polytypo 1.28.0 → 1.30.0

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.
Files changed (45) hide show
  1. checksums.yaml +4 -4
  2. data/README.md +4 -0
  3. data/lib/polytypo/data/VERSION +1 -1
  4. data/lib/polytypo/data/fixtures/bg.json +1 -1
  5. data/lib/polytypo/data/fixtures/cs.json +1 -1
  6. data/lib/polytypo/data/fixtures/da.json +1 -1
  7. data/lib/polytypo/data/fixtures/de-CH.json +1 -1
  8. data/lib/polytypo/data/fixtures/de-DE.json +1 -1
  9. data/lib/polytypo/data/fixtures/el.json +1 -1
  10. data/lib/polytypo/data/fixtures/en-GB.json +1 -1
  11. data/lib/polytypo/data/fixtures/en-US.json +1 -1
  12. data/lib/polytypo/data/fixtures/es.json +1 -1
  13. data/lib/polytypo/data/fixtures/et.json +1 -1
  14. data/lib/polytypo/data/fixtures/fi.json +1 -1
  15. data/lib/polytypo/data/fixtures/fr-CA.json +1 -1
  16. data/lib/polytypo/data/fixtures/fr.json +1 -1
  17. data/lib/polytypo/data/fixtures/hr.json +1 -1
  18. data/lib/polytypo/data/fixtures/hu.json +1 -1
  19. data/lib/polytypo/data/fixtures/it.json +1 -1
  20. data/lib/polytypo/data/fixtures/locale-resolution.json +13 -1
  21. data/lib/polytypo/data/fixtures/lt.json +1 -1
  22. data/lib/polytypo/data/fixtures/lv.json +1 -1
  23. data/lib/polytypo/data/fixtures/nb.json +1 -1
  24. data/lib/polytypo/data/fixtures/nl.json +1 -1
  25. data/lib/polytypo/data/fixtures/nn.json +1 -1
  26. data/lib/polytypo/data/fixtures/pl.json +1 -1
  27. data/lib/polytypo/data/fixtures/pt-BR.json +1 -1
  28. data/lib/polytypo/data/fixtures/pt-PT.json +1 -1
  29. data/lib/polytypo/data/fixtures/ro.json +1 -1
  30. data/lib/polytypo/data/fixtures/ru.json +1 -1
  31. data/lib/polytypo/data/fixtures/sk.json +1 -1
  32. data/lib/polytypo/data/fixtures/sl.json +1 -1
  33. data/lib/polytypo/data/fixtures/sq.json +255 -0
  34. data/lib/polytypo/data/fixtures/sr.json +1 -1
  35. data/lib/polytypo/data/fixtures/sv.json +1 -1
  36. data/lib/polytypo/data/fixtures/tr.json +1 -1
  37. data/lib/polytypo/data/fixtures/uk.json +1 -1
  38. data/lib/polytypo/data/locales/registry.json +3 -2
  39. data/lib/polytypo/data/locales/sq.json +85 -0
  40. data/lib/polytypo/data/rules/modes.md +11 -1
  41. data/lib/polytypo/data/rules/order.json +1 -1
  42. data/lib/polytypo/modes/html.rb +1 -1
  43. data/lib/polytypo/version.rb +1 -1
  44. data/lib/polytypo.rb +4 -0
  45. metadata +3 -1
checksums.yaml CHANGED
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  SHA256:
3
- metadata.gz: f416a8e2de674b261b99f2fd49baeb30c0027ab5821e92609c330a6ba13e5b9a
4
- data.tar.gz: fec989762e6dd2f9516aa9c94ac2ea8c2ff8be153453fafb28dd09c788276fb5
3
+ metadata.gz: 6e79003b325556a7bc53483e49a67e9c8b85bc502ba6a76eb6ffe0fb310b8ce8
4
+ data.tar.gz: c00d0eeded7fc2cdd43cd9eca6e46faa04838c9d750ce9580df382b8763b744d
5
5
  SHA512:
6
- metadata.gz: 17444f41b1f6fa46be1f683ac36a57c65542c4137efacad3afd9f39d625025e4cec62bdf90cb2d88fe4e024af50f0e7dd2a681e8b7ac343e3dd7f1cc87065225
7
- data.tar.gz: 60b5153c47f5a6301b10ada9712d593e7082629d01733f4a08e7a0384081bbdfd377e9fe6003128b713d88e9d217185f7618d9ec374ef7bd023bd3dd5787fcbc
6
+ metadata.gz: 05f98cbb256c36f883ac8c405fb5d3b3fffb991ce8fdfaacf2a0a1bd936b36ad26f5190bd2e7d9ac8543a77f60a843617db9138739c681e908c47a9b6eb721b2
7
+ data.tar.gz: db2c38cfc1234349ab077dbe4e08b6e3546fdd3e866d9e67995fba813d7059c403d495798bd25bc184b899fbd0443642c2c431a2bc744bdd22eab09e7d79d9b0
data/README.md CHANGED
@@ -62,6 +62,10 @@ Polytypo.transform(%q{<a title="test... wait">Wait... she said "go on."</a>}, lo
62
62
  # => "<a title=\"test... wait\">Wait… she said “go on.”</a>"
63
63
  ```
64
64
 
65
+ `html` mode leaves ten elements alone, with everything inside them: `code`, `pre`, `kbd`, `samp`,
66
+ `var`, `script`, `style`, `textarea`, `svg` and `math`. If you walk a document with a parser of your
67
+ own, read `Polytypo::SKIPPED_ELEMENTS` instead of copying the names; it is a frozen array.
68
+
65
69
  `locale:` has no default anywhere and must always be passed explicitly — there is no silent
66
70
  fallback to English. `mode:` defaults to `"text"` if omitted.
67
71
 
@@ -1 +1 @@
1
- 1.28.0
1
+ 1.30.0
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "bg",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "cs",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "da",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "de-CH",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "de-DE",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "el",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "en-GB",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "en-US",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "es",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "et",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "fi",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "fr-CA",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "fr",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "hr",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "hu",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "it",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "cases": [
4
4
  {
5
5
  "id": "exact-en-us",
@@ -319,6 +319,18 @@
319
319
  "resolves": "nn",
320
320
  "note": "section 3.4 step 3a: the region strip reaches nn, which needs no registry alias."
321
321
  },
322
+ {
323
+ "id": "strip-sq-al",
324
+ "tag": "sq-AL",
325
+ "resolves": "sq",
326
+ "note": "section 3.4 step 3a: the region strip reaches sq, which needs no registry alias."
327
+ },
328
+ {
329
+ "id": "strip-sq-xk",
330
+ "tag": "sq-XK",
331
+ "resolves": "sq",
332
+ "note": "section 3.4 step 3a: the region strip reaches sq, which needs no registry alias."
333
+ },
322
334
  {
323
335
  "id": "alias-no",
324
336
  "tag": "no",
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "lt",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "lv",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "nb",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "nl",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "nn",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "pl",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "pt-BR",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "pt-PT",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "ro",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "ru",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "sk",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "sl",
4
4
  "cases": [
5
5
  {
@@ -0,0 +1,255 @@
1
+ {
2
+ "spec": "1.30.0",
3
+ "locale": "sq",
4
+ "cases": [
5
+ {
6
+ "id": "sq-quotes-primary",
7
+ "rule": "quotes",
8
+ "mode": "text",
9
+ "in": "Ai tha: \"Jam i lodhur.\" dhe iku.",
10
+ "out": "Ai tha: “Jam i lodhur.” dhe iku.",
11
+ "note": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), ch. 8 footnote: “…” is the pinned primary form; the full stop of a quotation that is an independent sentence stays inside (§145 Shënim 2)."
12
+ },
13
+ {
14
+ "id": "sq-quotes-nested-secondary",
15
+ "rule": "quotes",
16
+ "mode": "text",
17
+ "in": "Ai tha: \"Ajo tha 'po' mua\" dhe iku.",
18
+ "out": "Ai tha: “Ajo tha ‘po’ mua” dhe iku.",
19
+ "note": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), §150 Shënim 2: a quotation inside a quotation takes single marks; ‘…’ is the pin."
20
+ },
21
+ {
22
+ "id": "sq-quotes-nested-at-end",
23
+ "rule": "quotes",
24
+ "mode": "text",
25
+ "in": "Ai tha: \"Ajo tha 'po'\" dhe iku.",
26
+ "out": "Ai tha: “Ajo tha ‘po’” dhe iku.",
27
+ "note": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), §150 Shënim 2: a nest that ends against the outer closer is still paired."
28
+ },
29
+ {
30
+ "id": "sq-quotes-already-typeset",
31
+ "rule": "quotes",
32
+ "mode": "text",
33
+ "in": "Ai tha “po” dhe iku.",
34
+ "out": "Ai tha “po” dhe iku.",
35
+ "note": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), ch. 8 footnote: text already carrying “…” is a fixed point."
36
+ },
37
+ {
38
+ "id": "sq-quotes-already-typeset-nested",
39
+ "rule": "quotes",
40
+ "mode": "text",
41
+ "in": "Ai tha “ajo tha ‘po’ mua” dhe iku.",
42
+ "out": "Ai tha “ajo tha ‘po’ mua” dhe iku.",
43
+ "note": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), §150 Shënim 2: already-typeset nesting is a fixed point."
44
+ },
45
+ {
46
+ "id": "sq-quotes-french-input",
47
+ "rule": "quotes",
48
+ "mode": "text",
49
+ "in": "Ai tha «po» dhe iku.",
50
+ "out": "Ai tha “po” dhe iku.",
51
+ "note": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), ch. 8 footnote: «…» is the permitted, less used form; the pin normalises it to “…”."
52
+ },
53
+ {
54
+ "id": "sq-quotes-low-high-input",
55
+ "rule": "quotes",
56
+ "mode": "text",
57
+ "in": "Ai tha „po“ dhe iku.",
58
+ "out": "Ai tha “po” dhe iku.",
59
+ "note": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), ch. 8: „…“ is not among the forms the source gives; it is normalised to the pinned pair."
60
+ },
61
+ {
62
+ "id": "sq-quotes-no-inner-space",
63
+ "rule": "quotes",
64
+ "mode": "text",
65
+ "in": "Ai tha: \" po \" dhe iku.",
66
+ "out": "Ai tha: “po” dhe iku.",
67
+ "note": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), §175: «Nuk lihen hapësira të bardha midis thonjëzave dhe tekstit futur brenda tyre»; innerSpace none."
68
+ },
69
+ {
70
+ "id": "sq-quotes-question-inside",
71
+ "rule": "quotes",
72
+ "mode": "text",
73
+ "in": "\"Pse?\" pyeti ai.",
74
+ "out": "“Pse?” pyeti ai.",
75
+ "note": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), §145 Shënim 2 and §150 Shënim 1: punctuation placement follows meaning; a question mark that belongs to the quotation stays inside."
76
+ },
77
+ {
78
+ "id": "sq-ellipsis-three-dots",
79
+ "rule": "ellipsis",
80
+ "mode": "text",
81
+ "in": "Prit... pastaj.",
82
+ "out": "Prit… pastaj.",
83
+ "note": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), ch. 7: the ellipsis is three consecutive dots; the engine sets them as one U+2026."
84
+ },
85
+ {
86
+ "id": "sq-ellipsis-before-question",
87
+ "rule": "ellipsis",
88
+ "mode": "text",
89
+ "in": "A është kjo...?",
90
+ "out": "A është kjo…?",
91
+ "note": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), §140 example «të mykura?...»: three dots stay with the terminal mark; abbreviatedAfterTerminal is false."
92
+ },
93
+ {
94
+ "id": "sq-ellipsis-before-exclamation",
95
+ "rule": "ellipsis",
96
+ "mode": "text",
97
+ "in": "Çfarë tani...!",
98
+ "out": "Çfarë tani…!",
99
+ "note": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), ch. 7: abbreviatedAfterTerminal is false; the dots are kept before «!»."
100
+ },
101
+ {
102
+ "id": "sq-dashes-parenthetical",
103
+ "rule": "dashes",
104
+ "mode": "text",
105
+ "in": "Libri - botuar para luftës - është i mirë.",
106
+ "out": "Libri – botuar para luftës – është i mirë.",
107
+ "note": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), §175: «Vizat paraprihen dhe ndiqen gjithmonë nga një hapësirë e bardhë»; U+2013 is the pin."
108
+ },
109
+ {
110
+ "id": "sq-dashes-em-input",
111
+ "rule": "dashes",
112
+ "mode": "text",
113
+ "in": "Libri — botuar para luftës — është i mirë.",
114
+ "out": "Libri – botuar para luftës – është i mirë.",
115
+ "note": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), §165 and §175: an em dash typed as the inserted-clause dash is normalised to the pinned spaced en dash."
116
+ },
117
+ {
118
+ "id": "sq-dashes-existing-en",
119
+ "rule": "dashes",
120
+ "mode": "text",
121
+ "in": "Libri – botuar para luftës – është i mirë.",
122
+ "out": "Libri – botuar para luftës – është i mirë.",
123
+ "note": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), §175: already-typeset spaced en dashes are a fixed point."
124
+ },
125
+ {
126
+ "id": "sq-ranges-none-hyphen-untouched",
127
+ "rule": "ranges",
128
+ "mode": "text",
129
+ "in": "vitet 1939-1944",
130
+ "out": "vitet 1939-1944",
131
+ "note": "Akademia e Shkencave e RP të Shqipërisë, «Drejtshkrimi i gjuhës shqipe» (1973), §68 and §69 disagree on one shape (hyphen for approximations and numbers, long dash for time spans); ranges.md §2: dash.range \"none\" disables the rule, so the hyphen is left as typed.",
132
+ "rules": {
133
+ "ranges": true
134
+ }
135
+ },
136
+ {
137
+ "id": "sq-ranges-none-approximate-quantity",
138
+ "rule": "ranges",
139
+ "mode": "text",
140
+ "in": "për 5-6 ditë",
141
+ "out": "për 5-6 ditë",
142
+ "note": "Akademia e Shkencave e RP të Shqipërisë, «Drejtshkrimi i gjuhës shqipe» (1973), §68 a): a hyphen marks an approximate quantity; ranges.md §2: dash.range \"none\" leaves it untouched.",
143
+ "rules": {
144
+ "ranges": true
145
+ }
146
+ },
147
+ {
148
+ "id": "sq-hyphen-noop",
149
+ "rule": "hyphen",
150
+ "mode": "text",
151
+ "in": "e-mail dhe 50-vjetor dhe A4-format",
152
+ "out": "e-mail dhe 50-vjetor dhe A4-format",
153
+ "note": "Akademia e Shkencave e RP të Shqipërisë, «Drejtshkrimi i gjuhës shqipe» (1973), §99 b): the line-break constraint is not expressible, so the hyphen lists are empty and the rule leaves the text unchanged."
154
+ },
155
+ {
156
+ "id": "sq-nbsp-units-bound",
157
+ "rule": "nbsp",
158
+ "mode": "text",
159
+ "in": "Rruga është 3 km dhe 5 kg dhe 7 cm dhe 4 dm dhe 90 ha",
160
+ "out": "Rruga është 3 km dhe 5 kg dhe 7 cm dhe 4 dm dhe 90 ha",
161
+ "note": "Akademia e Shkencave e RP të Shqipërisë, «Drejtshkrimi i gjuhës shqipe» (1973), §99 ç): measure abbreviations do not break from the preceding number; beforeUnits binds the written space with U+00A0."
162
+ },
163
+ {
164
+ "id": "sq-nbsp-square-unit",
165
+ "rule": "nbsp",
166
+ "mode": "text",
167
+ "in": "Sipërfaqja është 28 800 km² këtu",
168
+ "out": "Sipërfaqja është 28 800 km² këtu",
169
+ "note": "Akademia e Shkencave e RP të Shqipërisë, «Drejtshkrimi i gjuhës shqipe» (1973), §99 ç): «28 800 km²» is an example of a measure that does not break from its number."
170
+ },
171
+ {
172
+ "id": "sq-nbsp-unit-touching-inert",
173
+ "rule": "nbsp",
174
+ "mode": "text",
175
+ "in": "Rruga është 3km dhe 5kg",
176
+ "out": "Rruga është 3km dhe 5kg",
177
+ "note": "Akademia e Shkencave e RP të Shqipërisë, «Drejtshkrimi i gjuhës shqipe» (1973), §99 ç): the source states that the unit stays with the number, not whether a missing space is inserted; beforeUnits only converts a written space, so touching text is untouched."
178
+ },
179
+ {
180
+ "id": "sq-nbsp-percent-inert",
181
+ "rule": "nbsp",
182
+ "mode": "text",
183
+ "in": "Rritja është 100 % dhe 100% dhe 30‰ këtu",
184
+ "out": "Rritja është 100 % dhe 100% dhe 30‰ këtu",
185
+ "note": "Akademia e Shkencave e RP të Shqipërisë, «Drejtshkrimi i gjuhës shqipe» (1973), §99 ç) and p. 132: % and ‰ are printed closed up, which is typesetting and not a stated rule; neither is listed, so the text is untouched."
186
+ },
187
+ {
188
+ "id": "sq-nbsp-section-sign",
189
+ "rule": "nbsp",
190
+ "mode": "text",
191
+ "in": "shih § 12 dhe § 67",
192
+ "out": "shih § 12 dhe § 67",
193
+ "note": "Akademia e Shkencave e RP të Shqipërisë, «Drejtshkrimi i gjuhës shqipe» (1973), §99 d): the paragraph sign does not break from its number; afterSymbols binds it with U+00A0."
194
+ },
195
+ {
196
+ "id": "sq-nbsp-single-letter-unit-inert",
197
+ "rule": "nbsp",
198
+ "mode": "text",
199
+ "in": "Ka 5 m dhe 3 g dhe 2 l",
200
+ "out": "Ka 5 m dhe 3 g dhe 2 l",
201
+ "note": "nbsp.md §3.7: single-letter units cannot be told from words and are not listed; the text is untouched."
202
+ },
203
+ {
204
+ "id": "sq-nbsp-degree-inert",
205
+ "rule": "nbsp",
206
+ "mode": "text",
207
+ "in": "Sot 18 °C dhe 5 €",
208
+ "out": "Sot 18 °C dhe 5 €",
209
+ "note": "Akademia e Shkencave e RP të Shqipërisë, «Drejtshkrimi i gjuhës shqipe» (1973): neither °C nor a currency is addressed; the lists carry no entry and the text is untouched."
210
+ },
211
+ {
212
+ "id": "sq-spaces-before-punctuation",
213
+ "rule": "spaces",
214
+ "mode": "text",
215
+ "in": "Pse ? Jo !",
216
+ "out": "Pse? Jo!",
217
+ "note": "Locale-independent spaces rule: no sq-specific spacing before terminal marks is claimed."
218
+ },
219
+ {
220
+ "id": "sq-spaces-brackets",
221
+ "rule": "spaces",
222
+ "mode": "text",
223
+ "in": "Ai ( i qetë ) shkoi .",
224
+ "out": "Ai (i qetë) shkoi.",
225
+ "note": "Locale-independent spaces rule: no sq-specific bracket spacing is claimed."
226
+ },
227
+ {
228
+ "id": "sq-symbols-copyright",
229
+ "rule": "symbols",
230
+ "mode": "text",
231
+ "in": "(c) 2026",
232
+ "out": "© 2026",
233
+ "note": "Locale-independent symbols rule."
234
+ },
235
+ {
236
+ "id": "sq-apostrophe-foreign-name",
237
+ "rule": "apostrophe",
238
+ "mode": "text",
239
+ "in": "O'Brien erdhi.",
240
+ "out": "O’Brien erdhi.",
241
+ "note": "Locale-independent apostrophe rule: the straight apostrophe in a name becomes U+2019; elisionIdioms and elisionClitics are empty because the sources do not address them."
242
+ },
243
+ {
244
+ "id": "sq-quote-punctuation-none",
245
+ "rule": "quote-punctuation",
246
+ "mode": "text",
247
+ "in": "alfa “beta”, gamma",
248
+ "out": "alfa “beta”, gamma",
249
+ "note": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), §145 Shënim 2 and §150 Shënim 1: placement follows meaning, so punctuationPlacement is none and the rule does not move the comma.",
250
+ "rules": {
251
+ "quote-punctuation": true
252
+ }
253
+ }
254
+ ]
255
+ }
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "sr",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "sv",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "tr",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
3
3
  "locale": "uk",
4
4
  "cases": [
5
5
  {
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
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",
@@ -33,7 +33,8 @@
33
33
  "et",
34
34
  "da",
35
35
  "nb",
36
- "nn"
36
+ "nn",
37
+ "sq"
37
38
  ],
38
39
  "aliases": {
39
40
  "en": "en-US",
@@ -0,0 +1,85 @@
1
+ {
2
+ "locale": "sq",
3
+ "name": "Albanian",
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": "none"
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": ["km", "kg", "cm", "dm", "ha", "km²"],
40
+ "spacedUnits": [],
41
+ "closedUnits": [],
42
+ "beforeNumber": [],
43
+ "beforeWord": [],
44
+ "afterSymbols": ["§"],
45
+ "initialBinding": "none"
46
+ },
47
+ "sources": [
48
+ {
49
+ "rule": "quotes",
50
+ "cite": "Akademia e Shkencave e Shqipërisë, Instituti i Gjuhësisë dhe i Letërsisë, «Rregullat e pikësimit në gjuhën shqipe» (Shkenca, Tiranë 2002), ch. 8 «Thonjëzat», footnote p. 88: «Thonjëzat mund të realizohen grafikisht në dy forma që nuk paraqesin ndonjë ndryshim në përdorim. Thonjëzat e larta (“ ”) të quajtura dhe angleze, janë më të zakonshme në kompjuter. Thonjëzat e ulta (« ») të quajtura edhe franceze janë më pak të përdorshme»; §150 Shënim 2: «Duhet të përdoren edhe thonjëzat njëshe, në qoftë se përdoren thonjëzat brenda një teksti të mbyllur në thonjëza»; §175: «Nuk lihen hapësira të bardha midis thonjëzave dhe tekstit të futur brenda tyre»; §145 Shënim 2 and §150 Shënim 1 (full stop inside only when the quoted part is a syntactically independent sentence)",
51
+ "url": "https://archive.org/download/rregullat-e-pikesimit-ne-gjuhen-shqipe-akademia-e-shkencave-e-shqiperise-2002/Rregullat%20e%20pik%C3%ABsimit%20n%C3%AB%20gjuh%C3%ABn%20shqipe%2C%20Akademia%20e%20Shkencave%20e%20Shqip%C3%ABris%C3%AB%20%282002%29.pdf",
52
+ "note": "PICK-AND-PIN: “…” (U+201C, U+201D) with ‘…’ (U+2018, U+2019) inside. The source calls both forms equal in use and names the high marks the more common on a computer; every example in §§145–153 uses them. «…» (U+00AB, U+00BB) is the permitted, less used form, and the 1973 Drejtshkrimi uses it in its examples. »…« is not attested in any source read. innerSpace none. punctuationPlacement none: placement follows meaning, per §145 Shënim 2 and §150 Shënim 1. elisionIdioms and elisionClitics empty: not addressed. Read 2026-11-16 from archive.org page images of the scan."
53
+ },
54
+ {
55
+ "rule": "dashes",
56
+ "cite": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), §165: «Viza përdoret për të veçuar fjalitë e ndërkallura»; §175: «Vizat paraprihen dhe ndiqen gjithmonë nga një hapësirë e bardhë: tekst – fjali e ndërkallur – tekst»",
57
+ "url": "https://archive.org/download/rregullat-e-pikesimit-ne-gjuhen-shqipe-akademia-e-shkencave-e-shqiperise-2002/Rregullat%20e%20pik%C3%ABsimit%20n%C3%AB%20gjuh%C3%ABn%20shqipe%2C%20Akademia%20e%20Shkencave%20e%20Shqip%C3%ABris%C3%AB%20%282002%29.pdf",
58
+ "note": "dash.parenthetical = en-spaced (U+0020 U+2013 U+0020). The spacing is normative. The code point is PICK-AND-PIN: both sources call the dash «viza e gjatë» (2002 §163 and p. 109; 1973 §69), which sets it against the hyphen, «vizë lidhëse», and does not name en or em; the 2002 rules print it short throughout (heading «10. VIZA (–)») and the 1973 Drejtshkrimi prints it long. U+2013 is pinned. Read 2026-11-16 from archive.org page images of the scan."
59
+ },
60
+ {
61
+ "rule": "ranges",
62
+ "cite": "Akademia e Shkencave e RP të Shqipërisë, Instituti i Gjuhësisë dhe i Letërsisë, «Drejtshkrimi i gjuhës shqipe» (Tiranë 1973), §69 b): «Shkruhen me vizë të gjatë në mes tyre: … numërorët që shënojnë caqet e një hapësire kohore: periudha 1939—1944»; §68 a): approximate quantities take a hyphen, «10-15 vjet», «5-6 ditë»; §68 i): «27-51, 25-09»",
63
+ "url": "https://www.klasaletersi.com/wp-content/uploads/2017/03/Drejtshrimi-i-gjuh%C3%ABs-shqipe-1973.pdf",
64
+ "note": "dash.range = none. The source asks for a long dash in time spans and for a hyphen in approximate quantities and number groups of the same shape («5-6 ditë», «27-51»); the ranges rule reads only code points and cannot tell them apart, so converting would break the second norm. Read 2026-11-16 from the scan."
65
+ },
66
+ {
67
+ "rule": "ellipsis",
68
+ "cite": "Akademia e Shkencave e Shqipërisë, «Rregullat e pikësimit në gjuhën shqipe» (2002), ch. 7: «Shumëpikëshi është shenjë pikësimi e përbërë prej tri pikash të njëpasnjëshme»; §175: «… tre pikat vijnë menjëherë pas shkronjës së fundit»; §140 example «të mykura?...»",
69
+ "url": "https://archive.org/download/rregullat-e-pikesimit-ne-gjuhen-shqipe-akademia-e-shkencave-e-shqiperise-2002/Rregullat%20e%20pik%C3%ABsimit%20n%C3%AB%20gjuh%C3%ABn%20shqipe%2C%20Akademia%20e%20Shkencave%20e%20Shqip%C3%ABris%C3%AB%20%282002%29.pdf",
70
+ "note": "abbreviatedAfterTerminal = false: the example keeps three dots after a question mark. Read 2026-11-16 from archive.org page images of the scan."
71
+ },
72
+ {
73
+ "rule": "hyphen",
74
+ "cite": "Akademia e Shkencave e RP të Shqipërisë, «Drejtshkrimi i gjuhës shqipe» (1973), §99 b): ordinal suffixes after Arabic numerals and endings written with a hyphen are not divided at line end («Kongresi i 6-të», «SMT-ja, PTT-së, TEC-it»)",
75
+ "url": "https://www.klasaletersi.com/wp-content/uploads/2017/03/Drejtshrimi-i-gjuh%C3%ABs-shqipe-1973.pdf",
76
+ "note": "All three lists are empty: the constraint cannot be expressed, because a hyphen-rule suffix must follow a letter while here it follows a digit or an open set of abbreviations. The source is not silent. Read 2026-11-16 from the scan."
77
+ },
78
+ {
79
+ "rule": "nbsp",
80
+ "cite": "Akademia e Shkencave e RP të Shqipërisë, «Drejtshkrimi i gjuhës shqipe» (1973), §99 ç): «Nuk ndahen në fund të rreshtit: … shkurtimet e njësive të masave dhe shenjat e përqindjes e të përmijës nga shifra që u prin: … 35 cm, 50 dm, 40 km, 28 800 km², 90 ha, 3 m³, 200 g, 35 kg, 70 kv, 2 l; 100%, 112%, 30‰»; §99 d): «shenja e paragrafit dhe numri e shkronja që vijnë pas saj … : § 12»; note on p. 132: «Shenjat % (për qind) dhe ‰ (për mijë) mund të përdoren vetëm pas një numri të shënuar me shifra: 5%, 90%, 80‰»",
81
+ "url": "https://www.klasaletersi.com/wp-content/uploads/2017/03/Drejtshrimi-i-gjuh%C3%ABs-shqipe-1973.pdf",
82
+ "note": "beforeUnits = km kg cm dm ha km²; afterSymbols = §. That a measure abbreviation does not break from the number before it is normative (§99 ç)); the units are therefore bound with U+00A0 where a space is already written. Whether the separator must be inserted or deleted is not stated: the examples print measures spaced and % ‰ closed up, which is typesetting, not a rule, so spacedUnits and closedUnits are empty and % ‰ are not listed. Single-letter units (g, l) and m³ are excluded (nbsp.md §3.7); kv is not listed. Currency (€, lekë) and °C are not addressed. beforePunctuation, abbreviations and the other lists are empty, initialBinding is none. Read 2026-11-16 from the scan."
83
+ }
84
+ ]
85
+ }
@@ -19,7 +19,7 @@ step 9 with §3.8.5's content-line condition, added in 1.10.0, §3.8.4's carriag
19
19
  continuation line with the bails of §3.8.6 that use it, added in 1.11.0, and §3.8.4's node lines,
20
20
  declined keys, node markers and own-line region, with the changes to steps 1, 3, 4, 5, 6, 7 and 8
21
21
  that go with them, added in 1.11.0, and §3.9 with the amendments it carries to §3.1, §3.5 step 2,
22
- §4, §5, §7 item 7 and §8, added in 1.13.0, and §3.4's delimiter-neighbour rule with §3.7.3's autolink-literal tail, terminator guard and reference labels, and the amendments they carry to §3.4's deletion paragraph, §5 items 2 and 3, its fifth-part note and testing obligation, and §6, added in 1.17.2, and §3.4's escape-and-reference rule with the amendments it carries to §3.6, §3.7.3, §5 item 2's fifth-part note, §5 item 3 and the testing obligation, added in 1.17.4, and §3.4's bracket-shape rule, added in 1.17.5, and §3.6's whitespace-only text node rule, added in 1.23.0, and §3.6's ignored-tag rule, added in 1.23.1).
22
+ §4, §5, §7 item 7 and §8, added in 1.13.0, and §3.4's delimiter-neighbour rule with §3.7.3's autolink-literal tail, terminator guard and reference labels, and the amendments they carry to §3.4's deletion paragraph, §5 items 2 and 3, its fifth-part note and testing obligation, and §6, added in 1.17.2, and §3.4's escape-and-reference rule with the amendments it carries to §3.6, §3.7.3, §5 item 2's fifth-part note, §5 item 3 and the testing obligation, added in 1.17.4, and §3.4's bracket-shape rule, added in 1.17.5, and §3.6's whitespace-only text node rule, added in 1.23.0, and §3.6's ignored-tag rule, added in 1.23.1, and §3.6's published list, added in 1.30.0).
23
23
 
24
24
  ---
25
25
 
@@ -587,6 +587,16 @@ guessing from its name is exactly the kind of heuristic that behaves differently
587
587
  runtimes. **The skip list is closed**: extending it is a spec change, not an implementation
588
588
  decision.
589
589
 
590
+ **The list is published (since 1.30.0).** Every runtime exposes the ten element names above, as
591
+ lowercase strings in the order the first bullet gives them, from its public API (from the `html`
592
+ entry point, in a runtime that has one) as a constant a caller cannot modify: a frozen array, a tuple, a constant array, or, where the
593
+ language has no immutable collection, a function that returns a fresh copy on each call. The
594
+ mode's own membership test is built from this list, not from a second copy of it, and it is exactly §3.6's ten names: a
595
+ caller that walks a document with its own parser (a `.tsx` file, a template) reads it to decide
596
+ which elements to leave alone. How the constant is named follows each runtime's own conventions,
597
+ and its README says where to find it. Nothing about the list changes: it stays closed, and the
598
+ value moves only with a spec version.
599
+
590
600
  ### 3.7 Skip list — `markdown`
591
601
 
592
602
  #### 3.7.1 The dialect is chosen by the caller, never detected
@@ -1,5 +1,5 @@
1
1
  {
2
- "spec": "1.28.0",
2
+ "spec": "1.30.0",
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
  {
@@ -20,7 +20,7 @@ module Polytypo
20
20
  # modes.md 3.6, exhaustive and CLOSED: extending it is a spec change, not an implementation
21
21
  # decision. svg/math are here because in MathML a quotation mark, a hyphen and a prime are
22
22
  # operators and identifiers -- substituting a curly glyph changes what the expression means.
23
- SKIPPED_ELEMENTS = %w[code pre kbd samp var script style textarea svg math].freeze
23
+ SKIPPED_ELEMENTS = %w[code pre kbd samp var script style textarea svg math].each(&:freeze).freeze
24
24
 
25
25
  # HTML5 void elements: never pushed onto the element stack, since an author is not required
26
26
  # to close them and this tokenizer never synthesizes a matching end tag for one.
@@ -1,5 +1,5 @@
1
1
  # frozen_string_literal: true
2
2
 
3
3
  module Polytypo
4
- VERSION = "1.28.0"
4
+ VERSION = "1.30.0"
5
5
  end
data/lib/polytypo.rb CHANGED
@@ -17,6 +17,10 @@ require_relative "polytypo/modes/yaml"
17
17
  # (github.com/polytypo/polytypo). See spec/CONFORMANCE.md there for exactly what this runtime
18
18
  # implements.
19
19
  module Polytypo
20
+ # The elements whose whole subtree html mode leaves alone, as frozen lowercase strings in spec
21
+ # order (modes.md 3.6). The mode's own membership test reads this same array.
22
+ SKIPPED_ELEMENTS = Modes::Html::SKIPPED_ELEMENTS
23
+
20
24
  # Applies polytypo's rule pipeline to +input+ and returns the result.
21
25
  #
22
26
  # +locale+ is required, with no default -- an unknown locale raises Polytypo::Error with
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: 1.28.0
4
+ version: 1.30.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - Iurii Rogulia
@@ -69,6 +69,7 @@ files:
69
69
  - lib/polytypo/data/fixtures/ru.json
70
70
  - lib/polytypo/data/fixtures/sk.json
71
71
  - lib/polytypo/data/fixtures/sl.json
72
+ - lib/polytypo/data/fixtures/sq.json
72
73
  - lib/polytypo/data/fixtures/sr.json
73
74
  - lib/polytypo/data/fixtures/sv.json
74
75
  - lib/polytypo/data/fixtures/tr.json
@@ -102,6 +103,7 @@ files:
102
103
  - lib/polytypo/data/locales/ru.json
103
104
  - lib/polytypo/data/locales/sk.json
104
105
  - lib/polytypo/data/locales/sl.json
106
+ - lib/polytypo/data/locales/sq.json
105
107
  - lib/polytypo/data/locales/sr.json
106
108
  - lib/polytypo/data/locales/sv.json
107
109
  - lib/polytypo/data/locales/tr.json