Google Cloud Bucket 上传前承诺解决
Promise Resolving before Google Cloud Bucket Upload
我正在编写一些循环遍历 CSV 并在函数内创建 JSON 文件 based on the CSV. Included in the JSON is an array named photos, which is to contain the returned urls for the images that are being uploaded to 的代码。然而，承诺等待上传完成让我感到难过，因为一切都是 运行 异步的，并且在完成存储桶上传和返回之前完成 promise 和 JSON 编译url。在检索到 url 并将其添加到 currentJSON.photos 后，如何使 promise 解析？
const csv=require('csvtojson')
const fs = require('fs');
const {Storage} = require('@google-cloud/storage');
var serviceAccount = require("./my-firebase-storage-spot.json");
const testFolder = './Images/';
var csvFilePath = './Inventory.csv';
var dirArr = ['./Images/Subdirectory-A','./Images/Subdirectory-B','./Images/Subdirectory-C'];
var allData = [];
csv()
.fromFile(csvFilePath)
.subscribe((json)=>{
return new Promise((resolve,reject)=>{
for (var i in dirArr ) {
if (json['Name'] == dirArr[i]) {
var currentJSON = {
"photos" : [],
};
fs.readdir(testFolder+json['Name'], (err, files) => {
files.forEach(file => {
if (file.match(/.(jpg|jpeg|png|gif)$/i)){
var imgName = testFolder + json['Name'] + '/' + file;
bucket.upload(imgName, function (err, file) {
if (err) throw new Error(err);
//returned uploaded img address is found at file.metadata.mediaLink
currentJSON.photos.push(file.metadata.mediaLink);
});
}else {
//do nothing
}
});
});
allData.push(currentJSON);
}
}
resolve();
})
},onError,onComplete);
function onError() {
// console.log(err)
}
function onComplete() {
console.log('finito');
}
我尝试移动 resolve()，还尝试将上传器部分放入 onComplete() 函数（这会产生新的基于 promise 的问题）。
实际上，您的代码没有等待 readdir 回调函数的异步调用，也没有等待 bucket.upload 回调函数的异步调用。
当您使用这些函数的 promise 版本时，异步编码变得更容易。
bucket.upload 将 return 省略回调函数时的承诺，所以这很容易。
对于readdir到return的一个promise，你需要使用fs Promise API:然后就可以使用
基于承诺的 readdir 方法和使用
在您的代码中承诺。
所以使用 fs = require('fs').promises 而不是 fs = require('fs')
有了这些准备，您的代码可以变成这样：
const testFolder = './Images/';
var csvFilePath = './Inventory.csv';
var dirArr = ['./Images/Subdirectory-A','./Images/Subdirectory-B','./Images/Subdirectory-C'];
(async function () {
let arr = await csv().fromFile(csvFilePath);
arr = arr.filter(obj => dirArr.includes(obj.Name));
let allData = await Promise.all(arr.map(async obj => {
let files = await fs.readdir(testFolder + obj.Name);
files = files.filter(file => file.match(/\.(jpg|jpeg|png|gif)$/i));
let photos = await Promise.all(
files.map(async file => {
var imgName = testFolder + obj.Name + '/' + file;
let result = await bucket.upload(imgName);
return result.metadata.mediaLink;
})
);
return {photos};
}));
console.log('finito', allData);
})().catch(err => { // <-- The above async function runs immediately and returns a promise
console.log(err);
});
一些备注：
您的正则表达式存在缺陷。您打算匹配一个文字点，但您没有转义它（已在上面的代码中修复）。
allData 将包含一组 { photos: [......] } 个对象，我想知道为什么您不希望所有照片元素都成为一个数组的一部分。然而，我保留了你的逻辑，所以上面的代码仍然会在这些块中产生它们。可能，您还打算拥有其他属性（在 photos 旁边），这将使拥有这些单独的对象变得非常有用。
问题是您的代码没有在 forEach 中等待。我强烈建议寻找流并尝试尽可能并行地做事情。有一个非常强大的库可以为您完成这项工作。图书馆是 etl.
您可以从 csv 中并行读取行并并行处理它们，而不是逐行处理。
我试图解释下面代码中的行。希望它有意义。
const etl = require("etl");
const fs = require("fs");
const csvFilePath = `${__dirname }/Inventory.csv`;
const testFolder = "./Images/";
const dirArr = [
"./Images/Subdirectory-A",
"./Images/Subdirectory-B",
"./Images/Subdirectory-C"
];
fs.createReadStream(csvFilePath)
.pipe(etl.csv()) // parse the csv file
.pipe(etl.collect(10)) // this could be any value depending on how many you want to do in parallel.
.pipe(etl.map(async items => {
return Promise.all(items.map(async item => { // Iterate through 10 items
const finalResult = await Promise.all(dirArr.filter(i => i === item.Name).map(async () => { // filter the matching one and iterate
const files = await fs.promises.readdir(testFolder + item.Name); // read all files
const filteredFiles = files.filter(file => file.match(/\.(jpg|jpeg|png|gif)$/i)); // filter out only images
const result = await Promise.all(filteredFiles).map(async file => {
const imgName = `${testFolder}${item.Name}/${file}`;
const bucketUploadResult = await bucket.upload(imgName); // upload image
return bucketUploadResult.metadata.mediaLink;
});
return result; // This contains all the media link for matching files
}));
// eslint-disable-next-line no-console
console.log(finalResult); // Return arrays of media links for files
return finalResult;
}));
}))
.promise()
.then(() => console.log("finsihed"))
.catch(err => console.error(err));
这是一种方法，我们将一些功能提取到一些单独的辅助方法中，然后 trim 提取一些代码。我不得不推断出您的一些要求，但这似乎与我对您原始代码意图的理解非常吻合：
const csv=require('csvtojson')
const fs = require('fs');
const {Storage} = require('@google-cloud/storage');
var serviceAccount = require("./my-firebase-storage-spot.json");
const testFolder = './Images/';
var csvFilePath = './Inventory.csv';
var dirArr = ['./Images/Subdirectory-A','./Images/Subdirectory-B','./Images/Subdirectory-C'];
var allData = [];
// Using nodejs 'path' module ensures more reliable construction of file paths than string manipulation:
const path = require('path');
// Helper function to convert bucket.upload into a Promise
// From other responses, it looks like if you just omit the callback then it will be a Promise
const bucketUpload_p = fileName => new Promise((resolve, reject) => {
bucket.upload(fileName, function (err, file) {
if (err) reject(err);
resolve(file);
});
});
// Helper function to convert readdir into a Promise
// Again, there are other APIs out there to do this, but this is a rl simple solution too:
const readdir_p = dirName => new Promise((resolve, reject) => {
fs.readdir(dirName, function (err, files) {
if (err) reject(err);
resolve(files);
});
});
// Here we're expecting the string that we found in the "Name" property of our JSON from "subscribe".
// It should match one of the strings in `dirArr`, but this function's job ISN'T to check for that,
// we just trust that the code already found the right one.
const getImageFilesFromJson_p = jsonName => new Promise((resolve, reject) => {
const filePath = path.join(testFolder, jsonName);
try {
const files = await readdir_p(filePath);
resolve(files.filter(fileName => fileName.match(/\.(jpg|jpeg|png|gif)$/i)));
} catch (err) {
reject(err);
}
});
csv()
.fromFile(csvFilePath)
.subscribe(async json => {
// Here we appear to be validating that the "Name" prop from the received JSON matches one of the paths that
// we're expecting...? If that's the case, this is a slightly more semantic way to do it.
const nameFromJson = dirArr.find(dirName => json['Name'] === dirName);
// If we don't find that it matches one of our expecteds, we'll reject the promise.
if (!nameFromJson) {
// We can do whatever we want though in this case, I think it's maybe not necessarily an error:
// return Promise.resolve([]);
return Promise.reject('Did not receive a matching value in the Name property from \'.subscribe\'');
}
// We can use `await` here since `getImageFilesFromJson_p` returns a Promise
const imageFiles = await getImageFilesFromJson_p(nameFromJson);
// We're getting just the filenames; map them to build the full path
const fullPathArray = imageFiles.map(fileName => path.join(testFolder, nameFromJson, fileName));
// Here we Promise.all, using `.map` to convert the array of strings into an array of Promises;
// if they all resolve, we'll get the array of file objects returned from each invocation of `bucket.upload`
return Promise.all(fullPathArray.map(filePath => bucketUpload_p(filePath)))
.then(fileResults => {
// So, now we've finished our two asynchronous functions; now that that's done let's do all our data
// manipulation and resolve this promise
// Here we just extract the metadata property we want
const fileResultsMediaLinks = fileResults.map(file => file.metadata.mediaLink);
// Before we return anything, we'll add it to the global array in the format from the original code
allData.push({ photos: fileResultsMediaLinks });
// Returning this array, which is the `mediaLink` value from the metadata of each of the uploaded files.
return fileResultsMediaLinks;
})
}, onError, onComplete);
您正在寻找这个图书馆 ELT。
您可以从 CSV 中并行读取行并并行处理它们，而不是逐行处理。
我已经尝试解释下面代码中的行。希望这是有道理的。
const etl = require("etl");
const fs = require("fs");
const csvFilePath = `${__dirname }/Inventory.csv`;
const testFolder = "./Images/";
const dirArr = [
"./Images/Subdirectory-A",
"./Images/Subdirectory-B",
"./Images/Subdirectory-C"
];
fs.createReadStream(csvFilePath)
.pipe(etl.csv()) // parse the csv file
.pipe(etl.collect(10)) // this could be any value depending on how many you want to do in parallel.
.pipe(etl.map(async items => {
return Promise.all(items.map(async item => { // Iterate through 10 items
const finalResult = await Promise.all(dirArr.filter(i => i === item.Name).map(async () => { // filter the matching one and iterate
const files = await fs.promises.readdir(testFolder + item.Name); // read all files
const filteredFiles = files.filter(file => file.match(/\.(jpg|jpeg|png|gif)$/i)); // filter out only images
const result = await Promise.all(filteredFiles).map(async file => {
const imgName = `${testFolder}${item.Name}/${file}`;
const bucketUploadResult = await bucket.upload(imgName); // upload image
return bucketUploadResult.metadata.mediaLink;
});
return result; // This contains all the media link for matching files
}));
// eslint-disable-next-line no-console
console.log(finalResult); // Return arrays of media links for files
return finalResult;
}));
}))
.promise()
.then(() => console.log("finsihed"))
.catch(err => console.error(err));
我正在编写一些循环遍历 CSV 并在函数内创建 JSON 文件 based on the CSV. Included in the JSON is an array named photos, which is to contain the returned urls for the images that are being uploaded to promise 和 JSON 编译url。在检索到 url 并将其添加到 currentJSON.photos 后，如何使 promise 解析？
const csv=require('csvtojson')
const fs = require('fs');
const {Storage} = require('@google-cloud/storage');
var serviceAccount = require("./my-firebase-storage-spot.json");
const testFolder = './Images/';
var csvFilePath = './Inventory.csv';
var dirArr = ['./Images/Subdirectory-A','./Images/Subdirectory-B','./Images/Subdirectory-C'];
var allData = [];
csv()
.fromFile(csvFilePath)
.subscribe((json)=>{
return new Promise((resolve,reject)=>{
for (var i in dirArr ) {
if (json['Name'] == dirArr[i]) {
var currentJSON = {
"photos" : [],
};
fs.readdir(testFolder+json['Name'], (err, files) => {
files.forEach(file => {
if (file.match(/.(jpg|jpeg|png|gif)$/i)){
var imgName = testFolder + json['Name'] + '/' + file;
bucket.upload(imgName, function (err, file) {
if (err) throw new Error(err);
//returned uploaded img address is found at file.metadata.mediaLink
currentJSON.photos.push(file.metadata.mediaLink);
});
}else {
//do nothing
}
});
});
allData.push(currentJSON);
}
}
resolve();
})
},onError,onComplete);
function onError() {
// console.log(err)
}
function onComplete() {
console.log('finito');
}
我尝试移动 resolve()，还尝试将上传器部分放入 onComplete() 函数（这会产生新的基于 promise 的问题）。
实际上，您的代码没有等待 readdir 回调函数的异步调用，也没有等待 bucket.upload 回调函数的异步调用。
当您使用这些函数的 promise 版本时，异步编码变得更容易。
bucket.upload 将 return 省略回调函数时的承诺，所以这很容易。
对于readdir到return的一个promise，你需要使用fs Promise API:然后就可以使用
基于承诺的 readdir 方法和使用
在您的代码中承诺。
所以使用 fs = require('fs').promises 而不是 fs = require('fs')
有了这些准备，您的代码可以变成这样：
const testFolder = './Images/';
var csvFilePath = './Inventory.csv';
var dirArr = ['./Images/Subdirectory-A','./Images/Subdirectory-B','./Images/Subdirectory-C'];
(async function () {
let arr = await csv().fromFile(csvFilePath);
arr = arr.filter(obj => dirArr.includes(obj.Name));
let allData = await Promise.all(arr.map(async obj => {
let files = await fs.readdir(testFolder + obj.Name);
files = files.filter(file => file.match(/\.(jpg|jpeg|png|gif)$/i));
let photos = await Promise.all(
files.map(async file => {
var imgName = testFolder + obj.Name + '/' + file;
let result = await bucket.upload(imgName);
return result.metadata.mediaLink;
})
);
return {photos};
}));
console.log('finito', allData);
})().catch(err => { // <-- The above async function runs immediately and returns a promise
console.log(err);
});
一些备注：
您的正则表达式存在缺陷。您打算匹配一个文字点，但您没有转义它（已在上面的代码中修复）。
allData将包含一组{ photos: [......] }个对象，我想知道为什么您不希望所有照片元素都成为一个数组的一部分。然而，我保留了你的逻辑，所以上面的代码仍然会在这些块中产生它们。可能，您还打算拥有其他属性（在photos旁边），这将使拥有这些单独的对象变得非常有用。
问题是您的代码没有在 forEach 中等待。我强烈建议寻找流并尝试尽可能并行地做事情。有一个非常强大的库可以为您完成这项工作。图书馆是 etl.
您可以从 csv 中并行读取行并并行处理它们，而不是逐行处理。
我试图解释下面代码中的行。希望它有意义。
const etl = require("etl");
const fs = require("fs");
const csvFilePath = `${__dirname }/Inventory.csv`;
const testFolder = "./Images/";
const dirArr = [
"./Images/Subdirectory-A",
"./Images/Subdirectory-B",
"./Images/Subdirectory-C"
];
fs.createReadStream(csvFilePath)
.pipe(etl.csv()) // parse the csv file
.pipe(etl.collect(10)) // this could be any value depending on how many you want to do in parallel.
.pipe(etl.map(async items => {
return Promise.all(items.map(async item => { // Iterate through 10 items
const finalResult = await Promise.all(dirArr.filter(i => i === item.Name).map(async () => { // filter the matching one and iterate
const files = await fs.promises.readdir(testFolder + item.Name); // read all files
const filteredFiles = files.filter(file => file.match(/\.(jpg|jpeg|png|gif)$/i)); // filter out only images
const result = await Promise.all(filteredFiles).map(async file => {
const imgName = `${testFolder}${item.Name}/${file}`;
const bucketUploadResult = await bucket.upload(imgName); // upload image
return bucketUploadResult.metadata.mediaLink;
});
return result; // This contains all the media link for matching files
}));
// eslint-disable-next-line no-console
console.log(finalResult); // Return arrays of media links for files
return finalResult;
}));
}))
.promise()
.then(() => console.log("finsihed"))
.catch(err => console.error(err));
这是一种方法，我们将一些功能提取到一些单独的辅助方法中，然后 trim 提取一些代码。我不得不推断出您的一些要求，但这似乎与我对您原始代码意图的理解非常吻合：
const csv=require('csvtojson')
const fs = require('fs');
const {Storage} = require('@google-cloud/storage');
var serviceAccount = require("./my-firebase-storage-spot.json");
const testFolder = './Images/';
var csvFilePath = './Inventory.csv';
var dirArr = ['./Images/Subdirectory-A','./Images/Subdirectory-B','./Images/Subdirectory-C'];
var allData = [];
// Using nodejs 'path' module ensures more reliable construction of file paths than string manipulation:
const path = require('path');
// Helper function to convert bucket.upload into a Promise
// From other responses, it looks like if you just omit the callback then it will be a Promise
const bucketUpload_p = fileName => new Promise((resolve, reject) => {
bucket.upload(fileName, function (err, file) {
if (err) reject(err);
resolve(file);
});
});
// Helper function to convert readdir into a Promise
// Again, there are other APIs out there to do this, but this is a rl simple solution too:
const readdir_p = dirName => new Promise((resolve, reject) => {
fs.readdir(dirName, function (err, files) {
if (err) reject(err);
resolve(files);
});
});
// Here we're expecting the string that we found in the "Name" property of our JSON from "subscribe".
// It should match one of the strings in `dirArr`, but this function's job ISN'T to check for that,
// we just trust that the code already found the right one.
const getImageFilesFromJson_p = jsonName => new Promise((resolve, reject) => {
const filePath = path.join(testFolder, jsonName);
try {
const files = await readdir_p(filePath);
resolve(files.filter(fileName => fileName.match(/\.(jpg|jpeg|png|gif)$/i)));
} catch (err) {
reject(err);
}
});
csv()
.fromFile(csvFilePath)
.subscribe(async json => {
// Here we appear to be validating that the "Name" prop from the received JSON matches one of the paths that
// we're expecting...? If that's the case, this is a slightly more semantic way to do it.
const nameFromJson = dirArr.find(dirName => json['Name'] === dirName);
// If we don't find that it matches one of our expecteds, we'll reject the promise.
if (!nameFromJson) {
// We can do whatever we want though in this case, I think it's maybe not necessarily an error:
// return Promise.resolve([]);
return Promise.reject('Did not receive a matching value in the Name property from \'.subscribe\'');
}
// We can use `await` here since `getImageFilesFromJson_p` returns a Promise
const imageFiles = await getImageFilesFromJson_p(nameFromJson);
// We're getting just the filenames; map them to build the full path
const fullPathArray = imageFiles.map(fileName => path.join(testFolder, nameFromJson, fileName));
// Here we Promise.all, using `.map` to convert the array of strings into an array of Promises;
// if they all resolve, we'll get the array of file objects returned from each invocation of `bucket.upload`
return Promise.all(fullPathArray.map(filePath => bucketUpload_p(filePath)))
.then(fileResults => {
// So, now we've finished our two asynchronous functions; now that that's done let's do all our data
// manipulation and resolve this promise
// Here we just extract the metadata property we want
const fileResultsMediaLinks = fileResults.map(file => file.metadata.mediaLink);
// Before we return anything, we'll add it to the global array in the format from the original code
allData.push({ photos: fileResultsMediaLinks });
// Returning this array, which is the `mediaLink` value from the metadata of each of the uploaded files.
return fileResultsMediaLinks;
})
}, onError, onComplete);
您正在寻找这个图书馆 ELT。
您可以从 CSV 中并行读取行并并行处理它们，而不是逐行处理。
我已经尝试解释下面代码中的行。希望这是有道理的。
const etl = require("etl");
const fs = require("fs");
const csvFilePath = `${__dirname }/Inventory.csv`;
const testFolder = "./Images/";
const dirArr = [
"./Images/Subdirectory-A",
"./Images/Subdirectory-B",
"./Images/Subdirectory-C"
];
fs.createReadStream(csvFilePath)
.pipe(etl.csv()) // parse the csv file
.pipe(etl.collect(10)) // this could be any value depending on how many you want to do in parallel.
.pipe(etl.map(async items => {
return Promise.all(items.map(async item => { // Iterate through 10 items
const finalResult = await Promise.all(dirArr.filter(i => i === item.Name).map(async () => { // filter the matching one and iterate
const files = await fs.promises.readdir(testFolder + item.Name); // read all files
const filteredFiles = files.filter(file => file.match(/\.(jpg|jpeg|png|gif)$/i)); // filter out only images
const result = await Promise.all(filteredFiles).map(async file => {
const imgName = `${testFolder}${item.Name}/${file}`;
const bucketUploadResult = await bucket.upload(imgName); // upload image
return bucketUploadResult.metadata.mediaLink;
});
return result; // This contains all the media link for matching files
}));
// eslint-disable-next-line no-console
console.log(finalResult); // Return arrays of media links for files
return finalResult;
}));
}))
.promise()
.then(() => console.log("finsihed"))
.catch(err => console.error(err));