README
samples/wc2re.pl
t/00-load.t
-t/01-import.t
-t/02-wc2re.t
-t/10-jokers.t
-t/11-commas.t
-t/12-brackets.t
+t/02-can.t
+t/10-obj.t
+t/11-opts.t
+t/20-jokers.t
+t/21-commas.t
+t/22-brackets.t
+t/23-groups.t
t/90-boilerplate.t
t/91-pod.t
t/92-pod-coverage.t
use strict;
use warnings;
+use Carp qw/croak/;
use Text::Balanced qw/extract_bracketed/;
=head1 NAME
=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.
+
+ $rw = Regexp::Wildcards->new(
+ do => [ qw/jokers brackets/ ], # Do jokers and brackets.
+ capture => [ qw/any greedy/ ], # Capture *'s greedily.
+ );
+
+ $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 DESCRIPTION
-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.
+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. It can also keep original C<(...)> groups. Backspace (C<\>) is used as an escape character.
+
+Typesets that mimic the behaviour of Windows and Unix shells are also provided.
+
+=head1 METHODS
-=head1 VARIABLES
+=cut
+
+sub _check_self {
+ croak 'First argument isn\'t a valid ' . __PACKAGE__ . ' object'
+ unless ref $_[0] and $_[0]->isa(__PACKAGE__);
+}
+
+my %types = (
+ jokers => [ qw/jokers/ ],
+ sql => [ qw/sql/ ],
+ commas => [ qw/commas/ ],
+ brackets => [ qw/brackets/ ],
+ unix => [ qw/jokers brackets/ ],
+ win32 => [ qw/jokers commas/ ],
+);
+$types{$_} = $types{win32} for qw/dos os2 MSWin32 cygwin/;
+
+my %escapes = (
+ jokers => '?*',
+ sql => '%_',
+ commas => ',',
+ brackets => '{},',
+ groups => '()',
+);
-These variables control if the wildcards jokers and brackets must capture their match. They can be globally set by writing in your program
+my %captures = (
+ single => sub { $_[1] ? '(.)' : '.' },
+ any => sub { $_[1] ? ($_[0]->{greedy} ? '(.*)'
+ : '(.*?)')
+ : '.*' },
+ brackets => sub { $_[1] ? '(' : '(?:'; },
+ greedy => undef
+);
- $Regexp::Wildcards::CaptureSingle = 1;
- # From then, "exactly one" wildcards are capturing
+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;
+}
-or can be locally specified via C<local>
+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;
+}
- {
- local $Regexp::Wildcards::CaptureSingle = 1;
- # In this block, "exactly one" wildcards are capturing.
- ...
- }
- # Back to the situation from before the block
+sub do {
+ my $self = shift;
+ _check_self $self;
+ my $config = $self->_do(@_);
+ $self->{$_} = $config->{$_} for keys %$config;
+ $self;
+}
-This section describes also how those elements are translated by the L<functions|/FUNCTIONS>.
+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;
+}
+
+sub capture {
+ my $self = shift;
+ _check_self $self;
+ my $config = $self->_capture(@_);
+ $self->{$_} = $config->{$_} for keys %$config;
+ $self;
+}
+
+sub _type {
+ my ($self, $type) = @_;
+ $type = 'unix' unless defined $type;
+ croak 'Wrong type' unless exists $types{$type};
+ my $config = $self->_do($types{$type});
+ $config->{type} = $type;
+ $config;
+}
+
+sub type {
+ my $self = shift;
+ _check_self $self;
+ my $config = $self->_type(@_);
+ $self->{$_} = $config->{$_} for keys %$config;
+ $self;
+}
+
+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<< new [ do => $what | type => $type ], capture => $captures >>
+
+Constructs a new L<Regexp::Wildcard> object.
+
+C<do> lists all features that should be enabled when converting wildcards to regexps. Refer to L</do> for details on what can be passed in C<$what>.
+
+The C<type> specifies a predefined set of C<do> features to use.
+
+
+C<$type> can be any of C<'jokers'>, C<'sql'>, C<'commas'>, C<'brackets'>, C<'win32'> or C<'unix'>. An unknown value defaults to C<'unix'>, except for C<'dos'>, C<'os2'>, C<'MSWin32'> and C<'cygwin'> that default to C<'win32'>. With this set of options, you can pass C<$^O> as the C<$type> so that you get the corresponding shell behaviour.
+
+=over 4
+
+=item C<>
+
+For the C<$capture> syntax, refer to the L</capture> method.
+
+=head3 C<type>
+
+=head3 C<capture>
+
+=over 4
=head2 C<$CaptureSingle>
'a___b\\__' is translated to 'a(.)(.)(.)b\\_(.)' if $CaptureSingle is true
'a...b\\_.' otherwise (default)
-=cut
-
-our $CaptureSingle = 0;
-sub capture_single {
- return $CaptureSingle ? '(.)'
- : '.';
-}
-
-=head2 C<$CaptureAny>
+=item C<any>
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<(.*?)>).
'a(.*)b\\%(.*)' if $CaptureAny > 0
'a(.*?)b\\%(.*?)' otherwise
-=cut
-
-our $CaptureAny = 0;
-
-sub capture_any {
- return $CaptureAny ? (($CaptureAny > 0) ? '(.*)'
- : '(.*?)')
- : '.*';
-}
-
-=head2 C<$CaptureBrackets>
+=item C<brackets>
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.
'a{b\\},\\{c}' is translated to 'a(b\\}|\\{c)' if $CaptureBrackets is true
'a(?:b\\}|\\{c)' otherwise (default)
-=cut
-
-our $CaptureBrackets = 0;
-
-sub capture_brackets {
- return $CaptureBrackets ? '('
- : '(?:';
-}
-
-=head1 FUNCTIONS
+=back
-=head2 C<wc2re_jokers>
+=head2 C<jokers>
This function takes as its only argument the wildcard string to process, and returns the corresponding regular expression where the jokers C<?> (I<"exactly one">) and C<*> (I<"any">) have been translated into their regexp equivalents (see L</VARIABLES> for more details). All other unprotected regexp metacharacters are escaped.
=cut
-sub wc2re_jokers {
- my ($wc) = @_;
- $wc =~ s/(?<!\\)((?:\\\\)*[^\w\s?*\\])/\\$1/g;
- return do_jokers($wc);
-}
-
-=head2 C<wc2re_sql>
+=head2 C<sql>
Similar to the precedent, but for the SQL wildcards C<_> (I<"exactly one">) and C<%> (I<"any">). All other unprotected regexp metacharacters are escaped.
=cut
-sub wc2re_sql {
- my ($wc) = @_;
- $wc =~ s/(?<!\\)((?:\\\\)*[^\w\s%\\])/\\$1/g;
- return do_sql($wc);
-}
-
-=head2 C<wc2re_unix>
+=head2 C<shell>
This function conforms to standard Unix shell wildcard rules. It successively escapes all unprotected regexp special characters that doesn't hold any meaning for wildcards, turns C<?> and C<*> jokers into their regexp equivalents (see L</wc2re_jokers>), and changes bracketed blocks into (possibly capturing) alternations as described in L</VARIABLES>. If brackets are unbalanced, it tries to substitute as many of them as possible, and then escape the remaining C<{> and C<}>. Commas outside of any bracket-delimited block are also escaped.
# All the brackets and commas are escaped.
print 'ok' if wc2re_unix('{a{b,c\\}d,e}') eq '\\{a\\{b\\,c\\}d\\,e\\}';
-=cut
-
-sub wc2re_unix {
- my ($re) = @_;
- return unless defined $re;
- $re =~ s/(?<!\\)((?:\\\\)*[^\w\s?*\\\{\},])/\\$1/g;
- return do_bracketed(do_jokers($re));
-}
-
-=head2 C<wc2re_win32>
-
This one works just like the one before, but for Windows wildcards. Bracketed blocks are no longer handled (which means that brackets are escaped), but you can provide a comma-separated list of items.
# All the brackets are escaped, and commas are seen as list delimiters.
=cut
-sub wc2re_win32 {
- my ($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;
-}
-
-=head2 C<wc2re>
+=head2 C<convert>
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 :
=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
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;
use strict;
use warnings;
-use Regexp::Wildcards qw/wc2re/;
+use lib qw{blib/lib};
-my $type = (grep $^O eq $_, qw/dos os2 MSWin32 cygwin/) ? 'win32' : 'unix';
-print "For this system, type is $type\n";
+use Regexp::Wildcards;
+use Data::Dumper;
-{
- local $Regexp::Wildcards::CaptureBrackets = 1;
- local $Regexp::Wildcards::CaptureAny = -1;
- print $_, ' => ', wc2re($_ => $^O), "\n" for @ARGV;
-}
+my $rw = Regexp::Wildcards->new(
+ do => [ qw/brackets/ ],
+ capture => [ qw/single/ ],
+);
+use Data::Dumper;
+print Dumper($rw);
+
+$rw->capture(add => [ qw/brackets any greedy/ ]);
+print Dumper($rw);
+
+print $_, ' => ', $rw->convert($_), "\n" for @ARGV;
+++ /dev/null
-#!perl -T
-
-use strict;
-use warnings;
-
-use Test::More tests => 5;
-
-require Regexp::Wildcards;
-
-for (qw/wc2re_jokers wc2re_sql wc2re_unix wc2re_win32 wc2re/) {
- eval { Regexp::Wildcards->import($_) };
- ok(!$@, 'import ' . $_);
-}
--- /dev/null
+#!perl -T
+
+use strict;
+use warnings;
+
+use Test::More tests => 5;
+
+require Regexp::Wildcards;
+
+for (qw/new do capture type convert/) {
+ ok(Regexp::Wildcards->can($_), 'RW can ' . $_);
+}
+
+++ /dev/null
-#!perl -T
-
-use strict;
-use warnings;
-
-use Test::More tests => 10;
-
-use Regexp::Wildcards qw/wc2re wc2re_win32/;
-
-for my $O (qw/win32 dos os2 cygwin/, 'MSWin32') {
- for ('a{b,c}*', 'a?{b\\{,\\}c}') {
- ok(wc2re($_, $O) eq wc2re_win32($_), $_ . ' (' . $O . ')');
- }
-}
+++ /dev/null
-#!perl -T
-
-use strict;
-use warnings;
-
-use Test::More tests => 4 * (4 + 2 + 7 + 9 + 2) * 3;
-
-use Regexp::Wildcards qw/wc2re/;
-
-sub try {
- my ($t, $s, $x, $y) = @_;
- $y = $x unless defined $y;
- ok(wc2re('ab' . $x, $t) eq 'ab' . $y, $s . ' (begin) ['.$t.']');
- ok(wc2re('a' . $x . 'b', $t) eq 'a' . $y . 'b', $s . ' (middle) ['.$t.']');
- ok(wc2re($x . 'ab', $t) eq $y . 'ab', $s . ' (end) ['.$t.']');
-}
-
-sub alltests {
- my ($t, $one, $any) = @_;
-
- # Simple
-
- try $t, "simple $any", $any, '.*';
- try $t, "simple $one", $one, '.';
-
- ok(wc2re($one.$any.'ab', $t) eq '..*ab',
- "simple $one and $any (begin) [$t]");
- ok(wc2re($one.'a'.$any.'b', $t) eq '.a.*b',
- "simple $one and $any (middle) [$t]");
- ok(wc2re($one.'ab'.$any, $t) eq '.ab.*',
- "simple $one and $any (end) [$t]");
-
- ok(wc2re($any.'ab'.$one, $t) eq '.*ab.',
- "simple $any and $one (begin) [$t]");
- ok(wc2re('a'.$any.'b'.$one, $t) eq 'a.*b.',
- "simple $any and $one (middle) [$t]");
- ok(wc2re('ab'.$any.$one, $t) eq 'ab.*.',
- "simple $any and $one (end) [$t]");
-
- # Multiple
-
- try $t, "multiple $any", $any x 2, '.*';
- try $t, "multiple $one", $one x 2, '..';
-
- # Variables
-
- {
- local $Regexp::Wildcards::CaptureSingle = 1;
- try $t, "multiple capturing $one", $one.$one.'\\'.$one.$one,
- '(.)(.)\\'.$one.'(.)';
-
- local $Regexp::Wildcards::CaptureAny = 1;
- try $t, "multiple capturing $any (greedy)", $any.$any.'\\'.$any.$any,
- '(.*)\\'.$any.'(.*)';
- my $wc = $any.$any.$one.$one.'\\'.$one.$one.'\\'.$any.$any;
- try $t, "multiple capturing $any (greedy) and capturing $one",
- $wc, '(.*)(.)(.)\\'.$one.'(.)\\'.$any.'(.*)';
-
- $Regexp::Wildcards::CaptureSingle = 0;
- try $t, "multiple capturing $any (greedy) and non-capturing $one",
- $wc, '(.*)..\\'.$one.'.\\'.$any.'(.*)';
-
- $Regexp::Wildcards::CaptureAny = -1;
- try $t, "multiple capturing $any (non-greedy)", $any.$any.'\\'.$any.$any,
- '(.*?)\\'.$any.'(.*?)';
- try $t, "multiple capturing $any (non-greedy) and non-capturing $one",
- $wc, '(.*?)..\\'.$one.'.\\'.$any.'(.*?)';
-
- $Regexp::Wildcards::CaptureSingle = 1;
- try $t, "multiple capturing $any (non-greedy) and capturing $one",
- $wc, '(.*?)(.)(.)\\'.$one.'(.)\\'.$any.'(.*?)';
- }
-
- # Escaping
-
- try $t, "escaping $any", '\\'.$any;
- try $t, "escaping $one", '\\'.$one;
- try $t, "escaping \\\\\\$any", '\\\\\\'.$any;
- try $t, "escaping \\\\\\$one", '\\\\\\'.$one;
-
- try $t, "not escaping \\\\$any", '\\\\'.$any, '\\\\.*';
- try $t, "not escaping \\\\$one", '\\\\'.$one, '\\\\.';
-
- try $t, 'escaping \\', '\\', '\\\\';
- try $t, 'escaping regex characters', '[]', '\\[\\]';
- try $t, 'not escaping escaped regex characters', '\\\\\\[\\]';
-
- # Mixed
-
- try $t, "mixed $any and \\$any", $any.'\\'.$any.$any, '.*\\'.$any.'.*';
- try $t, "mixed $one and \\$one", $one.'\\'.$one.$one, '.\\'.$one.'.';
-}
-
-alltests $_, '?', '*' for qw/jokers unix win32/;
-alltests 'sql', '_', '%';
--- /dev/null
+#!perl -T
+
+use strict;
+use warnings;
+
+use Test::More tests => 24;
+
+use Regexp::Wildcards;
+
+my $rw = Regexp::Wildcards->new;
+ok(defined $rw, 'RW object is defined');
+is(ref $rw, 'Regexp::Wildcards', 'RW object is valid');
+
+my $rw2 = $rw->new;
+ok(defined $rw2, 'RW::new called as an object method works' );
+is(ref $rw2, 'Regexp::Wildcards', 'RW::new called as an object method works is valid');
+
+$rw2 = Regexp::Wildcards::new();
+ok(defined $rw2, 'RW::new called without a class works');
+is(ref $rw2, 'Regexp::Wildcards', 'RW::new called without a class is valid');
+
+eval { $rw2 = Regexp::Wildcards->new(qw/a b c/) };
+like($@, qr/Optional\s+arguments/, 'RW::new gets parameters as key => value pairs');
+
+my $fake = { };
+bless $fake, 'Regexp::Wildcards::Hlagh';
+for (qw/do capture type convert/) {
+ eval "Regexp::Wildcards::$_('Regexp::Wildcards')";
+ like($@, qr/^First\s+argument/, "RW::$_ isn't a class method");
+ eval "Regexp::Wildcards::$_(\$fake)";
+ like($@, qr/^First\s+argument/, "RW::$_ only applies to RW objects");
+}
+
+for (qw/do capture/) {
+ eval { $rw->$_(sub { 'dongs' }) };
+ like($@, qr/Wrong\s+option\s+set/, "RW::$_ don't want code references");
+
+ eval { $rw->$_(\*STDERR) };
+ like($@, qr/Wrong\s+option\s+set/, "RW::$_ don't want globs");
+
+ eval { $rw->$_(qw/a b c/) };
+ like($@, qr/Arguments\s+must\s+be\s+passed.*unique\s+scalar.*key\s+=>\s+value\s+pairs/, "RW::$_ gets parameters after the first as key => value pairs");
+}
+
+eval { $rw->type('monkey!') };
+like($@, qr/Wrong\s+type/, 'RW::type wants a type it knows');
+
+eval { $rw->convert(undef, 'again monkey!') };
+like($@, qr/Wrong\s+type/, 'RW::convert wants a type it knows');
+
+for (qw/convert/) {
+ ok(!defined $rw->$_(undef), "RW::$_ returns undef when passed undef");
+}
+++ /dev/null
-#!perl -T
-
-use strict;
-use warnings;
-
-use Test::More tests => 8;
-
-use Regexp::Wildcards qw/wc2re_unix wc2re_win32/;
-
-ok(wc2re_unix('a,b,c') eq 'a\\,b\\,c', 'unix: commas outside of brackets 1');
-ok(wc2re_unix('a\\,b\\\\\\,c') eq 'a\\,b\\\\\\,c',
- 'unix: commas outside of brackets 2');
-ok(wc2re_unix(',a,b,c\\\\,') eq '\\,a\\,b\\,c\\\\\\,',
- 'unix: commas outside of brackets at begin/ed');
-
-ok(wc2re_win32('a,b\\\\,c') eq '(?:a|b\\\\|c)', 'win32: commas');
-ok(wc2re_win32('a\\,b\\\\,c') eq '(?:a\\,b\\\\|c)', 'win32: escaped commas 1');
-ok(wc2re_win32('a\\,b\\\\\\,c') eq 'a\\,b\\\\\\,c', 'win32: escaped commas 2');
-
-ok(wc2re_win32(',a,b\\\\,') eq '(?:|a|b\\\\|)', 'win32: commas at begin/end');
-ok(wc2re_win32('\\,a,b\\\\\\,') eq '(?:\\,a|b\\\\\\,)',
- 'win32: escaped commas at begin/end');
--- /dev/null
+#!perl -T
+
+use strict;
+use warnings;
+
+use Test::More tests => 8;
+
+use Regexp::Wildcards;
+
+my $rw = Regexp::Wildcards->new();
+
+my $wc = 'a,b{c,d}e*f?(g)';
+my $none = quotemeta $wc;
+my $unix = 'a\\,b(?:c|d)e.*f.\\(g\\)';
+my $win32 = '(?:a|b\{c|d\}e.*f.\\(g\\))';
+my $jokers = 'a\\,b\\{c\\,d\\}e.*f.\\(g\\)';
+my $groups = 'a\\,b\\{c\\,d\\}e\\*f\\?(g)';
+my $jok_gr = 'a\\,b\\{c\\,d\\}e.*f.(g)';
+
+is($rw->convert($wc), $unix, 'nothing defaults to unix');
+$rw->type('win32');
+is($rw->convert($wc), $win32, 'set to win32');
+$rw->type();
+is($rw->convert($wc), $unix, 'reset to unix');
+
+$rw = Regexp::Wildcards->new(do => [ qw/jokers/ ], type => 'win32');
+is($rw->convert($wc), $jokers, 'do overrides type in new');
+$rw->do(add => 'groups');
+is($rw->convert($wc), $jok_gr, 'added groups to jokers');
+$rw->do(add => 'jokers');
+is($rw->convert($wc), $jok_gr, 'added jokers but it already exists');
+$rw->do(rem => 'jokers');
+is($rw->convert($wc), $groups, 'removed jokers, only groups remains');
+$rw->do();
+is($rw->convert($wc), $none, 'reset do');
+++ /dev/null
-#!perl -T
-
-use strict;
-use warnings;
-
-use Test::More tests => 27;
-
-use Regexp::Wildcards qw/wc2re_jokers wc2re_sql wc2re_unix wc2re_win32/;
-
-ok(wc2re_jokers('a{b\\\\,c\\\\}d') eq 'a\\{b\\\\\\,c\\\\\\}d', 'wc2re_jokers');
-
-ok(wc2re_sql('a{b\\\\,c\\\\}d') eq 'a\\{b\\\\\\,c\\\\\\}d', 'wc2re_sql');
-
-ok(wc2re_win32('a{b\\\\,c\\\\}d') eq '(?:a\\{b\\\\|c\\\\\\}d)', 'wc2re_win32');
-
-ok(wc2re_unix('{}') eq '(?:)', 'empty brackets');
-ok(wc2re_unix('{a}') eq '(?:a)', 'brackets 1');
-ok(wc2re_unix('{a,b}') eq '(?:a|b)', 'brackets 2');
-ok(wc2re_unix('{a,b,c}') eq '(?:a|b|c)', 'brackets 3');
-
-ok(wc2re_unix('a{b,c}d') eq 'a(?:b|c)d',
- '1 bracketed block');
-ok(wc2re_unix('a{b,c}d{e,,f}') eq 'a(?:b|c)d(?:e||f)',
- '2 bracketed blocks');
-ok(wc2re_unix('a{b,c}d{e,,f}{g,h,}') eq 'a(?:b|c)d(?:e||f)(?:g|h|)',
- '3 bracketed blocks');
-
-ok(wc2re_unix('{a{b}}') eq '(?:a(?:b))',
- '2 nested bracketed blocks 1');
-ok(wc2re_unix('{a,{b},c}') eq '(?:a|(?:b)|c)',
- '2 nested bracketed blocks 2');
-ok(wc2re_unix('{a,{b{d}e},c}') eq '(?:a|(?:b(?:d)e)|c)',
- '3 nested bracketed blocks');
-ok(wc2re_unix('{a,{b{d{}}e,f,,},c}') eq '(?:a|(?:b(?:d(?:))e|f||)|c)',
- '4 nested bracketed blocks');
-ok(wc2re_unix('{a,{b{d{}}e,f,,},c}{,g{{}h,i}}') eq '(?:a|(?:b(?:d(?:))e|f||)|c)(?:|g(?:(?:)h|i))',
- '4+3 nested bracketed blocks');
-
-ok(wc2re_unix('\\{\\\\}') eq '\\{\\\\\\}',
- 'escaping brackets');
-ok(wc2re_unix('\\{a,b,c\\\\\\}') eq '\\{a\\,b\\,c\\\\\\}',
- 'escaping commas 1');
-ok(wc2re_unix('\\{a\\\\,b\\,c}') eq '\\{a\\\\\\,b\\,c\\}',
- 'escaping commas 2');
-ok(wc2re_unix('\\{a\\\\,b\\,c\\}') eq '\\{a\\\\\\,b\\,c\\}',
- 'escaping commas 3');
-ok(wc2re_unix('\\{a\\\\,b\\,c\\\\}') eq '\\{a\\\\\\,b\\,c\\\\\\}',
- 'escaping brackets and commas');
-
-ok(wc2re_unix('{a\\},b\\{,c}') eq '(?:a\\}|b\\{|c)',
- 'overlapping brackets');
-ok(wc2re_unix('{a\\{b,c}d,e}') eq '(?:a\\{b|c)d\\,e\\}',
- 'partial unbalanced catching 1');
-ok(wc2re_unix('{a\\{\\\\}b,c\\\\}') eq '(?:a\\{\\\\)b\\,c\\\\\\}',
- 'partial unbalanced catching 2');
-ok(wc2re_unix('{a{b,c\\}d,e}') eq '\\{a\\{b\\,c\\}d\\,e\\}',
- 'no partial unbalanced catching');
-ok(wc2re_unix('{a,\\{,\\},b}') eq '(?:a|\\{|\\}|b)',
- 'substituting commas 1');
-ok(wc2re_unix('{a,\\{d,e,,\\}b,c}') eq '(?:a|\\{d|e||\\}b|c)',
- 'substituting commas 2');
-ok(wc2re_unix('{a,\\{d,e,,\\}b,c}\\\\{f,g,h,i}') eq '(?:a|\\{d|e||\\}b|c)\\\\(?:f|g|h|i)',
- 'handling the rest');
--- /dev/null
+#!perl -T
+
+use strict;
+use warnings;
+
+use Test::More tests => 2 * (4 + 2 + 7 + 9 + 2) * 3;
+
+use Regexp::Wildcards;
+
+sub try {
+ my ($rw, $s, $x, $y) = @_;
+ $y = $x unless defined $y;
+ my $t = $rw->{type};
+ is($rw->convert('ab' . $x), 'ab' . $y, $s . ' (begin) ['.$t.']');
+ is($rw->convert('a' . $x . 'b'), 'a' . $y . 'b', $s . ' (middle) ['.$t.']');
+ is($rw->convert($x . 'ab'), $y . 'ab', $s . ' (end) ['.$t.']');
+}
+
+sub alltests {
+ my ($t, $one, $any) = @_;
+
+ my $rw = Regexp::Wildcards->new;
+ $rw->type($t);
+
+ # Simple
+
+ try $rw, "simple $any", $any, '.*';
+ try $rw, "simple $one", $one, '.';
+
+ is($rw->convert($one.$any.'ab', $t), '..*ab',
+ "simple $one and $any (begin) [$t]");
+ is($rw->convert($one.'a'.$any.'b', $t), '.a.*b',
+ "simple $one and $any (middle) [$t]");
+ is($rw->convert($one.'ab'.$any, $t), '.ab.*',
+ "simple $one and $any (end) [$t]");
+
+ is($rw->convert($any.'ab'.$one, $t), '.*ab.',
+ "simple $any and $one (begin) [$t]");
+ is($rw->convert('a'.$any.'b'.$one, $t), 'a.*b.',
+ "simple $any and $one (middle) [$t]");
+ is($rw->convert('ab'.$any.$one, $t), 'ab.*.',
+ "simple $any and $one (end) [$t]");
+
+ # Multiple
+
+ try $rw, "multiple $any", $any x 2, '.*';
+ try $rw, "multiple $one", $one x 2, '..';
+
+ # Captures
+
+ $rw->capture('single');
+ try $rw, "multiple capturing $one", $one.$one.'\\'.$one.$one,
+ '(.)(.)\\'.$one.'(.)';
+
+ $rw->capture(add => [ qw/any greedy/ ]);
+ try $rw, "multiple capturing $any (greedy)", $any.$any.'\\'.$any.$any,
+ '(.*)\\'.$any.'(.*)';
+ my $wc = $any.$any.$one.$one.'\\'.$one.$one.'\\'.$any.$any;
+ try $rw, "multiple capturing $any (greedy) and capturing $one",
+ $wc, '(.*)(.)(.)\\'.$one.'(.)\\'.$any.'(.*)';
+
+ $rw->capture(set => [ qw/any greedy/ ]);
+ try $rw, "multiple capturing $any (greedy) and non-capturing $one",
+ $wc, '(.*)..\\'.$one.'.\\'.$any.'(.*)';
+
+ $rw->capture(rem => 'greedy');
+ try $rw, "multiple capturing $any (non-greedy)", $any.$any.'\\'.$any.$any,
+ '(.*?)\\'.$any.'(.*?)';
+ try $rw, "multiple capturing $any (non-greedy) and non-capturing $one",
+ $wc, '(.*?)..\\'.$one.'.\\'.$any.'(.*?)';
+
+ $rw->capture({ single => 1, any => 1 });
+ try $rw, "multiple capturing $any (non-greedy) and capturing $one",
+ $wc, '(.*?)(.)(.)\\'.$one.'(.)\\'.$any.'(.*?)';
+
+ $rw->capture();
+
+ # Escaping
+
+ try $rw, "escaping $any", '\\'.$any;
+ try $rw, "escaping $one", '\\'.$one;
+ try $rw, "escaping \\\\\\$any", '\\\\\\'.$any;
+ try $rw, "escaping \\\\\\$one", '\\\\\\'.$one;
+
+ try $rw, "not escaping \\\\$any", '\\\\'.$any, '\\\\.*';
+ try $rw, "not escaping \\\\$one", '\\\\'.$one, '\\\\.';
+
+ try $rw, 'escaping \\', '\\', '\\\\';
+ try $rw, 'escaping regex characters', '[]', '\\[\\]';
+ try $rw, 'not escaping escaped regex characters', '\\\\\\[\\]';
+
+ # Mixed
+
+ try $rw, "mixed $any and \\$any", $any.'\\'.$any.$any, '.*\\'.$any.'.*';
+ try $rw, "mixed $one and \\$one", $one.'\\'.$one.$one, '.\\'.$one.'.';
+}
+
+alltests 'jokers', '?', '*';
+alltests 'sql', '_', '%';
--- /dev/null
+#!perl -T
+
+use strict;
+use warnings;
+
+use Test::More tests => 8;
+
+use Regexp::Wildcards;
+
+my $rw = Regexp::Wildcards->new(); # unix
+
+is($rw->convert('a,b,c'), 'a\\,b\\,c', 'unix: commas outside of brackets 1');
+is($rw->convert('a\\,b\\\\\\,c'), 'a\\,b\\\\\\,c',
+ 'unix: commas outside of brackets 2');
+is($rw->convert(',a,b,c\\\\,'), '\\,a\\,b\\,c\\\\\\,',
+ 'unix: commas outside of brackets at begin/ed');
+
+$rw = Regexp::Wildcards->new(type => 'commas');
+
+is($rw->convert('a,b\\\\,c'), '(?:a|b\\\\|c)', 'win32: commas');
+is($rw->convert('a\\,b\\\\,c'), '(?:a\\,b\\\\|c)', 'win32: escaped commas 1');
+is($rw->convert('a\\,b\\\\\\,c'), 'a\\,b\\\\\\,c', 'win32: escaped commas 2');
+
+is($rw->convert(',a,b\\\\,'), '(?:|a|b\\\\|)', 'win32: commas at begin/end');
+is($rw->convert('\\,a,b\\\\\\,'), '(?:\\,a|b\\\\\\,)',
+ 'win32: escaped commas at begin/end');
--- /dev/null
+#!perl -T
+
+use strict;
+use warnings;
+
+use Test::More tests => 27;
+
+use Regexp::Wildcards;
+
+my $rw = Regexp::Wildcards->new(qw/do brackets/);
+
+is($rw->convert('a{b\\\\,c\\\\}d', 'jokers'), 'a\\{b\\\\\\,c\\\\\\}d','jokers');
+
+is($rw->convert('a{b\\\\,c\\\\}d', 'sql'), 'a\\{b\\\\\\,c\\\\\\}d', 'sql');
+
+is($rw->convert('a{b\\\\,c\\\\}d', 'win32'), '(?:a\\{b\\\\|c\\\\\\}d)','win32');
+
+is($rw->convert('{}'), '(?:)', 'empty brackets');
+is($rw->convert('{a}'), '(?:a)', 'brackets 1');
+is($rw->convert('{a,b}'), '(?:a|b)', 'brackets 2');
+is($rw->convert('{a,b,c}'), '(?:a|b|c)', 'brackets 3');
+
+is($rw->convert('a{b,c}d'), 'a(?:b|c)d',
+ '1 bracketed block');
+is($rw->convert('a{b,c}d{e,,f}'), 'a(?:b|c)d(?:e||f)',
+ '2 bracketed blocks');
+is($rw->convert('a{b,c}d{e,,f}{g,h,}'), 'a(?:b|c)d(?:e||f)(?:g|h|)',
+ '3 bracketed blocks');
+
+is($rw->convert('{a{b}}'), '(?:a(?:b))',
+ '2 nested bracketed blocks 1');
+is($rw->convert('{a,{b},c}'), '(?:a|(?:b)|c)',
+ '2 nested bracketed blocks 2');
+is($rw->convert('{a,{b{d}e},c}'), '(?:a|(?:b(?:d)e)|c)',
+ '3 nested bracketed blocks');
+is($rw->convert('{a,{b{d{}}e,f,,},c}'), '(?:a|(?:b(?:d(?:))e|f||)|c)',
+ '4 nested bracketed blocks');
+is($rw->convert('{a,{b{d{}}e,f,,},c}{,g{{}h,i}}'), '(?:a|(?:b(?:d(?:))e|f||)|c)(?:|g(?:(?:)h|i))',
+ '4+3 nested bracketed blocks');
+
+is($rw->convert('\\{\\\\}'), '\\{\\\\\\}',
+ 'escaping brackets');
+is($rw->convert('\\{a,b,c\\\\\\}'), '\\{a\\,b\\,c\\\\\\}',
+ 'escaping commas 1');
+is($rw->convert('\\{a\\\\,b\\,c}'), '\\{a\\\\\\,b\\,c\\}',
+ 'escaping commas 2');
+is($rw->convert('\\{a\\\\,b\\,c\\}'), '\\{a\\\\\\,b\\,c\\}',
+ 'escaping commas 3');
+is($rw->convert('\\{a\\\\,b\\,c\\\\}'), '\\{a\\\\\\,b\\,c\\\\\\}',
+ 'escaping brackets and commas');
+
+is($rw->convert('{a\\},b\\{,c}'), '(?:a\\}|b\\{|c)',
+ 'overlapping brackets');
+is($rw->convert('{a\\{b,c}d,e}'), '(?:a\\{b|c)d\\,e\\}',
+ 'partial unbalanced catching 1');
+is($rw->convert('{a\\{\\\\}b,c\\\\}'), '(?:a\\{\\\\)b\\,c\\\\\\}',
+ 'partial unbalanced catching 2');
+is($rw->convert('{a{b,c\\}d,e}'), '\\{a\\{b\\,c\\}d\\,e\\}',
+ 'no partial unbalanced catching');
+is($rw->convert('{a,\\{,\\},b}'), '(?:a|\\{|\\}|b)',
+ 'substituting commas 1');
+is($rw->convert('{a,\\{d,e,,\\}b,c}'), '(?:a|\\{d|e||\\}b|c)',
+ 'substituting commas 2');
+is($rw->convert('{a,\\{d,e,,\\}b,c}\\\\{f,g,h,i}'), '(?:a|\\{d|e||\\}b|c)\\\\(?:f|g|h|i)',
+ 'handling the rest');
--- /dev/null
+#!perl -T
+
+use strict;
+use warnings;
+
+use Test::More tests => 6;
+
+use Regexp::Wildcards;
+
+my $rw = Regexp::Wildcards->new(do => [ qw/jokers brackets groups/ ]);
+
+is($rw->convert('a(?)b'), 'a(.)b', 'groups: single');
+is($rw->convert('a(*)b'), 'a(.*)b', 'groups: any');
+is($rw->convert('(a),(b)'), '(a)\\,(b)', 'groups: commas');
+is($rw->convert('a({x,y})b'), 'a((?:x|y))b', 'groups: brackets');
+is($rw->convert('a({x,(y?),{z,(t*u)}})b'), 'a((?:x|(y.)|(?:z|(t.*u))))b',
+ 'groups: nested');
+is($rw->convert('(a*\\(b?\\))'), '(a.*\\(b.\\))', 'groups: escape');
projects / perl / modules / Regexp-Wildcards.git / commitdiff