From 5590d8cc8af29f6d1ff2158ddbef0e457279c5f1 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Lars=20Gust=C3=A4bel?= Date: Fri, 10 Aug 2007 12:02:32 +0000 Subject: RFC 1952 requires the FNAME field to be Latin-1. Do not include filenames that cannot be represented that way. --- Lib/gzip.py | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/Lib/gzip.py b/Lib/gzip.py index b6cc80e..e7f6737 100644 --- a/Lib/gzip.py +++ b/Lib/gzip.py @@ -153,6 +153,14 @@ class GzipFile: if fname.endswith(".gz"): fname = fname[:-3] flags = 0 + + # RFC 1952 requires the FNAME field to be Latin-1. Do not + # include filenames that cannot be represented that way. + try: + fname = fname.encode('latin-1') + except UnicodeEncodeError: + fname = '' + if fname: flags = FNAME self.fileobj.write(chr(flags).encode('latin-1')) @@ -160,8 +168,7 @@ class GzipFile: self.fileobj.write(b'\002') self.fileobj.write(b'\377') if fname: - # XXX: Ist utf-8 the correct encoding? - self.fileobj.write(fname.encode('utf-8') + b'\000') + self.fileobj.write(fname + b'\000') def _init_read(self): self.crc = zlib.crc32("") -- cgit v0.12