If you do something like a.pipe(b), the return value from that call is b.
So, I suspect one trouble you're having is when you do:
rs.pipe(es.split()) // split stream to break on newlines
rs.pipe(es.map(function(line) {
(function() {
callback(line)
})();
})
I'm assuming that you want to split the file into lines, and then operate
on each line. Try giving this a shot:
rs.pipe(es.split()) // split stream to break on newlines
.pipe(es.map(function(line) {
(function() {
callback(line)
})();
})
Notice that I'm calling pipe on the result of rs.pipe.
Does that fix anything?
On Friday, April 24, 2015 at 11:23:18 AM UTC-6, Marco Ippolito wrote:
>
> Hi all,
> I'm trying to extract in "streaming-mode" a list of lines from a txt file
> and than process them one-by-one in order, for example (or could be
> something else) to detect the language.
>
> This is my code:
>
> var path = require('path');
> var fs = require('fs');
> var util = require('util');
> var stream = require('stream');
> var es = require('event-stream');
> var cld = require('cld')
>
> var normalized_path = path.normalize(process.argv[2])
> var unified_unique_urls_file_path = path.join(process.cwd(),
> normalized_path)
> var unified_unique_urls_file_name = normalized_path + "_unified_unique.txt"
> var unified_unique_urls_file = unified_unique_urls_file_path + "/" +
> unified_unique_urls_file_name
>
> var lineNr = 1
> var rs = fs.createReadStream(unified_unique_urls_file)
>
> rs.pipe(es.split()) // split stream to break on newlines
> rs.pipe(es.map(function(line) {
> (function() {
> callback(line)
> })();
> })
> .on('error', function() {
> console.log('Error while reading file.');
> })
> .on('end', function() {
> console.log('Read entire file.');
> })
> );
>
> function callback(line) {
> var lineS = line.toString()
> var results_object = {};
> cld.detect(lineS, function(err, result) {
> //console.log(result);
> if (result != "undefined")
> results_object[lineS] = result["languages"][0]["code"]
> else
> results_object[lineS] = "undefined"
> });
> for (var key in results_object) {
> if (results_object.hasOwnProperty(key)) {
> //alert(key + " -> " + results_object[key]);
> console.log(key + " -> " + results_object[key]);
> }
> }
> }
>
> The problem is that it seems that the processing within the callback is
> executed only for the last line of the file:
> time ./languageDetection.js "baruffaldi_spa"
> http://aziende.corriere.it/2599852/baruffaldi-spa
> .....
> http://www.youinweb.it/profiles_it/20097/baruffaldi-(spa)_320924.htm
> http://www.baruffaldi.it
> -> it
>
> Any idea how to solve it?
>
> Marco
>
>
--
Job board: http://jobs.nodejs.org/
New group rules:
https://gist.github.com/othiym23/9886289#file-moderation-policy-md
Old group rules:
https://github.com/joyent/node/wiki/Mailing-List-Posting-Guidelines
---
You received this message because you are subscribed to the Google Groups
"nodejs" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To post to this group, send email to [email protected].
To view this discussion on the web visit
https://groups.google.com/d/msgid/nodejs/36b25ca7-bcf6-4e75-898d-8b3098287111%40googlegroups.com.
For more options, visit https://groups.google.com/d/optout.
