# Note that the order in this file is important.
#
# Format for first section:
-# NAME \s+ TYPE, arg-description [num-args] [flags] [longjump] ; DESCRIPTION
+# NAME \s+ TYPE, arg-description [struct regnode suffix] [flags] [longjump] ; DESCRIPTION
+# arg-description is currently unused
+# suffix is appended to 'struct_regnode_' giving which one to use. If empty,
+# it means plain 'struct regnode'. If the regnode is a string one, this
+# should instead refer to the base regnode, without the char[1] element
+# of the structure
# 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.
-#
+# a placeholder
+# longjump is 1 if the (first) argument holds the next offset (instead of the
+# usual 'next_offset' field
#
# run perl regen.pl after editing this file
+# +- suffix of which struct regnode to use e.g.,
+# | +- flags (S or V) struct regnode_1
+# un- | | +- longjmp (0, blank, or 1) blank means 0
+# Name Type used | | | ; comment
+# --------------------------------------------------------------------------
+# IFMATCH BRANCHJ, off 1 . 1 ; Succeeds if the following matches.
+# UNLESSM BRANCHJ, off 1 . 1 ; 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.
+#
+# If we were to start running out of regnodes, many of the ones that are
+# complements could be combined with their non-complement mates. For example,
+# POSIXU could have the flags field have the bottom bit mean do we complement
+# or not, and the type be shifted left 1 bit. Then all that would be needed to
+# extract which to do is a mask for the complement bit, and a right shift for
+# the other, an inconsequential increase in instructions. It might actually be
+# clearer and slightly faster given the case statement and assignment are
+# removed. Note that not everything could be collapsed: NPOSIXA, for example,
+# would require special handling for performance.
#* Exit points
# 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
+BOUND BOUND, no ; Like BOUNDA for non-utf8, otherwise like BOUNDU
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 Unicode rules
+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
+NBOUND NBOUND, no ; Like NBOUNDA for non-utf8, otherwise like BOUNDU
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 Unicode rules
+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:
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
-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
+
+# Must be sequential
+ANYOFH ANYOFH, sv 1 S ; Like ANYOF, but only has "High" matches, none in the bitmap; the flags field contains the lowest matchable UTF-8 start byte
+ANYOFHb ANYOFH, sv 1 S ; Like ANYOFH, but all matches share the same UTF-8 start byte, given in the flags field
+ANYOFHr ANYOFH, sv 1 S ; Like ANYOFH, but the flags field contains packed bounds for all matchable UTF-8 start bytes.
+ANYOFHs ANYOFH, sv:str 1 S ; Like ANYOFHb, but has a string field that gives the leading matchable UTF-8 bytes; flags field is len
+ANYOFR ANYOFR, packed 1 S ; Matches any character in the range given by its packed args: upper 12 bits is the max delta from the base lower 20; the flags field contains the lowest matchable UTF-8 start byte
+ANYOFRb ANYOFR, packed 1 S ; Like ANYOFR, but all matches share the same UTF-8 start byte, given in the flags field
+# There is no ANYOFRr because khw doesn't think there are likely to be
+# real-world cases where such a large range is used.
+#
+# And khw doesn't believe an ANYOFRs (which would behave like ANYOFHs) is
+# actually worth it. On two-byte UTF-8, the first byte alone is all we need,
+# and ANYOFR already does that. And we don't consider non-Unicode code points
+# or EBCDIC for performance decisions. If we had it, we would be comparing the
+# strings, and if they are equal convert to UV and then test to see if it is in
+# the range. The fast DFA we now use to do the conversion is slower than
+# comparing the strings, but not by much, and negligible in 2 or 3 byte
+# operations. (We don't have to compare the final byte as it has to be
+# different or else this wouldn't be a range.) So we might as well displense
+# with the comparisons that ANYOFRs would do, and go directly to do the
+# conversion .
+
+ANYOFHbbm ANYOFHbbm none bbm S ; Like ANYOFHb, but only for 2-byte UTF-8 characters; uses a bitmap to match the continuation byte
+
+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.
NPOSIXA NPOSIXD, none 0 S ; complement of POSIXA, [[:^class:]]
# End of order is important
-ASCII ASCII, none 0 S ; [[:ascii:]]
-NASCII ASCII, none 0 S ; [[:^ascii:]]
-
CLUMP CLUMP, no 0 V ; Match any extended grapheme cluster sequence
#* Alternation
#* 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...
+BRANCH BRANCH, node 1 V ; Match this alternative, or the next...
#*Literals
# NOTE: the relative ordering of these types is important do not change it
-
-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).
+# By convention, folding nodes begin with EXACTF; A digit 8 is in the name if
+# and only if it it requires a UTF-8 target string in order to successfully
+# match.
+
+EXACT EXACT, str ; Match this string (flags field is the length).
+
+#* In a long string node, the U32 argument is the length, and is
+#* immediately followed by the string.
+LEXACT EXACT, len:str 1; Match this long string (preceded by length; flags unused).
+EXACTL EXACT, str ; Like EXACT, but /l is in effect (used so locale-related warnings can be checked for)
+EXACTF EXACT, str ; Like EXACT, but match using /id rules; (string not UTF-8, ASCII folded; non-ASCII not)
+EXACTFL EXACT, str ; Like EXACT, but match using /il rules; (string not likely to be folded)
+EXACTFU EXACT, str ; Like EXACT, but match using /iu rules; (string folded)
+
+# The reason MICRO and SHARP S aren't folded in non-UTF8 patterns is because
+# they would fold to something that requires UTF-8. SHARP S would normally
+# fold to 'ss', but because of /aa, it instead folds to a pair of LATIN SMALL
+# LETTER LONG S characters (U+017F)
+EXACTFAA EXACT, str ; Like EXACT, but match using /iaa rules; (string folded except MICRO in non-UTF8 patterns; doesn't contain SHARP S unless UTF-8; folded length <= unfolded)
+# must immediately follow EXACTFAA
+EXACTFAA_NO_TRIE EXACT, str ; Like EXACTFAA, (string not UTF-8, folded except: MICRO, SHARP S; folded length <= unfolded, not currently trie-able)
# End of important relative ordering.
-EXACTFU_SS EXACT, str ; Match this string using /iu rules (w/len); (string folded iff in UTF-8; non-UTF8 folded length > unfolded).
-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).
+EXACTFUP EXACT, str ; Like EXACT, but match using /iu rules; (string not UTF-8, folded except MICRO: hence 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, (string is folded, and everything in it is above 255
+EXACT_REQ8 EXACT, str ; Like EXACT, but only UTF-8 encoded targets can match
+LEXACT_REQ8 EXACT, len:str 1 ; Like LEXACT, but only UTF-8 encoded targets can match
+EXACTFU_REQ8 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)
-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 and something that has the same effect for /l,
-# but these would be extremely uncommon
+#*New charclass like patterns
+LNBREAK LNBREAK, none ; generic newline pattern
+
+#*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
#*Do nothing types
#* (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.
+STAR STAR, node 0 V ; Match this (simple) thing 0 or more times: /A{0,}B/ where A is width 1 char
+PLUS PLUS, node 0 V ; Match this (simple) thing 1 or more times: /A{1,}B/ where A is width 1 char
-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.
+CURLY CURLY, sv 3 V ; Match this (simple) thing {n,m} times: /A{m,n}B/ where A is width 1 char
+CURLYN CURLY, no 3 V ; Capture next-after-this simple thing: /(A){m,n}B/ where A is width 1 char
+CURLYM CURLY, no 3 V ; Capture this medium-complex thing {n,m} times: /(A){m,n}B/ where A is fixed-length
+CURLYX CURLY, sv 3 V ; Match/Capture 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.
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 rules for non-utf8
-REFFL REF, num 1 V ; Match already matched string, folded in loc.
+REF REF, num 2 V ; Match some already matched string
+REFF REF, num 2 V ; Match already matched string, using /di rules.
+REFFL REF, num 2 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, folded using unicode rules for non-utf8
-REFFA REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII
+REFFU REF, num 2 V ; Match already matched string, usng /ui.
+REFFA REF, num 2 V ; Match already matched string, using /aai rules.
#*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 rules 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 rules for non-utf8
-NREFFA REF, num 1 V ; Match already matched string, folded using unicode rules for non-utf8, no mixing ASCII, non-ASCII
+REFN REF, no-sv 2 V ; Match some already matched string
+REFFN REF, no-sv 2 V ; Match already matched string, using /di rules.
+REFFLN REF, no-sv 2 V ; Match already matched string, using /li rules.
+REFFUN REF, num 2 V ; Match already matched string, using /ui rules.
+REFFAN REF, num 2 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.
+BRANCHJ BRANCHJ, off 2 V 1 ; BRANCH with long offset.
#*Special Case Regops
-IFMATCH BRANCHJ, off 1 . 1 ; Succeeds if the following matches.
-UNLESSM BRANCHJ, off 1 . 1 ; Fails if the following matches.
+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 preceded by switcher.
GROUPP GROUPP, num 1 ; Whether the group matched.
-
#*The heavy worker
-EVAL EVAL, evl/flags 2L ; Execute some Perl code.
+EVAL EVAL, evl/flags 2 ; Execute some Perl code.
#*Modifiers
#*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
+GOSUB GOSUB, num/ofs 2 ; recurse to paren arg1 at (signed) ofs arg2
#*Special conditionals
-NGROUPP NGROUPP, no-sv 1 ; Whether the group matched.
+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.
#*Backtracking Verbs
ENDLIKE ENDLIKE, none ; Used only for the type field of verbs
OPFAIL ENDLIKE, no-sv 1 ; Same as (?!), but with verb arg
-ACCEPT ENDLIKE, no-sv/num 2L ; Accepts the current matched string, with verbar
+ACCEPT ENDLIKE, no-sv/num 2 ; Accepts the current matched string, with verbar
#*Verbs With Arguments
VERB VERB, no-sv 1 ; Used only for the type field of verbs
#*Control what to keep in $&.
KEEPS KEEPS, no ; $& begins here.
-#*New charclass like patterns
-LNBREAK LNBREAK, none ; generic newline pattern
+#*Validate that lookbehind IFMATCH and UNLESSM end at the right place
+LOOKBEHIND_END END, no ; Return from lookbehind (IFMATCH/UNLESSM) and validate position
-# NEW STUFF SOMEWHERE ABOVE THIS LINE
+# NEW STUFF SOMEWHERE ABOVE THIS LINE. Stuff that regexec.c: find_byclass()
+# and regrepeat() use should go way above, near LNBREAK to allow a more compact
+# jump table to be generated for their switch() statements
################################################################################
#* mean "not seen anything to optimize yet".
PSEUDO PSEUDO, off ; Pseudo opcode for internal use.
+REGEX_SET REGEX_SET, depth p S ; Regex set, temporary node used in pre-optimization compilation
+
-------------------------------------------------------------------------------
# Format for second section:
# REGOP \t typelist [ \t typelist]
SKIP next:FAIL
CUTGROUP next:FAIL
KEEPS next:FAIL
+REF next:FAIL
https://perl5.git.perl.org / perl5.git / blobdiff