use strict;
use warnings;
-our $VERSION = "0.11";
+our $VERSION = "0.24";
our @ISA = qw(Exporter);
our @EXPORT_OK = ('regmust',
qw(is_regexp regexp_pattern
eval => 0x00200000, # HINT_RE_EVAL
);
+my $flags_hint = 0x02000000; # HINT_RE_FLAGS
+my $PMMOD_SHIFT = 0;
+my %reflags = (
+ m => 1 << ($PMMOD_SHIFT + 0),
+ s => 1 << ($PMMOD_SHIFT + 1),
+ i => 1 << ($PMMOD_SHIFT + 2),
+ x => 1 << ($PMMOD_SHIFT + 3),
+ p => 1 << ($PMMOD_SHIFT + 4),
+# special cases:
+ d => 0,
+ l => 1,
+ u => 2,
+ a => 3,
+ aa => 4,
+);
+
sub setcolor {
eval { # Ignore errors
require Term::Cap;
if (defined &DynaLoader::boot_DynaLoader) {
require XSLoader;
- XSLoader::load( __PACKAGE__, $VERSION);
+ XSLoader::load();
}
# else we're miniperl
# We need to work for miniperl, because the XS toolchain uses Text::Wrap, which
sub bits {
my $on = shift;
my $bits = 0;
- unless (@_) {
- require Carp;
- Carp::carp("Useless use of \"re\" pragma");
- }
+ ARG:
foreach my $idx (0..$#_){
my $s=$_[$idx];
if ($s eq 'Debug' or $s eq 'Debugcolor') {
} elsif ($EXPORT_OK{$s}) {
require Exporter;
re->export_to_level(2, 're', $s);
+ } elsif ($s =~ s/^\///) {
+ my $reflags = $^H{reflags} || 0;
+ my $seen_charset;
+ while ($s =~ m/( . )/gx) {
+ local $_ = $1;
+ if (/[adul]/) {
+ # The 'a' may be repeated; hide this from the rest of the
+ # code by counting and getting rid of all of them, then
+ # changing to 'aa' if there is a repeat.
+ if ($_ eq 'a') {
+ my $sav_pos = pos $s;
+ my $a_count = $s =~ s/a//g;
+ pos $s = $sav_pos - 1; # -1 because got rid of the 'a'
+ if ($a_count > 2) {
+ require Carp;
+ Carp::carp(
+ qq 'The "a" flag may only appear a maximum of twice'
+ );
+ }
+ elsif ($a_count == 2) {
+ $_ = 'aa';
+ }
+ }
+ if ($on) {
+ if ($seen_charset) {
+ require Carp;
+ if ($seen_charset ne $_) {
+ Carp::carp(
+ qq 'The "$seen_charset" and "$_" flags '
+ .qq 'are exclusive'
+ );
+ }
+ else {
+ Carp::carp(
+ qq 'The "$seen_charset" flag may not appear '
+ .qq 'twice'
+ );
+ }
+ }
+ $^H{reflags_charset} = $reflags{$_};
+ $seen_charset = $_;
+ }
+ else {
+ delete $^H{reflags_charset}
+ if defined $^H{reflags_charset}
+ && $^H{reflags_charset} == $reflags{$_};
+ }
+ } elsif (exists $reflags{$_}) {
+ $on
+ ? $reflags |= $reflags{$_}
+ : ($reflags &= ~$reflags{$_});
+ } else {
+ require Carp;
+ Carp::carp(
+ qq'Unknown regular expression flag "$_"'
+ );
+ next ARG;
+ }
+ }
+ ($^H{reflags} = $reflags or defined $^H{reflags_charset})
+ ? $^H |= $flags_hint
+ : ($^H &= ~$flags_hint);
} else {
require Carp;
Carp::carp("Unknown \"re\" subpragma '$s' (known ones are: ",
$pat = '(?{ $foo = 1 })';
use re 'eval';
- /foo${pat}bar/; # won't fail (when not under -T switch)
+ /foo${pat}bar/; # won't fail (when not under -T
+ # switch)
{
no re 'taint'; # the default
($x) = ($^X =~ /^(.*)$/s); # $x is not tainted here
no re 'eval'; # the default
- /foo${pat}bar/; # disallowed (with or without -T switch)
+ /foo${pat}bar/; # disallowed (with or without -T
+ # switch)
}
+ use re '/ix';
+ "FOO" =~ / foo /; # /ix implied
+ no re '/x';
+ "FOO" =~ /foo/; # just /i implied
+
use re 'debug'; # output debugging info during
- /^(.*)$/s; # compile and run time
+ /^(.*)$/s; # compile and run time
- use re 'debugcolor'; # same as 'debug', but with colored output
+ use re 'debugcolor'; # same as 'debug', but with colored
+ # output
...
- use re qw(Debug All); # Finer tuned debugging options.
- use re qw(Debug More);
- no re qw(Debug ALL); # Turn of all re debugging in this scope
+ use re qw(Debug All); # Same as "use re 'debug'", but you
+ # can use "Debug" with things other
+ # than 'All'
+ use re qw(Debug More); # 'All' plus output more details
+ no re qw(Debug ALL); # Turn on (almost) all re debugging
+ # in this scope
use re qw(is_regexp regexp_pattern); # import utility functions
my ($pat,$mods)=regexp_pattern(qr/foo/i);
if (is_regexp($obj)) {
print "Got regexp: ",
- scalar regexp_pattern($obj); # just as perl would stringify it
- } # but no hassle with blessed re's.
+ scalar regexp_pattern($obj); # just as perl would stringify
+ } # it but no hassle with blessed
+ # re's.
(We use $^X in these examples because it's tainted by default.)
When C<use re 'eval'> is in effect, a regexp is allowed to contain
C<(?{ ... })> zero-width assertions and C<(??{ ... })> postponed
-subexpressions, even if the regular expression contains
-variable interpolation. That is normally disallowed, since it is a
+subexpressions that are derived from variable interpolation, rather than
+appearing literally within the regexp. That is normally disallowed, since
+it is a
potential security risk. Note that this pragma is ignored when the regular
expression is obtained from tainted data, i.e. evaluation is always
disallowed with tainted regular expressions. See L<perlre/(?{ code })>
I<is> allowed if $pat is a precompiled regular expression, even
if $pat contains C<(?{ ... })> assertions or C<(??{ ... })> subexpressions.
+=head2 '/flags' mode
+
+When C<use re '/flags'> is specified, the given flags are automatically
+added to every regular expression till the end of the lexical scope.
+
+C<no re '/flags'> will turn off the effect of C<use re '/flags'> for the
+given flags.
+
+For example, if you want all your regular expressions to have /msx on by
+default, simply put
+
+ use re '/msx';
+
+at the top of your code.
+
+The character set /adul flags cancel each other out. So, in this example,
+
+ use re "/u";
+ "ss" =~ /\xdf/;
+ use re "/d";
+ "ss" =~ /\xdf/;
+
+the second C<use re> does an implicit C<no re '/u'>.
+
+Turning on one of the character set flags with C<use re> takes precedence over the
+C<locale> pragma and the 'unicode_strings' C<feature>, for regular
+expressions. Turning off one of these flags when it is active reverts to
+the behaviour specified by whatever other pragmata are in scope. For
+example:
+
+ use feature "unicode_strings";
+ no re "/u"; # does nothing
+ use re "/l";
+ no re "/l"; # reverts to unicode_strings behaviour
+
=head2 'debug' mode
When C<use re 'debug'> is in effect, perl emits debugging messages when
that understand termcap color sequences. Set C<$ENV{PERL_RE_TC}> to a
comma-separated list of C<termcap> properties to use for highlighting
strings on/off, pre-point part on/off.
-See L<perldebug/"Debugging regular expressions"> for additional info.
+See L<perldebug/"Debugging Regular Expressions"> for additional info.
As of 5.9.5 the directive C<use re 'debug'> and its equivalents are
lexically scoped, as the other directives are. However they have both
=item INTUIT
-Enable debugging of start point optimisations.
+Enable debugging of start-point optimisations.
=back
=item OPTIMISEM
-Enable enhanced optimisation debugging and start point optimisations.
+Enable enhanced optimisation debugging and start-point optimisations.
Probably not useful except when debugging the regexp engine itself.
=item OFFSETS
=item ALL
-Enable all options at once except OFFSETS, OFFSETSDBG and BUFFERS
+Enable all options at once except OFFSETS, OFFSETSDBG and BUFFERS.
+(To get every single option without exception, use both ALL and EXTRA.)
=item All
=item More
-Enable TRIEM and all execute compile and execute options.
+Enable the options enabled by "All", plus STATE, TRIEC, and TRIEM.
=back
=back
As of 5.9.5 the directive C<use re 'debug'> and its equivalents are
-lexically scoped, as the other directives are. However they have both
+lexically scoped, as are the other directives. However they have both
compile-time and run-time effects.
=head2 Exportable Functions
This function will not be confused by overloading or blessing. In
internals terms, this extracts the regexp pointer out of the
-PERL_MAGIC_qr structure so it it cannot be fooled.
+PERL_MAGIC_qr structure so it cannot be fooled.
=item regexp_pattern($ref)
reference then this routine returns false but defined in scalar context,
and the empty list in list context. Thus the following
- if (regexp_pattern($ref) eq '(?i-xsm:foo)')
+ if (regexp_pattern($ref) eq '(?^i:foo)')
will be warning free regardless of what $ref actually is.
Because the C<here> is before the C<.*> in the pattern, its position
can be determined exactly. That's not true, however, for the C<there>;
it could appear at any point after where the anchored string appeared.
-Perl uses both for its optimisations, prefering the longer, or, if they are
+Perl uses both for its optimisations, preferring the longer, or, if they are
equal, the floating.
B<NOTE:> This may not necessarily be the definitive longest anchored and