emscripten学习

what

emscripten是一个c/cpp的编译器，可以将c/cpp代码用 LLVM，编译为 WebAssembly。其中emcc 是他的cli，类似于常用的makefile的作用。

编译产物

可选的比较多 html js wasm 都可以自由组合

js产物源码解读

使用emcc 对一个c文件进行编译会产出一个js文件和一个wasm文件。js文件中的源码完全兼容了node环境和web环境，本部分仅讨论web环境。

if (ENVIRONMENT_IS_WEB || ENVIRONMENT_IS_WORKER) {
  if (ENVIRONMENT_IS_WORKER) { // Check worker, not web, since window could be polyfilled
    scriptDirectory = self.location.href;
  } else if (typeof document !== 'undefined' && document.currentScript) { // web
    scriptDirectory = document.currentScript.src;
  }
  // blob urls look like blob:http://site.com/etc/etc and we cannot infer anything from them.
  // otherwise, slice off the final part of the url to find the script directory.
  // if scriptDirectory does not contain a slash, lastIndexOf will return -1,
  // and scriptDirectory will correctly be replaced with an empty string.
  if (scriptDirectory.indexOf('blob:') !== 0) {
    scriptDirectory = scriptDirectory.substr(0, scriptDirectory.lastIndexOf('/')+1);
  } else {
    scriptDirectory = '';
  }

  // Differentiate the Web Worker from the Node Worker case, as reading must
  // be done differently.
  {

// include: web_or_worker_shell_read.js


  read_ = function shell_read(url) {
      var xhr = new XMLHttpRequest();
      xhr.open('GET', url, false);
      xhr.send(null);
      return xhr.responseText;
  };

  if (ENVIRONMENT_IS_WORKER) {
    readBinary = function readBinary(url) {
        var xhr = new XMLHttpRequest();
        xhr.open('GET', url, false);
        xhr.responseType = 'arraybuffer';
        xhr.send(null);
        return new Uint8Array(/** @type{!ArrayBuffer} */(xhr.response));
    };
  }

  readAsync = function readAsync(url, onload, onerror) {
    var xhr = new XMLHttpRequest();
    xhr.open('GET', url, true);
    xhr.responseType = 'arraybuffer';
    xhr.onload = function xhr_onload() {
      if (xhr.status == 200 || (xhr.status == 0 && xhr.response)) { // file URLs can return 0
        onload(xhr.response);
        return;
      }
      onerror();
    };
    xhr.onerror = onerror;
    xhr.send(null);
  };

// end include: web_or_worker_shell_read.js
  }

  setWindowTitle = function(title) { document.title = title };
} else
{
  throw new Error('environment detection error');
}

以上为em 构建的在web中的文件系统

如何改造em输出的模块
em会取全局的Module对象 并且支持Module对象的改造，可以通过这个方式改写em中的

em中的一些常用函数
js中定义了常用的工具函数，比如如何通过方法名访问c模块或者c函数，c与js中数据类型的转换
这部分其实就是https://emscripten.org/docs/a...的内容

em js的生命周期

function preRun() {

  if (Module['preRun']) {
    if (typeof Module['preRun'] == 'function') Module['preRun'] = [Module['preRun']];
    while (Module['preRun'].length) {
      addOnPreRun(Module['preRun'].shift());
    }
  }

  callRuntimeCallbacks(__ATPRERUN__);
}

function initRuntime() {
  checkStackCookie();
  assert(!runtimeInitialized);
  runtimeInitialized = true;
  if (!Module["noFSInit"] && !FS.init.initialized) FS.init();
TTY.init();
  callRuntimeCallbacks(__ATINIT__);
}

function preMain() {
  checkStackCookie();
  FS.ignorePermissions = false;
  callRuntimeCallbacks(__ATMAIN__);
}

function exitRuntime() {
  checkStackCookie();
  runtimeExited = true;
}

这里可以增加在asm运行中的钩子函数

核心函数createWasm

function createWasm() {
  // prepare imports
  var info = {
    'env': asmLibraryArg,
    'wasi_snapshot_preview1': asmLibraryArg,
  };
  // Load the wasm module and create an instance of using native support in the JS engine.
  // handle a generated wasm instance, receiving its exports and
  // performing other necessary setup
  /** @param {WebAssembly.Module=} module*/
  function receiveInstance(instance, module) {
    var exports = instance.exports;

    Module['asm'] = exports;

    wasmMemory = Module['asm']['memory'];
    assert(wasmMemory, "memory not found in wasm exports");
    // This assertion doesn't hold when emscripten is run in --post-link
    // mode.
    // TODO(sbc): Read INITIAL_MEMORY out of the wasm file in post-link mode.
    //assert(wasmMemory.buffer.byteLength === 16777216);
    updateGlobalBufferAndViews(wasmMemory.buffer);

    wasmTable = Module['asm']['__indirect_function_table'];
    assert(wasmTable, "table not found in wasm exports");

    removeRunDependency('wasm-instantiate');
  }
  // we can't run yet (except in a pthread, where we have a custom sync instantiator)
  addRunDependency('wasm-instantiate');

  // Async compilation can be confusing when an error on the page overwrites Module
  // (for example, if the order of elements is wrong, and the one defining Module is
  // later), so we save Module and check it later.
  var trueModule = Module;
  function receiveInstantiatedSource(output) {
    // 'output' is a WebAssemblyInstantiatedSource object which has both the module and instance.
    // receiveInstance() will swap in the exports (to Module.asm) so they can be called
    assert(Module === trueModule, 'the Module object should not be replaced during async compilation - perhaps the order of HTML elements is wrong?');
    trueModule = null;
    // TODO: Due to Closure regression https://github.com/google/closure-compiler/issues/3193, the above line no longer optimizes out down to the following line.
    // When the regression is fixed, can restore the above USE_PTHREADS-enabled path.
    receiveInstance(output['instance']);
  }

  function instantiateArrayBuffer(receiver) {
    return getBinaryPromise().then(function(binary) {
      return WebAssembly.instantiate(binary, info);
    }).then(receiver, function(reason) {
      err('failed to asynchronously prepare wasm: ' + reason);

      abort(reason);
    });
  }

  // Prefer streaming instantiation if available.
  function instantiateAsync() {
    if (!wasmBinary &&
        typeof WebAssembly.instantiateStreaming === 'function' &&
        !isDataURI(wasmBinaryFile) &&
        // Don't use streaming for file:// delivered objects in a webview, fetch them synchronously.
        !isFileURI(wasmBinaryFile) &&
        typeof fetch === 'function') {
      return fetch(wasmBinaryFile, { credentials: 'same-origin' }).then(function (response) {
        var result = WebAssembly.instantiateStreaming(response, info);
        return result.then(receiveInstantiatedSource, function(reason) {
            // We expect the most common failure cause to be a bad MIME type for the binary,
            // in which case falling back to ArrayBuffer instantiation should work.
            err('wasm streaming compile failed: ' + reason);
            err('falling back to ArrayBuffer instantiation');
            return instantiateArrayBuffer(receiveInstantiatedSource);
          });
      });
    } else {
      return instantiateArrayBuffer(receiveInstantiatedSource);
    }
  }

  // User shell pages can write their own Module.instantiateWasm = function(imports, successCallback) callback
  // to manually instantiate the Wasm module themselves. This allows pages to run the instantiation parallel
  // to any other async startup actions they are performing.
  if (Module['instantiateWasm']) {
    try {
      var exports = Module['instantiateWasm'](info, receiveInstance);
      return exports;
    } catch(e) {
      err('Module.instantiateWasm callback failed with error: ' + e);
      return false;
    }
  }

  instantiateAsync();
  return {}; // no exports yet; we'll fill them in later
}

加载wasm文件，这里主要是进行了初始化的申明 包含了内存空间的申明和依赖的注入，这里都是由em自动管理的

关注点 wasm的加载 看到源码中wasm文件都是远程加载的 此时我们需要替换我们的wasm文件到cdn上，我们需要增加Module['locateFile'] 保证我们的wasm 可以指向我们需要的地址

var wasmBinaryFile = 'xxx.wasm';
if (!isDataURI(wasmBinaryFile)) {//dataurl 判断 这里只要不是base64的都会为true
  wasmBinaryFile = locateFile(wasmBinaryFile);
}

// `/` should be present at the end if `scriptDirectory` is not empty
var scriptDirectory = '';
function locateFile(path) {
  if (Module['locateFile']) {
    return Module['locateFile'](path, scriptDirectory);
  }
  return scriptDirectory + path;
}

if (ENVIRONMENT_IS_WORKER) { // Check worker, not web, since window could be polyfilled
    scriptDirectory = self.location.href;
  } else if (typeof document !== 'undefined' && document.currentScript) { // web
    scriptDirectory = document.currentScript.src;
  }
//scriptDirectory就是脚本的src  不过这个不重要 Module['locateFile']可以从入参中获取

执行完数createWasm 我们就获得了一个promise

源码中还有关键的函数钩子 Module.instantiateWasm 我们可以在这里获取wasm的实例，到此 整个wasm的初始化后的输出模块我们就可以获得了

main函数的运行
这里值得是c中的main函数，如果是模块输出其实不需要main函数
他对照了模块中的run函数 在加载后 默认是会直接运行的 我们可以通过noInitialRun让主函数不执行，然后利用模块的run函数去运行，支持参数的传入，非常适合wasm模块的初始化场景

工程化设计

1. 编写定制化的Module对象，必须改写的函数主要是生命周期函数和'locateFile'
2. 梳理c/cpp模块的边界，哪些是js完成哪些是c完成，确认输入输出，这里可以用组件化的思路解决
3. 编译c代码，输出为js和wasm即可
4. 对export出来的模块进行二次包装，主要函数的整理，入参的类型处理
5. 完成组件的生命周期的控制
6. 联调核心功能