Regex Issue with Nodejs and alternatives

Question

I want to recognize football matches with Regex in JavaScript:

1
15/06 16:00
Brasília

Brasilien
3:0 (1:0)
Japan

2
23/06 16:00
Recife 

Uruguay
-
Tahiti

This text contains:

Date and Time of the match
The Place where the match is
The two teams
the score if the game is already played OR if not it contains a "-"

i have build a regex with http://regex101.com/ site:

(\d\d\/\d\d)\s(\d\d:\d\d)\s(.+)\s\s\s(.+)\s(?:-|(\d):(\d)\s\(\d:\d\))\s(.+)

This regex is should capture both alternatives(with score and without) Here is a link to the whole testing stuff: http://regex101.com/r/bF3lU4

My Code in JavaScript with NodeJS:

function CreateMatchesFromString(data)
{
    var re = /(\d\d\/\d\d)\s(\d\d:\d\d)\s(.+)\s\s\s(.+)\s(?:-|(\d):(\d)\s\(\d:\d\))\s(.+)/g;
    var myArray;

    while ((myArray = re.exec(data)) !== null)
    {
        console.log("date:"+ myArray[1]);
        console.log("time:"+ myArray[2]);
        console.log("place:"+ myArray[3]);
        console.log("Home:"+ myArray[4]);
        console.log("Away:"+ myArray[5]);
    }
}

But i not get the Away-Team which is the Capture Group 5! My Output:

date:26/06
time:22:00
place:Curitiba
Home:Algerien
Away:undefined

I get it only when i not make an alternative expression with "|":

(\d\d\/\d\d)\s(\d\d:\d\d)\s(.+)\s\s\s(.+)\s-\s(.+)

Or when i use "[" "]" instead of the "(" and ")" for grouping the alternatives.

What is the problem? Is it a a bug in Nodejs regex-engine because it ignores the last capture group!? Or is the Regex wrong?

Best Regards Michael

score 1 · Accepted Answer · 2014-03-23 23:27:29Z

Your problem could be just the capture group's.
This regex doesn't change your original (I don't know enough about your data)
just alters the capture groups.

edit - This works with your test data. Its the same regex but added some whitespace parts.

 #  /[^\S\r\n]*(?:\r?\n)(\d\d\/\d\d)[^\S\r\n]+(\d\d:\d\d)[^\S\r\n]*(?:\r?\n)(.+)(?:\r?\n)[^\S\r\n]*(?:\r?\n)(.+)(?:\r?\n)(?:-|(\d):(\d)[^\S\r\n]+\(\d:\d\))[^\S\r\n]*(?:\r?\n)(.+)/

 [^\S\r\n]*                         
 (?: \r? \n )                       # linebreak 
 # ---------------
 ( \d\d / \d\d )                    # (1), Date
 [^\S\r\n]+ 
 ( \d\d : \d\d )                    # (2), Time
 [^\S\r\n]* 
 (?: \r? \n )                       # linebreak 
 # ---------------
 ( .+ )                             # (3), Place
 (?: \r? \n )                       # linebreak 
 # ---------------
 [^\S\r\n]*                         # blank line
 (?: \r? \n )                       # linebreak 
 # ---------------
 ( .+ )                             # (4), Home
 (?: \r? \n )                       # linebreak 
 # ---------------
 (?:
      -                             # No score
   |                                # or,
      ( \d )                        # (5), Score home
      :                             # :
      ( \d )                        # (6), Score away
      [^\S\r\n]+ 
      \( \d : \d \)
 )
 [^\S\r\n]* 
 (?: \r? \n )                       # linebreak 
 # ---------------
 ( .+ )                             # (7), Away

Untested JS code

 var pattern = /[^\S\r\n]*(?:\r?\n)(\d\d\/\d\d)[^\S\r\n]+(\d\d:\d\d)[^\S\r\n]*(?:\r?\n)(.+)(?:\r?\n)[^\S\r\n]*(?:\r?\n)(.+)(?:\r?\n)(?:-|(\d):(\d)[^\S\r\n]+\(\d:\d\))[^\S\r\n]*(?:\r?\n)(.+)/g;
 while ((match = pattern.exec( data )) != null)
 {
      console.log( "\n" );
      console.log( "Date:  " + match[1] + "\n";
      console.log( "Time:  " + match[2] + "\n";
      console.log( "Place: " + match[3] + "\n";
      console.log( "Home:  " + match[4] + "\n";
      console.log( "Away:  " + match[7] + "\n";

      console.log( "Score: ";
      if (match[5] != null) {
          console.log( match[5] + " to " + match[6] + "\n";
      }
      else {
          console.log( "no info\n";
      }
 }

Perl test case

$/ = undef;
$str = <DATA>;

while ( $str =~ /[^\S\r\n]*(?:\r?\n)(\d\d\/\d\d)[^\S\r\n]+(\d\d:\d\d)[^\S\r\n]*(?:\r?\n)(.+)(?:\r?\n)[^\S\r\n]*(?:\r?\n)(.+)(?:\r?\n)(?:-|(\d):(\d)[^\S\r\n]+\(\d:\d\))[^\S\r\n]*(?:\r?\n)(.+)/g )
{
    print "\n";
    print "Date:  $1\n";
    print "Time:  $2\n";
    print "Place: $3\n";
    print "Home:  $4\n";
    print "Away:  $7\n";

    print "Score: ";
    if  ( defined $5 ) {
       print "$5 to $6\n";
    }
    else {
       print "no info\n";
    }
}

__DATA__

1
15/06 16:00
Brasília

Brasilien
3:0 (1:0)
Japan

2
23/06 16:00
Recife 

Uruguay
-
Tahiti

Output >>

Date:  15/06
Time:  16:00
Place: Brasflia
Home:  Brasilien
Away:  Japan
Score: 3 to 0

Date:  23/06
Time:  16:00
Place: Recife
Home:  Uruguay
Away:  Tahiti
Score: no info

Now it works!Thank you! But i not understand why this is working and the more simpler regex not!?

Collectives™ on Stack Overflow

Regex Issue with Nodejs and alternatives

1 Answer 1

3 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

3 Comments

Your Answer

Sign up or log in

Post as a guest

Related