From 884a85d94578171599d19165e3c12f32eace83d3 Mon Sep 17 00:00:00 2001
From: Mark McIntyre <mark@mocktech.net>
Date: Thu, 15 Feb 2024 14:52:59 -0500
Subject: [PATCH] finished chuck-file

---
 python/chunk-file | 112 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 112 insertions(+)
 create mode 100755 python/chunk-file

diff --git a/python/chunk-file b/python/chunk-file
new file mode 100755
index 0000000..f419a4e
--- /dev/null
+++ b/python/chunk-file
@@ -0,0 +1,112 @@
+#!/usr/bin/env python3
+
+"""
+Will break apart large files into smaller files
+"""
+
+import argparse
+import re
+import os
+import glob
+
+
+def parse_args():
+    argp = argparse.ArgumentParser(
+            description="Will break a large file into smaller files"
+    )
+
+    argp.add_argument(
+            'large_file',
+            help="Full path for large file"
+    )
+
+    argp.add_argument(
+            '--prefix', '-p',
+            default='small',
+            help="Prefix for the smaller files (default: %(default)s)"
+    )
+
+    argp.add_argument(
+            '--extension', '-x',
+            default='txt',
+            help="Extension for the smaller files (default: %(default)s)"
+    )
+
+    argp.add_argument(
+            '--size', '-s',
+            default='10K',
+            help="File size limits (5K, 10M, 2G)"
+    )
+
+    argp.add_argument(
+            '--old', '-o',
+            action='store_true',
+            help="Reuse existing small files; default behavior is to remove existing files for new ones"
+    )
+            
+    # Future functionality:
+    # argp.add_argument(
+    #         '--count', '-c',
+    #         type=int,
+    #         default=1,
+    #         help="Number of files to generate (default: %(default)s)"
+    # )
+
+    return argp.parse_args()
+
+
+def main():
+    args = parse_args()
+
+    file_complete = False
+    file_count = 1
+
+    # get the chunk file size
+    size_value = args.size
+    size_value_parts = re.match(r'(\d+)([BbKkMmGgTt]?)', size_value).groups()
+    if size_value_parts[1]:
+        factor = (
+                (size_value_parts[1].lower() == 'k' and 1) or
+                (size_value_parts[1].lower() == 'm' and 2) or
+                (size_value_parts[1].lower() == 'g' and 3) or
+                (size_value_parts[1].lower() == 't' and 4)
+        )
+        size_limit = int(size_value_parts[0]) * 1024**factor
+    else:
+        size_limit - int(size_value_parts[0])
+
+    if not args.old:
+        print("Removing previous files...")
+        previous_files = glob.glob(f"{args.prefix}-*.{args.extension}")
+
+        for previous_file in previous_files:
+            os.remove(previous_file)
+
+    print(f"Begin chunking large file {args.large_file}...")
+    with open(args.large_file) as large_file:
+        for line in large_file:
+            output_filename = f"{args.prefix}-{file_count:00005}.{args.extension}"
+
+            if not file_complete:
+                file_mode = 'a' if os.path.isfile(output_filename) else 'w'
+
+                with open(output_filename, file_mode) as small_file:
+                    small_file.write(line)
+
+                with open(output_filename, 'r') as small_file:
+                    small_file.seek(0, os.SEEK_END)
+                    output_file_size = small_file.tell()
+
+                if output_file_size > size_limit:
+                    file_complete = True
+
+            else:
+                file_complete = False
+                file_count += 1
+
+    print(f"Large file {args.large_file} chunked into {file_count} files no bigger than {args.size}")
+
+
+if __name__ == "__main__":
+    main()
+