regexec.c: White-space only; no code changes

[perl5.git] / regcomp.sym

# regcomp.sym
#
# File has two sections, divided by a line of dashes '-'. 
#
# Empty rows after #-comment are removed from input are ignored
#
# 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 [num-args] [flags] [longjump-len] ; DESCRIPTION
#   flag <S> means is REGNODE_SIMPLE; flag <V> means is REGNODE_VARIES
#
#
# run perl regen.pl after editing this file
# Also update perlredebguts.pod



#* Exit points

END         END,        no        ; End of program.
SUCCEED     END,        no        ; Return from a subroutine, basically.

#* Anchors:

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.
# 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, ALNUM, SPACE, DIGIT, 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
# 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.

#* [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

# Order (within each group) of the below is important.  See ordering comment
# above.  The PLACEHOLDERn ones are wasting a value.  Right now, we have plenty
# to spare, but these would be obvious candidates if ever we ran out of node
# types in a U8.
ALNUM       ALNUM,      no 0 S    ; Match any alphanumeric character using native charset semantics for non-utf8
ALNUML      ALNUM,      no 0 S    ; Match any alphanumeric char in locale
ALNUMU      ALNUM,      no 0 S    ; Match any alphanumeric char using Unicode semantics
ALNUMA      ALNUM,      no 0 S    ; Match [A-Za-z_0-9]
NALNUM      NALNUM,     no 0 S    ; Match any non-alphanumeric character using native charset semantics for non-utf8
NALNUML     NALNUM,     no 0 S    ; Match any non-alphanumeric char in locale
NALNUMU     NALNUM,     no 0 S    ; Match any non-alphanumeric char using Unicode semantics
NALNUMA     NALNUM,     no 0 S    ; Match [^A-Za-z_0-9]
SPACE       SPACE,      no 0 S    ; Match any whitespace character using native charset semantics for non-utf8
SPACEL      SPACE,      no 0 S    ; Match any whitespace char in locale
SPACEU      SPACE,      no 0 S    ; Match any whitespace char using Unicode semantics
SPACEA      SPACE,      no 0 S    ; Match [ \t\n\f\r]
NSPACE      NSPACE,     no 0 S    ; Match any non-whitespace character using native charset semantics for non-utf8
NSPACEL     NSPACE,     no 0 S    ; Match any non-whitespace char in locale
NSPACEU     NSPACE,     no 0 S    ; Match any non-whitespace char using Unicode semantics
NSPACEA     NSPACE,     no 0 S    ; Match [^ \t\n\f\r]
DIGIT       DIGIT,      no 0 S    ; Match any numeric character using native charset semantics for non-utf8
DIGITL      DIGIT,      no 0 S    ; Match any numeric character in locale
PLACEHOLDER1 NOTHING,   no        ; placeholder for missing DIGITU
DIGITA      DIGIT,      no 0 S    ; Match [0-9]
NDIGIT      NDIGIT,     no 0 S    ; Match any non-numeric character using native charset semantics for non-utf8
NDIGITL     NDIGIT,     no 0 S    ; Match any non-numeric character in locale
PLACEHOLDER2 NOTHING,   no        ; placeholder for missing NDIGITU
NDIGITA     NDIGIT,     no 0 S    ; Match [^0-9]

POSIXD      POSIXD,     none 0 S   ; currently unused except as a placeholder
POSIXL      POSIXD,     none 0 S   ; currently unused except as a placeholder
POSIXU      POSIXD,     none 0 S   ; currently unused except as a placeholder
POSIXA      POSIXD,     none 0 S   ; Some [[:class:]] under /a; the FLAGS field gives which one
NPOSIXD     POSIXD,     none 0 S   ; currently unused except as a placeholder
NPOSIXL     POSIXD,     none 0 S   ; currently unused except as a placeholder
NPOSIXU     POSIXD,     none 0 S   ; currently unused except as a placeholder
NPOSIXA     POSIXD,     none 0 S   ; complement of POSIXA, [[:^class:]]
# End of order is important (within groups)

CLUMP       CLUMP,      no 0 V    ; 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      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).
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).
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

#*Do nothing types

NOTHING     NOTHING,    no        ; Match empty string.
# A variant of above which delimits a group, thus stops optimizations
TAIL        NOTHING,    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        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.

CURLY       CURLY,      sv 2 V    ; Match this simple thing {n,m} times.
CURLYN      CURLY,      no 2 V    ; Capture next-after-this simple thing 
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
WHILEM      WHILEM,     no 0 V    ; Do curly processing and see if rest matches.

#*Buffer related

# 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.

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.
# 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

#*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
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

IFMATCH     BRANCHJ,    off 1 . 2 ; Succeeds if the following matches.
UNLESSM     BRANCHJ,    off 1 . 2 ; 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.

#*Modifiers

MINMOD      MINMOD,     no        ; Next operator is not greedy.
LOGICAL     LOGICAL,    no        ; Next opcode should set the flag only.

# This is not used yet
RENUM       BRANCHJ,    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,       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
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.            
INSUBP      INSUBP,     num 1     ; Whether we are in a specific recurse.  
DEFINEP     DEFINEP,    none 1    ; Never execute directly.               

#*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.


#*Verbs With Arguments
VERB        VERB,       no-sv 1   ; Used only for the type field of verbs
PRUNE       VERB,       no-sv 1   ; Pattern fails at this startpoint if no-backtracking through this 
MARKPOINT   VERB,       no-sv 1   ; Push the current location for rollback by cut.
SKIP        VERB,       no-sv 1   ; On failure skip forward (to the mark) before retrying
COMMIT      VERB,       no-sv 1   ; Pattern fails outright if backtracking through this
CUTGROUP    VERB,       no-sv 1   ; On failure go to the next alternation in the group

#*Control what to keep in $&.
KEEPS       KEEPS,      no        ; $& begins here.

#*New charclass like patterns
LNBREAK     LNBREAK,    none      ; generic newline pattern

# regcomp.c expects the node number of the complement to be one greater than
# the non-complement
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)

# 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
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".
PSEUDO      PSEUDO,     off       ; Pseudo opcode for internal use.

-------------------------------------------------------------------------------
# Format for second section:
# REGOP \t typelist [ \t typelist] [# Comment]
# typelist= namelist
#         = namelist:FAIL
#         = name:count

# Anything below is a state
#
#
TRIE            next:FAIL
EVAL            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
COMMIT          next:FAIL
MARKPOINT       next:FAIL
SKIP            next:FAIL
CUTGROUP        next:FAIL
KEEPS           next:FAIL