def _email_decode_header(header):
"""Decode a message header value without converting charset.
Returns a list of (decoded_string, charset) pairs containing each of the
decoded parts of the header. Charset is None for non-encoded parts of the
header, otherwise a lower-case string containing the name of the character
set specified in the encoded string.
An email.errors.HeaderParseError may be raised when certain decoding error
occurs (e.g. a base64 decoding exception).
"""
# If no encoding, just return the header
header = str(header)
if not email.header.ecre.search(header):
return [(header, None)]
decoded = []
dec = ''
for line in header.splitlines():
# This line might not have an encoding in it
if not email.header.ecre.search(line):
decoded.append((line, None))
continue
parts = email.header.ecre.split(line)
while parts:
unenc = parts.pop(0).strip()
if unenc:
# Should we continue a long line?
if decoded and decoded[-1][1] is None:
decoded[-1] = (decoded[-1][0] + SPACE + unenc, None)
else:
decoded.append((unenc, None))
if parts:
charset, encoding = [s.lower() for s in parts[0:2]]
encoded = parts[2]
dec = None
if encoding == 'q':
dec = email.quoprimime.header_decode(encoded)
elif encoding == 'b':
paderr = len(encoded) % 4 # Postel's law: add missing padding
if paderr:
encoded += '==='[:4 - paderr]
try:
dec = email.base64mime.decode(encoded)
except binascii.Error, e:
dec = None
if dec is None:
dec = encoded
if decoded and decoded[-1][1] == charset:
decoded[-1] = (decoded[-1][0] + dec, decoded[-1][1])
else:
decoded.append((dec, charset))
del parts[0:3]
def main():
username = raw_input('Username: '******'Password: '******'imap.gmail.com', 993)
im.login(username, password)
dup_cnt = 0
line_yet = False
res, boxes = im.list()
for box_info in boxes:
flags, delim, name = re.search('\((.*?)\) "(.*?)" "(.*)"',
box_info).groups()
if '\Noselect' in flags: continue
name_d = name.decode('imap4-utf-7')
if name_d not in mboxes_to_check: continue
print '* Mailbox: %s' % name_d
res, data = im.select(name, readonly=True)
if res != 'OK':
print >> sys.stderr, '* Something bad happened.'
raise SystemExit
mail_cnt = int(data[0])
visit = {}
prev_per_mil = -1
res, [nums_s] = im.search(None, 'ALL')
nums = nums_s.split()
for i, num in enumerate(nums):
num = int(num)
res, data = im.fetch(num, '(BODY.PEEK[HEADER])')
header = data[0][1]
digest = hashlib.sha1(header).hexdigest()
arr = {}
try:
del key
except NameError:
pass
for row in header.splitlines():
if not row: continue
if row.startswith(' '):
arr[key] += row
else:
try:
key, val = row.split(': ', 1)
arr[key] = val
except ValueError:
pass
try:
subj = email.header.decode_header(arr['Subject'])[0]
subj = subj[0].decode(
'euc-kr' if subj[1] in ['ibm-euckr', '5601'] else
subj[1] if subj[1] else 'utf-8', 'replace')
except KeyError:
subj = '?'
try:
date = arr['Date']
except KeyError:
date = '?'
if digest in visit:
if line_yet:
print
line_yet = False
print '* Duplicate: %d. %s (%s)' % (num, subj, date)
dup_cnt += 1
continue
visit[digest] = {'subj': subj, 'date': date}
per_mil = 1000 * (i + 1) / len(nums)
if prev_per_mil != per_mil:
print '\r%d.%d%% (%d/%d)' % (per_mil / 10, per_mil % 10, i + 1,
len(nums)),
sys.stdout.flush()
line_yet = True
prev_per_mil = per_mil
if line_yet:
print
line_yet = False
print '* %d duplicate(s) found.' % dup_cnt
def main():
username = raw_input('Username: '******'Password: '******'imap.gmail.com', 993)
im.login(username, password)
dup_cnt = 0
line_yet = False
res, boxes = im.list()
for box_info in boxes:
flags, delim, name = re.search('\((.*?)\) "(.*?)" "(.*)"', box_info).groups()
if '\Noselect' in flags: continue
name_d = name.decode('imap4-utf-7')
if name_d not in mboxes_to_check: continue
print '* Mailbox: %s' % name_d
res, data = im.select(name, readonly=True)
if res != 'OK':
print >> sys.stderr, '* Something bad happened.'
raise SystemExit
mail_cnt = int(data[0])
visit = {}
prev_per_mil = -1
res, [nums_s] = im.search(None, 'ALL')
nums = nums_s.split()
for i, num in enumerate(nums):
num = int(num)
res, data = im.fetch(num, '(BODY.PEEK[HEADER])')
header = data[0][1]
digest = hashlib.sha1(header).hexdigest()
arr = {}
try: del key
except NameError: pass
for row in header.splitlines():
if not row: continue
if row.startswith(' '):
arr[key] += row
else:
try:
key, val = row.split(': ', 1)
arr[key] = val
except ValueError: pass
try:
subj = email.header.decode_header(arr['Subject'])[0]
subj = subj[0].decode('euc-kr' if subj[1] in ['ibm-euckr', '5601'] else subj[1] if subj[1] else 'utf-8', 'replace')
except KeyError: subj = '?'
try: date = arr['Date']
except KeyError: date = '?'
if digest in visit:
if line_yet: print; line_yet = False
print '* Duplicate: %d. %s (%s)' % (num, subj, date)
dup_cnt += 1
continue
visit[digest] = {'subj': subj, 'date': date}
per_mil = 1000*(i+1)/len(nums)
if prev_per_mil != per_mil:
print '\r%d.%d%% (%d/%d)' % (per_mil/10, per_mil%10, i+1, len(nums)),
sys.stdout.flush()
line_yet = True
prev_per_mil = per_mil
if line_yet: print; line_yet = False
print '* %d duplicate(s) found.' % dup_cnt