From 560ff3cacfa3409299bda27b6cd46ee4bca4153e Mon Sep 17 00:00:00 2001
From: Andrew Daniels <adaniels@quantopian.com>
Date: Thu, 4 May 2017 10:19:09 -0400
Subject: [PATCH] MAINT: Display diff if input to daily bar writer has
 gaps/extra bars

---
 tests/data/test_us_equity_pricing.py | 10 +++++++---
 zipline/data/us_equity_pricing.py    | 17 ++++++++++++++++-
 2 files changed, 23 insertions(+), 4 deletions(-)

diff --git a/tests/data/test_us_equity_pricing.py b/tests/data/test_us_equity_pricing.py
index 12c4ce80..c56d8df7 100644
--- a/tests/data/test_us_equity_pricing.py
+++ b/tests/data/test_us_equity_pricing.py
@@ -13,6 +13,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 from sys import maxsize
+import re
 
 from nose_parameterized import parameterized
 from numpy import (
@@ -399,9 +400,12 @@ class BcolzDailyBarWriterMissingDataTestCase(WithAssetFinder,
 
         # There are 21 sessions between the start and end date for this
         # asset, and we excluded one.
-        expected_msg = (
-            'Got 20 rows for daily bars table with first day=2015-06-02, last '
-            'day=2015-06-30, expected 21 rows.'
+        expected_msg = re.escape(
+            "Got 20 rows for daily bars table with first day=2015-06-02, last "
+            "day=2015-06-30, expected 21 rows.\n"
+            "Missing sessions: "
+            "[Timestamp('2015-06-15 00:00:00+0000', tz='UTC')]\n"
+            "Extra sessions: []"
         )
         with self.assertRaisesRegexp(AssertionError, expected_msg):
             writer.write(bar_data)
diff --git a/zipline/data/us_equity_pricing.py b/zipline/data/us_equity_pricing.py
index a599b778..ce2f7427 100644
--- a/zipline/data/us_equity_pricing.py
+++ b/zipline/data/us_equity_pricing.py
@@ -42,6 +42,7 @@ from pandas import (
     NaT,
     read_csv,
     read_sql,
+    to_datetime,
     Timestamp,
 )
 from pandas.tslib import iNaT
@@ -356,11 +357,25 @@ class BcolzDailyBarWriter(object):
             ]
             assert len(table) == len(asset_sessions), (
                 'Got {} rows for daily bars table with first day={}, last '
-                'day={}, expected {} rows.'.format(
+                'day={}, expected {} rows.\n'
+                'Missing sessions: {}\n'
+                'Extra sessions: {}'.format(
                     len(table),
                     asset_first_day.date(),
                     asset_last_day.date(),
                     len(asset_sessions),
+                    asset_sessions.difference(
+                        to_datetime(
+                            np.array(table['day']),
+                            unit='s',
+                            utc=True,
+                        )
+                    ).tolist(),
+                    to_datetime(
+                        np.array(table['day']),
+                        unit='s',
+                        utc=True,
+                    ).difference(asset_sessions).tolist(),
                 )
             )