Extract the opcode data from regen/opcode.pl into regen/opcodes

Whilst it is possible to open regen/opcode.pl and parse it to find the __END__
token, it's not the cleanest approach.

1 files changed, 5 insertions, 552 deletions

diff --git a/regen/opcode.pl b/regen/opcode.pl
index 5b7aee73ab..54b78b8aeb 100755
--- a/regen/opcode.pl
+++ b/regen/opcode.pl
@@ -6,7 +6,7 @@
 #    opnames.h
 #    pp.sym
 #
-# from information stored in the DATA section of this file, plus the
+# from information stored in regen/opcodes, plus the
 # values hardcoded into this script in @raw_alias.
 #
 # Accepts the standard regen_lib -q and -v args.
@@ -31,7 +31,9 @@ select $oc;
 my %seen;
 my (@ops, %desc, %check, %ckname, %flags, %args, %opnum);
 
-while (<DATA>) {
+open OPS, 'regen/opcodes' or die $!;
+
+while (<OPS>) {
     chop;
     next unless $_;
     next if /^#/;
@@ -419,7 +421,7 @@ print $on <<EO_OP_IS_COMMENT;
 
 /* the OP_IS_(SOCKET|FILETEST) macros are optimized to a simple range
     check because all the member OPs are contiguous in opcode.pl
-    <DATA> table.  opcode.pl verifies the range contiguity.  */
+    <OPS> table.  opcode.pl verifies the range contiguity.  */
 
 EO_OP_IS_COMMENT
 
@@ -565,552 +567,3 @@ sub tab {
 #	gmtime not OK (list context)
 
 #	Suspicious wrt "additional mode of failure": warn, die, select.
-
-__END__
-
-# New ops always go at the end
-# The restriction on having custom as the last op has been removed
-
-# A recapitulation of the format of this file:
-# The file consists of five columns: the name of the op, an English
-# description, the name of the "check" routine used to optimize this
-# operation, some flags, and a description of the operands.
-
-# The flags consist of options followed by a mandatory op class signifier
-
-# The classes are:
-# baseop      - 0            unop     - 1            binop      - 2
-# logop       - |            listop   - @            pmop       - /
-# padop/svop  - $            padop    - # (unused)   loop       - {
-# baseop/unop - %            loopexop - }            filestatop - -
-# pvop/svop   - "            cop      - ;
-
-# Other options are:
-#   needs stack mark                    - m
-#   needs constant folding              - f
-#   produces a scalar                   - s
-#   produces an integer                 - i
-#   needs a target                      - t
-#   target can be in a pad              - T
-#   has a corresponding integer version - I
-#   has side effects                    - d
-#   uses $_ if no argument given        - u
-
-# Values for the operands are:
-# scalar      - S            list     - L            array     - A
-# hash        - H            sub (CV) - C            file      - F
-# socket      - Fs           filetest - F-           filetest_access - F-+
-
-# reference - R
-# "?" denotes an optional operand.
-
-# Nothing.
-
-null		null operation		ck_null		0	
-stub		stub			ck_null		0
-scalar		scalar			ck_fun		s%	S
-
-# Pushy stuff.
-
-pushmark	pushmark		ck_null		s0	
-wantarray	wantarray		ck_null		is0	
-
-const		constant item		ck_svconst	s$	
-
-gvsv		scalar variable		ck_null		ds$	
-gv		glob value		ck_null		ds$	
-gelem		glob elem		ck_null		d2	S S
-padsv		private variable	ck_null		ds0
-padav		private array		ck_null		d0
-padhv		private hash		ck_null		d0
-padany		private value		ck_null		d0
-
-pushre		push regexp		ck_null		d/
-
-# References and stuff.
-
-rv2gv		ref-to-glob cast	ck_rvconst	ds1	
-rv2sv		scalar dereference	ck_rvconst	ds1	
-av2arylen	array length		ck_null		is1	
-rv2cv		subroutine dereference	ck_rvconst	d1
-anoncode	anonymous subroutine	ck_anoncode	$	
-prototype	subroutine prototype	ck_null		s%	S
-refgen		reference constructor	ck_spair	m1	L
-srefgen		single ref constructor	ck_null		fs1	S
-ref		reference-type operator	ck_fun		stu%	S?
-bless		bless			ck_fun		s@	S S?
-
-# Pushy I/O.
-
-backtick	quoted execution (``, qx)	ck_open		tu%	S?
-# glob defaults its first arg to $_
-glob		glob			ck_glob		t@	S?
-readline	<HANDLE>		ck_readline	t%	F?
-rcatline	append I/O operator	ck_null		t$
-
-# Bindable operators.
-
-regcmaybe	regexp internal guard	ck_fun		s1	S
-regcreset	regexp internal reset	ck_fun		s1	S
-regcomp		regexp compilation	ck_null		s|	S
-match		pattern match (m//)	ck_match	d/
-qr		pattern quote (qr//)	ck_match	s/
-subst		substitution (s///)	ck_match	dis/	S
-substcont	substitution iterator	ck_null		dis|	
-trans		transliteration (tr///)	ck_match	is"	S
-# transr (the /r version) is further down.
-
-# Lvalue operators.
-# sassign is special-cased for op class
-
-sassign		scalar assignment	ck_sassign	s0
-aassign		list assignment		ck_null		t2	L L
-
-chop		chop			ck_spair	mts%	L
-schop		scalar chop		ck_null		stu%	S?
-chomp		chomp			ck_spair	mTs%	L
-schomp		scalar chomp		ck_null		sTu%	S?
-defined		defined operator	ck_defined	isu%	S?
-undef		undef operator		ck_lfun		s%	S?
-study		study			ck_fun		su%	S?
-pos		match position		ck_lfun		stu%	S?
-
-preinc		preincrement (++)		ck_lfun		dIs1	S
-i_preinc	integer preincrement (++)	ck_lfun		dis1	S
-predec		predecrement (--)		ck_lfun		dIs1	S
-i_predec	integer predecrement (--)	ck_lfun		dis1	S
-postinc		postincrement (++)		ck_lfun		dIst1	S
-i_postinc	integer postincrement (++)	ck_lfun		disT1	S
-postdec		postdecrement (--)		ck_lfun		dIst1	S
-i_postdec	integer postdecrement (--)	ck_lfun		disT1	S
-
-# Ordinary operators.
-
-pow		exponentiation (**)	ck_null		fsT2	S S
-
-multiply	multiplication (*)	ck_null		IfsT2	S S
-i_multiply	integer multiplication (*)	ck_null		ifsT2	S S
-divide		division (/)		ck_null		IfsT2	S S
-i_divide	integer division (/)	ck_null		ifsT2	S S
-modulo		modulus (%)		ck_null		IifsT2	S S
-i_modulo	integer modulus (%)	ck_null		ifsT2	S S
-repeat		repeat (x)		ck_repeat	mt2	L S
-
-add		addition (+)		ck_null		IfsT2	S S
-i_add		integer addition (+)	ck_null		ifsT2	S S
-subtract	subtraction (-)		ck_null		IfsT2	S S
-i_subtract	integer subtraction (-)	ck_null		ifsT2	S S
-concat		concatenation (.) or string	ck_concat	fsT2	S S
-stringify	string			ck_fun		fsT@	S
-
-left_shift	left bitshift (<<)	ck_bitop	fsT2	S S
-right_shift	right bitshift (>>)	ck_bitop	fsT2	S S
-
-lt		numeric lt (<)		ck_null		Iifs2	S S
-i_lt		integer lt (<)		ck_null		ifs2	S S
-gt		numeric gt (>)		ck_null		Iifs2	S S
-i_gt		integer gt (>)		ck_null		ifs2	S S
-le		numeric le (<=)		ck_null		Iifs2	S S
-i_le		integer le (<=)		ck_null		ifs2	S S
-ge		numeric ge (>=)		ck_null		Iifs2	S S
-i_ge		integer ge (>=)		ck_null		ifs2	S S
-eq		numeric eq (==)		ck_null		Iifs2	S S
-i_eq		integer eq (==)		ck_null		ifs2	S S
-ne		numeric ne (!=)		ck_null		Iifs2	S S
-i_ne		integer ne (!=)		ck_null		ifs2	S S
-ncmp		numeric comparison (<=>)	ck_null		Iifst2	S S
-i_ncmp		integer comparison (<=>)	ck_null		ifst2	S S
-
-slt		string lt		ck_null		ifs2	S S
-sgt		string gt		ck_null		ifs2	S S
-sle		string le		ck_null		ifs2	S S
-sge		string ge		ck_null		ifs2	S S
-seq		string eq		ck_null		ifs2	S S
-sne		string ne		ck_null		ifs2	S S
-scmp		string comparison (cmp)	ck_null		ifst2	S S
-
-bit_and		bitwise and (&)		ck_bitop	fst2	S S
-bit_xor		bitwise xor (^)		ck_bitop	fst2	S S
-bit_or		bitwise or (|)		ck_bitop	fst2	S S
-
-negate		negation (-)		ck_null		Ifst1	S
-i_negate	integer negation (-)	ck_null		ifsT1	S
-not		not			ck_null		ifs1	S
-complement	1's complement (~)	ck_bitop	fst1	S
-
-smartmatch	smart match		ck_smartmatch	s2
-
-# High falutin' math.
-
-atan2		atan2			ck_fun		fsT@	S S
-sin		sin			ck_fun		fsTu%	S?
-cos		cos			ck_fun		fsTu%	S?
-rand		rand			ck_fun		sT%	S?
-srand		srand			ck_fun		sT%	S?
-exp		exp			ck_fun		fsTu%	S?
-log		log			ck_fun		fsTu%	S?
-sqrt		sqrt			ck_fun		fsTu%	S?
-
-# Lowbrow math.
-
-int		int			ck_fun		fsTu%	S?
-hex		hex			ck_fun		fsTu%	S?
-oct		oct			ck_fun		fsTu%	S?
-abs		abs			ck_fun		fsTu%	S?
-
-# String stuff.
-
-length		length			ck_fun		ifsTu%	S?
-substr		substr			ck_substr	st@	S S S? S?
-vec		vec			ck_fun		ist@	S S S
-
-index		index			ck_index	isT@	S S S?
-rindex		rindex			ck_index	isT@	S S S?
-
-sprintf		sprintf			ck_fun		fmst@	S L
-formline	formline		ck_fun		ms@	S L
-ord		ord			ck_fun		ifsTu%	S?
-chr		chr			ck_fun		fsTu%	S?
-crypt		crypt			ck_fun		fsT@	S S
-ucfirst		ucfirst			ck_fun		fstu%	S?
-lcfirst		lcfirst			ck_fun		fstu%	S?
-uc		uc			ck_fun		fstu%	S?
-lc		lc			ck_fun		fstu%	S?
-quotemeta	quotemeta		ck_fun		fstu%	S?
-
-# Arrays.
-
-rv2av		array dereference	ck_rvconst	dt1	
-aelemfast	constant array element	ck_null		s$	A S
-aelem		array element		ck_null		s2	A S
-aslice		array slice		ck_null		m@	A L
-
-aeach		each on array		ck_each		%	A
-akeys		keys on array		ck_each		t%	A
-avalues		values on array		ck_each		t%	A
-
-# Hashes.
-
-each		each			ck_each		%	H
-values		values			ck_each		t%	H
-keys		keys			ck_each		t%	H
-delete		delete			ck_delete	%	S
-exists		exists			ck_exists	is%	S
-rv2hv		hash dereference	ck_rvconst	dt1	
-helem		hash element		ck_null		s2	H S
-hslice		hash slice		ck_null		m@	H L
-boolkeys	boolkeys		ck_fun		%	H
-
-# Explosives and implosives.
-
-unpack		unpack			ck_unpack	@	S S?
-pack		pack			ck_fun		mst@	S L
-split		split			ck_split	t@	S S S
-join		join or string		ck_join		mst@	S L
-
-# List operators.
-
-list		list			ck_null		m@	L
-lslice		list slice		ck_null		2	H L L
-anonlist	anonymous list ([])	ck_fun		ms@	L
-anonhash	anonymous hash ({})	ck_fun		ms@	L
-
-splice		splice			ck_push		m@	A S? S? L
-push		push			ck_push		imsT@	A L
-pop		pop			ck_shift	s%	A?
-shift		shift			ck_shift	s%	A?
-unshift		unshift			ck_push		imsT@	A L
-sort		sort			ck_sort		dm@	C? L
-reverse		reverse			ck_fun		mt@	L
-
-grepstart	grep			ck_grep		dm@	C L
-grepwhile	grep iterator		ck_null		dt|	
-
-mapstart	map			ck_grep		dm@	C L
-mapwhile	map iterator		ck_null		dt|
-
-# Range stuff.
-
-range		flipflop		ck_null		|	S S
-flip		range (or flip)		ck_null		1	S S
-flop		range (or flop)		ck_null		1
-
-# Control.
-
-and		logical and (&&)		ck_null		|	
-or		logical or (||)			ck_null		|	
-xor		logical xor			ck_null		fs2	S S	
-dor		defined or (//)			ck_null		|
-cond_expr	conditional expression		ck_null		d|	
-andassign	logical and assignment (&&=)	ck_null		s|	
-orassign	logical or assignment (||=)	ck_null		s|	
-dorassign	defined or assignment (//=)	ck_null		s|
-
-method		method lookup		ck_method	d1
-entersub	subroutine entry	ck_subr		dmt1	L
-leavesub	subroutine exit		ck_null		1	
-leavesublv	lvalue subroutine return	ck_null		1	
-caller		caller			ck_fun		t%	S?
-warn		warn			ck_fun		imst@	L
-die		die			ck_die		dimst@	L
-reset		symbol reset		ck_fun		is%	S?
-
-lineseq		line sequence		ck_null		@	
-nextstate	next statement		ck_null		s;	
-dbstate		debug next statement	ck_null		s;	
-unstack		iteration finalizer	ck_null		s0
-enter		block entry		ck_null		0	
-leave		block exit		ck_null		@	
-scope		block			ck_null		@	
-enteriter	foreach loop entry	ck_null		d{	
-iter		foreach loop iterator	ck_null		0	
-enterloop	loop entry		ck_null		d{	
-leaveloop	loop exit		ck_null		2	
-return		return			ck_return	dm@	L
-last		last			ck_null		ds}	
-next		next			ck_null		ds}	
-redo		redo			ck_null		ds}	
-dump		dump			ck_null		ds}	
-goto		goto			ck_null		ds}	
-exit		exit			ck_exit		ds%	S?
-method_named	method with known name	ck_null		d$
-
-entergiven	given()			ck_null		d|
-leavegiven	leave given block	ck_null		1
-enterwhen	when()			ck_null		d|
-leavewhen	leave when block	ck_null		1
-break		break			ck_null		0
-continue	continue		ck_null		0
-
-# I/O.
-
-open		open			ck_open		ismt@	F S? L
-close		close			ck_fun		is%	F?
-pipe_op		pipe			ck_fun		is@	F F
-
-fileno		fileno			ck_fun		ist%	F
-umask		umask			ck_fun		ist%	S?
-binmode		binmode			ck_fun		s@	F S?
-
-tie		tie			ck_fun		idms@	R S L
-untie		untie			ck_fun		is%	R
-tied		tied			ck_fun		s%	R
-dbmopen		dbmopen			ck_fun		is@	H S S
-dbmclose	dbmclose		ck_fun		is%	H
-
-sselect		select system call	ck_select	t@	S S S S
-select		select			ck_select	st@	F?
-
-getc		getc			ck_eof		st%	F?
-read		read			ck_fun		imst@	F R S S?
-enterwrite	write			ck_fun		dis%	F?
-leavewrite	write exit		ck_null		1	
-
-prtf		printf			ck_listiob	ims@	F? L
-print		print			ck_listiob	ims@	F? L
-say		say			ck_listiob	ims@	F? L
-
-sysopen		sysopen			ck_fun		s@	F S S S?
-sysseek		sysseek			ck_fun		s@	F S S
-sysread		sysread			ck_fun		imst@	F R S S?
-syswrite	syswrite		ck_fun		imst@	F S S? S?
-
-eof		eof			ck_eof		is%	F?
-tell		tell			ck_fun		st%	F?
-seek		seek			ck_fun		s@	F S S
-# truncate really behaves as if it had both "S S" and "F S"
-truncate	truncate		ck_trunc	is@	S S
-
-fcntl		fcntl			ck_fun		st@	F S S
-ioctl		ioctl			ck_fun		st@	F S S
-flock		flock			ck_fun		isT@	F S
-
-# Sockets.  OP_IS_SOCKET wants them consecutive (so moved 1st 2)
-
-send		send			ck_fun		imst@	Fs S S S?
-recv		recv			ck_fun		imst@	Fs R S S
-
-socket		socket			ck_fun		is@	Fs S S S
-sockpair	socketpair		ck_fun		is@	Fs Fs S S S
-
-bind		bind			ck_fun		is@	Fs S
-connect		connect			ck_fun		is@	Fs S
-listen		listen			ck_fun		is@	Fs S
-accept		accept			ck_fun		ist@	Fs Fs
-shutdown	shutdown		ck_fun		ist@	Fs S
-
-gsockopt	getsockopt		ck_fun		is@	Fs S S
-ssockopt	setsockopt		ck_fun		is@	Fs S S S
-
-getsockname	getsockname		ck_fun		is%	Fs
-getpeername	getpeername		ck_fun		is%	Fs
-
-# Stat calls.  OP_IS_FILETEST wants them consecutive.
-
-lstat		lstat			ck_ftst		u-	F
-stat		stat			ck_ftst		u-	F
-ftrread		-R			ck_ftst		isu-	F-+
-ftrwrite	-W			ck_ftst		isu-	F-+
-ftrexec		-X			ck_ftst		isu-	F-+
-fteread		-r			ck_ftst		isu-	F-+
-ftewrite	-w			ck_ftst		isu-	F-+
-fteexec		-x			ck_ftst		isu-	F-+
-ftis		-e			ck_ftst		isu-	F-
-ftsize		-s			ck_ftst		istu-	F-
-ftmtime		-M			ck_ftst		stu-	F-
-ftatime		-A			ck_ftst		stu-	F-
-ftctime		-C			ck_ftst		stu-	F-
-ftrowned	-O			ck_ftst		isu-	F-
-fteowned	-o			ck_ftst		isu-	F-
-ftzero		-z			ck_ftst		isu-	F-
-ftsock		-S			ck_ftst		isu-	F-
-ftchr		-c			ck_ftst		isu-	F-
-ftblk		-b			ck_ftst		isu-	F-
-ftfile		-f			ck_ftst		isu-	F-
-ftdir		-d			ck_ftst		isu-	F-
-ftpipe		-p			ck_ftst		isu-	F-
-ftsuid		-u			ck_ftst		isu-	F-
-ftsgid		-g			ck_ftst		isu-	F-
-ftsvtx		-k			ck_ftst		isu-	F-
-ftlink		-l			ck_ftst		isu-	F-
-fttty		-t			ck_ftst		is-	F-
-fttext		-T			ck_ftst		isu-	F-
-ftbinary	-B			ck_ftst		isu-	F-
-
-# File calls.
-
-# chdir really behaves as if it had both "S?" and "F?"
-chdir		chdir			ck_chdir	isT%	S?
-chown		chown			ck_fun		imsT@	L
-chroot		chroot			ck_fun		isTu%	S?
-unlink		unlink			ck_fun		imsTu@	L
-chmod		chmod			ck_fun		imsT@	L
-utime		utime			ck_fun		imsT@	L
-rename		rename			ck_fun		isT@	S S
-link		link			ck_fun		isT@	S S
-symlink		symlink			ck_fun		isT@	S S
-readlink	readlink		ck_fun		stu%	S?
-mkdir		mkdir			ck_fun		isTu@	S? S?
-rmdir		rmdir			ck_fun		isTu%	S?
-
-# Directory calls.
-
-open_dir	opendir			ck_fun		is@	F S
-readdir		readdir			ck_fun		%	F
-telldir		telldir			ck_fun		st%	F
-seekdir		seekdir			ck_fun		s@	F S
-rewinddir	rewinddir		ck_fun		s%	F
-closedir	closedir		ck_fun		is%	F
-
-# Process control.
-
-fork		fork			ck_null		ist0	
-wait		wait			ck_null		isT0	
-waitpid		waitpid			ck_fun		isT@	S S
-system		system			ck_exec		imsT@	S? L
-exec		exec			ck_exec		dimsT@	S? L
-kill		kill			ck_fun		dimsT@	L
-getppid		getppid			ck_null		isT0	
-getpgrp		getpgrp			ck_fun		isT%	S?
-setpgrp		setpgrp			ck_fun		isT@	S? S?
-getpriority	getpriority		ck_fun		isT@	S S
-setpriority	setpriority		ck_fun		isT@	S S S
-
-# Time calls.
-
-# NOTE: MacOS patches the 'i' of time() away later when the interpreter
-# is created because in MacOS time() is already returning times > 2**31-1,
-# that is, non-integers.
-
-time		time			ck_null		isT0	
-tms		times			ck_null		0	
-localtime	localtime		ck_fun		t%	S?
-gmtime		gmtime			ck_fun		t%	S?
-alarm		alarm			ck_fun		istu%	S?
-sleep		sleep			ck_fun		isT%	S?
-
-# Shared memory.
-
-shmget		shmget			ck_fun		imst@	S S S
-shmctl		shmctl			ck_fun		imst@	S S S
-shmread		shmread			ck_fun		imst@	S S S S
-shmwrite	shmwrite		ck_fun		imst@	S S S S
-
-# Message passing.
-
-msgget		msgget			ck_fun		imst@	S S
-msgctl		msgctl			ck_fun		imst@	S S S
-msgsnd		msgsnd			ck_fun		imst@	S S S
-msgrcv		msgrcv			ck_fun		imst@	S S S S S
-
-# Semaphores.
-
-semop		semop			ck_fun		imst@	S S
-semget		semget			ck_fun		imst@	S S S
-semctl		semctl			ck_fun		imst@	S S S S
-
-# Eval.
-
-require		require			ck_require	du%	S?
-dofile		do "file"		ck_fun		d1	S
-hintseval	eval hints		ck_svconst	s$
-entereval	eval "string"		ck_eval		d%	S
-leaveeval	eval "string" exit	ck_null		1	S
-#evalonce	eval constant string	ck_null		d1	S
-entertry	eval {block}		ck_eval		d|	
-leavetry	eval {block} exit	ck_null		@	
-
-# Get system info.
-
-ghbyname	gethostbyname		ck_fun		%	S
-ghbyaddr	gethostbyaddr		ck_fun		@	S S
-ghostent	gethostent		ck_null		0	
-gnbyname	getnetbyname		ck_fun		%	S
-gnbyaddr	getnetbyaddr		ck_fun		@	S S
-gnetent		getnetent		ck_null		0	
-gpbyname	getprotobyname		ck_fun		%	S
-gpbynumber	getprotobynumber	ck_fun		@	S
-gprotoent	getprotoent		ck_null		0	
-gsbyname	getservbyname		ck_fun		@	S S
-gsbyport	getservbyport		ck_fun		@	S S
-gservent	getservent		ck_null		0	
-shostent	sethostent		ck_fun		is%	S
-snetent		setnetent		ck_fun		is%	S
-sprotoent	setprotoent		ck_fun		is%	S
-sservent	setservent		ck_fun		is%	S
-ehostent	endhostent		ck_null		is0	
-enetent		endnetent		ck_null		is0	
-eprotoent	endprotoent		ck_null		is0	
-eservent	endservent		ck_null		is0	
-gpwnam		getpwnam		ck_fun		%	S
-gpwuid		getpwuid		ck_fun		%	S
-gpwent		getpwent		ck_null		0	
-spwent		setpwent		ck_null		is0	
-epwent		endpwent		ck_null		is0	
-ggrnam		getgrnam		ck_fun		%	S
-ggrgid		getgrgid		ck_fun		%	S
-ggrent		getgrent		ck_null		0	
-sgrent		setgrent		ck_null		is0	
-egrent		endgrent		ck_null		is0	
-getlogin	getlogin		ck_null		st0	
-
-# Miscellaneous.
-
-syscall		syscall			ck_fun		imst@	S L
-
-# For multi-threading
-lock		lock			ck_rfun		s%	R
-
-# For state support
-
-once		once			ck_null		|	
-
-custom		unknown custom operator		ck_null		0
-
-# For smart dereference for each/keys/values
-reach		each on reference			ck_each		%	S
-rkeys		keys on reference			ck_each		t%	S
-rvalues		values on reference			ck_each		t%	S
-
-# y///r
-transr		transliteration (tr///)	ck_match	is"	S