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] ; DESCRIPTION
15#   flag <S> means is REGNODE_SIMPLE; flag <V> means is REGNODE_VARIES; <.> is
16#   a placeholder
17#   longjump is 1 if the (first) argument holds the next offset.
18#
19#
20# run perl regen.pl after editing this file
21
22
23
24#* Exit points
25
26END         END,        no        ; End of program.
27SUCCEED     END,        no        ; Return from a subroutine, basically.
28
29#* Line Start Anchors:
30#Note flags field for SBOL indicates if it is a /^/ or a /\A/
31SBOL        BOL,        no        ; Match "" at beginning of line: /^/, /\A/
32MBOL        BOL,        no        ; Same, assuming multiline: /^/m
33
34#* Line End Anchors:
35SEOL        EOL,        no        ; Match "" at end of line: /$/
36MEOL        EOL,        no        ; Same, assuming multiline: /$/m
37EOS         EOL,        no        ; Match "" at end of string: /\z/
38
39#* Match Start Anchors:
40GPOS        GPOS,       no        ; Matches where last m//g left off.
41
42#* Word Boundary Opcodes:
43# The regops that have varieties that vary depending on the character set regex
44# modifiers have to ordered thusly: /d, /l, /u, /a, /aa.  This is because code
45# in regcomp.c uses the enum value of the modifier as an offset from the /d
46# version.  The complements must come after the non-complements.
47# BOUND, POSIX and their complements are affected, as well as EXACTF.
48BOUND       BOUND,      no        ; Like BOUNDA for non-utf8, otherwise match "" between any Unicode \w\W or \W\w
49BOUNDL      BOUND,      no        ; Like BOUND/BOUNDU, but \w and \W are defined by current locale
50BOUNDU      BOUND,      no        ; Match "" at any boundary of a given type using /u rules.
51BOUNDA      BOUND,      no        ; Match "" at any boundary between \w\W or \W\w, where \w is [_a-zA-Z0-9]
52# All NBOUND nodes are required by code in regexec.c to be greater than all BOUND ones
53NBOUND      NBOUND,     no        ; Like NBOUNDA for non-utf8, otherwise match "" between any Unicode \w\w or \W\W
54NBOUNDL     NBOUND,     no        ; Like NBOUND/NBOUNDU, but \w and \W are defined by current locale
55NBOUNDU     NBOUND,     no        ; Match "" at any non-boundary of a given type using using /u rules.
56NBOUNDA     NBOUND,     no        ; Match "" betweeen any \w\w or \W\W, where \w is [_a-zA-Z0-9]
57
58#* [Special] alternatives:
59REG_ANY     REG_ANY,    no 0 S    ; Match any one character (except newline).
60SANY        REG_ANY,    no 0 S    ; Match any one character.
61ANYOF       ANYOF,      sv charclass S    ; Match character in (or not in) this class, single char match only
62ANYOFD      ANYOF,      sv charclass S    ; Like ANYOF, but /d is in effect
63ANYOFL      ANYOF,      sv charclass S    ; Like ANYOF, but /l is in effect
64ANYOFPOSIXL ANYOF,      sv charclass_posixl S    ; Like ANYOFL, but matches [[:posix:]] classes
65ANYOFH      ANYOF,      sv 1 S    ; Like ANYOF, but only has "High" matches, none in the bitmap; non-zero flags "f" means "f" is the first UTF-8 byte shared in common by all code points matched
66ANYOFM      ANYOFM      byte 1 S  ; Like ANYOF, but matches an invariant byte as determined by the mask and arg
67NANYOFM     ANYOFM      byte 1 S  ; complement of ANYOFM
68
69#* POSIX Character Classes:
70# Order of the below is important.  See ordering comment above.
71POSIXD      POSIXD,     none 0 S   ; Some [[:class:]] under /d; the FLAGS field gives which one
72POSIXL      POSIXD,     none 0 S   ; Some [[:class:]] under /l; the FLAGS field gives which one
73POSIXU      POSIXD,     none 0 S   ; Some [[:class:]] under /u; the FLAGS field gives which one
74POSIXA      POSIXD,     none 0 S   ; Some [[:class:]] under /a; the FLAGS field gives which one
75NPOSIXD     NPOSIXD,    none 0 S   ; complement of POSIXD, [[:^class:]]
76NPOSIXL     NPOSIXD,    none 0 S   ; complement of POSIXL, [[:^class:]]
77NPOSIXU     NPOSIXD,    none 0 S   ; complement of POSIXU, [[:^class:]]
78NPOSIXA     NPOSIXD,    none 0 S   ; complement of POSIXA, [[:^class:]]
79# End of order is important
80
81CLUMP       CLUMP,      no 0 V    ; Match any extended grapheme cluster sequence
82
83#* Alternation
84
85#* BRANCH        The set of branches constituting a single choice are
86#*               hooked together with their "next" pointers, since
87#*               precedence prevents anything being concatenated to
88#*               any individual branch.  The "next" pointer of the last
89#*               BRANCH in a choice points to the thing following the
90#*               whole choice.  This is also where the final "next"
91#*               pointer of each individual branch points; each branch
92#*               starts with the operand node of a BRANCH node.
93#*
94BRANCH      BRANCH,     node 0 V  ; Match this alternative, or the next...
95
96#*Literals
97# NOTE: the relative ordering of these types is important do not change it
98
99EXACT       EXACT,      str       ; Match this string (preceded by length).
100EXACTL      EXACT,      str       ; Like EXACT, but /l is in effect (used so locale-related warnings can be checked for).
101EXACTF      EXACT,      str       ; Match this string using /id rules (w/len); (string not UTF-8, not guaranteed to be folded).
102EXACTFL     EXACT,      str       ; Match this string using /il rules (w/len); (string not guaranteed to be folded).
103EXACTFU     EXACT,      str	  ; Match this string using /iu rules (w/len); (string folded iff in UTF-8; non-UTF8 folded length <= unfolded).
104EXACTFAA    EXACT,      str	  ; Match this string using /iaa rules (w/len) (string folded iff in UTF-8; non-UTF8 folded length <= unfolded).
105
106# End of important relative ordering.
107
108EXACTFUP    EXACT,      str	  ; Match this string using /iu rules (w/len); (string not UTF-8, not guaranteed to be folded; and its Problematic).
109# In order for a non-UTF-8 EXACTFAA to think the pattern is pre-folded when
110# matching a UTF-8 target string, there would have to be something like an
111# EXACTFAA_MICRO which would not be considered pre-folded for UTF-8 targets,
112# since the fold of the MICRO SIGN would not be done, and would be
113# representable in the UTF-8 target string.
114
115EXACTFLU8   EXACT,      str	  ; Like EXACTFU, but use /il, UTF-8, folded, and everything in it is above 255.
116EXACTFAA_NO_TRIE  EXACT, str	  ; Match this string using /iaa rules (w/len) (string not UTF-8, not guaranteed to be folded, not currently trie-able).
117
118
119EXACT_ONLY8 EXACT,      str       ; Like EXACT, but only UTF-8 encoded targets can match
120EXACTFU_ONLY8 EXACT,    str       ; Like EXACTFU, but only UTF-8 encoded targets can match
121# One could add EXACTFAA8 and and something that has the same effect for /l,
122# but these would be extremely uncommon
123
124EXACTFU_S_EDGE EXACT,   str       ; /di rules, but nothing in it precludes /ui, except begins and/or ends with [Ss]; (string not UTF-8; compile-time only).
125
126#*Do nothing types
127
128NOTHING     NOTHING,    no        ; Match empty string.
129#*A variant of above which delimits a group, thus stops optimizations
130TAIL        NOTHING,    no        ; Match empty string. Can jump here from outside.
131
132#*Loops
133
134#* STAR,PLUS    '?', and complex '*' and '+', are implemented as
135#*               circular BRANCH structures.  Simple cases
136#*               (one character per match) are implemented with STAR
137#*               and PLUS for speed and to minimize recursive plunges.
138#*
139STAR        STAR,       node 0 V  ; Match this (simple) thing 0 or more times.
140PLUS        PLUS,       node 0 V  ; Match this (simple) thing 1 or more times.
141
142CURLY       CURLY,      sv 2 V    ; Match this simple thing {n,m} times.
143CURLYN      CURLY,      no 2 V    ; Capture next-after-this simple thing
144CURLYM      CURLY,      no 2 V    ; Capture this medium-complex thing {n,m} times.
145CURLYX      CURLY,      sv 2 V    ; Match this complex thing {n,m} times.
146
147#*This terminator creates a loop structure for CURLYX
148WHILEM      WHILEM,     no 0 V    ; Do curly processing and see if rest matches.
149
150#*Buffer related
151
152#*OPEN,CLOSE,GROUPP     ...are numbered at compile time.
153OPEN        OPEN,       num 1     ; Mark this point in input as start of #n.
154CLOSE       CLOSE,      num 1     ; Close corresponding OPEN of #n.
155SROPEN      SROPEN,     none      ; Same as OPEN, but for script run
156SRCLOSE     SRCLOSE,    none      ; Close preceding SROPEN
157
158REF         REF,        num 1 V   ; Match some already matched string
159REFF        REF,        num 1 V   ; Match already matched string, using /di rules.
160REFFL       REF,        num 1 V   ; Match already matched string, using /li rules.
161# N?REFF[AU] could have been implemented using the FLAGS field of the
162# regnode, but by having a separate node type, we can use the existing switch
163# statement to avoid some tests
164REFFU       REF,        num 1 V   ; Match already matched string, usng /ui.
165REFFA       REF,        num 1 V   ; Match already matched string, using /aai rules.
166
167#*Named references.  Code in regcomp.c assumes that these all are after
168#*the numbered references
169NREF        REF,        no-sv 1 V ; Match some already matched string
170NREFF       REF,        no-sv 1 V ; Match already matched string, using /di rules.
171NREFFL      REF,        no-sv 1 V ; Match already matched string, using /li rules.
172NREFFU      REF,        num   1 V ; Match already matched string, using /ui rules.
173NREFFA      REF,        num   1 V ; Match already matched string, using /aai rules.
174
175#*Support for long RE
176LONGJMP     LONGJMP,    off 1 . 1 ; Jump far away.
177BRANCHJ     BRANCHJ,    off 1 V 1 ; BRANCH with long offset.
178
179#*Special Case Regops
180IFMATCH     BRANCHJ,    off 1 . 1 ; Succeeds if the following matches; non-zero flags "f", next_off "o" means lookbehind assertion starting "f..(f-o)" characters before current
181UNLESSM     BRANCHJ,    off 1 . 1 ; Fails if the following matches; non-zero flags "f", next_off "o" means lookbehind assertion starting "f..(f-o)" characters before current
182SUSPEND     BRANCHJ,    off 1 V 1 ; "Independent" sub-RE.
183IFTHEN      BRANCHJ,    off 1 V 1 ; Switch, should be preceded by switcher.
184GROUPP      GROUPP,     num 1     ; Whether the group matched.
185
186
187#*The heavy worker
188
189EVAL        EVAL,       evl/flags 2L ; Execute some Perl code.
190
191#*Modifiers
192
193MINMOD      MINMOD,     no        ; Next operator is not greedy.
194LOGICAL     LOGICAL,    no        ; Next opcode should set the flag only.
195
196#*This is not used yet
197RENUM       BRANCHJ,    off 1 . 1 ; Group with independently numbered parens.
198
199#*Trie Related
200
201#* Behave the same as A|LIST|OF|WORDS would. The '..C' variants
202#* have inline charclass data (ascii only), the 'C' store it in the
203#* structure.
204# NOTE: the relative order of the TRIE-like regops  is significant
205
206TRIE        TRIE,       trie 1    ; Match many EXACT(F[ALU]?)? at once. flags==type
207TRIEC       TRIE,trie charclass   ; Same as TRIE, but with embedded charclass data
208
209# For start classes, contains an added fail table.
210AHOCORASICK     TRIE,   trie 1    ; Aho Corasick stclass. flags==type
211AHOCORASICKC    TRIE,trie charclass   ; Same as AHOCORASICK, but with embedded charclass data
212
213#*Regex Subroutines
214GOSUB       GOSUB,      num/ofs 2L    ; recurse to paren arg1 at (signed) ofs arg2
215
216#*Special conditionals
217NGROUPP     NGROUPP,    no-sv 1   ; Whether the group matched.
218INSUBP      INSUBP,     num 1     ; Whether we are in a specific recurse.
219DEFINEP     DEFINEP,    none 1    ; Never execute directly.
220
221#*Backtracking Verbs
222ENDLIKE     ENDLIKE,    none      ; Used only for the type field of verbs
223OPFAIL      ENDLIKE,    no-sv 1   ; Same as (?!), but with verb arg
224ACCEPT      ENDLIKE,    no-sv/num 2L   ; Accepts the current matched string, with verbar
225
226#*Verbs With Arguments
227VERB        VERB,       no-sv 1   ; Used only for the type field of verbs
228PRUNE       VERB,       no-sv 1   ; Pattern fails at this startpoint if no-backtracking through this
229MARKPOINT   VERB,       no-sv 1   ; Push the current location for rollback by cut.
230SKIP        VERB,       no-sv 1   ; On failure skip forward (to the mark) before retrying
231COMMIT      VERB,       no-sv 1   ; Pattern fails outright if backtracking through this
232CUTGROUP    VERB,       no-sv 1   ; On failure go to the next alternation in the group
233
234#*Control what to keep in $&.
235KEEPS       KEEPS,      no        ; $& begins here.
236
237#*New charclass like patterns
238LNBREAK     LNBREAK,    none      ; generic newline pattern
239
240# NEW STUFF SOMEWHERE ABOVE THIS LINE
241
242################################################################################
243
244#*SPECIAL  REGOPS
245
246#* This is not really a node, but an optimized away piece of a "long"
247#* node.  To simplify debugging output, we mark it as if it were a node
248OPTIMIZED   NOTHING,    off       ; Placeholder for dump.
249
250#* Special opcode with the property that no opcode in a compiled program
251#* will ever be of this type. Thus it can be used as a flag value that
252#* no other opcode has been seen. END is used similarly, in that an END
253#* node cant be optimized. So END implies "unoptimizable" and PSEUDO
254#* mean "not seen anything to optimize yet".
255PSEUDO      PSEUDO,     off       ; Pseudo opcode for internal use.
256
257-------------------------------------------------------------------------------
258# Format for second section:
259# REGOP \t typelist [ \t typelist]
260# typelist= namelist
261#         = namelist:FAIL
262#         = name:count
263
264# Anything below is a state
265#
266#
267TRIE            next:FAIL
268EVAL            B,postponed_AB:FAIL
269CURLYX          end:FAIL
270WHILEM          A_pre,A_min,A_max,B_min,B_max:FAIL
271BRANCH          next:FAIL
272CURLYM          A,B:FAIL
273IFMATCH         A:FAIL
274CURLY           B_min,B_max:FAIL
275COMMIT          next:FAIL
276MARKPOINT       next:FAIL
277SKIP            next:FAIL
278CUTGROUP        next:FAIL
279KEEPS           next:FAIL
280