[PATCH v6] Add git-p4.fallbackEncoding

From

TVTzadik Vanderhoof <tzadik.vanderhoof@gmail.com>

Date

Apr 29, 2021, 07:39 UTC

Message-ID

<20210429073905.837-1-tzadik.vanderhoof@gmail.com>

In-Reply-To

<20210428145824.43c4t7hkjfqjyspb@tb-raspi4>

    File "C:/Program Files/Git/bin/git-p4.py", line 774, in p4CmdList
        value = value.decode() UnicodeDecodeError: 'utf-8' codec can't
        decode byte Ox93 in position 42: invalid start byte

Signed-off-by: Tzadik Vanderhoof <tzadik.vanderhoof@gmail.com>
---
 Documentation/git-p4.txt                   |  9 ++
 git-p4.py                                  | 11 ++-
 t/t9836-git-p4-config-fallback-encoding.sh | 98 ++++++++++++++++++++++
 3 files changed, 117 insertions(+), 1 deletion(-)
 create mode 100755 t/t9836-git-p4-config-fallback-encoding.sh

diff --git a/Documentation/git-p4.txt b/Documentation/git-p4.txt
index f89e68b424..86d3ffa644 100644
--- a/Documentation/git-p4.txt
+++ b/Documentation/git-p4.txt
@@ -638,6 +638,15 @@ git-p4.pathEncoding::
 	to transcode the paths to UTF-8. As an example, Perforce on Windows
 	often uses "cp1252" to encode path names.
 
+git-p4.fallbackEncoding::
+	Perforce changeset descriptions can be stored in any encoding.
+	Git-p4 first tries to interpret each description as UTF-8. If that
+	fails, this config allows another encoding to be tried. You can specify,
+	for example, "cp1252". If git-p4.fallbackEncoding is "replace", UTF-8 will
+	be used, with invalid UTF-8 characters replaced by the Unicode replacement
+	character. The default is "none": there is no fallback, and any non UTF-8
+	character will cause git-p4 to immediately fail.
+
 git-p4.largeFileSystem::
 	Specify the system that is used for large (binary) files. Please note
 	that large file systems do not support the 'git p4 submit' command.
diff --git a/git-p4.py b/git-p4.py
index 09c9e93ac4..202fb01bdf 100755
--- a/git-p4.py
+++ b/git-p4.py
@@ -771,7 +771,16 @@ def p4CmdList(cmd, stdin=None, stdin_mode='w+b', cb=None, skip_info=False,
                 for key, value in entry.items():
                     key = key.decode()
                     if isinstance(value, bytes) and not (key in ('data', 'path', 'clientFile') or key.startswith('depotFile')):
-                        value = value.decode()
+                        try:
+                            value = value.decode()
+                        except UnicodeDecodeError:
+                            fallbackEncoding = gitConfig("git-p4.fallbackEncoding").lower() or 'none'
+                            if fallbackEncoding == 'none':
+                                raise Exception("UTF-8 decoding failed. Consider using git config git-p4.fallbackEncoding")
+                            elif fallbackEncoding == 'replace':
+                                value = value.decode(errors='replace')
+                            else:
+                                value = value.decode(encoding=fallbackEncoding)
                     decoded_entry[key] = value
                 # Parse out data if it's an error response
                 if decoded_entry.get('code') == 'error' and 'data' in decoded_entry:
diff --git a/t/t9836-git-p4-config-fallback-encoding.sh b/t/t9836-git-p4-config-fallback-encoding.sh
new file mode 100755
index 0000000000..901bb3759d
--- /dev/null
+++ b/t/t9836-git-p4-config-fallback-encoding.sh
@@ -0,0 +1,98 @@
+#!/bin/sh
+
+test_description='test git-p4.fallbackEncoding config'
+
+GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME=main
+export GIT_TEST_DEFAULT_INITIAL_BRANCH_NAME
+
+. ./lib-git-p4.sh
+
+test_expect_success 'start p4d' '
+	start_p4d
+'
+
+test_expect_success 'add Unicode description' '
+	cd "$cli" &&
+	echo file1 >file1 &&
+	p4 add file1 &&
+	p4 submit -d documentación
+'
+
+# Unicode descriptions cause "git p4 clone" to crash with a UnicodeDecodeError in some
+# environments. This test determines if that is the case in our environment. If so,
+# we create a file called "clone_fails". In subsequent tests, we check whether that
+# file exists to determine what behavior to expect.
+
+clone_fails="$TRASH_DIRECTORY/clone_fails"
+
+# If clone fails with git-p4.fallbackEncoding set to "none", create the "clone_fails" file,
+# and make sure the error message is correct
+
+test_expect_success 'clone with git-p4.fallbackEncoding set to "none"' '
+	git config --global git-p4.fallbackEncoding none &&
+	test_when_finished cleanup_git && {
+		git p4 clone --dest="$git" //depot@all 2>error || (
+			>"$clone_fails" &&
+			grep "UTF-8 decoding failed. Consider using git config git-p4.fallbackEncoding" error
+		)
+	}
+'
+
+# If clone fails with git-p4.fallbackEncoding set to "none", it should also fail when it's unset,
+# also with the correct error message.  Otherwise the clone should succeed.
+
+test_expect_success 'clone with git-p4.fallbackEncoding unset' '
+	git config --global --unset git-p4.fallbackEncoding &&
+	test_when_finished cleanup_git && {
+		(
+			test -f "$clone_fails" &&
+			test_must_fail git p4 clone --dest="$git" //depot@all 2>error &&
+			grep "UTF-8 decoding failed. Consider using git config git-p4.fallbackEncoding" error
+		) ||
+		(
+			! test -f "$clone_fails" &&
+			git p4 clone --dest="$git" //depot@all 2>error
+		)
+	}
+'
+
+# Whether or not "clone_fails" exists, setting git-p4.fallbackEncoding
+# to "cp1252" should cause clone to succeed and get the right description
+
+test_expect_success 'clone with git-p4.fallbackEncoding set to "cp1252"' '
+	git config --global git-p4.fallbackEncoding cp1252 &&
+	test_when_finished cleanup_git &&
+	(
+		git p4 clone --dest="$git" //depot@all &&
+		cd "$git" &&
+		git log --oneline >log &&
+		desc=$(head -1 log | cut -d" " -f2) &&
+		test "$desc" = "documentación"
+	)
+'
+
+# Setting git-p4.fallbackEncoding to "replace" should always cause clone to succeed.
+# If "clone_fails" exists, the description should contain the Unicode replacement
+# character, otherwise the description should be correct (since we're on a system that
+# doesn't have the Unicode issue)
+
+test_expect_success 'clone with git-p4.fallbackEncoding set to "replace"' '
+	git config --global git-p4.fallbackEncoding replace &&
+	test_when_finished cleanup_git &&
+	(
+		git p4 clone --dest="$git" //depot@all &&
+		cd "$git" &&
+		git log --oneline >log &&
+		desc=$(head -1 log | cut -d" " -f2) &&
+		{
+			(test -f "$clone_fails" &&
+				test "$desc" = "documentaci�n"
+			) ||
+			(! test -f "$clone_fails" &&
+				test "$desc" = "documentación"
+			)
+		}
+	)
+'
+
+test_done

-- 
2.31.1