[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 \s+ TYPE, arg-description [flags] [num-args] [longjump-len] ; 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 0 S    ; Match any one character (except newline).
SANY        REG_ANY,    no 0 S    ; Match any one character.
CANY        REG_ANY,    no 0 S    ; Match any one byte.
ANYOF       ANYOF,      sv 0 S    ; Match character in (or not in) this class.
ALNUM       ALNUM,      no 0 S    ; Match any alphanumeric character
ALNUML      ALNUM,      no 0 S    ; Match any alphanumeric char in locale
NALNUM      NALNUM,     no 0 S    ; Match any non-alphanumeric character
NALNUML     NALNUM,     no 0 S    ; Match any non-alphanumeric char in locale
SPACE       SPACE,      no 0 S    ; Match any whitespace character
SPACEL      SPACE,      no 0 S    ; Match any whitespace char in locale
NSPACE      NSPACE,     no 0 S    ; Match any non-whitespace character
NSPACEL     NSPACE,     no 0 S    ; Match any non-whitespace char in locale
DIGIT       DIGIT,      no 0 S    ; Match any numeric character
DIGITL      DIGIT,      no        ; Match any numeric character in locale
NDIGIT      NDIGIT,     no 0 S    ; Match any non-numeric character
NDIGITL     NDIGIT,     no        ; Match any non-numeric character in locale
CLUMP       CLUMP,      no 0 V    ; 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 0 V  ; 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 0 V    ; 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 0 V  ; Match this (simple) thing 0 or more times.
PLUS        PLUS,       node 0 V  ; Match this (simple) thing 1 or more times.

CURLY       CURLY,      sv 2 V    ; Match this simple thing {n,m} times.
CURLYN      CURLY,      no 2 V    ; Capture next-after-this simple thing 
CURLYM      CURLY,      no 2 V    ; Capture this medium-complex thing {n,m} times. 
CURLYX      CURLY,      sv 2 V    ; Match this complex thing {n,m} times.

# This terminator creates a loop structure for CURLYX
WHILEM      WHILEM,     no 0 V    ; 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 V   ; Match some already matched string
REFF        REF,        num 1 V   ; Match already matched string, folded
REFFL       REF,        num 1 V   ; Match already matched string, folded in loc.


IFMATCH     BRANCHJ,    off 1 . 2 ; Succeeds if the following matches.
UNLESSM     BRANCHJ,    off 1 . 2 ; Fails if the following matches.
SUSPEND     BRANCHJ,    off 1 V 1 ; "Independent" sub-RE.
IFTHEN      BRANCHJ,    off 1 V 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 V 1 ; BRANCH with long offset.

#*The heavy worker (57)

EVAL        EVAL,       evl 1     ; Execute some Perl code.

#*Modifiers (58..59)

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

# This is not used yet (60)
RENUM       BRANCHJ,    off 1 . 1 ; Group with independently numbered parens.

#*Trie Related (61..62)

# 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 V ; Match some already matched string
NREFF       REF,        no-sv 1 V ; Match already matched string, folded
NREFFL      REF,        no-sv 1 V ; 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 0 S  ; vertical whitespace         (Perl 6)
NVERTWS     NVERTWS,    none 0 S  ; not vertical whitespace     (Perl 6)
HORIZWS     HORIZWS,    none 0 S  ; horizontal whitespace       (Perl 6)
NHORIZWS    NHORIZWS,   none 0 S  ; 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	11	# Format for first section:
f9ef50a7	12	# NAME \s+ TYPE, arg-description [flags] [num-args] [longjump-len] ; DESCRIPTION
03363afd	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
f8abb37e NC	21	END END, no ; End of program.
f8abb37e NC	22	SUCCEED END, no ; Return from a subroutine, basically.
d09b2d29	23
1de06328 YO	24	#* Anchors: (2..13)
1de06328 YO	25
f8abb37e NC	26	BOL BOL, no ; Match "" at beginning of line.
	27	MBOL BOL, no ; Same, assuming multiline.
	28	SBOL BOL, no ; Same, assuming singleline.
	29	EOS EOL, no ; Match "" at end of string.
	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.
d09b2d29	38
1de06328 YO	39	#* [Special] alternatives: (14..30)
1de06328 YO	40
f9ef50a7 NC	41	REG_ANY REG_ANY, no 0 S ; Match any one character (except newline).
	42	SANY REG_ANY, no 0 S ; Match any one character.
	43	CANY REG_ANY, no 0 S ; Match any one byte.
	44	ANYOF ANYOF, sv 0 S ; Match character in (or not in) this class.
	45	ALNUM ALNUM, no 0 S ; Match any alphanumeric character
	46	ALNUML ALNUM, no 0 S ; Match any alphanumeric char in locale
	47	NALNUM NALNUM, no 0 S ; Match any non-alphanumeric character
	48	NALNUML NALNUM, no 0 S ; Match any non-alphanumeric char in locale
	49	SPACE SPACE, no 0 S ; Match any whitespace character
	50	SPACEL SPACE, no 0 S ; Match any whitespace char in locale
	51	NSPACE NSPACE, no 0 S ; Match any non-whitespace character
	52	NSPACEL NSPACE, no 0 S ; Match any non-whitespace char in locale
	53	DIGIT DIGIT, no 0 S ; Match any numeric character
f8abb37e	54	DIGITL DIGIT, no ; Match any numeric character in locale
f9ef50a7	55	NDIGIT NDIGIT, no 0 S ; Match any non-numeric character
f8abb37e	56	NDIGITL NDIGIT, no ; Match any non-numeric character in locale
f9ef50a7	57	CLUMP CLUMP, no 0 V ; Match any combining character sequence
d09b2d29	58
1de06328 YO	59	#* Alternation (31)
1de06328 YO	60
f8abb37e NC	61	# BRANCH The set of branches constituting a single choice are hooked
	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.
d09b2d29	68	#
f9ef50a7	69	BRANCH BRANCH, node 0 V ; Match this alternative, or the next...
d09b2d29	70
1de06328 YO	71	#*Back pointer (32)
1de06328 YO	72
f8abb37e NC	73	# BACK Normal "next" pointers all implicitly point forward; BACK
f8abb37e NC	74	# exists to make loop structures possible.
d09b2d29	75	# not used
f9ef50a7	76	BACK BACK, no 0 V ; Match "", "next" ptr points backward.
d09b2d29	77
1de06328 YO	78	#*Literals (33..35)
1de06328 YO	79
f8abb37e NC	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
f8abb37e	86	NOTHING NOTHING, no ; Match empty string.
d09b2d29	87	# A variant of above which delimits a group, thus stops optimizations
f8abb37e	88	TAIL NOTHING, no ; Match empty string. Can jump here from outside.
d09b2d29	89
1de06328 YO	90	#*Loops (38..44)
1de06328 YO	91
f8abb37e NC	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.
d09b2d29	96	#
f9ef50a7 NC	97	STAR STAR, node 0 V ; Match this (simple) thing 0 or more times.
f9ef50a7 NC	98	PLUS PLUS, node 0 V ; Match this (simple) thing 1 or more times.
d09b2d29	99
f9ef50a7 NC	100	CURLY CURLY, sv 2 V ; Match this simple thing {n,m} times.
	101	CURLYN CURLY, no 2 V ; Capture next-after-this simple thing
	102	CURLYM CURLY, no 2 V ; Capture this medium-complex thing {n,m} times.
	103	CURLYX CURLY, sv 2 V ; Match this complex thing {n,m} times.
d09b2d29 IZ	104
d09b2d29 IZ	105	# This terminator creates a loop structure for CURLYX
f9ef50a7	106	WHILEM WHILEM, no 0 V ; Do curly processing and see if rest matches.
d09b2d29	107
1de06328 YO	108	#*Buffer related (45..49)
1de06328 YO	109
f8abb37e NC	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.
d09b2d29	113
f9ef50a7 NC	114	REF REF, num 1 V ; Match some already matched string
	115	REFF REF, num 1 V ; Match already matched string, folded
	116	REFFL REF, num 1 V ; Match already matched string, folded in loc.
d09b2d29	117
1de06328	118
f9ef50a7 NC	119	IFMATCH BRANCHJ, off 1 . 2 ; Succeeds if the following matches.
	120	UNLESSM BRANCHJ, off 1 . 2 ; Fails if the following matches.
	121	SUSPEND BRANCHJ, off 1 V 1 ; "Independent" sub-RE.
	122	IFTHEN BRANCHJ, off 1 V 1 ; Switch, should be preceeded by switcher .
f8abb37e	123	GROUPP GROUPP, num 1 ; Whether the group matched.
d09b2d29	124
1de06328 YO	125	#*Support for long RE (55..56)
1de06328 YO	126
f9ef50a7 NC	127	LONGJMP LONGJMP, off 1 . 1 ; Jump far away.
f9ef50a7 NC	128	BRANCHJ BRANCHJ, off 1 V 1 ; BRANCH with long offset.
d09b2d29	129
5014f7da	130	#*The heavy worker (57)
1de06328	131
f8abb37e	132	EVAL EVAL, evl 1 ; Execute some Perl code.
d09b2d29	133
5014f7da	134	#*Modifiers (58..59)
1de06328	135
f8abb37e NC	136	MINMOD MINMOD, no ; Next operator is not greedy.
f8abb37e NC	137	LOGICAL LOGICAL, no ; Next opcode should set the flag only.
d09b2d29	138
5014f7da	139	# This is not used yet (60)
f9ef50a7	140	RENUM BRANCHJ, off 1 . 1 ; Group with independently numbered parens.
d09b2d29	141
5014f7da	142	#*Trie Related (61..62)
1de06328 YO	143
	144	# Behave the same as A\|LIST\|OF\|WORDS would. The '..C' variants have
	145	# inline charclass data (ascii only), the 'C' store it in the structure.
	146	# NOTE: the relative order of the TRIE-like regops is signifigant
ce5e9471	147
f8abb37e NC	148	TRIE TRIE, trie 1 ; Match many EXACT(FL?)? at once. flags==type
f8abb37e NC	149	TRIEC TRIE,trie charclass ; Same as TRIE, but with embedded charclass data
3dab1dad	150
1de06328	151	# For start classes, contains an added fail table.
f8abb37e NC	152	AHOCORASICK TRIE, trie 1 ; Aho Corasick stclass. flags==type
f8abb37e NC	153	AHOCORASICKC TRIE,trie charclass ; Same as AHOCORASICK, but with embedded charclass data
1de06328	154
1a147d38	155	#*Regex Subroutines (65..66)
f8abb37e NC	156	GOSUB GOSUB, num/ofs 2L ; recurse to paren arg1 at (signed) ofs arg2
f8abb37e NC	157	GOSTART GOSTART, no ; recurse to start of pattern
03363afd	158
81714fb9	159	#*Named references (67..69)
f9ef50a7 NC	160	NREF REF, no-sv 1 V ; Match some already matched string
	161	NREFF REF, no-sv 1 V ; Match already matched string, folded
	162	NREFFL REF, no-sv 1 V ; Match already matched string, folded in loc.
81714fb9 YO	163
81714fb9 YO	164
7f69552c	165	#*Special conditionals (70..72)
f8abb37e NC	166	NGROUPP NGROUPP, no-sv 1 ; Whether the group matched.
	167	INSUBP INSUBP, num 1 ; Whether we are in a specific recurse.
	168	DEFINEP DEFINEP, none 1 ; Never execute directly.
0a4db386	169
5d458dd8	170	#*Bactracking Verbs
f8abb37e NC	171	ENDLIKE ENDLIKE, none ; Used only for the type field of verbs
	172	OPFAIL ENDLIKE, none ; Same as (?!)
	173	ACCEPT ENDLIKE, parno 1 ; Accepts the current matched string.
5d458dd8 YO	174
	175
	176	#*Verbs With Arguments
f8abb37e NC	177	VERB VERB, no-sv 1 ; Used only for the type field of verbs
	178	PRUNE VERB, no-sv 1 ; Pattern fails at this startpoint if no-backtracking through this
	179	MARKPOINT VERB, no-sv 1 ; Push the current location for rollback by cut.
	180	SKIP VERB, no-sv 1 ; On failure skip forward (to the mark) before retrying
	181	COMMIT VERB, no-sv 1 ; Pattern fails outright if backtracking through this
	182	CUTGROUP VERB, no-sv 1 ; On failure go to the next alternation in the group
e2e6a0f1	183
ee9b8eae	184	#*Control what to keep in $&.
f8abb37e	185	KEEPS KEEPS, no ; $& begins here.
ee9b8eae	186
e1d1eefb	187	#*New charclass like patterns
f8abb37e	188	LNBREAK LNBREAK, none ; generic newline pattern
f9ef50a7 NC	189	VERTWS VERTWS, none 0 S ; vertical whitespace (Perl 6)
	190	NVERTWS NVERTWS, none 0 S ; not vertical whitespace (Perl 6)
	191	HORIZWS HORIZWS, none 0 S ; horizontal whitespace (Perl 6)
	192	NHORIZWS NHORIZWS, none 0 S ; not horizontal whitespace (Perl 6)
e1d1eefb	193
f8abb37e	194	FOLDCHAR FOLDCHAR, codepoint 1 ; codepoint with tricky case folding properties.
32e6a07c	195
e1d1eefb	196	# NEW STUFF ABOVE THIS LINE
1de06328	197
03363afd YO	198	################################################################################
03363afd YO	199
7f69552c	200	#*SPECIAL REGOPS
1de06328 YO	201
	202	# This is not really a node, but an optimized away piece of a "long" node.
	203	# To simplify debugging output, we mark it as if it were a node
f8abb37e	204	OPTIMIZED NOTHING, off ; Placeholder for dump.
1de06328	205
3dab1dad YO	206	# Special opcode with the property that no opcode in a compiled program
	207	# will ever be of this type. Thus it can be used as a flag value that
	208	# no other opcode has been seen. END is used similarly, in that an END
	209	# node cant be optimized. So END implies "unoptimizable" and PSEUDO mean
	210	# "not seen anything to optimize yet".
f8abb37e	211	PSEUDO PSEUDO, off ; Pseudo opcode for internal use.
1de06328	212
03363afd YO	213	-------------------------------------------------------------------------------
	214	# Format for second section:
	215	# REGOP \t typelist [ \t typelist] [# Comment]
	216	# typelist= namelist
	217	# = namelist:FAIL
	218	# = name:count
	219
	220	# Anything below is a state
	221	#
	222	#
f8abb37e NC	223	TRIE next:FAIL
	224	EVAL AB:FAIL
	225	CURLYX end:FAIL
	226	WHILEM A_pre,A_min,A_max,B_min,B_max:FAIL
	227	BRANCH next:FAIL
	228	CURLYM A,B:FAIL
	229	IFMATCH A:FAIL
	230	CURLY B_min_known,B_min,B_max:FAIL
	231	COMMIT next:FAIL
	232	MARKPOINT next:FAIL
	233	SKIP next:FAIL
	234	CUTGROUP next:FAIL
	235	KEEPS next:FAIL