updates

.gitignore

@@ -0,0 +1 @@
+venv

split_zip_into_under_5GB_chunks.py

@@ -1,67 +1,7 @@
+#!/Users/shelbybark/code/cmg_split_zip_into_chunks/venv/bin/python3
 import os
-import zipfile
-from shutil import copy2
-
-def split_zip_into_groups(zip_path, max_group_size_gb):
-    # Open the existing zip file in read mode
-    with zipfile.ZipFile(zip_path, 'r') as zip_ref:
-        # Extract all the contents into a temporary directory
-        temp_dir = os.path.splitext(zip_path)[0] + '_extracted'
-        if not os.path.exists(temp_dir):
-            os.makedirs(temp_dir)
-        
-        zip_ref.extractall(temp_dir)
-    
-    # Get a list of all files in the temporary directory
-    file_list = [os.path.join(root, f) for root, dirs, files in os.walk(temp_dir) for f in files]
-    
-    # Calculate the maximum size in bytes for each group
-    max_group_size_bytes = max_group_size_gb * 1024**3
-    
-    # Create a new directory to hold the split zip files
-    output_dir = os.path.splitext(zip_path)[0] + '_split'
-    if not os.path.exists(output_dir):
-        os.makedirs(output_dir)
-    
-    group_count = 1
-    current_group_size = 0
-    current_group_files = []
-    
-    for file in file_list:
-        # Get the size of the current file in bytes
-        file_size = os.path.getsize(file)
-        
-        if current_group_size + file_size > max_group_size_bytes:
-            # If adding the current file exceeds the group size, save the current group and create a new one
-            output_zip_path = os.path.join(output_dir, f'group_{group_count}.zip')
-            
-            with zipfile.ZipFile(output_zip_path, 'w', zipfile.ZIP_DEFLATED) as zip_ref:
-                for file in current_group_files:
-                    # Copy each file to the temporary directory and add it to the new zip
-                    temp_file = os.path.join(temp_dir, os.path.relpath(file, start=temp_dir))
-                    copy2(file, temp_file)
-                    zip_ref.write(temp_file, os.path.relpath(file, start=temp_dir))
-                    os.remove(temp_file)  # Clean up the temporary file
-        
-            group_count += 1
-            current_group_size = 0
-            current_group_files = []
-        
-        current_group_size += file_size
-        current_group_files.append(file)
-    
-    # If there are any remaining files in the last group, save them too
-    if current_group_files:
-        output_zip_path = os.path.join(output_dir, f'group_{group_count}.zip')
-        with zipfile.ZipFile(output_zip_path, 'w', zipfile.ZIP_DEFLATED) as zip_ref:
-            for file in current_group_files:
-                temp_file = os.path.join(temp_dir, os.path.relpath(file, start=temp_dir))
-                copy2(file, temp_file)
-                zip_ref.write(temp_file, os.path.relpath(file, start=temp_dir))
-                os.remove(temp_file)  # Clean up the temporary file
-    
-    # Clean up the temporary directory
-    shutil.rmtree(temp_dir)
+from zipfile import ZipFile, ZIP_DEFLATED
+import io
 
 def get_zip_path():
     while True:
@@ -71,7 +11,62 @@ def get_zip_path():
         else:
             print(f"The file at {zip_path} does not exist. Please try again.")
 
-# Example usage
-zip_path = get_zip_path()
-max_group_size_gb = 5
-split_zip_into_groups(zip_path, max_group_size_gb)
+def split_and_zip(file_path):
+
+    with ZipFile(file_path, 'r') as zip_ref:
+        total_size = 0
+        for file in zip_ref.namelist():
+            total_size += zip_ref.getinfo(file).file_size
+
+    # Define the maximum group size in bytes
+    max_group_size = 5 * 1024 ** 3
+
+    # Calculate the number of groups
+    num_groups = -(-total_size // max_group_size)  # Ceiling division
+
+    # print(f"Total size: { round(total_size / 1024.0 / 1024.0 / 1024.0, 6)} GB")
+    print(f"Max group size: { max_group_size } GB")
+    print(f"Total size: { total_size } GB")
+    print(f"Number of groups: {num_groups}")
+
+    # Create a temporary directory for storing intermediate files
+    tmp_dir = 'temp'
+    os.makedirs(tmp_dir, exist_ok=True)
+
+    # Iterate over each group
+    for i in range(num_groups):
+        start_index = i * max_group_size
+        end_index = min((i + 1) * max_group_size, total_size)
+        
+        # Extract the files for this group from the zipped file
+        with ZipFile(file_path, 'r') as zip_file:
+            group_files = [(zip_file.infolist()[j].filename, 
+                            io.BytesIO(), 
+                            zip_file.open(zip_file.infolist()[j].filename, 'r')) 
+                           for j in range(start_index, end_index)]
+
+        # Write each file to a new zip file
+        with open(os.path.join(tmp_dir, f'group_{i}.zip'), 'wb') as group_zip:
+            group_zip.write(b'PK' + b'\x01\x0a' * 20)
+            for filename, buffer, file in group_files:
+                group_zip.write(f'{filename}\x00')
+                group_zip.writestr(filename, buffer.read())
+                del buffer
+
+        # Clean up
+        os.remove(file_path)
+
+    # Zip the intermediate files into final zip files
+    for i in range(num_groups):
+        with open(os.path.join(tmp_dir, f'group_{i}.zip'), 'rb') as group_zip:
+            with ZipFile(f'output_group_{i}.zip', 'w', compression=ZIP_DEFLATED) as output_zip:
+                for file_info in group_zip.infolist():
+                    if file_info.filename.startswith('group_'):
+                        output_zip.writestr(file_info.filename[len('group_'):], group_zip.open(file_info.filename, 'r').read())
+
+    # Clean up
+    os.rmdir(tmp_dir)
+
+zip_file = get_zip_path()
+# split_and_zip('input.zip')
+split_and_zip(zip_file)