[PATCH v12 04/10] utf8: teach same_encoding() alternative UTF encoding names

From

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

Date

Mar 15, 2018, 22:57 UTC

Message-ID

<20180315225746.18119-5-lars.schneider@autodesk.com>

In-Reply-To

<20180315225746.18119-1-lars.schneider@autodesk.com>

From: Lars Schneider <larsxschneider@gmail.com>

This function is used in a subsequent commit.

Signed-off-by: Lars Schneider <larsxschneider@gmail.com>
---
 utf8.c | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/utf8.c b/utf8.c
index 2c27ce0137..c30daf4d34 100644
--- a/utf8.c
+++ b/utf8.c
@@ -401,11 +401,27 @@ void strbuf_utf8_replace(struct strbuf *sb_src, int pos, int width,
 	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;
-	if (!strcasecmp(name, "utf-8") || !strcasecmp(name, "utf8"))
+	if (same_utf_encoding("utf-8", name))
 		return 1;
 	return 0;
 }
@@ -414,6 +430,8 @@ int same_encoding(const char *src, const char *dst)
 {
 	if (is_encoding_utf8(src) && is_encoding_utf8(dst))
 		return 1;
+	if (same_utf_encoding(src, dst))
+		return 1;
 	return !strcasecmp(src, dst);
 }
 

-- 
2.16.2