taraskevizer 1.7.5 → 2.0.1

package/README.md

@@ -7,31 +7,40 @@ $ npm i taraskevizer
 ## Usage
 
 ```js
-import { tarask, ALPHABET } from 'taraskevizer';
-
-const result = tarask(text);
-// or
-const result = tarask(text, {
-	html: {
-		abc: ALPHABET.ARABIC,
-		g: false,
-		// ...
-	},
-	nonHtml: false,
-});
-```
-
-## API
+import { tarask, taraskToHtml, ALPHABET, J, VARIATION } from 'taraskevizer';
 
-### tarask(text, options?)
+const taraskedText = tarask(text);
+// планета -> плянэта
 
-Returns a `string`
-
-#### text
+const taraskedText = tarask(
+	text,
+	{
+		abc: ALPHABET.CYRILLIC,
+		j: J.ALWAYS,
+	},
+	{
+		nodeColors: true,
+		variations: VARIATION.FIRST,
+		h: false,
+	}
+);
+// планета і Гродна -> пл\x1b[32mя\x1b[0mн\x1b[32mэ\x1b[0mта \x1b[32mй\x1b[0m \x1b[35mГорадня\x1b[0m
+
+const taraskedText = taraskToHtml(
+	text,
+	{
+		abc: ALPHABET.LATIN,
+	},
+	{
+		g: false, // ignored, because alphabet is set to latin
+	}
+);
+// энергія планеты -> en<tarF>erg</tarF>ija p<tarF>lan</tarF>ety
+```
 
-Type: `string`
+### Function signatures are in [this file](./dist/index.d.ts)
 
-## Options
+## TaraskOptions
 
 Type: `object`
 
@@ -64,15 +73,28 @@ When to replace `і`(`i`) by `й`(`j`) after vowels:
 2 = always
 ```
 
-### html
+### OVERRIDE_toTarask
 
-Type: `boolean|object`
+Type:
 
-Default value: `false`
+```
+(
+    text: string,
+    replaceWithDict: (
+        text: string,
+        dict?: [RegExp, string | ((...substrings: string[]) => string)][]
+    ) => string,
+    wordlist: [RegExp, string][],
+    softers: [RegExp, string][],
+    afterTarask: (text: string) => string
+) => string
+```
+
+Default value: internal function `toTarask`
 
-If `true|object`, some parts of a text are wrapped in HTML tags.
+## HtmlOptions
 
-#### html.g
+### g
 
 Type: `boolean`
 
@@ -86,21 +108,15 @@ false: <tarH>г</tarH> <tarH>Г</tarH>
 true: <tarH>ґ</tarH> <tarH>Ґ</tarH>
 ```
 
-### nonHtml
-
-Type: `boolean|object`
-
-Default value: `false`
-
-If `html` is defined, will be ignored
+## NonHtmlOptions
 
-#### nonHtml.nodeColors
+### nodeColors
 
 Type: `boolean`
 
 Default value: `false`
 
-#### nonHtml.h
+### h
 
 Type: `boolean`
 
@@ -114,7 +130,7 @@ false: Ґ ґ
 true: Г г
 ```
 
-#### nonHtml.variations
+### variations
 
 Type: `number`
 
@@ -128,25 +144,6 @@ Which variation should be if a part of word is variable?
 2 = all:    (Гродна|Горадня)
 ```
 
-### OVERRIDE_toTarask
-
-Type:
-
-```
-(
-    text: string,
-    replaceWithDict: (
-        text: string,
-        dict?: [RegExp, string | ((...substrings: string[]) => string)][]
-    ) => string,
-    wordlist: [RegExp, string][],
-    softers: [RegExp, string][],
-    afterTarask: (text: string) => string
-) => string
-```
-
-Default value: internal function `toTarask`
-
 ## HTML tags
 
 ### tarF

package/bin/index.js

@@ -1,5 +1,5 @@
 #!/usr/bin/env node
-import { tarask } from '../dist/index.js';
+import { tarask, taraskToHtml } from '../dist/index.js';
 import { readFile } from 'fs/promises';
 
 const print = (...msgs) => {
@@ -20,72 +20,75 @@ if (checkForOptions(['-v', '--version'])) {
 	process.exit(0);
 }
 
-const stgs = {
-	nonHtml: {
-		variations: 2,
-		nodeColors: true,
-	},
-};
+/** @type {Partial<import('../dist/types.js').TaraskOptions>} */
+const taraskOptions = {};
+/** @type {Partial<import('../dist/types.js').NonHtmlOptions>} */
+const nonHtmlOptions = { variations: 2, nodeColors: true };
+/** @type {Partial<import('../dist/types.js').HtmlOptions>} */
+const htmlOptions = { g: true };
+
+let isHtml = false;
 
 const optionDict = [
 	[
 		['--latin', '-l'],
 		() => {
-			stgs.abc = 1;
+			taraskOptions.abc = 1;
 		},
 	],
 	[
 		['--arabic', '-a'],
 		() => {
-			stgs.abc = 2;
+			taraskOptions.abc = 2;
 		},
 	],
 	[
 		['--greek', '-gr'],
 		() => {
-			stgs.abc = 3;
+			taraskOptions.abc = 3;
 		},
 	],
 	[
 		['--jrandom', '-jr'],
 		() => {
-			stgs.j = 1;
+			taraskOptions.j = 1;
 		},
 	],
 	[
 		['--jalways', '-ja'],
 		() => {
-			stgs.j = 2;
+			taraskOptions.j = 2;
 		},
 	],
 	[
 		['--h', '-h'],
 		() => {
-			stgs.nonHtml.h = true;
+			nonHtmlOptions.h = true;
+			htmlOptions.g = false;
 		},
 	],
 	[
 		['--no-variations', '-nv'],
 		() => {
-			stgs.nonHtml.variations = 0;
+			nonHtmlOptions.variations = 0;
 		},
 	],
 	[
 		['--first-variation-only', '-fvo'],
 		() => {
-			stgs.nonHtml.variations = 1;
+			nonHtmlOptions.variations = 1;
 		},
 	],
 	[
 		['--no-color', '-nc'],
 		() => {
-			stgs.nonHtml.nodeColors = false;
+			nonHtmlOptions.nodeColors = false;
 		},
 	],
 	[
 		['--html', '-html'],
 		() => {
-			stgs.html = {};
+			isHtml = true;
 		},
 	],
 ];
@@ -102,4 +105,8 @@ optionEater: while (true) {
 
 const text = process.argv.join(' ');
 
-console.log(tarask(text, stgs));
+console.log(
+	isHtml
+		? taraskToHtml(text, taraskOptions, htmlOptions)
+		: tarask(text, taraskOptions, nonHtmlOptions)
+);

package/dist/index.cjs

@@ -24,7 +24,8 @@ __export(src_exports, {
   J: () => J,
   VARIATION: () => VARIATION,
   gobj: () => gobj,
-  tarask: () => tarask
+  tarask: () => tarask,
+  taraskToHtml: () => taraskToHtml
 });
 module.exports = __toCommonJS(src_exports);
 
@@ -1362,7 +1363,7 @@ var rawWordlist = [
   [/экумен/, "экумэн"],
   [/елісейск/, "элізэйск"],
   [/энцыкла/, "энцыкля"],
-  [/энерг/, "энэрг"],
+  [/энерг/, "энэрґ"],
   [/эфект/, "эфэкт"],
   [/эфемер/, "эфэмэр"],
   [/эцюд/, "этуд"],
@@ -1617,7 +1618,7 @@ var rawWordlist = [
   [/сцей /, "сьц(ей|яў) "],
   [/ (г|(?:най)?ч)асьц\(ей\)\(яў\) /, " $1асьцей "],
   /* а > у */
-  [/(абед| дон|енск|[іы]зм|завод|інстытут| канал|крым|(?:кле|пола|слу)цк|лёндан|мадрыд| рым)а [^-]/, "$1у "],
+  [/(абед| дон|енск|[іы]зм|завод|інстытут| канал|крым|(?:кле|пола|слу)цк|лёндан|мадрыд| рым)а (?!-)/, "$1у "],
   [/(бэрлін|нясвіж|парыж)а /, "$1(а|у) "],
   [/дуная /, "дунаю "],
   /* Грэцкія назовы */
@@ -2015,7 +2016,7 @@ var gwords = [
   "аґрэст",
   " біґ ",
   " бразґ",
-  "буґацьці",
+  "буґацці",
   "бурґ",
   "вашынґт",
   "возґр",
@@ -2098,9 +2099,8 @@ var gwords = [
   "райхстаґ",
   " уґанд",
   // 'фоґель',
-  " цуґл",
+  " цуґл"
   // 'шваґер'
-  "энэрґ"
 ].reverse();
 var gobj = {
   "г": "ґ",
@@ -2126,13 +2126,12 @@ for (const word of gwords)
   wordlist.push([RegExp(word.replace(/ґ/g, "г"), "g"), word]);
 
 // src/tarask.ts
-var isObject = (arg) => typeof arg === "object";
 var isUpperCase = (str) => str === str.toUpperCase();
-var getLastLetter = (word) => {
-  for (let i = word.length - 1; i >= 0; i--)
-    if (/\p{L}/u.test(word[i]))
-      return word[i];
-  throw new Error(`the last letter of the word ${word} not found`);
+var getLastLetter = (word, i) => {
+  for (let i2 = word.length - 1; i2 >= 0; i2--)
+    if (/\p{L}/u.test(word[i2]))
+      return word[i2];
+  throw new Error(`the last letter of the word ${word} not found. index: ${i}`);
 };
 var NOFIX_CHAR = " ￿ ";
 var NOFIX_REGEX = new RegExp(NOFIX_CHAR, "g");
@@ -2175,17 +2174,14 @@ var afterTarask = [
     ($0, $1, $2) => /([ая]ў|ну)$/.test($2) ? $1 + "ь і" + $2 : $0
   ]
 ];
-var tarask = (text, options = {}) => {
-  const { abc = 0, j = 0, html = false, nonHtml = false } = options;
-  const isHtmlObject = isObject(html);
-  const isNonHtmlObject = isObject(nonHtml);
-  const apply = html ? tagApplications.html : tagApplications.nonHtml;
-  const noFix = [];
-  const LEFT_ANGLE_BRACKET = html ? "&lt;" : "<";
+var noFix = [];
+var process = (text, LEFT_ANGLE_BRACKET, options) => {
+  const { abc, j, OVERRIDE_toTarask: _toTarask = toTarask } = options;
+  const noFix2 = [];
   text = ` ${text.trim()} `.replace(/�/g, "").replace(/<([,.]?)([.\s]*?)>/g, ($0, $1, $2) => {
     if ($1 === ",")
       return LEFT_ANGLE_BRACKET + $2 + ">";
-    noFix[noFix.length] = $1 === "." ? $2 : $0;
+    noFix2[noFix2.length] = $1 === "." ? $2 : $0;
     return NOFIX_CHAR;
   }).replace(/г'(?![еёіюя])/g, "ґ").replace(/([\n\t])/g, " $1 ").replace(/ - /g, " — ").replace(/(\p{P}|\p{S}|\d)/gu, " $1 ").replace(/ ['`’] (?=\S)/g, "ʼ").replace(/\(/g, "&#40");
   let splittedOrig, splitted;
@@ -2193,7 +2189,7 @@ var tarask = (text, options = {}) => {
     replaceWithDict(text, letters[abc]),
     lettersUpperCase[abc]
   ).split(" ");
-  text = (options.OVERRIDE_toTarask || toTarask)(
+  text = _toTarask(
     text.toLowerCase(),
     replaceWithDict,
     wordlist,
@@ -2208,35 +2204,69 @@ var tarask = (text, options = {}) => {
   splitted = text.split(" ");
   if (abc !== ALPHABET.ARABIC)
     splitted = restoreCase(splitted, splittedOrig);
-  if (html || isNonHtmlObject && nonHtml.nodeColors)
-    splitted = toTags(
-      splitted,
-      splittedOrig,
-      abc === ALPHABET.CYRILLIC,
-      apply.F
+  return { splittedOrig, splitted };
+};
+var applyNoFix = (text) => {
+  if (noFix.length)
+    text = text.replace(NOFIX_REGEX, () => noFix.shift());
+  noFix = [];
+  return text;
+};
+var join = (textArr) => textArr.join(" ").replace(/&nbsp;/g, " ").replace(/ (\p{P}|\p{S}|\d|&#40) /gu, "$1");
+var finilize = (text, newLine) => text.replace(/ \t /g, "	").replace(/ \n /g, newLine).trim();
+var replaceG = (text, replacer) => text.replace(
+  G_REGEX,
+  // @ts-ignore
+  replacer
+);
+var getCompletedOptions = (options) => ({
+  abc: 0,
+  j: 0,
+  ...options
+});
+var taraskToHtml = (text, taraskOptions, htmlOptions = {}) => {
+  const options = getCompletedOptions(taraskOptions);
+  const apply = tagApplications.html;
+  const isCyrillic = options.abc === ALPHABET.CYRILLIC;
+  const { splitted, splittedOrig } = process(text, "&lt;", options);
+  addTags(splitted, splittedOrig, isCyrillic, apply.F);
+  text = join(splitted);
+  if (isCyrillic)
+    text = replaceG(
+      text,
+      htmlOptions.g ? apply.H("$&") : ($0) => apply.H(gobj[$0])
     );
-  text = splitted.join(" ").replace(/&nbsp;/g, " ").replace(/ (\p{P}|\p{S}|\d|&#40) /gu, "$1");
-  let gReplacer;
-  if (abc === ALPHABET.CYRILLIC) {
-    if (isHtmlObject) {
-      gReplacer = html.g ? apply.H("$&") : ($0) => apply.H(gobj[$0]);
-    } else if (isNonHtmlObject) {
-      if (nonHtml.nodeColors) {
-        gReplacer = nonHtml.h ? ($0) => apply.H(gobj[$0]) : apply.H("$&");
-      } else if (nonHtml.h) {
-        gReplacer = ($0) => gobj[$0];
-      }
-    }
-  }
-  if (gReplacer)
+  return finilize(
+    applyNoFix(text).replace(OPTIONAL_WORDS_REGEX, ($0) => {
+      const options2 = $0.slice(1, -1).split("|");
+      const main = options2.shift();
+      return `<tarL data-l='${options2}'>${main}</tarL>`;
+    }),
+    "<br>"
+  );
+};
+var tarask = (text, taraskOptions, nonHtmlOptions = {}) => {
+  const options = getCompletedOptions(taraskOptions);
+  const apply = tagApplications.nonHtml;
+  const isCyrillic = options.abc === ALPHABET.CYRILLIC;
+  const { splitted, splittedOrig } = process(text, "&lt;", options);
+  if (nonHtmlOptions.nodeColors)
+    addTags(splitted, splittedOrig, isCyrillic, apply.F);
+  text = join(splitted);
+  if (isCyrillic && (nonHtmlOptions.h || nonHtmlOptions.nodeColors))
+    text = replaceG(
+      text,
+      nonHtmlOptions.nodeColors ? nonHtmlOptions.h ? ($0) => apply.H(gobj[$0]) : apply.H("$&") : ($0) => gobj[$0]
+    );
+  if ("variations" in nonHtmlOptions && nonHtmlOptions.variations !== VARIATION.ALL) {
+    const wordIndex = nonHtmlOptions.variations ?? 0;
+    const replacer = ($0) => $0.slice(1, -1).split("|")[wordIndex];
     text = text.replace(
-      G_REGEX,
-      // @ts-ignore
-      gReplacer
+      OPTIONAL_WORDS_REGEX,
+      nonHtmlOptions.nodeColors ? ($0) => tagApplications.nonHtml.L(replacer($0)) : replacer
     );
-  if (noFix.length)
-    text = text.replace(NOFIX_REGEX, () => noFix.shift());
-  return (html ? finalizer.html(text) : finalizer.nonHtml(text, nonHtml)).replace(/ \t /g, "	").trim();
+  }
+  return finilize(applyNoFix(text).replace(/&#40/g, "("), "\n");
 };
 var restoreCase = (text, orig) => {
   for (let i = 0; i < text.length; i++) {
@@ -2252,7 +2282,7 @@ var restoreCase = (text, orig) => {
       continue;
     if (word === "зь") {
       text[i] = isUpperCase(orig[i + 1]) ? "ЗЬ" : "Зь";
-    } else if (isUpperCase(getLastLetter(oWord))) {
+    } else if (isUpperCase(getLastLetter(oWord, i))) {
       text[i] = word.toUpperCase();
     } else {
       text[i] = word[0] === "(" ? word.replace(
@@ -2263,13 +2293,13 @@ var restoreCase = (text, orig) => {
   }
   return text;
 };
-var toTags = (text, orig, isCyrillic, applyF) => {
+var addTags = (text, orig, isCyrillic, applyF) => {
   for (let i = 0; i < text.length; i++) {
     const word = text[i];
     const oWord = orig[i];
     if (oWord === word)
       continue;
-    const wordH = isCyrillic ? word.replace(G_REGEX, ($0) => gobj[$0]) : word;
+    const wordH = isCyrillic ? replaceG(word, ($0) => gobj[$0]) : word;
     if (oWord === wordH)
       continue;
     if (!/\(/.test(word)) {
@@ -2314,7 +2344,6 @@ var toTags = (text, orig, isCyrillic, applyF) => {
     }
     text[i] = word.slice(0, fromStart) + applyF(word.slice(fromStart, fromWordEnd + 1)) + word.slice(fromWordEnd + 1);
   }
-  return text;
 };
 var toTarask = (text, replaceWithDict2, wordlist2, softers2, afterTarask2) => {
   text = replaceWithDict2(text, wordlist2);
@@ -2342,29 +2371,12 @@ var replaceIbyJ = (text, always = false) => text.replace(
   /([аеёіоуыэюя] )і (ў?)/g,
   always ? ($0, $1, $2) => toJ($1, $2) : ($0, $1, $2) => Math.random() >= 0.5 ? toJ($1, $2) : $0
 );
-var finalizer = {
-  html: (text) => text.replace(OPTIONAL_WORDS_REGEX, ($0) => {
-    const options = $0.slice(1, -1).split("|");
-    const main = options.shift();
-    return `<tarL data-l='${options}'>${main}</tarL>`;
-  }).replace(/ \n /g, "<br>"),
-  nonHtml(text, options) {
-    if (isObject(options) && "variations" in options && options.variations !== VARIATION.ALL) {
-      const WORD_INDEX = options.variations ?? 0;
-      const replacer = ($0) => $0.slice(1, -1).split("|")[WORD_INDEX];
-      text = text.replace(
-        OPTIONAL_WORDS_REGEX,
-        options.nodeColors ? ($0) => tagApplications.nonHtml.L(replacer($0)) : replacer
-      );
-    }
-    return text.replace(/&#40/g, "(").replace(/ \n /g, "\n");
-  }
-};
 // Annotate the CommonJS export names for ESM import in node:
 0 && (module.exports = {
   ALPHABET,
   J,
   VARIATION,
   gobj,
-  tarask
+  tarask,
+  taraskToHtml
 });

package/dist/index.d.cts

@@ -1,13 +1,15 @@
 type ModifyObjectType<T, TResultObj> = T extends object ? T extends (...args: any[]) => any ? T : TResultObj : T;
-type DeepPartial<T> = ModifyObjectType<T, {
-    [P in keyof T]?: DeepPartial<T[P]>;
-}>;
-type DeepReadonly<T> = ModifyObjectType<T, {
-    readonly [P in keyof T]: DeepReadonly<T[P]>;
+type DeepPartialReadonly<T> = ModifyObjectType<T, {
+    readonly [P in keyof T]?: DeepPartialReadonly<T[P]>;
 }>;
 type Alphabet = 0 | 1 | 2 | 3;
 type OptionJ = 0 | 1 | 2;
 type Variation = 0 | 1 | 2;
+type TaraskOptions = {
+    abc: Alphabet;
+    j: OptionJ;
+    OVERRIDE_toTarask?: ToTarask;
+};
 type NonHtmlOptions = {
     nodeColors: boolean;
     h: boolean;
@@ -18,15 +20,7 @@ type HtmlOptions = {
 };
 type ReplaceWithDict = (text: string, dict?: ExtendedDict) => string;
 type ToTarask = (text: string, replaceWithDict: ReplaceWithDict, wordlist: Dict, softers: Dict, afterTarask: ExtendedDict) => string;
-type TaraskOptionsStrict = {
-    abc: Alphabet;
-    j: OptionJ;
-    html: boolean | HtmlOptions;
-    nonHtml: boolean | NonHtmlOptions;
-    OVERRIDE_toTarask?: ToTarask;
-};
-type TaraskOptions = DeepPartial<TaraskOptionsStrict>;
-type Tarask = (text: string, options?: DeepReadonly<TaraskOptions>) => string;
+type Tarask<TOptions extends object> = (text: string, taraskOptions?: DeepPartialReadonly<TaraskOptions>, options?: DeepPartialReadonly<TOptions>) => string;
 type Dict<T = RegExp> = [T, string][];
 type ExtendedDict = [
     RegExp,
@@ -52,7 +46,8 @@ declare const VARIATION: {
     readonly FIRST: 1;
     readonly ALL: 2;
 };
-declare const tarask: Tarask;
+declare const taraskToHtml: Tarask<HtmlOptions>;
+declare const tarask: Tarask<NonHtmlOptions>;
 
 declare const gobj: {
     readonly г: "ґ";
@@ -61,4 +56,4 @@ declare const gobj: {
     readonly Ґ: "Г";
 };
 
-export { ALPHABET, AlphabetDependentDict, Dict, ExtendedDict, HtmlOptions, J, NonHtmlOptions, ReplaceWithDict, Tarask, TaraskOptions, TaraskOptionsStrict, ToTarask, VARIATION, gobj, tarask };
+export { ALPHABET, AlphabetDependentDict, DeepPartialReadonly, Dict, ExtendedDict, HtmlOptions, J, NonHtmlOptions, ReplaceWithDict, Tarask, TaraskOptions, ToTarask, VARIATION, gobj, tarask, taraskToHtml };

package/dist/index.d.ts

@@ -1,13 +1,15 @@
 type ModifyObjectType<T, TResultObj> = T extends object ? T extends (...args: any[]) => any ? T : TResultObj : T;
-type DeepPartial<T> = ModifyObjectType<T, {
-    [P in keyof T]?: DeepPartial<T[P]>;
-}>;
-type DeepReadonly<T> = ModifyObjectType<T, {
-    readonly [P in keyof T]: DeepReadonly<T[P]>;
+type DeepPartialReadonly<T> = ModifyObjectType<T, {
+    readonly [P in keyof T]?: DeepPartialReadonly<T[P]>;
 }>;
 type Alphabet = 0 | 1 | 2 | 3;
 type OptionJ = 0 | 1 | 2;
 type Variation = 0 | 1 | 2;
+type TaraskOptions = {
+    abc: Alphabet;
+    j: OptionJ;
+    OVERRIDE_toTarask?: ToTarask;
+};
 type NonHtmlOptions = {
     nodeColors: boolean;
     h: boolean;
@@ -18,15 +20,7 @@ type HtmlOptions = {
 };
 type ReplaceWithDict = (text: string, dict?: ExtendedDict) => string;
 type ToTarask = (text: string, replaceWithDict: ReplaceWithDict, wordlist: Dict, softers: Dict, afterTarask: ExtendedDict) => string;
-type TaraskOptionsStrict = {
-    abc: Alphabet;
-    j: OptionJ;
-    html: boolean | HtmlOptions;
-    nonHtml: boolean | NonHtmlOptions;
-    OVERRIDE_toTarask?: ToTarask;
-};
-type TaraskOptions = DeepPartial<TaraskOptionsStrict>;
-type Tarask = (text: string, options?: DeepReadonly<TaraskOptions>) => string;
+type Tarask<TOptions extends object> = (text: string, taraskOptions?: DeepPartialReadonly<TaraskOptions>, options?: DeepPartialReadonly<TOptions>) => string;
 type Dict<T = RegExp> = [T, string][];
 type ExtendedDict = [
     RegExp,
@@ -52,7 +46,8 @@ declare const VARIATION: {
     readonly FIRST: 1;
     readonly ALL: 2;
 };
-declare const tarask: Tarask;
+declare const taraskToHtml: Tarask<HtmlOptions>;
+declare const tarask: Tarask<NonHtmlOptions>;
 
 declare const gobj: {
     readonly г: "ґ";
@@ -61,4 +56,4 @@ declare const gobj: {
     readonly Ґ: "Г";
 };
 
-export { ALPHABET, AlphabetDependentDict, Dict, ExtendedDict, HtmlOptions, J, NonHtmlOptions, ReplaceWithDict, Tarask, TaraskOptions, TaraskOptionsStrict, ToTarask, VARIATION, gobj, tarask };
+export { ALPHABET, AlphabetDependentDict, DeepPartialReadonly, Dict, ExtendedDict, HtmlOptions, J, NonHtmlOptions, ReplaceWithDict, Tarask, TaraskOptions, ToTarask, VARIATION, gobj, tarask, taraskToHtml };

package/dist/index.js

@@ -1332,7 +1332,7 @@ var rawWordlist = [
   [/экумен/, "экумэн"],
   [/елісейск/, "элізэйск"],
   [/энцыкла/, "энцыкля"],
-  [/энерг/, "энэрг"],
+  [/энерг/, "энэрґ"],
   [/эфект/, "эфэкт"],
   [/эфемер/, "эфэмэр"],
   [/эцюд/, "этуд"],
@@ -1587,7 +1587,7 @@ var rawWordlist = [
   [/сцей /, "сьц(ей|яў) "],
   [/ (г|(?:най)?ч)асьц\(ей\)\(яў\) /, " $1асьцей "],
   /* а > у */
-  [/(абед| дон|енск|[іы]зм|завод|інстытут| канал|крым|(?:кле|пола|слу)цк|лёндан|мадрыд| рым)а [^-]/, "$1у "],
+  [/(абед| дон|енск|[іы]зм|завод|інстытут| канал|крым|(?:кле|пола|слу)цк|лёндан|мадрыд| рым)а (?!-)/, "$1у "],
   [/(бэрлін|нясвіж|парыж)а /, "$1(а|у) "],
   [/дуная /, "дунаю "],
   /* Грэцкія назовы */
@@ -1985,7 +1985,7 @@ var gwords = [
   "аґрэст",
   " біґ ",
   " бразґ",
-  "буґацьці",
+  "буґацці",
   "бурґ",
   "вашынґт",
   "возґр",
@@ -2068,9 +2068,8 @@ var gwords = [
   "райхстаґ",
   " уґанд",
   // 'фоґель',
-  " цуґл",
+  " цуґл"
   // 'шваґер'
-  "энэрґ"
 ].reverse();
 var gobj = {
   "г": "ґ",
@@ -2096,13 +2095,12 @@ for (const word of gwords)
   wordlist.push([RegExp(word.replace(/ґ/g, "г"), "g"), word]);
 
 // src/tarask.ts
-var isObject = (arg) => typeof arg === "object";
 var isUpperCase = (str) => str === str.toUpperCase();
-var getLastLetter = (word) => {
-  for (let i = word.length - 1; i >= 0; i--)
-    if (/\p{L}/u.test(word[i]))
-      return word[i];
-  throw new Error(`the last letter of the word ${word} not found`);
+var getLastLetter = (word, i) => {
+  for (let i2 = word.length - 1; i2 >= 0; i2--)
+    if (/\p{L}/u.test(word[i2]))
+      return word[i2];
+  throw new Error(`the last letter of the word ${word} not found. index: ${i}`);
 };
 var NOFIX_CHAR = " ￿ ";
 var NOFIX_REGEX = new RegExp(NOFIX_CHAR, "g");
@@ -2145,17 +2143,14 @@ var afterTarask = [
     ($0, $1, $2) => /([ая]ў|ну)$/.test($2) ? $1 + "ь і" + $2 : $0
   ]
 ];
-var tarask = (text, options = {}) => {
-  const { abc = 0, j = 0, html = false, nonHtml = false } = options;
-  const isHtmlObject = isObject(html);
-  const isNonHtmlObject = isObject(nonHtml);
-  const apply = html ? tagApplications.html : tagApplications.nonHtml;
-  const noFix = [];
-  const LEFT_ANGLE_BRACKET = html ? "&lt;" : "<";
+var noFix = [];
+var process = (text, LEFT_ANGLE_BRACKET, options) => {
+  const { abc, j, OVERRIDE_toTarask: _toTarask = toTarask } = options;
+  const noFix2 = [];
   text = ` ${text.trim()} `.replace(/�/g, "").replace(/<([,.]?)([.\s]*?)>/g, ($0, $1, $2) => {
     if ($1 === ",")
       return LEFT_ANGLE_BRACKET + $2 + ">";
-    noFix[noFix.length] = $1 === "." ? $2 : $0;
+    noFix2[noFix2.length] = $1 === "." ? $2 : $0;
     return NOFIX_CHAR;
   }).replace(/г'(?![еёіюя])/g, "ґ").replace(/([\n\t])/g, " $1 ").replace(/ - /g, " — ").replace(/(\p{P}|\p{S}|\d)/gu, " $1 ").replace(/ ['`’] (?=\S)/g, "ʼ").replace(/\(/g, "&#40");
   let splittedOrig, splitted;
@@ -2163,7 +2158,7 @@ var tarask = (text, options = {}) => {
     replaceWithDict(text, letters[abc]),
     lettersUpperCase[abc]
   ).split(" ");
-  text = (options.OVERRIDE_toTarask || toTarask)(
+  text = _toTarask(
     text.toLowerCase(),
     replaceWithDict,
     wordlist,
@@ -2178,35 +2173,69 @@ var tarask = (text, options = {}) => {
   splitted = text.split(" ");
   if (abc !== ALPHABET.ARABIC)
     splitted = restoreCase(splitted, splittedOrig);
-  if (html || isNonHtmlObject && nonHtml.nodeColors)
-    splitted = toTags(
-      splitted,
-      splittedOrig,
-      abc === ALPHABET.CYRILLIC,
-      apply.F
+  return { splittedOrig, splitted };
+};
+var applyNoFix = (text) => {
+  if (noFix.length)
+    text = text.replace(NOFIX_REGEX, () => noFix.shift());
+  noFix = [];
+  return text;
+};
+var join = (textArr) => textArr.join(" ").replace(/&nbsp;/g, " ").replace(/ (\p{P}|\p{S}|\d|&#40) /gu, "$1");
+var finilize = (text, newLine) => text.replace(/ \t /g, "	").replace(/ \n /g, newLine).trim();
+var replaceG = (text, replacer) => text.replace(
+  G_REGEX,
+  // @ts-ignore
+  replacer
+);
+var getCompletedOptions = (options) => ({
+  abc: 0,
+  j: 0,
+  ...options
+});
+var taraskToHtml = (text, taraskOptions, htmlOptions = {}) => {
+  const options = getCompletedOptions(taraskOptions);
+  const apply = tagApplications.html;
+  const isCyrillic = options.abc === ALPHABET.CYRILLIC;
+  const { splitted, splittedOrig } = process(text, "&lt;", options);
+  addTags(splitted, splittedOrig, isCyrillic, apply.F);
+  text = join(splitted);
+  if (isCyrillic)
+    text = replaceG(
+      text,
+      htmlOptions.g ? apply.H("$&") : ($0) => apply.H(gobj[$0])
     );
-  text = splitted.join(" ").replace(/&nbsp;/g, " ").replace(/ (\p{P}|\p{S}|\d|&#40) /gu, "$1");
-  let gReplacer;
-  if (abc === ALPHABET.CYRILLIC) {
-    if (isHtmlObject) {
-      gReplacer = html.g ? apply.H("$&") : ($0) => apply.H(gobj[$0]);
-    } else if (isNonHtmlObject) {
-      if (nonHtml.nodeColors) {
-        gReplacer = nonHtml.h ? ($0) => apply.H(gobj[$0]) : apply.H("$&");
-      } else if (nonHtml.h) {
-        gReplacer = ($0) => gobj[$0];
-      }
-    }
-  }
-  if (gReplacer)
+  return finilize(
+    applyNoFix(text).replace(OPTIONAL_WORDS_REGEX, ($0) => {
+      const options2 = $0.slice(1, -1).split("|");
+      const main = options2.shift();
+      return `<tarL data-l='${options2}'>${main}</tarL>`;
+    }),
+    "<br>"
+  );
+};
+var tarask = (text, taraskOptions, nonHtmlOptions = {}) => {
+  const options = getCompletedOptions(taraskOptions);
+  const apply = tagApplications.nonHtml;
+  const isCyrillic = options.abc === ALPHABET.CYRILLIC;
+  const { splitted, splittedOrig } = process(text, "&lt;", options);
+  if (nonHtmlOptions.nodeColors)
+    addTags(splitted, splittedOrig, isCyrillic, apply.F);
+  text = join(splitted);
+  if (isCyrillic && (nonHtmlOptions.h || nonHtmlOptions.nodeColors))
+    text = replaceG(
+      text,
+      nonHtmlOptions.nodeColors ? nonHtmlOptions.h ? ($0) => apply.H(gobj[$0]) : apply.H("$&") : ($0) => gobj[$0]
+    );
+  if ("variations" in nonHtmlOptions && nonHtmlOptions.variations !== VARIATION.ALL) {
+    const wordIndex = nonHtmlOptions.variations ?? 0;
+    const replacer = ($0) => $0.slice(1, -1).split("|")[wordIndex];
     text = text.replace(
-      G_REGEX,
-      // @ts-ignore
-      gReplacer
+      OPTIONAL_WORDS_REGEX,
+      nonHtmlOptions.nodeColors ? ($0) => tagApplications.nonHtml.L(replacer($0)) : replacer
     );
-  if (noFix.length)
-    text = text.replace(NOFIX_REGEX, () => noFix.shift());
-  return (html ? finalizer.html(text) : finalizer.nonHtml(text, nonHtml)).replace(/ \t /g, "	").trim();
+  }
+  return finilize(applyNoFix(text).replace(/&#40/g, "("), "\n");
 };
 var restoreCase = (text, orig) => {
   for (let i = 0; i < text.length; i++) {
@@ -2222,7 +2251,7 @@ var restoreCase = (text, orig) => {
       continue;
     if (word === "зь") {
       text[i] = isUpperCase(orig[i + 1]) ? "ЗЬ" : "Зь";
-    } else if (isUpperCase(getLastLetter(oWord))) {
+    } else if (isUpperCase(getLastLetter(oWord, i))) {
       text[i] = word.toUpperCase();
     } else {
       text[i] = word[0] === "(" ? word.replace(
@@ -2233,13 +2262,13 @@ var restoreCase = (text, orig) => {
   }
   return text;
 };
-var toTags = (text, orig, isCyrillic, applyF) => {
+var addTags = (text, orig, isCyrillic, applyF) => {
   for (let i = 0; i < text.length; i++) {
     const word = text[i];
     const oWord = orig[i];
     if (oWord === word)
       continue;
-    const wordH = isCyrillic ? word.replace(G_REGEX, ($0) => gobj[$0]) : word;
+    const wordH = isCyrillic ? replaceG(word, ($0) => gobj[$0]) : word;
     if (oWord === wordH)
       continue;
     if (!/\(/.test(word)) {
@@ -2284,7 +2313,6 @@ var toTags = (text, orig, isCyrillic, applyF) => {
     }
     text[i] = word.slice(0, fromStart) + applyF(word.slice(fromStart, fromWordEnd + 1)) + word.slice(fromWordEnd + 1);
   }
-  return text;
 };
 var toTarask = (text, replaceWithDict2, wordlist2, softers2, afterTarask2) => {
   text = replaceWithDict2(text, wordlist2);
@@ -2312,28 +2340,11 @@ var replaceIbyJ = (text, always = false) => text.replace(
   /([аеёіоуыэюя] )і (ў?)/g,
   always ? ($0, $1, $2) => toJ($1, $2) : ($0, $1, $2) => Math.random() >= 0.5 ? toJ($1, $2) : $0
 );
-var finalizer = {
-  html: (text) => text.replace(OPTIONAL_WORDS_REGEX, ($0) => {
-    const options = $0.slice(1, -1).split("|");
-    const main = options.shift();
-    return `<tarL data-l='${options}'>${main}</tarL>`;
-  }).replace(/ \n /g, "<br>"),
-  nonHtml(text, options) {
-    if (isObject(options) && "variations" in options && options.variations !== VARIATION.ALL) {
-      const WORD_INDEX = options.variations ?? 0;
-      const replacer = ($0) => $0.slice(1, -1).split("|")[WORD_INDEX];
-      text = text.replace(
-        OPTIONAL_WORDS_REGEX,
-        options.nodeColors ? ($0) => tagApplications.nonHtml.L(replacer($0)) : replacer
-      );
-    }
-    return text.replace(/&#40/g, "(").replace(/ \n /g, "\n");
-  }
-};
 export {
   ALPHABET,
   J,
   VARIATION,
   gobj,
-  tarask
+  tarask,
+  taraskToHtml
 };

package/package.json

@@ -2,7 +2,7 @@
 	"name": "taraskevizer",
 	"author": "GooseOb",
 	"license": "MIT",
-	"version": "1.7.5",
+	"version": "2.0.1",
 	"private": false,
 	"homepage": "https://gooseob.github.io/taraskevizatar/",
 	"main": "dist/index.js",
@@ -20,7 +20,7 @@
 	"scripts": {
 		"build": "tsup --config build-config/index.js",
 		"build:bun_EXPERIMENTAL": "bun ./build-config/bun.ts",
-		"dev": "esrun --watch=src/*,test/* --send-code-mode=temporaryFile test",
+		"dev": "esrun --watch=src/*,test/*,bin/* --send-code-mode=temporaryFile test",
 		"dev:bun": "bun ./test/bun-watch.ts",
 		"dev-bun": "bun test --watch",
 		"test": "esrun --send-code-mode=temporaryFile test",