#2834: Change re module semantics, so that str and bytes mixing is forbidden,
and str (unicode) patterns get full unicode matching by default. The re.ASCII
flag is also introduced to ask for ASCII matching instead.
diff --git a/Lib/tarfile.py b/Lib/tarfile.py
index ecb32f6..222b433 100644
--- a/Lib/tarfile.py
+++ b/Lib/tarfile.py
@@ -1368,7 +1368,7 @@
# "%d %s=%s\n" % (length, keyword, value). length is the size
# of the complete record including the length field itself and
# the newline. keyword and value are both UTF-8 encoded strings.
- regex = re.compile(r"(\d+) ([^=]+)=", re.U)
+ regex = re.compile(br"(\d+) ([^=]+)=")
pos = 0
while True:
match = regex.match(buf, pos)