utf8: teach same_encoding() alternative UTF encoding names

The function same_encoding() could only recognize alternative names for
UTF-8 encodings. Teach it to recognize all kinds of alternative UTF
encoding names (e.g. utf16).

While we are at it, fix a crash that would occur if same_encoding() was
called with a NULL argument and a non-NULL argument.

This function is used in a subsequent commit.

Signed-off-by: Lars Schneider <larsxschneider@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/utf8.c b/utf8.c
index 2c27ce0137f8a60ca2fadf855f2c67738931e2f8..40f4b142d6983cb134992ffffa07413b75a6cece 100644 (file)
--- a/utf8.c
+++ b/utf8.c
@@ -401,18 +401,40 @@ void strbuf_utf8_replace(struct strbuf *sb_src, int pos, int width,
        strbuf_release(&sb_dst);
 }
 
        strbuf_release(&sb_dst);
 }
 

+/*
+ * Returns true (1) if the src encoding name matches the dst encoding
+ * name directly or one of its alternative names. E.g. UTF-16BE is the
+ * same as UTF16BE.
+ */
+static int same_utf_encoding(const char *src, const char *dst)
+{
+       if (istarts_with(src, "utf") && istarts_with(dst, "utf")) {
+               /* src[3] or dst[3] might be '\0' */
+               int i = (src[3] == '-' ? 4 : 3);
+               int j = (dst[3] == '-' ? 4 : 3);
+               return !strcasecmp(src+i, dst+j);
+       }
+       return 0;
+}
+

 int is_encoding_utf8(const char *name)
 {
        if (!name)
                return 1;
 int is_encoding_utf8(const char *name)
 {
        if (!name)
                return 1;

-       if (!strcasecmp(name, "utf-8") || !strcasecmp(name, "utf8"))
+       if (same_utf_encoding("utf-8", name))

                return 1;
        return 0;
 }
 
 int same_encoding(const char *src, const char *dst)
 {
                return 1;
        return 0;
 }
 
 int same_encoding(const char *src, const char *dst)
 {

-       if (is_encoding_utf8(src) && is_encoding_utf8(dst))
+       static const char utf8[] = "UTF-8";
+
+       if (!src)
+               src = utf8;
+       if (!dst)
+               dst = utf8;
+       if (same_utf_encoding(src, dst))

                return 1;
        return !strcasecmp(src, dst);
 }
                return 1;
        return !strcasecmp(src, dst);
 }