From 88c8c9616516015e2fe0b502cdb92dc4efcc0c10 Mon Sep 17 00:00:00 2001 From: Karl Williamson Date: Fri, 4 Feb 2011 10:42:28 -0700 Subject: [PATCH] l1_char_class_tab.h: Remove multi-char fold targets These are not currently used, and slow things down, as regular expressions that have them, such as /[Etl]/i now have to go out and load utf8 code. This remains the case, though, for bracketed character classes that include [KkSs]. --- l1_char_class_tab.h | 42 +++++++++++++++++++++--------------------- regen/mk_PL_charclass.pl | 2 +- 2 files changed, 22 insertions(+), 22 deletions(-) diff --git a/l1_char_class_tab.h b/l1_char_class_tab.h index d43f87a..4f82607 100644 --- a/l1_char_class_tab.h +++ b/l1_char_class_tab.h @@ -70,31 +70,31 @@ /* U+3E '>' */ _CC_GRAPH_A|_CC_GRAPH_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_PUNCT_A|_CC_PUNCT_L1, /* U+3F '?' */ _CC_GRAPH_A|_CC_GRAPH_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_PUNCT_A|_CC_PUNCT_L1, /* U+40 '@' */ _CC_GRAPH_A|_CC_GRAPH_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_PUNCT_A|_CC_PUNCT_L1, -/* U+41 'A' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1|_CC_XDIGIT_A, +/* U+41 'A' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1|_CC_XDIGIT_A, /* U+42 'B' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1|_CC_XDIGIT_A, /* U+43 'C' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1|_CC_XDIGIT_A, /* U+44 'D' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1|_CC_XDIGIT_A, /* U+45 'E' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1|_CC_XDIGIT_A, -/* U+46 'F' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1|_CC_XDIGIT_A, +/* U+46 'F' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1|_CC_XDIGIT_A, /* U+47 'G' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, -/* U+48 'H' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, -/* U+49 'I' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, -/* U+4A 'J' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, +/* U+48 'H' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, +/* U+49 'I' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, +/* U+4A 'J' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+4B 'K' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, -/* U+4C 'L' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, +/* U+4C 'L' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+4D 'M' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, -/* U+4E 'N' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, +/* U+4E 'N' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+4F 'O' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+50 'P' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+51 'Q' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+52 'R' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+53 'S' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, -/* U+54 'T' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, +/* U+54 'T' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+55 'U' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+56 'V' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, -/* U+57 'W' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, +/* U+57 'W' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+58 'X' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, -/* U+59 'Y' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, +/* U+59 'Y' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+5A 'Z' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_UPPER_A|_CC_UPPER_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+5B '[' */ _CC_GRAPH_A|_CC_GRAPH_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_PUNCT_A|_CC_PUNCT_L1, /* U+5C '\' */ _CC_GRAPH_A|_CC_GRAPH_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_PUNCT_A|_CC_PUNCT_L1, @@ -102,31 +102,31 @@ /* U+5E '^' */ _CC_GRAPH_A|_CC_GRAPH_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_PUNCT_A|_CC_PUNCT_L1, /* U+5F '_' */ _CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_PUNCT_A|_CC_PUNCT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+60 '`' */ _CC_GRAPH_A|_CC_GRAPH_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_PUNCT_A|_CC_PUNCT_L1, -/* U+61 'a' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1|_CC_XDIGIT_A, +/* U+61 'a' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1|_CC_XDIGIT_A, /* U+62 'b' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1|_CC_XDIGIT_A, /* U+63 'c' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1|_CC_XDIGIT_A, /* U+64 'd' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1|_CC_XDIGIT_A, /* U+65 'e' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1|_CC_XDIGIT_A, -/* U+66 'f' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1|_CC_XDIGIT_A, +/* U+66 'f' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1|_CC_XDIGIT_A, /* U+67 'g' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, -/* U+68 'h' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, -/* U+69 'i' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, -/* U+6A 'j' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, +/* U+68 'h' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, +/* U+69 'i' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, +/* U+6A 'j' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+6B 'k' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, -/* U+6C 'l' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, +/* U+6C 'l' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+6D 'm' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, -/* U+6E 'n' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, +/* U+6E 'n' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+6F 'o' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+70 'p' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+71 'q' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+72 'r' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+73 's' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, -/* U+74 't' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, +/* U+74 't' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+75 'u' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+76 'v' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, -/* U+77 'w' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, +/* U+77 'w' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+78 'x' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, -/* U+79 'y' */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, +/* U+79 'y' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+7A 'z' */ _CC_ALNUMC_A|_CC_ALNUMC_L1|_CC_ALPHA_A|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_A|_CC_GRAPH_L1|_CC_IDFIRST_A|_CC_IDFIRST_L1|_CC_LOWER_A|_CC_LOWER_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_WORDCHAR_A|_CC_WORDCHAR_L1, /* U+7B '{' */ _CC_GRAPH_A|_CC_GRAPH_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_PUNCT_A|_CC_PUNCT_L1, /* U+7C '|' */ _CC_GRAPH_A|_CC_GRAPH_L1|_CC_PRINT_A|_CC_PRINT_L1|_CC_PUNCT_A|_CC_PUNCT_L1, @@ -228,7 +228,7 @@ /* U+DC U WITH DIAERESIS */ _CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1, /* U+DD Y WITH ACUTE */ _CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1, /* U+DE THORN */ _CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_PRINT_L1|_CC_UPPER_L1|_CC_WORDCHAR_L1, -/* U+DF sharp s */ _CC_NONLATIN1_FOLD|_CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1, +/* U+DF sharp s */ _CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1, /* U+E0 a with grave */ _CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1, /* U+E1 a with acute */ _CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1, /* U+E2 a with circumflex */ _CC_ALNUMC_L1|_CC_ALPHA_L1|_CC_CHARNAME_CONT|_CC_GRAPH_L1|_CC_IDFIRST_L1|_CC_LOWER_L1|_CC_PRINT_L1|_CC_WORDCHAR_L1, diff --git a/regen/mk_PL_charclass.pl b/regen/mk_PL_charclass.pl index 5b2cca7..b616f85 100644 --- a/regen/mk_PL_charclass.pl +++ b/regen/mk_PL_charclass.pl @@ -71,7 +71,7 @@ while (<$fh>) { my $from = hex $hex_from; # Perl only deals with C and F folds - next if $fold_type ne 'C' and $fold_type ne 'F'; + next if $fold_type ne 'C'; # Not currently used: && $fold_type ne 'F'; # Get each code point in the range that participates in this line's fold. # The hash has keys of each code point in the range, and values of what it -- 2.7.4