# Note that the order in this file is important.
#
# Format for first section:
-# NAME \s+ TYPE, arg-description [num-args] [flags] [longjump-len] ; DESCRIPTION
-# flag <S> means is REGNODE_SIMPLE; flag <V> means is REGNODE_VARIES
+# NAME \s+ TYPE, arg-description [num-args] [flags] [longjump] ; DESCRIPTION
+# flag <S> means is REGNODE_SIMPLE; flag <V> means is REGNODE_VARIES; <.> is
+# a placeholder
+# longjump is 1 if the (first) argument holds the next offset.
#
#
# run perl regen.pl after editing this file
#* [Special] alternatives:
REG_ANY REG_ANY, no 0 S ; Match any one character (except newline).
SANY REG_ANY, no 0 S ; Match any one character.
-ANYOF ANYOF, sv 1 S ; Match character in (or not in) this class, single char match only
-ANYOFL ANYOF, sv 1 S ; Like ANYOF, but /l is in effect
+ANYOF ANYOF, sv charclass S ; Match character in (or not in) this class, single char match only
+ANYOFD ANYOF, sv charclass S ; Like ANYOF, but /d is in effect
+ANYOFL ANYOF, sv charclass S ; Like ANYOF, but /l is in effect
+ANYOFPOSIXL ANYOF, sv charclass_posixl S ; Like ANYOFL, but matches [[:posix:]] classes
+ANYOFM ANYOFM byte 1 S ; Like ANYOF, but matches an invariant byte as determined by the mask and arg
+NANYOFM ANYOFM byte 1 S ; complement of ANYOFM
#* POSIX Character Classes:
# Order of the below is important. See ordering comment above.
NPOSIXA NPOSIXD, none 0 S ; complement of POSIXA, [[:^class:]]
# End of order is important
+ASCII ASCII, none 0 S ; [[:ascii:]]
+NASCII ASCII, none 0 S ; [[:^ascii:]]
+
CLUMP CLUMP, no 0 V ; Match any extended grapheme cluster sequence
#* Alternation
# NOTE: the relative ordering of these types is important do not change it
EXACT EXACT, str ; Match this string (preceded by length).
-EXACTL EXACT, str ; Like EXACT, but /l is in effect.
+EXACTL EXACT, str ; Like EXACT, but /l is in effect (used so locale-related warnings can be checked for).
EXACTF EXACT, str ; Match this non-UTF-8 string (not guaranteed to be folded) using /id rules (w/len).
EXACTFL EXACT, str ; Match this string (not guaranteed to be folded) using /il rules (w/len).
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).
-EXACTFA EXACT, str ; Match this string (not guaranteed to be folded) using /iaa rules (w/len).
+EXACTFAA EXACT, str ; Match this string (not guaranteed to be folded) using /iaa rules (w/len).
# End of important relative ordering.
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).
-EXACTFLU8 EXACT, str ; Rare cirucmstances: like EXACTFU, but is under /l, UTF-8, folded, and everything in it is above 255.
-EXACTFA_NO_TRIE EXACT, str ; Match this string (which is not trie-able; not guaranteed to be folded) using /iaa rules (w/len).
+EXACTFLU8 EXACT, str ; Rare circumstances: like EXACTFU, but is under /l, UTF-8, folded, and everything in it is above 255.
+EXACTFAA_NO_TRIE EXACT, str ; Match this string (which is not trie-able; not guaranteed to be folded) using /iaa rules (w/len).
+
+EXACT_ONLY8 EXACT, str ; Like EXACT, but no strings that aren't in UTF-8 can match
+EXACTFU_ONLY8 EXACT, str ; Like EXACTFU, but no strings that aren't in UTF-8 can match
+# One could add EXACTFAA8 and and something that has the same effect for /l,
+# but these would be extremely uncommon
#*Do nothing types
#*OPEN,CLOSE,GROUPP ...are numbered at compile time.
OPEN OPEN, num 1 ; Mark this point in input as start of #n.
-CLOSE CLOSE, num 1 ; Analogous to OPEN.
+CLOSE CLOSE, num 1 ; Close corresponding OPEN of #n.
+SROPEN SROPEN, none ; Same as OPEN, but for script run
+SRCLOSE SRCLOSE, none ; Close preceding SROPEN
REF REF, num 1 V ; Match some already matched string
REFF REF, num 1 V ; Match already matched string, folded using native charset rules for non-utf8
BRANCHJ BRANCHJ, off 1 V 1 ; BRANCH with long offset.
#*Special Case Regops
-IFMATCH BRANCHJ, off 1 . 2 ; Succeeds if the following matches.
-UNLESSM BRANCHJ, off 1 . 2 ; Fails if the following matches.
+IFMATCH BRANCHJ, off 1 . 1 ; Succeeds if the following matches.
+UNLESSM BRANCHJ, off 1 . 1 ; Fails if the following matches.
SUSPEND BRANCHJ, off 1 V 1 ; "Independent" sub-RE.
IFTHEN BRANCHJ, off 1 V 1 ; Switch, should be preceded by switcher.
GROUPP GROUPP, num 1 ; Whether the group matched.
#*Regex Subroutines
GOSUB GOSUB, num/ofs 2L ; recurse to paren arg1 at (signed) ofs arg2
-GOSTART GOSTART, no ; recurse to start of pattern
#*Special conditionals
NGROUPP NGROUPP, no-sv 1 ; Whether the group matched.
#*Backtracking Verbs
ENDLIKE ENDLIKE, none ; Used only for the type field of verbs
-OPFAIL ENDLIKE, none ; Same as (?!)
-ACCEPT ENDLIKE, parno 1 ; Accepts the current matched string.
-
+OPFAIL ENDLIKE, no-sv 1 ; Same as (?!), but with verb arg
+ACCEPT ENDLIKE, no-sv/num 2L ; Accepts the current matched string, with verbar
#*Verbs With Arguments
VERB VERB, no-sv 1 ; Used only for the type field of verbs
#
#
TRIE next:FAIL
-EVAL AB:FAIL
+EVAL B,postponed_AB:FAIL
CURLYX end:FAIL
WHILEM A_pre,A_min,A_max,B_min,B_max:FAIL
BRANCH next:FAIL
CURLYM A,B:FAIL
IFMATCH A:FAIL
-CURLY B_min_known,B_min,B_max:FAIL
+CURLY B_min,B_max:FAIL
COMMIT next:FAIL
MARKPOINT next:FAIL
SKIP next:FAIL