use strict;
use warnings;
+use Carp qw/croak/;
use Text::Balanced qw/extract_bracketed/;
=head1 NAME
=head1 VERSION
-Version 0.08
+Version 1.00
=cut
-our $VERSION = '0.08';
+use vars qw/$VERSION/;
+BEGIN {
+ $VERSION = '1.00';
+}
=head1 SYNOPSIS
- use Regexp::Wildcards qw/wc2re/;
+ use Regexp::Wildcards;
+
+ my $rw = Regexp::Wildcards->new(type => 'unix');
my $re;
- $re = wc2re 'a{b?,c}*' => 'unix'; # Do it Unix style.
- $re = wc2re 'a?,b*' => 'win32'; # Do it Windows style.
- $re = wc2re '*{x,y}?' => 'jokers'; # Process the jokers & escape the rest.
- $re = wc2re '%a_c%' => 'sql'; # Turn SQL wildcards into regexps.
+ $re = $rw->convert('a{b?,c}*'); # Do it Unix shell style.
+ $re = $rw->convert('a?,b*', 'win32'); # Do it Windows shell style.
+ $re = $rw->convert('*{x,y}?', 'jokers'); # Process the jokers and escape the rest.
+ $re = $rw->convert('%a_c%', 'sql'); # Turn SQL wildcards into regexps.
-=head1 DESCRIPTION
+ $rw = Regexp::Wildcards->new(
+ do => [ qw/jokers brackets/ ], # Do jokers and brackets.
+ capture => [ qw/any greedy/ ], # Capture *'s greedily.
+ );
-In many situations, users may want to specify patterns to match but don't need the full power of regexps. Wildcards make one of those sets of simplified rules. This module converts wildcard expressions to Perl regular expressions, so that you can use them for matching. It handles the C<*> and C<?> shell jokers, as well as Unix bracketed alternatives C<{,}>, but also C<%> and C<_> SQL wildcards. Backspace (C<\>) is used as an escape character. Wrappers are provided to mimic the behaviour of Windows and Unix shells.
+ $rw->do(add => 'groups'); # Don't escape groups.
+ $rw->capture(rem => [ qw/greedy/ ]); # Actually we want non-greedy matches.
+ $re = $rw->convert('*a{,(b)?}?c*'); # '(.*?)a(?:|(b).).c(.*?)'
+ $rw->capture(); # No more captures.
-=head1 VARIABLES
+=head1 DESCRIPTION
-These variables control if the wildcards jokers and brackets must capture their match. They can be globally set by writing in your program
+In many situations, users may want to specify patterns to match but don't need the full power of regexps. Wildcards make one of those sets of simplified rules. This module converts wildcard expressions to Perl regular expressions, so that you can use them for matching.
- $Regexp::Wildcards::CaptureSingle = 1;
- # From then, "exactly one" wildcards are capturing
+It handles the C<*> and C<?> jokers, as well as Unix bracketed alternatives C<{,}>, but also C<%> and C<_> SQL wildcards. It can also keep original C<(...)> groups. Backspace (C<\>) is used as an escape character.
-or can be locally specified via C<local>
+Typesets that mimic the behaviour of Windows and Unix shells are also provided.
- {
- local $Regexp::Wildcards::CaptureSingle = 1;
- # In this block, "exactly one" wildcards are capturing.
- ...
- }
- # Back to the situation from before the block
+=head1 METHODS
-This section describes also how those elements are translated by the L<functions|/FUNCTIONS>.
+=cut
-=head2 C<$CaptureSingle>
+sub _check_self {
+ croak 'First argument isn\'t a valid ' . __PACKAGE__ . ' object'
+ unless ref $_[0] and $_[0]->isa(__PACKAGE__);
+}
-When this variable is true, each occurence of unescaped I<"exactly one"> wildcards (i.e. C<?> jokers or C<_> for SQL wildcards) are made capturing in the resulting regexp (they are be replaced by C<(.)>). Otherwise, they are just replaced by C<.>. Default is the latter.
+my %types = (
+ jokers => [ qw/jokers/ ],
+ sql => [ qw/sql/ ],
+ commas => [ qw/commas/ ],
+ brackets => [ qw/brackets/ ],
+ unix => [ qw/jokers brackets/ ],
+ win32 => [ qw/jokers commas/ ],
+);
+$types{$_} = $types{win32} for qw/dos os2 MSWin32 cygwin/;
+
+my %escapes = (
+ jokers => '?*',
+ sql => '_%',
+ commas => ',',
+ brackets => '{},',
+ groups => '()',
+);
- For jokers :
- 'a???b\\??' is translated to 'a(.)(.)(.)b\\?(.)' if $CaptureSingle is true
- 'a...b\\?.' otherwise (default)
+my %captures = (
+ single => sub { $_[1] ? '(.)' : '.' },
+ any => sub { $_[1] ? ($_[0]->{greedy} ? '(.*)'
+ : '(.*?)')
+ : '.*' },
+ brackets => sub { $_[1] ? '(' : '(?:'; },
+ greedy => undef
+);
- For SQL wildcards :
- 'a___b\\__' is translated to 'a(.)(.)(.)b\\_(.)' if $CaptureSingle is true
- 'a...b\\_.' otherwise (default)
+sub _validate {
+ my $self = shift;
+ _check_self $self;
+ my $valid = shift;
+ my $old = shift;
+ $old = { } unless defined $old;
+ my $c;
+ if (@_ <= 1) {
+ $c = { set => $_[0] };
+ } elsif (@_ % 2) {
+ croak 'Arguments must be passed as an unique scalar or as key => value pairs';
+ } else {
+ my %args = @_;
+ $c = { map { (exists $args{$_}) ? ($_ => $args{$_}) : () } qw/set add rem/ };
+ }
+ for (qw/set add rem/) {
+ my $v = $c->{$_};
+ next unless defined $v;
+ my $cb = {
+ '' => sub { +{ ($_[0] => 1) x (exists $valid->{$_[0]}) } },
+ 'ARRAY' => sub { +{ map { ($_ => 1) x (exists $valid->{$_}) } @{$_[0]} } },
+ 'HASH' => sub { +{ map { ($_ => $_[0]->{$_}) x (exists $valid->{$_}) }
+ keys %{$_[0]} } }
+ }->{ ref $v };
+ croak 'Wrong option set' unless $cb;
+ $c->{$_} = $cb->($v);
+ }
+ my $config = (exists $c->{set}) ? $c->{set} : $old;
+ $config->{$_} = $c->{add}->{$_} for grep $c->{add}->{$_},
+ keys %{$c->{add} || {}};
+ delete $config->{$_} for grep $c->{rem}->{$_}, keys %{$c->{rem} || {}};
+ $config;
+}
-=cut
+sub _do {
+ my $self = shift;
+ my $config;
+ $config->{do} = $self->_validate(\%escapes, $self->{do}, @_);
+ $config->{escape} = '';
+ $config->{escape} .= $escapes{$_} for keys %{$config->{do}};
+ $config->{escape} = quotemeta $config->{escape};
+ $config;
+}
-our $CaptureSingle = 0;
+sub do {
+ my $self = shift;
+ _check_self $self;
+ my $config = $self->_do(@_);
+ $self->{$_} = $config->{$_} for keys %$config;
+ $self;
+}
-sub capture_single {
- return $CaptureSingle ? '(.)'
- : '.';
+sub _capture {
+ my $self = shift;
+ my $config;
+ $config->{capture} = $self->_validate(\%captures, $self->{capture}, @_);
+ $config->{greedy} = delete $config->{capture}->{greedy};
+ for (keys %captures) {
+ $config->{'c_' . $_} = $captures{$_}->($config, $config->{capture}->{$_})
+ if $captures{$_}; # Skip 'greedy'
+ }
+ $config;
}
-=head2 C<$CaptureAny>
+sub capture {
+ my $self = shift;
+ _check_self $self;
+ my $config = $self->_capture(@_);
+ $self->{$_} = $config->{$_} for keys %$config;
+ $self;
+}
-By default this variable is false, and successions of unescaped I<"any"> wildcards (i.e. C<*> jokers or C<%> for SQL wildcards) are replaced by B<one> single C<.*>. When it evalutes to true, those sequences of I<"any"> wildcards are made into B<one> capture, which is greedy (C<(.*)>) for C<$CaptureAny E<gt> 0> and otherwise non-greedy (C<(.*?)>).
+sub _type {
+ my ($self, $type) = @_;
+ $type = 'unix' unless defined $type;
+ croak 'Wrong type' unless exists $types{$type};
+ my $config = $self->_do($types{$type});
+ $config->{type} = $type;
+ $config;
+}
- For jokers :
- 'a***b\\**' is translated to 'a.*b\\*.*' if $CaptureAny is false (default)
- 'a(.*)b\\*(.*)' if $CaptureAny > 0
- 'a(.*?)b\\*(.*?)' otherwise
+sub type {
+ my $self = shift;
+ _check_self $self;
+ my $config = $self->_type(@_);
+ $self->{$_} = $config->{$_} for keys %$config;
+ $self;
+}
- For SQL wildcards :
- 'a%%%b\\%%' is translated to 'a.*b\\%.*' if $CaptureAny is false (default)
- 'a(.*)b\\%(.*)' if $CaptureAny > 0
- 'a(.*?)b\\%(.*?)' otherwise
+sub new {
+ my $class = shift;
+ $class = ref($class) || $class || __PACKAGE__;
+ croak 'Optional arguments must be passed as key => value pairs' if @_ % 2;
+ my %args = @_;
+ my $self = { };
+ bless $self, $class;
+ if (defined $args{do}) {
+ $self->do($args{do});
+ } else {
+ $self->type($args{type});
+ }
+ $self->capture($args{capture});
+}
-=cut
+=head2 C<< new [ do => $what E<verbar> type => $type ], capture => $captures >>
-our $CaptureAny = 0;
+Constructs a new L<Regexp::Wildcard> object.
-sub capture_any {
- return $CaptureAny ? (($CaptureAny > 0) ? '(.*)'
- : '(.*?)')
- : '.*';
-}
+C<do> lists all features that should be enabled when converting wildcards to regexps. Refer to L</do> for details on what can be passed in C<$what>.
-=head2 C<$CaptureBrackets>
+The C<type> specifies a predefined set of C<do> features to use. See L</type> for details on which types are valid. The C<do> option overrides C<type>.
-If this variable is set to true, valid brackets constructs are made into C<( | )> captures, and otherwise they are replaced by non-capturing alternations (C<(?: | >)), which is the default.
+C<capture> lists which atoms should be capturing. Refer to L</capture> for more details.
- 'a{b\\},\\{c}' is translated to 'a(b\\}|\\{c)' if $CaptureBrackets is true
- 'a(?:b\\}|\\{c)' otherwise (default)
+=head2 C<< do [ $what E<verbar> set => $c1, add => $c2, rem => $c3 ] >>
-=cut
+Specifies the list of metacharacters to convert.
+They are classified into five classes :
-our $CaptureBrackets = 0;
+=over 4
-sub capture_brackets {
- return $CaptureBrackets ? '('
- : '(?:';
-}
+=item C<'jokers'> converts C<?> to C<.> and C<*> to C<.*> ;
-=head1 FUNCTIONS
+ 'a**\\*b??\\?c' ==> 'a.*\\*b..\\?c'
-=head2 C<wc2re_jokers>
+=item C<'sql'> converts C<_> to C<.> and C<%> to C<.*> ;
-This function takes as its only argument the wildcard string to process, and returns the corresponding regular expression where the jokers C<?> (I<"exactly one">) and C<*> (I<"any">) have been translated into their regexp equivalents (see L</VARIABLES> for more details). All other unprotected regexp metacharacters are escaped.
+ 'a%%\\%b__\\_c' ==> 'a.*\\%b..\\_c'
- # Everything is escaped.
- print 'ok' if wc2re_jokers('{a{b,c}d,e}') eq '\\{a\\{b\\,c\\}d\\,e\\}';
+=item C<'commas'> converts all C<,> to C<|> and puts the complete resulting regular expression inside C<(?: ... )> ;
-=cut
+ 'a,b{c,d},e' ==> '(?:a|b\\{c|d\\}|e)'
-sub wc2re_jokers {
- my ($wc) = @_;
- $wc =~ s/(?<!\\)((?:\\\\)*[^\w\s?*\\])/\\$1/g;
- return do_jokers($wc);
-}
+=item C<'brackets'> converts all matching C<{ ... , ... }> brackets to C<(?: ... | ... )> alternations. If some brackets are unbalanced, it tries to substitute as many of them as possible, and then escape the remaining unmatched C<{> and C<}>. Commas outside of any bracket-delimited block are also escaped ;
-=head2 C<wc2re_sql>
+ 'a,b{c,d},e' ==> 'a\\,b(?:c|d)\\,e'
+ '{a\\{b,c}d,e}' ==> '(?:a\\{b|c)d\\,e\\}'
+ '{a{b,c\\}d,e}' ==> '\\{a\\{b\\,c\\}d\\,e\\}'
-Similar to the precedent, but for the SQL wildcards C<_> (I<"exactly one">) and C<%> (I<"any">). All other unprotected regexp metacharacters are escaped.
-
-=cut
-
-sub wc2re_sql {
- my ($wc) = @_;
- $wc =~ s/(?<!\\)((?:\\\\)*[^\w\s%\\])/\\$1/g;
- return do_sql($wc);
-}
+=item C<'groups'> keeps the parenthesis C<( ... )> of the original string without escaping them. Currently, no check is done to ensure that the parenthesis are matching.
-=head2 C<wc2re_unix>
+ 'a(b(c))d\\(\\)' ==> (no change)
-This function conforms to standard Unix shell wildcard rules. It successively escapes all unprotected regexp special characters that doesn't hold any meaning for wildcards, turns C<?> and C<*> jokers into their regexp equivalents (see L</wc2re_jokers>), and changes bracketed blocks into (possibly capturing) alternations as described in L</VARIABLES>. If brackets are unbalanced, it tries to substitute as many of them as possible, and then escape the remaining C<{> and C<}>. Commas outside of any bracket-delimited block are also escaped.
+=back
- # This is a valid bracket expression, and is completely translated.
- print 'ok' if wc2re_unix('{a{b,c}d,e}') eq '(?:a(?:b|c)d|e)';
+Each C<$c> can be any of :
-The function handles unbalanced bracket expressions, by escaping everything it can't recognize. For example :
+=over 4
- # The first comma is replaced, and the remaining brackets and comma are escaped.
- print 'ok' if wc2re_unix('{a\\{b,c}d,e}') eq '(?:a\\{b|c)d\\,e\\}';
+=item A hash reference, with wanted metacharacter group names (described above) as keys and booleans as values ;
- # All the brackets and commas are escaped.
- print 'ok' if wc2re_unix('{a{b,c\\}d,e}') eq '\\{a\\{b\\,c\\}d\\,e\\}';
+=item An array reference containing the list of wanted metacharacter classes ;
-=cut
+=item A plain scalar, when only one group is required.
-sub wc2re_unix {
- my ($re) = @_;
- return unless defined $re;
- $re =~ s/(?<!\\)((?:\\\\)*[^\w\s?*\\\{\},])/\\$1/g;
- return do_bracketed(do_jokers($re));
-}
+=back
-=head2 C<wc2re_win32>
+When C<set> is present, the classes given as its value replace the current object options. Then the C<add> classes are added, and the C<rem> classes removed.
-This one works just like the one before, but for Windows wildcards. Bracketed blocks are no longer handled (which means that brackets are escaped), but you can provide a comma-separated list of items.
+Passing a sole scalar C<$what> is equivalent as passing C<< set => $what >>.
+No argument means C<< set => [ ] >>.
- # All the brackets are escaped, and commas are seen as list delimiters.
- print 'ok' if wc2re_win32('{a{b,c}d,e}') eq '(?:\\{a\\{b|c\\}d|e\\})';
+ $rw->do(set => 'jokers'); # Only translate jokers.
+ $rw->do('jokers'); # Same.
+ $rw->do(add => [ qw/sql commas/ ]); # Translate also SQL and commas.
+ $rw->do(rem => 'jokers'); # Specifying both 'sql' and 'jokers' is useless.
+ $rw->do(); # Translate nothing.
-=cut
+=head2 C<type $type>
-sub wc2re_win32 {
- my ($wc) = @_;
- return unless defined $wc;
- $wc =~ s/(?<!\\)((?:\\\\)*[^\w\s?*\\,])/\\$1/g;
- my $re = do_jokers($wc);
- if ($re =~ /(?<!\\)(?:\\\\)*,/) { # win32 allows comma-separated lists
- $re = capture_brackets . do_commas($re) . ')';
- }
- return $re;
-}
+Notifies to convert the metacharacters that corresponds to the predefined type C<$type>. C<$type> can be any of C<'jokers'>, C<'sql'>, C<'commas'>, C<'brackets'>, C<'win32'> or C<'unix'>. An unknown or undefined value defaults to C<'unix'>, except for C<'dos'>, C<'os2'>, C<'MSWin32'> and C<'cygwin'> that default to C<'win32'>. This means that you can pass C<$^O> as the C<$type> and get the corresponding shell behaviour. Returns the object.
+
+ $rw->type('win32'); # Set type to win32.
+ $rw->type(); # Set type to unix.
-=head2 C<wc2re>
+=head2 C<< capture [ $captures E<verbar> set => $c1, add => $c2, rem => $c3 ] >>
-A generic function that wraps around all the different rules. The first argument is the wildcard expression, and the second one is the type of rules to apply which can be :
+Specifies the list of atoms to capture.
+This method works like L</do>, except that the classes are different :
=over 4
-=item C<'unix'>, C<'win32'>, C<'jokers'>, C<'sql'>
+=item C<'single'> will capture all unescaped I<"exactly one"> metacharacters, i.e. C<?> for wildcards or C<_> for SQL ;
+
+ 'a???b\\??' ==> 'a(.)(.)(.)b\\?(.)'
+ 'a___b\\__' ==> 'a(.)(.)(.)b\\_(.)'
+
+=item C<'any'> will capture all unescaped I<"any"> metacharacters, i.e. C<*> for wildcards or C<%> for SQL ;
-For one of those raw rule names, C<wc2re> simply maps to C<wc2re_unix>, C<wc2re_win32>, C<wc2re_jokers> and C<wc2re_sql> respectively.
+ 'a***b\\**' ==> 'a(.*)b\\*(.*)'
+ 'a%%%b\\%%' ==> 'a(.*)b\\%(.*)'
-=item C<$^O>
+=item C<'greedy'>, when used in conjunction with C<'any'>, will make the C<'any'> captures greedy (by default they are not) ;
-If you supply the Perl operating system name, the call is deferred to C<wc2re_win32> for C< $^O> equal to C<'dos'>, C<'os2'>, C<'MSWin32'> or C<'cygwin'>, and to C<wc2re_unix> in all the other cases.
+ 'a***b\\**' ==> 'a(.*?)b\\*(.*?)'
+ 'a%%%b\\%%' ==> 'a(.*?)b\\%(.*?)'
+
+=item C<'brackets'> will capture matching C<{ ... , ... }> alternations.
+
+ 'a{b\\},\\{c}' ==> 'a(b\\}|\\{c)'
=back
-If the type is undefined or not supported, it defaults to C<'unix'>.
+ $rw->capture(set => 'single'); # Only capture "exactly one" metacharacters.
+ $rw->capture('single'); # Same.
+ $rw->capture(add => [ qw/any greedy/ ]); # Also greedily capture "any" metacharacters.
+ $rw->capture(rem => 'greedy'); # No more greed please.
+ $rw->capture(); # Capture nothing.
- # Wraps to wc2re_jokers ($re eq 'a\\{b\\,c\\}.*').
- $re = wc2re 'a{b,c}*' => 'jokers';
+=head2 C<convert $wc [ , $type ]>
- # Wraps to wc2re_win32 ($re eq '(?:a\\{b|c\\}.*)')
- # or wc2re_unix ($re eq 'a(?:b|c).*') depending on $^O.
- $re = wc2re 'a{b,c}*' => $^O;
+Converts the wildcard expression C<$wc> into a regular expression according to the options stored into the L<Regexp::Wildcards> object, or to C<$type> if it's supplied. It successively escapes all unprotected regexp special characters that doesn't hold any meaning for wildcards, then replace C<'jokers'> or C<'sql'> and C<'commas'> or C<'brackets'> (depending on the L</do> or L</type> options), all of this by applying the C<'capture'> rules specified in the constructor or by L</capture>.
=cut
-my %types = (
- 'jokers' => \&wc2re_jokers,
- 'sql' => \&wc2re_sql,
- 'unix' => \&wc2re_unix,
- map { lc $_ => \&wc2re_win32 } qw/win32 dos os2 MSWin32 cygwin/
-);
-
-sub wc2re {
- my ($wc, $type) = @_;
+sub convert {
+ my ($self, $wc, $type) = @_;
+ _check_self $self;
+ my $config;
+ if (defined $type) {
+ $config = $self->_type($type);
+ } else {
+ $config = $self;
+ }
return unless defined $wc;
- $type = $type ? lc $type : 'unix';
- $type = 'unix' unless exists $types{$type};
- return $types{$type}($wc);
+ my $do = $config->{do};
+ my $e = $config->{escape};
+ $wc =~ s/(?<!\\)((?:\\\\)*[^\w\s\\$e])/\\$1/g;
+ return $self->_sql($wc) if $do->{sql};
+ $wc = $self->_jokers($wc) if $do->{jokers};
+ if ($do->{brackets}) {
+ $wc = $self->_bracketed($wc);
+ } elsif ($do->{commas}) {
+ if ($wc =~ /(?<!\\)(?:\\\\)*,/) { # win32 allows comma-separated lists
+ $wc = $self->{'c_brackets'} . $self->_commas($wc) . ')';
+ }
+ }
+ return $wc;
}
=head1 EXPORT
-These five functions are exported only on request : C<wc2re>, C<wc2re_unix>, C<wc2re_win32>, C<wc2re_jokers> and C<wc2re_sql>. The variables are not exported.
-
-=cut
-
-use base qw/Exporter/;
-
-our @EXPORT = ();
-our %EXPORT_TAGS = (
- 'funcs' => [ 'wc2re', map { 'wc2re_'.$_ } keys %types ],
-);
-our @EXPORT_OK = map { @$_ } values %EXPORT_TAGS;
-our @EXPORT_FAIL = qw/extract/,
- (map { 'do_'.$_ } qw/jokers sql commas brackets bracketed/),
- (map { 'capture_'.$_ } qw/single any brackets/);
-$EXPORT_TAGS{'all'} = [ @EXPORT_OK ];
+An object module shouldn't export any function, and so does this one.
=head1 DEPENDENCIES
-L<Text::Balanced>, which is bundled with perl since version 5.7.3
+L<Carp> (core module since perl 5), L<Text::Balanced> (since 5.7.3).
=head1 CAVEATS
This module does not implement the strange behaviours of Windows shell that result from the special handling of the three last characters (for the file extension). For example, Windows XP shell matches C<*a> like C<.*a>, C<*a?> like C<.*a.?>, C<*a??> like C<.*a.{0,2}> and so on.
-=head1 SEE ALSO
-
-Some modules provide incomplete alternatives as helper functions :
-
-L<Net::FTPServer> has a method for that. Only jokers are translated, and escaping won't preserve them.
-
-L<File::Find::Match::Util> has a C<wildcard> function that compiles a matcher. It only handles C<*>.
-
-L<Text::Buffer> has the C<convertWildcardToRegex> class method that handles jokers.
-
=head1 AUTHOR
Vincent Pit, C<< <perl at profvince.com> >>, L<http://www.profvince.com>.
perldoc Regexp::Wildcards
+Tests code coverage report is available at L<http://www.profvince.com/perl/cover/Regexp-Wildcards>.
+
=head1 COPYRIGHT & LICENSE
Copyright 2007-2008 Vincent Pit, all rights reserved.
=cut
-sub extract { extract_bracketed shift, '{', qr/.*?(?<!\\)(?:\\\\)*(?={)/; }
+sub _extract ($) { extract_bracketed $_[0], '{', qr/.*?(?<!\\)(?:\\\\)*(?={)/ }
-sub do_jokers {
- local $_ = shift;
+sub _jokers {
+ my $self = shift;
+ local $_ = $_[0];
# escape an odd number of \ that doesn't protect a regexp/wildcard special char
s/(?<!\\)((?:\\\\)*\\(?:[\w\s]|$))/\\$1/g;
# substitute ? preceded by an even number of \
- my $s = capture_single;
+ my $s = $self->{c_single};
s/(?<!\\)((?:\\\\)*)\?/$1$s/g;
# substitute * preceded by an even number of \
- $s = capture_any;
+ $s = $self->{c_any};
s/(?<!\\)((?:\\\\)*)\*+/$1$s/g;
return $_;
}
-sub do_sql {
- local $_ = shift;
+sub _sql {
+ my $self = shift;
+ local $_ = $_[0];
# escape an odd number of \ that doesn't protect a regexp/wildcard special char
s/(?<!\\)((?:\\\\)*\\(?:[^\W_]|\s|$))/\\$1/g;
# substitute _ preceded by an even number of \
- my $s = capture_single;
+ my $s = $self->{c_single};
s/(?<!\\)((?:\\\\)*)_/$1$s/g;
- # substitute * preceded by an even number of \
- $s = capture_any;
+ # substitute % preceded by an even number of \
+ $s = $self->{c_any};
s/(?<!\\)((?:\\\\)*)%+/$1$s/g;
return $_;
}
-sub do_commas {
- local $_ = shift;
+sub _commas {
+ local $_ = $_[1];
# substitute , preceded by an even number of \
s/(?<!\\)((?:\\\\)*),/$1|/g;
return $_;
}
-sub do_brackets {
- my $rest = shift;
+sub _brackets {
+ my ($self, $rest) = @_;
substr $rest, 0, 1, '';
chop $rest;
my ($re, $bracket, $prefix) = ('');
- while (($bracket, $rest, $prefix) = extract $rest and $bracket) {
- $re .= do_commas($prefix) . do_brackets($bracket);
+ while (do { ($bracket, $rest, $prefix) = _extract $rest; $bracket }) {
+ $re .= $self->_commas($prefix) . $self->_brackets($bracket);
}
- $re .= do_commas($rest);
- return capture_brackets . $re . ')';
+ $re .= $self->_commas($rest);
+ return $self->{c_brackets} . $re . ')';
}
-sub do_bracketed {
- my $rest = shift;
+sub _bracketed {
+ my ($self, $rest) = @_;
my ($re, $bracket, $prefix) = ('');
- while (($bracket, $rest, $prefix) = extract $rest and $bracket) {
- $re .= $prefix . do_brackets($bracket);
+ while (do { ($bracket, $rest, $prefix) = _extract $rest; $bracket }) {
+ $re .= $prefix . $self->_brackets($bracket);
}
$re .= $rest;
$re =~ s/(?<!\\)((?:\\\\)*[\{\},])/\\$1/g;
projects / perl / modules / Regexp-Wildcards.git / blobdiff