utf8: handle systems that don't write BOM for UTF-16

When serializing UTF-16 (and UTF-32), there are three possible ways to
write the stream. One can write the data with a BOM in either big-endian
or little-endian format, or one can write the data without a BOM in
big-endian format.

Most systems' iconv implementations choose to write it with a BOM in
some endianness, since this is the most foolproof, and it is resistant
to misinterpretation on Windows, where UTF-16 and the little-endian
serialization are very common. For compatibility with Windows and to
avoid accidental misuse there, Git always wants to write UTF-16 with a
BOM, and will refuse to read UTF-16 without it.

However, musl's iconv implementation writes UTF-16 without a BOM,
relying on the user to interpret it as big-endian. This causes t0028 and
the related functionality to fail, since Git won't read the file without
a BOM.

Add a Makefile and #define knob, ICONV_OMITS_BOM, that can be set if the
iconv implementation has this behavior. When set, Git will write a BOM
manually for UTF-16 and UTF-32 and then force the data to be written in
UTF-16BE or UTF-32BE. We choose big-endian behavior here because the
tests use the raw "UTF-16" encoding, which will be big-endian when the
implementation requires this knob to be set.

Update the tests to detect this case and write test data with an added
BOM if necessary. Always write the BOM in the tests in big-endian
format, since all iconv implementations that omit a BOM must use
big-endian serialization according to the Unicode standard.

Preserve the existing behavior for systems which do not have this knob
enabled, since they may use optimized implementations, including
defaulting to the native endianness, which may improve performance.

Signed-off-by: brian m. carlson <sandals@crustytoothpaste.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

3 files changed, 50 insertions, 5 deletions

diff --git a/Makefile b/Makefile
index 0e13a5b469..457311bc31 100644
--- a/Makefile
+++ b/Makefile
@@ -259,6 +259,10 @@ all::
 # Define OLD_ICONV if your library has an old iconv(), where the second
 # (input buffer pointer) parameter is declared with type (const char **).
 #
+# Define ICONV_OMITS_BOM if your iconv implementation does not write a
+# byte-order mark (BOM) when writing UTF-16 or UTF-32 and always writes in
+# big-endian format.
+#
 # Define NO_DEFLATE_BOUND if your zlib does not have deflateBound.
 #
 # Define NO_R_TO_GCC_LINKER if your gcc does not like "-R/path/lib"
@@ -1415,6 +1419,9 @@ ifndef NO_ICONV
 		EXTLIBS += $(ICONV_LINK) -liconv
 	endif
 endif
+ifdef ICONV_OMITS_BOM
+	BASIC_CFLAGS += -DICONV_OMITS_BOM
+endif
 ifdef NEEDS_LIBGEN
 	EXTLIBS += -lgen
 endif
diff --git a/t/t0028-working-tree-encoding.sh b/t/t0028-working-tree-encoding.sh
index e58ecbfc44..500229a9bd 100755
--- a/t/t0028-working-tree-encoding.sh
+++ b/t/t0028-working-tree-encoding.sh
@@ -6,6 +6,30 @@ test_description='working-tree-encoding conversion via gitattributes'
 
 GIT_TRACE_WORKING_TREE_ENCODING=1 && export GIT_TRACE_WORKING_TREE_ENCODING
 
+test_lazy_prereq NO_UTF16_BOM '
+	test $(printf abc | iconv -f UTF-8 -t UTF-16 | wc -c) = 6
+'
+
+test_lazy_prereq NO_UTF32_BOM '
+	test $(printf abc | iconv -f UTF-8 -t UTF-32 | wc -c) = 12
+'
+
+write_utf16 () {
+	if test_have_prereq NO_UTF16_BOM
+	then
+		printf '\xfe\xff'
+	fi &&
+	iconv -f UTF-8 -t UTF-16
+}
+
+write_utf32 () {
+	if test_have_prereq NO_UTF32_BOM
+	then
+		printf '\x00\x00\xfe\xff'
+	fi &&
+	iconv -f UTF-8 -t UTF-32
+}
+
 test_expect_success 'setup test files' '
 	git config core.eol lf &&
 
@@ -13,8 +37,8 @@ test_expect_success 'setup test files' '
 	echo "*.utf16 text working-tree-encoding=utf-16" >.gitattributes &&
 	echo "*.utf16lebom text working-tree-encoding=UTF-16LE-BOM" >>.gitattributes &&
 	printf "$text" >test.utf8.raw &&
-	printf "$text" | iconv -f UTF-8 -t UTF-16 >test.utf16.raw &&
-	printf "$text" | iconv -f UTF-8 -t UTF-32 >test.utf32.raw &&
+	printf "$text" | write_utf16 >test.utf16.raw &&
+	printf "$text" | write_utf32 >test.utf32.raw &&
 	printf "\377\376"                         >test.utf16lebom.raw &&
 	printf "$text" | iconv -f UTF-8 -t UTF-32LE >>test.utf16lebom.raw &&
 
@@ -124,8 +148,8 @@ do
 		test_when_finished "rm -f crlf.utf${i}.raw lf.utf${i}.raw" &&
 		test_when_finished "git reset --hard HEAD^" &&
 
-		cat lf.utf8.raw | iconv -f UTF-8 -t UTF-${i} >lf.utf${i}.raw &&
-		cat crlf.utf8.raw | iconv -f UTF-8 -t UTF-${i} >crlf.utf${i}.raw &&
+		cat lf.utf8.raw | write_utf${i} >lf.utf${i}.raw &&
+		cat crlf.utf8.raw | write_utf${i} >crlf.utf${i}.raw &&
 		cp crlf.utf${i}.raw eol.utf${i} &&
 
 		cat >expectIndexLF <<-EOF &&
@@ -223,7 +247,7 @@ test_expect_success ICONV_SHIFT_JIS 'check roundtrip encoding' '
 
 	text="hallo there!\nroundtrip test here!" &&
 	printf "$text" | iconv -f UTF-8 -t SHIFT-JIS >roundtrip.shift &&
-	printf "$text" | iconv -f UTF-8 -t UTF-16 >roundtrip.utf16 &&
+	printf "$text" | write_utf16 >roundtrip.utf16 &&
 	echo "*.shift text working-tree-encoding=SHIFT-JIS" >>.gitattributes &&
 
 	# SHIFT-JIS encoded files are round-trip checked by default...
diff --git a/utf8.c b/utf8.c
index 83824dc2f4..3b42fadffd 100644
--- a/utf8.c
+++ b/utf8.c
@@ -559,6 +559,10 @@ char *reencode_string_len(const char *in, size_t insz,
 	/*
 	 * For writing, UTF-16 iconv typically creates "UTF-16BE-BOM"
 	 * Some users under Windows want the little endian version
+	 *
+	 * We handle UTF-16 and UTF-32 ourselves only if the platform does not
+	 * provide a BOM (which we require), since we want to match the behavior
+	 * of the system tools and libc as much as possible.
 	 */
 	if (same_utf_encoding("UTF-16LE-BOM", out_encoding)) {
 		bom_str = utf16_le_bom;
@@ -568,6 +572,16 @@ char *reencode_string_len(const char *in, size_t insz,
 		bom_str = utf16_be_bom;
 		bom_len = sizeof(utf16_be_bom);
 		out_encoding = "UTF-16BE";
+#ifdef ICONV_OMITS_BOM
+	} else if (same_utf_encoding("UTF-16", out_encoding)) {
+		bom_str = utf16_be_bom;
+		bom_len = sizeof(utf16_be_bom);
+		out_encoding = "UTF-16BE";
+	} else if (same_utf_encoding("UTF-32", out_encoding)) {
+		bom_str = utf32_be_bom;
+		bom_len = sizeof(utf32_be_bom);
+		out_encoding = "UTF-32BE";
+#endif
 	}
 
 	conv = iconv_open(out_encoding, in_encoding);