Description: Fix the crash from #912099 ITS Tool 2.0.4 crashes when building some documentation, as reported in #912099. This comes from translations with invalid XML markup, which ITS Tool fails to merge (which is not abnormal), and to report these issues, needlessly encodes the original msgstr from unicode to bytes, causing it to be recoded using the default ascii codec, which fails when the msgstr contains anything out of ascii. . This patch removes the useless decoding, avoiding the failing subsequent recoding. It also explicitly encodes the output strings to be able to print them in all cases, even when the output encoding cannot be detected. Bug: https://github.com/itstool/itstool/issues/25 Bug-Debian: https://bugs.debian.org/912099 Forwarded: https://github.com/itstool/itstool/issues/25 Author: Tanguy Ortolo Last-Update: 2018-12-071 Index: itstool/itstool.in =================================================================== --- itstool.orig/itstool.in 2018-12-10 18:31:23.762143539 +0100 +++ itstool/itstool.in 2018-12-10 18:38:03.496777117 +0100 @@ -44,9 +44,22 @@ else: return str(s) ustr_type = str + def pr_str(s): + """Return a string that can be safely print()ed""" + # Since print works on both bytes and unicode, just return the argument + return s else: string_types = basestring, ustr = ustr_type = unicode + def pr_str(s): + """Return a string that can be safely print()ed""" + if isinstance(s, str): + # Since print works on str, just return the argument + return s + else: + # print may not work on unicode if the output encoding cannot be + # detected, so just encode with UTF-8 + return unicode.encode(s, 'utf-8') NS_ITS = 'http://www.w3.org/2005/11/its' NS_ITST = 'http://itstool.org/extensions/' @@ -1060,9 +1073,9 @@ if strict: raise else: - sys.stderr.write('Warning: Could not merge %stranslation for msgid:\n%s\n' % ( + sys.stderr.write(pr_str('Warning: Could not merge %stranslation for msgid:\n%s\n' % ( (lang + ' ') if lang is not None else '', - msgstr.encode('utf-8'))) + msgstr))) self._xml_err = '' return node def scan_node(node): @@ -1087,9 +1100,9 @@ if strict: raise else: - sys.stderr.write('Warning: Could not merge %stranslation for msgid:\n%s\n' % ( + sys.stderr.write(pr_str('Warning: Could not merge %stranslation for msgid:\n%s\n' % ( (lang + ' ') if lang is not None else '', - msgstr.encode('utf-8'))) + msgstr))) self._xml_err = '' ctxt.doc().freeDoc() return node