final submission for homework 4

370/homework/huffman.py

@@ -1,90 +1,20 @@
 import queue
-class Node():
+import heapq
+
+class Node:
     def __init__(self, c, weight):
         self.c = c
         self.weight = weight
         self.left = None
         self.right = None
 
+        self.code = ''
+  
     def __repr__(self):
         return f'{self.c}|{self.weight}'
 
-class MinHeap():
-    def __init__(self):
-        self.data = []
-    
-    def empty(self):
-        return self.size() == 0
-
-    def size(self):
-        return len(self.data)
-
-    def print(self):
-        for x in self.data:
-            print(x.c + str(x.freq))
-
-    def insert(self, val):
-        self.data.append(val)
-        self.__heapifyUp(len(self.data) - 1)
-
-    def extractMin(self):
-        temp = self.data[0]
-        self.__swap(0, -1)    
-        self.data.remove(self.data[-1])
-        self.__heapifyDown(0)
-        return temp
-
-    def __swap(self,i,j):
-        self.data[i], self.data[j] = self.data[j], self.data[i]
-
-    def __heapifyUp(self, idx):
-        if idx > 0:
-            parent = (idx - 1) // 2
-            if (self.data[parent].freq > self.data[idx].freq):
-                self.__swap(parent, idx)
-                self.__heapifyUp(parent)
-    
-    def __heapifyDown(self, idx):
-        data = self.data
-        left = 2 * idx + 1
-        right = 2 * idx + 2
-        mini = idx
-        if (left < len(data) and (data[left].freq < data[mini].freq)):
-            mini = left
-        if (right < len(data) and (data[right].freq < data[mini].freq)):
-            mini = right
-        if (mini is not idx):
-            self.__swap(mini, idx)
-            self.__heapifyDown(mini)
-
-    def printChar(self, c):
-        # Traverse through the tree until we get to a leaf then back out
-        tmp = self.data[0]
-        # keep going until we hit a leaf
-        while tmp.left is not None or tmp.right is not None:
-            # 0 if left : 1 if right
-            continue
-
-
-def main():
-    pq = MinHeap()
-    pq.insert(Node(' ', 1))
-    pq.insert(Node('d', 4))
-    pq.insert(Node('e', 10))
-    pq.insert(Node('i', 13))
-    pq.insert(Node('s', 2))
-    pq.insert(Node('m', 8))
-    pq.insert(Node('o', 6))
-
-
-    assert(list(map(lambda x: x.freq, pq.data)) == [1, 2, 6, 13, 4, 10, 8])
-    assert(pq.extractMin().freq == 1)
-    assert(list(map(lambda x: x.freq, pq.data)) == [2, 4, 6, 13, 8, 10])
-    assert(pq.extractMin().freq == 2)
-    assert(list(map(lambda x: x.freq, pq.data)) == [4, 8, 6, 13, 10])
-    assert(pq.extractMin().freq == 4)
-    pq.print()
-    print("Heap works")
+    def __lt__(self, other):
+        return self.weight < other.weight
 
 def frequencyMap(string):
     ret = []
@@ -99,25 +29,50 @@ def frequencyMap(string):
                 if k.c == i:
                     k.weight += 1
 
-    # Sort the charmap based on the frequencies
-    ret.sort(key=lambda x: x.weight)
+    # Sort the charmap alphabetically
+    ret.sort(key=lambda x: x.c)
     return ret
 
 
-def buildMinHeap(freqs):
-    heap = MinHeap()
-    _queue = queue.Queue()
-    while _queue.qsize() >= 2:
-        left = _queue.get()
-        right = _queue.get()
-        weight = left.weight + right.weight
-        root = Node('*', weight)
-    # Once there is one item in the queue left we can simply return the new thing
+def encode(freqs):
+    # add things to our min heap
+    heap = [i for i in freqs]
+    heapq.heapify(heap)
+
+    # now we can merge all the nodes together
+    while len(heap) > 1:
+        # pop two items from the queuee
+        left = heapq.heappop(heap)
+        right = heapq.heappop(heap)
+
+        # setup the new root node
+        root = Node('*', left.weight + right.weight)
+        root.left = left
+        root.right = right
+
+        # re-insert the new subtree into the minheap
+        heapq.heappush(heap, root)
+    # return the heap itself so we cna do stuff with it
     return heap
 
 
+def decode(root, binaryStr):
+    string = ''
+    curr = root
+    for i in binaryStr:
+        if i == '0':
+            curr = curr.left
+        else:
+            curr = curr.right
+        # check if we're at a leaf
+        if curr.left is None and curr.right is None:
+            string += curr.c
+            curr = root
+    print(string)
+
 
 def printEncoding(text, heap):
+    # prints out the encoding for a given string
     for i in text:
         heap.printChar(i)
     
@@ -126,8 +81,15 @@ def printEncoding(text, heap):
 if __name__ == "__main__":
     text = input()
     binary = input()
+    #print(f'{text}\n{binary}\n===================')
+
     # calculate the frequency of each character
     frequencies = frequencyMap(text)
-    print(frequencies)
-    heap = buildMinHeap(frequencies)
-    printEncoding(binary, heap)
+
+    # build up our heap to display info from
+    heap = encode(frequencies)[0]
+    #print(heap)
+
+    # decode the binary
+    decode(heap, binary)
+