utils: Add some ISO 8601 forms to get_date()

Support the forms listed by the W3C [1].  I also removed the
'%Y-%d-%m' form, which can be confused with the '%Y-%m-%d' ISO form.
The new ISO forms can use 'Z' to designate UTC or '[+-]HHMM' to
specify offsets from UTC.  Other time zone designators are not
supported.

The '%z' directive has only been supported since Python 3.2 [2], so if
you're running Pelican on Python 2.7, you're stuck with 'Z' for UTC.
Conveniently, we get ValueErrors for both invalid directives and
data/format missmatches, so we don't need special handling for the 2.7
case inside get_date().

[1]: http://www.w3.org/TR/NOTE-datetime
[2]: http://bugs.python.org/issue6641

docs/getting_started.rst

@@ -286,7 +286,10 @@ by the directory in which the file resides. For example, a file located at
 ``python/foobar/myfoobar.rst`` will have a category of ``foobar``. If you would
 like to organize your files in other ways where the name of the subfolder would
 not be a good category name, you can set the setting ``USE_FOLDER_AS_CATEGORY``
-to ``False``.
+to ``False``.  When parsing dates given in the page metadata, Pelican supports
+the W3C's `suggested subset ISO 8601`__.
+
+__ `W3C ISO 8601`_
 
 If you do not explicitly specify summary metadata for a given post, the
 ``SUMMARY_MAX_LENGTH`` setting can be used to specify how many words from the
@@ -478,3 +481,4 @@ metadata. That article will then be output to the ``drafts`` folder and not
 listed on the index page nor on any category page.
 
 .. _virtualenv: http://www.virtualenv.org/
+.. _W3C ISO 8601: http://www.w3.org/TR/NOTE-datetime

pelican/tests/test_utils.py

@@ -6,7 +6,7 @@ import os
 import datetime
 import time
 import locale
-from sys import platform
+from sys import platform, version_info
 from tempfile import mkdtemp
 
 from pelican.generators import TemplatePagesGenerator
@@ -37,26 +37,44 @@ class TestUtils(LoggedTestCase):
     def test_get_date(self):
         # valid ones
         date = datetime.datetime(year=2012, month=11, day=22)
-        date_hour = datetime.datetime(year=2012, month=11, day=22, hour=22,
+        date_hour = datetime.datetime(
-                                      minute=11)
+            year=2012, month=11, day=22, hour=22, minute=11)
-        date_hour_sec = datetime.datetime(year=2012, month=11, day=22, hour=22,
+        date_hour_sec = datetime.datetime(
-                                          minute=11, second=10)
+            year=2012, month=11, day=22, hour=22, minute=11, second=10)
-        dates = {'2012-11-22': date,
+        date_hour_sec_z = datetime.datetime(
-                 '2012/11/22': date,
+            year=2012, month=11, day=22, hour=22, minute=11, second=10,
-                 '2012-11-22 22:11': date_hour,
+            tzinfo=datetime.timezone.utc)
-                 '2012/11/22 22:11': date_hour,
+        date_hour_sec_0430 = datetime.datetime(
-                 '22-11-2012': date,
+            year=2012, month=11, day=22, hour=22, minute=11, second=10,
-                 '22/11/2012': date,
+            tzinfo=datetime.timezone(datetime.timedelta(hours=4, minutes=30)))
-                 '22.11.2012': date,
+        date_hour_sec_frac_z = datetime.datetime(
-                 '2012-22-11': date,
+            year=2012, month=11, day=22, hour=22, minute=11, second=10,
-                 '22.11.2012 22:11': date_hour,
+            microsecond=123000, tzinfo=datetime.timezone.utc)
-                 '2012-11-22 22:11:10': date_hour_sec}
+        dates = {
+            '2012-11-22': date,
+            '2012/11/22': date,
+            '2012-11-22 22:11': date_hour,
+            '2012/11/22 22:11': date_hour,
+            '22-11-2012': date,
+            '22/11/2012': date,
+            '22.11.2012': date,
+            '22.11.2012 22:11': date_hour,
+            '2012-11-22 22:11:10': date_hour_sec,
+            '2012-11-22T22:11:10Z': date_hour_sec_z,
+            '2012-11-22T22:11:10+0430': date_hour_sec_0430,
+            '2012-11-22T22:11:10.123Z': date_hour_sec_frac_z,
+            }
+
+        # invalid ones
+        invalid_dates = ['2010-110-12', 'yay']
+
+        if version_info < (3, 2):
+            dates.pop('2012-11-22T22:11:10-0500')
+            invalid_dates.append('2012-11-22T22:11:10-0500')
 
         for value, expected in dates.items():
             self.assertEqual(utils.get_date(value), expected, value)
 
-        # invalid ones
-        invalid_dates = ('2010-110-12', 'yay')
         for item in invalid_dates:
             self.assertRaises(ValueError, utils.get_date, item)
 

pelican/utils.py

@@ -15,7 +15,7 @@ from collections import Hashable
 from functools import partial
 
 from codecs import open, BOM_UTF8
-from datetime import datetime
+from datetime import datetime, timezone
 from itertools import groupby
 from jinja2 import Markup
 from operator import attrgetter
@@ -180,17 +180,39 @@ def get_date(string):
     If no format matches the given date, raise a ValueError.
     """
     string = re.sub(' +', ' ', string)
-    formats = ['%Y-%m-%d %H:%M', '%Y/%m/%d %H:%M',
+    formats = [
-               '%Y-%m-%d', '%Y/%m/%d',
+        # ISO 8601
-               '%d-%m-%Y', '%Y-%d-%m',  # Weird ones
+        '%Y',
-               '%d/%m/%Y', '%d.%m.%Y',
+        '%Y-%m',
-               '%d.%m.%Y %H:%M', '%Y-%m-%d %H:%M:%S']
+        '%Y-%m-%d',
+        '%Y-%m-%dT%H:%M%z',
+        '%Y-%m-%dT%H:%MZ',
+        '%Y-%m-%dT%H:%M',
+        '%Y-%m-%dT%H:%M:%S%z',
+        '%Y-%m-%dT%H:%M:%SZ',
+        '%Y-%m-%dT%H:%M:%S',
+        '%Y-%m-%dT%H:%M:%S.%f%z',
+        '%Y-%m-%dT%H:%M:%S.%fZ',
+        '%Y-%m-%dT%H:%M:%S.%f',
+        # end ISO 8601 forms
+        '%Y-%m-%d %H:%M',
+        '%Y-%m-%d %H:%M:%S',
+        '%Y/%m/%d %H:%M',
+        '%Y/%m/%d',
+        '%d-%m-%Y',
+        '%d.%m.%Y %H:%M',
+        '%d.%m.%Y',
+        '%d/%m/%Y',
+        ]
     for date_format in formats:
         try:
-            return datetime.strptime(string, date_format)
+            date = datetime.strptime(string, date_format)
         except ValueError:
-            pass
+            continue
-    raise ValueError("'%s' is not a valid date" % string)
+        if date_format.endswith('Z'):
+            date = date.replace(tzinfo=timezone.utc)
+        return date
+    raise ValueError('{0!r} is not a valid date'.format(string))
 
 
 class pelican_open(object):
@@ -510,15 +532,11 @@ def file_watcher(path):
 
 
 def set_date_tzinfo(d, tz_name=None):
-    """ Date without tzinfo shoudbe utc.
+    """Set the timezone for dates that don't have tzinfo"""
-    This function set the right tz to date that aren't utc and don't have
+    if tz_name and not d.tzinfo:
-    tzinfo.
-    """
-    if tz_name is not None:
         tz = pytz.timezone(tz_name)
         return tz.localize(d)
-    else:
+    return d
-        return d
 
 
 def mkdir_p(path):