use strict;
use warnings;
+use Carp qw/croak/;
use Text::Balanced qw/extract_bracketed/;
=head1 NAME
=head1 VERSION
-Version 0.06
+Version 1.03
=cut
-our $VERSION = '0.06';
+use vars qw/$VERSION/;
+BEGIN {
+ $VERSION = '1.03';
+}
=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.
- $Regexp::Wildcards::CaptureSingle = 1;
- # From then, "exactly one" wildcards are capturing
+It handles the C<*> and C<?> jokers, as well as Unix bracketed alternatives C<{,}>, but also C<%> and C<_> SQL wildcards.
+If required, it can also keep original C<(...)> groups or C<^> and C<$> anchors.
+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{$_} = $types{win32} for qw/dos os2 MSWin32 cygwin/;
+$types{$_} = $types{unix} for qw/linux
+ darwin machten next
+ aix irix hpux dgux dynixptx
+ bsdos freebsd openbsd
+ svr4 solaris sunos dec_osf
+ sco_sv unicos unicosmk/;
+
+my %escapes = (
+ jokers => '?*',
+ sql => '_%',
+ commas => ',',
+ brackets => '{},',
+ groups => '()',
+ anchors => '^$',
+);
- 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 %opts;
+ if (@_ <= 1) {
+ $opts{set} = defined $_[0] ? $_[0] : { };
+ } elsif (@_ % 2) {
+ croak 'Arguments must be passed as an unique scalar or as key => value pairs';
+ } else {
+ %opts = @_;
+ }
-=cut
+ my %checked;
+ for (qw/set add rem/) {
+ my $opt = $opts{$_};
+ next unless defined $opt;
+ 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 $opt };
+ croak 'Wrong option set' unless $cb;
+ $checked{$_} = $cb->($opt);
+ }
-our $CaptureSingle = 0;
+ my $config = (exists $checked{set}) ? $checked{set} : $old;
+ $config->{$_} = $checked{add}->{$_} for grep $checked{add}->{$_},
+ keys %{$checked{add} || {}};
+ delete $config->{$_} for grep $checked{rem}->{$_},
+ keys %{$checked{rem} || {}};
-sub capture_single {
- return $CaptureSingle ? '(.)'
- : '.';
+ $config;
}
-=head2 C<$CaptureAny>
+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};
+ $config;
+}
-By default this variable is false, and successions of unescaped I<"any"> wildcards (i.e. C<*> jokers or C<%> for SQL wildcards) are replaced by B<one> single C<.*>. When it evalutes to true, those sequences of I<"any"> wildcards are made into B<one> capture, which is greedy (C<(.*)>) for C<$CaptureAny E<gt> 0> and otherwise non-greedy (C<(.*?)>).
+sub do {
+ my $self = shift;
+ _check_self $self;
+ my $config = $self->_do(@_);
+ $self->{$_} = $config->{$_} for keys %$config;
+ $self;
+}
- For jokers :
- 'a***b\\**' is translated to 'a.*b\\*.*' if $CaptureAny is false (default)
- 'a(.*)b\\*(.*)' if $CaptureAny > 0
- 'a(.*?)b\\*(.*?)' otherwise
+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;
+}
- For SQL wildcards :
- 'a%%%b\\%%' is translated to 'a.*b\\%.*' if $CaptureAny is false (default)
- 'a(.*)b\\%(.*)' if $CaptureAny > 0
- 'a(.*?)b\\%(.*?)' otherwise
+sub capture {
+ my $self = shift;
+ _check_self $self;
+ my $config = $self->_capture(@_);
+ $self->{$_} = $config->{$_} for keys %$config;
+ $self;
+}
-=cut
+sub _type {
+ my ($self, $type) = @_;
+ $type = 'unix' unless defined $type;
+ croak 'Wrong type' unless exists $types{$type};
+ my $config = $self->_do($types{$type});
+ $config->{type} = $type;
+ $config;
+}
-our $CaptureAny = 0;
+sub type {
+ my $self = shift;
+ _check_self $self;
+ my $config = $self->_type(@_);
+ $self->{$_} = $config->{$_} for keys %$config;
+ $self;
+}
-sub capture_any {
- return $CaptureAny ? (($CaptureAny > 0) ? '(.*)'
- : '(.*?)')
- : '.*';
+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});
}
-=head2 C<$CaptureBrackets>
+=head2 C<< new [ do => $what E<verbar> type => $type ], capture => $captures >>
-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.
+Constructs a new L<Regexp::Wildcard> object.
- 'a{b\\},\\{c}' is translated to 'a(b\\}|\\{c)' if $CaptureBrackets is true
- 'a(?:b\\}|\\{c)' otherwise (default)
+C<do> lists all features that should be enabled when converting wildcards to regexps.
+Refer to L</do> for details on what can be passed in C<$what>.
-=cut
+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>.
-our $CaptureBrackets = 0;
+C<capture> lists which atoms should be capturing.
+Refer to L</capture> for more details.
-sub capture_brackets {
- return $CaptureBrackets ? '('
- : '(?:';
-}
+=head2 C<< do [ $what E<verbar> set => $c1, add => $c2, rem => $c3 ] >>
-=head1 FUNCTIONS
+Specifies the list of metacharacters to convert or to prevent for escaping.
+They fit into six classes :
-=head2 C<wc2re_jokers>
+=over 4
-This function takes as its only argument the wildcard string to process, and returns the corresponding regular expression where the jokers C<?> (I<"exactly one">) and C<*> (I<"any">) have been translated into their regexp equivalents (see L</VARIABLES> for more details). All other unprotected regexp metacharacters are escaped.
+=item *
- # Everything is escaped.
- print 'ok' if wc2re_jokers('{a{b,c}d,e}') eq '\\{a\\{b\\,c\\}d\\,e\\}';
+C<'jokers'>
-=cut
+Converts C<?> to C<.> and C<*> to C<.*>.
-sub wc2re_jokers {
- my ($wc) = @_;
- $wc =~ s/(?<!\\)((?:\\\\)*[^\w\s?*\\])/\\$1/g;
- return do_jokers($wc);
-}
+ 'a**\\*b??\\?c' ==> 'a.*\\*b..\\?c'
-=head2 C<wc2re_sql>
+=item *
-Similar to the precedent, but for the SQL wildcards C<_> (I<"exactly one">) and C<%> (I<"any">). All other unprotected regexp metacharacters are escaped.
-
-=cut
-
-sub wc2re_sql {
- my ($wc) = @_;
- $wc =~ s/(?<!\\)((?:\\\\)*[^\w\s%\\])/\\$1/g;
- return do_sql($wc);
-}
+C<'sql'>
-=head2 C<wc2re_unix>
+Converts C<_> to C<.> and C<%> to C<.*>.
-This function conforms to standard Unix shell wildcard rules. It successively escapes all unprotected regexp special characters that doesn't hold any meaning for wildcards, turns C<?> and C<*> jokers into their regexp equivalents (see L</wc2re_jokers>), and changes bracketed blocks into (possibly capturing) alternations as described in L</VARIABLES>. If brackets are unbalanced, it tries to substitute as many of them as possible, and then escape the remaining C<{> and C<}>. Commas outside of any bracket-delimited block are also escaped.
+ 'a%%\\%b__\\_c' ==> 'a.*\\%b..\\_c'
- # This is a valid bracket expression, and is completely translated.
- print 'ok' if wc2re_unix('{a{b,c}d,e}') eq '(?:a(?:b|c)d|e)';
+=item *
-The function handles unbalanced bracket expressions, by escaping everything it can't recognize. For example :
+C<'commas'>
- # The first comma is replaced, and the remaining brackets and comma are escaped.
- print 'ok' if wc2re_unix('{a\\{b,c}d,e}') eq '(?:a\\{b|c)d\\,e\\}';
+Converts all C<,> to C<|> and puts the complete resulting regular expression inside C<(?: ... )>.
- # All the brackets and commas are escaped.
- print 'ok' if wc2re_unix('{a{b,c\\}d,e}') eq '\\{a\\{b\\,c\\}d\\,e\\}';
+ 'a,b{c,d},e' ==> '(?:a|b\\{c|d\\}|e)'
-=cut
+=item *
-sub wc2re_unix {
- my ($re) = @_;
- return unless defined $re;
- $re =~ s/(?<!\\)((?:\\\\)*[^\w\s?*\\\{\},])/\\$1/g;
- return do_bracketed(do_jokers($re));
-}
+C<'brackets'>
-=head2 C<wc2re_win32>
+Converts all matching C<{ ... , ... }> brackets to C<(?: ... | ... )> alternations.
+If some brackets are unbalanced, it tries to substitute as many of them as possible, and then escape the remaining unmatched C<{> and C<}>.
+Commas outside of any bracket-delimited block are also escaped.
-This one works just like the one before, but for Windows wildcards. Bracketed blocks are no longer handled (which means that brackets are escaped), but you can provide a comma-separated list of items.
+ 'a,b{c,d},e' ==> 'a\\,b(?:c|d)\\,e'
+ '{a\\{b,c}d,e}' ==> '(?:a\\{b|c)d\\,e\\}'
+ '{a{b,c\\}d,e}' ==> '\\{a\\{b\\,c\\}d\\,e\\}'
- # All the brackets are escaped, and commas are seen as list delimiters.
- print 'ok' if wc2re_win32('{a{b,c}d,e}') eq '(?:\\{a\\{b|c\\}d|e\\})';
+=item *
-=cut
+C<'groups'>
-sub wc2re_win32 {
- my ($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 $re;
-}
+Keeps the parenthesis C<( ... )> of the original string without escaping them.
+Currently, no check is done to ensure that the parenthesis are matching.
+
+ 'a(b(c))d\\(\\)' ==> (no change)
+
+=item *
+
+C<'anchors'>
-=head2 C<wc2re>
+Prevents the I<beginning-of-line> C<^> and I<end-of-line> C<$> anchors to be escaped.
+Since C<[...]> character class are currently escaped, a C<^> will always be interpreted as I<beginning-of-line>.
+
+ 'a^b$c' ==> (no change)
+
+=back
-A generic function that wraps around all the different rules. The first argument is the wildcard expression, and the second one is the type of rules to apply which can be :
+Each C<$c> can be any of :
=over 4
-=item C<'unix'>, C<'win32'>, C<'jokers'>, C<'sql'>
+=item *
-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 hash reference, with wanted metacharacter group names (described above) as keys and booleans as values ;
-=item C<$^O>
+=item *
-If you supply the Perl operating system name, the call is deferred to C<wc2re_win32> for C< $^O> equal to C<'dos'>, C<'os2'>, C<'MSWin32'> or C<'cygwin'>, and to C<wc2re_unix> in all the other cases.
+An array reference containing the list of wanted metacharacter classes ;
+
+=item *
+
+A plain scalar, when only one group is required.
=back
-If the type is undefined or not supported, it defaults to C<'unix'>.
+When C<set> is present, the classes given as its value replace the current object options.
+Then the C<add> classes are added, and the C<rem> classes removed.
- # Wraps to wc2re_jokers ($re eq 'a\\{b\\,c\\}.*').
- $re = wc2re 'a{b,c}*' => 'jokers';
+Passing a sole scalar C<$what> is equivalent as passing C<< set => $what >>.
+No argument means C<< set => [ ] >>.
- # Wraps to wc2re_win32 ($re eq '(?:a\\{b|c\\}.*)')
- # or wc2re_unix ($re eq 'a(?:b|c).*') depending on $^O.
- $re = wc2re 'a{b,c}*' => $^O;
+ $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
+The C<do> method returns the L<Regexp::Wildcards> object.
-my %types = (
- 'jokers' => \&wc2re_jokers,
- 'sql' => \&wc2re_sql,
- 'unix' => \&wc2re_unix,
- map { lc $_ => \&wc2re_win32 } qw/win32 dos os2 MSWin32 cygwin/
-);
+=head2 C<type $type>
-sub wc2re {
- my ($wc, $type) = @_;
- return unless defined $wc;
- $type = $type ? lc $type : 'unix';
- $type = 'unix' unless exists $types{$type};
- return $types{$type}($wc);
-}
+Notifies to convert the metacharacters that corresponds to the predefined type C<$type>.
+C<$type> can be any of :
-=head1 EXPORT
+=over 4
+
+=item *
+
+C<'jokers'>, C<'sql'>, C<'commas'>, C<'brackets'>
+
+Singleton types that enable the corresponding C<do> classes.
+
+=item *
+
+C<'unix'>
-These five functions are exported only on request : C<wc2re>, C<wc2re_unix>, C<wc2re_win32>, C<wc2re_jokers> and C<wc2re_sql>. The variables are not exported.
+Covers typical Unix shell globbing features (effectively C<'jokers'> and C<'brackets'>).
+
+=item *
+
+C<$^O> values for common Unix systems
+
+Wrap to C<'unix'> (see L<perlport> for the list).
+
+=item *
+
+C<undef>
+
+Defaults to C<'unix'>.
+
+=item *
+
+C<'win32'>
+
+Covers typical Windows shell globbing features (effectively C<'jokers'> and C<'commas'>).
+
+=item *
+
+C<'dos'>, C<'os2'>, C<'MSWin32'>, C<'cygwin'>
+
+Wrap to C<'win32'>.
+
+=back
+
+In particular, you can usually pass C<$^O> as the C<$type> and get the corresponding shell behaviour.
+
+ $rw->type('win32'); # Set type to win32.
+ $rw->type($^O); # Set type to unix on Unices and win32 on Windows
+ $rw->type(); # Set type to unix.
+
+The C<type> method returns the L<Regexp::Wildcards> object.
+
+=head2 C<< capture [ $captures E<verbar> set => $c1, add => $c2, rem => $c3 ] >>
+
+Specifies the list of atoms to capture.
+This method works like L</do>, except that the classes are different :
+
+=over 4
+
+=item *
+
+C<'single'>
+
+Captures 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'>
+
+Captures all unescaped I<"any"> metacharacters, i.e. C<*> for wildcards or C<%> for SQL.
+
+ 'a***b\\**' ==> 'a(.*)b\\*(.*)'
+ 'a%%%b\\%%' ==> 'a(.*)b\\%(.*)'
+
+=item *
+
+C<'greedy'>
+
+When used in conjunction with C<'any'>, it makes the C<'any'> captures greedy (by default they are not).
+
+ 'a***b\\**' ==> 'a(.*?)b\\*(.*?)'
+ 'a%%%b\\%%' ==> 'a(.*?)b\\%(.*?)'
+
+=item *
+
+C<'brackets'>
+
+Capture matching C<{ ... , ... }> alternations.
+
+ 'a{b\\},\\{c}' ==> 'a(b\\}|\\{c)'
+
+=back
+
+ $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.
+
+The C<capture> method returns the L<Regexp::Wildcards> object.
+
+=head2 C<convert $wc [ , $type ]>
+
+Converts the wildcard expression C<$wc> into a regular expression according to the options stored into the L<Regexp::Wildcards> object, or to C<$type> if it's supplied.
+It successively escapes all unprotected regexp special characters that doesn't hold any meaning for wildcards, then replace C<'jokers'>, C<'sql'> and C<'commas'> or C<'brackets'> (depending on the L</do> or L</type> options), all of this by applying the C<'capture'> rules specified in the constructor or by L</capture>.
=cut
-use base qw/Exporter/;
+sub convert {
+ my ($self, $wc, $type) = @_;
+ _check_self $self;
+ my $config = (defined $type) ? $self->_type($type) : $self;
+ return unless defined $wc;
-our @EXPORT = ();
-our @EXPORT_OK = ('wc2re', map { 'wc2re_'.$_ } keys %types);
-our @EXPORT_FAIL = qw/extract/,
- (map { 'do_'.$_ } qw/jokers sql commas brackets bracketed/),
- (map { 'capture_'.$_ } qw/single any brackets/);
-our %EXPORT_TAGS = ( all => [ @EXPORT_OK ] );
+ my $e = $config->{escape};
+ # Escape :
+ # - an even number of \ that doesn't protect a regexp/wildcard metachar
+ # - an odd number of \ that doesn't protect a wildcard metachar
+ $wc =~ s/
+ (?<!\\)(
+ (?:\\\\)*
+ (?:
+ [^\w\s\\$e]
+ |
+ \\
+ (?: [^\W$e] | \s | $ )
+ )
+ )
+ /\\$1/gx;
+
+ my $do = $config->{do};
+ $wc = $self->_jokers($wc) if $do->{jokers};
+ $wc = $self->_sql($wc) if $do->{sql};
+ if ($do->{brackets}) {
+ $wc = $self->_bracketed($wc);
+ } elsif ($do->{commas} and $wc =~ /(?<!\\)(?:\\\\)*,/) {
+ $wc = $self->{'c_brackets'} . $self->_commas($wc) . ')';
+ }
-=head1 DEPENDENCIES
+ return $wc;
+}
-L<Text::Balanced>, which is bundled with perl since version 5.7.3
+=head1 EXPORT
-=head1 CAVEATS
+An object module shouldn't export any function, and so does this one.
-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 DEPENDENCIES
-=head1 SEE ALSO
+L<Carp> (core module since perl 5), L<Text::Balanced> (since 5.7.3).
-Some modules provide incomplete alternatives as helper functions :
+=head1 CAVEATS
-L<Net::FTPServer> has a method for that. Only jokers are translated, and escaping won't preserve them.
+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.
-L<File::Find::Match::Util> has a C<wildcard> function that compiles a matcher. It only handles C<*>.
+=head1 SEE ALSO
-L<Text::Buffer> has the C<convertWildcardToRegex> class method that handles jokers.
+L<Text::Glob>.
=head1 AUTHOR
-Vincent Pit, C<< <perl at profvince.com> >>
+Vincent Pit, C<< <perl at profvince.com> >>, L<http://www.profvince.com>.
+
+You can contact me by mail or on C<irc.perl.org> (vincent).
=head1 BUGS
-Please report any bugs or feature requests to
-C<bug-regexp-wildcards at rt.cpan.org>, or through the web interface at
-L<http://rt.cpan.org/NoAuth/ReportBug.html?Queue=Regexp-Wildcards>.
-I will be notified, and then you'll automatically be notified of progress on
-your bug as I make changes.
+Please report any bugs or feature requests to C<bug-regexp-wildcards at rt.cpan.org>, or through the web interface at L<http://rt.cpan.org/NoAuth/ReportBug.html?Queue=Regexp-Wildcards>. I will be notified, and then you'll automatically be notified of progress on your bug as I make changes.
=head1 SUPPORT
perldoc Regexp::Wildcards
+Tests code coverage report is available at L<http://www.profvince.com/perl/cover/Regexp-Wildcards>.
+
=head1 COPYRIGHT & LICENSE
-Copyright 2007 Vincent Pit, all rights reserved.
+Copyright 2007-2009 Vincent Pit, all rights reserved.
This program is free software; you can redistribute it and/or modify it
under the same terms as Perl itself.
=cut
-sub extract { extract_bracketed shift, '{', qr/.*?(?<!\\)(?:\\\\)*(?={)/; }
+sub _extract ($) { extract_bracketed $_[0], '{', qr/.*?(?<!\\)(?:\\\\)*(?={)/ }
-sub do_jokers {
- local $_ = shift;
- # escape an odd number of \ that doesn't protect a regexp/wildcard special char
- s/(?<!\\)((?:\\\\)*\\(?:[\w\s]|$))/\\$1/g;
+sub _jokers {
+ my $self = shift;
+ local $_ = $_[0];
# 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 $_ = shift;
- # escape an odd number of \ that doesn't protect a regexp/wildcard special char
- s/(?<!\\)((?:\\\\)*\\(?:[^\W_]|\s|$))/\\$1/g;
+sub _sql {
+ my $self = shift;
+ local $_ = $_[0];
# 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