@natlibfi/sfs-4900 1.1.4 → 2.0.0-alpha.4

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.
@@ -4,6 +4,10 @@ name: Melinda-node-tests
4
4
 
5
5
  on: push
6
6
 
7
+ permissions:
8
+ id-token: write # Required for OIDC
9
+ contents: read
10
+
7
11
  jobs:
8
12
  build-node-versions:
9
13
  name: Node version matrix
@@ -13,14 +17,14 @@ jobs:
13
17
 
14
18
  strategy:
15
19
  matrix:
16
- node-version: [20.x]
20
+ node-version: [22.x, 24.x]
17
21
  # See supported Node.js release schedule at https://nodejs.org/en/about/releases/
18
22
 
19
23
  steps:
20
24
  - name: Checkout the code
21
- uses: actions/checkout@v4
25
+ uses: actions/checkout@v5
22
26
  - name: Use Node.js ${{ matrix.node-version }}
23
- uses: actions/setup-node@v4
27
+ uses: actions/setup-node@v6
24
28
  with:
25
29
  node-version: ${{ matrix.node-version }}
26
30
  cache: 'npm'
@@ -33,11 +37,11 @@ jobs:
33
37
  njsscan:
34
38
  name: Njsscan-check
35
39
  runs-on: ubuntu-latest
36
- container: node:20
40
+ container: node:22
37
41
 
38
42
  steps:
39
43
  - name: Checkout the code
40
- uses: actions/checkout@v4
44
+ uses: actions/checkout@v5
41
45
  - name: nodejsscan scan
42
46
  id: njsscan
43
47
  uses: ajinabraham/njsscan-action@master
@@ -47,10 +51,10 @@ jobs:
47
51
  license-scan:
48
52
  name: License compliance check
49
53
  runs-on: ubuntu-latest
50
- container: node:20
54
+ container: node:22
51
55
 
52
56
  steps:
53
- - uses: actions/checkout@v4
57
+ - uses: actions/checkout@v5
54
58
  - uses: mikaelvesavuori/license-compliance-action@v1
55
59
  with:
56
60
  exclude_pattern: /^@natlibfi/
@@ -58,18 +62,27 @@ jobs:
58
62
  publish:
59
63
  name: Npm publishing
60
64
  runs-on: ubuntu-latest
61
- container: node:20
65
+ container: node:22
62
66
  needs: [build-node-versions, njsscan]
63
67
  if: contains(github.ref, 'refs/tags/')
64
68
 
65
69
  steps:
66
- - uses: actions/checkout@v4
70
+ - uses: actions/checkout@v5
67
71
  # Setup .npmrc file to publish to npm
68
- - uses: actions/setup-node@v4
72
+ - name: Prepare node for publish
73
+ uses: actions/setup-node@v6
69
74
  with:
70
- node-version: '20.x'
75
+ node-version: '22.x'
71
76
  registry-url: 'https://registry.npmjs.org'
72
- - run: npm ci
73
- - run: npm publish
74
- env:
75
- NODE_AUTH_TOKEN: ${{ secrets.SFS4900_NPM_TOKEN }}
77
+ - name: Update npm
78
+ run: npm install -g npm@latest
79
+ - name: Clean install
80
+ run: npm ci
81
+ # Publish stable release with --tag latest
82
+ - name: Publish stable release
83
+ if: ${{!contains(github.ref, '-alpha')}}
84
+ run: npm publish --tag=latest
85
+ # Publish pre-release without --tag latest
86
+ - name: Publish pre-release
87
+ if: contains(github.ref, '-alpha')
88
+ run: npm publish --tag=next
@@ -1,32 +1,24 @@
1
- "use strict";
2
-
3
- Object.defineProperty(exports, "__esModule", {
4
- value: true
5
- });
6
- exports.convertToLatin = convertToLatin;
7
- // Based on https://fi.wikipedia.org/wiki/Ven%C3%A4j%C3%A4n_translitterointi and https://fi.wikipedia.org/wiki/Ukrainan_translitterointi
8
-
9
- const consonants = ['б', 'в', 'г', 'ґ', 'д', 'ж', 'з', 'к', 'л', 'м', 'н', 'п', 'р', 'с', 'т', 'ф', 'х', 'ц', 'ч', 'ш', 'щ', 'Б', 'В', 'Г', 'Ґ', 'Д', 'Ж', 'З', 'К', 'Л', 'М', 'Н', 'П', 'Р', 'С', 'Т', 'Ф', 'Х', 'Ц', 'Ч', 'Ш', 'Щ'];
10
- const characters = ['А', 'а', 'Б', 'б', 'В', 'в', 'Г', 'г', 'Ґ', 'ґ', 'Д', 'д', 'Е', 'е', 'E', 'e', 'Ё', 'ё', 'Ё', 'ё', 'Є', 'є', 'Ж', 'ж', 'З', 'з', 'И', 'и', 'И', 'и', 'І', 'і', 'Ї', 'ї', 'Й', 'й', 'Й', 'й', 'Й', 'й', 'К', 'к', 'Л', 'л', 'М', 'м', 'Н', 'н', 'О', 'о', 'П', 'п', 'Р', 'р', 'С', 'с', 'Т', 'т', 'У', 'у', 'Ф', 'ф', 'Х', 'х', 'Ц', 'ц', 'Ч', 'ч', 'Ш', 'ш', 'Щ', 'щ', 'Ъ', 'ъ', 'Ы', 'ы', 'Ь', 'ь', 'Э', 'э', 'Ю', 'ю', 'Я', 'я', '’'];
1
+ const consonants = ["\u0431", "\u0432", "\u0433", "\u0491", "\u0434", "\u0436", "\u0437", "\u043A", "\u043B", "\u043C", "\u043D", "\u043F", "\u0440", "\u0441", "\u0442", "\u0444", "\u0445", "\u0446", "\u0447", "\u0448", "\u0449", "\u0411", "\u0412", "\u0413", "\u0490", "\u0414", "\u0416", "\u0417", "\u041A", "\u041B", "\u041C", "\u041D", "\u041F", "\u0420", "\u0421", "\u0422", "\u0424", "\u0425", "\u0426", "\u0427", "\u0428", "\u0429"];
2
+ const characters = ["\u0410", "\u0430", "\u0411", "\u0431", "\u0412", "\u0432", "\u0413", "\u0433", "\u0490", "\u0491", "\u0414", "\u0434", "\u0415", "\u0435", "E", "e", "\u0401", "\u0451", "\u0401", "\u0451", "\u0404", "\u0454", "\u0416", "\u0436", "\u0417", "\u0437", "\u0418", "\u0438", "\u0418", "\u0438", "\u0406", "\u0456", "\u0407", "\u0457", "\u0419", "\u0439", "\u0419", "\u0439", "\u0419", "\u0439", "\u041A", "\u043A", "\u041B", "\u043B", "\u041C", "\u043C", "\u041D", "\u043D", "\u041E", "\u043E", "\u041F", "\u043F", "\u0420", "\u0440", "\u0421", "\u0441", "\u0422", "\u0442", "\u0423", "\u0443", "\u0424", "\u0444", "\u0425", "\u0445", "\u0426", "\u0446", "\u0427", "\u0447", "\u0428", "\u0448", "\u0429", "\u0449", "\u042A", "\u044A", "\u042B", "\u044B", "\u042C", "\u044C", "\u042D", "\u044D", "\u042E", "\u044E", "\u042F", "\u044F", "\u2019"];
11
3
  const map = {
12
- 'А': 'A',
4
+ "\u0410": "A",
13
5
  // Both
14
- 'а': 'a',
15
- 'Б': 'B',
6
+ "\u0430": "a",
7
+ "\u0411": "B",
16
8
  // Both
17
- 'б': 'b',
18
- 'В': 'V',
9
+ "\u0431": "b",
10
+ "\u0412": "V",
19
11
  // Both
20
- 'в': 'v',
21
- 'Г': 'G',
12
+ "\u0432": "v",
13
+ "\u0413": "G",
22
14
  // rus, ukr h, Ґ ґ g, see code
23
- 'г': 'g',
24
- 'Ґ': 'G',
15
+ "\u0433": "g",
16
+ "\u0490": "G",
25
17
  // UKR-only
26
- 'ґ': 'g',
27
- 'Д': 'D',
18
+ "\u0491": "g",
19
+ "\u0414": "D",
28
20
  // both
29
- 'д': 'd',
21
+ "\u0434": "d",
30
22
  // 'Е': 'E', // UKR is simpler
31
23
  // 'е': 'e',
32
24
  // 'E': 'Je',
@@ -35,188 +27,181 @@ const map = {
35
27
  // 'ё': 'o',
36
28
  // 'Ё': 'Jo',
37
29
  // 'ё': 'jo',
38
- 'Є': 'Je',
30
+ "\u0404": "Je",
39
31
  // UKR only
40
- 'є': 'je',
41
- 'Ж': 'Ž',
32
+ "\u0454": "je",
33
+ "\u0416": "\u017D",
42
34
  // Both
43
- 'ж': 'ž',
44
- 'З': 'Z',
35
+ "\u0436": "\u017E",
36
+ "\u0417": "Z",
45
37
  // Both
46
- 'з': 'z',
47
- 'И': 'I',
38
+ "\u0437": "z",
39
+ "\u0418": "I",
48
40
  // RUS: 'i'/'ji'. UKR: 'y'. Default to 'i'
49
- 'и': 'i',
41
+ "\u0438": "i",
50
42
  //'И': 'Ji',
51
43
  //'и': 'ji',*/
52
- 'І': 'I',
44
+ "\u0406": "I",
53
45
  // UKR only
54
- 'і': 'i',
55
- 'Ї': 'Ji',
46
+ "\u0456": "i",
47
+ "\u0407": "Ji",
56
48
  // UKR only
57
- 'ї': 'ji',
58
- 'Й': 'I',
49
+ "\u0457": "ji",
50
+ "\u0419": "I",
59
51
  // RUS and UKR both map to 'i'/'j'/'', but the rules differ slightly. Map to I/i by default
60
- 'й': 'i',
52
+ "\u0439": "i",
61
53
  //'Й': 'J',
62
54
  //'й': 'j',
63
55
  //'Й': '',
64
56
  //'й': '',
65
- 'К': 'K',
57
+ "\u041A": "K",
66
58
  // both
67
- 'к': 'k',
68
- 'Л': 'L',
59
+ "\u043A": "k",
60
+ "\u041B": "L",
69
61
  // both
70
- 'л': 'l',
71
- 'М': 'M',
62
+ "\u043B": "l",
63
+ "\u041C": "M",
72
64
  // both
73
- 'м': 'm',
74
- 'Н': 'N',
65
+ "\u043C": "m",
66
+ "\u041D": "N",
75
67
  // both
76
- 'н': 'n',
77
- 'О': 'O',
68
+ "\u043D": "n",
69
+ "\u041E": "O",
78
70
  // both
79
- 'о': 'o',
80
- 'П': 'P',
71
+ "\u043E": "o",
72
+ "\u041F": "P",
81
73
  // both
82
- 'п': 'p',
83
- 'Р': 'R',
74
+ "\u043F": "p",
75
+ "\u0420": "R",
84
76
  // both
85
- 'р': 'r',
86
- 'С': 'S',
77
+ "\u0440": "r",
78
+ "\u0421": "S",
87
79
  // both
88
- 'с': 's',
89
- 'Т': 'T',
80
+ "\u0441": "s",
81
+ "\u0422": "T",
90
82
  // both
91
- 'т': 't',
92
- 'У': 'U',
83
+ "\u0442": "t",
84
+ "\u0423": "U",
93
85
  // both
94
- 'у': 'u',
95
- 'Ф': 'F',
86
+ "\u0443": "u",
87
+ "\u0424": "F",
96
88
  // both
97
- 'ф': 'f',
98
- 'Х': 'H',
89
+ "\u0444": "f",
90
+ "\u0425": "H",
99
91
  // UKR: h’
100
- 'х': 'h',
101
- 'Ц': 'Ts',
92
+ "\u0445": "h",
93
+ "\u0426": "Ts",
102
94
  // both
103
- 'ц': 'ts',
104
- 'Ч': 'Tš',
95
+ "\u0446": "ts",
96
+ "\u0427": "T\u0161",
105
97
  // both
106
- 'ч': 'tš',
107
- 'Ш': 'Š',
98
+ "\u0447": "t\u0161",
99
+ "\u0428": "\u0160",
108
100
  // both
109
- 'ш': 'š',
110
- 'Щ': 'Štš',
101
+ "\u0448": "\u0161",
102
+ "\u0429": "\u0160t\u0161",
111
103
  // both
112
- 'щ': 'štš',
113
- 'Ъ': '',
104
+ "\u0449": "\u0161t\u0161",
105
+ "\u042A": "",
114
106
  // both (UKR: no longer used)
115
- 'ъ': '',
116
- 'Ы': 'Y',
107
+ "\u044A": "",
108
+ "\u042B": "Y",
117
109
  // RUS onlt
118
- 'ы': 'y',
119
- 'Ь': '',
110
+ "\u044B": "y",
111
+ "\u042C": "",
120
112
  // both
121
- 'ь': '',
122
- 'Э': 'E',
113
+ "\u044C": "",
114
+ "\u042D": "E",
123
115
  // RUS only
124
- 'э': 'e',
125
- 'Ю': 'Ju',
116
+ "\u044D": "e",
117
+ "\u042E": "Ju",
126
118
  // Both
127
- 'ю': 'ju',
128
- 'Я': 'Ja',
119
+ "\u044E": "ju",
120
+ "\u042F": "Ja",
129
121
  // Both
130
- 'я': 'ja',
131
- '’': '' // UKR only
122
+ "\u044F": "ja",
123
+ "\u2019": ""
124
+ // UKR only
132
125
  };
133
- function createConverter(word, lang = 'rus') {
134
- // lang: 'rus' and 'ukr' supported
126
+ function createConverter(word, lang = "rus") {
135
127
  const warnings = [];
136
- //console.log(`LANG: ${lang}`); // eslint-disable-line no-console
137
-
138
128
  function eOrJe(char, previousCharacter) {
139
- if (lang === 'ukr') {
140
- return char === 'Е' ? 'E' : 'e';
129
+ if (lang === "ukr") {
130
+ return char === "\u0415" ? "E" : "e";
141
131
  }
142
132
  if (isConsonant(previousCharacter)) {
143
- if (['Ъ', 'Ь', 'ъ', 'ь'].includes(previousCharacter)) {
144
- return char === 'Е' ? 'Je' : 'je';
133
+ if (["\u042A", "\u042C", "\u044A", "\u044C"].includes(previousCharacter)) {
134
+ return char === "\u0415" ? "Je" : "je";
145
135
  }
146
- return char === 'Е' ? 'E' : 'e';
136
+ return char === "\u0415" ? "E" : "e";
147
137
  }
148
-
149
- //if (isFirstCharacter || ['Ъ','Ь','ъ','ь'].includes(previousCharacter) || !isConsonant(previousCharacter)) {
150
- return char === 'Е' ? 'Je' : 'je';
138
+ return char === "\u0415" ? "Je" : "je";
151
139
  }
152
140
  function gOrH(char) {
153
- if (lang === 'ukr') {
154
- return char === 'Г' ? 'H' : 'h';
141
+ if (lang === "ukr") {
142
+ return char === "\u0413" ? "H" : "h";
155
143
  }
156
- return char === 'Г' ? 'G' : 'g';
144
+ return char === "\u0413" ? "G" : "g";
157
145
  }
158
146
  function iOrJ(char, previousCharacter, isFirstCharacter, isLastCharacter) {
159
147
  if (isFirstCharacter) {
160
- // Both RUS and UKR
161
- return char === 'Й' ? 'J' : 'j';
148
+ return char === "\u0419" ? "J" : "j";
162
149
  }
163
- if (lang === 'ukr' && ['І', 'і'].includes(previousCharacter)) {
150
+ if (lang === "ukr" && ["\u0406", "\u0456"].includes(previousCharacter)) {
164
151
  if (isLastCharacter) {
165
- return '';
152
+ return "";
166
153
  }
167
- return char === 'Й' ? 'J' : 'j';
154
+ return char === "\u0419" ? "J" : "j";
168
155
  }
169
- if (lang === 'rus' && ['и', 'И'].includes(previousCharacter)) {
156
+ if (lang === "rus" && ["\u0438", "\u0418"].includes(previousCharacter)) {
170
157
  if (isLastCharacter) {
171
- return '';
158
+ return "";
172
159
  }
173
- return char === 'Й' ? 'J' : 'j';
160
+ return char === "\u0419" ? "J" : "j";
174
161
  }
175
- return char === 'Й' ? 'I' : 'i';
162
+ return char === "\u0419" ? "I" : "i";
176
163
  }
177
164
  function convertCharacter(char, i) {
178
165
  const previousCharacter = word[i - 1];
179
166
  const nextCharacter = word[i + 1];
180
- const isFirstCharacter = i === 0 || !characters.some(c => c === previousCharacter);
181
- if (['Г', 'г'].includes(char)) {
182
- // 'gogol' vs 'hohol'
167
+ const isFirstCharacter = i === 0 || !characters.some((c) => c === previousCharacter);
168
+ if (["\u0413", "\u0433"].includes(char)) {
183
169
  return gOrH(char);
184
170
  }
185
- if (['Е', 'е'].includes(char)) {
171
+ if (["\u0415", "\u0435"].includes(char)) {
186
172
  return eOrJe(char, previousCharacter);
187
173
  }
188
- if (['Ё', 'ё'].includes(char)) {
189
- // RUS only
190
- if (['ж', 'ч', 'ш', 'щ', 'Ж', 'Ч', 'Ш', 'Щ'].includes(previousCharacter)) {
191
- return previousCharacter === 'Ё' ? 'O' : 'o';
174
+ if (["\u0401", "\u0451"].includes(char)) {
175
+ if (["\u0436", "\u0447", "\u0448", "\u0449", "\u0416", "\u0427", "\u0428", "\u0429"].includes(previousCharacter)) {
176
+ return previousCharacter === "\u0401" ? "O" : "o";
192
177
  }
193
- return previousCharacter === 'Ё' ? 'Jo' : 'jo';
178
+ return previousCharacter === "\u0401" ? "Jo" : "jo";
194
179
  }
195
- if (['И', 'и'].includes(char)) {
196
- if (lang === 'ukr') {
197
- return char === 'И' ? 'Y' : 'y';
180
+ if (["\u0418", "\u0438"].includes(char)) {
181
+ if (lang === "ukr") {
182
+ return char === "\u0418" ? "Y" : "y";
198
183
  }
199
- if (['Ь', 'ь'].includes(previousCharacter)) {
200
- return char === 'И' ? 'Ji' : 'ji';
184
+ if (["\u042C", "\u044C"].includes(previousCharacter)) {
185
+ return char === "\u0418" ? "Ji" : "ji";
201
186
  }
202
- return char === 'И' ? 'I' : 'i';
187
+ return char === "\u0418" ? "I" : "i";
203
188
  }
204
- if (['Й', 'й'].includes(char)) {
205
- const isLastCharacter = i === word.length - 1 || !characters.some(c => c === nextCharacter);
189
+ if (["\u0419", "\u0439"].includes(char)) {
190
+ const isLastCharacter = i === word.length - 1 || !characters.some((c) => c === nextCharacter);
206
191
  return iOrJ(char, previousCharacter, isFirstCharacter, isLastCharacter);
207
192
  }
208
- if (lang === 'ukr') {
209
- if (char === 'Х') {
210
- return 'H\'';
193
+ if (lang === "ukr") {
194
+ if (char === "\u0425") {
195
+ return "H'";
211
196
  }
212
- if (char === 'х') {
213
- return 'h\'';
197
+ if (char === "\u0445") {
198
+ return "h'";
214
199
  }
215
200
  }
216
201
  return convertCharacter2();
217
202
  function convertCharacter2() {
218
203
  const converted = map[char];
219
- if (converted === undefined) {
204
+ if (converted === void 0) {
220
205
  warnings.push(`Character ${char} at position ${i} was not cyrillic.`);
221
206
  return char;
222
207
  }
@@ -228,9 +213,9 @@ function createConverter(word, lang = 'rus') {
228
213
  convertCharacter
229
214
  };
230
215
  }
231
- function convertToLatin(word, lang = 'rus') {
216
+ export function convertToLatin(word, lang = "rus") {
232
217
  const converter = createConverter(word, lang);
233
- const convertedWord = word.split('').map(converter.convertCharacter).join('');
218
+ const convertedWord = word.split("").map(converter.convertCharacter).join("");
234
219
  return {
235
220
  from: word,
236
221
  result: convertedWord,
@@ -240,4 +225,4 @@ function convertToLatin(word, lang = 'rus') {
240
225
  function isConsonant(char) {
241
226
  return consonants.includes(char);
242
227
  }
243
- //# sourceMappingURL=transliteration.js.map
228
+ //# sourceMappingURL=transliteration.js.map
@@ -1 +1,7 @@
1
- {"version":3,"file":"transliteration.js","names":["consonants","characters","map","createConverter","word","lang","warnings","eOrJe","char","previousCharacter","isConsonant","includes","gOrH","iOrJ","isFirstCharacter","isLastCharacter","convertCharacter","i","nextCharacter","some","c","length","convertCharacter2","converted","undefined","push","convertToLatin","converter","convertedWord","split","join","from","result"],"sources":["../src/transliteration.js"],"sourcesContent":["// Based on https://fi.wikipedia.org/wiki/Ven%C3%A4j%C3%A4n_translitterointi and https://fi.wikipedia.org/wiki/Ukrainan_translitterointi\n\nconst consonants = ['б', 'в', 'г', 'ґ', 'д', 'ж', 'з', 'к', 'л', 'м', 'н', 'п', 'р', 'с', 'т', 'ф', 'х', 'ц', 'ч', 'ш', 'щ', 'Б', 'В', 'Г', 'Ґ', 'Д', 'Ж', 'З', 'К', 'Л', 'М', 'Н', 'П', 'Р', 'С', 'Т', 'Ф', 'Х', 'Ц', 'Ч', 'Ш', 'Щ'];\n\nconst characters = ['А', 'а', 'Б', 'б', 'В', 'в', 'Г', 'г', 'Ґ', 'ґ', 'Д', 'д', 'Е', 'е', 'E', 'e', 'Ё', 'ё', 'Ё', 'ё', 'Є', 'є', 'Ж', 'ж', 'З', 'з', 'И', 'и', 'И', 'и', 'І', 'і', 'Ї', 'ї', 'Й', 'й', 'Й', 'й', 'Й', 'й', 'К', 'к', 'Л', 'л', 'М', 'м', 'Н', 'н', 'О', 'о', 'П', 'п', 'Р', 'р', 'С', 'с', 'Т', 'т', 'У', 'у', 'Ф', 'ф', 'Х', 'х', 'Ц', 'ц', 'Ч', 'ч', 'Ш', 'ш', 'Щ', 'щ', 'Ъ', 'ъ', 'Ы', 'ы', 'Ь', 'ь', 'Э', 'э', 'Ю', 'ю', 'Я', 'я', '’'];\n\nconst map = {\n 'А': 'A', // Both\n 'а': 'a',\n 'Б': 'B', // Both\n 'б': 'b',\n 'В': 'V', // Both\n 'в': 'v',\n 'Г': 'G', // rus, ukr h, Ґ ґ g, see code\n 'г': 'g',\n 'Ґ': 'G', // UKR-only\n 'ґ': 'g',\n 'Д': 'D', // both\n 'д': 'd',\n // 'Е': 'E', // UKR is simpler\n // 'е': 'e',\n // 'E': 'Je',\n // 'e': 'je',\n // 'Ё': 'O', // RUS only\n // 'ё': 'o',\n // 'Ё': 'Jo',\n // 'ё': 'jo',\n 'Є': 'Je', // UKR only\n 'є': 'je',\n 'Ж': 'Ž', // Both\n 'ж': 'ž',\n 'З': 'Z', // Both\n 'з': 'z',\n 'И': 'I', // RUS: 'i'/'ji'. UKR: 'y'. Default to 'i'\n 'и': 'i',\n //'И': 'Ji',\n //'и': 'ji',*/\n 'І': 'I', // UKR only\n 'і': 'i',\n 'Ї': 'Ji', // UKR only\n 'ї': 'ji',\n 'Й': 'I', // RUS and UKR both map to 'i'/'j'/'', but the rules differ slightly. Map to I/i by default\n 'й': 'i',\n //'Й': 'J',\n //'й': 'j',\n //'Й': '',\n //'й': '',\n 'К': 'K', // both\n 'к': 'k',\n 'Л': 'L', // both\n 'л': 'l',\n 'М': 'M', // both\n 'м': 'm',\n 'Н': 'N', // both\n 'н': 'n',\n 'О': 'O', // both\n 'о': 'o',\n 'П': 'P', // both\n 'п': 'p',\n 'Р': 'R', // both\n 'р': 'r',\n 'С': 'S', // both\n 'с': 's',\n 'Т': 'T', // both\n 'т': 't',\n 'У': 'U', // both\n 'у': 'u',\n 'Ф': 'F', // both\n 'ф': 'f',\n 'Х': 'H', // UKR: h’\n 'х': 'h',\n 'Ц': 'Ts', // both\n 'ц': 'ts',\n 'Ч': 'Tš', // both\n 'ч': 'tš',\n 'Ш': 'Š', // both\n 'ш': 'š',\n 'Щ': 'Štš', // both\n 'щ': 'štš',\n 'Ъ': '', // both (UKR: no longer used)\n 'ъ': '',\n 'Ы': 'Y', // RUS onlt\n 'ы': 'y',\n 'Ь': '', // both\n 'ь': '',\n 'Э': 'E', // RUS only\n 'э': 'e',\n 'Ю': 'Ju', // Both\n 'ю': 'ju',\n 'Я': 'Ja', // Both\n 'я': 'ja',\n '’': '' // UKR only\n};\n\nfunction createConverter(word, lang = 'rus') { // lang: 'rus' and 'ukr' supported\n const warnings = [];\n //console.log(`LANG: ${lang}`); // eslint-disable-line no-console\n\n function eOrJe(char, previousCharacter) {\n if (lang === 'ukr') {\n return char === 'Е' ? 'E' : 'e';\n }\n if (isConsonant(previousCharacter)) {\n if (['Ъ', 'Ь', 'ъ', 'ь'].includes(previousCharacter)) {\n return char === 'Е' ? 'Je' : 'je';\n }\n return char === 'Е' ? 'E' : 'e';\n }\n\n //if (isFirstCharacter || ['Ъ','Ь','ъ','ь'].includes(previousCharacter) || !isConsonant(previousCharacter)) {\n return char === 'Е' ? 'Je' : 'je';\n }\n\n function gOrH(char) {\n if (lang === 'ukr') {\n return char === 'Г' ? 'H' : 'h';\n }\n\n return char === 'Г' ? 'G' : 'g';\n }\n function iOrJ(char, previousCharacter, isFirstCharacter, isLastCharacter) {\n if (isFirstCharacter) { // Both RUS and UKR\n return char === 'Й' ? 'J' : 'j';\n }\n\n if (lang === 'ukr' && ['І', 'і'].includes(previousCharacter)) {\n if (isLastCharacter) {\n return '';\n }\n return char === 'Й' ? 'J' : 'j';\n }\n if (lang === 'rus' && ['и', 'И'].includes(previousCharacter)) {\n if (isLastCharacter) {\n return '';\n }\n return char === 'Й' ? 'J' : 'j';\n }\n return char === 'Й' ? 'I' : 'i';\n }\n\n function convertCharacter(char, i) {\n const previousCharacter = word[i - 1];\n const nextCharacter = word[i + 1];\n\n const isFirstCharacter = i === 0 || !characters.some(c => c === previousCharacter);\n\n if (['Г', 'г'].includes(char)) { // 'gogol' vs 'hohol'\n return gOrH(char);\n }\n\n if (['Е', 'е'].includes(char)) {\n return eOrJe(char, previousCharacter);\n }\n\n if (['Ё', 'ё'].includes(char)) { // RUS only\n if (['ж', 'ч', 'ш', 'щ', 'Ж', 'Ч', 'Ш', 'Щ'].includes(previousCharacter)) {\n return previousCharacter === 'Ё' ? 'O' : 'o';\n }\n return previousCharacter === 'Ё' ? 'Jo' : 'jo';\n }\n\n if (['И', 'и'].includes(char)) {\n if (lang === 'ukr') {\n return char === 'И' ? 'Y' : 'y';\n }\n if (['Ь', 'ь'].includes(previousCharacter)) {\n return char === 'И' ? 'Ji' : 'ji';\n }\n return char === 'И' ? 'I' : 'i';\n }\n\n if (['Й', 'й'].includes(char)) {\n const isLastCharacter = i === word.length - 1 || !characters.some(c => c === nextCharacter);\n return iOrJ(char, previousCharacter, isFirstCharacter, isLastCharacter);\n }\n\n if (lang === 'ukr') {\n if (char === 'Х') {\n return 'H\\'';\n }\n if (char === 'х') {\n return 'h\\'';\n }\n }\n\n return convertCharacter2();\n\n function convertCharacter2() {\n const converted = map[char];\n\n if (converted === undefined) {\n warnings.push(`Character ${char} at position ${i} was not cyrillic.`);\n return char;\n }\n\n return converted;\n }\n }\n\n return {\n warnings,\n convertCharacter\n };\n}\n\nexport function convertToLatin(word, lang = 'rus') {\n const converter = createConverter(word, lang);\n\n const convertedWord = word.split('').map(converter.convertCharacter).join('');\n\n return {\n from: word,\n result: convertedWord,\n warnings: converter.warnings\n };\n}\n\nfunction isConsonant(char) {\n return consonants.includes(char);\n}\n"],"mappings":";;;;;;AAAA;;AAEA,MAAMA,UAAU,GAAG,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC;AAErO,MAAMC,UAAU,GAAG,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC;AAE5b,MAAMC,GAAG,GAAG;EACV,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR;EACA;EACA;EACA;EACA;EACA;EACA;EACA;EACA,GAAG,EAAE,IAAI;EAAE;EACX,GAAG,EAAE,IAAI;EACT,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR;EACA;EACA,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,IAAI;EAAE;EACX,GAAG,EAAE,IAAI;EACT,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR;EACA;EACA;EACA;EACA,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,IAAI;EAAE;EACX,GAAG,EAAE,IAAI;EACT,GAAG,EAAE,IAAI;EAAE;EACX,GAAG,EAAE,IAAI;EACT,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,KAAK;EAAE;EACZ,GAAG,EAAE,KAAK;EACV,GAAG,EAAE,EAAE;EAAE;EACT,GAAG,EAAE,EAAE;EACP,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,EAAE;EAAE;EACT,GAAG,EAAE,EAAE;EACP,GAAG,EAAE,GAAG;EAAE;EACV,GAAG,EAAE,GAAG;EACR,GAAG,EAAE,IAAI;EAAE;EACX,GAAG,EAAE,IAAI;EACT,GAAG,EAAE,IAAI;EAAE;EACX,GAAG,EAAE,IAAI;EACT,GAAG,EAAE,EAAE,CAAC;AACV,CAAC;AAED,SAASC,eAAeA,CAACC,IAAI,EAAEC,IAAI,GAAG,KAAK,EAAE;EAAE;EAC7C,MAAMC,QAAQ,GAAG,EAAE;EACnB;;EAEA,SAASC,KAAKA,CAACC,IAAI,EAAEC,iBAAiB,EAAE;IACtC,IAAIJ,IAAI,KAAK,KAAK,EAAE;MAClB,OAAOG,IAAI,KAAK,GAAG,GAAG,GAAG,GAAG,GAAG;IACjC;IACA,IAAIE,WAAW,CAACD,iBAAiB,CAAC,EAAE;MAClC,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAACE,QAAQ,CAACF,iBAAiB,CAAC,EAAE;QACpD,OAAOD,IAAI,KAAK,GAAG,GAAG,IAAI,GAAG,IAAI;MACnC;MACA,OAAOA,IAAI,KAAK,GAAG,GAAG,GAAG,GAAG,GAAG;IACjC;;IAEA;IACA,OAAOA,IAAI,KAAK,GAAG,GAAG,IAAI,GAAG,IAAI;EACnC;EAEA,SAASI,IAAIA,CAACJ,IAAI,EAAE;IAClB,IAAIH,IAAI,KAAK,KAAK,EAAE;MAClB,OAAOG,IAAI,KAAK,GAAG,GAAG,GAAG,GAAG,GAAG;IACjC;IAEA,OAAOA,IAAI,KAAK,GAAG,GAAG,GAAG,GAAG,GAAG;EACjC;EACA,SAASK,IAAIA,CAACL,IAAI,EAAEC,iBAAiB,EAAEK,gBAAgB,EAAEC,eAAe,EAAE;IACxE,IAAID,gBAAgB,EAAE;MAAE;MACtB,OAAON,IAAI,KAAK,GAAG,GAAG,GAAG,GAAG,GAAG;IACjC;IAEA,IAAIH,IAAI,KAAK,KAAK,IAAI,CAAC,GAAG,EAAE,GAAG,CAAC,CAACM,QAAQ,CAACF,iBAAiB,CAAC,EAAE;MAC5D,IAAIM,eAAe,EAAE;QACnB,OAAO,EAAE;MACX;MACA,OAAOP,IAAI,KAAK,GAAG,GAAG,GAAG,GAAG,GAAG;IACjC;IACA,IAAIH,IAAI,KAAK,KAAK,IAAI,CAAC,GAAG,EAAE,GAAG,CAAC,CAACM,QAAQ,CAACF,iBAAiB,CAAC,EAAE;MAC5D,IAAIM,eAAe,EAAE;QACnB,OAAO,EAAE;MACX;MACA,OAAOP,IAAI,KAAK,GAAG,GAAG,GAAG,GAAG,GAAG;IACjC;IACA,OAAOA,IAAI,KAAK,GAAG,GAAG,GAAG,GAAG,GAAG;EACjC;EAEA,SAASQ,gBAAgBA,CAACR,IAAI,EAAES,CAAC,EAAE;IACjC,MAAMR,iBAAiB,GAAGL,IAAI,CAACa,CAAC,GAAG,CAAC,CAAC;IACrC,MAAMC,aAAa,GAAGd,IAAI,CAACa,CAAC,GAAG,CAAC,CAAC;IAEjC,MAAMH,gBAAgB,GAAGG,CAAC,KAAK,CAAC,IAAI,CAAChB,UAAU,CAACkB,IAAI,CAACC,CAAC,IAAIA,CAAC,KAAKX,iBAAiB,CAAC;IAElF,IAAI,CAAC,GAAG,EAAE,GAAG,CAAC,CAACE,QAAQ,CAACH,IAAI,CAAC,EAAE;MAAE;MAC/B,OAAOI,IAAI,CAACJ,IAAI,CAAC;IACnB;IAEA,IAAI,CAAC,GAAG,EAAE,GAAG,CAAC,CAACG,QAAQ,CAACH,IAAI,CAAC,EAAE;MAC7B,OAAOD,KAAK,CAACC,IAAI,EAAEC,iBAAiB,CAAC;IACvC;IAEA,IAAI,CAAC,GAAG,EAAE,GAAG,CAAC,CAACE,QAAQ,CAACH,IAAI,CAAC,EAAE;MAAE;MAC/B,IAAI,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,CAAC,CAACG,QAAQ,CAACF,iBAAiB,CAAC,EAAE;QACxE,OAAOA,iBAAiB,KAAK,GAAG,GAAG,GAAG,GAAG,GAAG;MAC9C;MACA,OAAOA,iBAAiB,KAAK,GAAG,GAAG,IAAI,GAAG,IAAI;IAChD;IAEA,IAAI,CAAC,GAAG,EAAE,GAAG,CAAC,CAACE,QAAQ,CAACH,IAAI,CAAC,EAAE;MAC7B,IAAIH,IAAI,KAAK,KAAK,EAAE;QAClB,OAAOG,IAAI,KAAK,GAAG,GAAG,GAAG,GAAG,GAAG;MACjC;MACA,IAAI,CAAC,GAAG,EAAE,GAAG,CAAC,CAACG,QAAQ,CAACF,iBAAiB,CAAC,EAAE;QAC1C,OAAOD,IAAI,KAAK,GAAG,GAAG,IAAI,GAAG,IAAI;MACnC;MACA,OAAOA,IAAI,KAAK,GAAG,GAAG,GAAG,GAAG,GAAG;IACjC;IAEA,IAAI,CAAC,GAAG,EAAE,GAAG,CAAC,CAACG,QAAQ,CAACH,IAAI,CAAC,EAAE;MAC7B,MAAMO,eAAe,GAAGE,CAAC,KAAKb,IAAI,CAACiB,MAAM,GAAG,CAAC,IAAI,CAACpB,UAAU,CAACkB,IAAI,CAACC,CAAC,IAAIA,CAAC,KAAKF,aAAa,CAAC;MAC3F,OAAOL,IAAI,CAACL,IAAI,EAAEC,iBAAiB,EAAEK,gBAAgB,EAAEC,eAAe,CAAC;IACzE;IAEA,IAAIV,IAAI,KAAK,KAAK,EAAE;MAClB,IAAIG,IAAI,KAAK,GAAG,EAAE;QAChB,OAAO,KAAK;MACd;MACA,IAAIA,IAAI,KAAK,GAAG,EAAE;QAChB,OAAO,KAAK;MACd;IACF;IAEA,OAAOc,iBAAiB,CAAC,CAAC;IAE1B,SAASA,iBAAiBA,CAAA,EAAG;MAC3B,MAAMC,SAAS,GAAGrB,GAAG,CAACM,IAAI,CAAC;MAE3B,IAAIe,SAAS,KAAKC,SAAS,EAAE;QAC3BlB,QAAQ,CAACmB,IAAI,CAAC,aAAajB,IAAI,gBAAgBS,CAAC,oBAAoB,CAAC;QACrE,OAAOT,IAAI;MACb;MAEA,OAAOe,SAAS;IAClB;EACF;EAEA,OAAO;IACLjB,QAAQ;IACRU;EACF,CAAC;AACH;AAEO,SAASU,cAAcA,CAACtB,IAAI,EAAEC,IAAI,GAAG,KAAK,EAAE;EACjD,MAAMsB,SAAS,GAAGxB,eAAe,CAACC,IAAI,EAAEC,IAAI,CAAC;EAE7C,MAAMuB,aAAa,GAAGxB,IAAI,CAACyB,KAAK,CAAC,EAAE,CAAC,CAAC3B,GAAG,CAACyB,SAAS,CAACX,gBAAgB,CAAC,CAACc,IAAI,CAAC,EAAE,CAAC;EAE7E,OAAO;IACLC,IAAI,EAAE3B,IAAI;IACV4B,MAAM,EAAEJ,aAAa;IACrBtB,QAAQ,EAAEqB,SAAS,CAACrB;EACtB,CAAC;AACH;AAEA,SAASI,WAAWA,CAACF,IAAI,EAAE;EACzB,OAAOR,UAAU,CAACW,QAAQ,CAACH,IAAI,CAAC;AAClC","ignoreList":[]}
1
+ {
2
+ "version": 3,
3
+ "sources": ["../src/transliteration.js"],
4
+ "sourcesContent": ["// Based on https://fi.wikipedia.org/wiki/Ven%C3%A4j%C3%A4n_translitterointi and https://fi.wikipedia.org/wiki/Ukrainan_translitterointi\n\nconst consonants = ['\u0431', '\u0432', '\u0433', '\u0491', '\u0434', '\u0436', '\u0437', '\u043A', '\u043B', '\u043C', '\u043D', '\u043F', '\u0440', '\u0441', '\u0442', '\u0444', '\u0445', '\u0446', '\u0447', '\u0448', '\u0449', '\u0411', '\u0412', '\u0413', '\u0490', '\u0414', '\u0416', '\u0417', '\u041A', '\u041B', '\u041C', '\u041D', '\u041F', '\u0420', '\u0421', '\u0422', '\u0424', '\u0425', '\u0426', '\u0427', '\u0428', '\u0429'];\n\nconst characters = ['\u0410', '\u0430', '\u0411', '\u0431', '\u0412', '\u0432', '\u0413', '\u0433', '\u0490', '\u0491', '\u0414', '\u0434', '\u0415', '\u0435', 'E', 'e', '\u0401', '\u0451', '\u0401', '\u0451', '\u0404', '\u0454', '\u0416', '\u0436', '\u0417', '\u0437', '\u0418', '\u0438', '\u0418', '\u0438', '\u0406', '\u0456', '\u0407', '\u0457', '\u0419', '\u0439', '\u0419', '\u0439', '\u0419', '\u0439', '\u041A', '\u043A', '\u041B', '\u043B', '\u041C', '\u043C', '\u041D', '\u043D', '\u041E', '\u043E', '\u041F', '\u043F', '\u0420', '\u0440', '\u0421', '\u0441', '\u0422', '\u0442', '\u0423', '\u0443', '\u0424', '\u0444', '\u0425', '\u0445', '\u0426', '\u0446', '\u0427', '\u0447', '\u0428', '\u0448', '\u0429', '\u0449', '\u042A', '\u044A', '\u042B', '\u044B', '\u042C', '\u044C', '\u042D', '\u044D', '\u042E', '\u044E', '\u042F', '\u044F', '\u2019'];\n\nconst map = {\n '\u0410': 'A', // Both\n '\u0430': 'a',\n '\u0411': 'B', // Both\n '\u0431': 'b',\n '\u0412': 'V', // Both\n '\u0432': 'v',\n '\u0413': 'G', // rus, ukr h, \u0490 \u0491 g, see code\n '\u0433': 'g',\n '\u0490': 'G', // UKR-only\n '\u0491': 'g',\n '\u0414': 'D', // both\n '\u0434': 'd',\n // '\u0415': 'E', // UKR is simpler\n // '\u0435': 'e',\n // 'E': 'Je',\n // 'e': 'je',\n // '\u0401': 'O', // RUS only\n // '\u0451': 'o',\n // '\u0401': 'Jo',\n // '\u0451': 'jo',\n '\u0404': 'Je', // UKR only\n '\u0454': 'je',\n '\u0416': '\u017D', // Both\n '\u0436': '\u017E',\n '\u0417': 'Z', // Both\n '\u0437': 'z',\n '\u0418': 'I', // RUS: 'i'/'ji'. UKR: 'y'. Default to 'i'\n '\u0438': 'i',\n //'\u0418': 'Ji',\n //'\u0438': 'ji',*/\n '\u0406': 'I', // UKR only\n '\u0456': 'i',\n '\u0407': 'Ji', // UKR only\n '\u0457': 'ji',\n '\u0419': 'I', // RUS and UKR both map to 'i'/'j'/'', but the rules differ slightly. Map to I/i by default\n '\u0439': 'i',\n //'\u0419': 'J',\n //'\u0439': 'j',\n //'\u0419': '',\n //'\u0439': '',\n '\u041A': 'K', // both\n '\u043A': 'k',\n '\u041B': 'L', // both\n '\u043B': 'l',\n '\u041C': 'M', // both\n '\u043C': 'm',\n '\u041D': 'N', // both\n '\u043D': 'n',\n '\u041E': 'O', // both\n '\u043E': 'o',\n '\u041F': 'P', // both\n '\u043F': 'p',\n '\u0420': 'R', // both\n '\u0440': 'r',\n '\u0421': 'S', // both\n '\u0441': 's',\n '\u0422': 'T', // both\n '\u0442': 't',\n '\u0423': 'U', // both\n '\u0443': 'u',\n '\u0424': 'F', // both\n '\u0444': 'f',\n '\u0425': 'H', // UKR: h\u2019\n '\u0445': 'h',\n '\u0426': 'Ts', // both\n '\u0446': 'ts',\n '\u0427': 'T\u0161', // both\n '\u0447': 't\u0161',\n '\u0428': '\u0160', // both\n '\u0448': '\u0161',\n '\u0429': '\u0160t\u0161', // both\n '\u0449': '\u0161t\u0161',\n '\u042A': '', // both (UKR: no longer used)\n '\u044A': '',\n '\u042B': 'Y', // RUS onlt\n '\u044B': 'y',\n '\u042C': '', // both\n '\u044C': '',\n '\u042D': 'E', // RUS only\n '\u044D': 'e',\n '\u042E': 'Ju', // Both\n '\u044E': 'ju',\n '\u042F': 'Ja', // Both\n '\u044F': 'ja',\n '\u2019': '' // UKR only\n};\n\nfunction createConverter(word, lang = 'rus') { // lang: 'rus' and 'ukr' supported\n const warnings = [];\n //console.log(`LANG: ${lang}`); // eslint-disable-line no-console\n\n function eOrJe(char, previousCharacter) {\n if (lang === 'ukr') {\n return char === '\u0415' ? 'E' : 'e';\n }\n if (isConsonant(previousCharacter)) {\n if (['\u042A', '\u042C', '\u044A', '\u044C'].includes(previousCharacter)) {\n return char === '\u0415' ? 'Je' : 'je';\n }\n return char === '\u0415' ? 'E' : 'e';\n }\n\n //if (isFirstCharacter || ['\u042A','\u042C','\u044A','\u044C'].includes(previousCharacter) || !isConsonant(previousCharacter)) {\n return char === '\u0415' ? 'Je' : 'je';\n }\n\n function gOrH(char) {\n if (lang === 'ukr') {\n return char === '\u0413' ? 'H' : 'h';\n }\n\n return char === '\u0413' ? 'G' : 'g';\n }\n function iOrJ(char, previousCharacter, isFirstCharacter, isLastCharacter) {\n if (isFirstCharacter) { // Both RUS and UKR\n return char === '\u0419' ? 'J' : 'j';\n }\n\n if (lang === 'ukr' && ['\u0406', '\u0456'].includes(previousCharacter)) {\n if (isLastCharacter) {\n return '';\n }\n return char === '\u0419' ? 'J' : 'j';\n }\n if (lang === 'rus' && ['\u0438', '\u0418'].includes(previousCharacter)) {\n if (isLastCharacter) {\n return '';\n }\n return char === '\u0419' ? 'J' : 'j';\n }\n return char === '\u0419' ? 'I' : 'i';\n }\n\n function convertCharacter(char, i) {\n const previousCharacter = word[i - 1];\n const nextCharacter = word[i + 1];\n\n const isFirstCharacter = i === 0 || !characters.some(c => c === previousCharacter);\n\n if (['\u0413', '\u0433'].includes(char)) { // 'gogol' vs 'hohol'\n return gOrH(char);\n }\n\n if (['\u0415', '\u0435'].includes(char)) {\n return eOrJe(char, previousCharacter);\n }\n\n if (['\u0401', '\u0451'].includes(char)) { // RUS only\n if (['\u0436', '\u0447', '\u0448', '\u0449', '\u0416', '\u0427', '\u0428', '\u0429'].includes(previousCharacter)) {\n return previousCharacter === '\u0401' ? 'O' : 'o';\n }\n return previousCharacter === '\u0401' ? 'Jo' : 'jo';\n }\n\n if (['\u0418', '\u0438'].includes(char)) {\n if (lang === 'ukr') {\n return char === '\u0418' ? 'Y' : 'y';\n }\n if (['\u042C', '\u044C'].includes(previousCharacter)) {\n return char === '\u0418' ? 'Ji' : 'ji';\n }\n return char === '\u0418' ? 'I' : 'i';\n }\n\n if (['\u0419', '\u0439'].includes(char)) {\n const isLastCharacter = i === word.length - 1 || !characters.some(c => c === nextCharacter);\n return iOrJ(char, previousCharacter, isFirstCharacter, isLastCharacter);\n }\n\n if (lang === 'ukr') {\n if (char === '\u0425') {\n return 'H\\'';\n }\n if (char === '\u0445') {\n return 'h\\'';\n }\n }\n\n return convertCharacter2();\n\n function convertCharacter2() {\n const converted = map[char];\n\n if (converted === undefined) {\n warnings.push(`Character ${char} at position ${i} was not cyrillic.`);\n return char;\n }\n\n return converted;\n }\n }\n\n return {\n warnings,\n convertCharacter\n };\n}\n\nexport function convertToLatin(word, lang = 'rus') {\n const converter = createConverter(word, lang);\n\n const convertedWord = word.split('').map(converter.convertCharacter).join('');\n\n return {\n from: word,\n result: convertedWord,\n warnings: converter.warnings\n };\n}\n\nfunction isConsonant(char) {\n return consonants.includes(char);\n}\n"],
5
+ "mappings": "AAEA,MAAM,aAAa,CAAC,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,QAAG;AAEpO,MAAM,aAAa,CAAC,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,KAAK,KAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,QAAG;AAE3b,MAAM,MAAM;AAAA,EACV,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EASL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA;AAAA;AAAA,EAGL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA;AAAA;AAAA;AAAA;AAAA,EAKL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AAAA,EACL,UAAK;AAAA,EACL,UAAK;AAAA;AACP;AAEA,SAAS,gBAAgB,MAAM,OAAO,OAAO;AAC3C,QAAM,WAAW,CAAC;AAGlB,WAAS,MAAM,MAAM,mBAAmB;AACtC,QAAI,SAAS,OAAO;AAClB,aAAO,SAAS,WAAM,MAAM;AAAA,IAC9B;AACA,QAAI,YAAY,iBAAiB,GAAG;AAClC,UAAI,CAAC,UAAK,UAAK,UAAK,QAAG,EAAE,SAAS,iBAAiB,GAAG;AACpD,eAAO,SAAS,WAAM,OAAO;AAAA,MAC/B;AACA,aAAO,SAAS,WAAM,MAAM;AAAA,IAC9B;AAGA,WAAO,SAAS,WAAM,OAAO;AAAA,EAC/B;AAEA,WAAS,KAAK,MAAM;AAClB,QAAI,SAAS,OAAO;AAClB,aAAO,SAAS,WAAM,MAAM;AAAA,IAC9B;AAEA,WAAO,SAAS,WAAM,MAAM;AAAA,EAC9B;AACA,WAAS,KAAK,MAAM,mBAAmB,kBAAkB,iBAAiB;AACxE,QAAI,kBAAkB;AACpB,aAAO,SAAS,WAAM,MAAM;AAAA,IAC9B;AAEA,QAAI,SAAS,SAAS,CAAC,UAAK,QAAG,EAAE,SAAS,iBAAiB,GAAG;AAC5D,UAAI,iBAAiB;AACnB,eAAO;AAAA,MACT;AACA,aAAO,SAAS,WAAM,MAAM;AAAA,IAC9B;AACA,QAAI,SAAS,SAAS,CAAC,UAAK,QAAG,EAAE,SAAS,iBAAiB,GAAG;AAC5D,UAAI,iBAAiB;AACnB,eAAO;AAAA,MACT;AACA,aAAO,SAAS,WAAM,MAAM;AAAA,IAC9B;AACA,WAAO,SAAS,WAAM,MAAM;AAAA,EAC9B;AAEA,WAAS,iBAAiB,MAAM,GAAG;AACjC,UAAM,oBAAoB,KAAK,IAAI,CAAC;AACpC,UAAM,gBAAgB,KAAK,IAAI,CAAC;AAEhC,UAAM,mBAAmB,MAAM,KAAK,CAAC,WAAW,KAAK,OAAK,MAAM,iBAAiB;AAEjF,QAAI,CAAC,UAAK,QAAG,EAAE,SAAS,IAAI,GAAG;AAC7B,aAAO,KAAK,IAAI;AAAA,IAClB;AAEA,QAAI,CAAC,UAAK,QAAG,EAAE,SAAS,IAAI,GAAG;AAC7B,aAAO,MAAM,MAAM,iBAAiB;AAAA,IACtC;AAEA,QAAI,CAAC,UAAK,QAAG,EAAE,SAAS,IAAI,GAAG;AAC7B,UAAI,CAAC,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,QAAG,EAAE,SAAS,iBAAiB,GAAG;AACxE,eAAO,sBAAsB,WAAM,MAAM;AAAA,MAC3C;AACA,aAAO,sBAAsB,WAAM,OAAO;AAAA,IAC5C;AAEA,QAAI,CAAC,UAAK,QAAG,EAAE,SAAS,IAAI,GAAG;AAC7B,UAAI,SAAS,OAAO;AAClB,eAAO,SAAS,WAAM,MAAM;AAAA,MAC9B;AACA,UAAI,CAAC,UAAK,QAAG,EAAE,SAAS,iBAAiB,GAAG;AAC1C,eAAO,SAAS,WAAM,OAAO;AAAA,MAC/B;AACA,aAAO,SAAS,WAAM,MAAM;AAAA,IAC9B;AAEA,QAAI,CAAC,UAAK,QAAG,EAAE,SAAS,IAAI,GAAG;AAC7B,YAAM,kBAAkB,MAAM,KAAK,SAAS,KAAK,CAAC,WAAW,KAAK,OAAK,MAAM,aAAa;AAC1F,aAAO,KAAK,MAAM,mBAAmB,kBAAkB,eAAe;AAAA,IACxE;AAEA,QAAI,SAAS,OAAO;AAClB,UAAI,SAAS,UAAK;AAChB,eAAO;AAAA,MACT;AACA,UAAI,SAAS,UAAK;AAChB,eAAO;AAAA,MACT;AAAA,IACF;AAEA,WAAO,kBAAkB;AAEzB,aAAS,oBAAoB;AAC3B,YAAM,YAAY,IAAI,IAAI;AAE1B,UAAI,cAAc,QAAW;AAC3B,iBAAS,KAAK,aAAa,IAAI,gBAAgB,CAAC,oBAAoB;AACpE,eAAO;AAAA,MACT;AAEA,aAAO;AAAA,IACT;AAAA,EACF;AAEA,SAAO;AAAA,IACL;AAAA,IACA;AAAA,EACF;AACF;AAEO,gBAAS,eAAe,MAAM,OAAO,OAAO;AACjD,QAAM,YAAY,gBAAgB,MAAM,IAAI;AAE5C,QAAM,gBAAgB,KAAK,MAAM,EAAE,EAAE,IAAI,UAAU,gBAAgB,EAAE,KAAK,EAAE;AAE5E,SAAO;AAAA,IACL,MAAM;AAAA,IACN,QAAQ;AAAA,IACR,UAAU,UAAU;AAAA,EACtB;AACF;AAEA,SAAS,YAAY,MAAM;AACzB,SAAO,WAAW,SAAS,IAAI;AACjC;",
6
+ "names": []
7
+ }
package/package.json CHANGED
@@ -1,6 +1,7 @@
1
1
  {
2
2
  "name": "@natlibfi/sfs-4900",
3
- "version": "1.1.4",
3
+ "type": "module",
4
+ "version": "2.0.0-alpha.4",
4
5
  "license": "MIT",
5
6
  "description": "Transliteration from cyrillic (Russian, Ukrainian) text to latin (Finnish) as defined in the SFS-4900 standard",
6
7
  "author": "The National Library of Finland",
@@ -18,101 +19,35 @@
18
19
  "Finnish",
19
20
  "transliteration"
20
21
  ],
21
- "homepage": "https://github.com/NatLibFi/sfs-4900",
22
+ "homepage": "https://www.npmjs.com/package/@natlibfi/sfs-4900",
22
23
  "bugs": {
23
24
  "url": "https://github.com/NatLibFi/sfs-4900/issues"
24
25
  },
25
26
  "repository": {
26
- "type": "git",
27
- "url": "git+ssh://git@github.com/natlibfi/sfs-4900.git"
27
+ "url": "https://github.com/NatLibFi/sfs-4900"
28
28
  },
29
29
  "main": "dist/transliteration.js",
30
30
  "engines": {
31
- "node": ">=20"
31
+ "node": ">=22"
32
32
  },
33
33
  "publishConfig": {
34
34
  "access": "public"
35
35
  },
36
36
  "scripts": {
37
37
  "prepare": "npm run build",
38
- "build": "babel ./src --source-maps --copy-files --delete-dir-on-start --out-dir=dist",
38
+ "build": "esbuild \"src/*.js\" --sourcemap --platform=node --outdir=dist",
39
39
  "lint": "eslint ./src",
40
40
  "lint:dev": "eslint --fix ./src",
41
41
  "test": "npm run lint && npm run test:base",
42
- "test:base": "cross-env NODE_ENV=test nyc mocha",
43
- "test:dev": "npm run lint:dev && cross-env NODE_ENV=test nyc mocha",
44
- "dev": "nodemon",
45
- "dev:debug": "cross-env LOG_LEVEL=debug DEBUG=@natlibfi/* NODE_ENV=test nodemon",
46
- "coverage": "npm run cover:unit && npm run cover:report",
47
- "cover:unit": "nyc --silent npm run test:base",
48
- "cover:report": "nyc report"
42
+ "test:base": "node --test --test-force-exit --experimental-test-coverage --test-reporter=spec './test/*.test.js'",
43
+ "dev:test": "cross-env DEBUG=@natlibfi/* NODE_ENV=test node --watch --test --experimental-test-coverage --test-reporter=spec './src/*.test.js' './src/**/*.test.js'"
49
44
  },
50
45
  "devDependencies": {
51
- "@babel/cli": "^7.28.3",
52
- "@babel/core": "^7.28.3",
53
- "@babel/preset-env": "^7.28.3",
54
- "@natlibfi/fixugen": "^2.0.15",
55
- "@natlibfi/fixura": "^3.0.14",
56
- "babel-plugin-istanbul": "^7.0.0",
57
- "chai": "^4.5.0",
46
+ "@natlibfi/fixugen": "next",
47
+ "@natlibfi/fixura": "next",
58
48
  "cross-env": "^7.0.3",
59
49
  "eslint": "^9.34.0",
60
- "mocha": "^11.7.2",
61
- "nyc": "^17.1.0"
50
+ "esbuild": "^0.25.9"
62
51
  },
63
- "eslintConfig": {
64
- "extends": [
65
- "@natlibfi/melinda-backend"
66
- ]
67
- },
68
- "babel": {
69
- "presets": [
70
- [
71
- "@babel/preset-env",
72
- {
73
- "targets": "maintained node versions"
74
- }
75
- ]
76
- ],
77
- "env": {
78
- "test": {
79
- "plugins": [
80
- "istanbul"
81
- ]
82
- }
83
- }
84
- },
85
- "mocha": {
86
- "spec": [
87
- "test/*.spec.js"
88
- ],
89
- "require": [
90
- "@babel/register"
91
- ],
92
- "inline-diffs": true,
93
- "maxDiffSize": 25000,
94
- "bail": true,
95
- "exit": true
96
- },
97
- "nodemonConfig": {
98
- "exec": "npm run test:dev",
99
- "watch": [
100
- "src/*",
101
- "test/*"
102
- ]
103
- },
104
- "nyc": {
105
- "exclude": [
106
- "test/*.spec.js"
107
- ],
108
- "reporter": [
109
- "text"
110
- ],
111
- "sourceMap": false,
112
- "instrument": false,
113
- "lines": 80,
114
- "statements": 80,
115
- "functions": 80,
116
- "branches": 80
117
- }
52
+ "dependencies": {}
118
53
  }
@@ -1,5 +1,6 @@
1
- import { expect } from 'chai';
2
- import { convertToLatin } from '../src/transliteration';
1
+ import assert from 'node:assert';
2
+ import {beforeEach, describe, it} from 'node:test';
3
+ import { convertToLatin } from '../src/transliteration.js';
3
4
 
4
5
  const mapping = [
5
6
  ['А', 'а'],['A','a'], ['Анапа', 'Anapa'],
@@ -86,10 +87,10 @@ const mappingUkr = [
86
87
  describe('Transliteration', function() {
87
88
 
88
89
  const testDefinitions = mapping.reduce((acc, item, i) => {
89
- if (i%3 === 0) {
90
- acc.push({});
90
+ if (i%3 === 0) {
91
+ acc.push({});
91
92
  }
92
-
93
+
93
94
  const current = acc[acc.length-1];
94
95
 
95
96
  switch(i%3) {
@@ -103,10 +104,10 @@ describe('Transliteration', function() {
103
104
 
104
105
  testDefinitions.forEach(test => {
105
106
  it(`converts ${test.from[0]} to ${test.to[0]} in ${test.word[0]} to ${test.word[1]}`, () => {
106
- expect(convertToLatin(test.word[0]).result).to.equal(test.word[1]);
107
+ assert.equal(convertToLatin(test.word[0]).result, test.word[1]);
107
108
  });
108
109
  it(`converts ${test.from[1]} to ${test.to[1]} in ${test.word[0]} to ${test.word[1]}`, () => {
109
- expect(convertToLatin(test.word[0]).result).to.equal(test.word[1]);
110
+ assert.equal(convertToLatin(test.word[0]).result, test.word[1]);
110
111
  });
111
112
 
112
113
  });
@@ -129,10 +130,10 @@ describe('Transliteration', function() {
129
130
 
130
131
  testDefinitionsUkr.forEach(test => {
131
132
  it(`converts UKR ${test.from[0]} to ${test.to[0]} in ${test.word[0]} to ${test.word[1]}`, () => {
132
- expect(convertToLatin(test.word[0], 'ukr').result).to.equal(test.word[1]);
133
+ assert.equal(convertToLatin(test.word[0], 'ukr').result, test.word[1]);
133
134
  });
134
135
  it(`converts UKR ${test.from[1]} to ${test.to[1]} in ${test.word[0]} to ${test.word[1]}`, () => {
135
- expect(convertToLatin(test.word[0], 'ukr').result).to.equal(test.word[1]);
136
+ assert.equal(convertToLatin(test.word[0], 'ukr').result, test.word[1]);
136
137
  });
137
138
 
138
139
  });
@@ -145,10 +146,10 @@ describe('Transliteration', function() {
145
146
  });
146
147
 
147
148
  it('adds warning to result', function() {
148
- expect(conversion.warnings).to.include('Character A at position 0 was not cyrillic.');
149
+ assert.partialDeepStrictEqual(conversion.warnings, ['Character A at position 0 was not cyrillic.']);
149
150
  });
150
151
  it('converts the cyrillic characters', function() {
151
- expect(conversion.result).to.equal('Anapa');
152
+ assert.equal(conversion.result, 'Anapa');
152
153
  });
153
154
  });
154
155
  });
package/.eslintignore DELETED
@@ -1,3 +0,0 @@
1
- bin/
2
- build/
3
- lib/