interscript-maps 3.2.2 → 3.2.3
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/interscript-maps.gemspec +1 -1
- data/maps/alalc-chr-Cher-Latn-2012.isc +98 -0
- data/maps/alalc-hye-Armn-Latn-2022.isc +160 -0
- data/maps/alalc-zgh-Tfng-Latn-2012.isc +63 -0
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 9d1392a72d2562b959ab45fa614e46b2280defa2de21aa8af5762184251d57d0
|
|
4
|
+
data.tar.gz: 5da67bfb8709c5f8c37052ef991efc84364c643dbd79cb937b49ffe8f15d9ee5
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: dbde51bf5db378aff5bda9a83f1f3c9d87ad7864ae70bce566e06347701c3ab581067b9728f2dfadb758209604734de54d8da17b452ae5ee29bac336ba6590f5
|
|
7
|
+
data.tar.gz: 3cb8848c30c81894d265d753fe65a119081b5598ad5039f52c2eb42f80fc9220a5a8472d4f6669b64125c124015c06bce4a75775efd78fb1d73731cdd52baa15
|
data/interscript-maps.gemspec
CHANGED
|
@@ -47,6 +47,104 @@ tests {
|
|
|
47
47
|
"Ꮿ" -> "ya"
|
|
48
48
|
"ᎣᏏᏲ" -> "osiyo"
|
|
49
49
|
"ᏣᎳᎩ" -> "tsalagi"
|
|
50
|
+
|
|
51
|
+
# Exhaustive per-row tests for alalc-chr-Cher-Latn-2012, generated from the source
|
|
52
|
+
# document's table.
|
|
53
|
+
# Source: ALA-LC Cherokee Romanization Table (2012 version; no earlier
|
|
54
|
+
# versions) (https://www.loc.gov/catdir/cpso/romanization/cherokee.pdf;
|
|
55
|
+
# local source interscript-private-references/alalc/alalc-cherokee.pdf).
|
|
56
|
+
# Single-page syllabary grid, 85 rows, in printed grid order (left to right,
|
|
57
|
+
# top to bottom). Complete: no skipped rows — every printed cell is a single
|
|
58
|
+
# one-to-one romanization encodable as a character rule. The v-series values
|
|
59
|
+
# (Ꭵ Ꭼ Ꮂ Ꮈ Ꮕ Ꮫ Ꮲ Ꮸ Ꮾ Ᏼ) are the table's rendering of the nasal vowel. Glyph
|
|
60
|
+
# codepoints verified against the PDF text layer.
|
|
61
|
+
# Provenance artifact: scripts/row-sources/alalc-chr-Cher-Latn-2012.json (85 rows).
|
|
62
|
+
# generated-by: maps/scripts/gen-row-tests.mjs (2026-11-14); regenerate from the artifact, do not hand-edit.
|
|
63
|
+
"Ꭰ" -> "a"
|
|
64
|
+
"Ꭱ" -> "e"
|
|
65
|
+
"Ꭲ" -> "i"
|
|
66
|
+
"Ꭳ" -> "o"
|
|
67
|
+
"Ꭴ" -> "u"
|
|
68
|
+
"Ꭵ" -> "v"
|
|
69
|
+
"Ꭶ" -> "ga"
|
|
70
|
+
"Ꭷ" -> "ka"
|
|
71
|
+
"Ꭸ" -> "ge"
|
|
72
|
+
"Ꭹ" -> "gi"
|
|
73
|
+
"Ꭺ" -> "go"
|
|
74
|
+
"Ꭻ" -> "gu"
|
|
75
|
+
"Ꭼ" -> "gv"
|
|
76
|
+
"Ꭽ" -> "ha"
|
|
77
|
+
"Ꭾ" -> "he"
|
|
78
|
+
"Ꭿ" -> "hi"
|
|
79
|
+
"Ꮀ" -> "ho"
|
|
80
|
+
"Ꮁ" -> "hu"
|
|
81
|
+
"Ꮂ" -> "hv"
|
|
82
|
+
"Ꮃ" -> "la"
|
|
83
|
+
"Ꮄ" -> "le"
|
|
84
|
+
"Ꮅ" -> "li"
|
|
85
|
+
"Ꮆ" -> "lo"
|
|
86
|
+
"Ꮇ" -> "lu"
|
|
87
|
+
"Ꮈ" -> "lv"
|
|
88
|
+
"Ꮉ" -> "ma"
|
|
89
|
+
"Ꮊ" -> "me"
|
|
90
|
+
"Ꮋ" -> "mi"
|
|
91
|
+
"Ꮌ" -> "mo"
|
|
92
|
+
"Ꮍ" -> "mu"
|
|
93
|
+
"Ꮎ" -> "na"
|
|
94
|
+
"Ꮏ" -> "hna"
|
|
95
|
+
"Ꮐ" -> "nah"
|
|
96
|
+
"Ꮑ" -> "ne"
|
|
97
|
+
"Ꮒ" -> "ni"
|
|
98
|
+
"Ꮓ" -> "no"
|
|
99
|
+
"Ꮔ" -> "nu"
|
|
100
|
+
"Ꮕ" -> "nv"
|
|
101
|
+
"Ꮖ" -> "qua"
|
|
102
|
+
"Ꮗ" -> "que"
|
|
103
|
+
"Ꮘ" -> "qui"
|
|
104
|
+
"Ꮙ" -> "quo"
|
|
105
|
+
"Ꮚ" -> "quu"
|
|
106
|
+
"Ꮛ" -> "quv"
|
|
107
|
+
"Ꮜ" -> "sa"
|
|
108
|
+
"Ꮝ" -> "s"
|
|
109
|
+
"Ꮞ" -> "se"
|
|
110
|
+
"Ꮟ" -> "si"
|
|
111
|
+
"Ꮠ" -> "so"
|
|
112
|
+
"Ꮡ" -> "su"
|
|
113
|
+
"Ꮢ" -> "sv"
|
|
114
|
+
"Ꮣ" -> "da"
|
|
115
|
+
"Ꮤ" -> "ta"
|
|
116
|
+
"Ꮥ" -> "de"
|
|
117
|
+
"Ꮦ" -> "te"
|
|
118
|
+
"Ꮧ" -> "di"
|
|
119
|
+
"Ꮨ" -> "ti"
|
|
120
|
+
"Ꮩ" -> "do"
|
|
121
|
+
"Ꮪ" -> "du"
|
|
122
|
+
"Ꮫ" -> "dv"
|
|
123
|
+
"Ꮬ" -> "dla"
|
|
124
|
+
"Ꮭ" -> "tla"
|
|
125
|
+
"Ꮮ" -> "tle"
|
|
126
|
+
"Ꮯ" -> "tli"
|
|
127
|
+
"Ꮰ" -> "tlo"
|
|
128
|
+
"Ꮱ" -> "tlu"
|
|
129
|
+
"Ꮲ" -> "tlv"
|
|
130
|
+
"Ꮳ" -> "tsa"
|
|
131
|
+
"Ꮴ" -> "tse"
|
|
132
|
+
"Ꮵ" -> "tsi"
|
|
133
|
+
"Ꮶ" -> "tso"
|
|
134
|
+
"Ꮷ" -> "tsu"
|
|
135
|
+
"Ꮸ" -> "tsv"
|
|
136
|
+
"Ꮹ" -> "wa"
|
|
137
|
+
"Ꮺ" -> "we"
|
|
138
|
+
"Ꮻ" -> "wi"
|
|
139
|
+
"Ꮼ" -> "wo"
|
|
140
|
+
"Ꮽ" -> "wu"
|
|
141
|
+
"Ꮾ" -> "wv"
|
|
142
|
+
"Ꮿ" -> "ya"
|
|
143
|
+
"Ᏸ" -> "ye"
|
|
144
|
+
"Ᏹ" -> "yi"
|
|
145
|
+
"Ᏺ" -> "yo"
|
|
146
|
+
"Ᏻ" -> "yu"
|
|
147
|
+
"Ᏼ" -> "yv"
|
|
50
148
|
}
|
|
51
149
|
|
|
52
150
|
stage main {
|
|
@@ -77,6 +77,166 @@ tests {
|
|
|
77
77
|
"Ռ․" -> "1000"
|
|
78
78
|
"Կարդա՛, գրի՛ր տարին բոլոր" -> "Karda, grir tarin bolor"
|
|
79
79
|
"Բարձրանում է աշխարհ մի անեզր, որ քոնն է անշուշտ և իմը." -> "Bardzranum ē ashkharh mi anezr, or kʻonn ē anshusht ev imě."
|
|
80
|
+
|
|
81
|
+
# Exhaustive per-row tests for alalc-hye-Armn-Latn-2022, generated from the source
|
|
82
|
+
# document's table.
|
|
83
|
+
# Source: ALA-LC Armenian Romanization Table (2022 version; earlier
|
|
84
|
+
# versions: 2011, 1997)
|
|
85
|
+
# (https://www.loc.gov/catdir/cpso/romanization/armenian.pdf; local source
|
|
86
|
+
# interscript-private-references/alalc/alalc-armenian.pdf). Rows in document
|
|
87
|
+
# order: the letter table pp. 1-2 line by line (upper then lower per printed
|
|
88
|
+
# line), the Note 3 soft-sign combination table (p. 2), then the
|
|
89
|
+
# letter-numeral table (p. 7) as printed column streams (left column
|
|
90
|
+
# top-down, then right). Primary values only: the bracketed West Armenian
|
|
91
|
+
# alternates are excluded per the map's encoding scope. Skipped
|
|
92
|
+
# un-expressible rows: the Ե/ե Y/y alternates (Note 2: initial position of a
|
|
93
|
+
# name followed by a vowel, Classical) and the Յ/յ Ḥ/ḥ alternates (Note 4:
|
|
94
|
+
# initial position of a word or stem in a compound, Classical) are
|
|
95
|
+
# position-dependent; the composite numerals ԺԱ․ ԺԲ․ ԻԱ․ ԻԲ․ ԼԱ․ ԼԲ․ are
|
|
96
|
+
# multi-letter values and the map encodes single-letter numeral rules only;
|
|
97
|
+
# the ․․․ continuation placeholders are not romanization rows. The
|
|
98
|
+
# punctuation section (pp. 5-6) is instruction prose, not a table: «» and ։
|
|
99
|
+
# are encoded as map rules but are not row-transcribed here; ՞ and ՜ require
|
|
100
|
+
# sentence-end repositioning and are un-encodable as character rules; ՛ has
|
|
101
|
+
# empty output, which the generator contract (non-empty to) excludes — it is
|
|
102
|
+
# already encoded as a map rule. The diacritics page (p. 4) repeats
|
|
103
|
+
# letter-table rows and adds none. The Ev row's printed lower-case
|
|
104
|
+
# vernacular cell is the ech-yiwn ligature և; եվ is not a printed table row
|
|
105
|
+
# (the map encodes it additionally). The printed rows for Զ/զ and Ս/ս carry
|
|
106
|
+
# a '(see Note 3)' reference marker; transcribed as plain Z/S values. The
|
|
107
|
+
# aspiration mark is U+02BB, the soft sign U+02B9, the numeral leader
|
|
108
|
+
# U+2024; tilded/macroned/dotted Latin letters are the printed precomposed
|
|
109
|
+
# forms.
|
|
110
|
+
# Provenance artifact: scripts/row-sources/alalc-hye-Armn-Latn-2022.json (128 rows).
|
|
111
|
+
# generated-by: maps/scripts/gen-row-tests.mjs (2026-11-14); regenerate from the artifact, do not hand-edit.
|
|
112
|
+
"Ա" -> "A"
|
|
113
|
+
"ա" -> "a"
|
|
114
|
+
"Բ" -> "B"
|
|
115
|
+
"բ" -> "b"
|
|
116
|
+
"Գ" -> "G"
|
|
117
|
+
"գ" -> "g"
|
|
118
|
+
"Դ" -> "D"
|
|
119
|
+
"դ" -> "d"
|
|
120
|
+
"Ե" -> "E"
|
|
121
|
+
"ե" -> "e"
|
|
122
|
+
"Զ" -> "Z"
|
|
123
|
+
"զ" -> "z"
|
|
124
|
+
"Է" -> "Ē"
|
|
125
|
+
"է" -> "ē"
|
|
126
|
+
"Ը" -> "Ě"
|
|
127
|
+
"ը" -> "ě"
|
|
128
|
+
"Թ" -> "Tʻ"
|
|
129
|
+
"թ" -> "tʻ"
|
|
130
|
+
"Ժ" -> "Zh"
|
|
131
|
+
"ժ" -> "zh"
|
|
132
|
+
"Ի" -> "I"
|
|
133
|
+
"ի" -> "i"
|
|
134
|
+
"Լ" -> "L"
|
|
135
|
+
"լ" -> "l"
|
|
136
|
+
"Խ" -> "Kh"
|
|
137
|
+
"խ" -> "kh"
|
|
138
|
+
"Ծ" -> "Ts"
|
|
139
|
+
"ծ" -> "ts"
|
|
140
|
+
"Կ" -> "K"
|
|
141
|
+
"կ" -> "k"
|
|
142
|
+
"Հ" -> "H"
|
|
143
|
+
"հ" -> "h"
|
|
144
|
+
"Ձ" -> "Dz"
|
|
145
|
+
"ձ" -> "dz"
|
|
146
|
+
"Ղ" -> "Gh"
|
|
147
|
+
"ղ" -> "gh"
|
|
148
|
+
"Ճ" -> "Ch"
|
|
149
|
+
"ճ" -> "ch"
|
|
150
|
+
"Մ" -> "M"
|
|
151
|
+
"մ" -> "m"
|
|
152
|
+
"Յ" -> "Y"
|
|
153
|
+
"յ" -> "y"
|
|
154
|
+
"Ն" -> "N"
|
|
155
|
+
"ն" -> "n"
|
|
156
|
+
"Շ" -> "Sh"
|
|
157
|
+
"շ" -> "sh"
|
|
158
|
+
"Ո" -> "O"
|
|
159
|
+
"ո" -> "o"
|
|
160
|
+
"Չ" -> "Chʻ"
|
|
161
|
+
"չ" -> "chʻ"
|
|
162
|
+
"Պ" -> "P"
|
|
163
|
+
"պ" -> "p"
|
|
164
|
+
"Ջ" -> "J"
|
|
165
|
+
"ջ" -> "j"
|
|
166
|
+
"Ռ" -> "Ṛ"
|
|
167
|
+
"ռ" -> "ṛ"
|
|
168
|
+
"Ս" -> "S"
|
|
169
|
+
"ս" -> "s"
|
|
170
|
+
"Վ" -> "V"
|
|
171
|
+
"վ" -> "v"
|
|
172
|
+
"Տ" -> "T"
|
|
173
|
+
"տ" -> "t"
|
|
174
|
+
"Ր" -> "R"
|
|
175
|
+
"ր" -> "r"
|
|
176
|
+
"Ց" -> "Tsʻ"
|
|
177
|
+
"ց" -> "tsʻ"
|
|
178
|
+
"Ւ" -> "W"
|
|
179
|
+
"ւ" -> "w"
|
|
180
|
+
"Ու" -> "U"
|
|
181
|
+
"ու" -> "u"
|
|
182
|
+
"Փ" -> "Pʻ"
|
|
183
|
+
"փ" -> "pʻ"
|
|
184
|
+
"Ք" -> "Kʻ"
|
|
185
|
+
"ք" -> "kʻ"
|
|
186
|
+
"Եւ" -> "Ew"
|
|
187
|
+
"եւ" -> "ew"
|
|
188
|
+
"Եվ" -> "Ev"
|
|
189
|
+
"և" -> "ev"
|
|
190
|
+
"Օ" -> "Ō"
|
|
191
|
+
"օ" -> "ō"
|
|
192
|
+
"Ֆ" -> "F"
|
|
193
|
+
"ֆ" -> "f"
|
|
194
|
+
"Գհ" -> "Gʹh"
|
|
195
|
+
"գհ" -> "gʹh"
|
|
196
|
+
"Դզ" -> "Dʹz"
|
|
197
|
+
"դզ" -> "dʹz"
|
|
198
|
+
"Կհ" -> "Kʹh"
|
|
199
|
+
"կհ" -> "kʹh"
|
|
200
|
+
"Սհ" -> "Sʹh"
|
|
201
|
+
"սհ" -> "sʹh"
|
|
202
|
+
"Տս" -> "Tʹs"
|
|
203
|
+
"տս" -> "tʹs"
|
|
204
|
+
"Ա․" -> "1"
|
|
205
|
+
"Բ․" -> "2"
|
|
206
|
+
"Գ․" -> "3"
|
|
207
|
+
"Դ․" -> "4"
|
|
208
|
+
"Ե․" -> "5"
|
|
209
|
+
"Զ․" -> "6"
|
|
210
|
+
"Է․" -> "7"
|
|
211
|
+
"Ը․" -> "8"
|
|
212
|
+
"Թ․" -> "9"
|
|
213
|
+
"Ժ․" -> "10"
|
|
214
|
+
"Ի․" -> "20"
|
|
215
|
+
"Լ․" -> "30"
|
|
216
|
+
"Խ․" -> "40"
|
|
217
|
+
"Ծ․" -> "50"
|
|
218
|
+
"Կ․" -> "60"
|
|
219
|
+
"Հ․" -> "70"
|
|
220
|
+
"Ձ․" -> "80"
|
|
221
|
+
"Ղ․" -> "90"
|
|
222
|
+
"Ճ․" -> "100"
|
|
223
|
+
"Մ․" -> "200"
|
|
224
|
+
"Յ․" -> "300"
|
|
225
|
+
"Ն․" -> "400"
|
|
226
|
+
"Շ․" -> "500"
|
|
227
|
+
"Ո․" -> "600"
|
|
228
|
+
"Չ․" -> "700"
|
|
229
|
+
"Պ․" -> "800"
|
|
230
|
+
"Ջ․" -> "900"
|
|
231
|
+
"Ռ․" -> "1000"
|
|
232
|
+
"Ս․" -> "2000"
|
|
233
|
+
"Վ․" -> "3000"
|
|
234
|
+
"Տ․" -> "4000"
|
|
235
|
+
"Ր․" -> "5000"
|
|
236
|
+
"Ց․" -> "6000"
|
|
237
|
+
"Ւ․" -> "7000"
|
|
238
|
+
"Փ․" -> "8000"
|
|
239
|
+
"Ք․" -> "9000"
|
|
80
240
|
}
|
|
81
241
|
|
|
82
242
|
stage main {
|
|
@@ -56,6 +56,69 @@ tests {
|
|
|
56
56
|
"ⵥ" -> "ẓ"
|
|
57
57
|
"ⴳⵯ" -> "g°"
|
|
58
58
|
"ⵯ" -> "°"
|
|
59
|
+
|
|
60
|
+
# Exhaustive per-row tests for alalc-zgh-Tfng-Latn-2012, generated from the source
|
|
61
|
+
# document's table.
|
|
62
|
+
# Source: ALA-LC Moroccan Tamazight Romanization Table (2012; no version
|
|
63
|
+
# year printed on the document, approval date CC:AAM 2012-01-22 from PDF
|
|
64
|
+
# metadata) (https://www.loc.gov/catdir/cpso/romanization/tamazight.pdf;
|
|
65
|
+
# local source interscript-private-references/alalc/alalc-tamazight.pdf).
|
|
66
|
+
# Single-page table, 43 rows, read as printed column streams (left column
|
|
67
|
+
# top-down, then right). Complete: no skipped rows — the table includes the
|
|
68
|
+
# labialized digraphs ⴳⵯ/ⴽⵯ and the tamatart ⵯ, all encodable. The PDF text
|
|
69
|
+
# layer drops the macron-below marks (U+0331) on the ⴲ ⴴ ⴸ ⵝ values and the
|
|
70
|
+
# entire value cells for ⵕ ⵟ ⴺ; those values are transcribed from the
|
|
71
|
+
# printed page image. Decomposed text-layer forms are NFC-normalized
|
|
72
|
+
# (h+U+0323 → ḥ U+1E25, s+U+0323 → ṣ, z+U+0323 → ẓ, d+U+0323 → ḍ). The ⴺ
|
|
73
|
+
# value (d with dot below and macron below) follows the printed glyph with
|
|
74
|
+
# the map's documented mark order (U+0323 then U+0331). The printed ⵄ ⵖ rows
|
|
75
|
+
# carry '(See note 1)' and ⵯ '(See note 2)' reference markers; transcribed
|
|
76
|
+
# as plain values.
|
|
77
|
+
# Provenance artifact: scripts/row-sources/alalc-zgh-Tfng-Latn-2012.json (43 rows).
|
|
78
|
+
# generated-by: maps/scripts/gen-row-tests.mjs (2026-11-14); regenerate from the artifact, do not hand-edit.
|
|
79
|
+
"ⴰ" -> "a"
|
|
80
|
+
"ⴱ" -> "b"
|
|
81
|
+
"ⴲ" -> "ḇ"
|
|
82
|
+
"ⴳ" -> "g"
|
|
83
|
+
"ⴳⵯ" -> "g°"
|
|
84
|
+
"ⴴ" -> "g̱"
|
|
85
|
+
"ⴵ" -> "ğ"
|
|
86
|
+
"ⴷ" -> "d"
|
|
87
|
+
"ⴸ" -> "ḏ"
|
|
88
|
+
"ⴹ" -> "ḍ"
|
|
89
|
+
"ⴺ" -> "ḍ̱"
|
|
90
|
+
"ⴻ" -> "e"
|
|
91
|
+
"ⴼ" -> "f"
|
|
92
|
+
"ⴽ" -> "k"
|
|
93
|
+
"ⴽⵯ" -> "k°"
|
|
94
|
+
"ⴿ" -> "k"
|
|
95
|
+
"ⵀ" -> "h"
|
|
96
|
+
"ⵃ" -> "ḥ"
|
|
97
|
+
"ⵄ" -> "ɛ"
|
|
98
|
+
"ⵅ" -> "x"
|
|
99
|
+
"ⵇ" -> "q"
|
|
100
|
+
"ⵉ" -> "i"
|
|
101
|
+
"ⵊ" -> "j"
|
|
102
|
+
"ⵍ" -> "l"
|
|
103
|
+
"ⵎ" -> "m"
|
|
104
|
+
"ⵏ" -> "n"
|
|
105
|
+
"ⵓ" -> "u"
|
|
106
|
+
"ⵔ" -> "r"
|
|
107
|
+
"ⵕ" -> "ṛ"
|
|
108
|
+
"ⵖ" -> "ɣ"
|
|
109
|
+
"ⵙ" -> "s"
|
|
110
|
+
"ⵚ" -> "ṣ"
|
|
111
|
+
"ⵛ" -> "c"
|
|
112
|
+
"ⵜ" -> "t"
|
|
113
|
+
"ⵝ" -> "ṯ"
|
|
114
|
+
"ⵞ" -> "č"
|
|
115
|
+
"ⵟ" -> "ṭ"
|
|
116
|
+
"ⵠ" -> "v"
|
|
117
|
+
"ⵡ" -> "w"
|
|
118
|
+
"ⵢ" -> "y"
|
|
119
|
+
"ⵣ" -> "z"
|
|
120
|
+
"ⵥ" -> "ẓ"
|
|
121
|
+
"ⵯ" -> "°"
|
|
59
122
|
}
|
|
60
123
|
|
|
61
124
|
stage main {
|