##// END OF EJS Templates
diffstat: fix parsing of filenames with spaces...
diffstat: fix parsing of filenames with spaces The patch changes the output of "hg diff --stat" when one file whose filename has spaces has changed, making it get the full filename instead of just the substring between the last space and the end of the filename. It also changes the diffstat generated by "hg email -d" when one of the commit messages starts with "diff". Because of the regex used to parse the filename, the diffstat generated by "hg email -d" will still be not correct if a commit message starts with "diff -r ". Before the patch Mercurial has the following behavior: $ echo "foobar">"file with spaces" $ hg add "file with spaces" $ hg diff --stat spaces | 1 + 1 files changed, 1 insertions(+), 0 deletions(-) $ hg diff --git --stat file with spaces | 1 + 1 files changed, 1 insertions(+), 0 deletions(-) After the patch: $ echo "foobar">"file with spaces" $ hg add "file with spaces" $ hg diff --stat file with spaces | 1 + 1 files changed, 1 insertions(+), 0 deletions(-) $ hg diff --git --stat file with spaces | 1 + 1 files changed, 1 insertions(+), 0 deletions(-) Before the patch: $ hg add mercurial/patch.py tests/tests-diffstat.t $ hg commit -m "diffstat: fix parsing of filenames" $ hg email -d --test tip This patch series consists of 1 patches. diffstat: fix parsing of filenames [...] filenames | 0 mercurial/patch.py | 6 ++++-- tests/test-diffstat.t | 17 +++++++++++++++++ 3 files changed, 21 insertions(+), 2 deletions(-) [...] After the patch: $ hg email -d --test tip This patch series consists of 1 patches. diffstat: fix parsing of filenames [...] mercurial/patch.py | 6 ++++-- tests/test-diffstat.t | 17 +++++++++++++++++ 3 files changed, 21 insertions(+), 2 deletions(-) [...]

File last commit:

r13047:6c375e07 default
r13395:104c9ed9 default
Show More
test-encoding.t
243 lines | 6.7 KiB | text/troff | Tads3Lexer
Test character encoding
$ hg init t
$ cd t
we need a repo with some legacy latin-1 changesets
$ hg unbundle $TESTDIR/legacy-encoding.hg
adding changesets
adding manifests
adding file changes
added 2 changesets with 2 changes to 1 files
(run 'hg update' to get a working copy)
$ hg co
1 files updated, 0 files merged, 0 files removed, 0 files unresolved
$ python << EOF
> f = file('latin-1', 'w'); f.write("latin-1 e' encoded: \xe9"); f.close()
> f = file('utf-8', 'w'); f.write("utf-8 e' encoded: \xc3\xa9"); f.close()
> f = file('latin-1-tag', 'w'); f.write("\xe9"); f.close()
> EOF
should fail with encoding error
$ echo "plain old ascii" > a
$ hg st
M a
? latin-1
? latin-1-tag
? utf-8
$ HGENCODING=ascii hg ci -l latin-1
transaction abort!
rollback completed
abort: decoding near ' encoded: \xe9': 'ascii' codec can't decode byte 0xe9 in position 20: ordinal not in range(128)! (esc)
[255]
these should work
$ echo "latin-1" > a
$ HGENCODING=latin-1 hg ci -l latin-1
$ echo "utf-8" > a
$ HGENCODING=utf-8 hg ci -l utf-8
$ HGENCODING=latin-1 hg tag `cat latin-1-tag`
$ HGENCODING=latin-1 hg branch `cat latin-1-tag`
marked working directory as branch \xe9 (esc)
$ HGENCODING=latin-1 hg ci -m 'latin1 branch'
$ rm .hg/branch
hg log (ascii)
$ hg --encoding ascii log
changeset: 5:093c6077d1c8
branch: ?
tag: tip
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin1 branch
changeset: 4:94db611b4196
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: Added tag ? for changeset ca661e7520de
changeset: 3:ca661e7520de
tag: ?
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: utf-8 e' encoded: ?
changeset: 2:650c6f3d55dd
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin-1 e' encoded: ?
changeset: 1:0e5b7e3f9c4a
user: test
date: Mon Jan 12 13:46:40 1970 +0000
summary: koi8-r: ????? = u'\u0440\u0442\u0443\u0442\u044c'
changeset: 0:1e78a93102a3
user: test
date: Mon Jan 12 13:46:40 1970 +0000
summary: latin-1 e': ? = u'\xe9'
hg log (latin-1)
$ hg --encoding latin-1 log
changeset: 5:093c6077d1c8
branch: \xe9 (esc)
tag: tip
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin1 branch
changeset: 4:94db611b4196
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: Added tag \xe9 for changeset ca661e7520de (esc)
changeset: 3:ca661e7520de
tag: \xe9 (esc)
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: utf-8 e' encoded: \xe9 (esc)
changeset: 2:650c6f3d55dd
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin-1 e' encoded: \xe9 (esc)
changeset: 1:0e5b7e3f9c4a
user: test
date: Mon Jan 12 13:46:40 1970 +0000
summary: koi8-r: \xd2\xd4\xd5\xd4\xd8 = u'\\u0440\\u0442\\u0443\\u0442\\u044c' (esc)
changeset: 0:1e78a93102a3
user: test
date: Mon Jan 12 13:46:40 1970 +0000
summary: latin-1 e': \xe9 = u'\\xe9' (esc)
hg log (utf-8)
$ hg --encoding utf-8 log
changeset: 5:093c6077d1c8
branch: \xc3\xa9 (esc)
tag: tip
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin1 branch
changeset: 4:94db611b4196
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: Added tag \xc3\xa9 for changeset ca661e7520de (esc)
changeset: 3:ca661e7520de
tag: \xc3\xa9 (esc)
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: utf-8 e' encoded: \xc3\xa9 (esc)
changeset: 2:650c6f3d55dd
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin-1 e' encoded: \xc3\xa9 (esc)
changeset: 1:0e5b7e3f9c4a
user: test
date: Mon Jan 12 13:46:40 1970 +0000
summary: koi8-r: \xc3\x92\xc3\x94\xc3\x95\xc3\x94\xc3\x98 = u'\\u0440\\u0442\\u0443\\u0442\\u044c' (esc)
changeset: 0:1e78a93102a3
user: test
date: Mon Jan 12 13:46:40 1970 +0000
summary: latin-1 e': \xc3\xa9 = u'\\xe9' (esc)
hg tags (ascii)
$ HGENCODING=ascii hg tags
tip 5:093c6077d1c8
? 3:ca661e7520de
hg tags (latin-1)
$ HGENCODING=latin-1 hg tags
tip 5:093c6077d1c8
\xe9 3:ca661e7520de (esc)
hg tags (utf-8)
$ HGENCODING=utf-8 hg tags
tip 5:093c6077d1c8
\xc3\xa9 3:ca661e7520de (esc)
hg branches (ascii)
$ HGENCODING=ascii hg branches
? 5:093c6077d1c8
default 4:94db611b4196 (inactive)
hg branches (latin-1)
$ HGENCODING=latin-1 hg branches
\xe9 5:093c6077d1c8 (esc)
default 4:94db611b4196 (inactive)
hg branches (utf-8)
$ HGENCODING=utf-8 hg branches
\xc3\xa9 5:093c6077d1c8 (esc)
default 4:94db611b4196 (inactive)
$ echo '[ui]' >> .hg/hgrc
$ echo 'fallbackencoding = koi8-r' >> .hg/hgrc
hg log (utf-8)
$ HGENCODING=utf-8 hg log
changeset: 5:093c6077d1c8
branch: \xc3\xa9 (esc)
tag: tip
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin1 branch
changeset: 4:94db611b4196
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: Added tag \xc3\xa9 for changeset ca661e7520de (esc)
changeset: 3:ca661e7520de
tag: \xc3\xa9 (esc)
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: utf-8 e' encoded: \xc3\xa9 (esc)
changeset: 2:650c6f3d55dd
user: test
date: Thu Jan 01 00:00:00 1970 +0000
summary: latin-1 e' encoded: \xc3\xa9 (esc)
changeset: 1:0e5b7e3f9c4a
user: test
date: Mon Jan 12 13:46:40 1970 +0000
summary: koi8-r: \xd1\x80\xd1\x82\xd1\x83\xd1\x82\xd1\x8c = u'\\u0440\\u0442\\u0443\\u0442\\u044c' (esc)
changeset: 0:1e78a93102a3
user: test
date: Mon Jan 12 13:46:40 1970 +0000
summary: latin-1 e': \xd0\x98 = u'\\xe9' (esc)
hg log (dolphin)
$ HGENCODING=dolphin hg log
abort: unknown encoding: dolphin, please check your locale settings
[255]
$ HGENCODING=ascii hg branch `cat latin-1-tag`
abort: decoding near '\xe9': 'ascii' codec can't decode byte 0xe9 in position 0: ordinal not in range(128)! (esc)
[255]
$ cp latin-1-tag .hg/branch
$ HGENCODING=latin-1 hg ci -m 'auto-promote legacy name'