def getmsgparts(self, m, L, level):
ctype = m.gettype()
if level or ctype != "text/plain":
print ". " * level + str(ctype)
if ctype == "text/plain":
L.append(m.getbodytext())
elif ctype in ("multipart/alternative", "multipart/mixed"):
for part in m.getbodyparts():
self.getmsgparts(part, L, level + 1)
elif ctype == "message/rfc822":
f = StringIO(m.getbodytext())
m = mhlib.Message("<folder>", 0, f)
self.getheaders(m, L)
self.getmsgparts(m, L, level + 1)
def formatresults(self,
text,
results,
maxlines=MAXLINES,
lo=0,
hi=sys.maxint):
stop = self.stopdict.has_key
words = [w for w in re.findall(r"\w+\*?", text.lower()) if not stop(w)]
pattern = r"\b(" + "|".join(words) + r")\b"
pattern = pattern.replace("*", ".*") # glob -> re syntax
prog = re.compile(pattern, re.IGNORECASE)
print '=' * 70
rank = lo
qw = self.index.query_weight(text)
for docid, score in results[lo:hi]:
rank += 1
path = self.docpaths[docid]
score = 100.0 * score / qw
print "Rank: %d Score: %d%% File: %s" % (rank, score, path)
path = os.path.join(self.mh.getpath(), path)
try:
fp = open(path)
except (IOError, OSError), msg:
print "Can't open:", msg
continue
msg = mhlib.Message("<folder>", 0, fp)
for header in "From", "To", "Cc", "Bcc", "Subject", "Date":
h = msg.getheader(header)
if h:
print "%-8s %s" % (header + ":", h)
text = self.getmessagetext(msg)
if text:
print
nleft = maxlines
for part in text:
for line in part.splitlines():
if prog.search(line):
print line
nleft -= 1
if nleft <= 0:
break
if nleft <= 0:
break
print '-' * 70
def writeparts(part, oname):
global partnum
content = part.getbody() # decoded content or list
if type(content) == ListType: # multiparts: recur for each
for subpart in content:
writeparts(subpart, oname)
else: # else single decoded part
assert type(content) == StringType # use filename if in headers
print
print part.getparamnames() # else make one with counter
fmode = 'wb'
fname = part.getparam('name')
if not fname:
fmode = 'w'
fname = oname + str(partnum)
if part.gettype() == 'text/plain':
fname = fname + '.txt'
elif part.gettype() == 'text/html':
fname = fname + '.html'
output = open(fname, fmode) # mode must be 'wb' on windows
print 'writing:', output.name # for word doc files, not 'w'
output.write(content)
partnum = partnum + 1
partnum = 0
input = open(iname, 'r') # open mail file
message = mhlib.Message('.', 0, input) # folder, number args ignored
writeparts(message, oname)
print 'done: wrote %s parts' % partnum