diff options
Diffstat (limited to 'misc/xml')
| -rwxr-xr-x | misc/xml/be-mail-to-xml | 175 | ||||
| -rwxr-xr-x | misc/xml/be-xml-to-mbox | 220 | ||||
| -rwxr-xr-x | misc/xml/catmutt | 59 |
3 files changed, 454 insertions, 0 deletions
diff --git a/misc/xml/be-mail-to-xml b/misc/xml/be-mail-to-xml new file mode 100755 index 0000000..5a1a88f --- /dev/null +++ b/misc/xml/be-mail-to-xml @@ -0,0 +1,175 @@ +#!/usr/bin/env python +# Copyright (C) 2009-2010 W. Trevor King <wking@drexel.edu> +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License along +# with this program; if not, write to the Free Software Foundation, Inc., +# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. +""" +Convert an mbox into xml suitable for input into be. + $ be-mbox-to-xml file.mbox | be import-xml -c <ID> - +mbox is a flat-file format, consisting of a series of messages. +Messages begin with a a From_ line, followed by RFC 822 email, +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 optparse +from time import asctime, gmtime, mktime +import types +from xml.sax.saxutils import escape + +BREAK = u'--' # signature separator +DEFAULT_ENCODING = get_output_encoding() + +KNOWN_IDS = [] + +def normalize_email_address(address): + """ + Standardize whitespace, etc. + """ + addr = email.utils.formataddr(email.utils.parseaddr(address)) + if len(addr) == 0: + return None + return addr + +def normalize_RFC_2822_date(date): + """ + Some email clients write non-RFC 2822-compliant date tags like: + Fri, 18 Sep 2009 08:49:02 -0400 (EDT) + with the non-standard (EDT) timezone name. This funtion attempts + to deal with such inconsistencies. + """ + time_tuple = email.utils.parsedate(date) + assert time_tuple != 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): + if line.startswith(BREAK): + break + 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: + 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'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: + new_fields[k] = fields[k] + 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: + refs = message[u'references'].split() + 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. + refs = fields[u'in-reply-to'].split() + found_ref = False + 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 + + if fields[u'alt-id'] != None: + KNOWN_IDS.append(fields[u'alt-id']) + + if message.is_multipart(): + ret = [] + alt_id = fields[u'alt-id'] + from_str = fields[u'author'] + date = fields[u'date'] + for m in message.walk(): + if m == message: + 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 + 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(), \ + # u"Unknown charset: %s" % charset + + if message[u'content-transfer-encoding'] == 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?" + if fields[u'content-type'].startswith(u"text/"): + body = strip_footer(unicode(body, encoding=charset)) + else: + body = base64.encode(body) + fields[u'body'] = body + lines = [u"<comment>"] + for tag,body in fields.items(): + if body != 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), + default='mbox', choices=formats) + 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>" + for message in mb: + print comment_message_to_xml(message) + print u"</be-xml>" + + +if __name__ == "__main__": + import sys + import codecs + + sys.stdout = codecs.getwriter(DEFAULT_ENCODING)(sys.stdout) + main(sys.argv) diff --git a/misc/xml/be-xml-to-mbox b/misc/xml/be-xml-to-mbox new file mode 100755 index 0000000..c8b7479 --- /dev/null +++ b/misc/xml/be-xml-to-mbox @@ -0,0 +1,220 @@ +#!/usr/bin/env python +# Copyright (C) 2009-2010 W. Trevor King <wking@drexel.edu> +# +# This program is free software; you can redistribute it and/or modify +# it under the terms of the GNU General Public License as published by +# the Free Software Foundation; either version 2 of the License, or +# (at your option) any later version. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License along +# with this program; if not, write to the Free Software Foundation, Inc., +# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. +""" +Convert xml output of `be list --xml` into mbox format for browsing +with a mail reader. For example + $ be list --xml --status=all | be-xml-to-mbox | catmutt + +mbox is a flat-file format, consisting of a series of messages. +Messages begin with a a From_ line, followed by RFC 822 email, +followed by a blank line. +""" + +#from mailbox import mbox, Message # the mailbox people really want an on-disk copy +import email.utils +from libbe.util.encoding import get_output_encoding +from libbe.util.utility import str_to_time as rfc2822_to_gmtime_integer +from time import asctime, gmtime +import types +try: # import core module, Python >= 2.5 + from xml.etree import ElementTree +except ImportError: # look for non-core module + from elementtree import ElementTree +from xml.sax.saxutils import unescape + + +DEFAULT_DOMAIN = "invalid.com" +DEFAULT_EMAIL = "dummy@" + DEFAULT_DOMAIN +DEFAULT_ENCODING = get_output_encoding() + +def rfc2822_to_asctime(rfc2822_string): + """Convert an RFC 2822-fomatted string into a asctime string. + >>> rfc2822_to_asctime("Thu, 01 Jan 1970 00:00:00 +0000") + "Thu Jan 01 00:00:00 1970" + """ + if rfc2822_string == "": + return asctime(gmtime(0)) + return asctime(gmtime(rfc2822_to_gmtime_integer(rfc2822_string))) + +class LimitedAttrDict (dict): + """ + Dict with error checking, to avoid invalid bug/comment fields. + """ + _attrs = [] # override with list of valid attribute names + def __init__(self, **kwargs): + dict.__init__(self) + for key,value in kwargs.items(): + self[key] = value + def __setitem__(self, key, item): + self._validate_key(key) + dict.__setitem__(self, key, item) + def _validate_key(self, key): + if key in self._attrs: + return + elif type(key) not in types.StringTypes: + raise TypeError, "Invalid attribute type %s for '%s'" % (type(key), key) + else: + raise ValueError, "Invalid attribute name '%s'" % key + +class Bug (LimitedAttrDict): + _attrs = [u"uuid", + u"short-name", + u"severity", + u"status", + u"assigned", + u"reporter", + u"creator", + u"created", + u"summary", + u"comments", + u"extra-strings"] + def print_to_mbox(self): + if "creator" in self: + # otherwise, probably a `be show` uuid-only bug to avoid + # root comments. + name,addr = email.utils.parseaddr(self["creator"]) + print "From %s %s" % (addr, rfc2822_to_asctime(self["created"])) + print "Message-id: <%s@%s>" % (self["uuid"], DEFAULT_DOMAIN) + print "Date: %s" % self["created"] + print "From: %s" % self["creator"] + print "Content-Type: %s; charset=%s" \ + % ("text/plain", DEFAULT_ENCODING) + print "Content-Transfer-Encoding: 8bit" + print "Subject: %s: %s" % (self["short-name"], self["summary"]) + if "extra-strings" in self: + for estr in self["extra-strings"]: + print "X-Extra-String: %s" % estr + print "" + print self["summary"] + print "" + if "comments" in self: + for comment in self["comments"]: + comment.print_to_mbox(self) + def init_from_etree(self, element): + assert element.tag == "bug", element.tag + for field in element.getchildren(): + text = unescape(unicode(field.text).decode("unicode_escape").strip()) + if field.tag == "comment": + comm = Comment() + comm.init_from_etree(field) + if "comments" in self: + self["comments"].append(comm) + else: + self["comments"] = [comm] + elif field.tag == "extra-string": + if "extra-strings" in self: + self["extra-strings"].append(text) + else: + self["extra-strings"] = [text] + else: + self[field.tag] = text + +def wrap_id(id): + if "@" not in id: + return "<%s@%s>" % (id, DEFAULT_DOMAIN) + return id + +class Comment (LimitedAttrDict): + _attrs = [u"uuid", + u"alt-id", + u"short-name", + u"in-reply-to", + u"author", + u"date", + u"content-type", + u"body", + u"extra-strings"] + def print_to_mbox(self, bug=None): + if bug == None: + bug = Bug() + bug[u"uuid"] = u"no-uuid" + name,addr = email.utils.parseaddr(self["author"]) + print "From %s %s" % (addr, rfc2822_to_asctime(self["date"])) + if "uuid" in self: id = self["uuid"] + elif "alt-id" in self: id = self["alt-id"] + else: id = None + if id != None: + print "Message-id: %s" % wrap_id(id) + if "alt-id" in self: + print "Alt-id: %s" % wrap_id(self["alt-id"]) + print "Date: %s" % self["date"] + print "From: %s" % self["author"] + subject = "" + if "short-name" in self: + subject += self["short-name"]+u": " + if "summary" in bug: + subject += bug["summary"] + else: + subject += u"no-subject" + print "Subject: %s" % subject + if "in-reply-to" not in self.keys(): + self["in-reply-to"] = bug["uuid"] + print "In-Reply-To: %s" % wrap_id(self["in-reply-to"]) + if "extra-strings" in self: + for estr in self["extra-strings"]: + print "X-Extra-String: %s" % estr + if self["content-type"].startswith("text/"): + print "Content-Transfer-Encoding: 8bit" + print "Content-Type: %s; charset=%s" \ + % (self["content-type"], DEFAULT_ENCODING) + else: + print "Content-Transfer-Encoding: base64" + print "Content-Type: %s;" % (self["content-type"]) + print "" + print self["body"] + print "" + def init_from_etree(self, element): + assert element.tag == "comment", element.tag + for field in element.getchildren(): + text = unescape(unicode(field.text).decode("unicode_escape").strip()) + if field.tag == "extra-string": + if "extra-strings" in self: + self["extra-strings"].append(text) + else: + self["extra-strings"] = [text] + else: + if field.tag == "body": + text+="\n" + self[field.tag] = text + +def print_to_mbox(element): + if element.tag == "bug": + b = Bug() + b.init_from_etree(element) + b.print_to_mbox() + elif element.tag == "comment": + c = Comment() + c.init_from_etree(element) + c.print_to_mbox() + elif element.tag in ["be-xml"]: + for elt in element.getchildren(): + print_to_mbox(elt) + +if __name__ == "__main__": + import codecs + import sys + + sys.stdin = codecs.getreader(DEFAULT_ENCODING)(sys.stdin) + sys.stdout = codecs.getwriter(DEFAULT_ENCODING)(sys.stdout) + + if len(sys.argv) == 1: # no filename given, use stdin + xml_unicode = sys.stdin.read() + else: + xml_unicode = codecs.open(sys.argv[1], "r", DEFAULT_ENCODING).read() + xml_str = xml_unicode.encode("unicode_escape").replace(r"\n", "\n") + elist = ElementTree.XML(xml_str) + print_to_mbox(elist) diff --git a/misc/xml/catmutt b/misc/xml/catmutt new file mode 100755 index 0000000..601f14f --- /dev/null +++ b/misc/xml/catmutt @@ -0,0 +1,59 @@ +#!/bin/sh + +# catmutt - wrap mutt allowing mboxes read from stdin. +# +# Copyright (C) 1998-1999 Moritz Barsnick <barsnick (at) gmx (dot) net>, +# 2009 William Trevor King <wking (at) drexel (dot) edu> +# +# This program is free software; you can redistribute it and/or +# modify it under the terms of the GNU General Public License +# version 2 as published by the Free Software Foundation. +# +# This program is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write to the Free Software +# Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA +# +# developed from grepm-0.6 +# http://www.barsnick.net/sw/grepm.html + +PROGNAME=`basename "$0"` +export TMPDIR="${TMPDIR-/tmp}" # used by mktemp +umask 077 + +if [ $# -gt 0 ] && [ "$1" = "--help" ]; then + echo 1>&2 "Usage: ${PROGNAME} [--help] mutt-arguments" + echo 1>&2 "" + echo 1>&2 "Read a mailbox file from stdin and opens it with mutt." + echo 1>&2 "For example: cat somefile.mbox | ${PROGNAME}" + exit 0 +fi + +# Note: the -t/-p options to mktemp are deprecated for mktemp (GNU +# coreutils) 7.1 in favor of --tmpdir but the --tmpdir option does not +# exist yet for my 6.10-3ubuntu2 coreutils +TMPFILE=`mktemp -t catmutt.XXXXXX` || exit 1 + +trap "rm -f ${TMPFILE}; exit 1" 1 2 3 13 15 + +cat > "${TMPFILE}" || exit 1 + +# Now that we've read in the mailbox file, reopen stdin for mutt/user +# interaction. When in a pipe we're not technically in a tty, so use +# a little hack from "greno" at +# http://www.linuxforums.org/forum/linux-programming-scripting/98607-bash-stdin-problem.html +tty="/dev/`ps -p$$ --no-heading | awk '{print $2}'`" +exec < ${tty} + +if [ `wc -c "${TMPFILE}" | awk '{print $1}'` -gt 0 ]; then + echo 1>&2 "Calling mutt on temporary mailbox file (${TMPFILE})." + mutt -R -f "${TMPFILE}" "$@" +else + echo 1>&2 "Empty mailbox input." +fi + +rm -f "${TMPFILE}" && echo 1>&2 "Deleted temporary mailbox file (${TMPFILE})." |