javascript - 将 JavaScript 字符串传递给编译为 WebAssembly 的 Rust 函数

Question

我有这个简单的 Rust 函数:

#[no_mangle]
pub fn compute(operator: &str, n1: i32, n2: i32) -> i32 {
    match operator {
        "SUM" => n1 + n2,
        "DIFF" => n1 - n2,
        "MULT" => n1 * n2,
        "DIV" => n1 / n2,
        _ => 0
    }
}

我正在成功地将其编译为 WebAssembly，但无法将 operator 参数从 JS 传递给 Rust。

调用 Rust 函数的 JS 行如下所示:

instance.exports.compute(operator, n1, n2);

operator是一个JS String和n1,n2是JS Number

n1 和 n2 被正确传递并且可以在编译函数中读取，所以我猜问题是我如何传递字符串。我想它是作为一个指针从 JS 传递到 WebAssembly，但找不到关于它如何工作的证据或 Material 。

我没有使用 Emscripten 并希望它保持独立(编译目标 wasm32-unknown-unknown)，但我看到他们将编译后的函数包装在 Module.cwrap，也许这会有所帮助？

Answer 1

最简单和最惯用的解决方案

大多数人应该使用wasm-bindgen ，这让整个过程变得简单多了!

低级手动实现

要在 JavaScript 和 Rust 之间传输字符串数据，您需要决定

1. 文本的编码:UTF-8(Rust 原生)或 UTF-16(JS 原生)。
2. 谁将拥有内存缓冲区:JS(调用者)或 Rust(被调用者)。
3. 如何表示字符串数据和长度:NUL 终止(C 风格)或不同长度(Rust 风格)。
4. 如果数据和长度是分开的，如何传达它们。

通用设置

为 WASM 构建 C dylibs 以帮助它们更小是很重要的。

Cargo.toml

[package]
name = "quick-maths"
version = "0.1.0"
authors = ["An Devloper <an.devloper@example.com>"]

[lib]
crate-type = ["cdylib"]

.cargo/config

[target.wasm32-unknown-unknown]
rustflags = [
    "-C", "link-args=--import-memory",
]

package.json

{
  "name": "quick-maths",
  "version": "0.1.0",
  "main": "index.js",
  "author": "An Devloper <an.devloper@example.com>",
  "license": "MIT",
  "scripts": {
    "example": "node ./index.js"
  },
  "dependencies": {
    "fs-extra": "^8.0.1",
    "text-encoding": "^0.7.0"
  }
}

我正在使用 NodeJS 12.1.0。

执行

$ rustup component add rust-std --target wasm32-unknown-unknown
$ cargo build --release --target wasm32-unknown-unknown

方案一

我决定:

1. 将JS字符串转为UTF-8，即 TextEncoder JS API 是最合适的。
2. 调用者应该拥有内存缓冲区。
3. 让长度成为一个单独的值。
4. 应该进行另一个结构和分配来保存指针和长度。

lib/src.rs

// A struct with a known memory layout that we can pass string information in
#[repr(C)]
pub struct JsInteropString {
    data: *const u8,
    len: usize,
}

// Our FFI shim function    
#[no_mangle]
pub unsafe extern "C" fn compute(s: *const JsInteropString, n1: i32, n2: i32) -> i32 {
    // Check for NULL (see corresponding comment in JS)
    let s = match s.as_ref() {
        Some(s) => s,
        None => return -1,
    };

    // Convert the pointer and length to a `&[u8]`.
    let data = std::slice::from_raw_parts(s.data, s.len);

    // Convert the `&[u8]` to a `&str`    
    match std::str::from_utf8(data) {
        Ok(s) => real_code::compute(s, n1, n2),
        Err(_) => -2,
    }
}

// I advocate that you keep your interesting code in a different
// crate for easy development and testing. Have a separate crate
// with the FFI shims.
mod real_code {
    pub fn compute(operator: &str, n1: i32, n2: i32) -> i32 {
        match operator {
            "SUM"  => n1 + n2,
            "DIFF" => n1 - n2,
            "MULT" => n1 * n2,
            "DIV"  => n1 / n2,
            _ => 0,
        }
    }
}

index.js

const fs = require('fs-extra');
const { TextEncoder } = require('text-encoding');

// Allocate some memory.
const memory = new WebAssembly.Memory({ initial: 20, maximum: 100 });

// Connect these memory regions to the imported module
const importObject = {
  env: { memory }
};

// Create an object that handles converting our strings for us
const memoryManager = (memory) => {
  var base = 0;

  // NULL is conventionally at address 0, so we "use up" the first 4
  // bytes of address space to make our lives a bit simpler.
  base += 4;

  return {
    encodeString: (jsString) => {
      // Convert the JS String to UTF-8 data
      const encoder = new TextEncoder();
      const encodedString = encoder.encode(jsString);

      // Organize memory with space for the JsInteropString at the
      // beginning, followed by the UTF-8 string bytes.
      const asU32 = new Uint32Array(memory.buffer, base, 2);
      const asBytes = new Uint8Array(memory.buffer, asU32.byteOffset + asU32.byteLength, encodedString.length);

      // Copy the UTF-8 into the WASM memory.
      asBytes.set(encodedString);

      // Assign the data pointer and length values.
      asU32[0] = asBytes.byteOffset;
      asU32[1] = asBytes.length;

      // Update our memory allocator base address for the next call
      const originalBase = base;
      base += asBytes.byteOffset + asBytes.byteLength;

      return originalBase;
    }
  };
};

const myMemory = memoryManager(memory);

fs.readFile('./target/wasm32-unknown-unknown/release/quick_maths.wasm')
  .then(bytes => WebAssembly.instantiate(bytes, importObject))
  .then(({ instance }) => {
    const argString = "MULT";
    const argN1 = 42;
    const argN2 = 100;

    const s = myMemory.encodeString(argString);
    const result = instance.exports.compute(s, argN1, argN2);

    console.log(result);
  });

执行

$ yarn run example
4200

解决方案2

我决定:

1. 将JS字符串转为UTF-8，即 TextEncoder JS API 是最合适的。
2. 模块应该拥有内存缓冲区。
3. 让长度成为一个单独的值。
4. 使用Box<String>作为底层数据结构。这允许 Rust 代码进一步使用分配。

src/lib.rs

// Very important to use `transparent` to prevent ABI issues
#[repr(transparent)]
pub struct JsInteropString(*mut String);

impl JsInteropString {
    // Unsafe because we create a string and say it's full of valid
    // UTF-8 data, but it isn't!
    unsafe fn with_capacity(cap: usize) -> Self {
        let mut d = Vec::with_capacity(cap);
        d.set_len(cap);
        let s = Box::new(String::from_utf8_unchecked(d));
        JsInteropString(Box::into_raw(s))
    }

    unsafe fn as_string(&self) -> &String {
        &*self.0
    }

    unsafe fn as_mut_string(&mut self) -> &mut String {
        &mut *self.0
    }

    unsafe fn into_boxed_string(self) -> Box<String> {
        Box::from_raw(self.0)
    }

    unsafe fn as_mut_ptr(&mut self) -> *mut u8 {
        self.as_mut_string().as_mut_vec().as_mut_ptr()
    }
}

#[no_mangle]
pub unsafe extern "C" fn stringPrepare(cap: usize) -> JsInteropString {
    JsInteropString::with_capacity(cap)
}

#[no_mangle]
pub unsafe extern "C" fn stringData(mut s: JsInteropString) -> *mut u8 {
    s.as_mut_ptr()
}

#[no_mangle]
pub unsafe extern "C" fn stringLen(s: JsInteropString) -> usize {
    s.as_string().len()
}

#[no_mangle]
pub unsafe extern "C" fn compute(s: JsInteropString, n1: i32, n2: i32) -> i32 {
    let s = s.into_boxed_string();
    real_code::compute(&s, n1, n2)
}

mod real_code {
    pub fn compute(operator: &str, n1: i32, n2: i32) -> i32 {
        match operator {
            "SUM"  => n1 + n2,
            "DIFF" => n1 - n2,
            "MULT" => n1 * n2,
            "DIV"  => n1 / n2,
            _ => 0,
        }
    }
}

index.js

const fs = require('fs-extra');
const { TextEncoder } = require('text-encoding');

class QuickMaths {
  constructor(instance) {
    this.instance = instance;
  }

  difference(n1, n2) {
    const { compute } = this.instance.exports;
    const op = this.copyJsStringToRust("DIFF");
    return compute(op, n1, n2);
  }

  copyJsStringToRust(jsString) {
    const { memory, stringPrepare, stringData, stringLen } = this.instance.exports;

    const encoder = new TextEncoder();
    const encodedString = encoder.encode(jsString);

    // Ask Rust code to allocate a string inside of the module's memory
    const rustString = stringPrepare(encodedString.length);

    // Get a JS view of the string data
    const rustStringData = stringData(rustString);
    const asBytes = new Uint8Array(memory.buffer, rustStringData, encodedString.length);

    // Copy the UTF-8 into the WASM memory.
    asBytes.set(encodedString);

    return rustString;
  }
}

async function main() {
  const bytes = await fs.readFile('./target/wasm32-unknown-unknown/release/quick_maths.wasm');
  const { instance } = await WebAssembly.instantiate(bytes);
  const maffs = new QuickMaths(instance);

  console.log(maffs.difference(100, 201));
}

main();

执行

$ yarn run example
-101

---

请注意，此过程可用于其他类型。您“只需”决定如何将数据表示为双方同意的一组字节，然后将其发送。

另见:

• Using the WebAssembly JavaScript API
• TextEncoder API
• Uint8Array / Uint32Array / TypedArray
• WebAssembly.Memory
• Hello, Rust! — Import memory buffer
• How to return a string (or similar) from Rust in WebAssembly?