From 87c0f1d1c95eb1766a1340cd100533dfd7a86d52 Mon Sep 17 00:00:00 2001 From: Guido van Rossum Date: Mon, 19 Nov 2007 18:03:44 +0000 Subject: Merged revisions 59041-59055 via svnmerge from svn+ssh://pythondev@svn.python.org/python/trunk ........ r59044 | neal.norwitz | 2007-11-18 17:46:20 -0800 (Sun, 18 Nov 2007) | 1 line Use a slightly more recent version than 1.5.2b2. ........ r59047 | walter.doerwald | 2007-11-19 04:14:05 -0800 (Mon, 19 Nov 2007) | 2 lines Fix typo in comment. ........ r59049 | walter.doerwald | 2007-11-19 04:41:10 -0800 (Mon, 19 Nov 2007) | 4 lines Fix for #1444: utf_8_sig.StreamReader was (indirectly through decode()) calling codecs.utf_8_decode() with final==True, which falled with incomplete byte sequences. Fix and test by James G. Sack. ........ r59051 | nick.coghlan | 2007-11-19 05:56:27 -0800 (Mon, 19 Nov 2007) | 1 line Enable some test_cmd_line_script debugging output to investigate failure on Mac OSX buildbot ........ r59053 | facundo.batista | 2007-11-19 08:30:24 -0800 (Mon, 19 Nov 2007) | 3 lines Fixed detail in add_type() explanation (issue 1463). ........ r59054 | guido.van.rossum | 2007-11-19 09:35:24 -0800 (Mon, 19 Nov 2007) | 2 lines Make this work stand-alone, too. ........ r59055 | guido.van.rossum | 2007-11-19 09:50:22 -0800 (Mon, 19 Nov 2007) | 3 lines Fix the OSX failures in this test -- they were due to /tmp being a symlink to /private/tmp. Adding a call to os.path.realpath() to temp_dir() fixed it. ........ --- Lib/encodings/utf_8_sig.py | 16 +++++++++++----- 1 file changed, 11 insertions(+), 5 deletions(-) (limited to 'Lib/encodings/utf_8_sig.py') diff --git a/Lib/encodings/utf_8_sig.py b/Lib/encodings/utf_8_sig.py index 07cd5eeb1b..1bb479203f 100644 --- a/Lib/encodings/utf_8_sig.py +++ b/Lib/encodings/utf_8_sig.py @@ -103,12 +103,18 @@ class StreamReader(codecs.StreamReader): pass def decode(self, input, errors='strict'): - if len(input) < 3 and codecs.BOM_UTF8.startswith(input): - # not enough data to decide if this is a BOM - # => try again on the next call - return ("", 0) + if len(input) < 3: + if codecs.BOM_UTF8.startswith(input): + # not enough data to decide if this is a BOM + # => try again on the next call + return ("", 0) + elif input[:3] == codecs.BOM_UTF8: + self.decode = codecs.utf_8_decode + (output, consumed) = codecs.utf_8_decode(input[3:],errors) + return (output, consumed+3) + # (else) no BOM present self.decode = codecs.utf_8_decode - return decode(input, errors) + return codecs.utf_8_decode(input, errors) ### encodings module API -- cgit v1.2.1