staticperl/perl/regcomp.sym

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

# Empty rows and #-comment rows are ignored.

# 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.
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.

# [Special] alternatives
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.
ALNUM           ALNUM,  no      Match any alphanumeric character
ALNUML          ALNUM,  no      Match any alphanumeric char in locale
NALNUM          NALNUM, no      Match any non-alphanumeric character
NALNUML         NALNUM, no      Match any non-alphanumeric char in locale
SPACE           SPACE,  no      Match any whitespace character
SPACEL          SPACE,  no      Match any whitespace char in locale
NSPACE          NSPACE, no      Match any non-whitespace character
NSPACEL         NSPACE, no      Match any non-whitespace char in locale
DIGIT           DIGIT,  no      Match any numeric character
DIGITL          DIGIT,  no      Match any numeric character in locale
NDIGIT          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

# 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    Match this alternative, or the next...

# 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).

# 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.

# 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    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.
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.
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.

# 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   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.

# grouping assertions
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
LONGJMP         LONGJMP,off 1 1 Jump far away.
BRANCHJ         BRANCHJ,off 1 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.

# 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.
Revision:	1.1
Committed:	Thu Jun 30 14:26:42 2005 UTC (21 years, 3 months ago) by root
Branch:	MAIN
CVS Tags:	PERL-5-8-7, HEAD
Branch point for:	PERL
Log Message:	* empty log message *
#	User	Rev	Content
1	root	1.1	# Format:
2			# NAME \t TYPE, arg-description [num-args] [longjump-len] \t DESCRIPTION
3
4			# Empty rows and #-comment rows are ignored.
5
6			# Exit points
7			END END, no End of program.
8			SUCCEED END, no Return from a subroutine, basically.
9
10			# Anchors:
11			BOL BOL, no Match "" at beginning of line.
12			MBOL BOL, no Same, assuming multiline.
13			SBOL BOL, no Same, assuming singleline.
14			EOS EOL, no Match "" at end of string.
15			EOL EOL, no Match "" at end of line.
16			MEOL EOL, no Same, assuming multiline.
17			SEOL EOL, no Same, assuming singleline.
18			BOUND BOUND, no Match "" at any word boundary
19			BOUNDL BOUND, no Match "" at any word boundary
20			NBOUND NBOUND, no Match "" at any word non-boundary
21			NBOUNDL NBOUND, no Match "" at any word non-boundary
22			GPOS GPOS, no Matches where last m//g left off.
23
24			# [Special] alternatives
25			REG_ANY REG_ANY, no Match any one character (except newline).
26			SANY REG_ANY, no Match any one character.
27			CANY REG_ANY, no Match any one byte.
28			ANYOF ANYOF, sv Match character in (or not in) this class.
29			ALNUM ALNUM, no Match any alphanumeric character
30			ALNUML ALNUM, no Match any alphanumeric char in locale
31			NALNUM NALNUM, no Match any non-alphanumeric character
32			NALNUML NALNUM, no Match any non-alphanumeric char in locale
33			SPACE SPACE, no Match any whitespace character
34			SPACEL SPACE, no Match any whitespace char in locale
35			NSPACE NSPACE, no Match any non-whitespace character
36			NSPACEL NSPACE, no Match any non-whitespace char in locale
37			DIGIT DIGIT, no Match any numeric character
38			DIGITL DIGIT, no Match any numeric character in locale
39			NDIGIT NDIGIT, no Match any non-numeric character
40			NDIGITL NDIGIT, no Match any non-numeric character in locale
41			CLUMP CLUMP, no Match any combining character sequence
42
43			# BRANCH The set of branches constituting a single choice are hooked
44			# together with their "next" pointers, since precedence prevents
45			# anything being concatenated to any individual branch. The
46			# "next" pointer of the last BRANCH in a choice points to the
47			# thing following the whole choice. This is also where the
48			# final "next" pointer of each individual branch points; each
49			# branch starts with the operand node of a BRANCH node.
50			#
51			BRANCH BRANCH, node Match this alternative, or the next...
52
53			# BACK Normal "next" pointers all implicitly point forward; BACK
54			# exists to make loop structures possible.
55			# not used
56			BACK BACK, no Match "", "next" ptr points backward.
57
58			# Literals
59			EXACT EXACT, sv Match this string (preceded by length).
60			EXACTF EXACT, sv Match this string, folded (prec. by length).
61			EXACTFL EXACT, sv Match this string, folded in locale (w/len).
62
63			# Do nothing
64			NOTHING NOTHING,no Match empty string.
65			# A variant of above which delimits a group, thus stops optimizations
66			TAIL NOTHING,no Match empty string. Can jump here from outside.
67
68			# STAR,PLUS '?', and complex '*' and '+', are implemented as circular
69			# BRANCH structures using BACK. Simple cases (one character
70			# per match) are implemented with STAR and PLUS for speed
71			# and to minimize recursive plunges.
72			#
73			STAR STAR, node Match this (simple) thing 0 or more times.
74			PLUS PLUS, node Match this (simple) thing 1 or more times.
75
76			CURLY CURLY, sv 2 Match this simple thing {n,m} times.
77			CURLYN CURLY, no 2 Match next-after-this simple thing
78			# {n,m} times, set parenths.
79			CURLYM CURLY, no 2 Match this medium-complex thing {n,m} times.
80			CURLYX CURLY, sv 2 Match this complex thing {n,m} times.
81
82			# This terminator creates a loop structure for CURLYX
83			WHILEM WHILEM, no Do curly processing and see if rest matches.
84
85			# OPEN,CLOSE,GROUPP ...are numbered at compile time.
86			OPEN OPEN, num 1 Mark this point in input as start of #n.
87			CLOSE CLOSE, num 1 Analogous to OPEN.
88
89			REF REF, num 1 Match some already matched string
90			REFF REF, num 1 Match already matched string, folded
91			REFFL REF, num 1 Match already matched string, folded in loc.
92
93			# grouping assertions
94			IFMATCH BRANCHJ,off 1 2 Succeeds if the following matches.
95			UNLESSM BRANCHJ,off 1 2 Fails if the following matches.
96			SUSPEND BRANCHJ,off 1 1 "Independent" sub-RE.
97			IFTHEN BRANCHJ,off 1 1 Switch, should be preceeded by switcher .
98			GROUPP GROUPP, num 1 Whether the group matched.
99
100			# Support for long RE
101			LONGJMP LONGJMP,off 1 1 Jump far away.
102			BRANCHJ BRANCHJ,off 1 1 BRANCH with long offset.
103
104			# The heavy worker
105			EVAL EVAL, evl 1 Execute some Perl code.
106
107			# Modifiers
108			MINMOD MINMOD, no Next operator is not greedy.
109			LOGICAL LOGICAL,no Next opcode should set the flag only.
110
111			# This is not used yet
112			RENUM BRANCHJ,off 1 1 Group with independently numbered parens.
113
114			# This is not really a node, but an optimized away piece of a "long" node.
115			# To simplify debugging output, we mark it as if it were a node
116			OPTIMIZED NOTHING,off Placeholder for dump.