2 # vim:set et ts=4 sw=4:
4 """Text utility functions
6 @contact: Debian FTP Master <ftpmaster@debian.org>
7 @copyright: 2000, 2001, 2002, 2003, 2004, 2005, 2006 James Troup <james@nocrew.org>
8 @license: GNU General Public License version 2 or later
11 # This program is free software; you can redistribute it and/or modify
12 # it under the terms of the GNU General Public License as published by
13 # the Free Software Foundation; either version 2 of the License, or
14 # (at your option) any later version.
16 # This program is distributed in the hope that it will be useful,
17 # but WITHOUT ANY WARRANTY; without even the implied warranty of
18 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
19 # GNU General Public License for more details.
21 # You should have received a copy of the GNU General Public License
22 # along with this program; if not, write to the Free Software
23 # Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
28 from dak_exceptions import *
29 from regexes import re_parse_maintainer
31 ################################################################################
35 Forces a string to UTF-8. If the string isn't already UTF-8,
36 it's assumed to be ISO-8859-1.
42 latin1_s = unicode(s,'iso8859-1')
43 return latin1_s.encode('utf-8')
45 def rfc2047_encode(s):
47 Encodes a (header) string per RFC2047 if necessary. If the
48 string is neither ASCII nor UTF-8, it's assumed to be ISO-8859-1.
51 codecs.lookup('ascii')[1](s)
56 codecs.lookup('utf-8')[1](s)
57 h = email.Header.Header(s, 'utf-8', 998)
60 h = email.Header.Header(s, 'iso-8859-1', 998)
63 ################################################################################
65 # <Culus> 'The standard sucks, but my tool is supposed to interoperate
66 # with it. I know - I'll fix the suckage and make things
69 def fix_maintainer(maintainer):
71 Parses a Maintainer or Changed-By field and returns:
72 1. an RFC822 compatible version,
73 2. an RFC2047 compatible version,
77 The name is forced to UTF-8 for both 1. and 3.. If the name field
78 contains '.' or ',' (as allowed by Debian policy), 1. and 2. are
79 switched to 'email (name)' format.
82 maintainer = maintainer.strip()
84 return ('', '', '', '')
86 if maintainer.find("<") == -1:
89 elif (maintainer[0] == "<" and maintainer[-1:] == ">"):
90 email = maintainer[1:-1]
93 m = re_parse_maintainer.match(maintainer)
95 raise ParseMaintError, "Doesn't parse as a valid Maintainer field."
99 # Get an RFC2047 compliant version of the name
100 rfc2047_name = rfc2047_encode(name)
102 # Force the name to be UTF-8
103 name = force_to_utf8(name)
105 if name.find(',') != -1 or name.find('.') != -1:
106 rfc822_maint = "%s (%s)" % (email, name)
107 rfc2047_maint = "%s (%s)" % (email, rfc2047_name)
109 rfc822_maint = "%s <%s>" % (name, email)
110 rfc2047_maint = "%s <%s>" % (rfc2047_name, email)
112 if email.find("@") == -1 and email.find("buildd_") != 0:
113 raise ParseMaintError, "No @ found in email address part."
115 return (rfc822_maint, rfc2047_maint, name, email)
117 ################################################################################