Support for parsing ordinal days of month and docs.

leezqcst · Jun 2, 2015 · 2953545 · 2953545
1 parent 1d89292
commit 2953545
Show file tree

Hide file tree

Showing 4 changed files with 69 additions and 6 deletions.
diff --git a/arrow/locales.py b/arrow/locales.py
@@ -61,6 +61,8 @@ class Locale(object):
     day_names = []
     day_abbreviations = []
 
+    ordinal_day_re = r'(\d+)'
+
     def __init__(self):
 
         self._month_name_to_ordinal = None
@@ -205,6 +207,8 @@ class EnglishLocale(Locale):
     day_names = ['', 'Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
     day_abbreviations = ['', 'Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', 'Sun']
 
+    ordinal_day_re = r'((?P<value>[2-3]?1(?=st)|[2-3]?2(?=nd)|[2-3]?3(?=rd)|[1-3]?[04-9](?=th)|1[1-3](?=th))(st|nd|rd|th))'
+
     def _ordinal_number(self, n):
         if n % 100 not in (11, 12, 13):
             remainder = abs(n) % 10

diff --git a/arrow/parser.py b/arrow/parser.py
@@ -17,7 +17,7 @@ class ParserError(RuntimeError):
 
 class DateTimeParser(object):
 
-    _FORMAT_RE = re.compile('(YYY?Y?|MM?M?M?|DD?D?D?|HH?|hh?|mm?|ss?|SS?S?S?S?S?|ZZ?|a|A|X)')
+    _FORMAT_RE = re.compile('(YYY?Y?|MM?M?M?|Do|DD?D?D?|HH?|hh?|mm?|ss?|SS?S?S?S?S?|ZZ?|a|A|X)')
 
     _ONE_THROUGH_SIX_DIGIT_RE = re.compile('\d{1,6}')
     _ONE_THROUGH_FIVE_DIGIT_RE = re.compile('\d{1,5}')
@@ -63,7 +63,8 @@ def __init__(self, locale='en_us'):
         self._input_re_map.update({
             'MMMM': self._choice_re(self.locale.month_names[1:], re.IGNORECASE),
             'MMM': self._choice_re(self.locale.month_abbreviations[1:],
-                                   re.IGNORECASE)
+                                   re.IGNORECASE),
+            'Do': re.compile(self.locale.ordinal_day_re)
         })
 
     def parse_iso(self, string):
@@ -116,7 +117,6 @@ def parse(self, string, fmt):
         parts = {}
 
         for token in tokens:
-
             try:
                 input_re = self._input_re_map[token]
             except KeyError:
@@ -125,10 +125,11 @@ def parse(self, string, fmt):
             match = input_re.search(string)
 
             if match:
-
                 token_values.append(match.group(0))
-                self._parse_token(token, match.group(0), parts)
-
+                if 'value' in match.groupdict():
+                    self._parse_token(token, match.groupdict()['value'], parts)
+                else:
+                    self._parse_token(token, match.group(0), parts)
                 index = match.span(0)[1]
                 string = string[index:]
 
@@ -177,6 +178,9 @@ def _parse_token(self, token, value, parts):
         elif token in ['DD', 'D']:
             parts['day'] = int(value)
 
+        elif token in ['Do']:
+            parts['day'] = int(value)
+
         elif token.upper() in ['HH', 'H']:
             parts['hour'] = int(value)
 

diff --git a/docs/index.rst b/docs/index.rst
@@ -393,6 +393,8 @@ Use the following tokens in parsing and formatting:
 +--------------------------------+--------------+-------------------------------------------+
 |                                |D             |1, 2, 3 ... 30, 31                         |
 +--------------------------------+--------------+-------------------------------------------+
+|                                |Do            |1st, 2nd, 3rd ... 30th, 31st               |
++--------------------------------+--------------+-------------------------------------------+
 |**Day of Week**                 |dddd          |Monday, Tuesday, Wednesday ...             |
 +--------------------------------+--------------+-------------------------------------------+
 |                                |ddd           |Mon, Tue, Wed ...                          |

diff --git a/tests/parser_tests.py b/tests/parser_tests.py
@@ -5,6 +5,7 @@
 import time
 
 from arrow import parser
+from arrow.parser import ParserError
 
 
 class DateTimeParserTests(Chai):
@@ -485,3 +486,55 @@ def test_localized_month_abbreviation(self):
             parser_.parse('2013-Gen-01', 'YYYY-MMM-DD'),
             datetime(2013, 1, 1)
         )
+
+class DateTimeParserMonthOrdinalDayTests(Chai):
+
+    def setUp(self):
+        super(DateTimeParserMonthOrdinalDayTests, self).setUp()
+
+        self.parser = parser.DateTimeParser('en_us')
+
+    def test_matches(self):
+        assertEqual(
+            self.parser.parse('January 1st, 2013', 'MMMM Do, YYYY'),
+            datetime(2013, 1, 1)
+        )
+        assertEqual(
+            self.parser.parse('January 2nd, 2013', 'MMMM Do, YYYY'),
+            datetime(2013, 1, 2)
+        )
+        assertEqual(
+            self.parser.parse('January 3rd, 2013', 'MMMM Do, YYYY'),
+            datetime(2013, 1, 3)
+        )
+        assertEqual(
+            self.parser.parse('January 4th, 2013', 'MMMM Do, YYYY'),
+            datetime(2013, 1, 4)
+        )
+        assertEqual(
+            self.parser.parse('January 11th, 2013', 'MMMM Do, YYYY'),
+            datetime(2013, 1, 11)
+        )
+        assertEqual(
+            self.parser.parse('January 12th, 2013', 'MMMM Do, YYYY'),
+            datetime(2013, 1, 12)
+        )
+        assertEqual(
+            self.parser.parse('January 13th, 2013', 'MMMM Do, YYYY'),
+            datetime(2013, 1, 13)
+        )
+        assertEqual(
+            self.parser.parse('January 21st, 2013', 'MMMM Do, YYYY'),
+            datetime(2013, 1, 21)
+        )
+        assertEqual(
+            self.parser.parse('January 31st, 2013', 'MMMM Do, YYYY'),
+            datetime(2013, 1, 31)
+        )
+
+    def test_no_match(self):
+        with assertRaises(ParserError):
+            self.parser.parse('January 1th, 2013', 'MMMM Do, YYYY')
+
+        with assertRaises(ParserError):
+            self.parser.parse('January 11st, 2013', 'MMMM Do, YYYY')