From 5b6c090749e31701bab7254d7ebb3cd121ef3d34 Mon Sep 17 00:00:00 2001 From: "Yann E. MORIN" Date: Sat, 31 Mar 2018 14:52:50 +0200 Subject: [PATCH] support/check-uniq-files: support weird locales and filenames Currently, when a filename contains characters not representable in the user's locale, we fail hard, especially when the host python is python3. This is because python2 and python3 handle encoding/decoding strings differently, with python3 presumable doing the right thing, but it breaks on some systems, while python2 presumable does the wrong thing, but it works everywhere. (Just joking, obviously...) Part of the issue being that the csv reader in python2 is broken with UTF8. We fix the issue by ditching the csv reader, and simply read the file in binary mode, manually partitioning the lines on the first comma. Then, we use the binary-encoded (really, un-encoded) package names and filenames as values and keys, respectively. Finally, for each filename or package we need to print, we try to decode them with the defaults for the user settings, but catch any decoding exception and fall back to dumping the raw, binary values. Which codec is used by default differs between Python version, but in all cases something sane is printed at least. Thanks a lot to Arnout for the live help doing this patch. :-) Reported-by: Jaap Crezee Signed-off-by: "Yann E. MORIN" Cc: Arnout Vandecappelle Cc: Jaap Crezee [Arnout: commit log improvement] Signed-off-by: Arnout Vandecappelle (Essensium/Mind) (cherry picked from commit 5563a1c6a48716debe2983869ddb757318094dce) Signed-off-by: Peter Korsgaard --- support/scripts/check-uniq-files | 19 +++++++++++++------ 1 file changed, 13 insertions(+), 6 deletions(-) diff --git a/support/scripts/check-uniq-files b/support/scripts/check-uniq-files index be808cce03..f110176274 100755 --- a/support/scripts/check-uniq-files +++ b/support/scripts/check-uniq-files @@ -26,16 +26,23 @@ def main(): return False file_to_pkg = defaultdict(list) - with open(args.packages_file_list[0], 'r') as pkg_file_list: - r = csv.reader(pkg_file_list, delimiter=',') - for row in r: - pkg = row[0] - file = row[1] + with open(args.packages_file_list[0], 'rb') as pkg_file_list: + for line in pkg_file_list.readlines(): + pkg, _, file = line.rstrip(b'\n').partition(b',') file_to_pkg[file].append(pkg) for file in file_to_pkg: if len(file_to_pkg[file]) > 1: - sys.stderr.write(warn.format(args.type, file, file_to_pkg[file])) + # If possible, try to decode the binary strings with + # the default user's locale + try: + sys.stderr.write(warn.format(args.type, file.decode(), + [p.decode() for p in file_to_pkg[file]])) + except UnicodeDecodeError: + # ... but fallback to just dumping them raw if they + # contain non-representable chars + sys.stderr.write(warn.format(args.type, file, + file_to_pkg[file])) if __name__ == "__main__": -- 2.39.2