# This program is free software; you can redistribute and/or modify it
# under the same terms as Perl itself.
-use strict;
-use warnings;
+# Note: we need to keep track of how many use declarations/BEGIN
+# blocks this module uses, so we can avoid printing them when user
+# asks for the BEGIN blocks in her program. Update the comments and
+# the count in concise_specials if you add or delete one. The
+# -MO=Concise counts as use #1.
-use Exporter ();
+use strict; # use #2
+use warnings; # uses #3 and #4, since warnings uses Carp
-our $VERSION = "0.55";
-our @ISA = qw(Exporter);
-our @EXPORT_OK = qw(set_style set_style_standard add_callback
- concise_cv concise_main);
+use Exporter (); # use #5
+our $VERSION = "0.85";
+our @ISA = qw(Exporter);
+our @EXPORT_OK = qw( set_style set_style_standard add_callback
+ concise_subref concise_cv concise_main
+ add_style walk_output compile reset_sequence );
+our %EXPORT_TAGS =
+ ( io => [qw( walk_output compile reset_sequence )],
+ style => [qw( add_style set_style_standard )],
+ cb => [qw( add_callback )],
+ mech => [qw( concise_subref concise_cv concise_main )], );
+
+# use #6
use B qw(class ppname main_start main_root main_cv cstring svref_2object
- SVf_IOK SVf_NOK SVf_POK SVf_IVisUV OPf_KIDS);
+ SVf_IOK SVf_NOK SVf_POK SVf_IVisUV SVf_FAKE OPf_KIDS OPf_SPECIAL
+ CVf_ANON PAD_FAKELEX_ANON PAD_FAKELEX_MULTI SVf_ROK);
-my %style =
+my %style =
("terse" =>
["(?(#label =>\n)?)(*( )*)#class (#addr) #name (?([#targ])?) "
. "#svclass~(?((#svaddr))?)~#svval~(?(label \"#coplabel\")?)\n",
"(*( )*)goto #class (#addr)\n",
"#class pp_#name"],
"concise" =>
- ["#hyphseq2 (*( (x( ;)x))*)<#classsym> "
- . "#exname#arg(?([#targarglife])?)~#flags(?(/#private)?)(x(;~->#next)x)\n",
- " (*( )*) goto #seq\n",
+ ["#hyphseq2 (*( (x( ;)x))*)<#classsym> #exname#arg(?([#targarglife])?)"
+ . "~#flags(?(/#private)?)(?(:#hints)?)(x(;~->#next)x)\n"
+ , " (*( )*) goto #seq\n",
"(?(<#seq>)?)#exname#arg(?([#targarglife])?)"],
"linenoise" =>
["(x(;(*( )*))x)#noise#arg(?([#targarg])?)(x( ;\n)x)",
"(?(#seq)?)#noise#arg(?([#targarg])?)"],
"debug" =>
["#class (#addr)\n\top_next\t\t#nextaddr\n\top_sibling\t#sibaddr\n\t"
- . "op_ppaddr\tPL_ppaddr[OP_#NAME]\n\top_type\t\t#typenum\n\top_seq\t\t"
- . "#seqnum\n\top_flags\t#flagval\n\top_private\t#privval\n"
+ . "op_ppaddr\tPL_ppaddr[OP_#NAME]\n\top_type\t\t#typenum\n" .
+ ($] > 5.009 ? '' : "\top_seq\t\t#seqnum\n")
+ . "\top_flags\t#flagval\n\top_private\t#privval\t#hintsval\n"
. "(?(\top_first\t#firstaddr\n)?)(?(\top_last\t\t#lastaddr\n)?)"
. "(?(\top_sv\t\t#svaddr\n)?)",
" GOTO #addr\n",
$ENV{B_CONCISE_TREE_FORMAT}],
);
-my($format, $gotofmt, $treefmt);
+# Renderings, ie how Concise prints, is controlled by these vars
+# primary:
+our $stylename; # selects current style from %style
+my $order = "basic"; # how optree is walked & printed: basic, exec, tree
+
+# rendering mechanics:
+# these 'formats' are the line-rendering templates
+# they're updated from %style when $stylename changes
+my ($format, $gotofmt, $treefmt);
+
+# lesser players:
+my $base = 36; # how <sequence#> is displayed
+my $big_endian = 1; # more <sequence#> display
+my $tree_style = 0; # tree-order details
+my $banner = 1; # print banner before optree is traversed
+my $do_main = 0; # force printing of main routine
+my $show_src; # show source code
+
+# another factor: can affect all styles!
+our @callbacks; # allow external management
+
+set_style_standard("concise");
+
my $curcv;
my $cop_seq_base;
-my @callbacks;
sub set_style {
($format, $gotofmt, $treefmt) = @_;
+ #warn "set_style: deprecated, use set_style_standard instead\n"; # someday
+ die "expecting 3 style-format args\n" unless @_ == 3;
+}
+
+sub add_style {
+ my ($newstyle,@args) = @_;
+ die "style '$newstyle' already exists, choose a new name\n"
+ if exists $style{$newstyle};
+ die "expecting 3 style-format args\n" unless @args == 3;
+ $style{$newstyle} = [@args];
+ $stylename = $newstyle; # update rendering state
}
sub set_style_standard {
- my($name) = @_;
- set_style(@{$style{$name}});
+ ($stylename) = @_; # update rendering state
+ die "err: style '$stylename' unknown\n" unless exists $style{$stylename};
+ set_style(@{$style{$stylename}});
}
sub add_callback {
push @callbacks, @_;
}
-sub concise_cv {
- my ($order, $cvref) = @_;
- my $cv = svref_2object($cvref);
+# output handle, used with all Concise-output printing
+our $walkHandle; # public for your convenience
+BEGIN { $walkHandle = \*STDOUT }
+
+sub walk_output { # updates $walkHandle
+ my $handle = shift;
+ return $walkHandle unless $handle; # allow use as accessor
+
+ if (ref $handle eq 'SCALAR') {
+ require Config;
+ die "no perlio in this build, can't call walk_output (\\\$scalar)\n"
+ unless $Config::Config{useperlio};
+ # in 5.8+, open(FILEHANDLE,MODE,REFERENCE) writes to string
+ open my $tmp, '>', $handle; # but cant re-set existing STDOUT
+ $walkHandle = $tmp; # so use my $tmp as intermediate var
+ return $walkHandle;
+ }
+ my $iotype = ref $handle;
+ die "expecting argument/object that can print\n"
+ unless $iotype eq 'GLOB' or $iotype and $handle->can('print');
+ $walkHandle = $handle;
+}
+
+sub concise_subref {
+ my($order, $coderef, $name) = @_;
+ my $codeobj = svref_2object($coderef);
+
+ return concise_stashref(@_)
+ unless ref $codeobj eq 'B::CV';
+ concise_cv_obj($order, $codeobj, $name);
+}
+
+sub concise_stashref {
+ my($order, $h) = @_;
+ local *s;
+ foreach my $k (sort keys %$h) {
+ next unless defined $h->{$k};
+ *s = $h->{$k};
+ my $coderef = *s{CODE} or next;
+ reset_sequence();
+ print "FUNC: ", *s, "\n";
+ my $codeobj = svref_2object($coderef);
+ next unless ref $codeobj eq 'B::CV';
+ eval { concise_cv_obj($order, $codeobj, $k) };
+ warn "err $@ on $codeobj" if $@;
+ }
+}
+
+# This should have been called concise_subref, but it was exported
+# under this name in versions before 0.56
+*concise_cv = \&concise_subref;
+
+sub concise_cv_obj {
+ my ($order, $cv, $name) = @_;
+ # name is either a string, or a CODE ref (copy of $cv arg??)
+
$curcv = $cv;
+
+ if (ref($cv->XSUBANY) =~ /B::(\w+)/) {
+ print $walkHandle "$name is a constant sub, optimized to a $1\n";
+ return;
+ }
+ if ($cv->XSUB) {
+ print $walkHandle "$name is XS code\n";
+ return;
+ }
+ if (class($cv->START) eq "NULL") {
+ no strict 'refs';
+ if (ref $name eq 'CODE') {
+ print $walkHandle "coderef $name has no START\n";
+ }
+ elsif (exists &$name) {
+ print $walkHandle "$name exists in stash, but has no START\n";
+ }
+ else {
+ print $walkHandle "$name not in symbol table\n";
+ }
+ return;
+ }
sequence($cv->START);
if ($order eq "exec") {
walk_exec($cv->START);
- } elsif ($order eq "basic") {
- walk_topdown($cv->ROOT, sub { $_[0]->concise($_[1]) }, 0);
+ }
+ elsif ($order eq "basic") {
+ # walk_topdown($cv->ROOT, sub { $_[0]->concise($_[1]) }, 0);
+ my $root = $cv->ROOT;
+ unless (ref $root eq 'B::NULL') {
+ walk_topdown($root, sub { $_[0]->concise($_[1]) }, 0);
+ } else {
+ print $walkHandle "B::NULL encountered doing ROOT on $cv. avoiding disaster\n";
+ }
} else {
- print tree($cv->ROOT, 0)
+ print $walkHandle tree($cv->ROOT, 0);
}
}
walk_exec(main_start);
} elsif ($order eq "tree") {
return if class(main_root) eq "NULL";
- print tree(main_root, 0);
+ print $walkHandle tree(main_root, 0);
} elsif ($order eq "basic") {
return if class(main_root) eq "NULL";
walk_topdown(main_root,
}
}
+sub concise_specials {
+ my($name, $order, @cv_s) = @_;
+ my $i = 1;
+ if ($name eq "BEGIN") {
+ splice(@cv_s, 0, 8); # skip 7 BEGIN blocks in this file. NOW 8 ??
+ } elsif ($name eq "CHECK") {
+ pop @cv_s; # skip the CHECK block that calls us
+ }
+ for my $cv (@cv_s) {
+ print $walkHandle "$name $i:\n";
+ $i++;
+ concise_cv_obj($order, $cv, $name);
+ }
+}
+
my $start_sym = "\e(0"; # "\cN" sometimes also works
my $end_sym = "\e(B"; # "\cO" respectively
-my @tree_decorations =
+my @tree_decorations =
([" ", "--", "+-", "|-", "| ", "`-", "-", 1],
[" ", "-", "+", "+", "|", "`", "", 0],
[" ", map("$start_sym$_$end_sym", "qq", "wq", "tq", "x ", "mq", "q"), 1],
[" ", map("$start_sym$_$end_sym", "q", "w", "t", "x", "m"), "", 0],
);
-my $tree_style = 0;
-
-my $base = 36;
-my $big_endian = 1;
-my $order = "basic";
-
-set_style_standard("concise");
+my @render_packs; # collect -stash=<packages>
-sub compile {
- my @options = grep(/^-/, @_);
- my @args = grep(!/^-/, @_);
- my $do_main = 0;
+sub compileOpts {
+ # set rendering state from options and args
+ my (@options,@args);
+ if (@_) {
+ @options = grep(/^-/, @_);
+ @args = grep(!/^-/, @_);
+ }
for my $o (@options) {
+ # mode/order
if ($o eq "-basic") {
$order = "basic";
} elsif ($o eq "-exec") {
$order = "exec";
} elsif ($o eq "-tree") {
$order = "tree";
- } elsif ($o eq "-compact") {
+ }
+ # tree-specific
+ elsif ($o eq "-compact") {
$tree_style |= 1;
} elsif ($o eq "-loose") {
$tree_style &= ~1;
$tree_style |= 2;
} elsif ($o eq "-ascii") {
$tree_style &= ~2;
- } elsif ($o eq "-main") {
- $do_main = 1;
- } elsif ($o =~ /^-base(\d+)$/) {
+ }
+ # sequence numbering
+ elsif ($o =~ /^-base(\d+)$/) {
$base = $1;
} elsif ($o eq "-bigendian") {
$big_endian = 1;
} elsif ($o eq "-littleendian") {
$big_endian = 0;
- } elsif (exists $style{substr($o, 1)}) {
- set_style(@{$style{substr($o, 1)}});
+ }
+ # miscellaneous, presentation
+ elsif ($o eq "-nobanner") {
+ $banner = 0;
+ } elsif ($o eq "-banner") {
+ $banner = 1;
+ }
+ elsif ($o eq "-main") {
+ $do_main = 1;
+ } elsif ($o eq "-nomain") {
+ $do_main = 0;
+ } elsif ($o eq "-src") {
+ $show_src = 1;
+ }
+ elsif ($o =~ /^-stash=(.*)/) {
+ my $pkg = $1;
+ no strict 'refs';
+ if (! %{$pkg.'::'}) {
+ eval "require $pkg";
+ } else {
+ require Config;
+ if (!$Config::Config{usedl}
+ && keys %{$pkg.'::'} == 1
+ && $pkg->can('bootstrap')) {
+ # It is something that we're statically linked to, but hasn't
+ # yet been used.
+ eval "require $pkg";
+ }
+ }
+ push @render_packs, $pkg;
+ }
+ # line-style options
+ elsif (exists $style{substr($o, 1)}) {
+ $stylename = substr($o, 1);
+ set_style_standard($stylename);
} else {
warn "Option $o unrecognized";
}
}
+ return (@args);
+}
+
+sub compile {
+ my (@args) = compileOpts(@_);
return sub {
- if (@args) {
- for my $objname (@args) {
- $objname = "main::" . $objname unless $objname =~ /::/;
- print "$objname:\n";
- eval "concise_cv(\$order, \\&$objname)";
- die "concise_cv($order, \\&$objname) failed: $@" if $@;
+ my @newargs = compileOpts(@_); # accept new rendering options
+ warn "disregarding non-options: @newargs\n" if @newargs;
+
+ for my $objname (@args) {
+ next unless $objname; # skip null args to avoid noisy responses
+
+ if ($objname eq "BEGIN") {
+ concise_specials("BEGIN", $order,
+ B::begin_av->isa("B::AV") ?
+ B::begin_av->ARRAY : ());
+ } elsif ($objname eq "INIT") {
+ concise_specials("INIT", $order,
+ B::init_av->isa("B::AV") ?
+ B::init_av->ARRAY : ());
+ } elsif ($objname eq "CHECK") {
+ concise_specials("CHECK", $order,
+ B::check_av->isa("B::AV") ?
+ B::check_av->ARRAY : ());
+ } elsif ($objname eq "UNITCHECK") {
+ concise_specials("UNITCHECK", $order,
+ B::unitcheck_av->isa("B::AV") ?
+ B::unitcheck_av->ARRAY : ());
+ } elsif ($objname eq "END") {
+ concise_specials("END", $order,
+ B::end_av->isa("B::AV") ?
+ B::end_av->ARRAY : ());
}
+ else {
+ # convert function names to subrefs
+ my $objref;
+ if (ref $objname) {
+ print $walkHandle "B::Concise::compile($objname)\n"
+ if $banner;
+ $objref = $objname;
+ } else {
+ $objname = "main::" . $objname unless $objname =~ /::/;
+ print $walkHandle "$objname:\n";
+ no strict 'refs';
+ unless (exists &$objname) {
+ print $walkHandle "err: unknown function ($objname)\n";
+ return;
+ }
+ $objref = \&$objname;
+ }
+ concise_subref($order, $objref, $objname);
+ }
+ }
+ for my $pkg (@render_packs) {
+ no strict 'refs';
+ concise_stashref($order, \%{$pkg.'::'});
}
- if (!@args or $do_main) {
- print "main program:\n" if $do_main;
+
+ if (!@args or $do_main or @render_packs) {
+ print $walkHandle "main program:\n" if $do_main;
concise_main($order);
}
+ return @args; # something
}
}
my %labels;
-my $lastnext;
+my $lastnext; # remembers op-chain, used to insert gotos
my %opclass = ('OP' => "0", 'UNOP' => "1", 'BINOP' => "2", 'LOGOP' => "|",
'LISTOP' => "@", 'PMOP' => "/", 'SVOP' => "\$", 'GVOP' => "*",
'PVOP' => '"', 'LOOP' => "{", 'COP' => ";", 'PADOP' => "#");
-no warnings 'qw'; # "Possible attempt to put comments..."
+no warnings 'qw'; # "Possible attempt to put comments..."; use #7
my @linenoise =
qw'# () sc ( @? 1 $* gv *{ m$ m@ m% m? p/ *$ $ $# & a& pt \\ s\\ rf bl
` *? <> ?? ?/ r/ c/ // qr s/ /c y/ = @= C sC Cp sp df un BM po +1 +I
my $chars = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ";
-sub op_flags {
+sub op_flags { # common flags (see BASOP.op_flags in op.h)
my($x) = @_;
my(@v);
push @v, "v" if ($x & 3) == 1;
my %sequence_num;
my $seq_max = 1;
+sub reset_sequence {
+ # reset the sequence
+ %sequence_num = ();
+ $seq_max = 1;
+ $lastnext = 0;
+}
+
sub seq {
my($op) = @_;
return "-" if not exists $sequence_num{$$op};
walk_topdown($kid, $sub, $level + 1);
}
}
- if (class($op) eq "PMOP" and $op->pmreplroot and $ {$op->pmreplroot}
- and $op->pmreplroot->isa("B::OP")) {
- walk_topdown($op->pmreplroot, $sub, $level + 1);
+ if (class($op) eq "PMOP") {
+ my $maybe_root = $op->pmreplroot;
+ if (ref($maybe_root) and $maybe_root->isa("B::OP")) {
+ # It really is the root of the replacement, not something
+ # else stored here for lack of space elsewhere
+ walk_topdown($maybe_root, $sub, $level + 1);
+ }
}
}
push @$targ, $ar;
push @todo, [$op->pmreplstart, $ar];
} elsif ($name =~ /^enter(loop|iter)$/) {
- $labels{$op->nextop->seq} = "NEXT";
- $labels{$op->lastop->seq} = "LAST";
- $labels{$op->redoop->seq} = "REDO";
+ if ($] > 5.009) {
+ $labels{${$op->nextop}} = "NEXT";
+ $labels{${$op->lastop}} = "LAST";
+ $labels{${$op->redoop}} = "REDO";
+ } else {
+ $labels{$op->nextop->seq} = "NEXT";
+ $labels{$op->lastop->seq} = "LAST";
+ $labels{$op->redoop->seq} = "REDO";
+ }
}
}
}
}
}
-sub fmt_line {
- my($hr, $fmt, $level) = @_;
- my $text = $fmt;
+sub fmt_line { # generate text-line for op.
+ my($hr, $op, $text, $level) = @_;
+
+ $_->($hr, $op, \$text, \$level, $stylename) for @callbacks;
+
+ return '' if $hr->{SKIP}; # suppress line if a callback said so
+ return '' if $hr->{goto} and $hr->{goto} eq '-'; # no goto nowhere
+
+ # spec: (?(text1#varText2)?)
$text =~ s/\(\?\(([^\#]*?)\#(\w+)([^\#]*?)\)\?\)/
- $hr->{$2} ? $1.$hr->{$2}.$3 : ""/eg;
+ $hr->{$2} ? $1.$hr->{$2}.$3 : ""/eg;
+
+ # spec: (x(exec_text;basic_text)x)
$text =~ s/\(x\((.*?);(.*?)\)x\)/$order eq "exec" ? $1 : $2/egs;
+
+ # spec: (*(text)*)
$text =~ s/\(\*\(([^;]*?)\)\*\)/$1 x $level/egs;
+
+ # spec: (*(text1;text2)*)
$text =~ s/\(\*\((.*?);(.*?)\)\*\)/$1 x ($level - 1) . $2 x ($level>0)/egs;
- $text =~ s/#([a-zA-Z]+)(\d+)/sprintf("%-$2s", $hr->{$1})/eg;
- $text =~ s/#([a-zA-Z]+)/$hr->{$1}/eg;
- $text =~ s/[ \t]*~+[ \t]*/ /g;
- return $text;
+
+ # convert #Var to tag=>val form: Var\t#var
+ $text =~ s/\#([A-Z][a-z]+)(\d+)?/\t\u$1\t\L#$1$2/gs;
+
+ # spec: #varN
+ $text =~ s/\#([a-zA-Z]+)(\d+)/sprintf("%-$2s", $hr->{$1})/eg;
+
+ $text =~ s/\#([a-zA-Z]+)/$hr->{$1}/eg; # populate #var's
+ $text =~ s/[ \t]*~+[ \t]*/ /g; # squeeze tildes
+
+ $text = "# $hr->{src}\n$text" if $show_src and $hr->{src};
+
+ chomp $text;
+ return "$text\n" if $text ne "" and $order ne "tree";
+ return $text; # suppress empty lines
}
-my %priv;
+our %priv; # used to display each opcode's BASEOP.op_private values
+
$priv{$_}{128} = "LVINTRO"
for ("pos", "substr", "vec", "threadsv", "gvsv", "rv2sv", "rv2hv", "rv2gv",
"rv2av", "rv2arylen", "aelem", "helem", "aslice", "hslice", "padsv",
- "padav", "padhv");
+ "padav", "padhv", "enteriter", "entersub");
$priv{$_}{64} = "REFC" for ("leave", "leavesub", "leavesublv", "leavewrite");
$priv{"aassign"}{64} = "COMMON";
+$priv{"aassign"}{32} = $] < 5.009 ? "PHASH" : "STATE";
+$priv{"sassign"}{32} = "STATE";
$priv{"sassign"}{64} = "BKWARD";
-$priv{$_}{64} = "RTIME" for ("match", "subst", "substcont");
+$priv{$_}{64} = "RTIME" for ("match", "subst", "substcont", "qr");
@{$priv{"trans"}}{1,2,4,8,16,64} = ("<UTF", ">UTF", "IDENT", "SQUASH", "DEL",
"COMPL", "GROWS");
+$priv{transr} = $priv{trans};
$priv{"repeat"}{64} = "DOLIST";
$priv{"leaveloop"}{64} = "CONT";
+$priv{$_}{4} = "DREFed" for (qw(rv2sv rv2av rv2hv));
@{$priv{$_}}{32,64,96} = ("DREFAV", "DREFHV", "DREFSV")
- for ("entersub", map("rv2${_}v", "a", "s", "h", "g"), "aelem", "helem");
-$priv{"entersub"}{16} = "DBG";
-$priv{"entersub"}{32} = "TARG";
-@{$priv{$_}}{4,8,128} = ("INARGS","AMPER","NO()") for ("entersub", "rv2cv");
+ for (qw(rv2gv rv2sv padsv aelem helem));
+$priv{$_}{16} = "STATE" for ("padav", "padhv", "padsv");
+@{$priv{"entersub"}}{1,4,16,32,64} = qw( DREF INARGS DBG TARG );
+@{$priv{rv2cv}}{1,8,128} = ("CONST","AMPER","NO()");
$priv{"gv"}{32} = "EARLYCV";
$priv{"aelem"}{16} = $priv{"helem"}{16} = "LVDEFER";
-$priv{$_}{16} = "OURINTR" for ("gvsv", "rv2sv", "rv2av", "rv2hv", "r2gv");
+$priv{$_}{16} = "OURINTR" for ("gvsv", "rv2sv", "rv2av", "rv2hv", "r2gv",
+ "enteriter");
+$priv{$_}{8} = 'LVSUB' for qw(rv2av rv2gv rv2hv padav padhv aelem helem
+ aslice hslice av2arylen keys rkeys substr pos vec);
$priv{$_}{16} = "TARGMY"
for (map(($_,"s$_"),"chop", "chomp"),
map(($_,"i_$_"), "postinc", "postdec", "multiply", "divide", "modulo",
"link", "symlink", "mkdir", "rmdir", "wait", "waitpid", "system",
"exec", "kill", "getppid", "getpgrp", "setpgrp", "getpriority",
"setpriority", "time", "sleep");
-@{$priv{"const"}}{8,16,32,64,128} = ("STRICT","ENTERED", '$[', "BARE", "WARN");
+$priv{$_}{4} = "REVERSED" for ("enteriter", "iter");
+@{$priv{"const"}}{4,8,16,32,64,128} = ("SHORT","STRICT","ENTERED",'$[',"BARE","WARN");
$priv{"flip"}{64} = $priv{"flop"}{64} = "LINENUM";
$priv{"list"}{64} = "GUESSED";
$priv{"delete"}{64} = "SLICE";
$priv{"exists"}{64} = "SUB";
-$priv{$_}{64} = "LOCALE"
- for ("sort", "prtf", "sprintf", "slt", "sle", "seq", "sne", "sgt", "sge",
- "scmp", "lc", "uc", "lcfirst", "ucfirst");
-@{$priv{"sort"}}{1,2,4} = ("NUM", "INT", "REV");
+@{$priv{"sort"}}{1,2,4,8,16,32,64} = ("NUM", "INT", "REV", "INPLACE","DESC","QSORT","STABLE");
+$priv{"reverse"}{8} = "INPLACE";
$priv{"threadsv"}{64} = "SVREFd";
@{$priv{$_}}{16,32,64,128} = ("INBIN","INCR","OUTBIN","OUTCR")
for ("open", "backtick");
$priv{"exit"}{128} = "VMS";
$priv{$_}{2} = "FTACCESS"
for ("ftrread", "ftrwrite", "ftrexec", "fteread", "ftewrite", "fteexec");
+$priv{"entereval"}{2} = "HAS_HH";
+if ($] >= 5.009) {
+ # Stacked filetests are post 5.8.x
+ $priv{$_}{4} = "FTSTACKED"
+ for ("ftrread", "ftrwrite", "ftrexec", "fteread", "ftewrite", "fteexec",
+ "ftis", "fteowned", "ftrowned", "ftzero", "ftsize", "ftmtime",
+ "ftatime", "ftctime", "ftsock", "ftchr", "ftblk", "ftfile", "ftdir",
+ "ftpipe", "ftlink", "ftsuid", "ftsgid", "ftsvtx", "fttty", "fttext",
+ "ftbinary");
+ # Lexical $_ is post 5.8.x
+ $priv{$_}{2} = "GREPLEX"
+ for ("mapwhile", "mapstart", "grepwhile", "grepstart");
+}
-sub private_flags {
- my($name, $x) = @_;
+our %hints; # used to display each COP's op_hints values
+
+# strict refs, subs, vars
+@hints{2,512,1024} = ('$', '&', '*');
+# integers, locale, bytes, arybase
+@hints{1,4,8,16,32} = ('i', 'l', 'b', '[');
+# block scope, localise %^H, $^OPEN (in), $^OPEN (out)
+@hints{256,131072,262144,524288} = ('{','%','<','>');
+# overload new integer, float, binary, string, re
+@hints{4096,8192,16384,32768,65536} = ('I', 'F', 'B', 'S', 'R');
+# taint and eval
+@hints{1048576,2097152} = ('T', 'E');
+# filetest access, UTF-8
+@hints{4194304,8388608} = ('X', 'U');
+
+sub _flags {
+ my($hash, $x) = @_;
my @s;
- for my $flag (128, 96, 64, 32, 16, 8, 4, 2, 1) {
- if ($priv{$name}{$flag} and $x & $flag and $x >= $flag) {
+ for my $flag (sort {$b <=> $a} keys %$hash) {
+ if ($hash->{$flag} and $x & $flag and $x >= $flag) {
$x -= $flag;
- push @s, $priv{$name}{$flag};
+ push @s, $hash->{$flag};
}
}
push @s, $x if $x;
return join(",", @s);
}
+sub private_flags {
+ my($name, $x) = @_;
+ _flags($priv{$name}, $x);
+}
+
+sub hints_flags {
+ my($x) = @_;
+ _flags(\%hints, $x);
+}
+
sub concise_sv {
- my($sv, $hr) = @_;
+ my($sv, $hr, $preferpv) = @_;
$hr->{svclass} = class($sv);
$hr->{svclass} = "UV"
if $hr->{svclass} eq "IV" and $sv->FLAGS & SVf_IVisUV;
+ Carp::cluck("bad concise_sv: $sv") unless $sv and $$sv;
$hr->{svaddr} = sprintf("%#x", $$sv);
- if ($hr->{svclass} eq "GV") {
+ if ($hr->{svclass} eq "GV" && $sv->isGV_with_GP()) {
my $gv = $sv;
- my $stash = $gv->STASH->NAME;
- if ($stash eq "main") {
+ my $stash = $gv->STASH->NAME; if ($stash eq "main") {
$stash = "";
} else {
$stash = $stash . "::";
$hr->{svval} = "*$stash" . $gv->SAFENAME;
return "*$stash" . $gv->SAFENAME;
} else {
- while (class($sv) eq "RV") {
- $hr->{svval} .= "\\";
- $sv = $sv->RV;
+ if ($] >= 5.011) {
+ while (class($sv) eq "IV" && $sv->FLAGS & SVf_ROK) {
+ $hr->{svval} .= "\\";
+ $sv = $sv->RV;
+ }
+ } else {
+ while (class($sv) eq "RV") {
+ $hr->{svval} .= "\\";
+ $sv = $sv->RV;
+ }
}
if (class($sv) eq "SPECIAL") {
$hr->{svval} .= ["Null", "sv_undef", "sv_yes", "sv_no"]->[$$sv];
+ } elsif ($preferpv && $sv->FLAGS & SVf_POK) {
+ $hr->{svval} .= cstring($sv->PV);
} elsif ($sv->FLAGS & SVf_NOK) {
$hr->{svval} .= $sv->NV;
} elsif ($sv->FLAGS & SVf_IOK) {
} elsif (class($sv) eq "HV") {
$hr->{svval} .= 'HASH';
}
- return $hr->{svclass} . " " . $hr->{svval};
+
+ $hr->{svval} = 'undef' unless defined $hr->{svval};
+ my $out = $hr->{svclass};
+ return $out .= " $hr->{svval}" ;
+ }
+}
+
+my %srclines;
+
+sub fill_srclines {
+ my $fullnm = shift;
+ if ($fullnm eq '-e') {
+ $srclines{$fullnm} = [ $fullnm, "-src not supported for -e" ];
+ return;
}
+ open (my $fh, '<', $fullnm)
+ or warn "# $fullnm: $!, (chdirs not supported by this feature yet)\n"
+ and return;
+ my @l = <$fh>;
+ chomp @l;
+ unshift @l, $fullnm; # like @{_<$fullnm} in debug, array starts at 1
+ $srclines{$fullnm} = \@l;
}
sub concise_op {
$h{extarg} = $h{targ} = $op->targ;
$h{extarg} = "" unless $h{extarg};
if ($h{name} eq "null" and $h{targ}) {
+ # targ holds the old type
$h{exname} = "ex-" . substr(ppname($h{targ}), 3);
$h{extarg} = "";
+ } elsif ($op->name =~ /^leave(sub(lv)?|write)?$/) {
+ # targ potentially holds a reference count
+ if ($op->private & 64) {
+ my $refs = "ref" . ($h{targ} != 1 ? "s" : "");
+ $h{targarglife} = $h{targarg} = "$h{targ} $refs";
+ }
} elsif ($h{targ}) {
my $padname = (($curcv->PADLIST->ARRAY)[0]->ARRAY)[$h{targ}];
if (defined $padname and class($padname) ne "SPECIAL") {
$h{targarg} = $padname->PVX;
- my $intro = $padname->NVX - $cop_seq_base;
- my $finish = int($padname->IVX) - $cop_seq_base;
- $finish = "end" if $finish == 999999999 - $cop_seq_base;
- $h{targarglife} = "$h{targarg}:$intro,$finish";
+ if ($padname->FLAGS & SVf_FAKE) {
+ if ($] < 5.009) {
+ $h{targarglife} = "$h{targarg}:FAKE";
+ } else {
+ # These changes relate to the jumbo closure fix.
+ # See changes 19939 and 20005
+ my $fake = '';
+ $fake .= 'a'
+ if $padname->PARENT_FAKELEX_FLAGS & PAD_FAKELEX_ANON;
+ $fake .= 'm'
+ if $padname->PARENT_FAKELEX_FLAGS & PAD_FAKELEX_MULTI;
+ $fake .= ':' . $padname->PARENT_PAD_INDEX
+ if $curcv->CvFLAGS & CVf_ANON;
+ $h{targarglife} = "$h{targarg}:FAKE:$fake";
+ }
+ }
+ else {
+ my $intro = $padname->COP_SEQ_RANGE_LOW - $cop_seq_base;
+ my $finish = int($padname->COP_SEQ_RANGE_HIGH) - $cop_seq_base;
+ $finish = "end" if $finish == 999999999 - $cop_seq_base;
+ $h{targarglife} = "$h{targarg}:$intro,$finish";
+ }
} else {
$h{targarglife} = $h{targarg} = "t" . $h{targ};
}
}
my $pmreplroot = $op->pmreplroot;
my $pmreplstart;
- if ($pmreplroot && $$pmreplroot && $pmreplroot->isa("B::GV")) {
+ if (ref($pmreplroot) eq "B::GV") {
# with C<@stash_array = split(/pat/, str);>,
- # *stash_array is stored in pmreplroot.
+ # *stash_array is stored in /pat/'s pmreplroot.
$h{arg} = "($precomp => \@" . $pmreplroot->NAME . ")";
+ } elsif (!ref($pmreplroot) and $pmreplroot) {
+ # same as the last case, except the value is actually a
+ # pad offset for where the GV is kept (this happens under
+ # ithreads)
+ my $gv = (($curcv->PADLIST->ARRAY)[1]->ARRAY)[$pmreplroot];
+ $h{arg} = "($precomp => \@" . $gv->NAME . ")";
} elsif ($ {$op->pmreplstart}) {
undef $lastnext;
$pmreplstart = "replstart->" . seq($op->pmreplstart);
} else {
$h{arg} = "($precomp)";
}
- } elsif ($h{class} eq "PVOP" and $h{name} ne "trans") {
+ } elsif ($h{class} eq "PVOP" and $h{name} !~ '^transr?\z') {
$h{arg} = '("' . $op->pv . '")';
$h{svval} = '"' . $op->pv . '"';
} elsif ($h{class} eq "COP") {
$h{coplabel} = $label;
$label = $label ? "$label: " : "";
my $loc = $op->file;
+ my $pathnm = $loc;
$loc =~ s[.*/][];
- $loc .= ":" . $op->line;
+ my $ln = $op->line;
+ $loc .= ":$ln";
my($stash, $cseq) = ($op->stash->NAME, $op->cop_seq - $cop_seq_base);
my $arybase = $op->arybase;
$arybase = $arybase ? ' $[=' . $arybase : "";
$h{arg} = "($label$stash $cseq $loc$arybase)";
+ if ($show_src) {
+ fill_srclines($pathnm) unless exists $srclines{$pathnm};
+ # Would love to retain Jim's use of // but this code needs to be
+ # portable to 5.8.x
+ my $line = $srclines{$pathnm}[$ln];
+ $line = "-src unavailable under -e" unless defined $line;
+ $h{src} = "$ln: $line";
+ }
} elsif ($h{class} eq "LOOP") {
$h{arg} = "(next->" . seq($op->nextop) . " last->" . seq($op->lastop)
. " redo->" . seq($op->redoop) . ")";
} elsif ($h{class} eq "LOGOP") {
undef $lastnext;
$h{arg} = "(other->" . seq($op->other) . ")";
- } elsif ($h{class} eq "SVOP") {
- if (! ${$op->sv}) {
- my $sv = (($curcv->PADLIST->ARRAY)[1]->ARRAY)[$op->targ];
- $h{arg} = "[" . concise_sv($sv, \%h) . "]";
- $h{targarglife} = $h{targarg} = "";
- } else {
- $h{arg} = "(" . concise_sv($op->sv, \%h) . ")";
+ }
+ elsif ($h{class} eq "SVOP" or $h{class} eq "PADOP") {
+ unless ($h{name} eq 'aelemfast' and $op->flags & OPf_SPECIAL) {
+ my $idx = ($h{class} eq "SVOP") ? $op->targ : $op->padix;
+ my $preferpv = $h{name} eq "method_named";
+ if ($h{class} eq "PADOP" or !${$op->sv}) {
+ my $sv = (($curcv->PADLIST->ARRAY)[1]->ARRAY)[$idx];
+ $h{arg} = "[" . concise_sv($sv, \%h, $preferpv) . "]";
+ $h{targarglife} = $h{targarg} = "";
+ } else {
+ $h{arg} = "(" . concise_sv($op->sv, \%h, $preferpv) . ")";
+ }
}
- } elsif ($h{class} eq "PADOP") {
- my $sv = (($curcv->PADLIST->ARRAY)[1]->ARRAY)[$op->padix];
- $h{arg} = "[" . concise_sv($sv, \%h) . "]";
}
$h{seq} = $h{hyphseq} = seq($op);
$h{seq} = "" if $h{seq} eq "-";
- $h{seqnum} = $op->seq;
+ if ($] > 5.009) {
+ $h{opt} = $op->opt;
+ $h{label} = $labels{$$op};
+ } else {
+ $h{seqnum} = $op->seq;
+ $h{label} = $labels{$op->seq};
+ }
$h{next} = $op->next;
$h{next} = (class($h{next}) eq "NULL") ? "(end)" : seq($h{next});
$h{nextaddr} = sprintf("%#x", $ {$op->next});
$h{flags} = op_flags($op->flags);
$h{privval} = $op->private;
$h{private} = private_flags($h{name}, $op->private);
+ if ($op->can("hints")) {
+ $h{hintsval} = $op->hints;
+ $h{hints} = hints_flags($h{hintsval});
+ } else {
+ $h{hintsval} = $h{hints} = '';
+ }
$h{addr} = sprintf("%#x", $$op);
- $h{label} = $labels{$op->seq};
$h{typenum} = $op->type;
$h{noise} = $linenoise[$op->type];
- $_->(\%h, $op, \$format, \$level) for @callbacks;
- return fmt_line(\%h, $format, $level);
+
+ return fmt_line(\%h, $op, $format, $level);
}
sub B::OP::concise {
my($op, $level) = @_;
if ($order eq "exec" and $lastnext and $$lastnext != $$op) {
- my $h = {"seq" => seq($lastnext), "class" => class($lastnext),
- "addr" => sprintf("%#x", $$lastnext)};
- print fmt_line($h, $gotofmt, $level+1);
+ # insert a 'goto' line
+ my $synth = {"seq" => seq($lastnext), "class" => class($lastnext),
+ "addr" => sprintf("%#x", $$lastnext),
+ "goto" => seq($lastnext), # simplify goto '-' removal
+ };
+ print $walkHandle fmt_line($synth, $op, $gotofmt, $level+1);
}
$lastnext = $op->next;
- print concise_op($op, $level, $format);
+ print $walkHandle concise_op($op, $level, $format);
}
# B::OP::terse (see Terse.pm) now just calls this
$curcv = main_cv unless $curcv;
if ($order eq "exec" and $lastnext and $$lastnext != $$op) {
+ # insert a 'goto'
my $h = {"seq" => seq($lastnext), "class" => class($lastnext),
"addr" => sprintf("%#x", $$lastnext)};
- print fmt_line($h, $style{"terse"}[1], $level+1);
+ print # $walkHandle
+ fmt_line($h, $op, $style{"terse"}[1], $level+1);
}
$lastnext = $op->next;
- print concise_op($op, $level, $style{"terse"}[0]);
+ print # $walkHandle
+ concise_op($op, $level, $style{"terse"}[0]);
}
sub tree {
if (substr($lines[$i], 0, 1) eq " ") {
$lines[$i] = $nokid . $lines[$i];
} else {
- $lines[$i] = $kid . $lines[$i];
+ $lines[$i] = $kid . $lines[$i];
}
}
$lines[$i] = $kids . $lines[$i];
# *** Warning: fragile kludge ahead ***
# Because the B::* modules run in the same interpreter as the code
-# they're compiling, their presence tends to distort the view we have
-# of the code we're looking at. In particular, perl gives sequence
-# numbers to both OPs in general and COPs in particular. If the
-# program we're looking at were run on its own, these numbers would
-# start at 1. Because all of B::Concise and all the modules it uses
-# are compiled first, though, by the time we get to the user's program
-# the sequence numbers are alreay at pretty high numbers, which would
-# be distracting if you're trying to tell OPs apart. Therefore we'd
-# like to subtract an offset from all the sequence numbers we display,
-# to restore the simpler view of the world. The trick is to know what
-# that offset will be, when we're still compiling B::Concise! If we
+# they're compiling, their presence tends to distort the view we have of
+# the code we're looking at. In particular, perl gives sequence numbers
+# to COPs. If the program we're looking at were run on its own, this
+# would start at 1. Because all of B::Concise and all the modules it
+# uses are compiled first, though, by the time we get to the user's
+# program the sequence number is already pretty high, which could be
+# distracting if you're trying to tell OPs apart. Therefore we'd like to
+# subtract an offset from all the sequence numbers we display, to
+# restore the simpler view of the world. The trick is to know what that
+# offset will be, when we're still compiling B::Concise! If we
# hardcoded a value, it would have to change every time B::Concise or
-# other modules we use do. To help a little, what we do here is
-# compile a little code at the end of the module, and compute the base
-# sequence number for the user's program as being a small offset
-# later, so all we have to worry about are changes in the offset.
-# (Note that we now only play this game with COP sequence numbers. OP
-# sequence numbers aren't used to refer to OPs from a distance, and
-# they don't have much significance, so we just generate our own
-# sequence numbers which are easier to control. This way we also don't
-# stand in the way of a possible future removal of OP sequence
-# numbers).
+# other modules we use do. To help a little, what we do here is compile
+# a little code at the end of the module, and compute the base sequence
+# number for the user's program as being a small offset later, so all we
+# have to worry about are changes in the offset.
+
+# [For 5.8.x and earlier perl is generating sequence numbers for all ops,
+# and using them to reference labels]
+
# When you say "perl -MO=Concise -e '$a'", the output should look like:
# Remember, this needs to stay the last things in the module.
# Why is this different for MacOS? Does it matter?
-my $cop_seq_mnum = $^O eq 'MacOS' ? 10 : 9;
+my $cop_seq_mnum = $^O eq 'MacOS' ? 12 : 11;
$cop_seq_base = svref_2object(eval 'sub{0;}')->START->cop_seq + $cop_seq_mnum;
1;
the inner workings of perl or other compiler backends. It can print OPs in
the order they appear in the OP tree, in the order they will execute, or
in a text approximation to their tree structure, and the format of the
-information displyed is customizable. Its function is similar to that of
+information displayed is customizable. Its function is similar to that of
perl's B<-Dx> debugging flag or the B<B::Terse> module, but it is more
sophisticated and flexible.
=head1 EXAMPLE
-Here's is a short example of output, using the default formatting
-conventions :
+Here's two outputs (or 'renderings'), using the -exec and -basic
+(i.e. default) formatting conventions on the same code snippet.
+
+ % perl -MO=Concise,-exec -e '$a = $b + 42'
+ 1 <0> enter
+ 2 <;> nextstate(main 1 -e:1) v
+ 3 <#> gvsv[*b] s
+ 4 <$> const[IV 42] s
+ * 5 <2> add[t3] sK/2
+ 6 <#> gvsv[*a] s
+ 7 <2> sassign vKS/2
+ 8 <@> leave[1 ref] vKP/REFC
+
+In this -exec rendering, each opcode is executed in the order shown.
+The add opcode, marked with '*', is discussed in more detail.
+
+The 1st column is the op's sequence number, starting at 1, and is
+displayed in base 36 by default. Here they're purely linear; the
+sequences are very helpful when looking at code with loops and
+branches.
+
+The symbol between angle brackets indicates the op's type, for
+example; <2> is a BINOP, <@> a LISTOP, and <#> is a PADOP, which is
+used in threaded perls. (see L</"OP class abbreviations">).
+
+The opname, as in B<'add[t1]'>, may be followed by op-specific
+information in parentheses or brackets (ex B<'[t1]'>).
+
+The op-flags (ex B<'sK/2'>) are described in (L</"OP flags
+abbreviations">).
% perl -MO=Concise -e '$a = $b + 42'
- 8 <@> leave[t1] vKP/REFC ->(end)
+ 8 <@> leave[1 ref] vKP/REFC ->(end)
1 <0> enter ->2
2 <;> nextstate(main 1 -e:1) v ->3
7 <2> sassign vKS/2 ->8
- 5 <2> add[t1] sK/2 ->6
+ * 5 <2> add[t1] sK/2 ->6
- <1> ex-rv2sv sK/1 ->4
3 <$> gvsv(*b) s ->4
4 <$> const(IV 42) s ->5
- <1> ex-rv2sv sKRM*/1 ->7
6 <$> gvsv(*a) s ->7
-Each line corresponds to an operator. Null ops appear as C<ex-opname>,
-where I<opname> is the op that has been optimized away by perl.
-
-The number on the first row indicates the op's sequence number. It's
-given in base 36 by default.
+The default rendering is top-down, so they're not in execution order.
+This form reflects the way the stack is used to parse and evaluate
+expressions; the add operates on the two terms below it in the tree.
-The symbol between angle brackets indicates the op's type : for example,
-<2> is a BINOP, <@> a LISTOP, etc. (see L</"OP class abbreviations">).
+Nullops appear as C<ex-opname>, where I<opname> is an op that has been
+optimized away by perl. They're displayed with a sequence-number of
+'-', because they are not executed (they don't appear in previous
+example), they're printed here because they reflect the parse.
-The opname may be followed by op-specific information in parentheses
-(e.g. C<gvsv(*b)>), and by targ information in brackets (e.g.
-C<leave[t1]>).
+The arrow points to the sequence number of the next op; they're not
+displayed in -exec mode, for obvious reasons.
-Next come the op flags. The common flags are listed below
-(L</"OP flags abbreviations">). The private flags follow, separated
-by a slash. For example, C<vKP/REFC> means that the leave op has
-public flags OPf_WANT_VOID, OPf_KIDS, and OPf_PARENS, and the private
-flag OPpREFCOUNTED.
+Note that because this rendering was done on a non-threaded perl, the
+PADOPs in the previous examples are now SVOPs, and some (but not all)
+of the square brackets have been replaced by round ones. This is a
+subtle feature to provide some visual distinction between renderings
+on threaded and un-threaded perls.
-Finally an arrow points to the sequence number of the next op.
=head1 OPTIONS
Arguments that don't start with a hyphen are taken to be the names of
-subroutines to print the OPs of; if no such functions are specified, the
-main body of the program (outside any subroutines, and not including use'd
-or require'd files) is printed.
+subroutines to render; if no such functions are specified, the main
+body of the program (outside any subroutines, and not including use'd
+or require'd files) is rendered. Passing C<BEGIN>, C<UNITCHECK>,
+C<CHECK>, C<INIT>, or C<END> will cause all of the corresponding
+special blocks to be printed. Arguments must follow options.
+
+Options affect how things are rendered (ie printed). They're presented
+here by their visual effect, 1st being strongest. They're grouped
+according to how they interrelate; within each group the options are
+mutually exclusive (unless otherwise stated).
+
+=head2 Options for Opcode Ordering
+
+These options control the 'vertical display' of opcodes. The display
+'order' is also called 'mode' elsewhere in this document.
=over 4
Print OPs in the order they appear in the OP tree (a preorder
traversal, starting at the root). The indentation of each OP shows its
-level in the tree. This mode is the default, so the flag is included
-simply for completeness.
+level in the tree, and the '->' at the end of the line indicates the
+next opcode in execution order. This mode is the default, so the flag
+is included simply for completeness.
=item B<-exec>
it isn't suitable for large programs (unless you have a very wide
terminal).
+=back
+
+=head2 Options for Line-Style
+
+These options select the line-style (or just style) used to render
+each opcode, and dictates what info is actually printed into each line.
+
+=over 4
+
+=item B<-concise>
+
+Use the author's favorite set of formatting conventions. This is the
+default, of course.
+
+=item B<-terse>
+
+Use formatting conventions that emulate the output of B<B::Terse>. The
+basic mode is almost indistinguishable from the real B<B::Terse>, and the
+exec mode looks very similar, but is in a more logical order and lacks
+curly brackets. B<B::Terse> doesn't have a tree mode, so the tree mode
+is only vaguely reminiscent of B<B::Terse>.
+
+=item B<-linenoise>
+
+Use formatting conventions in which the name of each OP, rather than being
+written out in full, is represented by a one- or two-character abbreviation.
+This is mainly a joke.
+
+=item B<-debug>
+
+Use formatting conventions reminiscent of B<B::Debug>; these aren't
+very concise at all.
+
+=item B<-env>
+
+Use formatting conventions read from the environment variables
+C<B_CONCISE_FORMAT>, C<B_CONCISE_GOTO_FORMAT>, and C<B_CONCISE_TREE_FORMAT>.
+
+=back
+
+=head2 Options for tree-specific formatting
+
+=over 4
+
=item B<-compact>
Use a tree format in which the minimum amount of space is used for the
terminal (or the horizontal scrolling mode of less(1)) and are suitable
for text documentation or email. This is the default.
-=item B<-main>
+=back
-Include the main program in the output, even if subroutines were also
-specified.
+These are pairwise exclusive, i.e. compact or loose, vt or ascii.
+
+=head2 Options controlling sequence numbering
+
+=over 4
=item B<-base>I<n>
=item B<-littleendian>
-Print seqence numbers with the least significant digit first.
+Print sequence numbers with the least significant digit first. This is
+obviously mutually exclusive with bigendian.
-=item B<-concise>
+=back
-Use the author's favorite set of formatting conventions. This is the
-default, of course.
+=head2 Other options
-=item B<-terse>
+=over 4
-Use formatting conventions that emulate the output of B<B::Terse>. The
-basic mode is almost indistinguishable from the real B<B::Terse>, and the
-exec mode looks very similar, but is in a more logical order and lacks
-curly brackets. B<B::Terse> doesn't have a tree mode, so the tree mode
-is only vaguely reminiscient of B<B::Terse>.
+=item B<-src>
+
+With this option, the rendering of each statement (starting with the
+nextstate OP) will be preceded by the 1st line of source code that
+generates it. For example:
+
+ 1 <0> enter
+ # 1: my $i;
+ 2 <;> nextstate(main 1 junk.pl:1) v:{
+ 3 <0> padsv[$i:1,10] vM/LVINTRO
+ # 3: for $i (0..9) {
+ 4 <;> nextstate(main 3 junk.pl:3) v:{
+ 5 <0> pushmark s
+ 6 <$> const[IV 0] s
+ 7 <$> const[IV 9] s
+ 8 <{> enteriter(next->j last->m redo->9)[$i:1,10] lKS
+ k <0> iter s
+ l <|> and(other->9) vK/1
+ # 4: print "line ";
+ 9 <;> nextstate(main 2 junk.pl:4) v
+ a <0> pushmark s
+ b <$> const[PV "line "] s
+ c <@> print vK
+ # 5: print "$i\n";
+ ...
+
+=item B<-stash="somepackage">
+
+With this, "somepackage" will be required, then the stash is
+inspected, and each function is rendered.
-=item B<-linenoise>
+=back
-Use formatting conventions in which the name of each OP, rather than being
-written out in full, is represented by a one- or two-character abbreviation.
-This is mainly a joke.
+The following options are pairwise exclusive.
-=item B<-debug>
+=over 4
-Use formatting conventions reminiscient of B<B::Debug>; these aren't
-very concise at all.
+=item B<-main>
-=item B<-env>
+Include the main program in the output, even if subroutines were also
+specified. This rendering is normally suppressed when a subroutine
+name or reference is given.
-Use formatting conventions read from the environment variables
-C<B_CONCISE_FORMAT>, C<B_CONCISE_GOTO_FORMAT>, and C<B_CONCISE_TREE_FORMAT>.
+=item B<-nomain>
+
+This restores the default behavior after you've changed it with '-main'
+(it's not normally needed). If no subroutine name/ref is given, main is
+rendered, regardless of this flag.
+
+=item B<-nobanner>
+
+Renderings usually include a banner line identifying the function name
+or stringified subref. This suppresses the printing of the banner.
+
+TBC: Remove the stringified coderef; while it provides a 'cookie' for
+each function rendered, the cookies used should be 1,2,3.. not a
+random hex-address. It also complicates string comparison of two
+different trees.
+
+=item B<-banner>
+
+restores default banner behavior.
+
+=item B<-banneris> => subref
+
+TBC: a hookpoint (and an option to set it) for a user-supplied
+function to produce a banner appropriate for users needs. It's not
+ideal, because the rendering-state variables, which are a natural
+candidate for use in concise.t, are unavailable to the user.
=back
+=head2 Option Stickiness
+
+If you invoke Concise more than once in a program, you should know that
+the options are 'sticky'. This means that the options you provide in
+the first call will be remembered for the 2nd call, unless you
+re-specify or change them.
+
+=head1 ABBREVIATIONS
+
+The concise style uses symbols to convey maximum info with minimal
+clutter (like hex addresses). With just a little practice, you can
+start to see the flowers, not just the branches, in the trees.
+
+=head2 OP class abbreviations
+
+These symbols appear before the op-name, and indicate the
+B:: namespace that represents the ops in your Perl code.
+
+ 0 OP (aka BASEOP) An OP with no children
+ 1 UNOP An OP with one child
+ 2 BINOP An OP with two children
+ | LOGOP A control branch OP
+ @ LISTOP An OP that could have lots of children
+ / PMOP An OP with a regular expression
+ $ SVOP An OP with an SV
+ " PVOP An OP with a string
+ { LOOP An OP that holds pointers for a loop
+ ; COP An OP that marks the start of a statement
+ # PADOP An OP with a GV on the pad
+
+=head2 OP flags abbreviations
+
+OP flags are either public or private. The public flags alter the
+behavior of each opcode in consistent ways, and are represented by 0
+or more single characters.
+
+ v OPf_WANT_VOID Want nothing (void context)
+ s OPf_WANT_SCALAR Want single value (scalar context)
+ l OPf_WANT_LIST Want list of any length (list context)
+ Want is unknown
+ K OPf_KIDS There is a firstborn child.
+ P OPf_PARENS This operator was parenthesized.
+ (Or block needs explicit scope entry.)
+ R OPf_REF Certified reference.
+ (Return container, not containee).
+ M OPf_MOD Will modify (lvalue).
+ S OPf_STACKED Some arg is arriving on the stack.
+ * OPf_SPECIAL Do something weird for this op (see op.h)
+
+Private flags, if any are set for an opcode, are displayed after a '/'
+
+ 8 <@> leave[1 ref] vKP/REFC ->(end)
+ 7 <2> sassign vKS/2 ->8
+
+They're opcode specific, and occur less often than the public ones, so
+they're represented by short mnemonics instead of single-chars; see
+F<op.h> for gory details, or try this quick 2-liner:
+
+ $> perl -MB::Concise -de 1
+ DB<1> |x \%B::Concise::priv
+
=head1 FORMATTING SPECIFICATIONS
-For each general style ('concise', 'terse', 'linenoise', etc.) there are
-three specifications: one of how OPs should appear in the basic or exec
-modes, one of how 'goto' lines should appear (these occur in the exec
-mode only), and one of how nodes should appear in tree mode. Each has the
-same format, described below. Any text that doesn't match a special
-pattern is copied verbatim.
+For each line-style ('concise', 'terse', 'linenoise', etc.) there are
+3 format-specs which control how OPs are rendered.
+
+The first is the 'default' format, which is used in both basic and exec
+modes to print all opcodes. The 2nd, goto-format, is used in exec
+mode when branches are encountered. They're not real opcodes, and are
+inserted to look like a closing curly brace. The tree-format is tree
+specific.
+
+When a line is rendered, the correct format-spec is copied and scanned
+for the following items; data is substituted in, and other
+manipulations like basic indenting are done, for each opcode rendered.
+
+There are 3 kinds of items that may be populated; special patterns,
+#vars, and literal text, which is copied verbatim. (Yes, it's a set
+of s///g steps.)
+
+=head2 Special Patterns
+
+These items are the primitives used to perform indenting, and to
+select text from amongst alternatives.
=over 4
value of I<var> surrounded by I<text1> and I<Text2>, otherwise
nothing.
+=item B<~>
+
+Any number of tildes and surrounding whitespace will be collapsed to
+a single space.
+
+=back
+
+=head2 # Variables
+
+These #vars represent opcode properties that you may want as part of
+your rendering. The '#' is intended as a private sigil; a #var's
+value is interpolated into the style-line, much like "read $this".
+
+These vars take 3 forms:
+
+=over 4
+
=item B<#>I<var>
-Generates the value of the variable I<var>.
+A property named 'var' is assumed to exist for the opcodes, and is
+interpolated into the rendering.
=item B<#>I<var>I<N>
-Generates the value of I<var>, left jutified to fill I<N> spaces.
+Generates the value of I<var>, left justified to fill I<N> spaces.
+Note that this means while you can have properties 'foo' and 'foo2',
+you cannot render 'foo2', but you could with 'foo2a'. You would be
+wise not to rely on this behavior going forward ;-)
-=item B<~>
+=item B<#>I<Var>
-Any number of tildes and surrounding whitespace will be collapsed to
-a single space.
+This ucfirst form of #var generates a tag-value form of itself for
+display; it converts '#Var' into a 'Var => #var' style, which is then
+handled as described above. (Imp-note: #Vars cannot be used for
+conditional-fills, because the => #var transform is done after the check
+for #Var's value).
=back
-The following variables are recognized:
+The following variables are 'defined' by B::Concise; when they are
+used in a style, their respective values are plugged into the
+rendering of each opcode.
+
+Only some of these are used by the standard styles, the others are
+provided for you to delve into optree mechanics, should you wish to
+add a new style (see L</add_style> below) that uses them. You can
+also add new ones using L</add_callback>.
=over 4
=item B<#addr>
-The address of the OP, in hexidecimal.
+The address of the OP, in hexadecimal.
=item B<#arg>
The OP-specific information of the OP (such as the SV for an SVOP, the
-non-local exit pointers for a LOOP, etc.) enclosed in paretheses.
+non-local exit pointers for a LOOP, etc.) enclosed in parentheses.
=item B<#class>
=item B<#firstaddr>
-The address of the OP's first child, in hexidecimal.
+The address of the OP's first child, in hexadecimal.
=item B<#flags>
The numeric value of the OP's flags.
+=item B<#hints>
+
+The COP's hint flags, rendered with abbreviated names if possible. An empty
+string if this is not a COP. Here are the symbols used:
+
+ $ strict refs
+ & strict subs
+ * strict vars
+ i integers
+ l locale
+ b bytes
+ [ arybase
+ { block scope
+ % localise %^H
+ < open in
+ > open out
+ I overload int
+ F overload float
+ B overload binary
+ S overload string
+ R overload re
+ T taint
+ E eval
+ X filetest access
+ U utf-8
+
+=item B<#hintsval>
+
+The numeric value of the COP's hint flags, or an empty string if this is not
+a COP.
+
=item B<#hyphseq>
The sequence number of the OP, or a hyphen if it doesn't have one.
=item B<#lastaddr>
-The address of the OP's last child, in hexidecimal.
+The address of the OP's last child, in hexadecimal.
=item B<#name>
=item B<#nextaddr>
-The address of the OP's next OP, in hexidecimal.
+The address of the OP's next OP, in hexadecimal.
=item B<#noise>
=item B<#seq>
-The sequence number of the OP. Note that this is now a sequence number
-generated by B::Concise, rather than the real op_seq value (for which
-see B<#seqnum>).
+The sequence number of the OP. Note that this is a sequence number
+generated by B::Concise.
=item B<#seqnum>
+5.8.x and earlier only. 5.9 and later do not provide this.
+
The real sequence number of the OP, as a regular number and not adjusted
to be relative to the start of the real program. (This will generally be
a fairly large number because all of B<B::Concise> is compiled before
your program is).
+=item B<#opt>
+
+Whether or not the op has been optimised by the peephole optimiser.
+
+Only available in 5.9 and later.
+
=item B<#sibaddr>
-The address of the OP's next youngest sibling, in hexidecimal.
+The address of the OP's next youngest sibling, in hexadecimal.
=item B<#svaddr>
-The address of the OP's SV, if it has an SV, in hexidecimal.
+The address of the OP's SV, if it has an SV, in hexadecimal.
=item B<#svclass>
=back
-=head1 ABBREVIATIONS
+=head1 One-Liner Command tips
-=head2 OP flags abbreviations
+=over 4
- v OPf_WANT_VOID Want nothing (void context)
- s OPf_WANT_SCALAR Want single value (scalar context)
- l OPf_WANT_LIST Want list of any length (list context)
- K OPf_KIDS There is a firstborn child.
- P OPf_PARENS This operator was parenthesized.
- (Or block needs explicit scope entry.)
- R OPf_REF Certified reference.
- (Return container, not containee).
- M OPf_MOD Will modify (lvalue).
- S OPf_STACKED Some arg is arriving on the stack.
- * OPf_SPECIAL Do something weird for this op (see op.h)
+=item perl -MO=Concise,bar foo.pl
-=head2 OP class abbreviations
+Renders only bar() from foo.pl. To see main, drop the ',bar'. To see
+both, add ',-main'
- 0 OP (aka BASEOP) An OP with no children
- 1 UNOP An OP with one child
- 2 BINOP An OP with two children
- | LOGOP A control branch OP
- @ LISTOP An OP that could have lots of children
- / PMOP An OP with a regular expression
- $ SVOP An OP with an SV
- " PVOP An OP with a string
- { LOOP An OP that holds pointers for a loop
- ; COP An OP that marks the start of a statement
- # PADOP An OP with a GV on the pad
+=item perl -MDigest::MD5=md5 -MO=Concise,md5 -e1
+
+Identifies md5 as an XS function. The export is needed so that BC can
+find it in main.
+
+=item perl -MPOSIX -MO=Concise,_POSIX_ARG_MAX -e1
+
+Identifies _POSIX_ARG_MAX as a constant sub, optimized to an IV.
+Although POSIX isn't entirely consistent across platforms, this is
+likely to be present in virtually all of them.
+
+=item perl -MPOSIX -MO=Concise,a -e 'print _POSIX_SAVED_IDS'
+
+This renders a print statement, which includes a call to the function.
+It's identical to rendering a file with a use call and that single
+statement, except for the filename which appears in the nextstate ops.
+
+=item perl -MPOSIX -MO=Concise,a -e 'sub a{_POSIX_SAVED_IDS}'
+
+This is B<very> similar to previous, only the first two ops differ. This
+subroutine rendering is more representative, insofar as a single main
+program will have many subs.
+
+=item perl -MB::Concise -e 'B::Concise::compile("-exec","-src", \%B::Concise::)->()'
+
+This renders all functions in the B::Concise package with the source
+lines. It eschews the O framework so that the stashref can be passed
+directly to B::Concise::compile(). See -stash option for a more
+convenient way to render a package.
+
+=back
=head1 Using B::Concise outside of the O framework
-It is possible to extend B<B::Concise> by using it outside of the B<O>
-framework and providing new styles and new variables.
+The common (and original) usage of B::Concise was for command-line
+renderings of simple code, as given in EXAMPLE. But you can also use
+B<B::Concise> from your code, and call compile() directly, and
+repeatedly. By doing so, you can avoid the compile-time only
+operation of O.pm, and even use the debugger to step through
+B::Concise::compile() itself.
+
+Once you're doing this, you may alter Concise output by adding new
+rendering styles, and by optionally adding callback routines which
+populate new variables, if such were referenced from those (just
+added) styles.
+
+=head2 Example: Altering Concise Renderings
use B::Concise qw(set_style add_callback);
- set_style($format, $gotofmt, $treefmt);
+ add_style($yourStyleName => $defaultfmt, $gotofmt, $treefmt);
add_callback
- (
- sub
- {
- my ($h, $op, $level, $format) = @_;
+ ( sub {
+ my ($h, $op, $format, $level, $stylename) = @_;
$h->{variable} = some_func($op);
- }
- );
- B::Concise::compile(@options)->();
-
-You can specify a style by calling the B<set_style> subroutine. If you
-have a new variable in your style, or you want to change the value of an
-existing variable, you will need to add a callback to specify the value
-for that variable.
-
-This is done by calling B<add_callback> passing references to any
-callback subroutines. The subroutines are called in the same order as
-they are added. Each subroutine is passed four parameters. These are a
-reference to a hash, the keys of which are the names of the variables
-and the values of which are their values, the op, the level and the
-format.
+ });
+ $walker = B::Concise::compile(@options,@subnames,@subrefs);
+ $walker->();
+
+=head2 set_style()
+
+B<set_style> accepts 3 arguments, and updates the three format-specs
+comprising a line-style (basic-exec, goto, tree). It has one minor
+drawback though; it doesn't register the style under a new name. This
+can become an issue if you render more than once and switch styles.
+Thus you may prefer to use add_style() and/or set_style_standard()
+instead.
+
+=head2 set_style_standard($name)
+
+This restores one of the standard line-styles: C<terse>, C<concise>,
+C<linenoise>, C<debug>, C<env>, into effect. It also accepts style
+names previously defined with add_style().
+
+=head2 add_style ()
+
+This subroutine accepts a new style name and three style arguments as
+above, and creates, registers, and selects the newly named style. It is
+an error to re-add a style; call set_style_standard() to switch between
+several styles.
+
+=head2 add_callback ()
+
+If your newly minted styles refer to any new #variables, you'll need
+to define a callback subroutine that will populate (or modify) those
+variables. They are then available for use in the style you've
+chosen.
+
+The callbacks are called for each opcode visited by Concise, in the
+same order as they are added. Each subroutine is passed five
+parameters.
+
+ 1. A hashref, containing the variable names and values which are
+ populated into the report-line for the op
+ 2. the op, as a B<B::OP> object
+ 3. a reference to the format string
+ 4. the formatting (indent) level
+ 5. the selected stylename
To define your own variables, simply add them to the hash, or change
existing values if you need to. The level and format are passed in as
references to scalars, but it is unlikely that they will need to be
changed or even used.
-To switch back to one of the standard styles like C<concise> or
-C<terse>, use C<set_style_standard>.
-
-To see the output, call the subroutine returned by B<compile> in the
-same way that B<O> does.
+=head2 Running B::Concise::compile()
+
+B<compile> accepts options as described above in L</OPTIONS>, and
+arguments, which are either coderefs, or subroutine names.
+
+It constructs and returns a $treewalker coderef, which when invoked,
+traverses, or walks, and renders the optrees of the given arguments to
+STDOUT. You can reuse this, and can change the rendering style used
+each time; thereafter the coderef renders in the new style.
+
+B<walk_output> lets you change the print destination from STDOUT to
+another open filehandle, or into a string passed as a ref (unless
+you've built perl with -Uuseperlio).
+
+ my $walker = B::Concise::compile('-terse','aFuncName', \&aSubRef); # 1
+ walk_output(\my $buf);
+ $walker->(); # 1 renders -terse
+ set_style_standard('concise'); # 2
+ $walker->(); # 2 renders -concise
+ $walker->(@new); # 3 renders whatever
+ print "3 different renderings: terse, concise, and @new: $buf\n";
+
+When $walker is called, it traverses the subroutines supplied when it
+was created, and renders them using the current style. You can change
+the style afterwards in several different ways:
+
+ 1. call C<compile>, altering style or mode/order
+ 2. call C<set_style_standard>
+ 3. call $walker, passing @new options
+
+Passing new options to the $walker is the easiest way to change
+amongst any pre-defined styles (the ones you add are automatically
+recognized as options), and is the only way to alter rendering order
+without calling compile again. Note however that rendering state is
+still shared amongst multiple $walker objects, so they must still be
+used in a coordinated manner.
+
+=head2 B::Concise::reset_sequence()
+
+This function (not exported) lets you reset the sequence numbers (note
+that they're numbered arbitrarily, their goal being to be human
+readable). Its purpose is mostly to support testing, i.e. to compare
+the concise output from two identical anonymous subroutines (but
+different instances). Without the reset, B::Concise, seeing that
+they're separate optrees, generates different sequence numbers in
+the output.
+
+=head2 Errors
+
+Errors in rendering (non-existent function-name, non-existent coderef)
+are written to the STDOUT, or wherever you've set it via
+walk_output().
+
+Errors using the various *style* calls, and bad args to walk_output(),
+result in die(). Use an eval if you wish to catch these errors and
+continue processing.
=head1 AUTHOR
https://perl5.git.perl.org / perl5.git / blobdiff