Pass data between gulp 4 tasks, pipes or commandline - javascript

I'm trying to do in my opinion a simple task but can't figure it out. Can't find it on google or here. Maybe i'm doing it completely wrong.
I need to change a property in a json file with gulp 4. To get the new value of the property I have another task or pipe (I don't care :-)) and want to pass it along.
Also, how to pass variable from command line? so in example: gulp release -branchname "foobar"
How can I do this. I know there are similar question here but nothing is working for me...
var gulp = require('gulp');
var git = require('gulp-git');
var jeditor = require("gulp-json-editor");
var paths = {
manifest: "vss-extension.json"
}
function getBranchName(){
console.log("Get the current branch name");
return git.revParse({args:'--abbrev-ref HEAD'}, function (err, branch) {
console.log('current git branch: ' + branch);
var currentBranch = branch;
return currentBranch;
});
// console.log("Current branch is: "+ branchName);
// return branchName;
}
function updateExtensionManifestVersion(foo){
var x = 10;
gulp.src(paths.manifest)
.pipe(jeditor(function(json) {
console.log("Append current branchname " + currentBranch + " to extension manifest id");
var currentId = json.id;
console.log("Current manifest id: "+ currentId);
// var branchName = git.revParse({args:'--abbrev-ref HEAD'}, function (err, branch) {
// console.log('current git branch: ' + branch);
// return branch;
// });
// console.log(branchName.branch);
var newId = currentId + "-" + branchName;
console.log("New manifest id: " + newId);
json.id = newId;
return json;
}))
.pipe(gulp.dest(paths.manifest));
}
gulp.task('release', gulp.series(getBranchName, updateExtensionManifestVersion, function(done) {
console.log("release is done");
done();
}));

To pass variables from command line you can use yargs as explained in this answer Pass Parameter to Gulp Task.
If you want to pass data between tasks set a global variable that will be accessible to both.

Related

Javascript Await Changes Local Variables? [closed]

Closed. This question is not reproducible or was caused by typos. It is not currently accepting answers.
This question was caused by a typo or a problem that can no longer be reproduced. While similar questions may be on-topic here, this one was resolved in a way less likely to help future readers.
Closed 3 years ago.
Improve this question
Anyone able to explain what I'm doing wrong with my use of asynchronous functions in Javascript?
Basically, I must use an asynchronous in my Node.js code to grab an open port for me to use. There is a local variable that is being set outside of the asynchronous call that I can access/use just fine until I await for the asynchronous function to return. After that, the local variable is undefined.
(async () => {
console.log("CHECK AFTER ASYNC1: " + csvFilePath);
// First, grab a valid open port
var port;
while (!port || portsInProcess.indexOf(port) >= 0) {
console.log("CHECK AFTER ASYNC2: " + csvFilePath);
port = await getPort();
console.log(port);
}
console.log("CHECK AFTER ASYNC3: " + csvFilePath);
portsInProcess.push(port);
// ... more code below...
Checks #1 and 2 are fine for the csvFilePath variable, but check #3 shows that it's undefined. The port number, however, is fine. This leads me to believe that there's some weirdness with asynchronous function calls in Javascript that ONLY affects local variables; the global variables I use further down are just fine. Unfortunately here, I cannot make the csvFilePath variable global since that will introduce race conditions on that variable too (which I'm preventing elsewhere; the while loop is to help prevent race conditions on the port number, which is basically unused in my simple tests on localhost).
Just in case it's helpful, here's the output I'm getting:
CHECK AFTER ASYNC1: data/text/crescent_topics.csv
CHECK AFTER ASYNC2: data/text/crescent_topics.csv
58562
CHECK AFTER ASYNC3: null
It might also be worth mentioning it's really only those first few lines of code to dynamically grab an open port that are the lines of code I added. The code that I had before which used a fixed port number worked just fine (including this csvFilePath variable remaining stable).
My understanding of the await functionality was that it makes the asynchronous function act more or less synchronously, which is what seems to be happening here; the code I have farther down that uses the port number is not running until after the port number is set. (But even if that wasn't the case, why is the csvFilePath variable being unset since I'm not altering it or using it in any way here?)
EDIT: Here's some more code to provide additional context
var spawn = require('child_process').spawn;
var fs = require("fs");
var async = require('async');
var zmq = require('zmq');
var readline = require('readline');
const getPort = require('get-port');
/* Export the Nebula class */
module.exports = Nebula;
/* Location of the data for the Crescent dataset */
var textDataPath = "data/text/";
var crescentRawDataPath = textDataPath + "crescent_raw";
var crescentTFIDF = textDataPath + "crescent tfidf.csv";
var crescentTopicModel = textDataPath + "crescent_topics.csv";
/* Location of the data for the UK Health dataset */
var ukHealthRawDataPath = textDataPath + "uk_health_raw";
var ukHealthTFIDF = textDataPath + "uk_health.csv";
/* Map CSV files for text data to raw text location */
var textRawDataMappings = {};
textRawDataMappings[crescentTFIDF] = crescentRawDataPath;
textRawDataMappings[crescentTopicModel] = crescentRawDataPath;
textRawDataMappings[ukHealthTFIDF] = ukHealthRawDataPath;
textRawDataMappings[textDataPath + "uk_health_sm.csv"] = ukHealthRawDataPath;
/* The pipelines available to use */
var flatTextUIs = ["cosmos", "composite", "sirius", "centaurus"];
var pipelines = {
andromeda: {
file: "pipelines/andromeda.py",
defaultData: "data/highD/Animal_Data_study.csv"
},
cosmos: {
file: "pipelines/cosmos.py",
defaultData: textDataPath + "crescent tfidf.csv"
},
sirius: {
file: "pipelines/sirius.py",
defaultData: "data/highD/Animal_Data_paper.csv"
},
centaurus: {
file: "pipelines/centaurus.py",
defaultData: "data/highD/Animal_Data_paper.csv"
},
twitter: {
file: "pipelines/twitter.py",
},
composite: {
file: "pipelines/composite.py",
defaultData: textDataPath + "crescent tfidf.csv"
},
elasticsearch: {
file: "pipelines/espipeline.py",
args: []
}
};
/* The locations of the different types of datasets on the server */
var textDataFolder = "data/text/";
var highDDataFolder = "data/highD/";
var customCSVFolder = "data/customCSV/";
var sirius_prototype = 2;
// An array to track the ports being processed to eliminate race conditions
// as much as possible
var portsInProcess = [];
var nextSessionNumber = 0;
var usedSessionNumbers = [];
/* Nebula class constructor */
function Nebula(io, pipelineAddr) {
/* This allows you to use "Nebula(obj)" as well as "new Nebula(obj)" */
if (!(this instanceof Nebula)) {
return new Nebula(io);
}
/* The group of rooms currently active, each with a string identifier
* Each room represents an instance of a visualization that can be shared
* among clients.
*/
this.rooms = {};
this.io = io;
/* For proper use in callback functions */
var self = this;
/* Accept new WebSocket clients */
io.on('connection', function(socket) {
// Skipped some irrelevant Socket.io callbacks
**// Use the csvFilePath to store the name of a user-defined CSV file
var csvFilePath = null;**
/* Helper function to tell the client that the CSV file is now ready for them
* to use. They are also sent a copy of the data
*/
var csvFileReady = function(csvFilePath) {
// Let the client know that the CSV file is now ready to be used on
// the server
socket.emit("csvDataReady");
// Prepare to parse the CSV file
var csvData = [];
const rl = readline.createInterface({
input: fs.createReadStream(csvFilePath),
crlfDelay: Infinity
});
// Print any error messages we encounter
rl.on('error', function (err) {
console.log("Error while parsing CSV file: " + csvFilePath);
console.log(err);
});
// Read each line of the CSV file one at a time and parse it
var columnHeaders = [];
var firstColumnName;
rl.on('line', function (data) {
var dataColumns = data.split(",");
// If we haven't saved any column names yet, do so first
if (columnHeaders.length == 0) {
columnHeaders = dataColumns;
firstColumnName = columnHeaders[0];
}
// Process each individual line of data in the CSV file
else {
var dataObj = {};
var i;
for (i = 0; i < dataColumns.length; i++) {
var key = columnHeaders[i];
var value = dataColumns[i];
dataObj[key] = value
}
csvData.push(dataObj);
}
});
// All lines are read, file is closed now.
rl.on('close', function () {
// On certain OSs, like Windows, an extra, blank line may be read
// Check for this and remove it if it exists
var lastObservation = csvData[csvData.length-1];
var lastObservationKeys = Object.keys(lastObservation);
if (lastObservationKeys.length = 1 && lastObservation[lastObservationKeys[0]] == "") {
csvData.pop();
}
// Provide the CSV data to the client
socket.emit("csvDataReadComplete", csvData, firstColumnName);
});
};
**/* Allows the client to specify a CSV file already on the server to use */
socket.on("setCSV", function(csvName) {
console.log("setCSV CALLED");
csvFilePath = "data/" + csvName;
csvFileReady(csvFilePath);
console.log("CSV FILE SET: " + csvFilePath);
});**
// Skipped some more irrelevant callbacks
/* a client/ a room. If the room doesn't next exist yet,
* initiate it and send the new room to the client. Otherwise, send
* the client the current state of the room.
*/
socket.on('join', function(roomName, user, pipeline, args) {
console.log("Join called for " + pipeline + " pipeline; room " + roomName);
socket.roomName = roomName;
socket.user = user;
socket.join(roomName);
console.log("CSV FILE PATH: " + csvFilePath);
var pipelineArgsCopy = [];
if (!self.rooms[roomName]) {
var room = {};
room.name = roomName;
room.count = 1;
room.points = new Map();
room.similarity_weights = new Map();
if (pipeline == "sirius" || pipeline == "centaurus") {
room.attribute_points = new Map();
room.attribute_similarity_weights = new Map();
room.observation_data = [];
room.attribute_data = [];
}
/* Create a pipeline client for this room */
console.log("CHECK BEFORE ASYNC: " + csvFilePath);
**// Here's the code snippet I provided above**
**(async () => {
console.log("CHECK AFTER ASYNC1: " + csvFilePath);
// First, grab a valid open port
var port;
while (!port || portsInProcess.indexOf(port) >= 0) {
console.log("CHECK AFTER ASYNC2: " + csvFilePath);
port = await getPort();
console.log(port);
}
console.log("CHECK AFTER ASYNC3: " + csvFilePath);**
portsInProcess.push(port);
console.log("CHECK AFTER ASYNC4: " + csvFilePath);
if (!pipelineAddr) {
var pythonArgs = ["-u"];
if (pipeline in pipelines) {
// A CSV file path should have already been set. This
// file path should be used to indicate where to find
// the desired file
console.log("LAST CHECK: " + csvFilePath);
if (!csvFilePath) {
csvFilePath = pipelines[pipeline].defaultData;
}
console.log("FINAL CSV FILE: " + csvFilePath);
pipelineArgsCopy.push(csvFilePath);
// If the UI supports reading flat text files, tell the
// pipeline where to find the files
if (flatTextUIs.indexOf(pipeline) >= 0) {
pipelineArgsCopy.push(textRawDataMappings[csvFilePath]);
}
// Set the remaining pipeline args
pythonArgs.push(pipelines[pipeline].file);
pythonArgs.push(port.toString());
if (pipeline != "twitter" && pipeline != "elasticsearch") {
pythonArgs = pythonArgs.concat(pipelineArgsCopy);
}
}
else {
pythonArgs.push(pipelines.cosmos.file);
pythonArgs.push(port.toString());
pythonArgs.push(pipelines.cosmos.defaultData);
pythonArgs.push(crescentRawDataPath);
}
// used in case of CosmosRadar
for (var key in args) {
if (args.hasOwnProperty(key)) {
pythonArgs.push("--" + key);
pythonArgs.push(args[key]);
}
}
// Dynamically determine which distance function should be
// used
if (pythonArgs.indexOf("--dist_func") < 0) {
if (pipeline === "twitter" || pipeline === "elasticsearch" ||
csvFilePath.startsWith(textDataPath)) {
pythonArgs.push("--dist_func", "cosine");
}
else {
pythonArgs.push("--dist_func", "euclidean");
}
}
console.log(pythonArgs);
console.log("");
var pipelineInstance = spawn("python2.7", pythonArgs, {stdout: "inherit"});
pipelineInstance.on("error", function(err) {
console.log("python2.7.exe not found. Trying python.exe");
pipelineInstance = spawn("python", pythonArgs,{stdout: "inherit"});
pipelineInstance.stdout.on("data", function(data) {
console.log("Pipeline: " + data.toString());
});
pipelineInstance.stderr.on("data", function(data) {
console.log("Pipeline error: " + data.toString());
});
});
/* Data received by node app from python process,
* ouptut this data to output stream(on 'data'),
* we want to convert that received data into a string and
* append it to the overall data String
*/
pipelineInstance.stdout.on("data", function(data) {
console.log("Pipeline STDOUT: " + data.toString());
});
pipelineInstance.stderr.on("data", function(data) {
console.log("Pipeline error: " + data.toString());
});
room.pipelineInstance = pipelineInstance;
}
/* Connect to the pipeline */
pipelineAddr = pipelineAddr || "tcp://127.0.0.1:" + port.toString();
room.pipelineSocket = zmq.socket('pair');
room.pipelineSocket.connect(pipelineAddr);
pipelineAddr = null;
portsInProcess.splice(portsInProcess.indexOf(port), 1);
/* Listens for messages from the pipeline */
room.pipelineSocket.on('message', function (msg) {
self.handleMessage(room, msg);
});
self.rooms[roomName] = socket.room = room;
invoke(room.pipelineSocket, "reset");
})();
}
else {
socket.room = self.rooms[roomName];
socket.room.count += 1;
if (pipeline == "sirius" || pipeline == "centaurus") {
socket.emit('update', sendRoom(socket.room, true), true);
socket.emit('update', sendRoom(socket.room, false), false);
}
else {
socket.emit('update', sendRoom(socket.room));
}
}
// Reset the csvFilePath to null for future UIs...
// I don't think this is actually necessary since
// csvFilePath is local to the "connections" message,
// which is called for every individual room
csvFilePath = null;
});
// Skipped the rest of the code; it's irrelevant
});
}
Full printouts:
setCSV CALLED
CSV FILE SET: data/text/crescent_topics.csv
Join called for sirius pipeline; room sirius0
CSV FILE PATH: data/text/crescent_topics.csv
CHECK BEFORE ASYNC: data/text/crescent_topics.csv
CHECK AFTER ASYNC1: data/text/crescent_topics.csv
CHECK AFTER ASYNC2: data/text/crescent_topics.csv
58562
CHECK AFTER ASYNC3: null
CHECK AFTER ASYNC4: null
LAST CHECK: null
FINAL CSV FILE: data/highD/Animal_Data_paper.csv
[ '-u',
'pipelines/sirius.py',
'58562',
'data/highD/Animal_Data_paper.csv',
undefined,
'--dist_func',
'euclidean' ]
Since bolding of code doesn't work, just search for the "**" to find the relevant pieces I've marked.
TL;DR There's a lot of communication happening between the client and server to establish an individualized communication that is directly linked to a specific dataset. The user has the ability to upload a custom CSV file to the system, but the code I'm working with right now is just trying to select an existing CSV file on the server, so I omitted the callbacks for the custom CSV file. Once the file has been selected, the client asks to "join" a room/session. The case I'm working with right now assumes that this is a new room/session as opposed to trying to do some shared room/session with another client. (Yes, I know, the code is messy for sharing rooms/sessions, but it works for the most part for now and is not my main concern.) Again, all this code worked just fine before the asynchronous code was added (and using a static port variable), so I don't know what changed so much by adding it.
Since you now included the whole code context, we can see that the issue is that the code after your async IIFE is what is causing the problem.
An async function returns a promise as soon as it hits an await. And, while that await is waiting for its asynchronous operation, the code following the call to the async function runs. In your case, you're essentially doing this:
var csvFilePath = someGoodValue;
(async () => {
port = await getPort();
console.log(csvFilePath); // this will be null
})();
csvFilePath = null; // this runs as soon as the above code hits the await
So, as soon as you hit your first await, the async function returns a promise and the code following it continues to run, hitting the line of code that resets your csvFilePath.
There are probably cleaner ways to restructure your code, but a simple thing you could do is this:
var csvFilePath = someGoodValue;
(async () => {
port = await getPort();
console.log(csvFilePath); // this will be null
})().finally(() => {
csvFilePath = null;
});
Note: .finally() is supported in node v10+. If you're using an older version, you can reset the path in both .then() and .catch().
Or, as your comment says, maybe you can just remove the resetting of the csvFilePath entirely.
I realized after some silly tests I tried that I'm resetting csvFilePath to null outside the asynchronous call, which is what is causing the error... Oops!

How do I make JakeJS watch work reliably with Vim?

I'm using a Jakefile to help me update Wordpress pages from the command line. I'm using Jake's watch task to re-build ever time I edit a file. When I edit a file with Vim, after the first successful build, Jake fails with following error :
WatchTask started for: default
cp home.html dist/home.html
exec wp --path=../wordpress post list --post_type=page --format=json --fields=ID,post_name { silent: true }
exec wp --path=../wordpress post update 2 dist/home.html --post_type=page
Success: Updated post 2.
jake aborted.
Error: File-task home.html has no existing file, and no action to create one.
at FileBase.isNeeded (/usr/local/lib/node_modules/jake/lib/task/file_task.js:50:17)
at TaskBase.run (/usr/local/lib/node_modules/jake/lib/task/task.js:256:26)
(See full trace by running task with --trace)
I've tried using a sleep function in the rule to delay the rebuild. I tried this because Vim, when saving a file, write the contents to a new temp file and then renames the new temp file to the original file name. I think the build fails because it's trying to build before the file is fully renamed. Using the sleep doesn't work reliably, it may work once or twice but then it fails the same way as above.
Here is my Jakefile:
var shell = require('shelljs');
var sleep = require('sleep');
shell.config.verbose = true;
const destDir = 'dist';
const wpDir = '../wordpress';
var files = new jake.FileList();
files.include('*.html');
var outputFiles = files.toArray().map(function(fileName){
return destDir + '/' + fileName;
});
var sourceFile = function(name) {
return name.substr(name.lastIndexOf('/') + 1);
}
function objectToStr(object) {
var s = '';
for(var property in object){
s += property + ': ' + object[property] + '\n';
}
return s;
}
function rmExt(name) {
return name.substr(0, name.lastIndexOf('.'));
}
directory(destDir);
task('default', [destDir].concat(outputFiles));
task('clean', function() {
jake.rmRf(destDir);
});
rule('dist/%.html', sourceFile, function() {
shell.cp(this.source, this.name);
var pages = JSON.parse(shell.exec('wp --path=' + wpDir
+ ' post list --post_type=page --format=json --fields=ID,post_name',
{ silent: true }).stdout);
var postId = null;
var l = pages.length;
for(var i = 0; i < l; i++){
if(pages[i].post_name === rmExt(this.source)){
postId = pages[i].ID;
break;
}
}
if(postId !== null){
shell.exec('wp --path=' + wpDir + ' post update ' + postId
+ ' ' + this.name + ' --post_type=page');
}else{
shell.echo('Unable to find matching post ID for file: ' + this.name);
}
shell.echo('1');
sleep.sleep(2);
shell.echo('2');
});
watchTask('watch', ['default'], function() {
this.watchFiles.include('*.html');
}
I found a reliable solution using the library node-watch. I replaced the watchTask with a normal Jake task and invoked the task I wanted to call using node-watch to watch the current working directory. The library node-watch is able filter files based on regex so the watch won't be trigger for the Vim swap file and the like. Below is the code I used:
task('watch', function() {
var defaultTask = jake.Task['default'];
defaultTask.invoke();
defaultTask.reenable(true);
watch('./', { filter: /.*.html$/ }, function(evt, name) {
defaultTask.invoke();
defaultTask.reenable(true);
});
});
Note: I also invoked the task I want to call when the watch task is first run to make sure any changes made before the watch started are built.

Node.js require caching

I am really stuck by nodejs cache system. I have this structure for my project :
Project/
apps/
jobs_processor/
app.js
processors.js
processors/
libs/
queue_manager.js
queue_manager.js require processors.js
var processors = require("../apps/jobs_processor/processors.js");
app.js require also processor.js
var processors = require("./processors.js");
If I take into account the documentation, I must have the same path may be to obtain the same object, is that right ? If so, how can I achieve that (have the same path) ?
Thanks.
EDIT:
If found a solution to my problem.
Here is the first version of queue_manager.js file
var _ = require("lodash");
var Utils = require("./utilities");
var Processors = require("../apps/jobs_processor/processors");
var Logger = require("./logger");
var QUEUES_CACHE = {};
exports.createJob = createJob;
exports.getCacheObject = getCacheObject;
function createJob(name, data) {
var cacheId = name.replace(/ /g, "_");
Logger.info("Cache ID: " + cacheId);
if (!QUEUES_CACHE[ cacheId ]) {
_.each(Processors, function (processor) {
Logger.debug("PROCESSOR NAME: " + processor.name);
Logger.debug("JOB NAME: " + name);
if (processor.name === name)
QUEUES_CACHE[ cacheId ] = processor;
});
if (!QUEUES_CACHE[ cacheId ])
throw new Error("Processor for job \"" + name + "\" not found.");
}
Logger.debug(Object.keys(QUEUES_CACHE));
return QUEUES_CACHE[ cacheId ].queue.add(data);
}
function getCacheObject() {
return QUEUES_CACHE;
}
And now the last version of the same file
var _ = require("lodash");
var Utils = require("./utilities");
var Logger = require("./logger");
exports.createJob = createJob;
function createJob(name, data) {
var Processors = require("../apps/jobs_processor/processors");
var processor;
_.each(Processors, function (element) {
Logger.debug("Processor name: " + element.name);
if (element.name === name)
processor = element;
});
return processor.queue.add(data);
}
Each time that i called createJob method, I require the processors module which is an array of each job processor that I have created.
Node.js will resolve the path before caching the module.
As long as your relative paths resolve to the same absolute path on disk, you're fine.

Passing a variable to PhantomJS via exec

I'm getting started with Grunt and wanting to pass a variable to a PhantomJS script I'm running via exec. What I want to be able to do is pass a url in for the script to take the screen capture from. Any help would be greatly appreciated, thanks!
Darren
Grunt script
exec('phantomjs screenshot.js',
function (error, stdout, stderr) {
// Handle output
}
);
screenshot.js
var page = require('webpage').create();
page.open('http://google.com', function () {
page.render('google.png');
phantom.exit();
});
Command-line arguments are accessible via module require('system').args (Module System). The first one is always the script name, which is then followed by the subsequent arguments
This script will enumerate all arguments and write out to console.
var args = require('system').args;
if (args.length === 1) {
console.log('Try to pass some arguments when invoking this script!');
}
else {
args.forEach(function(arg, i) {
console.log(i + ': ' + arg);
});
}
In your case, the solution is
Grunt
exec('phantomjs screenshot.js http://www.google.fr',
function (error, stdout, stderr) {
// Handle output
}
);
screenshot.js
var page = require('webpage').create();
var address = system.args[1];
page.open(address , function () {
page.render('google.png');
phantom.exit();
});
Here is an easy way to pass and pick args that are applicable. Very flexible and easy to maintain.
Use like:
phantomjs tests/script.js --test-id=457 --log-dir=somedir/
OR
phantomjs tests/script.js --log-dir=somedir/ --test-id=457
OR
phantomjs tests/script.js --test-id=457 --log-dir=somedir/
OR
phantomjs tests/script.js --test-id=457
Script:
var system = require('system');
// process args
var args = system.args;
// these args will be processed
var argsApplicable = ['--test-id', '--log-dir'];
// populated with the valid args provided in availableArgs but like argsValid.test_id
var argsValid = {};
if (args.length === 1) {
console.log('Try to pass some arguments when invoking this script!');
} else {
args.forEach(function(arg, i) {
// skip first arg which is script name
if(i != 0) {
var bits = arg.split('=');
//console.log(i + ': ' + arg);
if(bits.length !=2) {
console.log('Arguement has wrong format: '+arg);
}
if(argsApplicable.indexOf(bits[0]) != -1) {
var argVar = bits[0].replace(/\-/g, '_');
argVar = argVar.replace(/__/, '');
argsValid[argVar] = bits[1];
}
}
});
}
// enable below to test args
//require('utils').dump(argsValid);
//phantom.exit();

Crypto module - Node.js

Which is the simplest way to compare a hash of a file without storing it in a database?
For example:
var filename = __dirname + '/../public/index.html';
var shasum = crypto.createHash('sha1');
var s = fs.ReadStream(filename);
s.on('data', function(d) {
shasum.update(d);
});
s.on('end', function() {
var d = shasum.digest('hex');
console.log(d + ' ' + filename);
fs.writeFile(__dirname + "/../public/log.txt", d.toString() + '\n', function(err) {
if(err) {
console.log(err);
} else {
console.log("The file was saved!");
}
});
});
The above code returns the hash of the HTML file. If I edit the file how can I know if it has been changed? In other words, how can I know if the hash has been changed?
Any suggestions?
Edited
Now the hash is being saved in the log file. How can I retrieve the hash from the file and match it with the new generated one? A code example would be awesome to give me a better understanding.
There is no difference with this question, but it isn't clear for me yet how to implement it.
If you're looking for changes on a file, then you can use one of Node's filesystem functions, fs.watch. This is how it's used:
fs.watch(filename, function (event, filename) {
//event is either 'rename' or 'change'
//filename is the name of the file which triggered the event
});
The watch function is however not very consistent, so you can use fs.watchFile as an alternative. fs.watchFile uses stat polling, so it's quite a bit slower than fs.watch, which detects file changes instantly.
Watching a file will return an instance of fs.FSWatcher, which has the events change and error. Calling .close will stop watching for changes on the file.
Here's an example relating to your code:
var filename = __dirname + '/../public/index.html';
var shasum = crypto.createHash('sha1');
var oldhash = null;
var s = fs.ReadStream(filename);
s.on('data', function(d) {
shasum.update(d);
});
s.on('end', function() {
var d = shasum.digest('hex');
console.log(d + ' ' + filename);
oldhash = d.toString();
fs.writeFile(__dirname + "/../public/log.txt", d.toString() + '\n', function(err) {
if(err) {
console.log(err);
}
else {
console.log("The file was saved!");
}
});
});
//watch the log for changes
fs.watch(__dirname + "/../public/log.txt", function (event, filename) {
//read the log contents
fs.readFile(__dirname + "/../public/log.txt", function (err, data) {
//match variable data with the old hash
if (data == oldhash) {
//do something
}
});
});
What's the difference between this question and the previous one you asked? If you're not wanting to store it in a database, then store it as a file. If you want to save the hash for multiple files, then maybe put them in a JSON object and write them out as a .json file so they're easy to read/write.
EDIT
Given what you added to your question, it should be pretty simple. You might write a function to do check and re-write:
function updateHash (name, html, callback) {
var sha = crypto.createHash('sha1');
sha.update(html);
var newHash = sha.digest('hex');
var hashFileName = name + '.sha';
fs.readFile(hashFileName, 'utf8', function (err, oldHash) {
var changed = true;
if (err)
console.log(err); // probably indicates the file doesn't exist, but you should consider doing better error handling
if (oldHash === newHash)
changed = false;
fs.writeFile(hashFileName, newHash, { encoding: 'utf8' }, function (err) {
callback(err, changed);
});
});
}
updateHash('index.html', "<html><head><title>...", function (err, isChanged) {
// do something with this information ?
console.log(isChanged);
});

Categories