path: root/lib/auto.js

import arrayEach from 'lodash/_arrayEach';
import forOwn from 'lodash/_baseForOwn';
import indexOf from 'lodash/_baseIndexOf';
import isArray from 'lodash/isArray';
import okeys from 'lodash/keys';
import noop from 'lodash/noop';

import slice from './internal/slice';
import once from './internal/once';
import onlyOnce from './internal/onlyOnce';
import wrapAsync from './internal/wrapAsync';

/**
 * Determines the best order for running the {@link AsyncFunction}s in `tasks`, based on
 * their requirements. Each function can optionally depend on other functions
 * being completed first, and each function is run as soon as its requirements
 * are satisfied.
 *
 * If any of the {@link AsyncFunction}s pass an error to their callback, the `auto` sequence
 * will stop. Further tasks will not execute (so any other functions depending
 * on it will not run), and the main `callback` is immediately called with the
 * error.
 *
 * {@link AsyncFunction}s also receive an object containing the results of functions which
 * have completed so far as the first argument, if they have dependencies. If a
 * task function has no dependencies, it will only be passed a callback.
 *
 * @name auto
 * @static
 * @memberOf module:ControlFlow
 * @method
 * @category Control Flow
 * @param {Object} tasks - An object. Each of its properties is either a
 * function or an array of requirements, with the {@link AsyncFunction} itself the last item
 * in the array. The object's key of a property serves as the name of the task
 * defined by that property, i.e. can be used when specifying requirements for
 * other tasks. The function receives one or two arguments:
 * * a `results` object, containing the results of the previously executed
 *   functions, only passed if the task has any dependencies,
 * * a `callback(err, result)` function, which must be called when finished,
 *   passing an `error` (which can be `null`) and the result of the function's
 *   execution.
 * @param {number} [concurrency=Infinity] - An optional `integer` for
 * determining the maximum number of tasks that can be run in parallel. By
 * default, as many as possible.
 * @param {Function} [callback] - An optional callback which is called when all
 * the tasks have been completed. It receives the `err` argument if any `tasks`
 * pass an error to their callback. Results are always returned; however, if an
 * error occurs, no further `tasks` will be performed, and the results object
 * will only contain partial results. Invoked with (err, results).
 * @returns undefined
 * @example
 *
 * async.auto({
 *     // this function will just be passed a callback
 *     readData: async.apply(fs.readFile, 'data.txt', 'utf-8'),
 *     showData: ['readData', function(results, cb) {
 *         // results.readData is the file's contents
 *         // ...
 *     }]
 * }, callback);
 *
 * async.auto({
 *     get_data: function(callback) {
 *         console.log('in get_data');
 *         // async code to get some data
 *         callback(null, 'data', 'converted to array');
 *     },
 *     make_folder: function(callback) {
 *         console.log('in make_folder');
 *         // async code to create a directory to store a file in
 *         // this is run at the same time as getting the data
 *         callback(null, 'folder');
 *     },
 *     write_file: ['get_data', 'make_folder', function(results, callback) {
 *         console.log('in write_file', JSON.stringify(results));
 *         // once there is some data and the directory exists,
 *         // write the data to a file in the directory
 *         callback(null, 'filename');
 *     }],
 *     email_link: ['write_file', function(results, callback) {
 *         console.log('in email_link', JSON.stringify(results));
 *         // once the file is written let's email a link to it...
 *         // results.write_file contains the filename returned by write_file.
 *         callback(null, {'file':results.write_file, 'email':'user@example.com'});
 *     }]
 * }, function(err, results) {
 *     console.log('err = ', err);
 *     console.log('results = ', results);
 * });
 */
export default function (tasks, concurrency, callback) {
    if (typeof concurrency === 'function') {
        // concurrency is optional, shift the args.
        callback = concurrency;
        concurrency = null;
    }
    callback = once(callback || noop);
    var keys = okeys(tasks);
    var numTasks = keys.length;
    if (!numTasks) {
        return callback(null);
    }
    if (!concurrency) {
        concurrency = numTasks;
    }

    var results = {};
    var runningTasks = 0;
    var hasError = false;

    var listeners = Object.create(null);

    var readyTasks = [];

    // for cycle detection:
    var readyToCheck = []; // tasks that have been identified as reachable
    // without the possibility of returning to an ancestor task
    var uncheckedDependencies = {};

    forOwn(tasks, function (task, key) {
        if (!isArray(task)) {
            // no dependencies
            enqueueTask(key, [task]);
            readyToCheck.push(key);
            return;
        }

        var dependencies = task.slice(0, task.length - 1);
        var remainingDependencies = dependencies.length;
        if (remainingDependencies === 0) {
            enqueueTask(key, task);
            readyToCheck.push(key);
            return;
        }
        uncheckedDependencies[key] = remainingDependencies;

        arrayEach(dependencies, function (dependencyName) {
            if (!tasks[dependencyName]) {
                throw new Error('async.auto task `' + key +
                    '` has a non-existent dependency `' +
                    dependencyName + '` in ' +
                    dependencies.join(', '));
            }
            addListener(dependencyName, function () {
                remainingDependencies--;
                if (remainingDependencies === 0) {
                    enqueueTask(key, task);
                }
            });
        });
    });

    checkForDeadlocks();
    processQueue();

    function enqueueTask(key, task) {
        readyTasks.push(function () {
            runTask(key, task);
        });
    }

    function processQueue() {
        if (readyTasks.length === 0 && runningTasks === 0) {
            return callback(null, results);
        }
        while(readyTasks.length && runningTasks < concurrency) {
            var run = readyTasks.shift();
            run();
        }

    }

    function addListener(taskName, fn) {
        var taskListeners = listeners[taskName];
        if (!taskListeners) {
            taskListeners = listeners[taskName] = [];
        }

        taskListeners.push(fn);
    }

    function taskComplete(taskName) {
        var taskListeners = listeners[taskName] || [];
        arrayEach(taskListeners, function (fn) {
            fn();
        });
        processQueue();
    }


    function runTask(key, task) {
        if (hasError) return;

        var taskCallback = onlyOnce(function(err, result) {
            runningTasks--;
            if (arguments.length > 2) {
                result = slice(arguments, 1);
            }
            if (err) {
                var safeResults = {};
                forOwn(results, function(val, rkey) {
                    safeResults[rkey] = val;
                });
                safeResults[key] = result;
                hasError = true;
                listeners = Object.create(null);

                callback(err, safeResults);
            } else {
                results[key] = result;
                taskComplete(key);
            }
        });

        runningTasks++;
        var taskFn = wrapAsync(task[task.length - 1]);
        if (task.length > 1) {
            taskFn(results, taskCallback);
        } else {
            taskFn(taskCallback);
        }
    }

    function checkForDeadlocks() {
        // Kahn's algorithm
        // https://en.wikipedia.org/wiki/Topological_sorting#Kahn.27s_algorithm
        // http://connalle.blogspot.com/2013/10/topological-sortingkahn-algorithm.html
        var currentTask;
        var counter = 0;
        while (readyToCheck.length) {
            currentTask = readyToCheck.pop();
            counter++;
            arrayEach(getDependents(currentTask), function (dependent) {
                if (--uncheckedDependencies[dependent] === 0) {
                    readyToCheck.push(dependent);
                }
            });
        }

        if (counter !== numTasks) {
            throw new Error(
                'async.auto cannot execute tasks due to a recursive dependency'
            );
        }
    }

    function getDependents(taskName) {
        var result = [];
        forOwn(tasks, function (task, key) {
            if (isArray(task) && indexOf(task, taskName, 0) >= 0) {
                result.push(key);
            }
        });
        return result;
    }
}