perldebguts: Update regnodes to 5.14

This hadn't been updated for quite some time.  It just takes what is
in regcomp.sym, and removes some columns, and some reformatting.

1 files changed, 230 insertions, 109 deletions

diff --git a/pod/perldebguts.pod b/pod/perldebguts.pod
index e5970a3e54..9bc0b63de4 100644
--- a/pod/perldebguts.pod
+++ b/pod/perldebguts.pod
@@ -536,115 +536,236 @@ C<   >I<id>: I<TYPE> I<OPTIONAL-INFO> (I<next-id>)
 
 Here are the possible types, with short descriptions:
 
-    # TYPE arg-description [num-args] [longjump-len] DESCRIPTION
-
-    # Exit points
-    END		no	End of program.
-    SUCCEED	no	Return from a subroutine, basically.
-
-    # Anchors:
-    BOL		no	Match "" at beginning of line.
-    MBOL	no	Same, assuming multiline.
-    SBOL	no	Same, assuming singleline.
-    EOS		no	Match "" at end of string.
-    EOL		no	Match "" at end of line.
-    MEOL	no	Same, assuming multiline.
-    SEOL	no	Same, assuming singleline.
-    BOUND	no	Match "" at any word boundary
-    BOUNDL	no	Match "" at any word boundary
-    NBOUND	no	Match "" at any word non-boundary
-    NBOUNDL	no	Match "" at any word non-boundary
-    GPOS	no	Matches where last m//g left off.
-
-    # [Special] alternatives
-    ANY		no	Match any one character (except newline).
-    SANY	no	Match any one character.
-    ANYOF	sv	Match character in (or not in) this class.
-    ALNUM	no	Match any alphanumeric character
-    ALNUML	no	Match any alphanumeric char in locale
-    NALNUM	no	Match any non-alphanumeric character
-    NALNUML	no	Match any non-alphanumeric char in locale
-    SPACE	no	Match any whitespace character
-    SPACEL	no	Match any whitespace char in locale
-    NSPACE	no	Match any non-whitespace character
-    NSPACEL	no	Match any non-whitespace char in locale
-    DIGIT	no	Match any numeric character
-    NDIGIT	no	Match any non-numeric character
-
-    # 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	node	Match this alternative, or the next...
-
-    # BACK	Normal "next" pointers all implicitly point forward; BACK
-    #		exists to make loop structures possible.
-    # not used
-    BACK	no	Match "", "next" ptr points backward.
-
-    # Literals
-    EXACT	sv	Match this string (preceded by length).
-    EXACTF	sv	Match this string, folded (prec. by length).
-    EXACTFL	sv	Match this string, folded in locale (w/len).
-
-    # Do nothing
-    NOTHING	no	Match empty string.
-    # A variant of above which delimits a group, thus stops optimizations
-    TAIL	no	Match empty string. Can jump here from outside.
-
-    # 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	node	Match this (simple) thing 0 or more times.
-    PLUS	node	Match this (simple) thing 1 or more times.
-
-    CURLY	sv 2	Match this simple thing {n,m} times.
-    CURLYN	no 2	Match next-after-this simple thing 
-    #			{n,m} times, set parens.
-    CURLYM	no 2	Match this medium-complex thing {n,m} times.
-    CURLYX	sv 2	Match this complex thing {n,m} times.
-
-    # This terminator creates a loop structure for CURLYX
-    WHILEM	no	Do curly processing and see if rest matches.
-
-    # OPEN,CLOSE,GROUPP	...are numbered at compile time.
-    OPEN	num 1	Mark this point in input as start of #n.
-    CLOSE	num 1	Analogous to OPEN.
-
-    REF		num 1	Match some already matched string
-    REFF	num 1	Match already matched string, folded
-    REFFL	num 1	Match already matched string, folded in loc.
-
-    # grouping assertions
-    IFMATCH	off 1 2	Succeeds if the following matches.
-    UNLESSM	off 1 2	Fails if the following matches.
-    SUSPEND	off 1 1	"Independent" sub-regex.
-    IFTHEN	off 1 1	Switch, should be preceded by switcher.
-    GROUPP	num 1	Whether the group matched.
-
-    # Support for long regex
-    LONGJMP	off 1 1	Jump far away.
-    BRANCHJ	off 1 1	BRANCH with long offset.
-
-    # The heavy worker
-    EVAL	evl 1	Execute some Perl code.
-
-    # Modifiers
-    MINMOD	no	Next operator is not greedy.
-    LOGICAL	no	Next opcode should set the flag only.
-
-    # This is not used yet
-    RENUM	off 1 1	Group with independently numbered parens.
-
-    # 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	off	Placeholder for dump.
+ # TYPE arg-description [num-args] [longjump-len] DESCRIPTION
+
+ # Exit points
+ END   no        End of program.
+ SUCCEED   no        Return from a subroutine, basically.
+
+ # Anchors:
+
+ BOL        no      Match "" at beginning of line.
+ MBOL       no      Same, assuming multiline.
+ SBOL       no      Same, assuming singleline.
+ EOS        no      Match "" at end of string.
+ EOL        no      Match "" at end of line.
+ MEOL       no      Same, assuming multiline.
+ SEOL       no      Same, assuming singleline.
+ BOUND      no      Match "" at any word boundary using native charset
+                    semantics for non-utf8
+ BOUNDL     no      Match "" at any locale word boundary
+ BOUNDU     no      Match "" at any word boundary using Unicode semantics
+ BOUNDA     no      Match "" at any word boundary using ASCII semantics
+ NBOUND     no      Match "" at any word non-boundary using native charset
+                    semantics for non-utf8
+ NBOUNDL    no      Match "" at any locale word non-boundary
+ NBOUNDU    no      Match "" at any word non-boundary using Unicode semantics
+ NBOUNDA    no      Match "" at any word non-boundary using ASCII semantics
+ GPOS       no      Matches where last m//g left off.
+
+ # [Special] alternatives:
+
+ REG_ANY    no      Match any one character (except newline).
+ SANY       no      Match any one character.
+ CANY       no      Match any one byte.
+ ANYOF      sv      Match character in (or not in) this class, single char
+                    match only
+ ANYOFV     sv      Match character in (or not in) this class, can
+                    match-multiple chars
+ ALNUM      no      Match any alphanumeric character using native charset
+                    semantics for non-utf8
+ ALNUML     no      Match any alphanumeric char in locale
+ ALNUMU     no      Match any alphanumeric char using Unicode semantics
+ ALNUMA     no      Match [A-Za-z_0-9]
+ NALNUM     no      Match any non-alphanumeric character using native charset
+                    semantics for non-utf8
+ NALNUML    no      Match any non-alphanumeric char in locale
+ NALNUMU    no      Match any non-alphanumeric char using Unicode semantics
+ NALNUMA    no      Match [^A-Za-z_0-9]
+ SPACE      no      Match any whitespace character using native charset
+                    semantics for non-utf8
+ SPACEL     no      Match any whitespace char in locale
+ SPACEU     no      Match any whitespace char using Unicode semantics
+ SPACEA     no      Match [ \t\n\f\r]
+ NSPACE     no      Match any non-whitespace character using native charset
+                    semantics for non-utf8
+ NSPACEL    no      Match any non-whitespace char in locale
+ NSPACEU    no      Match any non-whitespace char using Unicode semantics
+ NSPACEA    no      Match [^ \t\n\f\r]
+ DIGIT      no      Match any numeric character using native charset semantics
+                    for non-utf8
+ DIGITL     no      Match any numeric character in locale
+ DIGITA     no      Match [0-9]
+ NDIGIT     no      Match any non-numeric character using native charset
+ i                  semantics for non-utf8
+ NDIGITL    no      Match any non-numeric character in locale
+ NDIGITA    no      Match [^0-9]
+ CLUMP      no      Match any extended grapheme cluster sequence
+
+ # 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	node        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       no      Match "", "next" ptr points backward.
+
+ # Literals
+
+ EXACT      str     Match this string (preceded by length).
+ EXACTF     str     Match this string, folded, native charset semantics for
+                    non-utf8 (prec. by length).
+ EXACTFL    str     Match this string, folded in locale (w/len).
+ EXACTFU    str     Match this string, folded, Unicode semantics for non-utf8
+                    (prec. by length).
+ EXACTFA    str	    Match this string, folded, Unicode semantics for non-utf8,
+                    but no ASCII-range character matches outside ASCII (prec.
+                    by length),.
+
+ # Do nothing types
+
+ NOTHING    no        Match empty string.
+ # A variant of above which delimits a group, thus stops optimizations
+ TAIL       no        Match empty string. Can jump here from outside.
+
+ # 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       node    Match this (simple) thing 0 or more times.
+ PLUS       node    Match this (simple) thing 1 or more times.
+
+ CURLY      sv 2    Match this simple thing {n,m} times.
+ CURLYN     no 2    Capture next-after-this simple thing
+ CURLYM     no 2    Capture this medium-complex thing {n,m} times.
+ CURLYX     sv 2    Match this complex thing {n,m} times.
+
+ # This terminator creates a loop structure for CURLYX
+ WHILEM     no      Do curly processing and see if rest matches.
+
+ # Buffer related
+
+ # OPEN,CLOSE,GROUPP     ...are numbered at compile time.
+ OPEN       num 1   Mark this point in input as start of #n.
+ CLOSE      num 1   Analogous to OPEN.
+
+ REF        num 1   Match some already matched string
+ REFF       num 1   Match already matched string, folded using native charset
+                    semantics for non-utf8
+ REFFL      num 1   Match already matched string, folded in loc.
+ REFFU      num 1   Match already matched string, folded using unicode
+                    semantics for non-utf8
+ REFFA      num 1   Match already matched string, folded using unicode
+                    semantics for non-utf8, no mixing ASCII, non-ASCII
+
+ # Named references.  Code in regcomp.c assumes that these all are after the
+ # numbered references
+ NREF       no-sv 1 Match some already matched string
+ NREFF      no-sv 1 Match already matched string, folded using native charset
+                    semantics for non-utf8
+ NREFFL     no-sv 1 Match already matched string, folded in loc.
+ NREFFU     num   1 Match already matched string, folded using unicode
+                    semantics for non-utf8
+ NREFFA     num   1 Match already matched string, folded using unicode
+                    semantics for non-utf8, no mixing ASCII, non-ASCII
+
+ IFMATCH    off 1 2 Succeeds if the following matches.
+ UNLESSM    off 1 2 Fails if the following matches.
+ SUSPEND    off 1 1 "Independent" sub-RE.
+ IFTHEN     off 1 1 Switch, should be preceded by switcher.
+ GROUPP     num 1   Whether the group matched.
+
+ # Support for long RE
+
+ LONGJMP    off 1 1 Jump far away.
+ BRANCHJ    off 1 1 BRANCH with long offset.
+
+ # The heavy worker
+
+ EVAL       evl 1   Execute some Perl code.
+
+ # Modifiers
+
+ MINMOD     no      Next operator is not greedy.
+ LOGICAL    no      Next opcode should set the flag only.
+
+ # This is not used yet
+ RENUM      off 1 1 Group with independently numbered parens.
+
+ # 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 significant
+
+ TRIE       trie 1    Match many EXACT(F[ALU]?)? at once. flags==type
+ TRIEC      charclass Same as TRIE, but with embedded charclass data
+
+ # For start classes, contains an added fail table.
+ AHOCORASICK trie 1   Aho Corasick stclass. flags==type
+ AHOCORASICKC charclass Same as AHOCORASICK, but with embedded charclass data
+
+ # Regex Subroutines
+ GOSUB      num/ofs 2L recurse to paren arg1 at (signed) ofs arg2
+ GOSTART    no         recurse to start of pattern
+
+ # Special conditionals
+ NGROUPP    no-sv 1   Whether the group matched.
+ INSUBP     num 1     Whether we are in a specific recurse.
+ DEFINEP    none 1    Never execute directly.
+
+ # Backtracking Verbs
+ ENDLIKE    none      Used only for the type field of verbs
+ OPFAIL     none      Same as (?!)
+ ACCEPT     parno 1   Accepts the current matched string.
+
+
+ # Verbs With Arguments
+ VERB       no-sv 1   Used only for the type field of verbs
+ PRUNE      no-sv 1   Pattern fails at this startpoint if no-backtracking through this
+ MARKPOINT  no-sv 1   Push the current location for rollback by cut.
+ SKIP       no-sv 1   On failure skip forward (to the mark) before retrying
+ COMMIT     no-sv 1   Pattern fails outright if backtracking through this
+ CUTGROUP   no-sv 1   On failure go to the next alternation in the group
+
+ # Control what to keep in $&.
+ KEEPS      no        $& begins here.
+
+ # New charclass like patterns
+ LNBREAK    none      generic newline pattern
+ VERTWS     none      vertical whitespace         (Perl 6)
+ NVERTWS    none      not vertical whitespace     (Perl 6)
+ HORIZWS    none      horizontal whitespace       (Perl 6)
+ NHORIZWS   none      not horizontal whitespace   (Perl 6)
+
+ FOLDCHAR   codepoint 1 codepoint with tricky case folding properties.
+
+ # 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
+ OPTIMIZED  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".
+ PSEUDO     off       Pseudo opcode for internal use.
 
 =for unprinted-credits
 Next section M-J. Dominus (mjd-perl-patch+@plover.com) 20010421