#
# File has two sections, divided by a line of dashes '-'.
#
-# Empty rows after #-comment are removed from input are ignored
+# Lines beginning with # are ignored, except for those that start with #*
+# which are included in pod/perldebguts.pod. # within a line may be part
+# of a description.
#
-# First section is for regops, second sectionis for regmatch-states
+# First section is for regops, second section is for regmatch-states
#
# Note that the order in this file is important.
#
# Format for first section:
-# NAME \s+ TYPE, arg-description [flags] [num-args] [longjump-len] ; DESCRIPTION
+# 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
-#* Exit points (0,1)
+#* Exit points
END END, no ; End of program.
SUCCEED END, no ; Return from a subroutine, basically.
-#* Anchors: (2..13)
-
-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.
-BOUND BOUND, no ; Match "" at any word boundary
-BOUNDL BOUND, no ; Match "" at any word boundary
-NBOUND NBOUND, no ; Match "" at any word non-boundary
-NBOUNDL NBOUND, no ; Match "" at any word non-boundary
-GPOS GPOS, no ; Matches where last m//g left off.
+#* 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
+
+#* 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/
-#* [Special] alternatives: (14..30)
+#* 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 ; 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 /u 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 ; 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 /u 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.
-ALNUM ALNUM, no 0 S ; Match any alphanumeric character
-ALNUML ALNUM, no 0 S ; Match any alphanumeric char in locale
-NALNUM NALNUM, no 0 S ; Match any non-alphanumeric character
-NALNUML NALNUM, no 0 S ; Match any non-alphanumeric char in locale
-SPACE SPACE, no 0 S ; Match any whitespace character
-SPACEL SPACE, no 0 S ; Match any whitespace char in locale
-NSPACE NSPACE, no 0 S ; Match any non-whitespace character
-NSPACEL NSPACE, no 0 S ; Match any non-whitespace char in locale
-DIGIT DIGIT, no 0 S ; Match any numeric character
-DIGITL DIGIT, no ; Match any numeric character in locale
-NDIGIT NDIGIT, no 0 S ; Match any non-numeric character
-NDIGITL NDIGIT, no ; Match any non-numeric character in locale
-CLUMP CLUMP, no 0 V ; Match any extended grapheme cluster sequence
+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
+ANYOFH ANYOF, sv 1 S ; Like ANYOF, but only has "High" matches, none in the bitmap;
+ANYOFHb ANYOF, sv 1 S ; Like ANYOFH, but all matches share the same first byte, the repurposed flags field contains it
+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
+POSIXU POSIXD, none 0 S ; Some [[:class:]] under /u; the FLAGS field gives which one
+POSIXA POSIXD, none 0 S ; Some [[:class:]] under /a; the FLAGS field gives which one
+NPOSIXD NPOSIXD, none 0 S ; complement of POSIXD, [[:^class:]]
+NPOSIXL NPOSIXD, none 0 S ; complement of POSIXL, [[:^class:]]
+NPOSIXU NPOSIXD, none 0 S ; complement of POSIXU, [[:^class:]]
+NPOSIXA NPOSIXD, none 0 S ; complement of POSIXA, [[:^class:]]
+# End of order is important
-#* Alternation (31)
+CLUMP CLUMP, no 0 V ; Match any extended grapheme cluster sequence
-# BRANCH The set of branches constituting a single choice are hooked
-# together with their "next" pointers, since precedence prevents
-# anything being concatenated to any individual branch. The
-# "next" pointer of the last BRANCH in a choice points to the
-# thing following the whole choice. This is also where the
-# final "next" pointer of each individual branch points; each
-# branch starts with the operand node of a BRANCH node.
-#
+#* Alternation
+
+#* BRANCH The set of branches constituting a single choice are
+#* hooked together with their "next" pointers, since
+#* precedence prevents anything being concatenated to
+#* any individual branch. The "next" pointer of the last
+#* BRANCH in a choice points to the thing following the
+#* whole choice. This is also where the final "next"
+#* pointer of each individual branch points; each branch
+#* starts with the operand node of a BRANCH node.
+#*
BRANCH BRANCH, node 0 V ; Match this alternative, or the next...
-#*Back pointer (32)
+#*Literals
+# NOTE: the relative ordering of these types is important do not change it
-# 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.
+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 string using /id rules (w/len); (string not UTF-8, not guaranteed to be folded).
+EXACTFL EXACT, str ; Match this string using /il rules (w/len); (string not guaranteed to be folded).
+EXACTFU EXACT, str ; Match this string using /iu rules (w/len); (string folded iff in UTF-8; non-UTF8 folded length <= unfolded).
+EXACTFAA EXACT, str ; Match this string using /iaa rules (w/len) (string folded iff in UTF-8; non-UTF8 folded length <= unfolded).
-#*Literals (33..35)
+# End of important relative ordering.
-EXACT EXACT, str ; Match this string (preceded by length).
-EXACTF EXACT, str ; Match this string, folded, native charset semantics for non-utf8 (prec. by length).
-EXACTFL EXACT, str ; Match this string, folded in locale (w/len).
+EXACTFUP EXACT, str ; Match this string using /iu rules (w/len); (string not UTF-8, not guaranteed to be folded; and its Problematic).
+# In order for a non-UTF-8 EXACTFAA to think the pattern is pre-folded when
+# matching a UTF-8 target string, there would have to be something like an
+# EXACTFAA_MICRO which would not be considered pre-folded for UTF-8 targets,
+# since the fold of the MICRO SIGN would not be done, and would be
+# representable in the UTF-8 target string.
+
+EXACTFLU8 EXACT, str ; Like EXACTFU, but use /il, UTF-8, folded, and everything in it is above 255.
+EXACTFAA_NO_TRIE EXACT, str ; Match this string using /iaa rules (w/len) (string not UTF-8, not guaranteed to be folded, not currently trie-able).
+
+
+EXACT_ONLY8 EXACT, str ; Like EXACT, but only UTF-8 encoded targets can match
+EXACTFU_ONLY8 EXACT, str ; Like EXACTFU, but only UTF-8 encoded targets can match
+# One could add EXACTFAA8 and something that has the same effect for /l,
+# but these would be extremely uncommon
+
+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).
-#*Do nothing types (36..37)
+#*Do nothing types
NOTHING NOTHING, no ; Match empty string.
-# A variant of above which delimits a group, thus stops optimizations
+#*A variant of above which delimits a group, thus stops optimizations
TAIL NOTHING, no ; Match empty string. Can jump here from outside.
-#*Loops (38..44)
+#*Loops
-# STAR,PLUS '?', and complex '*' and '+', are implemented as circular
-# BRANCH structures using BACK. Simple cases (one character
-# per match) are implemented with STAR and PLUS for speed
-# and to minimize recursive plunges.
-#
+#* STAR,PLUS '?', and complex '*' and '+', are implemented as
+#* circular BRANCH structures. Simple cases
+#* (one character per match) are implemented with STAR
+#* and PLUS for speed and to minimize recursive plunges.
+#*
STAR STAR, node 0 V ; Match this (simple) thing 0 or more times.
PLUS PLUS, node 0 V ; Match this (simple) thing 1 or more times.
CURLYM CURLY, no 2 V ; Capture this medium-complex thing {n,m} times.
CURLYX CURLY, sv 2 V ; Match this complex thing {n,m} times.
-# This terminator creates a loop structure for CURLYX
+#*This terminator creates a loop structure for CURLYX
WHILEM WHILEM, no 0 V ; Do curly processing and see if rest matches.
-#*Buffer related (45..49)
+#*Buffer related
-# OPEN,CLOSE,GROUPP ...are numbered at compile time.
+#*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
-REFFL REF, num 1 V ; Match already matched string, folded in loc.
-
+REFF REF, num 1 V ; Match already matched string, using /di rules.
+REFFL REF, num 1 V ; Match already matched string, using /li rules.
+# 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, usng /ui.
+REFFA REF, num 1 V ; Match already matched string, using /aai rules.
+
+#*Named references. Code in regcomp.c assumes that these all are after
+#*the numbered references
+REFN REF, no-sv 1 V ; Match some already matched string
+REFFN REF, no-sv 1 V ; Match already matched string, using /di rules.
+REFFLN REF, no-sv 1 V ; Match already matched string, using /li rules.
+REFFUN REF, num 1 V ; Match already matched string, using /ui rules.
+REFFAN REF, num 1 V ; Match already matched string, using /aai rules.
+
+#*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; non-zero flags "f", next_off "o" means lookbehind assertion starting "f..(f-o)" characters before current
+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
SUSPEND BRANCHJ, off 1 V 1 ; "Independent" sub-RE.
-IFTHEN BRANCHJ, off 1 V 1 ; Switch, should be preceeded by switcher .
+IFTHEN BRANCHJ, off 1 V 1 ; Switch, should be preceded by switcher.
GROUPP GROUPP, num 1 ; Whether the group matched.
-#*Support for long RE (55..56)
-LONGJMP LONGJMP, off 1 . 1 ; Jump far away.
-BRANCHJ BRANCHJ, off 1 V 1 ; BRANCH with long offset.
+#*The heavy worker
-#*The heavy worker (57)
+EVAL EVAL, evl/flags 2L ; Execute some Perl code.
-EVAL EVAL, evl 1 ; Execute some Perl code.
-
-#*Modifiers (58..59)
+#*Modifiers
MINMOD MINMOD, no ; Next operator is not greedy.
LOGICAL LOGICAL, no ; Next opcode should set the flag only.
-# This is not used yet (60)
+#*This is not used yet
RENUM BRANCHJ, off 1 . 1 ; Group with independently numbered parens.
-#*Trie Related (61..62)
+#*Trie Related
-# Behave the same as A|LIST|OF|WORDS would. The '..C' variants have
-# inline charclass data (ascii only), the 'C' store it in the structure.
-# NOTE: the relative order of the TRIE-like regops is signifigant
+#* Behave the same as A|LIST|OF|WORDS would. The '..C' variants
+#* have inline charclass data (ascii only), the 'C' store it in the
+#* structure.
+# NOTE: the relative order of the TRIE-like regops is significant
-TRIE TRIE, trie 1 ; Match many EXACT(FL?)? at once. flags==type
+TRIE TRIE, trie 1 ; Match many EXACT(F[ALU]?)? at once. flags==type
TRIEC TRIE,trie charclass ; Same as TRIE, but with embedded charclass data
# For start classes, contains an added fail table.
AHOCORASICK TRIE, trie 1 ; Aho Corasick stclass. flags==type
AHOCORASICKC TRIE,trie charclass ; Same as AHOCORASICK, but with embedded charclass data
-#*Regex Subroutines (65..66)
+#*Regex Subroutines
GOSUB GOSUB, num/ofs 2L ; recurse to paren arg1 at (signed) ofs arg2
-GOSTART GOSTART, no ; recurse to start of pattern
-
-#*Named references (67..69)
-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
-NREFFL REF, no-sv 1 V ; Match already matched string, folded in loc.
-
-#*Special conditionals (70..72)
-NGROUPP NGROUPP, no-sv 1 ; Whether the group matched.
+#*Special conditionals
+GROUPPN GROUPPN, no-sv 1 ; Whether the group matched.
INSUBP INSUBP, num 1 ; Whether we are in a specific recurse.
DEFINEP DEFINEP, none 1 ; Never execute directly.
-#*Bactracking Verbs
+#*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
#*New charclass like patterns
LNBREAK LNBREAK, none ; generic newline pattern
-VERTWS VERTWS, none 0 S ; vertical whitespace (Perl 6)
-NVERTWS NVERTWS, none 0 S ; not vertical whitespace (Perl 6)
-HORIZWS HORIZWS, none 0 S ; horizontal whitespace (Perl 6)
-NHORIZWS NHORIZWS, none 0 S ; not horizontal whitespace (Perl 6)
-
-FOLDCHAR FOLDCHAR, codepoint 1 ; codepoint with tricky case folding properties.
-# NEW STUFF ABOVE THIS LINE
+# NEW STUFF SOMEWHERE ABOVE THIS LINE
################################################################################
#*SPECIAL REGOPS
-# This is not really a node, but an optimized away piece of a "long" node.
-# To simplify debugging output, we mark it as if it were a node
+#* This is not really a node, but an optimized away piece of a "long"
+#* node. To simplify debugging output, we mark it as if it were a node
OPTIMIZED NOTHING, off ; Placeholder for dump.
-# Special opcode with the property that no opcode in a compiled program
-# will ever be of this type. Thus it can be used as a flag value that
-# no other opcode has been seen. END is used similarly, in that an END
-# node cant be optimized. So END implies "unoptimizable" and PSEUDO mean
-# "not seen anything to optimize yet".
+#* Special opcode with the property that no opcode in a compiled program
+#* will ever be of this type. Thus it can be used as a flag value that
+#* no other opcode has been seen. END is used similarly, in that an END
+#* node cant be optimized. So END implies "unoptimizable" and PSEUDO
+#* mean "not seen anything to optimize yet".
PSEUDO PSEUDO, off ; Pseudo opcode for internal use.
-------------------------------------------------------------------------------
# Format for second section:
-# REGOP \t typelist [ \t typelist] [# Comment]
+# REGOP \t typelist [ \t typelist]
# typelist= namelist
# = namelist:FAIL
# = name:count
#
#
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