commit cc5351f2c0502826f8b4143f3646d44e334ff7b8 Author: Mike FABIAN Date: Tue Jan 23 17:29:36 2018 +0100 Fix test cases tst-fnmatch and tst-regexloc for the new iso14651_t1_common file. See: http://pubs.opengroup.org/onlinepubs/7908799/xbd/re.html > A range expression represents the set of collating elements that fall > between two elements in the current collation sequence, > inclusively. It is expressed as the starting point and the ending > point separated by a hyphen (-). > > Range expressions must not be used in portable applications because > their behaviour is dependent on the collating sequence. Ranges will be > treated according to the current collating sequence, and include such > characters that fall within the range based on that collating > sequence, regardless of character values. This, however, means that > the interpretation will differ depending on collating sequence. If, > for instance, one collating sequence defines ä as a variant of a, > while another defines it as a letter following z, then the expression > [ä-z] is valid in the first language and invalid in the second. Therefore, using [a-z] does not make much sense except in the C/POSIX locale. The new iso14651_t1_common lists upper case and lower case Latin characters in a different order than the old one which causes surprising results for example in the de_DE locale: [a-z] now includes A because A comes after a in iso14651_t1_common but does not include Z because that comes after z in iso14651_t1_common. * posix/tst-fnmatch.input: Fix results for range expressions for non C locales. * posix/tst-regexloc.c: Do not use a range expression for de_DE.ISO-8859-1 locale. diff --git a/posix/tst-fnmatch.input b/posix/tst-fnmatch.input index 88b3f739a59333d5..589fb2a94038dbe3 100644 --- a/posix/tst-fnmatch.input +++ b/posix/tst-fnmatch.input @@ -418,21 +418,47 @@ C "-" "[Z-\\]]" NOMATCH # Following are tests outside the scope of IEEE 2003.2 since they are using # locales other than the C locale. The main focus of the tests is on the # handling of ranges and the recognition of character (vs bytes). +# +# See: +# +# http://pubs.opengroup.org/onlinepubs/7908799/xbd/re.html +# +# > A range expression represents the set of collating elements that fall +# > between two elements in the current collation sequence, +# > inclusively. It is expressed as the starting point and the ending +# > point separated by a hyphen (-). +# > +# > Range expressions must not be used in portable applications because +# > their behaviour is dependent on the collating sequence. Ranges will be +# > treated according to the current collating sequence, and include such +# > characters that fall within the range based on that collating +# > sequence, regardless of character values. This, however, means that +# > the interpretation will differ depending on collating sequence. If, +# > for instance, one collating sequence defines ä as a variant of a, +# > while another defines it as a letter following z, then the expression +# > [ä-z] is valid in the first language and invalid in the second. +# +# Therefore, using [a-z] does not make much sense except in the C/POSIX locale. +# The new iso14651_t1_common lists upper case and lower case Latin characters +# in a different order than the old one which causes surprising results +# for example in the de_DE locale: [a-z] now includes A because A comes +# after a in iso14651_t1_common but does not include Z because that comes +# after z in iso14651_t1_common. de_DE.ISO-8859-1 "a" "[a-z]" 0 de_DE.ISO-8859-1 "z" "[a-z]" 0 de_DE.ISO-8859-1 "ä" "[a-z]" 0 de_DE.ISO-8859-1 "ö" "[a-z]" 0 de_DE.ISO-8859-1 "ü" "[a-z]" 0 -de_DE.ISO-8859-1 "A" "[a-z]" NOMATCH +de_DE.ISO-8859-1 "A" "[a-z]" 0 # surprising but correct! de_DE.ISO-8859-1 "Z" "[a-z]" NOMATCH -de_DE.ISO-8859-1 "Ä" "[a-z]" NOMATCH -de_DE.ISO-8859-1 "Ö" "[a-z]" NOMATCH -de_DE.ISO-8859-1 "Ü" "[a-z]" NOMATCH +de_DE.ISO-8859-1 "Ä" "[a-z]" 0 # surprising but correct! +de_DE.ISO-8859-1 "Ö" "[a-z]" 0 # surprising but correct! +de_DE.ISO-8859-1 "Ü" "[a-z]" 0 # surprising but correct! de_DE.ISO-8859-1 "a" "[A-Z]" NOMATCH -de_DE.ISO-8859-1 "z" "[A-Z]" NOMATCH -de_DE.ISO-8859-1 "ä" "[A-Z]" NOMATCH -de_DE.ISO-8859-1 "ö" "[A-Z]" NOMATCH -de_DE.ISO-8859-1 "ü" "[A-Z]" NOMATCH +de_DE.ISO-8859-1 "z" "[A-Z]" 0 # surprising but correct! +de_DE.ISO-8859-1 "ä" "[A-Z]" 0 # surprising but correct! +de_DE.ISO-8859-1 "ö" "[A-Z]" 0 # surprising but correct! +de_DE.ISO-8859-1 "ü" "[A-Z]" 0 # surprising but correct! de_DE.ISO-8859-1 "A" "[A-Z]" 0 de_DE.ISO-8859-1 "Z" "[A-Z]" 0 de_DE.ISO-8859-1 "Ä" "[A-Z]" 0 @@ -515,16 +541,16 @@ de_DE.UTF-8 "z" "[a-z]" 0 de_DE.UTF-8 "ä" "[a-z]" 0 de_DE.UTF-8 "ö" "[a-z]" 0 de_DE.UTF-8 "ü" "[a-z]" 0 -de_DE.UTF-8 "A" "[a-z]" NOMATCH +de_DE.UTF-8 "A" "[a-z]" 0 # surprising but correct! de_DE.UTF-8 "Z" "[a-z]" NOMATCH -de_DE.UTF-8 "Ä" "[a-z]" NOMATCH -de_DE.UTF-8 "Ö" "[a-z]" NOMATCH -de_DE.UTF-8 "Ãœ" "[a-z]" NOMATCH +de_DE.UTF-8 "Ä" "[a-z]" 0 # surprising but correct! +de_DE.UTF-8 "Ö" "[a-z]" 0 # surprising but correct! +de_DE.UTF-8 "Ãœ" "[a-z]" 0 # surprising but correct! de_DE.UTF-8 "a" "[A-Z]" NOMATCH -de_DE.UTF-8 "z" "[A-Z]" NOMATCH -de_DE.UTF-8 "ä" "[A-Z]" NOMATCH -de_DE.UTF-8 "ö" "[A-Z]" NOMATCH -de_DE.UTF-8 "ü" "[A-Z]" NOMATCH +de_DE.UTF-8 "z" "[A-Z]" 0 # surprising but correct! +de_DE.UTF-8 "ä" "[A-Z]" 0 # surprising but correct! +de_DE.UTF-8 "ö" "[A-Z]" 0 # surprising but correct! +de_DE.UTF-8 "ü" "[A-Z]" 0 # surprising but correct! de_DE.UTF-8 "A" "[A-Z]" 0 de_DE.UTF-8 "Z" "[A-Z]" 0 de_DE.UTF-8 "Ä" "[A-Z]" 0 diff --git a/posix/tst-regexloc.c b/posix/tst-regexloc.c index 60235b4d3b3e396e..7fbc496d0ce5117f 100644 --- a/posix/tst-regexloc.c +++ b/posix/tst-regexloc.c @@ -29,8 +29,8 @@ do_test (void) if (setlocale (LC_ALL, "de_DE.ISO-8859-1") == NULL) puts ("cannot set locale"); - else if (regcomp (&re, "[a-f]*", 0) != REG_NOERROR) - puts ("cannot compile expression \"[a-f]*\""); + else if (regcomp (&re, "[abcdef]*", 0) != REG_NOERROR) + puts ("cannot compile expression \"[abcdef]*\""); else if (regexec (&re, "abcdefCDEF", 1, mat, 0) == REG_NOMATCH) puts ("no match"); else