From 472bd318df5acbc9b8572db5ea866d55b3f94e01 Mon Sep 17 00:00:00 2001
From: kamzata <kamzata@noreply.localhost>
Date: Sun, 12 May 2024 03:22:11 +0200
Subject: [PATCH] Add split_by_size_or_qty_and_compress.py

---
 split_by_size_or_qty_and_compress.py | 53 ++++++++++++++++++++++++++++
 1 file changed, 53 insertions(+)
 create mode 100644 split_by_size_or_qty_and_compress.py

diff --git a/split_by_size_or_qty_and_compress.py b/split_by_size_or_qty_and_compress.py
new file mode 100644
index 0000000..bd73a07
--- /dev/null
+++ b/split_by_size_or_qty_and_compress.py
@@ -0,0 +1,53 @@
+import fnmatch
+import os
+import zipfile
+
+###
+BYTE_SIZE_LIMIT = 22144
+QUANTITY_LIMIT = 10
+
+dir = os.listdir(os.getcwd())
+files_list = fnmatch.filter((dir),'*.xml')
+###
+
+
+def compress(file_names, zip_name):
+    compression = zipfile.ZIP_DEFLATED
+
+    zf = zipfile.ZipFile(zip_name, mode="w")
+    try:
+        for file_name in file_names:
+            zf.write(file_name, compress_type=compression)
+    except FileNotFoundError:
+        print("An error occurred")
+    finally:
+        zf.close()
+
+
+def split_by_size_or_qty_and_compress(files, size_limit = 1000000000, qty_limit = 100000):
+    if not (isinstance(files, list)):
+          raise TypeError("Not a valid file list")
+
+    num_files = len(files)
+    chunk = []
+    part_num = 1
+    count = 0
+    chunk_size = 0
+
+    for file in files:
+        count += 1
+        chunk_size += os.path.getsize(file)
+        
+        if(chunk_size > size_limit) or (len(chunk) >= qty_limit):
+            compress(chunk, "Part_" + str(part_num) + ".zip")
+            chunk.clear()
+            chunk_size = 0
+            part_num +=1
+        else:
+            chunk.append(file)
+
+        if(count == num_files):
+            compress(chunk, "Part_" + str(part_num) + ".zip")
+
+
+split_by_size_or_qty_and_compress(files_list, BYTE_SIZE_LIMIT, QUANTITY_LIMIT)
\ No newline at end of file