JS: Convert text into object array

Question

I need to convert this...

# 4.0.0 - 2016-01-01
- some text without category

# 3.12.0 - 2016-02-01
- Category: some text

# 3.11.4 - 2016-03-01
- Category: some multiple text
- Something: some text
- Anything: more text

...into an (object)array. I don't know how to keep all elements connected to its version.

The result should be look like this (example for last block)

[
    { 
        major: 3,
        minor: 11,
        patch = 4,
        date = '2016-03-01',
        entries = [
            { category: 'Category', 'some multiple text' },
            { category: 'Something', 'some text' },
            { category: 'Anything', 'more text' }
        ]
    }
]

As you can see in the first block, in entries the field category is optional.

This is how I try do it:

var lines = text.split('\n');
for(var i = 0;i < lines.length;i++){
    var meta = lines[i].split(' ');
    var version = meta[1].split('.');
    result['major'] = version[0];
    result['minor'] = version[1];
    result['patch'] = version[2];
    result['date'] = meta[3]
}

But this only works for the first line of each block.

Does it have to be in JavaScript ? Other engines (e.g. PCRE in PHP) provide better functionality like \G. — Jan
– Jan, Commented Mar 6, 2016 at 8:57

Nina Scholz · Accepted Answer · 2016-03-06 19:18:53Z

2

This proposal split the string into chunks and test the chunks for # or -. These line are evaluated and added to the result.

var text = '# 4.0.0 - 2016-01-01\n- some text without category\n- Just a text: with double point\n\n# 3.12.0 - 2016-02-01\n- Category: some text\n\n# 3.11.4 - 2016-03-01\n- Category: some multiple text\n- Something: some text\n- Anything: more text',
    result = function (text) {
        var array = text.split('\n'),
            o, r = [];
        array.forEach(function (a) {
            var p, v;
            if (a[0] === '#') {
                o = {};
                p = a.match(/^# ((.*) - )?(.*)$/);
                v = p[2].split('.');
                o.major = v[0];
                o.minor = v[1];
                o.patch = v[2];
                o.date = p[3];
                r.push(o);
            }
            if (a[0] === '-') {
                if (!o.entries) {
                    o.entries = [];
                }
                p = a.match(/^- ((\w*): )?(.*)$/);
                o.entries.push({ category: p[2], value: p[3] });
            }
        });
        return r;
    }(text);

document.write('<pre>' + JSON.stringify(result, 0, 4) + '</pre>');

edited Mar 6, 2016 at 19:18

answered Mar 6, 2016 at 9:33

Nina Scholz

388k26 gold badges367 silver badges417 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

user3142695 Over a year ago

Just one thing: Category should be only extracted if it is one single word. Example: Category: Some Text will give me a category field. But Just a text: with double point doesn't give me a category field, but only the value field.

Nina Scholz Over a year ago

@user3142695, please see edit, with edited regex: /^- ((\w*): )?(.*)$/ for word only search.

k-nut · Accepted Answer · 2016-03-06 09:23:56Z

This can be solved with writing different functions for the different types of lines and some regular expressions:

var text = `# 4.0.0 - 2016-01-01
- some text without category

# 3.12.0 - 2016-02-01
- Category: some text

# 3.11.4 - 2016-03-01
- Category: some multiple text
- Something: some text
- Anything: more text`;

var lines = text.split('\n');
var all = [];
for(var i = 0;i < lines.length;i++){
  var firstChar = lines[i].substr(0, 1);
  if (firstChar === '#'){
    all.push(extractVersionInfo(lines[i]));
  }
  else if (firstChar === "-"){
    all[all.length-1].entries.push(extractNote(lines[i]));
  }
}
console.log(all);

function extractNote(text){
  var withoutDash = text.substr(2);
  if (withoutDash.indexOf(":") !== -1){
    var parts = withoutDash.split(":");
    return {category: parts[0],
        value: parts[1]
       };
  }
  else {
    return {value: withoutDash};
  }
}

function extractVersionInfo(text){
  var pattern = /# ([0-9]+)\.([0-9]+)\.([0-9]+) - ([0-9]{4}-[0-9]{2}-[0-9]{2})/;
  var match = text.match(pattern);
  result = {};
  result.major = match[1];
  result.minor = match[2];
  result.patch = match[3];
  result.date = match[4];
  result.entries = [];
  return result;
}

Output:

[ { major: '4',
    minor: '0',
    patch: '0',
    date: '2016-01-01',
    entries: [ { value: 'some text without category' } ] },
  { major: '3',
    minor: '12',
    patch: '0',
    date: '2016-02-01',
    entries: [ { category: 'Category', value: ' some text' } ] },
  { major: '3',
    minor: '11',
    patch: '4',
    date: '2016-03-01',
    entries: 
     [ { category: 'Category', value: ' some multiple text' },
       { category: 'Something', value: ' some text' },
       { category: 'Anything', value: ' more text' } ] } ]

Collectives™ on Stack Overflow

JS: Convert text into object array

2 Answers 2

2 Comments

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

2 Answers 2

2 Comments

Comments

Your Answer

Sign up or log in

Post as a guest

Related