Add the support of hash content for e3.fs.get_filetree_state. ITPE-56

Author: liaiss

src/e3/fs.py

@@ -182,16 +182,21 @@ def find(
     return result
 
 
-def get_filetree_state(path: str, ignore_hidden: bool = True) -> str:
+def get_filetree_state(
+    path: str, ignore_hidden: bool = True, hash_content: bool = False
+) -> str:
     """Compute a hash on a filetree to reflect its current state.
 
     :param path: root path of the file tree to be checked
     :param ignore_hidden: if True (default) then files and directories
         tarting with a dot are ignored.
+    :param hash_content: if True, include the content in the hash.
+
     :return: a hash as a string
 
-    The function will not report changes in the hash if a file is modified
-    and its attributes (size, modification time and mode) are not changed.
+    By default, the function will not report changes in the hash if a file is
+    modified and its attributes (size, modification time and mode) are not
+    changed.
     This case is quite uncommon. By ignoring it we can compute efficiently a
     hash representing the state of the file tree without having to read the
     content of all files.
@@ -205,6 +210,10 @@ def compute_state(file_path: str) -> bytes:
         )
         return state.encode("utf-8")
 
+    def get_content(file_path: str) -> bytes:
+        with open(file_path, "rb") as f:
+            return f.read()
+
     path = os.path.abspath(path)
     result = hashlib.sha1()
     if os.path.isdir(path):
@@ -225,8 +234,15 @@ def compute_state(file_path: str) -> bytes:
                 full_path = os.path.join(root, path)
                 result.update(compute_state(full_path))
 
+                if hash_content:
+                    result.update(get_content(full_path))
+
     else:
         result.update(compute_state(path))
+
+        if hash_content:
+            result.update(get_content(path))
+
     return result.hexdigest()
 
 

tests/tests_e3/fs/main_test.py

@@ -191,6 +191,7 @@ def test_tree_state():
     time.sleep(2)
 
     e3.os.fs.touch("toto")
+    e3.os.fs.touch("toto2")
     state4 = e3.fs.get_filetree_state(current_dir)
     assert state4 != state3
     hidden = os.path.join(current_dir, ".h")
@@ -208,9 +209,28 @@ def test_tree_state():
     state6 = e3.fs.get_filetree_state("toto")
     assert isinstance(state6, str)
 
+    with open("toto", "wb") as f:
+        f.write(b"hello world.")
+
     # check that get_filetree_state accept unicode
     state7 = e3.fs.get_filetree_state("toto")
     assert isinstance(state7, str)
+    assert state7 != state6
+
+    # check that get_filetree_state with hash_content is different that the
+    # previous state
+    state8 = e3.fs.get_filetree_state("toto", hash_content=True)
+    assert isinstance(state8, str)
+    assert state8 != state7
+
+    # check that get_filetree_state with hash_content is working with directory
+    # and is different that the previous call without hash_content to true
+    with open("toto2", "wb") as f:
+        f.write(b"hello world 2.")
+
+    state9 = e3.fs.get_filetree_state(current_dir, hash_content=True)
+    assert isinstance(state9, str)
+    assert state9 != state4
 
 
 @pytest.mark.skipif(sys.platform == "win32", reason="test using symlink")