From b7fb31ea760ec8c5745748f45206660b26b58dfb Mon Sep 17 00:00:00 2001
From: KASR <karim.asrih@gmail.com>
Date: Thu, 27 Apr 2023 09:47:50 +0200
Subject: [PATCH] python script to verify the checksum of the llama models

Added Python script for verifying SHA256 checksums of files in a directory, which can run on multiple platforms. Improved the formatting of the output results for better readability.
---
 scripts/verify-checksum-models.py | 64 +++++++++++++++++++++++++++++++
 1 file changed, 64 insertions(+)
 create mode 100644 scripts/verify-checksum-models.py

diff --git a/scripts/verify-checksum-models.py b/scripts/verify-checksum-models.py
new file mode 100644
index 000000000..8963c156d
--- /dev/null
+++ b/scripts/verify-checksum-models.py
@@ -0,0 +1,64 @@
+import os
+import hashlib
+
+# Define the path to the llama directory (parent folder of script directory)
+llama_path = os.path.abspath(os.path.join(os.path.dirname(__file__), os.pardir))
+
+# Define the file with the list of hashes and filenames
+hash_list_file = os.path.join(llama_path, "SHA256SUMS")
+
+# Check if the hash list file exists
+if not os.path.exists(hash_list_file):
+    print(f"Hash list file not found: {hash_list_file}")
+    exit(1)
+
+# Read the hash file content and split it into an array of lines
+with open(hash_list_file, "r") as f:
+    hash_list = f.read().splitlines()
+
+# Create an array to store the results
+results = []
+
+# Loop over each line in the hash list
+for line in hash_list:
+    # Split the line into hash and filename
+    hash_value, filename = line.split("  ")
+
+    # Get the full path of the file by joining the models path and the filename
+    file_path = os.path.join(llama_path, filename)
+
+    # Informing user of the progress of the integrity check
+    print(f"Verifying the checksum of {file_path}")
+
+    # Check if the file exists
+    if os.path.exists(file_path):
+        # Calculate the SHA256 checksum of the file using hashlib
+        with open(file_path, "rb") as f:
+            file_hash = hashlib.sha256(f.read()).hexdigest()
+
+        # Compare the file hash with the expected hash
+        if file_hash == hash_value:
+            valid_checksum = "V"
+            file_missing = ""
+        else:
+            valid_checksum = ""
+            file_missing = ""
+    else:
+        valid_checksum = ""
+        file_missing = "X"
+
+    # Add the results to the array
+    results.append({
+        "filename": filename,
+        "valid checksum": valid_checksum,
+        "file missing": file_missing
+    })
+
+
+# Print column headers for results table
+print("\n" + "filename".ljust(40) + "valid checksum".center(20) + "file missing".center(20))
+print("-" * 80)
+
+# Output the results as a table
+for r in results:
+    print(f"{r['filename']:40} {r['valid checksum']:^20} {r['file missing']:^20}")