Merge branch 'jc/latin-1'

Some platforms no longer understand "latin-1" that is still seen in
the wild in e-mail headers; replace them with "iso-8859-1" that is
more widely known when conversion fails from/to it.

* jc/latin-1:
  utf8: accept "latin-1" as ISO-8859-1
  utf8: refactor code to decide fallback encoding

1 files changed, 25 insertions, 11 deletions

diff --git a/utf8.c b/utf8.c
index 00e10c86ad..0c8e011a58 100644
--- a/utf8.c
+++ b/utf8.c
@@ -489,6 +489,28 @@ char *reencode_string_iconv(const char *in, size_t insz, iconv_t conv, int *outs
 	return out;
 }
 
+static const char *fallback_encoding(const char *name)
+{
+	/*
+	 * Some platforms do not have the variously spelled variants of
+	 * UTF-8, so let's fall back to trying the most official
+	 * spelling. We do so only as a fallback in case the platform
+	 * does understand the user's spelling, but not our official
+	 * one.
+	 */
+	if (is_encoding_utf8(name))
+		return "UTF-8";
+
+	/*
+	 * Even though latin-1 is still seen in e-mail
+	 * headers, some platforms only install ISO-8859-1.
+	 */
+	if (!strcasecmp(name, "latin-1"))
+		return "ISO-8859-1";
+
+	return name;
+}
+
 char *reencode_string_len(const char *in, int insz,
 			  const char *out_encoding, const char *in_encoding,
 			  int *outsz)
@@ -501,17 +523,9 @@ char *reencode_string_len(const char *in, int insz,
 
 	conv = iconv_open(out_encoding, in_encoding);
 	if (conv == (iconv_t) -1) {
-		/*
-		 * Some platforms do not have the variously spelled variants of
-		 * UTF-8, so let's fall back to trying the most official
-		 * spelling. We do so only as a fallback in case the platform
-		 * does understand the user's spelling, but not our official
-		 * one.
-		 */
-		if (is_encoding_utf8(in_encoding))
-			in_encoding = "UTF-8";
-		if (is_encoding_utf8(out_encoding))
-			out_encoding = "UTF-8";
+		in_encoding = fallback_encoding(in_encoding);
+		out_encoding = fallback_encoding(out_encoding);
+
 		conv = iconv_open(out_encoding, in_encoding);
 		if (conv == (iconv_t) -1)
 			return NULL;