git-p4: fix git-p4.pathEncoding for removed files

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@gmail.com>
Reviewed-by: Luke Diamand <luke@diamand.org>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/git-p4.py b/git-p4.py
index c33dece5d29ebf59fa0b78a9fda2de48114b1fe3..5c6d8c20dac3fafc96d9f82ca1c486c4bfe4cd3e 100755 (executable)
--- a/git-p4.py
+++ b/git-p4.py
@@ -2388,11 +2388,24 @@ class P4Sync(Command, P4UserMap):
             self.gitStream.write(d)
         self.gitStream.write('\n')
 
+    def encodeWithUTF8(self, 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
+
     # output one file from the P4 stream
     # - helper for streamP4Files
 
     def streamOneP4File(self, file, contents):
         relPath = self.stripRepoPath(file['depotFile'], self.branchPrefixes)
+        relPath = self.encodeWithUTF8(relPath)
         if verbose:
             size = int(self.stream_file['fileSize'])
             sys.stdout.write('\r%s --> %s (%i MB)\n' % (file['depotFile'], relPath, size/1024/1024))
@@ -2465,16 +2478,6 @@ 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)
 
@@ -2482,6 +2485,7 @@ class P4Sync(Command, P4UserMap):
 
     def streamOneP4Deletion(self, file):
         relPath = self.stripRepoPath(file['path'], self.branchPrefixes)
+        relPath = self.encodeWithUTF8(relPath)
         if verbose:
             sys.stdout.write("delete %s\n" % relPath)
             sys.stdout.flush()

diff --git a/t/t9822-git-p4-path-encoding.sh b/t/t9822-git-p4-path-encoding.sh
index 7b83e696a92a5c97e8c022af2601d60a95ab1cbc..c78477c19b4330f990c0cdd7d96997b8ed2ed02c 100755 (executable)
--- 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
 '