package Sjis; ###################################################################### # # Sjis - Source code filter to escape ShiftJIS script # # http://search.cpan.org/dist/Char-Sjis/ # # Copyright (c) 2008, 2009, 2010, 2011, 2012, 2013 INABA Hitoshi ###################################################################### use 5.00503; BEGIN { if ($^X =~ / jperl /oxmsi) { die __FILE__, ": needs perl(not jperl) 5.00503 or later. (\$^X==$^X)"; } if (CORE::ord('A') == 193) { die __FILE__, ": is not US-ASCII script (may be EBCDIC or EBCDIK script)."; } if (CORE::ord('A') != 0x41) { die __FILE__, ": is not US-ASCII script (must be US-ASCII script)."; } } # 12.3. Delaying use Until Runtime # in Chapter 12. Packages, Libraries, and Modules # of ISBN 0-596-00313-7 Perl Cookbook, 2nd Edition. # (and so on) BEGIN { eval q{ use vars qw($VERSION) } } $VERSION = sprintf '%d.%02d', q$Revision: 0.87 $ =~ /(\d+)/oxmsg; BEGIN { require Esjis; } # poor Symbol.pm - substitute of real Symbol.pm BEGIN { my $genpkg = "Symbol::"; my $genseq = 0; sub gensym () { my $name = "GEN" . $genseq++; # here, no strict qw(refs); if strict.pm exists my $ref = \*{$genpkg . $name}; delete $$genpkg{$name}; $ref; } } # Column: local $@ # in Chapter 9. Osaete okitai Perl no kiso # of ISBN 10: 4798119172 | ISBN 13: 978-4798119175 MODAN Perl NYUMON # (and so on) # use strict; if strict.pm exists BEGIN { if (eval { local $@; CORE::require strict }) { strict::->import; } } # P.714 29.2.39. flock # in Chapter 29: Functions # of ISBN 0-596-00027-8 Programming Perl Third Edition. # P.863 flock # in Chapter 27: Functions # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. # P.228 Inlining Constant Functions # in Chapter 6: Subroutines # of ISBN 0-596-00027-8 Programming Perl Third Edition. # P.331 Inlining Constant Functions # in Chapter 7: Subroutines # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. sub LOCK_SH() {1} sub LOCK_EX() {2} sub LOCK_UN() {8} sub LOCK_NB() {4} sub unimport {} sub Sjis::escape_script; # regexp of character my $your_char = q{[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[\x00-\xFF]}; my $qq_char = qr/\\c[\x40-\x5F]|\\?(?:$your_char)/oxms; my $q_char = qr/$your_char/oxms; # P.1023 Appendix W.9 Multibyte Anchoring # of ISBN 1-56592-224-7 CJKV Information Processing my $anchor = ''; $anchor = q{${Esjis::anchor}}; BEGIN { eval q{ use vars qw($nest) } } # regexp of nested parens in qqXX # P.340 Matching Nested Constructs with Embedded Code # in Chapter 7: Perl # of ISBN 0-596-00289-0 Mastering Regular Expressions, Second edition my $qq_paren = qr{(?{local $nest=0}) (?>(?: \\c[\x40-\x5F] | \\? [\x81-\x9F\xE0-\xFC][\x00-\xFF] | \\ [\x00-\xFF] | [^()] | \( (?{$nest++}) | \) (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!)) }xms; my $qq_brace = qr{(?{local $nest=0}) (?>(?: \\c[\x40-\x5F] | \\? [\x81-\x9F\xE0-\xFC][\x00-\xFF] | \\ [\x00-\xFF] | [^{}] | \{ (?{$nest++}) | \} (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!)) }xms; my $qq_bracket = qr{(?{local $nest=0}) (?>(?: \\c[\x40-\x5F] | \\? [\x81-\x9F\xE0-\xFC][\x00-\xFF] | \\ [\x00-\xFF] | [^[\]] | \[ (?{$nest++}) | \] (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!)) }xms; my $qq_angle = qr{(?{local $nest=0}) (?>(?: \\c[\x40-\x5F] | \\? [\x81-\x9F\xE0-\xFC][\x00-\xFF] | \\ [\x00-\xFF] | [^<>] | \< (?{$nest++}) | \> (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!)) }xms; my $qq_scalar = qr{(?: \{ (?:$qq_brace)*? \} | (?: ::)? (?: [a-zA-Z_][a-zA-Z_0-9]* (?: ::[a-zA-Z_][a-zA-Z_0-9]* )* (?: \[ (?: \$\[ | \$\] | $qq_char )*? \] | \{ (?:$qq_brace)*? \} )* (?: (?: -> )? (?: \[ (?: \$\[ | \$\] | $qq_char )*? \] | \{ (?:$qq_brace)*? \} ) )* )) }xms; my $qq_variable = qr{(?: \{ (?:$qq_brace)*? \} | (?: ::)? (?: [0-9]+ | [^\x81-\x9F\xE0-\xFCa-zA-Z_0-9\[\]] | ^[A-Z] | [a-zA-Z_][a-zA-Z_0-9]* (?: ::[a-zA-Z_][a-zA-Z_0-9]* )* (?: \[ (?: \$\[ | \$\] | $qq_char )*? \] | \{ (?:$qq_brace)*? \} )* (?: (?: -> )? (?: \[ (?: \$\[ | \$\] | $qq_char )*? \] | \{ (?:$qq_brace)*? \} ) )* )) }xms; # regexp of nested parens in qXX my $q_paren = qr{(?{local $nest=0}) (?>(?: [\x81-\x9F\xE0-\xFC][\x00-\xFF] | [^()] | \( (?{$nest++}) | \) (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!)) }xms; my $q_brace = qr{(?{local $nest=0}) (?>(?: [\x81-\x9F\xE0-\xFC][\x00-\xFF] | [^{}] | \{ (?{$nest++}) | \} (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!)) }xms; my $q_bracket = qr{(?{local $nest=0}) (?>(?: [\x81-\x9F\xE0-\xFC][\x00-\xFF] | [^[\]] | \[ (?{$nest++}) | \] (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!)) }xms; my $q_angle = qr{(?{local $nest=0}) (?>(?: [\x81-\x9F\xE0-\xFC][\x00-\xFF] | [^<>] | \< (?{$nest++}) | \> (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!)) }xms; # P.854 31.17. use re # in Chapter 31. Pragmatic Modules # of ISBN 0-596-00027-8 Programming Perl Third Edition. # P.1026 re # in Chapter 29. Pragmatic Modules # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. my $matched = ''; my $s_matched = ''; $matched = q{$Esjis::matched}; $s_matched = q{ Esjis::s_matched();}; my $tr_variable = ''; # variable of tr/// my $sub_variable = ''; # variable of s/// my $bind_operator = ''; # =~ or !~ BEGIN { eval q{ use vars qw($slash) } } # when 'm//', '/' means regexp match 'm//' and '?' means regexp match '??' # when 'div', '/' means division operator and '?' means conditional operator (condition ? then : else) my @heredoc = (); # here document my @heredoc_delimiter = (); my $here_script = ''; # here script my $function_ord; # ord() to ord() or Sjis::ord() my $function_ord_; # ord to ord or Sjis::ord_ my $function_reverse; # reverse to reverse or Sjis::reverse my $function_getc; # getc to getc or Sjis::getc my $ignore_modules = join('|', qw( utf8 bytes charnames I18N::Japanese I18N::Collate I18N::JExt File::DosGlob Wild Wildcard Japanese )); # in Chapter 8: Standard Modules # of ISBN 0-596-00241-6 Perl in a Nutshell, Second Edition # when this script is main program if ($0 eq __FILE__) { # show usage unless (@ARGV) { die < Escaped_script.pl.e END } print Sjis::escape_script($ARGV[0]); exit 0; } my($package,$filename,$line,$subroutine,$hasargs,$wantarray,$evaltext,$is_require,$hints,$bitmask) = caller 0; # called any package not main if ($package ne 'main') { die < "@{[__PACKAGE__]}::$filename"' and rewrite "use $package;" to "use @{[__PACKAGE__]}::$package;" of script "$0". END } # P.302 Module Privacy and the Exporter # in Chapter 11: Modules # of ISBN 0-596-00027-8 Programming Perl Third Edition. # # A module can do anything it jolly well pleases when it's used, since use just # calls the ordinary import method for the module, and you can define that # method to do anything you like. # P.406 Module Privacy and the Exporter # in Chapter 11: Modules # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. # # A module can do anything it jolly well pleases when it's used, since use just # calls the ordinary import method for the module, and you can define that # method to do anything you like. sub import { if (Esjis::e("$filename.e")) { if (exists $ENV{'SJIS_DEBUG'}) { Esjis::unlink "$filename.e"; } elsif (Esjis::z("$filename.e")) { Esjis::unlink "$filename.e"; } else { my $e_mtime = (Esjis::stat("$filename.e"))[9]; my $mtime = (Esjis::stat($filename))[9]; my $__mtime__ = (Esjis::stat(__FILE__))[9]; if (($e_mtime < $mtime) or ($mtime < $__mtime__)) { Esjis::unlink "$filename.e"; } } } if (not Esjis::e("$filename.e")) { my $fh = gensym(); if (eval q{ use Fcntl qw(O_WRONLY O_APPEND O_CREAT); 1 } and CORE::sysopen($fh,"$filename.e",&O_WRONLY|&O_APPEND|&O_CREAT)) { } else { Esjis::_open_a($fh, "$filename.e") or die __FILE__, ": Can't write open file: $filename.e"; } if (0) { } elsif ($^O eq 'MacOS') { eval q{ CORE::require Mac::Files; Mac::Files::FSpSetFLock("$filename.e"); }; } elsif (exists $ENV{'SJIS_NONBLOCK'}) { # P.419 File Locking # in Chapter 16: Interprocess Communication # of ISBN 0-596-00027-8 Programming Perl Third Edition. # P.524 File Locking # in Chapter 15: Interprocess Communication # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. # P.571 Handling Race Conditions # in Chapter 23: Security # of ISBN 0-596-00027-8 Programming Perl Third Edition. # P.663 Handling Race Conditions # in Chapter 20: Security # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. # (and so on) eval q{ unless (flock($fh, LOCK_EX | LOCK_NB)) { warn __FILE__, ": Can't immediately write-lock the file: $filename.e"; exit; } }; } else { eval q{ flock($fh, LOCK_EX) }; } truncate($fh, 0) or die __FILE__, ": Can't truncate file: $filename.e"; seek($fh, 0, 0) or die __FILE__, ": Can't seek file: $filename.e"; my $e_script = Sjis::escape_script($filename); print {$fh} $e_script; my $mode = (Esjis::stat($filename))[2] & 0777; chmod $mode, "$filename.e"; if ($^O eq 'MacOS') { eval q{ CORE::require Mac::Files; Mac::Files::FSpRstFLock("$filename.e"); }; } close($fh) or die __FILE__, ": Can't close file: $filename.e"; } my $fh = gensym(); Esjis::_open_r($fh, "$filename.e") or die __FILE__, ": Can't read open file: $filename.e"; if (0) { } elsif ($^O eq 'MacOS') { eval q{ CORE::require Mac::Files; Mac::Files::FSpSetFLock("$filename.e"); }; } elsif (exists $ENV{'SJIS_NONBLOCK'}) { eval q{ unless (flock($fh, LOCK_SH | LOCK_NB)) { warn __FILE__, ": Can't immediately read-lock the file: $filename.e"; exit; } }; } else { eval q{ flock($fh, LOCK_SH) }; } my @switch = (); if ($^W) { push @switch, '-w'; } # P.707 29.2.33. exec # in Chapter 29: Functions # of ISBN 0-596-00027-8 Programming Perl Third Edition. # # If there is more than one argument in LIST, or if LIST is an array with more # than one value, the system shell will never be used. This also bypasses any # shell processing of the command. The presence or absence of metacharacters in # the arguments doesn't affect this list-triggered behavior, which makes it the # preferred from in security-conscious programs that do not with to expose # themselves to potential shell escapes. # Environment variable PERL5SHELL(Microsoft ports only) will never be used, too. # P.855 exec # in Chapter 27: Functions # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. # # If there is more than one argument in LIST, or if LIST is an array with more # than one value, the system shell will never be used. This also bypasses any # shell processing of the command. The presence or absence of metacharacters in # the arguments doesn't affect this list-triggered behavior, which makes it the # preferred from in security-conscious programs that do not wish to expose # themselves to injection attacks via shell escapes. # Environment variable PERL5SHELL(Microsoft ports only) will never be used, too. # P.489 #! and Quoting on Non-Unix Systems # in Chapter 19: The Command-Line Interface # of ISBN 0-596-00027-8 Programming Perl Third Edition. # P.578 #! and Quoting on Non-Unix Systems # in Chapter 17: The Command-Line Interface # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. # DOS-like system if ($^O =~ /\A (?: MSWin32 | NetWare | symbian | dos ) \z/oxms) { exit Esjis::_systemx( _escapeshellcmd_MSWin32($^X), # -I switch can not treat space included path # (map { '-I' . _escapeshellcmd_MSWin32($_) } @INC), (map { '-I' . $_ } @INC), @switch, '--', map { _escapeshellcmd_MSWin32($_) } "$filename.e", @ARGV ); } # MacOS system elsif ($^O eq 'MacOS') { my $system = Esjis::_systemx( _escapeshellcmd_MacOS($^X), (map { '-I' . _escapeshellcmd_MacOS($_) } @INC), @switch, '--', map { _escapeshellcmd_MacOS($_) } "$filename.e", @ARGV ); eval q{ CORE::require Mac::Files; Mac::Files::FSpRstFLock("$filename.e"); }; exit $system; } # UNIX-like system else { exit Esjis::_systemx( _escapeshellcmd($^X), (map { '-I' . _escapeshellcmd($_) } @INC), @switch, '--', map { _escapeshellcmd($_) } "$filename.e", @ARGV ); } } # escape shell command line on DOS-like system sub _escapeshellcmd_MSWin32 { my($word) = @_; if ($word =~ / [ ] /oxms) { # both DOS-like and UNIX-like shell quote return qq{"$word"}; } else { return $word; } } # escape shell command line on Mac OS sub _escapeshellcmd_MacOS { my($word) = @_; return $word; } # escape shell command line on UNIX-like system sub _escapeshellcmd { my($word) = @_; return $word; } # P.619 Source Filters # in Chapter 24: Common Practices # of ISBN 0-596-00027-8 Programming Perl Third Edition. # P.718 Source Filters # in Chapter 21: Common Practices # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. # escape ShiftJIS script sub Sjis::escape_script { my($script) = @_; my $e_script = ''; # read ShiftJIS script my $fh = gensym(); Esjis::_open_r($fh, $script) or die __FILE__, ": Can't open file: $script"; local $/ = undef; # slurp mode $_ = <$fh>; close($fh) or die __FILE__, ": Can't close file: $script"; if (/^ use Esjis(?:\s+[0-9\.]*)?\s*; $/oxms) { return $_; } else { # #! shebang line if (s/\A(#!.+?\n)//oms) { my $head = $1; $head =~ s/\bjperl\b/perl/gi; $e_script .= $head; } # DOS-like system header if (s/\A(\@rem\s*=\s*'.*?'\s*;\s*\n)//oms) { my $head = $1; $head =~ s/\bjperl\b/perl/gi; $e_script .= $head; } # P.618 Generating Perl in Other Languages # in Chapter 24: Common Practices # of ISBN 0-596-00027-8 Programming Perl Third Edition. # P.717 Generating Perl in Other Languages # in Chapter 21: Common Practices # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. if (s/(.*^#\s*line\s+\d+(?:\s+"(?:$q_char)+?")?\s*\n)//oms) { my $head = $1; $head =~ s/\bjperl\b/perl/gi; $e_script .= $head; } # P.210 5.10.3.3. Match-time code evaluation # in Chapter 5: Pattern Matching # of ISBN 0-596-00027-8 Programming Perl Third Edition. # P.255 Match-time code evaluation # in Chapter 5: Pattern Matching # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. $e_script .= sprintf("use Esjis %s;\n", $Sjis::VERSION); # require run-time routines version # use Sjis version qw(ord reverse getc); $function_ord = 'ord'; $function_ord_ = 'ord'; $function_reverse = 'reverse'; $function_getc = 'getc'; if (s/^ \s* use \s+ Sjis \s* ([^\x81-\x9F\xE0-\xFC;]*) ; \s* \n? $//oxms) { # require version my $list = $1; if ($list =~ s/\A ([0-9]+\.[0-9]+) \.0 \s* //oxms) { my $version = $1; if ($version ne $Sjis::VERSION) { my @file = grep -e, map {qq{$_/Sjis.pm}} @INC; my %file = map { $_ => 1 } @file; if (scalar(keys %file) >= 2) { my $file = join "\n", sort keys %file; warn < $Sjis::VERSION) { die "Script $0 required Sjis.pm $version, but @{[__FILE__]} is only version $Sjis::VERSION\n"; } } # demand ord, reverse, and getc if ($list !~ /\A \s* \z/oxms) { local $@; my @list = eval $list; for (@list) { $function_ord = 'Sjis::ord' if /\A ord \z/oxms; $function_ord_ = 'Sjis::ord_' if /\A ord \z/oxms; $function_reverse = 'Sjis::reverse' if /\A reverse \z/oxms; $function_getc = 'Sjis::getc' if /\A getc \z/oxms; } } } } # use Tk; --> use SjisTk::Widget; my @tkmodule = (); for my $widget (qw( Button Canvas Checkbutton Entry Frame Label Listbox MainWindow Message Menu Menubutton Radiobutton Scale Text Toplevel )) { if (/ $widget /xms) { push @tkmodule, " eval qq{ use SjisTk::$widget; };"; } } my $tkmodule = join "\n", @tkmodule; my $use_tk = <<"USE_TK"; BEGIN { if (\$] >= 5.007) { $tkmodule } else { eval qq{ use SjisTk::Entry; }; eval qq{ use SjisTk::MainWindow; }; } } USE_TK if (s/^ (\s* use \s+ Tk [^\x81-\x9F\xE0-\xFC:;]* ; \s*? \n) /$1$use_tk/oxmsg) { s/ \b (MainWindow \s* -> \s* new) \b /SjisTk::$1/oxmsg; s/^ (\s* use \s+ )(Tk::(?:Ballon|BrowseEntry|ColorEditor|Dialog|DialogBox|DirTree|FileSelect|HList|LabFrame|ROText|Table|TixGrid|TList|Tree) [^\x81-\x9F\xE0-\xFC:;]* ; \s*? ) \n /BEGIN { eval qq{ $1$2 ${1}Sjis${2} }};\n/oxmsg; } $slash = 'm//'; # Yes, I studied study yesterday. # P.359 The Study Function # in Chapter 7: Perl # of ISBN 0-596-00289-0 Mastering Regular Expressions, Second edition study $_; # while all script # one member of Tag-team # # P.315 "Tag-team" matching with /gc # in Chapter 7: Perl # of ISBN 0-596-00289-0 Mastering Regular Expressions, Second edition while (not /\G \z/oxgc) { # member $e_script .= escape(); } return $e_script; } # escape ShiftJIS part of script sub escape { # \n output here document # another member of Tag-team # # P.315 "Tag-team" matching with /gc # in Chapter 7: Perl # of ISBN 0-596-00289-0 Mastering Regular Expressions, Second edition if (/\G ( \n ) /oxgc) { # another member (and so on) my $heredoc = ''; if (scalar(@heredoc_delimiter) >= 1) { $slash = 'm//'; $heredoc = join '', @heredoc; @heredoc = (); # skip here document for my $heredoc_delimiter (@heredoc_delimiter) { /\G .*? \n $heredoc_delimiter \n/xmsgc; } @heredoc_delimiter = (); $here_script = ''; } return "\n" . $heredoc; } # ignore space, comment elsif (/\G (\s+|\#.*) /oxgc) { return $1; } # if (, elsif (, unless (, while (, until (, given ( and when ( # given, when # P.225 The given Statement # in Chapter 15: Smart Matching and given-when # of ISBN 978-0-596-52010-6 Learning Perl, Fifth Edition # P.133 The given Statement # in Chapter 4: Statements and Declarations # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. elsif (/\G ( (?: if | elsif | unless | while | until | given | when ) \s* \( ) /oxgc) { $slash = 'm//'; return $1; } # scalar variable ($scalar = ...) =~ tr///; # scalar variable ($scalar = ...) =~ s///; # state # P.68 Persistent, Private Variables # in Chapter 4: Subroutines # of ISBN 978-0-596-52010-6 Learning Perl, Fifth Edition # P.160 Persistent Lexically Scoped Variables: state # in Chapter 4: Statements and Declarations # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. # (and so on) elsif (/\G ( \( \s* (?: local \b | my \b | our \b | state \b )? \s* \$ $qq_scalar ) /oxgc) { my $e_string = e_string($1); if (/\G ( \s* = $qq_paren \) ) ( \s* (?: =~ | !~ ) \s* ) (?= (?: tr|y) \b ) /oxgc) { $tr_variable = $e_string . e_string($1); $bind_operator = $2; $slash = 'm//'; return ''; } elsif (/\G ( \s* = $qq_paren \) ) ( \s* (?: =~ | !~ ) \s* ) (?= s \b ) /oxgc) { $sub_variable = $e_string . e_string($1); $bind_operator = $2; $slash = 'm//'; return ''; } else { $slash = 'div'; return $e_string; } } # $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> Esjis::PREMATCH() elsif (/\G ( \$` | \$\{`\} | \$ \s* PREMATCH \b | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) /oxmsgc) { $slash = 'div'; return q{Esjis::PREMATCH()}; } # $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Esjis::MATCH() elsif (/\G ( \$& | \$\{&\} | \$ \s* MATCH \b | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) /oxmsgc) { $slash = 'div'; return q{Esjis::MATCH()}; } # $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Esjis::POSTMATCH() elsif (/\G ( \$ \s* POSTMATCH \b | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) /oxmsgc) { $slash = 'div'; return q{Esjis::POSTMATCH()}; } # scalar variable $scalar =~ tr///; # scalar variable $scalar =~ s///; elsif (/\G ( \$ $qq_scalar ) /oxgc) { my $scalar = e_string($1); if (/\G ( \s* (?: =~ | !~ ) \s* ) (?= (?: tr|y) \b ) /oxgc) { $tr_variable = $scalar; $bind_operator = $1; $slash = 'm//'; return ''; } elsif (/\G ( \s* (?: =~ | !~ ) \s* ) (?= s \b ) /oxgc) { $sub_variable = $scalar; $bind_operator = $1; $slash = 'm//'; return ''; } else { $slash = 'div'; return $scalar; } } # end of statement elsif (/\G ( [,;] ) /oxgc) { $slash = 'm//'; # clear tr/// variable $tr_variable = ''; # clear s/// variable $sub_variable = ''; $bind_operator = ''; return $1; } # bareword elsif (/\G ( \{ \s* (?: tr|index|rindex|reverse) \s* \} ) /oxmsgc) { return $1; } # $0 --> $0 elsif (/\G ( \$ 0 ) /oxmsgc) { $slash = 'div'; return $1; } elsif (/\G ( \$ \{ \s* 0 \s* \} ) /oxmsgc) { $slash = 'div'; return $1; } # $$ --> $$ elsif (/\G ( \$ \$ ) (?![\w\{]) /oxmsgc) { $slash = 'div'; return $1; } # $1, $2, $3 --> $2, $3, $4 (only when multibyte anchoring is enable) elsif (/\G \$ ([1-9][0-9]*) /oxmsgc) { $slash = 'div'; return e_capture($1); } elsif (/\G \$ \{ \s* ([1-9][0-9]*) \s* \} /oxmsgc) { $slash = 'div'; return e_capture($1); } # $$foo[ ... ] --> $ $foo->[ ... ] elsif (/\G \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \[ .+? \] ) /oxmsgc) { $slash = 'div'; return e_capture($1.'->'.$2); } # $$foo{ ... } --> $ $foo->{ ... } elsif (/\G \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ .+? \} ) /oxmsgc) { $slash = 'div'; return e_capture($1.'->'.$2); } # $$foo elsif (/\G \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) /oxmsgc) { $slash = 'div'; return e_capture($1); } # ${ foo } elsif (/\G \$ \s* \{ ( \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* ) \} /oxmsgc) { $slash = 'div'; return '${' . $1 . '}'; } # ${ ... } elsif (/\G \$ \s* \{ \s* ( $qq_brace ) \s* \} /oxmsgc) { $slash = 'div'; return e_capture($1); } # variable or function # $ @ % & * $ # elsif (/\G ( (?: [\$\@\%\&\*] | \$\# | -> | \b sub \b) \s* (?: split|chop|index|rindex|lc|uc|fc|chr|ord|reverse|getc|tr|y|q|qq|qx|qw|m|s|qr|glob|lstat|opendir|stat|unlink|chdir) ) \b /oxmsgc) { $slash = 'div'; return $1; } # $ $ $ $ $ $ $ $ $ $ $ $ $ $ # $ @ # \ ' " / ? ( ) [ ] < > elsif (/\G ( \$[\$\@\#\\\'\"\/\?\(\)\[\]\<\>] ) /oxmsgc) { $slash = 'div'; return $1; } # while () elsif (/\G \b (while \s* \( \s* <[\$]?[A-Za-z_][A-Za-z_0-9]*> \s* \)) \b /oxgc) { return $1; } # while () --- glob # avoid "Error: Runtime exception" of perl version 5.005_03 elsif (/\G \b while \s* \( \s* < ((?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC>\0\a\e\f\n\r\t])+?) > \s* \) \b /oxgc) { return 'while ($_ = Esjis::glob("' . $1 . '"))'; } # while (glob) elsif (/\G \b while \s* \( \s* glob \s* \) /oxgc) { return 'while ($_ = Esjis::glob_)'; } # while (glob(WILDCARD)) elsif (/\G \b while \s* \( \s* glob \b /oxgc) { return 'while ($_ = Esjis::glob'; } # doit if, doit unless, doit while, doit until, doit for, doit when elsif (/\G \b ( if | unless | while | until | for | when ) \b /oxgc) { $slash = 'm//'; return $1; } # functions of package Esjis elsif (/\G \b (CORE:: | ->[ ]* (?: atan2 | [a-z]{2,})) \b /oxgc) { $slash = 'm//'; return $1; } elsif (/\G \b bytes::substr \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'substr'; } elsif (/\G \b chop \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Esjis::chop'; } elsif (/\G \b bytes::index \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'index'; } elsif (/\G \b Sjis::index \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Sjis::index'; } elsif (/\G \b index \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Esjis::index'; } elsif (/\G \b bytes::rindex \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'rindex'; } elsif (/\G \b Sjis::rindex \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Sjis::rindex'; } elsif (/\G \b rindex \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Esjis::rindex'; } elsif (/\G \b lc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'Esjis::lc'; } elsif (/\G \b lcfirst (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'Esjis::lcfirst'; } elsif (/\G \b uc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'Esjis::uc'; } elsif (/\G \b ucfirst (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'Esjis::ucfirst'; } elsif (/\G \b fc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'Esjis::fc'; } # stacked file test operators # P.179 File Test Operators # in Chapter 12: File Tests # of ISBN 978-0-596-52010-6 Learning Perl, Fifth Edition # P.106 Named Unary and File Test Operators # in Chapter 3: Unary and Binary Operators # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. # (and so on) elsif (/\G (-[rwxoRWXOezfdlpSbcugkTB](?:\s+-[rwxoRWXOezfdlpSbcugkTB])+) \s* (\") ((?:$qq_char)+?) (\") /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1)," . e_qq('', $2,$4,$3) . ")"; } elsif (/\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) qq \s* (\#) ((?:$qq_char)+?) (\#) /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1)," . e_qq('qq',$2,$4,$3) . ")"; } elsif (/\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) qq \s* (\() ((?:$qq_paren)+?) (\)) /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1)," . e_qq('qq',$2,$4,$3) . ")"; } elsif (/\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) qq \s* (\{) ((?:$qq_brace)+?) (\}) /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1)," . e_qq('qq',$2,$4,$3) . ")"; } elsif (/\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) qq \s* (\[) ((?:$qq_bracket)+?) (\]) /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1)," . e_qq('qq',$2,$4,$3) . ")"; } elsif (/\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) qq \s* (\<) ((?:$qq_angle)+?) (\>) /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1)," . e_qq('qq',$2,$4,$3) . ")"; } elsif (/\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) qq \s* (\S) ((?:$qq_char)+?) (\3) /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1)," . e_qq('qq',$2,$4,$3) . ")"; } elsif (/\G (-[rwxoRWXOezfdlpSbcugkTB](?:\s+-[rwxoRWXOezfdlpSbcugkTB])+) \s* (\') ((?:\\\1|\\\\|$q_char)+?) (\') /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1)," . e_q ('', $2,$4,$3) . ")"; } elsif (/\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) q \s* (\#) ((?:\\\#|\\\\|$q_char)+?) (\#) /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1)," . e_q ('q', $2,$4,$3) . ")"; } elsif (/\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) q \s* (\() ((?:\\\)|\\\\|$q_paren)+?) (\)) /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1)," . e_q ('q', $2,$4,$3) . ")"; } elsif (/\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) q \s* (\{) ((?:\\\}|\\\\|$q_brace)+?) (\}) /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1)," . e_q ('q', $2,$4,$3) . ")"; } elsif (/\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) q \s* (\[) ((?:\\\]|\\\\|$q_bracket)+?) (\]) /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1)," . e_q ('q', $2,$4,$3) . ")"; } elsif (/\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) q \s* (\<) ((?:\\\>|\\\\|$q_angle)+?) (\>) /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1)," . e_q ('q', $2,$4,$3) . ")"; } elsif (/\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) q \s* (\S) ((?:\\\1|\\\\|$q_char)+?) (\3) /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1)," . e_q ('q', $2,$4,$3) . ")"; } elsif (/\G (-[rwxoRWXOezfdlpSbcugkTB](?:\s+-[rwxoRWXOezfdlpSbcugkTB])+) (\$ \w+(?: ::\w+)* (?: (?: ->)? (?: \( (?:$qq_paren)*? \) | \{ (?:$qq_brace)+? \} | \[ (?:$qq_bracket)+? \] ) )*) /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1),$2)"; } elsif (/\G (-[rwxoRWXOezfdlpSbcugkTB](?:\s+-[rwxoRWXOezfdlpSbcugkTB])+) \( ((?:$qq_paren)*?) \) /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1),$2)"; } elsif (/\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) (?= [a-z]+) /oxgc) { $slash = 'm//'; return "Esjis::filetest qw($1),"; } elsif (/\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) (\w+) /oxgc) { $slash = 'm//'; return "Esjis::filetest(qw($1),$2)"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ \s* (\") ((?:$qq_char)+?) (\") /oxgc) { $slash = 'm//'; return "Esjis::$1(" . e_qq('', $2,$4,$3) . ")"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ qq \s* (\#) ((?:$qq_char)+?) (\#) /oxgc) { $slash = 'm//'; return "Esjis::$1(" . e_qq('qq',$2,$4,$3) . ")"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ qq \s* (\() ((?:$qq_paren)+?) (\)) /oxgc) { $slash = 'm//'; return "Esjis::$1(" . e_qq('qq',$2,$4,$3) . ")"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ qq \s* (\{) ((?:$qq_brace)+?) (\}) /oxgc) { $slash = 'm//'; return "Esjis::$1(" . e_qq('qq',$2,$4,$3) . ")"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ qq \s* (\[) ((?:$qq_bracket)+?) (\]) /oxgc) { $slash = 'm//'; return "Esjis::$1(" . e_qq('qq',$2,$4,$3) . ")"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ qq \s* (\<) ((?:$qq_angle)+?) (\>) /oxgc) { $slash = 'm//'; return "Esjis::$1(" . e_qq('qq',$2,$4,$3) . ")"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ qq \s* (\S) ((?:$qq_char)+?) (\3) /oxgc) { $slash = 'm//'; return "Esjis::$1(" . e_qq('qq',$2,$4,$3) . ")"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ \s* (\') ((?:\\\1|\\\\|$q_char)+?) (\') /oxgc) { $slash = 'm//'; return "Esjis::$1(" . e_q ('', $2,$4,$3) . ")"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ q \s* (\#) ((?:\\\#|\\\\|$q_char)+?) (\#) /oxgc) { $slash = 'm//'; return "Esjis::$1(" . e_q ('q', $2,$4,$3) . ")"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ q \s* (\() ((?:\\\)|\\\\|$q_paren)+?) (\)) /oxgc) { $slash = 'm//'; return "Esjis::$1(" . e_q ('q', $2,$4,$3) . ")"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ q \s* (\{) ((?:\\\}|\\\\|$q_brace)+?) (\}) /oxgc) { $slash = 'm//'; return "Esjis::$1(" . e_q ('q', $2,$4,$3) . ")"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ q \s* (\[) ((?:\\\]|\\\\|$q_bracket)+?) (\]) /oxgc) { $slash = 'm//'; return "Esjis::$1(" . e_q ('q', $2,$4,$3) . ")"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ q \s* (\<) ((?:\\\>|\\\\|$q_angle)+?) (\>) /oxgc) { $slash = 'm//'; return "Esjis::$1(" . e_q ('q', $2,$4,$3) . ")"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ q \s* (\S) ((?:\\\1|\\\\|$q_char)+?) (\3) /oxgc) { $slash = 'm//'; return "Esjis::$1(" . e_q ('q', $2,$4,$3) . ")"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s* (\$ \w+(?: ::\w+)* (?: (?: ->)? (?: \( (?:$qq_paren)*? \) | \{ (?:$qq_brace)+? \} | \[ (?:$qq_bracket)+? \] ) )*) /oxgc) { $slash = 'm//'; return "Esjis::$1($2)"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s* \( ((?:$qq_paren)*?) \) /oxgc) { $slash = 'm//'; return "Esjis::$1($2)"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) (?= \s+ [a-z]+) /oxgc) { $slash = 'm//'; return "Esjis::$1"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ (\w+) /oxgc) { $slash = 'm//'; return "Esjis::$1(::"."$2)"; } elsif (/\G -(t) \s+ (\w+) /oxgc) { $slash = 'm//'; return "-t $2"; } elsif (/\G \b lstat (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'Esjis::lstat'; } elsif (/\G \b stat (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'Esjis::stat'; } # "-s '' ..." means file test "-s 'filename' ..." (not means "- s/// ...") elsif (/\G -s \s+ \s* (\") ((?:$qq_char)+?) (\") /oxgc) { $slash = 'm//'; return '-s ' . e_qq('', $1,$3,$2); } elsif (/\G -s \s+ qq \s* (\#) ((?:$qq_char)+?) (\#) /oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); } elsif (/\G -s \s+ qq \s* (\() ((?:$qq_paren)+?) (\)) /oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); } elsif (/\G -s \s+ qq \s* (\{) ((?:$qq_brace)+?) (\}) /oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); } elsif (/\G -s \s+ qq \s* (\[) ((?:$qq_bracket)+?) (\]) /oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); } elsif (/\G -s \s+ qq \s* (\<) ((?:$qq_angle)+?) (\>) /oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); } elsif (/\G -s \s+ qq \s* (\S) ((?:$qq_char)+?) (\3) /oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); } elsif (/\G -s \s+ \s* (\') ((?:\\\1|\\\\|$q_char)+?) (\') /oxgc) { $slash = 'm//'; return '-s ' . e_q ('', $1,$3,$2); } elsif (/\G -s \s+ q \s* (\#) ((?:\\\#|\\\\|$q_char)+?) (\#) /oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); } elsif (/\G -s \s+ q \s* (\() ((?:\\\)|\\\\|$q_paren)+?) (\)) /oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); } elsif (/\G -s \s+ q \s* (\{) ((?:\\\}|\\\\|$q_brace)+?) (\}) /oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); } elsif (/\G -s \s+ q \s* (\[) ((?:\\\]|\\\\|$q_bracket)+?) (\]) /oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); } elsif (/\G -s \s+ q \s* (\<) ((?:\\\>|\\\\|$q_angle)+?) (\>) /oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); } elsif (/\G -s \s+ q \s* (\S) ((?:\\\1|\\\\|$q_char)+?) (\3) /oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); } elsif (/\G -s \s* (\$ \w+(?: ::\w+)* (?: (?: ->)? (?: \( (?:$qq_paren)*? \) | \{ (?:$qq_brace)+? \} | \[ (?:$qq_bracket)+? \] ) )*) /oxgc) { $slash = 'm//'; return "-s $1"; } elsif (/\G -s \s* \( ((?:$qq_paren)*?) \) /oxgc) { $slash = 'm//'; return "-s ($1)"; } elsif (/\G -s (?= \s+ [a-z]+) /oxgc) { $slash = 'm//'; return '-s'; } elsif (/\G -s \s+ (\w+) /oxgc) { $slash = 'm//'; return "-s $1"; } elsif (/\G \b bytes::length (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'length'; } elsif (/\G \b bytes::chr (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'chr'; } elsif (/\G \b chr (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'Esjis::chr'; } elsif (/\G \b bytes::ord (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'div'; return 'ord'; } elsif (/\G \b ord (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'div'; return $function_ord; } elsif (/\G \b glob (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'Esjis::glob'; } elsif (/\G \b lc \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Esjis::lc_'; } elsif (/\G \b lcfirst \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Esjis::lcfirst_'; } elsif (/\G \b uc \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Esjis::uc_'; } elsif (/\G \b ucfirst \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Esjis::ucfirst_'; } elsif (/\G \b fc \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Esjis::fc_'; } elsif (/\G (-[rwxoRWXOezfdlpSbcugkTB](?:\s+-[rwxoRWXOezfdlpSbcugkTB])+) \b (?! \s* => ) /oxgc) { $slash = 'm//'; return "Esjis::filetest_(qw($1))"; } elsif (/\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \b (?! \s* => ) /oxgc) { $slash = 'm//'; return "Esjis::${1}_"; } elsif (/\G \b lstat \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Esjis::lstat_'; } elsif (/\G \b stat \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Esjis::stat_'; } elsif (/\G -s \b (?! \s* => ) /oxgc) { $slash = 'm//'; return '-s '; } elsif (/\G \b bytes::length \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'length'; } elsif (/\G \b bytes::chr \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'chr'; } elsif (/\G \b chr \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Esjis::chr_'; } elsif (/\G \b bytes::ord \b (?! \s* => ) /oxgc) { $slash = 'div'; return 'ord'; } elsif (/\G \b ord \b (?! \s* => ) /oxgc) { $slash = 'div'; return $function_ord_; } elsif (/\G \b glob \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Esjis::glob_'; } elsif (/\G \b reverse \b (?! \s* => ) /oxgc) { $slash = 'm//'; return $function_reverse; } elsif (/\G \b getc \b (?! \s* => ) /oxgc) { $slash = 'm//'; return $function_getc; } elsif (/\G \b opendir (\s* \( \s*) (?=[A-Za-z_]) /oxgc) { $slash = 'm//'; return "Esjis::opendir$1*"; } elsif (/\G \b opendir (\s+) (?=[A-Za-z_]) /oxgc) { $slash = 'm//'; return "Esjis::opendir$1*"; } elsif (/\G \b unlink \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Esjis::unlink'; } # chdir elsif (/\G \b (chdir) \b (?! \s* => ) /oxgc) { $slash = 'm//'; my $e = 'Esjis::chdir'; while (/\G ( \s+ | \( | \#.* ) /oxgc) { $e .= $1; } # end of chdir if (/\G (?= [,;\)\}\]] ) /oxgc) { return $e; } # chdir scalar value elsif (/\G ( [\$\@\&\*] $qq_scalar ) /oxgc) { return $e . e_string($1); } # chdir qq// elsif (/\G \b (qq) \b /oxgc) { if (/\G (\#) ((?:$qq_char)*?) (\#) /oxgc) { return $e . e_chdir('qq',$1,$3,$2); } # qq# # --> qr # # else { while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif (/\G (\() ((?:$qq_paren)*?) (\)) /oxgc) { return $e . e_chdir('qq',$1,$3,$2); } # qq ( ) --> qr ( ) elsif (/\G (\{) ((?:$qq_brace)*?) (\}) /oxgc) { return $e . e_chdir('qq',$1,$3,$2); } # qq { } --> qr { } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) /oxgc) { return $e . e_chdir('qq',$1,$3,$2); } # qq [ ] --> qr [ ] elsif (/\G (\<) ((?:$qq_angle)*?) (\>) /oxgc) { return $e . e_chdir('qq',$1,$3,$2); } # qq < > --> qr < > elsif (/\G ([*\-:?\\^|]) ((?:$qq_char)*?) (\1) /oxgc) { return $e . e_chdir('qq','{','}',$2); } # qq | | --> qr { } elsif (/\G (\S) ((?:$qq_char)*?) (\1) /oxgc) { return $e . e_chdir('qq',$1,$3,$2); } # qq * * --> qr * * } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # chdir q// elsif (/\G \b (q) \b /oxgc) { if (/\G (\#) ((?:\\\#|\\\\|$q_char)*?) (\#) /oxgc) { return $e . e_chdir_q('q',$1,$3,$2); } # q# # --> qr # # else { while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif (/\G (\() ((?:\\\\|\\\)|\\\(|$q_paren)*?) (\)) /oxgc) { return $e . e_chdir_q('q',$1,$3,$2); } # q ( ) --> qr ( ) elsif (/\G (\{) ((?:\\\\|\\\}|\\\{|$q_brace)*?) (\}) /oxgc) { return $e . e_chdir_q('q',$1,$3,$2); } # q { } --> qr { } elsif (/\G (\[) ((?:\\\\|\\\]|\\\[|$q_bracket)*?) (\]) /oxgc) { return $e . e_chdir_q('q',$1,$3,$2); } # q [ ] --> qr [ ] elsif (/\G (\<) ((?:\\\\|\\\>|\\\<|$q_angle)*?) (\>) /oxgc) { return $e . e_chdir_q('q',$1,$3,$2); } # q < > --> qr < > elsif (/\G ([*\-:?\\^|]) ((?:$q_char)*?) (\1) /oxgc) { return $e . e_chdir_q('q','{','}',$2); } # q | | --> qr { } elsif (/\G (\S) ((?:\\\\|\\\1| $q_char)*?) (\1) /oxgc) { return $e . e_chdir_q('q',$1,$3,$2); } # q * * --> qr * * } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # chdir '' elsif (/\G (\') /oxgc) { my $q_string = ''; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $q_string .= $1; } elsif (/\G (\\\') /oxgc) { $q_string .= $1; } elsif (/\G \' /oxgc) { return $e . e_chdir_q('',"'","'",$q_string); } elsif (/\G ($q_char) /oxgc) { $q_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } # chdir "" elsif (/\G (\") /oxgc) { my $qq_string = ''; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $qq_string .= $1; } elsif (/\G (\\\") /oxgc) { $qq_string .= $1; } elsif (/\G \" /oxgc) { return $e . e_chdir('','"','"',$qq_string); } elsif (/\G ($q_char) /oxgc) { $qq_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # split elsif (/\G \b (split) \b (?! \s* => ) /oxgc) { $slash = 'm//'; my $e = ''; while (/\G ( \s+ | \( | \#.* ) /oxgc) { $e .= $1; } # end of split if (/\G (?= [,;\)\}\]] ) /oxgc) { return 'Esjis::split' . $e; } # split scalar value elsif (/\G ( [\$\@\&\*] $qq_scalar ) /oxgc) { return 'Esjis::split' . $e . e_string($1); } # split literal space elsif (/\G \b qq (\#) [ ] (\#) /oxgc) { return 'Esjis::split' . $e . qq {qq$1 $2}; } elsif (/\G \b qq (\s*) (\() [ ] (\)) /oxgc) { return 'Esjis::split' . $e . qq{$1qq$2 $3}; } elsif (/\G \b qq (\s*) (\{) [ ] (\}) /oxgc) { return 'Esjis::split' . $e . qq{$1qq$2 $3}; } elsif (/\G \b qq (\s*) (\[) [ ] (\]) /oxgc) { return 'Esjis::split' . $e . qq{$1qq$2 $3}; } elsif (/\G \b qq (\s*) (\<) [ ] (\>) /oxgc) { return 'Esjis::split' . $e . qq{$1qq$2 $3}; } elsif (/\G \b qq (\s*) (\S) [ ] (\2) /oxgc) { return 'Esjis::split' . $e . qq{$1qq$2 $3}; } elsif (/\G \b q (\#) [ ] (\#) /oxgc) { return 'Esjis::split' . $e . qq {q$1 $2}; } elsif (/\G \b q (\s*) (\() [ ] (\)) /oxgc) { return 'Esjis::split' . $e . qq {$1q$2 $3}; } elsif (/\G \b q (\s*) (\{) [ ] (\}) /oxgc) { return 'Esjis::split' . $e . qq {$1q$2 $3}; } elsif (/\G \b q (\s*) (\[) [ ] (\]) /oxgc) { return 'Esjis::split' . $e . qq {$1q$2 $3}; } elsif (/\G \b q (\s*) (\<) [ ] (\>) /oxgc) { return 'Esjis::split' . $e . qq {$1q$2 $3}; } elsif (/\G \b q (\s*) (\S) [ ] (\2) /oxgc) { return 'Esjis::split' . $e . qq {$1q$2 $3}; } elsif (/\G ' [ ] ' /oxgc) { return 'Esjis::split' . $e . qq {' '}; } elsif (/\G " [ ] " /oxgc) { return 'Esjis::split' . $e . qq {" "}; } # split qq// elsif (/\G \b (qq) \b /oxgc) { if (/\G (\#) ((?:$qq_char)*?) (\#) /oxgc) { return e_split($e.'qr',$1,$3,$2,''); } # qq# # --> qr # # else { while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif (/\G (\() ((?:$qq_paren)*?) (\)) /oxgc) { return e_split($e.'qr',$1,$3,$2,''); } # qq ( ) --> qr ( ) elsif (/\G (\{) ((?:$qq_brace)*?) (\}) /oxgc) { return e_split($e.'qr',$1,$3,$2,''); } # qq { } --> qr { } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) /oxgc) { return e_split($e.'qr',$1,$3,$2,''); } # qq [ ] --> qr [ ] elsif (/\G (\<) ((?:$qq_angle)*?) (\>) /oxgc) { return e_split($e.'qr',$1,$3,$2,''); } # qq < > --> qr < > elsif (/\G ([*\-:?\\^|]) ((?:$qq_char)*?) (\1) /oxgc) { return e_split($e.'qr','{','}',$2,''); } # qq | | --> qr { } elsif (/\G (\S) ((?:$qq_char)*?) (\1) /oxgc) { return e_split($e.'qr',$1,$3,$2,''); } # qq * * --> qr * * } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # split qr// elsif (/\G \b (qr) \b /oxgc) { if (/\G (\#) ((?:$qq_char)*?) (\#) ([imosxpadlubB]*) /oxgc) { return e_split ($e.'qr',$1,$3,$2,$4); } # qr# # else { while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif (/\G (\() ((?:$qq_paren)*?) (\)) ([imosxpadlubB]*) /oxgc) { return e_split ($e.'qr',$1, $3, $2,$4); } # qr ( ) elsif (/\G (\{) ((?:$qq_brace)*?) (\}) ([imosxpadlubB]*) /oxgc) { return e_split ($e.'qr',$1, $3, $2,$4); } # qr { } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) ([imosxpadlubB]*) /oxgc) { return e_split ($e.'qr',$1, $3, $2,$4); } # qr [ ] elsif (/\G (\<) ((?:$qq_angle)*?) (\>) ([imosxpadlubB]*) /oxgc) { return e_split ($e.'qr',$1, $3, $2,$4); } # qr < > elsif (/\G (\') ((?:$qq_char)*?) (\') ([imosxpadlubB]*) /oxgc) { return e_split_q($e.'qr',$1, $3, $2,$4); } # qr ' ' elsif (/\G ([*\-:?\\^|]) ((?:$qq_char)*?) (\1) ([imosxpadlubB]*) /oxgc) { return e_split ($e.'qr','{','}',$2,$4); } # qr | | --> qr { } elsif (/\G (\S) ((?:$qq_char)*?) (\1) ([imosxpadlubB]*) /oxgc) { return e_split ($e.'qr',$1, $3, $2,$4); } # qr * * } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # split q// elsif (/\G \b (q) \b /oxgc) { if (/\G (\#) ((?:\\\#|\\\\|$q_char)*?) (\#) /oxgc) { return e_split_q($e.'qr',$1,$3,$2,''); } # q# # --> qr # # else { while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif (/\G (\() ((?:\\\\|\\\)|\\\(|$q_paren)*?) (\)) /oxgc) { return e_split_q($e.'qr',$1,$3,$2,''); } # q ( ) --> qr ( ) elsif (/\G (\{) ((?:\\\\|\\\}|\\\{|$q_brace)*?) (\}) /oxgc) { return e_split_q($e.'qr',$1,$3,$2,''); } # q { } --> qr { } elsif (/\G (\[) ((?:\\\\|\\\]|\\\[|$q_bracket)*?) (\]) /oxgc) { return e_split_q($e.'qr',$1,$3,$2,''); } # q [ ] --> qr [ ] elsif (/\G (\<) ((?:\\\\|\\\>|\\\<|$q_angle)*?) (\>) /oxgc) { return e_split_q($e.'qr',$1,$3,$2,''); } # q < > --> qr < > elsif (/\G ([*\-:?\\^|]) ((?:$q_char)*?) (\1) /oxgc) { return e_split_q($e.'qr','{','}',$2,''); } # q | | --> qr { } elsif (/\G (\S) ((?:\\\\|\\\1| $q_char)*?) (\1) /oxgc) { return e_split_q($e.'qr',$1,$3,$2,''); } # q * * --> qr * * } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # split m// elsif (/\G \b (m) \b /oxgc) { if (/\G (\#) ((?:$qq_char)*?) (\#) ([cgimosxpadlubB]*) /oxgc) { return e_split ($e.'qr',$1,$3,$2,$4); } # m# # --> qr # # else { while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif (/\G (\() ((?:$qq_paren)*?) (\)) ([cgimosxpadlubB]*) /oxgc) { return e_split ($e.'qr',$1, $3, $2,$4); } # m ( ) --> qr ( ) elsif (/\G (\{) ((?:$qq_brace)*?) (\}) ([cgimosxpadlubB]*) /oxgc) { return e_split ($e.'qr',$1, $3, $2,$4); } # m { } --> qr { } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) ([cgimosxpadlubB]*) /oxgc) { return e_split ($e.'qr',$1, $3, $2,$4); } # m [ ] --> qr [ ] elsif (/\G (\<) ((?:$qq_angle)*?) (\>) ([cgimosxpadlubB]*) /oxgc) { return e_split ($e.'qr',$1, $3, $2,$4); } # m < > --> qr < > elsif (/\G (\') ((?:$qq_char)*?) (\') ([cgimosxpadlubB]*) /oxgc) { return e_split_q($e.'qr',$1, $3, $2,$4); } # m ' ' --> qr ' ' elsif (/\G ([*\-:?\\^|]) ((?:$qq_char)*?) (\1) ([cgimosxpadlubB]*) /oxgc) { return e_split ($e.'qr','{','}',$2,$4); } # m | | --> qr { } elsif (/\G (\S) ((?:$qq_char)*?) (\1) ([cgimosxpadlubB]*) /oxgc) { return e_split ($e.'qr',$1, $3, $2,$4); } # m * * --> qr * * } die __FILE__, ": Search pattern not terminated"; } } # split '' elsif (/\G (\') /oxgc) { my $q_string = ''; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $q_string .= $1; } elsif (/\G (\\\') /oxgc) { $q_string .= $1; } # splitqr'' --> split qr'' elsif (/\G \' /oxgc) { return e_split_q($e.q{ qr},"'","'",$q_string,''); } # ' ' --> qr ' ' elsif (/\G ($q_char) /oxgc) { $q_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } # split "" elsif (/\G (\") /oxgc) { my $qq_string = ''; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $qq_string .= $1; } elsif (/\G (\\\") /oxgc) { $qq_string .= $1; } # splitqr"" --> split qr"" elsif (/\G \" /oxgc) { return e_split($e.q{ qr},'"','"',$qq_string,''); } # " " --> qr " " elsif (/\G ($q_char) /oxgc) { $qq_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } # split // elsif (/\G (\/) /oxgc) { my $regexp = ''; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $regexp .= $1; } elsif (/\G (\\\/) /oxgc) { $regexp .= $1; } # splitqr// --> split qr// elsif (/\G \/ ([cgimosxpadlubB]*) /oxgc) { return e_split($e.q{ qr}, '/','/',$regexp,$1); } # / / --> qr / / elsif (/\G ($q_char) /oxgc) { $regexp .= $1; } } die __FILE__, ": Search pattern not terminated"; } } # tr/// or y/// # about [cdsrbB]* (/B modifier) # # P.559 appendix C # of ISBN 4-89052-384-7 Programming perl # (Japanese title is: Perl puroguramingu) elsif (/\G \b (tr|y) \b /oxgc) { my $ope = $1; # $1 $2 $3 $4 $5 $6 if (/\G (\#) ((?:$qq_char)*?) (\#) ((?:$qq_char)*?) (\#) ([cdsrbB]*) /oxgc) { # tr# # # my @tr = ($tr_variable,$2); return e_tr(@tr,'',$4,$6); } else { my $e = ''; while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif (/\G (\() ((?:$qq_paren)*?) (\)) /oxgc) { my @tr = ($tr_variable,$2); while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif (/\G (\() ((?:$qq_paren)*?) (\)) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr ( ) ( ) elsif (/\G (\{) ((?:$qq_brace)*?) (\}) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr ( ) { } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr ( ) [ ] elsif (/\G (\<) ((?:$qq_angle)*?) (\>) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr ( ) < > elsif (/\G (\S) ((?:$qq_char)*?) (\1) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr ( ) * * } die __FILE__, ": Transliteration replacement not terminated"; } elsif (/\G (\{) ((?:$qq_brace)*?) (\}) /oxgc) { my @tr = ($tr_variable,$2); while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif (/\G (\() ((?:$qq_paren)*?) (\)) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr { } ( ) elsif (/\G (\{) ((?:$qq_brace)*?) (\}) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr { } { } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr { } [ ] elsif (/\G (\<) ((?:$qq_angle)*?) (\>) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr { } < > elsif (/\G (\S) ((?:$qq_char)*?) (\1) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr { } * * } die __FILE__, ": Transliteration replacement not terminated"; } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) /oxgc) { my @tr = ($tr_variable,$2); while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif (/\G (\() ((?:$qq_paren)*?) (\)) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr [ ] ( ) elsif (/\G (\{) ((?:$qq_brace)*?) (\}) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr [ ] { } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr [ ] [ ] elsif (/\G (\<) ((?:$qq_angle)*?) (\>) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr [ ] < > elsif (/\G (\S) ((?:$qq_char)*?) (\1) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr [ ] * * } die __FILE__, ": Transliteration replacement not terminated"; } elsif (/\G (\<) ((?:$qq_angle)*?) (\>) /oxgc) { my @tr = ($tr_variable,$2); while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif (/\G (\() ((?:$qq_paren)*?) (\)) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr < > ( ) elsif (/\G (\{) ((?:$qq_brace)*?) (\}) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr < > { } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr < > [ ] elsif (/\G (\<) ((?:$qq_angle)*?) (\>) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr < > < > elsif (/\G (\S) ((?:$qq_char)*?) (\1) ([cdsrbB]*) /oxgc) { return e_tr(@tr,$e,$2,$4); } # tr < > * * } die __FILE__, ": Transliteration replacement not terminated"; } # $1 $2 $3 $4 $5 $6 elsif (/\G (\S) ((?:$qq_char)*?) (\1) ((?:$qq_char)*?) (\1) ([cdsrbB]*) /oxgc) { # tr * * * my @tr = ($tr_variable,$2); return e_tr(@tr,'',$4,$6); } } die __FILE__, ": Transliteration pattern not terminated"; } } # qq// elsif (/\G \b (qq) \b /oxgc) { my $ope = $1; # if (/\G (\#) ((?:$qq_char)*?) (\#) /oxgc) { return e_qq($ope,$1,$3,$2); } # qq# # if (/\G (\#) /oxgc) { # qq# # my $qq_string = ''; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $qq_string .= $1; } elsif (/\G (\\\#) /oxgc) { $qq_string .= $1; } elsif (/\G (\#) /oxgc) { return e_qq($ope,'#','#',$qq_string); } elsif (/\G ($qq_char) /oxgc) { $qq_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } else { my $e = ''; while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } # elsif (/\G (\() ((?:$qq_paren)*?) (\)) /oxgc) { return $e . e_qq($ope,$1,$3,$2); } # qq ( ) elsif (/\G (\() /oxgc) { # qq ( ) my $qq_string = ''; local $nest = 1; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $qq_string .= $1; } elsif (/\G (\\\)) /oxgc) { $qq_string .= $1; } elsif (/\G (\() /oxgc) { $qq_string .= $1; $nest++; } elsif (/\G (\)) /oxgc) { if (--$nest == 0) { return $e . e_qq($ope,'(',')',$qq_string); } else { $qq_string .= $1; } } elsif (/\G ($qq_char) /oxgc) { $qq_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } # elsif (/\G (\{) ((?:$qq_brace)*?) (\}) /oxgc) { return $e . e_qq($ope,$1,$3,$2); } # qq { } elsif (/\G (\{) /oxgc) { # qq { } my $qq_string = ''; local $nest = 1; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $qq_string .= $1; } elsif (/\G (\\\}) /oxgc) { $qq_string .= $1; } elsif (/\G (\{) /oxgc) { $qq_string .= $1; $nest++; } elsif (/\G (\}) /oxgc) { if (--$nest == 0) { return $e . e_qq($ope,'{','}',$qq_string); } else { $qq_string .= $1; } } elsif (/\G ($qq_char) /oxgc) { $qq_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } # elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) /oxgc) { return $e . e_qq($ope,$1,$3,$2); } # qq [ ] elsif (/\G (\[) /oxgc) { # qq [ ] my $qq_string = ''; local $nest = 1; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $qq_string .= $1; } elsif (/\G (\\\]) /oxgc) { $qq_string .= $1; } elsif (/\G (\[) /oxgc) { $qq_string .= $1; $nest++; } elsif (/\G (\]) /oxgc) { if (--$nest == 0) { return $e . e_qq($ope,'[',']',$qq_string); } else { $qq_string .= $1; } } elsif (/\G ($qq_char) /oxgc) { $qq_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } # elsif (/\G (\<) ((?:$qq_angle)*?) (\>) /oxgc) { return $e . e_qq($ope,$1,$3,$2); } # qq < > elsif (/\G (\<) /oxgc) { # qq < > my $qq_string = ''; local $nest = 1; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $qq_string .= $1; } elsif (/\G (\\\>) /oxgc) { $qq_string .= $1; } elsif (/\G (\<) /oxgc) { $qq_string .= $1; $nest++; } elsif (/\G (\>) /oxgc) { if (--$nest == 0) { return $e . e_qq($ope,'<','>',$qq_string); } else { $qq_string .= $1; } } elsif (/\G ($qq_char) /oxgc) { $qq_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } # elsif (/\G (\S) ((?:$qq_char)*?) (\1) /oxgc) { return $e . e_qq($ope,$1,$3,$2); } # qq * * elsif (/\G (\S) /oxgc) { # qq * * my $delimiter = $1; my $qq_string = ''; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $qq_string .= $1; } elsif (/\G (\\\Q$delimiter\E) /oxgc) { $qq_string .= $1; } elsif (/\G (\Q$delimiter\E) /oxgc) { return $e . e_qq($ope,$delimiter,$delimiter,$qq_string); } elsif (/\G ($qq_char) /oxgc) { $qq_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # qr// elsif (/\G \b (qr) \b /oxgc) { my $ope = $1; if (/\G (\#) ((?:$qq_char)*?) (\#) ([imosxpadlubB]*) /oxgc) { # qr# # # return e_qr($ope,$1,$3,$2,$4); } else { my $e = ''; while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif (/\G (\() ((?:$qq_paren)*?) (\)) ([imosxpadlubB]*) /oxgc) { return $e . e_qr ($ope,$1, $3, $2,$4); } # qr ( ) elsif (/\G (\{) ((?:$qq_brace)*?) (\}) ([imosxpadlubB]*) /oxgc) { return $e . e_qr ($ope,$1, $3, $2,$4); } # qr { } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) ([imosxpadlubB]*) /oxgc) { return $e . e_qr ($ope,$1, $3, $2,$4); } # qr [ ] elsif (/\G (\<) ((?:$qq_angle)*?) (\>) ([imosxpadlubB]*) /oxgc) { return $e . e_qr ($ope,$1, $3, $2,$4); } # qr < > elsif (/\G (\') ((?:$qq_char)*?) (\') ([imosxpadlubB]*) /oxgc) { return $e . e_qr_q($ope,$1, $3, $2,$4); } # qr ' ' elsif (/\G ([*\-:?\\^|]) ((?:$qq_char)*?) (\1) ([imosxpadlubB]*) /oxgc) { return $e . e_qr ($ope,'{','}',$2,$4); } # qr | | --> qr { } elsif (/\G (\S) ((?:$qq_char)*?) (\1) ([imosxpadlubB]*) /oxgc) { return $e . e_qr ($ope,$1, $3, $2,$4); } # qr * * } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # qw// elsif (/\G \b (qw) \b /oxgc) { my $ope = $1; if (/\G (\#) (.*?) (\#) /oxmsgc) { # qw# # return e_qw($ope,$1,$3,$2); } else { my $e = ''; while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif (/\G (\() ([^(]*?) (\)) /oxmsgc) { return $e . e_qw($ope,$1,$3,$2); } # qw ( ) elsif (/\G (\() ((?:$q_paren)*?) (\)) /oxmsgc) { return $e . e_qw($ope,$1,$3,$2); } # qw ( ) elsif (/\G (\{) ([^{]*?) (\}) /oxmsgc) { return $e . e_qw($ope,$1,$3,$2); } # qw { } elsif (/\G (\{) ((?:$q_brace)*?) (\}) /oxmsgc) { return $e . e_qw($ope,$1,$3,$2); } # qw { } elsif (/\G (\[) ([^[]*?) (\]) /oxmsgc) { return $e . e_qw($ope,$1,$3,$2); } # qw [ ] elsif (/\G (\[) ((?:$q_bracket)*?) (\]) /oxmsgc) { return $e . e_qw($ope,$1,$3,$2); } # qw [ ] elsif (/\G (\<) ([^<]*?) (\>) /oxmsgc) { return $e . e_qw($ope,$1,$3,$2); } # qw < > elsif (/\G (\<) ((?:$q_angle)*?) (\>) /oxmsgc) { return $e . e_qw($ope,$1,$3,$2); } # qw < > elsif (/\G ([\x21-\x3F]) (.*?) (\1) /oxmsgc) { return $e . e_qw($ope,$1,$3,$2); } # qw * * elsif (/\G (\S) ((?:$q_char)*?) (\1) /oxmsgc) { return $e . e_qw($ope,$1,$3,$2); } # qw * * } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # qx// elsif (/\G \b (qx) \b /oxgc) { my $ope = $1; if (/\G (\#) ((?:$qq_char)*?) (\#) /oxgc) { # qx# # return e_qq($ope,$1,$3,$2); } else { my $e = ''; while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif (/\G (\() ((?:$qq_paren)*?) (\)) /oxgc) { return $e . e_qq($ope,$1,$3,$2); } # qx ( ) elsif (/\G (\{) ((?:$qq_brace)*?) (\}) /oxgc) { return $e . e_qq($ope,$1,$3,$2); } # qx { } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) /oxgc) { return $e . e_qq($ope,$1,$3,$2); } # qx [ ] elsif (/\G (\<) ((?:$qq_angle)*?) (\>) /oxgc) { return $e . e_qq($ope,$1,$3,$2); } # qx < > elsif (/\G (\') ((?:$qq_char)*?) (\') /oxgc) { return $e . e_q ($ope,$1,$3,$2); } # qx ' ' elsif (/\G (\S) ((?:$qq_char)*?) (\1) /oxgc) { return $e . e_qq($ope,$1,$3,$2); } # qx * * } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # q// elsif (/\G \b (q) \b /oxgc) { my $ope = $1; # if (/\G (\#) ((?:\\\#|\\\\|$q_char)*?) (\#) /oxgc) { return e_q($ope,$1,$3,$2); } # q# # # avoid "Error: Runtime exception" of perl version 5.005_03 # (and so on) if (/\G (\#) /oxgc) { # q# # my $q_string = ''; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $q_string .= $1; } elsif (/\G (\\\#) /oxgc) { $q_string .= $1; } elsif (/\G (\#) /oxgc) { return e_q($ope,'#','#',$q_string); } elsif (/\G ($q_char) /oxgc) { $q_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } else { my $e = ''; while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } # elsif (/\G (\() ((?:\\\)|\\\\|$q_paren)*?) (\)) /oxgc) { return $e . e_q($ope,$1,$3,$2); } # q ( ) elsif (/\G (\() /oxgc) { # q ( ) my $q_string = ''; local $nest = 1; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $q_string .= $1; } elsif (/\G (\\\)) /oxgc) { $q_string .= $1; } elsif (/\G (\\\() /oxgc) { $q_string .= $1; } elsif (/\G (\() /oxgc) { $q_string .= $1; $nest++; } elsif (/\G (\)) /oxgc) { if (--$nest == 0) { return $e . e_q($ope,'(',')',$q_string); } else { $q_string .= $1; } } elsif (/\G ($q_char) /oxgc) { $q_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } # elsif (/\G (\{) ((?:\\\}|\\\\|$q_brace)*?) (\}) /oxgc) { return $e . e_q($ope,$1,$3,$2); } # q { } elsif (/\G (\{) /oxgc) { # q { } my $q_string = ''; local $nest = 1; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $q_string .= $1; } elsif (/\G (\\\}) /oxgc) { $q_string .= $1; } elsif (/\G (\\\{) /oxgc) { $q_string .= $1; } elsif (/\G (\{) /oxgc) { $q_string .= $1; $nest++; } elsif (/\G (\}) /oxgc) { if (--$nest == 0) { return $e . e_q($ope,'{','}',$q_string); } else { $q_string .= $1; } } elsif (/\G ($q_char) /oxgc) { $q_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } # elsif (/\G (\[) ((?:\\\]|\\\\|$q_bracket)*?) (\]) /oxgc) { return $e . e_q($ope,$1,$3,$2); } # q [ ] elsif (/\G (\[) /oxgc) { # q [ ] my $q_string = ''; local $nest = 1; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $q_string .= $1; } elsif (/\G (\\\]) /oxgc) { $q_string .= $1; } elsif (/\G (\\\[) /oxgc) { $q_string .= $1; } elsif (/\G (\[) /oxgc) { $q_string .= $1; $nest++; } elsif (/\G (\]) /oxgc) { if (--$nest == 0) { return $e . e_q($ope,'[',']',$q_string); } else { $q_string .= $1; } } elsif (/\G ($q_char) /oxgc) { $q_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } # elsif (/\G (\<) ((?:\\\>|\\\\|$q_angle)*?) (\>) /oxgc) { return $e . e_q($ope,$1,$3,$2); } # q < > elsif (/\G (\<) /oxgc) { # q < > my $q_string = ''; local $nest = 1; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $q_string .= $1; } elsif (/\G (\\\>) /oxgc) { $q_string .= $1; } elsif (/\G (\\\<) /oxgc) { $q_string .= $1; } elsif (/\G (\<) /oxgc) { $q_string .= $1; $nest++; } elsif (/\G (\>) /oxgc) { if (--$nest == 0) { return $e . e_q($ope,'<','>',$q_string); } else { $q_string .= $1; } } elsif (/\G ($q_char) /oxgc) { $q_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } # elsif (/\G (\S) ((?:\\\1|\\\\|$q_char)*?) (\1) /oxgc) { return $e . e_q($ope,$1,$3,$2); } # q * * elsif (/\G (\S) /oxgc) { # q * * my $delimiter = $1; my $q_string = ''; while (not /\G \z/oxgc) { if (/\G (\\\\) /oxgc) { $q_string .= $1; } elsif (/\G (\\\Q$delimiter\E) /oxgc) { $q_string .= $1; } elsif (/\G (\Q$delimiter\E) /oxgc) { return $e . e_q($ope,$delimiter,$delimiter,$q_string); } elsif (/\G ($q_char) /oxgc) { $q_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # m// elsif (/\G \b (m) \b /oxgc) { my $ope = $1; if (/\G (\#) ((?:$qq_char)*?) (\#) ([cgimosxpadlubB]*) /oxgc) { # m# # return e_qr($ope,$1,$3,$2,$4); } else { my $e = ''; while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif (/\G (\() ((?:$qq_paren)*?) (\)) ([cgimosxpadlubB]*) /oxgc) { return $e . e_qr ($ope,$1, $3, $2,$4); } # m ( ) elsif (/\G (\{) ((?:$qq_brace)*?) (\}) ([cgimosxpadlubB]*) /oxgc) { return $e . e_qr ($ope,$1, $3, $2,$4); } # m { } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) ([cgimosxpadlubB]*) /oxgc) { return $e . e_qr ($ope,$1, $3, $2,$4); } # m [ ] elsif (/\G (\<) ((?:$qq_angle)*?) (\>) ([cgimosxpadlubB]*) /oxgc) { return $e . e_qr ($ope,$1, $3, $2,$4); } # m < > elsif (/\G (\?) ((?:$qq_char)*?) (\?) ([cgimosxpadlubB]*) /oxgc) { return $e . e_qr ($ope,$1, $3, $2,$4); } # m ? ? elsif (/\G (\') ((?:$qq_char)*?) (\') ([cgimosxpadlubB]*) /oxgc) { return $e . e_qr_q($ope,$1, $3, $2,$4); } # m ' ' elsif (/\G ([*\-:\\^|]) ((?:$qq_char)*?) (\1) ([cgimosxpadlubB]*) /oxgc) { return $e . e_qr ($ope,'{','}',$2,$4); } # m | | --> m { } elsif (/\G (\S) ((?:$qq_char)*?) (\1) ([cgimosxpadlubB]*) /oxgc) { return $e . e_qr ($ope,$1, $3, $2,$4); } # m * * } die __FILE__, ": Search pattern not terminated"; } } # s/// # about [cegimosxpradlubB]* (/cg modifier) # # P.67 Pattern-Matching Operators # of ISBN 0-596-00241-6 Perl in a Nutshell, Second Edition. elsif (/\G \b (s) \b /oxgc) { my $ope = $1; # $1 $2 $3 $4 $5 $6 if (/\G (\#) ((?:$qq_char)*?) (\#) ((?:$qq_char)*?) (\#) ([cegimosxpradlubB]*) /oxgc) { # s# # # return e_sub($sub_variable,$1,$2,$3,$3,$4,$5,$6); } else { my $e = ''; while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif (/\G (\() ((?:$qq_paren)*?) (\)) /oxgc) { my @s = ($1,$2,$3); while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } # $1 $2 $3 $4 elsif (/\G (\() ((?:$qq_paren)*?) (\)) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\{) ((?:$qq_brace)*?) (\}) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\<) ((?:$qq_angle)*?) (\>) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\') ((?:$qq_char)*?) (\') ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\$) ((?:$qq_char)*?) (\$) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\:) ((?:$qq_char)*?) (\:) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\@) ((?:$qq_char)*?) (\@) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\S) ((?:$qq_char)*?) (\1) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } } die __FILE__, ": Substitution replacement not terminated"; } elsif (/\G (\{) ((?:$qq_brace)*?) (\}) /oxgc) { my @s = ($1,$2,$3); while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } # $1 $2 $3 $4 elsif (/\G (\() ((?:$qq_paren)*?) (\)) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\{) ((?:$qq_brace)*?) (\}) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\<) ((?:$qq_angle)*?) (\>) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\') ((?:$qq_char)*?) (\') ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\$) ((?:$qq_char)*?) (\$) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\:) ((?:$qq_char)*?) (\:) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\@) ((?:$qq_char)*?) (\@) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\S) ((?:$qq_char)*?) (\1) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } } die __FILE__, ": Substitution replacement not terminated"; } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) /oxgc) { my @s = ($1,$2,$3); while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } # $1 $2 $3 $4 elsif (/\G (\() ((?:$qq_paren)*?) (\)) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\{) ((?:$qq_brace)*?) (\}) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\<) ((?:$qq_angle)*?) (\>) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\') ((?:$qq_char)*?) (\') ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\$) ((?:$qq_char)*?) (\$) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\S) ((?:$qq_char)*?) (\1) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } } die __FILE__, ": Substitution replacement not terminated"; } elsif (/\G (\<) ((?:$qq_angle)*?) (\>) /oxgc) { my @s = ($1,$2,$3); while (not /\G \z/oxgc) { if (/\G (\s+|\#.*) /oxgc) { $e .= $1; } # $1 $2 $3 $4 elsif (/\G (\() ((?:$qq_paren)*?) (\)) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\{) ((?:$qq_brace)*?) (\}) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\[) ((?:$qq_bracket)*?) (\]) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\<) ((?:$qq_angle)*?) (\>) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\') ((?:$qq_char)*?) (\') ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\$) ((?:$qq_char)*?) (\$) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\:) ((?:$qq_char)*?) (\:) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\@) ((?:$qq_char)*?) (\@) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } elsif (/\G (\S) ((?:$qq_char)*?) (\1) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,@s,$1,$2,$3,$4); } } die __FILE__, ": Substitution replacement not terminated"; } # $1 $2 $3 $4 $5 $6 elsif (/\G (\') ((?:$qq_char)*?) (\') ((?:$qq_char)*?) (\') ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,$1,$2,$3,$3,$4,$5,$6); } # $1 $2 $3 $4 $5 $6 elsif (/\G ([*\-:?\\^|]) ((?:$qq_char)*?) (\1) ((?:$qq_char)*?) (\1) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,'{',$2,'}','{',$4,'}',$6); # s | | | --> s { } { } } # $1 $2 $3 $4 $5 $6 elsif (/\G (\$) ((?:$qq_char)*?) (\1) ((?:$qq_char)*?) (\1) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,$1,$2,$3,$3,$4,$5,$6); } # $1 $2 $3 $4 $5 $6 elsif (/\G (\S) ((?:$qq_char)*?) (\1) ((?:$qq_char)*?) (\1) ([cegimosxpradlubB]*) /oxgc) { return e_sub($sub_variable,$1,$2,$3,$3,$4,$5,$6); } } die __FILE__, ": Substitution pattern not terminated"; } } # do elsif (/\G \b do (?= \s* \{ ) /oxmsgc) { return 'do'; } elsif (/\G \b do (?= \s+ (?: q|qq|qx) \b) /oxmsgc) { return 'Esjis::do'; } elsif (/\G \b do (?= \s+ \w+) /oxmsgc) { return 'do'; } elsif (/\G \b do (?= \s* \$ \w+ (?: ::\w+)* \( ) /oxmsgc) { return 'do'; } elsif (/\G \b do \b /oxmsgc) { return 'Esjis::do'; } # require ignore module elsif (/\G \b require (\s+ (?:$ignore_modules) .*? ;) ([ \t]* [#\n]) /oxmsgc) { return "# require$1$2"; } elsif (/\G \b require (\s+ (?:$ignore_modules) .*? ;) ([ \t]* [^\x81-\x9F\xE0-\xFC#]) /oxmsgc) { return "# require$1\n$2"; } elsif (/\G \b require (\s+ (?:$ignore_modules)) \b /oxmsgc) { return "# require$1"; } # require version number elsif (/\G \b require \s+ (0[0-7_]*) \s* ; /oxmsgc) { return "require $1;"; } elsif (/\G \b require \s+ ([1-9][0-9_]*(?:\.[0-9_]+)*) \s* ; /oxmsgc) { return "require $1;"; } elsif (/\G \b require \s+ (v[0-9][0-9_]*(?:\.[0-9_]+)*) \s* ; /oxmsgc) { return "require $1;"; } # require bare package name elsif (/\G \b require \s+ ([A-Za-z_]\w* (?: :: [A-Za-z_]\w*)*) \s* ; /oxmsgc) { return "require $1;"; } # require else elsif (/\G \b require \s* ; /oxmsgc) { return 'Esjis::require;'; } elsif (/\G \b require \b /oxmsgc) { return 'Esjis::require'; } # use strict; --> use strict; no strict qw(refs); elsif (/\G \b use (\s+ strict .*? ;) ([ \t]* [#\n]) /oxmsgc) { return "use$1 no strict qw(refs);$2"; } elsif (/\G \b use (\s+ strict .*? ;) ([ \t]* [^\x81-\x9F\xE0-\xFC#]) /oxmsgc) { return "use$1 no strict qw(refs);\n$2"; } elsif (/\G \b use (\s+ strict) \b /oxmsgc) { return "use$1; no strict qw(refs)"; } # use 5.12.0; --> use 5.12.0; no strict qw(refs); elsif (/\G \b use \s+ (([1-9][0-9_]*)(?:\.([0-9_]+))*) \s* ; /oxmsgc) { if (($2 >= 6) or (($2 == 5) and ($3 >= 12))) { return "use$1 no strict qw(refs);"; } else { return "use$1"; } } elsif (/\G \b use \s+ (v([0-9][0-9_]*)(?:\.([0-9_]+))*) \s* ; /oxmsgc) { if (($2 >= 6) or (($2 == 5) and ($3 >= 12))) { return "use$1 no strict qw(refs);"; } else { return "use$1"; } } # ignore use module elsif (/\G \b use (\s+ (?:$ignore_modules) .*? ;) ([ \t]* [#\n]) /oxmsgc) { return "# use$1$2"; } elsif (/\G \b use (\s+ (?:$ignore_modules) .*? ;) ([ \t]* [^\x81-\x9F\xE0-\xFC#]) /oxmsgc) { return "# use$1\n$2"; } elsif (/\G \b use (\s+ (?:$ignore_modules)) \b /oxmsgc) { return "# use$1"; } # ignore no module elsif (/\G \b no (\s+ (?:$ignore_modules) .*? ;) ([ \t]* [#\n]) /oxmsgc) { return "# no$1$2"; } elsif (/\G \b no (\s+ (?:$ignore_modules) .*? ;) ([ \t]* [^\x81-\x9F\xE0-\xFC#]) /oxmsgc) { return "# no$1\n$2"; } elsif (/\G \b no (\s+ (?:$ignore_modules)) \b /oxmsgc) { return "# no$1"; } # use without import elsif (/\G \b use \s+ (0[0-7_]*) \s* ; /oxmsgc) { return "use $1;"; } elsif (/\G \b use \s+ ([1-9][0-9_]*(?:\.[0-9_]+)*) \s* ; /oxmsgc) { return "use $1;"; } elsif (/\G \b use \s+ (v[0-9][0-9_]*(?:\.[0-9_]+)*) \s* ; /oxmsgc) { return "use $1;"; } elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s* (\() \s* \) \s* ; /oxmsgc) { return e_use_noimport($1); } elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s+ qw \s* (\() \s* \) \s* ; /oxmsgc) { return e_use_noimport($1); } elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s+ qw \s* (\{) \s* \} \s* ; /oxmsgc) { return e_use_noimport($1); } elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s+ qw \s* (\[) \s* \] \s* ; /oxmsgc) { return e_use_noimport($1); } elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s+ qw \s* (\<) \s* \> \s* ; /oxmsgc) { return e_use_noimport($1); } elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s+ qw \s* ([\x21-\x3F]) \s* \2 \s* ; /oxmsgc) { return e_use_noimport($1); } elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s+ qw \s* (\S) \s* \2 \s* ; /oxmsgc) { return e_use_noimport($1); } # use with import no parameter elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s* ; /oxmsgc) { return e_use_noparam($1); } # use with import parameters elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s* ( (\() [^\x81-\x9F\xE0-\xFC)]* \)) \s* ; /oxmsgc) { return e_use($1,$2); } elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s* ( (\') [^\x81-\x9F\xE0-\xFC']* \') \s* ; /oxmsgc) { return e_use($1,$2); } elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s* ( (\") [^\x81-\x9F\xE0-\xFC"]* \") \s* ; /oxmsgc) { return e_use($1,$2); } elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s+ ((?:q|qq|qw) \s* (\() [^\x81-\x9F\xE0-\xFC)]* \)) \s* ; /oxmsgc) { return e_use($1,$2); } elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s+ ((?:q|qq|qw) \s* (\{) (?:$q_char)*? \}) \s* ; /oxmsgc) { return e_use($1,$2); } elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s+ ((?:q|qq|qw) \s* (\[) (?:$q_char)*? \]) \s* ; /oxmsgc) { return e_use($1,$2); } elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s+ ((?:q|qq|qw) \s* (\<) [^\x81-\x9F\xE0-\xFC>]* \>) \s* ; /oxmsgc) { return e_use($1,$2); } elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s+ ((?:q|qq|qw) \s* ([\x21-\x3F]) .*? \3) \s* ; /oxmsgc) { return e_use($1,$2); } elsif (/\G \b use \s+ ([A-Z]\w*(?: ::\w+)*) \s+ ((?:q|qq|qw) \s* (\S) (?:$q_char)*? \3) \s* ; /oxmsgc) { return e_use($1,$2); } # no without unimport elsif (/\G \b no \s+ (0[0-7_]*) \s* ; /oxmsgc) { return "no $1;"; } elsif (/\G \b no \s+ ([1-9][0-9_]*(?:\.[0-9_]+)*) \s* ; /oxmsgc) { return "no $1;"; } elsif (/\G \b no \s+ (v[0-9][0-9_]*(?:\.[0-9_]+)*) \s* ; /oxmsgc) { return "no $1;"; } elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s* (\() \s* \) \s* ; /oxmsgc) { return e_no_nounimport($1); } elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s+ qw \s* (\() \s* \) \s* ; /oxmsgc) { return e_no_nounimport($1); } elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s+ qw \s* (\{) \s* \} \s* ; /oxmsgc) { return e_no_nounimport($1); } elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s+ qw \s* (\[) \s* \] \s* ; /oxmsgc) { return e_no_nounimport($1); } elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s+ qw \s* (\<) \s* \> \s* ; /oxmsgc) { return e_no_nounimport($1); } elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s+ qw \s* ([\x21-\x3F]) \s* \2 \s* ; /oxmsgc) { return e_no_nounimport($1); } elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s+ qw \s* (\S) \s* \2 \s* ; /oxmsgc) { return e_no_nounimport($1); } # no with unimport no parameter elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s* ; /oxmsgc) { return e_no_noparam($1); } # no with unimport parameters elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s* ( (\() [^\x81-\x9F\xE0-\xFC)]* \)) \s* ; /oxmsgc) { return e_no($1,$2); } elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s* ( (\') [^\x81-\x9F\xE0-\xFC']* \') \s* ; /oxmsgc) { return e_no($1,$2); } elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s* ( (\") [^\x81-\x9F\xE0-\xFC"]* \") \s* ; /oxmsgc) { return e_no($1,$2); } elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s+ ((?:q|qq|qw) \s* (\() [^\x81-\x9F\xE0-\xFC)]* \)) \s* ; /oxmsgc) { return e_no($1,$2); } elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s+ ((?:q|qq|qw) \s* (\{) (?:$q_char)*? \}) \s* ; /oxmsgc) { return e_no($1,$2); } elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s+ ((?:q|qq|qw) \s* (\[) (?:$q_char)*? \]) \s* ; /oxmsgc) { return e_no($1,$2); } elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s+ ((?:q|qq|qw) \s* (\<) [^\x81-\x9F\xE0-\xFC>]* \>) \s* ; /oxmsgc) { return e_no($1,$2); } elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s+ ((?:q|qq|qw) \s* ([\x21-\x3F]) .*? \3) \s* ; /oxmsgc) { return e_no($1,$2); } elsif (/\G \b no \s+ ([A-Z]\w*(?: ::\w+)*) \s+ ((?:q|qq|qw) \s* (\S) (?:$q_char)*? \3) \s* ; /oxmsgc) { return e_no($1,$2); } # use else elsif (/\G \b use \b /oxmsgc) { return "use"; } # use else elsif (/\G \b no \b /oxmsgc) { return "no"; } # '' elsif (/\G (? <= < operator elsif (/\G (<<=|<=>|<=|<) (?= \s* [A-Za-z_0-9'"`\$\@\&\*\(\+\-] )/oxgc) { return $1; } # elsif (/\G (<[\$]?[A-Za-z_][A-Za-z_0-9]*>) /oxgc) { return $1; } # --- glob # avoid "Error: Runtime exception" of perl version 5.005_03 elsif (/\G < ((?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC>\0\a\e\f\n\r\t])+?) > /oxgc) { return 'Esjis::glob("' . $1 . '")'; } # __DATA__ elsif (/\G ^ ( __DATA__ \n .*) \z /oxmsgc) { return $1; } # __END__ elsif (/\G ^ ( __END__ \n .*) \z /oxmsgc) { return $1; } # \cD Control-D # P.68 2.6.8. Other Literal Tokens # in Chapter 2: Bits and Pieces # of ISBN 0-596-00027-8 Programming Perl Third Edition. # P.76 Other Literal Tokens # in Chapter 2: Bits and Pieces # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. elsif (/\G ( \cD .*) \z /oxmsgc) { return $1; } # \cZ Control-Z elsif (/\G ( \cZ .*) \z /oxmsgc) { return $1; } # any operator before div elsif (/\G ( -- | \+\+ | [\)\}\]] ) /oxgc) { $slash = 'div'; return $1; } # any operator before m// # //, //= (defined-or) # P.164 Logical Operators # in Chapter 10: More Control Structures # of ISBN 978-0-596-52010-6 Learning Perl, Fifth Edition # P.119 C-Style Logical (Short-Circuit) Operators # in Chapter 3: Unary and Binary Operators # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. # (and so on) # ~~ # P.221 The Smart Match Operator # in Chapter 15: Smart Matching and given-when # of ISBN 978-0-596-52010-6 Learning Perl, Fifth Edition # P.112 Smartmatch Operator # in Chapter 3: Unary and Binary Operators # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. # (and so on) elsif (/\G ( !~~ | !~ | != | ! | %= | % | &&= | && | &= | & | -= | -> | - | :\s*= | : | <<= | <=> | <= | < | == | => | =~ | = | >>= | >> | >= | > | \*\*= | \*\* | \*= | \* | \+= | \+ | \.\.\. | \.\. | \.= | \. | \/\/= | \/\/ | \/= | \/ | \? | \\ | \^= | \^ | \b x= | \|\|= | \|\| | \|= | \| | ~~ | ~ | \b(?: and | cmp | eq | ge | gt | le | lt | ne | not | or | xor | x )\b | \b(?: print )\b | [,;\(\{\[] ) /oxgc) { $slash = 'm//'; return $1; } # other any character elsif (/\G ($q_char) /oxgc) { $slash = 'div'; return $1; } # system error else { die __FILE__, ": Oops, this shouldn't happen!"; } } # escape ShiftJIS string sub e_string { my($string) = @_; my $e_string = ''; local $slash = 'm//'; # P.1024 Appendix W.10 Multibyte Processing # of ISBN 1-56592-224-7 CJKV Information Processing # (and so on) my @char = $string =~ / \G (\\?(?:$q_char)) /oxmsg; # without { ... } if (not (grep(/\A \{ \z/xms, @char) and grep(/\A \} \z/xms, @char))) { if ($string !~ /< @{[Esjis::PREMATCH()]} elsif ($string =~ /\G ( \$` | \$\{`\} | \$ \s* PREMATCH \b | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) /oxmsgc) { $e_string .= q{Esjis::PREMATCH()}; $slash = 'div'; } # $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> @{[Esjis::MATCH()]} elsif ($string =~ /\G ( \$& | \$\{&\} | \$ \s* MATCH \b | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) /oxmsgc) { $e_string .= q{Esjis::MATCH()}; $slash = 'div'; } # $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> @{[Esjis::POSTMATCH()]} elsif ($string =~ /\G ( \$ \s* POSTMATCH \b | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) /oxmsgc) { $e_string .= q{Esjis::POSTMATCH()}; $slash = 'div'; } # bareword elsif ($string =~ /\G ( \{ \s* (?: tr|index|rindex|reverse) \s* \} ) /oxmsgc) { $e_string .= $1; $slash = 'div'; } # $0 --> $0 elsif ($string =~ /\G ( \$ 0 ) /oxmsgc) { $e_string .= $1; $slash = 'div'; } elsif ($string =~ /\G ( \$ \{ \s* 0 \s* \} ) /oxmsgc) { $e_string .= $1; $slash = 'div'; } # $$ --> $$ elsif ($string =~ /\G ( \$ \$ ) (?![\w\{]) /oxmsgc) { $e_string .= $1; $slash = 'div'; } # $1, $2, $3 --> $2, $3, $4 (only when multibyte anchoring is enable) elsif ($string =~ /\G \$ ([1-9][0-9]*) /oxmsgc) { $e_string .= e_capture($1); $slash = 'div'; } elsif ($string =~ /\G \$ \{ \s* ([1-9][0-9]*) \s* \} /oxmsgc) { $e_string .= e_capture($1); $slash = 'div'; } # $$foo[ ... ] --> $ $foo->[ ... ] elsif ($string =~ /\G \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \[ .+? \] ) /oxmsgc) { $e_string .= e_capture($1.'->'.$2); $slash = 'div'; } # $$foo{ ... } --> $ $foo->{ ... } elsif ($string =~ /\G \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ .+? \} ) /oxmsgc) { $e_string .= e_capture($1.'->'.$2); $slash = 'div'; } # $$foo elsif ($string =~ /\G \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) /oxmsgc) { $e_string .= e_capture($1); $slash = 'div'; } # ${ foo } elsif ($string =~ /\G \$ \s* \{ ( \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* ) \} /oxmsgc) { $e_string .= '${' . $1 . '}'; $slash = 'div'; } # ${ ... } elsif ($string =~ /\G \$ \s* \{ \s* ( $qq_brace ) \s* \} /oxmsgc) { $e_string .= e_capture($1); $slash = 'div'; } # variable or function # $ @ % & * $ # elsif ($string =~ /\G ( (?: [\$\@\%\&\*] | \$\# | -> | \b sub \b) \s* (?: split|chop|index|rindex|lc|uc|fc|chr|ord|reverse|getc|tr|y|q|qq|qx|qw|m|s|qr|glob|lstat|opendir|stat|unlink|chdir) ) \b /oxmsgc) { $e_string .= $1; $slash = 'div'; } # $ $ $ $ $ $ $ $ $ $ $ $ $ $ # $ @ # \ ' " / ? ( ) [ ] < > elsif ($string =~ /\G ( \$[\$\@\#\\\'\"\/\?\(\)\[\]\<\>] ) /oxmsgc) { $e_string .= $1; $slash = 'div'; } # functions of package Esjis elsif ($string =~ /\G \b (CORE:: | ->[ ]* (?: atan2 | [a-z]{2,})) \b /oxgc) { $e_string .= $1; $slash = 'm//'; } elsif ($string =~ /\G \b bytes::substr \b /oxgc) { $e_string .= 'substr'; $slash = 'm//'; } elsif ($string =~ /\G \b chop \b /oxgc) { $e_string .= 'Esjis::chop'; $slash = 'm//'; } elsif ($string =~ /\G \b bytes::index \b /oxgc) { $e_string .= 'index'; $slash = 'm//'; } elsif ($string =~ /\G \b Sjis::index \b /oxgc) { $e_string .= 'Sjis::index'; $slash = 'm//'; } elsif ($string =~ /\G \b index \b /oxgc) { $e_string .= 'Esjis::index'; $slash = 'm//'; } elsif ($string =~ /\G \b bytes::rindex \b /oxgc) { $e_string .= 'rindex'; $slash = 'm//'; } elsif ($string =~ /\G \b Sjis::rindex \b /oxgc) { $e_string .= 'Sjis::rindex'; $slash = 'm//'; } elsif ($string =~ /\G \b rindex \b /oxgc) { $e_string .= 'Esjis::rindex'; $slash = 'm//'; } elsif ($string =~ /\G \b lc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'Esjis::lc'; $slash = 'm//'; } elsif ($string =~ /\G \b lcfirst (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'Esjis::lcfirst'; $slash = 'm//'; } elsif ($string =~ /\G \b uc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'Esjis::uc'; $slash = 'm//'; } elsif ($string =~ /\G \b ucfirst (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'Esjis::ucfirst'; $slash = 'm//'; } elsif ($string =~ /\G \b fc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'Esjis::fc'; $slash = 'm//'; } elsif ($string =~ /\G (-[rwxoRWXOezfdlpSbcugkTB](?:\s+-[rwxoRWXOezfdlpSbcugkTB])+) \s* (\") ((?:$qq_char)+?) (\") /oxgc) { $e_string .= "Esjis::filetest(qw($1)," . e_qq('', $2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) qq \s* (\#) ((?:$qq_char)+?) (\#) /oxgc) { $e_string .= "Esjis::filetest(qw($1)," . e_qq('qq',$2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) qq \s* (\() ((?:$qq_paren)+?) (\)) /oxgc) { $e_string .= "Esjis::filetest(qw($1)," . e_qq('qq',$2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) qq \s* (\{) ((?:$qq_brace)+?) (\}) /oxgc) { $e_string .= "Esjis::filetest(qw($1)," . e_qq('qq',$2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) qq \s* (\[) ((?:$qq_bracket)+?) (\]) /oxgc) { $e_string .= "Esjis::filetest(qw($1)," . e_qq('qq',$2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) qq \s* (\<) ((?:$qq_angle)+?) (\>) /oxgc) { $e_string .= "Esjis::filetest(qw($1)," . e_qq('qq',$2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) qq \s* (\S) ((?:$qq_char)+?) (\3) /oxgc) { $e_string .= "Esjis::filetest(qw($1)," . e_qq('qq',$2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G (-[rwxoRWXOezfdlpSbcugkTB](?:\s+-[rwxoRWXOezfdlpSbcugkTB])+) \s* (\') ((?:\\\1|\\\\|$q_char)+?) (\') /oxgc) { $e_string .= "Esjis::filetest(qw($1)," . e_q ('', $2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) q \s* (\#) ((?:\\\#|\\\\|$q_char)+?) (\#) /oxgc) { $e_string .= "Esjis::filetest(qw($1)," . e_q ('q', $2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) q \s* (\() ((?:\\\)|\\\\|$q_paren)+?) (\)) /oxgc) { $e_string .= "Esjis::filetest(qw($1)," . e_q ('q', $2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) q \s* (\{) ((?:\\\}|\\\\|$q_brace)+?) (\}) /oxgc) { $e_string .= "Esjis::filetest(qw($1)," . e_q ('q', $2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) q \s* (\[) ((?:\\\]|\\\\|$q_bracket)+?) (\]) /oxgc) { $e_string .= "Esjis::filetest(qw($1)," . e_q ('q', $2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) q \s* (\<) ((?:\\\>|\\\\|$q_angle)+?) (\>) /oxgc) { $e_string .= "Esjis::filetest(qw($1)," . e_q ('q', $2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) q \s* (\S) ((?:\\\1|\\\\|$q_char)+?) (\3) /oxgc) { $e_string .= "Esjis::filetest(qw($1)," . e_q ('q', $2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G (-[rwxoRWXOezfdlpSbcugkTB](?:\s+-[rwxoRWXOezfdlpSbcugkTB])+) (\$ \w+(?: ::\w+)* (?: (?: ->)? (?: \( (?:$qq_paren)*? \) | \{ (?:$qq_brace)+? \} | \[ (?:$qq_bracket)+? \] ) )*) /oxgc) { $e_string .= "Esjis::filetest(qw($1),$2)"; $slash = 'm//'; } elsif ($string =~ /\G (-[rwxoRWXOezfdlpSbcugkTB](?:\s+-[rwxoRWXOezfdlpSbcugkTB])+) \( ((?:$qq_paren)*?) \) /oxgc) { $e_string .= "Esjis::filetest(qw($1),$2)"; $slash = 'm//'; } elsif ($string =~ /\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) (?= [a-z]+) /oxgc) { $e_string .= "Esjis::filetest qw($1),"; $slash = 'm//'; } elsif ($string =~ /\G ((?:-[rwxoRWXOezfdlpSbcugkTB]\s+){2,}) (\w+) /oxgc) { $e_string .= "Esjis::filetest(qw($1),$2)"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ \s* (\") ((?:$qq_char)+?) (\") /oxgc) { $e_string .= "Esjis::$1(" . e_qq('', $2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ qq \s* (\#) ((?:$qq_char)+?) (\#) /oxgc) { $e_string .= "Esjis::$1(" . e_qq('qq',$2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ qq \s* (\() ((?:$qq_paren)+?) (\)) /oxgc) { $e_string .= "Esjis::$1(" . e_qq('qq',$2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ qq \s* (\{) ((?:$qq_brace)+?) (\}) /oxgc) { $e_string .= "Esjis::$1(" . e_qq('qq',$2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ qq \s* (\[) ((?:$qq_bracket)+?) (\]) /oxgc) { $e_string .= "Esjis::$1(" . e_qq('qq',$2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ qq \s* (\<) ((?:$qq_angle)+?) (\>) /oxgc) { $e_string .= "Esjis::$1(" . e_qq('qq',$2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ qq \s* (\S) ((?:$qq_char)+?) (\3) /oxgc) { $e_string .= "Esjis::$1(" . e_qq('qq',$2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ \s* (\') ((?:\\\1|\\\\|$q_char)+?) (\') /oxgc) { $e_string .= "Esjis::$1(" . e_q ('', $2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ q \s* (\#) ((?:\\\#|\\\\|$q_char)+?) (\#) /oxgc) { $e_string .= "Esjis::$1(" . e_q ('q', $2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ q \s* (\() ((?:\\\)|\\\\|$q_paren)+?) (\)) /oxgc) { $e_string .= "Esjis::$1(" . e_q ('q', $2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ q \s* (\{) ((?:\\\}|\\\\|$q_brace)+?) (\}) /oxgc) { $e_string .= "Esjis::$1(" . e_q ('q', $2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ q \s* (\[) ((?:\\\]|\\\\|$q_bracket)+?) (\]) /oxgc) { $e_string .= "Esjis::$1(" . e_q ('q', $2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ q \s* (\<) ((?:\\\>|\\\\|$q_angle)+?) (\>) /oxgc) { $e_string .= "Esjis::$1(" . e_q ('q', $2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ q \s* (\S) ((?:\\\1|\\\\|$q_char)+?) (\3) /oxgc) { $e_string .= "Esjis::$1(" . e_q ('q', $2,$4,$3) . ")"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s* (\$ \w+(?: ::\w+)* (?: (?: ->)? (?: \( (?:$qq_paren)*? \) | \{ (?:$qq_brace)+? \} | \[ (?:$qq_bracket)+? \] ) )*) /oxgc) { $e_string .= "Esjis::$1($2)"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s* \( ((?:$qq_paren)*?) \) /oxgc) { $e_string .= "Esjis::$1($2)"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) (?= \s+ [a-z]+) /oxgc) { $e_string .= "Esjis::$1"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \s+ (\w+) /oxgc) { $e_string .= "Esjis::$1(::"."$2)"; $slash = 'm//'; } elsif ($string =~ /\G -(t) \s+ (\w+) /oxgc) { $e_string .= "-t $2"; $slash = 'm//'; } elsif ($string =~ /\G \b lstat (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'Esjis::lstat'; $slash = 'm//'; } elsif ($string =~ /\G \b stat (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'Esjis::stat'; $slash = 'm//'; } # "-s '' ..." means file test "-s 'filename' ..." (not means "- s/// ...") elsif ($string =~ /\G -s \s+ \s* (\") ((?:$qq_char)+?) (\") /oxgc) { $e_string .= '-s ' . e_qq('', $1,$3,$2); $slash = 'm//'; } elsif ($string =~ /\G -s \s+ qq \s* (\#) ((?:$qq_char)+?) (\#) /oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; } elsif ($string =~ /\G -s \s+ qq \s* (\() ((?:$qq_paren)+?) (\)) /oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; } elsif ($string =~ /\G -s \s+ qq \s* (\{) ((?:$qq_brace)+?) (\}) /oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; } elsif ($string =~ /\G -s \s+ qq \s* (\[) ((?:$qq_bracket)+?) (\]) /oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; } elsif ($string =~ /\G -s \s+ qq \s* (\<) ((?:$qq_angle)+?) (\>) /oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; } elsif ($string =~ /\G -s \s+ qq \s* (\S) ((?:$qq_char)+?) (\3) /oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; } elsif ($string =~ /\G -s \s+ \s* (\') ((?:\\\1|\\\\|$q_char)+?) (\') /oxgc) { $e_string .= '-s ' . e_q ('', $1,$3,$2); $slash = 'm//'; } elsif ($string =~ /\G -s \s+ q \s* (\#) ((?:\\\#|\\\\|$q_char)+?) (\#) /oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; } elsif ($string =~ /\G -s \s+ q \s* (\() ((?:\\\)|\\\\|$q_paren)+?) (\)) /oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; } elsif ($string =~ /\G -s \s+ q \s* (\{) ((?:\\\}|\\\\|$q_brace)+?) (\}) /oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; } elsif ($string =~ /\G -s \s+ q \s* (\[) ((?:\\\]|\\\\|$q_bracket)+?) (\]) /oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; } elsif ($string =~ /\G -s \s+ q \s* (\<) ((?:\\\>|\\\\|$q_angle)+?) (\>) /oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; } elsif ($string =~ /\G -s \s+ q \s* (\S) ((?:\\\1|\\\\|$q_char)+?) (\3) /oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; } elsif ($string =~ /\G -s \s* (\$ \w+(?: ::\w+)* (?: (?: ->)? (?: \( (?:$qq_paren)*? \) | \{ (?:$qq_brace)+? \} | \[ (?:$qq_bracket)+? \] ) )*) /oxgc) { $e_string .= "-s $1"; $slash = 'm//'; } elsif ($string =~ /\G -s \s* \( ((?:$qq_paren)*?) \) /oxgc) { $e_string .= "-s ($1)"; $slash = 'm//'; } elsif ($string =~ /\G -s (?= \s+ [a-z]+) /oxgc) { $e_string .= '-s'; $slash = 'm//'; } elsif ($string =~ /\G -s \s+ (\w+) /oxgc) { $e_string .= "-s $1"; $slash = 'm//'; } elsif ($string =~ /\G \b bytes::length (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'length'; $slash = 'm//'; } elsif ($string =~ /\G \b bytes::chr (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'chr'; $slash = 'm//'; } elsif ($string =~ /\G \b chr (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'Esjis::chr'; $slash = 'm//'; } elsif ($string =~ /\G \b bytes::ord (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'ord'; $slash = 'div'; } elsif ($string =~ /\G \b ord (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= $function_ord; $slash = 'div'; } elsif ($string =~ /\G \b glob (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'Esjis::glob'; $slash = 'm//'; } elsif ($string =~ /\G \b lc \b /oxgc) { $e_string .= 'Esjis::lc_'; $slash = 'm//'; } elsif ($string =~ /\G \b lcfirst \b /oxgc) { $e_string .= 'Esjis::lcfirst_'; $slash = 'm//'; } elsif ($string =~ /\G \b uc \b /oxgc) { $e_string .= 'Esjis::uc_'; $slash = 'm//'; } elsif ($string =~ /\G \b ucfirst \b /oxgc) { $e_string .= 'Esjis::ucfirst_'; $slash = 'm//'; } elsif ($string =~ /\G \b fc \b /oxgc) { $e_string .= 'Esjis::fc_'; $slash = 'm//'; } elsif ($string =~ /\G (-[rwxoRWXOezfdlpSbcugkTB](?:\s+-[rwxoRWXOezfdlpSbcugkTB])+) \b /oxgc) { $e_string .= "Esjis::filetest_(qw($1))"; $slash = 'm//'; } elsif ($string =~ /\G -([rwxoRWXOezsfdlpSbcugkTBMAC]) \b /oxgc) { $e_string .= "Esjis::${1}_"; $slash = 'm//'; } elsif ($string =~ /\G \b lstat \b /oxgc) { $e_string .= 'Esjis::lstat_'; $slash = 'm//'; } elsif ($string =~ /\G \b stat \b /oxgc) { $e_string .= 'Esjis::stat_'; $slash = 'm//'; } elsif ($string =~ /\G -s \b /oxgc) { $e_string .= '-s '; $slash = 'm//'; } elsif ($string =~ /\G \b bytes::length \b /oxgc) { $e_string .= 'length'; $slash = 'm//'; } elsif ($string =~ /\G \b bytes::chr \b /oxgc) { $e_string .= 'chr'; $slash = 'm//'; } elsif ($string =~ /\G \b chr \b /oxgc) { $e_string .= 'Esjis::chr_'; $slash = 'm//'; } elsif ($string =~ /\G \b bytes::ord \b /oxgc) { $e_string .= 'ord'; $slash = 'div'; } elsif ($string =~ /\G \b ord \b /oxgc) { $e_string .= $function_ord_; $slash = 'div'; } elsif ($string =~ /\G \b glob \b /oxgc) { $e_string .= 'Esjis::glob_'; $slash = 'm//'; } elsif ($string =~ /\G \b reverse \b /oxgc) { $e_string .= $function_reverse; $slash = 'm//'; } elsif ($string =~ /\G \b getc \b /oxgc) { $e_string .= $function_getc; $slash = 'm//'; } elsif ($string =~ /\G \b opendir (\s* \( \s*) (?=[A-Za-z_]) /oxgc) { $e_string .= "Esjis::opendir$1*"; $slash = 'm//'; } elsif ($string =~ /\G \b opendir (\s+) (?=[A-Za-z_]) /oxgc) { $e_string .= "Esjis::opendir$1*"; $slash = 'm//'; } elsif ($string =~ /\G \b unlink \b /oxgc) { $e_string .= 'Esjis::unlink'; $slash = 'm//'; } # chdir elsif ($string =~ /\G \b (chdir) \b (?! \s* => ) /oxgc) { $slash = 'm//'; $e_string .= 'Esjis::chdir'; while ($string =~ /\G ( \s+ | \( | \#.* ) /oxgc) { $e_string .= $1; } # end of chdir if ($string =~ /\G (?= [,;\)\}\]] ) /oxgc) { return $e_string; } # chdir scalar value elsif ($string =~ /\G ( [\$\@\&\*] $qq_scalar ) /oxgc) { $e_string .= e_string($1); next E_STRING_LOOP; } # chdir qq// elsif ($string =~ /\G \b (qq) \b /oxgc) { if ($string =~ /\G (\#) ((?:$qq_char)*?) (\#) /oxgc) { $e_string .= e_chdir('qq',$1,$3,$2); next E_STRING_LOOP; } # qq# # --> qr # # else { while ($string !~ /\G \z/oxgc) { if ($string =~ /\G (\s+|\#.*) /oxgc) { $e_string .= $1; } elsif ($string =~ /\G (\() ((?:$qq_paren)*?) (\)) /oxgc) { $e_string .= e_chdir('qq',$1,$3,$2); next E_STRING_LOOP; } # qq ( ) --> qr ( ) elsif ($string =~ /\G (\{) ((?:$qq_brace)*?) (\}) /oxgc) { $e_string .= e_chdir('qq',$1,$3,$2); next E_STRING_LOOP; } # qq { } --> qr { } elsif ($string =~ /\G (\[) ((?:$qq_bracket)*?) (\]) /oxgc) { $e_string .= e_chdir('qq',$1,$3,$2); next E_STRING_LOOP; } # qq [ ] --> qr [ ] elsif ($string =~ /\G (\<) ((?:$qq_angle)*?) (\>) /oxgc) { $e_string .= e_chdir('qq',$1,$3,$2); next E_STRING_LOOP; } # qq < > --> qr < > elsif ($string =~ /\G ([*\-:?\\^|]) ((?:$qq_char)*?) (\1) /oxgc) { $e_string .= e_chdir('qq','{','}',$2); next E_STRING_LOOP; } # qq | | --> qr { } elsif ($string =~ /\G (\S) ((?:$qq_char)*?) (\1) /oxgc) { $e_string .= e_chdir('qq',$1,$3,$2); next E_STRING_LOOP; } # qq * * --> qr * * } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # chdir q// elsif ($string =~ /\G \b (q) \b /oxgc) { if ($string =~ /\G (\#) ((?:\\\#|\\\\|$q_char)*?) (\#) /oxgc) { $e_string .= e_chdir_q('q',$1,$3,$2); next E_STRING_LOOP; } # q# # --> qr # # else { while ($string !~ /\G \z/oxgc) { if ($string =~ /\G (\s+|\#.*) /oxgc) { $e_string .= $1; } elsif ($string =~ /\G (\() ((?:\\\\|\\\)|\\\(|$q_paren)*?) (\)) /oxgc) { $e_string .= e_chdir_q('q',$1,$3,$2); next E_STRING_LOOP; } # q ( ) --> qr ( ) elsif ($string =~ /\G (\{) ((?:\\\\|\\\}|\\\{|$q_brace)*?) (\}) /oxgc) { $e_string .= e_chdir_q('q',$1,$3,$2); next E_STRING_LOOP; } # q { } --> qr { } elsif ($string =~ /\G (\[) ((?:\\\\|\\\]|\\\[|$q_bracket)*?) (\]) /oxgc) { $e_string .= e_chdir_q('q',$1,$3,$2); next E_STRING_LOOP; } # q [ ] --> qr [ ] elsif ($string =~ /\G (\<) ((?:\\\\|\\\>|\\\<|$q_angle)*?) (\>) /oxgc) { $e_string .= e_chdir_q('q',$1,$3,$2); next E_STRING_LOOP; } # q < > --> qr < > elsif ($string =~ /\G ([*\-:?\\^|]) ((?:$q_char)*?) (\1) /oxgc) { $e_string .= e_chdir_q('q','{','}',$2); next E_STRING_LOOP; } # q | | --> qr { } elsif ($string =~ /\G (\S) ((?:\\\\|\\\1| $q_char)*?) (\1) /oxgc) { $e_string .= e_chdir_q('q',$1,$3,$2); next E_STRING_LOOP; } # q * * --> qr * * } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # chdir '' elsif ($string =~ /\G (\') /oxgc) { my $q_string = ''; while ($string !~ /\G \z/oxgc) { if ($string =~ /\G (\\\\) /oxgc) { $q_string .= $1; } elsif ($string =~ /\G (\\\') /oxgc) { $q_string .= $1; } elsif ($string =~ /\G \' /oxgc) { $e_string .= e_chdir_q('',"'","'",$q_string); next E_STRING_LOOP; } elsif ($string =~ /\G ($q_char) /oxgc) { $q_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } # chdir "" elsif ($string =~ /\G (\") /oxgc) { my $qq_string = ''; while ($string !~ /\G \z/oxgc) { if ($string =~ /\G (\\\\) /oxgc) { $qq_string .= $1; } elsif ($string =~ /\G (\\\") /oxgc) { $qq_string .= $1; } elsif ($string =~ /\G \" /oxgc) { $e_string .= e_chdir('','"','"',$qq_string); next E_STRING_LOOP; } elsif ($string =~ /\G ($q_char) /oxgc) { $qq_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # split elsif ($string =~ /\G \b (split) \b (?! \s* => ) /oxgc) { $slash = 'm//'; my $e = ''; while ($string =~ /\G ( \s+ | \( | \#.* ) /oxgc) { $e .= $1; } # end of split if ($string =~ /\G (?= [,;\)\}\]] ) /oxgc) { return 'Esjis::split' . $e; } # split scalar value elsif ($string =~ /\G ( [\$\@\&\*] $qq_scalar ) /oxgc) { $e_string .= 'Esjis::split' . $e . e_string($1); next E_STRING_LOOP; } # split literal space elsif ($string =~ /\G \b qq (\#) [ ] (\#) /oxgc) { $e_string .= 'Esjis::split' . $e . qq {qq$1 $2}; next E_STRING_LOOP; } elsif ($string =~ /\G \b qq (\s*) (\() [ ] (\)) /oxgc) { $e_string .= 'Esjis::split' . $e . qq{$1qq$2 $3}; next E_STRING_LOOP; } elsif ($string =~ /\G \b qq (\s*) (\{) [ ] (\}) /oxgc) { $e_string .= 'Esjis::split' . $e . qq{$1qq$2 $3}; next E_STRING_LOOP; } elsif ($string =~ /\G \b qq (\s*) (\[) [ ] (\]) /oxgc) { $e_string .= 'Esjis::split' . $e . qq{$1qq$2 $3}; next E_STRING_LOOP; } elsif ($string =~ /\G \b qq (\s*) (\<) [ ] (\>) /oxgc) { $e_string .= 'Esjis::split' . $e . qq{$1qq$2 $3}; next E_STRING_LOOP; } elsif ($string =~ /\G \b qq (\s*) (\S) [ ] (\2) /oxgc) { $e_string .= 'Esjis::split' . $e . qq{$1qq$2 $3}; next E_STRING_LOOP; } elsif ($string =~ /\G \b q (\#) [ ] (\#) /oxgc) { $e_string .= 'Esjis::split' . $e . qq {q$1 $2}; next E_STRING_LOOP; } elsif ($string =~ /\G \b q (\s*) (\() [ ] (\)) /oxgc) { $e_string .= 'Esjis::split' . $e . qq {$1q$2 $3}; next E_STRING_LOOP; } elsif ($string =~ /\G \b q (\s*) (\{) [ ] (\}) /oxgc) { $e_string .= 'Esjis::split' . $e . qq {$1q$2 $3}; next E_STRING_LOOP; } elsif ($string =~ /\G \b q (\s*) (\[) [ ] (\]) /oxgc) { $e_string .= 'Esjis::split' . $e . qq {$1q$2 $3}; next E_STRING_LOOP; } elsif ($string =~ /\G \b q (\s*) (\<) [ ] (\>) /oxgc) { $e_string .= 'Esjis::split' . $e . qq {$1q$2 $3}; next E_STRING_LOOP; } elsif ($string =~ /\G \b q (\s*) (\S) [ ] (\2) /oxgc) { $e_string .= 'Esjis::split' . $e . qq {$1q$2 $3}; next E_STRING_LOOP; } elsif ($string =~ /\G ' [ ] ' /oxgc) { $e_string .= 'Esjis::split' . $e . qq {' '}; next E_STRING_LOOP; } elsif ($string =~ /\G " [ ] " /oxgc) { $e_string .= 'Esjis::split' . $e . qq {" "}; next E_STRING_LOOP; } # split qq// elsif ($string =~ /\G \b (qq) \b /oxgc) { if ($string =~ /\G (\#) ((?:$qq_char)*?) (\#) /oxgc) { $e_string .= e_split($e.'qr',$1,$3,$2,''); next E_STRING_LOOP; } # qq# # --> qr # # else { while ($string !~ /\G \z/oxgc) { if ($string =~ /\G (\s+|\#.*) /oxgc) { $e_string .= $e . $1; } elsif ($string =~ /\G (\() ((?:$qq_paren)*?) (\)) /oxgc) { $e_string .= e_split($e.'qr',$1,$3,$2,''); next E_STRING_LOOP; } # qq ( ) --> qr ( ) elsif ($string =~ /\G (\{) ((?:$qq_brace)*?) (\}) /oxgc) { $e_string .= e_split($e.'qr',$1,$3,$2,''); next E_STRING_LOOP; } # qq { } --> qr { } elsif ($string =~ /\G (\[) ((?:$qq_bracket)*?) (\]) /oxgc) { $e_string .= e_split($e.'qr',$1,$3,$2,''); next E_STRING_LOOP; } # qq [ ] --> qr [ ] elsif ($string =~ /\G (\<) ((?:$qq_angle)*?) (\>) /oxgc) { $e_string .= e_split($e.'qr',$1,$3,$2,''); next E_STRING_LOOP; } # qq < > --> qr < > elsif ($string =~ /\G ([*\-:?\\^|]) ((?:$qq_char)*?) (\1) /oxgc) { $e_string .= e_split($e.'qr','{','}',$2,''); next E_STRING_LOOP; } # qq | | --> qr { } elsif ($string =~ /\G (\S) ((?:$qq_char)*?) (\1) /oxgc) { $e_string .= e_split($e.'qr',$1,$3,$2,''); next E_STRING_LOOP; } # qq * * --> qr * * } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # split qr// elsif ($string =~ /\G \b (qr) \b /oxgc) { if ($string =~ /\G (\#) ((?:$qq_char)*?) (\#) ([imosxpadlubB]*) /oxgc) { $e_string .= e_split ($e.'qr',$1,$3,$2,$4); next E_STRING_LOOP; } # qr# # else { while ($string !~ /\G \z/oxgc) { if ($string =~ /\G (\s+|\#.*) /oxgc) { $e_string .= $e . $1; } elsif ($string =~ /\G (\() ((?:$qq_paren)*?) (\)) ([imosxpadlubB]*) /oxgc) { $e_string .= e_split ($e.'qr',$1, $3, $2,$4); next E_STRING_LOOP; } # qr ( ) elsif ($string =~ /\G (\{) ((?:$qq_brace)*?) (\}) ([imosxpadlubB]*) /oxgc) { $e_string .= e_split ($e.'qr',$1, $3, $2,$4); next E_STRING_LOOP; } # qr { } elsif ($string =~ /\G (\[) ((?:$qq_bracket)*?) (\]) ([imosxpadlubB]*) /oxgc) { $e_string .= e_split ($e.'qr',$1, $3, $2,$4); next E_STRING_LOOP; } # qr [ ] elsif ($string =~ /\G (\<) ((?:$qq_angle)*?) (\>) ([imosxpadlubB]*) /oxgc) { $e_string .= e_split ($e.'qr',$1, $3, $2,$4); next E_STRING_LOOP; } # qr < > elsif ($string =~ /\G (\') ((?:$qq_char)*?) (\') ([imosxpadlubB]*) /oxgc) { $e_string .= e_split_q($e.'qr',$1, $3, $2,$4); next E_STRING_LOOP; } # qr ' ' elsif ($string =~ /\G ([*\-:?\\^|]) ((?:$qq_char)*?) (\1) ([imosxpadlubB]*) /oxgc) { $e_string .= e_split ($e.'qr','{','}',$2,$4); next E_STRING_LOOP; } # qr | | --> qr { } elsif ($string =~ /\G (\S) ((?:$qq_char)*?) (\1) ([imosxpadlubB]*) /oxgc) { $e_string .= e_split ($e.'qr',$1, $3, $2,$4); next E_STRING_LOOP; } # qr * * } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # split q// elsif ($string =~ /\G \b (q) \b /oxgc) { if ($string =~ /\G (\#) ((?:\\\#|\\\\|$q_char)*?) (\#) /oxgc) { $e_string .= e_split_q($e.'qr',$1,$3,$2,''); next E_STRING_LOOP; } # q# # --> qr # # else { while ($string !~ /\G \z/oxgc) { if ($string =~ /\G (\s+|\#.*) /oxgc) { $e_string .= $e . $1; } elsif ($string =~ /\G (\() ((?:\\\\|\\\)|\\\(|$q_paren)*?) (\)) /oxgc) { $e_string .= e_split_q($e.'qr',$1,$3,$2,''); next E_STRING_LOOP; } # q ( ) --> qr ( ) elsif ($string =~ /\G (\{) ((?:\\\\|\\\}|\\\{|$q_brace)*?) (\}) /oxgc) { $e_string .= e_split_q($e.'qr',$1,$3,$2,''); next E_STRING_LOOP; } # q { } --> qr { } elsif ($string =~ /\G (\[) ((?:\\\\|\\\]|\\\[|$q_bracket)*?) (\]) /oxgc) { $e_string .= e_split_q($e.'qr',$1,$3,$2,''); next E_STRING_LOOP; } # q [ ] --> qr [ ] elsif ($string =~ /\G (\<) ((?:\\\\|\\\>|\\\<|$q_angle)*?) (\>) /oxgc) { $e_string .= e_split_q($e.'qr',$1,$3,$2,''); next E_STRING_LOOP; } # q < > --> qr < > elsif ($string =~ /\G ([*\-:?\\^|]) ((?:$q_char)*?) (\1) /oxgc) { $e_string .= e_split_q($e.'qr','{','}',$2,''); next E_STRING_LOOP; } # q | | --> qr { } elsif ($string =~ /\G (\S) ((?:\\\\|\\\1| $q_char)*?) (\1) /oxgc) { $e_string .= e_split_q($e.'qr',$1,$3,$2,''); next E_STRING_LOOP; } # q * * --> qr * * } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # split m// elsif ($string =~ /\G \b (m) \b /oxgc) { if ($string =~ /\G (\#) ((?:$qq_char)*?) (\#) ([cgimosxpadlubB]*) /oxgc) { $e_string .= e_split ($e.'qr',$1,$3,$2,$4); next E_STRING_LOOP; } # m# # --> qr # # else { while ($string !~ /\G \z/oxgc) { if ($string =~ /\G (\s+|\#.*) /oxgc) { $e_string .= $e . $1; } elsif ($string =~ /\G (\() ((?:$qq_paren)*?) (\)) ([cgimosxpadlubB]*) /oxgc) { $e_string .= e_split ($e.'qr',$1, $3, $2,$4); next E_STRING_LOOP; } # m ( ) --> qr ( ) elsif ($string =~ /\G (\{) ((?:$qq_brace)*?) (\}) ([cgimosxpadlubB]*) /oxgc) { $e_string .= e_split ($e.'qr',$1, $3, $2,$4); next E_STRING_LOOP; } # m { } --> qr { } elsif ($string =~ /\G (\[) ((?:$qq_bracket)*?) (\]) ([cgimosxpadlubB]*) /oxgc) { $e_string .= e_split ($e.'qr',$1, $3, $2,$4); next E_STRING_LOOP; } # m [ ] --> qr [ ] elsif ($string =~ /\G (\<) ((?:$qq_angle)*?) (\>) ([cgimosxpadlubB]*) /oxgc) { $e_string .= e_split ($e.'qr',$1, $3, $2,$4); next E_STRING_LOOP; } # m < > --> qr < > elsif ($string =~ /\G (\') ((?:$qq_char)*?) (\') ([cgimosxpadlubB]*) /oxgc) { $e_string .= e_split_q($e.'qr',$1, $3, $2,$4); next E_STRING_LOOP; } # m ' ' --> qr ' ' elsif ($string =~ /\G ([*\-:?\\^|]) ((?:$qq_char)*?) (\1) ([cgimosxpadlubB]*) /oxgc) { $e_string .= e_split ($e.'qr','{','}',$2,$4); next E_STRING_LOOP; } # m | | --> qr { } elsif ($string =~ /\G (\S) ((?:$qq_char)*?) (\1) ([cgimosxpadlubB]*) /oxgc) { $e_string .= e_split ($e.'qr',$1, $3, $2,$4); next E_STRING_LOOP; } # m * * --> qr * * } die __FILE__, ": Search pattern not terminated"; } } # split '' elsif ($string =~ /\G (\') /oxgc) { my $q_string = ''; while ($string !~ /\G \z/oxgc) { if ($string =~ /\G (\\\\) /oxgc) { $q_string .= $1; } elsif ($string =~ /\G (\\\') /oxgc) { $q_string .= $1; } # splitqr'' --> split qr'' elsif ($string =~ /\G \' /oxgc) { $e_string .= e_split_q($e.q{ qr},"'","'",$q_string,''); next E_STRING_LOOP; } # ' ' --> qr ' ' elsif ($string =~ /\G ($q_char) /oxgc) { $q_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } # split "" elsif ($string =~ /\G (\") /oxgc) { my $qq_string = ''; while ($string !~ /\G \z/oxgc) { if ($string =~ /\G (\\\\) /oxgc) { $qq_string .= $1; } elsif ($string =~ /\G (\\\") /oxgc) { $qq_string .= $1; } # splitqr"" --> split qr"" elsif ($string =~ /\G \" /oxgc) { $e_string .= e_split($e.q{ qr},'"','"',$qq_string,''); next E_STRING_LOOP; } # " " --> qr " " elsif ($string =~ /\G ($q_char) /oxgc) { $qq_string .= $1; } } die __FILE__, ": Can't find string terminator anywhere before EOF"; } # split // elsif ($string =~ /\G (\/) /oxgc) { my $regexp = ''; while ($string !~ /\G \z/oxgc) { if ($string =~ /\G (\\\\) /oxgc) { $regexp .= $1; } elsif ($string =~ /\G (\\\/) /oxgc) { $regexp .= $1; } # splitqr// --> split qr// elsif ($string =~ /\G \/ ([cgimosxpadlubB]*) /oxgc) { $e_string .= e_split($e.q{ qr}, '/','/',$regexp,$1); next E_STRING_LOOP; } # / / --> qr / / elsif ($string =~ /\G ($q_char) /oxgc) { $regexp .= $1; } } die __FILE__, ": Search pattern not terminated"; } } # qq// elsif ($string =~ /\G \b (qq) \b /oxgc) { my $ope = $1; if ($string =~ /\G (\#) ((?:$qq_char)*?) (\#) /oxgc) { # qq# # $e_string .= e_qq($ope,$1,$3,$2); } else { my $e = ''; while ($string !~ /\G \z/oxgc) { if ($string =~ /\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif ($string =~ /\G (\() ((?:$qq_paren)*?) (\)) /oxgc) { $e_string .= $e . e_qq($ope,$1,$3,$2); next E_STRING_LOOP; } # qq ( ) elsif ($string =~ /\G (\{) ((?:$qq_brace)*?) (\}) /oxgc) { $e_string .= $e . e_qq($ope,$1,$3,$2); next E_STRING_LOOP; } # qq { } elsif ($string =~ /\G (\[) ((?:$qq_bracket)*?) (\]) /oxgc) { $e_string .= $e . e_qq($ope,$1,$3,$2); next E_STRING_LOOP; } # qq [ ] elsif ($string =~ /\G (\<) ((?:$qq_angle)*?) (\>) /oxgc) { $e_string .= $e . e_qq($ope,$1,$3,$2); next E_STRING_LOOP; } # qq < > elsif ($string =~ /\G (\S) ((?:$qq_char)*?) (\1) /oxgc) { $e_string .= $e . e_qq($ope,$1,$3,$2); next E_STRING_LOOP; } # qq * * } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # qx// elsif ($string =~ /\G \b (qx) \b /oxgc) { my $ope = $1; if ($string =~ /\G (\#) ((?:$qq_char)*?) (\#) /oxgc) { # qx# # $e_string .= e_qq($ope,$1,$3,$2); } else { my $e = ''; while ($string !~ /\G \z/oxgc) { if ($string =~ /\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif ($string =~ /\G (\() ((?:$qq_paren)*?) (\)) /oxgc) { $e_string .= $e . e_qq($ope,$1,$3,$2); next E_STRING_LOOP; } # qx ( ) elsif ($string =~ /\G (\{) ((?:$qq_brace)*?) (\}) /oxgc) { $e_string .= $e . e_qq($ope,$1,$3,$2); next E_STRING_LOOP; } # qx { } elsif ($string =~ /\G (\[) ((?:$qq_bracket)*?) (\]) /oxgc) { $e_string .= $e . e_qq($ope,$1,$3,$2); next E_STRING_LOOP; } # qx [ ] elsif ($string =~ /\G (\<) ((?:$qq_angle)*?) (\>) /oxgc) { $e_string .= $e . e_qq($ope,$1,$3,$2); next E_STRING_LOOP; } # qx < > elsif ($string =~ /\G (\') ((?:$qq_char)*?) (\') /oxgc) { $e_string .= $e . e_q ($ope,$1,$3,$2); next E_STRING_LOOP; } # qx ' ' elsif ($string =~ /\G (\S) ((?:$qq_char)*?) (\1) /oxgc) { $e_string .= $e . e_qq($ope,$1,$3,$2); next E_STRING_LOOP; } # qx * * } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # q// elsif ($string =~ /\G \b (q) \b /oxgc) { my $ope = $1; if ($string =~ /\G (\#) ((?:\\\#|\\\\|$q_char)*?) (\#) /oxgc) { # q# # $e_string .= e_q($ope,$1,$3,$2); } else { my $e = ''; while ($string !~ /\G \z/oxgc) { if ($string =~ /\G (\s+|\#.*) /oxgc) { $e .= $1; } elsif ($string =~ /\G (\() ((?:\\\\|\\\)|\\\(|$q_paren)*?) (\)) /oxgc) { $e_string .= $e . e_q($ope,$1,$3,$2); next E_STRING_LOOP; } # q ( ) elsif ($string =~ /\G (\{) ((?:\\\\|\\\}|\\\{|$q_brace)*?) (\}) /oxgc) { $e_string .= $e . e_q($ope,$1,$3,$2); next E_STRING_LOOP; } # q { } elsif ($string =~ /\G (\[) ((?:\\\\|\\\]|\\\[|$q_bracket)*?) (\]) /oxgc) { $e_string .= $e . e_q($ope,$1,$3,$2); next E_STRING_LOOP; } # q [ ] elsif ($string =~ /\G (\<) ((?:\\\\|\\\>|\\\<|$q_angle)*?) (\>) /oxgc) { $e_string .= $e . e_q($ope,$1,$3,$2); next E_STRING_LOOP; } # q < > elsif ($string =~ /\G (\S) ((?:\\\\|\\\1| $q_char)*?) (\1) /oxgc) { $e_string .= $e . e_q($ope,$1,$3,$2); next E_STRING_LOOP; } # q * * } die __FILE__, ": Can't find string terminator anywhere before EOF"; } } # '' elsif ($string =~ /\G (? <= < operator elsif ($string =~ /\G (<<=|<=>|<=|<) (?= \s* [A-Za-z_0-9'"`\$\@\&\*\(\+\-] )/oxgc) { $e_string .= $1; } # elsif ($string =~ /\G (<[\$]?[A-Za-z_][A-Za-z_0-9]*>) /oxgc) { $e_string .= $1; } # --- glob elsif ($string =~ /\G < ((?:$q_char)+?) > /oxgc) { $e_string .= 'Esjis::glob("' . $1 . '")'; } # << (bit shift) --- not here document elsif ($string =~ /\G ( << \s* ) (?= [0-9\$\@\&] ) /oxgc) { $slash = 'm//'; $e_string .= $1; } # <<'HEREDOC' elsif ($string =~ /\G ( << '([a-zA-Z_0-9]*)' ) /oxgc) { $slash = 'm//'; my $here_quote = $1; my $delimiter = $2; # get here document if ($here_script eq '') { $here_script = CORE::substr $_, pos $_; $here_script =~ s/.*?\n//oxm; } if ($here_script =~ s/\A (.*?) \n $delimiter \n //xms) { push @heredoc, $1 . qq{\n$delimiter\n}; push @heredoc_delimiter, $delimiter; } else { die __FILE__, ": Can't find string terminator $delimiter anywhere before EOF"; } $e_string .= $here_quote; } # <<\HEREDOC elsif ($string =~ /\G ( << \\([a-zA-Z_0-9]+) ) /oxgc) { $slash = 'm//'; my $here_quote = $1; my $delimiter = $2; # get here document if ($here_script eq '') { $here_script = CORE::substr $_, pos $_; $here_script =~ s/.*?\n//oxm; } if ($here_script =~ s/\A (.*?) \n $delimiter \n //xms) { push @heredoc, $1 . qq{\n$delimiter\n}; push @heredoc_delimiter, $delimiter; } else { die __FILE__, ": Can't find string terminator $delimiter anywhere before EOF"; } $e_string .= $here_quote; } # <<"HEREDOC" elsif ($string =~ /\G ( << "([a-zA-Z_0-9]*)" ) /oxgc) { $slash = 'm//'; my $here_quote = $1; my $delimiter = $2; # get here document if ($here_script eq '') { $here_script = CORE::substr $_, pos $_; $here_script =~ s/.*?\n//oxm; } if ($here_script =~ s/\A (.*?) \n $delimiter \n //xms) { push @heredoc, e_heredoc($1) . qq{\n$delimiter\n}; push @heredoc_delimiter, $delimiter; } else { die __FILE__, ": Can't find string terminator $delimiter anywhere before EOF"; } $e_string .= $here_quote; } # < | - | :\s*= | : | <<= | <=> | <= | < | == | => | =~ | = | >>= | >> | >= | > | \*\*= | \*\* | \*= | \* | \+= | \+ | \.\.\. | \.\. | \.= | \. | \/\/= | \/\/ | \/= | \/ | \? | \\ | \^= | \^ | \b x= | \|\|= | \|\| | \|= | \| | ~~ | ~ | \b(?: and | cmp | eq | ge | gt | le | lt | ne | not | or | xor | x )\b | \b(?: print )\b | [,;\(\{\[] ) /oxgc) { $slash = 'm//'; $e_string .= $1; } # other any character elsif ($string =~ /\G ($q_char) /oxgc) { $e_string .= $1; } # system error else { die __FILE__, ": Oops, this shouldn't happen!"; } } return $e_string; } # # character class # sub character_class { my($char,$modifier) = @_; if ($char eq '.') { if ($modifier =~ /s/) { return '${Esjis::dot_s}'; } else { return '${Esjis::dot}'; } } else { return Esjis::classic_character_class($char); } } # # escape capture ($1, $2, $3, ...) # sub e_capture { return join '', '${Esjis::capture(', $_[0], ')}'; return join '', '$', $_[0]; } # # escape transliteration (tr/// or y///) # sub e_tr { my($variable,$charclass,$e,$charclass2,$modifier) = @_; my $e_tr = ''; $modifier ||= ''; $slash = 'div'; # quote character class 1 $charclass = q_tr($charclass); # quote character class 2 $charclass2 = q_tr($charclass2); # /b /B modifier if ($modifier =~ tr/bB//d) { if ($variable eq '') { $e_tr = qq{tr$charclass$e$charclass2$modifier}; } else { $e_tr = qq{$variable${bind_operator}tr$charclass$e$charclass2$modifier}; } } else { if ($variable eq '') { $e_tr = qq{Esjis::tr(\$_,' =~ ',$charclass,$e$charclass2,'$modifier')}; } else { $e_tr = qq{Esjis::tr($variable,'$bind_operator',$charclass,$e$charclass2,'$modifier')}; } } # clear tr/// variable $tr_variable = ''; $bind_operator = ''; return $e_tr; } # # quote for escape transliteration (tr/// or y///) # sub q_tr { my($charclass) = @_; # quote character class if ($charclass !~ /'/oxms) { return e_q('', "'", "'", $charclass); # --> q' ' } elsif ($charclass !~ /\//oxms) { return e_q('q', '/', '/', $charclass); # --> q/ / } elsif ($charclass !~ /\#/oxms) { return e_q('q', '#', '#', $charclass); # --> q# # } elsif ($charclass !~ /[\<\>]/oxms) { return e_q('q', '<', '>', $charclass); # --> q< > } elsif ($charclass !~ /[\(\)]/oxms) { return e_q('q', '(', ')', $charclass); # --> q( ) } elsif ($charclass !~ /[\{\}]/oxms) { return e_q('q', '{', '}', $charclass); # --> q{ } } else { for my $char (qw( ! " $ % & * + . : = ? @ ^ ` | ~ ), "\x00".."\x1F", "\x7F", "\xFF") { if ($charclass !~ /\Q$char\E/xms) { return e_q('q', $char, $char, $charclass); } } } return e_q('q', '{', '}', $charclass); } # # escape q string (q//, '') # sub e_q { my($ope,$delimiter,$end_delimiter,$string) = @_; $slash = 'div'; my @char = $string =~ / \G ($q_char) /oxmsg; for (my $i=0; $i <= $#char; $i++) { # escape last octet of multiple-octet if ($char[$i] =~ /\A ([\x80-\xFF].*) (\Q$delimiter\E|\Q$end_delimiter\E) \z/xms) { $char[$i] = $1 . '\\' . $2; } elsif (($char[$i] =~ /\A ([\x80-\xFF].*) (\\) \z/xms) and defined($char[$i+1]) and ($char[$i+1] eq '\\')) { $char[$i] = $1 . '\\' . $2; } } if (defined($char[-1]) and ($char[-1] =~ /\A ([\x80-\xFF].*) (\\) \z/xms)) { $char[-1] = $1 . '\\' . $2; } return join '', $ope, $delimiter, @char, $end_delimiter; return join '', $ope, $delimiter, $string, $end_delimiter; } # # escape qq string (qq//, "", qx//, ``) # sub e_qq { my($ope,$delimiter,$end_delimiter,$string) = @_; $slash = 'div'; my $left_e = 0; my $right_e = 0; my @char = $string =~ /\G( \\o\{ [0-7]+ \} | \\x\{ [0-9A-Fa-f]+ \} | \\N\{ [^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]* \} | \$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} | \$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} | \$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} | \$ \s* \d+ | \$ \s* \{ \s* \d+ \s* \} | \$ \$ (?![\w\{]) | \$ \s* \$ \s* $qq_variable | \\?(?:$q_char) )/oxmsg; for (my $i=0; $i <= $#char; $i++) { # "\L\u" --> "\u\L" if (($char[$i] eq '\L') and ($char[$i+1] eq '\u')) { @char[$i,$i+1] = @char[$i+1,$i]; } # "\U\l" --> "\l\U" elsif (($char[$i] eq '\U') and ($char[$i+1] eq '\l')) { @char[$i,$i+1] = @char[$i+1,$i]; } # octal escape sequence elsif ($char[$i] =~ /\A \\o \{ ([0-7]+) \} \z/oxms) { $char[$i] = Esjis::octchr($1); } # hexadecimal escape sequence elsif ($char[$i] =~ /\A \\x \{ ([0-9A-Fa-f]+) \} \z/oxms) { $char[$i] = Esjis::hexchr($1); } # \N{CHARNAME} --> N{CHARNAME} elsif ($char[$i] =~ /\A \\ ( N\{ ([^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]*) \} ) \z/oxms) { $char[$i] = $1; } if (0) { } # escape last octet of multiple-octet # my $metachar = qr/[\@\\\|]/oxms; # '|' is for qx//, ``, open() and system() # variable $delimiter and $end_delimiter can be '' elsif ($char[$i] =~ /\A ([\x80-\xFF].*) ([\@\\\|$delimiter$end_delimiter]) \z/xms) { $char[$i] = $1 . '\\' . $2; } # \F # # P.69 Table 2-6. Translation escapes # in Chapter 2: Bits and Pieces # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. # (and so on) # \u \l \U \L \F \Q \E elsif ($char[$i] =~ /\A ([<>]) \z/oxms) { if ($right_e < $left_e) { $char[$i] = '\\' . $char[$i]; } } elsif ($char[$i] eq '\u') { # "STRING @{[ LIST EXPR ]} MORE STRING" # P.257 Other Tricks You Can Do with Hard References # in Chapter 8: References # of ISBN 0-596-00027-8 Programming Perl Third Edition. # P.353 Other Tricks You Can Do with Hard References # in Chapter 8: References # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. # (and so on) $char[$i] = '@{[Esjis::ucfirst qq<'; $left_e++; } elsif ($char[$i] eq '\l') { $char[$i] = '@{[Esjis::lcfirst qq<'; $left_e++; } elsif ($char[$i] eq '\U') { $char[$i] = '@{[Esjis::uc qq<'; $left_e++; } elsif ($char[$i] eq '\L') { $char[$i] = '@{[Esjis::lc qq<'; $left_e++; } elsif ($char[$i] eq '\F') { $char[$i] = '@{[Esjis::fc qq<'; $left_e++; } elsif ($char[$i] eq '\Q') { $char[$i] = '@{[CORE::quotemeta qq<'; $left_e++; } elsif ($char[$i] eq '\E') { if ($right_e < $left_e) { $char[$i] = '>]}'; $right_e++; } else { $char[$i] = ''; } } elsif ($char[$i] eq '\Q') { while (1) { if (++$i > $#char) { last; } if ($char[$i] eq '\E') { last; } } } elsif ($char[$i] eq '\E') { } # $0 --> $0 elsif ($char[$i] =~ /\A \$ 0 \z/oxms) { } elsif ($char[$i] =~ /\A \$ \{ \s* 0 \s* \} \z/oxms) { } # $$ --> $$ elsif ($char[$i] =~ /\A \$\$ \z/oxms) { } # $1, $2, $3 --> $2, $3, $4 (only when multibyte anchoring is enable) elsif ($char[$i] =~ /\A \$ ([1-9][0-9]*) \z/oxms) { $char[$i] = e_capture($1); } elsif ($char[$i] =~ /\A \$ \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) { $char[$i] = e_capture($1); } # $$foo[ ... ] --> $ $foo->[ ... ] elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \[ (?:$qq_bracket)*? \] ) \z/oxms) { $char[$i] = e_capture($1.'->'.$2); } # $$foo{ ... } --> $ $foo->{ ... } elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ (?:$qq_brace)*? \} ) \z/oxms) { $char[$i] = e_capture($1.'->'.$2); } # $$foo elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) \z/oxms) { $char[$i] = e_capture($1); } # $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> Esjis::PREMATCH() elsif ($char[$i] =~ /\A ( \$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) \z/oxmsgc) { $char[$i] = '@{[Esjis::PREMATCH()]}'; } # $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Esjis::MATCH() elsif ($char[$i] =~ /\A ( \$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) \z/oxmsgc) { $char[$i] = '@{[Esjis::MATCH()]}'; } # $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Esjis::POSTMATCH() elsif ($char[$i] =~ /\A ( \$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) \z/oxmsgc) { $char[$i] = '@{[Esjis::POSTMATCH()]}'; } # ${ foo } --> ${ foo } elsif ($char[$i] =~ /\A \$ \s* \{ \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* \} \z/oxms) { } # ${ ... } elsif ($char[$i] =~ /\A \$ \s* \{ \s* ( .+ ) \s* \} \z/oxms) { $char[$i] = e_capture($1); } } # return string if ($left_e > $right_e) { return join '', $ope, $delimiter, @char, '>]}' x ($left_e - $right_e), $end_delimiter; } return join '', $ope, $delimiter, @char, $end_delimiter; } # # escape qw string (qw//) # sub e_qw { my($ope,$delimiter,$end_delimiter,$string) = @_; $slash = 'div'; # choice again delimiter my %octet = map {$_ => 1} ($string =~ /\G ([\x00-\xFF]) /oxmsg); if (not $octet{$end_delimiter}) { return join '', $ope, $delimiter, $string, $end_delimiter; } elsif (not $octet{')'}) { return join '', $ope, '(', $string, ')'; } elsif (not $octet{'}'}) { return join '', $ope, '{', $string, '}'; } elsif (not $octet{']'}) { return join '', $ope, '[', $string, ']'; } elsif (not $octet{'>'}) { return join '', $ope, '<', $string, '>'; } else { for my $char (qw( ! " $ % & * + - . / : = ? @ ^ ` | ~ ), "\x00".."\x1F", "\x7F", "\xFF") { if (not $octet{$char}) { return join '', $ope, $char, $string, $char; } } } # qw/AAA BBB C'CC/ --> ('AAA', 'BBB', 'C\'CC') my @string = CORE::split(/\s+/, $string); for my $string (@string) { my @octet = $string =~ /\G ([\x00-\xFF]) /oxmsg; for my $octet (@octet) { if ($octet =~ /\A (['\\]) \z/oxms) { $octet = '\\' . $1; } } $string = join '', @octet; } return join '', '(', (join ', ', map { "'$_'" } @string), ')'; } # # escape here document (<<"HEREDOC", < "\u\L" if (($char[$i] eq '\L') and ($char[$i+1] eq '\u')) { @char[$i,$i+1] = @char[$i+1,$i]; } # "\U\l" --> "\l\U" elsif (($char[$i] eq '\U') and ($char[$i+1] eq '\l')) { @char[$i,$i+1] = @char[$i+1,$i]; } # octal escape sequence elsif ($char[$i] =~ /\A \\o \{ ([0-7]+) \} \z/oxms) { $char[$i] = Esjis::octchr($1); } # hexadecimal escape sequence elsif ($char[$i] =~ /\A \\x \{ ([0-9A-Fa-f]+) \} \z/oxms) { $char[$i] = Esjis::hexchr($1); } # \N{CHARNAME} --> N{CHARNAME} elsif ($char[$i] =~ /\A \\ ( N\{ ([^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]*) \} ) \z/oxms) { $char[$i] = $1; } if (0) { } # escape character elsif ($char[$i] =~ /\A ([\x80-\xFF].*) ($metachar) \z/oxms) { $char[$i] = $1 . '\\' . $2; } # \u \l \U \L \F \Q \E elsif ($char[$i] =~ /\A ([<>]) \z/oxms) { if ($right_e < $left_e) { $char[$i] = '\\' . $char[$i]; } } elsif ($char[$i] eq '\u') { $char[$i] = '@{[Esjis::ucfirst qq<'; $left_e++; } elsif ($char[$i] eq '\l') { $char[$i] = '@{[Esjis::lcfirst qq<'; $left_e++; } elsif ($char[$i] eq '\U') { $char[$i] = '@{[Esjis::uc qq<'; $left_e++; } elsif ($char[$i] eq '\L') { $char[$i] = '@{[Esjis::lc qq<'; $left_e++; } elsif ($char[$i] eq '\F') { $char[$i] = '@{[Esjis::fc qq<'; $left_e++; } elsif ($char[$i] eq '\Q') { $char[$i] = '@{[CORE::quotemeta qq<'; $left_e++; } elsif ($char[$i] eq '\E') { if ($right_e < $left_e) { $char[$i] = '>]}'; $right_e++; } else { $char[$i] = ''; } } elsif ($char[$i] eq '\Q') { while (1) { if (++$i > $#char) { last; } if ($char[$i] eq '\E') { last; } } } elsif ($char[$i] eq '\E') { } # $0 --> $0 elsif ($char[$i] =~ /\A \$ 0 \z/oxms) { } elsif ($char[$i] =~ /\A \$ \{ \s* 0 \s* \} \z/oxms) { } # $$ --> $$ elsif ($char[$i] =~ /\A \$\$ \z/oxms) { } # $1, $2, $3 --> $2, $3, $4 (only when multibyte anchoring is enable) elsif ($char[$i] =~ /\A \$ ([1-9][0-9]*) \z/oxms) { $char[$i] = e_capture($1); } elsif ($char[$i] =~ /\A \$ \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) { $char[$i] = e_capture($1); } # $$foo[ ... ] --> $ $foo->[ ... ] elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \[ (?:$qq_bracket)*? \] ) \z/oxms) { $char[$i] = e_capture($1.'->'.$2); } # $$foo{ ... } --> $ $foo->{ ... } elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ (?:$qq_brace)*? \} ) \z/oxms) { $char[$i] = e_capture($1.'->'.$2); } # $$foo elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) \z/oxms) { $char[$i] = e_capture($1); } # $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> Esjis::PREMATCH() elsif ($char[$i] =~ /\A ( \$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) \z/oxmsgc) { $char[$i] = '@{[Esjis::PREMATCH()]}'; } # $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Esjis::MATCH() elsif ($char[$i] =~ /\A ( \$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) \z/oxmsgc) { $char[$i] = '@{[Esjis::MATCH()]}'; } # $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Esjis::POSTMATCH() elsif ($char[$i] =~ /\A ( \$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) \z/oxmsgc) { $char[$i] = '@{[Esjis::POSTMATCH()]}'; } # ${ foo } --> ${ foo } elsif ($char[$i] =~ /\A \$ \s* \{ \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* \} \z/oxms) { } # ${ ... } elsif ($char[$i] =~ /\A \$ \s* \{ \s* ( .+ ) \s* \} \z/oxms) { $char[$i] = e_capture($1); } } # return string if ($left_e > $right_e) { return join '', @char, '>]}' x ($left_e - $right_e); } return join '', @char; } # # escape regexp (m//, qr//) # sub e_qr { my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_; $modifier ||= ''; $modifier =~ tr/p//d; if ($modifier =~ /([adlu])/oxms) { my $line = 0; for (my $i=0; my($package,$filename,$use_line,$subroutine) = caller($i); $i++) { if ($filename ne __FILE__) { $line = $use_line + (CORE::substr($_,0,pos($_)) =~ tr/\n//) + 1; last; } } die qq{Unsupported modifier "$1" used at line $line.\n}; } $slash = 'div'; # literal null string pattern if ($string eq '') { $modifier =~ tr/bB//d; $modifier =~ tr/i//d; return join '', $ope, $delimiter, $end_delimiter, $modifier; } # /b /B modifier elsif ($modifier =~ tr/bB//d) { # choice again delimiter if ($delimiter =~ / [\@:] /oxms) { my @char = $string =~ /\G([\x00-\xFF])/oxmsg; my %octet = map {$_ => 1} @char; if (not $octet{')'}) { $delimiter = '('; $end_delimiter = ')'; } elsif (not $octet{'}'}) { $delimiter = '{'; $end_delimiter = '}'; } elsif (not $octet{']'}) { $delimiter = '['; $end_delimiter = ']'; } elsif (not $octet{'>'}) { $delimiter = '<'; $end_delimiter = '>'; } else { for my $char (qw( ! " $ % & * + - . / = ? ^ ` | ~ ), "\x00".."\x1F", "\x7F", "\xFF") { if (not $octet{$char}) { $delimiter = $char; $end_delimiter = $char; last; } } } } if (($ope =~ /\A m? \z/oxms) and ($delimiter eq '?')) { return join '', $ope, $delimiter, $string, $matched, $end_delimiter, $modifier; } else { return join '', $ope, $delimiter, '(?:', $string, ')', $matched, $end_delimiter, $modifier; } } my $ignorecase = ($modifier =~ /i/oxms) ? 1 : 0; my $metachar = qr/[\@\\|[\]{^]/oxms; # split regexp my @char = $string =~ /\G( \\o\{ [0-7]+ \} | \\ [0-7]{2,3} | \\x\{ [0-9A-Fa-f]+ \} | \\x [0-9A-Fa-f]{1,2} | \\c [\x40-\x5F] | \\N\{ [^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]* \} | \\p\{ [^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]* \} | \\P\{ [^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]* \} | \\ (?:$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\} | [\$\@] $qq_variable | \$ \s* \d+ | \$ \s* \{ \s* \d+ \s* \} | \$ \$ (?![\w\{]) | \$ \s* \$ \s* $qq_variable | \[\:\^ (?:alnum|alpha|ascii|blank|cntrl|digit|graph|lower|print|punct|space|upper|word|xdigit) :\] | \[\: (?:alnum|alpha|ascii|blank|cntrl|digit|graph|lower|print|punct|space|upper|word|xdigit) :\] | \[\^ | \(\? | (?:$q_char) )/oxmsg; # choice again delimiter if ($delimiter =~ / [\@:] /oxms) { my %octet = map {$_ => 1} @char; if (not $octet{')'}) { $delimiter = '('; $end_delimiter = ')'; } elsif (not $octet{'}'}) { $delimiter = '{'; $end_delimiter = '}'; } elsif (not $octet{']'}) { $delimiter = '['; $end_delimiter = ']'; } elsif (not $octet{'>'}) { $delimiter = '<'; $end_delimiter = '>'; } else { for my $char (qw( ! " $ % & * + - . / = ? ^ ` | ~ ), "\x00".."\x1F", "\x7F", "\xFF") { if (not $octet{$char}) { $delimiter = $char; $end_delimiter = $char; last; } } } } my $left_e = 0; my $right_e = 0; for (my $i=0; $i <= $#char; $i++) { # "\L\u" --> "\u\L" if (($char[$i] eq '\L') and ($char[$i+1] eq '\u')) { @char[$i,$i+1] = @char[$i+1,$i]; } # "\U\l" --> "\l\U" elsif (($char[$i] eq '\U') and ($char[$i+1] eq '\l')) { @char[$i,$i+1] = @char[$i+1,$i]; } # octal escape sequence elsif ($char[$i] =~ /\A \\o \{ ([0-7]+) \} \z/oxms) { $char[$i] = Esjis::octchr($1); } # hexadecimal escape sequence elsif ($char[$i] =~ /\A \\x \{ ([0-9A-Fa-f]+) \} \z/oxms) { $char[$i] = Esjis::hexchr($1); } # \N{CHARNAME} --> N\{CHARNAME} elsif ($char[$i] =~ /\A \\ (N) ( \{ ([^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]*) \} ) \z/oxms) { $char[$i] = $1 . '\\' . $2; } # \p{PROPERTY} --> p\{PROPERTY} elsif ($char[$i] =~ /\A \\ (p) ( \{ ([^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]*) \} ) \z/oxms) { $char[$i] = $1 . '\\' . $2; } # \P{PROPERTY} --> P\{PROPERTY} elsif ($char[$i] =~ /\A \\ (P) ( \{ ([^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]*) \} ) \z/oxms) { $char[$i] = $1 . '\\' . $2; } # \p, \P, \X --> p, P, X elsif ($char[$i] =~ /\A \\ ( [pPX] ) \z/oxms) { $char[$i] = $1; } if (0) { } # escape last octet of multiple-octet elsif ($char[$i] =~ /\A \\? ([\x80-\xFF].*) ($metachar|\Q$delimiter\E|\Q$end_delimiter\E) \z/xms) { $char[$i] = $1 . '\\' . $2; } # join separated multiple-octet elsif ($char[$i] =~ /\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms) { if ( ($i+3 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+3]) == 3) and (eval(sprintf '"%s%s%s%s"', @char[$i..$i+3]) =~ /\A $q_char \z/oxms)) { $char[$i] .= join '', splice @char, $i+1, 3; } elsif (($i+2 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+2]) == 2) and (eval(sprintf '"%s%s%s"', @char[$i..$i+2]) =~ /\A $q_char \z/oxms)) { $char[$i] .= join '', splice @char, $i+1, 2; } elsif (($i+1 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, $char[$i+1 ]) == 1) and (eval(sprintf '"%s%s"', @char[$i..$i+1]) =~ /\A $q_char \z/oxms)) { $char[$i] .= join '', splice @char, $i+1, 1; } } # open character class [...] elsif ($char[$i] eq '[') { my $left = $i; # [] make die "Unmatched [] in regexp ..." # (and so on) if ($char[$i+1] eq ']') { $i++; } while (1) { if (++$i > $#char) { die __FILE__, ": Unmatched [] in regexp"; } if ($char[$i] eq ']') { my $right = $i; # [...] if (grep(/\A [\$\@]/oxms,@char[$left+1..$right-1]) >= 1) { splice @char, $left, $right-$left+1, sprintf(q{@{[Esjis::charlist_qr(%s,'%s')]}}, join(',', map {qq_stuff($delimiter,$end_delimiter,$_)} @char[$left+1..$right-1]), $modifier); } else { splice @char, $left, $right-$left+1, Esjis::charlist_qr(@char[$left+1..$right-1], $modifier); } $i = $left; last; } } } # open character class [^...] elsif ($char[$i] eq '[^') { my $left = $i; # [^] make die "Unmatched [] in regexp ..." # (and so on) if ($char[$i+1] eq ']') { $i++; } while (1) { if (++$i > $#char) { die __FILE__, ": Unmatched [] in regexp"; } if ($char[$i] eq ']') { my $right = $i; # [^...] if (grep(/\A [\$\@]/oxms,@char[$left+1..$right-1]) >= 1) { splice @char, $left, $right-$left+1, sprintf(q{@{[Esjis::charlist_not_qr(%s,'%s')]}}, join(',', map {qq_stuff($delimiter,$end_delimiter,$_)} @char[$left+1..$right-1]), $modifier); } else { splice @char, $left, $right-$left+1, Esjis::charlist_not_qr(@char[$left+1..$right-1], $modifier); } $i = $left; last; } } } # rewrite character class or escape character elsif (my $char = character_class($char[$i],$modifier)) { $char[$i] = $char; } # /i modifier elsif ($ignorecase and ($char[$i] =~ /\A [\x00-\xFF] \z/oxms) and (Esjis::uc($char[$i]) ne Esjis::fc($char[$i]))) { if (CORE::length(Esjis::fc($char[$i])) == 1) { $char[$i] = '[' . Esjis::uc($char[$i]) . Esjis::fc($char[$i]) . ']'; } else { $char[$i] = '(?:' . Esjis::uc($char[$i]) . '|' . Esjis::fc($char[$i]) . ')'; } } # \u \l \U \L \F \Q \E elsif ($char[$i] =~ /\A [<>] \z/oxms) { if ($right_e < $left_e) { $char[$i] = '\\' . $char[$i]; } } elsif ($char[$i] eq '\u') { $char[$i] = '@{[Esjis::ucfirst qq<'; $left_e++; } elsif ($char[$i] eq '\l') { $char[$i] = '@{[Esjis::lcfirst qq<'; $left_e++; } elsif ($char[$i] eq '\U') { $char[$i] = '@{[Esjis::uc qq<'; $left_e++; } elsif ($char[$i] eq '\L') { $char[$i] = '@{[Esjis::lc qq<'; $left_e++; } elsif ($char[$i] eq '\F') { $char[$i] = '@{[Esjis::fc qq<'; $left_e++; } elsif ($char[$i] eq '\Q') { $char[$i] = '@{[CORE::quotemeta qq<'; $left_e++; } elsif ($char[$i] eq '\E') { if ($right_e < $left_e) { $char[$i] = '>]}'; $right_e++; } else { $char[$i] = ''; } } elsif ($char[$i] eq '\Q') { while (1) { if (++$i > $#char) { last; } if ($char[$i] eq '\E') { last; } } } elsif ($char[$i] eq '\E') { } # $0 --> $0 elsif ($char[$i] =~ /\A \$ 0 \z/oxms) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } elsif ($char[$i] =~ /\A \$ \{ \s* 0 \s* \} \z/oxms) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $$ --> $$ elsif ($char[$i] =~ /\A \$\$ \z/oxms) { } # $1, $2, $3 --> $2, $3, $4 (only when multibyte anchoring is enable) elsif ($char[$i] =~ /\A \$ ([1-9][0-9]*) \z/oxms) { $char[$i] = e_capture($1); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } elsif ($char[$i] =~ /\A \$ \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) { $char[$i] = e_capture($1); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $$foo[ ... ] --> $ $foo->[ ... ] elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \[ (?:$qq_bracket)*? \] ) \z/oxms) { $char[$i] = e_capture($1.'->'.$2); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $$foo{ ... } --> $ $foo->{ ... } elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ (?:$qq_brace)*? \} ) \z/oxms) { $char[$i] = e_capture($1.'->'.$2); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $$foo elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) \z/oxms) { $char[$i] = e_capture($1); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> Esjis::PREMATCH() elsif ($char[$i] =~ /\A ( \$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) \z/oxmsgc) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(Esjis::PREMATCH())]}'; } else { $char[$i] = '@{[Esjis::PREMATCH()]}'; } } # $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Esjis::MATCH() elsif ($char[$i] =~ /\A ( \$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) \z/oxmsgc) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(Esjis::MATCH())]}'; } else { $char[$i] = '@{[Esjis::MATCH()]}'; } } # $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Esjis::POSTMATCH() elsif ($char[$i] =~ /\A ( \$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) \z/oxmsgc) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(Esjis::POSTMATCH())]}'; } else { $char[$i] = '@{[Esjis::POSTMATCH()]}'; } } # ${ foo } elsif ($char[$i] =~ /\A \$ \s* \{ ( \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* ) \} \z/oxms) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # ${ ... } elsif ($char[$i] =~ /\A \$ \s* \{ \s* ( .+ ) \s* \} \z/oxms) { $char[$i] = e_capture($1); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $scalar or @array elsif ($char[$i] =~ /\A [\$\@].+ /oxms) { $char[$i] = e_string($char[$i]); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # quote character before ? + * { elsif (($i >= 1) and ($char[$i] =~ /\A [\?\+\*\{] \z/oxms)) { if ($char[$i-1] =~ /\A (?:[\x00-\xFF]|\\[0-7]{2,3}|\\x[0-9-A-Fa-f]{1,2}) \z/oxms) { } elsif (($ope =~ /\A m? \z/oxms) and ($delimiter eq '?')) { my $char = $char[$i-1]; if ($char[$i] eq '{') { die __FILE__, qq{: "MULTIBYTE{n}" should be "(MULTIBYTE){n}" in m?? (and shift \$1,\$2,\$3,...) ($char){n}}; } else { die __FILE__, qq{: "MULTIBYTE$char[$i]" should be "(MULTIBYTE)$char[$i]" in m?? (and shift \$1,\$2,\$3,...) ($char)$char[$i]}; } } else { $char[$i-1] = '(?:' . $char[$i-1] . ')'; } } } # make regexp string $modifier =~ tr/i//d; if ($left_e > $right_e) { if (($ope =~ /\A m? \z/oxms) and ($delimiter eq '?')) { return join '', $ope, $delimiter, $anchor, @char, '>]}' x ($left_e - $right_e), $matched, $end_delimiter, $modifier; } else { return join '', $ope, $delimiter, $anchor, '(?:', @char, '>]}' x ($left_e - $right_e), ')', $matched, $end_delimiter, $modifier; } } if (($ope =~ /\A m? \z/oxms) and ($delimiter eq '?')) { return join '', $ope, $delimiter, $anchor, @char, $matched, $end_delimiter, $modifier; } else { return join '', $ope, $delimiter, $anchor, '(?:', @char, ')', $matched, $end_delimiter, $modifier; } } # # double quote stuff # sub qq_stuff { my($delimiter,$end_delimiter,$stuff) = @_; # scalar variable or array variable if ($stuff =~ /\A [\$\@] /oxms) { return $stuff; } # quote by delimiter my %octet = map {$_ => 1} ($stuff =~ /\G ([\x00-\xFF]) /oxmsg); for my $char (qw( ! " $ % & * + - . / : = ? @ ^ ` | ~ ), "\x00".."\x1F", "\x7F", "\xFF") { next if $char eq $delimiter; next if $char eq $end_delimiter; if (not $octet{$char}) { return join '', 'qq', $char, $stuff, $char; } } return join '', 'qq', '<', $stuff, '>'; } # # escape regexp (m'', qr'' and m''b, qr''b) # sub e_qr_q { my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_; $modifier ||= ''; $modifier =~ tr/p//d; if ($modifier =~ /([adlu])/oxms) { my $line = 0; for (my $i=0; my($package,$filename,$use_line,$subroutine) = caller($i); $i++) { if ($filename ne __FILE__) { $line = $use_line + (CORE::substr($_,0,pos($_)) =~ tr/\n//) + 1; last; } } die qq{Unsupported modifier "$1" used at line $line.\n}; } $slash = 'div'; # literal null string pattern if ($string eq '') { $modifier =~ tr/bB//d; $modifier =~ tr/i//d; return join '', $ope, $delimiter, $end_delimiter, $modifier; } # with /b /B modifier elsif ($modifier =~ tr/bB//d) { return e_qr_qb($ope,$delimiter,$end_delimiter,$string,$modifier); } # without /b /B modifier else { return e_qr_qt($ope,$delimiter,$end_delimiter,$string,$modifier); } } # # escape regexp (m'', qr'') # sub e_qr_qt { my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_; my $ignorecase = ($modifier =~ /i/oxms) ? 1 : 0; # split regexp my @char = $string =~ /\G( \[\:\^ [a-z]+ \:\] | \[\: [a-z]+ \:\] | \[\^ | [\$\@\/\\] | \\? (?:$q_char) )/oxmsg; # unescape character for (my $i=0; $i <= $#char; $i++) { if (0) { } # escape last octet of multiple-octet elsif ($char[$i] =~ /\A ([\x80-\xFF].*) ([\\|\[\{\^]|\Q$delimiter\E|\Q$end_delimiter\E) \z/xms) { $char[$i] = $1 . '\\' . $2; } # open character class [...] elsif ($char[$i] eq '[') { my $left = $i; if ($char[$i+1] eq ']') { $i++; } while (1) { if (++$i > $#char) { die __FILE__, ": Unmatched [] in regexp"; } if ($char[$i] eq ']') { my $right = $i; # [...] splice @char, $left, $right-$left+1, Esjis::charlist_qr(@char[$left+1..$right-1], $modifier); $i = $left; last; } } } # open character class [^...] elsif ($char[$i] eq '[^') { my $left = $i; if ($char[$i+1] eq ']') { $i++; } while (1) { if (++$i > $#char) { die __FILE__, ": Unmatched [] in regexp"; } if ($char[$i] eq ']') { my $right = $i; # [^...] splice @char, $left, $right-$left+1, Esjis::charlist_not_qr(@char[$left+1..$right-1], $modifier); $i = $left; last; } } } # escape $ @ / and \ elsif ($char[$i] =~ /\A [\$\@\/\\] \z/oxms) { $char[$i] = '\\' . $char[$i]; } # rewrite character class or escape character elsif (my $char = character_class($char[$i],$modifier)) { $char[$i] = $char; } # /i modifier elsif ($ignorecase and ($char[$i] =~ /\A [\x00-\xFF] \z/oxms) and (Esjis::uc($char[$i]) ne Esjis::fc($char[$i]))) { if (CORE::length(Esjis::fc($char[$i])) == 1) { $char[$i] = '[' . Esjis::uc($char[$i]) . Esjis::fc($char[$i]) . ']'; } else { $char[$i] = '(?:' . Esjis::uc($char[$i]) . '|' . Esjis::fc($char[$i]) . ')'; } } # quote character before ? + * { elsif (($i >= 1) and ($char[$i] =~ /\A [\?\+\*\{] \z/oxms)) { if ($char[$i-1] =~ /\A [\x00-\xFF] \z/oxms) { } else { $char[$i-1] = '(?:' . $char[$i-1] . ')'; } } } $delimiter = '/'; $end_delimiter = '/'; $modifier =~ tr/i//d; return join '', $ope, $delimiter, $anchor, '(?:', @char, ')', $matched, $end_delimiter, $modifier; } # # escape regexp (m''b, qr''b) # sub e_qr_qb { my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_; # split regexp my @char = $string =~ /\G( \\\\ | [\$\@\/\\] | [\x00-\xFF] )/oxmsg; # unescape character for (my $i=0; $i <= $#char; $i++) { if (0) { } # remain \\ elsif ($char[$i] eq '\\\\') { } # escape $ @ / and \ elsif ($char[$i] =~ /\A [\$\@\/\\] \z/oxms) { $char[$i] = '\\' . $char[$i]; } } $delimiter = '/'; $end_delimiter = '/'; return join '', $ope, $delimiter, '(?:', @char, ')', $matched, $end_delimiter, $modifier; } # # escape regexp (s/here//) # sub e_s1 { my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_; $modifier ||= ''; $modifier =~ tr/p//d; if ($modifier =~ /([adlu])/oxms) { my $line = 0; for (my $i=0; my($package,$filename,$use_line,$subroutine) = caller($i); $i++) { if ($filename ne __FILE__) { $line = $use_line + (CORE::substr($_,0,pos($_)) =~ tr/\n//) + 1; last; } } die qq{Unsupported modifier "$1" used at line $line.\n}; } $slash = 'div'; # literal null string pattern if ($string eq '') { $modifier =~ tr/bB//d; $modifier =~ tr/i//d; return join '', $ope, $delimiter, $end_delimiter, $modifier; } # /b /B modifier elsif ($modifier =~ tr/bB//d) { # choice again delimiter if ($delimiter =~ / [\@:] /oxms) { my @char = $string =~ /\G([\x00-\xFF])/oxmsg; my %octet = map {$_ => 1} @char; if (not $octet{')'}) { $delimiter = '('; $end_delimiter = ')'; } elsif (not $octet{'}'}) { $delimiter = '{'; $end_delimiter = '}'; } elsif (not $octet{']'}) { $delimiter = '['; $end_delimiter = ']'; } elsif (not $octet{'>'}) { $delimiter = '<'; $end_delimiter = '>'; } else { for my $char (qw( ! " $ % & * + - . / = ? ^ ` | ~ ), "\x00".."\x1F", "\x7F", "\xFF") { if (not $octet{$char}) { $delimiter = $char; $end_delimiter = $char; last; } } } } my $prematch = ''; $prematch = q{(\G[\x00-\xFF]*?)}; 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 = $string =~ /\G( \\g \s* \{ \s* - \s* [1-9][0-9]* \s* \} | \\g \s* \{ \s* [1-9][0-9]* \s* \} | \\g \s* [1-9][0-9]* | \\o\{ [0-7]+ \} | \\ [1-9][0-9]* | \\ [0-7]{2,3} | \\x\{ [0-9A-Fa-f]+ \} | \\x [0-9A-Fa-f]{1,2} | \\c [\x40-\x5F] | \\N\{ [^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]* \} | \\p\{ [^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]* \} | \\P\{ [^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]* \} | \\ (?:$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\} | [\$\@] $qq_variable | \$ \s* \d+ | \$ \s* \{ \s* \d+ \s* \} | \$ \$ (?![\w\{]) | \$ \s* \$ \s* $qq_variable | \[\:\^ (?:alnum|alpha|ascii|blank|cntrl|digit|graph|lower|print|punct|space|upper|word|xdigit) :\] | \[\: (?:alnum|alpha|ascii|blank|cntrl|digit|graph|lower|print|punct|space|upper|word|xdigit) :\] | \[\^ | \(\? | (?:$q_char) )/oxmsg; # choice again delimiter if ($delimiter =~ / [\@:] /oxms) { my %octet = map {$_ => 1} @char; if (not $octet{')'}) { $delimiter = '('; $end_delimiter = ')'; } elsif (not $octet{'}'}) { $delimiter = '{'; $end_delimiter = '}'; } elsif (not $octet{']'}) { $delimiter = '['; $end_delimiter = ']'; } elsif (not $octet{'>'}) { $delimiter = '<'; $end_delimiter = '>'; } else { for my $char (qw( ! " $ % & * + - . / = ? ^ ` | ~ ), "\x00".."\x1F", "\x7F", "\xFF") { if (not $octet{$char}) { $delimiter = $char; $end_delimiter = $char; last; } } } } # count '(' my $parens = grep { $_ eq '(' } @char; my $left_e = 0; my $right_e = 0; for (my $i=0; $i <= $#char; $i++) { # "\L\u" --> "\u\L" if (($char[$i] eq '\L') and ($char[$i+1] eq '\u')) { @char[$i,$i+1] = @char[$i+1,$i]; } # "\U\l" --> "\l\U" elsif (($char[$i] eq '\U') and ($char[$i+1] eq '\l')) { @char[$i,$i+1] = @char[$i+1,$i]; } # octal escape sequence elsif ($char[$i] =~ /\A \\o \{ ([0-7]+) \} \z/oxms) { $char[$i] = Esjis::octchr($1); } # hexadecimal escape sequence elsif ($char[$i] =~ /\A \\x \{ ([0-9A-Fa-f]+) \} \z/oxms) { $char[$i] = Esjis::hexchr($1); } # \N{CHARNAME} --> N\{CHARNAME} elsif ($char[$i] =~ /\A \\ (N) ( \{ ([^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]*) \} ) \z/oxms) { $char[$i] = $1 . '\\' . $2; } # \p{PROPERTY} --> p\{PROPERTY} elsif ($char[$i] =~ /\A \\ (p) ( \{ ([^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]*) \} ) \z/oxms) { $char[$i] = $1 . '\\' . $2; } # \P{PROPERTY} --> P\{PROPERTY} elsif ($char[$i] =~ /\A \\ (P) ( \{ ([^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]*) \} ) \z/oxms) { $char[$i] = $1 . '\\' . $2; } # \p, \P, \X --> p, P, X elsif ($char[$i] =~ /\A \\ ( [pPX] ) \z/oxms) { $char[$i] = $1; } if (0) { } # escape last octet of multiple-octet elsif ($char[$i] =~ /\A \\? ([\x80-\xFF].*) ($metachar|\Q$delimiter\E|\Q$end_delimiter\E) \z/xms) { $char[$i] = $1 . '\\' . $2; } # join separated multiple-octet elsif ($char[$i] =~ /\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms) { if ( ($i+3 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+3]) == 3) and (eval(sprintf '"%s%s%s%s"', @char[$i..$i+3]) =~ /\A $q_char \z/oxms)) { $char[$i] .= join '', splice @char, $i+1, 3; } elsif (($i+2 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+2]) == 2) and (eval(sprintf '"%s%s%s"', @char[$i..$i+2]) =~ /\A $q_char \z/oxms)) { $char[$i] .= join '', splice @char, $i+1, 2; } elsif (($i+1 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, $char[$i+1 ]) == 1) and (eval(sprintf '"%s%s"', @char[$i..$i+1]) =~ /\A $q_char \z/oxms)) { $char[$i] .= join '', splice @char, $i+1, 1; } } # open character class [...] elsif ($char[$i] eq '[') { my $left = $i; if ($char[$i+1] eq ']') { $i++; } while (1) { if (++$i > $#char) { die __FILE__, ": Unmatched [] in regexp"; } if ($char[$i] eq ']') { my $right = $i; # [...] if (grep(/\A [\$\@]/oxms,@char[$left+1..$right-1]) >= 1) { splice @char, $left, $right-$left+1, sprintf(q{@{[Esjis::charlist_qr(%s,'%s')]}}, join(',', map {qq_stuff($delimiter,$end_delimiter,$_)} @char[$left+1..$right-1]), $modifier); } else { splice @char, $left, $right-$left+1, Esjis::charlist_qr(@char[$left+1..$right-1], $modifier); } $i = $left; last; } } } # open character class [^...] elsif ($char[$i] eq '[^') { my $left = $i; if ($char[$i+1] eq ']') { $i++; } while (1) { if (++$i > $#char) { die __FILE__, ": Unmatched [] in regexp"; } if ($char[$i] eq ']') { my $right = $i; # [^...] if (grep(/\A [\$\@]/oxms,@char[$left+1..$right-1]) >= 1) { splice @char, $left, $right-$left+1, sprintf(q{@{[Esjis::charlist_not_qr(%s,'%s')]}}, join(',', map {qq_stuff($delimiter,$end_delimiter,$_)} @char[$left+1..$right-1]), $modifier); } else { splice @char, $left, $right-$left+1, Esjis::charlist_not_qr(@char[$left+1..$right-1], $modifier); } $i = $left; last; } } } # rewrite character class or escape character elsif (my $char = character_class($char[$i],$modifier)) { $char[$i] = $char; } # /i modifier elsif ($ignorecase and ($char[$i] =~ /\A [\x00-\xFF] \z/oxms) and (Esjis::uc($char[$i]) ne Esjis::fc($char[$i]))) { if (CORE::length(Esjis::fc($char[$i])) == 1) { $char[$i] = '[' . Esjis::uc($char[$i]) . Esjis::fc($char[$i]) . ']'; } else { $char[$i] = '(?:' . Esjis::uc($char[$i]) . '|' . Esjis::fc($char[$i]) . ')'; } } # \u \l \U \L \F \Q \E elsif ($char[$i] =~ /\A [<>] \z/oxms) { if ($right_e < $left_e) { $char[$i] = '\\' . $char[$i]; } } elsif ($char[$i] eq '\u') { $char[$i] = '@{[Esjis::ucfirst qq<'; $left_e++; } elsif ($char[$i] eq '\l') { $char[$i] = '@{[Esjis::lcfirst qq<'; $left_e++; } elsif ($char[$i] eq '\U') { $char[$i] = '@{[Esjis::uc qq<'; $left_e++; } elsif ($char[$i] eq '\L') { $char[$i] = '@{[Esjis::lc qq<'; $left_e++; } elsif ($char[$i] eq '\F') { $char[$i] = '@{[Esjis::fc qq<'; $left_e++; } elsif ($char[$i] eq '\Q') { $char[$i] = '@{[CORE::quotemeta qq<'; $left_e++; } elsif ($char[$i] eq '\E') { if ($right_e < $left_e) { $char[$i] = '>]}'; $right_e++; } else { $char[$i] = ''; } } elsif ($char[$i] eq '\Q') { while (1) { if (++$i > $#char) { last; } if ($char[$i] eq '\E') { last; } } } elsif ($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); } } # $0 --> $0 elsif ($char[$i] =~ /\A \$ 0 \z/oxms) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } elsif ($char[$i] =~ /\A \$ \{ \s* 0 \s* \} \z/oxms) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $$ --> $$ elsif ($char[$i] =~ /\A \$\$ \z/oxms) { } # $1, $2, $3 --> $2, $3, $4 (only when multibyte anchoring is enable) elsif ($char[$i] =~ /\A \$ ([1-9][0-9]*) \z/oxms) { $char[$i] = e_capture($1); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } elsif ($char[$i] =~ /\A \$ \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) { $char[$i] = e_capture($1); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $$foo[ ... ] --> $ $foo->[ ... ] elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \[ (?:$qq_bracket)*? \] ) \z/oxms) { $char[$i] = e_capture($1.'->'.$2); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $$foo{ ... } --> $ $foo->{ ... } elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ (?:$qq_brace)*? \} ) \z/oxms) { $char[$i] = e_capture($1.'->'.$2); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $$foo elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) \z/oxms) { $char[$i] = e_capture($1); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> Esjis::PREMATCH() elsif ($char[$i] =~ /\A ( \$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) \z/oxmsgc) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(Esjis::PREMATCH())]}'; } else { $char[$i] = '@{[Esjis::PREMATCH()]}'; } } # $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Esjis::MATCH() elsif ($char[$i] =~ /\A ( \$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) \z/oxmsgc) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(Esjis::MATCH())]}'; } else { $char[$i] = '@{[Esjis::MATCH()]}'; } } # $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Esjis::POSTMATCH() elsif ($char[$i] =~ /\A ( \$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) \z/oxmsgc) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(Esjis::POSTMATCH())]}'; } else { $char[$i] = '@{[Esjis::POSTMATCH()]}'; } } # ${ foo } elsif ($char[$i] =~ /\A \$ \s* \{ ( \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* ) \} \z/oxms) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # ${ ... } elsif ($char[$i] =~ /\A \$ \s* \{ \s* ( .+ ) \s* \} \z/oxms) { $char[$i] = e_capture($1); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $scalar or @array elsif ($char[$i] =~ /\A [\$\@].+ /oxms) { $char[$i] = e_string($char[$i]); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # quote character before ? + * { elsif (($i >= 1) and ($char[$i] =~ /\A [\?\+\*\{] \z/oxms)) { if ($char[$i-1] =~ /\A (?:[\x00-\xFF]|\\[0-7]{2,3}|\\x[0-9-A-Fa-f]{1,2}) \z/oxms) { } else { $char[$i-1] = '(?:' . $char[$i-1] . ')'; } } } # make regexp string my $prematch = ''; $prematch = "($anchor)"; $modifier =~ tr/i//d; if ($left_e > $right_e) { return join '', $ope, $delimiter, $prematch, '(?:', @char, '>]}' x ($left_e - $right_e), ')', $matched, $end_delimiter, $modifier; } return join '', $ope, $delimiter, $prematch, '(?:', @char, ')', $matched, $end_delimiter, $modifier; } # # escape regexp (s'here'' or s'here''b) # sub e_s1_q { my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_; $modifier ||= ''; $modifier =~ tr/p//d; if ($modifier =~ /([adlu])/oxms) { my $line = 0; for (my $i=0; my($package,$filename,$use_line,$subroutine) = caller($i); $i++) { if ($filename ne __FILE__) { $line = $use_line + (CORE::substr($_,0,pos($_)) =~ tr/\n//) + 1; last; } } die qq{Unsupported modifier "$1" used at line $line.\n}; } $slash = 'div'; # literal null string pattern if ($string eq '') { $modifier =~ tr/bB//d; $modifier =~ tr/i//d; return join '', $ope, $delimiter, $end_delimiter, $modifier; } # with /b /B modifier elsif ($modifier =~ tr/bB//d) { return e_s1_qb($ope,$delimiter,$end_delimiter,$string,$modifier); } # without /b /B modifier else { return e_s1_qt($ope,$delimiter,$end_delimiter,$string,$modifier); } } # # escape regexp (s'here'') # sub e_s1_qt { my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_; my $ignorecase = ($modifier =~ /i/oxms) ? 1 : 0; # split regexp my @char = $string =~ /\G( \[\:\^ [a-z]+ \:\] | \[\: [a-z]+ \:\] | \[\^ | [\$\@\/\\] | \\? (?:$q_char) )/oxmsg; # unescape character for (my $i=0; $i <= $#char; $i++) { if (0) { } # escape last octet of multiple-octet elsif ($char[$i] =~ /\A ([\x80-\xFF].*) ([\\|\[\{\^]|\Q$delimiter\E|\Q$end_delimiter\E) \z/xms) { $char[$i] = $1 . '\\' . $2; } # open character class [...] elsif ($char[$i] eq '[') { my $left = $i; if ($char[$i+1] eq ']') { $i++; } while (1) { if (++$i > $#char) { die __FILE__, ": Unmatched [] in regexp"; } if ($char[$i] eq ']') { my $right = $i; # [...] splice @char, $left, $right-$left+1, Esjis::charlist_qr(@char[$left+1..$right-1], $modifier); $i = $left; last; } } } # open character class [^...] elsif ($char[$i] eq '[^') { my $left = $i; if ($char[$i+1] eq ']') { $i++; } while (1) { if (++$i > $#char) { die __FILE__, ": Unmatched [] in regexp"; } if ($char[$i] eq ']') { my $right = $i; # [^...] splice @char, $left, $right-$left+1, Esjis::charlist_not_qr(@char[$left+1..$right-1], $modifier); $i = $left; last; } } } # escape $ @ / and \ elsif ($char[$i] =~ /\A [\$\@\/\\] \z/oxms) { $char[$i] = '\\' . $char[$i]; } # rewrite character class or escape character elsif (my $char = character_class($char[$i],$modifier)) { $char[$i] = $char; } # /i modifier elsif ($ignorecase and ($char[$i] =~ /\A [\x00-\xFF] \z/oxms) and (Esjis::uc($char[$i]) ne Esjis::fc($char[$i]))) { if (CORE::length(Esjis::fc($char[$i])) == 1) { $char[$i] = '[' . Esjis::uc($char[$i]) . Esjis::fc($char[$i]) . ']'; } else { $char[$i] = '(?:' . Esjis::uc($char[$i]) . '|' . Esjis::fc($char[$i]) . ')'; } } # quote character before ? + * { elsif (($i >= 1) and ($char[$i] =~ /\A [\?\+\*\{] \z/oxms)) { if ($char[$i-1] =~ /\A [\x00-\xFF] \z/oxms) { } else { $char[$i-1] = '(?:' . $char[$i-1] . ')'; } } } $modifier =~ tr/i//d; $delimiter = '/'; $end_delimiter = '/'; my $prematch = ''; $prematch = "($anchor)"; return join '', $ope, $delimiter, $prematch, '(?:', @char, ')', $matched, $end_delimiter, $modifier; } # # escape regexp (s'here''b) # sub e_s1_qb { my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_; # split regexp my @char = $string =~ /\G( \\\\ | [\$\@\/\\] | [\x00-\xFF] )/oxmsg; # unescape character for (my $i=0; $i <= $#char; $i++) { if (0) { } # remain \\ elsif ($char[$i] eq '\\\\') { } # escape $ @ / and \ elsif ($char[$i] =~ /\A [\$\@\/\\] \z/oxms) { $char[$i] = '\\' . $char[$i]; } } $delimiter = '/'; $end_delimiter = '/'; my $prematch = ''; $prematch = q{(\G[\x00-\xFF]*?)}; return join '', $ope, $delimiter, $prematch, '(?:', @char, ')', $matched, $end_delimiter, $modifier; } # # escape regexp (s''here') # sub e_s2_q { my($ope,$delimiter,$end_delimiter,$string) = @_; $slash = 'div'; my @char = $string =~ / \G (\\\\|[\$\@\/\\]|$q_char) /oxmsg; for (my $i=0; $i <= $#char; $i++) { if (0) { } # escape last octet of multiple-octet elsif ($char[$i] =~ /\A ([\x80-\xFF].*) (\Q$delimiter\E|\Q$end_delimiter\E) \z/xms) { $char[$i] = $1 . '\\' . $2; } elsif (($char[$i] =~ /\A ([\x80-\xFF].*) (\\) \z/xms) and defined($char[$i+1]) and ($char[$i+1] eq '\\')) { $char[$i] = $1 . '\\' . $2; } # not escape \\ elsif ($char[$i] =~ /\A \\\\ \z/oxms) { } # escape $ @ / and \ elsif ($char[$i] =~ /\A [\$\@\/\\] \z/oxms) { $char[$i] = '\\' . $char[$i]; } } if (defined($char[-1]) and ($char[-1] =~ /\A ([\x80-\xFF].*) (\\) \z/xms)) { $char[-1] = $1 . '\\' . $2; } return join '', $ope, $delimiter, @char, $end_delimiter; } # # escape regexp (s/here/and here/modifier) # sub e_sub { my($variable,$delimiter1,$pattern,$end_delimiter1,$delimiter2,$replacement,$end_delimiter2,$modifier) = @_; $modifier ||= ''; $modifier =~ tr/p//d; if ($modifier =~ /([adlu])/oxms) { my $line = 0; for (my $i=0; my($package,$filename,$use_line,$subroutine) = caller($i); $i++) { if ($filename ne __FILE__) { $line = $use_line + (CORE::substr($_,0,pos($_)) =~ tr/\n//) + 1; last; } } die qq{Unsupported modifier "$1" used at line $line.\n}; } if ($variable eq '') { $variable = '$_'; $bind_operator = ' =~ '; } $slash = 'div'; # P.128 Start of match (or end of previous match): \G # in Chapter 3: Overview of Regular Expression Features and Flavors # P.312 Iterative Matching: Scalar Context, with /g # in Chapter 7: Perl # of ISBN 0-596-00272-6 Mastering Regular Expressions, Second edition # P.181 Where You Left Off: The \G Assertion # in Chapter 5: Pattern Matching # of ISBN 0-596-00027-8 Programming Perl Third Edition. # P.220 Where You Left Off: The \G Assertion # in Chapter 5: Pattern Matching # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. my $e_modifier = $modifier =~ tr/e//d; my $r_modifier = $modifier =~ tr/r//d; my $my = ''; if ($variable =~ s/\A \( \s* ( (?: local \b | my \b | our \b | state \b )? .+ ) \) \z/$1/oxms) { $my = $variable; $variable =~ s/ (?: local \b | my \b | our \b | state \b ) \s* //oxms; $variable =~ s/ = .+ \z//oxms; } (my $variable_basename = $variable) =~ s/ [\[\{].* \z//oxms; $variable_basename =~ s/ \s+ \z//oxms; # quote replacement string my $e_replacement = ''; if ($e_modifier >= 1) { $e_replacement = e_qq('', '', '', $replacement); $e_modifier--; } else { if ($delimiter2 eq "'") { $e_replacement = e_s2_q('qq', '/', '/', $replacement); } else { $e_replacement = e_qq ('qq', $delimiter2, $end_delimiter2, $replacement); } } my $local = ''; if ($variable_basename =~ /::/) { $local = 'local'; } else{ $local = 'my'; } my $sub = ''; # with /r if ($r_modifier) { if (0) { } # s///gr with multibyte anchoring elsif ($modifier =~ /g/oxms) { $sub = sprintf( # 1 2 3 4 5 6 7 8 9 10 11 1213 14 15 16 17 18 19 20 21 22 q, $local, # 1 $variable_basename, # 2 $variable, # 3 $local, # 4 $variable_basename, # 5 $variable_basename, # 6 ($delimiter1 eq "'") ? # 7 e_s1_q('m', $delimiter1, $end_delimiter1, $pattern, $modifier) : # : e_s1 ('m', $delimiter1, $end_delimiter1, $pattern, $modifier), # : $s_matched, # 8 $local, # 9 $variable_basename, # 10 $e_replacement, # 11 sprintf('%s_r=eval %s_r; ', $variable_basename, $variable_basename) x $e_modifier, # 12 $variable_basename, # 13 $variable_basename, # 14 $variable_basename, # 15 $variable_basename, # 16 $variable_basename, # 17 $variable_basename, # 18 $variable_basename, # 19 $variable_basename, # 20 $variable_basename, # 21 $variable_basename, # 22 ); } # s///gr without multibyte anchoring elsif ($modifier =~ /g/oxms) { $sub = sprintf( # 1 2 3 4 5 6 7 8 9 1011 12 13 14 15 q, $local, # 1 $variable_basename, # 2 $variable, # 3 $variable_basename, # 4 ($delimiter1 eq "'") ? # 5 e_s1_q('m', $delimiter1, $end_delimiter1, $pattern, $modifier) : # : e_s1 ('m', $delimiter1, $end_delimiter1, $pattern, $modifier), # : $s_matched, # 6 $local, # 7 $variable_basename, # 8 $e_replacement, # 9 sprintf('%s_r=eval %s_r; ', $variable_basename, $variable_basename) x $e_modifier, # 10 $variable_basename, # 11 $variable_basename, # 12 $variable_basename, # 13 $variable_basename, # 14 $variable_basename, # 15 ); } # s///r else { my $prematch = q{$`}; $prematch = q{${1}}; $sub = sprintf( # 1 2 3 4 5 6 7 8 9 10 q<(%s =~ %s) ? eval{%s local $^W=0; %s %s_r=%s; %s"%s%s_r$'" } : %s>, $variable, # 1 ($delimiter1 eq "'") ? # 2 e_s1_q('m', $delimiter1, $end_delimiter1, $pattern, $modifier) : # : e_s1 ('m', $delimiter1, $end_delimiter1, $pattern, $modifier), # : $s_matched, # 3 $local, # 4 $variable_basename, # 5 $e_replacement, # 6 sprintf('%s_r=eval %s_r; ', $variable_basename, $variable_basename) x $e_modifier, # 7 $prematch, # 8 $variable_basename, # 9 $variable, # 10 ); } # $var !~ s///r doesn't make sense if ($bind_operator =~ / !~ /oxms) { $sub = q{die("$0: Using !~ with s///r doesn't make sense"), } . $sub; } } # without /r else { if (0) { } # s///g with multibyte anchoring elsif ($modifier =~ /g/oxms) { $sub = sprintf( # 1 2 3 4 5 6 7 8 9 10 1112 13 14 15 16 17 18 19 20 21 2223 q, $local, # 1 $variable_basename, # 2 $local, # 3 $variable_basename, # 4 $variable, # 5 ($delimiter1 eq "'") ? # 6 e_s1_q('m', $delimiter1, $end_delimiter1, $pattern, $modifier) : # : e_s1 ('m', $delimiter1, $end_delimiter1, $pattern, $modifier), # : $s_matched, # 7 $local, # 8 $variable_basename, # 9 $e_replacement, # 10 sprintf('%s_r=eval %s_r; ', $variable_basename, $variable_basename) x $e_modifier, # 11 $variable, # 12 $variable_basename, # 13 $variable_basename, # 14 $variable, # 15 $variable_basename, # 16 $variable_basename, # 17 $variable_basename, # 18 $variable, # 19 $variable, # 20 $variable_basename, # 21 # Binary "!~" is just like "=~" except the return value is negated in the logical sense. # It returns false if the match succeeds, and true if it fails. # (and so on) ($bind_operator =~ / !~ /oxms) ? '!' : '', # 22 $variable_basename, # 23 ); } # s///g without multibyte anchoring elsif ($modifier =~ /g/oxms) { $sub = sprintf( # 1 2 3 4 5 6 7 8 9 10 11 12 13 14 1516 q, $local, # 1 $variable_basename, # 2 $variable, # 3 ($delimiter1 eq "'") ? # 4 e_s1_q('m', $delimiter1, $end_delimiter1, $pattern, $modifier) : # : e_s1 ('m', $delimiter1, $end_delimiter1, $pattern, $modifier), # : $s_matched, # 5 $local, # 6 $variable_basename, # 7 $e_replacement, # 8 sprintf('%s_r=eval %s_r; ', $variable_basename, $variable_basename) x $e_modifier, # 9 $variable, # 10 $variable_basename, # 11 $variable, # 12 $variable_basename, # 13 $variable_basename, # 14 ($bind_operator =~ / !~ /oxms) ? '!' : '', # 15 $variable_basename, # 16 ); } # s/// else { my $prematch = q{$`}; $prematch = q{${1}}; $sub = sprintf( ($bind_operator =~ / =~ /oxms) ? # 1 2 3 4 5 6 7 8 9 1011 q<(%s%s%s) ? eval{%s local $^W=0; %s %s_r=%s; %s%s="%s%s_r$'"; 1 } : undef> : # 1 2 3 4 5 6 7 8 9 1011 q<(%s%s%s) ? 1 : eval{%s local $^W=0; %s %s_r=%s; %s%s="%s%s_r$'"; undef }>, $variable, # 1 $bind_operator, # 2 ($delimiter1 eq "'") ? # 3 e_s1_q('m', $delimiter1, $end_delimiter1, $pattern, $modifier) : # : e_s1 ('m', $delimiter1, $end_delimiter1, $pattern, $modifier), # : $s_matched, # 4 $local, # 5 $variable_basename, # 6 $e_replacement, # 7 sprintf('%s_r=eval %s_r; ', $variable_basename, $variable_basename) x $e_modifier, # 8 $variable, # 9 $prematch, # 10 $variable_basename, # 11 ); } } # (my $foo = $bar) =~ s/// --> (my $foo = $bar, eval { ... })[1] if ($my ne '') { $sub = "($my, $sub)[1]"; } # clear s/// variable $sub_variable = ''; $bind_operator = ''; return $sub; } # # escape chdir (q//, '') # sub e_chdir_q { my($ope,$delimiter,$end_delimiter,$string) = @_; if ($^W) { if (Esjis::_MSWin32_5Cended_path($string)) { if ($] !~ /^5\.005/) { warn < "\u\L" if (($char[$i] eq '\L') and ($char[$i+1] eq '\u')) { @char[$i,$i+1] = @char[$i+1,$i]; } # "\U\l" --> "\l\U" elsif (($char[$i] eq '\U') and ($char[$i+1] eq '\l')) { @char[$i,$i+1] = @char[$i+1,$i]; } # octal escape sequence elsif ($char[$i] =~ /\A \\o \{ ([0-7]+) \} \z/oxms) { $char[$i] = Esjis::octchr($1); } # hexadecimal escape sequence elsif ($char[$i] =~ /\A \\x \{ ([0-9A-Fa-f]+) \} \z/oxms) { $char[$i] = Esjis::hexchr($1); } # \N{CHARNAME} --> N\{CHARNAME} elsif ($char[$i] =~ /\A \\ (N) ( \{ ([^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]*) \} ) \z/oxms) { $char[$i] = $1 . '\\' . $2; } # \p{PROPERTY} --> p\{PROPERTY} elsif ($char[$i] =~ /\A \\ (p) ( \{ ([^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]*) \} ) \z/oxms) { $char[$i] = $1 . '\\' . $2; } # \P{PROPERTY} --> P\{PROPERTY} elsif ($char[$i] =~ /\A \\ (P) ( \{ ([^\x81-\x9F\xE0-\xFC0-9\}][^\x81-\x9F\xE0-\xFC\}]*) \} ) \z/oxms) { $char[$i] = $1 . '\\' . $2; } # \p, \P, \X --> p, P, X elsif ($char[$i] =~ /\A \\ ( [pPX] ) \z/oxms) { $char[$i] = $1; } if (0) { } # escape last octet of multiple-octet elsif ($char[$i] =~ /\A \\? ([\x80-\xFF].*) ($metachar|\Q$delimiter\E|\Q$end_delimiter\E) \z/xms) { $char[$i] = $1 . '\\' . $2; } # join separated multiple-octet elsif ($char[$i] =~ /\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms) { if ( ($i+3 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+3]) == 3) and (eval(sprintf '"%s%s%s%s"', @char[$i..$i+3]) =~ /\A $q_char \z/oxms)) { $char[$i] .= join '', splice @char, $i+1, 3; } elsif (($i+2 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+2]) == 2) and (eval(sprintf '"%s%s%s"', @char[$i..$i+2]) =~ /\A $q_char \z/oxms)) { $char[$i] .= join '', splice @char, $i+1, 2; } elsif (($i+1 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, $char[$i+1 ]) == 1) and (eval(sprintf '"%s%s"', @char[$i..$i+1]) =~ /\A $q_char \z/oxms)) { $char[$i] .= join '', splice @char, $i+1, 1; } } # open character class [...] elsif ($char[$i] eq '[') { my $left = $i; if ($char[$i+1] eq ']') { $i++; } while (1) { if (++$i > $#char) { die __FILE__, ": Unmatched [] in regexp"; } if ($char[$i] eq ']') { my $right = $i; # [...] if (grep(/\A [\$\@]/oxms,@char[$left+1..$right-1]) >= 1) { splice @char, $left, $right-$left+1, sprintf(q{@{[Esjis::charlist_qr(%s,'%s')]}}, join(',', map {qq_stuff($delimiter,$end_delimiter,$_)} @char[$left+1..$right-1]), $modifier); } else { splice @char, $left, $right-$left+1, Esjis::charlist_qr(@char[$left+1..$right-1], $modifier); } $i = $left; last; } } } # open character class [^...] elsif ($char[$i] eq '[^') { my $left = $i; if ($char[$i+1] eq ']') { $i++; } while (1) { if (++$i > $#char) { die __FILE__, ": Unmatched [] in regexp"; } if ($char[$i] eq ']') { my $right = $i; # [^...] if (grep(/\A [\$\@]/oxms,@char[$left+1..$right-1]) >= 1) { splice @char, $left, $right-$left+1, sprintf(q{@{[Esjis::charlist_not_qr(%s,'%s')]}}, join(',', map {qq_stuff($delimiter,$end_delimiter,$_)} @char[$left+1..$right-1]), $modifier); } else { splice @char, $left, $right-$left+1, Esjis::charlist_not_qr(@char[$left+1..$right-1], $modifier); } $i = $left; last; } } } # rewrite character class or escape character elsif (my $char = character_class($char[$i],$modifier)) { $char[$i] = $char; } # P.794 29.2.161. split # in Chapter 29: Functions # of ISBN 0-596-00027-8 Programming Perl Third Edition. # P.951 split # in Chapter 27: Functions # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. # said "The //m modifier is assumed when you split on the pattern /^/", # but perl5.008 is not so. Therefore, this software adds //m. # (and so on) # split(m/^/) --> split(m/^/m) elsif (($char[$i] eq '^') and ($modifier !~ /m/oxms)) { $modifier .= 'm'; } # /i modifier elsif ($ignorecase and ($char[$i] =~ /\A [\x00-\xFF] \z/oxms) and (Esjis::uc($char[$i]) ne Esjis::fc($char[$i]))) { if (CORE::length(Esjis::fc($char[$i])) == 1) { $char[$i] = '[' . Esjis::uc($char[$i]) . Esjis::fc($char[$i]) . ']'; } else { $char[$i] = '(?:' . Esjis::uc($char[$i]) . '|' . Esjis::fc($char[$i]) . ')'; } } # \u \l \U \L \F \Q \E elsif ($char[$i] =~ /\A ([<>]) \z/oxms) { if ($right_e < $left_e) { $char[$i] = '\\' . $char[$i]; } } elsif ($char[$i] eq '\u') { $char[$i] = '@{[Esjis::ucfirst qq<'; $left_e++; } elsif ($char[$i] eq '\l') { $char[$i] = '@{[Esjis::lcfirst qq<'; $left_e++; } elsif ($char[$i] eq '\U') { $char[$i] = '@{[Esjis::uc qq<'; $left_e++; } elsif ($char[$i] eq '\L') { $char[$i] = '@{[Esjis::lc qq<'; $left_e++; } elsif ($char[$i] eq '\F') { $char[$i] = '@{[Esjis::fc qq<'; $left_e++; } elsif ($char[$i] eq '\Q') { $char[$i] = '@{[CORE::quotemeta qq<'; $left_e++; } elsif ($char[$i] eq '\E') { if ($right_e < $left_e) { $char[$i] = '>]}'; $right_e++; } else { $char[$i] = ''; } } elsif ($char[$i] eq '\Q') { while (1) { if (++$i > $#char) { last; } if ($char[$i] eq '\E') { last; } } } elsif ($char[$i] eq '\E') { } # $0 --> $0 elsif ($char[$i] =~ /\A \$ 0 \z/oxms) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } elsif ($char[$i] =~ /\A \$ \{ \s* 0 \s* \} \z/oxms) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $$ --> $$ elsif ($char[$i] =~ /\A \$\$ \z/oxms) { } # $1, $2, $3 --> $2, $3, $4 (only when multibyte anchoring is enable) elsif ($char[$i] =~ /\A \$ ([1-9][0-9]*) \z/oxms) { $char[$i] = e_capture($1); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } elsif ($char[$i] =~ /\A \$ \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) { $char[$i] = e_capture($1); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $$foo[ ... ] --> $ $foo->[ ... ] elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \[ (?:$qq_bracket)*? \] ) \z/oxms) { $char[$i] = e_capture($1.'->'.$2); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $$foo{ ... } --> $ $foo->{ ... } elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ (?:$qq_brace)*? \} ) \z/oxms) { $char[$i] = e_capture($1.'->'.$2); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $$foo elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) \z/oxms) { $char[$i] = e_capture($1); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> Esjis::PREMATCH() elsif ($char[$i] =~ /\A ( \$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) \z/oxmsgc) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(Esjis::PREMATCH())]}'; } else { $char[$i] = '@{[Esjis::PREMATCH()]}'; } } # $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Esjis::MATCH() elsif ($char[$i] =~ /\A ( \$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) \z/oxmsgc) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(Esjis::MATCH())]}'; } else { $char[$i] = '@{[Esjis::MATCH()]}'; } } # $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Esjis::POSTMATCH() elsif ($char[$i] =~ /\A ( \$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) \z/oxmsgc) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(Esjis::POSTMATCH())]}'; } else { $char[$i] = '@{[Esjis::POSTMATCH()]}'; } } # ${ foo } elsif ($char[$i] =~ /\A \$ \s* \{ ( \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* ) \} \z/oxms) { if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $1 . ')]}'; } } # ${ ... } elsif ($char[$i] =~ /\A \$ \s* \{ \s* ( .+ ) \s* \} \z/oxms) { $char[$i] = e_capture($1); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # $scalar or @array elsif ($char[$i] =~ /\A [\$\@].+ /oxms) { $char[$i] = e_string($char[$i]); if ($ignorecase) { $char[$i] = '@{[Esjis::ignorecase(' . $char[$i] . ')]}'; } } # quote character before ? + * { elsif (($i >= 1) and ($char[$i] =~ /\A [\?\+\*\{] \z/oxms)) { if ($char[$i-1] =~ /\A (?:[\x00-\xFF]|\\[0-7]{2,3}|\\x[0-9-A-Fa-f]{1,2}) \z/oxms) { } else { $char[$i-1] = '(?:' . $char[$i-1] . ')'; } } } # make regexp string $modifier =~ tr/i//d; if ($left_e > $right_e) { return join '', 'Esjis::split', $ope, $delimiter, @char, '>]}' x ($left_e - $right_e), $end_delimiter, $modifier; } return join '', 'Esjis::split', $ope, $delimiter, @char, $end_delimiter, $modifier; } # # escape regexp of split qr'' # sub e_split_q { my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_; $modifier ||= ''; $modifier =~ tr/p//d; if ($modifier =~ /([adlu])/oxms) { my $line = 0; for (my $i=0; my($package,$filename,$use_line,$subroutine) = caller($i); $i++) { if ($filename ne __FILE__) { $line = $use_line + (CORE::substr($_,0,pos($_)) =~ tr/\n//) + 1; last; } } die qq{Unsupported modifier "$1" used at line $line.\n}; } $slash = 'div'; # /b /B modifier if ($modifier =~ tr/bB//d) { return join '', 'split', $ope, $delimiter, $string, $end_delimiter, $modifier; } my $ignorecase = ($modifier =~ /i/oxms) ? 1 : 0; # split regexp my @char = $string =~ /\G( \[\:\^ [a-z]+ \:\] | \[\: [a-z]+ \:\] | \[\^ | \\? (?:$q_char) )/oxmsg; # unescape character for (my $i=0; $i <= $#char; $i++) { if (0) { } # escape last octet of multiple-octet elsif ($char[$i] =~ /\A ([\x80-\xFF].*) ([\\|\[\{\^]|\Q$delimiter\E|\Q$end_delimiter\E) \z/xms) { $char[$i] = $1 . '\\' . $2; } # open character class [...] elsif ($char[$i] eq '[') { my $left = $i; if ($char[$i+1] eq ']') { $i++; } while (1) { if (++$i > $#char) { die __FILE__, ": Unmatched [] in regexp"; } if ($char[$i] eq ']') { my $right = $i; # [...] splice @char, $left, $right-$left+1, Esjis::charlist_qr(@char[$left+1..$right-1], $modifier); $i = $left; last; } } } # open character class [^...] elsif ($char[$i] eq '[^') { my $left = $i; if ($char[$i+1] eq ']') { $i++; } while (1) { if (++$i > $#char) { die __FILE__, ": Unmatched [] in regexp"; } if ($char[$i] eq ']') { my $right = $i; # [^...] splice @char, $left, $right-$left+1, Esjis::charlist_not_qr(@char[$left+1..$right-1], $modifier); $i = $left; last; } } } # rewrite character class or escape character elsif (my $char = character_class($char[$i],$modifier)) { $char[$i] = $char; } # split(m/^/) --> split(m/^/m) elsif (($char[$i] eq '^') and ($modifier !~ /m/oxms)) { $modifier .= 'm'; } # /i modifier elsif ($ignorecase and ($char[$i] =~ /\A [\x00-\xFF] \z/oxms) and (Esjis::uc($char[$i]) ne Esjis::fc($char[$i]))) { if (CORE::length(Esjis::fc($char[$i])) == 1) { $char[$i] = '[' . Esjis::uc($char[$i]) . Esjis::fc($char[$i]) . ']'; } else { $char[$i] = '(?:' . Esjis::uc($char[$i]) . '|' . Esjis::fc($char[$i]) . ')'; } } # quote character before ? + * { elsif (($i >= 1) and ($char[$i] =~ /\A [\?\+\*\{] \z/oxms)) { if ($char[$i-1] =~ /\A [\x00-\xFF] \z/oxms) { } else { $char[$i-1] = '(?:' . $char[$i-1] . ')'; } } } $modifier =~ tr/i//d; return join '', 'Esjis::split', $ope, $delimiter, @char, $end_delimiter, $modifier; } # # escape use without import # sub e_use_noimport { my($module) = @_; my $expr = _pathof($module); my $fh = gensym(); for my $realfilename (_realfilename($expr)) { if (Esjis::_open_r($fh, $realfilename)) { local $/ = undef; # slurp mode my $script = <$fh>; close($fh) or die __FILE__, ": Can't close file: $realfilename"; if ($script =~ /^ \s* use \s+ Sjis \s* ([^\x81-\x9F\xE0-\xFC;]*) ; \s* \n? $/oxms) { return qq; } last; } } return qq; } # # escape no without unimport # sub e_no_nounimport { my($module) = @_; my $expr = _pathof($module); my $fh = gensym(); for my $realfilename (_realfilename($expr)) { if (Esjis::_open_r($fh, $realfilename)) { local $/ = undef; # slurp mode my $script = <$fh>; close($fh) or die __FILE__, ": Can't close file: $realfilename"; if ($script =~ /^ \s* use \s+ Sjis \s* ([^\x81-\x9F\xE0-\xFC;]*) ; \s* \n? $/oxms) { return qq; } last; } } return qq; } # # escape use with import no parameter # sub e_use_noparam { my($module) = @_; my $expr = _pathof($module); my $fh = gensym(); for my $realfilename (_realfilename($expr)) { if (Esjis::_open_r($fh, $realfilename)) { local $/ = undef; # slurp mode my $script = <$fh>; close($fh) or die __FILE__, ": Can't close file: $realfilename"; if ($script =~ /^ \s* use \s+ Sjis \s* ([^\x81-\x9F\xE0-\xFC;]*) ; \s* \n? $/oxms) { # P.326 UNIVERSAL: The Ultimate Ancestor Class # in Chapter 12: Objects # of ISBN 0-596-00027-8 Programming Perl Third Edition. # P.435 UNIVERSAL: The Ultimate Ancestor Class # in Chapter 12: Objects # of ISBN 978-0-596-00492-7 Programming Perl 4th Edition. # (and so on) return qq[BEGIN { Esjis::require '$expr'; $module->import() if $module->can('import'); }]; } last; } } return qq; } # # escape no with unimport no parameter # sub e_no_noparam { my($module) = @_; my $expr = _pathof($module); my $fh = gensym(); for my $realfilename (_realfilename($expr)) { if (Esjis::_open_r($fh, $realfilename)) { local $/ = undef; # slurp mode my $script = <$fh>; close($fh) or die __FILE__, ": Can't close file: $realfilename"; if ($script =~ /^ \s* use \s+ Sjis \s* ([^\x81-\x9F\xE0-\xFC;]*) ; \s* \n? $/oxms) { return qq[BEGIN { Esjis::require '$expr'; $module->unimport() if $module->can('unimport'); }]; } last; } } return qq; } # # escape use with import parameters # sub e_use { my($module,$list) = @_; my $expr = _pathof($module); my $fh = gensym(); for my $realfilename (_realfilename($expr)) { if (Esjis::_open_r($fh, $realfilename)) { local $/ = undef; # slurp mode my $script = <$fh>; close($fh) or die __FILE__, ": Can't close file: $realfilename"; if ($script =~ /^ \s* use \s+ Sjis \s* ([^\x81-\x9F\xE0-\xFC;]*) ; \s* \n? $/oxms) { return qq[BEGIN { Esjis::require '$expr'; $module->import($list) if $module->can('import'); }]; } last; } } return qq; } # # escape no with unimport parameters # sub e_no { my($module,$list) = @_; my $expr = _pathof($module); my $fh = gensym(); for my $realfilename (_realfilename($expr)) { if (Esjis::_open_r($fh, $realfilename)) { local $/ = undef; # slurp mode my $script = <$fh>; close($fh) or die __FILE__, ": Can't close file: $realfilename"; if ($script =~ /^ \s* use \s+ Sjis \s* ([^\x81-\x9F\xE0-\xFC;]*) ; \s* \n? $/oxms) { return qq[BEGIN { Esjis::require '$expr'; $module->unimport($list) if $module->can('unimport'); }]; } last; } } return qq; } # # file path of module # sub _pathof { my($expr) = @_; if ($^O eq 'MacOS') { $expr =~ s#::#:#g; } else { $expr =~ s#::#/#g; } $expr .= '.pm' if $expr !~ / \.pm \z/oxmsi; return $expr; } # # real file name of module # sub _realfilename { my($expr) = @_; if ($^O eq 'MacOS') { return map {"$_$expr"} @INC; } else { return map {"$_/$expr"} @INC; } } 1; __END__ =pod =head1 NAME Sjis - Source code filter to escape ShiftJIS script =head1 Install and Usage There are two steps there: =over 2 =item * You'll have to download Sjis.pm and Esjis.pm and put it in your perl lib directory. =item * You'll need to write "use Sjis;" at head of the script. =back =head1 SYNOPSIS use Sjis; use Sjis ver.sion; --- require minimum version use Sjis ver.sion.0; --- expects version (match or die) use Sjis qw(ord reverse getc); --- demand enhanced feature of ord, reverse, and getc use Sjis ver.sion qw(ord reverse getc); use Sjis ver.sion.0 qw(ord reverse getc); # "no Sjis;" not supported or $ perl Sjis.pm ShiftJIS_script.pl > Escaped_script.pl.e then $ perl Escaped_script.pl.e ShiftJIS_script.pl --- script written in ShiftJIS Escaped_script.pl.e --- escaped script functions: Sjis::ord(...); Sjis::reverse(...); Sjis::getc(...); Sjis::length(...); Sjis::substr(...); Sjis::index(...); Sjis::rindex(...); <*> glob(...); CORE::chop(...); CORE::ord(...); CORE::reverse(...); CORE::getc(...); CORE::index(...); CORE::rindex(...); emulate Perl5.6 on perl5.00503 use warnings; use warnings::register; emulate Perl5.16 use feature qw(fc); dummy functions: utf8::upgrade(...); utf8::downgrade(...); utf8::encode(...); utf8::decode(...); utf8::is_utf8(...); utf8::valid(...); bytes::chr(...); bytes::index(...); bytes::length(...); bytes::ord(...); bytes::rindex(...); bytes::substr(...); =head1 ABSTRACT Sjis software is "middleware" between perl interpreter and your Perl script written by ShiftJIS. Perl is optimized for problems which are about 90% working with text and about 10% everything else. But this "text" means US-ASCII text, and popular ShiftJIS is contained in "everything else." Please be not disappointed. The string of Perl3 or later can treat binary data. That is, the string of Perl3 or later can treat ShiftJIS. Perl is designed to make the easy jobs easy, without making the hard jobs impossible. Sjis software is Perl program designed to make the "easy jobs easy". By "use Sjis;", it automatically interpret your script as ShiftJIS. The various functions of perl including a regular expression can treat ShiftJIS now. The function length treats length per byte. This software does not use UTF8 flag. =head1 Yet Another Future Of JPerl is very useful software. -- Oops, note, this "JPerl" means "Japanized Perl" or "Japanese Perl". Therefore, it is unrelated to JPerl of the following. JPerl is an implementation of Perl written in Java. http://www.javainc.com/projects/jperl/ jPerl - Perl on the JVM http://www.dzone.com/links/175948.html Jamie's PERL scripts for bioinformatics http://code.google.com/p/jperl/ jperl (Jonathan Perl) https://github.com/jperl Now, the last version of JPerl is 5.005_04 and is not maintained now. Japanization modifier WATANABE Hirofumi said, "Because WATANABE am tired I give over maintaing JPerl." at Slide #15: "The future of JPerl" of L in The Perl Confernce Japan 1998. When I heard it, I thought that someone excluding me would maintain JPerl. And I slept every night hanging a sock. Night and day, I kept having hope. After 10 years, I noticed that white beard exists in the sock :-) This software is a source code filter to escape Perl script encoded by ShiftJIS given from STDIN or command line parameter. The character code is never converted by escaping the script. Neither the value of the character nor the length of the character string change even if it escapes. I learned the following things from the successful software. =over 2 =item * Upper Compatibility like Perl4 to Perl5 =item * Maximum Portability like jcode.pl =item * Handles Raw ShiftJIS, Doesn't use UTF8 flag like JPerl =item * Remains One Interpreter like Encode module =item * Code Set Independent like Ruby =item * There's more than one way to do it like Perl itself =back I am excited about this software and its future --- I hope you are too. =head1 JRE: JPerl Runtime Environment +---------------------------------------+ | JPerl Application Script | Your Script +---------------------------------------+ | Source Code Filter, Runtime Routine | ex. Sjis.pm, Esjis.pm +---------------------------------------+ | PVM 5.00503 or later | ex. perl 5.00503 +---------------------------------------+ A Perl Virtual Machine (PVM) enables a set of computer software programs and data structures to use a virtual machine model for the execution of other computer programs and scripts. The model used by a PVM accepts a form of computer intermediate language commonly referred to as Perl byteorientedcode. This language conceptually represents the instruction set of a byte-oriented, capability architecture. =head1 Basic Idea of Source Code Filter I discovered this mail again recently. [Tokyo.pm] jus Benkyoukai http://mail.pm.org/pipermail/tokyo-pm/1999-September/001854.html save as: SJIS.pm package SJIS; use Filter::Util::Call; sub multibyte_filter { my $status; if (($status = filter_read()) > 0 ) { s/([\x81-\x9f\xe0-\xef])([\x40-\x7e\x80-\xfc])/ sprintf("\\x%02x\\x%02x",ord($1),ord($2)) /eg; } $status; } sub import { filter_add(\&multibyte_filter); } 1; I am glad that I could confirm my idea is not so wrong. =head1 Command-line Wildcard Expansion on DOS-like Systems The default command shells on DOS-like systems (COMMAND.COM or cmd.exe) do not expand wildcard arguments supplied to programs. Instead, import of Esjis.pm works well. in Esjis.pm # # @ARGV wildcard globbing # sub import { if ($^O =~ /\A (?: MSWin32 | NetWare | symbian | dos ) \z/oxms) { my @argv = (); for (@ARGV) { # has space if (/\A (?:$q_char)*? [ ] /oxms) { if (my @glob = Esjis::glob(qq{"$_"})) { push @argv, @glob; } else { push @argv, $_; } } # has wildcard metachar elsif (/\A (?:$q_char)*? [*?] /oxms) { if (my @glob = Esjis::glob($_)) { push @argv, @glob; } else { push @argv, $_; } } # no wildcard globbing else { push @argv, $_; } } @ARGV = @argv; } } =head1 Software Composition Sjis.pm --- source code filter to escape ShiftJIS Esjis.pm --- run-time routines for Sjis.pm perl5.bat --- find and run perl5 without %PATH% settings perl55.bat --- find and run perl5.5 without %PATH% settings perl56.bat --- find and run perl5.6 without %PATH% settings perl58.bat --- find and run perl5.8 without %PATH% settings perl510.bat --- find and run perl5.10 without %PATH% settings perl512.bat --- find and run perl5.12 without %PATH% settings perl514.bat --- find and run perl5.14 without %PATH% settings perl516.bat --- find and run perl5.16 without %PATH% settings perl64.bat --- find and run perl64 without %PATH% settings perl64512.bat --- find and run perl5.12 (x64) without %PATH% settings perl64514.bat --- find and run perl5.14 (x64) without %PATH% settings perl64516.bat --- find and run perl5.16 (x64) without %PATH% settings aperl58.bat --- find and run ActivePerl 5.8 without %PATH% settings aperl510.bat --- find and run ActivePerl 5.10 without %PATH% settings aperl512.bat --- find and run ActivePerl 5.12 without %PATH% settings aperl514.bat --- find and run ActivePerl 5.14 without %PATH% settings aperl516.bat --- find and run ActivePerl 5.16 without %PATH% settings aperl64512.bat --- find and run ActivePerl 5.12 (x64) without %PATH% settings aperl64514.bat --- find and run ActivePerl 5.14 (x64) without %PATH% settings aperl64516.bat --- find and run ActivePerl 5.16 (x64) without %PATH% settings sperl58.bat --- find and run Strawberry Perl 5.8 without %PATH% settings sperl510.bat --- find and run Strawberry Perl 5.10 without %PATH% settings sperl512.bat --- find and run Strawberry Perl 5.12 without %PATH% settings sperl514.bat --- find and run Strawberry Perl 5.14 without %PATH% settings sperl516.bat --- find and run Strawberry Perl 5.16 without %PATH% settings sperl64512.bat --- find and run Strawberry Perl 5.12 (x64) without %PATH% settings sperl64514.bat --- find and run Strawberry Perl 5.14 (x64) without %PATH% settings sperl64516.bat --- find and run Strawberry Perl 5.16 (x64) without %PATH% settings strict.pm_ --- dummy strict.pm warnings.pm_ --- poor warnings.pm warnings/register.pm_ --- poor warnings/register.pm feature.pm_ --- dummy feature.pm =head1 Upper Compatibility by Escaping This software adds the function by 'Escaping' it always, and nothing of the past is broken. Therefore, 'Possible job' never becomes 'Impossible job'. This approach is effective in the field where the retreat is never permitted. Modern Perl/perl can not always solve the problem. Often, it means an incompatible upgrade part to traditional Perl should be rewound. =head1 Escaping Your Script (You do) You need write 'use Sjis;' in your script. --------------------------------- Before You do --------------------------------- (nothing) use Sjis; --------------------------------- =head1 Escaping Multiple-Octet Code (Sjis.pm provides) Insert chr(0x5c) before @ [ \ ] ^ ` { | and } in multiple-octet of =over 2 =item * string in single quote ('', q{}, <<'END' and qw{}) =item * string in double quote ("", qq{}, < m<...`/\...> -------------------------------------------------------------------------------- =head1 Multiple-Octet Character Regular Expression (Sjis.pm provides) Sjis.pm clusters multiple-octet character with quantifier, makes cluster from multiple-octet custom character classes. And makes multiple-octet version metasymbol from classic Perl character class shortcuts and POSIX-style character classes. -------------------------------------------------------------------------------- Before After -------------------------------------------------------------------------------- m/...MULTIOCT+.../ m/...(?:MULTIOCT)+.../ m/...[AN-EM].../ m/...(?:A[N-Z]|[B-D][A-Z]|E[A-M]).../ m/...\D.../ m/...(?:${Esjis::eD}).../ m/...[[:^digit:]].../ m/...(?:${Esjis::not_digit}).../ -------------------------------------------------------------------------------- =head1 Calling 'Esjis::ignorecase()' (Sjis.pm provides) Sjis.pm applies calling 'Esjis::ignorecase()' instead of /i modifier. -------------------------------------------------------------------------------- Before After -------------------------------------------------------------------------------- m/...$var.../i m/...@{[Esjis::ignorecase($var)]}.../ -------------------------------------------------------------------------------- =head1 Character-Oriented Regular Expression Regular expression works as character-oriented that has no /b modifier. -------------------------------------------------------------------------------- Before After -------------------------------------------------------------------------------- /regexp/ /ditto$Esjis::matched/ m/regexp/ m/ditto$Esjis::matched/ ?regexp? m?ditto$Esjis::matched? m?regexp? m?ditto$Esjis::matched? $_ =~ ($_ =~ m/ditto$Esjis::matched/) ? s/regexp/replacement/ eval{ Esjis::s_matched(); local $^W=0; my $__r=qq/replacement/; $_="${1}$__r$'"; 1 } : undef $_ !~ ($_ !~ m/ditto$Esjis::matched/) ? s/regexp/replacement/ 1 : eval{ Esjis::s_matched(); local $^W=0; my $__r=qq/replacement/; $_="${1}$__r$'"; undef } split(/regexp/) Esjis::split(qr/regexp/) split(m/regexp/) Esjis::split(qr/regexp/) split(qr/regexp/) Esjis::split(qr/regexp/) qr/regexp/ qr/ditto$Esjis::matched/ -------------------------------------------------------------------------------- =head1 Byte-Oriented Regular Expression Regular expression works as byte-oriented that has /b modifier. -------------------------------------------------------------------------------- Before After -------------------------------------------------------------------------------- /regexp/b /(?:regexp)$Esjis::matched/ m/regexp/b m/(?:regexp)$Esjis::matched/ ?regexp?b m?regexp$Esjis::matched? m?regexp?b m?regexp$Esjis::matched? $_ =~ ($_ =~ m/(\G[\x00-\xFF]*?)(?:regexp)$Esjis::matched/) ? s/regexp/replacement/b eval{ Esjis::s_matched(); local $^W=0; my $__r=qq/replacement/; $_="${1}$__r$'"; 1 } : undef $_ !~ ($_ !~ m/(\G[\x00-\xFF]*?)(?:regexp)$Esjis::matched/) ? s/regexp/replacement/b 1 : eval{ Esjis::s_matched(); local $^W=0; my $__r=qq/replacement/; $_="${1}$__r$'"; undef } split(/regexp/b) split(qr/regexp/) split(m/regexp/b) split(qr/regexp/) split(qr/regexp/b) split(qr/regexp/) qr/regexp/b qr/(?:regexp)$Esjis::matched/ -------------------------------------------------------------------------------- =head1 Escaping Character Classes (Esjis.pm provides) The character classes are redefined as follows to backward compatibility. --------------------------------------------------------------- Before After --------------------------------------------------------------- . ${Esjis::dot} ${Esjis::dot_s} (/s modifier) \d [0-9] \s [\x09\x0A\x0C\x0D\x20] \w [0-9A-Z_a-z] \D ${Esjis::eD} \S ${Esjis::eS} \W ${Esjis::eW} \h [\x09\x20] \v [\x0A\x0B\x0C\x0D] \H ${Esjis::eH} \V ${Esjis::eV} \C [\x00-\xFF] \X X (so, just 'X') \R ${Esjis::eR} \N ${Esjis::eN} --------------------------------------------------------------- Also POSIX-style character classes. --------------------------------------------------------------- Before After --------------------------------------------------------------- [:alnum:] [\x30-\x39\x41-\x5A\x61-\x7A] [:alpha:] [\x41-\x5A\x61-\x7A] [:ascii:] [\x00-\x7F] [:blank:] [\x09\x20] [:cntrl:] [\x00-\x1F\x7F] [:digit:] [\x30-\x39] [:graph:] [\x21-\x7F] [:lower:] [\x61-\x7A] [\x41-\x5A\x61-\x7A] (/i modifier) [:print:] [\x20-\x7F] [:punct:] [\x21-\x2F\x3A-\x3F\x40\x5B-\x5F\x60\x7B-\x7E] [:space:] [\x09\x0A\x0B\x0C\x0D\x20] [:upper:] [\x41-\x5A] [\x41-\x5A\x61-\x7A] (/i modifier) [:word:] [\x30-\x39\x41-\x5A\x5F\x61-\x7A] [:xdigit:] [\x30-\x39\x41-\x46\x61-\x66] [:^alnum:] ${Esjis::not_alnum} [:^alpha:] ${Esjis::not_alpha} [:^ascii:] ${Esjis::not_ascii} [:^blank:] ${Esjis::not_blank} [:^cntrl:] ${Esjis::not_cntrl} [:^digit:] ${Esjis::not_digit} [:^graph:] ${Esjis::not_graph} [:^lower:] ${Esjis::not_lower} ${Esjis::not_lower_i} (/i modifier) [:^print:] ${Esjis::not_print} [:^punct:] ${Esjis::not_punct} [:^space:] ${Esjis::not_space} [:^upper:] ${Esjis::not_upper} ${Esjis::not_upper_i} (/i modifier) [:^word:] ${Esjis::not_word} [:^xdigit:] ${Esjis::not_xdigit} --------------------------------------------------------------- Also \b and \B are redefined as follows to backward compatibility. --------------------------------------------------------------- Before After --------------------------------------------------------------- \b ${Esjis::eb} \B ${Esjis::eB} --------------------------------------------------------------- Definitions in Esjis.pm. --------------------------------------------------------------------------------------------------------------------------------------------------------- After Definition --------------------------------------------------------------------------------------------------------------------------------------------------------- ${Esjis::anchor} qr{\G(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC])*?} ${Esjis::dot} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x0A])} ${Esjis::dot_s} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC])} ${Esjis::eD} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC0-9])} ${Esjis::eS} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x09\x0A\x0C\x0D\x20])} ${Esjis::eW} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC0-9A-Z_a-z])} ${Esjis::eH} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x09\x20])} ${Esjis::eV} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x0A\x0B\x0C\x0D])} ${Esjis::eR} qr{(?:\x0D\x0A|[\x0A\x0D])} ${Esjis::eN} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x0A])} ${Esjis::not_alnum} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x30-\x39\x41-\x5A\x61-\x7A])} ${Esjis::not_alpha} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x41-\x5A\x61-\x7A])} ${Esjis::not_ascii} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x00-\x7F])} ${Esjis::not_blank} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x09\x20])} ${Esjis::not_cntrl} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x00-\x1F\x7F])} ${Esjis::not_digit} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x30-\x39])} ${Esjis::not_graph} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x21-\x7F])} ${Esjis::not_lower} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x61-\x7A])} ${Esjis::not_lower_i} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC])} ${Esjis::not_print} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x20-\x7F])} ${Esjis::not_punct} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x21-\x2F\x3A-\x3F\x40\x5B-\x5F\x60\x7B-\x7E])} ${Esjis::not_space} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x09\x0A\x0B\x0C\x0D\x20])} ${Esjis::not_upper} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x41-\x5A])} ${Esjis::not_upper_i} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC])} ${Esjis::not_word} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x30-\x39\x41-\x5A\x5F\x61-\x7A])} ${Esjis::not_xdigit} qr{(?:[\x81-\x9F\xE0-\xFC][\x00-\xFF]|[^\x81-\x9F\xE0-\xFC\x30-\x39\x41-\x46\x61-\x66])} ${Esjis::eb} qr{(?:\A(?=[0-9A-Z_a-z])|(?<=[\x00-\x2F\x40\x5B-\x5E\x60\x7B-\xFF])(?=[0-9A-Z_a-z])|(?<=[0-9A-Z_a-z])(?=[\x00-\x2F\x40\x5B-\x5E\x60\x7B-\xFF]|\z))} ${Esjis::eB} qr{(?:(?<=[0-9A-Z_a-z])(?=[0-9A-Z_a-z])|(?<=[\x00-\x2F\x40\x5B-\x5E\x60\x7B-\xFF])(?=[\x00-\x2F\x40\x5B-\x5E\x60\x7B-\xFF]))} --------------------------------------------------------------------------------------------------------------------------------------------------------- =head1 Un-Escaping \ of \N, \p, \P and \X (Sjis.pm provides) Sjis.pm removes '\' at head of alphanumeric regexp metasymbols \N, \p, \P and \X. By this method, you can avoid the trap of the abstraction. See also, Deprecate literal unescaped "{" in regexes. http://perl5.git.perl.org/perl.git/commit/2a53d3314d380af5ab5283758219417c6dfa36e9 ------------------------------------ Before After ------------------------------------ \N{CHARNAME} N\{CHARNAME} \p{L} p\{L} \p{^L} p\{^L} \p{\^L} p\{\^L} \pL pL \P{L} P\{L} \P{^L} P\{^L} \P{\^L} P\{\^L} \PL PL \X X ------------------------------------ =head1 Escaping Built-in Functions (Sjis.pm and Esjis.pm provide) Insert 'Esjis::' at head of function name. Esjis.pm provides your script Esjis::* functions. ------------------------------------------- Before After Works as ------------------------------------------- length length Byte substr substr Byte pos pos Byte split Esjis::split Character tr/// Esjis::tr Character tr///b tr/// Byte tr///B tr/// Byte y/// Esjis::tr Character y///b tr/// Byte y///B tr/// Byte chop Esjis::chop Character index Esjis::index Character rindex Esjis::rindex Character lc Esjis::lc Character lcfirst Esjis::lcfirst Character uc Esjis::uc Character ucfirst Esjis::ucfirst Character fc Esjis::fc Character chr Esjis::chr Character glob Esjis::glob Character lstat Esjis::lstat Character opendir Esjis::opendir Character stat Esjis::stat Character unlink Esjis::unlink Character chdir Esjis::chdir Character do Esjis::do Character require Esjis::require Character ------------------------------------------- ------------------------------------------------------------------------------------------------------------------------ Before After ------------------------------------------------------------------------------------------------------------------------ use Perl::Module; BEGIN { Esjis::require 'Perl/Module.pm'; Perl::Module->import() if Perl::Module->can('import'); } use Perl::Module @list; BEGIN { Esjis::require 'Perl/Module.pm'; Perl::Module->import(@list) if Perl::Module->can('import'); } use Perl::Module (); BEGIN { Esjis::require 'Perl/Module.pm'; } no Perl::Module; BEGIN { Esjis::require 'Perl/Module.pm'; Perl::Module->unimport() if Perl::Module->can('unimport'); } no Perl::Module @list; BEGIN { Esjis::require 'Perl/Module.pm'; Perl::Module->unimport(@list) if Perl::Module->can('unimport'); } no Perl::Module (); BEGIN { Esjis::require 'Perl/Module.pm'; } ------------------------------------------------------------------------------------------------------------------------ =head1 Escaping File Test Operators (Sjis.pm and Esjis.pm provide) Insert 'Esjis::' instead of '-' of operator. Available in MSWin32, MacOS, and UNIX-like systems -------------------------------------------------------------------------- Before After Meaning -------------------------------------------------------------------------- -r Esjis::r File or directory is readable by this (effective) user or group -w Esjis::w File or directory is writable by this (effective) user or group -e Esjis::e File or directory name exists -x Esjis::x File or directory is executable by this (effective) user or group -z Esjis::z File exists and has zero size (always false for directories) -f Esjis::f Entry is a plain file -d Esjis::d Entry is a directory -t -t The filehandle is a TTY (as reported by the isatty() system function; filenames can't be tested by this test) -T Esjis::T File looks like a "text" file -B Esjis::B File looks like a "binary" file -M Esjis::M Modification age (measured in days) -A Esjis::A Access age (measured in days) -C Esjis::C Inode-modification age (measured in days) -s Esjis::s File or directory exists and has nonzero size (the value is the size in bytes) -------------------------------------------------------------------------- Available in MacOS and UNIX-like systems -------------------------------------------------------------------------- Before After Meaning -------------------------------------------------------------------------- -R Esjis::R File or directory is readable by this real user or group -W Esjis::W File or directory is writable by this real user or group -X Esjis::X File or directory is executable by this real user or group -l Esjis::l Entry is a symbolic link -S Esjis::S Entry is a socket -------------------------------------------------------------------------- Not available in MSWin32 and MacOS -------------------------------------------------------------------------- Before After Meaning -------------------------------------------------------------------------- -o Esjis::o File or directory is owned by this (effective) user -O Esjis::O File or directory is owned by this real user -p Esjis::p Entry is a named pipe (a "fifo") -b Esjis::b Entry is a block-special file (like a mountable disk) -c Esjis::c Entry is a character-special file (like an I/O device) -u Esjis::u File or directory is setuid -g Esjis::g File or directory is setgid -k Esjis::k File or directory has the sticky bit set -------------------------------------------------------------------------- -w only inspects the read-only file attribute (FILE_ATTRIBUTE_READONLY), which determines whether the directory can be deleted, not whether it can be written to. Directories always have read and write access unless denied by discretionary access control lists (DACLs). (MSWin32) -R, -W, -X, -O are indistinguishable from -r, -w, -x, -o. (MSWin32) -g, -k, -l, -u, -A are not particularly meaningful. (MSWin32) -x (or -X) determine if a file ends in one of the executable suffixes. -S is meaningless. (MSWin32) As of Perl 5.00503, as a form of purely syntactic sugar, you can stack file test operators, in a way that -w -x $file is equivalent to -x $file && -w _ . if ( -w -r $file ) { print "The file is both readable and writable!\n"; } =head1 Escaping Function Name (You do) You need write 'Sjis::' at head of function name when you want character- oriented function. See 'Character-Oriented Functions'. -------------------------------------------------------- Function Character-Oriented Description -------------------------------------------------------- ord Sjis::ord reverse Sjis::reverse getc Sjis::getc length Sjis::length substr Sjis::substr index Sjis::index See 'About Indexes' rindex Sjis::rindex See 'About Rindexes' -------------------------------------------------------- About Indexes ------------------------------------------------------------------------- Function Works as Returns as Description ------------------------------------------------------------------------- index Character Byte JPerl semantics (most useful) (same as Esjis::index) Sjis::index Character Character Character-oriented semantics CORE::index Byte Byte Byte-oriented semantics (nothing) Byte Character (most useless) ------------------------------------------------------------------------- About Rindexes ------------------------------------------------------------------------- Function Works as Returns as Description ------------------------------------------------------------------------- rindex Character Byte JPerl semantics (most useful) (same as Esjis::rindex) Sjis::rindex Character Character Character-oriented semantics CORE::rindex Byte Byte Byte-oriented semantics (nothing) Byte Character (most useless) ------------------------------------------------------------------------- =head1 Character-Oriented Functions =over 2 =item * Ordinal Value of Character $ord = Sjis::ord($string); This function returns the numeric value (ASCII or ShiftJIS character) of the first character of $string, not Unicode. If $string is omitted, it uses $_. The return value is always unsigned. If you import ord "use Sjis qw(ord);", ord of your script will be rewritten in Sjis::ord. Sjis::ord is not compatible with ord of JPerl. Even if you do not know this function, there is no problem. This function can be created with a unpack function as before. =item * Reverse List or String @reverse = Sjis::reverse(@list); $reverse = Sjis::reverse(@list); In list context, this function returns a list value consisting of the elements of @list in the opposite order. In scalar context, the function concatenates all the elements of @list and then returns the reverse of that resulting string, character by character. If you import reverse "use Sjis qw(reverse);", reverse of your script will be rewritten in Sjis::reverse. Sjis::reverse is not compatible with reverse of JPerl. Even if you do not know this function, there is no problem. This function can be created with $rev = join('', reverse(split(//, $jstring))); as before. =item * Returns Next Character $getc = Sjis::getc(FILEHANDLE); $getc = Sjis::getc($filehandle); $getc = Sjis::getc; This function returns the next character from the input file attached to FILEHANDLE. It returns undef at end-of-file, or if an I/O error was encountered. If FILEHANDLE is omitted, the function reads from STDIN. This function is somewhat slow, but it's occasionally useful for single-character input from the keyboard -- provided you manage to get your keyboard input unbuffered. This function requests unbuffered input from the standard I/O library. Unfortunately, the standard I/O library is not so standard as to provide a portable way to tell the underlying operating system to supply unbuffered keyboard input to the standard I/O system. To do that, you have to be slightly more clever, and in an operating-system-dependent fashion. Under Unix you might say this: if ($BSD_STYLE) { system "stty cbreak /dev/tty 2>&1"; } else { system "stty", "-icanon", "eol", "\001"; } $key = Sjis::getc; if ($BSD_STYLE) { system "stty -cbreak /dev/tty 2>&1"; } else { system "stty", "icanon", "eol", "^@"; # ASCII NUL } print "\n"; This code puts the next character typed on the terminal in the string $key. If your stty program has options like cbreak, you'll need to use the code where $BSD_STYLE is true. Otherwise, you'll need to use the code where it is false. If you import getc "use Sjis qw(getc);", getc of your script will be rewritten in Sjis::getc. Sjis::getc is not compatible with getc of JPerl. Even if you do not know this function, there is no problem. This function can be created with CORE::getc as before. =item * Length by ShiftJIS Character $length = Sjis::length($string); $length = Sjis::length(); This function returns the length in characters (programmer-visible characters) of the scalar value $string. If $string is omitted, it returns the Sjis::length of $_. Do not try to use Sjis::length to find the size of an array or hash. Use scalar @array for the size of an array, and scalar keys %hash for the number of key/value pairs in a hash. (The scalar is typically omitted when redundant.) To find the length of a string in bytes rather than characters, say simply: $bytes = length($string); Even if you do not know this function, there is no problem. This function can be created with $len = split(//, $jstring); as before. =item * Substr by ShiftJIS Character $substr = Sjis::substr($string,$offset,$length,$replacement); $substr = Sjis::substr($string,$offset,$length); $substr = Sjis::substr($string,$offset); This function extracts a substring out of the string given by $string and returns it. The substring is extracted starting at $offset characters from the front of the string. If $offset is negative, the substring starts that far from the end of the string instead. If $length is omitted, everything to the end of the string is returned. If $length is negative, the length is calculated to leave that many characters off the end of the string. Otherwise, $length indicates the length of the substring to extract, which is sort of what you'd expect. For bytes, use the substr from built-in Perl functions. An alternative to using Sjis::substr as an lvalue is to specify the $replacement string as the fourth argument. This lets you replace parts of the $string and return what was there before in one operation, just as you can with splice. The next example also replaces the last character of $var with "Curly" and puts that replaced character into $oldstr: $oldstr = Sjis::substr($var, -1, 1, "Curly"); To prepend the string "Larry" to the current value of $var, use: Sjis::substr($var, 0, 0, "Larry"); To instead replace the first character of $var with "Moe", use: Sjis::substr($var, 0, 1, "Moe"); And, finally, to replace the last character of $var with "Curly", use: Sjis::substr($var, -1, 1, "Curly"); =item * Index by ShiftJIS Character $index = Sjis::index($string,$substring,$offset); $index = Sjis::index($string,$substring); This function searches for one string within another. It returns the character position of the first occurrence of $substring in $string. The $offset, if specified, says how many characters from the start to skip before beginning to look. Positions are based at 0. If the substring is not found, the function returns one less than the base, ordinarily -1. To work your way through a string, you might say: $pos = -1; while (($pos = Sjis::index($string, $lookfor, $pos)) > -1) { print "Found at $pos\n"; $pos++; } This function is realizable with a regular expression as before. There is no problem even if you do not know this function. =item * Rindex by ShiftJIS Character $rindex = Sjis::rindex($string,$substring,$offset); $rindex = Sjis::rindex($string,$substring); This function works just like Sjis::index except that it returns the character position of the last occurrence of $substring in $string (a reverse Sjis::index). The function returns -1 if $substring is not found. $offset, if specified, is the rightmost character position that may be returned. To work your way through a string backward, say: $pos = Sjis::length($string); while (($pos = Sjis::rindex($string, $lookfor, $pos)) >= 0) { print "Found at $pos\n"; $pos--; } This function is realizable with a regular expression as before. There is no problem even if you do not know this function. =item * Filename Globbing @glob = glob($expr); $glob = glob($expr); @glob = glob; $glob = glob; @glob = <*>; $glob = <*>; Performs filename expansion (globbing) on $expr, returning the next successive name on each call. If $expr is omitted, $_ is globbed instead. This operator is implemented via the Esjis::glob() function. See Esjis::glob of Esjis.pm for details. =back =head1 Byte-Oriented Functions =over 2 =item * Chop Byte String $byte = CORE::chop($string); $byte = CORE::chop(@list); $byte = CORE::chop; This function chops off the last byte of a string variable and returns the byte chopped. The CORE::chop operator is used primarily to remove the newline from the end of an input record, and is more efficient than using a substitution (s/\n$//). If that's all you're doing, then it would be safer to use chomp, since CORE::chop always shortens the string no matter what's there, and chomp is more selective. You cannot CORE::chop a literal, only a variable. If you CORE::chop a @list of variables, each string in the list is chopped: @lines = `cat myfile`; CORE::chop @lines; You can CORE::chop anything that is an lvalue, including an assignment: CORE::chop($cwd = `pwd`); CORE::chop($answer = ); This is different from: $answer = CORE::chop($temp = ); # WRONG which puts a newline into $answer because CORE::chop returns the byte chopped, not the remaining string (which is in $tmp). One way to get the result intended here is with substr: $answer = substr , 0, -1; But this is more commonly written as: CORE::chop($answer = ); In the most general case, CORE::chop can be expressed in terms of substr: $last_byte = CORE::chop($var); $last_byte = substr($var, -1, 1, ""); # same thing Once you understand this equivalence, you can use it to do bigger chops. To CORE::chop more than one byte, use substr as an lvalue, assigning a null string. The following removes the last five bytes of $caravan: substr($caravan, -5) = ""; The negative subscript causes substr to count from the end of the string instead of the beginning. If you wanted to save the bytes so removed, you could use the four-argument form of substr, creating something of a quintuple CORE::chop: $tail = substr($caravan, -5, 5, ""); If no argument is given, the function chops the $_ variable. =item * Ordinal Value of Byte $ord = CORE::ord($expr); This function returns the numeric value of the first byte of $expr, regardless of "use Sjis qw(ord);" exists or not. If $expr is omitted, it uses $_. The return value is always unsigned. If you want a signed value, use unpack('c',$expr). If you want all the bytes of the string converted to a list of numbers, use unpack('C*',$expr) instead. =item * Reverse List or Byte String @reverse = CORE::reverse(@list); $reverse = CORE::reverse(@list); In list context, this function returns a list value consisting of the elements of @list in the opposite order. In scalar context, the function concatenates all the elements of @list and then returns the reverse of that resulting string, byte by byte, regardless of "use Sjis qw(reverse);" exists or not. =item * Returns Next Byte $getc = CORE::getc(FILEHANDLE); $getc = CORE::getc($filehandle); $getc = CORE::getc; This function returns the next byte from the input file attached to FILEHANDLE. It returns undef at end-of-file, or if an I/O error was encountered. If FILEHANDLE is omitted, the function reads from STDIN. This function is somewhat slow, but it's occasionally useful for single-byte input from the keyboard -- provided you manage to get your keyboard input unbuffered. This function requests unbuffered input from the standard I/O library. Unfortunately, the standard I/O library is not so standard as to provide a portable way to tell the underlying operating system to supply unbuffered keyboard input to the standard I/O system. To do that, you have to be slightly more clever, and in an operating-system-dependent fashion. Under Unix you might say this: if ($BSD_STYLE) { system "stty cbreak /dev/tty 2>&1"; } else { system "stty", "-icanon", "eol", "\001"; } $key = CORE::getc; if ($BSD_STYLE) { system "stty -cbreak /dev/tty 2>&1"; } else { system "stty", "icanon", "eol", "^@"; # ASCII NUL } print "\n"; This code puts the next single-byte typed on the terminal in the string $key. If your stty program has options like cbreak, you'll need to use the code where $BSD_STYLE is true. Otherwise, you'll need to use the code where it is false. =item * Index by Byte String $index = CORE::index($string,$substring,$offset); $index = CORE::index($string,$substring); This function searches for one byte string within another. It returns the position of the first occurrence of $substring in $string. The $offset, if specified, says how many bytes from the start to skip before beginning to look. Positions are based at 0. If the substring is not found, the function returns one less than the base, ordinarily -1. To work your way through a string, you might say: $pos = -1; while (($pos = CORE::index($string, $lookfor, $pos)) > -1) { print "Found at $pos\n"; $pos++; } =item * Rindex by Byte String $rindex = CORE::rindex($string,$substring,$offset); $rindex = CORE::rindex($string,$substring); This function works just like CORE::index except that it returns the position of the last occurrence of $substring in $string (a reverse CORE::index). The function returns -1 if not $substring is found. $offset, if specified, is the rightmost position that may be returned. To work your way through a string backward, say: $pos = CORE::length($string); while (($pos = CORE::rindex($string, $lookfor, $pos)) >= 0) { print "Found at $pos\n"; $pos--; } =back =head1 Un-Escaping bytes::* Functions (Sjis.pm provides) Sjis.pm removes 'bytes::' at head of function name. --------------------------------------- Before After Works as --------------------------------------- bytes::chr chr Byte bytes::index index Byte bytes::length length Byte bytes::ord ord Byte bytes::rindex rindex Byte bytes::substr substr Byte --------------------------------------- =head1 Escaping Built-in Standard Module (Esjis.pm provides) Esjis.pm does "BEGIN { unshift @INC, '/Perl/site/lib/Sjis' }" at head. Store the standard module modified for Sjis software in this directory to override built-in standard modules. =head1 Escaping Standard Module Content (You do) You need copy built-in standard module to /Perl/site/lib/Sjis and change 'use utf8;' to 'use Sjis;' in its. You need help yourself for now. Back to and see 'Escaping Your Script'. Enjoy hacking!! =head1 Ignore Pragmas and Modules ----------------------------------------------------------- Before After ----------------------------------------------------------- use strict; use strict; no strict qw(refs); use 5.12.0; use 5.12.0; no strict qw(refs); require utf8; # require utf8; require bytes; # require bytes; require charnames; # require charnames; require I18N::Japanese; # require I18N::Japanese; require I18N::Collate; # require I18N::Collate; require I18N::JExt; # require I18N::JExt; require File::DosGlob; # require File::DosGlob; require Wild; # require Wild; require Wildcard; # require Wildcard; require Japanese; # require Japanese; use utf8; # use utf8; use bytes; # use bytes; use charnames; # use charnames; use I18N::Japanese; # use I18N::Japanese; use I18N::Collate; # use I18N::Collate; use I18N::JExt; # use I18N::JExt; use File::DosGlob; # use File::DosGlob; use Wild; # use Wild; use Wildcard; # use Wildcard; use Japanese; # use Japanese; no utf8; # no utf8; no bytes; # no bytes; no charnames; # no charnames; no I18N::Japanese; # no I18N::Japanese; no I18N::Collate; # no I18N::Collate; no I18N::JExt; # no I18N::JExt; no File::DosGlob; # no File::DosGlob; no Wild; # no Wild; no Wildcard; # no Wildcard; no Japanese; # no Japanese; ----------------------------------------------------------- Comment out pragma to ignore utf8 environment, and Esjis.pm provides these functions. =over 2 =item * Dummy utf8::upgrade $num_octets = utf8::upgrade($string); Returns the number of octets necessary to represent the string. =item * Dummy utf8::downgrade $success = utf8::downgrade($string[, FAIL_OK]); Returns true always. =item * Dummy utf8::encode utf8::encode($string); Returns nothing. =item * Dummy utf8::decode $success = utf8::decode($string); Returns true always. =item * Dummy utf8::is_utf8 $flag = utf8::is_utf8(STRING); Returns false always. =item * Dummy utf8::valid $flag = utf8::valid(STRING); Returns true always. =item * Dummy bytes::chr This function is same as chr. =item * Dummy bytes::index This function is same as index. =item * Dummy bytes::length This function is same as length. =item * Dummy bytes::ord This function is same as ord. =item * Dummy bytes::rindex This function is same as rindex. =item * Dummy bytes::substr This function is same as substr. =back =head1 Environment Variable This software uses the flock function for exclusive control. The execution of the program is blocked until it becomes possible to read or write the file. You can have it not block in the flock function by defining environment variable SJIS_NONBLOCK. Example: SET SJIS_NONBLOCK=1 (The value '1' doesn't have the meaning) =head1 Perl5.6 Emulation on perl5.005 Using warnings pragma on perl5.00503 by rename files. warnings.pm_ --> warnings.pm warnings/register.pm_ --> warnings/register.pm =head1 Perl5.16 Emulation Using feature pragma by rename files. feature.pm_ --> feature.pm =head1 MacJPerl on The MacOS The functions of MacJPerl was mimicked referring to the books and web. It is welcome if there is a bug report. The following software is necessary to execute Sjis software. 1. MacPerl module 2. Mac::Files module 3. ToolServer 4. MPW(Macintosh Programmer's Workshop) =head1 BUGS, LIMITATIONS, and COMPATIBILITY I have tested and verified this software using the best of my ability. However, a software containing much regular expression is bound to contain some bugs. Thus, if you happen to find a bug that's in Sjis software and not your own program, you can try to reduce it to a minimal test case and then report it to the following author's address. If you have an idea that could make this a more useful tool, please let everyone share it. =over 2 =item * format Function "format" can't handle multiple-octet code same as original Perl. =item * cloister of regular expression The cloister (?s) and (?i) of a regular expression will not be implemented for the time being. Cloister (?s) can be substituted with the .(dot) and \N on /s modifier. Cloister (?i) can be substituted with \F...\E. =item * chdir Function chdir() can always be executed with perl5.005. There are the following limitations for DOS-like system(any of MSWin32, NetWare, symbian, dos). On perl5.006 or perl5.00800, if path is ended by chr(0x5C), it needs jacode.pl library. On perl5.008001 or later, perl5.010, perl5.012, perl5.014, perl5.016, if path is ended by chr(0x5C), chdir succeeds when a short path name (8dot3name) can be acquired according to COMMAND.COM or cmd.exe. However, leaf-subdirectory of the current directory is a short path name (8dot3name). see also, Bug #81839 chdir does not work with chr(0x5C) at end of path http://bugs.activestate.com/show_bug.cgi?id=81839 =item * Sjis::substr as Lvalue Sjis::substr differs from CORE::substr, and cannot be used as a lvalue. To change part of a string, you can use the optional fourth argument which is the replacement string. Sjis::substr($string, 13, 4, "JPerl"); =item * Special Variables $` and $& need /( Capture All )/ Because $` and $& use $1. ------------------------------------------------------------------------------------------- Before After Works as ------------------------------------------------------------------------------------------- $` Esjis::PREMATCH() CORE::substr($&,0,CORE::length($&)-CORE::length($1)) $PREMATCH Esjis::PREMATCH() CORE::substr($&,0,CORE::length($&)-CORE::length($1)) ${^PREMATCH} Esjis::PREMATCH() CORE::substr($&,0,CORE::length($&)-CORE::length($1)) $& Esjis::MATCH() $1 $MATCH Esjis::MATCH() $1 ${^MATCH} Esjis::MATCH() $1 $' Esjis::POSTMATCH() $' $POSTMATCH Esjis::POSTMATCH() $' ${^POSTMATCH} Esjis::POSTMATCH() $' ------------------------------------------------------------------------------------------- =item * Limitation of Regular Expression This software has limitation from \G in multibyte anchoring. On perl5.006, perl5.008, perl5.010, perl5.012, perl5.014 and perl5.016 it doesn't match in the place in which it should match at over 32,767 octets. Moreover, at that time, neither the error nor warning are displayed. see also, Bug #89792 \G can't treat over 32,767 octets http://bugs.activestate.com/show_bug.cgi?id=89792 [perl #116379] \G can't treat over 32767 octet http://www.nntp.perl.org/group/perl.perl5.porters/2013/01/msg197320.html perlre - Perl regular expressions http://perldoc.perl.org/perlre.html regexp limit to 32767 is too small http://markmail.org/message/vtdmaxsa6xqb7fcz regexp limit to 32767 is too small? http://markmail.org/thread/bmmcshbtndbwr3j3 perlre length limit http://stackoverflow.com/questions/4592467/perlre-length-limit =item * Empty Variable in Regular Expression Unlike literal null string, an interpolated variable evaluated to the empty string can't use the most recent pattern from a previous successful regular expression. =item * Limitation of ?? and m?? Multibyte character needs ( ) which is before {n,m} {n,} {n} * and + in ?? or m??. As a result, you need to rewrite a script about $1,$2,$3,... You cannot use (?: ) ? {n,m}? {n,}? and {n}? in ?? and m??, because delimiter of m?? is '?'. =item * Look-behind Assertion The look-behind assertion like (?<=[A-Z]) is not prevented from matching trail octet of the previous multiple-octet code. =item * Modifier /a /d /l and /u of Regular Expression The concept of this software is not to use two or more encoding methods at the same time. Therefore, modifier /a /d /l and /u are not supported. \d means [0-9] always. =item * ${^WIN32_SLOPPY_STAT} is ignored Even if ${^WIN32_SLOPPY_STAT} is set to a true value, file test functions Esjis::*(), Esjis::lstat(), and Esjis::stat() on Microsoft Windows open the file for the path which has chr(0x5c) at end. =back =head1 AUTHOR INABA Hitoshi Eina@cpan.orgE This project was originated by INABA Hitoshi. =head1 LICENSE AND COPYRIGHT This software is free software; you can redistribute it and/or modify it under the same terms as Perl itself. See L. This software is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. =head1 My Goal P.401 See chapter 15: Unicode of ISBN 0-596-00027-8 Programming Perl Third Edition. Before the introduction of Unicode support in perl, The eq operator just compared the byte-strings represented by two scalars. Beginning with perl 5.8, eq compares two byte-strings with simultaneous consideration of the UTF8 flag. Information processing model beginning with perl 5.8 +----------------------+---------------------+ | Text strings | | +----------+-----------| Binary strings | | UTF8 | Latin-1 | | +----------+-----------+---------------------+ | UTF8 | Not UTF8 | | Flagged | Flagged | +--------------------------------------------+ http://perl-users.jp/articles/advent-calendar/2010/casual/4 You should memorize this figure. (Why is only Latin-1 special?) This change consequentially made a big gap between a past script and new script. Both scripts cannot re-use the code mutually any longer. Because a new method puts a strain in the programmer, it will still take time to replace all the in existence scripts. The biggest problem of new method is that the UTF8 flag can't synchronize to real encode of string. Thus you must debug about UTF8 flag, before your script. How to solve it by returning to a past method, let's drag out page 402 of the old dusty Programming Perl, 3rd ed. again. Information processing model beginning with perl3 or this software. +--------------------------------------------+ | Text strings as Binary strings | | Binary strings as Text strings | +--------------------------------------------+ | Not UTF8 Flagged | +--------------------------------------------+ Ideally, I'd like to achieve these five Goals: =over 2 =item * Goal #1: Old byte-oriented programs should not spontaneously break on the old byte-oriented data they used to work on. It has already been achieved by ShiftJIS designed for combining with old byte-oriented ASCII. =item * Goal #2: Old byte-oriented programs should magically start working on the new character-oriented data when appropriate. Still now, 1 octet is counted with 1 by embedded functions length, substr, index, rindex and pos that handle length and position of string. In this part, there is no change. The length of 1 character of 2 octet code is 2. On the other hand, the regular expression in the script is added the multibyte anchoring processing with this software, instead of you. figure of Goal #1 and Goal #2. GOAL#1 GOAL#2 (a) (b) (c) (d) (e) +--------------+-------+-------+-------+-------+-------+ | data | Old | Old | New | Old | New | +--------------+-------+-------+-------+-------+-------+ | script | Old | Old | New | +--------------+-------+---------------+---------------+ | interpreter | Old | New | +--------------+-------+-------------------------------+ Old --- Old byte-oriented New --- New character-oriented There is a combination from (a) to (e) in data, script and interpreter of old and new. Let's add the Encode module and this software did not exist at time of be written this document and JPerl did exist. (a) (b) (c) (d) (e) JPerl Encode,Sjis +--------------+-------+-------+-------+-------+-------+ | data | Old | Old | New | Old | New | +--------------+-------+-------+-------+-------+-------+ | script | Old | Old | New | +--------------+-------+---------------+---------------+ | interpreter | Old | New | +--------------+-------+-------------------------------+ Old --- Old byte-oriented New --- New character-oriented The reason why JPerl is very excellent is that it is at the position of (c). That is, it is not necessary to do a special description to the script to process new character-oriented string. Contrasting is Encode module and describing "use Sjis;" on this software, in this case, a new description is necessary. =item * Goal #3: Programs should run just as fast in the new character-oriented mode as in the old byte-oriented mode. It is impossible. Because the following time is necessary. (1) Time of escape script for old byte-oriented perl. (2) Time of processing regular expression by escaped script while multibyte anchoring. =item * Goal #4: Perl should remain one language, rather than forking into a byte-oriented Perl and a character-oriented Perl. JPerl remains one Perl language by forking to two interpreters. However, the Perl core team did not desire fork of the interpreter. As a result, Perl language forked contrary to goal #4. A character-oriented perl is not necessary to make it specially, because a byte-oriented perl can already treat the binary data. This software is only an application program of byte-oriented Perl, a filter program. And you will get support from the Perl community, when you solve the problem by the Perl script. =item * Goal #5: JPerl users will be able to maintain JPerl by Perl. May the JPerl be with you, always. =back Back when Programming Perl, 3rd ed. was written, UTF8 flag was not born and Perl is designed to make the easy jobs easy. This software provide programming environment like at that time. =head1 Words of Learning Perl Some computer scientists (the reductionists, in particular) would like to deny it, but people have funny-shaped minds. Mental geography is not linear, and cannot be mapped onto a flat surface without severe distortion. But for the last score years or so, computer reductionists have been first bowing down at the Temple of Orthogonality, then rising up to preach their ideas of ascetic rectitude to any who would listen. Their fervent but misguided desire was simply to squash your mind to fit their mindset, to smush your patterns of thought into some sort of Hyperdimensional Flatland. It's a joyless existence, being smushed. --- Learning Perl on Win32 Systems If you think this is a big headache, you're right. No one likes this situation, but Perl does the best it can with the input and encodings it has to deal with. If only we could reset history and not make so many mistakes nest time. --- Learning Perl 6th Edition =head1 SEE ALSO PERL PUROGURAMINGU Larry Wall, Randal L.Schwartz, Yoshiyuki Kondo December 1997 ISBN 4-89052-384-7 http://www.context.co.jp/~cond/books/old-books.html Programming Perl, Second Edition By Larry Wall, Tom Christiansen, Randal L. Schwartz October 1996 Pages: 670 ISBN 10: 1-56592-149-6 | ISBN 13: 9781565921498 http://shop.oreilly.com/product/9781565921498.do Programming Perl, Third Edition By Larry Wall, Tom Christiansen, Jon Orwant Third Edition July 2000 Pages: 1104 ISBN 10: 0-596-00027-8 | ISBN 13: 9780596000271 http://shop.oreilly.com/product/9780596000271.do The Perl Language Reference Manual (for Perl version 5.12.1) by Larry Wall and others Paperback (6"x9"), 724 pages Retail Price: $39.95 (pound 29.95 in UK) ISBN-13: 978-1-906966-02-7 http://www.network-theory.co.uk/perl/language/ Perl Pocket Reference, 5th Edition By Johan Vromans Publisher: O'Reilly Media Released: July 2011 Pages: 102 http://shop.oreilly.com/product/0636920018476.do Programming Perl, 4th Edition By: Tom Christiansen, brian d foy, Larry Wall, Jon Orwant Publisher: O'Reilly Media Formats: Print, Ebook, Safari Books Online Released: March 2012 Pages: 1130 Print ISBN: 978-0-596-00492-7 | ISBN 10: 0-596-00492-3 Ebook ISBN: 978-1-4493-9890-3 | ISBN 10: 1-4493-9890-1 http://shop.oreilly.com/product/9780596004927.do Perl Cookbook, Second Edition By Tom Christiansen, Nathan Torkington Second Edition August 2003 Pages: 964 ISBN 10: 0-596-00313-7 | ISBN 13: 9780596003135 http://shop.oreilly.com/product/9780596003135.do Perl in a Nutshell, Second Edition By Stephen Spainhour, Ellen Siever, Nathan Patwardhan Second Edition June 2002 Pages: 760 Series: In a Nutshell ISBN 10: 0-596-00241-6 | ISBN 13: 9780596002411 http://shop.oreilly.com/product/9780596002411.do Learning Perl on Win32 Systems By Randal L. Schwartz, Erik Olson, Tom Christiansen August 1997 Pages: 306 ISBN 10: 1-56592-324-3 | ISBN 13: 9781565923249 http://shop.oreilly.com/product/9781565923249.do Learning Perl, Fifth Edition By Randal L. Schwartz, Tom Phoenix, brian d foy June 2008 Pages: 352 Print ISBN:978-0-596-52010-6 | ISBN 10: 0-596-52010-7 Ebook ISBN:978-0-596-10316-3 | ISBN 10: 0-596-10316-6 http://shop.oreilly.com/product/9780596520113.do Learning Perl, 6th Edition By Randal L. Schwartz, brian d foy, Tom Phoenix June 2011 Pages: 390 ISBN-10: 1449303587 | ISBN-13: 978-1449303587 http://shop.oreilly.com/product/0636920018452.do Perl RESOURCE KIT UNIX EDITION Futato, Irving, Jepson, Patwardhan, Siever ISBN 10: 1-56592-370-7 http://shop.oreilly.com/product/9781565923706.do MODAN Perl NYUMON By Daisuke Maki 2009/2/10 Pages: 344 ISBN 10: 4798119172 | ISBN 13: 978-4798119175 http://www.seshop.com/product/detail/10250/ Understanding Japanese Information Processing By Ken Lunde January 1900 Pages: 470 ISBN 10: 1-56592-043-0 | ISBN 13: 9781565920439 http://shop.oreilly.com/product/9781565920439.do CJKV Information Processing Chinese, Japanese, Korean & Vietnamese Computing By Ken Lunde First Edition January 1999 Pages: 1128 ISBN 10: 1-56592-224-7 | ISBN 13: 9781565922242 http://shop.oreilly.com/product/9781565922242.do Mastering Regular Expressions, Second Edition By Jeffrey E. F. Friedl Second Edition July 2002 Pages: 484 ISBN 10: 0-596-00289-0 | ISBN 13: 9780596002893 http://shop.oreilly.com/product/9780596002893.do Mastering Regular Expressions, Third Edition By Jeffrey E. F. Friedl Third Edition August 2006 Pages: 542 ISBN 10: 0-596-52812-4 | ISBN 13:9780596528126 http://shop.oreilly.com/product/9780596528126.do Regular Expressions Cookbook By Jan Goyvaerts, Steven Levithan May 2009 Pages: 512 ISBN 10:0-596-52068-9 | ISBN 13: 978-0-596-52068-7 http://shop.oreilly.com/product/9780596520694.do JIS KANJI JITEN By Kouji Shibano Pages: 1456 ISBN 4-542-20129-5 http://www.webstore.jsa.or.jp/lib/lib.asp?fn=/manual/mnl01_12.htm UNIX MAGAZINE 1993 Aug Pages: 172 T1008901080816 ZASSHI 08901-8 http://ascii.asciimw.jp/books/books/detail/978-4-7561-5008-0.shtml MacPerl Power and Ease By Vicki Brown, Chris Nandor April 1998 Pages: 350 ISBN 10: 1881957322 | ISBN 13: 978-1881957324 http://www.amazon.com/Macperl-Power-Ease-Vicki-Brown/dp/1881957322 Windows NT Shell Scripting By Timothy Hill April 27, 1998 Pages: 400 ISBN 10: 1578700477 | ISBN 13: 9781578700479 http://search.barnesandnoble.com/Windows-NT-Shell-Scripting/Timothy-Hill/e/9781578700479/ Windows(R) Command-Line Administrators Pocket Consultant, 2nd Edition By William R. Stanek February 2009 Pages: 594 ISBN 10: 0-7356-2262-0 | ISBN 13: 978-0-7356-2262-3 http://shop.oreilly.com/product/9780735622623.do Other Tools http://search.cpan.org/dist/jacode/ http://search.cpan.org/dist/Char/ BackPAN http://backpan.perl.org/authors/id/I/IN/INA/ =head1 ACKNOWLEDGEMENTS This software was made referring to software and the document that the following hackers or persons had made. I am thankful to all persons. Rick Yamashita, Shift_JIS ttp://furukawablog.spaces.live.com/Blog/cns!1pmWgsL289nm7Shn7cS0jHzA!2225.entry (dead link) ttp://shino.tumblr.com/post/116166805/1981-us-jis (add 'h' at head) http://www.wdic.org/w/WDIC/%E3%82%B7%E3%83%95%E3%83%88JIS Larry Wall, Perl http://www.perl.org/ Kazumasa Utashiro, jcode.pl ftp://ftp.iij.ad.jp/pub/IIJ/dist/utashiro/perl/ http://log.utashiro.com/pub/2006/07/jkondo_a580.html Jeffrey E. F. Friedl, Mastering Regular Expressions http://regex.info/ SADAHIRO Tomoyuki, The right way of using Shift_JIS http://homepage1.nifty.com/nomenclator/perl/shiftjis.htm http://search.cpan.org/~sadahiro/ Yukihiro "Matz" Matsumoto, YAPC::Asia2006 Ruby on Perl(s) http://www.rubyist.net/~matz/slides/yapc2006/ jscripter, For jperl users http://homepage1.nifty.com/kazuf/jperl.html Bruce., Unicode in Perl http://www.rakunet.org/tsnet/TSabc/18/546.html Hiroaki Izumi, Perl5.8/Perl5.10 is not useful on the Windows. http://dl.dropbox.com/u/23756062/perlwin.html https://sites.google.com/site/hiroa63iz/perlwin TSUKAMOTO Makio, Perl memo/file path of Windows http://digit.que.ne.jp/work/wiki.cgi?Perl%E3%83%A1%E3%83%A2%2FWindows%E3%81%A7%E3%81%AE%E3%83%95%E3%82%A1%E3%82%A4%E3%83%AB%E3%83%91%E3%82%B9 chaichanPaPa, Matching Shift_JIS file name http://d.hatena.ne.jp/chaichanPaPa/20080802/1217660826 SUZUKI Norio, Jperl http://homepage2.nifty.com/kipp/perl/jperl/ WATANABE Hirofumi, Jperl http://www.cpan.org/src/5.0/jperl/ http://search.cpan.org/~watanabe/ ftp://ftp.oreilly.co.jp/pcjp98/watanabe/jperlconf.ppt Chuck Houpt, Michiko Nozu, MacJPerl http://habilis.net/macjperl/index.j.html Kenichi Ishigaki, Pod-PerldocJp, Welcome to modern Perl world http://search.cpan.org/dist/Pod-PerldocJp/ http://gihyo.jp/dev/serial/01/modern-perl/0031 http://gihyo.jp/dev/serial/01/modern-perl/0032 http://gihyo.jp/dev/serial/01/modern-perl/0033 Fuji, Goro (gfx), Perl Hackers Hub No.16 http://gihyo.jp/dev/serial/01/perl-hackers-hub/001602 Dan Kogai, Encode module http://search.cpan.org/dist/Encode/ http://www.archive.org/details/YAPCAsia2006TokyoPerl58andUnicodeMythsFactsandChanges (video) http://yapc.g.hatena.ne.jp/jkondo/ (audio) Juerd, Perl Unicode Advice http://juerd.nl/site.plp/perluniadvice daily dayflower, 2008-06-25 perluniadvice http://d.hatena.ne.jp/dayflower/20080625/1214374293 Jesse Vincent, Compatibility is a virtue http://www.nntp.perl.org/group/perl.perl5.porters/2010/05/msg159825.html Tokyo-pm archive http://mail.pm.org/pipermail/tokyo-pm/ http://mail.pm.org/pipermail/tokyo-pm/1999-September/001844.html http://mail.pm.org/pipermail/tokyo-pm/1999-September/001854.html ruby-list http://blade.nagaokaut.ac.jp/ruby/ruby-list/index.shtml http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/2440 http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/2446 http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/2569 http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/9427 http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/9431 http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/10500 http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/10501 http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/10502 http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/12385 http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/12392 http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/12393 http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/19156 =cut