From 74e12fbc03bb19ee8cbd880d0def24409ce0c6f8 Mon Sep 17 00:00:00 2001 From: Ulrich Drepper Date: Wed, 12 Nov 2003 06:13:10 +0000 Subject: Update. 2003-11-11 Jakub Jelinek * posix/regcomp.c (re_compile_fastmap_iter): Handle RE_ICASE with MB_CUR_MAX > 1 locales in the fastmap. 2003-11-11 Jakub Jelinek * posix/regex_internal.c (build_wcs_buffer): Fix comment typo. (build_wcs_upper_buffer): Likewise. Use towupper for wchar_t instead of toupper. * posix/Makefile (tests): Add bug-regex17 and bug-regex18. (bug-regex17-ENV, bug-regex18-ENV): Add LOCPATH. * posix/bug-regex18.c: New test. --- posix/Makefile | 6 ++-- posix/bug-regex18.c | 94 ++++++++++++++++++++++++++++++++++++++++++++++++++ posix/regcomp.c | 29 +++++++++++++++- posix/regex_internal.c | 10 +++--- 4 files changed, 131 insertions(+), 8 deletions(-) create mode 100644 posix/bug-regex18.c (limited to 'posix') diff --git a/posix/Makefile b/posix/Makefile index d6249a8f3e..10329577b5 100644 --- a/posix/Makefile +++ b/posix/Makefile @@ -76,8 +76,8 @@ tests := tstgetopt testfnm runtests runptests \ tst-chmod bug-regex1 bug-regex2 bug-regex3 bug-regex4 \ tst-gnuglob tst-regex bug-regex5 bug-regex6 bug-regex7 \ bug-regex8 bug-regex9 bug-regex10 bug-regex11 bug-regex12 \ - bug-regex13 bug-regex14 bug-regex15 bug-regex16 tst-nice \ - tst-nanosleep transbug + bug-regex13 bug-regex14 bug-regex15 bug-regex16 \ + bug-regex17 bug-regex18 tst-nice tst-nanosleep transbug ifeq (yes,$(build-shared)) test-srcs := globtest tests += wordexp-test tst-exec tst-spawn @@ -153,6 +153,8 @@ bug-regex1-ENV = LOCPATH=$(common-objpfx)localedata tst-regex-ENV = LOCPATH=$(common-objpfx)localedata bug-regex5-ENV = LOCPATH=$(common-objpfx)localedata bug-regex6-ENV = LOCPATH=$(common-objpfx)localedata +bug-regex17-ENV = LOCPATH=$(common-objpfx)localedata +bug-regex18-ENV = LOCPATH=$(common-objpfx)localedata testcases.h: TESTS TESTS2C.sed sed -f TESTS2C.sed < $< > $@T diff --git a/posix/bug-regex18.c b/posix/bug-regex18.c new file mode 100644 index 0000000000..503c36b39c --- /dev/null +++ b/posix/bug-regex18.c @@ -0,0 +1,94 @@ +/* Turkish regular expression tests. + Copyright (C) 2002, 2003 Free Software Foundation, Inc. + This file is part of the GNU C Library. + Contributed by Jakub Jelinek , 2002. + + The GNU C Library is free software; you can redistribute it and/or + modify it under the terms of the GNU Lesser General Public + License as published by the Free Software Foundation; either + version 2.1 of the License, or (at your option) any later version. + + The GNU C Library is distributed in the hope that it will be useful, + but WITHOUT ANY WARRANTY; without even the implied warranty of + MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + Lesser General Public License for more details. + + You should have received a copy of the GNU Lesser General Public + License along with the GNU C Library; if not, write to the Free + Software Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA + 02111-1307 USA. */ + +#include +#include +#include +#include +#include +#include + +/* Tests supposed to match. */ +struct +{ + const char *pattern; + const char *string; + int flags, nmatch; + regmatch_t rm[5]; +} tests[] = { + /* \xc4\xb0 LATIN CAPITAL LETTER I WITH DOT ABOVE + \xc4\xb1 LATIN SMALL LETTER DOTLESS I */ +#if 0 + /* XXX Not used since they fail so far. */ + { "\xc4\xb0I*\xc4\xb1$", "aBi\xc4\xb1\xc4\xb1I", REG_ICASE, 2, + { { 2, 8 }, { -1, -1 } } }, + { "[\xc4\xb0x]I*\xc4\xb1$", "aBi\xc4\xb1\xc4\xb1I", REG_ICASE, 2, + { { 2, 8 }, { -1, -1 } } }, + { "[^x]I*\xc4\xb1$", "aBi\xc4\xb1\xc4\xb1I", REG_ICASE, 2, + { { 2, 8 }, { -1, -1 } } } +#endif +}; + +int +main (void) +{ + regex_t re; + regmatch_t rm[5]; + size_t i; + int n, ret = 0; + + setlocale (LC_ALL, "tr_TR.UTF-8"); + for (i = 0; i < sizeof (tests) / sizeof (tests[0]); ++i) + { + n = regcomp (&re, tests[i].pattern, tests[i].flags); + if (n != 0) + { + char buf[500]; + regerror (n, &re, buf, sizeof (buf)); + printf ("regcomp %zd failed: %s\n", i, buf); + ret = 1; + continue; + } + + if (regexec (&re, tests[i].string, tests[i].nmatch, rm, 0)) + { + printf ("regexec %zd failed\n", i); + ret = 1; + regfree (&re); + continue; + } + + for (n = 0; n < tests[i].nmatch; ++n) + if (rm[n].rm_so != tests[i].rm[n].rm_so + || rm[n].rm_eo != tests[i].rm[n].rm_eo) + { + if (tests[i].rm[n].rm_so == -1 && tests[i].rm[n].rm_eo == -1) + break; + printf ("regexec match failure rm[%d] %d..%d\n", + n, rm[n].rm_so, rm[n].rm_eo); + ret = 1; + break; + } + + regfree (&re); + } + + return ret; +} diff --git a/posix/regcomp.c b/posix/regcomp.c index b0093d940e..2b850378b2 100644 --- a/posix/regcomp.c +++ b/posix/regcomp.c @@ -319,7 +319,29 @@ re_compile_fastmap_iter (bufp, init_state, fastmap) re_token_type_t type = dfa->nodes[node].type; if (type == CHARACTER) - re_set_fastmap (fastmap, icase, dfa->nodes[node].opr.c); + { + re_set_fastmap (fastmap, icase, dfa->nodes[node].opr.c); +#ifdef RE_ENABLE_I18N + if ((bufp->syntax & RE_ICASE) && !icase) + { + unsigned char *buf = alloca (MB_CUR_MAX), *p; + wchar_t wc; + mbstate_t state; + + p = buf; + *p++ = dfa->nodes[node].opr.c; + while (++node < dfa->nodes_len + && dfa->nodes[node].type == CHARACTER + && dfa->nodes[node].mb_partial) + *p++ = dfa->nodes[node].opr.c; + memset (&state, 0, sizeof (state)); + if (mbrtowc (&wc, (const char *) buf, p - buf, + &state) == p - buf + && __wcrtomb ((char *) buf, towlower (wc), &state) > 0) + re_set_fastmap (fastmap, 0, buf[0]); + } +#endif + } else if (type == SIMPLE_BRACKET) { int i, j, ch; @@ -367,6 +389,11 @@ re_compile_fastmap_iter (bufp, init_state, fastmap) memset (&state, '\0', sizeof (state)); __wcrtomb (buf, cset->mbchars[i], &state); re_set_fastmap (fastmap, icase, *(unsigned char *) buf); + if ((bufp->syntax & RE_ICASE) && !icase) + { + __wcrtomb (buf, towlower (cset->mbchars[i]), &state); + re_set_fastmap (fastmap, 0, *(unsigned char *) buf); + } } } #endif /* RE_ENABLE_I18N */ diff --git a/posix/regex_internal.c b/posix/regex_internal.c index f969c7c89f..e328243a57 100644 --- a/posix/regex_internal.c +++ b/posix/regex_internal.c @@ -220,7 +220,7 @@ build_wcs_buffer (pstr) pstr->cur_state = prev_st; } - /* Apply the translateion if we need. */ + /* Apply the translation if we need. */ if (pstr->trans != NULL && mbclen == 1) { int ch = pstr->trans[pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx]]; @@ -264,13 +264,13 @@ build_wcs_upper_buffer (pstr) { /* In case of a singlebyte character. */ int ch = pstr->raw_mbs[pstr->raw_mbs_idx + byte_idx]; - /* Apply the translateion if we need. */ + /* Apply the translation if we need. */ if (pstr->trans != NULL && mbclen == 1) { ch = pstr->trans[ch]; pstr->mbs_case[byte_idx] = ch; } - pstr->wcs[byte_idx] = iswlower (wc) ? toupper (wc) : wc; + pstr->wcs[byte_idx] = iswlower (wc) ? towupper (wc) : wc; pstr->mbs[byte_idx++] = islower (ch) ? toupper (ch) : ch; if (BE (mbclen == (size_t) -1, 0)) pstr->cur_state = prev_st; @@ -282,7 +282,7 @@ build_wcs_upper_buffer (pstr) else memcpy (pstr->mbs + byte_idx, pstr->raw_mbs + pstr->raw_mbs_idx + byte_idx, mbclen); - pstr->wcs[byte_idx++] = iswlower (wc) ? toupper (wc) : wc; + pstr->wcs[byte_idx++] = iswlower (wc) ? towupper (wc) : wc; /* Write paddings. */ for (remain_len = byte_idx + mbclen - 1; byte_idx < remain_len ;) pstr->wcs[byte_idx++] = WEOF; @@ -342,7 +342,7 @@ build_upper_buffer (pstr) int ch = pstr->raw_mbs[pstr->raw_mbs_idx + char_idx]; if (pstr->trans != NULL) { - ch = pstr->trans[ch]; + ch = pstr->trans[ch]; pstr->mbs_case[char_idx] = ch; } if (islower (ch)) -- cgit v1.2.3