mirror of
https://github.com/git-for-windows/git.git
synced 2025-12-14 10:37:53 -06:00
25754125ce
The behavior of "grep" when patterns contained a NUL-byte has always
been haphazard, and has served the vagaries of the implementation more
than anything else. A pattern containing a NUL-byte can only be
provided via "-f <file>". Since pickaxe (log search) has no such flag
the NUL-byte in patterns has only ever been supported by "grep" (and
not "log --grep").
Since 9eceddeec6 ("Use kwset in grep", 2011-08-21) patterns containing
"\0" were considered fixed. In 966be95549 ("grep: add tests to fix
blind spots with \0 patterns", 2017-05-20) I added tests for this
behavior.
Change the behavior to do the obvious thing, i.e. don't silently
discard a regex pattern and make it implicitly fixed just because they
contain a NUL-byte. Instead die if the backend in question can't
handle them, e.g. --basic-regexp is combined with such a pattern.
This is desired because from a user's point of view it's the obvious
thing to do. Whether we support BRE/ERE/Perl syntax is different from
whether our implementation is limited by C-strings. These patterns are
obscure enough that I think this behavior change is OK, especially
since we never documented the old behavior.
Doing this also makes it easier to replace the kwset backend with
something else, since we'll no longer strictly need it for anything we
can't easily use another fixed-string backend for.
Signed-off-by: Ævar Arnfjörð Bjarmason <avarab@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
128 lines
3.7 KiB
Bash
Executable File
128 lines
3.7 KiB
Bash
Executable File
#!/bin/sh
|
|
|
|
test_description='git grep with a binary pattern files'
|
|
|
|
. ./lib-gettext.sh
|
|
|
|
nul_match_internal () {
|
|
matches=$1
|
|
prereqs=$2
|
|
lc_all=$3
|
|
extra_flags=$4
|
|
flags=$5
|
|
pattern=$6
|
|
pattern_human=$(echo "$pattern" | sed 's/Q/<NUL>/g')
|
|
|
|
if test "$matches" = 1
|
|
then
|
|
test_expect_success $prereqs "LC_ALL='$lc_all' git grep $extra_flags -f f $flags '$pattern_human' a" "
|
|
printf '$pattern' | q_to_nul >f &&
|
|
LC_ALL='$lc_all' git grep $extra_flags -f f $flags a
|
|
"
|
|
elif test "$matches" = 0
|
|
then
|
|
test_expect_success $prereqs "LC_ALL='$lc_all' git grep $extra_flags -f f $flags '$pattern_human' a" "
|
|
>stderr &&
|
|
printf '$pattern' | q_to_nul >f &&
|
|
test_must_fail env LC_ALL=\"$lc_all\" git grep $extra_flags -f f $flags a 2>stderr &&
|
|
test_i18ngrep ! 'This is only supported with -P under PCRE v2' stderr
|
|
"
|
|
elif test "$matches" = P
|
|
then
|
|
test_expect_success $prereqs "error, PCRE v2 only: LC_ALL='$lc_all' git grep -f f $flags '$pattern_human' a" "
|
|
>stderr &&
|
|
printf '$pattern' | q_to_nul >f &&
|
|
test_must_fail env LC_ALL=\"$lc_all\" git grep -f f $flags a 2>stderr &&
|
|
test_i18ngrep 'This is only supported with -P under PCRE v2' stderr
|
|
"
|
|
else
|
|
test_expect_success "PANIC: Test framework error. Unknown matches value $matches" 'false'
|
|
fi
|
|
}
|
|
|
|
nul_match () {
|
|
matches=$1
|
|
matches_pcre2=$2
|
|
matches_pcre2_locale=$3
|
|
flags=$4
|
|
pattern=$5
|
|
pattern_human=$(echo "$pattern" | sed 's/Q/<NUL>/g')
|
|
|
|
nul_match_internal "$matches" "" "C" "" "$flags" "$pattern"
|
|
nul_match_internal "$matches_pcre2" "LIBPCRE2" "C" "-P" "$flags" "$pattern"
|
|
nul_match_internal "$matches_pcre2_locale" "LIBPCRE2,GETTEXT_LOCALE" "$is_IS_locale" "-P" "$flags" "$pattern"
|
|
}
|
|
|
|
test_expect_success 'setup' "
|
|
echo 'binaryQfileQm[*]cQ*æQð' | q_to_nul >a &&
|
|
git add a &&
|
|
git commit -m.
|
|
"
|
|
|
|
# Simple fixed-string matching that can use kwset (no -i && non-ASCII)
|
|
nul_match 1 1 1 '-F' 'yQf'
|
|
nul_match 0 0 0 '-F' 'yQx'
|
|
nul_match 1 1 1 '-Fi' 'YQf'
|
|
nul_match 0 0 0 '-Fi' 'YQx'
|
|
nul_match 1 1 1 '' 'yQf'
|
|
nul_match 0 0 0 '' 'yQx'
|
|
nul_match 1 1 1 '' 'æQð'
|
|
nul_match 1 1 1 '-F' 'eQm[*]c'
|
|
nul_match 1 1 1 '-Fi' 'EQM[*]C'
|
|
|
|
# Regex patterns that would match but shouldn't with -F
|
|
nul_match 0 0 0 '-F' 'yQ[f]'
|
|
nul_match 0 0 0 '-F' '[y]Qf'
|
|
nul_match 0 0 0 '-Fi' 'YQ[F]'
|
|
nul_match 0 0 0 '-Fi' '[Y]QF'
|
|
nul_match 0 0 0 '-F' 'æQ[ð]'
|
|
nul_match 0 0 0 '-F' '[æ]Qð'
|
|
|
|
# The -F kwset codepath can't handle -i && non-ASCII...
|
|
nul_match P 1 1 '-i' '[æ]Qð'
|
|
|
|
# ...PCRE v2 only matches non-ASCII with -i casefolding under UTF-8
|
|
# semantics
|
|
nul_match P P P '-Fi' 'ÆQ[Ð]'
|
|
nul_match P 0 1 '-i' 'ÆQ[Ð]'
|
|
nul_match P 0 1 '-i' '[Æ]QÐ'
|
|
nul_match P 0 1 '-i' '[Æ]Qð'
|
|
nul_match P 0 1 '-i' 'ÆQÐ'
|
|
|
|
# \0 in regexes can only work with -P & PCRE v2
|
|
nul_match P 1 1 '' 'yQ[f]'
|
|
nul_match P 1 1 '' '[y]Qf'
|
|
nul_match P 1 1 '-i' 'YQ[F]'
|
|
nul_match P 1 1 '-i' '[Y]Qf'
|
|
nul_match P 1 1 '' 'æQ[ð]'
|
|
nul_match P 1 1 '' '[æ]Qð'
|
|
nul_match P 0 1 '-i' 'ÆQ[Ð]'
|
|
nul_match P 1 1 '' 'eQm.*cQ'
|
|
nul_match P 1 1 '-i' 'EQM.*cQ'
|
|
nul_match P 0 0 '' 'eQm[*]c'
|
|
nul_match P 0 0 '-i' 'EQM[*]C'
|
|
|
|
# Assert that we're using REG_STARTEND and the pattern doesn't match
|
|
# just because it's cut off at the first \0.
|
|
nul_match 0 0 0 '-i' 'NOMATCHQð'
|
|
nul_match P 0 0 '-i' '[Æ]QNOMATCH'
|
|
nul_match P 0 0 '-i' '[æ]QNOMATCH'
|
|
|
|
# Ensure that the matcher doesn't regress to something that stops at
|
|
# \0
|
|
nul_match 0 0 0 '-F' 'yQ[f]'
|
|
nul_match 0 0 0 '-Fi' 'YQ[F]'
|
|
nul_match 0 0 0 '' 'yQNOMATCH'
|
|
nul_match 0 0 0 '' 'QNOMATCH'
|
|
nul_match 0 0 0 '-i' 'YQNOMATCH'
|
|
nul_match 0 0 0 '-i' 'QNOMATCH'
|
|
nul_match 0 0 0 '-F' 'æQ[ð]'
|
|
nul_match P P P '-Fi' 'ÆQ[Ð]'
|
|
nul_match P 0 1 '-i' 'ÆQ[Ð]'
|
|
nul_match 0 0 0 '' 'yQNÓMATCH'
|
|
nul_match 0 0 0 '' 'QNÓMATCH'
|
|
nul_match 0 0 0 '-i' 'YQNÓMATCH'
|
|
nul_match 0 0 0 '-i' 'QNÓMATCH'
|
|
|
|
test_done
|