perl5.git.perl.org Git - perl5.git/blame_incremental

Commit	Line	Data
	1	# regcomp.sym
	2	#
	3	# File has two sections, divided by a line of dashes '-'.
	4	#
	5	# Lines beginning with # are ignored, except for those that start with #*
	6	# which are included in pod/perldebguts.pod. # within a line may be part
	7	# of a description.
	8	#
	9	# First section is for regops, second section is for regmatch-states
	10	#
	11	# Note that the order in this file is important.
	12	#
	13	# Format for first section:
	14	# NAME \s+ TYPE, arg-description [num-args] [flags] [longjump-len] ; DESCRIPTION
	15	# flag <S> means is REGNODE_SIMPLE; flag <V> means is REGNODE_VARIES
	16	#
	17	#
	18	# run perl regen.pl after editing this file
	19
	20
	21
	22	#* Exit points
	23
	24	END END, no ; End of program.
	25	SUCCEED END, no ; Return from a subroutine, basically.
	26
	27	#* Line Start Anchors:
	28	#Note flags field for SBOL indicates if it is a /^/ or a /\A/
	29	SBOL BOL, no ; Match "" at beginning of line: /^/, /\A/
	30	MBOL BOL, no ; Same, assuming multiline: /^/m
	31
	32	#* Line End Anchors:
	33	SEOL EOL, no ; Match "" at end of line: /$/
	34	MEOL EOL, no ; Same, assuming multiline: /$/m
	35	EOS EOL, no ; Match "" at end of string: /\z/
	36
	37	#* Match Start Anchors:
	38	GPOS GPOS, no ; Matches where last m//g left off.
	39
	40	#* Word Boundary Opcodes:
	41	# The regops that have varieties that vary depending on the character set regex
	42	# modifiers have to ordered thusly: /d, /l, /u, /a, /aa. This is because code
	43	# in regcomp.c uses the enum value of the modifier as an offset from the /d
	44	# version. The complements must come after the non-complements.
	45	# BOUND, POSIX and their complements are affected, as well as EXACTF.
	46	BOUND BOUND, no ; Like BOUNDA for non-utf8, otherwise match "" between any Unicode \w\W or \W\w
	47	BOUNDL BOUND, no ; Like BOUND/BOUNDU, but \w and \W are defined by current locale
	48	BOUNDU BOUND, no ; Match "" at any boundary of a given type using Unicode rules
	49	BOUNDA BOUND, no ; Match "" at any boundary between \w\W or \W\w, where \w is [_a-zA-Z0-9]
	50	# All NBOUND nodes are required by code in regexec.c to be greater than all BOUND ones
	51	NBOUND NBOUND, no ; Like NBOUNDA for non-utf8, otherwise match "" between any Unicode \w\w or \W\W
	52	NBOUNDL NBOUND, no ; Like NBOUND/NBOUNDU, but \w and \W are defined by current locale
	53	NBOUNDU NBOUND, no ; Match "" at any non-boundary of a given type using using Unicode rules
	54	NBOUNDA NBOUND, no ; Match "" betweeen any \w\w or \W\W, where \w is [_a-zA-Z0-9]
	55
	56	#* [Special] alternatives:
	57	REG_ANY REG_ANY, no 0 S ; Match any one character (except newline).
	58	SANY REG_ANY, no 0 S ; Match any one character.
	59	ANYOF ANYOF, sv 1 S ; Match character in (or not in) this class, single char match only
	60	ANYOFD ANYOF, sv 1 S ; Like ANYOF, but /d is in effect
	61	ANYOFL ANYOF, sv 1 S ; Like ANYOF, but /l is in effect
	62
	63	#* POSIX Character Classes:
	64	# Order of the below is important. See ordering comment above.
	65	POSIXD POSIXD, none 0 S ; Some [[:class:]] under /d; the FLAGS field gives which one
	66	POSIXL POSIXD, none 0 S ; Some [[:class:]] under /l; the FLAGS field gives which one
	67	POSIXU POSIXD, none 0 S ; Some [[:class:]] under /u; the FLAGS field gives which one
	68	POSIXA POSIXD, none 0 S ; Some [[:class:]] under /a; the FLAGS field gives which one
	69	NPOSIXD NPOSIXD, none 0 S ; complement of POSIXD, [[:^class:]]
	70	NPOSIXL NPOSIXD, none 0 S ; complement of POSIXL, [[:^class:]]
	71	NPOSIXU NPOSIXD, none 0 S ; complement of POSIXU, [[:^class:]]
	72	NPOSIXA NPOSIXD, none 0 S ; complement of POSIXA, [[:^class:]]
	73	# End of order is important
	74
	75	ASCII ASCII, none 0 S ; [[:ascii:]]
	76	NASCII ASCII, none 0 S ; [[:^ascii:]]
	77
	78	CLUMP CLUMP, no 0 V ; Match any extended grapheme cluster sequence
	79
	80	#* Alternation
	81
	82	#* BRANCH The set of branches constituting a single choice are
	83	#* hooked together with their "next" pointers, since
	84	#* precedence prevents anything being concatenated to
	85	#* any individual branch. The "next" pointer of the last
	86	#* BRANCH in a choice points to the thing following the
	87	#* whole choice. This is also where the final "next"
	88	#* pointer of each individual branch points; each branch
	89	#* starts with the operand node of a BRANCH node.
	90	#*
	91	BRANCH BRANCH, node 0 V ; Match this alternative, or the next...
	92
	93	#*Literals
	94	# NOTE: the relative ordering of these types is important do not change it
	95
	96	EXACT EXACT, str ; Match this string (preceded by length).
	97	EXACTL EXACT, str ; Like EXACT, but /l is in effect (used so locale-related warnings can be checked for).
	98	EXACTF EXACT, str ; Match this non-UTF-8 string (not guaranteed to be folded) using /id rules (w/len).
	99	EXACTFL EXACT, str ; Match this string (not guaranteed to be folded) using /il rules (w/len).
	100	EXACTFU EXACT, str ; Match this string (folded iff in UTF-8, length in folding doesn't change if not in UTF-8) using /iu rules (w/len).
	101	EXACTFA EXACT, str ; Match this string (not guaranteed to be folded) using /iaa rules (w/len).
	102
	103	# End of important relative ordering.
	104
	105	EXACTFU_SS EXACT, str ; Match this string (folded iff in UTF-8, length in folding may change even if not in UTF-8) using /iu rules (w/len).
	106	EXACTFLU8 EXACT, str ; Rare cirucmstances: like EXACTFU, but is under /l, UTF-8, folded, and everything in it is above 255.
	107	EXACTFA_NO_TRIE EXACT, str ; Match this string (which is not trie-able; not guaranteed to be folded) using /iaa rules (w/len).
	108
	109	#*Do nothing types
	110
	111	NOTHING NOTHING, no ; Match empty string.
	112	#*A variant of above which delimits a group, thus stops optimizations
	113	TAIL NOTHING, no ; Match empty string. Can jump here from outside.
	114
	115	#*Loops
	116
	117	#* STAR,PLUS '?', and complex '*' and '+', are implemented as
	118	#* circular BRANCH structures. Simple cases
	119	#* (one character per match) are implemented with STAR
	120	#* and PLUS for speed and to minimize recursive plunges.
	121	#*
	122	STAR STAR, node 0 V ; Match this (simple) thing 0 or more times.
	123	PLUS PLUS, node 0 V ; Match this (simple) thing 1 or more times.
	124
	125	CURLY CURLY, sv 2 V ; Match this simple thing {n,m} times.
	126	CURLYN CURLY, no 2 V ; Capture next-after-this simple thing
	127	CURLYM CURLY, no 2 V ; Capture this medium-complex thing {n,m} times.
	128	CURLYX CURLY, sv 2 V ; Match this complex thing {n,m} times.
	129
	130	#*This terminator creates a loop structure for CURLYX
	131	WHILEM WHILEM, no 0 V ; Do curly processing and see if rest matches.
	132
	133	#*Buffer related
	134
	135	#*OPEN,CLOSE,GROUPP ...are numbered at compile time.
	136	OPEN OPEN, num 1 ; Mark this point in input as start of #n.
	137	CLOSE CLOSE, num 1 ; Close corresponding OPEN of #n.
	138	SROPEN SROPEN, none ; Same as OPEN, but for script run
	139	SRCLOSE SRCLOSE, none ; Close preceding SROPEN
	140
	141	REF REF, num 1 V ; Match some already matched string
	142	REFF REF, num 1 V ; Match already matched string, folded using native charset rules for non-utf8
	143	REFFL REF, num 1 V ; Match already matched string, folded in loc.
	144	# N?REFF[AU] could have been implemented using the FLAGS field of the
	145	# regnode, but by having a separate node type, we can use the existing switch
	146	# statement to avoid some tests
	147	REFFU REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8
	148	REFFA REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII
	149
	150	#*Named references. Code in regcomp.c assumes that these all are after
	151	#*the numbered references
	152	NREF REF, no-sv 1 V ; Match some already matched string
	153	NREFF REF, no-sv 1 V ; Match already matched string, folded using native charset rules for non-utf8
	154	NREFFL REF, no-sv 1 V ; Match already matched string, folded in loc.
	155	NREFFU REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8
	156	NREFFA REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII
	157
	158	#*Support for long RE
	159	LONGJMP LONGJMP, off 1 . 1 ; Jump far away.
	160	BRANCHJ BRANCHJ, off 1 V 1 ; BRANCH with long offset.
	161
	162	#*Special Case Regops
	163	IFMATCH BRANCHJ, off 1 . 2 ; Succeeds if the following matches.
	164	UNLESSM BRANCHJ, off 1 . 2 ; Fails if the following matches.
	165	SUSPEND BRANCHJ, off 1 V 1 ; "Independent" sub-RE.
	166	IFTHEN BRANCHJ, off 1 V 1 ; Switch, should be preceded by switcher.
	167	GROUPP GROUPP, num 1 ; Whether the group matched.
	168
	169
	170	#*The heavy worker
	171
	172	EVAL EVAL, evl/flags 2L ; Execute some Perl code.
	173
	174	#*Modifiers
	175
	176	MINMOD MINMOD, no ; Next operator is not greedy.
	177	LOGICAL LOGICAL, no ; Next opcode should set the flag only.
	178
	179	#*This is not used yet
	180	RENUM BRANCHJ, off 1 . 1 ; Group with independently numbered parens.
	181
	182	#*Trie Related
	183
	184	#* Behave the same as A\|LIST\|OF\|WORDS would. The '..C' variants
	185	#* have inline charclass data (ascii only), the 'C' store it in the
	186	#* structure.
	187	# NOTE: the relative order of the TRIE-like regops is significant
	188
	189	TRIE TRIE, trie 1 ; Match many EXACT(F[ALU]?)? at once. flags==type
	190	TRIEC TRIE,trie charclass ; Same as TRIE, but with embedded charclass data
	191
	192	# For start classes, contains an added fail table.
	193	AHOCORASICK TRIE, trie 1 ; Aho Corasick stclass. flags==type
	194	AHOCORASICKC TRIE,trie charclass ; Same as AHOCORASICK, but with embedded charclass data
	195
	196	#*Regex Subroutines
	197	GOSUB GOSUB, num/ofs 2L ; recurse to paren arg1 at (signed) ofs arg2
	198
	199	#*Special conditionals
	200	NGROUPP NGROUPP, no-sv 1 ; Whether the group matched.
	201	INSUBP INSUBP, num 1 ; Whether we are in a specific recurse.
	202	DEFINEP DEFINEP, none 1 ; Never execute directly.
	203
	204	#*Backtracking Verbs
	205	ENDLIKE ENDLIKE, none ; Used only for the type field of verbs
	206	OPFAIL ENDLIKE, no-sv 1 ; Same as (?!), but with verb arg
	207	ACCEPT ENDLIKE, no-sv/num 2L ; Accepts the current matched string, with verbar
	208
	209	#*Verbs With Arguments
	210	VERB VERB, no-sv 1 ; Used only for the type field of verbs
	211	PRUNE VERB, no-sv 1 ; Pattern fails at this startpoint if no-backtracking through this
	212	MARKPOINT VERB, no-sv 1 ; Push the current location for rollback by cut.
	213	SKIP VERB, no-sv 1 ; On failure skip forward (to the mark) before retrying
	214	COMMIT VERB, no-sv 1 ; Pattern fails outright if backtracking through this
	215	CUTGROUP VERB, no-sv 1 ; On failure go to the next alternation in the group
	216
	217	#*Control what to keep in $&.
	218	KEEPS KEEPS, no ; $& begins here.
	219
	220	#*New charclass like patterns
	221	LNBREAK LNBREAK, none ; generic newline pattern
	222
	223	# NEW STUFF SOMEWHERE ABOVE THIS LINE
	224
	225	################################################################################
	226
	227	#*SPECIAL REGOPS
	228
	229	#* This is not really a node, but an optimized away piece of a "long"
	230	#* node. To simplify debugging output, we mark it as if it were a node
	231	OPTIMIZED NOTHING, off ; Placeholder for dump.
	232
	233	#* Special opcode with the property that no opcode in a compiled program
	234	#* will ever be of this type. Thus it can be used as a flag value that
	235	#* no other opcode has been seen. END is used similarly, in that an END
	236	#* node cant be optimized. So END implies "unoptimizable" and PSEUDO
	237	#* mean "not seen anything to optimize yet".
	238	PSEUDO PSEUDO, off ; Pseudo opcode for internal use.
	239
	240	-------------------------------------------------------------------------------
	241	# Format for second section:
	242	# REGOP \t typelist [ \t typelist]
	243	# typelist= namelist
	244	# = namelist:FAIL
	245	# = name:count
	246
	247	# Anything below is a state
	248	#
	249	#
	250	TRIE next:FAIL
	251	EVAL B,postponed_AB:FAIL
	252	CURLYX end:FAIL
	253	WHILEM A_pre,A_min,A_max,B_min,B_max:FAIL
	254	BRANCH next:FAIL
	255	CURLYM A,B:FAIL
	256	IFMATCH A:FAIL
	257	CURLY B_min_known,B_min,B_max:FAIL
	258	COMMIT next:FAIL
	259	MARKPOINT next:FAIL
	260	SKIP next:FAIL
	261	CUTGROUP next:FAIL
	262	KEEPS next:FAIL

1

# regcomp.sym

2

#

3

# File has two sections, divided by a line of dashes '-'.

4

#

5

# Lines beginning with # are ignored, except for those that start with #*

6

# which are included in pod/perldebguts.pod. # within a line may be part

7

# of a description.

8

#

9

# First section is for regops, second section is for regmatch-states

10

#

11

# Note that the order in this file is important.

12

#

13

# Format for first section:

14

# NAME \s+ TYPE, arg-description [num-args] [flags] [longjump-len] ; DESCRIPTION

15

# flag <S> means is REGNODE_SIMPLE; flag <V> means is REGNODE_VARIES

16

#

17

#

18

# run perl regen.pl after editing this file

#* Exit points

END END, no ; End of program.

25

SUCCEED END, no ; Return from a subroutine, basically.

26

27

#* Line Start Anchors:

28

#Note flags field for SBOL indicates if it is a /^/ or a /\A/

29

SBOL BOL, no ; Match "" at beginning of line: /^/, /\A/

30

MBOL BOL, no ; Same, assuming multiline: /^/m

31

32

#* Line End Anchors:

33

SEOL EOL, no ; Match "" at end of line: /$/

34

MEOL EOL, no ; Same, assuming multiline: /$/m

35

EOS EOL, no ; Match "" at end of string: /\z/

36

37

#* Match Start Anchors:

38

GPOS GPOS, no ; Matches where last m//g left off.

39

40

#* Word Boundary Opcodes:

41

# The regops that have varieties that vary depending on the character set regex

42

# modifiers have to ordered thusly: /d, /l, /u, /a, /aa. This is because code

43

# in regcomp.c uses the enum value of the modifier as an offset from the /d

44

# version. The complements must come after the non-complements.

45

# BOUND, POSIX and their complements are affected, as well as EXACTF.

46

BOUND BOUND, no ; Like BOUNDA for non-utf8, otherwise match "" between any Unicode \w\W or \W\w

47

BOUNDL BOUND, no ; Like BOUND/BOUNDU, but \w and \W are defined by current locale

48

BOUNDU BOUND, no ; Match "" at any boundary of a given type using Unicode rules

49

BOUNDA BOUND, no ; Match "" at any boundary between \w\W or \W\w, where \w is [_a-zA-Z0-9]

50

# All NBOUND nodes are required by code in regexec.c to be greater than all BOUND ones

51

NBOUND NBOUND, no ; Like NBOUNDA for non-utf8, otherwise match "" between any Unicode \w\w or \W\W

52

NBOUNDL NBOUND, no ; Like NBOUND/NBOUNDU, but \w and \W are defined by current locale

53

NBOUNDU NBOUND, no ; Match "" at any non-boundary of a given type using using Unicode rules

54

NBOUNDA NBOUND, no ; Match "" betweeen any \w\w or \W\W, where \w is [_a-zA-Z0-9]

55

56

#* [Special] alternatives:

57

REG_ANY REG_ANY, no 0 S ; Match any one character (except newline).

58

SANY REG_ANY, no 0 S ; Match any one character.

59

ANYOF ANYOF, sv 1 S ; Match character in (or not in) this class, single char match only

60

ANYOFD ANYOF, sv 1 S ; Like ANYOF, but /d is in effect

61

ANYOFL ANYOF, sv 1 S ; Like ANYOF, but /l is in effect

62

63

#* POSIX Character Classes:

64

# Order of the below is important. See ordering comment above.

65

POSIXD POSIXD, none 0 S ; Some [[:class:]] under /d; the FLAGS field gives which one

66

POSIXL POSIXD, none 0 S ; Some [[:class:]] under /l; the FLAGS field gives which one

67

POSIXU POSIXD, none 0 S ; Some [[:class:]] under /u; the FLAGS field gives which one

68

POSIXA POSIXD, none 0 S ; Some [[:class:]] under /a; the FLAGS field gives which one

69

NPOSIXD NPOSIXD, none 0 S ; complement of POSIXD, [[:^class:]]

70

NPOSIXL NPOSIXD, none 0 S ; complement of POSIXL, [[:^class:]]

71

NPOSIXU NPOSIXD, none 0 S ; complement of POSIXU, [[:^class:]]

72

NPOSIXA NPOSIXD, none 0 S ; complement of POSIXA, [[:^class:]]

73

# End of order is important

74

75

ASCII ASCII, none 0 S ; [[:ascii:]]

76

NASCII ASCII, none 0 S ; [[:^ascii:]]

77

78

CLUMP CLUMP, no 0 V ; Match any extended grapheme cluster sequence

#* Alternation

#* BRANCH The set of branches constituting a single choice are

83

#* hooked together with their "next" pointers, since

84

#* precedence prevents anything being concatenated to

85

#* any individual branch. The "next" pointer of the last

86

#* BRANCH in a choice points to the thing following the

87

#* whole choice. This is also where the final "next"

88

#* pointer of each individual branch points; each branch

89

#* starts with the operand node of a BRANCH node.

90

#*

91

BRANCH BRANCH, node 0 V ; Match this alternative, or the next...

92

93

#*Literals

94

# NOTE: the relative ordering of these types is important do not change it

95

96

EXACT EXACT, str ; Match this string (preceded by length).

97

EXACTL EXACT, str ; Like EXACT, but /l is in effect (used so locale-related warnings can be checked for).

98

EXACTF EXACT, str ; Match this non-UTF-8 string (not guaranteed to be folded) using /id rules (w/len).

99

EXACTFL EXACT, str ; Match this string (not guaranteed to be folded) using /il rules (w/len).

100

EXACTFU EXACT, str ; Match this string (folded iff in UTF-8, length in folding doesn't change if not in UTF-8) using /iu rules (w/len).

101

EXACTFA EXACT, str ; Match this string (not guaranteed to be folded) using /iaa rules (w/len).

102

103

# End of important relative ordering.

104

105

EXACTFU_SS EXACT, str ; Match this string (folded iff in UTF-8, length in folding may change even if not in UTF-8) using /iu rules (w/len).

106

EXACTFLU8 EXACT, str ; Rare cirucmstances: like EXACTFU, but is under /l, UTF-8, folded, and everything in it is above 255.

107

EXACTFA_NO_TRIE EXACT, str ; Match this string (which is not trie-able; not guaranteed to be folded) using /iaa rules (w/len).

#*Do nothing types

NOTHING NOTHING, no ; Match empty string.

112

#*A variant of above which delimits a group, thus stops optimizations

113

TAIL NOTHING, no ; Match empty string. Can jump here from outside.

#*Loops

#* STAR,PLUS '?', and complex '*' and '+', are implemented as

118

#* circular BRANCH structures. Simple cases

119

#* (one character per match) are implemented with STAR

120

#* and PLUS for speed and to minimize recursive plunges.

121

#*

122

STAR STAR, node 0 V ; Match this (simple) thing 0 or more times.

123

PLUS PLUS, node 0 V ; Match this (simple) thing 1 or more times.

124

125

CURLY CURLY, sv 2 V ; Match this simple thing {n,m} times.

126

CURLYN CURLY, no 2 V ; Capture next-after-this simple thing

127

CURLYM CURLY, no 2 V ; Capture this medium-complex thing {n,m} times.

128

CURLYX CURLY, sv 2 V ; Match this complex thing {n,m} times.

129

130

#*This terminator creates a loop structure for CURLYX

131

WHILEM WHILEM, no 0 V ; Do curly processing and see if rest matches.

#*Buffer related

#*OPEN,CLOSE,GROUPP ...are numbered at compile time.

136

OPEN OPEN, num 1 ; Mark this point in input as start of #n.

137

CLOSE CLOSE, num 1 ; Close corresponding OPEN of #n.

138

SROPEN SROPEN, none ; Same as OPEN, but for script run

139

SRCLOSE SRCLOSE, none ; Close preceding SROPEN

140

141

REF REF, num 1 V ; Match some already matched string

142

REFF REF, num 1 V ; Match already matched string, folded using native charset rules for non-utf8

143

REFFL REF, num 1 V ; Match already matched string, folded in loc.

144

# N?REFF[AU] could have been implemented using the FLAGS field of the

145

# regnode, but by having a separate node type, we can use the existing switch

146

# statement to avoid some tests

147

REFFU REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8

148

REFFA REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII

149

150

#*Named references. Code in regcomp.c assumes that these all are after

151

#*the numbered references

152

NREF REF, no-sv 1 V ; Match some already matched string

153

NREFF REF, no-sv 1 V ; Match already matched string, folded using native charset rules for non-utf8

154

NREFFL REF, no-sv 1 V ; Match already matched string, folded in loc.

155

NREFFU REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8

156

NREFFA REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII

157

158

#*Support for long RE

159

LONGJMP LONGJMP, off 1 . 1 ; Jump far away.

160

BRANCHJ BRANCHJ, off 1 V 1 ; BRANCH with long offset.

161

162

#*Special Case Regops

163

IFMATCH BRANCHJ, off 1 . 2 ; Succeeds if the following matches.

164

UNLESSM BRANCHJ, off 1 . 2 ; Fails if the following matches.

165

SUSPEND BRANCHJ, off 1 V 1 ; "Independent" sub-RE.

166

IFTHEN BRANCHJ, off 1 V 1 ; Switch, should be preceded by switcher.

167

GROUPP GROUPP, num 1 ; Whether the group matched.

#*The heavy worker

EVAL EVAL, evl/flags 2L ; Execute some Perl code.

#*Modifiers

MINMOD MINMOD, no ; Next operator is not greedy.

177

LOGICAL LOGICAL, no ; Next opcode should set the flag only.

178

179

#*This is not used yet

180

RENUM BRANCHJ, off 1 . 1 ; Group with independently numbered parens.

#*Trie Related

#* Behave the same as A|LIST|OF|WORDS would. The '..C' variants

185

#* have inline charclass data (ascii only), the 'C' store it in the

186

#* structure.

187

# NOTE: the relative order of the TRIE-like regops is significant

188

189

TRIE TRIE, trie 1 ; Match many EXACT(F[ALU]?)? at once. flags==type

190

TRIEC TRIE,trie charclass ; Same as TRIE, but with embedded charclass data

191

192

# For start classes, contains an added fail table.

193

AHOCORASICK TRIE, trie 1 ; Aho Corasick stclass. flags==type

194

AHOCORASICKC TRIE,trie charclass ; Same as AHOCORASICK, but with embedded charclass data

195

196

#*Regex Subroutines

197

GOSUB GOSUB, num/ofs 2L ; recurse to paren arg1 at (signed) ofs arg2

198

199

#*Special conditionals

200

NGROUPP NGROUPP, no-sv 1 ; Whether the group matched.

201

INSUBP INSUBP, num 1 ; Whether we are in a specific recurse.

202

DEFINEP DEFINEP, none 1 ; Never execute directly.

203

204

#*Backtracking Verbs

205

ENDLIKE ENDLIKE, none ; Used only for the type field of verbs

206

OPFAIL ENDLIKE, no-sv 1 ; Same as (?!), but with verb arg

207

ACCEPT ENDLIKE, no-sv/num 2L ; Accepts the current matched string, with verbar

208

209

#*Verbs With Arguments

210

VERB VERB, no-sv 1 ; Used only for the type field of verbs

211

PRUNE VERB, no-sv 1 ; Pattern fails at this startpoint if no-backtracking through this

212

MARKPOINT VERB, no-sv 1 ; Push the current location for rollback by cut.

213

SKIP VERB, no-sv 1 ; On failure skip forward (to the mark) before retrying

214

COMMIT VERB, no-sv 1 ; Pattern fails outright if backtracking through this

215

CUTGROUP VERB, no-sv 1 ; On failure go to the next alternation in the group

216

217

#*Control what to keep in $&.

218

KEEPS KEEPS, no ; $& begins here.

219

220

#*New charclass like patterns

221

LNBREAK LNBREAK, none ; generic newline pattern

222

223

# NEW STUFF SOMEWHERE ABOVE THIS LINE

224

225

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

#*SPECIAL REGOPS

#* This is not really a node, but an optimized away piece of a "long"

230

#* node. To simplify debugging output, we mark it as if it were a node

231

OPTIMIZED NOTHING, off ; Placeholder for dump.

232

233

#* Special opcode with the property that no opcode in a compiled program

234

#* will ever be of this type. Thus it can be used as a flag value that

235

#* no other opcode has been seen. END is used similarly, in that an END

236

#* node cant be optimized. So END implies "unoptimizable" and PSEUDO

237

#* mean "not seen anything to optimize yet".

238

PSEUDO PSEUDO, off ; Pseudo opcode for internal use.

239

240

-------------------------------------------------------------------------------

241

# Format for second section:

242

# REGOP \t typelist [ \t typelist]

# typelist= namelist

# = namelist:FAIL

# = name:count

# Anything below is a state

#

#

TRIE next:FAIL

EVAL B,postponed_AB:FAIL

252

CURLYX end:FAIL

253

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