utf8: add function to detect prohibited UTF-16/32 BOM

Whenever a data stream is declared to be UTF-16BE, UTF-16LE, UTF-32BE
or UTF-32LE a BOM must not be used [1]. The function returns true if
this is the case.

This function is used in a subsequent commit.

[1] http://unicode.org/faq/utf_bom.html#bom10

Signed-off-by: Lars Schneider <larsxschneider@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

2 files changed, 35 insertions, 0 deletions

diff --git a/utf8.c b/utf8.c
index c30daf4d34..d16dc1f244 100644
--- a/utf8.c
+++ b/utf8.c
@@ -556,6 +556,32 @@ char *reencode_string_len(const char *in, int insz,
 }
 #endif
 
+static int has_bom_prefix(const char *data, size_t len,
+			  const char *bom, size_t bom_len)
+{
+	return (len >= bom_len) && !memcmp(data, bom, bom_len);
+}
+
+static const char utf16_be_bom[] = {0xFE, 0xFF};
+static const char utf16_le_bom[] = {0xFF, 0xFE};
+static const char utf32_be_bom[] = {0x00, 0x00, 0xFE, 0xFF};
+static const char utf32_le_bom[] = {0xFF, 0xFE, 0x00, 0x00};
+
+int has_prohibited_utf_bom(const char *enc, const char *data, size_t len)
+{
+	return (
+	  (same_utf_encoding("UTF-16BE", enc) ||
+	   same_utf_encoding("UTF-16LE", enc)) &&
+	  (has_bom_prefix(data, len, utf16_be_bom, sizeof(utf16_be_bom)) ||
+	   has_bom_prefix(data, len, utf16_le_bom, sizeof(utf16_le_bom)))
+	) || (
+	  (same_utf_encoding("UTF-32BE",  enc) ||
+	   same_utf_encoding("UTF-32LE", enc)) &&
+	  (has_bom_prefix(data, len, utf32_be_bom, sizeof(utf32_be_bom)) ||
+	   has_bom_prefix(data, len, utf32_le_bom, sizeof(utf32_le_bom)))
+	);
+}
+
 /*
  * Returns first character length in bytes for multi-byte `text` according to
  * `encoding`.
diff --git a/utf8.h b/utf8.h
index 6bbcf31a83..0db1db4519 100644
--- a/utf8.h
+++ b/utf8.h
@@ -70,4 +70,13 @@ typedef enum {
 void strbuf_utf8_align(struct strbuf *buf, align_type position, unsigned int width,
 		       const char *s);
 
+/*
+ * If a data stream is declared as UTF-16BE or UTF-16LE, then a UTF-16
+ * BOM must not be used [1]. The same applies for the UTF-32 equivalents.
+ * The function returns true if this rule is violated.
+ *
+ * [1] http://unicode.org/faq/utf_bom.html#bom10
+ */
+int has_prohibited_utf_bom(const char *enc, const char *data, size_t len);
+
 #endif