[PATCH v4] git-p4: add config git-p4.pathEncoding

From

larsxschneider@gmail.com <larsxschneider@gmail.com>

Date

Sep 2, 2015, 14:57 UTC

Message-ID

<1441205853-52065-2-git-send-email-larsxschneider@gmail.com>

In-Reply-To

<1441205853-52065-1-git-send-email-larsxschneider@gmail.com>

From: Lars Schneider <larsxschneider@gmail.com>

Signed-off-by: Lars Schneider <larsxschneider@gmail.com>
---
 Documentation/git-p4.txt        |  7 +++++
 git-p4.py                       |  3 ++
 t/t9822-git-p4-path-encoding.sh | 65 +++++++++++++++++++++++++++++++++++++++++
 3 files changed, 75 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..bf3adf9 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 my Windows
+	box uses “cp1252” to encode path names.
+
 Submit variables
 ~~~~~~~~~~~~~~~~
 git-p4.detectRenames::
diff --git a/git-p4.py b/git-p4.py
index 073f87b..706fcdc 100755
--- a/git-p4.py
+++ b/git-p4.py
@@ -2213,6 +2213,9 @@ 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')
+
         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..3a1779a
--- /dev/null
+++ b/t/t9822-git-p4-path-encoding.sh
@@ -0,0 +1,65 @@
+#!/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="\141\55\344\137\157\55\366\137\165\55\374\56\164\170\164"
+
+# You can generate the ISO8859_ESCAPED with the following command:
+# printf "$UTF8_ESCAPED" | \
+# iconv -f utf-8 -t iso8859-1 | \
+# xxd -ps -u -c 1 | xargs bash -c 'for v; do echo "ibase=16; obase=8; $v" | bc; done' bash | \
+# tr "\n" "\\"
+
+test_expect_success 'start p4d' '
+	start_p4d
+'
+
+test_expect_success 'Create a repo containing iso8859-1 encoded paths' '
+	cd "$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 . &&
+		git 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)