[PATCH v6] git-p4: add config git-p4.pathEncoding

[larsxschneider@gmail.com]

From: Lars Schneider <larsxschneider@gmail.com>

Perforce keeps the encoding of a path as given by the originating OS.
Git expects paths encoded as UTF-8. Add a config to tell git-p4 what
encoding Perforce had used for the paths. This encoding is used to
transcode the paths to UTF-8. As an example, Perforce on Windows often
uses “cp1252” to encode path names.

Signed-off-by: Lars Schneider <larsxschneider@gmail.com>
Acked-by: Luke Diamand <luke@diamand.org>
Signed-off-by: Lars Schneider <larsxschneider@gmail.com>
---
 Documentation/git-p4.txt        |  7 +++++
 git-p4.py                       | 11 ++++++++
 t/t9822-git-p4-path-encoding.sh | 60 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 78 insertions(+)
 create mode 100755 t/t9822-git-p4-path-encoding.sh

diff --git a/Documentation/git-p4.txt b/Documentation/git-p4.txt
index 82aa5d6..12a57d4 100644
--- a/Documentation/git-p4.txt
+++ b/Documentation/git-p4.txt
@@ -510,6 +510,13 @@ git-p4.useClientSpec::
 	option '--use-client-spec'.  See the "CLIENT SPEC" section above.
 	This variable is a boolean, not the name of a p4 client.
 
+git-p4.pathEncoding::
+	Perforce keeps the encoding of a path as given by the originating OS.
+	Git expects paths encoded as UTF-8. Use this config to tell git-p4
+	what encoding Perforce had used for the paths. This encoding is used
+	to transcode the paths to UTF-8. As an example, Perforce on Windows
+	often uses “cp1252” to encode path names.
+
 Submit variables
 ~~~~~~~~~~~~~~~~
 git-p4.detectRenames::
diff --git a/git-p4.py b/git-p4.py
index 073f87b..b1ad86d 100755
--- a/git-p4.py
+++ b/git-p4.py
@@ -2213,6 +2213,17 @@ class P4Sync(Command, P4UserMap):
             text = regexp.sub(r'$\1$', text)
             contents = [ text ]
 
+        if gitConfig("git-p4.pathEncoding"):
+            relPath = relPath.decode(gitConfig("git-p4.pathEncoding")).encode('utf8', 'replace')
+        elif self.verbose:
+            try:
+                relPath.decode('ascii')
+            except:
+                print (
+                    "Path with Non-ASCII characters detected and no path encoding defined. "
+                    "Please check the encoding: %s" % relPath
+                )
+
         self.gitStream.write("M %s inline %s\n" % (git_mode, relPath))
 
         # total length...
diff --git a/t/t9822-git-p4-path-encoding.sh b/t/t9822-git-p4-path-encoding.sh
new file mode 100755
index 0000000..e507ad7
--- /dev/null
+++ b/t/t9822-git-p4-path-encoding.sh
@@ -0,0 +1,60 @@
+#!/bin/sh
+
+test_description='Clone repositories with non ASCII paths'
+
+. ./lib-git-p4.sh
+
+UTF8_ESCAPED="a-\303\244_o-\303\266_u-\303\274.txt"
+ISO8859_ESCAPED="a-\344_o-\366_u-\374.txt"
+
+test_expect_success 'start p4d' '
+	start_p4d
+'
+
+test_expect_success 'Create a repo containing iso8859-1 encoded paths' '
+	(
+		cd "$cli" &&
+		ISO8859="$(printf "$ISO8859_ESCAPED")" &&
+		echo content123 >"$ISO8859" &&
+		p4 add "$ISO8859" &&
+		p4 submit -d "test commit"
+	)
+'
+
+test_expect_success 'Clone repo containing iso8859-1 encoded paths without git-p4.pathEncoding' '
+	git p4 clone --destination="$git" //depot &&
+	test_when_finished cleanup_git &&
+	(
+		cd "$git" &&
+		UTF8="$(printf "$UTF8_ESCAPED")" &&
+		echo $UTF8 >expect &&
+		git -c core.quotepath=false ls-files >actual &&
+		test_must_fail test_cmp expect actual
+	)
+'
+
+test_expect_success 'Clone repo containing iso8859-1 encoded paths with git-p4.pathEncoding' '
+
+	test_when_finished cleanup_git &&
+	(
+		cd "$git" &&
+		git init . &&
+		test_config git-p4.pathEncoding iso8859-1 &&
+		git p4 clone --use-client-spec --destination="$git" //depot &&
+		UTF8="$(printf "$UTF8_ESCAPED")" &&
+		echo $UTF8 >expect &&
+		git -c core.quotepath=false ls-files >actual &&
+		test_cmp expect actual &&
+		cat >expect <<-\EOF &&
+		content123
+		EOF
+		cat $UTF8 >actual &&
+		test_cmp expect actual
+	)
+'
+
+test_expect_success 'kill p4d' '
+	kill_p4d
+'
+
+test_done
-- 
1.9.5 (Apple Git-50.3)