[PATCH v11 04/10] utf8: add function to detect prohibited UTF-16/32 BOM

From

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

Date

Mar 9, 2018, 17:35 UTC

Message-ID

<20180309173536.62012-5-lars.schneider@autodesk.com>

In-Reply-To

<20180309173536.62012-1-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#bom10

Signed-off-by: Lars Schneider <larsxschneider@gmail.com>
---
 utf8.c | 26 ++++++++++++++++++++++++++
 utf8.h |  9 +++++++++
 2 files changed, 35 insertions(+)

diff --git a/utf8.c b/utf8.c
index 2c27ce0137..e4b99580f0 100644
--- a/utf8.c
+++ b/utf8.c
@@ -538,6 +538,32 @@ 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 (
+	  (!strcasecmp(enc, "UTF-16BE") || !strcasecmp(enc, "UTF-16LE") ||
+	   !strcasecmp(enc, "UTF16BE") || !strcasecmp(enc, "UTF16LE")) &&
+	  (has_bom_prefix(data, len, utf16_be_bom, sizeof(utf16_be_bom)) ||
+	   has_bom_prefix(data, len, utf16_le_bom, sizeof(utf16_le_bom)))
+	) || (
+	  (!strcasecmp(enc, "UTF-32BE") || !strcasecmp(enc, "UTF-32LE") ||
+	   !strcasecmp(enc, "UTF32BE") || !strcasecmp(enc, "UTF32LE")) &&
+	  (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

-- 
2.16.2