added are_files_equal to file_utils

CHANGELOG.rst

@@ -18,7 +18,7 @@ Change Log
   - Added extract_file_from_zip to zip_utils.
   - Added http_utils with download function.
   - Added get_app_specific_directory, get_os_name, and get_cpu_architecture_name to misc_utils.
-  - Added normalize_file_path to file_utils.
+  - Added normalize_file_path and are_files_equal to file_utils.
   - Added create_temporary_file_name and remove_temporary_file tmpfile_utils.
   - Minor fix to misc_utils.create_dict (do not create property only if its value is None).
 

dcicutils/file_utils.py

@@ -76,3 +76,23 @@ def normalize_file_path(path: str, home_directory: bool = True) -> str:
         if path.startswith(home_directory) and path != home_directory:
             path = "~/" + pathlib.Path(path).relative_to(home_directory).as_posix()
     return path
+
+
+def are_files_equal(filea: str, fileb: str) -> bool:
+    """
+    Returns True iff the contents of the two given files are exactly the same.
+    """
+    try:
+        with open(filea, "rb") as fa:
+            with open(fileb, "rb") as fb:
+                chunk_size = 4096
+                while True:
+                    chunka = fa.read(chunk_size)
+                    chunkb = fb.read(chunk_size)
+                    if chunka != chunkb:
+                        return False
+                    if not chunka:
+                        break
+        return True
+    except Exception:
+        return False

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "dcicutils"
-version = "8.8.4.1b7"  # TODO: To become 8.8.5
+version = "8.8.4.1b8"  # TODO: To become 8.8.5
 description = "Utility package for interacting with the 4DN Data Portal and other 4DN resources"
 authors = ["4DN-DCIC Team <support@4dnucleome.org>"]
 license = "MIT"