Node.js之异步流控制

时间 2019-11-06

标签 node.js node 异步控制栏目 Node.js 繁體版

原文原文链接

前言

在没有深度使用函数回调的经验的时候，去看这些内容仍是有一点吃力的。因为Node.js独特的异步特性，才出现了“回调地狱”的问题，这篇文章中，我比较详细的记录了如何解决异步流问题。javascript

文章会很长，并且这篇是对异步流模式的解释。文中会使用一个简单的网络蜘蛛的例子，它的做用是抓取指定URL的网页内容并保存在项目中，在文章的最后，能够找到整篇文章中的源码demo。java

1.原生JavaScript模式

本篇不针对初学者，所以会省略掉大部分的基础内容的讲解：node

(spider_v1.js)git

const request = require("request");
const fs = require("fs");
const mkdirp = require("mkdirp");
const path = require("path");
const utilities = require("./utilities");

function spider(url, callback) {
    const filename = utilities.urlToFilename(url);
    console.log(`filename: ${filename}`);

    fs.exists(filename, exists => {
        if (!exists) {
            console.log(`Downloading ${url}`);

            request(url, (err, response, body) => {
                if (err) {
                    callback(err);
                } else {
                    mkdirp(path.dirname(filename), err => {
                        if (err) {
                            callback(err);
                        } else {
                            fs.writeFile(filename, body, err => {
                                if (err) {
                                    callback(err);
                                } else {
                                    callback(null, filename, true);
                                }
                            });
                        }
                    });
                }
            });
        } else {
            callback(null, filename, false);
        }
    });
}

spider(process.argv[2], (err, filename, downloaded) => {
    if (err) {
        console.log(err);
    } else if (downloaded) {
        console.log(`Completed the download of ${filename}`);
    } else {
        console.log(`${filename} was already downloaded`);
    }
});

上边的代码的流程大概是这样的：程序员

把url转换成filename
判断该文件名是否存在，若存在直接返回，不然进入下一步
发请求，获取body
把body写入到文件中

这是一个很是简单版本的蜘蛛，他只能抓取一个url的内容，看到上边的回调多么使人头疼。那么咱们开始进行优化。github

首先，if else 这种方式能够进行优化，这个很简单，不用多说，放一个对比效果：编程

/// before
if (err) {
    callback(err);
} else {
    callback(null, filename, true);
}

/// after
if (err) {
    return callback(err);
}
callback(null, filename, true);

代码这么写，嵌套就会少一层，但经验丰富的程序员会认为，这样写太重强调了error，咱们编程的重点应该放在处理正确的数据上，在可读性上也存在这样的要求。api

另外一个优化是函数拆分，上边代码中的spider函数中，能够把下载文件和保存文件拆分出去。数组

(spider_v2.js)promise

const request = require("request");
const fs = require("fs");
const mkdirp = require("mkdirp");
const path = require("path");
const utilities = require("./utilities");

function saveFile(filename, contents, callback) {
    mkdirp(path.dirname(filename), err => {
        if (err) {
            return callback(err);
        }
        fs.writeFile(filename, contents, callback);
    });
}

function download(url, filename, callback) {
    console.log(`Downloading ${url}`);

    request(url, (err, response, body) => {
        if (err) {
            return callback(err);
        }
        saveFile(filename, body, err => {
            if (err) {
                return callback(err);
            }
            console.log(`Downloaded and saved: ${url}`);
            callback(null, body);
        });
    })
}

function spider(url, callback) {
    const filename = utilities.urlToFilename(url);
    console.log(`filename: ${filename}`);

    fs.exists(filename, exists => {
        if (exists) {
            return callback(null, filename, false);
        }
        download(url, filename, err => {
            if (err) {
                return callback(err);
            }
            callback(null, filename, true);
        })
    });
}

spider(process.argv[2], (err, filename, downloaded) => {
    if (err) {
        console.log(err);
    } else if (downloaded) {
        console.log(`Completed the download of ${filename}`);
    } else {
        console.log(`${filename} was already downloaded`);
    }
});

上边的代码基本上是采用原生优化后的结果，但这个蜘蛛的功能太过简单，咱们如今须要抓取某个网页中的全部url，这样才会引伸出串行和并行的问题。

(spider_v3.js)

const request = require("request");
const fs = require("fs");
const mkdirp = require("mkdirp");
const path = require("path");
const utilities = require("./utilities");

function saveFile(filename, contents, callback) {
    mkdirp(path.dirname(filename), err => {
        if (err) {
            return callback(err);
        }
        fs.writeFile(filename, contents, callback);
    });
}

function download(url, filename, callback) {
    console.log(`Downloading ${url}`);

    request(url, (err, response, body) => {
        if (err) {
            return callback(err);
        }
        saveFile(filename, body, err => {
            if (err) {
                return callback(err);
            }
            console.log(`Downloaded and saved: ${url}`);
            callback(null, body);
        });
    })
}

/// 最大的启发是实现了如何异步循环遍历数组
function spiderLinks(currentUrl, body, nesting, callback) {
    if (nesting === 0) {
        return process.nextTick(callback);
    }

    const links = utilities.getPageLinks(currentUrl, body);

    function iterate(index) {
        if (index === links.length) {
            return callback();
        }
        spider(links[index], nesting - 1, err => {
            if (err) {
                return callback(err);
            }
            iterate((index + 1));
        })
    }

    iterate(0);
}

function spider(url, nesting, callback) {
    const filename = utilities.urlToFilename(url);

    fs.readFile(filename, "utf8", (err, body) => {
        if (err) {
            if (err.code !== 'ENOENT') {
                return callback(err);
            }
            return download(url, filename, (err, body) => {
                if (err) {
                    return callback(err);
                }
                spiderLinks(url, body, nesting, callback);
            });
        }

        spiderLinks(url, body, nesting, callback);
    });
}

spider(process.argv[2], 2, (err, filename, downloaded) => {
    if (err) {
        console.log(err);
    } else if (downloaded) {
        console.log(`Completed the download of ${filename}`);
    } else {
        console.log(`${filename} was already downloaded`);
    }
});

上边的代码相比以前的代码多了两个核心功能，首先是经过辅助类获取到了某个body中的links：

const links = utilities.getPageLinks(currentUrl, body);

内部实现就不解释了，另外一个核心代码就是：

/// 最大的启发是实现了如何异步循环遍历数组
function spiderLinks(currentUrl, body, nesting, callback) {
    if (nesting === 0) {
        return process.nextTick(callback);
    }

    const links = utilities.getPageLinks(currentUrl, body);

    function iterate(index) {
        if (index === links.length) {
            return callback();
        }
        spider(links[index], nesting - 1, err => {
            if (err) {
                return callback(err);
            }
            iterate((index + 1));
        })
    }

    iterate(0);
}

能够说上边这一小段代码，就是采用原生实现异步串行的pattern了。除了这些以外，还引入了nesting的概念，经过这是这个属性，能够控制抓取层次。

到这里咱们就完整的实现了串行的功能，考虑到性能，咱们要开发并行抓取的功能。

(spider_v4.js)

const request = require("request");
const fs = require("fs");
const mkdirp = require("mkdirp");
const path = require("path");
const utilities = require("./utilities");

function saveFile(filename, contents, callback) {
    mkdirp(path.dirname(filename), err => {
        if (err) {
            return callback(err);
        }
        fs.writeFile(filename, contents, callback);
    });
}

function download(url, filename, callback) {
    console.log(`Downloading ${url}`);

    request(url, (err, response, body) => {
        if (err) {
            return callback(err);
        }
        saveFile(filename, body, err => {
            if (err) {
                return callback(err);
            }
            console.log(`Downloaded and saved: ${url}`);
            callback(null, body);
        });
    })
}

/// 最大的启发是实现了如何异步循环遍历数组
function spiderLinks(currentUrl, body, nesting, callback) {
    if (nesting === 0) {
        return process.nextTick(callback);
    }

    const links = utilities.getPageLinks(currentUrl, body);
    if (links.length === 0) {
        return process.nextTick(callback);
    }

    let completed = 0, hasErrors = false;

    function done(err) {
        if (err) {
            hasErrors = true;
            return callback(err);
        }

        if (++completed === links.length && !hasErrors) {
            return callback();
        }
    }

    links.forEach(link => {
        spider(link, nesting - 1, done);
    });
}

const spidering = new Map();

function spider(url, nesting, callback) {
    if (spidering.has(url)) {
        return process.nextTick(callback);
    }

    spidering.set(url, true);

    const filename = utilities.urlToFilename(url);

    /// In this pattern, there will be some issues.
    /// Possible problems to download the same url again and again。
    fs.readFile(filename, "utf8", (err, body) => {
        if (err) {
            if (err.code !== 'ENOENT') {
                return callback(err);
            }
            return download(url, filename, (err, body) => {
                if (err) {
                    return callback(err);
                }
                spiderLinks(url, body, nesting, callback);
            });
        }

        spiderLinks(url, body, nesting, callback);
    });
}

spider(process.argv[2], 2, (err, filename, downloaded) => {
    if (err) {
        console.log(err);
    } else if (downloaded) {
        console.log(`Completed the download of ${filename}`);
    } else {
        console.log(`${filename} was already downloaded`);
    }
});

这段代码一样很简单，也有两个核心内容。一个是如何实现并发：

/// 最大的启发是实现了如何异步循环遍历数组
function spiderLinks(currentUrl, body, nesting, callback) {
    if (nesting === 0) {
        return process.nextTick(callback);
    }

    const links = utilities.getPageLinks(currentUrl, body);
    if (links.length === 0) {
        return process.nextTick(callback);
    }

    let completed = 0, hasErrors = false;

    function done(err) {
        if (err) {
            hasErrors = true;
            return callback(err);
        }

        if (++completed === links.length && !hasErrors) {
            return callback();
        }
    }

    links.forEach(link => {
        spider(link, nesting - 1, done);
    });
}

上边的代码能够说是实现并发的一个pattern。利用循环遍从来实现。另外一个核心是，既然是并发的，那么利用fs.exists就会存在问题，可能会重复下载同一文件，这里的解决方案是：

使用Map缓存某一url，url应该做为key

如今咱们又有了新的需求，要求限制同时并发的最大数，那么在这里就引进了一个我认为最重要的概念：队列。

(task-Queue.js)

class TaskQueue {
    constructor(concurrency) {
        this.concurrency = concurrency;
        this.running = 0;
        this.queue = [];
    }

    pushTask(task) {
        this.queue.push(task);
        this.next();
    }

    next() {
        while (this.running < this.concurrency && this.queue.length) {
            const task = this.queue.shift();
            task(() => {
                this.running--;
                this.next();
            });
            this.running++;
        }
    }
}

module.exports = TaskQueue;

上边的代码就是队列的实现代码，核心是next()方法，能够看出，当task加入队列中后，会马上执行，这不是说这个任务必定立刻执行，而是指的是next会马上调用。

(spider_v5.js)

const request = require("request");
const fs = require("fs");
const mkdirp = require("mkdirp");
const path = require("path");
const utilities = require("./utilities");
const TaskQueue = require("./task-Queue");
const downloadQueue = new TaskQueue(2);

function saveFile(filename, contents, callback) {
    mkdirp(path.dirname(filename), err => {
        if (err) {
            return callback(err);
        }
        fs.writeFile(filename, contents, callback);
    });
}

function download(url, filename, callback) {
    console.log(`Downloading ${url}`);

    request(url, (err, response, body) => {
        if (err) {
            return callback(err);
        }
        saveFile(filename, body, err => {
            if (err) {
                return callback(err);
            }
            console.log(`Downloaded and saved: ${url}`);
            callback(null, body);
        });
    })
}

/// 最大的启发是实现了如何异步循环遍历数组
function spiderLinks(currentUrl, body, nesting, callback) {
    if (nesting === 0) {
        return process.nextTick(callback);
    }

    const links = utilities.getPageLinks(currentUrl, body);
    if (links.length === 0) {
        return process.nextTick(callback);
    }

    let completed = 0, hasErrors = false;

    links.forEach(link => {
        /// 给队列出传递一个任务，这个任务首先是一个函数，其次该函数接受一个参数
        /// 当调用任务时，触发该函数，而后给函数传递一个参数，告诉该函数在任务结束时干什么
        downloadQueue.pushTask(done => {
            spider(link, nesting - 1, err => {
                /// 这里表示，只要发生错误，队列就会退出
                if (err) {
                    hasErrors = true;
                    return callback(err);
                }
                if (++completed === links.length && !hasErrors) {
                    callback();
                }

                done();
            });
        });

    });
}

const spidering = new Map();

function spider(url, nesting, callback) {
    if (spidering.has(url)) {
        return process.nextTick(callback);
    }

    spidering.set(url, true);

    const filename = utilities.urlToFilename(url);

    /// In this pattern, there will be some issues.
    /// Possible problems to download the same url again and again。
    fs.readFile(filename, "utf8", (err, body) => {
        if (err) {
            if (err.code !== 'ENOENT') {
                return callback(err);
            }
            return download(url, filename, (err, body) => {
                if (err) {
                    return callback(err);
                }
                spiderLinks(url, body, nesting, callback);
            });
        }

        spiderLinks(url, body, nesting, callback);
    });
}

spider(process.argv[2], 2, (err, filename, downloaded) => {
    if (err) {
        console.log(`error: ${err}`);
    } else if (downloaded) {
        console.log(`Completed the download of ${filename}`);
    } else {
        console.log(`${filename} was already downloaded`);
    }
});

所以，为了限制并发的个数，只需在spiderLinks方法中，把task遍历放入队列就能够了。这相对来讲很简单。

到这里为止，咱们使用原生JavaScript实现了一个有相对完整功能的网络蜘蛛，既能串行，也能并发，还能够控制并发个数。

2.使用async库

把不一样的功能放到不一样的函数中，会给咱们带来巨大的好处，async库十分流行，它的性能也不错，它内部基于callback。

(spider_v6.js)

const request = require("request");
const fs = require("fs");
const mkdirp = require("mkdirp");
const path = require("path");
const utilities = require("./utilities");
const series = require("async/series");
const eachSeries = require("async/eachSeries");

function download(url, filename, callback) {
    console.log(`Downloading ${url}`);

    let body;

    series([
        callback => {
            request(url, (err, response, resBody) => {
                if (err) {
                    return callback(err);
                }
                body = resBody;
                callback();
            });
        },
        mkdirp.bind(null, path.dirname(filename)),
        callback => {
            fs.writeFile(filename, body, callback);
        }
    ], err => {
        if (err) {
            return callback(err);
        }
        console.log(`Downloaded and saved: ${url}`);
        callback(null, body);
    });
}

/// 最大的启发是实现了如何异步循环遍历数组
function spiderLinks(currentUrl, body, nesting, callback) {
    if (nesting === 0) {
        return process.nextTick(callback);
    }

    const links = utilities.getPageLinks(currentUrl, body);
    if (links.length === 0) {
        return process.nextTick(callback);
    }

    eachSeries(links, (link, cb) => {
        "use strict";
        spider(link, nesting - 1, cb);
    }, callback);
}

const spidering = new Map();

function spider(url, nesting, callback) {
    if (spidering.has(url)) {
        return process.nextTick(callback);
    }

    spidering.set(url, true);

    const filename = utilities.urlToFilename(url);

    fs.readFile(filename, "utf8", (err, body) => {
        if (err) {
            if (err.code !== 'ENOENT') {
                return callback(err);
            }
            return download(url, filename, (err, body) => {
                if (err) {
                    return callback(err);
                }
                spiderLinks(url, body, nesting, callback);
            });
        }

        spiderLinks(url, body, nesting, callback);
    });
}

spider(process.argv[2], 1, (err, filename, downloaded) => {
    if (err) {
        console.log(err);
    } else if (downloaded) {
        console.log(`Completed the download of ${filename}`);
    } else {
        console.log(`${filename} was already downloaded`);
    }
});

在上边的代码中，咱们只使用了async的三个功能：

const series = require("async/series"); // 串行
const eachSeries = require("async/eachSeries"); // 并行
const queue = require("async/queue"); // 队列

因为比较简单，就不作解释了。async中的队列的代码在(spider_v7.js)中，和上边咱们自定义的队列很类似，也不作更多解释了。

3.Promise

Promise是一个协议，有不少库实现了这个协议，咱们用的是ES6的实现。简单来讲promise就是一个约定，若是完成了，就调用它的resolve方法，失败了就调用它的reject方法。它内有实现了then方法，then返回promise自己，这样就造成了调用链。

其实Promise的内容有不少，在实际应用中是如何把普通的函数promise化。这方面的内容在这里也不讲了，我本身也未入流

(spider_v8.js)

const utilities = require("./utilities");
const request = utilities.promisify(require("request"));
const fs = require("fs");
const readFile = utilities.promisify(fs.readFile);
const writeFile = utilities.promisify(fs.writeFile);
const mkdirp = utilities.promisify(require("mkdirp"));
const path = require("path");


function saveFile(filename, contents, callback) {
    mkdirp(path.dirname(filename), err => {
        if (err) {
            return callback(err);
        }
        fs.writeFile(filename, contents, callback);
    });
}

function download(url, filename) {
    console.log(`Downloading ${url}`);

    let body;

    return request(url)
        .then(response => {
            "use strict";
            body = response.body;
            return mkdirp(path.dirname(filename));
        })
        .then(() => writeFile(filename, body))
        .then(() => {
            "use strict";
            console.log(`Downloaded adn saved: ${url}`);
            return body;
        });
}

/// promise编程的本质就是为了解决在函数中设置回调函数的问题
/// 经过中间层promise来实现异步函数同步化
function spiderLinks(currentUrl, body, nesting) {
    let promise = Promise.resolve();
    if (nesting === 0) {
        return promise;
    }

    const links = utilities.getPageLinks(currentUrl, body);

    links.forEach(link => {
        "use strict";
        promise = promise.then(() => spider(link, nesting - 1));
    });

    return promise;
}

function spider(url, nesting) {
    const filename = utilities.urlToFilename(url);

    return readFile(filename, "utf8")
        .then(
            body => spiderLinks(url, body, nesting),
            err => {
                "use strict";
                if (err.code !== 'ENOENT') {
                    /// 抛出错误，这个方便与在整个异步链的最后经过呢catch来捕获这个链中的错误
                    throw err;
                }
                return download(url, filename)
                    .then(body => spiderLinks(url, body, nesting));
            }
        );
}

spider(process.argv[2], 1)
    .then(() => {
        "use strict";
        console.log('Download complete');
    })
    .catch(err => {
        "use strict";
        console.log(err);
    });

能够看到上边的代码中的函数都是没有callback的，只须要在最后catch就能够了。

在设计api的时候，应该支持两种方式，及支持callback，又支持promise

function asyncDivision(dividend, divisor, cb) {
    return new Promise((resolve, reject) => {
        "use strict";
        process.nextTick(() => {
            const result = dividend / divisor;
            if (isNaN(result) || !Number.isFinite(result)) {
                const error = new Error("Invalid operands");
                if (cb) {
                    cb(error);
                }
                return reject(error);
            }

            if (cb) {
                cb(null, result);
            }
            resolve(result);
        });
    });
}

asyncDivision(10, 2, (err, result) => {
    "use strict";
    if (err) {
        return console.log(err);
    }
    console.log(result);
});

asyncDivision(22, 11)
    .then((result) => console.log(result))
    .catch((err) => console.log(err));

4.Generator

Generator颇有意思，他可让暂停函数和恢复函数，利用thunkify和co这两个库，咱们下边的代码实现起来很是酷。

(spider_v9.js)

const thunkify = require("thunkify");
const co = require("co");
const path = require("path");
const utilities = require("./utilities");

const request = thunkify(require("request"));
const fs = require("fs");
const mkdirp = thunkify(require("mkdirp"));
const readFile = thunkify(fs.readFile);
const writeFile = thunkify(fs.writeFile);
const nextTick = thunkify(process.nextTick);

function* download(url, filename) {
    console.log(`Downloading ${url}`);

    const response = yield request(url);
    console.log(response);

    const body = response[1];
    yield mkdirp(path.dirname(filename));

    yield writeFile(filename, body);

    console.log(`Downloaded and saved ${url}`);
    return body;
}

function* spider(url, nesting) {
    const filename = utilities.urlToFilename(url);

    let body;

    try {
        body = yield readFile(filename, "utf8");
    } catch (err) {
        if (err.code !== 'ENOENT') {
            throw err;
        }
        body = yield download(url, filename);
    }

    yield  spiderLinks(url, body, nesting);
}

function* spiderLinks(currentUrl, body, nesting) {
    if (nesting === 0) {
        return nextTick();
    }

    const links = utilities.getPageLinks(currentUrl, body);

    for (let i = 0; i < links.length; i++) {
        yield spider(links[i], nesting - 1);
    }
}

/// 经过co就自动处理了回调函数，直接返回了回调函数中的参数，把这些参数放到一个数组中，可是去掉了err信息
co(function* () {
    try {
        yield spider(process.argv[2], 1);
        console.log('Download complete');
    } catch (err) {
        console.log(err);
    }
});

总结

我并无写promise和generator并发的代码。以上这些内容来自于这本书nodejs-design-patternshttps://github.com/agelessman/MyBooks。

demo下载