[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,  str	Match this string (preceded by length).
EXACTF		EXACT,  str	Match this string, folded (prec. by length).
EXACTFL		EXACT,  str	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	Capture next-after-this simple thing 
CURLYM		CURLY,  no 2	Capture 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

#*Regex Subroutines (65..66) 
GOSUB		GOSUB,     num/ofs 2L	recurse to paren arg1 at (signed) ofs arg2
GOSTART		GOSTART,   no   	recurse to start of pattern

#*Named references (67..69)
NREF		REF,       no-sv 1	Match some already matched string
NREFF		REF,       no-sv 1	Match already matched string, folded
NREFFL		REF,       no-sv 1	Match already matched string, folded in loc.


#*Special conditionals  (70..72)
NGROUPP		NGROUPP,   no-sv 1	Whether the group matched.            
INSUBP		INSUBP,    num 1 	Whether we are in a specific recurse.  
DEFINEP		DEFINEP,   none 1 	Never execute directly.               

#*Bactracking Verbs
ENDLIKE		ENDLIKE,   none		Used only for the type field of verbs
OPFAIL		ENDLIKE,   none 	Same as (?!)
ACCEPT		ENDLIKE,   parno 1 	Accepts the current matched string.


#*Verbs With Arguments
VERB		VERB,	   no-sv 1	Used only for the type field of verbs
PRUNE		VERB,      no-sv 1 	Pattern fails at this startpoint if no-backtracking through this 
MARKPOINT	VERB,      no-sv 1	Push the current location for rollback by cut.
SKIP		VERB,      no-sv 1	On failure skip forward (to the mark) before retrying
COMMIT		VERB,      no-sv 1	Pattern fails outright if backtracking through this
CUTGROUP	VERB,      no-sv 1	On failure go to the next alternation in the group

#*Control what to keep in $&.
KEEPS		KEEPS,  no	$& begins here.

#*New charclass like patterns
LNBREAK		LNBREAK,   none		generic newline pattern
VERTWS		VERTWS,    none		vertical whitespace         (Perl 6)
NVERTWS		NVERTWS,   none		not vertical whitespace     (Perl 6)
HORIZWS		HORIZWS,   none		horizontal whitespace       (Perl 6)
NHORIZWS	NHORIZWS,  none		not horizontal whitespace   (Perl 6)

FOLDCHAR	FOLDCHAR,  codepoint 1	codepoint with tricky case folding properties.

# NEW STUFF ABOVE THIS LINE  

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

#*SPECIAL  REGOPS

# 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		next:FAIL
MARKPOINT	next:FAIL
SKIP		next:FAIL
CUTGROUP	next:FAIL
KEEPS		next: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
81714fb9 YO	80	EXACT EXACT, str Match this string (preceded by length).
	81	EXACTF EXACT, str Match this string, folded (prec. by length).
	82	EXACTFL EXACT, str Match this string, folded in locale (w/len).
d09b2d29	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.
40d049e4 YO	101	CURLYN CURLY, no 2 Capture next-after-this simple thing
40d049e4 YO	102	CURLYM CURLY, no 2 Capture this medium-complex thing {n,m} times.
d09b2d29 IZ	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
5d458dd8 YO	149	TRIE TRIE, trie 1 Match many EXACT(FL?)? at once. flags==type
5d458dd8 YO	150	TRIEC TRIE,trie charclass Same as TRIE, but with embedded charclass data
3dab1dad	151
1de06328	152	# For start classes, contains an added fail table.
5d458dd8 YO	153	AHOCORASICK TRIE, trie 1 Aho Corasick stclass. flags==type
5d458dd8 YO	154	AHOCORASICKC TRIE,trie charclass Same as AHOCORASICK, but with embedded charclass data
1de06328	155
1a147d38	156	#*Regex Subroutines (65..66)
5d458dd8	157	GOSUB GOSUB, num/ofs 2L recurse to paren arg1 at (signed) ofs arg2
1a147d38	158	GOSTART GOSTART, no recurse to start of pattern
03363afd	159
81714fb9	160	#*Named references (67..69)
ee9b8eae YO	161	NREF REF, no-sv 1 Match some already matched string
	162	NREFF REF, no-sv 1 Match already matched string, folded
	163	NREFFL REF, no-sv 1 Match already matched string, folded in loc.
81714fb9 YO	164
81714fb9 YO	165
7f69552c	166	#*Special conditionals (70..72)
0a4db386	167	NGROUPP NGROUPP, no-sv 1 Whether the group matched.
1a147d38	168	INSUBP INSUBP, num 1 Whether we are in a specific recurse.
0a4db386 YO	169	DEFINEP DEFINEP, none 1 Never execute directly.
0a4db386 YO	170
5d458dd8	171	#*Bactracking Verbs
e2e6a0f1 YO	172	ENDLIKE ENDLIKE, none Used only for the type field of verbs
	173	OPFAIL ENDLIKE, none Same as (?!)
	174	ACCEPT ENDLIKE, parno 1 Accepts the current matched string.
5d458dd8 YO	175
	176
	177	#*Verbs With Arguments
e2e6a0f1	178	VERB VERB, no-sv 1 Used only for the type field of verbs
5d458dd8	179	PRUNE VERB, no-sv 1 Pattern fails at this startpoint if no-backtracking through this
e2e6a0f1	180	MARKPOINT VERB, no-sv 1 Push the current location for rollback by cut.
5d458dd8	181	SKIP VERB, no-sv 1 On failure skip forward (to the mark) before retrying
e2e6a0f1	182	COMMIT VERB, no-sv 1 Pattern fails outright if backtracking through this
5d458dd8	183	CUTGROUP VERB, no-sv 1 On failure go to the next alternation in the group
e2e6a0f1	184
ee9b8eae YO	185	#*Control what to keep in $&.
	186	KEEPS KEEPS, no $& begins here.
	187
e1d1eefb YO	188	#*New charclass like patterns
	189	LNBREAK LNBREAK, none generic newline pattern
	190	VERTWS VERTWS, none vertical whitespace (Perl 6)
	191	NVERTWS NVERTWS, none not vertical whitespace (Perl 6)
	192	HORIZWS HORIZWS, none horizontal whitespace (Perl 6)
	193	NHORIZWS NHORIZWS, none not horizontal whitespace (Perl 6)
	194
32e6a07c YO	195	FOLDCHAR FOLDCHAR, codepoint 1 codepoint with tricky case folding properties.
32e6a07c YO	196
e1d1eefb	197	# NEW STUFF ABOVE THIS LINE
1de06328	198
03363afd YO	199	################################################################################
03363afd YO	200
7f69552c	201	#*SPECIAL REGOPS
1de06328 YO	202
	203	# This is not really a node, but an optimized away piece of a "long" node.
	204	# To simplify debugging output, we mark it as if it were a node
	205	OPTIMIZED NOTHING,off Placeholder for dump.
	206
3dab1dad YO	207	# Special opcode with the property that no opcode in a compiled program
	208	# will ever be of this type. Thus it can be used as a flag value that
	209	# no other opcode has been seen. END is used similarly, in that an END
	210	# node cant be optimized. So END implies "unoptimizable" and PSEUDO mean
	211	# "not seen anything to optimize yet".
	212	PSEUDO PSEUDO,off Pseudo opcode for internal use.
1de06328	213
03363afd YO	214	-------------------------------------------------------------------------------
	215	# Format for second section:
	216	# REGOP \t typelist [ \t typelist] [# Comment]
	217	# typelist= namelist
	218	# = namelist:FAIL
	219	# = name:count
	220
	221	# Anything below is a state
	222	#
	223	#
	224	TRIE next:FAIL
	225	EVAL AB:FAIL
c476f425 DM	226	CURLYX end:FAIL
c476f425 DM	227	WHILEM A_pre,A_min,A_max,B_min,B_max:FAIL
03363afd YO	228	BRANCH next:FAIL
	229	CURLYM A,B:FAIL
	230	IFMATCH A:FAIL
	231	CURLY B_min_known,B_min,B_max:FAIL
24b23f37	232	COMMIT next:FAIL
e2e6a0f1	233	MARKPOINT next:FAIL
5d458dd8 YO	234	SKIP next:FAIL
5d458dd8 YO	235	CUTGROUP next:FAIL
ee9b8eae	236	KEEPS next:FAIL