Merge branch 'master' of https://mit.cs.uchicago.edu/skr/cmsc13600-public

hw6/core.py

@@ -8,7 +8,7 @@ import os
 import json
 
 def imdb_title_words():
-    f = open('title.csv','r')
+    f = open('title.csv','r', errors='replace')
     line = f.readline()
 
     while line != "":
@@ -22,7 +22,7 @@ def imdb_title_words():
     f.close()
 
 def imdb_years():
-    f = open('title.csv','r')
+    f = open('title.csv','r', errors='replace')
     line = f.readline()
 
     while line != "":

hw6/countD.py

+from core import *
+from ooc import *
+
 """
 Get the dataset first, download title.csv put it in the pa1 folder
 https://www.dropbox.com/s/zl7yt8cl0lvajxg/title.csv?dl=0

hw6/ooc.py

@@ -66,13 +66,20 @@ class MemoryLimitedHashMap(object):
     return set([k for k in self._data])
 
 
-  def flushed(self):
+  def flushed(self, returnSubKeys=False):
     '''
     Returns a set over keys that have been flushed. 
     Tuple is (key, location)
+    
+    if returnSubKeys=True
+    The tuple is ((key,subkey), location), if no subkey is provided it's just 
+    (key)
     '''
-
-    return set([self.path2Key(k) for k in os.listdir(self.diskfile)])
+    
+    if not returnSubKeys:    
+        return set([self.path2Key(k) for k in os.listdir(self.diskfile)])
+    else:
+        return set([self.path2Subkey(k) for k in os.listdir(self.diskfile)])
 
   def keyPath(self, k, subkey):
     return self.diskfile+"/"+str(k)+ "_" + subkey
@@ -81,7 +88,11 @@ class MemoryLimitedHashMap(object):
     key = k.split("_")[0]
     return key
 
-  def flushKey(self, k, subkey):
+  def path2Subkey(self, k):
+    key = tuple(k.split("_"))
+    return key
+
+  def flushKey(self, k, subkey=""):
     '''
     Removes the key from the dictionary and 
     persists it to disk.