From 0ca103686f3896fcfb9e44601c35371d53140ca4 Mon Sep 17 00:00:00 2001 From: Kurtis Rader Date: Mon, 13 Jun 2016 19:00:30 -0700 Subject: remove unset vars from the environment Remove vars from the environment that are no longer set. Simplify the code by removing an unnecessary loop. Add some tests. Fixes #3124 --- tests/c-locale.err | 0 tests/c-locale.in | 35 ----------------------------- tests/c-locale.out | 4 ---- tests/c-locale.status | 1 - tests/locale.err | 0 tests/locale.in | 61 +++++++++++++++++++++++++++++++++++++++++++++++++++ tests/locale.out | 8 +++++++ tests/locale.status | 1 + 8 files changed, 70 insertions(+), 40 deletions(-) delete mode 100644 tests/c-locale.err delete mode 100644 tests/c-locale.in delete mode 100644 tests/c-locale.out delete mode 100644 tests/c-locale.status create mode 100644 tests/locale.err create mode 100644 tests/locale.in create mode 100644 tests/locale.out create mode 100644 tests/locale.status (limited to 'tests') diff --git a/tests/c-locale.err b/tests/c-locale.err deleted file mode 100644 index e69de29b..00000000 diff --git a/tests/c-locale.in b/tests/c-locale.in deleted file mode 100644 index d2f2bd5f..00000000 --- a/tests/c-locale.in +++ /dev/null @@ -1,35 +0,0 @@ -# Verify that fish can pass through non-ASCII characters in the C/POSIX -# locale. This is to prevent regression of -# https://github.com/fish-shell/fish-shell/issues/2802. -# -# These tests are needed because the relevant standards allow the functions -# mbrtowc() and wcrtomb() to treat bytes with the high bit set as either valid -# or invalid in the C/POSIX locales. GNU libc treats those bytes as invalid. -# Other libc implementations (e.g., BSD) treat them as valid. We want fish to -# always treat those bytes as valid. - -# The fish in the middle of the pipeline should be receiving a UTF-8 encoded -# version of the unicode from the echo. It should pass those bytes thru -# literally since it is in the C locale. We verify this by first passing the -# echo output directly to the `xxd` program then via a fish instance. The -# output should be "58c3bb58" for the first statement and "58c3bc58" for the -# second. -echo -n X\u00fbX | \ - xxd --plain -echo X\u00fcX | env LC_ALL=C ../test/root/bin/fish -c 'read foo; echo -n $foo' | \ - xxd --plain - -# This test is subtle. Despite the presence of the \u00fc unicode char (a "u" -# with an umlaut) the fact the locale is C/POSIX will cause the \xfc byte to -# be emitted rather than the usual UTF-8 sequence \xc3\xbc. That's because the -# few single-byte unicode chars (that are not ASCII) are generally in the -# ISO-8859-1 char set which is encompased by the C locale. The output should -# be "59fc59". -env LC_ALL=C ../test/root/bin/fish -c 'echo -n Y\u00fcY' | \ - xxd --plain - -# The user can specify a wide unicode character (one requiring more than a -# single byte). In the C/POSIX locales we substitute a question-mark for the -# unencodable wide char. The output should be "543f54". -env LC_ALL=C ../test/root/bin/fish -c 'echo -n T\u01fdT' | \ - xxd --plain diff --git a/tests/c-locale.out b/tests/c-locale.out deleted file mode 100644 index 10a94d3e..00000000 --- a/tests/c-locale.out +++ /dev/null @@ -1,4 +0,0 @@ -58c3bb58 -58c3bc58 -59fc59 -543f54 diff --git a/tests/c-locale.status b/tests/c-locale.status deleted file mode 100644 index 573541ac..00000000 --- a/tests/c-locale.status +++ /dev/null @@ -1 +0,0 @@ -0 diff --git a/tests/locale.err b/tests/locale.err new file mode 100644 index 00000000..e69de29b diff --git a/tests/locale.in b/tests/locale.in new file mode 100644 index 00000000..d08fd7fd --- /dev/null +++ b/tests/locale.in @@ -0,0 +1,61 @@ +# Test behavior related to the locale. + +# Verify that our UTF-8 locale produces the expected output. +echo -n A\u00FCA | xxd --plain + +# Verify that exporting a change to the C locale produces the expected output. +# The output should include the literal byte \xFC rather than the UTF-8 sequence for \u00FC. +begin + set -lx LC_ALL C + echo -n B\u00FCB | xxd --plain +end + +# Since the previous change was localized to a block it should no +# longer be in effect and we should be back to a UTF-8 locale. +echo -n C\u00FCC | xxd --plain + +# Verify that setting a non-exported locale var doesn't affect the behavior. +# The output should include the UTF-8 sequence for \u00FC rather than that literal byte. +# Just like the previous test. +begin + set -l LC_ALL C + echo -n D\u00FCD | xxd --plain +end + +# Verify that fish can pass through non-ASCII characters in the C/POSIX +# locale. This is to prevent regression of +# https://github.com/fish-shell/fish-shell/issues/2802. +# +# These tests are needed because the relevant standards allow the functions +# mbrtowc() and wcrtomb() to treat bytes with the high bit set as either valid +# or invalid in the C/POSIX locales. GNU libc treats those bytes as invalid. +# Other libc implementations (e.g., BSD) treat them as valid. We want fish to +# always treat those bytes as valid. + +# The fish in the middle of the pipeline should be receiving a UTF-8 encoded +# version of the unicode from the echo. It should pass those bytes thru +# literally since it is in the C locale. We verify this by first passing the +# echo output directly to the `xxd` program then via a fish instance. The +# output should be "58c3bb58" for the first statement and "58c3bc58" for the +# second. +echo -n X\u00FBX | \ + xxd --plain +echo X\u00FCX | env LC_ALL=C ../test/root/bin/fish -c 'read foo; echo -n $foo' | \ + xxd --plain + +# The next tests deliberately spawn another fish instance to test inheritence of env vars. + +# This test is subtle. Despite the presence of the \u00fc unicode char (a "u" +# with an umlaut) the fact the locale is C/POSIX will cause the \xfc byte to +# be emitted rather than the usual UTF-8 sequence \xc3\xbc. That's because the +# few single-byte unicode chars (that are not ASCII) are generally in the +# ISO 8859-x char sets which are encompassed by the C locale. The output should +# be "59fc59". +env LC_ALL=C ../test/root/bin/fish -c 'echo -n Y\u00FCY' | \ + xxd --plain + +# The user can specify a wide unicode character (one requiring more than a +# single byte). In the C/POSIX locales we substitute a question-mark for the +# unencodable wide char. The output should be "543f54". +env LC_ALL=C ../test/root/bin/fish -c 'echo -n T\u01FDT' | \ + xxd --plain diff --git a/tests/locale.out b/tests/locale.out new file mode 100644 index 00000000..b7c97c15 --- /dev/null +++ b/tests/locale.out @@ -0,0 +1,8 @@ +41c3bc41 +42fc42 +43c3bc43 +44c3bc44 +58c3bb58 +58c3bc58 +59fc59 +543f54 diff --git a/tests/locale.status b/tests/locale.status new file mode 100644 index 00000000..573541ac --- /dev/null +++ b/tests/locale.status @@ -0,0 +1 @@ +0 -- cgit v1.2.3