OPf_KIDS OPf_REF OPf_STACKED OPf_SPECIAL
OPpLVAL_INTRO OPpENTERSUB_AMPER OPpSLICE OPpCONST_BARE
OPpTRANS_SQUASH OPpTRANS_DELETE OPpTRANS_COMPLEMENT OPpTARGET_MY
- OPpCONST_ARYBASE
+ OPpCONST_ARYBASE OPpEXISTS_SUB
SVf_IOK SVf_NOK SVf_ROK SVf_POK
CVf_METHOD CVf_LOCKED CVf_LVALUE
- PMf_KEEP PMf_GLOBAL PMf_CONTINUE PMf_EVAL PMf_ONCE
+ PMf_KEEP PMf_GLOBAL PMf_CONTINUE PMf_EVAL PMf_ONCE PMf_SKIPWHITE
PMf_MULTILINE PMf_SINGLELINE PMf_FOLD PMf_EXTENDED);
$VERSION = 0.60;
use strict;
+use warnings ();
# Changes between 0.50 and 0.51:
# - fixed nulled leave with live enter in sort { }
# Todo:
# - finish tr/// changes
# - add option for even more parens (generalize \&foo change)
-# - {} around variables in strings ("${var}letters")
-# base/lex.t 25-27
-# comp/term.t 11
# - left/right context
-# - recognize `use utf8', `use integer', etc
# - treat top-level block specially for incremental output
-# - interpret high bit chars in string as utf8 \x{...} (when?)
# - copy comments (look at real text with $^P?)
# - avoid semis in one-statement blocks
# - associativity of &&=, ||=, ?:
# - more style options: brace style, hex vs. octal, quotes, ...
# - print big ints as hex/octal instead of decimal (heuristic?)
# - handle `my $x if 0'?
-# - include values of variables (e.g. set in BEGIN)
# - coordinate with Data::Dumper (both directions? see previous)
# - version using op_next instead of op_first/sibling?
# - avoid string copies (pass arrays, one big join?)
-# - auto-apply `-u'?
-# - -uPackage:: descend recursively?
# - here-docs?
# - <DATA>?
# curcv:
# CV for current sub (or main program) being deparsed
#
+# curcvlex:
+# Cached hash of lexical variables for curcv: keys are names,
+# each value is an array of pairs, indicating the cop_seq of scopes
+# in which a var of that name is valid.
+#
+# curcop:
+# COP for statement being deparsed
+#
# curstash:
# name of the current package for deparsed code
#
# subs_todo:
-# array of [cop_seq, GV, is_format?] for subs and formats we still
+# array of [cop_seq, CV, is_format?] for subs and formats we still
# want to deparse
#
# protos_todo:
# keys are addresses of GVs for subs and formats we've already
# deparsed (or at least put into subs_todo)
#
+# subs_declared
+# keys are names of subs for which we've printed declarations.
+# That means we can omit parentheses from the arguments.
+#
# parens: -p
# linenums: -l
# unquote: -q
sub todo {
my $self = shift;
- my($gv, $cv, $is_form) = @_;
+ my($cv, $is_form) = @_;
my $seq;
if (!null($cv->START) and is_state($cv->START)) {
$seq = $cv->START->cop_seq;
} else {
$seq = 0;
}
- push @{$self->{'subs_todo'}}, [$seq, $gv, $is_form];
+ push @{$self->{'subs_todo'}}, [$seq, $cv, $is_form];
}
sub next_todo {
my $self = shift;
my $ent = shift @{$self->{'subs_todo'}};
- my $name = $self->gv_name($ent->[1]);
+ my $cv = $ent->[1];
+ my $gv = $cv->GV;
+ my $name = $self->gv_name($gv);
if ($ent->[2]) {
return "format $name =\n"
. $self->deparse_format($ent->[1]->FORM). "\n";
} else {
- return "sub $name " . $self->deparse_sub($ent->[1]->CV);
+ $self->{'subs_declared'}{$name} = 1;
+ if ($name eq "BEGIN") {
+ my $use_dec = $self->begin_is_use($cv);
+ if (defined ($use_dec)) {
+ return () if 0 == length($use_dec);
+ return $use_dec;
+ }
+ }
+ return "sub $name " . $self->deparse_sub($cv);
+ }
+}
+
+# Return a "use" declaration for this BEGIN block, if appropriate
+sub begin_is_use {
+ my ($self, $cv) = @_;
+ my $root = $cv->ROOT;
+#require B::Debug;
+#B::walkoptree($cv->ROOT, "debug");
+ my $lineseq = $root->first;
+ return if $lineseq->name ne "lineseq";
+
+ my $req_op = $lineseq->first->sibling;
+ return if $req_op->name ne "require";
+
+ my $module;
+ if ($req_op->first->private & OPpCONST_BARE) {
+ # Actually it should always be a bareword
+ $module = $self->const_sv($req_op->first)->PV;
+ $module =~ s[/][::]g;
+ $module =~ s/.pm$//;
+ }
+ else {
+ $module = const($self->const_sv($req_op->first));
+ }
+
+ my $version;
+ my $version_op = $req_op->sibling;
+ return if class($version_op) eq "NULL";
+ if ($version_op->name eq "lineseq") {
+ # We have a version parameter; skip nextstate & pushmark
+ my $constop = $version_op->first->next->next;
+
+ return unless $self->const_sv($constop)->PV eq $module;
+ $constop = $constop->sibling;
+
+ $version = $self->const_sv($constop)->int_value;
+ $constop = $constop->sibling;
+ return if $constop->name ne "method_named";
+ return if $self->const_sv($constop)->PV ne "VERSION";
+ }
+
+ $lineseq = $version_op->sibling;
+ return if $lineseq->name ne "lineseq";
+ my $entersub = $lineseq->first->sibling;
+ if ($entersub->name eq "stub") {
+ return "use $module $version ();\n" if defined $version;
+ return "use $module ();\n";
+ }
+ return if $entersub->name ne "entersub";
+
+ # See if there are import arguments
+ my $args = '';
+
+ my $constop = $entersub->first->sibling; # Skip over pushmark
+ return unless $self->const_sv($constop)->PV eq $module;
+
+ # Pull out the arguments
+ for ($constop=$constop->sibling; $constop->name eq "const";
+ $constop = $constop->sibling) {
+ $args .= ", " if length($args);
+ $args .= $self->deparse($constop, 6);
+ }
+
+ my $use = 'use';
+ my $method_named = $constop;
+ return if $method_named->name ne "method_named";
+ my $method_name = $self->const_sv($method_named)->PV;
+
+ if ($method_name eq "unimport") {
+ $use = 'no';
+ }
+
+ # Certain pragmas are dealt with using hint bits,
+ # so we ignore them here
+ if ($module eq 'strict' || $module eq 'integer'
+ || $module eq 'bytes' || $module eq 'warnings') {
+ return "";
+ }
+
+ if (defined $version && length $args) {
+ return "$use $module $version ($args);\n";
+ } elsif (defined $version) {
+ return "$use $module $version;\n";
+ } elsif (length $args) {
+ return "$use $module ($args);\n";
+ } else {
+ return "$use $module;\n";
}
}
if ($op->next->name eq "entersub") {
return if $self->{'subs_done'}{$$gv}++;
return if class($gv->CV) eq "SPECIAL";
- $self->todo($gv, $gv->CV, 0);
+ $self->todo($gv->CV, 0);
$self->walk_sub($gv->CV);
} elsif ($op->next->name eq "enterwrite"
or ($op->next->name eq "rv2gv"
and $op->next->next->name eq "enterwrite")) {
return if $self->{'forms_done'}{$$gv}++;
return if class($gv->FORM) eq "SPECIAL";
- $self->todo($gv, $gv->FORM, 1);
+ $self->todo($gv->FORM, 1);
$self->walk_sub($gv->FORM);
}
}
}
sub stash_subs {
- my $self = shift;
- my $pack = shift;
- my(%stash, @ret);
- { no strict 'refs'; %stash = svref_2object(\%{$pack . "::"})->ARRAY }
- if ($pack eq "main") {
- $pack = "";
- } else {
- $pack = $pack . "::";
+ my ($self, $pack) = @_;
+ my (@ret, $stash);
+ if (!defined $pack) {
+ $pack = '';
+ $stash = \%::;
}
- my($key, $val);
- while (($key, $val) = each %stash) {
+ else {
+ $pack =~ s/(::)?$/::/;
+ no strict 'refs';
+ $stash = \%$pack;
+ }
+ my %stash = svref_2object($stash)->ARRAY;
+ while (my ($key, $val) = each %stash) {
+ next if $key eq 'main::'; # avoid infinite recursion
+ next if $key eq 'B::'; # don't automatically scan B
my $class = class($val);
if ($class eq "PV") {
# Just a prototype
# Just a name
push @{$self->{'protos_todo'}}, [$pack . $key, undef];
} elsif ($class eq "GV") {
- if (class($val->CV) ne "SPECIAL") {
+ if (class(my $cv = $val->CV) ne "SPECIAL") {
+ next unless $cv->FILE eq $0 || $self->{'files'}{$cv->FILE};
next if $self->{'subs_done'}{$$val}++;
- $self->todo($val, $val->CV, 0);
- $self->walk_sub($val->CV);
+ next if ${$cv->GV} != $$val;
+ $self->todo($cv, 0);
+ $self->walk_sub($cv);
}
if (class($val->FORM) ne "SPECIAL") {
next if $self->{'forms_done'}{$$val}++;
- $self->todo($val, $val->FORM, 1);
+ $self->todo($val->FORM, 1);
$self->walk_sub($val->FORM);
}
+ if (class($val->HV) ne "SPECIAL" && $key =~ /::$/) {
+ $self->stash_subs($pack . $key);
+ }
}
}
}
my $class = shift;
my $self = bless {}, $class;
$self->{'subs_todo'} = [];
+ $self->{'files'} = {};
$self->{'curstash'} = "main";
+ $self->{'curcop'} = undef;
$self->{'cuddle'} = "\n";
$self->{'indent_size'} = 4;
$self->{'use_tabs'} = 0;
$self->{'linenums'} = 0;
$self->{'parens'} = 0;
$self->{'ex_const'} = "'???'";
- $self->{'arybase'} = 0;
- $self->{'warnings'} = "\0"x12;
+
+ $self->{'ambient_arybase'} = 0;
+ $self->{'ambient_warnings'} = "\0"x12;
+ $self->{'ambient_hints'} = 0;
+ $self->init();
+
while (my $arg = shift @_) {
- if (substr($arg, 0, 2) eq "-u") {
- $self->stash_subs(substr($arg, 2));
+ if ($arg =~ /^-f(.*)/) {
+ $self->{'files'}{$1} = 1;
} elsif ($arg eq "-p") {
$self->{'parens'} = 1;
} elsif ($arg eq "-l") {
return $self;
}
+sub WARN_MASK () {
+ # Mask out the bits that C<use vars> uses
+ $warnings::Bits{all} | $warnings::DeadBits{all};
+}
+
+# Initialise the contextual information, either from
+# defaults provided with the ambient_pragmas method,
+# or from perl's own defaults otherwise.
+sub init {
+ my $self = shift;
+
+ $self->{'arybase'} = $self->{'ambient_arybase'};
+ $self->{'warnings'} = $self->{'ambient_warnings'} & WARN_MASK;
+ $self->{'hints'} = $self->{'ambient_hints'} & 0xFF;
+
+ # also a convenient place to clear out subs_declared
+ delete $self->{'subs_declared'};
+}
+
sub compile {
my(@args) = @_;
return sub {
my $self = B::Deparse->new(@args);
- $self->stash_subs("main");
+ my @BEGINs = B::begin_av->isa("B::AV") ? B::begin_av->ARRAY : ();
+ my @INITs = B::init_av->isa("B::AV") ? B::init_av->ARRAY : ();
+ my @ENDs = B::end_av->isa("B::AV") ? B::end_av->ARRAY : ();
+ for my $block (@BEGINs, @INITs, @ENDs) {
+ if ($block->FILE eq $0 || $self->{'files'}{$block->FILE}) {
+ $self->todo($block, 0);
+ $self->walk_sub($block);
+ }
+ }
+ $self->stash_subs();
$self->{'curcv'} = main_cv;
+ $self->{'curcvlex'} = undef;
$self->walk_sub(main_cv, main_start);
print $self->print_protos;
@{$self->{'subs_todo'}} =
my $self = shift;
my $sub = shift;
croak "Usage: ->coderef2text(CODEREF)" unless ref($sub) eq "CODE";
+
+ $self->init();
return $self->indent($self->deparse_sub(svref_2object($sub)));
}
+sub ambient_pragmas {
+ my $self = shift;
+ my ($arybase, $hint_bits, $warning_bits) = (0, 0, "\0"x12);
+
+ while (@_ > 1) {
+ my $name = shift();
+ my $val = shift();
+
+ if ($name eq 'strict') {
+ require strict;
+
+ if ($val eq 'none') {
+ $hint_bits &= ~strict::bits(qw/refs subs vars/);
+ next();
+ }
+
+ my @names;
+ if ($val eq "all") {
+ @names = qw/refs subs vars/;
+ }
+ elsif (ref $val) {
+ @names = @$val;
+ }
+ else {
+ @names = split' ', $val;
+ }
+ $hint_bits |= strict::bits(@names);
+ }
+
+ elsif ($name eq '$[') {
+ $arybase = $val;
+ }
+
+ elsif ($name eq 'integer'
+ || $name eq 'bytes'
+ || $name eq 'utf8') {
+ require "$name.pm";
+ if ($val) {
+ $hint_bits |= ${$::{"${name}::"}{"hint_bits"}};
+ }
+ else {
+ $hint_bits &= ~${$::{"${name}::"}{"hint_bits"}};
+ }
+ }
+
+ elsif ($name eq 're') {
+ require re;
+ if ($val eq 'none') {
+ $hint_bits &= ~re::bits(qw/taint eval asciirange/);
+ next();
+ }
+
+ my @names;
+ if ($val eq 'all') {
+ @names = qw/taint eval asciirange/;
+ }
+ elsif (ref $val) {
+ @names = @$val;
+ }
+ else {
+ @names = split' ',$val;
+ }
+ $hint_bits |= re::bits(@names);
+ }
+
+ elsif ($name eq 'warnings') {
+ if ($val eq 'none') {
+ $warning_bits = "\0"x12;
+ next();
+ }
+
+ my @names;
+ if (ref $val) {
+ @names = @$val;
+ }
+ else {
+ @names = split/\s+/, $val;
+ }
+
+ $warning_bits |= warnings::bits(@names);
+ }
+
+ elsif ($name eq 'warning_bits') {
+ $warning_bits = $val;
+ }
+
+ elsif ($name eq 'hint_bits') {
+ $hint_bits = $val;
+ }
+
+ else {
+ croak "Unknown pragma type: $name";
+ }
+ }
+ if (@_) {
+ croak "The ambient_pragmas method expects an even number of args";
+ }
+
+ $self->{'ambient_arybase'} = $arybase;
+ $self->{'ambient_warnings'} = $warning_bits;
+ $self->{'ambient_hints'} = $hint_bits;
+}
+
sub deparse {
my $self = shift;
my($op, $cx) = @_;
-# cluck if class($op) eq "NULL";
-# cluck unless $op;
-# return $self->$ {\("pp_" . $op->name)}($op, $cx);
-require Carp;
-Carp::confess() unless defined $op;
+
+ Carp::confess("Null op in deparse") if !defined($op)
+ || class($op) eq "NULL";
my $meth = "pp_" . $op->name;
return $self->$meth($op, $cx);
}
my $self = shift;
my $cv = shift;
my $proto = "";
+Carp::confess("SPECIAL in deparse_sub") if $cv->isa("B::SPECIAL");
+ local $self->{'curcop'} = $self->{'curcop'};
if ($cv->FLAGS & SVf_POK) {
$proto = "(". $cv->PV . ") ";
}
}
local($self->{'curcv'}) = $cv;
- local($self->{'curstash'}) = $self->{'curstash'};
+ local($self->{'curcvlex'});
+ local(@$self{qw'curstash warnings hints'})
+ = @$self{qw'curstash warnings hints'};
if (not null $cv->ROOT) {
# skip leavesub
return $proto . "{\n\t" .
if ($$sv) {
# uh-oh. inlinable sub... format it differently
return $proto . "{ " . const($sv) . " }\n";
- } else { # XSUB?
- return $proto . "{}\n";
+ } else { # XSUB? (or just a declaration)
+ return "$proto;\n";
}
}
my $form = shift;
my @text;
local($self->{'curcv'}) = $form;
- local($self->{'curstash'}) = $self->{'curstash'};
+ local($self->{'curcvlex'});
+ local(@$self{qw'curstash warnings hints'})
+ = @$self{'curstash warnings hints'};
my $op = $form->ROOT;
my $kid;
$op = $op->first->first; # skip leavewrite, lineseq
my($real_block, $self, $op, $cx) = @_;
my $kid;
my @kids;
- local($self->{'curstash'}) = $self->{'curstash'} if $real_block;
+
+ local(@$self{qw'curstash warnings hints'})
+ = @$self{qw'curstash warnings hints'} if $real_block;
if ($real_block) {
$kid = $op->first->sibling; # skip enter
if (is_miniwhile($kid)) {
sub gv_name {
my $self = shift;
my $gv = shift;
+Carp::confess() if $gv->isa("B::CV");
my $stash = $gv->STASH->NAME;
my $name = $gv->SAFENAME;
if ($stash eq $self->{'curstash'} or $globalnames{$name}
return $stash . $name;
}
-# Notice how subs and formats are inserted between statements here
-sub pp_nextstate {
+# Return the name to use for a stash variable.
+# If a lexical with the same name is in scope, it may need to be
+# fully-qualified.
+sub stash_variable {
+ my ($self, $prefix, $name) = @_;
+
+ return "$prefix$name" if $name =~ /::/;
+
+ unless ($prefix eq '$' || $prefix eq '@' ||
+ $prefix eq '%' || $prefix eq '$#') {
+ return "$prefix$name";
+ }
+
+ my $v = ($prefix eq '$#' ? '@' : $prefix) . $name;
+ return $prefix .$self->{'curstash'}.'::'. $name if $self->lex_in_scope($v);
+ return "$prefix$name";
+}
+
+sub lex_in_scope {
+ my ($self, $name) = @_;
+ $self->populate_curcvlex() if !defined $self->{'curcvlex'};
+
+ my $seq = $self->{'curcop'}->cop_seq;
+ return 0 if !exists $self->{'curcvlex'}{$name};
+ for my $a (@{$self->{'curcvlex'}{$name}}) {
+ my ($st, $en) = @$a;
+ return 1 if $seq > $st && $seq <= $en;
+ }
+ return 0;
+}
+
+sub populate_curcvlex {
my $self = shift;
- my($op, $cx) = @_;
- my @text;
- @text = $op->label . ": " if $op->label;
+ for (my $cv = $self->{'curcv'}; $$cv; $cv = $cv->OUTSIDE) {
+ my @padlist = $cv->PADLIST->ARRAY;
+ my @ns = $padlist[0]->ARRAY;
+
+ for (my $i=0; $i<@ns; ++$i) {
+ next if class($ns[$i]) eq "SPECIAL";
+ if (class($ns[$i]) eq "PV") {
+ # Probably that pesky lexical @_
+ next;
+ }
+ my $name = $ns[$i]->PVX;
+ my $seq_st = $ns[$i]->NVX;
+ my $seq_en = int($ns[$i]->IVX);
+
+ push @{$self->{'curcvlex'}{$name}}, [$seq_st, $seq_en];
+ }
+ }
+}
+
+# Recurses down the tree, looking for a COP
+sub find_cop {
+ my ($self, $op) = @_;
+ if ($op->flags & OPf_KIDS) {
+ for (my $o=$op->first; $$o; $o=$o->sibling) {
+ return $o if is_state($o);
+ my $r = $self->find_cop($o);
+ return $r if defined $r;
+ }
+ }
+ return undef;
+}
+
+# Returns a list of subs which should be inserted before the COP
+sub cop_subs {
+ my ($self, $op, $out_seq) = @_;
my $seq = $op->cop_seq;
+ # If we have nephews, then our sequence number indicates
+ # the cop_seq of the end of some sort of scope.
+ if (class($op->sibling) ne "NULL" && $op->sibling->flags & OPf_KIDS
+ and my $ncop = $self->find_cop($op->sibling)) {
+ $seq = $ncop->cop_seq;
+ }
+ $seq = $out_seq if defined($out_seq) && $out_seq < $seq;
+ return $self->seq_subs($seq);
+}
+
+sub seq_subs {
+ my ($self, $seq) = @_;
+ my @text;
+#push @text, "# ($seq)\n";
+
while (scalar(@{$self->{'subs_todo'}})
and $seq > $self->{'subs_todo'}[0][0]) {
push @text, $self->next_todo;
}
+ return @text;
+}
+
+# Notice how subs and formats are inserted between statements here;
+# also $[ assignments and pragmas.
+sub pp_nextstate {
+ my $self = shift;
+ my($op, $cx) = @_;
+ $self->{'curcop'} = $op;
+ my @text;
+ @text = $op->label . ": " if $op->label;
+#push @text, "# ", $op->cop_seq, "\n";
+ push @text, $self->cop_subs($op);
my $stash = $op->stashpv;
if ($stash ne $self->{'curstash'}) {
push @text, "package $stash;\n";
push @text, "\f#line " . $op->line .
' "' . $op->file, qq'"\n';
}
+
if ($self->{'arybase'} != $op->arybase) {
push @text, '$[ = '. $op->arybase .";\n";
$self->{'arybase'} = $op->arybase;
$warning_bits = "\0"x12;
}
else {
- $warning_bits = $warnings->PV;
+ $warning_bits = $warnings->PV & WARN_MASK;
}
if ($self->{'warnings'} ne $warning_bits) {
- push @text, 'BEGIN {${^WARNING_BITS} = '. cstring($warning_bits) ."}\n";
+ push @text, declare_warnings($self->{'warnings'}, $warning_bits);
$self->{'warnings'} = $warning_bits;
}
+ if ($self->{'hints'} != $op->private) {
+ push @text, declare_hints($self->{'hints'}, $op->private);
+ $self->{'hints'} = $op->private;
+ }
+
return join("", @text);
}
+sub declare_warnings {
+ my ($from, $to) = @_;
+ if ($to eq warnings::bits("all")) {
+ return "use warnings;\n";
+ }
+ elsif ($to eq "\0"x12) {
+ return "no warnings;\n";
+ }
+ return "BEGIN {\${^WARNING_BITS} = ".cstring($to)."}\n";
+}
+
+sub declare_hints {
+ my ($from, $to) = @_;
+ my $bits = $to;
+ return sprintf "BEGIN {\$^H &= ~0xFF; \$^H |= %x}\n", $bits;
+}
+
sub pp_dbstate { pp_nextstate(@_) }
sub pp_setstate { pp_nextstate(@_) }
sub pp_exists {
my $self = shift;
my($op, $cx) = @_;
+ my $arg;
+ if ($op->private & OPpEXISTS_SUB) {
+ # Checking for the existence of a subroutine
+ return $self->maybe_parens_func("exists",
+ $self->pp_rv2cv($op->first, 16), $cx, 16);
+ }
+ if ($op->flags & OPf_SPECIAL) {
+ # Array element, not hash element
+ return $self->maybe_parens_func("exists",
+ $self->pp_aelem($op->first, 16), $cx, 16);
+ }
return $self->maybe_parens_func("exists", $self->pp_helem($op->first, 16),
$cx, 16);
}
my($op, $cx) = @_;
my $arg;
if ($op->private & OPpSLICE) {
+ if ($op->flags & OPf_SPECIAL) {
+ # Deleting from an array, not a hash
+ return $self->maybe_parens_func("delete",
+ $self->pp_aslice($op->first, 16),
+ $cx, 16);
+ }
return $self->maybe_parens_func("delete",
$self->pp_hslice($op->first, 16),
$cx, 16);
} else {
+ if ($op->flags & OPf_SPECIAL) {
+ # Deleting from an array, not a hash
+ return $self->maybe_parens_func("delete",
+ $self->pp_aelem($op->first, 16),
+ $cx, 16);
+ }
return $self->maybe_parens_func("delete",
$self->pp_helem($op->first, 16),
$cx, 16);
my $name = $self->const_sv($op->first)->PV;
$name =~ s[/][::]g;
$name =~ s/\.pm//g;
- return "require($name)";
+ return "require $name";
} else {
$self->unop($op, $cx, "require");
}
my($op, $cx, $init) = @_;
my $enter = $op->first;
my $kid = $enter->sibling;
- local($self->{'curstash'}) = $self->{'curstash'};
+ local(@$self{qw'curstash warnings hints'})
+ = @$self{qw'curstash warnings hints'};
my $head = "";
my $bare = 0;
my $body;
my $cond = undef;
+ my $out_seq = $self->{'curcop'}->cop_seq;;
if ($kid->name eq "lineseq") { # bare or infinite loop
if (is_state $kid->last) { # infinite
$head = "for (;;) "; # shorter than while (1)
$cont = "\cK";
$body = $self->deparse($body, 0);
}
- return $head . "{\n\t" . $body . "\n\b}" . $cont;
+ $body .= "\n";
+ # If we have say C<{my $x=2; sub x{$x}}>, the sub must go inside
+ # the loop. So we insert any subs which are due here.
+ $body .= join"", $self->seq_subs($out_seq);
+
+ return $head . "{\n\t" . $body . "\b}" . $cont;
}
sub pp_leaveloop { loop_common(@_, "") }
my $self = shift;
my($op, $cx) = @_;
my $gv = $self->gv_or_padgv($op);
- return $self->maybe_local($op, $cx, "\$" . $self->gv_name($gv));
+ return $self->maybe_local($op, $cx, $self->stash_variable("\$",
+ $self->gv_name($gv)));
}
sub pp_gv {
my($op, $cx, $type) = @_;
my $kid = $op->first;
my $str = $self->deparse($kid, 0);
- return $type . (is_scalar($kid) ? $str : "{$str}");
+ return $self->stash_variable($type, $str) if is_scalar($kid);
+ return $type ."{$str}";
}
sub pp_rv2sv { maybe_local(@_, rv2x(@_, "\$")) }
my $arrow = is_subscriptable($kid->first) ? "" : "->";
$kid = $self->deparse($kid, 24) . $arrow;
}
+
+ # Doesn't matter how many prototypes there are, if
+ # they haven't happened yet!
+ my $declared = exists $self->{'subs_declared'}{$kid};
+
my $args;
- if (defined $proto and not $amper) {
+ if ($declared and defined $proto and not $amper) {
($amper, $args) = $self->check_proto($proto, @exprs);
if ($amper eq "&") {
$args = join(", ", map($self->deparse($_, 6), @exprs));
return $prefix . $amper. $kid;
}
} else {
- if (defined $proto and $proto eq "") {
+ # glob() invocations can be translated into calls of
+ # CORE::GLOBAL::glob with an second parameter, a number.
+ # Reverse this.
+ if ($kid eq "CORE::GLOBAL::glob") {
+ $kid = "glob";
+ $args =~ s/\s*,[^,]+$//;
+ }
+
+ # It's a syntax error to call CORE::GLOBAL::foo without a prefix,
+ # so it must have been translated from a keyword call. Translate
+ # it back.
+ $kid =~ s/^CORE::GLOBAL:://;
+
+ if (!$declared) {
+ return "$kid(" . $args . ")";
+ } elsif (defined $proto and $proto eq "") {
return $kid;
} elsif (defined $proto and $proto eq "\$") {
return $self->maybe_parens_func($kid, $args, $cx, 16);
}
# character escapes, but not delimiters that might need to be escaped
-sub escape_str { # ASCII
+sub escape_str { # ASCII, UTF8
my($str) = @_;
+ $str =~ s/(.)/ord($1)>255 ? sprintf("\\x{%x}", ord($1)) : $1/eg;
$str =~ s/\a/\\a/g;
# $str =~ s/\cH/\\b/g; # \b means someting different in a regex
$str =~ s/\t/\\t/g;
return $str;
}
+# Remove backslashes which precede literal control characters,
+# to avoid creating ambiguity when we escape the latter.
+sub re_unback {
+ my($str) = @_;
+
+ # the insane complexity here is due to the behaviour of "\c\"
+ $str =~ s/(^|[^\\]|\\c\\)(?<!\\c)\\(\\\\)*(?=[\0-\031\177-\377])/$1$2/g;
+ return $str;
+}
+
sub balanced_delim {
my($str) = @_;
my @str = split //, $str;
sub pp_const {
my $self = shift;
my($op, $cx) = @_;
+ if ($op->private & OPpCONST_ARYBASE) {
+ return '$[';
+ }
# if ($op->private & OPpCONST_BARE) { # trouble with `=>' autoquoting
# return $self->const_sv($op)->PV;
# }
my $sv = $self->const_sv($op);
# return const($sv);
- if ($op->private & OPpCONST_ARYBASE) {
- return '$[';
- }
my $c = const $sv;
return $c =~ /^-\d/ ? $self->maybe_parens($c, $cx, 21) : $c;
}
my $op = shift;
my $type = $op->name;
if ($type eq "const") {
- return uninterp(escape_str(unback($self->const_sv($op)->PV)));
+ return '$[' if $op->private & OPpCONST_ARYBASE;
+ return uninterp(escape_str(unback($self->const_sv($op)->as_string)));
} elsif ($type eq "concat") {
my $first = $self->dq($op->first);
my $last = $self->dq($op->last);
# Disambiguate "${foo}bar", "${foo}{bar}", "${foo}[1]"
- if ($last =~ /^[{\[\w]/) {
- $first =~ s/([%\$@])([A-Za-z_]\w*)$/${1}{$2}/;
+ if ($last =~ /^[A-Z\\\^\[\]_?]/) {
+ $first =~ s/([\$@])\^$/${1}{^}/; # "${^}W" etc
+ }
+ elsif ($last =~ /^[{\[\w]/) {
+ $first =~ s/([\$@])([A-Za-z_]\w*)$/${1}{$2}/;
}
return $first . $last;
} elsif ($type eq "uc") {
my $op = shift;
my $type = $op->name;
if ($type eq "const") {
- return re_uninterp($self->const_sv($op)->PV);
+ return '$[' if $op->private & OPpCONST_ARYBASE;
+ return re_uninterp(escape_str(re_unback($self->const_sv($op)->as_string)));
} elsif ($type eq "concat") {
my $first = $self->re_dq($op->first);
my $last = $self->re_dq($op->last);
# Disambiguate "${foo}bar", "${foo}{bar}", "${foo}[1]"
- if ($last =~ /^[{\[\w]/) {
- $first =~ s/([%\$@])([A-Za-z_]\w*)$/${1}{$2}/;
+ if ($last =~ /^[A-Z\\\^\[\]_?]/) {
+ $first =~ s/([\$@])\^$/${1}{^}/;
+ }
+ elsif ($last =~ /^[{\[\w]/) {
+ $first =~ s/([\$@])([A-Za-z_]\w*)$/${1}{$2}/;
}
return $first . $last;
} elsif ($type eq "uc") {
$kid = $kid->sibling;
}
if (null $kid) {
- $re = re_uninterp(escape_str($op->precomp));
+ $re = re_uninterp(escape_str(re_unback($op->precomp)));
} else {
$re = $self->deparse($kid, 1);
}
for (; !null($kid); $kid = $kid->sibling) {
push @exprs, $self->deparse($kid, 6);
}
+
+ # handle special case of split(), and split(" ") that compiles to /\s+/
+ $kid = $op->first;
+ if ($kid->flags & OPf_SPECIAL
+ && $exprs[0] eq '/\\s+/'
+ && $kid->pmflags & PMf_SKIPWHITE ) {
+ $exprs[0] = '" "';
+ }
+
$expr = "split(" . join(", ", @exprs) . ")";
if ($ary) {
return $self->maybe_parens("$ary = $expr", $cx, 7);
}
}
if (null $kid) {
- $re = re_uninterp(escape_str($op->precomp));
+ $re = re_uninterp(escape_str(re_unback($op->precomp)));
} else {
$re = $self->deparse($kid, 1);
}
C<$x = "$y"> is not the same as C<$x = $y>: the former makes the value
of $y into a string before doing the assignment.
-=item B<-u>I<PACKAGE>
+=item B<-f>I<FILE>
-Normally, B::Deparse deparses the main code of a program, all the subs
-called by the main program (and all the subs called by them,
-recursively), and any other subs in the main:: package. To include
-subs in other packages that aren't called directly, such as AUTOLOAD,
-DESTROY, other subs called automatically by perl, and methods (which
-aren't resolved to subs until runtime), use the B<-u> option. The
-argument to B<-u> is the name of a package, and should follow directly
-after the 'u'. Multiple B<-u> options may be given, separated by
-commas. Note that unlike some other backends, B::Deparse doesn't
-(yet) try to guess automatically when B<-u> is needed -- you must
-invoke it yourself.
+Normally, B::Deparse deparses the main code of a program, and all the subs
+defined in the same file. To include subs defined in other files, pass the
+B<-f> option with the filename. You can pass the B<-f> option several times, to
+include more than one secondary file. (Most of the time you don't want to
+use it at all.) You can also use this option to include subs which are
+defined in the scope of a B<#line> directive with two parameters.
=item B<-s>I<LETTERS>
options, like B<-u>, don't make sense for a single subroutine, so
don't pass them.
+=head2 ambient_pragmas
+
+ $deparse->ambient_pragmas(strict => 'all', '$[' => $[);
+
+The compilation of a subroutine can be affected by a few compiler
+directives, B<pragmas>. These are:
+
+=over 4
+
+=item *
+
+use strict;
+
+=item *
+
+use warnings;
+
+=item *
+
+Assigning to the special variable $[
+
+=item *
+
+use integer;
+
+=item *
+
+use bytes;
+
+=item *
+
+use utf8;
+
+=item *
+
+use re;
+
+=back
+
+Ordinarily, if you use B::Deparse on a subroutine which has
+been compiled in the presence of one or more of these pragmas,
+the output will include statements to turn on the appropriate
+directives. So if you then compile the code returned by coderef2text,
+it will behave the same way as the subroutine which you deparsed.
+
+However, you may know that you intend to use the results in a
+particular context, where some pragmas are already in scope. In
+this case, you use the B<ambient_pragmas> method to describe the
+assumptions you wish to make.
+
+The parameters it accepts are:
+
+=over 4
+
+=item strict
+
+Takes a string, possibly containing several values separated
+by whitespace. The special values "all" and "none" mean what you'd
+expect.
+
+ $deparse->ambient_pragmas(strict => 'subs refs');
+
+=item $[
+
+Takes a number, the value of the array base $[.
+
+=item bytes
+
+=item utf8
+
+=item integer
+
+If the value is true, then the appropriate pragma is assumed to
+be in the ambient scope, otherwise not.
+
+=item re
+
+Takes a string, possibly containing a whitespace-separated list of
+values. The values "all" and "none" are special. It's also permissible
+to pass an array reference here.
+
+ $deparser->ambient_pragmas(re => 'eval');
+
+
+=item warnings
+
+Takes a string, possibly containing a whitespace-separated list of
+values. The values "all" and "none" are special, again. It's also
+permissible to pass an array reference here.
+
+ $deparser->ambient_pragmas(warnings => [qw[void io]]);
+
+If one of the values is the string "FATAL", then all the warnings
+in that list will be considered fatal, just as with the B<warnings>
+pragma itself. Should you need to specify that some warnings are
+fatal, and others are merely enabled, you can pass the B<warnings>
+parameter twice:
+
+ $deparser->ambient_pragmas(
+ warnings => 'all',
+ warnings => [FATAL => qw/void io/],
+ );
+
+See L<perllexwarn> for more information about lexical warnings.
+
+=item hint_bits
+
+=item warning_bits
+
+These two parameters are used to specify the ambient pragmas in
+the format used by the special variables $^H and ${^WARNING_BITS}.
+
+They exist principally so that you can write code like:
+
+ { my ($hint_bits, $warning_bits);
+ BEGIN {($hint_bits, $warning_bits) = ($^H, ${^WARNING_BITS})}
+ $deparser->ambient_pragmas (
+ hint_bits => $hint_bits,
+ warning_bits => $warning_bits,
+ '$[' => 0 + $[
+ ); }
+
+which specifies that the ambient pragmas are exactly those which
+are in scope at the point of calling.
+
+=back
+
=head2 coderef2text
$body = $deparse->coderef2text(\&func)