Updated escaping code. utf8 regex debug output improvements

[perl5.git] / ext / re / re.pm

diff --git a/ext/re/re.pm b/ext/re/re.pm
index 3f142d9..51545ac 100644 (file)
--- a/ext/re/re.pm
+++ b/ext/re/re.pm
@@ -1,6 +1,6 @@
 package re;
 
 package re;
 

-$VERSION = 0.02;
+our $VERSION = 0.06_01;

 
 =head1 NAME
 
 
 =head1 NAME
 


@@ -30,6 +30,10 @@ re - Perl pragma to alter regular expression behaviour
     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);         # Similarly not lexically scoped.
+    no re qw(Debug ALL);           # Turn of all re dugging and unload the module.
+

 (We use $^X in these examples because it's tainted by default.)
 
 =head1 DESCRIPTION
 (We use $^X in these examples because it's tainted by default.)
 
 =head1 DESCRIPTION


@@ -42,21 +46,21 @@ other transformations.
 
 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 regex is allowed to contain
 C<(?{ ... })> zero-width assertions even if regular expression contains

-variable interpolation.  That is normally disallowed, since it is a 
+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
 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 expresssions.  See L<perlre/(?{ code })>.
+disallowed with tainted regular expressions.  See L<perlre/(?{ code })>.

 
 

-For the purpose of this pragma, interpolation of precompiled regular 
+For the purpose of this pragma, interpolation of precompiled regular

 expressions (i.e., the result of C<qr//>) is I<not> considered variable
 interpolation.  Thus:
 
     /foo${pat}bar/
 
 expressions (i.e., the result of C<qr//>) is I<not> considered variable
 interpolation.  Thus:
 
     /foo${pat}bar/
 

-I<is> allowed if $pat is a precompiled regular expression, even 
+I<is> allowed if $pat is a precompiled regular expression, even

 if $pat contains C<(?{ ... })> assertions.
 
 if $pat contains C<(?{ ... })> assertions.
 

-When C<use re 'debug'> is in effect, perl emits debugging messages when 
+When C<use re 'debug'> is in effect, perl emits debugging messages when

 compiling and using regular expressions.  The output is the same as that
 obtained by running a C<-DDEBUGGING>-enabled perl interpreter with the
 B<-Dr> switch. It may be quite voluminous depending on the complexity
 compiling and using regular expressions.  The output is the same as that
 obtained by running a C<-DDEBUGGING>-enabled perl interpreter with the
 B<-Dr> switch. It may be quite voluminous depending on the complexity


@@ -64,11 +68,129 @@ of the match.  Using C<debugcolor> instead of C<debug> enables a
 form of output that can be used to get a colorful display on terminals
 that understand termcap color sequences.  Set C<$ENV{PERL_RE_TC}> to a
 comma-separated list of C<termcap> properties to use for highlighting
 form of output that can be used to get a colorful display on terminals
 that understand termcap color sequences.  Set C<$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.  
+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.
 

-The directive C<use re 'debug'> is I<not lexically scoped>, as the
-other directives are.  It has both compile-time and run-time effects.
+Similarly C<use re 'Debug'> produces debugging output, the difference
+being that it allows the fine tuning of what debugging output will be
+emitted. Options are divided into three groups, those related to
+compilation, those related to execution and those related to special
+purposes. The options are as follows:
+
+=over 4
+
+=item Compile related options
+
+=over 4
+
+=item COMPILE
+
+Turns on all compile related debug options.
+
+=item PARSE
+
+Turns on debug output related to the process of parsing the pattern.
+
+=item OPTIMISE
+
+Enables output related to the optimisation phase of compilation.
+
+=item TRIE_COMPILE
+
+Detailed info about trie compilation.
+
+=item DUMP
+
+Dump the final program out after it is compiled and optimised.
+
+=item OFFSETS
+
+Dump offset information. This can be used to see how regops correlate
+to the pattern. Output format is
+
+   NODENUM:POSITION[LENGTH]
+
+Where 1 is the position of the first char in the string. Note that position
+can be 0, or larger than the actual length of the pattern, likewise length
+can be zero.
+
+=back
+
+=item Execute related options
+
+=over 4
+
+=item EXECUTE
+
+Turns on all execute related debug options.
+
+=item MATCH
+
+Turns on debugging of the main matching loop.
+
+=item TRIE_EXECUTE
+
+Extra debugging of how tries execute.
+
+=item INTUIT
+
+Enable debugging of start point optimisations.
+
+=back
+
+=item Extra debugging options
+
+=over 4
+
+=item EXTRA
+
+Turns on all "extra" debugging options.
+
+=item TRIE_MORE
+
+Enable enhanced TRIE debugging. Enhances both TRIE_EXECUTE
+and TRIE_COMPILE.
+
+=item OFFSETS_DEBUG
+
+Enable debugging of offsets information. This emits copious
+amounts of trace information and doesnt mesh well with other
+debug options.
+
+Almost definately only useful to people hacking
+on the offsets part of the debug engine.
+
+=back
+
+=item Other useful flags
+
+These are useful shortcuts to save on the typing.
+
+=over 4
+
+=item ALL
+
+Enable all compile and execute options at once.
+
+=item All
+
+Enable DUMP and all execute options. Equivelent to:
+
+  use re 'debug';
+
+=item MORE
+
+=item More
+
+Enable TRIE_MORE and all execute compile and execute options.
+
+=back 4
+
+=back 4
+
+The directive C<use re 'debug'> and its equivalents are I<not> lexically
+scoped, as the other directives are.  They have both compile-time and run-time
+effects.

 
 See L<perlmodlib/Pragmatic Modules>.
 
 
 See L<perlmodlib/Pragmatic Modules>.
 


@@ -77,8 +199,8 @@ See L<perlmodlib/Pragmatic Modules>.
 # N.B. File::Basename contains a literal for 'taint' as a fallback.  If
 # taint is changed here, File::Basename must be updated as well.
 my %bitmask = (
 # N.B. File::Basename contains a literal for 'taint' as a fallback.  If
 # taint is changed here, File::Basename must be updated as well.
 my %bitmask = (

-taint  => 0x00100000,
-eval   => 0x00200000,
+taint          => 0x00100000, # HINT_RE_TAINT
+eval           => 0x00200000, # HINT_RE_EVAL

 );
 
 sub setcolor {
 );
 
 sub setcolor {


@@ -95,35 +217,87 @@ sub setcolor {
  };
 }
 
  };
 }
 

+my %flags = (
+    COMPILE         => 0x0000FF,
+    PARSE           => 0x000001,
+    OPTIMISE        => 0x000002,
+    TRIE_COMPILE    => 0x000004,
+    DUMP            => 0x000008,
+    OFFSETS         => 0x000010,
+
+    EXECUTE         => 0x00FF00,
+    INTUIT          => 0x000100,
+    MATCH           => 0x000200,
+    TRIE_EXECUTE    => 0x000400,
+
+    EXTRA           => 0xFF0000,
+    TRIE_MORE       => 0x010000,
+    OFFSETS_DEBUG   => 0x020000,
+    STATE           => 0x040000,
+);
+$flags{ALL} = $flags{COMPILE} | $flags{EXECUTE};
+$flags{All} = $flags{all} = $flags{DUMP} | $flags{EXECUTE};
+$flags{More} = $flags{MORE} = $flags{ALL} | $flags{TRIE_MORE};
+
+my $installed = 0;
+
+sub _load_unload {
+    my $on = shift;
+    require XSLoader;
+    XSLoader::load('re');
+    install($on);
+}
+

 sub bits {
     my $on = shift;
     my $bits = 0;
 sub bits {
     my $on = shift;
     my $bits = 0;

-    unless(@_) {
+    unless (@_) {

        require Carp;
        Carp::carp("Useless use of \"re\" pragma");
     }
        require Carp;
        Carp::carp("Useless use of \"re\" pragma");
     }

-    foreach my $s (@_){
-      if ($s eq 'debug' or $s eq 'debugcolor') {
-         setcolor() if $s eq 'debugcolor';
-         require XSLoader;
-         XSLoader::load('re');
-         install() if $on;
-         uninstall() unless $on;
-         next;
-      }
-      $bits |= $bitmask{$s} || 0;
+    foreach my $idx (0..$#_){
+        my $s=$_[$idx];
+        if ($s eq 'Debug' or $s eq 'Debugcolor') {
+            setcolor() if $s eq 'Debugcolor';
+            ${^RE_DEBUG_FLAGS} = 0 unless defined ${^RE_DEBUG_FLAGS};
+            for my $idx ($idx+1..$#_) {
+                if ($flags{$_[$idx]}) {
+                    if ($on) {
+                        ${^RE_DEBUG_FLAGS} |= $flags{$_[$idx]};
+                    } else {
+                        ${^RE_DEBUG_FLAGS} &= ~ $flags{$_[$idx]};
+                    }
+                } else {
+                    require Carp;
+                    Carp::carp("Unknown \"re\" Debug flag '$_[$idx]', possible flags: ",
+                               join(", ",sort { $flags{$a} <=> $flags{$b} } keys %flags ) );
+                }
+            }
+            _load_unload($on ? 1 : ${^RE_DEBUG_FLAGS});
+            last;
+        } elsif ($s eq 'debug' or $s eq 'debugcolor') {
+           setcolor() if $s eq 'debugcolor';
+           _load_unload($on);
+        } elsif (exists $bitmask{$s}) {
+           $bits |= $bitmask{$s};
+       } else {
+           require Carp;
+           Carp::carp("Unknown \"re\" subpragma '$s' (known ones are: ",
+                       join(', ', map {qq('$_')} 'debug', 'debugcolor', sort keys %bitmask),
+                       ")");
+       }

     }
     $bits;
 }
 
 sub import {
     shift;
     }
     $bits;
 }
 
 sub import {
     shift;

-    $^H |= bits(1,@_);
+    $^H |= bits(1, @_);

 }
 
 sub unimport {
     shift;
 }
 
 sub unimport {
     shift;

-    $^H &= ~ bits(0,@_);
+    $^H &= ~ bits(0, @_);

 }
 
 1;
 }
 
 1;