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: |
e21ef692 KW |
14 | # NAME \s+ TYPE, arg-description [struct regnode suffix] [flags] [longjump] ; DESCRIPTION |
15 | # arg-description is currently unused | |
16 | # suffix is appended to 'struct_regnode_' giving which one to use. If empty, | |
17 | # it means plain 'struct regnode'. If the regnode is a string one, this | |
18 | # should instead refer to the base regnode, without the char[1] element | |
19 | # of the structure | |
46167d76 | 20 | # flag <S> means is REGNODE_SIMPLE; flag <V> means is REGNODE_VARIES; <.> is |
e21ef692 KW |
21 | # a placeholder |
22 | # longjump is 1 if the (first) argument holds the next offset (instead of the | |
23 | # usual 'next_offset' field | |
3dab1dad | 24 | # |
c476f425 | 25 | # run perl regen.pl after editing this file |
3dab1dad | 26 | |
e21ef692 KW |
27 | # +- suffix of which struct regnode to use e.g., |
28 | # | +- flags (S or V) struct regnode_1 | |
29 | # un- | | +- longjmp (0, blank, or 1) blank means 0 | |
30 | # Name Type used | | | ; comment | |
31 | # -------------------------------------------------------------------------- | |
32 | # IFMATCH BRANCHJ, off 1 . 1 ; Succeeds if the following matches. | |
33 | # UNLESSM BRANCHJ, off 1 . 1 ; Fails if the following matches. | |
34 | # SUSPEND BRANCHJ, off 1 V 1 ; "Independent" sub-RE. | |
35 | # IFTHEN BRANCHJ, off 1 V 1 ; Switch, should be preceded by switcher. | |
36 | # GROUPP GROUPP, num 1 ; Whether the group matched. | |
96bc7be8 KW |
37 | # |
38 | # If we were to start running out of regnodes, many of the ones that are | |
39 | # complements could be combined with their non-complement mates. For example, | |
40 | # POSIXU could have the flags field have the bottom bit mean do we complement | |
41 | # or not, and the type be shifted left 1 bit. Then all that would be needed to | |
42 | # extract which to do is a mask for the complement bit, and a right shift for | |
43 | # the other, an inconsequential increase in instructions. It might actually be | |
44 | # clearer and slightly faster given the case statement and assignment are | |
45 | # removed. Note that not everything could be collapsed: NPOSIXA, for example, | |
46 | # would require special handling for performance. | |
03363afd YO |
47 | |
48 | ||
381b57db | 49 | #* Exit points |
1de06328 | 50 | |
f8abb37e NC |
51 | END END, no ; End of program. |
52 | SUCCEED END, no ; Return from a subroutine, basically. | |
d09b2d29 | 53 | |
d3d47aac | 54 | #* Line Start Anchors: |
1645b83c | 55 | #Note flags field for SBOL indicates if it is a /^/ or a /\A/ |
d3d47aac YO |
56 | SBOL BOL, no ; Match "" at beginning of line: /^/, /\A/ |
57 | MBOL BOL, no ; Same, assuming multiline: /^/m | |
58 | ||
59 | #* Line End Anchors: | |
60 | SEOL EOL, no ; Match "" at end of line: /$/ | |
61 | MEOL EOL, no ; Same, assuming multiline: /$/m | |
62 | EOS EOL, no ; Match "" at end of string: /\z/ | |
63 | ||
64 | #* Match Start Anchors: | |
65 | GPOS GPOS, no ; Matches where last m//g left off. | |
66 | ||
67 | #* Word Boundary Opcodes: | |
693fefec KW |
68 | # The regops that have varieties that vary depending on the character set regex |
69 | # modifiers have to ordered thusly: /d, /l, /u, /a, /aa. This is because code | |
70 | # in regcomp.c uses the enum value of the modifier as an offset from the /d | |
71 | # version. The complements must come after the non-complements. | |
3018b823 | 72 | # BOUND, POSIX and their complements are affected, as well as EXACTF. |
0991ffc9 | 73 | BOUND BOUND, no ; Like BOUNDA for non-utf8, otherwise like BOUNDU |
c440a570 | 74 | BOUNDL BOUND, no ; Like BOUND/BOUNDU, but \w and \W are defined by current locale |
912b808c | 75 | BOUNDU BOUND, no ; Match "" at any boundary of a given type using /u rules. |
c440a570 | 76 | BOUNDA BOUND, no ; Match "" at any boundary between \w\W or \W\w, where \w is [_a-zA-Z0-9] |
693fefec | 77 | # All NBOUND nodes are required by code in regexec.c to be greater than all BOUND ones |
0991ffc9 | 78 | NBOUND NBOUND, no ; Like NBOUNDA for non-utf8, otherwise like BOUNDU |
c440a570 | 79 | NBOUNDL NBOUND, no ; Like NBOUND/NBOUNDU, but \w and \W are defined by current locale |
912b808c | 80 | NBOUNDU NBOUND, no ; Match "" at any non-boundary of a given type using using /u rules. |
c440a570 | 81 | NBOUNDA NBOUND, no ; Match "" betweeen any \w\w or \W\W, where \w is [_a-zA-Z0-9] |
d09b2d29 | 82 | |
381b57db | 83 | #* [Special] alternatives: |
f9ef50a7 NC |
84 | REG_ANY REG_ANY, no 0 S ; Match any one character (except newline). |
85 | SANY REG_ANY, no 0 S ; Match any one character. | |
46fc0c43 KW |
86 | ANYOF ANYOF, sv charclass S ; Match character in (or not in) this class, single char match only |
87 | ANYOFD ANYOF, sv charclass S ; Like ANYOF, but /d is in effect | |
88 | ANYOFL ANYOF, sv charclass S ; Like ANYOF, but /l is in effect | |
89 | ANYOFPOSIXL ANYOF, sv charclass_posixl S ; Like ANYOFL, but matches [[:posix:]] classes | |
f6eaa562 KW |
90 | |
91 | # Must be sequential | |
29a889ef | 92 | ANYOFH ANYOF, sv 1 S ; Like ANYOF, but only has "High" matches, none in the bitmap; the flags field contains the lowest matchable UTF-8 start byte |
a5bc0742 | 93 | ANYOFHb ANYOF, sv 1 S ; Like ANYOFH, but all matches share the same UTF-8 start byte, given in the flags field |
3146c00a | 94 | ANYOFHr ANYOF, sv 1 S ; Like ANYOFH, but the flags field contains packed bounds for all matchable UTF-8 start bytes. |
53d42e43 | 95 | ANYOFHs ANYOF, sv 1 S ; Like ANYOFHb, but has a string field that gives the leading matchable UTF-8 bytes; flags field is len |
2d5613be KW |
96 | ANYOFR ANYOFR, packed 1 S ; Matches any character in the range given by its packed args: upper 12 bits is the max delta from the base lower 20; the flags field contains the lowest matchable UTF-8 start byte |
97 | ANYOFRb ANYOFR, packed 1 S ; Like ANYOFR, but all matches share the same UTF-8 start byte, given in the flags field | |
98 | # There is no ANYOFRr because khw doesn't think there are likely to be real-world cases where such a large range is used. | |
f6eaa562 | 99 | |
ebee057d KW |
100 | ANYOFM ANYOFM, byte 1 S ; Like ANYOF, but matches an invariant byte as determined by the mask and arg |
101 | NANYOFM ANYOFM, byte 1 S ; complement of ANYOFM | |
693fefec | 102 | |
d3d47aac | 103 | #* POSIX Character Classes: |
3018b823 KW |
104 | # Order of the below is important. See ordering comment above. |
105 | POSIXD POSIXD, none 0 S ; Some [[:class:]] under /d; the FLAGS field gives which one | |
106 | POSIXL POSIXD, none 0 S ; Some [[:class:]] under /l; the FLAGS field gives which one | |
107 | POSIXU POSIXD, none 0 S ; Some [[:class:]] under /u; the FLAGS field gives which one | |
3615ea58 | 108 | POSIXA POSIXD, none 0 S ; Some [[:class:]] under /a; the FLAGS field gives which one |
3018b823 KW |
109 | NPOSIXD NPOSIXD, none 0 S ; complement of POSIXD, [[:^class:]] |
110 | NPOSIXL NPOSIXD, none 0 S ; complement of POSIXL, [[:^class:]] | |
111 | NPOSIXU NPOSIXD, none 0 S ; complement of POSIXU, [[:^class:]] | |
9e84774b | 112 | NPOSIXA NPOSIXD, none 0 S ; complement of POSIXA, [[:^class:]] |
3018b823 | 113 | # End of order is important |
693fefec | 114 | |
2448cf39 | 115 | CLUMP CLUMP, no 0 V ; Match any extended grapheme cluster sequence |
d09b2d29 | 116 | |
381b57db | 117 | #* Alternation |
1de06328 | 118 | |
65aa4ca7 FC |
119 | #* BRANCH The set of branches constituting a single choice are |
120 | #* hooked together with their "next" pointers, since | |
121 | #* precedence prevents anything being concatenated to | |
122 | #* any individual branch. The "next" pointer of the last | |
123 | #* BRANCH in a choice points to the thing following the | |
124 | #* whole choice. This is also where the final "next" | |
125 | #* pointer of each individual branch points; each branch | |
126 | #* starts with the operand node of a BRANCH node. | |
127 | #* | |
f9ef50a7 | 128 | BRANCH BRANCH, node 0 V ; Match this alternative, or the next... |
d09b2d29 | 129 | |
65aa4ca7 FC |
130 | #*Literals |
131 | # NOTE: the relative ordering of these types is important do not change it | |
938090ac KW |
132 | # By convention, folding nodes begin with EXACTF; A digit 8 is in the name if |
133 | # and only if it it requires a UTF-8 target string in order to successfully | |
134 | # match. | |
1de06328 | 135 | |
3ace85ea | 136 | EXACT EXACT, str ; Match this string (flags field is the length). |
ae06e581 KW |
137 | |
138 | #* In a long string node, the U32 argument is the length, and is | |
139 | #* immediately followed by the string. | |
140 | LEXACT EXACT, len:str 1; Match this long string (preceded by length; flags unused). | |
58ea1df2 KW |
141 | EXACTL EXACT, str ; Like EXACT, but /l is in effect (used so locale-related warnings can be checked for) |
142 | EXACTF EXACT, str ; Like EXACT, but match using /id rules; (string not UTF-8, ASCII folded; non-ASCII not) | |
143 | EXACTFL EXACT, str ; Like EXACT, but match using /il rules; (string not likely to be folded) | |
144 | EXACTFU EXACT, str ; Like EXACT, but match using /iu rules; (string folded) | |
145 | ||
146 | # The reason MICRO and SHARP S aren't folded in non-UTF8 patterns is because | |
147 | # they would fold to something that requires UTF-8. SHARP S would normally | |
148 | # fold to 'ss', but because of /aa, it instead folds to a pair of LATIN SMALL | |
149 | # LETTER LONG S characters (U+017F) | |
5f162c35 | 150 | EXACTFAA EXACT, str ; Like EXACT, but match using /iaa rules; (string folded except MICRO in non-UTF8 patterns; doesn't contain SHARP S unless UTF-8; folded length <= unfolded) |
f97d9711 KW |
151 | # must immediately follow EXACTFAA |
152 | EXACTFAA_NO_TRIE EXACT, str ; Like EXACTFAA, (string not UTF-8, folded except: MICRO, SHARP S; folded length <= unfolded, not currently trie-able) | |
2f306ab9 KW |
153 | |
154 | # End of important relative ordering. | |
155 | ||
5f162c35 | 156 | EXACTFUP EXACT, str ; Like EXACT, but match using /iu rules; (string not UTF-8, folded except MICRO: hence Problematic) |
aa419ff3 KW |
157 | # In order for a non-UTF-8 EXACTFAA to think the pattern is pre-folded when |
158 | # matching a UTF-8 target string, there would have to be something like an | |
159 | # EXACTFAA_MICRO which would not be considered pre-folded for UTF-8 targets, | |
160 | # since the fold of the MICRO SIGN would not be done, and would be | |
161 | # representable in the UTF-8 target string. | |
162 | ||
58ea1df2 | 163 | EXACTFLU8 EXACT, str ; Like EXACTFU, but use /il, UTF-8, (string is folded, and everything in it is above 255 |
3f2416ae KW |
164 | EXACT_REQ8 EXACT, str ; Like EXACT, but only UTF-8 encoded targets can match |
165 | LEXACT_REQ8 EXACT, len:str 1 ; Like LEXACT, but only UTF-8 encoded targets can match | |
166 | EXACTFU_REQ8 EXACT, str ; Like EXACTFU, but only UTF-8 encoded targets can match | |
efec1f81 | 167 | # One could add EXACTFAA8 and something that has the same effect for /l, |
a9f8c7ac | 168 | # but these would be extremely uncommon |
f6b4b99d | 169 | |
58ea1df2 | 170 | EXACTFU_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) |
8a100c91 | 171 | |
7af55186 KW |
172 | #*New charclass like patterns |
173 | LNBREAK LNBREAK, none ; generic newline pattern | |
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 | ||
381b57db | 189 | #*Do nothing types |
1de06328 | 190 | |
f8abb37e | 191 | NOTHING NOTHING, no ; Match empty string. |
65aa4ca7 | 192 | #*A variant of above which delimits a group, thus stops optimizations |
f8abb37e | 193 | TAIL NOTHING, no ; Match empty string. Can jump here from outside. |
d09b2d29 | 194 | |
381b57db | 195 | #*Loops |
1de06328 | 196 | |
65aa4ca7 | 197 | #* STAR,PLUS '?', and complex '*' and '+', are implemented as |
62e6ef33 | 198 | #* circular BRANCH structures. Simple cases |
65aa4ca7 FC |
199 | #* (one character per match) are implemented with STAR |
200 | #* and PLUS for speed and to minimize recursive plunges. | |
201 | #* | |
f9ef50a7 NC |
202 | STAR STAR, node 0 V ; Match this (simple) thing 0 or more times. |
203 | PLUS PLUS, node 0 V ; Match this (simple) thing 1 or more times. | |
d09b2d29 | 204 | |
f9ef50a7 NC |
205 | CURLY CURLY, sv 2 V ; Match this simple thing {n,m} times. |
206 | CURLYN CURLY, no 2 V ; Capture next-after-this simple thing | |
207 | CURLYM CURLY, no 2 V ; Capture this medium-complex thing {n,m} times. | |
208 | CURLYX CURLY, sv 2 V ; Match this complex thing {n,m} times. | |
d09b2d29 | 209 | |
65aa4ca7 | 210 | #*This terminator creates a loop structure for CURLYX |
f9ef50a7 | 211 | WHILEM WHILEM, no 0 V ; Do curly processing and see if rest matches. |
d09b2d29 | 212 | |
381b57db | 213 | #*Buffer related |
1de06328 | 214 | |
65aa4ca7 | 215 | #*OPEN,CLOSE,GROUPP ...are numbered at compile time. |
f8abb37e | 216 | OPEN OPEN, num 1 ; Mark this point in input as start of #n. |
48e88d42 | 217 | CLOSE CLOSE, num 1 ; Close corresponding OPEN of #n. |
07093db4 KW |
218 | SROPEN SROPEN, none ; Same as OPEN, but for script run |
219 | SRCLOSE SRCLOSE, none ; Close preceding SROPEN | |
d09b2d29 | 220 | |
f9ef50a7 | 221 | REF REF, num 1 V ; Match some already matched string |
912b808c KW |
222 | REFF REF, num 1 V ; Match already matched string, using /di rules. |
223 | REFFL REF, num 1 V ; Match already matched string, using /li rules. | |
781aab5c | 224 | # N?REFF[AU] could have been implemented using the FLAGS field of the |
01f98ec2 KW |
225 | # regnode, but by having a separate node type, we can use the existing switch |
226 | # statement to avoid some tests | |
912b808c KW |
227 | REFFU REF, num 1 V ; Match already matched string, usng /ui. |
228 | REFFA REF, num 1 V ; Match already matched string, using /aai rules. | |
d09b2d29 | 229 | |
65aa4ca7 FC |
230 | #*Named references. Code in regcomp.c assumes that these all are after |
231 | #*the numbered references | |
016b7209 KW |
232 | REFN REF, no-sv 1 V ; Match some already matched string |
233 | REFFN REF, no-sv 1 V ; Match already matched string, using /di rules. | |
234 | REFFLN REF, no-sv 1 V ; Match already matched string, using /li rules. | |
235 | REFFUN REF, num 1 V ; Match already matched string, using /ui rules. | |
236 | REFFAN REF, num 1 V ; Match already matched string, using /aai rules. | |
1de06328 | 237 | |
d3d47aac YO |
238 | #*Support for long RE |
239 | LONGJMP LONGJMP, off 1 . 1 ; Jump far away. | |
240 | BRANCHJ BRANCHJ, off 1 V 1 ; BRANCH with long offset. | |
241 | ||
242 | #*Special Case Regops | |
2abbd513 KW |
243 | IFMATCH 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 |
244 | UNLESSM 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 | |
f9ef50a7 | 245 | SUSPEND BRANCHJ, off 1 V 1 ; "Independent" sub-RE. |
65aa4ca7 | 246 | IFTHEN BRANCHJ, off 1 V 1 ; Switch, should be preceded by switcher. |
f8abb37e | 247 | GROUPP GROUPP, num 1 ; Whether the group matched. |
d09b2d29 | 248 | |
381b57db | 249 | #*The heavy worker |
1de06328 | 250 | |
13f27704 | 251 | EVAL EVAL, evl/flags 2L ; Execute some Perl code. |
d09b2d29 | 252 | |
381b57db | 253 | #*Modifiers |
1de06328 | 254 | |
f8abb37e NC |
255 | MINMOD MINMOD, no ; Next operator is not greedy. |
256 | LOGICAL LOGICAL, no ; Next opcode should set the flag only. | |
d09b2d29 | 257 | |
65aa4ca7 | 258 | #*This is not used yet |
f9ef50a7 | 259 | RENUM BRANCHJ, off 1 . 1 ; Group with independently numbered parens. |
d09b2d29 | 260 | |
381b57db | 261 | #*Regex Subroutines |
f8abb37e | 262 | GOSUB GOSUB, num/ofs 2L ; recurse to paren arg1 at (signed) ofs arg2 |
03363afd | 263 | |
381b57db | 264 | #*Special conditionals |
016b7209 | 265 | GROUPPN GROUPPN, no-sv 1 ; Whether the group matched. |
f8abb37e NC |
266 | INSUBP INSUBP, num 1 ; Whether we are in a specific recurse. |
267 | DEFINEP DEFINEP, none 1 ; Never execute directly. | |
0a4db386 | 268 | |
486ec47a | 269 | #*Backtracking Verbs |
f8abb37e | 270 | ENDLIKE ENDLIKE, none ; Used only for the type field of verbs |
fee50582 YO |
271 | OPFAIL ENDLIKE, no-sv 1 ; Same as (?!), but with verb arg |
272 | ACCEPT ENDLIKE, no-sv/num 2L ; Accepts the current matched string, with verbar | |
5d458dd8 YO |
273 | |
274 | #*Verbs With Arguments | |
f8abb37e NC |
275 | VERB VERB, no-sv 1 ; Used only for the type field of verbs |
276 | PRUNE VERB, no-sv 1 ; Pattern fails at this startpoint if no-backtracking through this | |
277 | MARKPOINT VERB, no-sv 1 ; Push the current location for rollback by cut. | |
278 | SKIP VERB, no-sv 1 ; On failure skip forward (to the mark) before retrying | |
279 | COMMIT VERB, no-sv 1 ; Pattern fails outright if backtracking through this | |
280 | CUTGROUP VERB, no-sv 1 ; On failure go to the next alternation in the group | |
e2e6a0f1 | 281 | |
ee9b8eae | 282 | #*Control what to keep in $&. |
f8abb37e | 283 | KEEPS KEEPS, no ; $& begins here. |
ee9b8eae | 284 | |
7af55186 KW |
285 | # NEW STUFF SOMEWHERE ABOVE THIS LINE. Stuff that regexec.c: find_byclass() |
286 | # and regrepeat() use should go way above, near LNBREAK to allow a more compact | |
287 | # jump table to be generated for their switch() statements | |
1de06328 | 288 | |
03363afd YO |
289 | ################################################################################ |
290 | ||
7f69552c | 291 | #*SPECIAL REGOPS |
1de06328 | 292 | |
65aa4ca7 FC |
293 | #* This is not really a node, but an optimized away piece of a "long" |
294 | #* node. To simplify debugging output, we mark it as if it were a node | |
f8abb37e | 295 | OPTIMIZED NOTHING, off ; Placeholder for dump. |
1de06328 | 296 | |
65aa4ca7 FC |
297 | #* Special opcode with the property that no opcode in a compiled program |
298 | #* will ever be of this type. Thus it can be used as a flag value that | |
299 | #* no other opcode has been seen. END is used similarly, in that an END | |
300 | #* node cant be optimized. So END implies "unoptimizable" and PSEUDO | |
301 | #* mean "not seen anything to optimize yet". | |
f8abb37e | 302 | PSEUDO PSEUDO, off ; Pseudo opcode for internal use. |
1de06328 | 303 | |
86451f01 KW |
304 | REGEX_SET REGEX_SET, depth p S ; Regex set, temporary node used in pre-optimization compilation |
305 | ||
03363afd YO |
306 | ------------------------------------------------------------------------------- |
307 | # Format for second section: | |
65aa4ca7 | 308 | # REGOP \t typelist [ \t typelist] |
03363afd YO |
309 | # typelist= namelist |
310 | # = namelist:FAIL | |
311 | # = name:count | |
312 | ||
313 | # Anything below is a state | |
314 | # | |
315 | # | |
f8abb37e | 316 | TRIE next:FAIL |
4ee16520 | 317 | EVAL B,postponed_AB:FAIL |
f8abb37e NC |
318 | CURLYX end:FAIL |
319 | WHILEM A_pre,A_min,A_max,B_min,B_max:FAIL | |
320 | BRANCH next:FAIL | |
321 | CURLYM A,B:FAIL | |
322 | IFMATCH A:FAIL | |
21cbe009 | 323 | CURLY B_min,B_max:FAIL |
f8abb37e NC |
324 | COMMIT next:FAIL |
325 | MARKPOINT next:FAIL | |
326 | SKIP next:FAIL | |
327 | CUTGROUP next:FAIL | |
328 | KEEPS next:FAIL |