# Copyright (c) 1996, 1997, 1998 Malcolm Beattie
# You may distribute under the terms of either the GNU General Public
# License or the Artistic License, as specified in the README file.
our $VERSION = '1.09_01';
# walkoptree_slow comes from B.pm (you are there),
# walkoptree comes from B.xs
@EXPORT_OK = qw(minus_c ppname save_BEGINs
class peekop cast_I32 cstring cchar hash threadsv_names
main_root main_start main_cv svref_2object opnumber
amagic_generation perlstring
walkoptree_slow walkoptree walkoptree_exec walksymtable
parents comppadlist sv_undef compile_stats timing_info
begin_av init_av check_av end_av regex_padav dowarn
defstash curstash warnhook diehook inc_gv
@B::SV
::ISA
= 'B::OBJECT';
@B::PVIV
::ISA
= qw(B::PV B::IV);
@B::PVNV
::ISA
= qw(B::PVIV B::NV);
@B::PVMG
::ISA
= 'B::PVNV';
# Change in the inheritance hierarchy post 5.9.0
@B::PVLV
::ISA
= $] > 5.009 ?
'B::GV' : 'B::PVMG';
@B::OP
::ISA
= 'B::OBJECT';
@B::BINOP
::ISA
= 'B::UNOP';
@B::LOGOP
::ISA
= 'B::UNOP';
@B::LISTOP
::ISA
= 'B::BINOP';
@B::PADOP
::ISA
= 'B::OP';
@B::LOOP
::ISA
= 'B::LISTOP';
@B::PMOP
::ISA
= 'B::LISTOP';
@B::SPECIAL
::ISA
= 'B::OBJECT';
# Stop "-w" from complaining about the lack of a real B::OBJECT class
my $name = (shift())->NAME;
# The regex below corresponds to the isCONTROLVAR macro
$name =~ s
/^([\cA-\cZ\c\\c[\c]\c?\c_\c^])/"^".
chr( utf8
::unicode_to_native
( 64 ^ ord($1) ))/e
;
# When we say unicode_to_native we really mean ascii_to_native,
# which matters iff this is a non-ASCII platform (EBCDIC).
return (($self->FLAGS() & SVf_IVisUV
()) ?
$self->UVX : $self->IV);
sub B
::NULL
::as_string
() {""}
sub B
::IV
::as_string
() {goto &B
::IV
::int_value
}
sub B
::PV
::as_string
() {goto &B
::PV
::PV
}
my ($class, $value) = @_;
walkoptree_debug
($value);
sub parents
{ \
@parents }
return sprintf("%s (0x%x) %s", class($op), $$op, $op->name);
my($op, $method, $level) = @_;
$op_count++; # just for statistics
warn(sprintf("walkoptree: %d. %s\n", $level, peekop
($op))) if $debug;
if ($$op && ($op->flags & OPf_KIDS
)) {
for ($kid = $op->first; $$kid; $kid = $kid->sibling) {
walkoptree_slow
($kid, $method, $level + 1);
if (class($op) eq 'PMOP' && ref($op->pmreplroot) && ${$op->pmreplroot}) {
walkoptree_slow
($op->pmreplroot, $method, $level + 1);
return "Total number of OPs processed: $op_count\n";
my ($sec, $min, $hr) = localtime;
my ($user, $sys) = times;
sprintf("%02d:%02d:%02d user=$user sys=$sys",
$hr, $min, $sec, $user, $sys);
# warn(sprintf("savesym: sym_%x => %s\n", $$obj, $value)); # debug
$symtable{sprintf("sym_%x", $$obj)} = $value;
return $symtable{sprintf("sym_%x", $$obj)};
my ($op, $method, $level) = @_;
my $prefix = " " x
$level;
for (; $$op; $op = $op->next) {
print $prefix, "goto $sym\n";
savesym
($op, sprintf("%s (0x%lx)", class($op), $$op));
/^(d?or(assign)?|and(assign)?|mapwhile|grepwhile|entertry|range|cond_expr)$/)
print $prefix, uc($1), " => {\n";
walkoptree_exec
($op->other, $method, $level + 1);
} elsif ($ppname eq "match" || $ppname eq "subst") {
my $pmreplstart = $op->pmreplstart;
print $prefix, "PMREPLSTART => {\n";
walkoptree_exec
($pmreplstart, $method, $level + 1);
} elsif ($ppname eq "substcont") {
print $prefix, "SUBSTCONT => {\n";
walkoptree_exec
($op->other->pmreplstart, $method, $level + 1);
} elsif ($ppname eq "enterloop") {
print $prefix, "REDO => {\n";
walkoptree_exec
($op->redoop, $method, $level + 1);
print $prefix, "}\n", $prefix, "NEXT => {\n";
walkoptree_exec
($op->nextop, $method, $level + 1);
print $prefix, "}\n", $prefix, "LAST => {\n";
walkoptree_exec
($op->lastop, $method, $level + 1);
} elsif ($ppname eq "subst") {
my $replstart = $op->pmreplstart;
print $prefix, "SUBST => {\n";
walkoptree_exec
($replstart, $method, $level + 1);
my ($symref, $method, $recurse, $prefix) = @_;
$prefix = '' unless defined $prefix;
while (($sym, $ref) = each %$symref) {
$fullname = "*main::".$prefix.$sym;
if ($sym ne "main::" && $sym ne "<none>::" && &$recurse($sym)) {
walksymtable
(\
%$fullname, $method, $recurse, $sym);
svref_2object
(\
*$fullname)->$method();
my ($class, $section, $symtable, $default) = @_;
$output_fh ||= FileHandle
->new_tmpfile;
my $obj = bless [-1, $section, $symtable, $default], $class;
$sections{$section} = $obj;
my ($class, $section) = @_;
return $sections{$section};
while (defined($_ = shift)) {
print $output_fh "$section->[1]\t$_\n";
my ($section, $fh, $format) = @_;
my $name = $section->name;
my $sym = $section->symtable || {};
my $default = $section->default;
exists($sym->{$1}) ?
$sym->{$1} : $default;
The C<B> module supplies classes which allow a Perl program to delve
into its own innards. It is the module used to implement the
"backends" of the Perl compiler. Usage of the compiler does not
require knowledge of this module: see the F<O> module for the
user-visible part. The C<B> module is of use to those who want to
write new compiler backends. This documentation assumes that the
reader knows a fair amount about perl's internals including such
things as SVs, OPs and the internal symbol table and syntax tree
The C<B> module contains a set of utility functions for querying the
current state of the Perl interpreter; typically these functions
return objects from the B::SV and B::OP classes, or their derived
classes. These classes in turn define methods for querying the
resulting objects about their own internal state.
The C<B> module exports a variety of functions: some are simple
utility functions, others provide a Perl program with a way to
get an initial "handle" on an internal object.
=head2 Functions Returning C<B::SV>, C<B::AV>, C<B::HV>, and C<B::CV> objects
For descriptions of the class hierarchy of these objects and the
methods that can be called on them, see below, L<"OVERVIEW OF
CLASSES"> and L<"SV-RELATED CLASSES">.
Returns the SV object corresponding to the C variable C<sv_undef>.
Returns the SV object corresponding to the C variable C<sv_yes>.
Returns the SV object corresponding to the C variable C<sv_no>.
=item svref_2object(SVREF)
Takes a reference to any Perl value, and turns the referred-to value
into an object in the appropriate B::OP-derived or B::SV-derived
class. Apart from functions such as C<main_root>, this is the primary
way to get an initial "handle" on an internal perl data structure
which can then be followed with the other access methods.
The returned object will only be valid as long as the underlying OPs
and SVs continue to exist. Do not attempt to use the object after the
underlying structures are freed.
Returns the SV object corresponding to the C variable C<amagic_generation>.
Returns the AV object (i.e. in class B::AV) representing INIT blocks.
Returns the AV object (i.e. in class B::AV) representing CHECK blocks.
Returns the AV object (i.e. in class B::AV) representing BEGIN blocks.
Returns the AV object (i.e. in class B::AV) representing END blocks.
Returns the AV object (i.e. in class B::AV) of the global comppadlist.
Only when perl was compiled with ithreads.
Return the (faked) CV corresponding to the main part of the Perl
=head2 Functions for Examining the Symbol Table
=item walksymtable(SYMREF, METHOD, RECURSE, PREFIX)
Walk the symbol table starting at SYMREF and call METHOD on each
symbol (a B::GV object) visited. When the walk reaches package
symbols (such as "Foo::") it invokes RECURSE, passing in the symbol
name, and only recurses into the package if that sub returns true.
PREFIX is the name of the SYMREF you're walking.
# Walk CGI's symbol table calling print_subs on each symbol.
# Recurse only into CGI::Util::
walksymtable(\%CGI::, 'print_subs', sub { $_[0] eq 'CGI::Util::' },
print_subs() is a B::GV method you have declared. Also see L<"B::GV
=head2 Functions Returning C<B::OP> objects or for walking op trees
For descriptions of the class hierarchy of these objects and the
methods that can be called on them, see below, L<"OVERVIEW OF
CLASSES"> and L<"OP-RELATED CLASSES">.
Returns the root op (i.e. an object in the appropriate B::OP-derived
class) of the main part of the Perl program.
Returns the starting op of the main part of the Perl program.
=item walkoptree(OP, METHOD)
Does a tree-walk of the syntax tree based at OP and calls METHOD on
each op it visits. Each node is visited before its children. If
C<walkoptree_debug> (see below) has been called to turn debugging on then
the method C<walkoptree_debug> is called on each op before METHOD is
=item walkoptree_debug(DEBUG)
Returns the current debugging flag for C<walkoptree>. If the optional
DEBUG argument is non-zero, it sets the debugging flag to that. See
the description of C<walkoptree> above for what the debugging flag
=head2 Miscellaneous Utility Functions
Return the PP function name (e.g. "pp_add") of op number OPNUM.
Returns a string in the form "0x..." representing the value of the
internal hash function used by perl on string STR.
Casts I to the internal I32 type used by that perl.
Does the equivalent of the C<-c> command-line option. Obviously, this
is only useful in a BEGIN block or else the flag is set too late.
Returns a double-quote-surrounded escaped version of STR which can
be used as a string in C source code.
Returns a double-quote-surrounded escaped version of STR which can
be used as a string in Perl source code.
Returns the class of an object without the part of the classname
preceding the first C<"::">. This is used to turn C<"B::UNOP"> into
In a perl compiled for threads, this returns a list of the special
per-thread threadsv variables.
=head1 OVERVIEW OF CLASSES
The C structures used by Perl's internals to hold SV and OP
information (PVIV, AV, HV, ..., OP, SVOP, UNOP, ...) are modelled on a
class hierarchy and the C<B> module gives access to them via a true
object hierarchy. Structure fields which point to other objects
(whether types of SV or types of OP) are represented by the C<B>
module as Perl objects of the appropriate class.
The bulk of the C<B> module is the methods for accessing fields of
Note that all access is read-only. You cannot modify the internals by
using this module. Also, note that the B::OP and B::SV objects created
by this module are only valid for as long as the underlying objects
exist; their creation doesn't increase the reference counts of the
underlying objects. Trying to access the fields of a freed object will
give incomprehensible results, or worse.
=head2 SV-RELATED CLASSES
B::IV, B::NV, B::RV, B::PV, B::PVIV, B::PVNV, B::PVMG, B::BM, B::PVLV,
B::AV, B::HV, B::CV, B::GV, B::FM, B::IO. These classes correspond in
the obvious way to the underlying C structures of similar names. The
inheritance hierarchy mimics the underlying C "inheritance". For 5.9.1
+--------------+----------+------------+
+-----+----+------+-----+-----+
B::BM B::AV B::GV B::HV B::CV B::IO
For 5.9.0 and earlier, PVLV is a direct subclass of PVMG, so the base
+------+-----+----+------+-----+-----+
B::PVLV B::BM B::AV B::GV B::HV B::CV B::IO
Access methods correspond to the underlying C macros for field access,
usually with the leading "class indication" prefix removed (Sv, Av,
Hv, ...). The leading prefix is only left in cases where its removal
would cause a clash in method name. For example, C<GvREFCNT> stays
as-is since its abbreviation would clash with the "superclass" method
C<REFCNT> (corresponding to the C function C<SvREFCNT>).
Returns a reference to the regular scalar corresponding to this
B::SV object. In other words, this method is the inverse operation
to the svref_2object() subroutine. This scalar and other data it points
at should be considered read-only: modifying them is neither safe nor
guaranteed to have a sensible effect.
Returns the value of the IV, I<interpreted as
a signed integer>. This will be misleading
if C<FLAGS & SVf_IVisUV>. Perhaps you want the
C<int_value> method instead?
This method returns the value of the IV as an integer.
It differs from C<IV> in that it returns the correct
value regardless of whether it's stored signed or
This method is the one you usually want. It constructs a
string using the length and offset information in the struct:
for ordinary scalars it will return the string that you'd see
from Perl, even if it contains null characters.
Same as B::RV::RV, except that it will die() if the PV isn't
This method is less often useful. It assumes that the string
stored in the struct is null-terminated, and disregards the
It is the appropriate method to use if you need to get the name
of a lexical variable from a padname array. Lexical variable names
are always stored with a null terminator, and the length field
(SvCUR) is overloaded for other purposes and can't be relied on here.
Only valid on r-magic, returns the string that generated the regexp.
Will die() if called on r-magic.
Only valid on r-magic, returns the integer value of the REGEX stored
This method returns TRUE if the GP field of the GV is NULL.
This method returns the name of the glob, but if the first
character of the name is a control character, then it converts
it to ^X first, so that *^G would return "^G" rather than "\cG".
It's useful if you want to print out the name of a variable.
If you restrict yourself to globs which exist at compile-time
then the result ought to be unambiguous, because code like
C<${"^G"} = 1> is compiled as two ops - a constant string and
a dereference (rv2gv) - so that the glob is created at runtime.
If you're working with globs at runtime, and need to disambiguate
*^G from *{"^G"}, then you should use the raw NAME method.
Takes one arguments ( 'stdin' | 'stdout' | 'stderr' ) and returns true
if the IoIFP of the object is equal to the handle whose name was
passed as argument ( i.e. $io->IsSTD('stderr') is true if
IoIFP($io) == PerlIO_stdin() ).
Like C<ARRAY>, but takes an index as an argument to get only one element,
rather than a list of all of them.
For constant subroutines, returns the constant SV returned by the subroutine.
=head2 OP-RELATED CLASSES
C<B::OP>, C<B::UNOP>, C<B::BINOP>, C<B::LOGOP>, C<B::LISTOP>, C<B::PMOP>,
C<B::SVOP>, C<B::PADOP>, C<B::PVOP>, C<B::LOOP>, C<B::COP>.
These classes correspond in the obvious way to the underlying C
structures of similar names. The inheritance hierarchy mimics the
underlying C "inheritance":
+---------------+--------+--------+
B::UNOP B::SVOP B::PADOP B::COP
Access methods correspond to the underlying C structre field names,
with the leading "class indication" prefix (C<"op_">) removed.
These methods get the values of similarly named fields within the OP
data structure. See top of C<op.h> for more info.
This returns the op name as a string (e.g. "add", "rv2av").
This returns the function name as a string (e.g. "PL_ppaddr[OP_ADD]",
This returns the op description from the global C PL_op_desc array
(e.g. "addition" "array deref").
Only when perl was compiled with ithreads.
Malcolm Beattie, C<mbeattie@sable.ox.ac.uk>