apply-pullreq: Add basic mangled-UTF-8 check

Add a basic check that looks for some common kinds of
mangled UTF-8 in commit messages.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 10 insertions, 0 deletions

diff --git a/apply-pullreq b/apply-pullreq
index b0e8860..be5f22f 100755
--- a/apply-pullreq
+++ b/apply-pullreq
@@ -121,6 +121,16 @@ if git shortlog --author=qemu-devel@nongnu.org master..staging | grep .; then
     exit 1
 fi
 
+
+# Check for incorrect UTF-8 copy/pasting
+# This is a very dubious heuristic that is essentially just looking
+# for mangled é or for =nn hex escapes. Still, it's better than nothing.
+if git log master..staging \
+    | grep -E "^ +[[:alpha:]-]+-by: .*(=[0-9A-F]{2}|é).*@"; then
+    echo "ERROR: pull request includes tag with UTF-8 error in person name"
+    exit 1
+fi
+
 # This should exit with an error status if any of the sub-builds fails.
 parallel-buildtest