From 73eb3f12f57f226c05e0220d95922ac03a41abdc Mon Sep 17 00:00:00 2001
From: Eddie Hebert <ehebert@quantopian.com>
Date: Thu, 1 Aug 2013 16:07:52 -0400
Subject: [PATCH] BUG: Prevent unintended keys from appearing in data bar.

The defaultdict behavior was allowing both algo code and
TradingAlgorithm wrappers to add unintended keys.

Remove use of defaultdict in favor of a dictionary that explicitly
adds the values in tradesimulation, otherwise allow a KeyError
if the bar is indexed with a sid that doesn't exist.

Also, when iterating over the keys in the data bar, only return
those keys that have pricing data.
---
 zipline/gens/tradesimulation.py | 11 +++++++++--
 zipline/protocol.py             |  7 ++++---
 2 files changed, 13 insertions(+), 5 deletions(-)

diff --git a/zipline/gens/tradesimulation.py b/zipline/gens/tradesimulation.py
index 521fa9f5..985f363c 100644
--- a/zipline/gens/tradesimulation.py
+++ b/zipline/gens/tradesimulation.py
@@ -15,7 +15,11 @@
 from logbook import Logger, Processor
 
 import zipline.finance.trading as trading
-from zipline.protocol import BarData, DATASOURCE_TYPE
+from zipline.protocol import (
+    BarData,
+    SIDData,
+    DATASOURCE_TYPE
+)
 from zipline.gens.utils import hash_args
 
 log = Logger('Trade Simulation')
@@ -198,5 +202,8 @@ class AlgorithmSimulator(object):
         Update the universe with new event information.
         """
         # Update our knowledge of this event's sid
-        sid_data = self.current_data[event.sid]
+        if event.sid in self.current_data:
+            sid_data = self.current_data[event.sid]
+        else:
+            sid_data = self.current_data[event.sid] = SIDData()
         sid_data.__dict__.update(event.__dict__)
diff --git a/zipline/protocol.py b/zipline/protocol.py
index 0376b49a..b32314eb 100644
--- a/zipline/protocol.py
+++ b/zipline/protocol.py
@@ -12,7 +12,6 @@
 # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 # See the License for the specific language governing permissions and
 # limitations under the License.
-from collections import defaultdict
 import datetime
 
 from . utils.protocol_utils import Enum
@@ -135,7 +134,7 @@ class BarData(object):
     """
 
     def __init__(self):
-        self._data = defaultdict(SIDData)
+        self._data = {}
         self._contains_override = None
 
     def __contains__(self, name):
@@ -164,7 +163,9 @@ class BarData(object):
         del self._data[name]
 
     def __iter__(self):
-        return self._data.iterkeys()
+        for sid, data in self._data.iteritems():
+            if len(data):
+                yield sid
 
     def keys(self):
         return self._data.keys()