From 618160147fb23e6de542cce94593fad8350ec183 Mon Sep 17 00:00:00 2001 From: bapt Date: Thu, 6 Oct 2016 19:46:43 +0000 Subject: [PATCH] localedef: Fix ctype dump (fixed wide spread errors) This commit is from John Marino in dragonfly with the following commit log: ==== This was a CTYPE encoding error involving consecutive points of the same ctype. It was reported by myself to Illumos over a year ago but I was unsure if it was only happening on BSD. Given the cause, the bug is also present on Illumos. Basically, if consecutive points were of the exact same ctype, they would be defined as a range regardless. For example, all of these would be considered equivalent: ... , (converts to .. ) , , (converts to .. ) , ... (converts to .. ) So all the points that shouldn't have been defined got "bridged" by the extreme points. The effects were recently reported to FreeBSD on PR 213013. There are countless places were the ctype flags are misdefined, so this is a major fix that has to be MFC'd. ==== This reveals a bad change I did on the testsuite: while 0x07FF is a valid unicode it is not used yet (reserved for future use) PR: 213013 Submitted by: marino@ Reported by: Kurtis Rader Obtained from: Dragonfly MFC after: 1 month --- contrib/netbsd-tests/lib/libc/locale/t_mbstowcs.c | 2 +- usr.bin/localedef/ctype.c | 6 +++--- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/contrib/netbsd-tests/lib/libc/locale/t_mbstowcs.c b/contrib/netbsd-tests/lib/libc/locale/t_mbstowcs.c index 0c443169362b..716a881a6946 100644 --- a/contrib/netbsd-tests/lib/libc/locale/t_mbstowcs.c +++ b/contrib/netbsd-tests/lib/libc/locale/t_mbstowcs.c @@ -88,7 +88,7 @@ static struct test { 0xFFFF, 0x5D, 0x5B, 0x10000, 0x10FFFF, 0x5D, 0x0A }, #ifdef __FreeBSD__ - { 1, -1, -1, 1, 1, -1, 1, 1, 1, 1, -1, 1, 1, -1, -1, + { 1, -1, -1, 1, 1, -1, -1, 1, 1, 1, -1, 1, 1, -1, -1, #else { 1, -1, -1, 1, 1, -1, -1, 1, 1, -1, -1, 1, 1, -1, -1, #endif diff --git a/usr.bin/localedef/ctype.c b/usr.bin/localedef/ctype.c index e737ed5f876b..0e238d79080f 100644 --- a/usr.bin/localedef/ctype.c +++ b/usr.bin/localedef/ctype.c @@ -407,9 +407,9 @@ dump_ctype(void) continue; } - if ((last_ct != NULL) && (last_ct->ctype == ctn->ctype)) { + if ((last_ct != NULL) && (last_ct->ctype == ctn->ctype) && + (last_ct->wc + 1 == wc)) { ct[rl.runetype_ext_nranges-1].max = wc; - last_ct = ctn; } else { rl.runetype_ext_nranges++; ct = realloc(ct, @@ -417,8 +417,8 @@ dump_ctype(void) ct[rl.runetype_ext_nranges - 1].min = wc; ct[rl.runetype_ext_nranges - 1].max = wc; ct[rl.runetype_ext_nranges - 1].map = ctn->ctype; - last_ct = ctn; } + last_ct = ctn; if (ctn->tolower == 0) { last_lo = NULL; } else if ((last_lo != NULL) &&