unicode-width-approximation 1.0.0

package/README.md

@@ -0,0 +1,77 @@
+# Unicode Width Approximation (WASM)
+
+A library for calculating the display width of Unicode strings in terminal/monospace environments.
+
+## Installation
+
+```bash
+npm install unicode-width-approximation
+```
+
+## Usage
+
+```javascript
+import {
+    getStringWidth,
+    getCodepointWidth,
+    isWideChar,
+    isZeroWidth
+} from "unicode-width-approximation";
+
+// Get width of strings
+console.log(getStringWidth("hello"));      // 5
+console.log(getStringWidth("中文"));        // 4
+console.log(getStringWidth("👨‍👩‍👧‍👦"));  // 2
+
+// Get width of single code points
+console.log(getCodepointWidth(0x41));    // 1 (ASCII 'A')
+console.log(getCodepointWidth(0x4E00));  // 2 (CJK)
+console.log(getCodepointWidth(0x1F600)); // 2 (emoji)
+```
+
+## TypeScript
+
+TypeScript type definitions are included.
+
+```typescript
+import { getStringWidth, getCodepointWidth } from "unicode-width-approximation";
+
+const width: number = getStringWidth("hello世界");
+console.log(width);  // 9
+```
+
+## API
+
+### `getStringWidth(s: string): number`
+
+Calculate the total display width of a string.
+
+### `getCodepointWidth(code: number): number`
+
+Get the display width of a single Unicode code point (0, 1, or 2).
+
+### `isWideChar(code: number): boolean`
+
+Check if a code point is a wide character (East Asian Wide or Fullwidth).
+
+### `isZeroWidth(code: number): boolean`
+
+Check if a code point is a zero-width character.
+
+## Building
+
+Requires [Emscripten](https://emscripten.org/) to be installed.
+
+```bash
+npm run build
+```
+
+## Testing
+
+```bash
+npm test
+```
+
+## License
+
+MIT License

package/index.d.ts

@@ -0,0 +1,52 @@
+/**
+ * Calculate the total display width of a string.
+ *
+ * This function segments the string into grapheme clusters and calculates
+ * the width based on the base character of each cluster.
+ *
+ * @param s - The input string.
+ * @returns The total display width in columns.
+ *
+ * @example
+ * ```typescript
+ * import { getStringWidth } from "unicode-width-approximation";
+ *
+ * getStringWidth("hello");      // 5
+ * getStringWidth("中文");        // 4
+ * getStringWidth("👨‍👩‍👧‍👦");  // 2
+ * ```
+ */
+export function getStringWidth(s: string): number;
+
+/**
+ * Get the display width of a single Unicode code point.
+ *
+ * @param code - The Unicode code point.
+ * @returns The display width (0, 1, or 2).
+ *
+ * @example
+ * ```typescript
+ * import { getCodepointWidth } from "unicode-width-approximation";
+ *
+ * getCodepointWidth(0x41);    // 1 (ASCII 'A')
+ * getCodepointWidth(0x4E00);  // 2 (CJK)
+ * getCodepointWidth(0x0300);  // 0 (combining mark)
+ * ```
+ */
+export function getCodepointWidth(code: number): number;
+
+/**
+ * Check if a code point is a wide character (East Asian Wide or Fullwidth).
+ *
+ * @param code - The Unicode code point.
+ * @returns True if the character has width 2.
+ */
+export function isWideChar(code: number): boolean;
+
+/**
+ * Check if a code point is a zero-width character.
+ *
+ * @param code - The Unicode code point.
+ * @returns True if the character has zero width.
+ */
+export function isZeroWidth(code: number): boolean;

package/index.js

@@ -0,0 +1,46 @@
+import createModule from "./wasm/UnicodeWidthApproximationWASM.js";
+
+const UnicodeWidthApproximationWASM = await createModule();
+
+/**
+ * Calculate the total display width of a string.
+ *
+ * This function segments the string into grapheme clusters and calculates
+ * the width based on the base character of each cluster.
+ *
+ * @param {string} s - The input string.
+ * @returns {number} The total display width in columns.
+ */
+export function getStringWidth(s) {
+    return UnicodeWidthApproximationWASM._getStringWidth(s);
+}
+
+/**
+ * Get the display width of a single Unicode code point.
+ *
+ * @param {number} code - The Unicode code point.
+ * @returns {number} The display width (0, 1, or 2).
+ */
+export function getCodepointWidth(code) {
+    return UnicodeWidthApproximationWASM._getCodepointWidth(code);
+}
+
+/**
+ * Check if a code point is a wide character (East Asian Wide or Fullwidth).
+ *
+ * @param {number} code - The Unicode code point.
+ * @returns {boolean} True if the character has width 2.
+ */
+export function isWideChar(code) {
+    return UnicodeWidthApproximationWASM._isWideChar(code);
+}
+
+/**
+ * Check if a code point is a zero-width character.
+ *
+ * @param {number} code - The Unicode code point.
+ * @returns {boolean} True if the character has zero width.
+ */
+export function isZeroWidth(code) {
+    return UnicodeWidthApproximationWASM._isZeroWidth(code);
+}

package/package.json

@@ -0,0 +1,38 @@
+{
+  "name": "unicode-width-approximation",
+  "version": "1.0.0",
+  "description": "A library for calculating the display width of Unicode strings.",
+  "type": "module",
+  "main": "index.js",
+  "types": "index.d.ts",
+  "files": [
+    "index.js",
+    "index.d.ts",
+    "wasm/UnicodeWidthApproximationWASM.js",
+    "wasm/UnicodeWidthApproximationWASM.wasm"
+  ],
+  "devDependencies": {
+    "@eslint/js": "^9.39.1",
+    "chai": "^0.1.7",
+    "eslint": "^9.39.1",
+    "globals": "^16.5.0",
+    "mocha": "^11.7.5"
+  },
+  "scripts": {
+    "build": "bash build.sh",
+    "lint": "npx eslint index.js test/**/*.js",
+    "test": "mocha test/**/*.js"
+  },
+  "homepage": "https://github.com/CyberZHG/UnicodeWidthApproximation",
+  "repository": "github:CyberZHG/UnicodeWidthApproximation",
+  "license": "MIT",
+  "keywords": [
+    "unicode",
+    "width",
+    "terminal",
+    "monospace",
+    "cjk",
+    "emoji",
+    "east-asian-width"
+  ]
+}