Add get_dir_hash method. #10

README.md

@@ -66,6 +66,7 @@ import fsutil
 -   [`extract_zip_file`](#extract_zip_file)
 -   [`get_dir_creation_date`](#get_dir_creation_date)
 -   [`get_dir_creation_date_formatted`](#get_dir_creation_date_formatted)
+-   [`get_dir_hash`](#get_dir_hash)
 -   [`get_dir_last_modified_date`](#get_dir_last_modified_date)
 -   [`get_dir_last_modified_date_formatted`](#get_dir_last_modified_date_formatted)
 -   [`get_dir_size`](#get_dir_size)
@@ -311,6 +312,14 @@ date = fsutil.get_dir_creation_date(path)
 date_str = fsutil.get_dir_creation_date_formatted(path, format='%Y-%m-%d %H:%M:%S')
 ```
 
+#### `get_dir_hash`
+
+```python
+# Get the hash of the directory at the given path using
+# the specified algorithm function (md5 by default).
+hash = fsutil.get_dir_hash(path)
+```
+
 #### `get_dir_last_modified_date`
 
 ```python

fsutil/__init__.py

@@ -435,6 +435,22 @@ def get_dir_creation_date_formatted(path, format="%Y-%m-%d %H:%M:%S"):
     return date.strftime(format)
 
 
+def get_dir_hash(path, func="md5"):
+    """
+    Get the hash of the directory at the given path using
+    the specified algorithm function (md5 by default).
+    """
+    assert_dir(path)
+    hash = hashlib.new(func)
+    files = search_files(path)
+    for file in sorted(files):
+        file_hash = get_file_hash(file, func=func)
+        file_hash_b = bytes(file_hash, "utf-8")
+        hash.update(file_hash_b)
+    hash_hex = hash.hexdigest()
+    return hash_hex
+
+
 def get_dir_last_modified_date(path):
     """
     Get the directory last modification date.
@@ -523,7 +539,7 @@ def get_file_extension(path):
 
 def get_file_hash(path, func="md5"):
     """
-    Get the hash of the file at the gived path using
+    Get the hash of the file at the given path using
     the specified algorithm function (md5 by default).
     """
     assert_file(path)

tests/test.py

@@ -490,6 +490,22 @@ def test_get_dir_creation_date_formatted(self):
         creation_date_re = re.compile(r"^[\d]{4}\/[\d]{2}\/[\d]{2}$")
         self.assertTrue(creation_date_re.match(creation_date_str))
 
+    def test_get_dir_hash(self):
+        f1_path = self.temp_path("x/a/b/f1.txt")
+        f2_path = self.temp_path("x/a/b/f2.txt")
+        f3_path = self.temp_path("x/j/k/f3.txt")
+        f4_path = self.temp_path("x/j/k/f4.txt")
+        f5_path = self.temp_path("x/y/z/f5.txt")
+        f6_path = self.temp_path("x/y/z/f6.txt")
+        fsutil.create_file(f1_path, content="hello world 1")
+        fsutil.create_file(f2_path, content="hello world 2")
+        fsutil.create_file(f3_path, content="hello world 3")
+        fsutil.create_file(f4_path, content="hello world 4")
+        fsutil.create_file(f5_path, content="hello world 5")
+        fsutil.create_file(f6_path, content="hello world 6")
+        hash = fsutil.get_dir_hash(self.temp_path("x/"))
+        self.assertEqual(hash, "eabe619c41f0c4611b7b9746bededfcb")
+
     def test_get_dir_last_modified_date(self):
         path = self.temp_path("a/b/c.txt")
         fsutil.create_file(path, content="Hello")