From a5f2a96b1b8c49b88727bb77636003dd5058246a Mon Sep 17 00:00:00 2001
From: unknown <sohamhaldar04@gmail.com>
Date: Mon, 18 Mar 2024 14:33:12 +0530
Subject: [PATCH 1/2] Soham Haldar| compressor.py decompressor.py| actually
 made sure that the file was being compressed

---
 compressor.py   | 63 +++++++++++++++++++++++++++++++++++++++++++++++++
 decompressor.py | 30 +++++++++++++++++++++++
 2 files changed, 93 insertions(+)
 create mode 100644 compressor.py
 create mode 100644 decompressor.py

diff --git a/compressor.py b/compressor.py
new file mode 100644
index 00000000..7c5a79dc
--- /dev/null
+++ b/compressor.py
@@ -0,0 +1,63 @@
+import math
+def compress(ifile, codes, ofile):
+    symbol_codes = {}
+    with open(codes, 'r') as f:
+        for line in f:
+            last_space_index = line.rfind(' ')
+            if last_space_index != -1:
+                symbol = line[:last_space_index]
+                code = line[last_space_index + 1:].strip()
+                symbol_codes[symbol] = code
+    with open(ifile, 'r') as f:
+        itext = f.read().strip()
+    compressed = ''
+    for c in itext:
+        if c.isalpha() :
+            c=c.upper()
+            if c in symbol_codes:
+                compressed += symbol_codes[c]
+    compressed_bytes = compress_bits(compressed)
+    with open(ofile, 'wb') as f:
+        f.write(compressed_bytes)
+    entropy(itext,compressed)
+def entropy(a,b):
+    D = {}
+    E = {}
+    for i in a:
+        if i not in D:
+            D[i]=1
+        else:
+            D[i]+=1
+    for i in b:
+        if i not in E:
+            E[i]=1
+        else:
+            E[i]+=1
+    entropya=0
+    for i in D:
+        entropya+=(D[i]/len(a))*math.log2((len(a)/D[i]))
+    entropyb=0
+    for i in E:
+        entropyb+=(E[i]/len(b))*math.log2((len(b)/E[i]))
+    print("The information gain from compression is: ",entropya-entropyb)
+def compress_bits(compressed):
+    compressed_bytes = bytearray()
+    current_byte = 0
+    bit_count = 0
+    for bit in compressed:
+        current_byte <<= 1
+        current_byte |= int(bit)
+        bit_count += 1
+        if bit_count == 8:
+            compressed_bytes.append(current_byte)
+            current_byte = 0
+            bit_count = 0
+    if bit_count > 0:
+        current_byte <<= (8 - bit_count)
+        compressed_bytes.append(current_byte)
+    return bytes(compressed_bytes)
+ifile = input("Enter your input filename: ")
+codes = input("Enter the filename where you have saved your codes: ")
+ofile = input("Enter the filename where you want your compressed document saved: ")
+compress(ifile, codes, ofile)
+print("Compressed code has been written to:", ofile)
\ No newline at end of file
diff --git a/decompressor.py b/decompressor.py
new file mode 100644
index 00000000..68dc7467
--- /dev/null
+++ b/decompressor.py
@@ -0,0 +1,30 @@
+def decompress(ifile, codes,ofile):
+    symbol_codes = {}
+    with open(codes, 'r') as f:
+        for line in f:
+            last_space_index = line.rfind(' ')
+            if last_space_index != -1:
+                symbol = line[:last_space_index]
+                code = line[last_space_index + 1:].strip()
+                symbol_codes[code] = symbol
+    with open(ifile, 'rb') as f:  # Open the compressed file in binary mode
+        compressed = f.read()
+    
+    # Convert binary data to a binary string
+    compressed_bits = ''.join(format(byte, '08b') for byte in compressed)
+    decompressed = ''
+    current = ''
+    for bit in compressed_bits:
+        current += bit
+        if current in symbol_codes.keys():
+            decompressed += symbol_codes[current]
+            current = ''
+    with open(ofile, 'w') as f:
+        f.write(decompressed)
+
+ifile = input("Enter your input (compressed) filename: ")
+codes = input("Enter the filename where you have saved your codes: ")
+ofile = input("Enter the filename where you want your decompressed document saved: ")
+decompress(ifile, codes,ofile)
+print("Decompressed code has been written to:", ofile)
+

From f11390f2e544d8f85e65aa7fef620682b510a2e4 Mon Sep 17 00:00:00 2001
From: unknown <sohamhaldar04@gmail.com>
Date: Mon, 18 Mar 2024 14:44:34 +0530
Subject: [PATCH 2/2] Soham Haldar| compressor.py decompressor.py README(1).md|
 Added README(1).md for my repo and actually made sure that the file was being
 compressed

---
 README(1).md | 3 +++
 1 file changed, 3 insertions(+)
 create mode 100644 README(1).md

diff --git a/README(1).md b/README(1).md
new file mode 100644
index 00000000..4398be6f
--- /dev/null
+++ b/README(1).md
@@ -0,0 +1,3 @@
+Huffman compressor:
+Use huffman.cpp to generate codes file and use compressor.py/decompressor.py for compression/decompression
+Note: we only consider spaces or alphabets here and not numbers.
\ No newline at end of file