gistfile1.js

/*
  invert.js
  
  given two lines of interlinear linguistic annotation on stdin, like:

  Ehiwac    c-a-kәri    sәgәbehem    h-ә-k-ec    әrɨgeh=i.
  spirit:8PL   8PL-R-say   spirit:7PL   7PL-R-give-8PL   sick=REL

  return a data structure like this:

[
  {
    'word': 'Ehiwac',
    'gloss': 'spirit'
  },
  {
    'word': 'c-a-kәri',
    'gloss': '8PL-R-say'
  }
  // etc
]

*/


var lines = [],
    words = [],
    glosses = [], 
    stdin = process.openStdin(),
    sys = require('sys');
    
stdin.setEncoding('utf8');

function trim(text){
  var rtrim = /^(\s|\u00A0)+|(\s|\u00A0)+$/g,
  return (text || "").replace( rtrim, "" );
};

function extractLines(text){
  var text = trim(text);
  return text.split('\n');
}

stdin.on('data', function (chunk) {
  var lines = extractLines(chunk)
  for(var i=0;i<lines.length;i++){ console.log(lines[i]) }
});