[PATCH 3/5] utf8: add function to detect prohibited UTF-16/32 BOM

From

tboegi@web.de <tboegi@web.de>

Date

Dec 31, 2017, 08:05 UTC

Message-ID

<20171231080556.22344-1-tboegi@web.de>

In-Reply-To

<20171229152222.39680-1-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>
Signed-off-by: Torsten Bögershausen <tboegi@web.de>
---
 utf8.c | 24 ++++++++++++++++++++++++
 utf8.h |  9 +++++++++
 2 files changed, 33 insertions(+)

diff --git a/utf8.c b/utf8.c
index 2c27ce0137..776660ee12 100644
--- a/utf8.c
+++ b/utf8.c
@@ -538,6 +538,30 @@ 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);
+}
+
+const char utf16_be_bom[] = {0xFE, 0xFF};
+const char utf16_le_bom[] = {0xFF, 0xFE};
+const char utf32_be_bom[] = {0x00, 0x00, 0xFE, 0xFF};
+const char utf32_le_bom[] = {0xFF, 0xFE, 0x00, 0x00};
+
+int has_prohibited_utf_bom(const char *enc, const char *data, size_t len)
+{
+	return (
+	  (!strcmp(enc, "UTF-16BE") || !strcmp(enc, "UTF-16LE")) &&
+	  (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-32BE") || !strcmp(enc, "UTF-32LE")) &&
+	  (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..4711429af9 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);
 
+/*
+ * 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.
+ *
+ * [1] http://unicode.org/faq/utf_bom.html#bom10
+ */
+int has_prohibited_utf_bom(const char *enc, const char *data, size_t len);
+
 #endif

-- 
2.16.0.rc0.4.ga4e00d4fa4