@lunarisapp/hyphen 0.0.6 → 1.1.0

package/README.md

@@ -2,15 +2,22 @@
 
 [![NPM Version](https://img.shields.io/npm/v/%40lunarisapp%2Fhyphen)](https://www.npmjs.com/package/@lunarisapp/hyphen)
 [![NPM Downloads](https://img.shields.io/npm/dm/%40lunarisapp%2Fhyphen)](https://www.npmjs.com/package/@lunarisapp/hyphen)
-[![CI/CD Status](https://img.shields.io/github/actions/workflow/status/LunarisApp/text-tools/checks.yml?label=CI%2FCD)](https://github.com/LunarisApp/text-tools/actions/workflows/checks.yml)
+[![CI Status](https://img.shields.io/github/actions/workflow/status/LunarisApp/text-tools/checks.yml?label=CI)](https://github.com/LunarisApp/text-tools/actions/workflows/checks.yml)
 
 A hyphenation library based on [LibreOffice dictionaries](https://git.libreoffice.org/dictionaries), inspired by [pyphen](https://github.com/Kozea/Pyphen).
 
 > [!TIP]
 > See also:
+>   - [@lunarisapp/language](https://github.com/LunarisApp/text-tools/tree/main/packages/language) for core linguistic breakdown: vowels, consonants, words, and sentences.
 >   - [@lunarisapp/stats](https://github.com/LunarisApp/text-tools/tree/main/packages/stats) for text statistics (e.g. word count, sentence count, etc.).
 >   - [@lunarisapp/readability](https://github.com/LunarisApp/text-tools/tree/main/packages/readability) for text readability scores (e.g. Flesch Reading Ease).
 
+## Features
+
+- Browser & Node.js support
+- Multi-language support
+- TypeScript support
+
 ## Installation
 
 ```bash
@@ -23,9 +30,9 @@ npm install @lunarisapp/hyphen
 import { TextHyphen } from '@lunarisapp/hyphen';
 
 const textHyphen = new TextHyphen({
-    lang: 'en_US',
-    left: 2,
-    right: 2,
+    lang: 'en_US',  // optional, en_US by default
+    left: 2,        // optional, 2 by default
+    right: 2,       // optional, 2 by default
 });
 
 // Gets the textHyphenation points for a word.

package/dist/index.d.mts

@@ -5,6 +5,10 @@ declare const beBy: HyphenDict;
 declare const bgBG: HyphenDict;
 declare const ca: HyphenDict;
 declare const daDK: HyphenDict;
+declare const deAT: HyphenDict;
+/**
+ * @deprecated Use `deAT` instead.
+ */
 declare const deDT: HyphenDict;
 declare const deCH: HyphenDict;
 declare const deDE: HyphenDict;
@@ -101,12 +105,13 @@ type Language = keyof typeof dictionaries;
 declare class TextHyphen {
     private readonly left;
     private readonly right;
-    private hd;
+    private readonly hd;
     constructor(props?: {
         lang?: Language;
         left?: number;
         right?: number;
     });
+    private filteredPositions;
     /**
      * Get the positions of possible hyphenation points in a word
      * @param word
@@ -137,4 +142,4 @@ declare class TextHyphen {
     inserted(word: string, hyphen?: string): string;
 }
 
-export { type Language, TextHyphen, afZa, asIn, beBy, bgBG, ca, daDK, deCH, deDE, deDT, dictionaries, enGB, enUS, eo, es, etEE, fr, gl, hrHR, huHU, idID, is, itIT, knIN, lt, lvLV, mnMN, mrIN, nbNO, nlNL, nnNO, paIN, plPL, ptBR, ptPT, roRO, ruRU, saIN, skSK, slSI, sqAL, sr, srLatn, sv, teIN, thTH, ukUA, zuZA };
+export { type Language, TextHyphen, afZa, asIn, beBy, bgBG, ca, daDK, deAT, deCH, deDE, deDT, dictionaries, enGB, enUS, eo, es, etEE, fr, gl, hrHR, huHU, idID, is, itIT, knIN, lt, lvLV, mnMN, mrIN, nbNO, nlNL, nnNO, paIN, plPL, ptBR, ptPT, roRO, ruRU, saIN, skSK, slSI, sqAL, sr, srLatn, sv, teIN, thTH, ukUA, zuZA };

package/dist/index.d.ts

@@ -5,6 +5,10 @@ declare const beBy: HyphenDict;
 declare const bgBG: HyphenDict;
 declare const ca: HyphenDict;
 declare const daDK: HyphenDict;
+declare const deAT: HyphenDict;
+/**
+ * @deprecated Use `deAT` instead.
+ */
 declare const deDT: HyphenDict;
 declare const deCH: HyphenDict;
 declare const deDE: HyphenDict;
@@ -101,12 +105,13 @@ type Language = keyof typeof dictionaries;
 declare class TextHyphen {
     private readonly left;
     private readonly right;
-    private hd;
+    private readonly hd;
     constructor(props?: {
         lang?: Language;
         left?: number;
         right?: number;
     });
+    private filteredPositions;
     /**
      * Get the positions of possible hyphenation points in a word
      * @param word
@@ -137,4 +142,4 @@ declare class TextHyphen {
     inserted(word: string, hyphen?: string): string;
 }
 
-export { type Language, TextHyphen, afZa, asIn, beBy, bgBG, ca, daDK, deCH, deDE, deDT, dictionaries, enGB, enUS, eo, es, etEE, fr, gl, hrHR, huHU, idID, is, itIT, knIN, lt, lvLV, mnMN, mrIN, nbNO, nlNL, nnNO, paIN, plPL, ptBR, ptPT, roRO, ruRU, saIN, skSK, slSI, sqAL, sr, srLatn, sv, teIN, thTH, ukUA, zuZA };
+export { type Language, TextHyphen, afZa, asIn, beBy, bgBG, ca, daDK, deAT, deCH, deDE, deDT, dictionaries, enGB, enUS, eo, es, etEE, fr, gl, hrHR, huHU, idID, is, itIT, knIN, lt, lvLV, mnMN, mrIN, nbNO, nlNL, nnNO, paIN, plPL, ptBR, ptPT, roRO, ruRU, saIN, skSK, slSI, sqAL, sr, srLatn, sv, teIN, thTH, ukUA, zuZA };

package/dist/index.js

@@ -27,6 +27,7 @@ __export(index_exports, {
   bgBG: () => bgBG,
   ca: () => ca,
   daDK: () => daDK,
+  deAT: () => deAT,
   deCH: () => deCH,
   deDE: () => deDE,
   deDT: () => deDT,
@@ -239254,6 +239255,7 @@ var beBy = hyph_be_BY_default;
 var bgBG = hyph_bg_BG_default;
 var ca = hyph_ca_default;
 var daDK = hyph_da_DK_default;
+var deAT = hyph_de_AT_default;
 var deDT = hyph_de_AT_default;
 var deCH = hyph_de_CH_default;
 var deDE = hyph_de_DE_default;
@@ -239369,50 +239371,61 @@ var HyphenDictParser = class {
     this.cache = /* @__PURE__ */ new Map();
     this.maxLen = 0;
     const lines = content.split("\n");
-    lines.forEach((line) => {
-      line = line.trim();
-      if (!line || IGNORED.some((i) => line.startsWith(i))) return;
-      const pattern = line.replace(
+    for (const line of lines) {
+      const trimmedLine = line.trim();
+      if (!trimmedLine || IGNORED.some((i) => trimmedLine.startsWith(i))) {
+        continue;
+      }
+      const pattern = trimmedLine.replace(
         /\^{2}([0-9a-f]{2})/g,
-        (match, hex) => String.fromCharCode(parseInt(hex, 16))
+        (_match, hex) => String.fromCharCode(Number.parseInt(hex, 16))
       );
       const parts = Array.from(pattern.matchAll(/(\d?)(\D?)/g));
       const tags = [];
       const values = [];
-      parts.forEach(([, num, char]) => {
-        tags.push(char);
-        values.push(num ? parseInt(num) : 0);
-      });
-      if (Math.max(...values) === 0) return;
+      for (const [, num, char] of parts) {
+        tags.push(char ?? "");
+        values.push(num ? Number.parseInt(num, 10) : 0);
+      }
+      if (Math.max(...values) === 0) {
+        continue;
+      }
       let start = 0, end = values.length;
-      while (!values[start]) start++;
-      while (!values[end - 1]) end--;
+      while (!values[start]) {
+        start++;
+      }
+      while (!values[end - 1]) {
+        end--;
+      }
       this.patterns.set(tags.join(""), [start, values.slice(start, end)]);
-    });
-    this.maxLen = Math.max(
-      ...Array.from(this.patterns.keys()).map((k) => k.length)
-    );
+    }
+    const lengths = Array.from(this.patterns.keys()).map((k) => k.length);
+    this.maxLen = lengths.length > 0 ? Math.max(...lengths) : 0;
   }
   positions(word) {
-    word = word.toLowerCase();
-    if (this.cache.has(word)) return this.cache.get(word);
-    const references = new Array(word.length + 2).fill(0);
-    const extendedWord = `.${word}.`;
+    const lowerWord = word.toLowerCase();
+    if (this.cache.has(lowerWord)) {
+      return this.cache.get(lowerWord);
+    }
+    const references = new Array(lowerWord.length + 2).fill(0);
+    const extendedWord = `.${lowerWord}.`;
     for (let i = 0; i < extendedWord.length - 1; i++) {
       for (let j = i + 1; j < Math.min(i + this.maxLen, extendedWord.length) + 1; j++) {
         const pattern = this.patterns.get(extendedWord.slice(i, j));
-        if (!pattern) continue;
+        if (!pattern) {
+          continue;
+        }
         const [offset, values] = pattern;
-        values.forEach((val, idx) => {
+        for (let idx = 0; idx < values.length; idx++) {
           references[i + offset + idx] = Math.max(
-            val,
+            values[idx],
             references[i + offset + idx]
           );
-        });
+        }
       }
     }
     const positions = references.map((val, idx) => val % 2 ? new DataInt(idx - 1) : null).filter(Boolean);
-    this.cache.set(word, positions);
+    this.cache.set(lowerWord, positions);
     return positions;
   }
 };
@@ -239424,20 +239437,23 @@ var TextHyphen = class {
     const dict = dictionaries[lang] || enUS;
     this.hd = new HyphenDictParser(dict);
   }
+  filteredPositions(word) {
+    const rightLimit = word.length - this.right;
+    return this.hd.positions(word).filter((pos) => this.left <= pos.value && pos.value <= rightLimit);
+  }
   /**
    * Get the positions of possible hyphenation points in a word
    * @param word
    */
   positions(word) {
-    const rightLimit = word.length - this.right;
-    return this.hd.positions(word).map((pos) => pos.value).filter((pos) => this.left <= pos && pos <= rightLimit);
+    return this.filteredPositions(word).map((pos) => pos.value);
   }
   /**
    * Get iterator for all possible variants of hyphenating the word.
    * @param word
    */
   *iterate(word) {
-    for (const position of this.hd.positions(word).reverse()) {
+    for (const position of this.filteredPositions(word).reverse()) {
       if (position.data) {
         const [change, index, cut] = position.data;
         const updatedIndex = index + position.value;
@@ -239469,9 +239485,9 @@ var TextHyphen = class {
    * @param hyphen
    */
   wrap(word, width, hyphen = "-") {
-    width -= hyphen.length;
+    const effectiveWidth = width - hyphen.length;
     for (const [w1, w2] of this.iterate(word)) {
-      if (w1.length <= width) {
+      if (w1.length <= effectiveWidth) {
         return [w1 + hyphen, w2];
       }
     }
@@ -239484,9 +239500,9 @@ var TextHyphen = class {
    */
   inserted(word, hyphen = "-") {
     const letters = [...word];
-    this.positions(word).reverse().forEach((pos) => {
+    for (const pos of this.positions(word).reverse()) {
       letters.splice(pos, 0, hyphen);
-    });
+    }
     return letters.join("");
   }
 };
@@ -239499,6 +239515,7 @@ var TextHyphen = class {
   bgBG,
   ca,
   daDK,
+  deAT,
   deCH,
   deDE,
   deDT,