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

#* Anchors:

BOL BOL, no ; Match "" at beginning of line.

30

MBOL BOL, no ; Same, assuming multiline.

31

SBOL BOL, no ; Same, assuming singleline.

32

EOS EOL, no ; Match "" at end of string.

33

EOL EOL, no ; Match "" at end of line.

34

MEOL EOL, no ; Same, assuming multiline.

35

SEOL EOL, no ; Same, assuming singleline.

36

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

37

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

38

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

39

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

40

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

41

BOUND BOUND, no ; Match "" at any word boundary using native charset semantics for non-utf8

42

BOUNDL BOUND, no ; Match "" at any locale word boundary

43

BOUNDU BOUND, no ; Match "" at any word boundary using Unicode semantics

44

BOUNDA BOUND, no ; Match "" at any word boundary using ASCII semantics

45

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

46

NBOUND NBOUND, no ; Match "" at any word non-boundary using native charset semantics for non-utf8

47

NBOUNDL NBOUND, no ; Match "" at any locale word non-boundary

48

NBOUNDU NBOUND, no ; Match "" at any word non-boundary using Unicode semantics

49

NBOUNDA NBOUND, no ; Match "" at any word non-boundary using ASCII semantics

50

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

51

52

#* [Special] alternatives:

53

54

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

55

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

56

CANY REG_ANY, no 0 S ; Match any one byte.

57

ANYOF ANYOF, sv 0 S ; Match character in (or not in) this class, single char match only

58

ANYOF_WARN_SUPER ANYOF, sv 0 S ; Match character in (or not in) this class, warn (if enabled) upon matching a char above Unicode max;

59

ANYOF_SYNTHETIC ANYOF, sv 0 S ; Synthetic start class

60

61

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

62

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

63

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

64

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

65

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

66

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

67

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

68

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

69

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

70

# End of order is important

71

72

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

#* Alternation

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

77

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

78

#* precedence prevents anything being concatenated to

79

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

80

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

81

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

82

#* pointer of each individual branch points; each branch

83

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

84

#*

85

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

#*Back pointer

#* BACK Normal "next" pointers all implicitly point forward;

90

#* BACK exists to make loop structures possible.

91

#* not used

92

BACK BACK, no 0 V ; Match "", "next" ptr points backward.

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

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

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).

103

EXACTFU_TRICKYFOLD EXACT, str ; Match this folded UTF-8 string using /iu rules

#*Do nothing types

NOTHING NOTHING, no ; Match empty string.

108

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

109

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

#*Loops

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

114

#* circular BRANCH structures using BACK. Simple cases

115

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

116

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

117

#*

118

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

119

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

120

121

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

122

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

123

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

124

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

125

126

#*This terminator creates a loop structure for CURLYX

127

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

#*Buffer related

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

132

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

133

CLOSE CLOSE, num 1 ; Analogous to OPEN.

134

135

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

136

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

137

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

138

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

139

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

140

# statement to avoid some tests

141

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

142

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

143

144

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

145

#*the numbered references

146

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

147

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

148

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

149

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

150

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

151

152

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

153

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

154

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

155

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

156

GROUPP GROUPP, num 1 ; Whether the group matched.

157

158

#*Support for long RE

159

160

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

161

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

#*The heavy worker

EVAL EVAL, evl 1 ; Execute some Perl code.

#*Modifiers

MINMOD MINMOD, no ; Next operator is not greedy.

170

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

171

172

#*This is not used yet

173

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

#*Trie Related

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

178

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

179

#* structure.

180

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

181

182

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

183

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

184

185

# For start classes, contains an added fail table.

186

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

187

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

188

189

#*Regex Subroutines

190

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

191

GOSTART GOSTART, no ; recurse to start of pattern

192

193

#*Special conditionals

194

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

195

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

196

DEFINEP DEFINEP, none 1 ; Never execute directly.

197

198

#*Backtracking Verbs

199

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

200

OPFAIL ENDLIKE, none ; Same as (?!)

201

ACCEPT ENDLIKE, parno 1 ; Accepts the current matched string.

202

203

204

#*Verbs With Arguments

205

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

206

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

207

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

208

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

209

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

210

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

211

212

#*Control what to keep in $&.

213

KEEPS KEEPS, no ; $& begins here.

214

215

#*New charclass like patterns

216

LNBREAK LNBREAK, none ; generic newline pattern

217

218

# NEW STUFF SOMEWHERE ABOVE THIS LINE

219

220

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

#*SPECIAL REGOPS

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

225

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

226

OPTIMIZED NOTHING, off ; Placeholder for dump.

227

228

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

229

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

230

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

231

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

232

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

233

PSEUDO PSEUDO, off ; Pseudo opcode for internal use.

234

235

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

236

# Format for second section:

237

# REGOP \t typelist [ \t typelist]

# 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