Integrate with Sarathy.

p4raw-id: //depot/cfgperl@5313

3 files changed, 184 insertions, 83 deletions

diff --git a/lib/File/Basename.pm b/lib/File/Basename.pm
index da2caee849..4581e7e93c 100644
--- a/lib/File/Basename.pm
+++ b/lib/File/Basename.pm
@@ -37,10 +37,10 @@ If the argument passed to it contains one of the substrings
 "VMS", "MSDOS", "MacOS", "AmigaOS" or "MSWin32", the file specification 
 syntax of that operating system is used in future calls to 
 fileparse(), basename(), and dirname().  If it contains none of
-these substrings, UNIX syntax is used.  This pattern matching is
+these substrings, Unix syntax is used.  This pattern matching is
 case-insensitive.  If you've selected VMS syntax, and the file
 specification you pass to one of these routines contains a "/",
-they assume you are using UNIX emulation and apply the UNIX syntax
+they assume you are using Unix emulation and apply the Unix syntax
 rules instead, for that function call only.
 
 If the argument passed to it contains one of the substrings "VMS",
@@ -73,7 +73,7 @@ file as the input file specification.
 
 =head1 EXAMPLES
 
-Using UNIX file syntax:
+Using Unix file syntax:
 
     ($base,$path,$type) = fileparse('/virgil/aeneid/draft.book7',
 				    '\.book\d+');
@@ -102,7 +102,7 @@ would yield
 The basename() routine returns the first element of the list produced
 by calling fileparse() with the same arguments, except that it always
 quotes metacharacters in the given suffixes.  It is provided for
-programmer compatibility with the UNIX shell command basename(1).
+programmer compatibility with the Unix shell command basename(1).
 
 =item C<dirname>
 
@@ -111,8 +111,8 @@ specification.  When using VMS or MacOS syntax, this is identical to the
 second element of the list produced by calling fileparse() with the same
 input file specification.  (Under VMS, if there is no directory information
 in the input file specification, then the current default device and
-directory are returned.)  When using UNIX or MSDOS syntax, the return
-value conforms to the behavior of the UNIX shell command dirname(1).  This
+directory are returned.)  When using Unix or MSDOS syntax, the return
+value conforms to the behavior of the Unix shell command dirname(1).  This
 is usually the same as the behavior of fileparse(), but differs in some
 cases.  For example, for the input file specification F<lib/>, fileparse()
 considers the directory name to be F<lib/>, while dirname() considers the
@@ -172,23 +172,23 @@ sub fileparse {
   if ($fstype =~ /^VMS/i) {
     if ($fullname =~ m#/#) { $fstype = '' }  # We're doing Unix emulation
     else {
-      ($dirpath,$basename) = ($fullname =~ /^(.*[:>\]])?(.*)/);
+      ($dirpath,$basename) = ($fullname =~ /^(.*[:>\]])?(.*)/s);
       $dirpath ||= '';  # should always be defined
     }
   }
   if ($fstype =~ /^MS(DOS|Win32)/i) {
-    ($dirpath,$basename) = ($fullname =~ /^((?:.*[:\\\/])?)(.*)/);
-    $dirpath .= '.\\' unless $dirpath =~ /[\\\/]$/;
+    ($dirpath,$basename) = ($fullname =~ /^((?:.*[:\\\/])?)(.*)/s);
+    $dirpath .= '.\\' unless $dirpath =~ /[\\\/]\z/;
   }
-  elsif ($fstype =~ /^MacOS/i) {
-    ($dirpath,$basename) = ($fullname =~ /^(.*:)?(.*)/);
+  elsif ($fstype =~ /^MacOS/si) {
+    ($dirpath,$basename) = ($fullname =~ /^(.*:)?(.*)/s);
   }
   elsif ($fstype =~ /^AmigaOS/i) {
-    ($dirpath,$basename) = ($fullname =~ /(.*[:\/])?(.*)/);
+    ($dirpath,$basename) = ($fullname =~ /(.*[:\/])?(.*)/s);
     $dirpath = './' unless $dirpath;
   }
   elsif ($fstype !~ /^VMS/i) {  # default to Unix
-    ($dirpath,$basename) = ($fullname =~ m#^(.*/)?(.*)#);
+    ($dirpath,$basename) = ($fullname =~ m#^(.*/)?(.*)#s);
     if ($^O eq 'VMS' and $fullname =~ m:/[^/]+/000000/?:) {
       # dev:[000000] is top of VMS tree, similar to Unix '/'
       ($basename,$dirpath) = ('',$fullname);
@@ -200,7 +200,7 @@ sub fileparse {
     $tail = '';
     foreach $suffix (@suffices) {
       my $pat = ($igncase ? '(?i)' : '') . "($suffix)\$";
-      if ($basename =~ s/$pat//) {
+      if ($basename =~ s/$pat//s) {
         $taint .= substr($suffix,0,0);
         $tail = $1 . $tail;
       }
@@ -238,30 +238,30 @@ sub dirname {
     }
     if ($fstype =~ /MacOS/i) { return $dirname }
     elsif ($fstype =~ /MSDOS/i) { 
-        $dirname =~ s/([^:])[\\\/]*$/$1/;
+        $dirname =~ s/([^:])[\\\/]*\z/$1/;
         unless( length($basename) ) {
 	    ($basename,$dirname) = fileparse $dirname;
-	    $dirname =~ s/([^:])[\\\/]*$/$1/;
+	    $dirname =~ s/([^:])[\\\/]*\z/$1/;
 	}
     }
     elsif ($fstype =~ /MSWin32/i) { 
-        $dirname =~ s/([^:])[\\\/]*$/$1/;
+        $dirname =~ s/([^:])[\\\/]*\z/$1/;
         unless( length($basename) ) {
 	    ($basename,$dirname) = fileparse $dirname;
-	    $dirname =~ s/([^:])[\\\/]*$/$1/;
+	    $dirname =~ s/([^:])[\\\/]*\z/$1/;
 	}
     }
     elsif ($fstype =~ /AmigaOS/i) {
-        if ( $dirname =~ /:$/) { return $dirname }
+        if ( $dirname =~ /:\z/) { return $dirname }
         chop $dirname;
-        $dirname =~ s#[^:/]+$## unless length($basename);
+        $dirname =~ s#[^:/]+\z## unless length($basename);
     }
     else { 
-        $dirname =~ s:(.)/*$:$1:;
+        $dirname =~ s:(.)/*\z:$1:s;
         unless( length($basename) ) {
 	    local($File::Basename::Fileparse_fstype) = $fstype;
 	    ($basename,$dirname) = fileparse $dirname;
-	    $dirname =~ s:(.)/*$:$1:;
+	    $dirname =~ s:(.)/*\z:$1:s;
 	}
     }
 
diff --git a/lib/File/Find.pm b/lib/File/Find.pm
index 42905dec80..074cff3c71 100644
--- a/lib/File/Find.pm
+++ b/lib/File/Find.pm
@@ -135,7 +135,7 @@ This library is useful for the C<find2perl> tool, which when fed,
 produces something like:
 
     sub wanted {
-        /^\.nfs.*$/ &&
+        /^\.nfs.*\z/s &&
         (($dev, $ino, $mode, $nlink, $uid, $gid) = lstat($_)) &&
         int(-M _) > 7 &&
         unlink($_)
@@ -306,7 +306,7 @@ sub _find_opt {
     Proc_Top_Item:
     foreach my $TOP (@_) {
         my $top_item = $TOP;
-        $top_item =~ s|/$||  unless $top_item eq '/';
+        $top_item =~ s|/\z|| unless $top_item eq '/';
         $Is_Dir= 0;
         
         ($topdev,$topino,$topmode,$topnlink) = stat $top_item;
@@ -338,7 +338,7 @@ sub _find_opt {
                 next Proc_Top_Item;
             }
             if (-d _) {
-		$top_item =~ s/\.dir$// if $Is_VMS;
+		$top_item =~ s/\.dir\z// if $Is_VMS;
 		_find_dir($wanted, $top_item, $topnlink);
 		$Is_Dir= 1;
             }
@@ -466,7 +466,7 @@ sub _find_dir($$$) {
 	if ($nlink == 2 && !$avoid_nlink) {
 	    # This dir has no subdirectories.
 	    for my $FN (@filenames) {
-		next if $FN =~ /^\.{1,2}$/;
+		next if $FN =~ /^\.{1,2}\z/;
 		
 		$name = $dir_pref . $FN;
 		$_ = ($no_chdir ? $name : $FN);
@@ -479,7 +479,7 @@ sub _find_dir($$$) {
 	    $subcount = $nlink - 2;
 
 	    for my $FN (@filenames) {
-		next if $FN =~ /^\.{1,2}$/;
+		next if $FN =~ /^\.{1,2}\z/;
 		if ($subcount > 0 || $avoid_nlink) {
 		    # Seen all the subdirs?
 		    # check for directoriness.
@@ -488,7 +488,7 @@ sub _find_dir($$$) {
 
 		    if (-d _) {
 			--$subcount;
-			$FN =~ s/\.dir$// if $Is_VMS;
+			$FN =~ s/\.dir\z// if $Is_VMS;
 			push @Stack,[$CdLvl,$dir_name,$FN,$sub_nlink];
 		    }
 		    else {
@@ -609,7 +609,7 @@ sub _find_dir_symlnk($$$) {
 	closedir(DIR);
 
 	for my $FN (@filenames) {
-	    next if $FN =~ /^\.{1,2}$/;
+	    next if $FN =~ /^\.{1,2}\z/;
 
 	    # follow symbolic links / do an lstat
 	    $new_loc = Follow_SymLink($loc_pref.$FN);
diff --git a/lib/fields.pm b/lib/fields.pm
index bc9e51320f..5a84e28f2e 100644
--- a/lib/fields.pm
+++ b/lib/fields.pm
@@ -8,59 +8,117 @@ fields - compile-time class fields
 
     {
         package Foo;
-        use fields qw(foo bar _private);
+        use fields qw(foo bar _Foo_private);
+	sub new {
+	    my Foo $self = shift;
+	    unless (ref $self) {
+		$self = fields::new($self);
+		$self->{_Foo_private} = "this is Foo's secret";
+	    }
+	    $self->{foo} = 10;
+	    $self->{bar} = 20;
+	    return $self;
+	}
     }
-    ...
-    my Foo $var = new Foo;
+
+    my Foo $var = Foo::->new;
     $var->{foo} = 42;
 
-    # This will generate a compile-time error.
+    # this will generate a compile-time error
     $var->{zap} = 42;
 
+    # subclassing
     {
         package Bar;
         use base 'Foo';
-        use fields 'bar';             # hides Foo->{bar}
-        use fields qw(baz _private);  # not shared with Foo
+        use fields qw(baz _Bar_private);	# not shared with Foo
+	sub new {
+	    my $class = shift;
+	    my $self = fields::new($class);
+	    $self->SUPER::new();		# init base fields
+	    $self->{baz} = 10;			# init own fields
+	    $self->{_Bar_private} = "this is Bar's secret";
+	    return $self;
+	}
     }
 
 =head1 DESCRIPTION
 
-The C<fields> pragma enables compile-time verified class fields.  It
-does so by updating the %FIELDS hash in the calling package.
+The C<fields> pragma enables compile-time verified class fields.
+
+NOTE: The current implementation keeps the declared fields in the %FIELDS
+hash of the calling package, but this may change in future versions.
+Do B<not> update the %FIELDS hash directly, because it must be created
+at compile-time for it to be fully useful, as is done by this pragma.
 
 If a typed lexical variable holding a reference is used to access a
-hash element and the %FIELDS hash of the given type exists, then the
-operation is turned into an array access at compile time.  The %FIELDS
-hash maps from hash element names to the array indices.  If the hash
-element is not present in the %FIELDS hash, then a compile-time error
-is signaled.
-
-Since the %FIELDS hash is used at compile-time, it must be set up at
-compile-time too.  This is made easier with the help of the 'fields'
-and the 'base' pragma modules.  The 'base' pragma will copy fields
-from base classes and the 'fields' pragma adds new fields.  Field
-names that start with an underscore character are made private to a
-class and are not visible to subclasses.  Inherited fields can be
+hash element and a package with the same name as the type has declared
+class fields using this pragma, then the operation is turned into an
+array access at compile time.
+
+The related C<base> pragma will combine fields from base classes and any
+fields declared using the C<fields> pragma.  This enables field
+inheritance to work properly.
+
+Field names that start with an underscore character are made private to
+the class and are not visible to subclasses.  Inherited fields can be
 overridden but will generate a warning if used together with the C<-w>
 switch.
 
 The effect of all this is that you can have objects with named fields
 which are as compact and as fast arrays to access.  This only works
 as long as the objects are accessed through properly typed variables.
-For untyped access to work you have to make sure that a reference to
-the proper %FIELDS hash is assigned to the 0'th element of the array
-object (so that the objects can be treated like an pseudo-hash).  A
-constructor like this does the job:
+If the objects are not typed, access is only checked at run time.
+
+The following functions are supported:
+
+=over 8
+
+=item new
 
-  sub new
-  {
-      my $class = shift;
-      no strict 'refs';
-      my $self = bless [\%{"$class\::FIELDS"}], $class;
-      $self;
-  }
+fields::new() creates and blesses a pseudo-hash comprised of the fields
+declared using the C<fields> pragma into the specified class.
+This makes it possible to write a constructor like this:
+
+    package Critter::Sounds;
+    use fields qw(cat dog bird);
+
+    sub new {
+	my Critter::Sounds $self = shift;
+	$self = fields::new($self) unless ref $self;
+	$self->{cat} = 'meow';				# scalar element
+	@$self{'dog','bird'} = ('bark','tweet');	# slice
+	return $self;
+    }
+
+=item phash
+
+fields::phash() can be used to create and initialize a plain (unblessed)
+pseudo-hash.  This function should always be used instead of creating
+pseudo-hashes directly.
+
+If the first argument is a reference to an array, the pseudo-hash will
+be created with keys from that array.  If a second argument is supplied,
+it must also be a reference to an array whose elements will be used as
+the values.  If the second array contains less elements than the first,
+the trailing elements of the pseudo-hash will not be initialized.
+This makes it particularly useful for creating a pseudo-hash from
+subroutine arguments:
+
+    sub dogtag {
+	my $tag = fields::phash([qw(name rank ser_num)], [@_]);
+    }
 
+fields::phash() also accepts a list of key-value pairs that will
+be used to construct the pseudo hash.  Examples:
+
+    my $tag = fields::phash(name => "Joe",
+			    rank => "captain",
+			    ser_num => 42);
+
+    my $pseudohash = fields::phash(%args);
+
+=back
 
 =head1 SEE ALSO
 
@@ -92,6 +150,8 @@ sub import {
     my $class = shift;
     return unless @_;
     my $package = caller(0);
+    # avoid possible typo warnings
+    %{"$package\::FIELDS"} = () unless %{"$package\::FIELDS"};
     my $fields = \%{"$package\::FIELDS"};
     my $fattr = ($attr{$package} ||= [1]);
     my $next = @$fattr;
@@ -131,11 +191,13 @@ sub import {
     }
 }
 
-sub inherit  # called by base.pm when $base_fields is nonempty
-{
+sub inherit  { # called by base.pm when $base_fields is nonempty
     my($derived, $base) = @_;
     my $base_attr = $attr{$base};
     my $derived_attr = $attr{$derived} ||= [];
+    # avoid possible typo warnings
+    %{"$base\::FIELDS"} = () unless %{"$base\::FIELDS"};
+    %{"$derived\::FIELDS"} = () unless %{"$derived\::FIELDS"};
     my $base_fields    = \%{"$base\::FIELDS"};
     my $derived_fields = \%{"$derived\::FIELDS"};
 
@@ -157,27 +219,66 @@ sub inherit  # called by base.pm when $base_fields is nonempty
 
 sub _dump  # sometimes useful for debugging
 {
-   for my $pkg (sort keys %attr) {
-      print "\n$pkg";
-      if (@{"$pkg\::ISA"}) {
-         print " (", join(", ", @{"$pkg\::ISA"}), ")";
-      }
-      print "\n";
-      my $fields = \%{"$pkg\::FIELDS"};
-      for my $f (sort {$fields->{$a} <=> $fields->{$b}} keys %$fields) {
-         my $no = $fields->{$f};
-         print "   $no: $f";
-         my $fattr = $attr{$pkg}[$no];
-         if (defined $fattr) {
-            my @a;
-	    push(@a, "public")    if $fattr & _PUBLIC;
-            push(@a, "private")   if $fattr & _PRIVATE;
-            push(@a, "inherited") if $no < $attr{$pkg}[0];
-            print "\t(", join(", ", @a), ")";
-         }
-         print "\n";
-      }
-   }
+    for my $pkg (sort keys %attr) {
+	print "\n$pkg";
+	if (@{"$pkg\::ISA"}) {
+	    print " (", join(", ", @{"$pkg\::ISA"}), ")";
+	}
+	print "\n";
+	my $fields = \%{"$pkg\::FIELDS"};
+	for my $f (sort {$fields->{$a} <=> $fields->{$b}} keys %$fields) {
+	    my $no = $fields->{$f};
+	    print "   $no: $f";
+	    my $fattr = $attr{$pkg}[$no];
+	    if (defined $fattr) {
+		my @a;
+		push(@a, "public")    if $fattr & _PUBLIC;
+		push(@a, "private")   if $fattr & _PRIVATE;
+		push(@a, "inherited") if $no < $attr{$pkg}[0];
+		print "\t(", join(", ", @a), ")";
+	    }
+	    print "\n";
+	}
+    }
+}
+
+sub new {
+    my $class = shift;
+    $class = ref $class if ref $class;
+    return bless [\%{$class . "::FIELDS"}], $class;
+}
+
+sub phash {
+    my $h;
+    my $v;
+    if (@_) {
+	if (ref $_[0] eq 'ARRAY') {
+	    my $a = shift;
+	    @$h{@$a} = 1 .. @$a;
+	    if (@_) {
+		$v = shift;
+		unless (! @_ and ref $v eq 'ARRAY') {
+		    require Carp;
+		    Carp::croak ("Expected at most two array refs\n");
+		}
+	    }
+	}
+	else {
+	    if (@_ % 2) {
+		require Carp;
+		Carp::croak ("Odd number of elements initializing pseudo-hash\n");
+	    }
+	    my $i = 0;
+	    @$h{grep ++$i % 2, @_} = 1 .. @_ / 2;
+	    $i = 0;
+	    $v = [grep $i++ % 2, @_];
+	}
+    }
+    else {
+	$h = {};
+	$v = [];
+    }
+    [ $h, @$v ];
 }
 
 1;