summaryrefslogtreecommitdiff
path: root/utf8.h
diff options
context:
space:
mode:
Diffstat (limited to 'utf8.h')
-rw-r--r--utf8.h40
1 files changed, 35 insertions, 5 deletions
diff --git a/utf8.h b/utf8.h
index da19b43114..edea55e093 100644
--- a/utf8.h
+++ b/utf8.h
@@ -1,6 +1,8 @@
#ifndef GIT_UTF8_H
#define GIT_UTF8_H
+struct strbuf;
+
typedef unsigned int ucs_char_t; /* assuming 32bit int */
size_t display_mode_esc_sequence_len(const char *s);
@@ -25,14 +27,14 @@ void strbuf_utf8_replace(struct strbuf *sb, int pos, int width,
#ifndef NO_ICONV
char *reencode_string_iconv(const char *in, size_t insz,
- iconv_t conv, int *outsz);
-char *reencode_string_len(const char *in, int insz,
+ iconv_t conv, size_t *outsz);
+char *reencode_string_len(const char *in, size_t insz,
const char *out_encoding,
const char *in_encoding,
- int *outsz);
+ size_t *outsz);
#else
-static inline char *reencode_string_len(const char *a, int b,
- const char *c, const char *d, int *e)
+static inline char *reencode_string_len(const char *a, size_t b,
+ const char *c, const char *d, size_t *e)
{ if (e) *e = 0; return NULL; }
#endif
@@ -75,4 +77,32 @@ 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