Preserve multibyte UTF-8 characters when obfuscating.
This version uses the unicode 'replace' option, so non-UTF-8
encodings will still be mangled. Luckily, there aren't any
of those.
#!/bin/sh
hg init
touch a
hg add a
hg ci -m "a" -d "1000000 0"
echo 123 > b
hg add b
hg diff | sed -e "s/\(+++ [a-zA-Z0-9_/.-]*\).*/\1/" \
-e "s/\(--- [a-zA-Z0-9_/.-]*\).*/\1/"
hg diff -r tip | sed -e "s/\(+++ [a-zA-Z0-9_/.-]*\).*/\1/" \
-e "s/\(--- [a-zA-Z0-9_/.-]*\).*/\1/"
echo foo > a
hg diff | sed -e "s/\(+++ [a-zA-Z0-9_/.-]*\).*/\1/" \
-e "s/\(--- [a-zA-Z0-9_/.-]*\).*/\1/"