
{
|
|
248
|
+
"id": "nb-nbsp-degree-bare-inert",
|
|
249
|
+
"rule": "nbsp",
|
|
250
|
+
"mode": "text",
|
|
251
|
+
"in": "I dag 18 °C, men i går berre 5°.",
|
|
252
|
+
"out": "I dag 18 °C, men i går berre 5°.",
|
|
253
|
+
"note": "Språkrådet, «Mellomrom»: «I dag er det 18 °C, men i går var det berre 5°»; a bare degree sign is written closed up and is not a listed unit."
|
|
254
|
+
},
|
|
255
|
+
{
|
|
256
|
+
"id": "nb-nbsp-abbreviations-inert",
|
|
257
|
+
"rule": "nbsp",
|
|
258
|
+
"mode": "text",
|
|
259
|
+
"in": "f.eks. og m.a.o. og m.m.",
|
|
260
|
+
"out": "f.eks. og m.a.o. og m.m.",
|
|
261
|
+
"note": "Språkrådet, «Punktum»: Norwegian abbreviations are written without an inner space, so there is nothing to bind."
|
|
262
|
+
},
|
|
263
|
+
{
|
|
264
|
+
"id": "nb-nbsp-section-sign-inert",
|
|
265
|
+
"rule": "nbsp",
|
|
266
|
+
"mode": "text",
|
|
267
|
+
"in": "se § 10 og $ 10",
|
|
268
|
+
"out": "se § 10 og $ 10",
|
|
269
|
+
"note": "Språkrådet, «Mellomrom»: «§ 10» and «$ 10» are written with a space, but no source says the space is non-breaking, so it is left as typed."
|
|
270
|
+
},
|
|
271
|
+
{
|
|
272
|
+
"id": "nb-spaces-before-punctuation",
|
|
273
|
+
"rule": "spaces",
|
|
274
|
+
"mode": "text",
|
|
275
|
+
"in": "Hva nå ? Ikke !",
|
|
276
|
+
"out": "Hva nå? Ikke!",
|
|
277
|
+
"note": "Språkrådet, «Mellomrom»: no space is written before ? or !."
|
|
278
|
+
},
|
|
279
|
+
{
|
|
280
|
+
"id": "nb-spaces-brackets",
|
|
281
|
+
"rule": "spaces",
|
|
282
|
+
"mode": "text",
|
|
283
|
+
"in": "Han ( stille ) gikk .",
|
|
284
|
+
"out": "Han (stille) gikk.",
|
|
285
|
+
"note": "spaces.md: no space inside brackets or before a full stop."
|
|
286
|
+
},
|
|
287
|
+
{
|
|
288
|
+
"id": "nb-symbols-copyright",
|
|
289
|
+
"rule": "symbols",
|
|
290
|
+
"mode": "text",
|
|
291
|
+
"in": "(c) 2026",
|
|
292
|
+
"out": "© 2026",
|
|
293
|
+
"note": "symbols.md: (c) becomes ©."
|
|
294
|
+
},
|
|
295
|
+
{
|
|
296
|
+
"id": "nb-apostrophe-foreign-name",
|
|
297
|
+
"rule": "apostrophe",
|
|
298
|
+
"mode": "text",
|
|
299
|
+
"in": "O'Brien kom.",
|
|
300
|
+
"out": "O’Brien kom.",
|
|
301
|
+
"note": "apostrophe.md: a straight apostrophe inside a word becomes U+2019."
|
|
302
|
+
},
|
|
303
|
+
{
|
|
304
|
+
"id": "nb-quote-punctuation-none",
|
|
305
|
+
"rule": "quote-punctuation",
|
|
306
|
+
"rules": {
|
|
307
|
+
"quote-punctuation": true
|
|
308
|
+
},
|
|
309
|
+
"mode": "text",
|
|
310
|
+
"in": "alfa «beta», gamma",
|
|
311
|
+
"out": "alfa «beta», gamma",
|
|
312
|
+
"note": "Språkrådet, «Hermeteikn»: punctuationPlacement is none, because the full stop and question or exclamation mark go inside only when they belong to the quotation; the rule is a no-op and the comma stays where it stands."
|
|
313
|
+
}
|
|
314
|
+
]
|
|
315
|
+
}
|
|
@@ -0,0 +1,85 @@
|
|
|
1
|
+
{
|
|
2
|
+
"locale": "nb",
|
|
3
|
+
"name": "Norwegian Bokmål",
|
|
4
|
+
"quotes": {
|
|
5
|
+
"primary": {
|
|
6
|
+
"open": "«",
|
|
7
|
+
"close": "»",
|
|
8
|
+
"innerSpace": "none"
|
|
9
|
+
},
|
|
10
|
+
"secondary": {
|
|
11
|
+
"open": "‘",
|
|
12
|
+
"close": "’",
|
|
13
|
+
"innerSpace": "none"
|
|
14
|
+
},
|
|
15
|
+
"punctuationPlacement": "none",
|
|
16
|
+
"elisionIdioms": [],
|
|
17
|
+
"elisionClitics": {
|
|
18
|
+
"before": [],
|
|
19
|
+
"after": []
|
|
20
|
+
}
|
|
21
|
+
},
|
|
22
|
+
"dash": {
|
|
23
|
+
"parenthetical": "en-spaced",
|
|
24
|
+
"range": "en-tight"
|
|
25
|
+
},
|
|
26
|
+
"ellipsis": {
|
|
27
|
+
"abbreviatedAfterTerminal": false
|
|
28
|
+
},
|
|
29
|
+
"hyphen": {
|
|
30
|
+
"prefixes": [],
|
|
31
|
+
"suffixes": [],
|
|
32
|
+
"compounds": []
|
|
33
|
+
},
|
|
34
|
+
"nbsp": {
|
|
35
|
+
"beforePunctuation": [],
|
|
36
|
+
"narrowBeforePunctuation": [],
|
|
37
|
+
"afterShortWords": [],
|
|
38
|
+
"abbreviations": [],
|
|
39
|
+
"beforeUnits": [],
|
|
40
|
+
"spacedUnits": ["%", "kr", "km", "kg", "cm", "°C"],
|
|
41
|
+
"closedUnits": [],
|
|
42
|
+
"beforeNumber": [],
|
|
43
|
+
"beforeWord": [],
|
|
44
|
+
"afterSymbols": [],
|
|
45
|
+
"initialBinding": "none"
|
|
46
|
+
},
|
|
47
|
+
"sources": [
|
|
48
|
+
{
|
|
49
|
+
"rule": "quotes",
|
|
50
|
+
"cite": "Språkrådet, «Hermeteikn» (Godt og korrekt språk › Tegn); språkspørsmål «Hermeteikn, kva slags?» and «Sitat i sitat» (last updated 1 January 2024): «Dei to formene for hermeteikn som er vanlegast i norsk, er doble ″komma″ oppe og doble «vinkelteikn». Dei blir rekna som like rette»; «Eit sitat inni eit anna sitat bør helst markerast med enkle hermeteikn»; «Enkle vinklar er mindre brukt, men […] kan gjerne brukast»; «Komma skal setjast utanfor, anten det opphavleg høyrer til sitatet eller ikkje»",
|
|
51
|
+
"url": "https://sprakradet.no/godt-og-korrekt-sprak/rettskriving-og-grammatikk/tegn/hermeteikn/",
|
|
52
|
+
"note": "PICK-AND-PIN: «…» (U+00AB open, U+00BB close) with ‘…’ (U+2018, U+2019) inside. Språkrådet calls the doubled-comma form and the guillemet form equally correct, lists «…» first and as usual in books and newspapers, and reports, as far as it knows («Så vidt vi veit»), that Standard Norge and Microsoft agreed to make the guillemets the computer default; the doubled-comma form (”…” or “…”, U+201D or U+201C opening) is the equally correct rival and is normalised to the pinned pair. The »…« (U+00BB opening) reading in the issue is the Danish form and is not attested in any Språkrådet page read. Secondary: «Sitat i sitat» names single marks as the preferred inner level and uses ‘…’ in its examples; the Hermeteikn page also lists ’…’ (U+2019 both sides), which «Hermeteikn, kva slags?» calls the traditional Norwegian form («9 9 er det tradisjonelle i norsk») and the FAQ allows ‹…› (U+2039, U+203A), so the choice among the three single forms is a pin; ‘…’ is pinned because it is the form of the FAQ's own examples (including its gåsaugo ‘hermeteikn’) and keeps the opening and closing marks distinct. innerSpace none: no example has a space between a mark and the text. punctuationPlacement none: the comma goes outside, while the full stop and a question or exclamation mark go inside only when they belong to the quotation, so placement depends on meaning. ACCEPTED GAP: «Sitat i sitat» recommends a thin space (U+2009) between a double and a single mark that touch; the schema cannot express it, and an authored U+2009 is left untouched. elisionIdioms and elisionClitics empty: not addressed. Six of the nine pages read are in Nynorsk (Tankestrek, Punktum and Bindestrek are in Bokmål); Språkrådet publishes these rules on its common pages without a separate rule for the other written standard. Read 2026-11-15 via a text-extraction reader; direct fetch returned HTTP 403."
|
|
53
|
+
},
|
|
54
|
+
{
|
|
55
|
+
"rule": "dashes",
|
|
56
|
+
"cite": "Språkrådet, «Tankestrek» (Bokmål): «Tankestrek kan brukes ved innskudd og tilføyelse, med ett mellomrom («luft») på begge sider»; «Vi bruker kort tankestrek (–), ikke lang (—)»; «Tankestreken (–) er lengre enn bindestreken (-)»; «Mellomrom»: «Det skal vere mellomrom føre (og etter) ein tankestrek ved innskot og i liknande funksjonar»",
|
|
57
|
+
"url": "https://sprakradet.no/godt-og-korrekt-sprak/rettskriving-og-grammatikk/tegn/tankestrek/",
|
|
58
|
+
"note": "dash.parenthetical = en-spaced (U+0020 U+2013 U+0020). The spacing and the short dash are stated; the page names Alt+0150 (Windows-1252 0x96 = U+2013) and rejects the long dash U+2014, so an em dash is normalised to the en dash by citation. The dialogue dash (replikkstrek) is not encoded. Read 2026-11-15 via a text-extraction reader; direct fetch returned HTTP 403."
|
|
59
|
+
},
|
|
60
|
+
{
|
|
61
|
+
"rule": "ranges",
|
|
62
|
+
"cite": "Språkrådet, «Tankestrek»: «Streken svarer i slike tilfeller til fra ... til, mellom ... og» and «Her skal det ikke være mellomrom på hver side av tankestreken» (1. mai–10. september, årene 1349–54, kapitlene 2–10, 2–0); «Mellomrom»: «Det skal ikkje vere mellomrom føre og etter tankestrekar som viser tidsrom, avstandar» (opningstid: 9–19)",
|
|
63
|
+
"url": "https://sprakradet.no/godt-og-korrekt-sprak/rettskriving-og-grammatikk/tegn/tankestrek/",
|
|
64
|
+
"note": "dash.range = en-tight (U+2013, no spaces). Unlike Danish, Norwegian writes the range with the dash, not the hyphen. The abbreviated second member (1349–54) is Språkrådet's own example; the ranges rule's digit-run guards decide which of the typed forms are converted (ranges.md §3.2). Read 2026-11-15 via a text-extraction reader; direct fetch returned HTTP 403."
|
|
65
|
+
},
|
|
66
|
+
{
|
|
67
|
+
"rule": "ellipsis",
|
|
68
|
+
"cite": "Språkrådet, «Mellomrom» («eller ...?», «Svarte f…!») and «Punktum» («Han er vel ikke …?»)",
|
|
69
|
+
"url": "https://sprakradet.no/godt-og-korrekt-sprak/rettskriving-og-grammatikk/mellomrom/",
|
|
70
|
+
"note": "abbreviatedAfterTerminal = false: the terminal mark follows the dots in every example, so no source reduces the dots after ? or !. Spacing around the dots (a space before them when a word is omitted, none when letters are omitted) depends on what is omitted and is not encoded. Read 2026-11-15 via a text-extraction reader; direct fetch returned HTTP 403."
|
|
71
|
+
},
|
|
72
|
+
{
|
|
73
|
+
"rule": "hyphen",
|
|
74
|
+
"cite": "Språkrådet, «Bindestrek»: «Også der førsteleddet er et siffer e.l., skal ordet skrives med bindestrek» (2.-prioritetslån, 50-årsdag, A4-format); «Sammensetninger med en forkortelse eller en enkelt bokstav som førsteledd skal ha bindestrek» (e-post, EU-motstander)",
|
|
75
|
+
"url": "https://sprakradet.no/godt-og-korrekt-sprak/rettskriving-og-grammatikk/tegn/bindestrek/",
|
|
76
|
+
"note": "All three lists are empty: the page says when a hyphen is written, not where a line must not break. Read 2026-11-15 via a text-extraction reader; direct fetch returned HTTP 403."
|
|
77
|
+
},
|
|
78
|
+
{
|
|
79
|
+
"rule": "nbsp",
|
|
80
|
+
"cite": "Språkrådet, «Mellomrom»: «Det skal vere mellomrom mellom tal og (forkorta) nemningar anten nemninga står framfor talet eller etter det» (10 kr, 5,68 kg, 10 %, +5 °C, § 10); språkspørsmål «Prosentteikn og mellomrom» (last updated 1 January 2024): «Det rette er 25 %» and «Bruk gjerne det som heiter hardt eller fast mellomrom, så skil ikkje talet og teiknet lag ved linjeskift»; «Kronebeløp: rekkjefølgje, komma og strek»: «I vanleg tekst er 500 kr (eller helst 500 kroner) i utgangspunktet det beste» and «Etter kr skal det ikkje stå punktum»; «Punktum»: f.eks., m.a.o., m.m. written without an inner space",
|
|
81
|
+
"url": "https://sprakradet.no/godt-og-korrekt-sprak/rettskriving-og-grammatikk/mellomrom/",
|
|
82
|
+
"note": "(1) spacedUnits = % kr km kg cm °C: the space between number and unit is stated; a hard space is stated only for %, and the others take the same pin (as in `da`). 10 kr, 5,68 kg and +5 °C are exemplified; km and cm rest on the general rule for abbreviated designations. kr is listed without a full stop: «Kronebeløp» states «Etter kr skal det ikkje stå punktum, bortsett frå til slutt i setningar». A bare ° is written closed up in the source («5°»), so only the °C form is listed. Single-letter and common-word units (m, l, min) are excluded (nbsp.md §3.7). (2) closedUnits empty. (3) abbreviations empty: Norwegian abbreviations carry no inner space, so there is nothing to bind. (4) afterSymbols empty: «§ 10» and «$ 10» are written with a space, but no source says it is non-breaking. beforePunctuation, narrowBeforePunctuation, afterShortWords, beforeUnits, beforeNumber, beforeWord empty and initialBinding none: not addressed. Not expressible and so not covered: grouping of thousands with a space («3 562 987 675») and the prefix form «kr 500,–» and the whole-krone dash (Tankestrek: «Tankestrek kan brukes for å angi hele kronebeløp»). Read 2026-11-15 via a text-extraction reader; direct fetch returned HTTP 403."
|
|
83
|
+
}
|
|
84
|
+
]
|
|
85
|
+
}
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.27.0",
|
|
3
3
|
"$comment": "Locale resolution input. Algorithm is specified in spec/rules/locale-resolution.md and is identical in every runtime — never delegate it to a platform locale-negotiation library. \"spec\" here must track spec/VERSION exactly — it is not itself the global version source; scripts/validate-spec.mjs enforces the match.",
|
|
4
4
|
"locales": [
|
|
5
5
|
"en-US",
|
|
@@ -31,11 +31,13 @@
|
|
|
31
31
|
"lt",
|
|
32
32
|
"lv",
|
|
33
33
|
"et",
|
|
34
|
-
"da"
|
|
34
|
+
"da",
|
|
35
|
+
"nb"
|
|
35
36
|
],
|
|
36
37
|
"aliases": {
|
|
37
38
|
"en": "en-US",
|
|
38
39
|
"de": "de-DE",
|
|
39
|
-
"pt": "pt-PT"
|
|
40
|
+
"pt": "pt-PT",
|
|
41
|
+
"no": "nb"
|
|
40
42
|
}
|
|
41
43
|
}
|
|
@@ -132,7 +132,7 @@ module-level mutable state, reentrant).
|
|
|
132
132
|
|
|
133
133
|
- **Never fall back to English**, or to any other default, under any circumstance. Not on an
|
|
134
134
|
unknown language, not on a malformed tag, not on an empty string.
|
|
135
|
-
- **Never fall back to a "nearest" language.** `
|
|
135
|
+
- **Never fall back to a "nearest" language.** `nn` does not resolve to `nb`, `nl` does not
|
|
136
136
|
resolve to `de`, `pt` does not resolve to `fr`.
|
|
137
137
|
- **Never fall back to the first entry of `registry.locales`.**
|
|
138
138
|
- **Never consult the host environment** — `LANG`, `LC_ALL`, `navigator.language`,
|
|
@@ -177,7 +177,7 @@ Against `spec/locales/registry.json` as of spec 0.2.0:
|
|
|
177
177
|
| `DE` | `de` | canonicalise, alias | `de-DE` |
|
|
178
178
|
| `xx-YY` | `xx-YY` | no exact, no alias, strip → `xx`, no exact, no alias | **throw** `POLYTYPO_UNKNOWN_LOCALE` |
|
|
179
179
|
| `xx` | `xx` | no exact, no alias, nothing to strip | **throw** `POLYTYPO_UNKNOWN_LOCALE` |
|
|
180
|
-
| `
|
|
180
|
+
| `nn-NO` | `nn-NO` | strip → `nn`, miss | **throw** `POLYTYPO_UNKNOWN_LOCALE` |
|
|
181
181
|
| `eng` | — | fails §3.3 (length 3) | **throw** `POLYTYPO_UNKNOWN_LOCALE` |
|
|
182
182
|
| `sr-Latn` | — | fails §3.3 (length 7) | **throw** `POLYTYPO_UNKNOWN_LOCALE` |
|
|
183
183
|
| `es-419` | — | fails §3.3 (region not `A`–`Z`) | **throw** `POLYTYPO_UNKNOWN_LOCALE` |
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
{
|
|
2
|
-
"spec": "1.
|
|
2
|
+
"spec": "1.27.0",
|
|
3
3
|
"$comment": "Single source of truth for pipeline order. Rules run in ascending `order`. Disabling a rule removes it from the sequence and never reorders the rest. Rule ids are public API (see docs/ARCHITECTURE.md section 5). \"spec\" here must track spec/VERSION exactly — it is not itself the global version source; scripts/validate-spec.mjs enforces the match.",
|
|
4
4
|
"rules": [
|
|
5
5
|
{
|
data/lib/polytypo/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: polytypo
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 1.
|
|
4
|
+
version: 1.27.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Iurii Rogulia
|
|
@@ -59,6 +59,7 @@ files:
|
|
|
59
59
|
- lib/polytypo/data/fixtures/locale-resolution.json
|
|
60
60
|
- lib/polytypo/data/fixtures/lt.json
|
|
61
61
|
- lib/polytypo/data/fixtures/lv.json
|
|
62
|
+
- lib/polytypo/data/fixtures/nb.json
|
|
62
63
|
- lib/polytypo/data/fixtures/nl.json
|
|
63
64
|
- lib/polytypo/data/fixtures/pl.json
|
|
64
65
|
- lib/polytypo/data/fixtures/pt-BR.json
|
|
@@ -89,6 +90,7 @@ files:
|
|
|
89
90
|
- lib/polytypo/data/locales/it.json
|
|
90
91
|
- lib/polytypo/data/locales/lt.json
|
|
91
92
|
- lib/polytypo/data/locales/lv.json
|
|
93
|
+
- lib/polytypo/data/locales/nb.json
|
|
92
94
|
- lib/polytypo/data/locales/nl.json
|
|
93
95
|
- lib/polytypo/data/locales/pl.json
|
|
94
96
|
- lib/polytypo/data/locales/pt-BR.json
|