mirror of
https://github.com/git/git
synced 2024-09-13 13:24:41 +00:00
44570188a0
Fix a bug introduced in18547aacf5("grep/pcre: support utf-8", 2016-06-25) that was missed due to a blindspot in our tests, as discussed in the previous commit. I then blindly copied the same bug in94da9193a6("grep: add support for PCRE v2", 2017-06-01) when adding the PCRE v2 code. We should not tell PCRE that we're processing UTF-8 just because we're dealing with non-ASCII. In the case of e.g. "log --encoding=<...>" under is_utf8_locale() the haystack might be in ISO-8859-1, and the needle might be in a non-UTF-8 encoding. Maybe we should be more strict here and die earlier? Should we also be converting the needle to the encoding in question, and failing if it's not a string that's valid in that encoding? Maybe. But for now matching this as non-UTF8 at least has some hope of producing sensible results, since we know that our default heuristic of assuming the text to be matched is in the user locale encoding isn't true when we've explicitly encoded it to be in a different encoding. Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com> Signed-off-by: Junio C Hamano <gitster@pobox.com>
94 lines
2.5 KiB
Bash
Executable file
94 lines
2.5 KiB
Bash
Executable file
#!/bin/sh
|
|
|
|
test_description='test log with i18n features'
|
|
. ./lib-gettext.sh
|
|
|
|
# two forms of é
|
|
utf8_e=$(printf '\303\251')
|
|
latin1_e=$(printf '\351')
|
|
|
|
# invalid UTF-8
|
|
invalid_e=$(printf '\303\50)') # ")" at end to close opening "("
|
|
|
|
test_expect_success 'create commits in different encodings' '
|
|
test_tick &&
|
|
cat >msg <<-EOF &&
|
|
utf8
|
|
|
|
t${utf8_e}st
|
|
EOF
|
|
git add msg &&
|
|
git -c i18n.commitencoding=utf8 commit -F msg &&
|
|
cat >msg <<-EOF &&
|
|
latin1
|
|
|
|
t${latin1_e}st
|
|
EOF
|
|
git add msg &&
|
|
git -c i18n.commitencoding=ISO-8859-1 commit -F msg
|
|
'
|
|
|
|
test_expect_success 'log --grep searches in log output encoding (utf8)' '
|
|
cat >expect <<-\EOF &&
|
|
latin1
|
|
utf8
|
|
EOF
|
|
git log --encoding=utf8 --format=%s --grep=$utf8_e >actual &&
|
|
test_cmp expect actual
|
|
'
|
|
|
|
test_expect_success !MINGW 'log --grep searches in log output encoding (latin1)' '
|
|
cat >expect <<-\EOF &&
|
|
latin1
|
|
utf8
|
|
EOF
|
|
git log --encoding=ISO-8859-1 --format=%s --grep=$latin1_e >actual &&
|
|
test_cmp expect actual
|
|
'
|
|
|
|
test_expect_success !MINGW 'log --grep does not find non-reencoded values (utf8)' '
|
|
git log --encoding=utf8 --format=%s --grep=$latin1_e >actual &&
|
|
test_must_be_empty actual
|
|
'
|
|
|
|
test_expect_success 'log --grep does not find non-reencoded values (latin1)' '
|
|
git log --encoding=ISO-8859-1 --format=%s --grep=$utf8_e >actual &&
|
|
test_must_be_empty actual
|
|
'
|
|
|
|
for engine in fixed basic extended perl
|
|
do
|
|
prereq=
|
|
if test $engine = "perl"
|
|
then
|
|
prereq="PCRE"
|
|
else
|
|
prereq=""
|
|
fi
|
|
force_regex=
|
|
if test $engine != "fixed"
|
|
then
|
|
force_regex=.*
|
|
fi
|
|
test_expect_success GETTEXT_LOCALE,$prereq "-c grep.patternType=$engine log --grep does not find non-reencoded values (latin1 + locale)" "
|
|
cat >expect <<-\EOF &&
|
|
latin1
|
|
utf8
|
|
EOF
|
|
LC_ALL=\"$is_IS_locale\" git -c grep.patternType=$engine log --encoding=ISO-8859-1 --format=%s --grep=\"$force_regex$latin1_e\" >actual &&
|
|
test_cmp expect actual
|
|
"
|
|
|
|
test_expect_success GETTEXT_LOCALE,$prereq "-c grep.patternType=$engine log --grep does not find non-reencoded values (latin1 + locale)" "
|
|
LC_ALL=\"$is_IS_locale\" git -c grep.patternType=$engine log --encoding=ISO-8859-1 --format=%s --grep=\"$force_regex$utf8_e\" >actual &&
|
|
test_must_be_empty actual
|
|
"
|
|
|
|
test_expect_success GETTEXT_LOCALE,$prereq "-c grep.patternType=$engine log --grep does not die on invalid UTF-8 value (latin1 + locale + invalid needle)" "
|
|
LC_ALL=\"$is_IS_locale\" git -c grep.patternType=$engine log --encoding=ISO-8859-1 --format=%s --grep=\"$force_regex$invalid_e\" >actual &&
|
|
test_must_be_empty actual
|
|
"
|
|
done
|
|
|
|
test_done
|