view release on metacpan or  search on metacpan

Changes  view on Meta::CPAN

0.46  2009-12-02 00:00:00
  - fix bug of split q//
  - created by INABA Hitoshi

0.45  2009-11-30 00:00:00
  - fix bug of Esjis::split when string is empty
  - created by INABA Hitoshi

0.44  2009-11-16 00:00:00
  - support given and when keywords
  - support \gN, \g{N}, and \g{-N} in s///
  - support stacked filetest operators
  - created by INABA Hitoshi

0.43  2009-10-12 00:00:00
  - support UTF-2 (aka UTF-8)
  - fix bug of join separated multiple octet of EUCJP, INFOMIXV6ALS, and GB18030
  - created by INABA Hitoshi

0.42  2009-09-28 00:00:00
  - rewrite split(m/^/) to split(m/^/m) on any version of perl

lib/Ebig5.pm  view on Meta::CPAN

        return join '', $ope, $delimiter, $prematch, '(?:', $string, ')', $matched, $end_delimiter, $modifier;
    }

    my $ignorecase = ($modifier =~ /i/oxms) ? 1 : 0;
    my $metachar = qr/[\@\\|[\]{^]/oxms;

    # split regexp
    my @char = $string =~ /\G((?>
        [^\x81-\xFE\\\$\@\[\(]|[\x81-\xFE][\x00-\xFF] |
        \\                               (?>[1-9][0-9]*)            |
        \\g (?>\s*)                      (?>[1-9][0-9]*)            |
        \\g (?>\s*) \{ (?>\s*)           (?>[1-9][0-9]*) (?>\s*) \} |
        \\g (?>\s*) \{ (?>\s*) - (?>\s*) (?>[1-9][0-9]*) (?>\s*) \} |
        \\x                              (?>[0-9A-Fa-f]{1,2})       |
        \\                               (?>[0-7]{2,3})             |
        \\c                              [\x40-\x5F]                |
        \\x\{                            (?>[0-9A-Fa-f]+)        \} |
        \\o\{                            (?>[0-7]+)              \} |
        \\[bBNpP]\{                      (?>[^\x81-\xFE0-9\}][^\x81-\xFE\}]*) \} |
        \\ $q_char                           |
        \$` | \$\{`\} | \$ (?>\s*) PREMATCH  | \$ (?>\s*) \{ (?>\s*) PREMATCH  (?>\s*) \} | \$ (?>\s*) \{\^PREMATCH\}  |
        \$& | \$\{&\} | \$ (?>\s*) MATCH     | \$ (?>\s*) \{ (?>\s*) MATCH     (?>\s*) \} | \$ (?>\s*) \{\^MATCH\}     |
                        \$ (?>\s*) POSTMATCH | \$ (?>\s*) \{ (?>\s*) POSTMATCH (?>\s*) \} | \$ (?>\s*) \{\^POSTMATCH\} |

lib/Ebig5.pm  view on Meta::CPAN

                }
            }
        }
        elsif ($char[$i] eq '\E') {
        }

        # \0 --> \0
        elsif ($char[$i] =~ /\A \\ (?>\s*) 0 \z/oxms) {
        }

        # \g{N}, \g{-N}

        # P.108 Using Simple Patterns
        # in Chapter 7: In the World of Regular Expressions
        # of ISBN 978-0-596-52010-6 Learning Perl, Fifth Edition

        # P.221 Capturing
        # in Chapter 5: Pattern Matching
        # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.

        # \g{-1}, \g{-2}, \g{-3} --> \g{-1}, \g{-2}, \g{-3}
        elsif ($char[$i] =~ /\A \\g (?>\s*) \{ (?>\s*) - (?>\s*) ((?>[1-9][0-9]*)) (?>\s*) \} \z/oxms) {
        }

        # \g{1}, \g{2}, \g{3} --> \g{2}, \g{3}, \g{4} (only when multibyte anchoring is enable)
        elsif ($char[$i] =~ /\A \\g (?>\s*) \{ (?>\s*) ((?>[1-9][0-9]*)) (?>\s*) \} \z/oxms) {
            if ($1 <= $parens) {
                $char[$i] = '\\g{' . ($1 + 1) . '}';
            }
        }

        # \g1, \g2, \g3 --> \g2, \g3, \g4 (only when multibyte anchoring is enable)
        elsif ($char[$i] =~ /\A \\g (?>\s*) ((?>[1-9][0-9]*)) \z/oxms) {
            if ($1 <= $parens) {
                $char[$i] = '\\g' . ($1 + 1);
            }
        }

        # \1, \2, \3 --> \2, \3, \4 (only when multibyte anchoring is enable)
        elsif ($char[$i] =~ /\A \\ (?>\s*) ((?>[1-9][0-9]*)) \z/oxms) {
            if ($1 <= $parens) {
                $char[$i] = '\\' . ($1 + 1);
            }
        }