git-p4: handle utf16 filetype properly

One of the filetypes that p4 supports is utf16.  Its behavior is
odd in this case.  The data delivered through "p4 -G print" is
not encoded in utf16, although "p4 print -o" will produce the
proper utf16-encoded file.

When dealing with this filetype, discard the data from -G, and
instead read the contents directly.

An alternate approach would be to try to encode the data in
python.  That worked for true utf16 files, but for other files
marked as utf16, p4 delivers mangled text in no recognizable encoding.

Add a test case to check utf16 handling, and +k and +ko handling.

Reported-by: Chris Li <git@chrisli.org>
Acked-by: Luke Diamand <luke@diamand.org>
Signed-off-by: Pete Wyckoff <pw@padd.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 108 insertions, 0 deletions

diff --git a/t/t9802-git-p4-filetype.sh b/t/t9802-git-p4-filetype.sh
new file mode 100755
index 000000000..3b358ef8d
--- /dev/null
+++ b/t/t9802-git-p4-filetype.sh
@@ -0,0 +1,108 @@
+#!/bin/sh
+
+test_description='git-p4 p4 filetype tests'
+
+. ./lib-git-p4.sh
+
+test_expect_success 'start p4d' '
+	start_p4d
+'
+
+test_expect_success 'utf-16 file create' '
+	(
+		cd "$cli" &&
+
+		# p4 saves this verbatim
+		printf "three\nline\ntext\n" >f-ascii &&
+		p4 add -t text f-ascii &&
+
+		# p4 adds \377\376 header
+		cp f-ascii f-ascii-as-utf16 &&
+		p4 add -t utf16 f-ascii-as-utf16 &&
+
+		# p4 saves this exactly as iconv produced it
+		printf "three\nline\ntext\n" | iconv -f ascii -t utf-16 >f-utf16 &&
+		p4 add -t utf16 f-utf16 &&
+
+		# this also is unchanged
+		cp f-utf16 f-utf16-as-text &&
+		p4 add -t text f-utf16-as-text &&
+
+		p4 submit -d "f files" &&
+
+		# force update of client files
+		p4 sync -f
+	)
+'
+
+test_expect_success 'utf-16 file test' '
+	test_when_finished cleanup_git &&
+	"$GITP4" clone --dest="$git" //depot@all &&
+	(
+		cd "$git" &&
+
+		test_cmp "$cli/f-ascii" f-ascii &&
+		test_cmp "$cli/f-ascii-as-utf16" f-ascii-as-utf16 &&
+		test_cmp "$cli/f-utf16" f-utf16 &&
+		test_cmp "$cli/f-utf16-as-text" f-utf16-as-text
+	)
+'
+
+test_expect_success 'keyword file create' '
+	(
+		cd "$cli" &&
+
+		printf "id\n\$Id\$\n\$Author\$\ntext\n" >k-text-k &&
+		p4 add -t text+k k-text-k &&
+
+		cp k-text-k k-text-ko &&
+		p4 add -t text+ko k-text-ko &&
+
+		cat k-text-k | iconv -f ascii -t utf-16 >k-utf16-k &&
+		p4 add -t utf16+k k-utf16-k &&
+
+		cp k-utf16-k k-utf16-ko &&
+		p4 add -t utf16+ko k-utf16-ko &&
+
+		p4 submit -d "k files" &&
+		p4 sync -f
+	)
+'
+
+build_smush() {
+	cat >k_smush.py <<-\EOF &&
+	import re, sys
+	sys.stdout.write(re.sub(r'(?i)\$(Id|Header|Author|Date|DateTime|Change|File|Revision):[^$]*\$', r'$\1$', sys.stdin.read()))
+	EOF
+	cat >ko_smush.py <<-\EOF
+	import re, sys
+	sys.stdout.write(re.sub(r'(?i)\$(Id|Header):[^$]*\$', r'$\1$', sys.stdin.read()))
+	EOF
+}
+
+test_expect_success 'keyword file test' '
+	build_smush &&
+	test_when_finished rm -f k_smush.py ko_smush.py &&
+	test_when_finished cleanup_git &&
+	"$GITP4" clone --dest="$git" //depot@all &&
+	(
+		cd "$git" &&
+
+		# text, ensure unexpanded
+		"$PYTHON_PATH" "$TRASH_DIRECTORY/k_smush.py" <"$cli/k-text-k" >cli-k-text-k-smush &&
+		test_cmp cli-k-text-k-smush k-text-k &&
+		"$PYTHON_PATH" "$TRASH_DIRECTORY/ko_smush.py" <"$cli/k-text-ko" >cli-k-text-ko-smush &&
+		test_cmp cli-k-text-ko-smush k-text-ko &&
+
+		# utf16, even though p4 expands keywords, git-p4 does not
+		# try to undo that
+		test_cmp "$cli/k-utf16-k" k-utf16-k &&
+		test_cmp "$cli/k-utf16-ko" k-utf16-ko
+	)
+'
+
+test_expect_success 'kill p4d' '
+	kill_p4d
+'
+
+test_done