Commit | Line | Data |
---|---|---|
03363afd YO |
1 | # regcomp.sym |
2 | # | |
3 | # File has two sections, divided by a line of dashes '-'. | |
4 | # | |
65aa4ca7 FC |
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. | |
03363afd | 8 | # |
486ec47a | 9 | # First section is for regops, second section is for regmatch-states |
03363afd | 10 | # |
3dab1dad YO |
11 | # Note that the order in this file is important. |
12 | # | |
03363afd | 13 | # Format for first section: |
519ebf3d KW |
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 | |
03363afd | 16 | # |
3dab1dad | 17 | # |
c476f425 | 18 | # run perl regen.pl after editing this file |
3dab1dad | 19 | |
03363afd YO |
20 | |
21 | ||
381b57db | 22 | #* Exit points |
1de06328 | 23 | |
f8abb37e NC |
24 | END END, no ; End of program. |
25 | SUCCEED END, no ; Return from a subroutine, basically. | |
d09b2d29 | 26 | |
381b57db | 27 | #* Anchors: |
1de06328 | 28 | |
f8abb37e NC |
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. | |
693fefec KW |
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. | |
3018b823 | 40 | # BOUND, POSIX and their complements are affected, as well as EXACTF. |
850b7ec9 | 41 | BOUND BOUND, no ; Match "" at any word boundary using native charset rules for non-utf8 |
f2284805 | 42 | BOUNDL BOUND, no ; Match "" at any locale word boundary |
850b7ec9 KW |
43 | BOUNDU BOUND, no ; Match "" at any word boundary using Unicode rules |
44 | BOUNDA BOUND, no ; Match "" at any word boundary using ASCII rules | |
693fefec | 45 | # All NBOUND nodes are required by code in regexec.c to be greater than all BOUND ones |
850b7ec9 | 46 | NBOUND NBOUND, no ; Match "" at any word non-boundary using native charset rules for non-utf8 |
f2284805 | 47 | NBOUNDL NBOUND, no ; Match "" at any locale word non-boundary |
850b7ec9 KW |
48 | NBOUNDU NBOUND, no ; Match "" at any word non-boundary using Unicode rules |
49 | NBOUNDA NBOUND, no ; Match "" at any word non-boundary using ASCII rules | |
f8abb37e | 50 | GPOS GPOS, no ; Matches where last m//g left off. |
d09b2d29 | 51 | |
381b57db | 52 | #* [Special] alternatives: |
1de06328 | 53 | |
f9ef50a7 NC |
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. | |
0e019ad6 | 57 | ANYOF ANYOF, sv 0 S ; Match character in (or not in) this class, single char match only |
693fefec | 58 | |
3018b823 KW |
59 | # Order of the below is important. See ordering comment above. |
60 | POSIXD POSIXD, none 0 S ; Some [[:class:]] under /d; the FLAGS field gives which one | |
61 | POSIXL POSIXD, none 0 S ; Some [[:class:]] under /l; the FLAGS field gives which one | |
62 | POSIXU POSIXD, none 0 S ; Some [[:class:]] under /u; the FLAGS field gives which one | |
3615ea58 | 63 | POSIXA POSIXD, none 0 S ; Some [[:class:]] under /a; the FLAGS field gives which one |
3018b823 KW |
64 | NPOSIXD NPOSIXD, none 0 S ; complement of POSIXD, [[:^class:]] |
65 | NPOSIXL NPOSIXD, none 0 S ; complement of POSIXL, [[:^class:]] | |
66 | NPOSIXU NPOSIXD, none 0 S ; complement of POSIXU, [[:^class:]] | |
9e84774b | 67 | NPOSIXA NPOSIXD, none 0 S ; complement of POSIXA, [[:^class:]] |
3018b823 | 68 | # End of order is important |
693fefec | 69 | |
2448cf39 | 70 | CLUMP CLUMP, no 0 V ; Match any extended grapheme cluster sequence |
d09b2d29 | 71 | |
381b57db | 72 | #* Alternation |
1de06328 | 73 | |
65aa4ca7 FC |
74 | #* BRANCH The set of branches constituting a single choice are |
75 | #* hooked together with their "next" pointers, since | |
76 | #* precedence prevents anything being concatenated to | |
77 | #* any individual branch. The "next" pointer of the last | |
78 | #* BRANCH in a choice points to the thing following the | |
79 | #* whole choice. This is also where the final "next" | |
80 | #* pointer of each individual branch points; each branch | |
81 | #* starts with the operand node of a BRANCH node. | |
82 | #* | |
f9ef50a7 | 83 | BRANCH BRANCH, node 0 V ; Match this alternative, or the next... |
d09b2d29 | 84 | |
381b57db | 85 | #*Back pointer |
1de06328 | 86 | |
65aa4ca7 FC |
87 | #* BACK Normal "next" pointers all implicitly point forward; |
88 | #* BACK exists to make loop structures possible. | |
89 | #* not used | |
f9ef50a7 | 90 | BACK BACK, no 0 V ; Match "", "next" ptr points backward. |
d09b2d29 | 91 | |
65aa4ca7 FC |
92 | #*Literals |
93 | # NOTE: the relative ordering of these types is important do not change it | |
1de06328 | 94 | |
f8abb37e | 95 | EXACT EXACT, str ; Match this string (preceded by length). |
a36afff1 KW |
96 | EXACTF EXACT, str ; Match this non-UTF-8 string (not guaranteed to be folded) using /id rules (w/len). |
97 | EXACTFL EXACT, str ; Match this string (not guaranteed to be folded) using /il rules (w/len). | |
3c760661 | 98 | 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). |
8c1182fd | 99 | EXACTFA EXACT, str ; Match this string (not guaranteed to be folded) using /iaa rules (w/len). |
3c760661 | 100 | 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). |
098b07d5 | 101 | EXACTFA_NO_TRIE EXACT, str ; Match this string (which is not trie-able; not guaranteed to be folded) using /iaa rules (w/len). |
d09b2d29 | 102 | |
381b57db | 103 | #*Do nothing types |
1de06328 | 104 | |
f8abb37e | 105 | NOTHING NOTHING, no ; Match empty string. |
65aa4ca7 | 106 | #*A variant of above which delimits a group, thus stops optimizations |
f8abb37e | 107 | TAIL NOTHING, no ; Match empty string. Can jump here from outside. |
d09b2d29 | 108 | |
381b57db | 109 | #*Loops |
1de06328 | 110 | |
65aa4ca7 FC |
111 | #* STAR,PLUS '?', and complex '*' and '+', are implemented as |
112 | #* circular BRANCH structures using BACK. Simple cases | |
113 | #* (one character per match) are implemented with STAR | |
114 | #* and PLUS for speed and to minimize recursive plunges. | |
115 | #* | |
f9ef50a7 NC |
116 | STAR STAR, node 0 V ; Match this (simple) thing 0 or more times. |
117 | PLUS PLUS, node 0 V ; Match this (simple) thing 1 or more times. | |
d09b2d29 | 118 | |
f9ef50a7 NC |
119 | CURLY CURLY, sv 2 V ; Match this simple thing {n,m} times. |
120 | CURLYN CURLY, no 2 V ; Capture next-after-this simple thing | |
121 | CURLYM CURLY, no 2 V ; Capture this medium-complex thing {n,m} times. | |
122 | CURLYX CURLY, sv 2 V ; Match this complex thing {n,m} times. | |
d09b2d29 | 123 | |
65aa4ca7 | 124 | #*This terminator creates a loop structure for CURLYX |
f9ef50a7 | 125 | WHILEM WHILEM, no 0 V ; Do curly processing and see if rest matches. |
d09b2d29 | 126 | |
381b57db | 127 | #*Buffer related |
1de06328 | 128 | |
65aa4ca7 | 129 | #*OPEN,CLOSE,GROUPP ...are numbered at compile time. |
f8abb37e NC |
130 | OPEN OPEN, num 1 ; Mark this point in input as start of #n. |
131 | CLOSE CLOSE, num 1 ; Analogous to OPEN. | |
d09b2d29 | 132 | |
f9ef50a7 | 133 | REF REF, num 1 V ; Match some already matched string |
850b7ec9 | 134 | REFF REF, num 1 V ; Match already matched string, folded using native charset rules for non-utf8 |
f9ef50a7 | 135 | REFFL REF, num 1 V ; Match already matched string, folded in loc. |
781aab5c | 136 | # N?REFF[AU] could have been implemented using the FLAGS field of the |
01f98ec2 KW |
137 | # regnode, but by having a separate node type, we can use the existing switch |
138 | # statement to avoid some tests | |
850b7ec9 KW |
139 | REFFU REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8 |
140 | REFFA REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII | |
d09b2d29 | 141 | |
65aa4ca7 FC |
142 | #*Named references. Code in regcomp.c assumes that these all are after |
143 | #*the numbered references | |
01f98ec2 | 144 | NREF REF, no-sv 1 V ; Match some already matched string |
850b7ec9 | 145 | NREFF REF, no-sv 1 V ; Match already matched string, folded using native charset rules for non-utf8 |
01f98ec2 | 146 | NREFFL REF, no-sv 1 V ; Match already matched string, folded in loc. |
850b7ec9 KW |
147 | NREFFU REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8 |
148 | NREFFA REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII | |
1de06328 | 149 | |
f9ef50a7 NC |
150 | IFMATCH BRANCHJ, off 1 . 2 ; Succeeds if the following matches. |
151 | UNLESSM BRANCHJ, off 1 . 2 ; Fails if the following matches. | |
152 | SUSPEND BRANCHJ, off 1 V 1 ; "Independent" sub-RE. | |
65aa4ca7 | 153 | IFTHEN BRANCHJ, off 1 V 1 ; Switch, should be preceded by switcher. |
f8abb37e | 154 | GROUPP GROUPP, num 1 ; Whether the group matched. |
d09b2d29 | 155 | |
381b57db | 156 | #*Support for long RE |
1de06328 | 157 | |
f9ef50a7 NC |
158 | LONGJMP LONGJMP, off 1 . 1 ; Jump far away. |
159 | BRANCHJ BRANCHJ, off 1 V 1 ; BRANCH with long offset. | |
d09b2d29 | 160 | |
381b57db | 161 | #*The heavy worker |
1de06328 | 162 | |
f8abb37e | 163 | EVAL EVAL, evl 1 ; Execute some Perl code. |
d09b2d29 | 164 | |
381b57db | 165 | #*Modifiers |
1de06328 | 166 | |
f8abb37e NC |
167 | MINMOD MINMOD, no ; Next operator is not greedy. |
168 | LOGICAL LOGICAL, no ; Next opcode should set the flag only. | |
d09b2d29 | 169 | |
65aa4ca7 | 170 | #*This is not used yet |
f9ef50a7 | 171 | RENUM BRANCHJ, off 1 . 1 ; Group with independently numbered parens. |
d09b2d29 | 172 | |
381b57db | 173 | #*Trie Related |
1de06328 | 174 | |
65aa4ca7 FC |
175 | #* Behave the same as A|LIST|OF|WORDS would. The '..C' variants |
176 | #* have inline charclass data (ascii only), the 'C' store it in the | |
177 | #* structure. | |
486ec47a | 178 | # NOTE: the relative order of the TRIE-like regops is significant |
ce5e9471 | 179 | |
7986cb47 | 180 | TRIE TRIE, trie 1 ; Match many EXACT(F[ALU]?)? at once. flags==type |
f8abb37e | 181 | TRIEC TRIE,trie charclass ; Same as TRIE, but with embedded charclass data |
3dab1dad | 182 | |
1de06328 | 183 | # For start classes, contains an added fail table. |
f8abb37e NC |
184 | AHOCORASICK TRIE, trie 1 ; Aho Corasick stclass. flags==type |
185 | AHOCORASICKC TRIE,trie charclass ; Same as AHOCORASICK, but with embedded charclass data | |
1de06328 | 186 | |
381b57db | 187 | #*Regex Subroutines |
f8abb37e NC |
188 | GOSUB GOSUB, num/ofs 2L ; recurse to paren arg1 at (signed) ofs arg2 |
189 | GOSTART GOSTART, no ; recurse to start of pattern | |
03363afd | 190 | |
381b57db | 191 | #*Special conditionals |
f8abb37e NC |
192 | NGROUPP NGROUPP, no-sv 1 ; Whether the group matched. |
193 | INSUBP INSUBP, num 1 ; Whether we are in a specific recurse. | |
194 | DEFINEP DEFINEP, none 1 ; Never execute directly. | |
0a4db386 | 195 | |
486ec47a | 196 | #*Backtracking Verbs |
f8abb37e NC |
197 | ENDLIKE ENDLIKE, none ; Used only for the type field of verbs |
198 | OPFAIL ENDLIKE, none ; Same as (?!) | |
199 | ACCEPT ENDLIKE, parno 1 ; Accepts the current matched string. | |
5d458dd8 YO |
200 | |
201 | ||
202 | #*Verbs With Arguments | |
f8abb37e NC |
203 | VERB VERB, no-sv 1 ; Used only for the type field of verbs |
204 | PRUNE VERB, no-sv 1 ; Pattern fails at this startpoint if no-backtracking through this | |
205 | MARKPOINT VERB, no-sv 1 ; Push the current location for rollback by cut. | |
206 | SKIP VERB, no-sv 1 ; On failure skip forward (to the mark) before retrying | |
207 | COMMIT VERB, no-sv 1 ; Pattern fails outright if backtracking through this | |
208 | CUTGROUP VERB, no-sv 1 ; On failure go to the next alternation in the group | |
e2e6a0f1 | 209 | |
ee9b8eae | 210 | #*Control what to keep in $&. |
f8abb37e | 211 | KEEPS KEEPS, no ; $& begins here. |
ee9b8eae | 212 | |
e1d1eefb | 213 | #*New charclass like patterns |
f8abb37e | 214 | LNBREAK LNBREAK, none ; generic newline pattern |
3172e3fd | 215 | |
381b57db | 216 | # NEW STUFF SOMEWHERE ABOVE THIS LINE |
1de06328 | 217 | |
03363afd YO |
218 | ################################################################################ |
219 | ||
7f69552c | 220 | #*SPECIAL REGOPS |
1de06328 | 221 | |
65aa4ca7 FC |
222 | #* This is not really a node, but an optimized away piece of a "long" |
223 | #* node. To simplify debugging output, we mark it as if it were a node | |
f8abb37e | 224 | OPTIMIZED NOTHING, off ; Placeholder for dump. |
1de06328 | 225 | |
65aa4ca7 FC |
226 | #* Special opcode with the property that no opcode in a compiled program |
227 | #* will ever be of this type. Thus it can be used as a flag value that | |
228 | #* no other opcode has been seen. END is used similarly, in that an END | |
229 | #* node cant be optimized. So END implies "unoptimizable" and PSEUDO | |
230 | #* mean "not seen anything to optimize yet". | |
f8abb37e | 231 | PSEUDO PSEUDO, off ; Pseudo opcode for internal use. |
1de06328 | 232 | |
03363afd YO |
233 | ------------------------------------------------------------------------------- |
234 | # Format for second section: | |
65aa4ca7 | 235 | # REGOP \t typelist [ \t typelist] |
03363afd YO |
236 | # typelist= namelist |
237 | # = namelist:FAIL | |
238 | # = name:count | |
239 | ||
240 | # Anything below is a state | |
241 | # | |
242 | # | |
f8abb37e NC |
243 | TRIE next:FAIL |
244 | EVAL AB:FAIL | |
245 | CURLYX end:FAIL | |
246 | WHILEM A_pre,A_min,A_max,B_min,B_max:FAIL | |
247 | BRANCH next:FAIL | |
248 | CURLYM A,B:FAIL | |
249 | IFMATCH A:FAIL | |
250 | CURLY B_min_known,B_min,B_max:FAIL | |
251 | COMMIT next:FAIL | |
252 | MARKPOINT next:FAIL | |
253 | SKIP next:FAIL | |
254 | CUTGROUP next:FAIL | |
255 | KEEPS next:FAIL |