diff options
Diffstat (limited to 'misc/xml/be-mail-to-xml')
-rwxr-xr-x | misc/xml/be-mail-to-xml | 99 |
1 files changed, 53 insertions, 46 deletions
diff --git a/misc/xml/be-mail-to-xml b/misc/xml/be-mail-to-xml index 6155baa..6071c74 100755 --- a/misc/xml/be-mail-to-xml +++ b/misc/xml/be-mail-to-xml @@ -27,19 +27,21 @@ followed by a blank line. import base64 import email.utils -from libbe.util.encoding import get_output_encoding -from libbe.util.utility import time_to_str -import mailbox # the mailbox people really want an on-disk copy +import mailbox # the mailbox people really want an on-disk copy import optparse -from time import asctime, gmtime, mktime import types +from time import mktime from xml.sax.saxutils import escape -BREAK = u'--' # signature separator +from libbe.util.encoding import get_output_encoding +from libbe.util.utility import time_to_str + +BREAK = u'--' # signature separator DEFAULT_ENCODING = get_output_encoding() KNOWN_IDS = [] + def normalize_email_address(address): """ Standardize whitespace, etc. @@ -49,6 +51,7 @@ def normalize_email_address(address): return None return addr + def normalize_RFC_2822_date(date): """ Some email clients write non-RFC 2822-compliant date tags like: @@ -57,60 +60,59 @@ def normalize_RFC_2822_date(date): to deal with such inconsistencies. """ time_tuple = email.utils.parsedate(date) - assert time_tuple != None, \ + assert time_tuple is not None, \ 'unparsable date: "%s"' % date return time_to_str(mktime(time_tuple)) + def strip_footer(body): body_lines = body.splitlines() - for i,line in enumerate(body_lines): + for i, line in enumerate(body_lines): if line.startswith(BREAK): break - i += 1 # increment past the current valid line. + i += 1 # increment past the current valid line. return u'\n'.join(body_lines[:i]).strip() + def comment_message_to_xml(message, fields=None): - if fields == None: + if fields is None: fields = {} - new_fields = {} - new_fields[u'alt-id'] = message[u'message-id'] - new_fields[u'in-reply-to'] = message[u'in-reply-to'] - new_fields[u'author'] = normalize_email_address(message[u'from']) - new_fields[u'date'] = message[u'date'] - if new_fields[u'date'] != None: + new_fields = {u'alt-id': message[u'message-id'], u'in-reply-to': message[u'in-reply-to'], + u'author': normalize_email_address(message[u'from']), u'date': message[u'date']} + if new_fields[u'date'] is not None: new_fields[u'date'] = normalize_RFC_2822_date(new_fields[u'date']) new_fields[u'content-type'] = message.get_content_type() - for k,v in new_fields.items(): - if v != None and type(v) != types.UnicodeType: - fields[k] = unicode(v, encoding=DEFAULT_ENCODING) - elif v == None and k in fields: + for k, v in new_fields.items(): + if v is not None and type(v) != types.UnicodeType: + fields[k] = str(v, encoding=DEFAULT_ENCODING) + elif v is None and k in fields: new_fields[k] = fields[k] - for k,v in fields.items(): + for k, v in fields.items(): if k not in new_fields: new_fields.k = fields[k] fields = new_fields - if fields[u'in-reply-to'] == None: - if message[u'references'] != None: + if fields[u'in-reply-to'] is None: + if message[u'references'] is not None: refs = message[u'references'].split() - for ref in refs: # search for a known reference id. + for ref in refs: # search for a known reference id. if ref in KNOWN_IDS: fields[u'in-reply-to'] = ref break - if fields[u'in-reply-to'] == None and len(refs) > 0: - fields[u'in-reply-to'] = refs[0] # default to the first - else: # check for mutliple in-reply-to references. + if fields[u'in-reply-to'] is None and len(refs) > 0: + fields[u'in-reply-to'] = refs[0] # default to the first + else: # check for mutliple in-reply-to references. refs = fields[u'in-reply-to'].split() found_ref = False - for ref in refs: # search for a known reference id. + for ref in refs: # search for a known reference id. if ref in KNOWN_IDS: fields[u'in-reply-to'] = ref found_ref = True break if found_ref == False and len(refs) > 0: - fields[u'in-reply-to'] = refs[0] # default to the first + fields[u'in-reply-to'] = refs[0] # default to the first - if fields[u'alt-id'] != None: + if fields[u'alt-id'] is not None: KNOWN_IDS.append(fields[u'alt-id']) if message.is_multipart(): @@ -123,51 +125,56 @@ def comment_message_to_xml(message, fields=None): continue fields[u'author'] = from_str fields[u'date'] = date - if len(ret) > 0: # we've added one part already - fields.pop(u'alt-id') # don't pass alt-id to other parts - fields[u'in-reply-to'] = alt_id # others respond to first + if len(ret) > 0: # we've added one part already + fields.pop(u'alt-id') # don't pass alt-id to other parts + fields[u'in-reply-to'] = alt_id # others respond to first ret.append(comment_message_to_xml(m, fields)) return u'\n'.join(ret) charset = message.get_content_charset(DEFAULT_ENCODING).lower() - #assert charset == DEFAULT_ENCODING.lower(), \ + # assert charset == DEFAULT_ENCODING.lower(), \ # u"Unknown charset: %s" % charset - if message[u'content-transfer-encoding'] == None: + if message[u'content-transfer-encoding'] is None: encoding = DEFAULT_ENCODING else: encoding = message[u'content-transfer-encoding'].lower() - body = message.get_payload(decode=True) # attempt to decode - assert body != None, "Unable to decode?" + body = message.get_payload(decode=True) # attempt to decode + assert body is not None, "Unable to decode?" if fields[u'content-type'].startswith(u"text/"): - body = strip_footer(unicode(body, encoding=charset)) + body = strip_footer(str(body, encoding=charset)) else: - body = base64.encode(body) + body = base64.encodebytes(body) fields[u'body'] = body lines = [u"<comment>"] - for tag,body in fields.items(): - if body != None: + for tag, body in fields.items(): + if body is not None: ebody = escape(body) lines.append(u" <%s>%s</%s>" % (tag, ebody, tag)) lines.append(u"</comment>") return u'\n'.join(lines) + def main(argv): parser = optparse.OptionParser(usage='%prog [options] mailbox') formats = ['mbox', 'Maildir', 'MH', 'Babyl', 'MMDF'] parser.add_option('-f', '--format', type='choice', dest='format', help="Select the mailbox format from %s. See the mailbox module's documention for descriptions of these formats." \ - % ', '.join(formats), + % ', '.join(formats), default='mbox', choices=formats) - options,args = parser.parse_args(argv) + options, args = parser.parse_args(argv) mailbox_file = args[1] reader = getattr(mailbox, options.format) mb = reader(mailbox_file, factory=None) - print u'<?xml version="1.0" encoding="%s" ?>' % DEFAULT_ENCODING - print u"<be-xml>" + print + u'<?xml version="1.0" encoding="%s" ?>' % DEFAULT_ENCODING + print + u"<be-xml>" for message in mb: - print comment_message_to_xml(message) - print u"</be-xml>" + print + comment_message_to_xml(message) + print + u"</be-xml>" if __name__ == "__main__": |