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	ANYOFM ANYOFM byte 1 S ; Like ANYOF, but matches an invariant byte as determined by the mask and arg
	63
	64	#* POSIX Character Classes:
	65	# Order of the below is important. See ordering comment above.
	66	POSIXD POSIXD, none 0 S ; Some [[:class:]] under /d; the FLAGS field gives which one
	67	POSIXL POSIXD, none 0 S ; Some [[:class:]] under /l; the FLAGS field gives which one
	68	POSIXU POSIXD, none 0 S ; Some [[:class:]] under /u; the FLAGS field gives which one
	69	POSIXA POSIXD, none 0 S ; Some [[:class:]] under /a; the FLAGS field gives which one
	70	NPOSIXD NPOSIXD, none 0 S ; complement of POSIXD, [[:^class:]]
	71	NPOSIXL NPOSIXD, none 0 S ; complement of POSIXL, [[:^class:]]
	72	NPOSIXU NPOSIXD, none 0 S ; complement of POSIXU, [[:^class:]]
	73	NPOSIXA NPOSIXD, none 0 S ; complement of POSIXA, [[:^class:]]
	74	# End of order is important
	75
	76	ASCII ASCII, none 0 S ; [[:ascii:]]
	77	NASCII ASCII, none 0 S ; [[:^ascii:]]
	78
	79	CLUMP CLUMP, no 0 V ; Match any extended grapheme cluster sequence
	80
	81	#* Alternation
	82
	83	#* BRANCH The set of branches constituting a single choice are
	84	#* hooked together with their "next" pointers, since
	85	#* precedence prevents anything being concatenated to
	86	#* any individual branch. The "next" pointer of the last
	87	#* BRANCH in a choice points to the thing following the
	88	#* whole choice. This is also where the final "next"
	89	#* pointer of each individual branch points; each branch
	90	#* starts with the operand node of a BRANCH node.
	91	#*
	92	BRANCH BRANCH, node 0 V ; Match this alternative, or the next...
	93
	94	#*Literals
	95	# NOTE: the relative ordering of these types is important do not change it
	96
	97	EXACT EXACT, str ; Match this string (preceded by length).
	98	EXACTL EXACT, str ; Like EXACT, but /l is in effect (used so locale-related warnings can be checked for).
	99	EXACTF EXACT, str ; Match this non-UTF-8 string (not guaranteed to be folded) using /id rules (w/len).
	100	EXACTFL EXACT, str ; Match this string (not guaranteed to be folded) using /il rules (w/len).
	101	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).
	102	EXACTFAA EXACT, str ; Match this string (not guaranteed to be folded) using /iaa rules (w/len).
	103
	104	# End of important relative ordering.
	105
	106	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).
	107	EXACTFLU8 EXACT, str ; Rare circumstances: like EXACTFU, but is under /l, UTF-8, folded, and everything in it is above 255.
	108	EXACTFAA_NO_TRIE EXACT, str ; Match this string (which is not trie-able; not guaranteed to be folded) using /iaa rules (w/len).
	109
	110	#*Do nothing types
	111
	112	NOTHING NOTHING, no ; Match empty string.
	113	#*A variant of above which delimits a group, thus stops optimizations
	114	TAIL NOTHING, no ; Match empty string. Can jump here from outside.
	115
	116	#*Loops
	117
	118	#* STAR,PLUS '?', and complex '*' and '+', are implemented as
	119	#* circular BRANCH structures. Simple cases
	120	#* (one character per match) are implemented with STAR
	121	#* and PLUS for speed and to minimize recursive plunges.
	122	#*
	123	STAR STAR, node 0 V ; Match this (simple) thing 0 or more times.
	124	PLUS PLUS, node 0 V ; Match this (simple) thing 1 or more times.
	125
	126	CURLY CURLY, sv 2 V ; Match this simple thing {n,m} times.
	127	CURLYN CURLY, no 2 V ; Capture next-after-this simple thing
	128	CURLYM CURLY, no 2 V ; Capture this medium-complex thing {n,m} times.
	129	CURLYX CURLY, sv 2 V ; Match this complex thing {n,m} times.
	130
	131	#*This terminator creates a loop structure for CURLYX
	132	WHILEM WHILEM, no 0 V ; Do curly processing and see if rest matches.
	133
	134	#*Buffer related
	135
	136	#*OPEN,CLOSE,GROUPP ...are numbered at compile time.
	137	OPEN OPEN, num 1 ; Mark this point in input as start of #n.
	138	CLOSE CLOSE, num 1 ; Close corresponding OPEN of #n.
	139	SROPEN SROPEN, none ; Same as OPEN, but for script run
	140	SRCLOSE SRCLOSE, none ; Close preceding SROPEN
	141
	142	REF REF, num 1 V ; Match some already matched string
	143	REFF REF, num 1 V ; Match already matched string, folded using native charset rules for non-utf8
	144	REFFL REF, num 1 V ; Match already matched string, folded in loc.
	145	# N?REFF[AU] could have been implemented using the FLAGS field of the
	146	# regnode, but by having a separate node type, we can use the existing switch
	147	# statement to avoid some tests
	148	REFFU REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8
	149	REFFA REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII
	150
	151	#*Named references. Code in regcomp.c assumes that these all are after
	152	#*the numbered references
	153	NREF REF, no-sv 1 V ; Match some already matched string
	154	NREFF REF, no-sv 1 V ; Match already matched string, folded using native charset rules for non-utf8
	155	NREFFL REF, no-sv 1 V ; Match already matched string, folded in loc.
	156	NREFFU REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8
	157	NREFFA REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII
	158
	159	#*Support for long RE
	160	LONGJMP LONGJMP, off 1 . 1 ; Jump far away.
	161	BRANCHJ BRANCHJ, off 1 V 1 ; BRANCH with long offset.
	162
	163	#*Special Case Regops
	164	IFMATCH BRANCHJ, off 1 . 2 ; Succeeds if the following matches.
	165	UNLESSM BRANCHJ, off 1 . 2 ; Fails if the following matches.
	166	SUSPEND BRANCHJ, off 1 V 1 ; "Independent" sub-RE.
	167	IFTHEN BRANCHJ, off 1 V 1 ; Switch, should be preceded by switcher.
	168	GROUPP GROUPP, num 1 ; Whether the group matched.
	169
	170
	171	#*The heavy worker
	172
	173	EVAL EVAL, evl/flags 2L ; Execute some Perl code.
	174
	175	#*Modifiers
	176
	177	MINMOD MINMOD, no ; Next operator is not greedy.
	178	LOGICAL LOGICAL, no ; Next opcode should set the flag only.
	179
	180	#*This is not used yet
	181	RENUM BRANCHJ, off 1 . 1 ; Group with independently numbered parens.
	182
	183	#*Trie Related
	184
	185	#* Behave the same as A\|LIST\|OF\|WORDS would. The '..C' variants
	186	#* have inline charclass data (ascii only), the 'C' store it in the
	187	#* structure.
	188	# NOTE: the relative order of the TRIE-like regops is significant
	189
	190	TRIE TRIE, trie 1 ; Match many EXACT(F[ALU]?)? at once. flags==type
	191	TRIEC TRIE,trie charclass ; Same as TRIE, but with embedded charclass data
	192
	193	# For start classes, contains an added fail table.
	194	AHOCORASICK TRIE, trie 1 ; Aho Corasick stclass. flags==type
	195	AHOCORASICKC TRIE,trie charclass ; Same as AHOCORASICK, but with embedded charclass data
	196
	197	#*Regex Subroutines
	198	GOSUB GOSUB, num/ofs 2L ; recurse to paren arg1 at (signed) ofs arg2
	199
	200	#*Special conditionals
	201	NGROUPP NGROUPP, no-sv 1 ; Whether the group matched.
	202	INSUBP INSUBP, num 1 ; Whether we are in a specific recurse.
	203	DEFINEP DEFINEP, none 1 ; Never execute directly.
	204
	205	#*Backtracking Verbs
	206	ENDLIKE ENDLIKE, none ; Used only for the type field of verbs
	207	OPFAIL ENDLIKE, no-sv 1 ; Same as (?!), but with verb arg
	208	ACCEPT ENDLIKE, no-sv/num 2L ; Accepts the current matched string, with verbar
	209
	210	#*Verbs With Arguments
	211	VERB VERB, no-sv 1 ; Used only for the type field of verbs
	212	PRUNE VERB, no-sv 1 ; Pattern fails at this startpoint if no-backtracking through this
	213	MARKPOINT VERB, no-sv 1 ; Push the current location for rollback by cut.
	214	SKIP VERB, no-sv 1 ; On failure skip forward (to the mark) before retrying
	215	COMMIT VERB, no-sv 1 ; Pattern fails outright if backtracking through this
	216	CUTGROUP VERB, no-sv 1 ; On failure go to the next alternation in the group
	217
	218	#*Control what to keep in $&.
	219	KEEPS KEEPS, no ; $& begins here.
	220
	221	#*New charclass like patterns
	222	LNBREAK LNBREAK, none ; generic newline pattern
	223
	224	# NEW STUFF SOMEWHERE ABOVE THIS LINE
	225
	226	################################################################################
	227
	228	#*SPECIAL REGOPS
	229
	230	#* This is not really a node, but an optimized away piece of a "long"
	231	#* node. To simplify debugging output, we mark it as if it were a node
	232	OPTIMIZED NOTHING, off ; Placeholder for dump.
	233
	234	#* Special opcode with the property that no opcode in a compiled program
	235	#* will ever be of this type. Thus it can be used as a flag value that
	236	#* no other opcode has been seen. END is used similarly, in that an END
	237	#* node cant be optimized. So END implies "unoptimizable" and PSEUDO
	238	#* mean "not seen anything to optimize yet".
	239	PSEUDO PSEUDO, off ; Pseudo opcode for internal use.
	240
	241	-------------------------------------------------------------------------------
	242	# Format for second section:
	243	# REGOP \t typelist [ \t typelist]
	244	# typelist= namelist
	245	# = namelist:FAIL
	246	# = name:count
	247
	248	# Anything below is a state
	249	#
	250	#
	251	TRIE next:FAIL
	252	EVAL B,postponed_AB:FAIL
	253	CURLYX end:FAIL
	254	WHILEM A_pre,A_min,A_max,B_min,B_max:FAIL
	255	BRANCH next:FAIL
	256	CURLYM A,B:FAIL
	257	IFMATCH A:FAIL
	258	CURLY B_min_known,B_min,B_max:FAIL
	259	COMMIT next:FAIL
	260	MARKPOINT next:FAIL
	261	SKIP next:FAIL
	262	CUTGROUP next:FAIL
	263	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

ANYOFM ANYOFM byte 1 S ; Like ANYOF, but matches an invariant byte as determined by the mask and arg

63

64

#* POSIX Character Classes:

65

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

66

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

67

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

68

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

69

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

70

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

71

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

72

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

73

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

74

# End of order is important

75

76

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

77

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

78

79

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

#* Alternation

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

84

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

85

#* precedence prevents anything being concatenated to

86

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

87

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

88

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

89

#* pointer of each individual branch points; each branch

90

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

91

#*

92

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

93

94

#*Literals

95

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

96

97

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

98

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

99

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

100

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

101

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).

102

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

103

104

# End of important relative ordering.

105

106

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).

107

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

108

EXACTFAA_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.

113

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

114

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

#*Loops

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

119

#* circular BRANCH structures. Simple cases

120

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

121

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

122

#*

123

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

124

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

125

126

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

127

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

128

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

129

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

130

131

#*This terminator creates a loop structure for CURLYX

132

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

#*Buffer related

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

137

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

138

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

139

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

140

SRCLOSE SRCLOSE, none ; Close preceding SROPEN

141

142

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

143

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

144

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

145

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

146

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

147

# statement to avoid some tests

148

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

149

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

150

151

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

152

#*the numbered references

153

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

154

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

155

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

156

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

157

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

158

159

#*Support for long RE

160

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

161

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

162

163

#*Special Case Regops

164

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

165

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

166

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

167

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

168

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.

178

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

179

180

#*This is not used yet

181

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

#*Trie Related

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

186

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

187

#* structure.

188

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

189

190

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

191

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

192

193

# For start classes, contains an added fail table.

194

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

195

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

196

197

#*Regex Subroutines

198

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

199

200

#*Special conditionals

201

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

202

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

203

DEFINEP DEFINEP, none 1 ; Never execute directly.

204

205

#*Backtracking Verbs

206

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

207

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

208

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

209

210

#*Verbs With Arguments

211

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

212

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

213

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

214

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

215

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

216

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

217

218

#*Control what to keep in $&.

219

KEEPS KEEPS, no ; $& begins here.

220

221

#*New charclass like patterns

222

LNBREAK LNBREAK, none ; generic newline pattern

223

224

# NEW STUFF SOMEWHERE ABOVE THIS LINE

225

226

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

#*SPECIAL REGOPS

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

231

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

232

OPTIMIZED NOTHING, off ; Placeholder for dump.

233

234

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

235

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

236

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

237

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

238

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

239

PSEUDO PSEUDO, off ; Pseudo opcode for internal use.

240

241

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

242

# Format for second section:

243

# REGOP \t typelist [ \t typelist]

# typelist= namelist

# = namelist:FAIL

# = name:count

# Anything below is a state

#

#

TRIE next:FAIL

EVAL B,postponed_AB:FAIL

253

CURLYX end:FAIL

254

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