在遍历数组和保存到mongoose时遇到麻烦.回调的问题

Having trouble iterating through array and saving to mongoose. Callback issue?

本文关键字:麻烦 遇到 回调 问题 mongoose 数组 遍历 保存      更新时间:2023-09-26

我正在学习node, express, mongo,在这个过程中,还有javascript。我正试图获得一个功能,使用rssparser,获得一个故事列表,并将它们保存到mongoose数据库。

我已经让RSS pull工作了,并且我正在迭代故事,这是我遇到问题的保存。我想1)检查这个故事是否已经存在于数据库中,2)如果不存在,保存它。我想我在回调的处理方式上迷失了方向。这是我当前的代码,带有注释。

rssparser.parseURL(url, options, function(err,out){
    // out.items is an array of the items pulled
    var items = out.items;
    var story;
    for (var i=0; i<items.length; i++){
        //create a mongoose story
        story = new schemas.Stories({
            title: items[i].title,
            url: items[i].url,
            summary: items[i].summary,
            published: items[i].published_at
        });
        //TODO: for testing - these show up correctly.  
        //If I pull 10 stories, I get 10 entries from here that match
        //So "story" is holding the current story
        console.log("items[i] is :" + items[i].title);
        console.log("story title is : " + story.title);
        // setup query to see if it's already in db
        var query = schemas.Stories.findOne({
            "title" : story.title,
            "url" : story.url
        });

        //execute the query
        query.exec( function(err, row){
            if(err) console.log("error-query: " + err);
            console.log("row: "+ row);
            if(!row) {
                // not there, so save
                console.log('about to save story.title: ' + story.title);
                story.save(function (err){
                    console.log("error in save: " + err);
                });
            }
        });
    }
});

当它运行时,我看到的是大量控制台输出:

它开始显示所有的故事(许多被省略了):

items[i] is :TSA Drops Plan to Let Passengers Carry Small Knives on Planes               
story title is : TSA Drops Plan to Let Passengers Carry Small Knives on Planes           
items[i] is :BUILDING COLLAPSE:1 Reportedly Dead, 13 Pulled From Philly Rubble           
story title is : BUILDING COLLAPSE:1 Reportedly Dead, 13 Pulled From Philly Rubble       
items[i] is :CONTROVERSIAL PAST: Obama's UN Nominee Once Likened US 'Sins' to Nazis'     
story title is : CONTROVERSIAL PAST: Obama's UN Nominee Once Likened US 'Sins' to Nazis' 
items[i] is :WRITING OUT WRIGHTS: Bill Gives First Powered Flight Nod to Whitehead       
story title is : WRITING OUT WRIGHTS: Bill Gives First Powered Flight Nod to Whitehead   
items[i] is :BREAKING NEWS: Rice Named to Top Security Post Despite Libya Fallout        
story title is : BREAKING NEWS: Rice Named to Top Security Post Despite Libya Fallout   

然后继续(省略了很多):

row: null                                                                     
about to save story.title: Best Ribs in America                               
row: null                                                                     
about to save story.title: Best Ribs in America                               
row: null                                                                     
about to save story.title: Best Ribs in America                               
row: null                                                                     
about to save story.title: Best Ribs in America                               
row: null                                                                     
about to save story.title: Best Ribs in America                               
row: null                                                                     
about to save story.title: Best Ribs in America                               
row: { title: 'Best Ribs in America',                                         
  url: 'http://www.foxnews.com/leisure/2013/06/05/10-best-ribs-in-america/',  
  published: 1370463800000,                                                   
  _id: 51af9f881995d40425000023,                                              
  __v: 0 }                                                                    

它重复"about to save"标题(这是提要中的最后一个故事),并保存该故事一次,如最后一行所示。

console.log的输出显示了我所放置的内容,所有的故事标题输出在顶部,然后query.exec()调用中的所有内容在底部。

这样做的问题是,一旦执行回调,exec回调中引用的故事将被设置为for循环中迭代的最后一个内容,因为所有执行的函数都引用了变量的相同实例。

解决这个问题的最简单的方法是简单地将for循环中的每个东西包装在一个带参数的函数中,然后立即执行,如:
rssparser.parseURL(url, options, function(err,out){
    // out.items is an array of the items pulled
    var items = out.items;
    for (var i=0; i<items.length; i++){
        (function(item) {
            //create a mongoose story
            var story = new schemas.Stories({
                title: item.title,
                url: item.url,
                summary: item.summary,
                published: item.published_at
            });
            // setup query to see if it's already in db
            var query = schemas.Stories.findOne({
                "title" : story.title,
                "url" : story.url
            });
            //execute the query
            query.exec( function(err, row){
                if(err) console.log("error-query: " + err);
                console.log("row: "+ row);
                if(!row) {
                    // not there, so save
                    console.log('about to save story.title: ' + story.title);
                    story.save(function (err){
                        console.log("error in save: " + err);
                    });
                }
            });
        })(items[i]);
    }
});

我还没有测试过这个,但我相信你会发现它会解决你的问题

另一种更简单、更清晰、更好的方法是在数组上的forEach循环中迭代项,如果你的平台支持(node.js支持)——这个版本甚至更漂亮:

rssparser.parseURL(url, options, function(err,out){
    // out.items is an array of the items pulled
    out.items.forEach(function(item) {
        //create a mongoose story
        var story = new schemas.Stories({
            title: item.title,
            url: item.url,
            summary: item.summary,
            published: item.published_at
        });
        // setup query to see if it's already in db
        var query = schemas.Stories.findOne({
            "title" : story.title,
            "url" : story.url
        });
        //execute the query
        query.exec( function(err, row){
            if(err) console.log("error-query: " + err);
            console.log("row: "+ row);
            if(!row) {
                // not there, so save
                console.log('about to save story.title: ' + story.title);
                story.save(function (err){
                    console.log("error in save: " + err);
                });
            }
        });
    });
});

node是事件驱动的服务器,javascript也是事件驱动的,所以你可以异步调用。

你需要使用一些异步模式来做你想做的。

首先,如果你正在使用mongoose,你可以利用它的模式类来检查已经存在的项目,而不需要再次查询数据库:

var mongoose = require('mongoose');
var schema = new mongoose.Schema({
    title: String,
    url: { type: String, unique: true },
    summary: String,
    published: Date
})
var model = mongoose.model('stories', schema)

url是唯一的,因此保存将导致重复错误,并且mongoose不会保存查询。

现在要遍历项并保存每个项我们需要某种模式,幸运的是我们有async:

var async = require('async');
rssparser.parseURL(url, options, function(err, out){
    async.each(out.items, function(item, callback){
        var m = new model({
            title: item.title,
            url: item.url,
            summary: item.summary,
            published: item.published_at
        })
        m.save(function(err, result){
            callback(null)
        });
    }, function(err){
        //we complete the saving we can do stuff here       
    });
}

我们在并行模式下使用async,因为我们不关心一些是否重复。你也可以用一个数组来跟踪它,你可以把err ||结果推给它您可以看到您保存了多少项。