[PATCH v2 1/1] Support working-tree-encoding "UTF-16LE-BOM"

[tboegi@web.de]

From: Torsten Bögershausen <tboegi@web.de>

Users who want UTF-16 files in the working tree set the .gitattributes
like this:
test.txt working-tree-encoding=UTF-16

The unicode standard itself defines 3 possible ways how to encode UTF-16.
The following 3 versions convert all back to 'g' 'i' 't' in UTF-8:

a) UTF-16, without BOM, big endian:
$ printf "\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c
0000000    g   i   t

b) UTF-16, with BOM, little endian:
$ printf "\377\376g\000i\000t\000" | iconv -f UTF-16 -t UTF-8 | od -c
0000000    g   i   t

c) UTF-16, with BOM, big endian:
$ printf "\376\377\000g\000i\000t" | iconv -f UTF-16 -t UTF-8 | od -c
0000000    g   i   t

Git uses libiconv to convert from UTF-8 in the index into ITF-16 in the
working tree.
After a checkout, the resulting file has a BOM and is encoded in "UTF-16",
in the version (c) above.
This is what iconv generates, more details follow below.

iconv (and libiconv) can generate UTF-16, UTF-16LE or UTF-16BE:

d) UTF-16
$ printf 'git' | iconv -f UTF-8 -t UTF-16 | od -c
0000000  376 377  \0   g  \0   i  \0   t

e) UTF-16LE
$ printf 'git' | iconv -f UTF-8 -t UTF-16LE | od -c
0000000    g  \0   i  \0   t  \0

f)  UTF-16BE
$ printf 'git' | iconv -f UTF-8 -t UTF-16BE | od -c
0000000   \0   g  \0   i  \0   t

There is no way to generate version (b) from above in a Git working tree,
but that is what some applications need.
(All fully unicode aware applications should be able to read all 3 variants,
but in practise we are not there yet).

When producing UTF-16 as an output, iconv generates the big endian version
with a BOM. (big endian is probably chosen for historical reasons).

iconv can produce UTF-16 files with little endianess by using "UTF-16LE"
as encoding, and that file does not have a BOM.

Not all users (especially under Windows) are happy with this.
Some tools are not fully unicode aware and can only handle version (b).

Today there is no way to produce version (b) with iconv (or libiconv).
Looking into the history of iconv, it seems as if version (c) will
be used in all future iconv versions (for compatibility reasons).

Solve this dilemma and introduce a Git-specific "UTF-16LE-BOM".
libiconv can not handle the encoding, so Git pick it up, handles the BOM
and uses libiconv to convert the rest of the stream.

Rported-by: Adrián Gimeno Balaguer <adrigibal@gmail.com>
Signed-off-by: Torsten Bögershausen <tboegi@web.de>
---

I still think it makes sense to support  UTF-16, little endian and
with BOM in Git.
This V2 should make more clear, what standards we follow, and why
the naming scheme of Unicode does not cover all use cases in real world.

 Documentation/gitattributes.txt  |  4 +--
 compat/precompose_utf8.c         |  2 +-
 t/t0028-working-tree-encoding.sh | 12 ++++++++-
 utf8.c                           | 42 ++++++++++++++++++++++++--------
 utf8.h                           |  2 +-
 5 files changed, 47 insertions(+), 15 deletions(-)

diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt
index b8392fc330..4a88ab8be7 100644
--- a/Documentation/gitattributes.txt
+++ b/Documentation/gitattributes.txt
@@ -343,13 +343,13 @@ automatic line ending conversion based on your platform.
 ------------------------

 Use the following attributes if your '*.ps1' files are UTF-16 little
-endian encoded without BOM and you want Git to use Windows line endings
+endian encoded with BOM and you want Git to use Windows line endings
 in the working directory. Please note, it is highly recommended to
 explicitly define the line endings with `eol` if the `working-tree-encoding`
 attribute is used to avoid ambiguity.

 ------------------------
-*.ps1		text working-tree-encoding=UTF-16LE eol=CRLF
+*.ps1		text working-tree-encoding=UTF-16LE-BOM eol=CRLF
 ------------------------

 You can get a list of all available encodings on your platform with the
diff --git a/compat/precompose_utf8.c b/compat/precompose_utf8.c
index de61c15d34..136250fbf6 100644
--- a/compat/precompose_utf8.c
+++ b/compat/precompose_utf8.c
@@ -79,7 +79,7 @@ void precompose_argv(int argc, const char **argv)
 		size_t namelen;
 		oldarg = argv[i];
 		if (has_non_ascii(oldarg, (size_t)-1, &namelen)) {
-			newarg = reencode_string_iconv(oldarg, namelen, ic_precompose, NULL);
+			newarg = reencode_string_iconv(oldarg, namelen, ic_precompose, 0, NULL);
 			if (newarg)
 				argv[i] = newarg;
 		}
diff --git a/t/t0028-working-tree-encoding.sh b/t/t0028-working-tree-encoding.sh
index 7e87b5a200..e58ecbfc44 100755
--- a/t/t0028-working-tree-encoding.sh
+++ b/t/t0028-working-tree-encoding.sh
@@ -11,9 +11,12 @@ test_expect_success 'setup test files' '

 	text="hallo there!\ncan you read me?" &&
 	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 "$text" | iconv -f UTF-8 -t UTF-32 >test.utf32.raw &&
+	printf "\377\376"                         >test.utf16lebom.raw &&
+	printf "$text" | iconv -f UTF-8 -t UTF-32LE >>test.utf16lebom.raw &&

 	# Line ending tests
 	printf "one\ntwo\nthree\n" >lf.utf8.raw &&
@@ -32,7 +35,8 @@ test_expect_success 'setup test files' '
 	# Add only UTF-16 file, we will add the UTF-32 file later
 	cp test.utf16.raw test.utf16 &&
 	cp test.utf32.raw test.utf32 &&
-	git add .gitattributes test.utf16 &&
+	cp test.utf16lebom.raw test.utf16lebom &&
+	git add .gitattributes test.utf16 test.utf16lebom &&
 	git commit -m initial
 '

@@ -51,6 +55,12 @@ test_expect_success 're-encode to UTF-16 on checkout' '
 	test_cmp_bin test.utf16.raw test.utf16
 '

+test_expect_success 're-encode to UTF-16-LE-BOM on checkout' '
+	rm test.utf16lebom &&
+	git checkout test.utf16lebom &&
+	test_cmp_bin test.utf16lebom.raw test.utf16lebom
+'
+
 test_expect_success 'check $GIT_DIR/info/attributes support' '
 	test_when_finished "rm -f test.utf32.git" &&
 	test_when_finished "git reset --hard HEAD" &&
diff --git a/utf8.c b/utf8.c
index eb78587504..83824dc2f4 100644
--- a/utf8.c
+++ b/utf8.c
@@ -4,6 +4,11 @@

 /* This code is originally from http://www.cl.cam.ac.uk/~mgk25/ucs/ */

+static const char utf16_be_bom[] = {'\xFE', '\xFF'};
+static const char utf16_le_bom[] = {'\xFF', '\xFE'};
+static const char utf32_be_bom[] = {'\0', '\0', '\xFE', '\xFF'};
+static const char utf32_le_bom[] = {'\xFF', '\xFE', '\0', '\0'};
+
 struct interval {
 	ucs_char_t first;
 	ucs_char_t last;
@@ -470,16 +475,17 @@ int utf8_fprintf(FILE *stream, const char *format, ...)
 #else
 	typedef char * iconv_ibp;
 #endif
-char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv, size_t *outsz_p)
+char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv,
+			    size_t bom_len, size_t *outsz_p)
 {
 	size_t outsz, outalloc;
 	char *out, *outpos;
 	iconv_ibp cp;

 	outsz = insz;
-	outalloc = st_add(outsz, 1); /* for terminating NUL */
+	outalloc = st_add(outsz, 1 + bom_len); /* for terminating NUL */
 	out = xmalloc(outalloc);
-	outpos = out;
+	outpos = out + bom_len;
 	cp = (iconv_ibp)in;

 	while (1) {
@@ -540,10 +546,30 @@ char *reencode_string_len(const char *in, size_t insz,
 {
 	iconv_t conv;
 	char *out;
+	const char *bom_str = NULL;
+	size_t bom_len = 0;

 	if (!in_encoding)
 		return NULL;

+	/* UTF-16LE-BOM is the same as UTF-16 for reading */
+	if (same_utf_encoding("UTF-16LE-BOM", in_encoding))
+		in_encoding = "UTF-16";
+
+	/*
+	 * For writing, UTF-16 iconv typically creates "UTF-16BE-BOM"
+	 * Some users under Windows want the little endian version
+	 */
+	if (same_utf_encoding("UTF-16LE-BOM", out_encoding)) {
+		bom_str = utf16_le_bom;
+		bom_len = sizeof(utf16_le_bom);
+		out_encoding = "UTF-16LE";
+	} else if (same_utf_encoding("UTF-16BE-BOM", out_encoding)) {
+		bom_str = utf16_be_bom;
+		bom_len = sizeof(utf16_be_bom);
+		out_encoding = "UTF-16BE";
+	}
+
 	conv = iconv_open(out_encoding, in_encoding);
 	if (conv == (iconv_t) -1) {
 		in_encoding = fallback_encoding(in_encoding);
@@ -553,9 +579,10 @@ char *reencode_string_len(const char *in, size_t insz,
 		if (conv == (iconv_t) -1)
 			return NULL;
 	}
-
-	out = reencode_string_iconv(in, insz, conv, outsz);
+	out = reencode_string_iconv(in, insz, conv, bom_len, outsz);
 	iconv_close(conv);
+	if (out && bom_str && bom_len)
+		memcpy(out, bom_str, bom_len);
 	return out;
 }
 #endif
@@ -566,11 +593,6 @@ static int has_bom_prefix(const char *data, size_t len,
 	return data && bom && (len >= bom_len) && !memcmp(data, bom, bom_len);
 }

-static const char utf16_be_bom[] = {'\xFE', '\xFF'};
-static const char utf16_le_bom[] = {'\xFF', '\xFE'};
-static const char utf32_be_bom[] = {'\0', '\0', '\xFE', '\xFF'};
-static const char utf32_le_bom[] = {'\xFF', '\xFE', '\0', '\0'};
-
 int has_prohibited_utf_bom(const char *enc, const char *data, size_t len)
 {
 	return (
diff --git a/utf8.h b/utf8.h
index edea55e093..84efbfcb1f 100644
--- a/utf8.h
+++ b/utf8.h
@@ -27,7 +27,7 @@ void strbuf_utf8_replace(struct strbuf *sb, int pos, int width,

 #ifndef NO_ICONV
 char *reencode_string_iconv(const char *in, size_t insz,
-			    iconv_t conv, size_t *outsz);
+			    iconv_t conv, size_t bom_len, size_t *outsz);
 char *reencode_string_len(const char *in, size_t insz,
 			  const char *out_encoding,
 			  const char *in_encoding,
--
2.20.1.2.gb21ebb671