d_pseudofork for configure.com

[perl5.git] / regcomp.sym

diff --git a/regcomp.sym b/regcomp.sym
index c831bce..656988e 100644 (file)
--- a/regcomp.sym
+++ b/regcomp.sym
@@ -1,13 +1,28 @@
-# Format:
+# 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 sectionis for regmatch-states
+#
+# Note that the order in this file is important.
+#
+# Format for first section: 

 # NAME \t TYPE, arg-description [num-args] [longjump-len] \t DESCRIPTION
 # NAME \t TYPE, arg-description [num-args] [longjump-len] \t DESCRIPTION

+#
+#
+# run perl regen.pl after editing this file
+

 
 

-# Empty rows and #-comment rows are ignored.

 
 

-# Exit points
+#* Exit points (0,1)
+

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

-# Anchors:
+#* Anchors: (2..13)
+

 BOL            BOL,    no      Match "" at beginning of line.
 MBOL           BOL,    no      Same, assuming multiline.
 SBOL           BOL,    no      Same, assuming singleline.
 BOL            BOL,    no      Match "" at beginning of line.
 MBOL           BOL,    no      Same, assuming multiline.
 SBOL           BOL,    no      Same, assuming singleline.


@@ -16,45 +31,34 @@ 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
 MEOL           EOL,    no      Same, assuming multiline.
 SEOL           EOL,    no      Same, assuming singleline.
 BOUND          BOUND,  no      Match "" at any word boundary

-BOUNDUTF8      BOUND,  no      Match "" at any word boundary

 BOUNDL         BOUND,  no      Match "" at any word boundary
 BOUNDL         BOUND,  no      Match "" at any word boundary

-BOUNDLUTF8     BOUND,  no      Match "" at any word boundary

 NBOUND         NBOUND, no      Match "" at any word non-boundary
 NBOUND         NBOUND, no      Match "" at any word non-boundary

-NBOUNDUTF8     NBOUND, no      Match "" at any word non-boundary

 NBOUNDL                NBOUND, no      Match "" at any word non-boundary
 NBOUNDL                NBOUND, no      Match "" at any word non-boundary

-NBOUNDLUTF8    NBOUND, no      Match "" at any word non-boundary

 GPOS           GPOS,   no      Matches where last m//g left off.
 
 GPOS           GPOS,   no      Matches where last m//g left off.
 

-# [Special] alternatives
-ANY            ANY,    no      Match any one character (except newline).
-ANYUTF8                ANY,    no      Match any one Unicode character (except newline).
-SANY           ANY,    no      Match any one character.
-SANYUTF8       ANY,    no      Match any one Unicode character.
+#* [Special] alternatives: (14..30)
+
+REG_ANY                REG_ANY,    no  Match any one character (except newline).
+SANY           REG_ANY,    no  Match any one character.
+CANY           REG_ANY,    no  Match any one byte.

 ANYOF          ANYOF,  sv      Match character in (or not in) this class.
 ANYOF          ANYOF,  sv      Match character in (or not in) this class.

-ANYOFUTF8      ANYOF,  sv 1    Match character in (or not in) this class.

 ALNUM          ALNUM,  no      Match any alphanumeric character
 ALNUM          ALNUM,  no      Match any alphanumeric character

-ALNUMUTF8      ALNUM,  no      Match any alphanumeric character

 ALNUML         ALNUM,  no      Match any alphanumeric char in locale
 ALNUML         ALNUM,  no      Match any alphanumeric char in locale

-ALNUMLUTF8     ALNUM,  no      Match any alphanumeric char in locale

 NALNUM         NALNUM, no      Match any non-alphanumeric character
 NALNUM         NALNUM, no      Match any non-alphanumeric character

-NALNUMUTF8     NALNUM, no      Match any non-alphanumeric character

 NALNUML                NALNUM, no      Match any non-alphanumeric char in locale
 NALNUML                NALNUM, no      Match any non-alphanumeric char in locale

-NALNUMLUTF8    NALNUM, no      Match any non-alphanumeric char in locale

 SPACE          SPACE,  no      Match any whitespace character
 SPACE          SPACE,  no      Match any whitespace character

-SPACEUTF8      SPACE,  no      Match any whitespace character

 SPACEL         SPACE,  no      Match any whitespace char in locale
 SPACEL         SPACE,  no      Match any whitespace char in locale

-SPACELUTF8     SPACE,  no      Match any whitespace char in locale

 NSPACE         NSPACE, no      Match any non-whitespace character
 NSPACE         NSPACE, no      Match any non-whitespace character

-NSPACEUTF8     NSPACE, no      Match any non-whitespace character

 NSPACEL                NSPACE, no      Match any non-whitespace char in locale
 NSPACEL                NSPACE, no      Match any non-whitespace char in locale

-NSPACELUTF8    NSPACE, no      Match any non-whitespace char in locale

 DIGIT          DIGIT,  no      Match any numeric character
 DIGIT          DIGIT,  no      Match any numeric character

-DIGITUTF8      DIGIT,  no      Match any numeric character
+DIGITL         DIGIT,  no      Match any numeric character in locale

 NDIGIT         NDIGIT, no      Match any non-numeric character
 NDIGIT         NDIGIT, no      Match any non-numeric character

-NDIGITUTF8     NDIGIT, no      Match any non-numeric character
+NDIGITL                NDIGIT, no      Match any non-numeric character in locale

 CLUMP          CLUMP,  no      Match any combining character sequence
 
 CLUMP          CLUMP,  no      Match any combining character sequence
 

-# BRANCH       The set of branches constituting a single choice are hooked
+#* Alternation (31)
+
+# 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
 #              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


@@ -64,21 +68,27 @@ CLUMP               CLUMP,  no      Match any combining character sequence
 #
 BRANCH         BRANCH, node    Match this alternative, or the next...
 
 #
 BRANCH         BRANCH, node    Match this alternative, or the next...
 

+#*Back pointer (32)
+

 # BACK         Normal "next" pointers all implicitly point forward; BACK
 #              exists to make loop structures possible.
 # not used
 BACK           BACK,   no      Match "", "next" ptr points backward.
 
 # BACK         Normal "next" pointers all implicitly point forward; BACK
 #              exists to make loop structures possible.
 # not used
 BACK           BACK,   no      Match "", "next" ptr points backward.
 

-# Literals
-EXACT          EXACT,  sv      Match this string (preceded by length).
-EXACTF         EXACT,  sv      Match this string, folded (prec. by length).
-EXACTFL                EXACT,  sv      Match this string, folded in locale (w/len).
+#*Literals (33..35)
+
+EXACT          EXACT,  str     Match this string (preceded by length).
+EXACTF         EXACT,  str     Match this string, folded (prec. by length).
+EXACTFL                EXACT,  str     Match this string, folded in locale (w/len).
+
+#*Do nothing types (36..37)

 
 

-# Do nothing

 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.
 
 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 (38..44)
+

 # 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
 # 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


@@ -88,14 +98,15 @@ STAR                STAR,   node    Match this (simple) thing 0 or more times.
 PLUS           PLUS,   node    Match this (simple) thing 1 or more times.
 
 CURLY          CURLY,  sv 2    Match this simple thing {n,m} times.
 PLUS           PLUS,   node    Match this (simple) thing 1 or more times.
 
 CURLY          CURLY,  sv 2    Match this simple thing {n,m} times.

-CURLYN         CURLY,  no 2    Match next-after-this simple thing 
-#                              {n,m} times, set parenths.
-CURLYM         CURLY,  no 2    Match this medium-complex thing {n,m} times.
+CURLYN         CURLY,  no 2    Capture next-after-this simple thing 
+CURLYM         CURLY,  no 2    Capture this medium-complex thing {n,m} times. 

 CURLYX         CURLY,  sv 2    Match this complex thing {n,m} times.
 
 # This terminator creates a loop structure for CURLYX
 WHILEM         WHILEM, no      Do curly processing and see if rest matches.
 
 CURLYX         CURLY,  sv 2    Match this complex thing {n,m} times.
 
 # This terminator creates a loop structure for CURLYX
 WHILEM         WHILEM, no      Do curly processing and see if rest matches.
 

+#*Buffer related (45..49)
+

 # 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.
 # 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.


@@ -104,27 +115,109 @@ REF              REF,    num 1   Match some already matched string
 REFF           REF,    num 1   Match already matched string, folded
 REFFL          REF,    num 1   Match already matched string, folded in loc.
 
 REFF           REF,    num 1   Match already matched string, folded
 REFFL          REF,    num 1   Match already matched string, folded in loc.
 

-# grouping assertions
+#*Grouping assertions (50..54)
+

 IFMATCH                BRANCHJ,off 1 2 Succeeds if the following matches.
 UNLESSM                BRANCHJ,off 1 2 Fails if the following matches.
 SUSPEND                BRANCHJ,off 1 1 "Independent" sub-RE.
 IFTHEN         BRANCHJ,off 1 1 Switch, should be preceeded by switcher .
 GROUPP         GROUPP, num 1   Whether the group matched.
 
 IFMATCH                BRANCHJ,off 1 2 Succeeds if the following matches.
 UNLESSM                BRANCHJ,off 1 2 Fails if the following matches.
 SUSPEND                BRANCHJ,off 1 1 "Independent" sub-RE.
 IFTHEN         BRANCHJ,off 1 1 Switch, should be preceeded by switcher .
 GROUPP         GROUPP, num 1   Whether the group matched.
 

-# Support for long RE
+#*Support for long RE (55..56)
+

 LONGJMP                LONGJMP,off 1 1 Jump far away.
 BRANCHJ                BRANCHJ,off 1 1 BRANCH with long offset.
 
 LONGJMP                LONGJMP,off 1 1 Jump far away.
 BRANCHJ                BRANCHJ,off 1 1 BRANCH with long offset.
 

-# The heavy worker
+#*The heavy worker (57..58)
+

 EVAL           EVAL,   evl 1   Execute some Perl code.
 
 EVAL           EVAL,   evl 1   Execute some Perl code.
 

-# Modifiers
+#*Modifiers (59..60)
+

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

-# This is not used yet
+# This is not used yet (61)

 RENUM          BRANCHJ,off 1 1 Group with independently numbered parens.
 
 RENUM          BRANCHJ,off 1 1 Group with independently numbered parens.
 

+#*Trie Related (62..64)
+
+# 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
+
+TRIE           TRIE,     trie 1        Match many EXACT(FL?)? 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) 
+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           NREF,      no-sv 1      Match some already matched string
+NREFF          NREF,      no-sv 1      Match already matched string, folded
+NREFFL         NREF,      no-sv 1      Match already matched string, folded in loc.
+
+
+#*Special conditionals  (70..72)
+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.               
+
+#*Bactracking 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
+
+# NEW STUFF ABOVE THIS LINE -- Please update counts below. 
+
+################################################################################
+
+#*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.
 # 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