Perl Regexp::Common 模块

Regexp::Common模块提供了一系列基础的正则表达式，可以非常方便有效的完成许多复杂的文本过滤处理任务，下面简单介绍一些例子，详细信息请参考

# 标准用法

 use Regexp::Common;
 while (<>) {
     /$RE{num}{real}/               and print q{a number};
     /$RE{quoted}/                  and print q{a ['"`] quoted string};
     /$RE{delimited}{-delim=>'/'}/  and print q{a /.../ sequence};
     /$RE{balanced}{-parens=>'()'}/ and print q{balanced parentheses};
     /$RE{profanity}/               and print q{a #*@%-ing word};
 }

 # 函数接口用法
 use Regexp::Common 'RE_ALL';
 while (<>) {
     $_ =~ RE_num_real()              and print q{a number};
     $_ =~ RE_quoted()                and print q{a ['"`] quoted string};
     $_ =~ RE_delimited(-delim=>'/')  and print q{a /.../ sequence};
     $_ =~ RE_balanced(-parens=>'()'} and print q{balanced parentheses};
     $_ =~ RE_profanity()             and print q{a #*@%-ing word};
 }

 # 内联用法
 if ( $RE{num}{int}->matches($text) ) {...}


 # ...AND SUBSTITUTION
 my $cropped = $RE{ws}{crop}->subs($uncropped);


 # 自定义
 use Regexp::Common 'pattern';

 pattern name   => ['name', 'mine'],
         create => '(?i:J[.]?\s+A[.]?\s+Perl-Hacker)',
         ;
 my $name_matcher = $RE{name}{mine};

 pattern name    => [ 'lineof', '-char=_' ],
         create  => sub {
                        my $flags = shift;
                        my $char = quotemeta $flags->{-char};
                        return '(?:^$char+$)';
                    },
         match   => sub {
                        my ($self, $str) = @_;
                        return $str !~ /[^$self->{flags}{-char}]/;
                    },
         subs   => sub {
                        my ($self, $str, $replacement) = @_;
                        $_[1] =~ s/^$self->{flags}{-char}+$//g;
                   },
         ;

 my $asterisks = $RE{lineof}{-char=>'*'};

 # DECIDING WHICH PATTERNS TO LOAD.
 use Regexp::Common qw /comment number/;  # Comment and number patterns.
 use Regexp::Common qw /no_defaults/;     # Don't load any patterns.
 use Regexp::Common qw /!delimited/;      # All, but delimited patterns.

子模块Regexp::Common::comment用法

    use Regexp::Common qw /comment/;
    while (<>) {
        /$RE{comment}{C}/       and  print "Contains a C comment\n";
        /$RE{comment}{C++}/     and  print "Contains a C++ comment\n";
        /$RE{comment}{PHP}/     and  print "Contains a PHP comment\n";
        /$RE{comment}{Java}/    and  print "Contains a Java comment\n";
        /$RE{comment}{Perl}/    and  print "Contains a Perl comment\n";
        /$RE{comment}{awk}/     and  print "Contains an awk comment\n";
        /$RE{comment}{HTML}/    and  print "Contains an HTML comment\n";
    }

    use Regexp::Common qw /comment RE_comment_HTML/;
    while (<>) {
        $_ =~ RE_comment_HTML() and  print "Contains an HTML comment\n";
    }

    # 获取代码里面的注释或者非注释
    my $string = read_file($fileName) ;
    my $comment =~  m/$RE{comment}{Java}/g;
    my $code =~ s/$RE{comment}{Java}//g;