# 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
END END, no ; End of program.
SUCCEED END, no ; Return from a subroutine, basically.
-#* Anchors:
+#* Line Start Anchors:
+#Note flags field for SBOL indicates if it is a /^/ or a /\A/
+SBOL BOL, no ; Match "" at beginning of line: /^/, /\A/
+MBOL BOL, no ; Same, assuming multiline: /^/m
-BOL BOL, no ; Match "" at beginning of line.
-MBOL BOL, no ; Same, assuming multiline.
-SBOL BOL, no ; Same, assuming singleline.
-EOS EOL, no ; Match "" at end of string.
-EOL EOL, no ; Match "" at end of line.
-MEOL EOL, no ; Same, assuming multiline.
-SEOL EOL, no ; Same, assuming singleline.
+#* Line End Anchors:
+SEOL EOL, no ; Match "" at end of line: /$/
+MEOL EOL, no ; Same, assuming multiline: /$/m
+EOS EOL, no ; Match "" at end of string: /\z/
+
+#* Match Start Anchors:
+GPOS GPOS, no ; Matches where last m//g left off.
+
+#* Word Boundary Opcodes:
# The regops that have varieties that vary depending on the character set regex
# modifiers have to ordered thusly: /d, /l, /u, /a, /aa. This is because code
# in regcomp.c uses the enum value of the modifier as an offset from the /d
# version. The complements must come after the non-complements.
# BOUND, POSIX and their complements are affected, as well as EXACTF.
-BOUND BOUND, no ; Match "" at any word boundary using native charset semantics for non-utf8
-BOUNDL BOUND, no ; Match "" at any locale word boundary
-BOUNDU BOUND, no ; Match "" at any word boundary using Unicode semantics
-BOUNDA BOUND, no ; Match "" at any word boundary using ASCII semantics
+BOUND BOUND, no ; Like BOUNDA for non-utf8, otherwise match "" between any Unicode \w\W or \W\w
+BOUNDL BOUND, no ; Like BOUND/BOUNDU, but \w and \W are defined by current locale
+BOUNDU BOUND, no ; Match "" at any boundary of a given type using Unicode rules
+BOUNDA BOUND, no ; Match "" at any boundary between \w\W or \W\w, where \w is [_a-zA-Z0-9]
# All NBOUND nodes are required by code in regexec.c to be greater than all BOUND ones
-NBOUND NBOUND, no ; Match "" at any word non-boundary using native charset semantics for non-utf8
-NBOUNDL NBOUND, no ; Match "" at any locale word non-boundary
-NBOUNDU NBOUND, no ; Match "" at any word non-boundary using Unicode semantics
-NBOUNDA NBOUND, no ; Match "" at any word non-boundary using ASCII semantics
-GPOS GPOS, no ; Matches where last m//g left off.
+NBOUND NBOUND, no ; Like NBOUNDA for non-utf8, otherwise match "" between any Unicode \w\w or \W\W
+NBOUNDL NBOUND, no ; Like NBOUND/NBOUNDU, but \w and \W are defined by current locale
+NBOUNDU NBOUND, no ; Match "" at any non-boundary of a given type using using Unicode rules
+NBOUNDA NBOUND, no ; Match "" betweeen any \w\w or \W\W, where \w is [_a-zA-Z0-9]
#* [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.
-CANY REG_ANY, no 0 S ; Match any one byte.
-ANYOF ANYOF, sv 0 S ; Match character in (or not in) this class, single char match only
-
+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.
POSIXD POSIXD, none 0 S ; Some [[:class:]] under /d; the FLAGS field gives which one
POSIXL POSIXD, none 0 S ; Some [[:class:]] under /l; the FLAGS field gives which one
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
#*
BRANCH BRANCH, node 0 V ; Match this alternative, or the next...
-#*Back pointer
-
-#* BACK Normal "next" pointers all implicitly point forward;
-#* BACK exists to make loop structures possible.
-#* not used
-BACK BACK, no 0 V ; Match "", "next" ptr points backward.
-
#*Literals
# 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 (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).
-EXACTFU_TRICKYFOLD EXACT, str ; Match this folded UTF-8 string using /iu rules
+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
#*Loops
#* STAR,PLUS '?', and complex '*' and '+', are implemented as
-#* circular BRANCH structures using BACK. Simple cases
+#* circular BRANCH structures. Simple cases
#* (one character per match) are implemented with STAR
#* and PLUS for speed and to minimize recursive plunges.
#*
#*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 semantics for non-utf8
+REFF REF, num 1 V ; Match already matched string, folded using native charset rules for non-utf8
REFFL REF, num 1 V ; Match already matched string, folded in loc.
# N?REFF[AU] could have been implemented using the FLAGS field of the
# regnode, but by having a separate node type, we can use the existing switch
# statement to avoid some tests
-REFFU REF, num 1 V ; Match already matched string, folded using unicode semantics for non-utf8
-REFFA REF, num 1 V ; Match already matched string, folded using unicode semantics for non-utf8, no mixing ASCII, non-ASCII
+REFFU REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8
+REFFA REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII
#*Named references. Code in regcomp.c assumes that these all are after
#*the numbered references
NREF REF, no-sv 1 V ; Match some already matched string
-NREFF REF, no-sv 1 V ; Match already matched string, folded using native charset semantics for non-utf8
+NREFF REF, no-sv 1 V ; Match already matched string, folded using native charset rules for non-utf8
NREFFL REF, no-sv 1 V ; Match already matched string, folded in loc.
-NREFFU REF, num 1 V ; Match already matched string, folded using unicode semantics for non-utf8
-NREFFA REF, num 1 V ; Match already matched string, folded using unicode semantics for non-utf8, no mixing ASCII, non-ASCII
+NREFFU REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8
+NREFFA REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII
+
+#*Support for long RE
+LONGJMP LONGJMP, off 1 . 1 ; Jump far away.
+BRANCHJ BRANCHJ, off 1 V 1 ; BRANCH with long offset.
-IFMATCH BRANCHJ, off 1 . 2 ; Succeeds if the following matches.
-UNLESSM BRANCHJ, off 1 . 2 ; Fails if the following matches.
+#*Special Case Regops
+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.
-#*Support for long RE
-
-LONGJMP LONGJMP, off 1 . 1 ; Jump far away.
-BRANCHJ BRANCHJ, off 1 V 1 ; BRANCH with long offset.
#*The heavy worker
-EVAL EVAL, evl 1 ; Execute some Perl code.
+EVAL EVAL, evl/flags 2L ; Execute some Perl code.
#*Modifiers
#*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