summaryrefslogtreecommitdiff
path: root/utf8.h
diff options
context:
space:
mode:
Diffstat (limited to 'utf8.h')
-rw-r--r--utf8.h28
1 files changed, 28 insertions, 0 deletions
diff --git a/utf8.h b/utf8.h
index 6bbcf31a83..cce654a64a 100644
--- a/utf8.h
+++ b/utf8.h
@@ -70,4 +70,32 @@ 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);
+
+/*
+ * 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