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>
(cherry picked from commit f608b4064d)
This commit is contained in:
Richard Levitte 2015-07-13 16:50:16 +02:00
parent 2794dec7b2
commit 13e742a439

17
util/toutf8.sh Normal file
View file

@ -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