#*Literals
# NOTE: the relative ordering of these types is important do not change it
+# 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).
# 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 in non-UTF8 patterns: MICRO, SHARP S; folded length <= unfolded)
+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.
-EXACTFUP EXACT, str ; Like EXACT, but match using /iu rules; (string not UTF-8, folded except MICRO, SHARP S: hence Problematic)
+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,
# 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
-EXACTFAA_NO_TRIE EXACT, str ; Like EXACT, but match using /iaa rules (string not UTF-8, not guaranteed to be folded, not currently trie-able)
-
-
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
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)
+#*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
NOTHING NOTHING, no ; Match empty string.
#*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
#*Control what to keep in $&.
KEEPS KEEPS, no ; $& begins here.
-#*New charclass like patterns
-LNBREAK LNBREAK, none ; generic newline pattern
-
-# 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
################################################################################