package re;
-# pragma for controlling the regex engine
+# pragma for controlling the regexp engine
use strict;
use warnings;
-our $VERSION = "0.09";
+our $VERSION = "0.11";
our @ISA = qw(Exporter);
-my @XS_FUNCTIONS = qw(regmust);
-my %XS_FUNCTIONS = map { $_ => 1 } @XS_FUNCTIONS;
-our @EXPORT_OK = (@XS_FUNCTIONS,
+our @EXPORT_OK = ('regmust',
qw(is_regexp regexp_pattern
regname regnames regnames_count));
our %EXPORT_OK = map { $_ => 1 } @EXPORT_OK;
-# *** WARNING *** WARNING *** WARNING *** WARNING *** WARNING ***
-#
-# If you modify these values see comment below!
-
my %bitmask = (
taint => 0x00100000, # HINT_RE_TAINT
eval => 0x00200000, # HINT_RE_EVAL
);
-# - File::Basename contains a literal for 'taint' as a fallback. If
-# taint is changed here, File::Basename must be updated as well.
-#
-# - ExtUtils::ParseXS uses a hardcoded
-# BEGIN { $^H |= 0x00200000 }
-# in it to allow re.xs to be built. So if 'eval' is changed here then
-# ExtUtils::ParseXS must be changed as well.
-#
-# *** WARNING *** WARNING *** WARNING *** WARNING *** WARNING ***
-
sub setcolor {
eval { # Ignore errors
require Term::Cap;
OPTIMISEM => 0x100000,
STACK => 0x280000,
BUFFERS => 0x400000,
+ GPOS => 0x800000,
);
$flags{ALL} = -1 & ~($flags{OFFSETS}|$flags{OFFSETSDBG}|$flags{BUFFERS});
$flags{All} = $flags{all} = $flags{DUMP} | $flags{EXECUTE};
-$flags{Extra} = $flags{EXECUTE} | $flags{COMPILE};
+$flags{Extra} = $flags{EXECUTE} | $flags{COMPILE} | $flags{GPOS};
$flags{More} = $flags{MORE} = $flags{All} | $flags{TRIEC} | $flags{TRIEM} | $flags{STATE};
$flags{State} = $flags{DUMP} | $flags{EXECUTE} | $flags{STATE};
$flags{TRIE} = $flags{DUMP} | $flags{EXECUTE} | $flags{TRIEC};
-my $installed;
-my $installed_error;
-
-sub _do_install {
- if ( ! defined($installed) ) {
- require XSLoader;
- $installed = eval { XSLoader::load('re', $VERSION) } || 0;
- $installed_error = $@;
- }
+if (defined &DynaLoader::boot_DynaLoader) {
+ require XSLoader;
+ XSLoader::load( __PACKAGE__, $VERSION);
}
+# else we're miniperl
+# We need to work for miniperl, because the XS toolchain uses Text::Wrap, which
+# uses re 'taint'.
sub _load_unload {
my ($on)= @_;
if ($on) {
- _do_install();
- if ( ! $installed ) {
- die "'re' not installed!? ($installed_error)";
- } else {
- # We call install() every time, as if we didn't, we wouldn't
- # "see" any changes to the color environment var since
- # the last time it was called.
-
- # install() returns an integer, which if casted properly
- # in C resolves to a structure containing the regex
- # hooks. Setting it to a random integer will guarantee
- # segfaults.
- $^H{regcomp} = install();
- }
+ # We call install() every time, as if we didn't, we wouldn't
+ # "see" any changes to the color environment var since
+ # the last time it was called.
+
+ # install() returns an integer, which if casted properly
+ # in C resolves to a structure containing the regexp
+ # hooks. Setting it to a random integer will guarantee
+ # segfaults.
+ $^H{regcomp} = install();
} else {
delete $^H{regcomp};
}
last;
} elsif (exists $bitmask{$s}) {
$bits |= $bitmask{$s};
- } elsif ($XS_FUNCTIONS{$s}) {
- _do_install();
- if (! $installed) {
- require Carp;
- Carp::croak("\"re\" function '$s' not available");
- }
- require Exporter;
- re->export_to_level(2, 're', $s);
} elsif ($EXPORT_OK{$s}) {
require Exporter;
re->export_to_level(2, 're', $s);
=head2 'taint' mode
When C<use re 'taint'> is in effect, and a tainted string is the target
-of a regex, the regex memories (or values returned by the m// operator
-in list context) are tainted. This feature is useful when regex operations
+of a regexp, the regexp memories (or values returned by the m// operator
+in list context) are tainted. This feature is useful when regexp operations
on tainted data aren't meant to extract safe substrings, but to perform
other transformations.
=head2 'eval' mode
-When C<use re 'eval'> is in effect, a regex is allowed to contain
-C<(?{ ... })> zero-width assertions even if regular expression contains
+When C<use re 'eval'> is in effect, a regexp is allowed to contain
+C<(?{ ... })> zero-width assertions and C<(??{ ... })> postponed
+subexpressions, even if the regular expression contains
variable interpolation. That is normally disallowed, since it is a
potential security risk. Note that this pragma is ignored when the regular
expression is obtained from tainted data, i.e. evaluation is always
-disallowed with tainted regular expressions. See L<perlre/(?{ code })>.
+disallowed with tainted regular expressions. See L<perlre/(?{ code })>
+and L<perlre/(??{ code })>.
For the purpose of this pragma, interpolation of precompiled regular
expressions (i.e., the result of C<qr//>) is I<not> considered variable
/foo${pat}bar/
I<is> allowed if $pat is a precompiled regular expression, even
-if $pat contains C<(?{ ... })> assertions.
+if $pat contains C<(?{ ... })> assertions or C<(??{ ... })> subexpressions.
=head2 'debug' mode
=item OPTIMISEM
Enable enhanced optimisation debugging and start point optimisations.
-Probably not useful except when debugging the regex engine itself.
+Probably not useful except when debugging the regexp engine itself.
=item OFFSETS
my ($pat, $mods) = regexp_pattern($ref);
-In scalar context it returns the same as perl would when strigifying a raw
+In scalar context it returns the same as perl would when stringifying a raw
C<qr//> with the same pattern inside. If the argument is not a compiled
reference then this routine returns false but defined in scalar context,
and the empty list in list context. Thus the following
=item regmust($ref)
If the argument is a compiled regular expression as returned by C<qr//>,
-then this function returns what the optimiser consiers to be the longest
+then this function returns what the optimiser considers to be the longest
anchored fixed string and longest floating fixed string in the pattern.
A I<fixed string> is defined as being a substring that must appear for the