From: Richard Levitte <levitte@openssl.org>
Date: Mon, 13 Jul 2015 14:50:16 +0000 (+0200)
Subject: Small script to re-encode files that need it to UTF-8
X-Git-Tag: OpenSSL_1_1_0-pre1~924
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=f608b4064d58ca4dfdfdfc921308b51cb96205e2;p=openssl

Small script to re-encode files that need it to UTF-8

This requires 'iconv' and that 'file' can take the options '-b' and '-i'.

Reviewed-by: Rich Salz <rsalz@openssl.org>
---

diff --git a/util/toutf8.sh b/util/toutf8.sh
new file mode 100644
index 0000000000..8a4254b3df
--- /dev/null
+++ b/util/toutf8.sh
@@ -0,0 +1,17 @@
+#! /bin/sh
+#
+# Very simple script to detect and convert files that we want to re-encode to UTF8
+
+git ls-tree -r --name-only HEAD | \
+    while read F; do
+	charset=`file -bi "$F" | sed -e 's|.*charset=||'`
+	if [ "$charset" != "utf-8" -a "$charset" != "binary" -a "$charset" != "us-ascii" ]; then
+	    iconv -f ISO-8859-1 -t UTF8 < "$F" > "$F.utf8" && \
+		( cmp -s "$F" "$F.utf8" || \
+			( echo "$F"
+			  mv "$F" "$F.iso-8859-1"
+			  mv "$F.utf8" "$F"
+			)
+		)
+	fi
+    done