1 package Regexp::Wildcards;
7 use Text::Balanced qw/extract_bracketed/;
11 Regexp::Wildcards - Converts wildcard expressions to Perl regular expressions.
19 use vars qw/$VERSION/;
26 use Regexp::Wildcards;
28 my $rw = Regexp::Wildcards->new(type => 'unix');
31 $re = $rw->convert('a{b?,c}*'); # Do it Unix shell style.
32 $re = $rw->convert('a?,b*', 'win32'); # Do it Windows shell style.
33 $re = $rw->convert('*{x,y}?', 'jokers'); # Process the jokers and escape the rest.
34 $re = $rw->convert('%a_c%', 'sql'); # Turn SQL wildcards into regexps.
36 $rw = Regexp::Wildcards->new(
37 do => [ qw/jokers brackets/ ], # Do jokers and brackets.
38 capture => [ qw/any greedy/ ], # Capture *'s greedily.
41 $rw->do(add => 'groups'); # Don't escape groups.
42 $rw->capture(rem => [ qw/greedy/ ]); # Actually we want non-greedy matches.
43 $re = $rw->convert('*a{,(b)?}?c*'); # '(.*?)a(?:|(b).).c(.*?)'
44 $rw->capture(); # No more captures.
48 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.
50 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.
52 Typesets that mimic the behaviour of Windows and Unix shells are also provided.
59 croak 'First argument isn\'t a valid ' . __PACKAGE__ . ' object'
60 unless ref $_[0] and $_[0]->isa(__PACKAGE__);
64 jokers => [ qw/jokers/ ],
66 commas => [ qw/commas/ ],
67 brackets => [ qw/brackets/ ],
68 unix => [ qw/jokers brackets/ ],
69 win32 => [ qw/jokers commas/ ],
71 $types{$_} = $types{win32} for qw/dos os2 MSWin32 cygwin/;
82 single => sub { $_[1] ? '(.)' : '.' },
83 any => sub { $_[1] ? ($_[0]->{greedy} ? '(.*)'
86 brackets => sub { $_[1] ? '(' : '(?:'; },
95 $old = { } unless defined $old;
98 $c = { set => $_[0] };
100 croak 'Arguments must be passed as an unique scalar or as key => value pairs';
103 $c = { map { (exists $args{$_}) ? ($_ => $args{$_}) : () } qw/set add rem/ };
105 for (qw/set add rem/) {
107 next unless defined $v;
109 '' => sub { +{ ($_[0] => 1) x (exists $valid->{$_[0]}) } },
110 'ARRAY' => sub { +{ map { ($_ => 1) x (exists $valid->{$_}) } @{$_[0]} } },
111 'HASH' => sub { +{ map { ($_ => $_[0]->{$_}) x (exists $valid->{$_}) }
114 croak 'Wrong option set' unless $cb;
115 $c->{$_} = $cb->($v);
117 my $config = (exists $c->{set}) ? $c->{set} : $old;
118 $config->{$_} = $c->{add}->{$_} for grep $c->{add}->{$_},
119 keys %{$c->{add} || {}};
120 delete $config->{$_} for grep $c->{rem}->{$_}, keys %{$c->{rem} || {}};
127 $config->{do} = $self->_validate(\%escapes, $self->{do}, @_);
128 $config->{escape} = '';
129 $config->{escape} .= $escapes{$_} for keys %{$config->{do}};
130 $config->{escape} = quotemeta $config->{escape};
137 my $config = $self->_do(@_);
138 $self->{$_} = $config->{$_} for keys %$config;
145 $config->{capture} = $self->_validate(\%captures, $self->{capture}, @_);
146 $config->{greedy} = delete $config->{capture}->{greedy};
147 for (keys %captures) {
148 $config->{'c_' . $_} = $captures{$_}->($config, $config->{capture}->{$_})
149 if $captures{$_}; # Skip 'greedy'
157 my $config = $self->_capture(@_);
158 $self->{$_} = $config->{$_} for keys %$config;
163 my ($self, $type) = @_;
164 $type = 'unix' unless defined $type;
165 croak 'Wrong type' unless exists $types{$type};
166 my $config = $self->_do($types{$type});
167 $config->{type} = $type;
174 my $config = $self->_type(@_);
175 $self->{$_} = $config->{$_} for keys %$config;
181 $class = ref($class) || $class || __PACKAGE__;
182 croak 'Optional arguments must be passed as key => value pairs' if @_ % 2;
186 if (defined $args{do}) {
187 $self->do($args{do});
189 $self->type($args{type});
191 $self->capture($args{capture});
194 =head2 C<< new [ do => $what E<verbar> type => $type ], capture => $captures >>
196 Constructs a new L<Regexp::Wildcard> object.
198 C<do> lists all features that should be enabled when converting wildcards to regexps. Refer to L</do> for details on what can be passed in C<$what>.
200 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>.
202 C<capture> lists which atoms should be capturing. Refer to L</capture> for more details.
204 =head2 C<< do [ $what E<verbar> set => $c1, add => $c2, rem => $c3 ] >>
206 Specifies the list of metacharacters to convert.
207 They are classified into five classes :
213 C<'jokers'> converts C<?> to C<.> and C<*> to C<.*> ;
215 'a**\\*b??\\?c' ==> 'a.*\\*b..\\?c'
219 C<'sql'> converts C<_> to C<.> and C<%> to C<.*> ;
221 'a%%\\%b__\\_c' ==> 'a.*\\%b..\\_c'
225 C<'commas'> converts all C<,> to C<|> and puts the complete resulting regular expression inside C<(?: ... )> ;
227 'a,b{c,d},e' ==> '(?:a|b\\{c|d\\}|e)'
231 C<'brackets'> converts all matching C<{ ... , ... }> brackets to C<(?: ... | ... )> alternations. If some brackets are unbalanced, it tries to substitute as many of them as possible, and then escape the remaining unmatched C<{> and C<}>. Commas outside of any bracket-delimited block are also escaped ;
233 'a,b{c,d},e' ==> 'a\\,b(?:c|d)\\,e'
234 '{a\\{b,c}d,e}' ==> '(?:a\\{b|c)d\\,e\\}'
235 '{a{b,c\\}d,e}' ==> '\\{a\\{b\\,c\\}d\\,e\\}'
239 C<'groups'> keeps the parenthesis C<( ... )> of the original string without escaping them. Currently, no check is done to ensure that the parenthesis are matching.
241 'a(b(c))d\\(\\)' ==> (no change)
245 Each C<$c> can be any of :
251 A hash reference, with wanted metacharacter group names (described above) as keys and booleans as values ;
255 An array reference containing the list of wanted metacharacter classes ;
259 A plain scalar, when only one group is required.
263 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.
265 Passing a sole scalar C<$what> is equivalent as passing C<< set => $what >>.
266 No argument means C<< set => [ ] >>.
268 $rw->do(set => 'jokers'); # Only translate jokers.
269 $rw->do('jokers'); # Same.
270 $rw->do(add => [ qw/sql commas/ ]); # Translate also SQL and commas.
271 $rw->do(rem => 'jokers'); # Specifying both 'sql' and 'jokers' is useless.
272 $rw->do(); # Translate nothing.
276 Notifies to convert the metacharacters that corresponds to the predefined type C<$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.
278 $rw->type('win32'); # Set type to win32.
279 $rw->type(); # Set type to unix.
281 =head2 C<< capture [ $captures E<verbar> set => $c1, add => $c2, rem => $c3 ] >>
283 Specifies the list of atoms to capture.
284 This method works like L</do>, except that the classes are different :
290 C<'single'> will capture all unescaped I<"exactly one"> metacharacters, i.e. C<?> for wildcards or C<_> for SQL ;
292 'a???b\\??' ==> 'a(.)(.)(.)b\\?(.)'
293 'a___b\\__' ==> 'a(.)(.)(.)b\\_(.)'
297 C<'any'> will capture all unescaped I<"any"> metacharacters, i.e. C<*> for wildcards or C<%> for SQL ;
299 'a***b\\**' ==> 'a(.*)b\\*(.*)'
300 'a%%%b\\%%' ==> 'a(.*)b\\%(.*)'
304 C<'greedy'>, when used in conjunction with C<'any'>, will make the C<'any'> captures greedy (by default they are not) ;
306 'a***b\\**' ==> 'a(.*?)b\\*(.*?)'
307 'a%%%b\\%%' ==> 'a(.*?)b\\%(.*?)'
311 C<'brackets'> will capture matching C<{ ... , ... }> alternations.
313 'a{b\\},\\{c}' ==> 'a(b\\}|\\{c)'
317 $rw->capture(set => 'single'); # Only capture "exactly one" metacharacters.
318 $rw->capture('single'); # Same.
319 $rw->capture(add => [ qw/any greedy/ ]); # Also greedily capture "any" metacharacters.
320 $rw->capture(rem => 'greedy'); # No more greed please.
321 $rw->capture(); # Capture nothing.
323 =head2 C<convert $wc [ , $type ]>
325 Converts the wildcard expression C<$wc> into a regular expression according to the options stored into the L<Regexp::Wildcards> object, or to C<$type> if it's supplied. It successively escapes all unprotected regexp special characters that doesn't hold any meaning for wildcards, then replace C<'jokers'> or C<'sql'> and C<'commas'> or C<'brackets'> (depending on the L</do> or L</type> options), all of this by applying the C<'capture'> rules specified in the constructor or by L</capture>.
330 my ($self, $wc, $type) = @_;
334 $config = $self->_type($type);
338 return unless defined $wc;
339 my $do = $config->{do};
340 my $e = $config->{escape};
341 $wc =~ s/(?<!\\)((?:\\\\)*[^\w\s\\$e])/\\$1/g;
343 $wc = $self->_jokers($wc);
344 } elsif ($do->{sql}) {
345 $wc = $self->_sql($wc);
347 if ($do->{brackets}) {
348 $wc = $self->_bracketed($wc);
349 } elsif ($do->{commas}) {
350 if ($wc =~ /(?<!\\)(?:\\\\)*,/) { # win32 allows comma-separated lists
351 $wc = $self->{'c_brackets'} . $self->_commas($wc) . ')';
359 An object module shouldn't export any function, and so does this one.
363 L<Carp> (core module since perl 5), L<Text::Balanced> (since 5.7.3).
367 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.
371 Vincent Pit, C<< <perl at profvince.com> >>, L<http://www.profvince.com>.
373 You can contact me by mail or on #perl @ FreeNode (vincent or Prof_Vince).
377 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.
381 You can find documentation for this module with the perldoc command.
383 perldoc Regexp::Wildcards
385 Tests code coverage report is available at L<http://www.profvince.com/perl/cover/Regexp-Wildcards>.
387 =head1 COPYRIGHT & LICENSE
389 Copyright 2007-2008 Vincent Pit, all rights reserved.
391 This program is free software; you can redistribute it and/or modify it
392 under the same terms as Perl itself.
396 sub _extract ($) { extract_bracketed $_[0], '{', qr/.*?(?<!\\)(?:\\\\)*(?={)/ }
401 # escape an odd number of \ that doesn't protect a regexp/wildcard special char
402 s/(?<!\\)((?:\\\\)*\\(?:[\w\s]|$))/\\$1/g;
403 # substitute ? preceded by an even number of \
404 my $s = $self->{c_single};
405 s/(?<!\\)((?:\\\\)*)\?/$1$s/g;
406 # substitute * preceded by an even number of \
408 s/(?<!\\)((?:\\\\)*)\*+/$1$s/g;
415 # escape an odd number of \ that doesn't protect a regexp/wildcard special char
416 s/(?<!\\)((?:\\\\)*\\(?:[^\W_]|\s|$))/\\$1/g;
417 # substitute _ preceded by an even number of \
418 my $s = $self->{c_single};
419 s/(?<!\\)((?:\\\\)*)_/$1$s/g;
420 # substitute % preceded by an even number of \
422 s/(?<!\\)((?:\\\\)*)%+/$1$s/g;
428 # substitute , preceded by an even number of \
429 s/(?<!\\)((?:\\\\)*),/$1|/g;
434 my ($self, $rest) = @_;
435 substr $rest, 0, 1, '';
437 my ($re, $bracket, $prefix) = ('');
438 while (do { ($bracket, $rest, $prefix) = _extract $rest; $bracket }) {
439 $re .= $self->_commas($prefix) . $self->_brackets($bracket);
441 $re .= $self->_commas($rest);
442 return $self->{c_brackets} . $re . ')';
446 my ($self, $rest) = @_;
447 my ($re, $bracket, $prefix) = ('');
448 while (do { ($bracket, $rest, $prefix) = _extract $rest; $bracket }) {
449 $re .= $prefix . $self->_brackets($bracket);
452 $re =~ s/(?<!\\)((?:\\\\)*[\{\},])/\\$1/g;
456 1; # End of Regexp::Wildcards