decoder codebook integrated as header into message

main.py

@@ -2,7 +2,7 @@ import math
 
 
 def Q_statistik():
-    with open('Text.txt', 'r', encoding='utf-8') as file:
+    with open('Text.txt', 'r', encoding='latin-1') as file:
         text = file.read()
 
     freq = {}
@@ -27,11 +27,10 @@ def Q_statistik():
 
 
 def fano_encoder(probabilities):
-    # Key = probability im Dictionary
     sorted_probs = sorted(probabilities.items(), key=lambda x: x[1], reverse=True)
 
     def fano_recursive(symbols):
-        if len(symbols) == 1:  # Keine neuen Teilmengen möglich
+        if len(symbols) == 1:
             return {symbols[0][0]: ""}
 
         total = sum([symbol[1] for symbol in symbols])
@@ -60,21 +59,68 @@ def fano_encoder(probabilities):
     return fano_recursive(sorted_probs)
 
 
-def Q_Fanoencoder(input_path='Text.txt', output_path='EncodedText.txt'):
+def Q_Fanoencoder():
     _, probabilities, _, _ = Q_statistik()
     fano_codes = fano_encoder(probabilities)
 
-    with open(input_path, 'r', encoding='utf-8') as file:
+    with open('Text.txt', 'r', encoding='latin-1') as file:
         text = file.read()
 
     encoded_text = ''.join([fano_codes[char] for char in text])
 
-    with open(output_path, 'w', encoding='utf-8') as file:
-        file.write(encoded_text)
+    coding_table_bin = ''.join(
+        [format(ord(char), '08b') +
+         format(len(code), '08b') +
+         code
+         for char, code in fano_codes.items()]
+    )
+
+    coding_table_length = len(coding_table_bin)
+    header = f'{coding_table_length:016b}'  # 2 bytes for the length in binary
+    final_encoded_text = header + coding_table_bin + encoded_text
+
+    with open('EncodedText.txt', 'w', encoding='latin-1') as file:
+        file.write(final_encoded_text)
 
     return text, encoded_text, fano_codes
 
 
+def Q_decoder():
+    with open('EncodedText.txt', 'r', encoding='latin-1') as file:
+        encoded_text = file.read()
+
+    coding_table_length = int(encoded_text[:16], 2)
+
+    coding_table_bin = encoded_text[16:16 + coding_table_length]
+    encoded_text = encoded_text[16 + coding_table_length:]
+
+    #  Codebuch
+    fano_codes = {}
+    i = 0
+    while i < len(coding_table_bin):
+        char_bin = coding_table_bin[i:i + 8]
+        char = chr(int(char_bin, 2))
+        i += 8
+        code_length_bin = coding_table_bin[i:i + 8]
+        code_length = int(code_length_bin, 2)
+        i += 8
+        code = coding_table_bin[i:i + code_length]
+        fano_codes[code] = char
+        i += code_length
+
+    #  Text
+    decoded_text = ''
+    current_code = ''
+    for bit in encoded_text:
+        current_code += bit
+        if current_code in fano_codes:
+            decoded_text += fano_codes[current_code]
+            current_code = ''
+
+    with open('DecodedText.txt', 'w', encoding='latin-1') as file:
+        file.write(decoded_text)
+
+
 def calculate_compression_rate(original_text, encoded_text, fano_codes):
     original_length_bits = len(original_text) * 8
     encoded_length_bits = len(encoded_text)
@@ -98,6 +144,7 @@ def main():
     print(f"Originale Länge in Bits: {original_length_bits}")
     print(f"Gesamte codierte Länge in Bits (inkl. Codetabelle): {total_encoded_bits}")
     print(f"Kompressionsrate: {compression_rate:.2f}%")
+    Q_decoder()
 
 
 if __name__ == '__main__':