Javascript 带有nodej和备选方案的正则表达式问题

我想用JavaScript识别带有正则表达式的足球比赛：

1
15/06 16:00
Brasília

Brasilien
3:0 (1:0)
Japan

2
23/06 16:00
Recife 

Uruguay
-
Tahiti

该文本包含：

• 比赛日期和时间
• 比赛地点
• 两队
• 如果游戏已玩或未玩，则分数包含“-”

我已使用以下站点构建了一个正则表达式：

此正则表达式应捕获两个备选方案（有分数和无分数） 下面是整个测试内容的链接：

我的JavaScript代码与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]);
    }
}

但是我没有得到客场球队，那就是第五组！ 我的输出：

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

只有当我没有用“|”替换表达式时，我才得到它：

或者当我使用“[”“]”而不是“（“and”）”对备选方案进行分组时

有什么问题？ 这是不是因为忽略了最后一个捕获组而导致Nodejs正则表达式引擎中的错误！？或 正则表达式错了吗

致意

---

Michael

您的问题可能只是捕获组的问题。
此正则表达式不会更改您的原始数据（我对您的数据了解不够）
只是改变了捕获组

编辑-这适用于您的测试数据。它是相同的正则表达式，但添加了一些空白部分

 #  /[^\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

未测试的JS代码

 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测试用例

$/ = 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

---

但是我需要这些小组来获取数据@rubiktubik-给你。现在它工作了！非常感谢。但我不明白为什么这是工作和更简单的正则表达式不！？

 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";
      }
 }

$/ = 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

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