한빛출판네트워크

$html =~ s{
            (](?!href))*hrefs*)
            (&(&[^;]+;)?(?:.(?!3))+(?:3)?)
            ([^>]+>)
        }
        {$1 . decode_entities($2) .  $4}gsexi;

/(](?!href))*hrefs*)(&(&[^;]+;)?(?:.(?!3))+(?:3)?)([^>]+>)/

• 신중하게 문서화 하기
• /x 스위치를 사용해서 여러줄에 걸쳐서 표현하기
• 가능하다면 함수안에서 처리할 수 있도록 감싸기

select the_date as "date",
round(months_between(first_date,second_date),0) months_old
,product,extract(year from the_date) year
,case
    when a=b then "c"
    else "d"
    end tough_one
from ...
where ...

x = (3 + 2) / y

my @tokens = (
    [ OP  => "x" ],
    [ OP  => "=" ],
    [ OP  => "(" ],
    [ INT => "3" ],
    [ VAR => "+" ],
    [ INT => "2" ],
    [ OP  => ")" ],
    [ OP  => "/" ],
    [ VAR => "y" ],
);

select the_date as "date",
round(months_between(first_date,second_date),0) months_old
,product,extract(year from the_date) year
,case
    when a=b then "c"
        else "d"
    end tough_one
from ...
where ...

my $lparen  = qr/(/;
my $rparen  = qr/)/;
my $keyword = qr/(?i:select|from|as)/; # 이 문제에서 필요로 하는 키워드 전부
my $comma   = qr/,/;
my $text    = qr/(?:w+|"w+"|"w+")/;
my $op      = qr{[-=+*/<>]};

sub lexer {
    my $sql = shift;
    return sub {
        LEXER: {
            return ["KEYWORD", $1] if $sql =~ /G ($keyword) /gcx;
            return ["COMMA",   ""] if $sql =~ /G ($comma)   /gcx;
            return ["OP",      $1] if $sql =~ /G ($op)      /gcx;
            return ["PAREN",    1] if $sql =~ /G $lparen    /gcx;
            return ["PAREN",   -1] if $sql =~ /G $rparen    /gcx;
            return ["TEXT",    $1] if $sql =~ /G ($text)    /gcx;
            redo LEXER             if $sql =~ /G s+        /gcx;
        }
    };
}

my $lexer = lexer($sql);

while (defined (my $token = $lexer->())) {
    # 토큰을 이용해 작업하기
}

use HOP::Lexer "make_lexer";
my @sql   = $sql;
my $lexer = make_lexer(
    sub { shift @sql },
    [ "KEYWORD", qr/(?i:select|from|as)/          ],
    [ "COMMA",   qr/,/                            ],
    [ "OP",      qr{[-=+*/]}                      ],
    [ "PAREN",   qr/(/,      sub { [shift,  1] } ],
    [ "PAREN",   qr/)/,      sub { [shift, -1] } ],
    [ "TEXT",    qr/(?:w+|"w+"|"w+")/, &text  ],
    [ "SPACE",   qr/s*/,     sub {}              ],
);

sub text {
    my ($label, $value) = @_;
    $value =~ s/^[""]//;
    $value =~ s/[""]$//;
    return [ $label, $value ];
}

[ $label, $pattern, $optional_subroutine ]

[ "KEYWORD", qr/(?i:select|from|as)/ ],

[ "TEXT", qr/(?:w+|"w+"|"w+")/, &text ],

sub text {
    my ($label, $value) = @_;
    $value =~ s/^[""]//;
    $value =~ s/[""]$//;
    return [ $label, $value ];
}

[ "SPACE", qr/s*/, sub {} ],

[ "PAREN", qr/(/, sub { [shift,  1] } ],
[ "PAREN", qr/)/, sub { [shift, -1] } ],

while ( defined (my $token = $lexer->() ) { ... }

[ "KEYWORD",      "select" ]
[ "TEXT",       "the_date" ]
[ "KEYWORD",          "as" ]
[ "TEXT",           "date" ]
[ "COMMA",             "," ]
[ "TEXT",          "round" ]
[ "PAREN",               1 ]
[ "TEXT", "months_between" ]
[ "PAREN",               1 ]

01:  my $inside_parens = 0;
02:  while ( defined (my $token = $lexer->()) ) {
03:      my ($label, $value) = @$token;
04:      $inside_parens += $value if "PAREN" eq $label;
05:      next if $inside_parens || "TEXT" ne $label;
06:      if (defined (my $next = $lexer->("peek"))) {
07:          my ($next_label, $next_value) = @$next;
08:          if ("COMMA" eq $next_label) {
09:              print "$valuen";
10:          }
11:          elsif ("KEYWORD" eq $next_label && "from" eq $next_value) {
12:              print "$valuen";
13:              last; # 끝났군요!
14:          }
15:      }
16:  }

#!/usr/bin/perl

use strict;
use warnings;
use HOP::Lexer "make_lexer";

#
# SQL 명령문을 HEREDOC을 이용해서 저장
#
my $sql = <<"END_SQL";
select the_date as "date",
round(months_between(first_date,second_date),0) months_old
,product,extract(year from the_date) year
,case
  when a=b then "c"
    else "d"
      end tough_one
      from XXX
END_SQL

#
# 렉서 생성
#
my @sql   = $sql;           # 지금은 하나의 sql을 처리하지만 그 이상도 가능
my $lexer = make_lexer(
    sub { shift @sql },     # 반복자(iterator)
    [ "KEYWORD", qr{ (?i:select|from|as) }x                      ],
    [ "COMMA",   qr{ ,                   }x                      ],
    [ "OP",      qr{ [-=+*/]             }x                      ],
    [ "PAREN",   qr{ (                  }x, sub { [shift,  1] } ],
    [ "PAREN",   qr{ )                  }x, sub { [shift, -1] } ],
    [ "TEXT",    qr{ (?:w+|"w+"|"w+") }x, &text              ],
    [ "SPACE",   qr{ s*                 }x, sub {}              ],
);

#
# TEXT 토큰 값의 앞 뒤 인용부호 제거
#
sub text {
    my ( $label, $value ) = @_;
    $value =~ s{ ^ [""]   }{}x;
    $value =~ s{   [""] $ }{}x;
    return [ $label, $value ];
}

#
# 렉서가 반환하는 토큰을 이용해서 별칭(alias)를 찾는다.
#
my $inside_parens = 0;
while ( defined ( my $token = $lexer->() ) ) {
    my ( $label, $value ) = @$token;
    $inside_parens += $value if "PAREN" eq $label;
    next if $inside_parens || "TEXT" ne $label;
    if ( defined ( my $next = $lexer->("peek") ) ) {
        my ( $next_label, $next_value ) = @$next;
        if ( "COMMA" eq $next_label ) {
            print "$valuen";
        }
        elsif ( "KEYWORD" eq $next_label && "from" eq $next_value ) {
            print "$valuen";
            last; # 끝났군요!
        }
    }
}

date
months_old
product
year
tough_one