package Latin7;
######################################################################
#
# Latin7 - Source code filter to escape Latin-7 script
#
# http://search.cpan.org/dist/Char-Latin7/
#
# Copyright (c) 2008, 2009, 2010, 2011, 2012, 2013, 2014 INABA Hitoshi <ina@cpan.org>
######################################################################
use 5.00503; # Galapagos Consensus 1998 for primetools
# use 5.008001; # Lancaster Consensus 2013 for toolchains
# 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: 1.01 $ =~ /(\d+)/oxmsg;
BEGIN {
if ($^X =~ / jperl /oxmsi) {
die __FILE__, ": needs perl(not jperl) 5.00503 or later. (\$^X==$^X)";
}
if (CORE::ord('A') == 193) {
die __FILE__, ": is not US-ASCII script (may be EBCDIC or EBCDIK script).";
}
if (CORE::ord('A') != 0x41) {
die __FILE__, ": is not US-ASCII script (must be US-ASCII script).";
}
}
BEGIN { CORE::require Elatin7; }
# instead of Symbol.pm
BEGIN {
my $genpkg = "Symbol::";
my $genseq = 0;
sub gensym () {
my $name = "GEN" . $genseq++;
# here, no strict qw(refs); if strict.pm exists
my $ref = \*{$genpkg . $name};
delete $$genpkg{$name};
$ref;
}
}
# Column: local $@
# in Chapter 9. Osaete okitai Perl no kiso
# of ISBN 10: 4798119172 | ISBN 13: 978-4798119175 MODAN Perl NYUMON
# (and so on)
# use strict; if strict.pm exists
BEGIN {
if (eval { local $@; CORE::require strict }) {
strict::->import;
}
}
# P.714 29.2.39. flock
# in Chapter 29: Functions
# of ISBN 0-596-00027-8 Programming Perl Third Edition.
# P.863 flock
# in Chapter 27: Functions
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
# P.228 Inlining Constant Functions
# in Chapter 6: Subroutines
# of ISBN 0-596-00027-8 Programming Perl Third Edition.
# P.331 Inlining Constant Functions
# in Chapter 7: Subroutines
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
sub LOCK_SH() {1}
sub LOCK_EX() {2}
sub LOCK_UN() {8}
sub LOCK_NB() {4}
sub unimport {}
sub Latin7::escape_script;
# 6.18. Matching Multiple-Byte Characters
# in Chapter 6. Pattern Matching
# of ISBN 978-1-56592-243-3 Perl Perl Cookbook.
# (and so on)
# regexp of character
my $your_char = q{[\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] |
\\ [\x00-\xFF] |
[^()] |
\( (?{$nest++}) |
\) (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!))
}xms;
my $qq_brace = qr{(?{local $nest=0}) (?>(?:
\\c[\x40-\x5F] |
\\ [\x00-\xFF] |
[^{}] |
\{ (?{$nest++}) |
\} (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!))
}xms;
my $qq_bracket = qr{(?{local $nest=0}) (?>(?:
\\c[\x40-\x5F] |
\\ [\x00-\xFF] |
[^[\]] |
\[ (?{$nest++}) |
\] (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!))
}xms;
my $qq_angle = qr{(?{local $nest=0}) (?>(?:
\\c[\x40-\x5F] |
\\ [\x00-\xFF] |
[^<>] |
\< (?{$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]+ |
[^a-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;
my $qq_substr = qr{(?: Latin7::substr | CORE::substr | substr ) \( $qq_paren \)
}xms;
# regexp of nested parens in qXX
my $q_paren = qr{(?{local $nest=0}) (?>(?:
[^()] |
\( (?{$nest++}) |
\) (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!))
}xms;
my $q_brace = qr{(?{local $nest=0}) (?>(?:
[^{}] |
\{ (?{$nest++}) |
\} (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!))
}xms;
my $q_bracket = qr{(?{local $nest=0}) (?>(?:
[^[\]] |
\[ (?{$nest++}) |
\] (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!))
}xms;
my $q_angle = qr{(?{local $nest=0}) (?>(?:
[^<>] |
\< (?{$nest++}) |
\> (?(?{$nest>0})(?{$nest--})|(?!)))*) (?(?{$nest!=0})(?!))
}xms;
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 Latin7::ord()
my $function_ord_; # ord to ord or Latin7::ord_
my $function_reverse; # reverse to reverse or Latin7::reverse
my $function_getc; # getc to getc or Latin7::getc
my $ignore_modules = join('|', qw(
utf8
bytes
charnames
I18N::Japanese
I18N::Collate
I18N::JExt
File::DosGlob
Wild
Wildcard
Japanese
));
# when this script is main program
if ($0 eq __FILE__) {
# show usage
unless (@ARGV) {
die <<END;
$0: usage
perl $0 Latin-7_script.pl > Escaped_script.pl.e
END
}
print Latin7::escape_script($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 "$0".
END
}
# P.302 Module Privacy and the Exporter
# in Chapter 11: Modules
# of ISBN 0-596-00027-8 Programming Perl Third Edition.
#
# A module can do anything it jolly well pleases when it's used, since use just
# calls the ordinary import method for the module, and you can define that
# method to do anything you like.
# P.406 Module Privacy and the Exporter
# in Chapter 11: Modules
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
#
# A module can do anything it jolly well pleases when it's used, since use just
# calls the ordinary import method for the module, and you can define that
# method to do anything you like.
sub import {
if (-e("$filename.e")) {
if (exists $ENV{'SJIS_DEBUG'}) {
unlink "$filename.e";
}
elsif (-z("$filename.e")) {
unlink "$filename.e";
}
else {
#----------------------------------------------------
# older >
# newer >>>>>
#----------------------------------------------------
# Filter >
# Source >>>>>
# Escape >>> needs re-escape (Source was changed)
#
# Filter >>>
# Source >>>>>
# Escape > needs re-escape (Source was changed)
#
# Filter >>>>>
# Source >>>
# Escape > needs re-escape (Source was changed)
#
# Filter >>>>>
# Source >
# Escape >>> needs re-escape (Filter was changed)
#
# Filter >
# Source >>>
# Escape >>>>> executable without re-escape
#
# Filter >>>
# Source >
# Escape >>>>> executable without re-escape
#----------------------------------------------------
my $mtime_filter = (stat(__FILE__ ))[9];
my $mtime_source = (stat($filename ))[9];
my $mtime_escape = (stat("$filename.e"))[9];
if (($mtime_escape < $mtime_source) or ($mtime_escape < $mtime_filter)) {
unlink "$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,"$filename.e",&O_WRONLY|&O_APPEND|&O_CREAT)) {
}
else {
Elatin7::_open_a($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) };
}
eval q{ truncate($fh, 0) };
seek($fh, 0, 0) or die __FILE__, ": Can't seek file: $filename.e";
my $e_script = Latin7::escape_script($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";
}
my $fh = gensym();
Elatin7::_open_r($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 ($^W) {
push @switch, '-w';
}
# P.707 29.2.33. exec
# in Chapter 29: Functions
# of ISBN 0-596-00027-8 Programming Perl Third Edition.
#
# If there is more than one argument in LIST, or if LIST is an array with more
# than one value, the system shell will never be used. This also bypasses any
# shell processing of the command. The presence or absence of metacharacters in
# the arguments doesn't affect this list-triggered behavior, which makes it the
# preferred from in security-conscious programs that do not with to expose
# themselves to potential shell escapes.
# Environment variable PERL5SHELL(Microsoft ports only) will never be used, too.
# P.855 exec
# in Chapter 27: Functions
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
#
# If there is more than one argument in LIST, or if LIST is an array with more
# than one value, the system shell will never be used. This also bypasses any
# shell processing of the command. The presence or absence of metacharacters in
# the arguments doesn't affect this list-triggered behavior, which makes it the
# preferred from in security-conscious programs that do not wish to expose
# themselves to injection attacks via shell escapes.
# Environment variable PERL5SHELL(Microsoft ports only) will never be used, too.
# P.489 #! and Quoting on Non-Unix Systems
# in Chapter 19: The Command-Line Interface
# of ISBN 0-596-00027-8 Programming Perl Third Edition.
# P.578 #! and Quoting on Non-Unix Systems
# in Chapter 17: The Command-Line Interface
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
# DOS-like system
if ($^O =~ /\A (?: MSWin32 | NetWare | symbian | dos ) \z/oxms) {
exit Elatin7::_systemx(
_escapeshellcmd_MSWin32($^X),
# -I switch can not treat space included path
# (map { '-I' . _escapeshellcmd_MSWin32($_) } @INC),
(map { '-I' . $_ } @INC),
@switch,
'--',
map { _escapeshellcmd_MSWin32($_) } "$filename.e", @ARGV
);
}
# UNIX-like system
else {
exit Elatin7::_systemx(
_escapeshellcmd($^X),
(map { '-I' . _escapeshellcmd($_) } @INC),
@switch,
'--',
map { _escapeshellcmd($_) } "$filename.e", @ARGV
);
}
}
# escape shell command line on DOS-like system
sub _escapeshellcmd_MSWin32 {
my($word) = @_;
if ($word =~ / [ ] /oxms) {
# both DOS-like and UNIX-like shell quote
return qq{"$word"};
}
else {
return $word;
}
}
# escape shell command line on UNIX-like system
sub _escapeshellcmd {
my($word) = @_;
return $word;
}
# P.619 Source Filters
# in Chapter 24: Common Practices
# of ISBN 0-596-00027-8 Programming Perl Third Edition.
# P.718 Source Filters
# in Chapter 21: Common Practices
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
# escape Latin-7 script
sub Latin7::escape_script {
my($script) = @_;
my $e_script = '';
# read Latin-7 script
my $fh = gensym();
Elatin7::_open_r($fh, $script) or die __FILE__, ": Can't open file: $script";
local $/ = undef; # slurp mode
$_ = <$fh>;
close($fh) or die __FILE__, ": Can't close file: $script";
if (/^ use Elatin7(?:\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.
# '...' quote to avoid "Octal number in vector unsupported" on perl 5.6
$e_script .= sprintf("use Elatin7 '%s.0'; # 'quote' for perl5.6\n", $Latin7::VERSION); # require run-time routines version
# use Latin7 version qw(ord reverse getc);
$function_ord = 'ord';
$function_ord_ = 'ord';
$function_reverse = 'reverse';
$function_getc = 'getc';
if (s/^ \s* use \s+ Latin7 \s* ([^;]*) ; \s* \n? $//oxms) {
# require version
my $list = $1;
if ($list =~ s/\A ([0-9]+\.[0-9]+) \.0 \s* //oxms) {
my $version = $1;
if ($version ne $Latin7::VERSION) {
my @file = grep -e, map {qq{$_/Latin7.pm}} @INC;
my %file = map { $_ => 1 } @file;
if (scalar(keys %file) >= 2) {
my $file = join "\n", sort keys %file;
warn <<END;
****************************************************
C A U T I O N
CONFLICT Latin7.pm FILE
$file
****************************************************
END
}
die "Script $0 expects Latin7.pm $version, but @{[__FILE__]} is version $Latin7::VERSION\n";
}
$e_script .= qq{die "Script \$0 expects Elatin7.pm $version, but \\\$Elatin7::VERSION is \$Elatin7::VERSION" if \$Elatin7::VERSION ne '$version';\n};
}
elsif ($list =~ s/\A ([0-9]+(?:\.[0-9]*)) \s* //oxms) {
my $version = $1;
if ($version > $Latin7::VERSION) {
die "Script $0 required Latin7.pm $version, but @{[__FILE__]} is only version $Latin7::VERSION\n";
}
}
# demand ord, reverse, and getc
if ($list !~ /\A \s* \z/oxms) {
local $@;
my @list = eval $list;
for (@list) {
$function_ord = 'Latin7::ord' if /\A ord \z/oxms;
$function_ord_ = 'Latin7::ord_' if /\A ord \z/oxms;
$function_reverse = 'Latin7::reverse' if /\A reverse \z/oxms;
$function_getc = 'Latin7::getc' if /\A getc \z/oxms;
}
}
}
}
$slash = 'm//';
# P.359 The Study Function
# in Chapter 7: Perl
# of ISBN 0-596-00289-0 Mastering Regular Expressions, Second edition
study $_; # Yes, I studied study yesterday.
# while all script
# 6.14. Matching from Where the Last Pattern Left Off
# in Chapter 6. Pattern Matching
# of ISBN 0-596-00313-7 Perl Cookbook, 2nd Edition.
# (and so on)
# one member of Tag-team
#
# P.128 Start of match (or end of previous match): \G
# P.130 Advanced Use of \G with Perl
# in Chapter 3: Overview of Regular Expression Features and Flavors
# P.255 Use leading anchors
# P.256 Expose ^ and \G at the front expressions
# in Chapter 6: Crafting an Efficient Expression
# 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 Latin-7 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} --> Elatin7::PREMATCH()
elsif (/\G ( \$` | \$\{`\} | \$ \s* PREMATCH \b | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) /oxmsgc) {
$slash = 'div';
return q{Elatin7::PREMATCH()};
}
# $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Elatin7::MATCH()
elsif (/\G ( \$& | \$\{&\} | \$ \s* MATCH \b | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) /oxmsgc) {
$slash = 'div';
return q{Elatin7::MATCH()};
}
# $', ${'} --> $', ${'}
elsif (/\G ( \$' | \$\{'\} ) /oxmsgc) {
$slash = 'div';
return $1;
}
# $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Elatin7::POSTMATCH()
elsif (/\G ( \$ \s* POSTMATCH \b | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) /oxmsgc) {
$slash = 'div';
return q{Elatin7::POSTMATCH()};
}
# scalar variable $scalar =~ tr///;
# scalar variable $scalar =~ s///;
# substr() =~ tr///;
# substr() =~ s///;
elsif (/\G ( \$ $qq_scalar | $qq_substr ) /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 after s/// with multibyte anchoring
# $1, $2, $3 --> $1, $2, $3 otherwise
elsif (/\G \$ ([1-9][0-9]*) /oxmsgc) {
$slash = 'div';
return e_capture($1);
}
elsif (/\G \$ \{ \s* ([1-9][0-9]*) \s* \} /oxmsgc) {
$slash = 'div';
return e_capture($1);
}
# $$foo[ ... ] --> $ $foo->[ ... ]
elsif (/\G \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \[ .+? \] ) /oxmsgc) {
$slash = 'div';
return e_capture($1.'->'.$2);
}
# $$foo{ ... } --> $ $foo->{ ... }
elsif (/\G \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ .+? \} ) /oxmsgc) {
$slash = 'div';
return e_capture($1.'->'.$2);
}
# $$foo
elsif (/\G \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) /oxmsgc) {
$slash = 'div';
return e_capture($1);
}
# ${ foo }
elsif (/\G \$ \s* \{ ( \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* ) \} /oxmsgc) {
$slash = 'div';
return '${' . $1 . '}';
}
# ${ ... }
elsif (/\G \$ \s* \{ \s* ( $qq_brace ) \s* \} /oxmsgc) {
$slash = 'div';
return e_capture($1);
}
# variable or function
# $ @ % & * $ #
elsif (/\G ( (?: [\$\@\%\&\*] | \$\# | -> | \b sub \b) \s* (?: split | chop | index | rindex | lc | uc | fc | chr | ord | reverse | getc | tr | y | q | qq | qx | qw | m | s | qr | glob | lstat | opendir | stat | unlink | chdir ) ) \b /oxmsgc) {
$slash = 'div';
return $1;
}
# $ $ $ $ $ $ $ $ $ $ $ $ $ $
# $ @ # \ ' " / ? ( ) [ ] < >
elsif (/\G ( \$[\$\@\#\\\'\"\/\?\(\)\[\]\<\>] ) /oxmsgc) {
$slash = 'div';
return $1;
}
# while (<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* \( \s* < ((?:[^>\0\a\e\f\n\r\t])+?) > \s* \) \b /oxgc) {
return 'while ($_ = Elatin7::glob("' . $1 . '"))';
}
# while (glob)
elsif (/\G \b while \s* \( \s* glob \s* \) /oxgc) {
return 'while ($_ = Elatin7::glob_)';
}
# while (glob(WILDCARD))
elsif (/\G \b while \s* \( \s* glob \b /oxgc) {
return 'while ($_ = Elatin7::glob';
}
# doit if, doit unless, doit while, doit until, doit for, doit when
elsif (/\G \b ( if | unless | while | until | for | when ) \b /oxgc) { $slash = 'm//'; return $1; }
# subroutines of package Elatin7
elsif (/\G \b (CORE:: | ->[ ]* (?: atan2 | [a-z]{2,})) \b /oxgc) { $slash = 'm//'; return $1; }
elsif (/\G \b bytes::substr \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'substr'; }
elsif (/\G \b chop \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Elatin7::chop'; }
elsif (/\G \b bytes::index \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'index'; }
elsif (/\G \b Latin7::index \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Latin7::index'; }
elsif (/\G \b index \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Elatin7::index'; }
elsif (/\G \b bytes::rindex \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'rindex'; }
elsif (/\G \b Latin7::rindex \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Latin7::rindex'; }
elsif (/\G \b rindex \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Elatin7::rindex'; }
elsif (/\G \b lc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'Elatin7::lc'; }
elsif (/\G \b lcfirst (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'Elatin7::lcfirst'; }
elsif (/\G \b uc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'Elatin7::uc'; }
elsif (/\G \b ucfirst (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'Elatin7::ucfirst'; }
elsif (/\G \b fc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'Elatin7::fc'; }
# "-s '' ..." means file test "-s 'filename' ..." (not means "- s/// ...")
elsif (/\G -s \s+ \s* (\") ((?:$qq_char)+?) (\") /oxgc) { $slash = 'm//'; return '-s ' . e_qq('', $1,$3,$2); }
elsif (/\G -s \s+ qq \s* (\#) ((?:$qq_char)+?) (\#) /oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); }
elsif (/\G -s \s+ qq \s* (\() ((?:$qq_paren)+?) (\)) /oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); }
elsif (/\G -s \s+ qq \s* (\{) ((?:$qq_brace)+?) (\}) /oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); }
elsif (/\G -s \s+ qq \s* (\[) ((?:$qq_bracket)+?) (\]) /oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); }
elsif (/\G -s \s+ qq \s* (\<) ((?:$qq_angle)+?) (\>) /oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); }
elsif (/\G -s \s+ qq \s* (\S) ((?:$qq_char)+?) (\1) /oxgc) { $slash = 'm//'; return '-s ' . e_qq('qq',$1,$3,$2); }
elsif (/\G -s \s+ \s* (\') ((?:\\\'|\\\\|$q_char)+?) (\') /oxgc) { $slash = 'm//'; return '-s ' . e_q ('', $1,$3,$2); }
elsif (/\G -s \s+ q \s* (\#) ((?:\\\#|\\\\|$q_char)+?) (\#) /oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); }
elsif (/\G -s \s+ q \s* (\() ((?:\\\)|\\\\|$q_paren)+?) (\)) /oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); }
elsif (/\G -s \s+ q \s* (\{) ((?:\\\}|\\\\|$q_brace)+?) (\}) /oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); }
elsif (/\G -s \s+ q \s* (\[) ((?:\\\]|\\\\|$q_bracket)+?) (\]) /oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); }
elsif (/\G -s \s+ q \s* (\<) ((?:\\\>|\\\\|$q_angle)+?) (\>) /oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); }
elsif (/\G -s \s+ q \s* (\S) ((?:\\\1|\\\\|$q_char)+?) (\1) /oxgc) { $slash = 'm//'; return '-s ' . e_q ('q', $1,$3,$2); }
elsif (/\G -s \s* (\$ \w+(?: ::\w+)* (?: (?: ->)? (?: [\$\@\%\&\*]\* | \$\#\* | \( (?:$qq_paren)*? \) | [\@\%\*]? \{ (?:$qq_brace)+? \} | [\@\%]? \[ (?:$qq_bracket)+? \] ) )*) /oxgc)
{ $slash = 'm//'; return "-s $1"; }
elsif (/\G -s \s* \( ((?:$qq_paren)*?) \) /oxgc) { $slash = 'm//'; return "-s ($1)"; }
elsif (/\G -s (?= \s+ [a-z]+) /oxgc) { $slash = 'm//'; return '-s'; }
elsif (/\G -s \s+ (\w+) /oxgc) { $slash = 'm//'; return "-s $1"; }
elsif (/\G \b bytes::length (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'length'; }
elsif (/\G \b bytes::chr (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'chr'; }
elsif (/\G \b chr (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'Elatin7::chr'; }
elsif (/\G \b bytes::ord (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'div'; return 'ord'; }
elsif (/\G \b ord (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'div'; return $function_ord; }
elsif (/\G \b glob (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $slash = 'm//'; return 'Elatin7::glob'; }
elsif (/\G \b lc \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Elatin7::lc_'; }
elsif (/\G \b lcfirst \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Elatin7::lcfirst_'; }
elsif (/\G \b uc \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Elatin7::uc_'; }
elsif (/\G \b ucfirst \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Elatin7::ucfirst_'; }
elsif (/\G \b fc \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Elatin7::fc_'; }
elsif (/\G -s \b (?! \s* => ) /oxgc) { $slash = 'm//'; return '-s '; }
elsif (/\G \b bytes::length \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'length'; }
elsif (/\G \b bytes::chr \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'chr'; }
elsif (/\G \b chr \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Elatin7::chr_'; }
elsif (/\G \b bytes::ord \b (?! \s* => ) /oxgc) { $slash = 'div'; return 'ord'; }
elsif (/\G \b ord \b (?! \s* => ) /oxgc) { $slash = 'div'; return $function_ord_; }
elsif (/\G \b glob \b (?! \s* => ) /oxgc) { $slash = 'm//'; return 'Elatin7::glob_'; }
elsif (/\G \b reverse \b (?! \s* => ) /oxgc) { $slash = 'm//'; return $function_reverse; }
elsif (/\G \b getc \b (?! \s* => ) /oxgc) { $slash = 'm//'; return $function_getc; }
# split
elsif (/\G \b (split) \b (?! \s* => ) /oxgc) {
$slash = 'm//';
my $e = '';
while (/\G ( \s+ | \( | \#.* ) /oxgc) {
$e .= $1;
}
# end of split
if (/\G (?= [,;\)\}\]] ) /oxgc) { return 'Elatin7::split' . $e; }
# split scalar value
elsif (/\G ( [\$\@\&\*] $qq_scalar ) /oxgc) { return 'Elatin7::split' . $e . e_string($1); }
# split literal space
elsif (/\G \b qq (\#) [ ] (\#) /oxgc) { return 'Elatin7::split' . $e . qq {qq$1 $2}; }
elsif (/\G \b qq (\s*) (\() [ ] (\)) /oxgc) { return 'Elatin7::split' . $e . qq{$1qq$2 $3}; }
elsif (/\G \b qq (\s*) (\{) [ ] (\}) /oxgc) { return 'Elatin7::split' . $e . qq{$1qq$2 $3}; }
elsif (/\G \b qq (\s*) (\[) [ ] (\]) /oxgc) { return 'Elatin7::split' . $e . qq{$1qq$2 $3}; }
elsif (/\G \b qq (\s*) (\<) [ ] (\>) /oxgc) { return 'Elatin7::split' . $e . qq{$1qq$2 $3}; }
elsif (/\G \b qq (\s*) (\S) [ ] (\2) /oxgc) { return 'Elatin7::split' . $e . qq{$1qq$2 $3}; }
elsif (/\G \b q (\#) [ ] (\#) /oxgc) { return 'Elatin7::split' . $e . qq {q$1 $2}; }
elsif (/\G \b q (\s*) (\() [ ] (\)) /oxgc) { return 'Elatin7::split' . $e . qq {$1q$2 $3}; }
elsif (/\G \b q (\s*) (\{) [ ] (\}) /oxgc) { return 'Elatin7::split' . $e . qq {$1q$2 $3}; }
elsif (/\G \b q (\s*) (\[) [ ] (\]) /oxgc) { return 'Elatin7::split' . $e . qq {$1q$2 $3}; }
elsif (/\G \b q (\s*) (\<) [ ] (\>) /oxgc) { return 'Elatin7::split' . $e . qq {$1q$2 $3}; }
elsif (/\G \b q (\s*) (\S) [ ] (\2) /oxgc) { return 'Elatin7::split' . $e . qq {$1q$2 $3}; }
elsif (/\G ' [ ] ' /oxgc) { return 'Elatin7::split' . $e . qq {' '}; }
elsif (/\G " [ ] " /oxgc) { return 'Elatin7::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]* [^#]) /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]* [^#]) /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 ge '012'))) {
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]* [^#]) /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]* [^#]) /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'"`\$\@\&\*\(\+\-] )/oxgc) {
return $1;
}
# <FILEHANDLE>
elsif (/\G (<[\$]?[A-Za-z_][A-Za-z_0-9]*>) /oxgc) {
return $1;
}
# <WILDCARD> --- glob
# avoid "Error: Runtime exception" of perl version 5.005_03
elsif (/\G < ((?:[^>\0\a\e\f\n\r\t])+?) > /oxgc) {
return 'Elatin7::glob("' . $1 . '")';
}
# __DATA__
elsif (/\G ^ ( __DATA__ \n .*) \z /oxmsgc) { return $1; }
# __END__
elsif (/\G ^ ( __END__ \n .*) \z /oxmsgc) { return $1; }
# \cD Control-D
# P.68 2.6.8. Other Literal Tokens
# in Chapter 2: Bits and Pieces
# of ISBN 0-596-00027-8 Programming Perl Third Edition.
# P.76 Other Literal Tokens
# in Chapter 2: Bits and Pieces
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
elsif (/\G ( \cD .*) \z /oxmsgc) { return $1; }
# \cZ Control-Z
elsif (/\G ( \cZ .*) \z /oxmsgc) { return $1; }
# any operator before div
elsif (/\G (
-- | \+\+ |
[\)\}\]]
) /oxgc) { $slash = 'div'; return $1; }
# yada-yada or triple-dot operator
elsif (/\G (
\.\.\.
) /oxgc) { $slash = 'm//'; return q{die('Unimplemented')}; }
# 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 $1; }
# system error
else {
die __FILE__, ": Oops, this shouldn't happen!";
}
}
# escape Latin-7 string
sub e_string {
my($string) = @_;
my $e_string = '';
local $slash = 'm//';
# P.1024 Appendix W.10 Multibyte Processing
# of ISBN 1-56592-224-7 CJKV Information Processing
# (and so on)
my @char = $string =~ / \G (\\?(?:$q_char)) /oxmsg;
# without { ... }
if (not (grep(/\A \{ \z/xms, @char) and grep(/\A \} \z/xms, @char))) {
if ($string !~ /<</oxms) {
return $string;
}
}
E_STRING_LOOP:
while ($string !~ /\G \z/oxgc) {
if (0) {
}
# $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> @{[Elatin7::PREMATCH()]}
elsif ($string =~ /\G ( \$` | \$\{`\} | \$ \s* PREMATCH \b | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) /oxmsgc) {
$e_string .= q{Elatin7::PREMATCH()};
$slash = 'div';
}
# $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> @{[Elatin7::MATCH()]}
elsif ($string =~ /\G ( \$& | \$\{&\} | \$ \s* MATCH \b | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) /oxmsgc) {
$e_string .= q{Elatin7::MATCH()};
$slash = 'div';
}
# $', ${'} --> $', ${'}
elsif ($string =~ /\G ( \$' | \$\{'\} ) /oxmsgc) {
$e_string .= $1;
$slash = 'div';
}
# $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> @{[Elatin7::POSTMATCH()]}
elsif ($string =~ /\G ( \$ \s* POSTMATCH \b | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) /oxmsgc) {
$e_string .= q{Elatin7::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 after s/// with multibyte anchoring
# $1, $2, $3 --> $1, $2, $3 otherwise
elsif ($string =~ /\G \$ ([1-9][0-9]*) /oxmsgc) {
$e_string .= e_capture($1);
$slash = 'div';
}
elsif ($string =~ /\G \$ \{ \s* ([1-9][0-9]*) \s* \} /oxmsgc) {
$e_string .= e_capture($1);
$slash = 'div';
}
# $$foo[ ... ] --> $ $foo->[ ... ]
elsif ($string =~ /\G \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \[ .+? \] ) /oxmsgc) {
$e_string .= e_capture($1.'->'.$2);
$slash = 'div';
}
# $$foo{ ... } --> $ $foo->{ ... }
elsif ($string =~ /\G \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ .+? \} ) /oxmsgc) {
$e_string .= e_capture($1.'->'.$2);
$slash = 'div';
}
# $$foo
elsif ($string =~ /\G \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) /oxmsgc) {
$e_string .= e_capture($1);
$slash = 'div';
}
# ${ foo }
elsif ($string =~ /\G \$ \s* \{ ( \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* ) \} /oxmsgc) {
$e_string .= '${' . $1 . '}';
$slash = 'div';
}
# ${ ... }
elsif ($string =~ /\G \$ \s* \{ \s* ( $qq_brace ) \s* \} /oxmsgc) {
$e_string .= e_capture($1);
$slash = 'div';
}
# variable or function
# $ @ % & * $ #
elsif ($string =~ /\G ( (?: [\$\@\%\&\*] | \$\# | -> | \b sub \b) \s* (?: split | chop | index | rindex | lc | uc | fc | chr | ord | reverse | getc | tr | y | q | qq | qx | qw | m | s | qr | glob | lstat | opendir | stat | unlink | chdir ) ) \b /oxmsgc) {
$e_string .= $1;
$slash = 'div';
}
# $ $ $ $ $ $ $ $ $ $ $ $ $ $
# $ @ # \ ' " / ? ( ) [ ] < >
elsif ($string =~ /\G ( \$[\$\@\#\\\'\"\/\?\(\)\[\]\<\>] ) /oxmsgc) {
$e_string .= $1;
$slash = 'div';
}
# subroutines of package Elatin7
elsif ($string =~ /\G \b (CORE:: | ->[ ]* (?: atan2 | [a-z]{2,})) \b /oxgc) { $e_string .= $1; $slash = 'm//'; }
elsif ($string =~ /\G \b bytes::substr \b /oxgc) { $e_string .= 'substr'; $slash = 'm//'; }
elsif ($string =~ /\G \b chop \b /oxgc) { $e_string .= 'Elatin7::chop'; $slash = 'm//'; }
elsif ($string =~ /\G \b bytes::index \b /oxgc) { $e_string .= 'index'; $slash = 'm//'; }
elsif ($string =~ /\G \b Latin7::index \b /oxgc) { $e_string .= 'Latin7::index'; $slash = 'm//'; }
elsif ($string =~ /\G \b index \b /oxgc) { $e_string .= 'Elatin7::index'; $slash = 'm//'; }
elsif ($string =~ /\G \b bytes::rindex \b /oxgc) { $e_string .= 'rindex'; $slash = 'm//'; }
elsif ($string =~ /\G \b Latin7::rindex \b /oxgc) { $e_string .= 'Latin7::rindex'; $slash = 'm//'; }
elsif ($string =~ /\G \b rindex \b /oxgc) { $e_string .= 'Elatin7::rindex'; $slash = 'm//'; }
elsif ($string =~ /\G \b lc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'Elatin7::lc'; $slash = 'm//'; }
elsif ($string =~ /\G \b lcfirst (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'Elatin7::lcfirst'; $slash = 'm//'; }
elsif ($string =~ /\G \b uc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'Elatin7::uc'; $slash = 'm//'; }
elsif ($string =~ /\G \b ucfirst (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'Elatin7::ucfirst'; $slash = 'm//'; }
elsif ($string =~ /\G \b fc (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'Elatin7::fc'; $slash = 'm//'; }
# "-s '' ..." means file test "-s 'filename' ..." (not means "- s/// ...")
elsif ($string =~ /\G -s \s+ \s* (\") ((?:$qq_char)+?) (\") /oxgc) { $e_string .= '-s ' . e_qq('', $1,$3,$2); $slash = 'm//'; }
elsif ($string =~ /\G -s \s+ qq \s* (\#) ((?:$qq_char)+?) (\#) /oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; }
elsif ($string =~ /\G -s \s+ qq \s* (\() ((?:$qq_paren)+?) (\)) /oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; }
elsif ($string =~ /\G -s \s+ qq \s* (\{) ((?:$qq_brace)+?) (\}) /oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; }
elsif ($string =~ /\G -s \s+ qq \s* (\[) ((?:$qq_bracket)+?) (\]) /oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; }
elsif ($string =~ /\G -s \s+ qq \s* (\<) ((?:$qq_angle)+?) (\>) /oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; }
elsif ($string =~ /\G -s \s+ qq \s* (\S) ((?:$qq_char)+?) (\1) /oxgc) { $e_string .= '-s ' . e_qq('qq',$1,$3,$2); $slash = 'm//'; }
elsif ($string =~ /\G -s \s+ \s* (\') ((?:\\\'|\\\\|$q_char)+?) (\') /oxgc) { $e_string .= '-s ' . e_q ('', $1,$3,$2); $slash = 'm//'; }
elsif ($string =~ /\G -s \s+ q \s* (\#) ((?:\\\#|\\\\|$q_char)+?) (\#) /oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; }
elsif ($string =~ /\G -s \s+ q \s* (\() ((?:\\\)|\\\\|$q_paren)+?) (\)) /oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; }
elsif ($string =~ /\G -s \s+ q \s* (\{) ((?:\\\}|\\\\|$q_brace)+?) (\}) /oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; }
elsif ($string =~ /\G -s \s+ q \s* (\[) ((?:\\\]|\\\\|$q_bracket)+?) (\]) /oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; }
elsif ($string =~ /\G -s \s+ q \s* (\<) ((?:\\\>|\\\\|$q_angle)+?) (\>) /oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; }
elsif ($string =~ /\G -s \s+ q \s* (\S) ((?:\\\1|\\\\|$q_char)+?) (\1) /oxgc) { $e_string .= '-s ' . e_q ('q', $1,$3,$2); $slash = 'm//'; }
elsif ($string =~ /\G -s \s* (\$ \w+(?: ::\w+)* (?: (?: ->)? (?: [\$\@\%\&\*]\* | \$\#\* | \( (?:$qq_paren)*? \) | [\@\%\*]? \{ (?:$qq_brace)+? \} | [\@\%]? \[ (?:$qq_bracket)+? \] ) )*) /oxgc)
{ $e_string .= "-s $1"; $slash = 'm//'; }
elsif ($string =~ /\G -s \s* \( ((?:$qq_paren)*?) \) /oxgc) { $e_string .= "-s ($1)"; $slash = 'm//'; }
elsif ($string =~ /\G -s (?= \s+ [a-z]+) /oxgc) { $e_string .= '-s'; $slash = 'm//'; }
elsif ($string =~ /\G -s \s+ (\w+) /oxgc) { $e_string .= "-s $1"; $slash = 'm//'; }
elsif ($string =~ /\G \b bytes::length (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'length'; $slash = 'm//'; }
elsif ($string =~ /\G \b bytes::chr (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'chr'; $slash = 'm//'; }
elsif ($string =~ /\G \b chr (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'Elatin7::chr'; $slash = 'm//'; }
elsif ($string =~ /\G \b bytes::ord (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'ord'; $slash = 'div'; }
elsif ($string =~ /\G \b ord (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= $function_ord; $slash = 'div'; }
elsif ($string =~ /\G \b glob (?= \s+[A-Za-z_]|\s*['"`\$\@\&\*\(]) /oxgc) { $e_string .= 'Elatin7::glob'; $slash = 'm//'; }
elsif ($string =~ /\G \b lc \b /oxgc) { $e_string .= 'Elatin7::lc_'; $slash = 'm//'; }
elsif ($string =~ /\G \b lcfirst \b /oxgc) { $e_string .= 'Elatin7::lcfirst_'; $slash = 'm//'; }
elsif ($string =~ /\G \b uc \b /oxgc) { $e_string .= 'Elatin7::uc_'; $slash = 'm//'; }
elsif ($string =~ /\G \b ucfirst \b /oxgc) { $e_string .= 'Elatin7::ucfirst_'; $slash = 'm//'; }
elsif ($string =~ /\G \b fc \b /oxgc) { $e_string .= 'Elatin7::fc_'; $slash = 'm//'; }
elsif ($string =~ /\G -s \b /oxgc) { $e_string .= '-s '; $slash = 'm//'; }
elsif ($string =~ /\G \b bytes::length \b /oxgc) { $e_string .= 'length'; $slash = 'm//'; }
elsif ($string =~ /\G \b bytes::chr \b /oxgc) { $e_string .= 'chr'; $slash = 'm//'; }
elsif ($string =~ /\G \b chr \b /oxgc) { $e_string .= 'Elatin7::chr_'; $slash = 'm//'; }
elsif ($string =~ /\G \b bytes::ord \b /oxgc) { $e_string .= 'ord'; $slash = 'div'; }
elsif ($string =~ /\G \b ord \b /oxgc) { $e_string .= $function_ord_; $slash = 'div'; }
elsif ($string =~ /\G \b glob \b /oxgc) { $e_string .= 'Elatin7::glob_'; $slash = 'm//'; }
elsif ($string =~ /\G \b reverse \b /oxgc) { $e_string .= $function_reverse; $slash = 'm//'; }
elsif ($string =~ /\G \b getc \b /oxgc) { $e_string .= $function_getc; $slash = 'm//'; }
# split
elsif ($string =~ /\G \b (split) \b (?! \s* => ) /oxgc) {
$slash = 'm//';
my $e = '';
while ($string =~ /\G ( \s+ | \( | \#.* ) /oxgc) {
$e .= $1;
}
# end of split
if ($string =~ /\G (?= [,;\)\}\]] ) /oxgc) { return 'Elatin7::split' . $e; }
# split scalar value
elsif ($string =~ /\G ( [\$\@\&\*] $qq_scalar ) /oxgc) { $e_string .= 'Elatin7::split' . $e . e_string($1); next E_STRING_LOOP; }
# split literal space
elsif ($string =~ /\G \b qq (\#) [ ] (\#) /oxgc) { $e_string .= 'Elatin7::split' . $e . qq {qq$1 $2}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b qq (\s*) (\() [ ] (\)) /oxgc) { $e_string .= 'Elatin7::split' . $e . qq{$1qq$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b qq (\s*) (\{) [ ] (\}) /oxgc) { $e_string .= 'Elatin7::split' . $e . qq{$1qq$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b qq (\s*) (\[) [ ] (\]) /oxgc) { $e_string .= 'Elatin7::split' . $e . qq{$1qq$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b qq (\s*) (\<) [ ] (\>) /oxgc) { $e_string .= 'Elatin7::split' . $e . qq{$1qq$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b qq (\s*) (\S) [ ] (\2) /oxgc) { $e_string .= 'Elatin7::split' . $e . qq{$1qq$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b q (\#) [ ] (\#) /oxgc) { $e_string .= 'Elatin7::split' . $e . qq {q$1 $2}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b q (\s*) (\() [ ] (\)) /oxgc) { $e_string .= 'Elatin7::split' . $e . qq {$1q$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b q (\s*) (\{) [ ] (\}) /oxgc) { $e_string .= 'Elatin7::split' . $e . qq {$1q$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b q (\s*) (\[) [ ] (\]) /oxgc) { $e_string .= 'Elatin7::split' . $e . qq {$1q$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b q (\s*) (\<) [ ] (\>) /oxgc) { $e_string .= 'Elatin7::split' . $e . qq {$1q$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G \b q (\s*) (\S) [ ] (\2) /oxgc) { $e_string .= 'Elatin7::split' . $e . qq {$1q$2 $3}; next E_STRING_LOOP; }
elsif ($string =~ /\G ' [ ] ' /oxgc) { $e_string .= 'Elatin7::split' . $e . qq {' '}; next E_STRING_LOOP; }
elsif ($string =~ /\G " [ ] " /oxgc) { $e_string .= 'Elatin7::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 .= 'Elatin7::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 .= $1; }
# yada-yada or triple-dot operator
elsif ($string =~ /\G (
\.\.\.
) /oxgc) { $slash = 'm//'; $e_string .= q{die('Unimplemented')}; }
# any operator before m//
elsif ($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 ($modifier =~ /s/) {
return '${Elatin7::dot_s}';
}
else {
return '${Elatin7::dot}';
}
}
else {
return Elatin7::classic_character_class($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 '') {
$e_tr = qq{Elatin7::tr(\$_,' =~ ',$charclass,$e$charclass2,'$modifier')};
}
else {
$e_tr = qq{Elatin7::tr($variable,'$bind_operator',$charclass,$e$charclass2,'$modifier')};
}
}
# clear tr/// variable
$tr_variable = '';
$bind_operator = '';
return $e_tr;
}
#
# quote for escape transliteration (tr/// or y///)
#
sub q_tr {
my($charclass) = @_;
# quote character class
if ($charclass !~ /'/oxms) {
return e_q('', "'", "'", $charclass); # --> q' '
}
elsif ($charclass !~ /\//oxms) {
return e_q('q', '/', '/', $charclass); # --> q/ /
}
elsif ($charclass !~ /\#/oxms) {
return e_q('q', '#', '#', $charclass); # --> q# #
}
elsif ($charclass !~ /[\<\>]/oxms) {
return e_q('q', '<', '>', $charclass); # --> q< >
}
elsif ($charclass !~ /[\(\)]/oxms) {
return e_q('q', '(', ')', $charclass); # --> q( )
}
elsif ($charclass !~ /[\{\}]/oxms) {
return e_q('q', '{', '}', $charclass); # --> q{ }
}
else {
for my $char (qw( ! " $ % & * + . : = ? @ ^ ` | ~ ), "\x00".."\x1F", "\x7F", "\xFF") {
if ($charclass !~ /\Q$char\E/xms) {
return e_q('q', $char, $char, $charclass);
}
}
}
return e_q('q', '{', '}', $charclass);
}
#
# escape q string (q//, '')
#
sub e_q {
my($ope,$delimiter,$end_delimiter,$string) = @_;
$slash = 'div';
return join '', $ope, $delimiter, $string, $end_delimiter;
}
#
# escape qq string (qq//, "", qx//, ``)
#
sub e_qq {
my($ope,$delimiter,$end_delimiter,$string) = @_;
$slash = 'div';
my $left_e = 0;
my $right_e = 0;
my @char = $string =~ /\G(
\\o\{ [0-7]+ \} |
\\x\{ [0-9A-Fa-f]+ \} |
\\N\{ [^0-9\}][^\}]* \} |
\$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} |
\$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} |
\$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} |
\$ \s* \d+ |
\$ \s* \{ \s* \d+ \s* \} |
\$ \$ (?![\w\{]) |
\$ \s* \$ \s* $qq_variable |
\\?(?:$q_char)
)/oxmsg;
for (my $i=0; $i <= $#char; $i++) {
# "\L\u" --> "\u\L"
if (($char[$i] eq '\L') and ($char[$i+1] eq '\u')) {
@char[$i,$i+1] = @char[$i+1,$i];
}
# "\U\l" --> "\l\U"
elsif (($char[$i] eq '\U') and ($char[$i+1] eq '\l')) {
@char[$i,$i+1] = @char[$i+1,$i];
}
# octal escape sequence
elsif ($char[$i] =~ /\A \\o \{ ([0-7]+) \} \z/oxms) {
$char[$i] = Elatin7::octchr($1);
}
# hexadecimal escape sequence
elsif ($char[$i] =~ /\A \\x \{ ([0-9A-Fa-f]+) \} \z/oxms) {
$char[$i] = Elatin7::hexchr($1);
}
# \N{CHARNAME} --> N{CHARNAME}
elsif ($char[$i] =~ /\A \\ ( N\{ ([^0-9\}][^\}]*) \} ) \z/oxms) {
$char[$i] = $1;
}
if (0) {
}
# \F
#
# P.69 Table 2-6. Translation escapes
# in Chapter 2: Bits and Pieces
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
# (and so on)
# \u \l \U \L \F \Q \E
elsif ($char[$i] =~ /\A ([<>]) \z/oxms) {
if ($right_e < $left_e) {
$char[$i] = '\\' . $char[$i];
}
}
elsif ($char[$i] eq '\u') {
# "STRING @{[ LIST EXPR ]} MORE STRING"
# P.257 Other Tricks You Can Do with Hard References
# in Chapter 8: References
# of ISBN 0-596-00027-8 Programming Perl Third Edition.
# P.353 Other Tricks You Can Do with Hard References
# in Chapter 8: References
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
# (and so on)
$char[$i] = '@{[Elatin7::ucfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\l') {
$char[$i] = '@{[Elatin7::lcfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\U') {
$char[$i] = '@{[Elatin7::uc qq<';
$left_e++;
}
elsif ($char[$i] eq '\L') {
$char[$i] = '@{[Elatin7::lc qq<';
$left_e++;
}
elsif ($char[$i] eq '\F') {
$char[$i] = '@{[Elatin7::fc qq<';
$left_e++;
}
elsif ($char[$i] eq '\Q') {
$char[$i] = '@{[CORE::quotemeta qq<';
$left_e++;
}
elsif ($char[$i] eq '\E') {
if ($right_e < $left_e) {
$char[$i] = '>]}';
$right_e++;
}
else {
$char[$i] = '';
}
}
elsif ($char[$i] eq '\Q') {
while (1) {
if (++$i > $#char) {
last;
}
if ($char[$i] eq '\E') {
last;
}
}
}
elsif ($char[$i] eq '\E') {
}
# $0 --> $0
elsif ($char[$i] =~ /\A \$ 0 \z/oxms) {
}
elsif ($char[$i] =~ /\A \$ \{ \s* 0 \s* \} \z/oxms) {
}
# $$ --> $$
elsif ($char[$i] =~ /\A \$\$ \z/oxms) {
}
# $1, $2, $3 --> $2, $3, $4 after s/// with multibyte anchoring
# $1, $2, $3 --> $1, $2, $3 otherwise
elsif ($char[$i] =~ /\A \$ ([1-9][0-9]*) \z/oxms) {
$char[$i] = e_capture($1);
}
elsif ($char[$i] =~ /\A \$ \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
}
# $$foo[ ... ] --> $ $foo->[ ... ]
elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \[ (?:$qq_bracket)*? \] ) \z/oxms) {
$char[$i] = e_capture($1.'->'.$2);
}
# $$foo{ ... } --> $ $foo->{ ... }
elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ (?:$qq_brace)*? \} ) \z/oxms) {
$char[$i] = e_capture($1.'->'.$2);
}
# $$foo
elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) \z/oxms) {
$char[$i] = e_capture($1);
}
# $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> Elatin7::PREMATCH()
elsif ($char[$i] =~ /\A ( \$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) \z/oxmsgc) {
$char[$i] = '@{[Elatin7::PREMATCH()]}';
}
# $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Elatin7::MATCH()
elsif ($char[$i] =~ /\A ( \$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) \z/oxmsgc) {
$char[$i] = '@{[Elatin7::MATCH()]}';
}
# $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Elatin7::POSTMATCH()
elsif ($char[$i] =~ /\A ( \$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) \z/oxmsgc) {
$char[$i] = '@{[Elatin7::POSTMATCH()]}';
}
# ${ foo } --> ${ foo }
elsif ($char[$i] =~ /\A \$ \s* \{ \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* \} \z/oxms) {
}
# ${ ... }
elsif ($char[$i] =~ /\A \$ \s* \{ \s* ( .+ ) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
}
}
# return string
if ($left_e > $right_e) {
return join '', $ope, $delimiter, @char, '>]}' x ($left_e - $right_e), $end_delimiter;
}
return join '', $ope, $delimiter, @char, $end_delimiter;
}
#
# escape qw string (qw//)
#
sub e_qw {
my($ope,$delimiter,$end_delimiter,$string) = @_;
$slash = 'div';
# choice again delimiter
my %octet = map {$_ => 1} ($string =~ /\G ([\x00-\xFF]) /oxmsg);
if (not $octet{$end_delimiter}) {
return join '', $ope, $delimiter, $string, $end_delimiter;
}
elsif (not $octet{')'}) {
return join '', $ope, '(', $string, ')';
}
elsif (not $octet{'}'}) {
return join '', $ope, '{', $string, '}';
}
elsif (not $octet{']'}) {
return join '', $ope, '[', $string, ']';
}
elsif (not $octet{'>'}) {
return join '', $ope, '<', $string, '>';
}
else {
for my $char (qw( ! " $ % & * + - . / : = ? @ ^ ` | ~ ), "\x00".."\x1F", "\x7F", "\xFF") {
if (not $octet{$char}) {
return join '', $ope, $char, $string, $char;
}
}
}
# qw/AAA BBB C'CC/ --> ('AAA', 'BBB', 'C\'CC')
my @string = CORE::split(/\s+/, $string);
for my $string (@string) {
my @octet = $string =~ /\G ([\x00-\xFF]) /oxmsg;
for my $octet (@octet) {
if ($octet =~ /\A (['\\]) \z/oxms) {
$octet = '\\' . $1;
}
}
$string = join '', @octet;
}
return join '', '(', (join ', ', map { "'$_'" } @string), ')';
}
#
# escape here document (<<"HEREDOC", <<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 =~ /\G(
\\o\{ [0-7]+ \} |
\\x\{ [0-9A-Fa-f]+ \} |
\\N\{ [^0-9\}][^\}]* \} |
\$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} |
\$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} |
\$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} |
\$ \s* \d+ |
\$ \s* \{ \s* \d+ \s* \} |
\$ \$ (?![\w\{]) |
\$ \s* \$ \s* $qq_variable |
\\?(?:$q_char)
)/oxmsg;
for (my $i=0; $i <= $#char; $i++) {
# "\L\u" --> "\u\L"
if (($char[$i] eq '\L') and ($char[$i+1] eq '\u')) {
@char[$i,$i+1] = @char[$i+1,$i];
}
# "\U\l" --> "\l\U"
elsif (($char[$i] eq '\U') and ($char[$i+1] eq '\l')) {
@char[$i,$i+1] = @char[$i+1,$i];
}
# octal escape sequence
elsif ($char[$i] =~ /\A \\o \{ ([0-7]+) \} \z/oxms) {
$char[$i] = Elatin7::octchr($1);
}
# hexadecimal escape sequence
elsif ($char[$i] =~ /\A \\x \{ ([0-9A-Fa-f]+) \} \z/oxms) {
$char[$i] = Elatin7::hexchr($1);
}
# \N{CHARNAME} --> N{CHARNAME}
elsif ($char[$i] =~ /\A \\ ( N\{ ([^0-9\}][^\}]*) \} ) \z/oxms) {
$char[$i] = $1;
}
if (0) {
}
# \u \l \U \L \F \Q \E
elsif ($char[$i] =~ /\A ([<>]) \z/oxms) {
if ($right_e < $left_e) {
$char[$i] = '\\' . $char[$i];
}
}
elsif ($char[$i] eq '\u') {
$char[$i] = '@{[Elatin7::ucfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\l') {
$char[$i] = '@{[Elatin7::lcfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\U') {
$char[$i] = '@{[Elatin7::uc qq<';
$left_e++;
}
elsif ($char[$i] eq '\L') {
$char[$i] = '@{[Elatin7::lc qq<';
$left_e++;
}
elsif ($char[$i] eq '\F') {
$char[$i] = '@{[Elatin7::fc qq<';
$left_e++;
}
elsif ($char[$i] eq '\Q') {
$char[$i] = '@{[CORE::quotemeta qq<';
$left_e++;
}
elsif ($char[$i] eq '\E') {
if ($right_e < $left_e) {
$char[$i] = '>]}';
$right_e++;
}
else {
$char[$i] = '';
}
}
elsif ($char[$i] eq '\Q') {
while (1) {
if (++$i > $#char) {
last;
}
if ($char[$i] eq '\E') {
last;
}
}
}
elsif ($char[$i] eq '\E') {
}
# $0 --> $0
elsif ($char[$i] =~ /\A \$ 0 \z/oxms) {
}
elsif ($char[$i] =~ /\A \$ \{ \s* 0 \s* \} \z/oxms) {
}
# $$ --> $$
elsif ($char[$i] =~ /\A \$\$ \z/oxms) {
}
# $1, $2, $3 --> $2, $3, $4 after s/// with multibyte anchoring
# $1, $2, $3 --> $1, $2, $3 otherwise
elsif ($char[$i] =~ /\A \$ ([1-9][0-9]*) \z/oxms) {
$char[$i] = e_capture($1);
}
elsif ($char[$i] =~ /\A \$ \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
}
# $$foo[ ... ] --> $ $foo->[ ... ]
elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \[ (?:$qq_bracket)*? \] ) \z/oxms) {
$char[$i] = e_capture($1.'->'.$2);
}
# $$foo{ ... } --> $ $foo->{ ... }
elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ (?:$qq_brace)*? \} ) \z/oxms) {
$char[$i] = e_capture($1.'->'.$2);
}
# $$foo
elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) \z/oxms) {
$char[$i] = e_capture($1);
}
# $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> Elatin7::PREMATCH()
elsif ($char[$i] =~ /\A ( \$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) \z/oxmsgc) {
$char[$i] = '@{[Elatin7::PREMATCH()]}';
}
# $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Elatin7::MATCH()
elsif ($char[$i] =~ /\A ( \$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) \z/oxmsgc) {
$char[$i] = '@{[Elatin7::MATCH()]}';
}
# $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Elatin7::POSTMATCH()
elsif ($char[$i] =~ /\A ( \$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) \z/oxmsgc) {
$char[$i] = '@{[Elatin7::POSTMATCH()]}';
}
# ${ foo } --> ${ foo }
elsif ($char[$i] =~ /\A \$ \s* \{ \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* \} \z/oxms) {
}
# ${ ... }
elsif ($char[$i] =~ /\A \$ \s* \{ \s* ( .+ ) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
}
}
# return string
if ($left_e > $right_e) {
return join '', @char, '>]}' x ($left_e - $right_e);
}
return join '', @char;
}
#
# escape regexp (m//, qr//)
#
sub e_qr {
my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_;
$modifier ||= '';
$modifier =~ tr/p//d;
if ($modifier =~ /([adlu])/oxms) {
my $line = 0;
for (my $i=0; my($package,$filename,$use_line,$subroutine) = caller($i); $i++) {
if ($filename ne __FILE__) {
$line = $use_line + (CORE::substr($_,0,pos($_)) =~ tr/\n//) + 1;
last;
}
}
die qq{Unsupported modifier "$1" used at line $line.\n};
}
$slash = 'div';
# literal null string pattern
if ($string eq '') {
$modifier =~ tr/bB//d;
$modifier =~ tr/i//d;
return join '', $ope, $delimiter, $end_delimiter, $modifier;
}
# /b /B modifier
elsif ($modifier =~ tr/bB//d) {
# choice again delimiter
if ($delimiter =~ / [\@:] /oxms) {
my @char = $string =~ /\G([\x00-\xFF])/oxmsg;
my %octet = map {$_ => 1} @char;
if (not $octet{')'}) {
$delimiter = '(';
$end_delimiter = ')';
}
elsif (not $octet{'}'}) {
$delimiter = '{';
$end_delimiter = '}';
}
elsif (not $octet{']'}) {
$delimiter = '[';
$end_delimiter = ']';
}
elsif (not $octet{'>'}) {
$delimiter = '<';
$end_delimiter = '>';
}
else {
for my $char (qw( ! " $ % & * + - . / = ? ^ ` | ~ ), "\x00".."\x1F", "\x7F", "\xFF") {
if (not $octet{$char}) {
$delimiter = $char;
$end_delimiter = $char;
last;
}
}
}
}
if (($ope =~ /\A m? \z/oxms) and ($delimiter eq '?')) {
return join '', $ope, $delimiter, $string, $matched, $end_delimiter, $modifier;
}
else {
return join '', $ope, $delimiter, '(?:', $string, ')', $matched, $end_delimiter, $modifier;
}
}
my $ignorecase = ($modifier =~ /i/oxms) ? 1 : 0;
my $metachar = qr/[\@\\|[\]{^]/oxms;
# split regexp
my @char = $string =~ /\G(
\\o\{ [0-7]+ \} |
\\ [0-7]{2,3} |
\\x\{ [0-9A-Fa-f]+ \} |
\\x [0-9A-Fa-f]{1,2} |
\\c [\x40-\x5F] |
\\N\{ [^0-9\}][^\}]* \} |
\\p\{ [^0-9\}][^\}]* \} |
\\P\{ [^0-9\}][^\}]* \} |
\\ (?:$q_char) |
\$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} |
\$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} |
\$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} |
[\$\@] $qq_variable |
\$ \s* \d+ |
\$ \s* \{ \s* \d+ \s* \} |
\$ \$ (?![\w\{]) |
\$ \s* \$ \s* $qq_variable |
\[\:\^ (?:alnum|alpha|ascii|blank|cntrl|digit|graph|lower|print|punct|space|upper|word|xdigit) :\] |
\[\: (?:alnum|alpha|ascii|blank|cntrl|digit|graph|lower|print|punct|space|upper|word|xdigit) :\] |
\[\^ |
\(\? |
(?:$q_char)
)/oxmsg;
# choice again delimiter
if ($delimiter =~ / [\@:] /oxms) {
my %octet = map {$_ => 1} @char;
if (not $octet{')'}) {
$delimiter = '(';
$end_delimiter = ')';
}
elsif (not $octet{'}'}) {
$delimiter = '{';
$end_delimiter = '}';
}
elsif (not $octet{']'}) {
$delimiter = '[';
$end_delimiter = ']';
}
elsif (not $octet{'>'}) {
$delimiter = '<';
$end_delimiter = '>';
}
else {
for my $char (qw( ! " $ % & * + - . / = ? ^ ` | ~ ), "\x00".."\x1F", "\x7F", "\xFF") {
if (not $octet{$char}) {
$delimiter = $char;
$end_delimiter = $char;
last;
}
}
}
}
my $left_e = 0;
my $right_e = 0;
for (my $i=0; $i <= $#char; $i++) {
# "\L\u" --> "\u\L"
if (($char[$i] eq '\L') and ($char[$i+1] eq '\u')) {
@char[$i,$i+1] = @char[$i+1,$i];
}
# "\U\l" --> "\l\U"
elsif (($char[$i] eq '\U') and ($char[$i+1] eq '\l')) {
@char[$i,$i+1] = @char[$i+1,$i];
}
# octal escape sequence
elsif ($char[$i] =~ /\A \\o \{ ([0-7]+) \} \z/oxms) {
$char[$i] = Elatin7::octchr($1);
}
# hexadecimal escape sequence
elsif ($char[$i] =~ /\A \\x \{ ([0-9A-Fa-f]+) \} \z/oxms) {
$char[$i] = Elatin7::hexchr($1);
}
# \N{CHARNAME} --> N\{CHARNAME}
elsif ($char[$i] =~ /\A \\ (N) ( \{ ([^0-9\}][^\}]*) \} ) \z/oxms) {
$char[$i] = $1 . '\\' . $2;
}
# \p{PROPERTY} --> p\{PROPERTY}
elsif ($char[$i] =~ /\A \\ (p) ( \{ ([^0-9\}][^\}]*) \} ) \z/oxms) {
$char[$i] = $1 . '\\' . $2;
}
# \P{PROPERTY} --> P\{PROPERTY}
elsif ($char[$i] =~ /\A \\ (P) ( \{ ([^0-9\}][^\}]*) \} ) \z/oxms) {
$char[$i] = $1 . '\\' . $2;
}
# \p, \P, \X --> p, P, X
elsif ($char[$i] =~ /\A \\ ( [pPX] ) \z/oxms) {
$char[$i] = $1;
}
if (0) {
}
# join separated multiple-octet
elsif ($char[$i] =~ /\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms) {
if ( ($i+3 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+3]) == 3) and (eval(sprintf '"%s%s%s%s"', @char[$i..$i+3]) =~ /\A $q_char \z/oxms)) {
$char[$i] .= join '', splice @char, $i+1, 3;
}
elsif (($i+2 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+2]) == 2) and (eval(sprintf '"%s%s%s"', @char[$i..$i+2]) =~ /\A $q_char \z/oxms)) {
$char[$i] .= join '', splice @char, $i+1, 2;
}
elsif (($i+1 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, $char[$i+1 ]) == 1) and (eval(sprintf '"%s%s"', @char[$i..$i+1]) =~ /\A $q_char \z/oxms)) {
$char[$i] .= join '', splice @char, $i+1, 1;
}
}
# open character class [...]
elsif ($char[$i] eq '[') {
my $left = $i;
# [] make die "Unmatched [] in regexp ..."
# (and so on)
if ($char[$i+1] eq ']') {
$i++;
}
while (1) {
if (++$i > $#char) {
die __FILE__, ": Unmatched [] in regexp";
}
if ($char[$i] eq ']') {
my $right = $i;
# [...]
if (grep(/\A [\$\@]/oxms,@char[$left+1..$right-1]) >= 1) {
splice @char, $left, $right-$left+1, sprintf(q{@{[Elatin7::charlist_qr(%s,'%s')]}}, join(',', map {qq_stuff($delimiter,$end_delimiter,$_)} @char[$left+1..$right-1]), $modifier);
}
else {
splice @char, $left, $right-$left+1, Elatin7::charlist_qr(@char[$left+1..$right-1], $modifier);
}
$i = $left;
last;
}
}
}
# open character class [^...]
elsif ($char[$i] eq '[^') {
my $left = $i;
# [^] make die "Unmatched [] in regexp ..."
# (and so on)
if ($char[$i+1] eq ']') {
$i++;
}
while (1) {
if (++$i > $#char) {
die __FILE__, ": Unmatched [] in regexp";
}
if ($char[$i] eq ']') {
my $right = $i;
# [^...]
if (grep(/\A [\$\@]/oxms,@char[$left+1..$right-1]) >= 1) {
splice @char, $left, $right-$left+1, sprintf(q{@{[Elatin7::charlist_not_qr(%s,'%s')]}}, join(',', map {qq_stuff($delimiter,$end_delimiter,$_)} @char[$left+1..$right-1]), $modifier);
}
else {
splice @char, $left, $right-$left+1, Elatin7::charlist_not_qr(@char[$left+1..$right-1], $modifier);
}
$i = $left;
last;
}
}
}
# rewrite character class or escape character
elsif (my $char = character_class($char[$i],$modifier)) {
$char[$i] = $char;
}
# /i modifier
elsif ($ignorecase and ($char[$i] =~ /\A [\x00-\xFF] \z/oxms) and (Elatin7::uc($char[$i]) ne Elatin7::fc($char[$i]))) {
if (CORE::length(Elatin7::fc($char[$i])) == 1) {
$char[$i] = '[' . Elatin7::uc($char[$i]) . Elatin7::fc($char[$i]) . ']';
}
else {
$char[$i] = '(?:' . Elatin7::uc($char[$i]) . '|' . Elatin7::fc($char[$i]) . ')';
}
}
# \u \l \U \L \F \Q \E
elsif ($char[$i] =~ /\A [<>] \z/oxms) {
if ($right_e < $left_e) {
$char[$i] = '\\' . $char[$i];
}
}
elsif ($char[$i] eq '\u') {
$char[$i] = '@{[Elatin7::ucfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\l') {
$char[$i] = '@{[Elatin7::lcfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\U') {
$char[$i] = '@{[Elatin7::uc qq<';
$left_e++;
}
elsif ($char[$i] eq '\L') {
$char[$i] = '@{[Elatin7::lc qq<';
$left_e++;
}
elsif ($char[$i] eq '\F') {
$char[$i] = '@{[Elatin7::fc qq<';
$left_e++;
}
elsif ($char[$i] eq '\Q') {
$char[$i] = '@{[CORE::quotemeta qq<';
$left_e++;
}
elsif ($char[$i] eq '\E') {
if ($right_e < $left_e) {
$char[$i] = '>]}';
$right_e++;
}
else {
$char[$i] = '';
}
}
elsif ($char[$i] eq '\Q') {
while (1) {
if (++$i > $#char) {
last;
}
if ($char[$i] eq '\E') {
last;
}
}
}
elsif ($char[$i] eq '\E') {
}
# $0 --> $0
elsif ($char[$i] =~ /\A \$ 0 \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
elsif ($char[$i] =~ /\A \$ \{ \s* 0 \s* \} \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $$ --> $$
elsif ($char[$i] =~ /\A \$\$ \z/oxms) {
}
# $1, $2, $3 --> $2, $3, $4 after s/// with multibyte anchoring
# $1, $2, $3 --> $1, $2, $3 otherwise
elsif ($char[$i] =~ /\A \$ ([1-9][0-9]*) \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
elsif ($char[$i] =~ /\A \$ \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo[ ... ] --> $ $foo->[ ... ]
elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \[ (?:$qq_bracket)*? \] ) \z/oxms) {
$char[$i] = e_capture($1.'->'.$2);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo{ ... } --> $ $foo->{ ... }
elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ (?:$qq_brace)*? \} ) \z/oxms) {
$char[$i] = e_capture($1.'->'.$2);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo
elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> Elatin7::PREMATCH()
elsif ($char[$i] =~ /\A ( \$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(Elatin7::PREMATCH())]}';
}
else {
$char[$i] = '@{[Elatin7::PREMATCH()]}';
}
}
# $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Elatin7::MATCH()
elsif ($char[$i] =~ /\A ( \$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(Elatin7::MATCH())]}';
}
else {
$char[$i] = '@{[Elatin7::MATCH()]}';
}
}
# $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Elatin7::POSTMATCH()
elsif ($char[$i] =~ /\A ( \$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(Elatin7::POSTMATCH())]}';
}
else {
$char[$i] = '@{[Elatin7::POSTMATCH()]}';
}
}
# ${ foo }
elsif ($char[$i] =~ /\A \$ \s* \{ ( \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* ) \} \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# ${ ... }
elsif ($char[$i] =~ /\A \$ \s* \{ \s* ( .+ ) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $scalar or @array
elsif ($char[$i] =~ /\A [\$\@].+ /oxms) {
$char[$i] = e_string($char[$i]);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# quote character before ? + * {
elsif (($i >= 1) and ($char[$i] =~ /\A [\?\+\*\{] \z/oxms)) {
if ($char[$i-1] =~ /\A (?:\\[0-7]{2,3}|\\x[0-9-A-Fa-f]{1,2}) \z/oxms) {
}
elsif (($ope =~ /\A m? \z/oxms) and ($delimiter eq '?')) {
my $char = $char[$i-1];
if ($char[$i] eq '{') {
die __FILE__, qq{: "MULTIBYTE{n}" should be "(MULTIBYTE){n}" in m?? (and shift \$1,\$2,\$3,...) ($char){n}};
}
else {
die __FILE__, qq{: "MULTIBYTE$char[$i]" should be "(MULTIBYTE)$char[$i]" in m?? (and shift \$1,\$2,\$3,...) ($char)$char[$i]};
}
}
else {
$char[$i-1] = '(?:' . $char[$i-1] . ')';
}
}
}
# make regexp string
$modifier =~ tr/i//d;
if ($left_e > $right_e) {
if (($ope =~ /\A m? \z/oxms) and ($delimiter eq '?')) {
return join '', $ope, $delimiter, $anchor, @char, '>]}' x ($left_e - $right_e), $matched, $end_delimiter, $modifier;
}
else {
return join '', $ope, $delimiter, $anchor, '(?:', @char, '>]}' x ($left_e - $right_e), ')', $matched, $end_delimiter, $modifier;
}
}
if (($ope =~ /\A m? \z/oxms) and ($delimiter eq '?')) {
return join '', $ope, $delimiter, $anchor, @char, $matched, $end_delimiter, $modifier;
}
else {
return join '', $ope, $delimiter, $anchor, '(?:', @char, ')', $matched, $end_delimiter, $modifier;
}
}
#
# double quote stuff
#
sub qq_stuff {
my($delimiter,$end_delimiter,$stuff) = @_;
# scalar variable or array variable
if ($stuff =~ /\A [\$\@] /oxms) {
return $stuff;
}
# quote by delimiter
my %octet = map {$_ => 1} ($stuff =~ /\G ([\x00-\xFF]) /oxmsg);
for my $char (qw( ! " $ % & * + - . / : = ? @ ^ ` | ~ ), "\x00".."\x1F", "\x7F", "\xFF") {
next if $char eq $delimiter;
next if $char eq $end_delimiter;
if (not $octet{$char}) {
return join '', 'qq', $char, $stuff, $char;
}
}
return join '', 'qq', '<', $stuff, '>';
}
#
# escape regexp (m'', qr'', and m''b, qr''b)
#
sub e_qr_q {
my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_;
$modifier ||= '';
$modifier =~ tr/p//d;
if ($modifier =~ /([adlu])/oxms) {
my $line = 0;
for (my $i=0; my($package,$filename,$use_line,$subroutine) = caller($i); $i++) {
if ($filename ne __FILE__) {
$line = $use_line + (CORE::substr($_,0,pos($_)) =~ tr/\n//) + 1;
last;
}
}
die qq{Unsupported modifier "$1" used at line $line.\n};
}
$slash = 'div';
# literal null string pattern
if ($string eq '') {
$modifier =~ tr/bB//d;
$modifier =~ tr/i//d;
return join '', $ope, $delimiter, $end_delimiter, $modifier;
}
# with /b /B modifier
elsif ($modifier =~ tr/bB//d) {
return e_qr_qb($ope,$delimiter,$end_delimiter,$string,$modifier);
}
# without /b /B modifier
else {
return e_qr_qt($ope,$delimiter,$end_delimiter,$string,$modifier);
}
}
#
# escape regexp (m'', qr'')
#
sub e_qr_qt {
my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_;
my $ignorecase = ($modifier =~ /i/oxms) ? 1 : 0;
# split regexp
my @char = $string =~ /\G(
\[\:\^ [a-z]+ \:\] |
\[\: [a-z]+ \:\] |
\[\^ |
[\$\@\/\\] |
\\? (?:$q_char)
)/oxmsg;
# unescape character
for (my $i=0; $i <= $#char; $i++) {
if (0) {
}
# 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, Elatin7::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, Elatin7::charlist_not_qr(@char[$left+1..$right-1], $modifier);
$i = $left;
last;
}
}
}
# escape $ @ / and \
elsif ($char[$i] =~ /\A [\$\@\/\\] \z/oxms) {
$char[$i] = '\\' . $char[$i];
}
# rewrite character class or escape character
elsif (my $char = character_class($char[$i],$modifier)) {
$char[$i] = $char;
}
# /i modifier
elsif ($ignorecase and ($char[$i] =~ /\A [\x00-\xFF] \z/oxms) and (Elatin7::uc($char[$i]) ne Elatin7::fc($char[$i]))) {
if (CORE::length(Elatin7::fc($char[$i])) == 1) {
$char[$i] = '[' . Elatin7::uc($char[$i]) . Elatin7::fc($char[$i]) . ']';
}
else {
$char[$i] = '(?:' . Elatin7::uc($char[$i]) . '|' . Elatin7::fc($char[$i]) . ')';
}
}
# quote character before ? + * {
elsif (($i >= 1) and ($char[$i] =~ /\A [\?\+\*\{] \z/oxms)) {
if ($char[$i-1] =~ /\A [\x00-\xFF] \z/oxms) {
}
else {
$char[$i-1] = '(?:' . $char[$i-1] . ')';
}
}
}
$delimiter = '/';
$end_delimiter = '/';
$modifier =~ tr/i//d;
return join '', $ope, $delimiter, $anchor, '(?:', @char, ')', $matched, $end_delimiter, $modifier;
}
#
# escape regexp (m''b, qr''b)
#
sub e_qr_qb {
my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_;
# split regexp
my @char = $string =~ /\G(
\\\\ |
[\$\@\/\\] |
[\x00-\xFF]
)/oxmsg;
# unescape character
for (my $i=0; $i <= $#char; $i++) {
if (0) {
}
# remain \\
elsif ($char[$i] eq '\\\\') {
}
# escape $ @ / and \
elsif ($char[$i] =~ /\A [\$\@\/\\] \z/oxms) {
$char[$i] = '\\' . $char[$i];
}
}
$delimiter = '/';
$end_delimiter = '/';
return join '', $ope, $delimiter, '(?:', @char, ')', $matched, $end_delimiter, $modifier;
}
#
# escape regexp (s/here//)
#
sub e_s1 {
my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_;
$modifier ||= '';
$modifier =~ tr/p//d;
if ($modifier =~ /([adlu])/oxms) {
my $line = 0;
for (my $i=0; my($package,$filename,$use_line,$subroutine) = caller($i); $i++) {
if ($filename ne __FILE__) {
$line = $use_line + (CORE::substr($_,0,pos($_)) =~ tr/\n//) + 1;
last;
}
}
die qq{Unsupported modifier "$1" used at line $line.\n};
}
$slash = 'div';
# literal null string pattern
if ($string eq '') {
$modifier =~ tr/bB//d;
$modifier =~ tr/i//d;
return join '', $ope, $delimiter, $end_delimiter, $modifier;
}
# /b /B modifier
elsif ($modifier =~ tr/bB//d) {
# choice again delimiter
if ($delimiter =~ / [\@:] /oxms) {
my @char = $string =~ /\G([\x00-\xFF])/oxmsg;
my %octet = map {$_ => 1} @char;
if (not $octet{')'}) {
$delimiter = '(';
$end_delimiter = ')';
}
elsif (not $octet{'}'}) {
$delimiter = '{';
$end_delimiter = '}';
}
elsif (not $octet{']'}) {
$delimiter = '[';
$end_delimiter = ']';
}
elsif (not $octet{'>'}) {
$delimiter = '<';
$end_delimiter = '>';
}
else {
for my $char (qw( ! " $ % & * + - . / = ? ^ ` | ~ ), "\x00".."\x1F", "\x7F", "\xFF") {
if (not $octet{$char}) {
$delimiter = $char;
$end_delimiter = $char;
last;
}
}
}
}
my $prematch = '';
return join '', $ope, $delimiter, $prematch, '(?:', $string, ')', $matched, $end_delimiter, $modifier;
}
my $ignorecase = ($modifier =~ /i/oxms) ? 1 : 0;
my $metachar = qr/[\@\\|[\]{^]/oxms;
# split regexp
my @char = $string =~ /\G(
\\g \s* \{ \s* - \s* [1-9][0-9]* \s* \} |
\\g \s* \{ \s* [1-9][0-9]* \s* \} |
\\g \s* [1-9][0-9]* |
\\o\{ [0-7]+ \} |
\\ [1-9][0-9]* |
\\ [0-7]{2,3} |
\\x\{ [0-9A-Fa-f]+ \} |
\\x [0-9A-Fa-f]{1,2} |
\\c [\x40-\x5F] |
\\N\{ [^0-9\}][^\}]* \} |
\\p\{ [^0-9\}][^\}]* \} |
\\P\{ [^0-9\}][^\}]* \} |
\\ (?:$q_char) |
\$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} |
\$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} |
\$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} |
[\$\@] $qq_variable |
\$ \s* \d+ |
\$ \s* \{ \s* \d+ \s* \} |
\$ \$ (?![\w\{]) |
\$ \s* \$ \s* $qq_variable |
\[\:\^ (?:alnum|alpha|ascii|blank|cntrl|digit|graph|lower|print|punct|space|upper|word|xdigit) :\] |
\[\: (?:alnum|alpha|ascii|blank|cntrl|digit|graph|lower|print|punct|space|upper|word|xdigit) :\] |
\[\^ |
\(\? |
(?:$q_char)
)/oxmsg;
# choice again delimiter
if ($delimiter =~ / [\@:] /oxms) {
my %octet = map {$_ => 1} @char;
if (not $octet{')'}) {
$delimiter = '(';
$end_delimiter = ')';
}
elsif (not $octet{'}'}) {
$delimiter = '{';
$end_delimiter = '}';
}
elsif (not $octet{']'}) {
$delimiter = '[';
$end_delimiter = ']';
}
elsif (not $octet{'>'}) {
$delimiter = '<';
$end_delimiter = '>';
}
else {
for my $char (qw( ! " $ % & * + - . / = ? ^ ` | ~ ), "\x00".."\x1F", "\x7F", "\xFF") {
if (not $octet{$char}) {
$delimiter = $char;
$end_delimiter = $char;
last;
}
}
}
}
# count '('
my $parens = grep { $_ eq '(' } @char;
my $left_e = 0;
my $right_e = 0;
for (my $i=0; $i <= $#char; $i++) {
# "\L\u" --> "\u\L"
if (($char[$i] eq '\L') and ($char[$i+1] eq '\u')) {
@char[$i,$i+1] = @char[$i+1,$i];
}
# "\U\l" --> "\l\U"
elsif (($char[$i] eq '\U') and ($char[$i+1] eq '\l')) {
@char[$i,$i+1] = @char[$i+1,$i];
}
# octal escape sequence
elsif ($char[$i] =~ /\A \\o \{ ([0-7]+) \} \z/oxms) {
$char[$i] = Elatin7::octchr($1);
}
# hexadecimal escape sequence
elsif ($char[$i] =~ /\A \\x \{ ([0-9A-Fa-f]+) \} \z/oxms) {
$char[$i] = Elatin7::hexchr($1);
}
# \N{CHARNAME} --> N\{CHARNAME}
elsif ($char[$i] =~ /\A \\ (N) ( \{ ([^0-9\}][^\}]*) \} ) \z/oxms) {
$char[$i] = $1 . '\\' . $2;
}
# \p{PROPERTY} --> p\{PROPERTY}
elsif ($char[$i] =~ /\A \\ (p) ( \{ ([^0-9\}][^\}]*) \} ) \z/oxms) {
$char[$i] = $1 . '\\' . $2;
}
# \P{PROPERTY} --> P\{PROPERTY}
elsif ($char[$i] =~ /\A \\ (P) ( \{ ([^0-9\}][^\}]*) \} ) \z/oxms) {
$char[$i] = $1 . '\\' . $2;
}
# \p, \P, \X --> p, P, X
elsif ($char[$i] =~ /\A \\ ( [pPX] ) \z/oxms) {
$char[$i] = $1;
}
if (0) {
}
# join separated multiple-octet
elsif ($char[$i] =~ /\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms) {
if ( ($i+3 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+3]) == 3) and (eval(sprintf '"%s%s%s%s"', @char[$i..$i+3]) =~ /\A $q_char \z/oxms)) {
$char[$i] .= join '', splice @char, $i+1, 3;
}
elsif (($i+2 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+2]) == 2) and (eval(sprintf '"%s%s%s"', @char[$i..$i+2]) =~ /\A $q_char \z/oxms)) {
$char[$i] .= join '', splice @char, $i+1, 2;
}
elsif (($i+1 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, $char[$i+1 ]) == 1) and (eval(sprintf '"%s%s"', @char[$i..$i+1]) =~ /\A $q_char \z/oxms)) {
$char[$i] .= join '', splice @char, $i+1, 1;
}
}
# open character class [...]
elsif ($char[$i] eq '[') {
my $left = $i;
if ($char[$i+1] eq ']') {
$i++;
}
while (1) {
if (++$i > $#char) {
die __FILE__, ": Unmatched [] in regexp";
}
if ($char[$i] eq ']') {
my $right = $i;
# [...]
if (grep(/\A [\$\@]/oxms,@char[$left+1..$right-1]) >= 1) {
splice @char, $left, $right-$left+1, sprintf(q{@{[Elatin7::charlist_qr(%s,'%s')]}}, join(',', map {qq_stuff($delimiter,$end_delimiter,$_)} @char[$left+1..$right-1]), $modifier);
}
else {
splice @char, $left, $right-$left+1, Elatin7::charlist_qr(@char[$left+1..$right-1], $modifier);
}
$i = $left;
last;
}
}
}
# open character class [^...]
elsif ($char[$i] eq '[^') {
my $left = $i;
if ($char[$i+1] eq ']') {
$i++;
}
while (1) {
if (++$i > $#char) {
die __FILE__, ": Unmatched [] in regexp";
}
if ($char[$i] eq ']') {
my $right = $i;
# [^...]
if (grep(/\A [\$\@]/oxms,@char[$left+1..$right-1]) >= 1) {
splice @char, $left, $right-$left+1, sprintf(q{@{[Elatin7::charlist_not_qr(%s,'%s')]}}, join(',', map {qq_stuff($delimiter,$end_delimiter,$_)} @char[$left+1..$right-1]), $modifier);
}
else {
splice @char, $left, $right-$left+1, Elatin7::charlist_not_qr(@char[$left+1..$right-1], $modifier);
}
$i = $left;
last;
}
}
}
# rewrite character class or escape character
elsif (my $char = character_class($char[$i],$modifier)) {
$char[$i] = $char;
}
# /i modifier
elsif ($ignorecase and ($char[$i] =~ /\A [\x00-\xFF] \z/oxms) and (Elatin7::uc($char[$i]) ne Elatin7::fc($char[$i]))) {
if (CORE::length(Elatin7::fc($char[$i])) == 1) {
$char[$i] = '[' . Elatin7::uc($char[$i]) . Elatin7::fc($char[$i]) . ']';
}
else {
$char[$i] = '(?:' . Elatin7::uc($char[$i]) . '|' . Elatin7::fc($char[$i]) . ')';
}
}
# \u \l \U \L \F \Q \E
elsif ($char[$i] =~ /\A [<>] \z/oxms) {
if ($right_e < $left_e) {
$char[$i] = '\\' . $char[$i];
}
}
elsif ($char[$i] eq '\u') {
$char[$i] = '@{[Elatin7::ucfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\l') {
$char[$i] = '@{[Elatin7::lcfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\U') {
$char[$i] = '@{[Elatin7::uc qq<';
$left_e++;
}
elsif ($char[$i] eq '\L') {
$char[$i] = '@{[Elatin7::lc qq<';
$left_e++;
}
elsif ($char[$i] eq '\F') {
$char[$i] = '@{[Elatin7::fc qq<';
$left_e++;
}
elsif ($char[$i] eq '\Q') {
$char[$i] = '@{[CORE::quotemeta qq<';
$left_e++;
}
elsif ($char[$i] eq '\E') {
if ($right_e < $left_e) {
$char[$i] = '>]}';
$right_e++;
}
else {
$char[$i] = '';
}
}
elsif ($char[$i] eq '\Q') {
while (1) {
if (++$i > $#char) {
last;
}
if ($char[$i] eq '\E') {
last;
}
}
}
elsif ($char[$i] eq '\E') {
}
# \0 --> \0
elsif ($char[$i] =~ /\A \\ \s* 0 \z/oxms) {
}
# \g{N}, \g{-N}
# P.108 Using Simple Patterns
# in Chapter 7: In the World of Regular Expressions
# of ISBN 978-0-596-52010-6 Learning Perl, Fifth Edition
# P.221 Capturing
# in Chapter 5: Pattern Matching
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
# \g{-1}, \g{-2}, \g{-3} --> \g{-1}, \g{-2}, \g{-3}
elsif ($char[$i] =~ /\A \\g \s* \{ \s* - \s* ([1-9][0-9]*) \s* \} \z/oxms) {
}
# \g{1}, \g{2}, \g{3} --> \g{2}, \g{3}, \g{4} (only when multibyte anchoring is enable)
elsif ($char[$i] =~ /\A \\g \s* \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) {
}
# \g1, \g2, \g3 --> \g2, \g3, \g4 (only when multibyte anchoring is enable)
elsif ($char[$i] =~ /\A \\g \s* ([1-9][0-9]*) \z/oxms) {
}
# \1, \2, \3 --> \2, \3, \4 (only when multibyte anchoring is enable)
elsif ($char[$i] =~ /\A \\ \s* ([1-9][0-9]*) \z/oxms) {
}
# $0 --> $0
elsif ($char[$i] =~ /\A \$ 0 \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
elsif ($char[$i] =~ /\A \$ \{ \s* 0 \s* \} \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $$ --> $$
elsif ($char[$i] =~ /\A \$\$ \z/oxms) {
}
# $1, $2, $3 --> $2, $3, $4 after s/// with multibyte anchoring
# $1, $2, $3 --> $1, $2, $3 otherwise
elsif ($char[$i] =~ /\A \$ ([1-9][0-9]*) \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
elsif ($char[$i] =~ /\A \$ \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo[ ... ] --> $ $foo->[ ... ]
elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \[ (?:$qq_bracket)*? \] ) \z/oxms) {
$char[$i] = e_capture($1.'->'.$2);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo{ ... } --> $ $foo->{ ... }
elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ (?:$qq_brace)*? \} ) \z/oxms) {
$char[$i] = e_capture($1.'->'.$2);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo
elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> Elatin7::PREMATCH()
elsif ($char[$i] =~ /\A ( \$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(Elatin7::PREMATCH())]}';
}
else {
$char[$i] = '@{[Elatin7::PREMATCH()]}';
}
}
# $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Elatin7::MATCH()
elsif ($char[$i] =~ /\A ( \$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(Elatin7::MATCH())]}';
}
else {
$char[$i] = '@{[Elatin7::MATCH()]}';
}
}
# $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Elatin7::POSTMATCH()
elsif ($char[$i] =~ /\A ( \$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(Elatin7::POSTMATCH())]}';
}
else {
$char[$i] = '@{[Elatin7::POSTMATCH()]}';
}
}
# ${ foo }
elsif ($char[$i] =~ /\A \$ \s* \{ ( \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* ) \} \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# ${ ... }
elsif ($char[$i] =~ /\A \$ \s* \{ \s* ( .+ ) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $scalar or @array
elsif ($char[$i] =~ /\A [\$\@].+ /oxms) {
$char[$i] = e_string($char[$i]);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# quote character before ? + * {
elsif (($i >= 1) and ($char[$i] =~ /\A [\?\+\*\{] \z/oxms)) {
if ($char[$i-1] =~ /\A (?:\\[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 =~ /([adlu])/oxms) {
my $line = 0;
for (my $i=0; my($package,$filename,$use_line,$subroutine) = caller($i); $i++) {
if ($filename ne __FILE__) {
$line = $use_line + (CORE::substr($_,0,pos($_)) =~ tr/\n//) + 1;
last;
}
}
die qq{Unsupported modifier "$1" used at line $line.\n};
}
$slash = 'div';
# literal null string pattern
if ($string eq '') {
$modifier =~ tr/bB//d;
$modifier =~ tr/i//d;
return join '', $ope, $delimiter, $end_delimiter, $modifier;
}
# with /b /B modifier
elsif ($modifier =~ tr/bB//d) {
return e_s1_qb($ope,$delimiter,$end_delimiter,$string,$modifier);
}
# without /b /B modifier
else {
return e_s1_qt($ope,$delimiter,$end_delimiter,$string,$modifier);
}
}
#
# escape regexp (s'here'')
#
sub e_s1_qt {
my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_;
my $ignorecase = ($modifier =~ /i/oxms) ? 1 : 0;
# split regexp
my @char = $string =~ /\G(
\[\:\^ [a-z]+ \:\] |
\[\: [a-z]+ \:\] |
\[\^ |
[\$\@\/\\] |
\\? (?:$q_char)
)/oxmsg;
# unescape character
for (my $i=0; $i <= $#char; $i++) {
if (0) {
}
# open character class [...]
elsif ($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, Elatin7::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, Elatin7::charlist_not_qr(@char[$left+1..$right-1], $modifier);
$i = $left;
last;
}
}
}
# escape $ @ / and \
elsif ($char[$i] =~ /\A [\$\@\/\\] \z/oxms) {
$char[$i] = '\\' . $char[$i];
}
# rewrite character class or escape character
elsif (my $char = character_class($char[$i],$modifier)) {
$char[$i] = $char;
}
# /i modifier
elsif ($ignorecase and ($char[$i] =~ /\A [\x00-\xFF] \z/oxms) and (Elatin7::uc($char[$i]) ne Elatin7::fc($char[$i]))) {
if (CORE::length(Elatin7::fc($char[$i])) == 1) {
$char[$i] = '[' . Elatin7::uc($char[$i]) . Elatin7::fc($char[$i]) . ']';
}
else {
$char[$i] = '(?:' . Elatin7::uc($char[$i]) . '|' . Elatin7::fc($char[$i]) . ')';
}
}
# quote character before ? + * {
elsif (($i >= 1) and ($char[$i] =~ /\A [\?\+\*\{] \z/oxms)) {
if ($char[$i-1] =~ /\A [\x00-\xFF] \z/oxms) {
}
else {
$char[$i-1] = '(?:' . $char[$i-1] . ')';
}
}
}
$modifier =~ tr/i//d;
$delimiter = '/';
$end_delimiter = '/';
my $prematch = '';
return join '', $ope, $delimiter, $prematch, '(?:', @char, ')', $matched, $end_delimiter, $modifier;
}
#
# escape regexp (s'here''b)
#
sub e_s1_qb {
my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_;
# split regexp
my @char = $string =~ /\G(
\\\\ |
[\$\@\/\\] |
[\x00-\xFF]
)/oxmsg;
# unescape character
for (my $i=0; $i <= $#char; $i++) {
if (0) {
}
# remain \\
elsif ($char[$i] eq '\\\\') {
}
# escape $ @ / and \
elsif ($char[$i] =~ /\A [\$\@\/\\] \z/oxms) {
$char[$i] = '\\' . $char[$i];
}
}
$delimiter = '/';
$end_delimiter = '/';
my $prematch = '';
return join '', $ope, $delimiter, $prematch, '(?:', @char, ')', $matched, $end_delimiter, $modifier;
}
#
# escape regexp (s''here')
#
sub e_s2_q {
my($ope,$delimiter,$end_delimiter,$string) = @_;
$slash = 'div';
my @char = $string =~ / \G (\\\\|[\$\@\/\\]|$q_char) /oxmsg;
for (my $i=0; $i <= $#char; $i++) {
if (0) {
}
# not escape \\
elsif ($char[$i] =~ /\A \\\\ \z/oxms) {
}
# escape $ @ / and \
elsif ($char[$i] =~ /\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 =~ /([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
# P.130 Advanced Use of \G with Perl
# in Chapter 3: Overview of Regular Expression Features and Flavors
# P.312 Iterative Matching: Scalar Context, with /g
# in Chapter 7: Perl
# of ISBN 0-596-00289-0 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 $sub = '';
# with /r
if ($r_modifier) {
if (0) {
}
# s///gr without multibyte anchoring
elsif ($modifier =~ /g/oxms) {
$sub = sprintf(
# 1 2 3 4 5
q<eval{local $Latin7::re_t=%s; while($Latin7::re_t =~ %s){%s local $^W=0; local $Latin7::re_r=%s; %s$Latin7::re_t="$`$Latin7::re_r$'"; pos($Latin7::re_t)=length "$`$Latin7::re_r"; } return $Latin7::re_t}>,
$variable, # 1
($delimiter1 eq "'") ? # 2
e_s1_q('m', $delimiter1, $end_delimiter1, $pattern, $modifier) : # :
e_s1 ('m', $delimiter1, $end_delimiter1, $pattern, $modifier), # :
$s_matched, # 3
$e_replacement, # 4
'$Latin7::re_r=eval $Latin7::re_r; ' x $e_modifier, # 5
);
}
# s///r
else {
my $prematch = q{$`};
$sub = sprintf(
# 1 2 3 4 5 6 7
q<(%s =~ %s) ? eval{%s local $^W=0; local $Latin7::re_r=%s; %s"%s$Latin7::re_r$'" } : %s>,
$variable, # 1
($delimiter1 eq "'") ? # 2
e_s1_q('m', $delimiter1, $end_delimiter1, $pattern, $modifier) : # :
e_s1 ('m', $delimiter1, $end_delimiter1, $pattern, $modifier), # :
$s_matched, # 3
$e_replacement, # 4
'$Latin7::re_r=eval $Latin7::re_r; ' x $e_modifier, # 5
$prematch, # 6
$variable, # 7
);
}
# $var !~ s///r doesn't make sense
if ($bind_operator =~ / !~ /oxms) {
$sub = q{die("$0: Using !~ with s///r doesn't make sense"), } . $sub;
}
}
# without /r
else {
if (0) {
}
# s///g without multibyte anchoring
elsif ($modifier =~ /g/oxms) {
$sub = sprintf(
# 1 2 3 4 5 6 7 8
q<eval{local $Latin7::re_n=0; while(%s =~ %s){%s local $^W=0; local $Latin7::re_r=%s; %s%s="$`$Latin7::re_r$'"; pos(%s)=length "$`$Latin7::re_r"; $Latin7::re_n++} return %s$Latin7::re_n}>,
$variable, # 1
($delimiter1 eq "'") ? # 2
e_s1_q('m', $delimiter1, $end_delimiter1, $pattern, $modifier) : # :
e_s1 ('m', $delimiter1, $end_delimiter1, $pattern, $modifier), # :
$s_matched, # 3
$e_replacement, # 4
'$Latin7::re_r=eval $Latin7::re_r; ' x $e_modifier, # 5
$variable, # 6
$variable, # 7
($bind_operator =~ / !~ /oxms) ? '!' : '', # 8
);
}
# s///
else {
my $prematch = q{$`};
$sub = sprintf(
($bind_operator =~ / =~ /oxms) ?
# 1 2 3 4 5 6 7 8
q<(%s%s%s) ? eval{%s local $^W=0; local $Latin7::re_r=%s; %s%s="%s$Latin7::re_r$'"; 1 } : undef> :
# 1 2 3 4 5 6 7 8
q<(%s%s%s) ? 1 : eval{%s local $^W=0; local $Latin7::re_r=%s; %s%s="%s$Latin7::re_r$'"; undef }>,
$variable, # 1
$bind_operator, # 2
($delimiter1 eq "'") ? # 3
e_s1_q('m', $delimiter1, $end_delimiter1, $pattern, $modifier) : # :
e_s1 ('m', $delimiter1, $end_delimiter1, $pattern, $modifier), # :
$s_matched, # 4
$e_replacement, # 5
'$Latin7::re_r=eval $Latin7::re_r; ' x $e_modifier, # 6
$variable, # 7
$prematch, # 8
);
}
}
# (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 =~ /([adlu])/oxms) {
my $line = 0;
for (my $i=0; my($package,$filename,$use_line,$subroutine) = caller($i); $i++) {
if ($filename ne __FILE__) {
$line = $use_line + (CORE::substr($_,0,pos($_)) =~ tr/\n//) + 1;
last;
}
}
die qq{Unsupported modifier "$1" used at line $line.\n};
}
$slash = 'div';
# /b /B modifier
if ($modifier =~ tr/bB//d) {
return join '', 'split', $ope, $delimiter, $string, $end_delimiter, $modifier;
}
my $ignorecase = ($modifier =~ /i/oxms) ? 1 : 0;
my $metachar = qr/[\@\\|[\]{^]/oxms;
# split regexp
my @char = $string =~ /\G(
\\o\{ [0-7]+ \} |
\\ [0-7]{2,3} |
\\x\{ [0-9A-Fa-f]+ \} |
\\x [0-9A-Fa-f]{1,2} |
\\c [\x40-\x5F] |
\\N\{ [^0-9\}][^\}]* \} |
\\p\{ [^0-9\}][^\}]* \} |
\\P\{ [^0-9\}][^\}]* \} |
\\ (?:$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] =~ /\A \\o \{ ([0-7]+) \} \z/oxms) {
$char[$i] = Elatin7::octchr($1);
}
# hexadecimal escape sequence
elsif ($char[$i] =~ /\A \\x \{ ([0-9A-Fa-f]+) \} \z/oxms) {
$char[$i] = Elatin7::hexchr($1);
}
# \N{CHARNAME} --> N\{CHARNAME}
elsif ($char[$i] =~ /\A \\ (N) ( \{ ([^0-9\}][^\}]*) \} ) \z/oxms) {
$char[$i] = $1 . '\\' . $2;
}
# \p{PROPERTY} --> p\{PROPERTY}
elsif ($char[$i] =~ /\A \\ (p) ( \{ ([^0-9\}][^\}]*) \} ) \z/oxms) {
$char[$i] = $1 . '\\' . $2;
}
# \P{PROPERTY} --> P\{PROPERTY}
elsif ($char[$i] =~ /\A \\ (P) ( \{ ([^0-9\}][^\}]*) \} ) \z/oxms) {
$char[$i] = $1 . '\\' . $2;
}
# \p, \P, \X --> p, P, X
elsif ($char[$i] =~ /\A \\ ( [pPX] ) \z/oxms) {
$char[$i] = $1;
}
if (0) {
}
# join separated multiple-octet
elsif ($char[$i] =~ /\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms) {
if ( ($i+3 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+3]) == 3) and (eval(sprintf '"%s%s%s%s"', @char[$i..$i+3]) =~ /\A $q_char \z/oxms)) {
$char[$i] .= join '', splice @char, $i+1, 3;
}
elsif (($i+2 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, @char[$i+1..$i+2]) == 2) and (eval(sprintf '"%s%s%s"', @char[$i..$i+2]) =~ /\A $q_char \z/oxms)) {
$char[$i] .= join '', splice @char, $i+1, 2;
}
elsif (($i+1 <= $#char) and (grep(/\A (?: \\ [0-7]{2,3} | \\x [0-9A-Fa-f]{1,2}) \z/oxms, $char[$i+1 ]) == 1) and (eval(sprintf '"%s%s"', @char[$i..$i+1]) =~ /\A $q_char \z/oxms)) {
$char[$i] .= join '', splice @char, $i+1, 1;
}
}
# open character class [...]
elsif ($char[$i] eq '[') {
my $left = $i;
if ($char[$i+1] eq ']') {
$i++;
}
while (1) {
if (++$i > $#char) {
die __FILE__, ": Unmatched [] in regexp";
}
if ($char[$i] eq ']') {
my $right = $i;
# [...]
if (grep(/\A [\$\@]/oxms,@char[$left+1..$right-1]) >= 1) {
splice @char, $left, $right-$left+1, sprintf(q{@{[Elatin7::charlist_qr(%s,'%s')]}}, join(',', map {qq_stuff($delimiter,$end_delimiter,$_)} @char[$left+1..$right-1]), $modifier);
}
else {
splice @char, $left, $right-$left+1, Elatin7::charlist_qr(@char[$left+1..$right-1], $modifier);
}
$i = $left;
last;
}
}
}
# open character class [^...]
elsif ($char[$i] eq '[^') {
my $left = $i;
if ($char[$i+1] eq ']') {
$i++;
}
while (1) {
if (++$i > $#char) {
die __FILE__, ": Unmatched [] in regexp";
}
if ($char[$i] eq ']') {
my $right = $i;
# [^...]
if (grep(/\A [\$\@]/oxms,@char[$left+1..$right-1]) >= 1) {
splice @char, $left, $right-$left+1, sprintf(q{@{[Elatin7::charlist_not_qr(%s,'%s')]}}, join(',', map {qq_stuff($delimiter,$end_delimiter,$_)} @char[$left+1..$right-1]), $modifier);
}
else {
splice @char, $left, $right-$left+1, Elatin7::charlist_not_qr(@char[$left+1..$right-1], $modifier);
}
$i = $left;
last;
}
}
}
# rewrite character class or escape character
elsif (my $char = character_class($char[$i],$modifier)) {
$char[$i] = $char;
}
# P.794 29.2.161. split
# in Chapter 29: Functions
# of ISBN 0-596-00027-8 Programming Perl Third Edition.
# P.951 split
# in Chapter 27: Functions
# of ISBN 978-0-596-00492-7 Programming Perl 4th Edition.
# said "The //m modifier is assumed when you split on the pattern /^/",
# but perl5.008 is not so. Therefore, this software adds //m.
# (and so on)
# split(m/^/) --> split(m/^/m)
elsif (($char[$i] eq '^') and ($modifier !~ /m/oxms)) {
$modifier .= 'm';
}
# /i modifier
elsif ($ignorecase and ($char[$i] =~ /\A [\x00-\xFF] \z/oxms) and (Elatin7::uc($char[$i]) ne Elatin7::fc($char[$i]))) {
if (CORE::length(Elatin7::fc($char[$i])) == 1) {
$char[$i] = '[' . Elatin7::uc($char[$i]) . Elatin7::fc($char[$i]) . ']';
}
else {
$char[$i] = '(?:' . Elatin7::uc($char[$i]) . '|' . Elatin7::fc($char[$i]) . ')';
}
}
# \u \l \U \L \F \Q \E
elsif ($char[$i] =~ /\A ([<>]) \z/oxms) {
if ($right_e < $left_e) {
$char[$i] = '\\' . $char[$i];
}
}
elsif ($char[$i] eq '\u') {
$char[$i] = '@{[Elatin7::ucfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\l') {
$char[$i] = '@{[Elatin7::lcfirst qq<';
$left_e++;
}
elsif ($char[$i] eq '\U') {
$char[$i] = '@{[Elatin7::uc qq<';
$left_e++;
}
elsif ($char[$i] eq '\L') {
$char[$i] = '@{[Elatin7::lc qq<';
$left_e++;
}
elsif ($char[$i] eq '\F') {
$char[$i] = '@{[Elatin7::fc qq<';
$left_e++;
}
elsif ($char[$i] eq '\Q') {
$char[$i] = '@{[CORE::quotemeta qq<';
$left_e++;
}
elsif ($char[$i] eq '\E') {
if ($right_e < $left_e) {
$char[$i] = '>]}';
$right_e++;
}
else {
$char[$i] = '';
}
}
elsif ($char[$i] eq '\Q') {
while (1) {
if (++$i > $#char) {
last;
}
if ($char[$i] eq '\E') {
last;
}
}
}
elsif ($char[$i] eq '\E') {
}
# $0 --> $0
elsif ($char[$i] =~ /\A \$ 0 \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
elsif ($char[$i] =~ /\A \$ \{ \s* 0 \s* \} \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $$ --> $$
elsif ($char[$i] =~ /\A \$\$ \z/oxms) {
}
# $1, $2, $3 --> $2, $3, $4 after s/// with multibyte anchoring
# $1, $2, $3 --> $1, $2, $3 otherwise
elsif ($char[$i] =~ /\A \$ ([1-9][0-9]*) \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
elsif ($char[$i] =~ /\A \$ \{ \s* ([1-9][0-9]*) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo[ ... ] --> $ $foo->[ ... ]
elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \[ (?:$qq_bracket)*? \] ) \z/oxms) {
$char[$i] = e_capture($1.'->'.$2);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo{ ... } --> $ $foo->{ ... }
elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) ( \{ (?:$qq_brace)*? \} ) \z/oxms) {
$char[$i] = e_capture($1.'->'.$2);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $$foo
elsif ($char[$i] =~ /\A \$ ( \$ [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* ) \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $`, ${`}, $PREMATCH, ${PREMATCH}, ${^PREMATCH} --> Elatin7::PREMATCH()
elsif ($char[$i] =~ /\A ( \$` | \$\{`\} | \$ \s* PREMATCH | \$ \s* \{ \s* PREMATCH \s* \} | \$ \s* \{\^PREMATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(Elatin7::PREMATCH())]}';
}
else {
$char[$i] = '@{[Elatin7::PREMATCH()]}';
}
}
# $&, ${&}, $MATCH, ${MATCH}, ${^MATCH} --> Elatin7::MATCH()
elsif ($char[$i] =~ /\A ( \$& | \$\{&\} | \$ \s* MATCH | \$ \s* \{ \s* MATCH \s* \} | \$ \s* \{\^MATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(Elatin7::MATCH())]}';
}
else {
$char[$i] = '@{[Elatin7::MATCH()]}';
}
}
# $POSTMATCH, ${POSTMATCH}, ${^POSTMATCH} --> Elatin7::POSTMATCH()
elsif ($char[$i] =~ /\A ( \$ \s* POSTMATCH | \$ \s* \{ \s* POSTMATCH \s* \} | \$ \s* \{\^POSTMATCH\} ) \z/oxmsgc) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(Elatin7::POSTMATCH())]}';
}
else {
$char[$i] = '@{[Elatin7::POSTMATCH()]}';
}
}
# ${ foo }
elsif ($char[$i] =~ /\A \$ \s* \{ ( \s* [A-Za-z_][A-Za-z0-9_]*(?: ::[A-Za-z_][A-Za-z0-9_]*)* \s* ) \} \z/oxms) {
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $1 . ')]}';
}
}
# ${ ... }
elsif ($char[$i] =~ /\A \$ \s* \{ \s* ( .+ ) \s* \} \z/oxms) {
$char[$i] = e_capture($1);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# $scalar or @array
elsif ($char[$i] =~ /\A [\$\@].+ /oxms) {
$char[$i] = e_string($char[$i]);
if ($ignorecase) {
$char[$i] = '@{[Elatin7::ignorecase(' . $char[$i] . ')]}';
}
}
# quote character before ? + * {
elsif (($i >= 1) and ($char[$i] =~ /\A [\?\+\*\{] \z/oxms)) {
if ($char[$i-1] =~ /\A (?:\\[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 '', 'Elatin7::split', $ope, $delimiter, @char, '>]}' x ($left_e - $right_e), $end_delimiter, $modifier;
}
return join '', 'Elatin7::split', $ope, $delimiter, @char, $end_delimiter, $modifier;
}
#
# escape regexp of split qr''
#
sub e_split_q {
my($ope,$delimiter,$end_delimiter,$string,$modifier) = @_;
$modifier ||= '';
$modifier =~ tr/p//d;
if ($modifier =~ /([adlu])/oxms) {
my $line = 0;
for (my $i=0; my($package,$filename,$use_line,$subroutine) = caller($i); $i++) {
if ($filename ne __FILE__) {
$line = $use_line + (CORE::substr($_,0,pos($_)) =~ tr/\n//) + 1;
last;
}
}
die qq{Unsupported modifier "$1" used at line $line.\n};
}
$slash = 'div';
# /b /B modifier
if ($modifier =~ tr/bB//d) {
return join '', 'split', $ope, $delimiter, $string, $end_delimiter, $modifier;
}
my $ignorecase = ($modifier =~ /i/oxms) ? 1 : 0;
# split regexp
my @char = $string =~ /\G(
\[\:\^ [a-z]+ \:\] |
\[\: [a-z]+ \:\] |
\[\^ |
\\? (?:$q_char)
)/oxmsg;
# unescape character
for (my $i=0; $i <= $#char; $i++) {
if (0) {
}
# open character class [...]
elsif ($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, Elatin7::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, Elatin7::charlist_not_qr(@char[$left+1..$right-1], $modifier);
$i = $left;
last;
}
}
}
# rewrite character class or escape character
elsif (my $char = character_class($char[$i],$modifier)) {
$char[$i] = $char;
}
# split(m/^/) --> split(m/^/m)
elsif (($char[$i] eq '^') and ($modifier !~ /m/oxms)) {
$modifier .= 'm';
}
# /i modifier
elsif ($ignorecase and ($char[$i] =~ /\A [\x00-\xFF] \z/oxms) and (Elatin7::uc($char[$i]) ne Elatin7::fc($char[$i]))) {
if (CORE::length(Elatin7::fc($char[$i])) == 1) {
$char[$i] = '[' . Elatin7::uc($char[$i]) . Elatin7::fc($char[$i]) . ']';
}
else {
$char[$i] = '(?:' . Elatin7::uc($char[$i]) . '|' . Elatin7::fc($char[$i]) . ')';
}
}
# quote character before ? + * {
elsif (($i >= 1) and ($char[$i] =~ /\A [\?\+\*\{] \z/oxms)) {
if ($char[$i-1] =~ /\A [\x00-\xFF] \z/oxms) {
}
else {
$char[$i-1] = '(?:' . $char[$i-1] . ')';
}
}
}
$modifier =~ tr/i//d;
return join '', 'Elatin7::split', $ope, $delimiter, @char, $end_delimiter, $modifier;
}
1;
__END__
=pod
=head1 NAME
Latin7 - Source code filter to escape Latin-7 script
=head1 Install and Usage
There are two steps there:
=over 2
=item * You'll have to download Latin7.pm and Elatin7.pm and put it in your perl lib directory.
=item * You'll need to write "use Latin7;" at head of the script.
=back
=head1 SYNOPSIS
use Latin7;
use Latin7 ver.sion; --- require minimum version
use Latin7 ver.sion.0; --- expects version (match or die)
# "no Latin7;" not supported
or
$ perl Latin7.pm Latin-7_script.pl > Escaped_script.pl.e
then
$ perl Escaped_script.pl.e
Latin-7_script.pl --- script written in Latin-7
Escaped_script.pl.e --- escaped script
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
Latin7 software is "middleware" between perl interpreter and your Perl script
written in Latin-7.
Perl is optimized for problems which are about 90% working with text and about
10% everything else. Even if this "text" doesn't contain Latin-7, Perl3 or later
can treat Latin-7 as binary data.
By "use Latin7;", it automatically interpret your script as Latin-7. The various
functions of perl including a regular expression can treat Latin-7 now.
The function length treats length per byte. This software does not use UTF8
flag.
=head1 Yet Another Future Of
JPerl is very useful software. -- Oops, note, this "JPerl" means "Japanized Perl"
or "Japanese Perl". Therefore, it is unrelated to JPerl of the following.
JPerl is an implementation of Perl written in Java.
http://www.javainc.com/projects/jperl/
jPerl - Perl on the JVM
http://www.dzone.com/links/175948.html
Jamie's PERL scripts for bioinformatics
http://code.google.com/p/jperl/
jperl (Jonathan Perl)
https://github.com/jperl
Now, the last version of JPerl is 5.005_04 and is not maintained now.
Japanization modifier WATANABE Hirofumi said,
"Because WATANABE am tired I give over maintaing JPerl."
at Slide #15: "The future of JPerl" of
L<ftp://ftp.oreilly.co.jp/pcjp98/watanabe/jperlconf.ppt>
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 Latin-7
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 * Remains One Language Handling Raw Latin-7, Doesn't Use UTF8 flag like JPerl
=item * Remains One Interpreter like Encode module
=item * Code Set Independent like Ruby
=item * Monolithic Script like cpanminus
=item * There's more than one way to do it like Perl itself
=back
I am excited about this software and Perl's future --- I hope you are too.
=head1 JRE: JPerl Runtime Environment
+---------------------------------------+
| JPerl Application Script | Your Script
+---------------------------------------+
| Source Code Filter, Runtime Routine | ex. Latin7.pm, Elatin7.pm
+---------------------------------------+
| PVM 5.00503 or later | ex. perl 5.00503
+---------------------------------------+
A Perl Virtual Machine (PVM) enables a set of computer software programs and
data structures to use a virtual machine model for the execution of other
computer programs and scripts. The model used by a PVM accepts a form of
computer intermediate language commonly referred to as Perl byteorientedcode.
This language conceptually represents the instruction set of a byte-oriented,
capability architecture.
=head1 Basic Idea of Source Code Filter
I discovered this mail again recently.
[Tokyo.pm] jus Benkyoukai
http://mail.pm.org/pipermail/tokyo-pm/1999-September/001854.html
save as: SJIS.pm
package SJIS;
use Filter::Util::Call;
sub multibyte_filter {
my $status;
if (($status = filter_read()) > 0 ) {
s/([\x81-\x9f\xe0-\xef])([\x40-\x7e\x80-\xfc])/
sprintf("\\x%02x\\x%02x",ord($1),ord($2))
/eg;
}
$status;
}
sub import {
filter_add(\&multibyte_filter);
}
1;
I am glad that I could confirm my idea is not so wrong.
=head1 Command-line Wildcard Expansion on DOS-like Systems
The default command shells on DOS-like systems (COMMAND.COM or cmd.exe or
Win95Cmd.exe) do not expand wildcard arguments supplied to programs. Instead,
import of Elatin7.pm works well.
in Elatin7.pm
#
# @ARGV wildcard globbing
#
sub import {
if ($^O =~ /\A (?: MSWin32 | NetWare | symbian | dos ) \z/oxms) {
my @argv = ();
for (@ARGV) {
# has space
if (/\A (?:$q_char)*? [ ] /oxms) {
if (my @glob = Elatin7::glob(qq{"$_"})) {
push @argv, @glob;
}
else {
push @argv, $_;
}
}
# has wildcard metachar
elsif (/\A (?:$q_char)*? [*?] /oxms) {
if (my @glob = Elatin7::glob($_)) {
push @argv, @glob;
}
else {
push @argv, $_;
}
}
# no wildcard globbing
else {
push @argv, $_;
}
}
@ARGV = @argv;
}
}
=head1 Software Composition
Latin7.pm --- source code filter to escape Latin-7
Elatin7.pm --- run-time routines for Latin7.pm
=head1 Upper Compatibility by Escaping
This software adds the function by 'Escaping' it always, and nothing of the
past is broken. Therefore, 'Possible job' never becomes 'Impossible job'.
This approach is effective in the field where the retreat is never permitted.
It means incompatible upgrade of Perl should be rewound.
=head1 Escaping Your Script (You do)
You need write 'use Latin7;' in your script.
---------------------------------
Before You do
---------------------------------
(nothing) use Latin7;
---------------------------------
=head1 Calling 'Elatin7::ignorecase()' (Latin7.pm provides)
Latin7.pm applies calling 'Elatin7::ignorecase()' instead of /i modifier.
--------------------------------------------------------------------------------
Before After
--------------------------------------------------------------------------------
m/...$var.../i m/...@{[Elatin7::ignorecase($var)]}.../
--------------------------------------------------------------------------------
=head1 Escaping Character Classes (Elatin7.pm provides)
The character classes are redefined as follows to backward compatibility.
---------------------------------------------------------------
Before After
---------------------------------------------------------------
. ${Elatin7::dot}
${Elatin7::dot_s} (/s modifier)
\d [0-9] (universally)
\s \s
\w [0-9A-Z_a-z] (universally)
\D ${Elatin7::eD}
\S ${Elatin7::eS}
\W ${Elatin7::eW}
\h [\x09\x20]
\v [\x0A\x0B\x0C\x0D]
\H ${Elatin7::eH}
\V ${Elatin7::eV}
\C [\x00-\xFF]
\X X (so, just 'X')
\R ${Elatin7::eR}
\N ${Elatin7::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:] [\s\x0B]
[: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:] ${Elatin7::not_alnum}
[:^alpha:] ${Elatin7::not_alpha}
[:^ascii:] ${Elatin7::not_ascii}
[:^blank:] ${Elatin7::not_blank}
[:^cntrl:] ${Elatin7::not_cntrl}
[:^digit:] ${Elatin7::not_digit}
[:^graph:] ${Elatin7::not_graph}
[:^lower:] ${Elatin7::not_lower}
${Elatin7::not_lower_i} (/i modifier)
[:^print:] ${Elatin7::not_print}
[:^punct:] ${Elatin7::not_punct}
[:^space:] ${Elatin7::not_space}
[:^upper:] ${Elatin7::not_upper}
${Elatin7::not_upper_i} (/i modifier)
[:^word:] ${Elatin7::not_word}
[:^xdigit:] ${Elatin7::not_xdigit}
---------------------------------------------------------------
\b and \B are redefined as follows to backward compatibility.
---------------------------------------------------------------
Before After
---------------------------------------------------------------
\b ${Elatin7::eb}
\B ${Elatin7::eB}
---------------------------------------------------------------
Definitions in Elatin7.pm.
---------------------------------------------------------------------------------------------------------------------------------------------------------
After Definition
---------------------------------------------------------------------------------------------------------------------------------------------------------
${Elatin7::dot} qr{(?:[^\x0A])}
${Elatin7::dot_s} qr{(?:[\x00-\xFF])}
${Elatin7::eD} qr{(?:[^0-9])}
${Elatin7::eS} qr{(?:[^\s])}
${Elatin7::eW} qr{(?:[^0-9A-Z_a-z])}
${Elatin7::eH} qr{(?:[^\x09\x20])}
${Elatin7::eV} qr{(?:[^\x0A\x0B\x0C\x0D])}
${Elatin7::eR} qr{(?:\x0D\x0A|[\x0A\x0D])}
${Elatin7::eN} qr{(?:[^\x0A])}
${Elatin7::not_alnum} qr{(?:[^\x30-\x39\x41-\x5A\x61-\x7A])}
${Elatin7::not_alpha} qr{(?:[^\x41-\x5A\x61-\x7A])}
${Elatin7::not_ascii} qr{(?:[^\x00-\x7F])}
${Elatin7::not_blank} qr{(?:[^\x09\x20])}
${Elatin7::not_cntrl} qr{(?:[^\x00-\x1F\x7F])}
${Elatin7::not_digit} qr{(?:[^\x30-\x39])}
${Elatin7::not_graph} qr{(?:[^\x21-\x7F])}
${Elatin7::not_lower} qr{(?:[^\x61-\x7A])}
${Elatin7::not_lower_i} qr{(?:[\x00-\xFF])}
${Elatin7::not_print} qr{(?:[^\x20-\x7F])}
${Elatin7::not_punct} qr{(?:[^\x21-\x2F\x3A-\x3F\x40\x5B-\x5F\x60\x7B-\x7E])}
${Elatin7::not_space} qr{(?:[^\s\x0B])}
${Elatin7::not_upper} qr{(?:[^\x41-\x5A])}
${Elatin7::not_upper_i} qr{(?:[\x00-\xFF])}
${Elatin7::not_word} qr{(?:[^\x30-\x39\x41-\x5A\x5F\x61-\x7A])}
${Elatin7::not_xdigit} qr{(?:[^\x30-\x39\x41-\x46\x61-\x66])}
${Elatin7::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))}
${Elatin7::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 (Latin7.pm provides)
Latin7.pm removes '\' at head of alphanumeric regexp metasymbols \N, \p, \P
and \X. By this method, you can avoid the trap of the abstraction.
See also,
Deprecate literal unescaped "{" in regexes.
http://perl5.git.perl.org/perl.git/commit/2a53d3314d380af5ab5283758219417c6dfa36e9
------------------------------------
Before After
------------------------------------
\N{CHARNAME} N\{CHARNAME}
\p{L} p\{L}
\p{^L} p\{^L}
\p{\^L} p\{\^L}
\pL pL
\P{L} P\{L}
\P{^L} P\{^L}
\P{\^L} P\{\^L}
\PL PL
\X X
------------------------------------
=head1 Escaping Built-in Functions (Latin7.pm and Elatin7.pm provide)
Insert 'Elatin7::' at head of function name. Elatin7.pm provides your script Elatin7::*
subroutines.
-------------------------------------------
Before After Works as
-------------------------------------------
lc Elatin7::lc Character
lcfirst Elatin7::lcfirst Character
uc Elatin7::uc Character
ucfirst Elatin7::ucfirst Character
fc Elatin7::fc Character
chr Elatin7::chr Character
glob Elatin7::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 Un-Escaping bytes::* Subroutines (Latin7.pm provides)
Latin7.pm removes 'bytes::' at head of subroutine 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 Standard Module Content (You do)
You need copy built-in standard module to /Perl/site/lib/Latin7 and change
'use utf8;' to 'use Latin7;' 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 Elatin7.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 subroutine is same as chr.
=item * Dummy bytes::index
This subroutine is same as index.
=item * Dummy bytes::length
This subroutine is same as length.
=item * Dummy bytes::ord
This subroutine is same as ord.
=item * Dummy bytes::rindex
This subroutine is same as rindex.
=item * Dummy bytes::substr
This subroutine 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 BUGS, LIMITATIONS, and COMPATIBILITY
I have tested and verified this software using the best of my ability.
However, a software containing much regular expression is bound to contain
some bugs. Thus, if you happen to find a bug that's in Latin7 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 * cloister of regular expression
The cloister (?s) and (?i) of a regular expression will not be implemented for
the time being. Cloister (?s) can be substituted with the .(dot) and \N on /s
modifier. Cloister (?i) can be substituted with \F...\E.
=item * Modifier /a /d /l and /u of Regular Expression
The concept of this software is not to use two or more encoding methods as
literal string and literal of regexp in one Perl script. Therefore, modifier
/a, /d, /l, and /u are not supported.
\d means [0-9] universally.
=item * Named Character
A named character, such \N{GREEK SMALL LETTER EPSILON}, \N{greek:epsilon}, or
\N{epsilon} is not supported.
=item * Unicode Properties (aka Character Properties) of Regular Expression
Unicode properties (aka character properties) of regexp are not available.
Also (?[]) in regexp of Perl 5.18 is not available. There is no plans to currently
support these.
=item * eval "string"
The function which escapes "string" of eval has not been implemented yet. It will
be supported in future versions.
=item * Delimiter of String and Regexp
qq//, q//, qw//, qx//, qr//, m//, s///, tr///, and y/// can't use a wide character
as the delimiter.
=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 |
+--------------------------------------------+
http://perl-users.jp/articles/advent-calendar/2010/casual/4
You should memorize this figure.
(Why is only Latin-1 special?)
This change consequentially made a big gap between a past script and
new script. Both scripts cannot re-use the code mutually any longer.
Because a new method puts a strain in the programmer, it will still take
time to replace all the in existence scripts.
The biggest problem of new method is that the UTF8 flag can't synchronize
to real encode of string. Thus you must debug about UTF8 flag, before
your script. How to solve it by returning to a this method, let's drag out
page 402 of the old dusty Programming Perl, 3rd ed. again.
Information processing model beginning with perl3 or this software of
UNIX/C-ism.
+--------------------------------------------+
| Text strings as Binary strings |
| Binary strings as Text strings |
+--------------------------------------------+
| Not UTF8 Flagged, UNIX/C-ism |
+--------------------------------------------+
Script could be written in native encoding of operating systems.
- Like contents of a file
- Like a file name on the file systems
- Like command lines
- Like environment variables
- Like parameters of API
In UNIX Everything is a File
- In UNIX everything is a stream of bytes
- In UNIX the filesystem is used as a universal name space
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.
This goal has been achieved by that this software is additional code
for perl like utf8 pragma. Perl should work same as past Perl if added
nothing.
=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 built-in 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,japerl Encode,Latin7
+--------------+-------+-------+-------+-------+-------+
| 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.
=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.
Someday, I want to ask Larry Wall about this goal in the elevator.
=item * Goal #4:
Perl should remain one language, rather than forking into a
byte-oriented Perl and a character-oriented Perl.
JPerl remains one Perl language by forking to two interpreters.
However, the Perl core team did not desire fork of the interpreter.
As a result, Perl language forked contrary to goal #4.
A character-oriented perl is not necessary to make it specially,
because a byte-oriented perl can already treat the binary data.
This software is only an application program of byte-oriented Perl,
a filter program.
And you will get support from the Perl community, when you solve the
problem by the Perl script.
Latin7 software remains one language and one interpreter.
=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 Perl's motto
Some computer scientists (the reductionists, in particular) would
like to deny it, but people have funny-shaped minds. Mental geography
is not linear, and cannot be mapped onto a flat surface without
severe distortion. But for the last score years or so, computer
reductionists have been first bowing down at the Temple of Orthogonality,
then rising up to preach their ideas of ascetic rectitude to any who
would listen.
Their fervent but misguided desire was simply to squash your mind to
fit their mindset, to smush your patterns of thought into some sort of
Hyperdimensional Flatland. It's a joyless existence, being smushed.
--- Learning Perl on Win32 Systems
If you think this is a big headache, you're right. No one likes
this situation, but Perl does the best it can with the input and
encodings it has to deal with. If only we could reset history and
not make so many mistakes next time.
--- Learning Perl 6th Edition
The most important thing for most people to know about handling
Unicode data in Perl, however, is that if you don't ever use any Uni-
code data -- if none of your files are marked as UTF-8 and you don't
use UTF-8 locales -- then you can happily pretend that you're back in
Perl 5.005_03 land; the Unicode features will in no way interfere with
your code unless you're explicitly using them. Sometimes the twin
goals of embracing Unicode but not disturbing old-style byte-oriented
scripts has led to compromise and confusion, but it's the Perl way to
silently do the right thing, which is what Perl ends up doing.
--- Advanced Perl Programming, 2nd Edition
=head1 SEE ALSO
PERL PUROGURAMINGU
Larry Wall, Randal L.Schwartz, Yoshiyuki Kondo
December 1997
ISBN 4-89052-384-7
http://www.context.co.jp/~cond/books/old-books.html
Programming Perl, Second Edition
By Larry Wall, Tom Christiansen, Randal L. Schwartz
October 1996
Pages: 670
ISBN 10: 1-56592-149-6 | ISBN 13: 9781565921498
http://shop.oreilly.com/product/9781565921498.do
Programming Perl, Third Edition
By Larry Wall, Tom Christiansen, Jon Orwant
Third Edition July 2000
Pages: 1104
ISBN 10: 0-596-00027-8 | ISBN 13: 9780596000271
http://shop.oreilly.com/product/9780596000271.do
The Perl Language Reference Manual (for Perl version 5.12.1)
by Larry Wall and others
Paperback (6"x9"), 724 pages
Retail Price: $39.95 (pound 29.95 in UK)
ISBN-13: 978-1-906966-02-7
http://www.network-theory.co.uk/perl/language/
Perl Pocket Reference, 5th Edition
By Johan Vromans
Publisher: O'Reilly Media
Released: July 2011
Pages: 102
http://shop.oreilly.com/product/0636920018476.do
Programming Perl, 4th Edition
By: Tom Christiansen, brian d foy, Larry Wall, Jon Orwant
Publisher: O'Reilly Media
Formats: Print, Ebook, Safari Books Online
Released: March 2012
Pages: 1130
Print ISBN: 978-0-596-00492-7 | ISBN 10: 0-596-00492-3
Ebook ISBN: 978-1-4493-9890-3 | ISBN 10: 1-4493-9890-1
http://shop.oreilly.com/product/9780596004927.do
Perl Cookbook
By Tom Christiansen, Nathan Torkington
August 1998
Pages: 800
ISBN 10: 1-56592-243-3 | ISBN 13: 978-1-56592-243-3
http://shop.oreilly.com/product/9781565922433.do
Perl Cookbook, Second Edition
By Tom Christiansen, Nathan Torkington
Second Edition August 2003
Pages: 964
ISBN 10: 0-596-00313-7 | ISBN 13: 9780596003135
http://shop.oreilly.com/product/9780596003135.do
Perl in a Nutshell, Second Edition
By Stephen Spainhour, Ellen Siever, Nathan Patwardhan
Second Edition June 2002
Pages: 760
Series: In a Nutshell
ISBN 10: 0-596-00241-6 | ISBN 13: 9780596002411
http://shop.oreilly.com/product/9780596002411.do
Learning Perl on Win32 Systems
By Randal L. Schwartz, Erik Olson, Tom Christiansen
August 1997
Pages: 306
ISBN 10: 1-56592-324-3 | ISBN 13: 9781565923249
http://shop.oreilly.com/product/9781565923249.do
Learning Perl, Fifth Edition
By Randal L. Schwartz, Tom Phoenix, brian d foy
June 2008
Pages: 352
Print ISBN:978-0-596-52010-6 | ISBN 10: 0-596-52010-7
Ebook ISBN:978-0-596-10316-3 | ISBN 10: 0-596-10316-6
http://shop.oreilly.com/product/9780596520113.do
Learning Perl, 6th Edition
By Randal L. Schwartz, brian d foy, Tom Phoenix
June 2011
Pages: 390
ISBN-10: 1449303587 | ISBN-13: 978-1449303587
http://shop.oreilly.com/product/0636920018452.do
Advanced Perl Programming, 2nd Edition
By Simon Cozens
June 2005
Pages: 300
ISBN-10: 0-596-00456-7 | ISBN-13: 978-0-596-00456-9
http://shop.oreilly.com/product/9780596004569.do
Perl RESOURCE KIT UNIX EDITION
Futato, Irving, Jepson, Patwardhan, Siever
ISBN 10: 1-56592-370-7
http://shop.oreilly.com/product/9781565923706.do
MODAN Perl NYUMON
By Daisuke Maki
2009/2/10
Pages: 344
ISBN 10: 4798119172 | ISBN 13: 978-4798119175
http://www.seshop.com/product/detail/10250/
Understanding Japanese Information Processing
By Ken Lunde
January 1900
Pages: 470
ISBN 10: 1-56592-043-0 | ISBN 13: 9781565920439
http://shop.oreilly.com/product/9781565920439.do
CJKV Information Processing
Chinese, Japanese, Korean & Vietnamese Computing
By Ken Lunde
First Edition January 1999
Pages: 1128
ISBN 10: 1-56592-224-7 | ISBN 13: 9781565922242
http://shop.oreilly.com/product/9781565922242.do
Mastering Regular Expressions, Second Edition
By Jeffrey E. F. Friedl
Second Edition July 2002
Pages: 484
ISBN 10: 0-596-00289-0 | ISBN 13: 9780596002893
http://shop.oreilly.com/product/9780596002893.do
Mastering Regular Expressions, Third Edition
By Jeffrey E. F. Friedl
Third Edition August 2006
Pages: 542
ISBN 10: 0-596-52812-4 | ISBN 13:9780596528126
http://shop.oreilly.com/product/9780596528126.do
Regular Expressions Cookbook
By Jan Goyvaerts, Steven Levithan
May 2009
Pages: 512
ISBN 10:0-596-52068-9 | ISBN 13: 978-0-596-52068-7
http://shop.oreilly.com/product/9780596520694.do
JIS KANJI JITEN
By Kouji Shibano
Pages: 1456
ISBN 4-542-20129-5
http://www.webstore.jsa.or.jp/lib/lib.asp?fn=/manual/mnl01_12.htm
UNIX MAGAZINE
1993 Aug
Pages: 172
T1008901080816 ZASSHI 08901-8
http://ascii.asciimw.jp/books/books/detail/978-4-7561-5008-0.shtml
LINUX NIHONGO KANKYO
By YAMAGATA Hiroo, Stephen J. Turnbull, Craig Oda, Robert J. Bickel
June, 2000
Pages: 376
ISBN 4-87311-016-5
http://www.oreilly.co.jp/books/4873110165/
MacPerl Power and Ease
By Vicki Brown, Chris Nandor
April 1998
Pages: 350
ISBN 10: 1881957322 | ISBN 13: 978-1881957324
http://www.amazon.com/Macperl-Power-Ease-Vicki-Brown/dp/1881957322
Windows NT Shell Scripting
By Timothy Hill
April 27, 1998
Pages: 400
ISBN 10: 1578700477 | ISBN 13: 9781578700479
http://search.barnesandnoble.com/Windows-NT-Shell-Scripting/Timothy-Hill/e/9781578700479/
Windows(R) Command-Line Administrators Pocket Consultant, 2nd Edition
By William R. Stanek
February 2009
Pages: 594
ISBN 10: 0-7356-2262-0 | ISBN 13: 978-0-7356-2262-3
http://shop.oreilly.com/product/9780735622623.do
CPAN Directory INABA Hitoshi
http://search.cpan.org/~ina/
BackPAN
http://backpan.perl.org/authors/id/I/IN/INA/
Recent Perl packages by "INABA Hitoshi"
http://code.activestate.com/ppm/author:INABA-Hitoshi/
=head1 ACKNOWLEDGEMENTS
This software was made referring to software and the document that the
following hackers or persons had made.
I am thankful to all persons.
Rick Yamashita, Shift_JIS
ttp://furukawablog.spaces.live.com/Blog/cns!1pmWgsL289nm7Shn7cS0jHzA!2225.entry (dead link)
ttp://shino.tumblr.com/post/116166805/1981-us-jis
(add 'h' at head)
http://www.wdic.org/w/WDIC/%E3%82%B7%E3%83%95%E3%83%88JIS
Larry Wall, Perl
http://www.perl.org/
Kazumasa Utashiro, jcode.pl
ftp://ftp.iij.ad.jp/pub/IIJ/dist/utashiro/perl/
http://log.utashiro.com/pub/2006/07/jkondo_a580.html
Jeffrey E. F. Friedl, Mastering Regular Expressions
http://regex.info/
SADAHIRO Tomoyuki, The right way of using Shift_JIS
http://homepage1.nifty.com/nomenclator/perl/shiftjis.htm
http://search.cpan.org/~sadahiro/
Yukihiro "Matz" Matsumoto, YAPC::Asia2006 Ruby on Perl(s)
http://www.rubyist.net/~matz/slides/yapc2006/
jscripter, For jperl users
http://homepage1.nifty.com/kazuf/jperl.html
Bruce., Unicode in Perl
http://www.rakunet.org/tsnet/TSabc/18/546.html
Hiroaki Izumi, Perl5.8/Perl5.10 is not useful on the Windows.
http://dl.dropbox.com/u/23756062/perlwin.html
https://sites.google.com/site/hiroa63iz/perlwin
TSUKAMOTO Makio, Perl memo/file path of Windows
http://digit.que.ne.jp/work/wiki.cgi?Perl%E3%83%A1%E3%83%A2%2FWindows%E3%81%A7%E3%81%AE%E3%83%95%E3%82%A1%E3%82%A4%E3%83%AB%E3%83%91%E3%82%B9
chaichanPaPa, Matching Shift_JIS file name
http://d.hatena.ne.jp/chaichanPaPa/20080802/1217660826
SUZUKI Norio, Jperl
http://homepage2.nifty.com/kipp/perl/jperl/
WATANABE Hirofumi, Jperl
http://www.cpan.org/src/5.0/jperl/
http://search.cpan.org/~watanabe/
ftp://ftp.oreilly.co.jp/pcjp98/watanabe/jperlconf.ppt
Chuck Houpt, Michiko Nozu, MacJPerl
http://habilis.net/macjperl/index.j.html
Kenichi Ishigaki, Pod-PerldocJp, Welcome to modern Perl world
http://search.cpan.org/dist/Pod-PerldocJp/
http://gihyo.jp/dev/serial/01/modern-perl/0031
http://gihyo.jp/dev/serial/01/modern-perl/0032
http://gihyo.jp/dev/serial/01/modern-perl/0033
Fuji, Goro (gfx), Perl Hackers Hub No.16
http://gihyo.jp/dev/serial/01/perl-hackers-hub/001602
Dan Kogai, Encode module
http://search.cpan.org/dist/Encode/
http://www.archive.org/details/YAPCAsia2006TokyoPerl58andUnicodeMythsFactsandChanges (video)
http://yapc.g.hatena.ne.jp/jkondo/ (audio)
Takahashi Masatuyo, JPerl Wiki
http://ja.jperl.wikia.com/wiki/JPerl_Wiki
Juerd, Perl Unicode Advice
http://juerd.nl/site.plp/perluniadvice
daily dayflower, 2008-06-25 perluniadvice
http://d.hatena.ne.jp/dayflower/20080625/1214374293
Jesse Vincent, Compatibility is a virtue
http://www.nntp.perl.org/group/perl.perl5.porters/2010/05/msg159825.html
Tokyo-pm archive
http://mail.pm.org/pipermail/tokyo-pm/
http://mail.pm.org/pipermail/tokyo-pm/1999-September/001844.html
http://mail.pm.org/pipermail/tokyo-pm/1999-September/001854.html
Error: Runtime exception on jperl 5.005_03
http://www.rakunet.org/tsnet/TSperl/12/374.html
http://www.rakunet.org/tsnet/TSperl/12/375.html
http://www.rakunet.org/tsnet/TSperl/12/376.html
http://www.rakunet.org/tsnet/TSperl/12/377.html
http://www.rakunet.org/tsnet/TSperl/12/378.html
http://www.rakunet.org/tsnet/TSperl/12/379.html
http://www.rakunet.org/tsnet/TSperl/12/380.html
http://www.rakunet.org/tsnet/TSperl/12/382.html
ruby-list
http://blade.nagaokaut.ac.jp/ruby/ruby-list/index.shtml
http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/2440
http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/2446
http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/2569
http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/9427
http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/9431
http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/10500
http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/10501
http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/10502
http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/12385
http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/12392
http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/12393
http://blade.nagaokaut.ac.jp/cgi-bin/scat.rb/ruby/ruby-list/19156
Object-oriented with Perl
http://www.freeml.com/perl-oo/486
http://www.freeml.com/perl-oo/487
http://www.freeml.com/perl-oo/490
http://www.freeml.com/perl-oo/491
http://www.freeml.com/perl-oo/492
http://www.freeml.com/perl-oo/494
http://www.freeml.com/perl-oo/514
=cut
# Did you fun enough? ^o^)