From b5c74dca4ee024aad1ea180bd5b593f1a61bb71d Mon Sep 17 00:00:00 2001
From: openhands <openhands@all-hands.dev>
Date: Wed, 26 Mar 2025 16:27:36 +0000
Subject: [PATCH] Add unit tests for utils.hash_file function

---
 tests/__init__.py   |  0
 tests/test_utils.py | 49 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 49 insertions(+)
 create mode 100644 tests/__init__.py
 create mode 100644 tests/test_utils.py

diff --git a/tests/__init__.py b/tests/__init__.py
new file mode 100644
index 00000000..e69de29b
diff --git a/tests/test_utils.py b/tests/test_utils.py
new file mode 100644
index 00000000..f6471e68
--- /dev/null
+++ b/tests/test_utils.py
@@ -0,0 +1,49 @@
+import os
+import tempfile
+import unittest
+from app.utils import hash_file
+
+class TestUtils(unittest.TestCase):
+    def test_hash_file_empty(self):
+        """Test hashing an empty file"""
+        with tempfile.NamedTemporaryFile(delete=False) as tmp_file:
+            pass
+        
+        try:
+            # Known SHA-256 hash of an empty file
+            expected_hash = "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855"
+            self.assertEqual(hash_file(tmp_file.name), expected_hash)
+        finally:
+            os.unlink(tmp_file.name)
+    
+    def test_hash_file_with_content(self):
+        """Test hashing a file with known content"""
+        content = b"Hello, World!"
+        with tempfile.NamedTemporaryFile(delete=False) as tmp_file:
+            tmp_file.write(content)
+            tmp_file.flush()
+        
+        try:
+            # Known SHA-256 hash of "Hello, World!"
+            expected_hash = "dffd6021bb2bd5b0af676290809ec3a53191dd81c7f70a4b28688a362182986f"
+            self.assertEqual(hash_file(tmp_file.name), expected_hash)
+        finally:
+            os.unlink(tmp_file.name)
+    
+    def test_hash_file_large_content(self):
+        """Test hashing a file larger than the chunk size"""
+        # Create content larger than the default chunk size (65536)
+        content = b"x" * 100000
+        with tempfile.NamedTemporaryFile(delete=False) as tmp_file:
+            tmp_file.write(content)
+            tmp_file.flush()
+        
+        try:
+            # Test that we can hash a large file
+            hash_result = hash_file(tmp_file.name)
+            self.assertEqual(len(hash_result), 64)  # SHA-256 hashes are 64 characters long
+        finally:
+            os.unlink(tmp_file.name)
+
+if __name__ == '__main__':
+    unittest.main()
\ No newline at end of file