On 01/09/15 00:10, larsxschneider@xxxxxxxxx wrote:
From: Lars Schneider <larsxschneider@xxxxxxxxx>
Signed-off-by: Lars Schneider <larsxschneider@xxxxxxxxx>
---
Documentation/git-p4.txt | 5 +++++
git-p4.py | 6 ++++++
t/t9821-git-p4-path-encoding.sh | 38 ++++++++++++++++++++++++++++++++++++++
3 files changed, 49 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..14bb79c 100644
--- a/Documentation/git-p4.txt
+++ b/Documentation/git-p4.txt
@@ -252,6 +252,11 @@ 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..1626fc5
--- /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
+
+UTF8_ESCAPED="a-\303\244_o-\303\266_u-\303\274.txt"
+
+test_expect_success 'start p4d' '
+ start_p4d
+'
+
+test_expect_success 'Create a repo containing iso8859-1 encoded paths' '
+ cd "$cli" &&
+
+ ISO8859="$(printf "$UTF8_ESCAPED" | iconv -f utf-8 -t iso8859-1)" &&
+ >"$ISO8859" &&
+ p4 add "$ISO8859" &&
+ p4 submit -d "test commit"
+'
Sorry for being persistant,
but you can't create files with names that are ISO-8859-1 encoded under Mac OS,
we end up like this:
a-%E4_o-%F6_u-%FC.txt
(And I'm still not convinced, that we need to call iconv each time we execute
the TC,
for a string that is always the same.
The string can be converted once, and embedded in the TC:
The following should work under Mac OS (but I don't have p4 to test it)
ISO8859_ESCAPED="a-\303\244_o-\303\266_u-\303\274.txt"
UTF8_ESCAPED="\141\055\303\203\302\244\137\157\055\303\203\302\266\137\165\055\303\203\302\274\056\164\170\164"
ISO8859=$(printf "$ISO8859_ESCAPED")
+
+test_expect_success 'Clone repo containing iso8859-1 encoded paths' '
+ git p4 clone --destination="$git" --path-encoding=iso8859-1 //depot &&
+ test_when_finished cleanup_git &&
+ (
+ cd "$git" &&
+ printf "$UTF8_ESCAPED\n" >expect &&
+ test_config core.quotepath false &&
+ git ls-files >actual &&
+ test_cmp expect actual
+ )
+'
The ls-files can be written shorter (if we like short code)
+ git -c core.quotepath=false ls-files >actual &&
--
To unsubscribe from this list: send the line "unsubscribe git" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html