1 package Regexp::Wildcards;
7 use Text::Balanced qw/extract_bracketed/;
11 Regexp::Wildcards - Converts wildcard expressions to Perl regular expressions.
19 our $VERSION = '0.08';
23 use Regexp::Wildcards;
25 my $rw = Regexp::Wildcards->new(type => 'unix');
28 $re = $rw->convert('a{b?,c}*'); # Do it Unix shell style.
29 $re = $rw->convert('a?,b*', 'win32'); # Do it Windows shell style.
30 $re = $rw->convert('*{x,y}?', 'jokers'); # Process the jokers and escape the rest.
31 $re = $rw->convert('%a_c%', 'sql'); # Turn SQL wildcards into regexps.
33 $rw = Regexp::Wildcards->new(
34 do => [ qw/jokers brackets/ ], # Do jokers and brackets.
35 capture => [ qw/any greedy/ ], # Capture *'s greedily.
38 $rw->do(add => 'groups'); # Don't escape groups.
39 $rw->capture(rem => [ qw/greedy/ ]); # Actually we want non-greedy matches.
40 $re = $rw->convert('*a{,(b)?}?c*'); # '(.*?)a(?:|(b).).c(.*?)'
41 $rw->capture(); # No more captures.
45 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.
47 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.
49 Typesets that mimic the behaviour of Windows and Unix shells are also provided.
56 croak 'First argument isn\'t a valid ' . __PACKAGE__ . ' object'
57 unless ref $_[0] and $_[0]->isa(__PACKAGE__);
61 jokers => [ qw/jokers/ ],
63 commas => [ qw/commas/ ],
64 brackets => [ qw/brackets/ ],
65 unix => [ qw/jokers brackets/ ],
66 win32 => [ qw/jokers commas/ ],
68 $types{$_} = $types{win32} for qw/dos os2 MSWin32 cygwin/;
79 single => sub { $_[1] ? '(.)' : '.' },
80 any => sub { $_[1] ? ($_[0]->{greedy} ? '(.*)'
83 brackets => sub { $_[1] ? '(' : '(?:'; },
92 $old = { } unless defined $old;
95 $c = { set => $_[0] };
97 croak 'Arguments must be passed as an unique scalar or as key => value pairs';
100 $c = { map { (exists $args{$_}) ? ($_ => $args{$_}) : () } qw/set add rem/ };
102 for (qw/set add rem/) {
104 next unless defined $v;
106 '' => sub { +{ ($_[0] => 1) x (exists $valid->{$_[0]}) } },
107 'ARRAY' => sub { +{ map { ($_ => 1) x (exists $valid->{$_}) } @{$_[0]} } },
108 'HASH' => sub { +{ map { ($_ => $_[0]->{$_}) x (exists $valid->{$_}) }
111 croak 'Wrong option set' unless $cb;
112 $c->{$_} = $cb->($v);
114 my $config = (exists $c->{set}) ? $c->{set} : $old;
115 $config->{$_} = $c->{add}->{$_} for grep $c->{add}->{$_},
116 keys %{$c->{add} || {}};
117 delete $config->{$_} for grep $c->{rem}->{$_}, keys %{$c->{rem} || {}};
124 $config->{do} = $self->_validate(\%escapes, $self->{do}, @_);
125 $config->{escape} = '';
126 $config->{escape} .= $escapes{$_} for keys %{$config->{do}};
127 $config->{escape} = quotemeta $config->{escape};
134 my $config = $self->_do(@_);
135 $self->{$_} = $config->{$_} for keys %$config;
142 $config->{capture} = $self->_validate(\%captures, $self->{capture}, @_);
143 $config->{greedy} = delete $config->{capture}->{greedy};
144 for (keys %captures) {
145 $config->{'c_' . $_} = $captures{$_}->($config, $config->{capture}->{$_})
146 if $captures{$_}; # Skip 'greedy'
154 my $config = $self->_capture(@_);
155 $self->{$_} = $config->{$_} for keys %$config;
160 my ($self, $type) = @_;
161 $type = 'unix' unless defined $type;
162 croak 'Wrong type' unless exists $types{$type};
163 my $config = $self->_do($types{$type});
164 $config->{type} = $type;
171 my $config = $self->_type(@_);
172 $self->{$_} = $config->{$_} for keys %$config;
178 $class = ref($class) || $class || __PACKAGE__;
179 croak 'Optional arguments must be passed as key => value pairs' if @_ % 2;
183 if (defined $args{do}) {
184 $self->do($args{do});
186 $self->type($args{type});
188 $self->capture($args{capture});
191 =head2 C<< new [ do => $what E<verbar> type => $type ], capture => $captures >>
193 Constructs a new L<Regexp::Wildcard> object.
195 C<do> lists all features that should be enabled when converting wildcards to regexps. Refer to L</do> for details on what can be passed in C<$what>.
197 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>.
199 C<capture> lists which atoms should be capturing. Refer to L</capture> for more details.
201 =head2 C<< do [ $what E<verbar> set => $c1, add => $c2, rem => $c3 ] >>
203 Specifies the list of metacharacters to convert.
204 They are classified into five classes :
208 =item C<'jokers'> converts C<?> to C<.> and C<*> to C<.*> ;
210 'a**\\*b??\\?c' ==> 'a.*\\*b..\\?c'
212 =item C<'sql'> converts C<_> to C<.> and C<%> to C<.*> ;
214 'a%%\\%b__\\_c' ==> 'a.*\\%b..\\_c'
216 =item C<'commas'> converts all C<,> to C<|> and puts the complete resulting regular expression inside C<(?: ... )> ;
218 'a,b{c,d},e' ==> '(?:a|b\\{c|d\\}|e)'
220 =item C<'brackets'> converts all matching C<{ ... , ... }> brackets to C<(?: ... | ... )> alternations. If some brackets are unbalanced, it tries to substitute as many of them as possible, and then escape the remaining unmatched C<{> and C<}>. Commas outside of any bracket-delimited block are also escaped ;
222 'a,b{c,d},e' ==> 'a\\,b(?:c|d)\\,e'
223 '{a\\{b,c}d,e}' ==> '(?:a\\{b|c)d\\,e\\}'
224 '{a{b,c\\}d,e}' ==> '\\{a\\{b\\,c\\}d\\,e\\}'
226 =item C<'groups'> keeps the parenthesis C<( ... )> of the original string without escaping them. Currently, no check is done to ensure that the parenthesis are matching.
228 'a(b(c))d\\(\\)' ==> (no change)
232 Each C<$c> can be any of :
236 =item A hash reference, with wanted metacharacter group names (described above) as keys and booleans as values ;
238 =item An array reference containing the list of wanted metacharacter classes ;
240 =item A plain scalar, when only one group is required.
244 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.
246 Passing a sole scalar C<$what> is equivalent as passing C<< set => $what >>.
247 No argument means C<< set => [ ] >>.
249 $rw->do(set => 'jokers'); # Only translate jokers.
250 $rw->do('jokers'); # Same.
251 $rw->do(add => [ qw/sql commas/ ]); # Translate also SQL and commas.
252 $rw->do(rem => 'jokers'); # Specifying both 'sql' and 'jokers' is useless.
253 $rw->do(); # Translate nothing.
257 Notifies to convert the metacharacters that corresponds to the predefined type C<$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.
259 $rw->type('win32'); # Set type to win32.
260 $rw->type(); # Set type to unix.
262 =head2 C<< capture [ $captures E<verbar> set => $c1, add => $c2, rem => $c3 ] >>
264 Specifies the list of atoms to capture.
265 This method works like L</do>, except that the classes are different :
269 =item C<'single'> will capture all unescaped I<"exactly one"> metacharacters, i.e. C<?> for wildcards or C<_> for SQL ;
271 'a???b\\??' ==> 'a(.)(.)(.)b\\?(.)'
272 'a___b\\__' ==> 'a(.)(.)(.)b\\_(.)'
274 =item C<'any'> will capture all unescaped I<"any"> metacharacters, i.e. C<*> for wildcards or C<%> for SQL ;
276 'a***b\\**' ==> 'a(.*)b\\*(.*)'
277 'a%%%b\\%%' ==> 'a(.*)b\\%(.*)'
279 =item C<'greedy'>, when used in conjunction with C<'any'>, will make the C<'any'> captures greedy (by default they are not) ;
281 'a***b\\**' ==> 'a(.*?)b\\*(.*?)'
282 'a%%%b\\%%' ==> 'a(.*?)b\\%(.*?)'
284 =item C<'brackets'> will capture matching C<{ ... , ... }> alternations.
286 'a{b\\},\\{c}' ==> 'a(b\\}|\\{c)'
290 $rw->capture(set => 'single'); # Only capture "exactly one" metacharacters.
291 $rw->capture('single'); # Same.
292 $rw->capture(add => [ qw/any greedy/ ]); # Also greedily capture "any" metacharacters.
293 $rw->capture(rem => 'greedy'); # No more greed please.
294 $rw->capture(); # Capture nothing.
296 =head2 C<convert $wc [ , $type ]>
298 Converts the wildcard expression C<$wc> into a regular expression according to the options stored into the L<Regexp::Wildcards> object, or to C<$type> if it's supplied. It successively escapes all unprotected regexp special characters that doesn't hold any meaning for wildcards, then replace C<'jokers'> or C<'sql'> and C<'commas'> or C<'brackets'> (depending on the L</do> or L</type> options), all of this by applying the C<'capture'> rules specified in the constructor or by L</capture>.
303 my ($self, $wc, $type) = @_;
307 $config = $self->_type($type);
311 return unless defined $wc;
312 my $do = $config->{do};
313 my $e = $config->{escape};
314 $wc =~ s/(?<!\\)((?:\\\\)*[^\w\s\\$e])/\\$1/g;
315 return $self->_sql($wc) if $do->{sql};
316 $wc = $self->_jokers($wc) if $do->{jokers};
317 if ($do->{brackets}) {
318 $wc = $self->_bracketed($wc);
319 } elsif ($do->{commas}) {
320 if ($wc =~ /(?<!\\)(?:\\\\)*,/) { # win32 allows comma-separated lists
321 $wc = $self->{'c_brackets'} . $self->_commas($wc) . ')';
329 An object module shouldn't export any function, and so does this one.
333 L<Text::Balanced>, which is bundled with perl since version 5.7.3
337 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.
341 Vincent Pit, C<< <perl at profvince.com> >>, L<http://www.profvince.com>.
343 You can contact me by mail or on #perl @ FreeNode (vincent or Prof_Vince).
347 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.
351 You can find documentation for this module with the perldoc command.
353 perldoc Regexp::Wildcards
355 Tests code coverage report is available at L<http://www.profvince.com/perl/cover/Regexp-Wildcards>.
357 =head1 COPYRIGHT & LICENSE
359 Copyright 2007-2008 Vincent Pit, all rights reserved.
361 This program is free software; you can redistribute it and/or modify it
362 under the same terms as Perl itself.
366 sub _extract ($) { extract_bracketed $_[0], '{', qr/.*?(?<!\\)(?:\\\\)*(?={)/ }
371 # escape an odd number of \ that doesn't protect a regexp/wildcard special char
372 s/(?<!\\)((?:\\\\)*\\(?:[\w\s]|$))/\\$1/g;
373 # substitute ? preceded by an even number of \
374 my $s = $self->{c_single};
375 s/(?<!\\)((?:\\\\)*)\?/$1$s/g;
376 # substitute * preceded by an even number of \
378 s/(?<!\\)((?:\\\\)*)\*+/$1$s/g;
385 # escape an odd number of \ that doesn't protect a regexp/wildcard special char
386 s/(?<!\\)((?:\\\\)*\\(?:[^\W_]|\s|$))/\\$1/g;
387 # substitute _ preceded by an even number of \
388 my $s = $self->{c_single};
389 s/(?<!\\)((?:\\\\)*)_/$1$s/g;
390 # substitute % preceded by an even number of \
392 s/(?<!\\)((?:\\\\)*)%+/$1$s/g;
398 # substitute , preceded by an even number of \
399 s/(?<!\\)((?:\\\\)*),/$1|/g;
404 my ($self, $rest) = @_;
405 substr $rest, 0, 1, '';
407 my ($re, $bracket, $prefix) = ('');
408 while (do { ($bracket, $rest, $prefix) = _extract $rest; $bracket }) {
409 $re .= $self->_commas($prefix) . $self->_brackets($bracket);
411 $re .= $self->_commas($rest);
412 return $self->{c_brackets} . $re . ')';
416 my ($self, $rest) = @_;
417 my ($re, $bracket, $prefix) = ('');
418 while (do { ($bracket, $rest, $prefix) = _extract $rest; $bracket }) {
419 $re .= $prefix . $self->_brackets($bracket);
422 $re =~ s/(?<!\\)((?:\\\\)*[\{\},])/\\$1/g;
426 1; # End of Regexp::Wildcards