[PATCH] git-p4: add "--path-encoding" option

[larsxschneider@gmail.com]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset=y, Size: 3589 bytes --]

From: Lars Schneider <larsxschneider@gmail.com>

Signed-off-by: Lars Schneider <larsxschneider@gmail.com>
---
 Documentation/git-p4.txt        |  4 ++++
 git-p4.py                       |  6 ++++++
 t/t9821-git-p4-path-encoding.sh | 38 ++++++++++++++++++++++++++++++++++++++
 3 files changed, 48 insertions(+)
 create mode 100755 t/t9821-git-p4-path-encoding.sh

diff --git a/Documentation/git-p4.txt b/Documentation/git-p4.txt
index 82aa5d6..98b6c0f 100644
--- a/Documentation/git-p4.txt
+++ b/Documentation/git-p4.txt
@@ -252,6 +252,10 @@ Git repository:
 	Use a client spec to find the list of interesting files in p4.
 	See the "CLIENT SPEC" section below.
 
+----path-encoding <encoding>::
+	The encoding to use when reading p4 client paths. With this option
+	non ASCII paths are properly stored in Git. For example, the encoding 'cp1252' is often used on Windows systems.
+
 -/ <path>::
 	Exclude selected depot paths when cloning or syncing.
 
diff --git a/git-p4.py b/git-p4.py
index 073f87b..2b3bfc4 100755
--- a/git-p4.py
+++ b/git-p4.py
@@ -1981,6 +1981,8 @@ class P4Sync(Command, P4UserMap):
                 optparse.make_option("--silent", dest="silent", action="store_true"),
                 optparse.make_option("--detect-labels", dest="detectLabels", action="store_true"),
                 optparse.make_option("--import-labels", dest="importLabels", action="store_true"),
+                optparse.make_option("--path-encoding", dest="pathEncoding", type="string",
+                                     help="Encoding to use for paths"),
                 optparse.make_option("--import-local", dest="importIntoRemotes", action="store_false",
                                      help="Import into refs/heads/ , not refs/remotes"),
                 optparse.make_option("--max-changes", dest="maxChanges",
@@ -2025,6 +2027,7 @@ class P4Sync(Command, P4UserMap):
         self.clientSpecDirs = None
         self.tempBranches = []
         self.tempBranchLocation = "git-p4-tmp"
+        self.pathEncoding = None
 
         if gitConfig("git-p4.syncFromOrigin") == "false":
             self.syncWithOrigin = False
@@ -2213,6 +2216,9 @@ class P4Sync(Command, P4UserMap):
             text = regexp.sub(r'$\1$', text)
             contents = [ text ]
 
+        if self.pathEncoding:
+            relPath = relPath.decode(self.pathEncoding).encode('utf8', 'replace')
+
         self.gitStream.write("M %s inline %s\n" % (git_mode, relPath))
 
         # total length...
diff --git a/t/t9821-git-p4-path-encoding.sh b/t/t9821-git-p4-path-encoding.sh
new file mode 100755
index 0000000..f6bb79c
--- /dev/null
+++ b/t/t9821-git-p4-path-encoding.sh
@@ -0,0 +1,38 @@
+#!/bin/sh
+
+test_description='Clone repositories with non ASCII paths'
+
+. ./lib-git-p4.sh
+
+test_expect_success 'start p4d' '
+	start_p4d
+'
+
+test_expect_success 'Create a repo containing cp1251 encoded paths' '
+	cd "$cli" &&
+
+	FILENAME="$(echo "a-ä_o-ö_u-ü.txt" | iconv -f utf-8 -t cp1252)" &&
+	>"$FILENAME" &&
+	p4 add "$FILENAME" &&
+	p4 submit -d "test"
+'
+
+test_expect_success 'Clone repo containing cp1251 encoded paths' '
+	git p4 clone --destination="$git" --path-encoding=cp1252 //depot &&
+	test_when_finished cleanup_git &&
+	(
+		cd "$git" &&
+		git init . &&
+		cat >expect <<-\EOF &&
+		"a-\303\244_o-\303\266_u-\303\274.txt"
+		EOF
+		git ls-files >actual &&
+		test_cmp expect actual
+	)
+'
+
+test_expect_success 'kill p4d' '
+	kill_p4d
+'
+
+test_done
-- 
2.5.1.1.g36ff854