[PATCH v9 4/8] utf8: add function to detect a missing UTF-16/32 BOM

From

lars.schneider@autodesk.com <lars.schneider@autodesk.com>

Date

Mar 4, 2018, 20:14 UTC

Message-ID

<20180304201418.60958-5-lars.schneider@autodesk.com>

In-Reply-To

<20180304201418.60958-1-lars.schneider@autodesk.com>

From: Lars Schneider <larsxschneider@gmail.com>

This function is used in a subsequent commit.

[1] http://unicode.org/faq/utf_bom.html#gen6
[2] http://www.unicode.org/versions/Unicode10.0.0/ch03.pdf
     Section 3.10, D98, page 132
[3] https://encoding.spec.whatwg.org/#utf-16le

Signed-off-by: Lars Schneider <larsxschneider@gmail.com>
---
 utf8.c | 13 +++++++++++++
 utf8.h | 19 +++++++++++++++++++
 2 files changed, 32 insertions(+)

diff --git a/utf8.c b/utf8.c
index 914881cd1f..5113d26e56 100644
--- a/utf8.c
+++ b/utf8.c
@@ -562,6 +562,19 @@ int has_prohibited_utf_bom(const char *enc, const char *data, size_t len)
 	);
 }
 
+int is_missing_required_utf_bom(const char *enc, const char *data, size_t len)
+{
+	return (
+	   !strcmp(enc, "UTF-16") &&
+	   !(has_bom_prefix(data, len, utf16_be_bom, sizeof(utf16_be_bom)) ||
+	     has_bom_prefix(data, len, utf16_le_bom, sizeof(utf16_le_bom)))
+	) || (
+	   !strcmp(enc, "UTF-32") &&
+	   !(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 0db1db4519..cce654a64a 100644
--- a/utf8.h
+++ b/utf8.h
@@ -79,4 +79,23 @@ void strbuf_utf8_align(struct strbuf *buf, align_type position, unsigned int wid
  */
 int has_prohibited_utf_bom(const char *enc, const char *data, size_t len);
 
+/*
+ * If the endianness is not defined in the encoding name, then we
+ * require a BOM. The function returns true if a required BOM is missing.
+ *
+ * The Unicode standard instructs to assume big-endian if there in no
+ * BOM for UTF-16/32 [1][2]. However, the W3C/WHATWG encoding standard
+ * used in HTML5 recommends to assume little-endian to "deal with
+ * deployed content" [3].
+ *
+ * Therefore, strictly requiring a BOM seems to be the safest option for
+ * content in Git.
+ *
+ * [1] http://unicode.org/faq/utf_bom.html#gen6
+ * [2] http://www.unicode.org/versions/Unicode10.0.0/ch03.pdf
+ *     Section 3.10, D98, page 132
+ * [3] https://encoding.spec.whatwg.org/#utf-16le
+ */
+int is_missing_required_utf_bom(const char *enc, const char *data, size_t len);
+
 #endif

-- 
2.16.2