From 9d2edc0e17cc16eaea49dbea379b85ba4f1e610e Mon Sep 17 00:00:00 2001
From: Jay Weisskopf <jay@jayschwa.net>
Date: Tue, 3 Jul 2018 15:08:32 -0400
Subject: Accept more than 6 fractional digits in `isoparse`

RFC 3339 does not specify a limit to the number of fractional digits
that can be provided. In the wild, languages like Go will provide up
to 9 digits by default.

Since the standard library's `datetime` only supports precision down
to microseconds, any extra digits in the fractional component are
truncated.

Fixes #786
---
 dateutil/parser/isoparser.py | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

(limited to 'dateutil/parser')

diff --git a/dateutil/parser/isoparser.py b/dateutil/parser/isoparser.py
index 7c755e5..172972b 100644
--- a/dateutil/parser/isoparser.py
+++ b/dateutil/parser/isoparser.py
@@ -88,7 +88,7 @@ class isoparser(object):
         - ``hh``
         - ``hh:mm`` or ``hhmm``
         - ``hh:mm:ss`` or ``hhmmss``
-        - ``hh:mm:ss.sss`` or ``hh:mm:ss.ssssss`` (3-6 sub-second digits)
+        - ``hh:mm:ss.ssssss`` (Up to 6 sub-second digits)
 
         Midnight is a special case for `hh`, as the standard supports both
         00:00 and 24:00 as a representation. The decimal separator can be
@@ -199,10 +199,9 @@ class isoparser(object):
         return self._parse_tzstr(tzstr, zero_as_utc=zero_as_utc)
 
     # Constants
-    _MICROSECOND_END_REGEX = re.compile(b'[-+Z]+')
     _DATE_SEP = b'-'
     _TIME_SEP = b':'
-    _MICRO_SEPS = b'.,'
+    _FRACTION_REGEX = re.compile(b'[\\.,]([0-9]+)')
 
     def _parse_isodate(self, dt_str):
         try:
@@ -357,16 +356,14 @@ class isoparser(object):
                     pos += 1
 
             if comp == 3:
-                # Microsecond
-                if timestr[pos:pos + 1] not in self._MICRO_SEPS:
+                # Fraction of a second
+                frac = self._FRACTION_REGEX.match(timestr[pos:])
+                if not frac:
                     continue
 
-                pos += 1
-                us_str = self._MICROSECOND_END_REGEX.split(timestr[pos:pos + 6],
-                                                           1)[0]
-
+                us_str = frac.group(1)[:6]  # Truncate to microseconds
                 components[comp] = int(us_str) * 10**(6 - len(us_str))
-                pos += len(us_str)
+                pos += len(frac.group())
 
         if pos < len_str:
             raise ValueError('Unused components in ISO string')
-- 
cgit v1.2.3