Merge branch 'as/pretty-truncate' into maint

The "%<(10,trunc)%s" pretty format specifier in the log family of
commands is used to truncate the string to a given length (e.g. 10
in the example) with padding to column-align the output, but did
not take into account that number of bytes and number of display
columns are different.

* as/pretty-truncate:
  pretty.c: format string with truncate respects logOutputEncoding
  t4205, t6006: add tests that fail with i18n.logOutputEncoding set
  t4205 (log-pretty-format): use `tformat` rather than `format`
  t4041, t4205, t6006, t7102: don't hardcode tested encoding value
  t4205 (log-pretty-formats): don't hardcode SHA-1 in expected outputs
This commit is contained in:
Junio C Hamano 2014-06-25 11:45:31 -07:00
commit ad5d893907
5 changed files with 282 additions and 72 deletions

View file

@ -1506,13 +1506,18 @@ void format_commit_message(const struct commit *commit,
context.commit = commit;
context.pretty_ctx = pretty_ctx;
context.wrap_start = sb->len;
/*
* convert a commit message to UTF-8 first
* as far as 'format_commit_item' assumes it in UTF-8
*/
context.message = logmsg_reencode(commit,
&context.commit_encoding,
output_enc);
utf8);
strbuf_expand(sb, format, format_commit_item, &context);
rewrap_message_tail(sb, &context, 0, 0, 0);
/* then convert a commit message to an actual output encoding */
if (output_enc) {
if (same_encoding(utf8, output_enc))
output_enc = NULL;

View file

@ -11,6 +11,9 @@ This test tries to verify the sanity of the --submodule option of git diff.
. ./test-lib.sh
# Tested non-UTF-8 encoding
test_encoding="ISO8859-1"
# String "added" in German (translated with Google Translate), encoded in UTF-8,
# used in sample commit log messages in add_file() function below.
added=$(printf "hinzugef\303\274gt")
@ -23,8 +26,8 @@ add_file () {
echo "$name" >"$name" &&
git add "$name" &&
test_tick &&
msg_added_iso88591=$(echo "Add $name ($added $name)" | iconv -f utf-8 -t iso8859-1) &&
git -c 'i18n.commitEncoding=iso8859-1' commit -m "$msg_added_iso88591"
msg_added_iso88591=$(echo "Add $name ($added $name)" | iconv -f utf-8 -t $test_encoding) &&
git -c "i18n.commitEncoding=$test_encoding" commit -m "$msg_added_iso88591"
done >/dev/null &&
git rev-parse --short --verify HEAD
)

View file

@ -7,6 +7,9 @@
test_description='Test pretty formats'
. ./test-lib.sh
# Tested non-UTF-8 encoding
test_encoding="ISO8859-1"
sample_utf8_part=$(printf "f\303\244ng")
commit_msg () {
@ -27,8 +30,8 @@ test_expect_success 'set up basic repos' '
>bar &&
git add foo &&
test_tick &&
git config i18n.commitEncoding iso8859-1 &&
git commit -m "$(commit_msg iso8859-1)" &&
git config i18n.commitEncoding $test_encoding &&
git commit -m "$(commit_msg $test_encoding)" &&
git add bar &&
test_tick &&
git commit -m "add bar" &&
@ -56,8 +59,8 @@ test_expect_success 'alias user-defined format' '
test_cmp expected actual
'
test_expect_success 'alias user-defined tformat with %s (iso8859-1 encoding)' '
git config i18n.logOutputEncoding iso8859-1 &&
test_expect_success 'alias user-defined tformat with %s (ISO8859-1 encoding)' '
git config i18n.logOutputEncoding $test_encoding &&
git log --oneline >expected-s &&
git log --pretty="tformat:%h %s" >actual-s &&
git config --unset i18n.logOutputEncoding &&
@ -141,9 +144,7 @@ test_expect_success 'setup more commits' '
'
test_expect_success 'left alignment formatting' '
git log --pretty="format:%<(40)%s" >actual &&
# complete the incomplete line at the end
echo >>actual &&
git log --pretty="tformat:%<(40)%s" >actual &&
qz_to_tab_space <<EOF >expected &&
message two Z
message one Z
@ -153,10 +154,19 @@ EOF
test_cmp expected actual
'
test_expect_success 'left alignment formatting. i18n.logOutputEncoding' '
git -c i18n.logOutputEncoding=$test_encoding log --pretty="tformat:%<(40)%s" >actual &&
qz_to_tab_space <<EOF | iconv -f utf-8 -t $test_encoding >expected &&
message two Z
message one Z
add bar Z
$(commit_msg) Z
EOF
test_cmp expected actual
'
test_expect_success 'left alignment formatting at the nth column' '
git log --pretty="format:%h %<|(40)%s" >actual &&
# complete the incomplete line at the end
echo >>actual &&
git log --pretty="tformat:%h %<|(40)%s" >actual &&
qz_to_tab_space <<EOF >expected &&
$head1 message two Z
$head2 message one Z
@ -166,10 +176,19 @@ EOF
test_cmp expected actual
'
test_expect_success 'left alignment formatting at the nth column. i18n.logOutputEncoding' '
git -c i18n.logOutputEncoding=$test_encoding log --pretty="tformat:%h %<|(40)%s" >actual &&
qz_to_tab_space <<EOF | iconv -f utf-8 -t $test_encoding >expected &&
$head1 message two Z
$head2 message one Z
$head3 add bar Z
$head4 $(commit_msg) Z
EOF
test_cmp expected actual
'
test_expect_success 'left alignment formatting with no padding' '
git log --pretty="format:%<(1)%s" >actual &&
# complete the incomplete line at the end
echo >>actual &&
git log --pretty="tformat:%<(1)%s" >actual &&
cat <<EOF >expected &&
message two
message one
@ -179,10 +198,19 @@ EOF
test_cmp expected actual
'
test_expect_success 'left alignment formatting with no padding. i18n.logOutputEncoding' '
git -c i18n.logOutputEncoding=$test_encoding log --pretty="tformat:%<(1)%s" >actual &&
cat <<EOF | iconv -f utf-8 -t $test_encoding >expected &&
message two
message one
add bar
$(commit_msg)
EOF
test_cmp expected actual
'
test_expect_success 'left alignment formatting with trunc' '
git log --pretty="format:%<(10,trunc)%s" >actual &&
# complete the incomplete line at the end
echo >>actual &&
git log --pretty="tformat:%<(10,trunc)%s" >actual &&
qz_to_tab_space <<EOF >expected &&
message ..
message ..
@ -192,10 +220,19 @@ EOF
test_cmp expected actual
'
test_expect_success 'left alignment formatting with trunc. i18n.logOutputEncoding' '
git -c i18n.logOutputEncoding=$test_encoding log --pretty="tformat:%<(10,trunc)%s" >actual &&
qz_to_tab_space <<EOF | iconv -f utf-8 -t $test_encoding >expected &&
message ..
message ..
add bar Z
initial...
EOF
test_cmp expected actual
'
test_expect_success 'left alignment formatting with ltrunc' '
git log --pretty="format:%<(10,ltrunc)%s" >actual &&
# complete the incomplete line at the end
echo >>actual &&
git log --pretty="tformat:%<(10,ltrunc)%s" >actual &&
qz_to_tab_space <<EOF >expected &&
..sage two
..sage one
@ -205,10 +242,19 @@ EOF
test_cmp expected actual
'
test_expect_success 'left alignment formatting with ltrunc. i18n.logOutputEncoding' '
git -c i18n.logOutputEncoding=$test_encoding log --pretty="tformat:%<(10,ltrunc)%s" >actual &&
qz_to_tab_space <<EOF | iconv -f utf-8 -t $test_encoding >expected &&
..sage two
..sage one
add bar Z
..${sample_utf8_part}lich
EOF
test_cmp expected actual
'
test_expect_success 'left alignment formatting with mtrunc' '
git log --pretty="format:%<(10,mtrunc)%s" >actual &&
# complete the incomplete line at the end
echo >>actual &&
git log --pretty="tformat:%<(10,mtrunc)%s" >actual &&
qz_to_tab_space <<EOF >expected &&
mess.. two
mess.. one
@ -218,10 +264,19 @@ EOF
test_cmp expected actual
'
test_expect_success 'left alignment formatting with mtrunc. i18n.logOutputEncoding' '
git -c i18n.logOutputEncoding=$test_encoding log --pretty="tformat:%<(10,mtrunc)%s" >actual &&
qz_to_tab_space <<EOF | iconv -f utf-8 -t $test_encoding >expected &&
mess.. two
mess.. one
add bar Z
init..lich
EOF
test_cmp expected actual
'
test_expect_success 'right alignment formatting' '
git log --pretty="format:%>(40)%s" >actual &&
# complete the incomplete line at the end
echo >>actual &&
git log --pretty="tformat:%>(40)%s" >actual &&
qz_to_tab_space <<EOF >expected &&
Z message two
Z message one
@ -231,10 +286,19 @@ EOF
test_cmp expected actual
'
test_expect_success 'right alignment formatting. i18n.logOutputEncoding' '
git -c i18n.logOutputEncoding=$test_encoding log --pretty="tformat:%>(40)%s" >actual &&
qz_to_tab_space <<EOF | iconv -f utf-8 -t $test_encoding >expected &&
Z message two
Z message one
Z add bar
Z $(commit_msg)
EOF
test_cmp expected actual
'
test_expect_success 'right alignment formatting at the nth column' '
git log --pretty="format:%h %>|(40)%s" >actual &&
# complete the incomplete line at the end
echo >>actual &&
git log --pretty="tformat:%h %>|(40)%s" >actual &&
qz_to_tab_space <<EOF >expected &&
$head1 message two
$head2 message one
@ -244,10 +308,19 @@ EOF
test_cmp expected actual
'
test_expect_success 'right alignment formatting at the nth column. i18n.logOutputEncoding' '
git -c i18n.logOutputEncoding=$test_encoding log --pretty="tformat:%h %>|(40)%s" >actual &&
qz_to_tab_space <<EOF | iconv -f utf-8 -t $test_encoding >expected &&
$head1 message two
$head2 message one
$head3 add bar
$head4 $(commit_msg)
EOF
test_cmp expected actual
'
test_expect_success 'right alignment formatting with no padding' '
git log --pretty="format:%>(1)%s" >actual &&
# complete the incomplete line at the end
echo >>actual &&
git log --pretty="tformat:%>(1)%s" >actual &&
cat <<EOF >expected &&
message two
message one
@ -257,10 +330,19 @@ EOF
test_cmp expected actual
'
test_expect_success 'right alignment formatting with no padding. i18n.logOutputEncoding' '
git -c i18n.logOutputEncoding=$test_encoding log --pretty="tformat:%>(1)%s" >actual &&
cat <<EOF | iconv -f utf-8 -t $test_encoding >expected &&
message two
message one
add bar
$(commit_msg)
EOF
test_cmp expected actual
'
test_expect_success 'center alignment formatting' '
git log --pretty="format:%><(40)%s" >actual &&
# complete the incomplete line at the end
echo >>actual &&
git log --pretty="tformat:%><(40)%s" >actual &&
qz_to_tab_space <<EOF >expected &&
Z message two Z
Z message one Z
@ -270,10 +352,18 @@ EOF
test_cmp expected actual
'
test_expect_success 'center alignment formatting. i18n.logOutputEncoding' '
git -c i18n.logOutputEncoding=$test_encoding log --pretty="tformat:%><(40)%s" >actual &&
qz_to_tab_space <<EOF | iconv -f utf-8 -t $test_encoding >expected &&
Z message two Z
Z message one Z
Z add bar Z
Z $(commit_msg) Z
EOF
test_cmp expected actual
'
test_expect_success 'center alignment formatting at the nth column' '
git log --pretty="format:%h %><|(40)%s" >actual &&
# complete the incomplete line at the end
echo >>actual &&
git log --pretty="tformat:%h %><|(40)%s" >actual &&
qz_to_tab_space <<EOF >expected &&
$head1 message two Z
$head2 message one Z
@ -283,10 +373,19 @@ EOF
test_cmp expected actual
'
test_expect_success 'center alignment formatting at the nth column. i18n.logOutputEncoding' '
git -c i18n.logOutputEncoding=$test_encoding log --pretty="tformat:%h %><|(40)%s" >actual &&
qz_to_tab_space <<EOF | iconv -f utf-8 -t $test_encoding >expected &&
$head1 message two Z
$head2 message one Z
$head3 add bar Z
$head4 $(commit_msg) Z
EOF
test_cmp expected actual
'
test_expect_success 'center alignment formatting with no padding' '
git log --pretty="format:%><(1)%s" >actual &&
# complete the incomplete line at the end
echo >>actual &&
git log --pretty="tformat:%><(1)%s" >actual &&
cat <<EOF >expected &&
message two
message one
@ -296,11 +395,23 @@ EOF
test_cmp expected actual
'
# save HEAD's SHA-1 digest (with no abbreviations) to use it below
# as far as the next test amends HEAD
old_head1=$(git rev-parse --verify HEAD~0)
test_expect_success 'center alignment formatting with no padding. i18n.logOutputEncoding' '
git -c i18n.logOutputEncoding=$test_encoding log --pretty="tformat:%><(1)%s" >actual &&
cat <<EOF | iconv -f utf-8 -t $test_encoding >expected &&
message two
message one
add bar
$(commit_msg)
EOF
test_cmp expected actual
'
test_expect_success 'left/right alignment formatting with stealing' '
git commit --amend -m short --author "long long long <long@me.com>" &&
git log --pretty="format:%<(10,trunc)%s%>>(10,ltrunc)% an" >actual &&
# complete the incomplete line at the end
echo >>actual &&
git log --pretty="tformat:%<(10,trunc)%s%>>(10,ltrunc)% an" >actual &&
cat <<EOF >expected &&
short long long long
message .. A U Thor
@ -309,6 +420,20 @@ initial... A U Thor
EOF
test_cmp expected actual
'
test_expect_success 'left/right alignment formatting with stealing. i18n.logOutputEncoding' '
git -c i18n.logOutputEncoding=$test_encoding log --pretty="tformat:%<(10,trunc)%s%>>(10,ltrunc)% an" >actual &&
cat <<EOF | iconv -f utf-8 -t $test_encoding >expected &&
short long long long
message .. A U Thor
add bar A U Thor
initial... A U Thor
EOF
test_cmp expected actual
'
# get new digests (with no abbreviations)
head1=$(git rev-parse --verify HEAD~0) &&
head2=$(git rev-parse --verify HEAD~1) &&
test_expect_success 'log decoration properly follows tag chain' '
git tag -a tag1 -m tag1 &&
@ -317,9 +442,9 @@ test_expect_success 'log decoration properly follows tag chain' '
git commit --amend -m shorter &&
git log --no-walk --tags --pretty="%H %d" --decorate=full >actual &&
cat <<EOF >expected &&
6a908c10688b2503073c39c9ba26322c73902bb5 (tag: refs/tags/tag2)
9f716384d92283fb915a4eee5073f030638e05f9 (tag: refs/tags/message-one)
b87e4cccdb77336ea79d89224737be7ea8e95367 (tag: refs/tags/message-two)
$head1 (tag: refs/tags/tag2)
$head2 (tag: refs/tags/message-one)
$old_head1 (tag: refs/tags/message-two)
EOF
sort actual >actual1 &&
test_cmp expected actual1

View file

@ -9,19 +9,32 @@ test_description='git rev-list --pretty=format test'
. "$TEST_DIRECTORY"/lib-terminal.sh
test_tick
# Tested non-UTF-8 encoding
test_encoding="ISO8859-1"
# String "added" in German
# (translated with Google Translate),
# encoded in UTF-8, used as a commit log message below.
added=$(printf "added (hinzugef\303\274gt) foo")
added_iso88591=$(echo "$added" | iconv -f utf-8 -t iso8859-1)
added_utf8_part=$(printf "\303\274")
added_utf8_part_iso88591=$(echo "$added_utf8_part" | iconv -f utf-8 -t $test_encoding)
added=$(printf "added (hinzugef${added_utf8_part}gt) foo")
added_iso88591=$(echo "$added" | iconv -f utf-8 -t $test_encoding)
# same but "changed"
changed=$(printf "changed (ge\303\244ndert) foo")
changed_iso88591=$(echo "$changed" | iconv -f utf-8 -t iso8859-1)
changed_utf8_part=$(printf "\303\244")
changed_utf8_part_iso88591=$(echo "$changed_utf8_part" | iconv -f utf-8 -t $test_encoding)
changed=$(printf "changed (ge${changed_utf8_part}ndert) foo")
changed_iso88591=$(echo "$changed" | iconv -f utf-8 -t $test_encoding)
# Count of char to truncate
# Number is chosen so, that non-ACSII characters
# (see $added_utf8_part and $changed_utf8_part)
# fall into truncated parts of appropriate words both from left and right
truncate_count=20
test_expect_success 'setup' '
: >foo &&
git add foo &&
git config i18n.commitEncoding iso8859-1 &&
git config i18n.commitEncoding $test_encoding &&
git commit -m "$added_iso88591" &&
head1=$(git rev-parse --verify HEAD) &&
head1_short=$(git rev-parse --verify --short $head1) &&
@ -124,9 +137,9 @@ EOF
test_format encoding %e <<EOF
commit $head2
iso8859-1
$test_encoding
commit $head1
iso8859-1
$test_encoding
EOF
test_format subject %s <<EOF
@ -136,6 +149,13 @@ commit $head1
$added
EOF
test_format subject-truncated "%<($truncate_count,trunc)%s" <<EOF
commit $head2
changed (ge${changed_utf8_part}ndert)..
commit $head1
added (hinzugef${added_utf8_part}gt..
EOF
test_format body %b <<EOF
commit $head2
commit $head1
@ -203,16 +223,16 @@ test_expect_success '%C(auto) respects --color=auto (stdout not tty)' '
)
'
iconv -f utf-8 -t iso8859-1 > commit-msg <<EOF
iconv -f utf-8 -t $test_encoding > commit-msg <<EOF
Test printing of complex bodies
This commit message is much longer than the others,
and it will be encoded in iso8859-1. We should therefore
include an iso8859 character: ¡bueno!
and it will be encoded in $test_encoding. We should therefore
include an ISO8859 character: ¡bueno!
EOF
test_expect_success 'setup complex body' '
git config i18n.commitencoding iso8859-1 &&
git config i18n.commitencoding $test_encoding &&
echo change2 >foo && git commit -a -F commit-msg &&
head3=$(git rev-parse --verify HEAD) &&
head3_short=$(git rev-parse --short $head3)
@ -220,11 +240,11 @@ test_expect_success 'setup complex body' '
test_format complex-encoding %e <<EOF
commit $head3
iso8859-1
$test_encoding
commit $head2
iso8859-1
$test_encoding
commit $head1
iso8859-1
$test_encoding
EOF
test_format complex-subject %s <<EOF
@ -236,20 +256,47 @@ commit $head1
$added_iso88591
EOF
test_format complex-subject-trunc "%<($truncate_count,trunc)%s" <<EOF
commit $head3
Test printing of c..
commit $head2
changed (ge${changed_utf8_part_iso88591}ndert)..
commit $head1
added (hinzugef${added_utf8_part_iso88591}gt..
EOF
test_format complex-subject-mtrunc "%<($truncate_count,mtrunc)%s" <<EOF
commit $head3
Test prin..ex bodies
commit $head2
changed (..dert) foo
commit $head1
added (hi..f${added_utf8_part_iso88591}gt) foo
EOF
test_format complex-subject-ltrunc "%<($truncate_count,ltrunc)%s" <<EOF
commit $head3
.. of complex bodies
commit $head2
..ged (ge${changed_utf8_part_iso88591}ndert) foo
commit $head1
.. (hinzugef${added_utf8_part_iso88591}gt) foo
EOF
test_expect_success 'prepare expected messages (for test %b)' '
cat <<-EOF >expected.utf-8 &&
commit $head3
This commit message is much longer than the others,
and it will be encoded in iso8859-1. We should therefore
include an iso8859 character: ¡bueno!
and it will be encoded in $test_encoding. We should therefore
include an ISO8859 character: ¡bueno!
commit $head2
commit $head1
EOF
iconv -f utf-8 -t iso8859-1 expected.utf-8 >expected.iso8859-1
iconv -f utf-8 -t $test_encoding expected.utf-8 >expected.ISO8859-1
'
test_format complex-body %b <expected.iso8859-1
test_format complex-body %b <expected.ISO8859-1
# Git uses i18n.commitEncoding if no i18n.logOutputEncoding set
# so unset i18n.commitEncoding to test encoding conversion
@ -264,6 +311,33 @@ commit $head1
$added
EOF
test_format complex-subject-commitencoding-unset-trunc "%<($truncate_count,trunc)%s" <<EOF
commit $head3
Test printing of c..
commit $head2
changed (ge${changed_utf8_part}ndert)..
commit $head1
added (hinzugef${added_utf8_part}gt..
EOF
test_format complex-subject-commitencoding-unset-mtrunc "%<($truncate_count,mtrunc)%s" <<EOF
commit $head3
Test prin..ex bodies
commit $head2
changed (..dert) foo
commit $head1
added (hi..f${added_utf8_part}gt) foo
EOF
test_format complex-subject-commitencoding-unset-ltrunc "%<($truncate_count,ltrunc)%s" <<EOF
commit $head3
.. of complex bodies
commit $head2
..ged (ge${changed_utf8_part}ndert) foo
commit $head1
.. (hinzugef${added_utf8_part}gt) foo
EOF
test_format complex-body-commitencoding-unset %b <expected.utf-8
test_expect_success '%x00 shows NUL' '

View file

@ -22,6 +22,9 @@ commit_msg () {
fi
}
# Tested non-UTF-8 encoding
test_encoding="ISO8859-1"
test_expect_success 'creating initial files and commits' '
test_tick &&
echo "1st file" >first &&
@ -41,7 +44,7 @@ test_expect_success 'creating initial files and commits' '
echo "1st line 2nd file" >secondfile &&
echo "2nd line 2nd file" >>secondfile &&
git -c "i18n.commitEncoding=iso8859-1" commit -a -m "$(commit_msg iso8859-1)" &&
git -c "i18n.commitEncoding=$test_encoding" commit -a -m "$(commit_msg $test_encoding)" &&
head5=$(git rev-parse --verify HEAD)
'
# git log --pretty=oneline # to see those SHA1 involved
@ -64,10 +67,10 @@ test_expect_success 'reset --hard message' '
test_cmp .expected .actual
'
test_expect_success 'reset --hard message (iso8859-1 logoutputencoding)' '
test_expect_success 'reset --hard message (ISO8859-1 logoutputencoding)' '
hex=$(git log -1 --format="%h") &&
git -c "i18n.logOutputEncoding=iso8859-1" reset --hard > .actual &&
echo HEAD is now at $hex $(commit_msg iso8859-1) > .expected &&
git -c "i18n.logOutputEncoding=$test_encoding" reset --hard > .actual &&
echo HEAD is now at $hex $(commit_msg $test_encoding) > .expected &&
test_cmp .expected .actual
'
@ -331,7 +334,7 @@ test_expect_success 'redoing the last two commits should succeed' '
echo "1st line 2nd file" >secondfile &&
echo "2nd line 2nd file" >>secondfile &&
git -c "i18n.commitEncoding=iso8859-1" commit -a -m "$(commit_msg iso8859-1)" &&
git -c "i18n.commitEncoding=$test_encoding" commit -a -m "$(commit_msg $test_encoding)" &&
check_changes $head5
'