interscript-maps 3.2.4 → 3.3.0
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/interscript-maps.gemspec +1 -1
- data/maps/alalc-aze-Cyrl-Latn-1997.isc +48 -11
- data/maps/alalc-ben-Beng-Latn-2017.isc +68 -17
- data/maps/alalc-sat-Olck-Latn-2017.isc +7 -3
- data/maps/bsi-rus-Cyrl-Latn-2979-1958.isc +233 -0
- data/maps/din-ab-Cyrl-Latn-1460-2-2011.isc +8 -4
- data/maps/din-atv-Cyrl-Latn-1460-2-2011.isc +8 -4
- data/maps/din-az-Cyrl-Latn-1460-2-2011.isc +10 -6
- data/maps/din-ba-Cyrl-Latn-1460-2-2011.isc +10 -6
- data/maps/din-urd-Arab-Latn-31635-2011.isc +7 -1
- data/maps/iso-ben-Beng-Latn-15919-2001.isc +5 -0
- data/maps/iso-ben-Beng-Latn-15919-2026.isc +228 -0
- data/maps/iso-doi-Takr-Latn-15919-2026.isc +182 -0
- data/maps/iso-guj-Gujr-Latn-15919-2026.isc +231 -0
- data/maps/iso-heb-Hebr-Latn-259-1984.isc +426 -0
- data/maps/iso-heb-Hebr-Latn-259-2-1994.isc +469 -0
- data/maps/iso-inc-Kthi-Latn-15919-2001.isc +121 -0
- data/maps/iso-inc-Kthi-Latn-15919-2026.isc +197 -0
- data/maps/iso-jpn-Hrkt-Latn-3602-1989.isc +53 -0
- data/maps/iso-kan-Kana-Latn-15919-2001.isc +8 -4
- data/maps/iso-kan-Kana-Latn-15919-2026.isc +229 -0
- data/maps/iso-kas-Shrd-Latn-15919-2026.isc +208 -0
- data/maps/iso-mal-Mlym-Latn-15919-2001.isc +1 -0
- data/maps/iso-mal-Mlym-Latn-15919-2026.isc +223 -0
- data/maps/iso-mar-Deva-Latn-15919-2001.isc +1 -1
- data/maps/iso-mar-Modi-Latn-15919-2026.isc +204 -0
- data/maps/iso-new-Newa-Latn-15919-2026.isc +221 -0
- data/maps/iso-ori-Orya-Latn-15919-2026.isc +222 -0
- data/maps/iso-pan-Guru-Latn-15919-2026.isc +222 -0
- data/maps/iso-pra-Brah-Latn-15919-2026.isc +231 -0
- data/maps/iso-san-Deva-Latn-15919-2001.isc +5 -2
- data/maps/iso-san-Deva-Latn-15919-2026.isc +278 -0
- data/maps/iso-san-Gran-Latn-15919-2026.isc +208 -0
- data/maps/iso-sin-Sinh-Latn-15919-2001.isc +174 -0
- data/maps/iso-sin-Sinh-Latn-15919-2026.isc +238 -0
- data/maps/iso-tam-Taml-Latn-15919-2001.isc +1 -0
- data/maps/iso-tam-Taml-Latn-15919-2026.isc +178 -0
- data/maps/iso-tel-Telu-Latn-15919-2001.isc +7 -0
- data/maps/iso-tel-Telu-Latn-15919-2026.isc +229 -0
- data/maps/odni-che-Cyrl-Latn-2015.isc +19 -19
- data/maps/odni-mkd-Cyrl-Latn-2015.isc +11 -16
- data/maps/var-jpn-Hrkt-Latn-komaba-2009.isc +417 -0
- metadata +24 -2
- data/maps/bsi-rus-Cyrl-Latn-1958.isc +0 -199
|
@@ -0,0 +1,231 @@
|
|
|
1
|
+
system "ISO:guj-Gujr:Latn:15919-2026" {
|
|
2
|
+
|
|
3
|
+
metadata {
|
|
4
|
+
authority_id iso
|
|
5
|
+
id 15919-2026
|
|
6
|
+
language iso-639-2:guj
|
|
7
|
+
source_script Gujr
|
|
8
|
+
destination_script Latn
|
|
9
|
+
name "ISO/DIS 15919 (2026) Information and documentation -- Transliteration of Indic scripts into Latin characters (Gujarati; DIS stage)"
|
|
10
|
+
url https://www.iso.org/committee/48820.html
|
|
11
|
+
creation_date 2026
|
|
12
|
+
adoption_date 2026
|
|
13
|
+
description { Second edition (DIS stage) of ISO 15919, Transliteration of Indic scripts into Latin characters.
|
|
14
|
+
Encoded from the committee ballot ISO/TC 46/WG 3 N125; per-script tables of clause 7,
|
|
15
|
+
numerals of normative Annex A, Rule 17 Vedic accents, and options 9.8/9.9/9.10 as
|
|
16
|
+
selectable variants (languages opt98 opt99 opt10). See notes for provenance and errata. }
|
|
17
|
+
|
|
18
|
+
notes {
|
|
19
|
+
note "Encoded from ISO/DIS 15919 (2026), ISO/TC 46/WG 3 N125 (DIS stage draft, 2026-01-26), Table 7.4 plus the numerals of normative Annex A Table A.2; shared-table content verified against ISO/CD 15919 (2025, N108) and ISO 15919 WD (2024, N88). The DIS is not yet a published International Standard."
|
|
20
|
+
note "Rule 2 convention: inherent a with a consonant is always transliterated (consonant rows carry the inherent a)."
|
|
21
|
+
note "virama is deleted in the default behavior (clause 6 printed virama hex list); option 9.10 (language selector opt10) instead renders virama as middle dot U+00B7."
|
|
22
|
+
note "Option selectors (W3 languages, single-select): opt98 = clause 9.8 upper-case for all initial vowels (first letter capitalised for digraph outputs); opt99 = clause 9.9 unusual conjuncts marked with equals sign U+003D via the script's zero-width joiner; opt10 = clause 9.10 explicit virama middle dot. Option 9.1 (non-uniform e/o) is available by character substitution on outputs and is not separately staged."
|
|
23
|
+
note "Cross-check (audit axis): Wikipedia ISO 15919 table (2001-reflected) vs corpus map agreement 50/59 printed rows; systematic divergences recorded as findings, not fixes: vocalic r/l rows (corpus ṛ-family vs ISO r̥-family), long e/o rows (corpus e/o vs ISO ē/ō), avagraha (corpus :’ vs ISO ')."
|
|
24
|
+
}
|
|
25
|
+
}
|
|
26
|
+
|
|
27
|
+
languages opt98 opt99 opt10
|
|
28
|
+
|
|
29
|
+
tests {
|
|
30
|
+
"અ" -> "a"
|
|
31
|
+
"ક" -> "ka"
|
|
32
|
+
"આ" -> "ā"
|
|
33
|
+
"ા" -> "ā"
|
|
34
|
+
"ખ" -> "kha"
|
|
35
|
+
"ઇ" -> "i"
|
|
36
|
+
"િ" -> "i"
|
|
37
|
+
"ગ" -> "ga"
|
|
38
|
+
"ઈ" -> "ī"
|
|
39
|
+
"ી" -> "ī"
|
|
40
|
+
"ઘ" -> "gha"
|
|
41
|
+
"ઉ" -> "u"
|
|
42
|
+
"ુ" -> "u"
|
|
43
|
+
"ઙ" -> "ṅa"
|
|
44
|
+
"ઊ" -> "ū"
|
|
45
|
+
"ૂ" -> "ū"
|
|
46
|
+
"ચ" -> "ca"
|
|
47
|
+
"ઋ" -> "r̥"
|
|
48
|
+
"ૃ" -> "r̥"
|
|
49
|
+
"છ" -> "cha"
|
|
50
|
+
"ૠ" -> "r̥̄"
|
|
51
|
+
"ૄ" -> "r̥̄"
|
|
52
|
+
"જ" -> "ja"
|
|
53
|
+
"ઌ" -> "l̥"
|
|
54
|
+
"ૢ" -> "l̥"
|
|
55
|
+
"ઝ" -> "jha"
|
|
56
|
+
"ૡ" -> "l̥̄"
|
|
57
|
+
"ૣ" -> "l̥̄"
|
|
58
|
+
"ઞ" -> "ña"
|
|
59
|
+
"એ" -> "ē"
|
|
60
|
+
"ે" -> "ē"
|
|
61
|
+
"ટ" -> "ṭa"
|
|
62
|
+
"ઐ" -> "ai"
|
|
63
|
+
"ૈ" -> "ai"
|
|
64
|
+
"ઠ" -> "ṭha"
|
|
65
|
+
"ઓ" -> "ō"
|
|
66
|
+
"ો" -> "ō"
|
|
67
|
+
"ડ" -> "ḍa"
|
|
68
|
+
"ઔ" -> "au"
|
|
69
|
+
"ૌ" -> "au"
|
|
70
|
+
"ઢ" -> "ḍha"
|
|
71
|
+
"ઍ" -> "ê"
|
|
72
|
+
"ૅ" -> "ê"
|
|
73
|
+
"ણ" -> "ṇa"
|
|
74
|
+
"ઑ" -> "ô"
|
|
75
|
+
"ૉ" -> "ô"
|
|
76
|
+
"ત" -> "ta"
|
|
77
|
+
"શ" -> "śa"
|
|
78
|
+
"થ" -> "tha"
|
|
79
|
+
"ષ" -> "ṣa"
|
|
80
|
+
"દ" -> "da"
|
|
81
|
+
"સ" -> "sa"
|
|
82
|
+
"ધ" -> "dha"
|
|
83
|
+
"હ" -> "ha"
|
|
84
|
+
"ન" -> "na"
|
|
85
|
+
"ક઼" -> "qa"
|
|
86
|
+
"પ" -> "pa"
|
|
87
|
+
"ખ઼" -> "k͟ha"
|
|
88
|
+
"ફ" -> "pha"
|
|
89
|
+
"ગ઼" -> "ġa"
|
|
90
|
+
"બ" -> "ba"
|
|
91
|
+
"જ઼" -> "za"
|
|
92
|
+
"ભ" -> "bha"
|
|
93
|
+
"ૹ" -> "źa"
|
|
94
|
+
"મ" -> "ma"
|
|
95
|
+
"ફ઼" -> "fa"
|
|
96
|
+
"ય" -> "ya"
|
|
97
|
+
"ં" -> "ṁ"
|
|
98
|
+
"ર" -> "ra"
|
|
99
|
+
"ઁ" -> "m̐"
|
|
100
|
+
"લ" -> "la"
|
|
101
|
+
"ઃ" -> "ḥ"
|
|
102
|
+
"ળ" -> "ḷa"
|
|
103
|
+
"ઽ" -> "'"
|
|
104
|
+
"વ" -> "va"
|
|
105
|
+
"૦" -> "0"
|
|
106
|
+
"૧" -> "1"
|
|
107
|
+
"૨" -> "2"
|
|
108
|
+
"૩" -> "3"
|
|
109
|
+
"૪" -> "4"
|
|
110
|
+
"૫" -> "5"
|
|
111
|
+
"૬" -> "6"
|
|
112
|
+
"૭" -> "7"
|
|
113
|
+
"૮" -> "8"
|
|
114
|
+
"૯" -> "9"
|
|
115
|
+
}
|
|
116
|
+
|
|
117
|
+
stage main {
|
|
118
|
+
|
|
119
|
+
# Table 7.4 rows (clause 7), Table A.2 numerals, clause 6 virama, options 9.8/9.9/9.10
|
|
120
|
+
parallel {
|
|
121
|
+
|
|
122
|
+
sub "અ" "a"
|
|
123
|
+
sub "અ" "A" when opt98
|
|
124
|
+
sub "ક" "ka"
|
|
125
|
+
sub "આ" "ā"
|
|
126
|
+
sub "ા" "ā"
|
|
127
|
+
sub "આ" "Ā" when opt98
|
|
128
|
+
sub "ખ" "kha"
|
|
129
|
+
sub "ઇ" "i"
|
|
130
|
+
sub "િ" "i"
|
|
131
|
+
sub "ઇ" "I" when opt98
|
|
132
|
+
sub "ગ" "ga"
|
|
133
|
+
sub "ઈ" "ī"
|
|
134
|
+
sub "ી" "ī"
|
|
135
|
+
sub "ઈ" "Ī" when opt98
|
|
136
|
+
sub "ઘ" "gha"
|
|
137
|
+
sub "ઉ" "u"
|
|
138
|
+
sub "ુ" "u"
|
|
139
|
+
sub "ઉ" "U" when opt98
|
|
140
|
+
sub "ઙ" "ṅa"
|
|
141
|
+
sub "ઊ" "ū"
|
|
142
|
+
sub "ૂ" "ū"
|
|
143
|
+
sub "ઊ" "Ū" when opt98
|
|
144
|
+
sub "ચ" "ca"
|
|
145
|
+
sub "ઋ" "r̥"
|
|
146
|
+
sub "ૃ" "r̥"
|
|
147
|
+
sub "ઋ" "R̥" when opt98
|
|
148
|
+
sub "છ" "cha"
|
|
149
|
+
sub "ૠ" "r̥̄"
|
|
150
|
+
sub "ૄ" "r̥̄"
|
|
151
|
+
sub "ૠ" "R̥̄" when opt98
|
|
152
|
+
sub "જ" "ja"
|
|
153
|
+
sub "ઌ" "l̥"
|
|
154
|
+
sub "ૢ" "l̥"
|
|
155
|
+
sub "ઌ" "L̥" when opt98
|
|
156
|
+
sub "ઝ" "jha"
|
|
157
|
+
sub "ૡ" "l̥̄"
|
|
158
|
+
sub "ૣ" "l̥̄"
|
|
159
|
+
sub "ૡ" "L̥̄" when opt98
|
|
160
|
+
sub "ઞ" "ña"
|
|
161
|
+
sub "એ" "ē"
|
|
162
|
+
sub "ે" "ē"
|
|
163
|
+
sub "એ" "Ē" when opt98
|
|
164
|
+
sub "ટ" "ṭa"
|
|
165
|
+
sub "ઐ" "ai"
|
|
166
|
+
sub "ૈ" "ai"
|
|
167
|
+
sub "ઐ" "Ai" when opt98
|
|
168
|
+
sub "ઠ" "ṭha"
|
|
169
|
+
sub "ઓ" "ō"
|
|
170
|
+
sub "ો" "ō"
|
|
171
|
+
sub "ઓ" "Ō" when opt98
|
|
172
|
+
sub "ડ" "ḍa"
|
|
173
|
+
sub "ઔ" "au"
|
|
174
|
+
sub "ૌ" "au"
|
|
175
|
+
sub "ઔ" "Au" when opt98
|
|
176
|
+
sub "ઢ" "ḍha"
|
|
177
|
+
sub "ઍ" "ê"
|
|
178
|
+
sub "ૅ" "ê"
|
|
179
|
+
sub "ઍ" "Ê" when opt98
|
|
180
|
+
sub "ણ" "ṇa"
|
|
181
|
+
sub "ઑ" "ô"
|
|
182
|
+
sub "ૉ" "ô"
|
|
183
|
+
sub "ઑ" "Ô" when opt98
|
|
184
|
+
sub "ત" "ta"
|
|
185
|
+
sub "શ" "śa"
|
|
186
|
+
sub "થ" "tha"
|
|
187
|
+
sub "ષ" "ṣa"
|
|
188
|
+
sub "દ" "da"
|
|
189
|
+
sub "સ" "sa"
|
|
190
|
+
sub "ધ" "dha"
|
|
191
|
+
sub "હ" "ha"
|
|
192
|
+
sub "ન" "na"
|
|
193
|
+
sub "ક઼" "qa"
|
|
194
|
+
sub "પ" "pa"
|
|
195
|
+
sub "ખ઼" "k͟ha"
|
|
196
|
+
sub "ફ" "pha"
|
|
197
|
+
sub "ગ઼" "ġa"
|
|
198
|
+
sub "બ" "ba"
|
|
199
|
+
sub "જ઼" "za"
|
|
200
|
+
sub "ભ" "bha"
|
|
201
|
+
sub "ૹ" "źa"
|
|
202
|
+
sub "મ" "ma"
|
|
203
|
+
sub "ફ઼" "fa"
|
|
204
|
+
sub "ય" "ya"
|
|
205
|
+
sub "ં" "ṁ"
|
|
206
|
+
sub "ર" "ra"
|
|
207
|
+
sub "ઁ" "m̐"
|
|
208
|
+
sub "લ" "la"
|
|
209
|
+
sub "ઃ" "ḥ"
|
|
210
|
+
sub "ળ" "ḷa"
|
|
211
|
+
sub "ઽ" "'"
|
|
212
|
+
sub "વ" "va"
|
|
213
|
+
sub "્" ""
|
|
214
|
+
sub "્" "·" when opt10
|
|
215
|
+
sub "" ""
|
|
216
|
+
sub "" "=" when opt99
|
|
217
|
+
sub "૦" "0"
|
|
218
|
+
sub "૧" "1"
|
|
219
|
+
sub "૨" "2"
|
|
220
|
+
sub "૩" "3"
|
|
221
|
+
sub "૪" "4"
|
|
222
|
+
sub "૫" "5"
|
|
223
|
+
sub "૬" "6"
|
|
224
|
+
sub "૭" "7"
|
|
225
|
+
sub "૮" "8"
|
|
226
|
+
sub "૯" "9"
|
|
227
|
+
}
|
|
228
|
+
|
|
229
|
+
compose
|
|
230
|
+
}
|
|
231
|
+
}
|
|
@@ -0,0 +1,426 @@
|
|
|
1
|
+
system "ISO:heb-Hebr:Latn:259-1984" {
|
|
2
|
+
|
|
3
|
+
metadata {
|
|
4
|
+
authority_id iso
|
|
5
|
+
id 259-1984
|
|
6
|
+
language iso-639-2:heb
|
|
7
|
+
source_script Hebr
|
|
8
|
+
destination_script Latn
|
|
9
|
+
name "ISO 259:1984 Documentation -- Transliteration of Hebrew characters into Latin characters"
|
|
10
|
+
url https://www.iso.org/standard/4161.html
|
|
11
|
+
creation_date 1984
|
|
12
|
+
description { Establishes the system for the transliteration of Hebrew characters into Latin
|
|
13
|
+
characters, following the principles of stringent conversion (full rendering of the
|
|
14
|
+
consonants and their diacritics). First edition 1984-10-01, prepared by ISO/TC 46;
|
|
15
|
+
cancels and replaces ISO/R 259:1962. This map encodes Table 1, the consonant table
|
|
16
|
+
(43 rows), together with the notes to the table (geresh and gershayim abbreviation
|
|
17
|
+
handling). The vocalized Table 2 of the standard is not part of this consonantal
|
|
18
|
+
encoding.
|
|
19
|
+
}
|
|
20
|
+
|
|
21
|
+
notes {
|
|
22
|
+
note "Clause 0.3.3: one constant character per letter; final forms take their letter's row and Table 1 has no final-form rows. Table 2 (vowel signs, rows 44-59) is the vocalized extension and is out of scope of this consonantal map: Hebrew vowel signs (U+05B0-U+05BB), the teamim (U+0591-U+05AF), meteg (U+05BD), rafe (U+05BF), upper dot (U+05C4), lower dot (U+05C5), qamats qatan (U+05C7) and residual dagesh (U+05BC), shin dot (U+05C1) and sin dot (U+05C2) marks are deleted from the input, giving the consonantal skeleton."
|
|
23
|
+
note "Dagesh lene, mappiq and shuruq render as the Annex A dot above (Annex code 4/7) on rows 3, 5, 7, 9, 11, 13, 16, 18, 20, 22, 24, 26, 28, 31, 33, 35, 39, 41 and 43; on rows 16 and 33 the dot above stacks over the dot below of the base output. Row 38 is a typographic variant of row 37 (one Unicode sequence U+05E9 U+05C1, raised caron) and maps identically to row 37."
|
|
24
|
+
note "Notes to the table: geresh U+05F3 renders as U+02B9 (notes 1.1 and 2.1, the abbreviation geresh); gershayim U+05F4 renders as U+02BA (note 2.2; the Hebrew placement between the last two letters of the abbreviation is preserved by pass-through); the period passes through unchanged (note 2.3). Letters carrying geresh for foreign phonemes (note 1.1) render as their Table 1 letter plus U+02B9: gimel-geresh, zayin-geresh and tsadi-geresh, per note 1.2 (table letter + original mark); the official print reads the tsadi-geresh value as U+1E63 + U+02B9 (s with dot below + prime), matching the note 1.2 recommendation. The print's unpointed example readings Gʹin / Zʹan treat yod and alef as vowel bearers, which belongs to the vocalization this consonantal map does not encode; this map renders the Table 1 rows strictly (g + U+02B9 + y + n; z + U+02B9 + alef + n)."
|
|
25
|
+
note "Unpointed shin U+05E9 renders as shin with sin dot (row 37, U+0161). Alphabetic Presentation Forms equal to their decompositions (U+FB2A-U+FB2D and the point-bearing letter forms U+FB30-U+FB3C, U+FB3E, U+FB40, U+FB41, U+FB43, U+FB44, U+FB46-U+FB4E) are accepted as input and render by their Table 1 rows; the rafe forms U+FB4C, U+FB4D and U+FB4E render as the bare letter (Table 1 has no rafe row). Composed letter+vowel forms and the alef-lamed ligature U+FB4F are out of scope and pass through."
|
|
26
|
+
note "Mark-order normalization moves dagesh and the shin/sin dots next to their base letter (canonical combining order places the vowel signs first). Letter-first legacy stacks and canonical NFC stacks are fully handled; a fully non-canonical stack (vowel, shin dot, dagesh) may leave the dagesh unrendered. Maqaf U+05BE, paseq U+05C0, sof pasuq U+05C3, nun hafukha U+05C6 and the Hebrew ligatures U+05F0-U+05F2 are outside the standard's tables and pass through unchanged."
|
|
27
|
+
note "Encoded from the official ISO 259:1984(E) edition and verified cell for cell against Table 1, Table 2 and the Annex A diacritical-sign positions. The official text confirms the adjudicated readings, including row 41 (Annex A 4/2 and 4/7: acute with the dagesh dot above), row 38 (4/15, the raised-caron typographic variant, no dot) and row 39 (4/7 and 4/15). Table 2 (rows 44-59), out of the consonantal scope here, is likewise verified in the official text for a future vocalized extension."
|
|
28
|
+
}
|
|
29
|
+
}
|
|
30
|
+
|
|
31
|
+
tests {
|
|
32
|
+
# Table 1, consonant rows (the standard's row numbering)
|
|
33
|
+
"א" -> "ʾ̲"
|
|
34
|
+
"ב" -> "b"
|
|
35
|
+
"בּ" -> "ḃ"
|
|
36
|
+
"ג" -> "g"
|
|
37
|
+
"גּ" -> "ḡ"
|
|
38
|
+
"ד" -> "d"
|
|
39
|
+
"דּ" -> "ḋ"
|
|
40
|
+
"ה" -> "h"
|
|
41
|
+
"הּ" -> "ḣ"
|
|
42
|
+
"ו" -> "w"
|
|
43
|
+
"וּ" -> "ẇ"
|
|
44
|
+
"ז" -> "z"
|
|
45
|
+
"זּ" -> "ż"
|
|
46
|
+
"ח" -> "ḥ"
|
|
47
|
+
"ט" -> "ṭ"
|
|
48
|
+
"טּ" -> "ṭ̇"
|
|
49
|
+
"י" -> "y"
|
|
50
|
+
"יּ" -> "ẏ"
|
|
51
|
+
"כ" -> "k"
|
|
52
|
+
"כּ" -> "k̇"
|
|
53
|
+
"ל" -> "l"
|
|
54
|
+
"לּ" -> "l̇"
|
|
55
|
+
"מ" -> "m"
|
|
56
|
+
"מּ" -> "ṁ"
|
|
57
|
+
"נ" -> "n"
|
|
58
|
+
"נּ" -> "ṅ"
|
|
59
|
+
"ס" -> "s"
|
|
60
|
+
"סּ" -> "ṡ"
|
|
61
|
+
"ע" -> "ʿ̲"
|
|
62
|
+
"פ" -> "p"
|
|
63
|
+
"פּ" -> "ṗ"
|
|
64
|
+
"צ" -> "ṣ"
|
|
65
|
+
"צּ" -> "ṩ"
|
|
66
|
+
"ק" -> "q"
|
|
67
|
+
"קּ" -> "q̇"
|
|
68
|
+
"ר" -> "r"
|
|
69
|
+
"שׁ" -> "š"
|
|
70
|
+
# row 38, the raised-caron typographic variant, is the same sequence as row 37
|
|
71
|
+
"שּׁ" -> "ṧ"
|
|
72
|
+
"שּׁ" -> "ṧ"
|
|
73
|
+
"ש" -> "š"
|
|
74
|
+
"שׂ" -> "ś"
|
|
75
|
+
"שּׂ" -> "ṥ"
|
|
76
|
+
"שּׂ" -> "ṥ"
|
|
77
|
+
"ת" -> "t"
|
|
78
|
+
"תּ" -> "ṫ"
|
|
79
|
+
# final forms, clause 0.3.3 (the letter's constant character)
|
|
80
|
+
"ך" -> "k"
|
|
81
|
+
"ם" -> "m"
|
|
82
|
+
"ן" -> "n"
|
|
83
|
+
"ף" -> "p"
|
|
84
|
+
"ץ" -> "ṣ"
|
|
85
|
+
# mark-order normalization: canonical NFC stacks and legacy letter-first stacks
|
|
86
|
+
"בַּ" -> "ḃ"
|
|
87
|
+
"בַּ" -> "ḃ"
|
|
88
|
+
"שָׁ" -> "š"
|
|
89
|
+
"שָּׁ" -> "ṧ"
|
|
90
|
+
# vocalized input renders the consonantal skeleton
|
|
91
|
+
"בַיִת" -> "byt"
|
|
92
|
+
"תּוֹרָה" -> "ṫwrh"
|
|
93
|
+
# Alphabetic Presentation Forms, decomposition equivalents of the rows
|
|
94
|
+
"שׁ" -> "š"
|
|
95
|
+
"שּׁ" -> "ṧ"
|
|
96
|
+
"שּׂ" -> "ṥ"
|
|
97
|
+
"בּ" -> "ḃ"
|
|
98
|
+
"הּ" -> "ḣ"
|
|
99
|
+
"וּ" -> "ẇ"
|
|
100
|
+
"וֹ" -> "w"
|
|
101
|
+
"בֿ" -> "b"
|
|
102
|
+
# notes to the table: the standard's own examples
|
|
103
|
+
# the print shows sentence-initial capitals (Gʹin, Zʹan); this consonantal
|
|
104
|
+
# map renders the Table 1 rows strictly, so unpointed mater letters keep
|
|
105
|
+
# their consonant outputs (yod row 17 -> y, alef row 1 -> ʾ + low line);
|
|
106
|
+
# the print's vowel readings come from the unencoded vocalization
|
|
107
|
+
"ג׳ין" -> "gʹyn"
|
|
108
|
+
"ז׳אן" -> "zʹʾ̲n"
|
|
109
|
+
"פרופ׳" -> "prwpʹ"
|
|
110
|
+
"ק״מ" -> "qʺm"
|
|
111
|
+
"ד." -> "d."
|
|
112
|
+
}
|
|
113
|
+
|
|
114
|
+
stage main {
|
|
115
|
+
|
|
116
|
+
# MARK-ORDER NORMALIZATION
|
|
117
|
+
# The canonical combining order places the vowel signs (ccc 10-20) before
|
|
118
|
+
# the dagesh (ccc 21) and the shin/sin dots (ccc 24-25). Move the dots back
|
|
119
|
+
# next to the letter so the letter+dot sequences of Table 1 match.
|
|
120
|
+
sub {
|
|
121
|
+
from "ְּ"
|
|
122
|
+
to "ְּ"
|
|
123
|
+
}
|
|
124
|
+
sub {
|
|
125
|
+
from "ְׁ"
|
|
126
|
+
to "ְׁ"
|
|
127
|
+
}
|
|
128
|
+
sub {
|
|
129
|
+
from "ְׂ"
|
|
130
|
+
to "ְׂ"
|
|
131
|
+
}
|
|
132
|
+
sub {
|
|
133
|
+
from "ֱּ"
|
|
134
|
+
to "ֱּ"
|
|
135
|
+
}
|
|
136
|
+
sub {
|
|
137
|
+
from "ֱׁ"
|
|
138
|
+
to "ֱׁ"
|
|
139
|
+
}
|
|
140
|
+
sub {
|
|
141
|
+
from "ֱׂ"
|
|
142
|
+
to "ֱׂ"
|
|
143
|
+
}
|
|
144
|
+
sub {
|
|
145
|
+
from "ֲּ"
|
|
146
|
+
to "ֲּ"
|
|
147
|
+
}
|
|
148
|
+
sub {
|
|
149
|
+
from "ֲׁ"
|
|
150
|
+
to "ֲׁ"
|
|
151
|
+
}
|
|
152
|
+
sub {
|
|
153
|
+
from "ֲׂ"
|
|
154
|
+
to "ֲׂ"
|
|
155
|
+
}
|
|
156
|
+
sub {
|
|
157
|
+
from "ֳּ"
|
|
158
|
+
to "ֳּ"
|
|
159
|
+
}
|
|
160
|
+
sub {
|
|
161
|
+
from "ֳׁ"
|
|
162
|
+
to "ֳׁ"
|
|
163
|
+
}
|
|
164
|
+
sub {
|
|
165
|
+
from "ֳׂ"
|
|
166
|
+
to "ֳׂ"
|
|
167
|
+
}
|
|
168
|
+
sub {
|
|
169
|
+
from "ִּ"
|
|
170
|
+
to "ִּ"
|
|
171
|
+
}
|
|
172
|
+
sub {
|
|
173
|
+
from "ִׁ"
|
|
174
|
+
to "ִׁ"
|
|
175
|
+
}
|
|
176
|
+
sub {
|
|
177
|
+
from "ִׂ"
|
|
178
|
+
to "ִׂ"
|
|
179
|
+
}
|
|
180
|
+
sub {
|
|
181
|
+
from "ֵּ"
|
|
182
|
+
to "ֵּ"
|
|
183
|
+
}
|
|
184
|
+
sub {
|
|
185
|
+
from "ֵׁ"
|
|
186
|
+
to "ֵׁ"
|
|
187
|
+
}
|
|
188
|
+
sub {
|
|
189
|
+
from "ֵׂ"
|
|
190
|
+
to "ֵׂ"
|
|
191
|
+
}
|
|
192
|
+
sub {
|
|
193
|
+
from "ֶּ"
|
|
194
|
+
to "ֶּ"
|
|
195
|
+
}
|
|
196
|
+
sub {
|
|
197
|
+
from "ֶׁ"
|
|
198
|
+
to "ֶׁ"
|
|
199
|
+
}
|
|
200
|
+
sub {
|
|
201
|
+
from "ֶׂ"
|
|
202
|
+
to "ֶׂ"
|
|
203
|
+
}
|
|
204
|
+
sub {
|
|
205
|
+
from "ַּ"
|
|
206
|
+
to "ַּ"
|
|
207
|
+
}
|
|
208
|
+
sub {
|
|
209
|
+
from "ַׁ"
|
|
210
|
+
to "ַׁ"
|
|
211
|
+
}
|
|
212
|
+
sub {
|
|
213
|
+
from "ַׂ"
|
|
214
|
+
to "ַׂ"
|
|
215
|
+
}
|
|
216
|
+
sub {
|
|
217
|
+
from "ָּ"
|
|
218
|
+
to "ָּ"
|
|
219
|
+
}
|
|
220
|
+
sub {
|
|
221
|
+
from "ָׁ"
|
|
222
|
+
to "ָׁ"
|
|
223
|
+
}
|
|
224
|
+
sub {
|
|
225
|
+
from "ָׂ"
|
|
226
|
+
to "ָׂ"
|
|
227
|
+
}
|
|
228
|
+
sub {
|
|
229
|
+
from "ֹּ"
|
|
230
|
+
to "ֹּ"
|
|
231
|
+
}
|
|
232
|
+
sub {
|
|
233
|
+
from "ֹׁ"
|
|
234
|
+
to "ֹׁ"
|
|
235
|
+
}
|
|
236
|
+
sub {
|
|
237
|
+
from "ֹׂ"
|
|
238
|
+
to "ֹׂ"
|
|
239
|
+
}
|
|
240
|
+
sub {
|
|
241
|
+
from "ֺּ"
|
|
242
|
+
to "ֺּ"
|
|
243
|
+
}
|
|
244
|
+
sub {
|
|
245
|
+
from "ֺׁ"
|
|
246
|
+
to "ֺׁ"
|
|
247
|
+
}
|
|
248
|
+
sub {
|
|
249
|
+
from "ֺׂ"
|
|
250
|
+
to "ֺׂ"
|
|
251
|
+
}
|
|
252
|
+
sub {
|
|
253
|
+
from "ֻּ"
|
|
254
|
+
to "ֻּ"
|
|
255
|
+
}
|
|
256
|
+
sub {
|
|
257
|
+
from "ֻׁ"
|
|
258
|
+
to "ֻׁ"
|
|
259
|
+
}
|
|
260
|
+
sub {
|
|
261
|
+
from "ֻׂ"
|
|
262
|
+
to "ֻׂ"
|
|
263
|
+
}
|
|
264
|
+
sub {
|
|
265
|
+
from "ּׁ"
|
|
266
|
+
to "ּׁ"
|
|
267
|
+
}
|
|
268
|
+
sub {
|
|
269
|
+
from "ּׂ"
|
|
270
|
+
to "ּׂ"
|
|
271
|
+
}
|
|
272
|
+
|
|
273
|
+
# CHARACTERS
|
|
274
|
+
parallel {
|
|
275
|
+
# Table 1, rows 1-43 (the standard's row numbering; dagesh, mappiq and
|
|
276
|
+
# shuruq rows render the Annex A dot above, code 4/7)
|
|
277
|
+
sub "א" "ʾ̲"
|
|
278
|
+
sub "בּ" "ḃ"
|
|
279
|
+
sub "ב" "b"
|
|
280
|
+
sub "גּ" "ḡ"
|
|
281
|
+
sub "ג" "g"
|
|
282
|
+
sub "דּ" "ḋ"
|
|
283
|
+
sub "ד" "d"
|
|
284
|
+
sub "הּ" "ḣ"
|
|
285
|
+
sub "ה" "h"
|
|
286
|
+
sub "וּ" "ẇ"
|
|
287
|
+
sub "ו" "w"
|
|
288
|
+
sub "זּ" "ż"
|
|
289
|
+
sub "ז" "z"
|
|
290
|
+
sub "ח" "ḥ"
|
|
291
|
+
sub "טּ" "ṭ̇"
|
|
292
|
+
sub "ט" "ṭ"
|
|
293
|
+
sub "יּ" "ẏ"
|
|
294
|
+
sub "י" "y"
|
|
295
|
+
sub "כּ" "k̇"
|
|
296
|
+
sub "כ" "k"
|
|
297
|
+
sub "לּ" "l̇"
|
|
298
|
+
sub "ל" "l"
|
|
299
|
+
sub "מּ" "ṁ"
|
|
300
|
+
sub "מ" "m"
|
|
301
|
+
sub "נּ" "ṅ"
|
|
302
|
+
sub "נ" "n"
|
|
303
|
+
sub "סּ" "ṡ"
|
|
304
|
+
sub "ס" "s"
|
|
305
|
+
sub "ע" "ʿ̲"
|
|
306
|
+
sub "פּ" "ṗ"
|
|
307
|
+
sub "פ" "p"
|
|
308
|
+
sub "צּ" "ṩ"
|
|
309
|
+
sub "צ" "ṣ"
|
|
310
|
+
sub "קּ" "q̇"
|
|
311
|
+
sub "ק" "q"
|
|
312
|
+
sub "ר" "r"
|
|
313
|
+
# rows 37-41: shin and sin (row 38 is the raised-caron typographic
|
|
314
|
+
# variant of row 37 and shares its sequence and output)
|
|
315
|
+
sub "שּׁ" "ṧ"
|
|
316
|
+
sub "שּׁ" "ṧ"
|
|
317
|
+
sub "שׁ" "š"
|
|
318
|
+
sub "שּׂ" "ṥ"
|
|
319
|
+
sub "שּׂ" "ṥ"
|
|
320
|
+
sub "שׂ" "ś"
|
|
321
|
+
# unpointed shin reads as shin with sin dot (row 37)
|
|
322
|
+
sub "ש" "š"
|
|
323
|
+
sub "תּ" "ṫ"
|
|
324
|
+
sub "ת" "t"
|
|
325
|
+
# clause 0.3.3: final forms take their letter's rows
|
|
326
|
+
sub "ךּ" "k̇"
|
|
327
|
+
sub "ך" "k"
|
|
328
|
+
sub "ם" "m"
|
|
329
|
+
sub "ן" "n"
|
|
330
|
+
sub "ףּ" "ṗ"
|
|
331
|
+
sub "ף" "p"
|
|
332
|
+
sub "ץ" "ṣ"
|
|
333
|
+
# Alphabetic Presentation Forms, decomposition equivalents of the rows
|
|
334
|
+
# (the rafe forms render as the bare letter: no Table 1 rafe row)
|
|
335
|
+
sub "שׁ" "š"
|
|
336
|
+
sub "שׂ" "ś"
|
|
337
|
+
sub "שּׁ" "ṧ"
|
|
338
|
+
sub "שּׂ" "ṥ"
|
|
339
|
+
sub "אּ" "ʾ̲"
|
|
340
|
+
sub "בּ" "ḃ"
|
|
341
|
+
sub "גּ" "ḡ"
|
|
342
|
+
sub "דּ" "ḋ"
|
|
343
|
+
sub "הּ" "ḣ"
|
|
344
|
+
sub "וּ" "ẇ"
|
|
345
|
+
sub "זּ" "ż"
|
|
346
|
+
sub "טּ" "ṭ̇"
|
|
347
|
+
sub "יּ" "ẏ"
|
|
348
|
+
sub "ךּ" "k̇"
|
|
349
|
+
sub "כּ" "k̇"
|
|
350
|
+
sub "לּ" "l̇"
|
|
351
|
+
sub "מּ" "ṁ"
|
|
352
|
+
sub "נּ" "ṅ"
|
|
353
|
+
sub "סּ" "ṡ"
|
|
354
|
+
sub "ףּ" "ṗ"
|
|
355
|
+
sub "פּ" "ṗ"
|
|
356
|
+
sub "צּ" "ṩ"
|
|
357
|
+
sub "קּ" "q̇"
|
|
358
|
+
sub "רּ" "r"
|
|
359
|
+
sub "שּ" "š"
|
|
360
|
+
sub "תּ" "ṫ"
|
|
361
|
+
sub "וֹ" "w"
|
|
362
|
+
sub "בֿ" "b"
|
|
363
|
+
sub "כֿ" "k"
|
|
364
|
+
sub "פֿ" "p"
|
|
365
|
+
# notes to the table: geresh and gershayim (notes 1.1, 2.1, 2.2)
|
|
366
|
+
sub "׳" "ʹ"
|
|
367
|
+
sub "״" "ʺ"
|
|
368
|
+
# vocalization and apparatus outside Table 1: the consonantal skeleton
|
|
369
|
+
sub "ְ" ""
|
|
370
|
+
sub "ֱ" ""
|
|
371
|
+
sub "ֲ" ""
|
|
372
|
+
sub "ֳ" ""
|
|
373
|
+
sub "ִ" ""
|
|
374
|
+
sub "ֵ" ""
|
|
375
|
+
sub "ֶ" ""
|
|
376
|
+
sub "ַ" ""
|
|
377
|
+
sub "ָ" ""
|
|
378
|
+
sub "ֹ" ""
|
|
379
|
+
sub "ֺ" ""
|
|
380
|
+
sub "ֻ" ""
|
|
381
|
+
# residual dagesh (letters without a dagesh row: alef, het, resh)
|
|
382
|
+
sub "ּ" ""
|
|
383
|
+
sub "ֽ" ""
|
|
384
|
+
sub "ֿ" ""
|
|
385
|
+
sub "ׁ" ""
|
|
386
|
+
sub "ׂ" ""
|
|
387
|
+
sub "ׄ" ""
|
|
388
|
+
sub "ׅ" ""
|
|
389
|
+
sub "ׇ" ""
|
|
390
|
+
# teamim (cantillation marks)
|
|
391
|
+
sub "֑" ""
|
|
392
|
+
sub "֒" ""
|
|
393
|
+
sub "֓" ""
|
|
394
|
+
sub "֔" ""
|
|
395
|
+
sub "֕" ""
|
|
396
|
+
sub "֖" ""
|
|
397
|
+
sub "֗" ""
|
|
398
|
+
sub "֘" ""
|
|
399
|
+
sub "֙" ""
|
|
400
|
+
sub "֚" ""
|
|
401
|
+
sub "֛" ""
|
|
402
|
+
sub "֜" ""
|
|
403
|
+
sub "֝" ""
|
|
404
|
+
sub "֞" ""
|
|
405
|
+
sub "֟" ""
|
|
406
|
+
sub "֠" ""
|
|
407
|
+
sub "֡" ""
|
|
408
|
+
sub "֢" ""
|
|
409
|
+
sub "֣" ""
|
|
410
|
+
sub "֤" ""
|
|
411
|
+
sub "֥" ""
|
|
412
|
+
sub "֦" ""
|
|
413
|
+
sub "֧" ""
|
|
414
|
+
sub "֨" ""
|
|
415
|
+
sub "֩" ""
|
|
416
|
+
sub "֪" ""
|
|
417
|
+
sub "֫" ""
|
|
418
|
+
sub "֬" ""
|
|
419
|
+
sub "֭" ""
|
|
420
|
+
sub "֮" ""
|
|
421
|
+
sub "֯" ""
|
|
422
|
+
}
|
|
423
|
+
|
|
424
|
+
}
|
|
425
|
+
|
|
426
|
+
}
|