interscript-maps 3.3.1 → 3.3.2

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.
@@ -13,12 +13,153 @@ metadata {
13
13
  description
14
14
 
15
15
  notes {
16
+ note "Encoded from the Wikipedia presentation of ISO 11940
17
+ (https://en.wikipedia.org/wiki/ISO_11940, CC BY-SA 4.0, retrieved
18
+ 2026-11-19) as the interim working source; the official ISO
19
+ 11940:1998 document remains the purchase of record for provenance."
20
+ note "The standard distinguishes the abbreviation symbol paiyannoi
21
+ from the sentence terminator angkhandiao (transliterated ǂ and
22
+ ǀ), but TIS 620-2533 and Unicode encode both uses as U+0E2F; the
23
+ map carries the paiyannoi reading ǂ. The ICU/CLDR implementation
24
+ substitutes a double dagger for both uses."
25
+ note "ICU/CLDR divergences from ISO 11940 are not reproduced: the
26
+ horn is U+031B, not a prime (ฅ ฒ ษ); ฏ is ṭ, not t̩; ำ is å, not
27
+ ả; phinthu U+0E3A is ring below U+0325, not ˌ; ฯ is ǂ, not ‡;
28
+ ๚ is ǁ, not ||. Preposed vowels are not transposed, per the
29
+ standard's recommendation: เชียงใหม่ transliterates
30
+ echīyngıh̄m̀, not the ICU form cheīyngh̄ım̀."
31
+ note "Character sequencing (clause 4.2): left to right, and top to
32
+ bottom at the same horizontal position, with tone marks and
33
+ thanthakhat preceding any other marks attached to a consonant.
34
+ The parallel substitution preserves Thai storage order, so marks
35
+ stacked on one consonant are emitted in stored order; a stateless
36
+ map cannot reorder a stack into the clause's tone-marks-first
37
+ sequence. The standard denies that sara u and nikkhahit can
38
+ combine; stored together they emit u plus ring above in stored
39
+ order."
40
+ note "Consonant diacritics follow the standard's entry order -
41
+ base letter, macron, then dot below, horn, or macron below -
42
+ and compose normalises each output to canonical (NFC) form
43
+ where a precomposed character exists (e.g. k with dot below as
44
+ U+1E33). U+0E45 (isolated lakkhangyao) transliterates ɨ per the
45
+ standard's provision, which notes the isolated letter should not
46
+ occur. U+0E3F (baht) is outside the working source's tables and
47
+ passes through unchanged."
16
48
  }
17
49
  }
18
50
 
19
51
  tests {
20
52
  "ภาษาไทย" -> "p̣hās̛̄āịthy"
21
53
  "เชียงใหม่" -> "echīyngıh̄m̀"
54
+
55
+ # Exhaustive per-row tests for iso-tha-Thai-Latn-11940-1998, generated from the source
56
+ # document's table.
57
+ # Source: ISO 11940:1998 Thai transliteration, all tables. Working source:
58
+ # the Wikipedia presentation "ISO 11940"
59
+ # (https://en.wikipedia.org/wiki/ISO_11940), CC BY-SA 4.0, retrieved
60
+ # 2026-11-19; used as the interim source pending acquisition of the official
61
+ # ISO 11940:1998 document, which remains the purchase of record for
62
+ # provenance. Rows in document order: the 46-consonant presentation table
63
+ # (44 consonant letters plus the ฤ/ฦ rows), the vowel-sign table (repeated ฤ
64
+ # ฦ ย ว อ entries deduplicated; ฤๅ/ฦๅ encoded as the constituent pairs), the
65
+ # isolated-lakkhangyao provision (ɨ), the other-combining-marks table
66
+ # (phinthu as ring below per the ISO column; the ICU CLDR implementation's ˌ
67
+ # is a recorded divergence), and the punctuation-and-digits table (paiyannoi
68
+ # reading ǂ for U+0E2F; the standard's angkhandiao reading ǀ is
69
+ # unrepresentable because TIS 620/Unicode do not distinguish the two uses).
70
+ # Expected strings are the post-compose (NFC where a precomposed character
71
+ # exists) forms. Excludes U+0E3F baht, which the working source's tables do
72
+ # not cover.
73
+ # Provenance artifact: scripts/row-sources/iso-tha-Thai-Latn-11940-1998.json (88 rows).
74
+ # generated-by: maps/scripts/gen-row-tests.mjs (2026-11-19); regenerate from the artifact, do not hand-edit.
75
+ "ก" -> "k"
76
+ "ข" -> "k̄h"
77
+ "ฃ" -> "ḳ̄h"
78
+ "ค" -> "kh"
79
+ "ฅ" -> "k̛h"
80
+ "ฆ" -> "ḳh"
81
+ "ง" -> "ng"
82
+ "จ" -> "c"
83
+ "ฉ" -> "c̄h"
84
+ "ช" -> "ch"
85
+ "ซ" -> "s"
86
+ "ฌ" -> "c̣h"
87
+ "ญ" -> "ỵ"
88
+ "ฎ" -> "ḍ"
89
+ "ฏ" -> "ṭ"
90
+ "ฐ" -> "ṭ̄h"
91
+ "ฑ" -> "ṯh"
92
+ "ฒ" -> "t̛h"
93
+ "ณ" -> "ṇ"
94
+ "ด" -> "d"
95
+ "ต" -> "t"
96
+ "ถ" -> "t̄h"
97
+ "ท" -> "th"
98
+ "ธ" -> "ṭh"
99
+ "น" -> "n"
100
+ "บ" -> "b"
101
+ "ป" -> "p"
102
+ "ผ" -> "p̄h"
103
+ "ฝ" -> "f̄"
104
+ "พ" -> "ph"
105
+ "ฟ" -> "f"
106
+ "ภ" -> "p̣h"
107
+ "ม" -> "m"
108
+ "ย" -> "y"
109
+ "ร" -> "r"
110
+ "ฤ" -> "v"
111
+ "ล" -> "l"
112
+ "ฦ" -> "ł"
113
+ "ว" -> "w"
114
+ "ศ" -> "ṣ̄"
115
+ "ษ" -> "s̛̄"
116
+ "ส" -> "s̄"
117
+ "ห" -> "h̄"
118
+ "ฬ" -> "ḷ"
119
+ "อ" -> "x"
120
+ "ฮ" -> "ḥ"
121
+ "ะ" -> "a"
122
+ "ั" -> "ạ"
123
+ "า" -> "ā"
124
+ "ำ" -> "å"
125
+ "ิ" -> "i"
126
+ "ี" -> "ī"
127
+ "ึ" -> "ụ"
128
+ "ื" -> "ụ̄"
129
+ "ุ" -> "u"
130
+ "ู" -> "ū"
131
+ "เ" -> "e"
132
+ "แ" -> "æ"
133
+ "โ" -> "o"
134
+ "ใ" -> "ı"
135
+ "ไ" -> "ị"
136
+ "ฤๅ" -> "vɨ"
137
+ "ฦๅ" -> "łɨ"
138
+ "ๅ" -> "ɨ"
139
+ "่" -> "̀"
140
+ "้" -> "̂"
141
+ "๊" -> "́"
142
+ "๋" -> "̌"
143
+ "็" -> "̆"
144
+ "์" -> "̒"
145
+ "๎" -> "~"
146
+ "ํ" -> "̊"
147
+ "ฺ" -> "̥"
148
+ "ๆ" -> "«"
149
+ "ฯ" -> "ǂ"
150
+ "๏" -> "§"
151
+ "๚" -> "ǁ"
152
+ "๛" -> "»"
153
+ "๐" -> "0"
154
+ "๑" -> "1"
155
+ "๒" -> "2"
156
+ "๓" -> "3"
157
+ "๔" -> "4"
158
+ "๕" -> "5"
159
+ "๖" -> "6"
160
+ "๗" -> "7"
161
+ "๘" -> "8"
162
+ "๙" -> "9"
22
163
  }
23
164
 
24
165
 
@@ -83,7 +224,7 @@ stage main {
83
224
  sub "\u0e37" "ụ̄"
84
225
  sub "\u0e38" "u"
85
226
  sub "\u0e39" "ū"
86
- sub "\u0e3a" "–̥"
227
+ sub "\u0e3a" "̥"
87
228
  sub "\u0e40" "e"
88
229
  sub "\u0e41" "æ"
89
230
  sub "\u0e42" "o"
metadata CHANGED
@@ -1,7 +1,7 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: interscript-maps
3
3
  version: !ruby/object:Gem::Version
4
- version: 3.3.1
4
+ version: 3.3.2
5
5
  platform: ruby
6
6
  authors:
7
7
  - Ribose Inc.
@@ -20,6 +20,7 @@ files:
20
20
  - README.adoc
21
21
  - interscript-maps.gemspec
22
22
  - interscript-maps.yaml
23
+ - libs/ara-latn-233-2026.isc
23
24
  - libs/hebr-latn.isc
24
25
  - libs/jawi-latn.isc
25
26
  - libs/posix.iml
@@ -335,6 +336,8 @@ files:
335
336
  - maps/icao-ukr-Cyrl-Latn-9303.isc
336
337
  - maps/iso-ara-Arab-Latn-233-1984.isc
337
338
  - maps/iso-ara-Arab-Latn-233-2-1993.isc
339
+ - maps/iso-ara-Arab-Latn-233-2026-modified.isc
340
+ - maps/iso-ara-Arab-Latn-233-2026.isc
338
341
  - maps/iso-asm-Beng-Latn-15919-2001.isc
339
342
  - maps/iso-ben-Beng-Latn-15919-2001.isc
340
343
  - maps/iso-ben-Beng-Latn-15919-2026.isc
@@ -347,6 +350,7 @@ files:
347
350
  - maps/iso-heb-Hebr-Latn-259-1984.isc
348
351
  - maps/iso-heb-Hebr-Latn-259-2-1994.isc
349
352
  - maps/iso-hin-Deva-Latn-15919-2001.isc
353
+ - maps/iso-hye-Armn-Latn-9985-2026.isc
350
354
  - maps/iso-inc-Deva-Latn-15919-2001.isc
351
355
  - maps/iso-inc-Kthi-Latn-15919-2001.isc
352
356
  - maps/iso-inc-Kthi-Latn-15919-2026.isc
@@ -355,6 +359,7 @@ files:
355
359
  - maps/iso-kan-Kana-Latn-15919-2026.isc
356
360
  - maps/iso-kas-Shrd-Latn-15919-2026.isc
357
361
  - maps/iso-kat-Geor-Latn-9984-1996.isc
362
+ - maps/iso-kat-Geor-Latn-9984-2026.isc
358
363
  - maps/iso-kor-Hang-Latn-1996-method1.isc
359
364
  - maps/iso-kor-Hang-Latn-1996-method2.isc
360
365
  - maps/iso-mal-Mlym-Latn-15919-2001.isc
@@ -374,7 +379,9 @@ files:
374
379
  - maps/iso-pra-Brah-Latn-15919-2026.isc
375
380
  - maps/iso-pra-Deva-Latn-15919-2001.isc
376
381
  - maps/iso-prs-Arab-Latn-233-3-1999.isc
382
+ - maps/iso-prs-Arab-Latn-233-3-2026.isc
377
383
  - maps/iso-rus-Cyrl-Latn-9-1995.isc
384
+ - maps/iso-rus-Cyrl-Latn-9-2026.isc
378
385
  - maps/iso-san-Deva-Latn-15919-2001.isc
379
386
  - maps/iso-san-Deva-Latn-15919-2026.isc
380
387
  - maps/iso-san-Gran-Latn-15919-2026.isc