[perl5.git] / regcomp.sym

# regcomp.sym
#
# File has two sections, divided by a line of dashes '-'. 
#
# Empty rows after #-comment are removed from input are ignored
#
# First section is for regops, second sectionis for regmatch-states
#
# Note that the order in this file is important.
#
# Format for first section: 
# NAME \t TYPE, arg-description [num-args] [longjump-len] \t DESCRIPTION
#
#
# run perl regen.pl after editing this file


#* Exit points (0,1)

END		END,    no	End of program.
SUCCEED		END,    no	Return from a subroutine, basically.

#* Anchors: (2..13)

BOL		BOL,    no	Match "" at beginning of line.
MBOL		BOL,    no	Same, assuming multiline.
SBOL		BOL,    no	Same, assuming singleline.
EOS		EOL,    no	Match "" at end of string.
EOL		EOL,    no	Match "" at end of line.
MEOL		EOL,    no	Same, assuming multiline.
SEOL		EOL,    no	Same, assuming singleline.
BOUND		BOUND,  no	Match "" at any word boundary
BOUNDL		BOUND,  no	Match "" at any word boundary
NBOUND		NBOUND, no	Match "" at any word non-boundary
NBOUNDL		NBOUND, no	Match "" at any word non-boundary
GPOS		GPOS,   no	Matches where last m//g left off.

#* [Special] alternatives: (14..30)

REG_ANY		REG_ANY,    no	Match any one character (except newline).
SANY		REG_ANY,    no	Match any one character.
CANY		REG_ANY,    no	Match any one byte.
ANYOF		ANYOF,  sv	Match character in (or not in) this class.
ALNUM		ALNUM,  no	Match any alphanumeric character
ALNUML		ALNUM,  no	Match any alphanumeric char in locale
NALNUM		NALNUM, no	Match any non-alphanumeric character
NALNUML		NALNUM, no	Match any non-alphanumeric char in locale
SPACE		SPACE,  no	Match any whitespace character
SPACEL		SPACE,  no	Match any whitespace char in locale
NSPACE		NSPACE, no	Match any non-whitespace character
NSPACEL		NSPACE, no	Match any non-whitespace char in locale
DIGIT		DIGIT,  no	Match any numeric character
DIGITL		DIGIT,  no	Match any numeric character in locale
NDIGIT		NDIGIT, no	Match any non-numeric character
NDIGITL		NDIGIT, no	Match any non-numeric character in locale
CLUMP		CLUMP,  no	Match any combining character sequence

#* Alternation (31)

# BRANCH  	The set of branches constituting a single choice are hooked
#		together with their "next" pointers, since precedence prevents
#		anything being concatenated to any individual branch.  The
#		"next" pointer of the last BRANCH in a choice points to the
#		thing following the whole choice.  This is also where the
#		final "next" pointer of each individual branch points; each
#		branch starts with the operand node of a BRANCH node.
#
BRANCH		BRANCH, node	Match this alternative, or the next...

#*Back pointer (32)

# BACK		Normal "next" pointers all implicitly point forward; BACK
#		exists to make loop structures possible.
# not used
BACK		BACK,   no	Match "", "next" ptr points backward.

#*Literals (33..35)

EXACT		EXACT,  sv	Match this string (preceded by length).
EXACTF		EXACT,  sv	Match this string, folded (prec. by length).
EXACTFL		EXACT,  sv	Match this string, folded in locale (w/len).

#*Do nothing types (36..37)

NOTHING		NOTHING,no	Match empty string.
# A variant of above which delimits a group, thus stops optimizations
TAIL		NOTHING,no	Match empty string. Can jump here from outside.

#*Loops (38..44)

# STAR,PLUS	'?', and complex '*' and '+', are implemented as circular
#		BRANCH structures using BACK.  Simple cases (one character
#		per match) are implemented with STAR and PLUS for speed
#		and to minimize recursive plunges.
#
STAR		STAR,   node	Match this (simple) thing 0 or more times.
PLUS		PLUS,   node	Match this (simple) thing 1 or more times.

CURLY		CURLY,  sv 2	Match this simple thing {n,m} times.
CURLYN		CURLY,  no 2	Match next-after-this simple thing 
#				{n,m} times, set parenths.
CURLYM		CURLY,  no 2	Match this medium-complex thing {n,m} times.
CURLYX		CURLY,  sv 2	Match this complex thing {n,m} times.

# This terminator creates a loop structure for CURLYX
WHILEM		WHILEM, no	Do curly processing and see if rest matches.

#*Buffer related (45..49)

# OPEN,CLOSE,GROUPP	...are numbered at compile time.
OPEN		OPEN,   num 1	Mark this point in input as start of #n.
CLOSE		CLOSE,  num 1	Analogous to OPEN.

REF		REF,    num 1	Match some already matched string
REFF		REF,    num 1	Match already matched string, folded
REFFL		REF,    num 1	Match already matched string, folded in loc.

#*Grouping assertions (50..54)

IFMATCH		BRANCHJ,off 1 2	Succeeds if the following matches.
UNLESSM		BRANCHJ,off 1 2	Fails if the following matches.
SUSPEND		BRANCHJ,off 1 1	"Independent" sub-RE.
IFTHEN		BRANCHJ,off 1 1	Switch, should be preceeded by switcher .
GROUPP		GROUPP, num 1	Whether the group matched.

#*Support for long RE (55..56)

LONGJMP		LONGJMP,off 1 1	Jump far away.
BRANCHJ		BRANCHJ,off 1 1	BRANCH with long offset.

#*The heavy worker (57..58)

EVAL		EVAL,   evl 1	Execute some Perl code.

#*Modifiers (59..60)

MINMOD		MINMOD, no	Next operator is not greedy.
LOGICAL		LOGICAL,no	Next opcode should set the flag only.

# This is not used yet (61)
RENUM		BRANCHJ,off 1 1	Group with independently numbered parens.

#*Trie Related (62..64)

# Behave the same as A|LIST|OF|WORDS would. The '..C' variants have  
# inline charclass data (ascii only), the 'C' store it in the structure.
# NOTE: the relative order of the TRIE-like regops  is signifigant

TRIE		TRIE,   trie 1	Match many EXACT(FL?)? at once. flags==type
TRIEC		TRIE,   trie charclass	Same as TRIE, but with embedded charclass data

# For start classes, contains an added fail table.
AHOCORASICK	TRIE,   trie 1	Aho Corasick stclass. flags==type
AHOCORASICKC	TRIE,   trie charclass	Same as AHOCORASICK, but with embedded charclass data

#*Recursion (65) 
RECURSE		RECURSE,   num/ofs 2L	recurse to paren arg1 at (signed) ofs arg2
SRECURSE	RECURSE,   no   	recurse to start of pattern

# NEW STUFF ABOVE THIS LINE -- Please update counts below. 

################################################################################

#*SPECIAL  REGOPS (65, 66)

# This is not really a node, but an optimized away piece of a "long" node.
# To simplify debugging output, we mark it as if it were a node
OPTIMIZED	NOTHING,off	Placeholder for dump.

# Special opcode with the property that no opcode in a compiled program
# will ever be of this type. Thus it can be used as a flag value that
# no other opcode has been seen. END is used similarly, in that an END
# node cant be optimized. So END implies "unoptimizable" and PSEUDO mean
# "not seen anything to optimize yet".
PSEUDO		PSEUDO,off	Pseudo opcode for internal use.

-------------------------------------------------------------------------------
# Format for second section:
# REGOP \t typelist [ \t typelist] [# Comment]
# typelist= namelist
#         = namelist:FAIL
#         = name:count

# Anything below is a state
#
#
TRIE    	next:FAIL	
EVAL    	AB:FAIL	
CURLYX  	end:FAIL	
WHILEM  	A_pre,A_min,A_max,B_min,B_max:FAIL
BRANCH  	next:FAIL	
CURLYM  	A,B:FAIL	
IFMATCH 	A:FAIL	
CURLY   	B_min_known,B_min,B_max:FAIL
Commit	Line	Data
03363afd YO	1	# regcomp.sym
	2	#
	3	# File has two sections, divided by a line of dashes '-'.
	4	#
	5	# Empty rows after #-comment are removed from input are ignored
	6	#
	7	# First section is for regops, second sectionis for regmatch-states
	8	#
3dab1dad YO	9	# Note that the order in this file is important.
3dab1dad YO	10	#
03363afd YO	11	# Format for first section:
	12	# NAME \t TYPE, arg-description [num-args] [longjump-len] \t DESCRIPTION
	13	#
3dab1dad	14	#
c476f425	15	# run perl regen.pl after editing this file
3dab1dad	16
03363afd YO	17
03363afd YO	18
1de06328 YO	19	#* Exit points (0,1)
1de06328 YO	20
d09b2d29 IZ	21	END END, no End of program.
	22	SUCCEED END, no Return from a subroutine, basically.
	23
1de06328 YO	24	#* Anchors: (2..13)
1de06328 YO	25
d09b2d29 IZ	26	BOL BOL, no Match "" at beginning of line.
	27	MBOL BOL, no Same, assuming multiline.
	28	SBOL BOL, no Same, assuming singleline.
b85d18e9	29	EOS EOL, no Match "" at end of string.
d09b2d29 IZ	30	EOL EOL, no Match "" at end of line.
	31	MEOL EOL, no Same, assuming multiline.
	32	SEOL EOL, no Same, assuming singleline.
	33	BOUND BOUND, no Match "" at any word boundary
	34	BOUNDL BOUND, no Match "" at any word boundary
	35	NBOUND NBOUND, no Match "" at any word non-boundary
	36	NBOUNDL NBOUND, no Match "" at any word non-boundary
	37	GPOS GPOS, no Matches where last m//g left off.
	38
1de06328 YO	39	#* [Special] alternatives: (14..30)
1de06328 YO	40
22c35a8c	41	REG_ANY REG_ANY, no Match any one character (except newline).
22c35a8c	42	SANY REG_ANY, no Match any one character.
f33976b4	43	CANY REG_ANY, no Match any one byte.
d09b2d29 IZ	44	ANYOF ANYOF, sv Match character in (or not in) this class.
	45	ALNUM ALNUM, no Match any alphanumeric character
	46	ALNUML ALNUM, no Match any alphanumeric char in locale
	47	NALNUM NALNUM, no Match any non-alphanumeric character
	48	NALNUML NALNUM, no Match any non-alphanumeric char in locale
	49	SPACE SPACE, no Match any whitespace character
	50	SPACEL SPACE, no Match any whitespace char in locale
	51	NSPACE NSPACE, no Match any non-whitespace character
	52	NSPACEL NSPACE, no Match any non-whitespace char in locale
	53	DIGIT DIGIT, no Match any numeric character
b8c5462f	54	DIGITL DIGIT, no Match any numeric character in locale
d09b2d29	55	NDIGIT NDIGIT, no Match any non-numeric character
b8c5462f	56	NDIGITL NDIGIT, no Match any non-numeric character in locale
a0ed51b3	57	CLUMP CLUMP, no Match any combining character sequence
d09b2d29	58
1de06328 YO	59	#* Alternation (31)
	60
	61	# BRANCH The set of branches constituting a single choice are hooked
d09b2d29 IZ	62	# together with their "next" pointers, since precedence prevents
	63	# anything being concatenated to any individual branch. The
	64	# "next" pointer of the last BRANCH in a choice points to the
	65	# thing following the whole choice. This is also where the
	66	# final "next" pointer of each individual branch points; each
	67	# branch starts with the operand node of a BRANCH node.
	68	#
	69	BRANCH BRANCH, node Match this alternative, or the next...
	70
1de06328 YO	71	#*Back pointer (32)
1de06328 YO	72
d09b2d29 IZ	73	# BACK Normal "next" pointers all implicitly point forward; BACK
	74	# exists to make loop structures possible.
	75	# not used
	76	BACK BACK, no Match "", "next" ptr points backward.
	77
1de06328 YO	78	#*Literals (33..35)
1de06328 YO	79
d09b2d29 IZ	80	EXACT EXACT, sv Match this string (preceded by length).
	81	EXACTF EXACT, sv Match this string, folded (prec. by length).
	82	EXACTFL EXACT, sv Match this string, folded in locale (w/len).
	83
1de06328 YO	84	#*Do nothing types (36..37)
1de06328 YO	85
d09b2d29 IZ	86	NOTHING NOTHING,no Match empty string.
	87	# A variant of above which delimits a group, thus stops optimizations
	88	TAIL NOTHING,no Match empty string. Can jump here from outside.
	89
1de06328 YO	90	#*Loops (38..44)
1de06328 YO	91
d09b2d29 IZ	92	# STAR,PLUS '?', and complex '*' and '+', are implemented as circular
	93	# BRANCH structures using BACK. Simple cases (one character
	94	# per match) are implemented with STAR and PLUS for speed
	95	# and to minimize recursive plunges.
	96	#
	97	STAR STAR, node Match this (simple) thing 0 or more times.
	98	PLUS PLUS, node Match this (simple) thing 1 or more times.
	99
	100	CURLY CURLY, sv 2 Match this simple thing {n,m} times.
	101	CURLYN CURLY, no 2 Match next-after-this simple thing
	102	# {n,m} times, set parenths.
	103	CURLYM CURLY, no 2 Match this medium-complex thing {n,m} times.
	104	CURLYX CURLY, sv 2 Match this complex thing {n,m} times.
	105
	106	# This terminator creates a loop structure for CURLYX
	107	WHILEM WHILEM, no Do curly processing and see if rest matches.
	108
1de06328 YO	109	#*Buffer related (45..49)
1de06328 YO	110
d09b2d29 IZ	111	# OPEN,CLOSE,GROUPP ...are numbered at compile time.
	112	OPEN OPEN, num 1 Mark this point in input as start of #n.
	113	CLOSE CLOSE, num 1 Analogous to OPEN.
	114
	115	REF REF, num 1 Match some already matched string
	116	REFF REF, num 1 Match already matched string, folded
	117	REFFL REF, num 1 Match already matched string, folded in loc.
	118
1de06328 YO	119	#*Grouping assertions (50..54)
1de06328 YO	120
d09b2d29 IZ	121	IFMATCH BRANCHJ,off 1 2 Succeeds if the following matches.
	122	UNLESSM BRANCHJ,off 1 2 Fails if the following matches.
	123	SUSPEND BRANCHJ,off 1 1 "Independent" sub-RE.
	124	IFTHEN BRANCHJ,off 1 1 Switch, should be preceeded by switcher .
	125	GROUPP GROUPP, num 1 Whether the group matched.
	126
1de06328 YO	127	#*Support for long RE (55..56)
1de06328 YO	128
d09b2d29 IZ	129	LONGJMP LONGJMP,off 1 1 Jump far away.
	130	BRANCHJ BRANCHJ,off 1 1 BRANCH with long offset.
	131
1de06328 YO	132	#*The heavy worker (57..58)
1de06328 YO	133
d09b2d29 IZ	134	EVAL EVAL, evl 1 Execute some Perl code.
d09b2d29 IZ	135
1de06328 YO	136	#*Modifiers (59..60)
1de06328 YO	137
d09b2d29 IZ	138	MINMOD MINMOD, no Next operator is not greedy.
	139	LOGICAL LOGICAL,no Next opcode should set the flag only.
	140
1de06328	141	# This is not used yet (61)
d09b2d29 IZ	142	RENUM BRANCHJ,off 1 1 Group with independently numbered parens.
d09b2d29 IZ	143
1de06328 YO	144	#*Trie Related (62..64)
	145
	146	# Behave the same as A\|LIST\|OF\|WORDS would. The '..C' variants have
	147	# inline charclass data (ascii only), the 'C' store it in the structure.
	148	# NOTE: the relative order of the TRIE-like regops is signifigant
ce5e9471	149
3dab1dad	150	TRIE TRIE, trie 1 Match many EXACT(FL?)? at once. flags==type
786e8c11	151	TRIEC TRIE, trie charclass Same as TRIE, but with embedded charclass data
3dab1dad	152
1de06328 YO	153	# For start classes, contains an added fail table.
	154	AHOCORASICK TRIE, trie 1 Aho Corasick stclass. flags==type
	155	AHOCORASICKC TRIE, trie charclass Same as AHOCORASICK, but with embedded charclass data
	156
6bda09f9 YO	157	#*Recursion (65)
	158	RECURSE RECURSE, num/ofs 2L recurse to paren arg1 at (signed) ofs arg2
	159	SRECURSE RECURSE, no recurse to start of pattern
03363afd	160
1de06328 YO	161	# NEW STUFF ABOVE THIS LINE -- Please update counts below.
1de06328 YO	162
03363afd YO	163	################################################################################
	164
	165	#*SPECIAL REGOPS (65, 66)
1de06328 YO	166
	167	# This is not really a node, but an optimized away piece of a "long" node.
	168	# To simplify debugging output, we mark it as if it were a node
	169	OPTIMIZED NOTHING,off Placeholder for dump.
	170
3dab1dad YO	171	# Special opcode with the property that no opcode in a compiled program
	172	# will ever be of this type. Thus it can be used as a flag value that
	173	# no other opcode has been seen. END is used similarly, in that an END
	174	# node cant be optimized. So END implies "unoptimizable" and PSEUDO mean
	175	# "not seen anything to optimize yet".
	176	PSEUDO PSEUDO,off Pseudo opcode for internal use.
1de06328	177
03363afd YO	178	-------------------------------------------------------------------------------
	179	# Format for second section:
	180	# REGOP \t typelist [ \t typelist] [# Comment]
	181	# typelist= namelist
	182	# = namelist:FAIL
	183	# = name:count
	184
	185	# Anything below is a state
	186	#
	187	#
	188	TRIE next:FAIL
	189	EVAL AB:FAIL
c476f425 DM	190	CURLYX end:FAIL
c476f425 DM	191	WHILEM A_pre,A_min,A_max,B_min,B_max:FAIL
03363afd YO	192	BRANCH next:FAIL
	193	CURLYM A,B:FAIL
	194	IFMATCH A:FAIL
	195	CURLY B_min_known,B_min,B_max:FAIL
	196