@natlibfi/sfs-4900 3.0.0 → 3.0.1-alpha.1
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.
package/dist/transliteration.js
CHANGED
|
@@ -1,3 +1,4 @@
|
|
|
1
|
+
"use strict";
|
|
1
2
|
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
3
|
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"];
|
|
3
4
|
const map = {
|
|
@@ -130,7 +131,7 @@ function createConverter(word, lang = "rus") {
|
|
|
130
131
|
return char === "\u0415" ? "E" : "e";
|
|
131
132
|
}
|
|
132
133
|
if (isConsonant(previousCharacter)) {
|
|
133
|
-
if (["\u042A", "\u042C", "\u044A", "\u044C"]
|
|
134
|
+
if (includesAny(["\u042A", "\u042C", "\u044A", "\u044C"], previousCharacter)) {
|
|
134
135
|
return char === "\u0415" ? "Je" : "je";
|
|
135
136
|
}
|
|
136
137
|
return char === "\u0415" ? "E" : "e";
|
|
@@ -147,13 +148,13 @@ function createConverter(word, lang = "rus") {
|
|
|
147
148
|
if (isFirstCharacter) {
|
|
148
149
|
return char === "\u0419" ? "J" : "j";
|
|
149
150
|
}
|
|
150
|
-
if (lang === "ukr" && ["\u0406", "\u0456"]
|
|
151
|
+
if (lang === "ukr" && includesAny(["\u0406", "\u0456"], previousCharacter)) {
|
|
151
152
|
if (isLastCharacter) {
|
|
152
153
|
return "";
|
|
153
154
|
}
|
|
154
155
|
return char === "\u0419" ? "J" : "j";
|
|
155
156
|
}
|
|
156
|
-
if (lang === "rus" && ["\u0438", "\u0418"]
|
|
157
|
+
if (lang === "rus" && includesAny(["\u0438", "\u0418"], previousCharacter)) {
|
|
157
158
|
if (isLastCharacter) {
|
|
158
159
|
return "";
|
|
159
160
|
}
|
|
@@ -172,7 +173,7 @@ function createConverter(word, lang = "rus") {
|
|
|
172
173
|
return eOrJe(char, previousCharacter);
|
|
173
174
|
}
|
|
174
175
|
if (["\u0401", "\u0451"].includes(char)) {
|
|
175
|
-
if (["\u0436", "\u0447", "\u0448", "\u0449", "\u0416", "\u0427", "\u0428", "\u0429"]
|
|
176
|
+
if (includesAny(["\u0436", "\u0447", "\u0448", "\u0449", "\u0416", "\u0427", "\u0428", "\u0429"], previousCharacter)) {
|
|
176
177
|
return previousCharacter === "\u0401" ? "O" : "o";
|
|
177
178
|
}
|
|
178
179
|
return previousCharacter === "\u0401" ? "Jo" : "jo";
|
|
@@ -181,7 +182,7 @@ function createConverter(word, lang = "rus") {
|
|
|
181
182
|
if (lang === "ukr") {
|
|
182
183
|
return char === "\u0418" ? "Y" : "y";
|
|
183
184
|
}
|
|
184
|
-
if (["\u042C", "\u044C"]
|
|
185
|
+
if (includesAny(["\u042C", "\u044C"], previousCharacter)) {
|
|
185
186
|
return char === "\u0418" ? "Ji" : "ji";
|
|
186
187
|
}
|
|
187
188
|
return char === "\u0418" ? "I" : "i";
|
|
@@ -215,7 +216,7 @@ function createConverter(word, lang = "rus") {
|
|
|
215
216
|
}
|
|
216
217
|
export function convertToLatin(word, lang = "rus") {
|
|
217
218
|
const converter = createConverter(word, lang);
|
|
218
|
-
const convertedWord = word.split("").map(converter.convertCharacter).join("");
|
|
219
|
+
const convertedWord = word.split("").map((char, i) => converter.convertCharacter(char, i)).join("");
|
|
219
220
|
return {
|
|
220
221
|
from: word,
|
|
221
222
|
result: convertedWord,
|
|
@@ -223,6 +224,9 @@ export function convertToLatin(word, lang = "rus") {
|
|
|
223
224
|
};
|
|
224
225
|
}
|
|
225
226
|
function isConsonant(char) {
|
|
226
|
-
return consonants.includes(char);
|
|
227
|
+
return char !== void 0 && consonants.includes(char);
|
|
228
|
+
}
|
|
229
|
+
function includesAny(list, value) {
|
|
230
|
+
return value !== void 0 && list.includes(value);
|
|
227
231
|
}
|
|
228
232
|
//# sourceMappingURL=transliteration.js.map
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"version": 3,
|
|
3
|
-
"sources": ["../src/transliteration.
|
|
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')
|
|
5
|
-
"mappings": "
|
|
3
|
+
"sources": ["../src/transliteration.ts"],
|
|
4
|
+
"sourcesContent": ["// Based on https://fi.wikipedia.org/wiki/Ven%C3%A4j%C3%A4n_translitterointi and https://fi.wikipedia.org/wiki/Ukrainan_translitterointi\n\nexport type Lang = 'rus' | 'ukr';\n\nexport interface ConversionResult {\n from: string;\n result: string;\n warnings: string[];\n}\n\nconst consonants: string[] = ['\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: string[] = ['\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: Record<string, string> = {\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\ninterface Converter {\n warnings: string[];\n convertCharacter: (char: string, i: number) => string;\n}\n\nfunction createConverter(word: string, lang: Lang = 'rus'): Converter {\n const warnings: string[] = [];\n //console.log(`LANG: ${lang}`); // eslint-disable-line no-console\n\n function eOrJe(char: string, previousCharacter?: string): string {\n if (lang === 'ukr') {\n return char === '\u0415' ? 'E' : 'e';\n }\n if (isConsonant(previousCharacter)) {\n if (includesAny(['\u042A', '\u042C', '\u044A', '\u044C'], 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: string): string {\n if (lang === 'ukr') {\n return char === '\u0413' ? 'H' : 'h';\n }\n\n return char === '\u0413' ? 'G' : 'g';\n }\n function iOrJ(char: string, previousCharacter: string | undefined, isFirstCharacter: boolean, isLastCharacter: boolean): string {\n if (isFirstCharacter) { // Both RUS and UKR\n return char === '\u0419' ? 'J' : 'j';\n }\n\n if (lang === 'ukr' && includesAny(['\u0406', '\u0456'], previousCharacter)) {\n if (isLastCharacter) {\n return '';\n }\n return char === '\u0419' ? 'J' : 'j';\n }\n if (lang === 'rus' && includesAny(['\u0438', '\u0418'], 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: string, i: number): string {\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 (includesAny(['\u0436', '\u0447', '\u0448', '\u0449', '\u0416', '\u0427', '\u0428', '\u0429'], 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 (includesAny(['\u042C', '\u044C'], 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(): string {\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: string, lang: Lang = 'rus'): ConversionResult {\n const converter = createConverter(word, lang);\n\n const convertedWord = word.split('').map((char, i) => converter.convertCharacter(char, i)).join('');\n\n return {\n from: word,\n result: convertedWord,\n warnings: converter.warnings\n };\n}\n\nfunction isConsonant(char?: string): boolean {\n return char !== undefined && consonants.includes(char);\n}\n\nfunction includesAny(list: string[], value?: string): boolean {\n return value !== undefined && list.includes(value);\n}\n"],
|
|
5
|
+
"mappings": ";AAUA,MAAM,aAAuB,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;AAE9O,MAAM,aAAuB,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;AAErc,MAAM,MAA8B;AAAA,EAClC,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;AAOA,SAAS,gBAAgB,MAAc,OAAa,OAAkB;AACpE,QAAM,WAAqB,CAAC;AAG5B,WAAS,MAAM,MAAc,mBAAoC;AAC/D,QAAI,SAAS,OAAO;AAClB,aAAO,SAAS,WAAM,MAAM;AAAA,IAC9B;AACA,QAAI,YAAY,iBAAiB,GAAG;AAClC,UAAI,YAAY,CAAC,UAAK,UAAK,UAAK,QAAG,GAAG,iBAAiB,GAAG;AACxD,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,MAAsB;AAClC,QAAI,SAAS,OAAO;AAClB,aAAO,SAAS,WAAM,MAAM;AAAA,IAC9B;AAEA,WAAO,SAAS,WAAM,MAAM;AAAA,EAC9B;AACA,WAAS,KAAK,MAAc,mBAAuC,kBAA2B,iBAAkC;AAC9H,QAAI,kBAAkB;AACpB,aAAO,SAAS,WAAM,MAAM;AAAA,IAC9B;AAEA,QAAI,SAAS,SAAS,YAAY,CAAC,UAAK,QAAG,GAAG,iBAAiB,GAAG;AAChE,UAAI,iBAAiB;AACnB,eAAO;AAAA,MACT;AACA,aAAO,SAAS,WAAM,MAAM;AAAA,IAC9B;AACA,QAAI,SAAS,SAAS,YAAY,CAAC,UAAK,QAAG,GAAG,iBAAiB,GAAG;AAChE,UAAI,iBAAiB;AACnB,eAAO;AAAA,MACT;AACA,aAAO,SAAS,WAAM,MAAM;AAAA,IAC9B;AACA,WAAO,SAAS,WAAM,MAAM;AAAA,EAC9B;AAEA,WAAS,iBAAiB,MAAc,GAAmB;AACzD,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,YAAY,CAAC,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,UAAK,QAAG,GAAG,iBAAiB,GAAG;AAC5E,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,YAAY,CAAC,UAAK,QAAG,GAAG,iBAAiB,GAAG;AAC9C,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,oBAA4B;AACnC,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,MAAc,OAAa,OAAyB;AACjF,QAAM,YAAY,gBAAgB,MAAM,IAAI;AAE5C,QAAM,gBAAgB,KAAK,MAAM,EAAE,EAAE,IAAI,CAAC,MAAM,MAAM,UAAU,iBAAiB,MAAM,CAAC,CAAC,EAAE,KAAK,EAAE;AAElG,SAAO;AAAA,IACL,MAAM;AAAA,IACN,QAAQ;AAAA,IACR,UAAU,UAAU;AAAA,EACtB;AACF;AAEA,SAAS,YAAY,MAAwB;AAC3C,SAAO,SAAS,UAAa,WAAW,SAAS,IAAI;AACvD;AAEA,SAAS,YAAY,MAAgB,OAAyB;AAC5D,SAAO,UAAU,UAAa,KAAK,SAAS,KAAK;AACnD;",
|
|
6
6
|
"names": []
|
|
7
7
|
}
|
package/eslint.config.mjs
CHANGED
|
@@ -1,12 +1,25 @@
|
|
|
1
|
+
import tseslint from 'typescript-eslint';
|
|
2
|
+
|
|
1
3
|
// Eslint configuration object for src
|
|
2
4
|
const configSrc = {
|
|
3
5
|
files: [
|
|
4
|
-
"src
|
|
6
|
+
"src/**/*.ts"
|
|
5
7
|
],
|
|
6
8
|
linterOptions: {
|
|
7
9
|
reportUnusedDisableDirectives: true,
|
|
8
10
|
},
|
|
11
|
+
languageOptions: {
|
|
12
|
+
parser: tseslint.parser,
|
|
13
|
+
parserOptions: {
|
|
14
|
+
projectService: true,
|
|
15
|
+
tsconfigRootDir: import.meta.dirname,
|
|
16
|
+
},
|
|
17
|
+
},
|
|
18
|
+
plugins: {
|
|
19
|
+
"@typescript-eslint": tseslint.plugin,
|
|
20
|
+
},
|
|
9
21
|
rules: {
|
|
22
|
+
...tseslint.configs.recommended[0].rules,
|
|
10
23
|
"no-console": "warn",
|
|
11
24
|
"eqeqeq": ["error", "always"],
|
|
12
25
|
"no-const-assign": "error",
|
|
@@ -26,7 +39,8 @@ const configSrc = {
|
|
|
26
39
|
"checkForEach": false
|
|
27
40
|
}
|
|
28
41
|
],
|
|
29
|
-
"no-unused-vars":
|
|
42
|
+
"no-unused-vars": "off",
|
|
43
|
+
"@typescript-eslint/no-unused-vars": [
|
|
30
44
|
"error",
|
|
31
45
|
{
|
|
32
46
|
"argsIgnorePattern": "next"
|
|
@@ -49,4 +63,4 @@ const configIgnores = {
|
|
|
49
63
|
export default [
|
|
50
64
|
configSrc,
|
|
51
65
|
configIgnores
|
|
52
|
-
];
|
|
66
|
+
];
|
package/package.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "@natlibfi/sfs-4900",
|
|
3
3
|
"type": "module",
|
|
4
|
-
"version": "3.0.
|
|
4
|
+
"version": "3.0.1-alpha.1",
|
|
5
5
|
"license": "MIT",
|
|
6
6
|
"description": "Transliteration from cyrillic (Russian, Ukrainian) text to latin (Finnish) as defined in the SFS-4900 standard",
|
|
7
7
|
"author": "The National Library of Finland",
|
|
@@ -35,7 +35,8 @@
|
|
|
35
35
|
},
|
|
36
36
|
"scripts": {
|
|
37
37
|
"prepare": "npm run build",
|
|
38
|
-
"build": "esbuild \"src/*.
|
|
38
|
+
"build": "esbuild \"src/*.ts\" --sourcemap --platform=node --outdir=dist",
|
|
39
|
+
"typecheck": "tsc --noEmit",
|
|
39
40
|
"lint": "eslint ./src",
|
|
40
41
|
"lint:dev": "eslint --fix ./src",
|
|
41
42
|
"test": "npm run lint && npm run test:base",
|
|
@@ -43,10 +44,21 @@
|
|
|
43
44
|
"dev:test": "cross-env DEBUG=@natlibfi/* NODE_ENV=test node --watch --test --experimental-test-coverage --test-reporter=spec './src/*.test.js' './src/**/*.test.js'"
|
|
44
45
|
},
|
|
45
46
|
"devDependencies": {
|
|
46
|
-
"@natlibfi/fixugen": "^
|
|
47
|
-
"@natlibfi/fixura": "^
|
|
47
|
+
"@natlibfi/fixugen": "^4.0.0",
|
|
48
|
+
"@natlibfi/fixura": "^5.0.0",
|
|
49
|
+
"@types/node": "^24.0.0",
|
|
48
50
|
"cross-env": "^10.1.0",
|
|
49
51
|
"esbuild": "^0.28.2",
|
|
50
|
-
"eslint": "^10.
|
|
52
|
+
"eslint": "^10.14.0",
|
|
53
|
+
"typescript": "^6.0.3",
|
|
54
|
+
"typescript-eslint": "^8.72.2"
|
|
55
|
+
},
|
|
56
|
+
"overrides": {
|
|
57
|
+
"eslint": {
|
|
58
|
+
"minimatch": "^11.0.8"
|
|
59
|
+
},
|
|
60
|
+
"typescript-eslint": {
|
|
61
|
+
"minimatch": "^11.0.8"
|
|
62
|
+
}
|
|
51
63
|
}
|
|
52
64
|
}
|
|
@@ -1,8 +1,15 @@
|
|
|
1
1
|
import assert from 'node:assert';
|
|
2
2
|
import {beforeEach, describe, it} from 'node:test';
|
|
3
3
|
import { convertToLatin } from '../src/transliteration.js';
|
|
4
|
+
import type { ConversionResult, Lang } from '../src/transliteration.js';
|
|
4
5
|
|
|
5
|
-
|
|
6
|
+
interface TestDefinition {
|
|
7
|
+
from?: string[];
|
|
8
|
+
to?: string[];
|
|
9
|
+
word?: string[];
|
|
10
|
+
}
|
|
11
|
+
|
|
12
|
+
const mapping: string[][] = [
|
|
6
13
|
['А', 'а'],['A','a'], ['Анапа', 'Anapa'],
|
|
7
14
|
['Б', 'б'],['B','b'], ['Бабаево', 'Babajevo'],
|
|
8
15
|
['В', 'в'],['V','v'], ['Всеволожск', 'Vsevoložsk'],
|
|
@@ -41,10 +48,10 @@ const mapping = [
|
|
|
41
48
|
['Э', 'э'],['E','e'], ['Энгельс', 'Engels'],
|
|
42
49
|
['Ю', 'ю'],['Ju','ju'], ['Юрюзань', 'Jurjuzan'],
|
|
43
50
|
['Я', 'я'],['Ja','ja'], ['Ярославль', 'Jaroslavl'],
|
|
44
|
-
|
|
51
|
+
|
|
45
52
|
];
|
|
46
53
|
|
|
47
|
-
const mappingUkr = [
|
|
54
|
+
const mappingUkr: string[][] = [
|
|
48
55
|
['А', 'а'],['A','a'], ['Алушта', 'Alušta'],
|
|
49
56
|
['Б', 'б'],['B','b'], ['Бобринець', 'Bobrynets'],
|
|
50
57
|
['В', 'в'],['V','v'], ['Вишневе', 'Vyšneve'],
|
|
@@ -84,16 +91,15 @@ const mappingUkr = [
|
|
|
84
91
|
//['Ъ', 'ъ'],['', ''], ei esiinny nykyortografiassa];
|
|
85
92
|
];
|
|
86
93
|
|
|
87
|
-
|
|
88
|
-
|
|
89
|
-
|
|
90
|
-
if (i%3 === 0) {
|
|
94
|
+
function buildTestDefinitions(mapping: string[][]): TestDefinition[] {
|
|
95
|
+
return mapping.reduce<TestDefinition[]>((acc, item, i) => {
|
|
96
|
+
if (i % 3 === 0) {
|
|
91
97
|
acc.push({});
|
|
92
98
|
}
|
|
93
99
|
|
|
94
|
-
const current = acc[acc.length-1];
|
|
100
|
+
const current = acc[acc.length - 1];
|
|
95
101
|
|
|
96
|
-
switch(i%3) {
|
|
102
|
+
switch (i % 3) {
|
|
97
103
|
case 0: current.from = item; break;
|
|
98
104
|
case 1: current.to = item; break;
|
|
99
105
|
case 2: current.word = item; break;
|
|
@@ -101,56 +107,38 @@ describe('Transliteration', function() {
|
|
|
101
107
|
return acc;
|
|
102
108
|
|
|
103
109
|
}, []);
|
|
110
|
+
}
|
|
104
111
|
|
|
112
|
+
function runTests(testDefinitions: TestDefinition[], lang?: Lang) {
|
|
105
113
|
testDefinitions.forEach(test => {
|
|
106
|
-
it(`converts ${test.from[0]} to ${test.to[0]} in ${test.word[0]} to ${test.word[1]}`, () => {
|
|
107
|
-
assert.equal(convertToLatin(test.word[0]).result, test.word[1]);
|
|
114
|
+
it(`converts ${lang === 'ukr' ? 'UKR' : ''} ${test.from?.[0]} to ${test.to?.[0]} in ${test.word?.[0]} to ${test.word?.[1]}`, () => {
|
|
115
|
+
assert.equal(convertToLatin(test.word?.[0] ?? '', lang).result, test.word?.[1]);
|
|
108
116
|
});
|
|
109
|
-
it(`converts ${test.from[1]} to ${test.to[1]} in ${test.word[0]} to ${test.word[1]}`, () => {
|
|
110
|
-
assert.equal(convertToLatin(test.word[0]).result, test.word[1]);
|
|
117
|
+
it(`converts ${lang === 'ukr' ? 'UKR' : ''} ${test.from?.[1]} to ${test.to?.[1]} in ${test.word?.[0]} to ${test.word?.[1]}`, () => {
|
|
118
|
+
assert.equal(convertToLatin(test.word?.[0] ?? '', lang).result, test.word?.[1]);
|
|
111
119
|
});
|
|
112
120
|
|
|
113
121
|
});
|
|
122
|
+
}
|
|
114
123
|
|
|
115
|
-
|
|
116
|
-
if (i%3 === 0) {
|
|
117
|
-
acc.push({});
|
|
118
|
-
}
|
|
119
|
-
|
|
120
|
-
const current = acc[acc.length-1];
|
|
121
|
-
|
|
122
|
-
switch(i%3) {
|
|
123
|
-
case 0: current.from = item; break;
|
|
124
|
-
case 1: current.to = item; break;
|
|
125
|
-
case 2: current.word = item; break;
|
|
126
|
-
}
|
|
127
|
-
return acc;
|
|
128
|
-
|
|
129
|
-
}, []);
|
|
124
|
+
describe('Transliteration', function() {
|
|
130
125
|
|
|
131
|
-
|
|
132
|
-
it(`converts UKR ${test.from[0]} to ${test.to[0]} in ${test.word[0]} to ${test.word[1]}`, () => {
|
|
133
|
-
assert.equal(convertToLatin(test.word[0], 'ukr').result, test.word[1]);
|
|
134
|
-
});
|
|
135
|
-
it(`converts UKR ${test.from[1]} to ${test.to[1]} in ${test.word[0]} to ${test.word[1]}`, () => {
|
|
136
|
-
assert.equal(convertToLatin(test.word[0], 'ukr').result, test.word[1]);
|
|
137
|
-
});
|
|
126
|
+
runTests(buildTestDefinitions(mapping));
|
|
138
127
|
|
|
139
|
-
|
|
128
|
+
runTests(buildTestDefinitions(mappingUkr), 'ukr');
|
|
140
129
|
|
|
141
130
|
|
|
142
131
|
describe('when given non-cyrillic characters', function() {
|
|
143
|
-
let conversion;
|
|
132
|
+
let conversion: ConversionResult;
|
|
144
133
|
beforeEach(() => {
|
|
145
134
|
conversion = convertToLatin('Aнапа');
|
|
146
135
|
});
|
|
147
136
|
|
|
148
137
|
it('adds warning to result', function() {
|
|
149
|
-
assert.
|
|
138
|
+
assert.deepStrictEqual(conversion.warnings, ['Character A at position 0 was not cyrillic.']);
|
|
150
139
|
});
|
|
151
140
|
it('converts the cyrillic characters', function() {
|
|
152
141
|
assert.equal(conversion.result, 'Anapa');
|
|
153
142
|
});
|
|
154
143
|
});
|
|
155
144
|
});
|
|
156
|
-
|
package/tsconfig.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
1
|
+
{
|
|
2
|
+
"include": [
|
|
3
|
+
"src"
|
|
4
|
+
],
|
|
5
|
+
"exclude": [
|
|
6
|
+
"node_modules",
|
|
7
|
+
"dist",
|
|
8
|
+
"src/*.test.ts"
|
|
9
|
+
],
|
|
10
|
+
"compilerOptions": {
|
|
11
|
+
// File Layout
|
|
12
|
+
"rootDir": "./src",
|
|
13
|
+
"outDir": "./dist",
|
|
14
|
+
// Environment Settings
|
|
15
|
+
"module": "nodenext",
|
|
16
|
+
"moduleResolution": "nodenext",
|
|
17
|
+
"target": "esnext",
|
|
18
|
+
"typeRoots": [
|
|
19
|
+
"./node_modules/@types"
|
|
20
|
+
],
|
|
21
|
+
"types": [
|
|
22
|
+
"node"
|
|
23
|
+
],
|
|
24
|
+
"lib": [
|
|
25
|
+
"esnext"
|
|
26
|
+
],
|
|
27
|
+
// Other Outputs
|
|
28
|
+
"sourceMap": true,
|
|
29
|
+
"declaration": true,
|
|
30
|
+
"declarationMap": true,
|
|
31
|
+
// Stricter Typechecking Options
|
|
32
|
+
"noUncheckedIndexedAccess": true,
|
|
33
|
+
// Style Options
|
|
34
|
+
"noImplicitReturns": true,
|
|
35
|
+
"noImplicitOverride": true,
|
|
36
|
+
"noUnusedLocals": true,
|
|
37
|
+
"noUnusedParameters": true,
|
|
38
|
+
"noFallthroughCasesInSwitch": true,
|
|
39
|
+
"noPropertyAccessFromIndexSignature": true,
|
|
40
|
+
// Recommended Options
|
|
41
|
+
"strict": true,
|
|
42
|
+
"isolatedModules": true,
|
|
43
|
+
"noUncheckedSideEffectImports": true,
|
|
44
|
+
"moduleDetection": "force",
|
|
45
|
+
"skipLibCheck": true,
|
|
46
|
+
"allowImportingTsExtensions": true,
|
|
47
|
+
"noEmit": false,
|
|
48
|
+
// Customized options
|
|
49
|
+
"allowJs": true,
|
|
50
|
+
"checkJs": true,
|
|
51
|
+
"esModuleInterop": true,
|
|
52
|
+
"allowUnreachableCode": false,
|
|
53
|
+
"strictFunctionTypes": true,
|
|
54
|
+
"strictNullChecks": true,
|
|
55
|
+
"removeComments": true,
|
|
56
|
+
// Only allow syntax accepted by Node >= 23.6
|
|
57
|
+
"erasableSyntaxOnly": true,
|
|
58
|
+
// Proposed options from Node docs: https://nodejs.org/api/typescript.html#type-stripping
|
|
59
|
+
"rewriteRelativeImportExtensions": true,
|
|
60
|
+
"verbatimModuleSyntax": true,
|
|
61
|
+
"forceConsistentCasingInFileNames": true
|
|
62
|
+
}
|
|
63
|
+
}
|