Last active
May 22, 2016 08:59
-
-
Save binarymax/d3691180e65ff7f0dec5 to your computer and use it in GitHub Desktop.
Parses news.ycombinator.com comment archive into word2vec digestable format.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env node | |
var linestream = require('line-stream'); | |
var htmldecode = require('htmldec'); | |
var s = linestream(); | |
var numbers = "zero,one,two,three,four,five,six,seven,eight,nine".split(','); | |
var reletter = /[a-z_]/i; | |
var renumber = /[0-9]/; | |
var reclose = /\<\/[^\>]+\>/g; | |
var respace = / +/g; | |
var reopen = /\<[^\>]+\>/g; | |
var reapos = /\'/g; | |
var reund1 = / _/g; | |
var reund2 = /_ /g; | |
var reurl = /(ftp|http|https):\/\/(\w+:{0,1}\w*@)?(\S+)(:[0-9]+)?(\/|\/([\w#!:.?+=&%@!\-\/]))?/g; | |
s.on('data',function(line) { | |
var json; | |
var text; | |
var chr = ""; | |
var out = ""; | |
try { | |
json = JSON.parse(line); | |
} catch (ex) { | |
return; | |
} | |
if (!json.body) return; | |
if (!json.body.text) return; | |
text = json.body.text||''; | |
text = htmldecode(text); | |
text = text.replace(reopen,' ').replace(reclose,' '); | |
text = text.replace(reurl,' '); | |
text = text.replace(reapos,'_').replace(reund1,'').replace(reund2,''); | |
for (var i=0, l=text.length; i<l; i++) { | |
chr = text[i]; | |
if(reletter.test(chr)) { | |
out+=chr.toLowerCase(); | |
} else if (renumber.test(chr)) { | |
out+=numbers[parseInt(chr)]; | |
} else { | |
out += ' '; | |
} | |
} | |
out += ' '; | |
out = out.replace(respace,' '); | |
process.stdout.write(out); | |
}); | |
process.stdin.pipe(s); |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment