node-docx-html-converter 0.1.0

package/README.md

@@ -0,0 +1,60 @@
+# node-docx-html-converter
+
+DOCX ↔ HTML conversion via Rust WASM. Two main functions:
+
+- **docxToHtml** — DOCX bytes → HTML string
+- **htmlToDocx** — HTML string → DOCX bytes
+
+## Install
+
+```bash
+npm install node-docx-html-converter
+```
+
+## Usage
+
+### ESM (sync)
+
+```js
+import { docxToHtml, htmlToDocx } from 'node-docx-html-converter';
+import fs from 'fs';
+
+// DOCX → HTML
+const docxBuffer = fs.readFileSync('document.docx');
+const html = docxToHtml(docxBuffer);
+// or embeddable fragment:
+const embed = docxToHtml(docxBuffer, { embed: true });
+
+// HTML → DOCX
+const htmlStr = fs.readFileSync('output.html', 'utf8');
+const docxBytes = htmlToDocx(htmlStr);
+fs.writeFileSync('output.docx', docxBytes);
+```
+
+### CommonJS (sync)
+
+```js
+const { docxToHtml, htmlToDocx } = require('node-docx-html-converter');
+
+const html = docxToHtml(docxBuffer);
+const docxBytes = htmlToDocx(htmlStr);
+```
+
+## API
+
+### docxToHtml(docxBuffer, options?)
+
+- `docxBuffer` — `Buffer` or `Uint8Array` with .docx file bytes
+- `options.embed` — if true, returns embeddable fragment (no DOCTYPE)
+- `options.noH4` — when true, bold from paragraph style not applied to list items
+- `options.debugLayout` — when true, adds colored borders for debugging
+- Returns: `string`
+
+### htmlToDocx(html)
+
+- `html` — HTML string (full document or embed fragment from docx-html-converter)
+- Returns: `Buffer`
+
+### calculate_html(html)
+
+Recalculates page breaks for contentEditable. Returns reflowed HTML.

package/index.cjs

@@ -0,0 +1,34 @@
+/**
+ * node-docx-html-converter (CommonJS)
+ */
+const pkg = require('docx-html-converter');
+
+/**
+ * Converts DOCX bytes to HTML.
+ * @param {Buffer|Uint8Array} docxBuffer - Raw .docx file bytes
+ * @param {{ embed?: boolean, noH4?: boolean, debugLayout?: boolean }} [options]
+ * @returns {string} HTML string
+ */
+function docxToHtml(docxBuffer, options = {}) {
+  const { embed = false, noH4 = false, debugLayout = false } = options;
+  const arr = docxBuffer instanceof Uint8Array ? docxBuffer : new Uint8Array(docxBuffer);
+  return embed
+    ? pkg.convert_docx_embed(arr, noH4, debugLayout)
+    : pkg.convert_docx(arr, noH4, debugLayout);
+}
+
+/**
+ * Converts HTML to DOCX bytes.
+ * @param {string} html - HTML string
+ * @returns {Buffer} Raw .docx file bytes
+ */
+function htmlToDocx(html) {
+  const result = pkg.convert_html_to_docx(html);
+  return Buffer.from(result);
+}
+
+module.exports = {
+  docxToHtml,
+  htmlToDocx,
+  calculate_html: pkg.calculate_html,
+};

package/index.d.ts

@@ -0,0 +1,21 @@
+/**
+ * Converts DOCX bytes to HTML.
+ */
+export function docxToHtml(
+  docxBuffer: Buffer | Uint8Array,
+  options?: {
+    embed?: boolean;
+    noH4?: boolean;
+    debugLayout?: boolean;
+  }
+): string;
+
+/**
+ * Converts HTML (docx-html-converter format) to DOCX bytes.
+ */
+export function htmlToDocx(html: string): Buffer;
+
+/**
+ * Recalculates page breaks in HTML "Word-style".
+ */
+export function calculate_html(html: string): string;

package/index.js

@@ -0,0 +1,41 @@
+/**
+ * node-docx-html-converter
+ * DOCX ↔ HTML conversion via Rust WASM.
+ */
+import pkg from 'docx-html-converter';
+const { convert_docx, convert_docx_embed, convert_html_to_docx, calculate_html } = pkg;
+
+/**
+ * Converts DOCX bytes to HTML.
+ * @param {Buffer|Uint8Array} docxBuffer - Raw .docx file bytes
+ * @param {{ embed?: boolean, noH4?: boolean, debugLayout?: boolean }} [options]
+ *   - embed: if true, returns embeddable fragment (no DOCTYPE/html wrapper)
+ *   - noH4: when true, bold from paragraph style is not applied to list items
+ *   - debugLayout: when true, adds colored borders for debugging
+ * @returns {string} HTML string
+ */
+export function docxToHtml(docxBuffer, options = {}) {
+  const { embed = false, noH4 = false, debugLayout = false } = options;
+  const arr = docxBuffer instanceof Uint8Array ? docxBuffer : new Uint8Array(docxBuffer);
+  return embed
+    ? convert_docx_embed(arr, noH4, debugLayout)
+    : convert_docx(arr, noH4, debugLayout);
+}
+
+/**
+ * Converts HTML (docx-html-converter format) to DOCX bytes.
+ * @param {string} html - HTML string (full document or embed fragment)
+ * @returns {Buffer} Raw .docx file bytes
+ */
+export function htmlToDocx(html) {
+  const result = convert_html_to_docx(html);
+  return Buffer.from(result);
+}
+
+/**
+ * Recalculates page breaks in HTML "Word-style".
+ * Use when the user edits text in a contentEditable div.
+ * @param {string} html - HTML string
+ * @returns {string} Reflowed HTML
+ */
+export { calculate_html };

package/node_modules/docx-html-converter/README.md

@@ -0,0 +1,118 @@
+# docx-html-converter
+
+Конвертер DOCX в HTML на Rust с поддержкой WASM. Преобразует документы Word в HTML с сохранением стилей, таблиц, списков, заголовков и колонтитулов. Верхний padding основного контента равен высоте зоны header (вычисляется после рендера колонтитулов).
+
+## Установка
+
+```bash
+npm install docx-html-converter
+```
+
+## API
+
+### `convert_docx(docx_buffer, no_h4?, debug_layout?)`
+
+Конвертирует DOCX в полный HTML-документ (DOCTYPE, html, head, body).
+
+- **docx_buffer** — `Uint8Array` с байтами .docx файла
+- **no_h4** — опционально; при `true` жирный из стиля параграфа (например, Heading 4) не применяется к элементам списка
+- **debug_layout** — опционально; при `true` добавляет яркие цветные рамки для отладки (красный=страница, зелёный=контент, синий=header, оранжевый=footer, фиолетовый=таблица)
+
+```javascript
+import { convert_docx } from 'docx-html-converter';
+
+const response = await fetch('/document.docx');
+const buffer = new Uint8Array(await response.arrayBuffer());
+const html = convert_docx(buffer);
+```
+
+### `convert_docx_embed(docx_buffer, no_h4?, debug_layout?)`
+
+Конвертирует DOCX в встраиваемый HTML-фрагмент (div со стилями, без обёртки документа). Подходит для вставки в существующую страницу. При `debug_layout: true` — цветные рамки для отладки (см. выше).
+
+Каждый div страницы (`.page`) имеет `id="document-docx-{номер}"` и атрибут `contenteditable` для редактирования на фронтенде.
+
+```javascript
+import { convert_docx_embed } from 'docx-html-converter';
+
+const embed = convert_docx_embed(buffer);
+document.getElementById('editor').innerHTML = embed;
+// Каждая страница: <div class="page" id="document-docx-1" contenteditable>...
+```
+
+### `calculate_html(html)`
+
+Пересчитывает разбиение на страницы в HTML «по-вордовски». Используйте при редактировании текста в contentEditable — передайте обновлённый HTML, чтобы получить переразбитый контент.
+
+```javascript
+import { convert_docx_embed, calculate_html } from 'docx-html-converter';
+
+const embed = convert_docx_embed(buffer);
+const container = document.getElementById('editor');
+container.innerHTML = embed;
+
+// Для пересчёта страниц нужен полный HTML: обёртка docx-html-embed + стили + страницы
+container.addEventListener('input', () => {
+  const htmlForRecalc = getHtmlForRecalculate(container);
+  const recalculated = calculate_html(htmlForRecalc);
+  container.innerHTML = recalculated;
+});
+
+/**
+ * Возвращает HTML, готовый для calculate_html.
+ * Нужен полный фрагмент: div.docx-html-embed + <style> + страницы.
+ * container — либо сам embed, либо родитель (например #editor).
+ */
+function getHtmlForRecalculate(container: HTMLElement): string {
+  const embed =
+    container.closest?.('.docx-html-embed') ??
+    container.querySelector?.('.docx-html-embed') ??
+    container;
+  return embed.outerHTML;
+}
+```
+
+## Сборка и запуск
+
+### DOCX → HTML (Rust)
+
+```bash
+cargo run                    # выбор .docx из src/files/
+cargo run -- file.docx       # указать файл
+```
+
+### HTML → DOCX
+
+```bash
+# Сначала: npm install в packages/html-docx-converter
+cd packages/html-docx-converter && npm install && cd ../..
+
+cargo run -- to-docx                    # выбор .html из списка
+cargo run -- to-docx output-embed.html   # указать файл
+```
+
+Результат сохраняется в `packages/html-docx-converter/files/docx_results/`.
+
+### npm (Node.js)
+
+```bash
+# Для bundler (webpack, vite и т.д.)
+npm run build
+
+# Для Node.js
+npm run build:node
+```
+
+## Rust
+
+Библиотека также доступна как Rust crate:
+
+```rust
+use docx_html_converter::{convert_docx_from_bytes, convert_docx_embed_from_bytes, calculate_html};
+
+let html = convert_docx_from_bytes(&docx_bytes, false, false)?;
+let embed = convert_docx_embed_from_bytes(&docx_bytes, false, false)?;
+// With debug layout (bright borders: red=page, green=content, blue=header, orange=footer, magenta=table):
+let embed_debug = convert_docx_embed_from_bytes(&docx_bytes, false, true)?;
+let recalculated = calculate_html(&embed)?;
+```

package/node_modules/docx-html-converter/docx_html_converter.d.ts

@@ -0,0 +1,29 @@
+/* tslint:disable */
+/* eslint-disable */
+
+/**
+ * Recalculates page breaks in HTML "Word-style". Call when the user edits text
+ * in a contentEditable div — pass the updated HTML to get reflowed pages.
+ */
+export function calculate_html(html: string): string;
+
+/**
+ * Converts DOCX bytes to HTML.
+ *
+ * * `docx_buffer` — Uint8Array with raw .docx file bytes
+ * * `no_h4` — optional; when true, bold from paragraph style is not applied to list items.
+ *   Omit or pass false for correct default behavior.
+ */
+export function convert_docx(docx_buffer: Uint8Array, no_h4?: boolean | null, debug_layout?: boolean | null): string;
+
+/**
+ * Converts DOCX bytes to an embeddable HTML fragment (div with styles, no document wrapper).
+ * Use when embedding into an existing page. Preserves all styles and fonts.
+ */
+export function convert_docx_embed(docx_buffer: Uint8Array, no_h4?: boolean | null, debug_layout?: boolean | null): string;
+
+/**
+ * Converts HTML (docx-html-converter format) to DOCX bytes.
+ * Returns Uint8Array with raw .docx file bytes.
+ */
+export function convert_html_to_docx(html: string): Uint8Array;

package/node_modules/docx-html-converter/docx_html_converter.js

@@ -0,0 +1,252 @@
+/* @ts-self-types="./docx_html_converter.d.ts" */
+
+/**
+ * Recalculates page breaks in HTML "Word-style". Call when the user edits text
+ * in a contentEditable div — pass the updated HTML to get reflowed pages.
+ * @param {string} html
+ * @returns {string}
+ */
+function calculate_html(html) {
+    let deferred3_0;
+    let deferred3_1;
+    try {
+        const ptr0 = passStringToWasm0(html, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.calculate_html(ptr0, len0);
+        var ptr2 = ret[0];
+        var len2 = ret[1];
+        if (ret[3]) {
+            ptr2 = 0; len2 = 0;
+            throw takeFromExternrefTable0(ret[2]);
+        }
+        deferred3_0 = ptr2;
+        deferred3_1 = len2;
+        return getStringFromWasm0(ptr2, len2);
+    } finally {
+        wasm.__wbindgen_free(deferred3_0, deferred3_1, 1);
+    }
+}
+exports.calculate_html = calculate_html;
+
+/**
+ * Converts DOCX bytes to HTML.
+ *
+ * * `docx_buffer` — Uint8Array with raw .docx file bytes
+ * * `no_h4` — optional; when true, bold from paragraph style is not applied to list items.
+ *   Omit or pass false for correct default behavior.
+ * @param {Uint8Array} docx_buffer
+ * @param {boolean | null} [no_h4]
+ * @param {boolean | null} [debug_layout]
+ * @returns {string}
+ */
+function convert_docx(docx_buffer, no_h4, debug_layout) {
+    let deferred3_0;
+    let deferred3_1;
+    try {
+        const ptr0 = passArray8ToWasm0(docx_buffer, wasm.__wbindgen_malloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.convert_docx(ptr0, len0, isLikeNone(no_h4) ? 0xFFFFFF : no_h4 ? 1 : 0, isLikeNone(debug_layout) ? 0xFFFFFF : debug_layout ? 1 : 0);
+        var ptr2 = ret[0];
+        var len2 = ret[1];
+        if (ret[3]) {
+            ptr2 = 0; len2 = 0;
+            throw takeFromExternrefTable0(ret[2]);
+        }
+        deferred3_0 = ptr2;
+        deferred3_1 = len2;
+        return getStringFromWasm0(ptr2, len2);
+    } finally {
+        wasm.__wbindgen_free(deferred3_0, deferred3_1, 1);
+    }
+}
+exports.convert_docx = convert_docx;
+
+/**
+ * Converts DOCX bytes to an embeddable HTML fragment (div with styles, no document wrapper).
+ * Use when embedding into an existing page. Preserves all styles and fonts.
+ * @param {Uint8Array} docx_buffer
+ * @param {boolean | null} [no_h4]
+ * @param {boolean | null} [debug_layout]
+ * @returns {string}
+ */
+function convert_docx_embed(docx_buffer, no_h4, debug_layout) {
+    let deferred3_0;
+    let deferred3_1;
+    try {
+        const ptr0 = passArray8ToWasm0(docx_buffer, wasm.__wbindgen_malloc);
+        const len0 = WASM_VECTOR_LEN;
+        const ret = wasm.convert_docx_embed(ptr0, len0, isLikeNone(no_h4) ? 0xFFFFFF : no_h4 ? 1 : 0, isLikeNone(debug_layout) ? 0xFFFFFF : debug_layout ? 1 : 0);
+        var ptr2 = ret[0];
+        var len2 = ret[1];
+        if (ret[3]) {
+            ptr2 = 0; len2 = 0;
+            throw takeFromExternrefTable0(ret[2]);
+        }
+        deferred3_0 = ptr2;
+        deferred3_1 = len2;
+        return getStringFromWasm0(ptr2, len2);
+    } finally {
+        wasm.__wbindgen_free(deferred3_0, deferred3_1, 1);
+    }
+}
+exports.convert_docx_embed = convert_docx_embed;
+
+/**
+ * Converts HTML (docx-html-converter format) to DOCX bytes.
+ * Returns Uint8Array with raw .docx file bytes.
+ * @param {string} html
+ * @returns {Uint8Array}
+ */
+function convert_html_to_docx(html) {
+    const ptr0 = passStringToWasm0(html, wasm.__wbindgen_malloc, wasm.__wbindgen_realloc);
+    const len0 = WASM_VECTOR_LEN;
+    const ret = wasm.convert_html_to_docx(ptr0, len0);
+    if (ret[3]) {
+        throw takeFromExternrefTable0(ret[2]);
+    }
+    var v2 = getArrayU8FromWasm0(ret[0], ret[1]).slice();
+    wasm.__wbindgen_free(ret[0], ret[1] * 1, 1);
+    return v2;
+}
+exports.convert_html_to_docx = convert_html_to_docx;
+
+function __wbg_get_imports() {
+    const import0 = {
+        __proto__: null,
+        __wbg_getRandomValues_3f44b700395062e5: function() { return handleError(function (arg0, arg1) {
+            globalThis.crypto.getRandomValues(getArrayU8FromWasm0(arg0, arg1));
+        }, arguments); },
+        __wbindgen_cast_0000000000000001: function(arg0, arg1) {
+            // Cast intrinsic for `Ref(String) -> Externref`.
+            const ret = getStringFromWasm0(arg0, arg1);
+            return ret;
+        },
+        __wbindgen_init_externref_table: function() {
+            const table = wasm.__wbindgen_externrefs;
+            const offset = table.grow(4);
+            table.set(0, undefined);
+            table.set(offset + 0, undefined);
+            table.set(offset + 1, null);
+            table.set(offset + 2, true);
+            table.set(offset + 3, false);
+        },
+    };
+    return {
+        __proto__: null,
+        "./docx_html_converter_bg.js": import0,
+    };
+}
+
+function addToExternrefTable0(obj) {
+    const idx = wasm.__externref_table_alloc();
+    wasm.__wbindgen_externrefs.set(idx, obj);
+    return idx;
+}
+
+function getArrayU8FromWasm0(ptr, len) {
+    ptr = ptr >>> 0;
+    return getUint8ArrayMemory0().subarray(ptr / 1, ptr / 1 + len);
+}
+
+function getStringFromWasm0(ptr, len) {
+    ptr = ptr >>> 0;
+    return decodeText(ptr, len);
+}
+
+let cachedUint8ArrayMemory0 = null;
+function getUint8ArrayMemory0() {
+    if (cachedUint8ArrayMemory0 === null || cachedUint8ArrayMemory0.byteLength === 0) {
+        cachedUint8ArrayMemory0 = new Uint8Array(wasm.memory.buffer);
+    }
+    return cachedUint8ArrayMemory0;
+}
+
+function handleError(f, args) {
+    try {
+        return f.apply(this, args);
+    } catch (e) {
+        const idx = addToExternrefTable0(e);
+        wasm.__wbindgen_exn_store(idx);
+    }
+}
+
+function isLikeNone(x) {
+    return x === undefined || x === null;
+}
+
+function passArray8ToWasm0(arg, malloc) {
+    const ptr = malloc(arg.length * 1, 1) >>> 0;
+    getUint8ArrayMemory0().set(arg, ptr / 1);
+    WASM_VECTOR_LEN = arg.length;
+    return ptr;
+}
+
+function passStringToWasm0(arg, malloc, realloc) {
+    if (realloc === undefined) {
+        const buf = cachedTextEncoder.encode(arg);
+        const ptr = malloc(buf.length, 1) >>> 0;
+        getUint8ArrayMemory0().subarray(ptr, ptr + buf.length).set(buf);
+        WASM_VECTOR_LEN = buf.length;
+        return ptr;
+    }
+
+    let len = arg.length;
+    let ptr = malloc(len, 1) >>> 0;
+
+    const mem = getUint8ArrayMemory0();
+
+    let offset = 0;
+
+    for (; offset < len; offset++) {
+        const code = arg.charCodeAt(offset);
+        if (code > 0x7F) break;
+        mem[ptr + offset] = code;
+    }
+    if (offset !== len) {
+        if (offset !== 0) {
+            arg = arg.slice(offset);
+        }
+        ptr = realloc(ptr, len, len = offset + arg.length * 3, 1) >>> 0;
+        const view = getUint8ArrayMemory0().subarray(ptr + offset, ptr + len);
+        const ret = cachedTextEncoder.encodeInto(arg, view);
+
+        offset += ret.written;
+        ptr = realloc(ptr, len, offset, 1) >>> 0;
+    }
+
+    WASM_VECTOR_LEN = offset;
+    return ptr;
+}
+
+function takeFromExternrefTable0(idx) {
+    const value = wasm.__wbindgen_externrefs.get(idx);
+    wasm.__externref_table_dealloc(idx);
+    return value;
+}
+
+let cachedTextDecoder = new TextDecoder('utf-8', { ignoreBOM: true, fatal: true });
+cachedTextDecoder.decode();
+function decodeText(ptr, len) {
+    return cachedTextDecoder.decode(getUint8ArrayMemory0().subarray(ptr, ptr + len));
+}
+
+const cachedTextEncoder = new TextEncoder();
+
+if (!('encodeInto' in cachedTextEncoder)) {
+    cachedTextEncoder.encodeInto = function (arg, view) {
+        const buf = cachedTextEncoder.encode(arg);
+        view.set(buf);
+        return {
+            read: arg.length,
+            written: buf.length
+        };
+    };
+}
+
+let WASM_VECTOR_LEN = 0;
+
+const wasmPath = `${__dirname}/docx_html_converter_bg.wasm`;
+const wasmBytes = require('fs').readFileSync(wasmPath);
+const wasmModule = new WebAssembly.Module(wasmBytes);
+let wasm = new WebAssembly.Instance(wasmModule, __wbg_get_imports()).exports;
+wasm.__wbindgen_start();

package/node_modules/docx-html-converter/package.json

@@ -0,0 +1,12 @@
+{
+  "name": "docx-html-converter",
+  "description": "Convert DOCX to HTML with styles, tables, lists. WASM + Rust. Includes calculate_html for contentEditable page recalculation.",
+  "version": "0.4.2",
+  "files": [
+    "docx_html_converter_bg.wasm",
+    "docx_html_converter.js",
+    "docx_html_converter.d.ts"
+  ],
+  "main": "docx_html_converter.js",
+  "types": "docx_html_converter.d.ts"
+}

package/package.json

@@ -0,0 +1,38 @@
+{
+  "name": "node-docx-html-converter",
+  "version": "0.1.0",
+  "description": "Convert DOCX ↔ HTML using Rust WASM. Two functions: docxToHtml and htmlToDocx.",
+  "type": "module",
+  "main": "index.cjs",
+  "module": "index.js",
+  "types": "index.d.ts",
+  "exports": {
+    ".": {
+      "import": "./index.js",
+      "require": "./index.cjs",
+      "types": "./index.d.ts"
+    }
+  },
+  "files": [
+    "index.js",
+    "index.cjs",
+    "index.d.ts"
+  ],
+  "scripts": {
+    "build": "cd .. && npm run build:node",
+    "prepublishOnly": "npm run build"
+  },
+  "dependencies": {
+    "docx-html-converter": "file:../pkg"
+  },
+  "bundledDependencies": [
+    "docx-html-converter"
+  ],
+  "keywords": [
+    "docx",
+    "html",
+    "converter",
+    "word"
+  ],
+  "license": "MIT"
+}