office-oxide-wasm 0.1.0

package/bundler/office_oxide_bg.wasm.d.ts

@@ -0,0 +1,14 @@
+/* tslint:disable */
+/* eslint-disable */
+export const memory: WebAssembly.Memory;
+export const __wbg_wasmdocument_free: (a: number, b: number) => void;
+export const wasmdocument_formatName: (a: number, b: number) => void;
+export const wasmdocument_new: (a: number, b: number, c: number, d: number, e: number) => void;
+export const wasmdocument_plainText: (a: number, b: number) => void;
+export const wasmdocument_toHtml: (a: number, b: number) => void;
+export const wasmdocument_toIr: (a: number, b: number) => void;
+export const wasmdocument_toMarkdown: (a: number, b: number) => void;
+export const __wbindgen_export: (a: number, b: number) => number;
+export const __wbindgen_export2: (a: number, b: number, c: number, d: number) => number;
+export const __wbindgen_add_to_stack_pointer: (a: number) => number;
+export const __wbindgen_export3: (a: number, b: number, c: number) => void;

package/node/office_oxide.d.ts

@@ -0,0 +1,34 @@
+/* tslint:disable */
+/* eslint-disable */
+
+/**
+ * A parsed Office document for use in JavaScript/WASM.
+ */
+export class WasmDocument {
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Return the format name: "docx", "xlsx", or "pptx".
+     */
+    formatName(): string;
+    /**
+     * Create a new document from raw bytes and a format string ("docx", "xlsx", "pptx").
+     */
+    constructor(data: Uint8Array, format: string);
+    /**
+     * Extract plain text from the document.
+     */
+    plainText(): string;
+    /**
+     * Convert the document to an HTML fragment.
+     */
+    toHtml(): string;
+    /**
+     * Convert the document to a JSON IR representation.
+     */
+    toIr(): any;
+    /**
+     * Convert the document to markdown.
+     */
+    toMarkdown(): string;
+}

package/node/office_oxide.js

@@ -0,0 +1,318 @@
+/* @ts-self-types="./office_oxide.d.ts" */
+
+/**
+ * A parsed Office document for use in JavaScript/WASM.
+ */
+class WasmDocument {
+    __destroy_into_raw() {
+        const ptr = this.__wbg_ptr;
+        this.__wbg_ptr = 0;
+        WasmDocumentFinalization.unregister(this);
+        return ptr;
+    }
+    free() {
+        const ptr = this.__destroy_into_raw();
+        wasm.__wbg_wasmdocument_free(ptr, 0);
+    }
+    /**
+     * Return the format name: "docx", "xlsx", or "pptx".
+     * @returns {string}
+     */
+    formatName() {
+        let deferred1_0;
+        let deferred1_1;
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.wasmdocument_formatName(retptr, this.__wbg_ptr);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            deferred1_0 = r0;
+            deferred1_1 = r1;
+            return getStringFromWasm0(r0, r1);
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+            wasm.__wbindgen_export3(deferred1_0, deferred1_1, 1);
+        }
+    }
+    /**
+     * Create a new document from raw bytes and a format string ("docx", "xlsx", "pptx").
+     * @param {Uint8Array} data
+     * @param {string} format
+     */
+    constructor(data, format) {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            const ptr0 = passArray8ToWasm0(data, wasm.__wbindgen_export);
+            const len0 = WASM_VECTOR_LEN;
+            const ptr1 = passStringToWasm0(format, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+            const len1 = WASM_VECTOR_LEN;
+            wasm.wasmdocument_new(retptr, ptr0, len0, ptr1, len1);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
+            if (r2) {
+                throw takeObject(r1);
+            }
+            this.__wbg_ptr = r0 >>> 0;
+            WasmDocumentFinalization.register(this, this.__wbg_ptr, this);
+            return this;
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+     * Extract plain text from the document.
+     * @returns {string}
+     */
+    plainText() {
+        let deferred1_0;
+        let deferred1_1;
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.wasmdocument_plainText(retptr, this.__wbg_ptr);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            deferred1_0 = r0;
+            deferred1_1 = r1;
+            return getStringFromWasm0(r0, r1);
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+            wasm.__wbindgen_export3(deferred1_0, deferred1_1, 1);
+        }
+    }
+    /**
+     * Convert the document to an HTML fragment.
+     * @returns {string}
+     */
+    toHtml() {
+        let deferred1_0;
+        let deferred1_1;
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.wasmdocument_toHtml(retptr, this.__wbg_ptr);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            deferred1_0 = r0;
+            deferred1_1 = r1;
+            return getStringFromWasm0(r0, r1);
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+            wasm.__wbindgen_export3(deferred1_0, deferred1_1, 1);
+        }
+    }
+    /**
+     * Convert the document to a JSON IR representation.
+     * @returns {any}
+     */
+    toIr() {
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.wasmdocument_toIr(retptr, this.__wbg_ptr);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            var r2 = getDataViewMemory0().getInt32(retptr + 4 * 2, true);
+            if (r2) {
+                throw takeObject(r1);
+            }
+            return takeObject(r0);
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+        }
+    }
+    /**
+     * Convert the document to markdown.
+     * @returns {string}
+     */
+    toMarkdown() {
+        let deferred1_0;
+        let deferred1_1;
+        try {
+            const retptr = wasm.__wbindgen_add_to_stack_pointer(-16);
+            wasm.wasmdocument_toMarkdown(retptr, this.__wbg_ptr);
+            var r0 = getDataViewMemory0().getInt32(retptr + 4 * 0, true);
+            var r1 = getDataViewMemory0().getInt32(retptr + 4 * 1, true);
+            deferred1_0 = r0;
+            deferred1_1 = r1;
+            return getStringFromWasm0(r0, r1);
+        } finally {
+            wasm.__wbindgen_add_to_stack_pointer(16);
+            wasm.__wbindgen_export3(deferred1_0, deferred1_1, 1);
+        }
+    }
+}
+if (Symbol.dispose) WasmDocument.prototype[Symbol.dispose] = WasmDocument.prototype.free;
+exports.WasmDocument = WasmDocument;
+
+function __wbg_get_imports() {
+    const import0 = {
+        __proto__: null,
+        __wbg_String_8564e559799eccda: function(arg0, arg1) {
+            const ret = String(getObject(arg1));
+            const ptr1 = passStringToWasm0(ret, wasm.__wbindgen_export, wasm.__wbindgen_export2);
+            const len1 = WASM_VECTOR_LEN;
+            getDataViewMemory0().setInt32(arg0 + 4 * 1, len1, true);
+            getDataViewMemory0().setInt32(arg0 + 4 * 0, ptr1, true);
+        },
+        __wbg___wbindgen_throw_6ddd609b62940d55: function(arg0, arg1) {
+            throw new Error(getStringFromWasm0(arg0, arg1));
+        },
+        __wbg_new_a70fbab9066b301f: function() {
+            const ret = new Array();
+            return addHeapObject(ret);
+        },
+        __wbg_new_ab79df5bd7c26067: function() {
+            const ret = new Object();
+            return addHeapObject(ret);
+        },
+        __wbg_set_282384002438957f: function(arg0, arg1, arg2) {
+            getObject(arg0)[arg1 >>> 0] = takeObject(arg2);
+        },
+        __wbg_set_6be42768c690e380: function(arg0, arg1, arg2) {
+            getObject(arg0)[takeObject(arg1)] = takeObject(arg2);
+        },
+        __wbindgen_cast_0000000000000001: function(arg0) {
+            // Cast intrinsic for `F64 -> Externref`.
+            const ret = arg0;
+            return addHeapObject(ret);
+        },
+        __wbindgen_cast_0000000000000002: function(arg0, arg1) {
+            // Cast intrinsic for `Ref(String) -> Externref`.
+            const ret = getStringFromWasm0(arg0, arg1);
+            return addHeapObject(ret);
+        },
+        __wbindgen_object_clone_ref: function(arg0) {
+            const ret = getObject(arg0);
+            return addHeapObject(ret);
+        },
+        __wbindgen_object_drop_ref: function(arg0) {
+            takeObject(arg0);
+        },
+    };
+    return {
+        __proto__: null,
+        "./office_oxide_bg.js": import0,
+    };
+}
+
+const WasmDocumentFinalization = (typeof FinalizationRegistry === 'undefined')
+    ? { register: () => {}, unregister: () => {} }
+    : new FinalizationRegistry(ptr => wasm.__wbg_wasmdocument_free(ptr >>> 0, 1));
+
+function addHeapObject(obj) {
+    if (heap_next === heap.length) heap.push(heap.length + 1);
+    const idx = heap_next;
+    heap_next = heap[idx];
+
+    heap[idx] = obj;
+    return idx;
+}
+
+function dropObject(idx) {
+    if (idx < 1028) return;
+    heap[idx] = heap_next;
+    heap_next = idx;
+}
+
+let cachedDataViewMemory0 = null;
+function getDataViewMemory0() {
+    if (cachedDataViewMemory0 === null || cachedDataViewMemory0.buffer.detached === true || (cachedDataViewMemory0.buffer.detached === undefined && cachedDataViewMemory0.buffer !== wasm.memory.buffer)) {
+        cachedDataViewMemory0 = new DataView(wasm.memory.buffer);
+    }
+    return cachedDataViewMemory0;
+}
+
+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 getObject(idx) { return heap[idx]; }
+
+let heap = new Array(1024).fill(undefined);
+heap.push(undefined, null, true, false);
+
+let heap_next = heap.length;
+
+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 takeObject(idx) {
+    const ret = getObject(idx);
+    dropObject(idx);
+    return ret;
+}
+
+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}/office_oxide_bg.wasm`;
+const wasmBytes = require('fs').readFileSync(wasmPath);
+const wasmModule = new WebAssembly.Module(wasmBytes);
+let wasm = new WebAssembly.Instance(wasmModule, __wbg_get_imports()).exports;

package/node/office_oxide_bg.wasm.d.ts

@@ -0,0 +1,14 @@
+/* tslint:disable */
+/* eslint-disable */
+export const memory: WebAssembly.Memory;
+export const __wbg_wasmdocument_free: (a: number, b: number) => void;
+export const wasmdocument_formatName: (a: number, b: number) => void;
+export const wasmdocument_new: (a: number, b: number, c: number, d: number, e: number) => void;
+export const wasmdocument_plainText: (a: number, b: number) => void;
+export const wasmdocument_toHtml: (a: number, b: number) => void;
+export const wasmdocument_toIr: (a: number, b: number) => void;
+export const wasmdocument_toMarkdown: (a: number, b: number) => void;
+export const __wbindgen_export: (a: number, b: number) => number;
+export const __wbindgen_export2: (a: number, b: number, c: number, d: number) => number;
+export const __wbindgen_add_to_stack_pointer: (a: number) => number;
+export const __wbindgen_export3: (a: number, b: number, c: number) => void;

package/package.json

@@ -0,0 +1,95 @@
+{
+  "name": "office-oxide-wasm",
+  "version": "0.1.0",
+  "description": "Fast Office document processing (DOCX/XLSX/PPTX/DOC/XLS/PPT) compiled to WebAssembly. Rust core, zero JS dependencies. Works in Node.js, bundlers, and browsers.",
+  "license": "MIT OR Apache-2.0",
+  "author": "Yury Fedoseev",
+  "repository": {
+    "type": "git",
+    "url": "git+https://github.com/yfedoseev/office_oxide.git"
+  },
+  "homepage": "https://oxide.fyi",
+  "bugs": {
+    "url": "https://github.com/yfedoseev/office_oxide/issues"
+  },
+  "engines": {
+    "node": ">=18"
+  },
+  "type": "module",
+  "main": "./node/office_oxide.js",
+  "module": "./bundler/office_oxide.js",
+  "browser": "./web/office_oxide.js",
+  "types": "./bundler/office_oxide.d.ts",
+  "exports": {
+    ".": {
+      "types": "./bundler/office_oxide.d.ts",
+      "node": {
+        "require": "./node/office_oxide.js",
+        "default": "./node/office_oxide.js"
+      },
+      "browser": {
+        "import": "./web/office_oxide.js",
+        "default": "./web/office_oxide.js"
+      },
+      "import": "./bundler/office_oxide.js",
+      "default": "./bundler/office_oxide.js"
+    },
+    "./node": {
+      "types": "./node/office_oxide.d.ts",
+      "default": "./node/office_oxide.js"
+    },
+    "./web": {
+      "types": "./web/office_oxide.d.ts",
+      "default": "./web/office_oxide.js"
+    },
+    "./bundler": {
+      "types": "./bundler/office_oxide.d.ts",
+      "default": "./bundler/office_oxide.js"
+    },
+    "./package.json": "./package.json"
+  },
+  "sideEffects": [
+    "./web/office_oxide.js",
+    "./bundler/office_oxide.js"
+  ],
+  "files": [
+    "node/office_oxide.js",
+    "node/office_oxide.d.ts",
+    "node/office_oxide_bg.wasm",
+    "node/office_oxide_bg.wasm.d.ts",
+    "bundler/office_oxide.js",
+    "bundler/office_oxide_bg.js",
+    "bundler/office_oxide.d.ts",
+    "bundler/office_oxide_bg.wasm",
+    "bundler/office_oxide_bg.wasm.d.ts",
+    "web/office_oxide.js",
+    "web/office_oxide.d.ts",
+    "web/office_oxide_bg.wasm",
+    "web/office_oxide_bg.wasm.d.ts",
+    "README.md",
+    "LICENSE-MIT",
+    "LICENSE-APACHE"
+  ],
+  "keywords": [
+    "docx",
+    "xlsx",
+    "pptx",
+    "doc",
+    "xls",
+    "ppt",
+    "office",
+    "wasm",
+    "webassembly",
+    "text-extraction",
+    "document-parser",
+    "rust",
+    "rust-wasm",
+    "serverless",
+    "node",
+    "browser",
+    "zero-dependency",
+    "typescript",
+    "esm",
+    "cjs"
+  ]
+}

package/web/office_oxide.d.ts

@@ -0,0 +1,73 @@
+/* tslint:disable */
+/* eslint-disable */
+
+/**
+ * A parsed Office document for use in JavaScript/WASM.
+ */
+export class WasmDocument {
+    free(): void;
+    [Symbol.dispose](): void;
+    /**
+     * Return the format name: "docx", "xlsx", or "pptx".
+     */
+    formatName(): string;
+    /**
+     * Create a new document from raw bytes and a format string ("docx", "xlsx", "pptx").
+     */
+    constructor(data: Uint8Array, format: string);
+    /**
+     * Extract plain text from the document.
+     */
+    plainText(): string;
+    /**
+     * Convert the document to an HTML fragment.
+     */
+    toHtml(): string;
+    /**
+     * Convert the document to a JSON IR representation.
+     */
+    toIr(): any;
+    /**
+     * Convert the document to markdown.
+     */
+    toMarkdown(): string;
+}
+
+export type InitInput = RequestInfo | URL | Response | BufferSource | WebAssembly.Module;
+
+export interface InitOutput {
+    readonly memory: WebAssembly.Memory;
+    readonly __wbg_wasmdocument_free: (a: number, b: number) => void;
+    readonly wasmdocument_formatName: (a: number, b: number) => void;
+    readonly wasmdocument_new: (a: number, b: number, c: number, d: number, e: number) => void;
+    readonly wasmdocument_plainText: (a: number, b: number) => void;
+    readonly wasmdocument_toHtml: (a: number, b: number) => void;
+    readonly wasmdocument_toIr: (a: number, b: number) => void;
+    readonly wasmdocument_toMarkdown: (a: number, b: number) => void;
+    readonly __wbindgen_export: (a: number, b: number) => number;
+    readonly __wbindgen_export2: (a: number, b: number, c: number, d: number) => number;
+    readonly __wbindgen_add_to_stack_pointer: (a: number) => number;
+    readonly __wbindgen_export3: (a: number, b: number, c: number) => void;
+}
+
+export type SyncInitInput = BufferSource | WebAssembly.Module;
+
+/**
+ * Instantiates the given `module`, which can either be bytes or
+ * a precompiled `WebAssembly.Module`.
+ *
+ * @param {{ module: SyncInitInput }} module - Passing `SyncInitInput` directly is deprecated.
+ *
+ * @returns {InitOutput}
+ */
+export function initSync(module: { module: SyncInitInput } | SyncInitInput): InitOutput;
+
+/**
+ * If `module_or_path` is {RequestInfo} or {URL}, makes a request and
+ * for everything else, calls `WebAssembly.instantiate` directly.
+ *
+ * @param {{ module_or_path: InitInput | Promise<InitInput> }} module_or_path - Passing `InitInput` directly is deprecated.
+ *
+ * @returns {Promise<InitOutput>}
+ */
+export default function __wbg_init (module_or_path?: { module_or_path: InitInput | Promise<InitInput> } | InitInput | Promise<InitInput>): Promise<InitOutput>;