larsxschneider@xxxxxxxxx writes: > From: Lars Schneider <larsxschneider@xxxxxxxxx> > > In a9e38359e3 we taught git-p4 a way to re-encode path names from what > was used in Perforce to UTF-8. This path re-encoding worked properly for > "added" paths. "Removed" paths were not re-encoded and therefore > different from the "added" paths. Consequently, these files were not > removed in a git-p4 cloned Git repository because the path names did not > match. > > Fix this by moving the re-encoding to a place that affects "added" and > "removed" paths. Add a test to demonstrate the issue. > > Signed-off-by: Lars Schneider <larsxschneider@xxxxxxxxx> > --- Thanks. The above description makes me wonder what happens to "modified" paths, but presumably they are handled in a separate codepath? Or does this also cover not just "removed" but also paths with any change? Luke, does this look good? > Notes: > Base Commit: d1271bddd4 (v2.11.0) > Diff on Web: https://github.com/git/git/compare/d1271bddd4...larsxschneider:05a82caa69 > Checkout: git fetch https://github.com/larsxschneider/git git-p4/fix-path-encoding-v1 && git checkout 05a82caa69 > > git-p4.py | 19 +++++++++---------- > t/t9822-git-p4-path-encoding.sh | 16 ++++++++++++++++ > 2 files changed, 25 insertions(+), 10 deletions(-) > > diff --git a/git-p4.py b/git-p4.py > index fd5ca52462..8f311cb4e8 100755 > --- a/git-p4.py > +++ b/git-p4.py > @@ -2366,6 +2366,15 @@ class P4Sync(Command, P4UserMap): > break > > path = wildcard_decode(path) > + try: > + path.decode('ascii') > + except: > + encoding = 'utf8' > + if gitConfig('git-p4.pathEncoding'): > + encoding = gitConfig('git-p4.pathEncoding') > + path = path.decode(encoding, 'replace').encode('utf8', 'replace') > + if self.verbose: > + print 'Path with non-ASCII characters detected. Used %s to encode: %s ' % (encoding, path) > return path > > def splitFilesIntoBranches(self, commit): > @@ -2495,16 +2504,6 @@ class P4Sync(Command, P4UserMap): > text = regexp.sub(r'$\1$', text) > contents = [ text ] > > - try: > - relPath.decode('ascii') > - except: > - encoding = 'utf8' > - if gitConfig('git-p4.pathEncoding'): > - encoding = gitConfig('git-p4.pathEncoding') > - relPath = relPath.decode(encoding, 'replace').encode('utf8', 'replace') > - if self.verbose: > - print 'Path with non-ASCII characters detected. Used %s to encode: %s ' % (encoding, relPath) > - > if self.largeFileSystem: > (git_mode, contents) = self.largeFileSystem.processContent(git_mode, relPath, contents) > > diff --git a/t/t9822-git-p4-path-encoding.sh b/t/t9822-git-p4-path-encoding.sh > index 7b83e696a9..c78477c19b 100755 > --- a/t/t9822-git-p4-path-encoding.sh > +++ b/t/t9822-git-p4-path-encoding.sh > @@ -51,6 +51,22 @@ test_expect_success 'Clone repo containing iso8859-1 encoded paths with git-p4.p > ) > ' > > +test_expect_success 'Delete iso8859-1 encoded paths and clone' ' > + ( > + cd "$cli" && > + ISO8859="$(printf "$ISO8859_ESCAPED")" && > + p4 delete "$ISO8859" && > + p4 submit -d "remove file" > + ) && > + git p4 clone --destination="$git" //depot@all && > + test_when_finished cleanup_git && > + ( > + cd "$git" && > + git -c core.quotepath=false ls-files >actual && > + test_must_be_empty actual > + ) > +' > + > test_expect_success 'kill p4d' ' > kill_p4d > '