3 # File has two sections, divided by a line of dashes '-'.
5 # Empty rows after #-comment are removed from input are ignored
7 # First section is for regops, second sectionis for regmatch-states
9 # Note that the order in this file is important.
11 # Format for first section:
12 # NAME \s+ TYPE, arg-description [flags] [num-args] [longjump-len] ; DESCRIPTION
15 # run perl regen.pl after editing this file
21 END END, no ; End of program.
22 SUCCEED END, no ; Return from a subroutine, basically.
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.
39 #* [Special] alternatives: (14..30)
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
54 DIGITL DIGIT, no ; Match any numeric character in locale
55 NDIGIT NDIGIT, no 0 S ; Match any non-numeric character
56 NDIGITL NDIGIT, no ; Match any non-numeric character in locale
57 CLUMP CLUMP, no 0 V ; Match any combining character sequence
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.
69 BRANCH BRANCH, node 0 V ; Match this alternative, or the next...
73 # BACK Normal "next" pointers all implicitly point forward; BACK
74 # exists to make loop structures possible.
76 BACK BACK, no 0 V ; Match "", "next" ptr points backward.
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).
84 #*Do nothing types (36..37)
86 NOTHING NOTHING, no ; Match empty string.
87 # A variant of above which delimits a group, thus stops optimizations
88 TAIL NOTHING, no ; Match empty string. Can jump here from outside.
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.
97 STAR STAR, node 0 V ; Match this (simple) thing 0 or more times.
98 PLUS PLUS, node 0 V ; Match this (simple) thing 1 or more times.
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.
105 # This terminator creates a loop structure for CURLYX
106 WHILEM WHILEM, no 0 V ; Do curly processing and see if rest matches.
108 #*Buffer related (45..49)
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.
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.
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 .
123 GROUPP GROUPP, num 1 ; Whether the group matched.
125 #*Support for long RE (55..56)
127 LONGJMP LONGJMP, off 1 . 1 ; Jump far away.
128 BRANCHJ BRANCHJ, off 1 V 1 ; BRANCH with long offset.
130 #*The heavy worker (57)
132 EVAL EVAL, evl 1 ; Execute some Perl code.
136 MINMOD MINMOD, no ; Next operator is not greedy.
137 LOGICAL LOGICAL, no ; Next opcode should set the flag only.
139 # This is not used yet (60)
140 RENUM BRANCHJ, off 1 . 1 ; Group with independently numbered parens.
142 #*Trie Related (61..62)
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
148 TRIE TRIE, trie 1 ; Match many EXACT(FL?)? at once. flags==type
149 TRIEC TRIE,trie charclass ; Same as TRIE, but with embedded charclass data
151 # For start classes, contains an added fail table.
152 AHOCORASICK TRIE, trie 1 ; Aho Corasick stclass. flags==type
153 AHOCORASICKC TRIE,trie charclass ; Same as AHOCORASICK, but with embedded charclass data
155 #*Regex Subroutines (65..66)
156 GOSUB GOSUB, num/ofs 2L ; recurse to paren arg1 at (signed) ofs arg2
157 GOSTART GOSTART, no ; recurse to start of pattern
159 #*Named references (67..69)
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.
165 #*Special conditionals (70..72)
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.
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.
176 #*Verbs With Arguments
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
184 #*Control what to keep in $&.
185 KEEPS KEEPS, no ; $& begins here.
187 #*New charclass like patterns
188 LNBREAK LNBREAK, none ; generic newline pattern
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)
194 FOLDCHAR FOLDCHAR, codepoint 1 ; codepoint with tricky case folding properties.
196 # NEW STUFF ABOVE THIS LINE
198 ################################################################################
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
204 OPTIMIZED NOTHING, off ; Placeholder for dump.
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".
211 PSEUDO PSEUDO, off ; Pseudo opcode for internal use.
213 -------------------------------------------------------------------------------
214 # Format for second section:
215 # REGOP \t typelist [ \t typelist] [# Comment]
220 # Anything below is a state
226 WHILEM A_pre,A_min,A_max,B_min,B_max:FAIL
230 CURLY B_min_known,B_min,B_max:FAIL