mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-09-26 18:29:57 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 10

Patch by Mike Meyer:

Browse source 
Extended the rfc822 parsedate routines to handle the cases they failed
on in an archive of ~37,000 messages.  I believe the changes are
compatible, in that all previously correct parsing are still correct.

[I still see problems with some messages, but no showstoppers.]
This commit is contained in:
Guido van Rossum 1998-12-23 22:22:10 +00:00
parent 9a4d63730e
commit db01ee0e22
1 changed files with 19 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

24
Lib/rfc822.py
View file

@ -748,9 +748,11 @@ def dump_address_pair(pair):
# Parse a date field # Parse a date field
_monthnames = ['Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', _monthnames = ['jan', 'feb', 'mar', 'apr', 'may', 'jun', 'jul',
'Aug', 'Sep', 'Oct', 'Nov', 'Dec'] 'aug', 'sep', 'oct', 'nov', 'dec',
_daynames = ['Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun'] 'january', 'february', 'march', 'april', 'may', 'june', 'july',
'august', 'september', 'october', 'november', 'december']
_daynames = ['mon', 'tue', 'wed', 'thu', 'fri', 'sat', 'sun']
# The timezone table does not include the military time zones defined # The timezone table does not include the military time zones defined
# in RFC822, other than Z. According to RFC1123, the description in # in RFC822, other than Z. According to RFC1123, the description in
@ -773,7 +775,7 @@ def parsedate_tz(data):
Accounts for military timezones. Accounts for military timezones.
""" """
data = string.split(data) data = string.split(data)
if data[0][-1] == ',' or data[0] in _daynames: if data[0][-1] in (',', '.') or string.lower(data[0]) in _daynames:
# There's a dayname here. Skip it # There's a dayname here. Skip it
del data[0] del data[0]
if len(data) == 3: # RFC 850 date, deprecated if len(data) == 3: # RFC 850 date, deprecated
@ -791,11 +793,23 @@ def parsedate_tz(data):
return None return None
data = data[:5] data = data[:5]
[dd, mm, yy, tm, tz] = data [dd, mm, yy, tm, tz] = data
mm = string.lower(mm)
if not mm in _monthnames: if not mm in _monthnames:
dd, mm, yy, tm, tz = mm, dd, tm, yy, tz dd, mm = mm, string.lower(dd)
if not mm in _monthnames: if not mm in _monthnames:
return None return None
mm = _monthnames.index(mm)+1 mm = _monthnames.index(mm)+1
if dd[-1] == ',':
dd = dd[:-1]
i = string.find(yy, ':')
if i > 0:
yy, tm = tm, yy
if yy[-1] == ',':
yy = yy[:-1]
if yy[0] not in string.digits:
yy, tz = tz, yy
if tm[-1] == ',':
tm = tm[:-1]
tm = string.splitfields(tm, ':') tm = string.splitfields(tm, ':')
if len(tm) == 2: if len(tm) == 2:
[thh, tmm] = tm [thh, tmm] = tm