# ex: ts=4 tw=0 sw=4 expandtab
import mailbox, email, re
import StringIO
"""
css
classes:
body: the body of the email
quoted: quoted text
sig: duh
level1header: top level headers
level2header: you get the idea
resentheader: for resent-*
level1content: ...
level2content: ...
resentcontent: ...
"""
CSSFILE = "../mailformat.css"
headermap = [
[['To','From','Cc','Bcc','Date','Subject','Newsgroups'],['level1header','level1content']],
[['User-Agent','Organization','List-Id','Reply-To','In-Reply-To','Message-Id','References'],['level2header','level2content']],
[['Resent-From','Resent-Bcc','Resent-Cc'],['resentheader','resentcontent']]
]
class chunk:
def __init__(self,chunk,type):
self.chunk = chunk
self.type = type
class body_chunker:
def __init__(self,mailbody):
self.body = mailbody
self.chunks = []
self.inquote = False
self.insig = False
self._build_chunks()
def _build_chunks(self):
quote = ""
body = ""
sig = ""
for line in StringIO.StringIO(self.body).readlines():
if re.search("^(>|\|).*",line):
quote += line
if self.inquote:
continue
else:
self.chunks.append(chunk(body,'body'))
body = ""
self.inquote = True
elif re.search("^-- $",line) or self.insig:
self.insig = True
sig += line
else:
if self.inquote:
#we've reached the end of a quote
self.chunks.append(chunk(quote,'quote'))
quote = ""
self.inquote = False
body += line
if quote != "":
self.chunks.append(chunk(quote,'quote'))
if body != "":
self.chunks.append(chunk(body,'body'))
if self.insig:
self.chunks.append(chunk(sig,'sig'))
class mailformatter:
def __init__(self,filename):
self.filename = filename
self.data=""
self.cssfile = CSSFILE
def setcss(self, cssfile):
self.cssfile = cssfile
def _do_headers(self,msg):
"""loop through each headergroup => color mapping,
and return the html"""
headers = ""
for headergroup in headermap:
for header in headergroup[0]:
if msg.has_key(header):
headers += """%s: %s\n""" % (headergroup[1][0],header,headergroup[1][1],
self._htmlescape(msg[header]))
headers +="\n"
return headers
def _do_body(self,msg):
data = ""
if msg.is_multipart():
for m in msg.get_payload():
data += self._do_body(m)
else:
#only return text/plain messages, the True argument to get_payload
#will decode it if it's qoupri or base64
if msg.get_content_type() == "text/plain":
data = self._sub_all(msg.get_payload(None, True))
return data
def _do_urls(self,chunk,cls):
return re.sub("(http://[^ <>\n]+)","\\1" % cls,chunk)
def _sub_all(self,chunk):
data = ""
self.b = body_chunker(chunk)
for part in self.b.chunks:
part.chunk = self._do_urls(self._htmlescape(part.chunk),part.type)
data += "%s" % (part.type,part.chunk)
return data
def _stringfactory(self, fp):
return fp.read()
def _htmlescape(self,foo):
return foo.replace("&","&").replace("<","<").replace(">",">")
def parse(self):
f = file(self.filename,'r')
if f:
self.ct = "text/html"
self.data += """
%s