Commit | Line | Data |
03363afd |
1 | # regcomp.sym |
2 | # |
3 | # File has two sections, divided by a line of dashes '-'. |
4 | # |
5 | # Empty rows after #-comment are removed from input are ignored |
6 | # |
7 | # First section is for regops, second sectionis for regmatch-states |
8 | # |
3dab1dad |
9 | # Note that the order in this file is important. |
10 | # |
03363afd |
11 | # Format for first section: |
f8abb37e |
12 | # NAME \s+ TYPE, arg-description [num-args] [longjump-len] ; DESCRIPTION |
03363afd |
13 | # |
3dab1dad |
14 | # |
c476f425 |
15 | # run perl regen.pl after editing this file |
3dab1dad |
16 | |
03363afd |
17 | |
18 | |
1de06328 |
19 | #* Exit points (0,1) |
20 | |
f8abb37e |
21 | END END, no ; End of program. |
22 | SUCCEED END, no ; Return from a subroutine, basically. |
d09b2d29 |
23 | |
1de06328 |
24 | #* Anchors: (2..13) |
25 | |
f8abb37e |
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. |
d09b2d29 |
38 | |
1de06328 |
39 | #* [Special] alternatives: (14..30) |
40 | |
f8abb37e |
41 | REG_ANY REG_ANY, no ; Match any one character (except newline). |
42 | SANY REG_ANY, no ; Match any one character. |
43 | CANY REG_ANY, no ; Match any one byte. |
44 | ANYOF ANYOF, sv ; Match character in (or not in) this class. |
45 | ALNUM ALNUM, no ; Match any alphanumeric character |
46 | ALNUML ALNUM, no ; Match any alphanumeric char in locale |
47 | NALNUM NALNUM, no ; Match any non-alphanumeric character |
48 | NALNUML NALNUM, no ; Match any non-alphanumeric char in locale |
49 | SPACE SPACE, no ; Match any whitespace character |
50 | SPACEL SPACE, no ; Match any whitespace char in locale |
51 | NSPACE NSPACE, no ; Match any non-whitespace character |
52 | NSPACEL NSPACE, no ; Match any non-whitespace char in locale |
53 | DIGIT DIGIT, no ; Match any numeric character |
54 | DIGITL DIGIT, no ; Match any numeric character in locale |
55 | NDIGIT NDIGIT, no ; Match any non-numeric character |
56 | NDIGITL NDIGIT, no ; Match any non-numeric character in locale |
57 | CLUMP CLUMP, no ; Match any combining character sequence |
d09b2d29 |
58 | |
1de06328 |
59 | #* Alternation (31) |
60 | |
f8abb37e |
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. |
d09b2d29 |
68 | # |
f8abb37e |
69 | BRANCH BRANCH, node ; Match this alternative, or the next... |
d09b2d29 |
70 | |
1de06328 |
71 | #*Back pointer (32) |
72 | |
f8abb37e |
73 | # BACK Normal "next" pointers all implicitly point forward; BACK |
74 | # exists to make loop structures possible. |
d09b2d29 |
75 | # not used |
f8abb37e |
76 | BACK BACK, no ; Match "", "next" ptr points backward. |
d09b2d29 |
77 | |
1de06328 |
78 | #*Literals (33..35) |
79 | |
f8abb37e |
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). |
d09b2d29 |
83 | |
1de06328 |
84 | #*Do nothing types (36..37) |
85 | |
f8abb37e |
86 | NOTHING NOTHING, no ; Match empty string. |
d09b2d29 |
87 | # A variant of above which delimits a group, thus stops optimizations |
f8abb37e |
88 | TAIL NOTHING, no ; Match empty string. Can jump here from outside. |
d09b2d29 |
89 | |
1de06328 |
90 | #*Loops (38..44) |
91 | |
f8abb37e |
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. |
d09b2d29 |
96 | # |
f8abb37e |
97 | STAR STAR, node ; Match this (simple) thing 0 or more times. |
98 | PLUS PLUS, node ; Match this (simple) thing 1 or more times. |
d09b2d29 |
99 | |
f8abb37e |
100 | CURLY CURLY, sv 2 ; Match this simple thing {n,m} times. |
101 | CURLYN CURLY, no 2 ; Capture next-after-this simple thing |
102 | CURLYM CURLY, no 2 ; Capture this medium-complex thing {n,m} times. |
103 | CURLYX CURLY, sv 2 ; Match this complex thing {n,m} times. |
d09b2d29 |
104 | |
105 | # This terminator creates a loop structure for CURLYX |
f8abb37e |
106 | WHILEM WHILEM, no ; Do curly processing and see if rest matches. |
d09b2d29 |
107 | |
1de06328 |
108 | #*Buffer related (45..49) |
109 | |
f8abb37e |
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. |
d09b2d29 |
113 | |
f8abb37e |
114 | REF REF, num 1 ; Match some already matched string |
115 | REFF REF, num 1 ; Match already matched string, folded |
116 | REFFL REF, num 1 ; Match already matched string, folded in loc. |
d09b2d29 |
117 | |
1de06328 |
118 | #*Grouping assertions (50..54) |
119 | |
f8abb37e |
120 | IFMATCH BRANCHJ, off 1 2 ; Succeeds if the following matches. |
121 | UNLESSM BRANCHJ, off 1 2 ; Fails if the following matches. |
122 | SUSPEND BRANCHJ, off 1 1 ; "Independent" sub-RE. |
123 | IFTHEN BRANCHJ, off 1 1 ; Switch, should be preceeded by switcher . |
124 | GROUPP GROUPP, num 1 ; Whether the group matched. |
d09b2d29 |
125 | |
1de06328 |
126 | #*Support for long RE (55..56) |
127 | |
f8abb37e |
128 | LONGJMP LONGJMP, off 1 1 ; Jump far away. |
129 | BRANCHJ BRANCHJ, off 1 1 ; BRANCH with long offset. |
d09b2d29 |
130 | |
5014f7da |
131 | #*The heavy worker (57) |
1de06328 |
132 | |
f8abb37e |
133 | EVAL EVAL, evl 1 ; Execute some Perl code. |
d09b2d29 |
134 | |
5014f7da |
135 | #*Modifiers (58..59) |
1de06328 |
136 | |
f8abb37e |
137 | MINMOD MINMOD, no ; Next operator is not greedy. |
138 | LOGICAL LOGICAL, no ; Next opcode should set the flag only. |
d09b2d29 |
139 | |
5014f7da |
140 | # This is not used yet (60) |
f8abb37e |
141 | RENUM BRANCHJ, off 1 1 ; Group with independently numbered parens. |
d09b2d29 |
142 | |
5014f7da |
143 | #*Trie Related (61..62) |
1de06328 |
144 | |
145 | # Behave the same as A|LIST|OF|WORDS would. The '..C' variants have |
146 | # inline charclass data (ascii only), the 'C' store it in the structure. |
147 | # NOTE: the relative order of the TRIE-like regops is signifigant |
ce5e9471 |
148 | |
f8abb37e |
149 | TRIE TRIE, trie 1 ; Match many EXACT(FL?)? at once. flags==type |
150 | TRIEC TRIE,trie charclass ; Same as TRIE, but with embedded charclass data |
3dab1dad |
151 | |
1de06328 |
152 | # For start classes, contains an added fail table. |
f8abb37e |
153 | AHOCORASICK TRIE, trie 1 ; Aho Corasick stclass. flags==type |
154 | AHOCORASICKC TRIE,trie charclass ; Same as AHOCORASICK, but with embedded charclass data |
1de06328 |
155 | |
1a147d38 |
156 | #*Regex Subroutines (65..66) |
f8abb37e |
157 | GOSUB GOSUB, num/ofs 2L ; recurse to paren arg1 at (signed) ofs arg2 |
158 | GOSTART GOSTART, no ; recurse to start of pattern |
03363afd |
159 | |
81714fb9 |
160 | #*Named references (67..69) |
f8abb37e |
161 | NREF REF, no-sv 1 ; Match some already matched string |
162 | NREFF REF, no-sv 1 ; Match already matched string, folded |
163 | NREFFL REF, no-sv 1 ; Match already matched string, folded in loc. |
81714fb9 |
164 | |
165 | |
7f69552c |
166 | #*Special conditionals (70..72) |
f8abb37e |
167 | NGROUPP NGROUPP, no-sv 1 ; Whether the group matched. |
168 | INSUBP INSUBP, num 1 ; Whether we are in a specific recurse. |
169 | DEFINEP DEFINEP, none 1 ; Never execute directly. |
0a4db386 |
170 | |
5d458dd8 |
171 | #*Bactracking Verbs |
f8abb37e |
172 | ENDLIKE ENDLIKE, none ; Used only for the type field of verbs |
173 | OPFAIL ENDLIKE, none ; Same as (?!) |
174 | ACCEPT ENDLIKE, parno 1 ; Accepts the current matched string. |
5d458dd8 |
175 | |
176 | |
177 | #*Verbs With Arguments |
f8abb37e |
178 | VERB VERB, no-sv 1 ; Used only for the type field of verbs |
179 | PRUNE VERB, no-sv 1 ; Pattern fails at this startpoint if no-backtracking through this |
180 | MARKPOINT VERB, no-sv 1 ; Push the current location for rollback by cut. |
181 | SKIP VERB, no-sv 1 ; On failure skip forward (to the mark) before retrying |
182 | COMMIT VERB, no-sv 1 ; Pattern fails outright if backtracking through this |
183 | CUTGROUP VERB, no-sv 1 ; On failure go to the next alternation in the group |
e2e6a0f1 |
184 | |
ee9b8eae |
185 | #*Control what to keep in $&. |
f8abb37e |
186 | KEEPS KEEPS, no ; $& begins here. |
ee9b8eae |
187 | |
e1d1eefb |
188 | #*New charclass like patterns |
f8abb37e |
189 | LNBREAK LNBREAK, none ; generic newline pattern |
190 | VERTWS VERTWS, none ; vertical whitespace (Perl 6) |
191 | NVERTWS NVERTWS, none ; not vertical whitespace (Perl 6) |
192 | HORIZWS HORIZWS, none ; horizontal whitespace (Perl 6) |
193 | NHORIZWS NHORIZWS, none ; not horizontal whitespace (Perl 6) |
e1d1eefb |
194 | |
f8abb37e |
195 | FOLDCHAR FOLDCHAR, codepoint 1 ; codepoint with tricky case folding properties. |
32e6a07c |
196 | |
e1d1eefb |
197 | # NEW STUFF ABOVE THIS LINE |
1de06328 |
198 | |
03363afd |
199 | ################################################################################ |
200 | |
7f69552c |
201 | #*SPECIAL REGOPS |
1de06328 |
202 | |
203 | # This is not really a node, but an optimized away piece of a "long" node. |
204 | # To simplify debugging output, we mark it as if it were a node |
f8abb37e |
205 | OPTIMIZED NOTHING, off ; Placeholder for dump. |
1de06328 |
206 | |
3dab1dad |
207 | # Special opcode with the property that no opcode in a compiled program |
208 | # will ever be of this type. Thus it can be used as a flag value that |
209 | # no other opcode has been seen. END is used similarly, in that an END |
210 | # node cant be optimized. So END implies "unoptimizable" and PSEUDO mean |
211 | # "not seen anything to optimize yet". |
f8abb37e |
212 | PSEUDO PSEUDO, off ; Pseudo opcode for internal use. |
1de06328 |
213 | |
03363afd |
214 | ------------------------------------------------------------------------------- |
215 | # Format for second section: |
216 | # REGOP \t typelist [ \t typelist] [# Comment] |
217 | # typelist= namelist |
218 | # = namelist:FAIL |
219 | # = name:count |
220 | |
221 | # Anything below is a state |
222 | # |
223 | # |
f8abb37e |
224 | TRIE next:FAIL |
225 | EVAL AB:FAIL |
226 | CURLYX end:FAIL |
227 | WHILEM A_pre,A_min,A_max,B_min,B_max:FAIL |
228 | BRANCH next:FAIL |
229 | CURLYM A,B:FAIL |
230 | IFMATCH A:FAIL |
231 | CURLY B_min_known,B_min,B_max:FAIL |
232 | COMMIT next:FAIL |
233 | MARKPOINT next:FAIL |
234 | SKIP next:FAIL |
235 | CUTGROUP next:FAIL |
236 | KEEPS next:FAIL |