The Perl Toolchain Summit 2025 Needs You: You can help 🙏 Learn more

package UTF2;
######################################################################
#
# UTF2 - Source code filter to UTF-2 script
#
# Copyright (c) 2008, 2009, 2010, 2011, 2012 INABA Hitoshi <ina@cpan.org>
#
######################################################################
use 5.00503;
BEGIN {
if ($^X =~ m/ jperl /oxmsi) {
die __FILE__, ": needs perl(not jperl) 5.00503 or later. (\$^X==$^X)";
}
if (ord('A') == 193) {
die __FILE__, ": is not US-ASCII script (may be EBCDIC or EBCDIK script).";
}
if (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: 0.81 $ =~ m/(\d+)/oxmsg;
use Eutf2;
# 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;
}
}
# use strict; if strict.pm exists
BEGIN {
if (eval {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.
sub LOCK_SH() {1}
sub LOCK_EX() {2}
sub LOCK_UN() {8}
sub LOCK_NB() {4}
# P.707 29.2.33. exec
# in Chapter 29: Functions
# of ISBN 0-596-00027-8 Programming Perl Third Edition.
# P.855 exec
# in Chapter 27: Functions
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
$| = 1;
sub import() {}
sub unimport() {}
sub UTF2::escape_script;
# regexp of character
my $your_char = q{(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\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 $anchor = '';
BEGIN { eval q{ use vars qw($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] |
\\? (?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF] |
\\ [\x00-\xFF] |
[^()] |
\( (?{$nest++}) |
\) (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!))
}xms;
my $qq_brace = qr{(?{local $nest=0}) (?>(?:
\\c[\x40-\x5F] |
\\? (?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF] |
\\ [\x00-\xFF] |
[^{}] |
\{ (?{$nest++}) |
\} (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!))
}xms;
my $qq_bracket = qr{(?{local $nest=0}) (?>(?:
\\c[\x40-\x5F] |
\\? (?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF] |
\\ [\x00-\xFF] |
[^[\]] |
\[ (?{$nest++}) |
\] (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!))
}xms;
my $qq_angle = qr{(?{local $nest=0}) (?>(?:
\\c[\x40-\x5F] |
\\? (?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF] |
\\ [\x00-\xFF] |
[^<>] |
\< (?{$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]+ |
[^\x80-\xFFa-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}) (?>(?:
(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF] |
[^()] |
\( (?{$nest++}) |
\) (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!))
}xms;
my $q_brace = qr{(?{local $nest=0}) (?>(?:
(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF] |
[^{}] |
\{ (?{$nest++}) |
\} (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!))
}xms;
my $q_bracket = qr{(?{local $nest=0}) (?>(?:
(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF] |
[^[\]] |
\[ (?{$nest++}) |
\] (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!))
}xms;
my $q_angle = qr{(?{local $nest=0}) (?>(?:
(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF] |
[^<>] |
\< (?{$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 $use_re_eval = '';
my $matched = '';
my $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 UTF2::ord()
my $function_ord_; # ord to ord or UTF2::ord_
my $function_reverse; # reverse to reverse or UTF2::reverse
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 <<END;
$0: usage
perl $0 UTF-2_script.pl > Escaped_script.pl.e
END
}
print UTF2::escape_script($ARGV[0]);
exit 0;
}
my($package,$filename,$line,$subroutine,$hasargs,$wantarray,$evaltext,$is_require,$hints,$bitmask) = caller 0;
# called any package not main
if ($package ne 'main') {
die <<END;
@{[__FILE__]}: escape by manually command '$^X @{[__FILE__]} "$filename" > "@{[__PACKAGE__]}::$filename"'
and rewrite "use $package;" to "use @{[__PACKAGE__]}::$package;" of script "$0".
END
}
if (-e("$filename.e")) {
if (exists $ENV{'SJIS_DEBUG'}) {
unlink "$filename.e";
}
elsif (-z("$filename.e")) {
unlink "$filename.e";
}
else {
my $e_mtime = (stat("$filename.e"))[9];
my $mtime = (stat($filename))[9];
my $__mtime__ = (stat(__FILE__))[9];
if (($e_mtime < $mtime) or ($mtime < $__mtime__)) {
unlink "$filename.e";
}
}
}
if (not -e("$filename.e")) {
my $fh = gensym();
if (eval q{ use Fcntl qw(O_WRONLY O_APPEND O_CREAT); 1 } and CORE::sysopen($fh,"$filename.e",&O_WRONLY|&O_APPEND|&O_CREAT)) {
}
else {
open($fh, ">>$filename.e") or die __FILE__, ": Can't write open file: $filename.e";
}
if (0) {
}
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 $e_script = UTF2::escape_script($filename);
print {$fh} $e_script;
my $mode = (stat($filename))[2] & 0777;
chmod $mode, "$filename.e";
close($fh) or die __FILE__, ": Can't close file: $filename.e";
}
# P.565 23.1.2. Cleaning Up Your Environment
# in Chapter 23: Security
# of ISBN 0-596-00027-8 Programming Perl Third Edition.
# P.656 Cleaning Up Your Environment
# in Chapter 20: Security
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
# local $ENV{'PATH'} = '.';
local @ENV{qw(IFS CDPATH ENV BASH_ENV)};
my $fh = gensym();
open($fh, "$filename.e") or die __FILE__, ": Can't read open file: $filename.e";
if (0) {
}
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 ($^W) {
push @switch, '-w';
}
# P.489 #! and Quoting on Non-Unix Systems
# in Chapter 19: The Command-Line Interface
# of ISBN 0-596-00027-8 Programming Perl Third Edition.
# P.578 #! and Quoting on Non-Unix Systems
# in Chapter 17: The Command-Line Interface
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
# DOS-like system
if ($^O =~ /\A (?: MSWin32 | NetWare | symbian | dos ) \z/oxms) {
exit system
_escapeshellcmd_MSWin32($^X),
# -I switch can not treat space included path
# (map { '-I' . _escapeshellcmd_MSWin32($_) } @INC),
(map { '-I' . $_ } @INC),
@switch,
'--',
map { _escapeshellcmd_MSWin32($_) } "$filename.e", @ARGV;
}
# UNIX-like system
else {
exit system
_escapeshellcmd($^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 =~ m/ $anchor [ ] /oxms) {
return qq{"$word"};
}
else {
return $word;
}
}
# escape shell command line on UNIX-like system
sub _escapeshellcmd {
my($word) = @_;
$word =~ s/([\t\n\r\x20!"#\$%&'()*+;<=>?\[\\\]^`{|}~\x7F\xFF])/\\$1/g;
return $word;
}
# P.619 Source Filters
# in Chapter 24: Common Practices
# of ISBN 0-596-00027-8 Programming Perl Third Edition.
# P.718 Source Filters
# in Chapter 21: Common Practices
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
# escape UTF-2 script
sub UTF2::escape_script {
my($script) = @_;
my $e_script = '';
# read UTF-2 script
my $fh = gensym();
open($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 (m/^ use Eutf2(?:\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 Eutf2 %s;\n%s", $Eutf2::VERSION, $use_re_eval); # require run-time routines version
# use UTF2 version qw(ord reverse);
$function_ord = 'ord';
$function_ord_ = 'ord';
$function_reverse = 'reverse';
if (s/^ \s* use \s+ UTF2 \s* ([^\x80-\xFF;]*) ; \s* \n? $//oxms) {
# require version
my $list = $1;
if ($list =~ s/\A ([0-9]+(?:\.[0-9]*)) \s* //oxms) {
my $version = $1;
if ($version > $VERSION) {
die __FILE__, ": version $version required--this is only version $VERSION";
}
}
# demand ord and reverse
if ($list !~ m/\A \s* \z/oxms) {
local $@;
my @list = eval $list;
for (@list) {
$function_ord = 'UTF2::ord' if m/\A ord \z/oxms;
$function_ord_ = 'UTF2::ord_' if m/\A ord \z/oxms;
$function_reverse = 'UTF2::reverse' if m/\A reverse \z/oxms;
}
}
}
}
$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 UTF-2 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} --> Eutf2::PREMATCH()
elsif (/\G ( \$` | \$\{`\} | \$ \s* PREMATCH \b | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) /oxmsgc) {
$slash = 'div';
return q{Eutf2::PREMATCH()};
}
# $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Eutf2::MATCH()
elsif (/\G ( \$& | \$\{&\} | \$ \s* MATCH \b | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) /oxmsgc) {
$slash = 'div';
return q{Eutf2::MATCH()};
}
# $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Eutf2::POSTMATCH()
elsif (/\G ( \$ \s* POSTMATCH \b | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) /oxmsgc) {
$slash = 'div';
return q{Eutf2::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|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 (<FILEHANDLE>)
elsif (/\G \b (while \s* \( \s* <[\$]?[A-Za-z_][A-Za-z_0-9]*> \s* \)) \b /oxgc) {
return $1;
}
# while (<WILDCARD>) --- glob
# avoid "Error: Runtime exception" of perl version 5.005_03
elsif (/\G \b while \s* \( \s* < ((?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF>\0\a\e\f\n\r\t])+?) > \s* \) \b /oxgc) {
return 'while ($_ = Eutf2::glob("' . $1 . '"))';
}
# while (glob)
elsif (/\G \b while \s* \( \s* glob \s* \) /oxgc) {
return 'while ($_ = Eutf2::glob_)';
}
# while (glob(WILDCARD))
elsif (/\G \b while \s* \( \s* glob \b /oxgc) {
return 'while ($_ = Eutf2::glob';
}
# doit if, doit unless, doit while, doit until, doit for, doit when
elsif (m{\G \b ( if | unless | while | until | for | when ) \b }oxgc) { $slash = 'm//'; return $1; }
# functions of package Eutf2
elsif (m{\G \b (CORE:: | ->[ ]* (?: atan2 | [a-z]{2,})) \b }oxgc) { $slash = 'm//'; return $1; }
elsif (m{\G \b bytes::substr \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'substr'; }
elsif (m{\G \b chop \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'Eutf2::chop'; }
elsif (m{\G \b bytes::index \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'index'; }
elsif (m{\G \b UTF2::index \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'UTF2::index'; }
elsif (m{\G \b index \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'Eutf2::index'; }
elsif (m{\G \b bytes::rindex \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'rindex'; }
elsif (m{\G \b UTF2::rindex \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'UTF2::rindex'; }
elsif (m{\G \b rindex \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'Eutf2::rindex'; }
elsif (m{\G \b lc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $slash = 'm//'; return 'Eutf2::lc'; }
elsif (m{\G \b lcfirst (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $slash = 'm//'; return 'Eutf2::lcfirst'; }
elsif (m{\G \b uc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $slash = 'm//'; return 'Eutf2::uc'; }
elsif (m{\G \b ucfirst (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $slash = 'm//'; return 'Eutf2::ucfirst'; }
elsif (m{\G \b fc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $slash = 'm//'; return 'Eutf2::fc'; }
# "-s '' ..." means file test "-s 'filename' ..." (not means "- s/// ...")
elsif (m{\G -s \s+ \s* (\") ((?:$qq_char)+?) (\") }oxgc) { $slash = 'm//'; return '-s ' . e_qq('', $1,$3,$2); }
elsif (m{\G -s \s+ qq \s* (\#) ((?:$qq_char)+?) (\#) }oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); }
elsif (m{\G -s \s+ qq \s* (\() ((?:$qq_paren)+?) (\)) }oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); }
elsif (m{\G -s \s+ qq \s* (\{) ((?:$qq_brace)+?) (\}) }oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); }
elsif (m{\G -s \s+ qq \s* (\[) ((?:$qq_bracket)+?) (\]) }oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); }
elsif (m{\G -s \s+ qq \s* (\<) ((?:$qq_angle)+?) (\>) }oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); }
elsif (m{\G -s \s+ qq \s* (\S) ((?:$qq_char)+?) (\3) }oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); }
elsif (m{\G -s \s+ \s* (\') ((?:\\\1|\\\\|$q_char)+?) (\') }oxgc) { $slash = 'm//'; return '-s ' . e_q ('', $1,$3,$2); }
elsif (m{\G -s \s+ q \s* (\#) ((?:\\\#|\\\\|$q_char)+?) (\#) }oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); }
elsif (m{\G -s \s+ q \s* (\() ((?:\\\)|\\\\|$q_paren)+?) (\)) }oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); }
elsif (m{\G -s \s+ q \s* (\{) ((?:\\\}|\\\\|$q_brace)+?) (\}) }oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); }
elsif (m{\G -s \s+ q \s* (\[) ((?:\\\]|\\\\|$q_bracket)+?) (\]) }oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); }
elsif (m{\G -s \s+ q \s* (\<) ((?:\\\>|\\\\|$q_angle)+?) (\>) }oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); }
elsif (m{\G -s \s+ q \s* (\S) ((?:\\\1|\\\\|$q_char)+?) (\3) }oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); }
elsif (m{\G -s \s* (\$ \w+(?: ::\w+)* (?: (?: ->)? (?: \( (?:$qq_paren)*? \) | \{ (?:$qq_brace)+? \} | \[ (?:$qq_bracket)+? \] ) )*) }oxgc)
{ $slash = 'm//'; return "-s $1"; }
elsif (m{\G -s \s* \( ((?:$qq_paren)*?) \) }oxgc) { $slash = 'm//'; return "-s ($1)"; }
elsif (m{\G -s (?= \s+ [a-z]+) }oxgc) { $slash = 'm//'; return '-s'; }
elsif (m{\G -s \s+ (\w+) }oxgc) { $slash = 'm//'; return "-s $1"; }
elsif (m{\G \b bytes::length (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $slash = 'm//'; return 'length'; }
elsif (m{\G \b bytes::chr (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $slash = 'm//'; return 'chr'; }
elsif (m{\G \b chr (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $slash = 'm//'; return 'Eutf2::chr'; }
elsif (m{\G \b bytes::ord (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $slash = 'div'; return 'ord'; }
elsif (m{\G \b ord (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $slash = 'div'; return $function_ord; }
elsif (m{\G \b glob (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $slash = 'm//'; return 'Eutf2::glob'; }
elsif (m{\G \b lc \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'Eutf2::lc_'; }
elsif (m{\G \b lcfirst \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'Eutf2::lcfirst_'; }
elsif (m{\G \b uc \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'Eutf2::uc_'; }
elsif (m{\G \b ucfirst \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'Eutf2::ucfirst_'; }
elsif (m{\G \b fc \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'Eutf2::fc_'; }
elsif (m{\G -s \b (?! \s* => ) }oxgc) { $slash = 'm//'; return '-s '; }
elsif (m{\G \b bytes::length \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'length'; }
elsif (m{\G \b bytes::chr \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'chr'; }
elsif (m{\G \b chr \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'Eutf2::chr_'; }
elsif (m{\G \b bytes::ord \b (?! \s* => ) }oxgc) { $slash = 'div'; return 'ord'; }
elsif (m{\G \b ord \b (?! \s* => ) }oxgc) { $slash = 'div'; return $function_ord_; }
elsif (m{\G \b glob \b (?! \s* => ) }oxgc) { $slash = 'm//'; return 'Eutf2::glob_'; }
elsif (m{\G \b reverse \b (?! \s* => ) }oxgc) { $slash = 'm//'; return $function_reverse; }
# split
elsif (m{\G \b (split) \b (?! \s* => ) }oxgc) {
$slash = 'm//';
my $e = '';
while (/\G ( \s+ | \( | \#.* ) /oxgc) {
$e .= $1;
}
# end of split
if (/\G (?= [,;\)\}\]] ) /oxgc) { return 'Eutf2::split' . $e; }
# split scalar value
elsif (/\G ( [\$\@\&\*] $qq_scalar ) /oxgc) { return 'Eutf2::split' . $e . e_string($1); }
# split literal space
elsif (/\G \b qq (\#) [ ] (\#) /oxgc) { return 'Eutf2::split' . $e . qq {qq$1 $2}; }
elsif (/\G \b qq (\s*) (\() [ ] (\)) /oxgc) { return 'Eutf2::split' . $e . qq{$1qq$2 $3}; }
elsif (/\G \b qq (\s*) (\{) [ ] (\}) /oxgc) { return 'Eutf2::split' . $e . qq{$1qq$2 $3}; }
elsif (/\G \b qq (\s*) (\[) [ ] (\]) /oxgc) { return 'Eutf2::split' . $e . qq{$1qq$2 $3}; }
elsif (/\G \b qq (\s*) (\<) [ ] (\>) /oxgc) { return 'Eutf2::split' . $e . qq{$1qq$2 $3}; }
elsif (/\G \b qq (\s*) (\S) [ ] (\2) /oxgc) { return 'Eutf2::split' . $e . qq{$1qq$2 $3}; }
elsif (/\G \b q (\#) [ ] (\#) /oxgc) { return 'Eutf2::split' . $e . qq {q$1 $2}; }
elsif (/\G \b q (\s*) (\() [ ] (\)) /oxgc) { return 'Eutf2::split' . $e . qq {$1q$2 $3}; }
elsif (/\G \b q (\s*) (\{) [ ] (\}) /oxgc) { return 'Eutf2::split' . $e . qq {$1q$2 $3}; }
elsif (/\G \b q (\s*) (\[) [ ] (\]) /oxgc) { return 'Eutf2::split' . $e . qq {$1q$2 $3}; }
elsif (/\G \b q (\s*) (\<) [ ] (\>) /oxgc) { return 'Eutf2::split' . $e . qq {$1q$2 $3}; }
elsif (/\G \b q (\s*) (\S) [ ] (\2) /oxgc) { return 'Eutf2::split' . $e . qq {$1q$2 $3}; }
elsif (/\G ' [ ] ' /oxgc) { return 'Eutf2::split' . $e . qq {' '}; }
elsif (/\G " [ ] " /oxgc) { return 'Eutf2::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,$6);
}
}
die __FILE__, ": Substitution pattern not terminated";
}
}
# require ignore module
elsif (/\G \b require (\s+ (?:$ignore_modules) .*? ;) ([ \t]* [#\n]) /oxmsgc) { return "# require$1$2"; }
elsif (/\G \b require (\s+ (?:$ignore_modules) .*? ;) ([ \t]* [^\x80-\xFF#]) /oxmsgc) { return "# require$1\n$2"; }
elsif (/\G \b require (\s+ (?:$ignore_modules)) \b /oxmsgc) { return "# require$1"; }
# 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]* [^\x80-\xFF#]) /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]* [^\x80-\xFF#]) /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]* [^\x80-\xFF#]) /oxmsgc) { return "# no$1\n$2"; }
elsif (/\G \b no (\s+ (?:$ignore_modules)) \b /oxmsgc) { return "# no$1"; }
# use else
elsif (/\G \b use \b /oxmsgc) { return "use"; }
# use else
elsif (/\G \b no \b /oxmsgc) { return "no"; }
# ''
elsif (/\G (?<![\w\$\@\%\&\*]) (\') /oxgc) {
my $q_string = '';
while (not /\G \z/oxgc) {
if (/\G (\\\\) /oxgc) { $q_string .= $1; }
elsif (/\G (\\\') /oxgc) { $q_string .= $1; }
elsif (/\G \' /oxgc) { return e_q('', "'","'",$q_string); }
elsif (/\G ($q_char) /oxgc) { $q_string .= $1; }
}
die __FILE__, ": Can't find string terminator anywhere before EOF";
}
# ""
elsif (/\G (\") /oxgc) {
my $qq_string = '';
while (not /\G \z/oxgc) {
if (/\G (\\\\) /oxgc) { $qq_string .= $1; }
elsif (/\G (\\\") /oxgc) { $qq_string .= $1; }
elsif (/\G \" /oxgc) { return e_qq('', '"','"',$qq_string); }
elsif (/\G ($q_char) /oxgc) { $qq_string .= $1; }
}
die __FILE__, ": Can't find string terminator anywhere before EOF";
}
# ``
elsif (/\G (\`) /oxgc) {
my $qx_string = '';
while (not /\G \z/oxgc) {
if (/\G (\\\\) /oxgc) { $qx_string .= $1; }
elsif (/\G (\\\`) /oxgc) { $qx_string .= $1; }
elsif (/\G \` /oxgc) { return e_qq('', '`','`',$qx_string); }
elsif (/\G ($q_char) /oxgc) { $qx_string .= $1; }
}
die __FILE__, ": Can't find string terminator anywhere before EOF";
}
# // --- not divide operator (num / num), not defined-or
elsif (($slash eq 'm//') and /\G (\/) /oxgc) {
my $regexp = '';
while (not /\G \z/oxgc) {
if (/\G (\\\\) /oxgc) { $regexp .= $1; }
elsif (/\G (\\\/) /oxgc) { $regexp .= $1; }
elsif (/\G \/ ([cgimosxpadlubB]*) /oxgc) { return e_qr('', '/','/',$regexp,$1); }
elsif (/\G ($q_char) /oxgc) { $regexp .= $1; }
}
die __FILE__, ": Search pattern not terminated";
}
# ?? --- not conditional operator (condition ? then : else)
elsif (($slash eq 'm//') and /\G (\?) /oxgc) {
my $regexp = '';
while (not /\G \z/oxgc) {
if (/\G (\\\\) /oxgc) { $regexp .= $1; }
elsif (/\G (\\\?) /oxgc) { $regexp .= $1; }
elsif (/\G \? ([cgimosxpadlubB]*) /oxgc) { return e_qr('m','?','?',$regexp,$1); }
elsif (/\G ($q_char) /oxgc) { $regexp .= $1; }
}
die __FILE__, ": Search pattern not terminated";
}
# << (bit shift) --- not here document
elsif (/\G ( << \s* ) (?= [0-9\$\@\&] ) /oxgc) { $slash = 'm//'; return $1; }
# <<'HEREDOC'
elsif (/\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";
}
return $here_quote;
}
# <<\HEREDOC
# P.66 2.6.6. "Here" Documents
# in Chapter 2: Bits and Pieces
# of ISBN 0-596-00027-8 Programming Perl Third Edition.
# P.73 "Here" Documents
# in Chapter 2: Bits and Pieces
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
elsif (/\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";
}
return $here_quote;
}
# <<"HEREDOC"
elsif (/\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";
}
return $here_quote;
}
# <<HEREDOC
elsif (/\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";
}
return $here_quote;
}
# <<`HEREDOC`
elsif (/\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";
}
return $here_quote;
}
# <<= <=> <= < operator
elsif (/\G (<<=|<=>|<=|<) (?= \s* [A-Za-z_0-9'"`\$\@\&\*\(\+\-] )/oxgc) {
return $1;
}
# <FILEHANDLE>
elsif (/\G (<[\$]?[A-Za-z_][A-Za-z_0-9]*>) /oxgc) {
return $1;
}
# <WILDCARD> --- glob
# avoid "Error: Runtime exception" of perl version 5.005_03
elsif (/\G < ((?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF>\0\a\e\f\n\r\t])+?) > /oxgc) {
return 'Eutf2::glob("' . $1 . '")';
}
# __DATA__
elsif (/\G ^ ( __DATA__ \n .*) \z /oxmsgc) { return $1; }
# __END__
elsif (/\G ^ ( __END__ \n .*) \z /oxmsgc) { return $1; }
# \cD Control-D
# P.68 2.6.8. Other Literal Tokens
# in Chapter 2: Bits and Pieces
# of ISBN 0-596-00027-8 Programming Perl Third Edition.
# P.76 Other Literal Tokens
# in Chapter 2: Bits and Pieces
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
elsif (/\G ( \cD .*) \z /oxmsgc) { return $1; }
# \cZ Control-Z
elsif (/\G ( \cZ .*) \z /oxmsgc) { return $1; }
# any operator before div
elsif (/\G (
-- | \+\+ |
[\)\}\]]
) /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 $1; }
# system error
else {
die __FILE__, ": Oops, this shouldn't happen!";
}
}
# escape UTF-2 string
sub e_string {
my($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 = $string =~ m/ \G (\\?(?:$q_char)) /oxmsg;
# without { ... }
if (not (grep(m/\A \{ \z/xms, @char) and grep(m/\A \} \z/xms, @char))) {
if ($string !~ /<</oxms) {
return $string;
}
}
E_STRING_LOOP:
while ($string !~ /\G \z/oxgc) {
if (0) {
}
# $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> @{[Eutf2::PREMATCH()]}
elsif ($string =~ /\G ( \$` | \$\{`\} | \$ \s* PREMATCH \b | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) /oxmsgc) {
$e_string .= q{Eutf2::PREMATCH()};
$slash = 'div';
}
# $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> @{[Eutf2::MATCH()]}
elsif ($string =~ /\G ( \$& | \$\{&\} | \$ \s* MATCH \b | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) /oxmsgc) {
$e_string .= q{Eutf2::MATCH()};
$slash = 'div';
}
# $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> @{[Eutf2::POSTMATCH()]}
elsif ($string =~ /\G ( \$ \s* POSTMATCH \b | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) /oxmsgc) {
$e_string .= q{Eutf2::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|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;
$slash = 'div';
}
# functions of package Eutf2
elsif ($string =~ m{\G \b (CORE:: | ->[ ]* (?: atan2 | [a-z]{2,})) \b }oxgc) { $e_string .= $1; $slash = 'm//'; }
elsif ($string =~ m{\G \b bytes::substr \b }oxgc) { $e_string .= 'substr'; $slash = 'm//'; }
elsif ($string =~ m{\G \b chop \b }oxgc) { $e_string .= 'Eutf2::chop'; $slash = 'm//'; }
elsif ($string =~ m{\G \b bytes::index \b }oxgc) { $e_string .= 'index'; $slash = 'm//'; }
elsif ($string =~ m{\G \b UTF2::index \b }oxgc) { $e_string .= 'UTF2::index'; $slash = 'm//'; }
elsif ($string =~ m{\G \b index \b }oxgc) { $e_string .= 'Eutf2::index'; $slash = 'm//'; }
elsif ($string =~ m{\G \b bytes::rindex \b }oxgc) { $e_string .= 'rindex'; $slash = 'm//'; }
elsif ($string =~ m{\G \b UTF2::rindex \b }oxgc) { $e_string .= 'UTF2::rindex'; $slash = 'm//'; }
elsif ($string =~ m{\G \b rindex \b }oxgc) { $e_string .= 'Eutf2::rindex'; $slash = 'm//'; }
elsif ($string =~ m{\G \b lc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $e_string .= 'Eutf2::lc'; $slash = 'm//'; }
elsif ($string =~ m{\G \b lcfirst (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $e_string .= 'Eutf2::lcfirst'; $slash = 'm//'; }
elsif ($string =~ m{\G \b uc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $e_string .= 'Eutf2::uc'; $slash = 'm//'; }
elsif ($string =~ m{\G \b ucfirst (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $e_string .= 'Eutf2::ucfirst'; $slash = 'm//'; }
elsif ($string =~ m{\G \b fc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $e_string .= 'Eutf2::fc'; $slash = 'm//'; }
# "-s '' ..." means file test "-s 'filename' ..." (not means "- s/// ...")
elsif ($string =~ m{\G -s \s+ \s* (\") ((?:$qq_char)+?) (\") }oxgc) { $e_string .= '-s ' . e_qq('', $1,$3,$2); $slash = 'm//'; }
elsif ($string =~ m{\G -s \s+ qq \s* (\#) ((?:$qq_char)+?) (\#) }oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; }
elsif ($string =~ m{\G -s \s+ qq \s* (\() ((?:$qq_paren)+?) (\)) }oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; }
elsif ($string =~ m{\G -s \s+ qq \s* (\{) ((?:$qq_brace)+?) (\}) }oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; }
elsif ($string =~ m{\G -s \s+ qq \s* (\[) ((?:$qq_bracket)+?) (\]) }oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; }
elsif ($string =~ m{\G -s \s+ qq \s* (\<) ((?:$qq_angle)+?) (\>) }oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; }
elsif ($string =~ m{\G -s \s+ qq \s* (\S) ((?:$qq_char)+?) (\3) }oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; }
elsif ($string =~ m{\G -s \s+ \s* (\') ((?:\\\1|\\\\|$q_char)+?) (\') }oxgc) { $e_string .= '-s ' . e_q ('', $1,$3,$2); $slash = 'm//'; }
elsif ($string =~ m{\G -s \s+ q \s* (\#) ((?:\\\#|\\\\|$q_char)+?) (\#) }oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; }
elsif ($string =~ m{\G -s \s+ q \s* (\() ((?:\\\)|\\\\|$q_paren)+?) (\)) }oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; }
elsif ($string =~ m{\G -s \s+ q \s* (\{) ((?:\\\}|\\\\|$q_brace)+?) (\}) }oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; }
elsif ($string =~ m{\G -s \s+ q \s* (\[) ((?:\\\]|\\\\|$q_bracket)+?) (\]) }oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; }
elsif ($string =~ m{\G -s \s+ q \s* (\<) ((?:\\\>|\\\\|$q_angle)+?) (\>) }oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; }
elsif ($string =~ m{\G -s \s+ q \s* (\S) ((?:\\\1|\\\\|$q_char)+?) (\3) }oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; }
elsif ($string =~ m{\G -s \s* (\$ \w+(?: ::\w+)* (?: (?: ->)? (?: \( (?:$qq_paren)*? \) | \{ (?:$qq_brace)+? \} | \[ (?:$qq_bracket)+? \] ) )*) }oxgc)
{ $e_string .= "-s $1"; $slash = 'm//'; }
elsif ($string =~ m{\G -s \s* \( ((?:$qq_paren)*?) \) }oxgc) { $e_string .= "-s ($1)"; $slash = 'm//'; }
elsif ($string =~ m{\G -s (?= \s+ [a-z]+) }oxgc) { $e_string .= '-s'; $slash = 'm//'; }
elsif ($string =~ m{\G -s \s+ (\w+) }oxgc) { $e_string .= "-s $1"; $slash = 'm//'; }
elsif ($string =~ m{\G \b bytes::length (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $e_string .= 'length'; $slash = 'm//'; }
elsif ($string =~ m{\G \b bytes::chr (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $e_string .= 'chr'; $slash = 'm//'; }
elsif ($string =~ m{\G \b chr (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $e_string .= 'Eutf2::chr'; $slash = 'm//'; }
elsif ($string =~ m{\G \b bytes::ord (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $e_string .= 'ord'; $slash = 'div'; }
elsif ($string =~ m{\G \b ord (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $e_string .= $function_ord; $slash = 'div'; }
elsif ($string =~ m{\G \b glob (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) }oxgc) { $e_string .= 'Eutf2::glob'; $slash = 'm//'; }
elsif ($string =~ m{\G \b lc \b }oxgc) { $e_string .= 'Eutf2::lc_'; $slash = 'm//'; }
elsif ($string =~ m{\G \b lcfirst \b }oxgc) { $e_string .= 'Eutf2::lcfirst_'; $slash = 'm//'; }
elsif ($string =~ m{\G \b uc \b }oxgc) { $e_string .= 'Eutf2::uc_'; $slash = 'm//'; }
elsif ($string =~ m{\G \b ucfirst \b }oxgc) { $e_string .= 'Eutf2::ucfirst_'; $slash = 'm//'; }
elsif ($string =~ m{\G \b fc \b }oxgc) { $e_string .= 'Eutf2::fc_'; $slash = 'm//'; }
elsif ($string =~ m{\G -s \b }oxgc) { $e_string .= '-s '; $slash = 'm//'; }
elsif ($string =~ m{\G \b bytes::length \b }oxgc) { $e_string .= 'length'; $slash = 'm//'; }
elsif ($string =~ m{\G \b bytes::chr \b }oxgc) { $e_string .= 'chr'; $slash = 'm//'; }
elsif ($string =~ m{\G \b chr \b }oxgc) { $e_string .= 'Eutf2::chr_'; $slash = 'm//'; }
elsif ($string =~ m{\G \b bytes::ord \b }oxgc) { $e_string .= 'ord'; $slash = 'div'; }
elsif ($string =~ m{\G \b ord \b }oxgc) { $e_string .= $function_ord_; $slash = 'div'; }
elsif ($string =~ m{\G \b glob \b }oxgc) { $e_string .= 'Eutf2::glob_'; $slash = 'm//'; }
elsif ($string =~ m{\G \b reverse \b }oxgc) { $e_string .= $function_reverse; $slash = 'm//'; }
# split
elsif ($string =~ m{\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 'Eutf2::split' . $e; }
# split scalar value
elsif ($string =~ /\G ( [\$\@\&\*] $qq_scalar ) /oxgc) { $e_string .= 'Eutf2::split' . $e . e_string($1); next E_STRING_LOOP; }
# split literal space
elsif ($string =~ /\G \b qq (\#) [ ] (\#) /oxgc) { $e_string .= 'Eutf2::split' . $e . qq {qq$1 $2}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b qq (\s*) (\() [ ] (\)) /oxgc) { $e_string .= 'Eutf2::split' . $e . qq{$1qq$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b qq (\s*) (\{) [ ] (\}) /oxgc) { $e_string .= 'Eutf2::split' . $e . qq{$1qq$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b qq (\s*) (\[) [ ] (\]) /oxgc) { $e_string .= 'Eutf2::split' . $e . qq{$1qq$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b qq (\s*) (\<) [ ] (\>) /oxgc) { $e_string .= 'Eutf2::split' . $e . qq{$1qq$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b qq (\s*) (\S) [ ] (\2) /oxgc) { $e_string .= 'Eutf2::split' . $e . qq{$1qq$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b q (\#) [ ] (\#) /oxgc) { $e_string .= 'Eutf2::split' . $e . qq {q$1 $2}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b q (\s*) (\() [ ] (\)) /oxgc) { $e_string .= 'Eutf2::split' . $e . qq {$1q$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b q (\s*) (\{) [ ] (\}) /oxgc) { $e_string .= 'Eutf2::split' . $e . qq {$1q$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b q (\s*) (\[) [ ] (\]) /oxgc) { $e_string .= 'Eutf2::split' . $e . qq {$1q$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b q (\s*) (\<) [ ] (\>) /oxgc) { $e_string .= 'Eutf2::split' . $e . qq {$1q$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b q (\s*) (\S) [ ] (\2) /oxgc) { $e_string .= 'Eutf2::split' . $e . qq {$1q$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G ' [ ] ' /oxgc) { $e_string .= 'Eutf2::split' . $e . qq {' '}; next E_STRING_LOOP; }
elsif ($string =~ /\G " [ ] " /oxgc) { $e_string .= 'Eutf2::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 (?<![\w\$\@\%\&\*]) (\') ((?:\\\'|\\\\|$q_char)*?) (\') /oxgc) { $e_string .= e_q('',$1,$3,$2); }
# ""
elsif ($string =~ /\G (\") ((?:$qq_char)*?) (\") /oxgc) { $e_string .= e_qq('',$1,$3,$2); }
# ``
elsif ($string =~ /\G (\`) ((?:$qq_char)*?) (\`) /oxgc) { $e_string .= e_qq('',$1,$3,$2); }
# <<= <=> <= < operator
elsif ($string =~ /\G (<<=|<=>|<=|<) (?= \s* [A-Za-z_0-9'"`\$\@\&\*\(\+\-] )/oxgc) { $e_string .= $1; }
# <FILEHANDLE>
elsif ($string =~ /\G (<[\$]?[A-Za-z_][A-Za-z_0-9]*>) /oxgc) { $e_string .= $1; }
# <WILDCARD> --- glob
elsif ($string =~ /\G < ((?:$q_char)+?) > /oxgc) {
$e_string .= 'Eutf2::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;
}
# <<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;
}
# <<`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;
}
# any operator before div
elsif ($string =~ /\G (
-- | \+\+ |
[\)\}\]]
) /oxgc) { $slash = 'div'; $e_string .= $1; }
# any operator before m//
elsif ($string =~ /\G (
!~~ | !~ | != | ! |
%= | % |
&&= | && | &= | & |
-= | -> | - |
:\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 ($modifier =~ /s/) {
return '@{Eutf2::dot_s}';
}
else {
return '@{Eutf2::dot}';
}
}
else {
return Eutf2::classic_character_class($char);
}
}
#
# escape capture ($1, $2, $3, ...)
#
sub e_capture {
return join '', '$', $_[0];
}
#
# escape transliteration (tr/// or y///)
#
sub e_tr {
my($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 '') {
$e_tr = qq{Eutf2::tr(\$_,' =~ ',$charclass,$e$charclass2,'$modifier')};
}
else {
$e_tr = qq{Eutf2::tr($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 !~ m/'/oxms) {
return e_q('', "'", "'", $charclass); # --> q' '
}
elsif ($charclass !~ m{/}oxms) {
return e_q('q', '/', '/', $charclass); # --> q/ /
}
elsif ($charclass !~ m/\#/oxms) {
return e_q('q', '#', '#', $charclass); # --> q# #
}
elsif ($charclass !~ m/[\<\>]/oxms) {
return e_q('q', '<', '>', $charclass); # --> q< >
}
elsif ($charclass !~ m/[\(\)]/oxms) {
return e_q('q', '(', ')', $charclass); # --> q( )
}
elsif ($charclass !~ m/[\{\}]/oxms) {
return e_q('q', '{', '}', $charclass); # --> q{ }
}
else {
for my $char (qw( ! " $ % & * + . : = ? @ ^ ` | ~ ), "\x00".."\x1F", "\x7F", "\xFF") {
if ($charclass !~ m/\Q$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';
return join '', $ope, $delimiter, $string, $end_delimiter;
}
#
# escape qq string (qq//, "", qx//, ``)
#
sub e_qq {
my($ope,$delimiter,$end_delimiter,$string) = @_;
$slash = 'div';
my $metachar = qr/[\@\\\|]/oxms; # '|' is for qx//, ``, open() and system()
my $left_e = 0;
my $right_e = 0;
my @char = $string =~ m{ \G (
\\o\{ [0-7]+ \} |
\\x\{ [0-9A-Fa-f]+ \} |
\\N\{ [^\x80-\xFF0-9\}][^\x80-\xFF\}]* \} |
\$` | \$\{`\} | \$ \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] =~ m/\A \\o \{ ([0-7]+) \} \z/oxms) {
$char[$i] = Eutf2::octchr($1);
}
# hexadecimal escape sequence
elsif ($char[$i] =~ m/\A \\x \{ ([0-9A-Fa-f]+) \} \z/oxms) {
$char[$i] = Eutf2::hexchr($1);
}
# \N{CHARNAME} --> N{CHARNAME}
elsif ($char[$i] =~ m/\A \\ ( N\{ ([^\x80-\xFF0-9\}][^\x80-\xFF\}]*) \} ) \z/oxms) {
$char[$i] = $1;
}
if (0) {
}
# escape last octet of multiple-octet
elsif ($char[$i] =~ m/\A ([\x80-\xFF].*) ($metachar|\Q$delimiter\E|\Q$end_delimiter\E) \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[$i] =~ m/\A ([<>]) \z/oxms) {
if ($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] = '@{[Eutf2::ucfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\l') {
$char[$i] = '@{[Eutf2::lcfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\U') {
$char[$i] = '@{[Eutf2::uc qq<';
$left_e++;
}
elsif ($char[$i] eq '\L') {
$char[$i] = '@{[Eutf2::lc qq<';
$left_e++;
}
elsif ($char[$i] eq '\F') {
$char[$i] = '@{[Eutf2::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[$i] =~ m/\A \$ 0 \z/oxms) {
}
elsif ($char[$i] =~ m/\A \$ \{ \s* 0 \s* \} \z/oxms) {
}
# $$ --> $$
elsif ($char[$i] =~ m/\A \$\$ \z/oxms) {
}
# $1, $2, $3 --> $2, $3, $4 (only when multibyte anchoring is enable)
elsif ($char[$i] =~ m/\A \$ ([1-9][0-9]*) \z/oxms) {
$char[$i] = e_capture($1);
}
elsif ($char[$i] =~ m/\A \$ \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
}
# $$foo[ ... ] --> $ $foo->[ ... ]
elsif ($char[$i] =~ m/\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);
}
# $$foo{ ... } --> $ $foo->{ ... }
elsif ($char[$i] =~ m/\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ (?:$qq_brace)*? \} ) \z/oxms) {
$char[$i] = e_capture($1.'->'.$2);
}
# $$foo
elsif ($char[$i] =~ m/\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) \z/oxms) {
$char[$i] = e_capture($1);
}
# $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> Eutf2::PREMATCH()
elsif ($char[$i] =~ /\A ( \$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) \z/oxmsgc) {
$char[$i] = '@{[Eutf2::PREMATCH()]}';
}
# $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Eutf2::MATCH()
elsif ($char[$i] =~ /\A ( \$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) \z/oxmsgc) {
$char[$i] = '@{[Eutf2::MATCH()]}';
}
# $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Eutf2::POSTMATCH()
elsif ($char[$i] =~ /\A ( \$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) \z/oxmsgc) {
$char[$i] = '@{[Eutf2::POSTMATCH()]}';
}
# ${ foo } --> ${ foo }
elsif ($char[$i] =~ m/\A \$ \s* \{ \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* \} \z/oxms) {
}
# ${ ... }
elsif ($char[$i] =~ m/\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 =~ m/\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 =~ m/\G ([\x00-\xFF]) /oxmsg;
for my $octet (@octet) {
if ($octet =~ m/\A (['\\]) \z/oxms) {
$octet = '\\' . $1;
}
}
$string = join '', @octet;
}
return join '', '(', (join ', ', map { "'$_'" } @string), ')';
}
#
# escape here document (<<"HEREDOC", <<HEREDOC, <<`HEREDOC`)
#
sub e_heredoc {
my($string) = @_;
$slash = 'm//';
my $metachar = qr/[\@\\|]/oxms; # '|' is for <<`HEREDOC`
my $left_e = 0;
my $right_e = 0;
my @char = $string =~ m{ \G (
\\o\{ [0-7]+ \} |
\\x\{ [0-9A-Fa-f]+ \} |
\\N\{ [^\x80-\xFF0-9\}][^\x80-\xFF\}]* \} |
\$` | \$\{`\} | \$ \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] =~ m/\A \\o \{ ([0-7]+) \} \z/oxms) {
$char[$i] = Eutf2::octchr($1);
}
# hexadecimal escape sequence
elsif ($char[$i] =~ m/\A \\x \{ ([0-9A-Fa-f]+) \} \z/oxms) {
$char[$i] = Eutf2::hexchr($1);
}
# \N{CHARNAME} --> N{CHARNAME}
elsif ($char[$i] =~ m/\A \\ ( N\{ ([^\x80-\xFF0-9\}][^\x80-\xFF\}]*) \} ) \z/oxms) {
$char[$i] = $1;
}
if (0) {
}
# escape character
elsif ($char[$i] =~ m/\A ([\x80-\xFF].*) ($metachar) \z/oxms) {
$char[$i] = $1 . '\\' . $2;
}
# \u \l \U \L \F \Q \E
elsif ($char[$i] =~ m/\A ([<>]) \z/oxms) {
if ($right_e < $left_e) {
$char[$i] = '\\' . $char[$i];
}
}
elsif ($char[$i] eq '\u') {
$char[$i] = '@{[Eutf2::ucfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\l') {
$char[$i] = '@{[Eutf2::lcfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\U') {
$char[$i] = '@{[Eutf2::uc qq<';
$left_e++;
}
elsif ($char[$i] eq '\L') {
$char[$i] = '@{[Eutf2::lc qq<';
$left_e++;
}
elsif ($char[$i] eq '\F') {
$char[$i] = '@{[Eutf2::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[$i] =~ m/\A \$ 0 \z/oxms) {
}
elsif ($char[$i] =~ m/\A \$ \{ \s* 0 \s* \} \z/oxms) {
}
# $$ --> $$
elsif ($char[$i] =~ m/\A \$\$ \z/oxms) {
}
# $1, $2, $3 --> $2, $3, $4 (only when multibyte anchoring is enable)
elsif ($char[$i] =~ m/\A \$ ([1-9][0-9]*) \z/oxms) {
$char[$i] = e_capture($1);
}
elsif ($char[$i] =~ m/\A \$ \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
}
# $$foo[ ... ] --> $ $foo->[ ... ]
elsif ($char[$i] =~ m/\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);
}
# $$foo{ ... } --> $ $foo->{ ... }
elsif ($char[$i] =~ m/\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ (?:$qq_brace)*? \} ) \z/oxms) {
$char[$i] = e_capture($1.'->'.$2);
}
# $$foo
elsif ($char[$i] =~ m/\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) \z/oxms) {
$char[$i] = e_capture($1);
}
# $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> Eutf2::PREMATCH()
elsif ($char[$i] =~ /\A ( \$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) \z/oxmsgc) {
$char[$i] = '@{[Eutf2::PREMATCH()]}';
}
# $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Eutf2::MATCH()
elsif ($char[$i] =~ /\A ( \$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) \z/oxmsgc) {
$char[$i] = '@{[Eutf2::MATCH()]}';
}
# $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Eutf2::POSTMATCH()
elsif ($char[$i] =~ /\A ( \$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) \z/oxmsgc) {
$char[$i] = '@{[Eutf2::POSTMATCH()]}';
}
# ${ foo } --> ${ foo }
elsif ($char[$i] =~ m/\A \$ \s* \{ \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* \} \z/oxms) {
}
# ${ ... }
elsif ($char[$i] =~ m/\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 =~ m/([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 =~ m/ [\@:] /oxms) {
my @char = $string =~ m{\G([\x00-\xFF])}oxmsg;
my %octet = map {$_ => 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 =~ m/\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 =~ m/i/oxms) ? 1 : 0;
my $metachar = qr/[\@\\|[\]{^]/oxms;
# split regexp
my @char = $string =~ m{\G(
\\o\{ [0-7]+ \} |
\\ [0-7]{2,3} |
\\x\{ [0-9A-Fa-f]+ \} |
\\x [0-9A-Fa-f]{1,2} |
\\c [\x40-\x5F] |
\\N\{ [^\x80-\xFF0-9\}][^\x80-\xFF\}]* \} |
\\p\{ [^\x80-\xFF0-9\}][^\x80-\xFF\}]* \} |
\\P\{ [^\x80-\xFF0-9\}][^\x80-\xFF\}]* \} |
\\ (?:$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 =~ m/ [\@:] /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] =~ m/\A \\o \{ ([0-7]+) \} \z/oxms) {
$char[$i] = Eutf2::octchr($1);
}
# hexadecimal escape sequence
elsif ($char[$i] =~ m/\A \\x \{ ([0-9A-Fa-f]+) \} \z/oxms) {
$char[$i] = Eutf2::hexchr($1);
}
# \N{CHARNAME} --> N{CHARNAME}
elsif ($char[$i] =~ m/\A \\ ( N\{ ([^\x80-\xFF0-9\}][^\x80-\xFF\}]*) \} ) \z/oxms) {
$char[$i] = $1;
}
# \p{PROPERTY} --> p{PROPERTY}
elsif ($char[$i] =~ m/\A \\ ( p\{ ([^\x80-\xFF0-9\}][^\x80-\xFF\}]*) \} ) \z/oxms) {
$char[$i] = $1;
}
# \P{PROPERTY} --> P{PROPERTY}
elsif ($char[$i] =~ m/\A \\ ( P\{ ([^\x80-\xFF0-9\}][^\x80-\xFF\}]*) \} ) \z/oxms) {
$char[$i] = $1;
}
# \p, \P, \X --> p, P, X
elsif ($char[$i] =~ m/\A \\ ( [pPX] ) \z/oxms) {
$char[$i] = $1;
}
if (0) {
}
# join separated multiple-octet
elsif ($char[$i] =~ m/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms) {
if ( ($i+3 <= $#char) and (grep(m/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+3]) == 3) and (eval(sprintf '"%s%s%s%s"', @char[$i..$i+3]) =~ m/\A $q_char \z/oxms)) {
$char[$i] .= join '', splice @char, $i+1, 3;
}
elsif (($i+2 <= $#char) and (grep(m/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+2]) == 2) and (eval(sprintf '"%s%s%s"', @char[$i..$i+2]) =~ m/\A $q_char \z/oxms)) {
$char[$i] .= join '', splice @char, $i+1, 2;
}
elsif (($i+1 <= $#char) and (grep(m/\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]) =~ m/\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;
# [...]
splice @char, $left, $right-$left+1, Eutf2::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;
# [^...]
splice @char, $left, $right-$left+1, Eutf2::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] =~ m/\A [\x00-\xFF] \z/oxms) and (Eutf2::uc($char[$i]) ne Eutf2::fc($char[$i]))) {
if (CORE::length(Eutf2::fc($char[$i])) == 1) {
$char[$i] = '[' . Eutf2::uc($char[$i]) . Eutf2::fc($char[$i]) . ']';
}
else {
$char[$i] = '(?:' . Eutf2::uc($char[$i]) . '|' . Eutf2::fc($char[$i]) . ')';
}
}
# \u \l \U \L \F \Q \E
elsif ($char[$i] =~ m/\A [<>] \z/oxms) {
if ($right_e < $left_e) {
$char[$i] = '\\' . $char[$i];
}
}
elsif ($char[$i] eq '\u') {
$char[$i] = '@{[Eutf2::ucfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\l') {
$char[$i] = '@{[Eutf2::lcfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\U') {
$char[$i] = '@{[Eutf2::uc qq<';
$left_e++;
}
elsif ($char[$i] eq '\L') {
$char[$i] = '@{[Eutf2::lc qq<';
$left_e++;
}
elsif ($char[$i] eq '\F') {
$char[$i] = '@{[Eutf2::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[$i] =~ m/\A \$ 0 \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
elsif ($char[$i] =~ m/\A \$ \{ \s* 0 \s* \} \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $$ --> $$
elsif ($char[$i] =~ m/\A \$\$ \z/oxms) {
}
# $1, $2, $3 --> $2, $3, $4 (only when multibyte anchoring is enable)
elsif ($char[$i] =~ m/\A \$ ([1-9][0-9]*) \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
elsif ($char[$i] =~ m/\A \$ \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo[ ... ] --> $ $foo->[ ... ]
elsif ($char[$i] =~ m/\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] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo{ ... } --> $ $foo->{ ... }
elsif ($char[$i] =~ m/\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ (?:$qq_brace)*? \} ) \z/oxms) {
$char[$i] = e_capture($1.'->'.$2);
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo
elsif ($char[$i] =~ m/\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] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> Eutf2::PREMATCH()
elsif ($char[$i] =~ /\A ( \$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(Eutf2::PREMATCH())]}';
}
else {
$char[$i] = '@{[Eutf2::PREMATCH()]}';
}
}
# $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Eutf2::MATCH()
elsif ($char[$i] =~ /\A ( \$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(Eutf2::MATCH())]}';
}
else {
$char[$i] = '@{[Eutf2::MATCH()]}';
}
}
# $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Eutf2::POSTMATCH()
elsif ($char[$i] =~ /\A ( \$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(Eutf2::POSTMATCH())]}';
}
else {
$char[$i] = '@{[Eutf2::POSTMATCH()]}';
}
}
# ${ foo }
elsif ($char[$i] =~ m/\A \$ \s* \{ ( \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* ) \} \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# ${ ... }
elsif ($char[$i] =~ m/\A \$ \s* \{ \s* ( .+ ) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $scalar or @array
elsif ($char[$i] =~ m/\A [\$\@].+ /oxms) {
$char[$i] = e_string($char[$i]);
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# quote character before ? + * {
elsif (($i >= 1) and ($char[$i] =~ m/\A [\?\+\*\{] \z/oxms)) {
if ($char[$i-1] =~ m/\A (?:[\x00-\xFF]|\\[0-7]{2,3}|\\x[0-9-A-Fa-f]{1,2}) \z/oxms) {
}
elsif (($ope =~ m/\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 =~ m/\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 =~ m/\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, $modifier;
}
}
#
# escape regexp (m'', qr'' and m''b, qr''b)
#
sub e_qr_q {
my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_;
$modifier ||= '';
$modifier =~ tr/p//d;
if ($modifier =~ m/([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 =~ m/i/oxms) ? 1 : 0;
# split regexp
my @char = $string =~ m{\G(
\[\:\^ [a-z]+ \:\] |
\[\: [a-z]+ \:\] |
\[\^ |
[\$\@/\\] |
\\? (?:$q_char)
)}oxmsg;
# unescape character
for (my $i=0; $i <= $#char; $i++) {
if (0) {
}
# 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, Eutf2::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, Eutf2::charlist_not_qr(@char[$left+1..$right-1], $modifier);
$i = $left;
last;
}
}
}
# escape $ @ / and \
elsif ($char[$i] =~ m{\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] =~ m/\A [\x00-\xFF] \z/oxms) and (Eutf2::uc($char[$i]) ne Eutf2::fc($char[$i]))) {
if (CORE::length(Eutf2::fc($char[$i])) == 1) {
$char[$i] = '[' . Eutf2::uc($char[$i]) . Eutf2::fc($char[$i]) . ']';
}
else {
$char[$i] = '(?:' . Eutf2::uc($char[$i]) . '|' . Eutf2::fc($char[$i]) . ')';
}
}
# quote character before ? + * {
elsif (($i >= 1) and ($char[$i] =~ m/\A [\?\+\*\{] \z/oxms)) {
if ($char[$i-1] =~ m/\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 =~ m{\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] =~ m{\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 =~ m/([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 =~ m/ [\@:] /oxms) {
my @char = $string =~ m{\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 = '';
return join '', $ope, $delimiter, $prematch, '(?:', $string, ')', $matched, $end_delimiter, $modifier;
}
my $ignorecase = ($modifier =~ m/i/oxms) ? 1 : 0;
my $metachar = qr/[\@\\|[\]{^]/oxms;
# split regexp
my @char = $string =~ m{\G(
\\g \s* \{ \s* - \s* [1-9][0-9]* \s* \} |
\\g \s* \{ \s* [1-9][0-9]* \s* \} |
\\g \s* [1-9][0-9]* |
\\o\{ [0-7]+ \} |
\\ [1-9][0-9]* |
\\ [0-7]{2,3} |
\\x\{ [0-9A-Fa-f]+ \} |
\\x [0-9A-Fa-f]{1,2} |
\\c [\x40-\x5F] |
\\N\{ [^\x80-\xFF0-9\}][^\x80-\xFF\}]* \} |
\\p\{ [^\x80-\xFF0-9\}][^\x80-\xFF\}]* \} |
\\P\{ [^\x80-\xFF0-9\}][^\x80-\xFF\}]* \} |
\\ (?:$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 =~ m/ [\@:] /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] =~ m/\A \\o \{ ([0-7]+) \} \z/oxms) {
$char[$i] = Eutf2::octchr($1);
}
# hexadecimal escape sequence
elsif ($char[$i] =~ m/\A \\x \{ ([0-9A-Fa-f]+) \} \z/oxms) {
$char[$i] = Eutf2::hexchr($1);
}
# \N{CHARNAME} --> N{CHARNAME}
elsif ($char[$i] =~ m/\A \\ ( N\{ ([^\x80-\xFF0-9\}][^\x80-\xFF\}]*) \} ) \z/oxms) {
$char[$i] = $1;
}
# \p{PROPERTY} --> p{PROPERTY}
elsif ($char[$i] =~ m/\A \\ ( p\{ ([^\x80-\xFF0-9\}][^\x80-\xFF\}]*) \} ) \z/oxms) {
$char[$i] = $1;
}
# \P{PROPERTY} --> P{PROPERTY}
elsif ($char[$i] =~ m/\A \\ ( P\{ ([^\x80-\xFF0-9\}][^\x80-\xFF\}]*) \} ) \z/oxms) {
$char[$i] = $1;
}
# \p, \P, \X --> p, P, X
elsif ($char[$i] =~ m/\A \\ ( [pPX] ) \z/oxms) {
$char[$i] = $1;
}
if (0) {
}
# join separated multiple-octet
elsif ($char[$i] =~ m/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms) {
if ( ($i+3 <= $#char) and (grep(m/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+3]) == 3) and (eval(sprintf '"%s%s%s%s"', @char[$i..$i+3]) =~ m/\A $q_char \z/oxms)) {
$char[$i] .= join '', splice @char, $i+1, 3;
}
elsif (($i+2 <= $#char) and (grep(m/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+2]) == 2) and (eval(sprintf '"%s%s%s"', @char[$i..$i+2]) =~ m/\A $q_char \z/oxms)) {
$char[$i] .= join '', splice @char, $i+1, 2;
}
elsif (($i+1 <= $#char) and (grep(m/\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]) =~ m/\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;
# [...]
splice @char, $left, $right-$left+1, Eutf2::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, Eutf2::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] =~ m/\A [\x00-\xFF] \z/oxms) and (Eutf2::uc($char[$i]) ne Eutf2::fc($char[$i]))) {
if (CORE::length(Eutf2::fc($char[$i])) == 1) {
$char[$i] = '[' . Eutf2::uc($char[$i]) . Eutf2::fc($char[$i]) . ']';
}
else {
$char[$i] = '(?:' . Eutf2::uc($char[$i]) . '|' . Eutf2::fc($char[$i]) . ')';
}
}
# \u \l \U \L \F \Q \E
elsif ($char[$i] =~ m/\A [<>] \z/oxms) {
if ($right_e < $left_e) {
$char[$i] = '\\' . $char[$i];
}
}
elsif ($char[$i] eq '\u') {
$char[$i] = '@{[Eutf2::ucfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\l') {
$char[$i] = '@{[Eutf2::lcfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\U') {
$char[$i] = '@{[Eutf2::uc qq<';
$left_e++;
}
elsif ($char[$i] eq '\L') {
$char[$i] = '@{[Eutf2::lc qq<';
$left_e++;
}
elsif ($char[$i] eq '\F') {
$char[$i] = '@{[Eutf2::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[$i] =~ m/\A \\ \s* 0 \z/oxms) {
}
# \g{N}, \g{-N}
# P.108 Using Simple Patterns
# in Chapter 7: In the World of Regular Expressions
# of ISBN 978-0-596-52010-6 Learning Perl, Fifth Edition
# P.221 Capturing
# in Chapter 5: Pattern Matching
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
# \g{-1}, \g{-2}, \g{-3} --> \g{-1}, \g{-2}, \g{-3}
elsif ($char[$i] =~ m/\A \\g \s* \{ \s* - \s* ([1-9][0-9]*) \s* \} \z/oxms) {
}
# \g{1}, \g{2}, \g{3} --> \g{2}, \g{3}, \g{4} (only when multibyte anchoring is enable)
elsif ($char[$i] =~ m/\A \\g \s* \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) {
}
# \g1, \g2, \g3 --> \g2, \g3, \g4 (only when multibyte anchoring is enable)
elsif ($char[$i] =~ m/\A \\g \s* ([1-9][0-9]*) \z/oxms) {
}
# \1, \2, \3 --> \2, \3, \4 (only when multibyte anchoring is enable)
elsif ($char[$i] =~ m/\A \\ \s* ([1-9][0-9]*) \z/oxms) {
}
# $0 --> $0
elsif ($char[$i] =~ m/\A \$ 0 \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
elsif ($char[$i] =~ m/\A \$ \{ \s* 0 \s* \} \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $$ --> $$
elsif ($char[$i] =~ m/\A \$\$ \z/oxms) {
}
# $1, $2, $3 --> $2, $3, $4 (only when multibyte anchoring is enable)
elsif ($char[$i] =~ m/\A \$ ([1-9][0-9]*) \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
elsif ($char[$i] =~ m/\A \$ \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo[ ... ] --> $ $foo->[ ... ]
elsif ($char[$i] =~ m/\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] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo{ ... } --> $ $foo->{ ... }
elsif ($char[$i] =~ m/\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ (?:$qq_brace)*? \} ) \z/oxms) {
$char[$i] = e_capture($1.'->'.$2);
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo
elsif ($char[$i] =~ m/\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] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> Eutf2::PREMATCH()
elsif ($char[$i] =~ /\A ( \$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(Eutf2::PREMATCH())]}';
}
else {
$char[$i] = '@{[Eutf2::PREMATCH()]}';
}
}
# $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Eutf2::MATCH()
elsif ($char[$i] =~ /\A ( \$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(Eutf2::MATCH())]}';
}
else {
$char[$i] = '@{[Eutf2::MATCH()]}';
}
}
# $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Eutf2::POSTMATCH()
elsif ($char[$i] =~ /\A ( \$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(Eutf2::POSTMATCH())]}';
}
else {
$char[$i] = '@{[Eutf2::POSTMATCH()]}';
}
}
# ${ foo }
elsif ($char[$i] =~ m/\A \$ \s* \{ ( \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* ) \} \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# ${ ... }
elsif ($char[$i] =~ m/\A \$ \s* \{ \s* ( .+ ) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $scalar or @array
elsif ($char[$i] =~ m/\A [\$\@].+ /oxms) {
$char[$i] = e_string($char[$i]);
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# quote character before ? + * {
elsif (($i >= 1) and ($char[$i] =~ m/\A [\?\+\*\{] \z/oxms)) {
if ($char[$i-1] =~ m/\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 = '';
$modifier =~ tr/i//d;
if ($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 =~ m/([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 =~ m/i/oxms) ? 1 : 0;
# split regexp
my @char = $string =~ m{\G(
\[\:\^ [a-z]+ \:\] |
\[\: [a-z]+ \:\] |
\[\^ |
[\$\@/\\] |
\\? (?:$q_char)
)}oxmsg;
# unescape character
for (my $i=0; $i <= $#char; $i++) {
if (0) {
}
# open character class [...]
elsif ($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, Eutf2::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, Eutf2::charlist_not_qr(@char[$left+1..$right-1], $modifier);
$i = $left;
last;
}
}
}
# escape $ @ / and \
elsif ($char[$i] =~ m{\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] =~ m/\A [\x00-\xFF] \z/oxms) and (Eutf2::uc($char[$i]) ne Eutf2::fc($char[$i]))) {
if (CORE::length(Eutf2::fc($char[$i])) == 1) {
$char[$i] = '[' . Eutf2::uc($char[$i]) . Eutf2::fc($char[$i]) . ']';
}
else {
$char[$i] = '(?:' . Eutf2::uc($char[$i]) . '|' . Eutf2::fc($char[$i]) . ')';
}
}
# quote character before ? + * {
elsif (($i >= 1) and ($char[$i] =~ m/\A [\?\+\*\{] \z/oxms)) {
if ($char[$i-1] =~ m/\A [\x00-\xFF] \z/oxms) {
}
else {
$char[$i-1] = '(?:' . $char[$i-1] . ')';
}
}
}
$modifier =~ tr/i//d;
$delimiter = '/';
$end_delimiter = '/';
my $prematch = '';
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 =~ m{\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] =~ m{\A [\$\@/\\] \z}oxms) {
$char[$i] = '\\' . $char[$i];
}
}
$delimiter = '/';
$end_delimiter = '/';
my $prematch = '';
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 = $string =~ m/ \G (\\\\|[\$\@\/\\]|$q_char) /oxmsg;
for (my $i=0; $i <= $#char; $i++) {
if (0) {
}
# not escape \\
elsif ($char[$i] =~ m{\A \\\\ \z}oxms) {
}
# escape $ @ / and \
elsif ($char[$i] =~ m{\A [\$\@/\\] \z}oxms) {
$char[$i] = '\\' . $char[$i];
}
}
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 =~ m/([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 without multibyte anchoring
elsif ($modifier =~ m/g/oxms) {
$sub = sprintf(
# 1 2 3 4 5 6 7 8 9 10 1112 13 14 15 16
q<eval{%s %s_t=%s; while(%s_t%s%s){%s local $^W=0; %s %s_r=%s; %s%s_t="$`%s_r$'"; pos(%s_t)=length "$`%s_r"; } return %s_t}>,
$local, # 1
$variable_basename, # 2
$variable, # 3
$variable_basename, # 4
$bind_operator, # 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_basename, # 12
$variable_basename, # 13
$variable_basename, # 14
$variable_basename, # 15
$variable_basename, # 16
);
}
# s///r
else {
my $prematch = q{$`};
$sub = sprintf(
# 1 2 3 4 5 6 7 8 9 10 11
q<(%s%s%s) ? eval{%s local $^W=0; %s %s_r=%s; %s"%s%s_r$'" } : %s>,
$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
$prematch, # 9
$variable_basename, # 10
$variable, # 11
);
}
# $var !~ s///r doesn't make sense
if ($bind_operator =~ m/ !~ /oxms) {
$sub = q{die("$0: Using !~ with s///r doesn't make sense"), } . $sub;
}
}
# without /r
else {
if (0) {
}
# s///g without multibyte anchoring
elsif ($modifier =~ m/g/oxms) {
$sub = sprintf(
# 1 2 3 4 5 6 7 8 9 1011 12 13 14 15 16
q<eval{%s %s_n=0; while(%s%s%s){%s local $^W=0; %s %s_r=%s; %s%s="$`%s_r$'"; pos(%s)=length "$`%s_r"; %s_n++} return %s_n}>,
$local, # 1
$variable_basename, # 2
$variable, # 3
$bind_operator, # 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, # 11
$variable_basename, # 12
$variable, # 13
$variable_basename, # 14
$variable_basename, # 15
$variable_basename, # 16
);
}
# s///
else {
my $prematch = q{$`};
$sub = sprintf(
# 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>,
$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 regexp of split qr//
#
sub e_split {
my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_;
$modifier ||= '';
$modifier =~ tr/p//d;
if ($modifier =~ m/([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 =~ m/i/oxms) ? 1 : 0;
my $metachar = qr/[\@\\|[\]{^]/oxms;
# split regexp
my @char = $string =~ m{\G(
\\o\{ [0-7]+ \} |
\\ [0-7]{2,3} |
\\x\{ [0-9A-Fa-f]+ \} |
\\x [0-9A-Fa-f]{1,2} |
\\c [\x40-\x5F] |
\\N\{ [^\x80-\xFF0-9\}][^\x80-\xFF\}]* \} |
\\p\{ [^\x80-\xFF0-9\}][^\x80-\xFF\}]* \} |
\\P\{ [^\x80-\xFF0-9\}][^\x80-\xFF\}]* \} |
\\ (?:$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;
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] =~ m/\A \\o \{ ([0-7]+) \} \z/oxms) {
$char[$i] = Eutf2::octchr($1);
}
# hexadecimal escape sequence
elsif ($char[$i] =~ m/\A \\x \{ ([0-9A-Fa-f]+) \} \z/oxms) {
$char[$i] = Eutf2::hexchr($1);
}
# \N{CHARNAME} --> N{CHARNAME}
elsif ($char[$i] =~ m/\A \\ ( N\{ ([^\x80-\xFF0-9\}][^\x80-\xFF\}]*) \} ) \z/oxms) {
$char[$i] = $1;
}
# \p{PROPERTY} --> p{PROPERTY}
elsif ($char[$i] =~ m/\A \\ ( p\{ ([^\x80-\xFF0-9\}][^\x80-\xFF\}]*) \} ) \z/oxms) {
$char[$i] = $1;
}
# \P{PROPERTY} --> P{PROPERTY}
elsif ($char[$i] =~ m/\A \\ ( P\{ ([^\x80-\xFF0-9\}][^\x80-\xFF\}]*) \} ) \z/oxms) {
$char[$i] = $1;
}
# \p, \P, \X --> p, P, X
elsif ($char[$i] =~ m/\A \\ ( [pPX] ) \z/oxms) {
$char[$i] = $1;
}
if (0) {
}
# join separated multiple-octet
elsif ($char[$i] =~ m/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms) {
if ( ($i+3 <= $#char) and (grep(m/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+3]) == 3) and (eval(sprintf '"%s%s%s%s"', @char[$i..$i+3]) =~ m/\A $q_char \z/oxms)) {
$char[$i] .= join '', splice @char, $i+1, 3;
}
elsif (($i+2 <= $#char) and (grep(m/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+2]) == 2) and (eval(sprintf '"%s%s%s"', @char[$i..$i+2]) =~ m/\A $q_char \z/oxms)) {
$char[$i] .= join '', splice @char, $i+1, 2;
}
elsif (($i+1 <= $#char) and (grep(m/\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]) =~ m/\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;
# [...]
splice @char, $left, $right-$left+1, Eutf2::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, Eutf2::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/m/oxms)) {
$modifier .= 'm';
}
# /i modifier
elsif ($ignorecase and ($char[$i] =~ m/\A [\x00-\xFF] \z/oxms) and (Eutf2::uc($char[$i]) ne Eutf2::fc($char[$i]))) {
if (CORE::length(Eutf2::fc($char[$i])) == 1) {
$char[$i] = '[' . Eutf2::uc($char[$i]) . Eutf2::fc($char[$i]) . ']';
}
else {
$char[$i] = '(?:' . Eutf2::uc($char[$i]) . '|' . Eutf2::fc($char[$i]) . ')';
}
}
# \u \l \U \L \F \Q \E
elsif ($char[$i] =~ m/\A ([<>]) \z/oxms) {
if ($right_e < $left_e) {
$char[$i] = '\\' . $char[$i];
}
}
elsif ($char[$i] eq '\u') {
$char[$i] = '@{[Eutf2::ucfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\l') {
$char[$i] = '@{[Eutf2::lcfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\U') {
$char[$i] = '@{[Eutf2::uc qq<';
$left_e++;
}
elsif ($char[$i] eq '\L') {
$char[$i] = '@{[Eutf2::lc qq<';
$left_e++;
}
elsif ($char[$i] eq '\F') {
$char[$i] = '@{[Eutf2::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[$i] =~ m/\A \$ 0 \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
elsif ($char[$i] =~ m/\A \$ \{ \s* 0 \s* \} \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $$ --> $$
elsif ($char[$i] =~ m/\A \$\$ \z/oxms) {
}
# $1, $2, $3 --> $2, $3, $4 (only when multibyte anchoring is enable)
elsif ($char[$i] =~ m/\A \$ ([1-9][0-9]*) \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
elsif ($char[$i] =~ m/\A \$ \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo[ ... ] --> $ $foo->[ ... ]
elsif ($char[$i] =~ m/\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] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo{ ... } --> $ $foo->{ ... }
elsif ($char[$i] =~ m/\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ (?:$qq_brace)*? \} ) \z/oxms) {
$char[$i] = e_capture($1.'->'.$2);
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo
elsif ($char[$i] =~ m/\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] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> Eutf2::PREMATCH()
elsif ($char[$i] =~ /\A ( \$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(Eutf2::PREMATCH())]}';
}
else {
$char[$i] = '@{[Eutf2::PREMATCH()]}';
}
}
# $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Eutf2::MATCH()
elsif ($char[$i] =~ /\A ( \$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(Eutf2::MATCH())]}';
}
else {
$char[$i] = '@{[Eutf2::MATCH()]}';
}
}
# $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Eutf2::POSTMATCH()
elsif ($char[$i] =~ /\A ( \$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(Eutf2::POSTMATCH())]}';
}
else {
$char[$i] = '@{[Eutf2::POSTMATCH()]}';
}
}
# ${ foo }
elsif ($char[$i] =~ m/\A \$ \s* \{ ( \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* ) \} \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $1 . ')]}';
}
}
# ${ ... }
elsif ($char[$i] =~ m/\A \$ \s* \{ \s* ( .+ ) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# $scalar or @array
elsif ($char[$i] =~ m/\A [\$\@].+ /oxms) {
$char[$i] = e_string($char[$i]);
if ($ignorecase) {
$char[$i] = '@{[Eutf2::ignorecase(' . $char[$i] . ')]}';
}
}
# quote character before ? + * {
elsif (($i >= 1) and ($char[$i] =~ m/\A [\?\+\*\{] \z/oxms)) {
if ($char[$i-1] =~ m/\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 '', 'Eutf2::split', $ope, $delimiter, @char, '>]}' x ($left_e - $right_e), $end_delimiter, $modifier;
}
return join '', 'Eutf2::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 =~ m/([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 =~ m/i/oxms) ? 1 : 0;
# split regexp
my @char = $string =~ m{\G(
\[\:\^ [a-z]+ \:\] |
\[\: [a-z]+ \:\] |
\[\^ |
\\? (?:$q_char)
)}oxmsg;
# unescape character
for (my $i=0; $i <= $#char; $i++) {
if (0) {
}
# open character class [...]
elsif ($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, Eutf2::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, Eutf2::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/m/oxms)) {
$modifier .= 'm';
}
# /i modifier
elsif ($ignorecase and ($char[$i] =~ m/\A [\x00-\xFF] \z/oxms) and (Eutf2::uc($char[$i]) ne Eutf2::fc($char[$i]))) {
if (CORE::length(Eutf2::fc($char[$i])) == 1) {
$char[$i] = '[' . Eutf2::uc($char[$i]) . Eutf2::fc($char[$i]) . ']';
}
else {
$char[$i] = '(?:' . Eutf2::uc($char[$i]) . '|' . Eutf2::fc($char[$i]) . ')';
}
}
# quote character before ? + * {
elsif (($i >= 1) and ($char[$i] =~ m/\A [\?\+\*\{] \z/oxms)) {
if ($char[$i-1] =~ m/\A [\x00-\xFF] \z/oxms) {
}
else {
$char[$i-1] = '(?:' . $char[$i-1] . ')';
}
}
}
$modifier =~ tr/i//d;
return join '', 'Eutf2::split', $ope, $delimiter, @char, $end_delimiter, $modifier;
}
1;
__END__
=pod
=head1 NAME
UTF2 - Source code filter to escape UTF-2
=head1 SYNOPSIS
use UTF2;
use UTF2 version; --- require version
use UTF2 qw(ord reverse); --- demand enhanced feature of ord and reverse
use UTF2 version qw(ord reverse);
# "no UTF2;" not supported
or
$ perl UTF2.pm UTF-2_script.pl > Escaped_script.pl.e
then
$ perl Escaped_script.pl.e
UTF-2_script.pl --- script written in UTF-2
Escaped_script.pl.e --- escaped script
functions:
UTF2::ord(...);
UTF2::reverse(...);
UTF2::length(...);
UTF2::substr(...);
UTF2::index(...);
UTF2::rindex(...);
CORE::chop(...);
CORE::ord(...);
CORE::reverse(...);
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
Let's start with a bit of history: jperl 4.019+1.3 introduced UTF-2 support.
You could apply chop() and regexps even to complex CJK characters.
JPerl in CPAN Perl Ports (Binary Distributions)
said before,
As of Perl 5.8.0 it is suggested that instead of JPerl (which is
based on a quite old release of Perl) you should just use Perl 5.8.0,
since it can do all that JPerl did, and more.
But was it really so?
In this country, UTF-2 is widely used on mainframe I/O, the personal computer,
and the cellular phone. This software treats UTF-2 directly, but doesn't treat
Latin-1. Therefore, this software doesn't use UTF8 flag.
Shall we escape from the encode problem?
=head1 Yet Another Future Of
JPerl is very useful software. -- Oops, note, this "JPerl" means Japanized or
Japanese Perl, so is unrelated to Java and JVM. Therefore, I named this software
better, fitter UTF2.
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
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 UTF-2
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 UTF-2, 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
Let's make yet another future by JPerl's future.
=head1 JRE: JPerl Runtime Environment
+---------------------------------------+
| JPerl Application Script | Your Script
+---------------------------------------+
| Source Code Filter, Runtime Routine | ex. UTF2.pm, Eutf2.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
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 Software Composition
UTF2.pm --- source code filter to escape UTF-2
Eutf2.pm --- run-time routines for UTF2.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
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
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
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 UTF2;' in your script.
---------------------------------
Before You do
---------------------------------
(nothing) use UTF2;
---------------------------------
=head1 Multiple-Octet Character Regular Expression (UTF2.pm provides)
UTF2.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/...@{Eutf2::eD}.../
m/...[[:^digit:]].../ m/...@{Eutf2::not_digit}.../
--------------------------------------------------------------------------------
=head1 Calling 'Eutf2::ignorecase()' (UTF2.pm provides)
UTF2.pm applies calling 'Eutf2::ignorecase()' instead of /i modifier.
--------------------------------------------------------------------------------
Before After
--------------------------------------------------------------------------------
m/...$var.../i m/...@{[Eutf2::ignorecase($var)]}.../
--------------------------------------------------------------------------------
=head1 Character-Oriented Regular Expression
Regular expression works as character-oriented that has no /b modifier.
--------------------------------------------------------------------------------
Before After
--------------------------------------------------------------------------------
/regexp/ /ditto@Eutf2::matched/
m/regexp/ m/ditto@Eutf2::matched/
?regexp? m?ditto@Eutf2::matched?
m?regexp? m?ditto@Eutf2::matched?
s/regexp/replacement/ ($_ =~ m/ditto@Eutf2::matched/) ?
eval{ Eutf2::s_matched(); local $^W=0; my $__r=qq/replacement/; $_="${1}$__r$'"; 1 } :
undef
split(/regexp/) Eutf2::split(qr/regexp/)
split(m/regexp/) Eutf2::split(qr/regexp/)
split(qr/regexp/) Eutf2::split(qr/regexp/)
qr/regexp/ qr/ditto@Eutf2::matched/
--------------------------------------------------------------------------------
=head1 Byte-Oriented Regular Expression
Regular expression works as byte-oriented that has /b modifier.
--------------------------------------------------------------------------------
Before After
--------------------------------------------------------------------------------
/regexp/b /(?:regexp)@Eutf2::matched/
m/regexp/b m/(?:regexp)@Eutf2::matched/
?regexp?b m?regexp@Eutf2::matched?
m?regexp?b m?regexp@Eutf2::matched?
s/regexp/replacement/b ($_ =~ m/(\G[\x00-\xFF]*?)(?:regexp)@Eutf2::matched/) ?
eval{ Eutf2::s_matched(); local $^W=0; my $__r=qq/replacement/; $_="${1}$__r$'"; 1 } :
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)@Eutf2::matched/
--------------------------------------------------------------------------------
=head1 Escaping Character Classes (Eutf2.pm provides)
The character classes are redefined as follows to backward compatibility.
---------------------------------------------------------------
Before After
---------------------------------------------------------------
. @{Eutf2::dot}
@{Eutf2::dot_s} (/s modifier)
\d [0-9]
\s [\x09\x0A\x0C\x0D\x20]
\w [0-9A-Z_a-z]
\D @{Eutf2::eD}
\S @{Eutf2::eS}
\W @{Eutf2::eW}
\h [\x09\x20]
\v [\x0A\x0B\x0C\x0D]
\H @{Eutf2::eH}
\V @{Eutf2::eV}
\C [\x00-\xFF]
\X X (so, just 'X')
\R @{Eutf2::eR}
\N @{Eutf2::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:] @{Eutf2::not_alnum}
[:^alpha:] @{Eutf2::not_alpha}
[:^ascii:] @{Eutf2::not_ascii}
[:^blank:] @{Eutf2::not_blank}
[:^cntrl:] @{Eutf2::not_cntrl}
[:^digit:] @{Eutf2::not_digit}
[:^graph:] @{Eutf2::not_graph}
[:^lower:] @{Eutf2::not_lower}
@{Eutf2::not_lower_i} (/i modifier)
[:^print:] @{Eutf2::not_print}
[:^punct:] @{Eutf2::not_punct}
[:^space:] @{Eutf2::not_space}
[:^upper:] @{Eutf2::not_upper}
@{Eutf2::not_upper_i} (/i modifier)
[:^word:] @{Eutf2::not_word}
[:^xdigit:] @{Eutf2::not_xdigit}
---------------------------------------------------------------
Also \b and \B are redefined as follows to backward compatibility.
---------------------------------------------------------------
Before After
---------------------------------------------------------------
\b @{Eutf2::eb}
\B @{Eutf2::eB}
---------------------------------------------------------------
Definitions in Eutf2.pm.
---------------------------------------------------------------------------------------------------------------------------------------------------------
After Definition
---------------------------------------------------------------------------------------------------------------------------------------------------------
@{Eutf2::anchor} qr{\G(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF])*?}
@{Eutf2::dot} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x0A])}
@{Eutf2::dot_s} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF])}
@{Eutf2::eD} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF0-9])}
@{Eutf2::eS} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x09\x0A\x0C\x0D\x20])}
@{Eutf2::eW} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF0-9A-Z_a-z])}
@{Eutf2::eH} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x09\x20])}
@{Eutf2::eV} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x0A\x0B\x0C\x0D])}
@{Eutf2::eR} qr{(?:\x0D\x0A|[\x0A\x0D])}
@{Eutf2::eN} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x0A])}
@{Eutf2::not_alnum} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x30-\x39\x41-\x5A\x61-\x7A])}
@{Eutf2::not_alpha} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x41-\x5A\x61-\x7A])}
@{Eutf2::not_ascii} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x00-\x7F])}
@{Eutf2::not_blank} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x09\x20])}
@{Eutf2::not_cntrl} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x00-\x1F\x7F])}
@{Eutf2::not_digit} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x30-\x39])}
@{Eutf2::not_graph} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x21-\x7F])}
@{Eutf2::not_lower} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x61-\x7A])}
@{Eutf2::not_lower_i} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF])}
@{Eutf2::not_print} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x20-\x7F])}
@{Eutf2::not_punct} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x21-\x2F\x3A-\x3F\x40\x5B-\x5F\x60\x7B-\x7E])}
@{Eutf2::not_space} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x09\x0A\x0B\x0C\x0D\x20])}
@{Eutf2::not_upper} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x41-\x5A])}
@{Eutf2::not_upper_i} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF])}
@{Eutf2::not_word} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x30-\x39\x41-\x5A\x5F\x61-\x7A])}
@{Eutf2::not_xdigit} qr{(?:(?:[\xC2-\xDF]|[\xE0-\xE0][\xA0-\xBF]|[\xE1-\xEC][\x80-\xBF]|[\xED-\xED][\x80-\x9F]|[\xEE-\xEF][\x80-\xBF]|[\xF0-\xF0][\x90-\xBF][\x80-\xBF]|[\xF1-\xF3][\x80-\xBF][\x80-\xBF]|[\xF4-\xF4][\x80-\x8F][\x80-\xBF])[\x00-\xFF]|[^\x80-\xFF\x30-\x39\x41-\x46\x61-\x66])}
@{Eutf2::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))}
@{Eutf2::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 (UTF2.pm provides)
UTF2.pm removes '\' at head of alphanumeric regexp metasymbols \N, \p, \P
and \X. By this method, you can avoid the trap of the abstraction.
------------------------------------
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 (UTF2.pm and Eutf2.pm provide)
Insert 'Eutf2::' at head of function name. Eutf2.pm provides your script Eutf2::*
functions.
-------------------------------------------
Before After Works as
-------------------------------------------
length length Byte
substr substr Byte
pos pos Byte
split Eutf2::split Character
tr/// Eutf2::tr Character
tr///b tr/// Byte
tr///B tr/// Byte
y/// Eutf2::tr Character
y///b tr/// Byte
y///B tr/// Byte
chop Eutf2::chop Character
lc Eutf2::lc Character
lcfirst Eutf2::lcfirst Character
uc Eutf2::uc Character
ucfirst Eutf2::ucfirst Character
fc Eutf2::fc Character
chr Eutf2::chr Character
glob Eutf2::glob Character
-------------------------------------------
------------------------------------------------------------------------------------------------------------------------
Before After
------------------------------------------------------------------------------------------------------------------------
use Perl::Module; BEGIN { require 'Perl/Module.pm'; Perl::Module->import() if Perl::Module->can('import'); }
use Perl::Module @list; BEGIN { require 'Perl/Module.pm'; Perl::Module->import(@list) if Perl::Module->can('import'); }
use Perl::Module (); BEGIN { require 'Perl/Module.pm'; }
no Perl::Module; BEGIN { require 'Perl/Module.pm'; Perl::Module->unimport() if Perl::Module->can('unimport'); }
no Perl::Module @list; BEGIN { require 'Perl/Module.pm'; Perl::Module->unimport(@list) if Perl::Module->can('unimport'); }
no Perl::Module (); BEGIN { require 'Perl/Module.pm'; }
------------------------------------------------------------------------------------------------------------------------
=head1 Escaping Function Name (You do)
You need write 'UTF2::' at head of function name when you want character-
oriented function. See 'Character-Oriented Functions'.
--------------------------------------------------------
Function Character-Oriented Description
--------------------------------------------------------
ord UTF2::ord
reverse UTF2::reverse
length UTF2::length
substr UTF2::substr
index UTF2::index See 'About Indexes'
rindex UTF2::rindex See 'About Rindexes'
--------------------------------------------------------
About Indexes
-------------------------------------------------------------------------
Function Works as Returns as Description
-------------------------------------------------------------------------
index Character Byte JPerl semantics (most useful)
(same as Eutf2::index)
UTF2::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 Eutf2::rindex)
UTF2::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 * Order Of Character
$ord = UTF2::ord($string);
This function returns the numeric value (ASCII or UTF-2 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 UTF2 qw(ord);", ord of your script will be rewritten in
UTF2::ord. UTF2::ord is not compatible with ord of JPerl.
=item * Reverse List Or String
@reverse = UTF2::reverse(@list);
$reverse = UTF2::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 UTF2 qw(reverse);", reverse of your script will be
rewritten in UTF2::reverse. UTF2::reverse is not compatible with reverse of
JPerl.
=item * Length By UTF-2 Character
$length = UTF2::length($string);
$length = UTF2::length();
This function returns the length in characters (programmer-visible characters) of
the scalar value $string. If $string is omitted, it returns the UTF2::length of
$_.
Do not try to use UTF2::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);
=item * Substr By UTF-2 Character
$substr = UTF2::substr($string,$offset,$length,$replacement);
$substr = UTF2::substr($string,$offset,$length);
$substr = UTF2::substr($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 UTF2::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:
$oldstr = UTF2::substr($var, -1, 1, "Curly");
To prepend the string "Larry" to the current value of $var, use:
UTF2::substr($var, 0, 0, "Larry");
To instead replace the first character of $var with "Moe", use:
UTF2::substr($var, 0, 1, "Moe");
And, finally, to replace the last character of $var with "Curly", use:
UTF2::substr($var, -1, 1, "Curly");
=item * Index By UTF-2 Character
$index = UTF2::index($string,$substring,$offset);
$index = UTF2::index($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 = UTF2::index($string, $lookfor, $pos)) > -1) {
print "Found at $pos\n";
$pos++;
}
=item * Rindex By UTF-2 Character
$rindex = UTF2::rindex($string,$substring,$offset);
$rindex = UTF2::rindex($string,$substring);
This function works just like UTF2::index except that it returns the character
position of the last occurrence of $substring in $string (a reverse UTF2::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:
$pos = UTF2::length($string);
while (($pos = UTF2::rindex($string, $lookfor, $pos)) >= 0) {
print "Found at $pos\n";
$pos--;
}
=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 = <STDIN>);
This is different from:
$answer = CORE::chop($temp = <STDIN>); # 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:
$answer = substr <STDIN>, 0, -1;
But this is more commonly written as:
CORE::chop($answer = <STDIN>);
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 * Order Of Byte
$ord = CORE::ord($expr);
This function returns the numeric value of the first byte of $expr, regardless
of "use UTF2 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 UTF2 qw(reverse);" exists or not.
=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 (UTF2.pm provides)
UTF2.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 (Eutf2.pm provides)
Eutf2.pm does "BEGIN { unshift @INC, '/Perl/site/lib/UTF2' }" at head.
Store the standard module modified for UTF2 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/UTF2 and change
'use utf8;' to 'use UTF2;' 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 Eutf2.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
$flag = utf8::valid(STRING);
Returns true always.
=item * Dummy bytes::chr
This function is same as chr.
=item * Dummy bytes::index
This function is same as index.
=item * Dummy bytes::length
This function is same as length.
=item * Dummy bytes::ord
This function is same as ord.
=item * Dummy bytes::rindex
This function is same as rindex.
=item * Dummy bytes::substr
This function is same as substr.
=back
=head1 Environment Variable
This software uses the flock function for exclusive control. The execution of the
program is blocked until it becomes possible to read or write the file.
You can have it not block in the flock function by defining environment variable
SJIS_NONBLOCK.
Example:
SET SJIS_NONBLOCK=1
(The value '1' doesn't have the meaning)
=head1 Perl5.6 Emulation On perl5.005
Using warnings pragma on perl5.00503 by rename files.
warnings.pm_ --> warnings.pm
warnings/register.pm_ --> warnings/register.pm
=head1 Perl5.16 Emulation On perl5.005
Using feature pragma on perl5.00503 by rename files.
feature.pm_ --> feature.pm
=head1 BUGS AND LIMITATIONS
I have tested and verified this software using the best of my ability.
However, a software containing much regular expression is bound to contain
some bugs. Thus, if you happen to find a bug that's in UTF2 software and not
your own program, you can try to reduce it to a minimal test case and then
report it to the following author's address. If you have an idea that could
make this a more useful tool, please let everyone share it.
=over 2
=item * format
Function "format" can't handle multiple-octet code same as original Perl.
=item * UTF2::substr As Lvalue
UTF2::substr differs from CORE::substr, and cannot be used as a lvalue.
To change part of a string, you can use the optional fourth argument which is the
replacement string.
UTF2::substr($string, 13, 4, "JPerl");
=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 * 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.
=back
=head1 AUTHOR
INABA Hitoshi E<lt>ina@cpan.orgE<gt>
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<perlartistic>.
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 |
+--------------------------------------------+
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 with 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 UTF-2 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,UTF2
+--------------+-------+-------+-------+-------+-------+
| 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 UTF2;" 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.
=item * Goal #4:
Perl should remain one language, rather than forking into a
byte-oriented Perl and a character-oriented Perl.
JPerl makes 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 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 SEE ALSO
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
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
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
Perl Pocket Reference, 5th Edition
By Johan Vromans
Publisher: O'Reilly Media
Released: July 2011
Pages: 102
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
Perl Cookbook, Second Edition
By Tom Christiansen, Nathan Torkington
Second Edition August 2003
Pages: 964
ISBN 10: 0-596-00313-7 | ISBN 13: 9780596003135
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
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
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
Perl RESOURCE KIT UNIX EDITION
Futato, Irving, Jepson, Patwardhan, Siever
ISBN 10: 1-56592-370-7
Understanding Japanese Information Processing
By Ken Lunde
January 1900
Pages: 470
ISBN 10: 1-56592-043-0 | ISBN 13: 9781565920439
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
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
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
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
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
JIS KANJI JITEN
Kouji Shibano
Pages: 1456
ISBN 4-542-20129-5
UNIX MAGAZINE
1993 Aug
Pages: 172
T1008901080816 ZASSHI 08901-8
MacPerl Power and Ease
By Vicki Brown, Chris Nandor
April 1998
Pages: 350
ISBN 10: 1881957322 | ISBN 13: 978-1881957324
Other Tools
BackPAN
=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)
(add 'h' at head)
Larry Wall, Perl
Kazumasa Utashiro, jcode.pl
Jeffrey E. F. Friedl, Mastering Regular Expressions
SADAHIRO Tomoyuki, The right way of using Shift_JIS
Yukihiro "Matz" Matsumoto, YAPC::Asia2006 Ruby on Perl(s)
http://www.rubyist.net/~matz/slides/yapc2006/
jscripter, For jperl users
Bruce., Unicode in Perl
Hiroaki Izumi, Perl5.8/Perl5.10 is not useful on the Windows.
TSUKAMOTO Makio, Perl memo/file path of Windows
chaichanPaPa, Matching Shift_JIS file name
SUZUKI Norio, Jperl
WATANABE Hirofumi, Jperl
Chuck Houpt, Michiko Nozu, MacJPerl
Kenichi Ishigaki, Pod-PerldocJp, Welcome to modern Perl world
Dan Kogai, Encode module
Juerd, Perl Unicode Advice
daily dayflower, 2008-06-25 perluniadvice
Jesse Vincent, Compatibility is a virtue
Tokyo-pm archive
ruby-list
=cut