convert: check for detectable errors in UTF encodings

Check that new content is valid with respect to the user defined
'working-tree-encoding' attribute.

Signed-off-by: Lars Schneider <[email protected]>
Signed-off-by: Junio C Hamano <[email protected]>

Author: larsxschneider

convert.c

@@ -266,6 +266,64 @@ static int will_convert_lf_to_crlf(size_t len, struct text_stat *stats,
 
 }
 
+static int validate_encoding(const char *path, const char *enc,
+		      const char *data, size_t len, int die_on_error)
+{
+	/* We only check for UTF here as UTF?? can be an alias for UTF-?? */
+	if (istarts_with(enc, "UTF")) {
+		/*
+		 * Check for detectable errors in UTF encodings
+		 */
+		if (has_prohibited_utf_bom(enc, data, len)) {
+			const char *error_msg = _(
+				"BOM is prohibited in '%s' if encoded as %s");
+			/*
+			 * This advice is shown for UTF-??BE and UTF-??LE encodings.
+			 * We cut off the last two characters of the encoding name
+			 * to generate the encoding name suitable for BOMs.
+			 */
+			const char *advise_msg = _(
+				"The file '%s' contains a byte order "
+				"mark (BOM). Please use UTF-%s as "
+				"working-tree-encoding.");
+			const char *stripped = NULL;
+			char *upper = xstrdup_toupper(enc);
+			upper[strlen(upper)-2] = '\0';
+			if (!skip_prefix(upper, "UTF-", &stripped))
+				skip_prefix(stripped, "UTF", &stripped);
+			advise(advise_msg, path, stripped);
+			free(upper);
+			if (die_on_error)
+				die(error_msg, path, enc);
+			else {
+				return error(error_msg, path, enc);
+			}
+
+		} else if (is_missing_required_utf_bom(enc, data, len)) {
+			const char *error_msg = _(
+				"BOM is required in '%s' if encoded as %s");
+			const char *advise_msg = _(
+				"The file '%s' is missing a byte order "
+				"mark (BOM). Please use UTF-%sBE or UTF-%sLE "
+				"(depending on the byte order) as "
+				"working-tree-encoding.");
+			const char *stripped = NULL;
+			char *upper = xstrdup_toupper(enc);
+			if (!skip_prefix(upper, "UTF-", &stripped))
+				skip_prefix(stripped, "UTF", &stripped);
+			advise(advise_msg, path, stripped, stripped);
+			free(upper);
+			if (die_on_error)
+				die(error_msg, path, enc);
+			else {
+				return error(error_msg, path, enc);
+			}
+		}
+
+	}
+	return 0;
+}
+
 static const char *default_encoding = "UTF-8";
 
 static int encode_to_git(const char *path, const char *src, size_t src_len,
@@ -291,6 +349,9 @@ static int encode_to_git(const char *path, const char *src, size_t src_len,
 	if (!buf && !src)
 		return 1;
 
+	if (validate_encoding(path, enc, src, src_len, die_on_error))
+		return 0;
+
 	dst = reencode_string_len(src, src_len, default_encoding, enc,
 				  &dst_len);
 	if (!dst) {

t/t0028-working-tree-encoding.sh

@@ -62,6 +62,52 @@ test_expect_success 'check $GIT_DIR/info/attributes support' '
 
 for i in 16 32
 do
+	test_expect_success "check prohibited UTF-${i} BOM" '
+		test_when_finished "git reset --hard HEAD" &&
+
+		echo "*.utf${i}be text working-tree-encoding=utf-${i}be" >>.gitattributes &&
+		echo "*.utf${i}le text working-tree-encoding=utf-${i}LE" >>.gitattributes &&
+
+		# Here we add a UTF-16 (resp. UTF-32) files with BOM (big/little-endian)
+		# but we tell Git to treat it as UTF-16BE/UTF-16LE (resp. UTF-32).
+		# In these cases the BOM is prohibited.
+		cp bebom.utf${i}be.raw bebom.utf${i}be &&
+		test_must_fail git add bebom.utf${i}be 2>err.out &&
+		test_i18ngrep "fatal: BOM is prohibited .* utf-${i}be" err.out &&
+		test_i18ngrep "use UTF-${i} as working-tree-encoding" err.out &&
+
+		cp lebom.utf${i}le.raw lebom.utf${i}be &&
+		test_must_fail git add lebom.utf${i}be 2>err.out &&
+		test_i18ngrep "fatal: BOM is prohibited .* utf-${i}be" err.out &&
+		test_i18ngrep "use UTF-${i} as working-tree-encoding" err.out &&
+
+		cp bebom.utf${i}be.raw bebom.utf${i}le &&
+		test_must_fail git add bebom.utf${i}le 2>err.out &&
+		test_i18ngrep "fatal: BOM is prohibited .* utf-${i}LE" err.out &&
+		test_i18ngrep "use UTF-${i} as working-tree-encoding" err.out &&
+
+		cp lebom.utf${i}le.raw lebom.utf${i}le &&
+		test_must_fail git add lebom.utf${i}le 2>err.out &&
+		test_i18ngrep "fatal: BOM is prohibited .* utf-${i}LE" err.out &&
+		test_i18ngrep "use UTF-${i} as working-tree-encoding" err.out
+	'
+
+	test_expect_success "check required UTF-${i} BOM" '
+		test_when_finished "git reset --hard HEAD" &&
+
+		echo "*.utf${i} text working-tree-encoding=utf-${i}" >>.gitattributes &&
+
+		cp nobom.utf${i}be.raw nobom.utf${i} &&
+		test_must_fail git add nobom.utf${i} 2>err.out &&
+		test_i18ngrep "fatal: BOM is required .* utf-${i}" err.out &&
+		test_i18ngrep "use UTF-${i}BE or UTF-${i}LE" err.out &&
+
+		cp nobom.utf${i}le.raw nobom.utf${i} &&
+		test_must_fail git add nobom.utf${i} 2>err.out &&
+		test_i18ngrep "fatal: BOM is required .* utf-${i}" err.out &&
+		test_i18ngrep "use UTF-${i}BE or UTF-${i}LE" err.out
+	'
+
 	test_expect_success "eol conversion for UTF-${i} encoded files on checkout" '
 		test_when_finished "rm -f crlf.utf${i}.raw lf.utf${i}.raw" &&
 		test_when_finished "git reset --hard HEAD^" &&
@@ -139,4 +185,20 @@ test_expect_success 'error if encoding round trip is not the same during refresh
 	test_i18ngrep "error: .* overwritten by checkout:" err.out
 '
 
+test_expect_success 'error if encoding garbage is already in Git' '
+	BEFORE_STATE=$(git rev-parse HEAD) &&
+	test_when_finished "git reset --hard $BEFORE_STATE" &&
+
+	# Skip the UTF-16 filter for the added file
+	# This simulates a Git version that has no checkoutEncoding support
+	cp nobom.utf16be.raw nonsense.utf16 &&
+	TEST_HASH=$(git hash-object --no-filters -w nonsense.utf16) &&
+	git update-index --add --cacheinfo 100644 $TEST_HASH nonsense.utf16 &&
+	COMMIT=$(git commit-tree -p $(git rev-parse HEAD) -m "plain commit" $(git write-tree)) &&
+	git update-ref refs/heads/master $COMMIT &&
+
+	git diff 2>err.out &&
+	test_i18ngrep "error: BOM is required" err.out
+'
+
 test_done