[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
#
#


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