git/t/t0020-crlf.sh

440 строки
8.7 KiB
Bash
Исходник Обычный вид История

#!/bin/sh
test_description='CRLF conversion'
. ./test-lib.sh
q_to_nul () {
perl -pe 'y/Q/\000/'
}
safecrlf: Add mechanism to warn about irreversible crlf conversions CRLF conversion bears a slight chance of corrupting data. autocrlf=true will convert CRLF to LF during commit and LF to CRLF during checkout. A file that contains a mixture of LF and CRLF before the commit cannot be recreated by git. For text files this is the right thing to do: it corrects line endings such that we have only LF line endings in the repository. But for binary files that are accidentally classified as text the conversion can corrupt data. If you recognize such corruption early you can easily fix it by setting the conversion type explicitly in .gitattributes. Right after committing you still have the original file in your work tree and this file is not yet corrupted. You can explicitly tell git that this file is binary and git will handle the file appropriately. Unfortunately, the desired effect of cleaning up text files with mixed line endings and the undesired effect of corrupting binary files cannot be distinguished. In both cases CRLFs are removed in an irreversible way. For text files this is the right thing to do because CRLFs are line endings, while for binary files converting CRLFs corrupts data. This patch adds a mechanism that can either warn the user about an irreversible conversion or can even refuse to convert. The mechanism is controlled by the variable core.safecrlf, with the following values: - false: disable safecrlf mechanism - warn: warn about irreversible conversions - true: refuse irreversible conversions The default is to warn. Users are only affected by this default if core.autocrlf is set. But the current default of git is to leave core.autocrlf unset, so users will not see warnings unless they deliberately chose to activate the autocrlf mechanism. The safecrlf mechanism's details depend on the git command. The general principles when safecrlf is active (not false) are: - we warn/error out if files in the work tree can modified in an irreversible way without giving the user a chance to backup the original file. - for read-only operations that do not modify files in the work tree we do not not print annoying warnings. There are exceptions. Even though... - "git add" itself does not touch the files in the work tree, the next checkout would, so the safety triggers; - "git apply" to update a text file with a patch does touch the files in the work tree, but the operation is about text files and CRLF conversion is about fixing the line ending inconsistencies, so the safety does not trigger; - "git diff" itself does not touch the files in the work tree, it is often run to inspect the changes you intend to next "git add". To catch potential problems early, safety triggers. The concept of a safety check was originally proposed in a similar way by Linus Torvalds. Thanks to Dimitry Potapov for insisting on getting the naked LF/autocrlf=true case right. Signed-off-by: Steffen Prohaska <prohaska@zib.de>
2008-02-06 14:25:58 +03:00
q_to_cr () {
tr Q '\015'
}
append_cr () {
sed -e 's/$/Q/' | tr Q '\015'
}
remove_cr () {
tr '\015' Q <"$1" | grep Q >/dev/null &&
tr '\015' Q <"$1" | sed -ne 's/Q$//p'
}
test_expect_success setup '
git config core.autocrlf false &&
for w in Hello world how are you; do echo $w; done >one &&
mkdir dir &&
for w in I am very very fine thank you; do echo $w; done >dir/two &&
for w in Oh here is NULQin text here; do echo $w; done | q_to_nul >three &&
git add . &&
git commit -m initial &&
one=`git rev-parse HEAD:one` &&
dir=`git rev-parse HEAD:dir` &&
two=`git rev-parse HEAD:dir/two` &&
three=`git rev-parse HEAD:three` &&
for w in Some extra lines here; do echo $w; done >>one &&
git diff >patch.file &&
patched=`git hash-object --stdin <one` &&
git read-tree --reset -u HEAD &&
echo happy.
'
safecrlf: Add mechanism to warn about irreversible crlf conversions CRLF conversion bears a slight chance of corrupting data. autocrlf=true will convert CRLF to LF during commit and LF to CRLF during checkout. A file that contains a mixture of LF and CRLF before the commit cannot be recreated by git. For text files this is the right thing to do: it corrects line endings such that we have only LF line endings in the repository. But for binary files that are accidentally classified as text the conversion can corrupt data. If you recognize such corruption early you can easily fix it by setting the conversion type explicitly in .gitattributes. Right after committing you still have the original file in your work tree and this file is not yet corrupted. You can explicitly tell git that this file is binary and git will handle the file appropriately. Unfortunately, the desired effect of cleaning up text files with mixed line endings and the undesired effect of corrupting binary files cannot be distinguished. In both cases CRLFs are removed in an irreversible way. For text files this is the right thing to do because CRLFs are line endings, while for binary files converting CRLFs corrupts data. This patch adds a mechanism that can either warn the user about an irreversible conversion or can even refuse to convert. The mechanism is controlled by the variable core.safecrlf, with the following values: - false: disable safecrlf mechanism - warn: warn about irreversible conversions - true: refuse irreversible conversions The default is to warn. Users are only affected by this default if core.autocrlf is set. But the current default of git is to leave core.autocrlf unset, so users will not see warnings unless they deliberately chose to activate the autocrlf mechanism. The safecrlf mechanism's details depend on the git command. The general principles when safecrlf is active (not false) are: - we warn/error out if files in the work tree can modified in an irreversible way without giving the user a chance to backup the original file. - for read-only operations that do not modify files in the work tree we do not not print annoying warnings. There are exceptions. Even though... - "git add" itself does not touch the files in the work tree, the next checkout would, so the safety triggers; - "git apply" to update a text file with a patch does touch the files in the work tree, but the operation is about text files and CRLF conversion is about fixing the line ending inconsistencies, so the safety does not trigger; - "git diff" itself does not touch the files in the work tree, it is often run to inspect the changes you intend to next "git add". To catch potential problems early, safety triggers. The concept of a safety check was originally proposed in a similar way by Linus Torvalds. Thanks to Dimitry Potapov for insisting on getting the naked LF/autocrlf=true case right. Signed-off-by: Steffen Prohaska <prohaska@zib.de>
2008-02-06 14:25:58 +03:00
test_expect_success 'safecrlf: autocrlf=input, all CRLF' '
git config core.autocrlf input &&
git config core.safecrlf true &&
for w in I am all CRLF; do echo $w; done | append_cr >allcrlf &&
test_must_fail git add allcrlf
safecrlf: Add mechanism to warn about irreversible crlf conversions CRLF conversion bears a slight chance of corrupting data. autocrlf=true will convert CRLF to LF during commit and LF to CRLF during checkout. A file that contains a mixture of LF and CRLF before the commit cannot be recreated by git. For text files this is the right thing to do: it corrects line endings such that we have only LF line endings in the repository. But for binary files that are accidentally classified as text the conversion can corrupt data. If you recognize such corruption early you can easily fix it by setting the conversion type explicitly in .gitattributes. Right after committing you still have the original file in your work tree and this file is not yet corrupted. You can explicitly tell git that this file is binary and git will handle the file appropriately. Unfortunately, the desired effect of cleaning up text files with mixed line endings and the undesired effect of corrupting binary files cannot be distinguished. In both cases CRLFs are removed in an irreversible way. For text files this is the right thing to do because CRLFs are line endings, while for binary files converting CRLFs corrupts data. This patch adds a mechanism that can either warn the user about an irreversible conversion or can even refuse to convert. The mechanism is controlled by the variable core.safecrlf, with the following values: - false: disable safecrlf mechanism - warn: warn about irreversible conversions - true: refuse irreversible conversions The default is to warn. Users are only affected by this default if core.autocrlf is set. But the current default of git is to leave core.autocrlf unset, so users will not see warnings unless they deliberately chose to activate the autocrlf mechanism. The safecrlf mechanism's details depend on the git command. The general principles when safecrlf is active (not false) are: - we warn/error out if files in the work tree can modified in an irreversible way without giving the user a chance to backup the original file. - for read-only operations that do not modify files in the work tree we do not not print annoying warnings. There are exceptions. Even though... - "git add" itself does not touch the files in the work tree, the next checkout would, so the safety triggers; - "git apply" to update a text file with a patch does touch the files in the work tree, but the operation is about text files and CRLF conversion is about fixing the line ending inconsistencies, so the safety does not trigger; - "git diff" itself does not touch the files in the work tree, it is often run to inspect the changes you intend to next "git add". To catch potential problems early, safety triggers. The concept of a safety check was originally proposed in a similar way by Linus Torvalds. Thanks to Dimitry Potapov for insisting on getting the naked LF/autocrlf=true case right. Signed-off-by: Steffen Prohaska <prohaska@zib.de>
2008-02-06 14:25:58 +03:00
'
test_expect_success 'safecrlf: autocrlf=input, mixed LF/CRLF' '
git config core.autocrlf input &&
git config core.safecrlf true &&
for w in Oh here is CRLFQ in text; do echo $w; done | q_to_cr >mixed &&
test_must_fail git add mixed
safecrlf: Add mechanism to warn about irreversible crlf conversions CRLF conversion bears a slight chance of corrupting data. autocrlf=true will convert CRLF to LF during commit and LF to CRLF during checkout. A file that contains a mixture of LF and CRLF before the commit cannot be recreated by git. For text files this is the right thing to do: it corrects line endings such that we have only LF line endings in the repository. But for binary files that are accidentally classified as text the conversion can corrupt data. If you recognize such corruption early you can easily fix it by setting the conversion type explicitly in .gitattributes. Right after committing you still have the original file in your work tree and this file is not yet corrupted. You can explicitly tell git that this file is binary and git will handle the file appropriately. Unfortunately, the desired effect of cleaning up text files with mixed line endings and the undesired effect of corrupting binary files cannot be distinguished. In both cases CRLFs are removed in an irreversible way. For text files this is the right thing to do because CRLFs are line endings, while for binary files converting CRLFs corrupts data. This patch adds a mechanism that can either warn the user about an irreversible conversion or can even refuse to convert. The mechanism is controlled by the variable core.safecrlf, with the following values: - false: disable safecrlf mechanism - warn: warn about irreversible conversions - true: refuse irreversible conversions The default is to warn. Users are only affected by this default if core.autocrlf is set. But the current default of git is to leave core.autocrlf unset, so users will not see warnings unless they deliberately chose to activate the autocrlf mechanism. The safecrlf mechanism's details depend on the git command. The general principles when safecrlf is active (not false) are: - we warn/error out if files in the work tree can modified in an irreversible way without giving the user a chance to backup the original file. - for read-only operations that do not modify files in the work tree we do not not print annoying warnings. There are exceptions. Even though... - "git add" itself does not touch the files in the work tree, the next checkout would, so the safety triggers; - "git apply" to update a text file with a patch does touch the files in the work tree, but the operation is about text files and CRLF conversion is about fixing the line ending inconsistencies, so the safety does not trigger; - "git diff" itself does not touch the files in the work tree, it is often run to inspect the changes you intend to next "git add". To catch potential problems early, safety triggers. The concept of a safety check was originally proposed in a similar way by Linus Torvalds. Thanks to Dimitry Potapov for insisting on getting the naked LF/autocrlf=true case right. Signed-off-by: Steffen Prohaska <prohaska@zib.de>
2008-02-06 14:25:58 +03:00
'
test_expect_success 'safecrlf: autocrlf=true, all LF' '
git config core.autocrlf true &&
git config core.safecrlf true &&
for w in I am all LF; do echo $w; done >alllf &&
test_must_fail git add alllf
safecrlf: Add mechanism to warn about irreversible crlf conversions CRLF conversion bears a slight chance of corrupting data. autocrlf=true will convert CRLF to LF during commit and LF to CRLF during checkout. A file that contains a mixture of LF and CRLF before the commit cannot be recreated by git. For text files this is the right thing to do: it corrects line endings such that we have only LF line endings in the repository. But for binary files that are accidentally classified as text the conversion can corrupt data. If you recognize such corruption early you can easily fix it by setting the conversion type explicitly in .gitattributes. Right after committing you still have the original file in your work tree and this file is not yet corrupted. You can explicitly tell git that this file is binary and git will handle the file appropriately. Unfortunately, the desired effect of cleaning up text files with mixed line endings and the undesired effect of corrupting binary files cannot be distinguished. In both cases CRLFs are removed in an irreversible way. For text files this is the right thing to do because CRLFs are line endings, while for binary files converting CRLFs corrupts data. This patch adds a mechanism that can either warn the user about an irreversible conversion or can even refuse to convert. The mechanism is controlled by the variable core.safecrlf, with the following values: - false: disable safecrlf mechanism - warn: warn about irreversible conversions - true: refuse irreversible conversions The default is to warn. Users are only affected by this default if core.autocrlf is set. But the current default of git is to leave core.autocrlf unset, so users will not see warnings unless they deliberately chose to activate the autocrlf mechanism. The safecrlf mechanism's details depend on the git command. The general principles when safecrlf is active (not false) are: - we warn/error out if files in the work tree can modified in an irreversible way without giving the user a chance to backup the original file. - for read-only operations that do not modify files in the work tree we do not not print annoying warnings. There are exceptions. Even though... - "git add" itself does not touch the files in the work tree, the next checkout would, so the safety triggers; - "git apply" to update a text file with a patch does touch the files in the work tree, but the operation is about text files and CRLF conversion is about fixing the line ending inconsistencies, so the safety does not trigger; - "git diff" itself does not touch the files in the work tree, it is often run to inspect the changes you intend to next "git add". To catch potential problems early, safety triggers. The concept of a safety check was originally proposed in a similar way by Linus Torvalds. Thanks to Dimitry Potapov for insisting on getting the naked LF/autocrlf=true case right. Signed-off-by: Steffen Prohaska <prohaska@zib.de>
2008-02-06 14:25:58 +03:00
'
test_expect_success 'safecrlf: autocrlf=true mixed LF/CRLF' '
git config core.autocrlf true &&
git config core.safecrlf true &&
for w in Oh here is CRLFQ in text; do echo $w; done | q_to_cr >mixed &&
test_must_fail git add mixed
safecrlf: Add mechanism to warn about irreversible crlf conversions CRLF conversion bears a slight chance of corrupting data. autocrlf=true will convert CRLF to LF during commit and LF to CRLF during checkout. A file that contains a mixture of LF and CRLF before the commit cannot be recreated by git. For text files this is the right thing to do: it corrects line endings such that we have only LF line endings in the repository. But for binary files that are accidentally classified as text the conversion can corrupt data. If you recognize such corruption early you can easily fix it by setting the conversion type explicitly in .gitattributes. Right after committing you still have the original file in your work tree and this file is not yet corrupted. You can explicitly tell git that this file is binary and git will handle the file appropriately. Unfortunately, the desired effect of cleaning up text files with mixed line endings and the undesired effect of corrupting binary files cannot be distinguished. In both cases CRLFs are removed in an irreversible way. For text files this is the right thing to do because CRLFs are line endings, while for binary files converting CRLFs corrupts data. This patch adds a mechanism that can either warn the user about an irreversible conversion or can even refuse to convert. The mechanism is controlled by the variable core.safecrlf, with the following values: - false: disable safecrlf mechanism - warn: warn about irreversible conversions - true: refuse irreversible conversions The default is to warn. Users are only affected by this default if core.autocrlf is set. But the current default of git is to leave core.autocrlf unset, so users will not see warnings unless they deliberately chose to activate the autocrlf mechanism. The safecrlf mechanism's details depend on the git command. The general principles when safecrlf is active (not false) are: - we warn/error out if files in the work tree can modified in an irreversible way without giving the user a chance to backup the original file. - for read-only operations that do not modify files in the work tree we do not not print annoying warnings. There are exceptions. Even though... - "git add" itself does not touch the files in the work tree, the next checkout would, so the safety triggers; - "git apply" to update a text file with a patch does touch the files in the work tree, but the operation is about text files and CRLF conversion is about fixing the line ending inconsistencies, so the safety does not trigger; - "git diff" itself does not touch the files in the work tree, it is often run to inspect the changes you intend to next "git add". To catch potential problems early, safety triggers. The concept of a safety check was originally proposed in a similar way by Linus Torvalds. Thanks to Dimitry Potapov for insisting on getting the naked LF/autocrlf=true case right. Signed-off-by: Steffen Prohaska <prohaska@zib.de>
2008-02-06 14:25:58 +03:00
'
test_expect_success 'safecrlf: print warning only once' '
git config core.autocrlf input &&
git config core.safecrlf warn &&
for w in I am all LF; do echo $w; done >doublewarn &&
git add doublewarn &&
git commit -m "nowarn" &&
for w in Oh here is CRLFQ in text; do echo $w; done | q_to_cr >doublewarn &&
test $(git add doublewarn 2>&1 | grep "CRLF will be replaced by LF" | wc -l) = 1
'
test_expect_success 'switch off autocrlf, safecrlf, reset HEAD' '
git config core.autocrlf false &&
git config core.safecrlf false &&
git reset --hard HEAD^
'
test_expect_success 'update with autocrlf=input' '
rm -f tmp one dir/two three &&
git read-tree --reset -u HEAD &&
git config core.autocrlf input &&
for f in one dir/two
do
append_cr <$f >tmp && mv -f tmp $f &&
git update-index -- $f || {
echo Oops
false
break
}
done &&
differs=`git diff-index --cached HEAD` &&
test -z "$differs" || {
echo Oops "$differs"
false
}
'
test_expect_success 'update with autocrlf=true' '
rm -f tmp one dir/two three &&
git read-tree --reset -u HEAD &&
git config core.autocrlf true &&
for f in one dir/two
do
append_cr <$f >tmp && mv -f tmp $f &&
git update-index -- $f || {
echo "Oops $f"
false
break
}
done &&
differs=`git diff-index --cached HEAD` &&
test -z "$differs" || {
echo Oops "$differs"
false
}
'
test_expect_success 'checkout with autocrlf=true' '
rm -f tmp one dir/two three &&
git config core.autocrlf true &&
git read-tree --reset -u HEAD &&
for f in one dir/two
do
remove_cr "$f" >tmp && mv -f tmp $f &&
git update-index -- $f || {
echo "Eh? $f"
false
break
}
done &&
test "$one" = `git hash-object --stdin <one` &&
test "$two" = `git hash-object --stdin <dir/two` &&
differs=`git diff-index --cached HEAD` &&
test -z "$differs" || {
echo Oops "$differs"
false
}
'
test_expect_success 'checkout with autocrlf=input' '
rm -f tmp one dir/two three &&
git config core.autocrlf input &&
git read-tree --reset -u HEAD &&
for f in one dir/two
do
if remove_cr "$f" >/dev/null
then
echo "Eh? $f"
false
break
else
git update-index -- $f
fi
done &&
test "$one" = `git hash-object --stdin <one` &&
test "$two" = `git hash-object --stdin <dir/two` &&
differs=`git diff-index --cached HEAD` &&
test -z "$differs" || {
echo Oops "$differs"
false
}
'
test_expect_success 'apply patch (autocrlf=input)' '
rm -f tmp one dir/two three &&
git config core.autocrlf input &&
git read-tree --reset -u HEAD &&
git apply patch.file &&
test "$patched" = "`git hash-object --stdin <one`" || {
echo "Eh? apply without index"
false
}
'
test_expect_success 'apply patch --cached (autocrlf=input)' '
rm -f tmp one dir/two three &&
git config core.autocrlf input &&
git read-tree --reset -u HEAD &&
git apply --cached patch.file &&
test "$patched" = `git rev-parse :one` || {
echo "Eh? apply with --cached"
false
}
'
test_expect_success 'apply patch --index (autocrlf=input)' '
rm -f tmp one dir/two three &&
git config core.autocrlf input &&
git read-tree --reset -u HEAD &&
git apply --index patch.file &&
test "$patched" = `git rev-parse :one` &&
test "$patched" = `git hash-object --stdin <one` || {
echo "Eh? apply with --index"
false
}
'
test_expect_success 'apply patch (autocrlf=true)' '
rm -f tmp one dir/two three &&
git config core.autocrlf true &&
git read-tree --reset -u HEAD &&
git apply patch.file &&
test "$patched" = "`remove_cr one | git hash-object --stdin`" || {
echo "Eh? apply without index"
false
}
'
test_expect_success 'apply patch --cached (autocrlf=true)' '
rm -f tmp one dir/two three &&
git config core.autocrlf true &&
git read-tree --reset -u HEAD &&
git apply --cached patch.file &&
test "$patched" = `git rev-parse :one` || {
echo "Eh? apply without index"
false
}
'
test_expect_success 'apply patch --index (autocrlf=true)' '
rm -f tmp one dir/two three &&
git config core.autocrlf true &&
git read-tree --reset -u HEAD &&
git apply --index patch.file &&
test "$patched" = `git rev-parse :one` &&
test "$patched" = "`remove_cr one | git hash-object --stdin`" || {
echo "Eh? apply with --index"
false
}
'
test_expect_success '.gitattributes says two is binary' '
rm -f tmp one dir/two three &&
echo "two -crlf" >.gitattributes &&
git config core.autocrlf true &&
git read-tree --reset -u HEAD &&
if remove_cr dir/two >/dev/null
then
echo "Huh?"
false
else
: happy
fi &&
if remove_cr one >/dev/null
then
: happy
else
echo "Huh?"
false
fi &&
if remove_cr three >/dev/null
then
echo "Huh?"
false
else
: happy
fi
'
test_expect_success '.gitattributes says two is input' '
rm -f tmp one dir/two three &&
echo "two crlf=input" >.gitattributes &&
git read-tree --reset -u HEAD &&
if remove_cr dir/two >/dev/null
then
echo "Huh?"
false
else
: happy
fi
'
test_expect_success '.gitattributes says two and three are text' '
rm -f tmp one dir/two three &&
echo "t* crlf" >.gitattributes &&
git read-tree --reset -u HEAD &&
if remove_cr dir/two >/dev/null
then
: happy
else
echo "Huh?"
false
fi &&
if remove_cr three >/dev/null
then
: happy
else
echo "Huh?"
false
fi
'
test_expect_success 'in-tree .gitattributes (1)' '
echo "one -crlf" >>.gitattributes &&
git add .gitattributes &&
git commit -m "Add .gitattributes" &&
rm -rf tmp one dir .gitattributes patch.file three &&
git read-tree --reset -u HEAD &&
if remove_cr one >/dev/null
then
echo "Eh? one should not have CRLF"
false
else
: happy
fi &&
remove_cr three >/dev/null || {
echo "Eh? three should still have CRLF"
false
}
'
test_expect_success 'in-tree .gitattributes (2)' '
rm -rf tmp one dir .gitattributes patch.file three &&
git read-tree --reset HEAD &&
git checkout-index -f -q -u -a &&
if remove_cr one >/dev/null
then
echo "Eh? one should not have CRLF"
false
else
: happy
fi &&
remove_cr three >/dev/null || {
echo "Eh? three should still have CRLF"
false
}
'
test_expect_success 'in-tree .gitattributes (3)' '
rm -rf tmp one dir .gitattributes patch.file three &&
git read-tree --reset HEAD &&
git checkout-index -u .gitattributes &&
git checkout-index -u one dir/two three &&
if remove_cr one >/dev/null
then
echo "Eh? one should not have CRLF"
false
else
: happy
fi &&
remove_cr three >/dev/null || {
echo "Eh? three should still have CRLF"
false
}
'
test_expect_success 'in-tree .gitattributes (4)' '
rm -rf tmp one dir .gitattributes patch.file three &&
git read-tree --reset HEAD &&
git checkout-index -u one dir/two three &&
git checkout-index -u .gitattributes &&
if remove_cr one >/dev/null
then
echo "Eh? one should not have CRLF"
false
else
: happy
fi &&
remove_cr three >/dev/null || {
echo "Eh? three should still have CRLF"
false
}
'
test_expect_success 'invalid .gitattributes (must not crash)' '
echo "three +crlf" >>.gitattributes &&
git diff
'
test_done