Merge pull request #674 from valory-xyz/fix/incosisten-hashing

Fix incosistent hashing

aea/helpers/ipfs/base.py

@@ -22,14 +22,12 @@
 import hashlib
 import io
 import os
-import re
 from pathlib import Path
 from typing import Any, Dict, Generator, Optional, Sized, Tuple, cast
 
 import base58
 
 from aea.helpers.cid import to_v1
-from aea.helpers.io import open_file
 from aea.helpers.ipfs.utils import _protobuf_python_implementation
 
 
@@ -43,35 +41,13 @@
     from aea.helpers.ipfs.pb.merkledag_pb2 import PBNode  # type: ignore
 
 
-def _dos2unix(file_content: bytes) -> bytes:
-    """
-    Replace occurrences of Windows line terminator CR/LF with only LF.
-
-    :param file_content: the content of the file.
-    :return: the same content but with the line terminator
-    """
-    return re.sub(b"\r\n", b"\n", file_content, flags=re.M)
-
-
-def _is_text(file_path: str) -> bool:
-    """Check if a file can be read as text or not."""
-    try:
-        with open_file(file_path, "r") as f:
-            f.read()
-        return True
-    except UnicodeDecodeError:
-        return False
-
-
 def _read(file_path: str) -> bytes:
-    """Read a file, replacing Windows line endings if it is a text file."""
-    is_text = _is_text(file_path)
+    """Read and verify the file is not empty."""
     with open(file_path, "rb") as file:
-        file_b = file.read()
-        if is_text:
-            file_b = _dos2unix(file_b)
-
-    return file_b
+        data = file.read()
+    if len(data) == 0:
+        raise ValueError(f"File cannot be empty: {file_path}")
+    return data
 
 
 def chunks(data: Sized, size: int) -> Generator:

tests/test_helpers/test_ipfs/test_base.py

@@ -1,7 +1,7 @@
 # -*- coding: utf-8 -*-
 # ------------------------------------------------------------------------------
 #
-#   Copyright 2022 Valory AG
+#   Copyright 2022-2023 Valory AG
 #   Copyright 2018-2021 Fetch.AI Limited
 #
 #   Licensed under the Apache License, Version 2.0 (the "License");
@@ -22,23 +22,12 @@
 import tempfile
 from pathlib import Path
 from tempfile import TemporaryDirectory
-from unittest.mock import patch
 
 import pytest
 from aea_cli_ipfs.ipfs_utils import IPFSTool  # type: ignore
 
 from aea.helpers.cid import to_v1
-from aea.helpers.ipfs.base import IPFSHashOnly, _is_text
-
-
-def test_is_text_negative():
-    """Test the helper method 'is_text' negative case."""
-    # https://gehrcke.de/2015/12/how-to-raise-unicodedecodeerror-in-python-3/
-    with patch(
-        "aea.helpers.ipfs.base.open_file",
-        side_effect=UnicodeDecodeError("foo", b"bytes", 1, 2, "Fake reason"),
-    ):
-        assert not _is_text("path")
+from aea.helpers.ipfs.base import IPFSHashOnly
 
 
 def test_hash_for_big_file():

tests/test_package_manager/test_v0.py

@@ -147,7 +147,7 @@ def test_update_fingerprints(self, caplog) -> None:
                 path=packages_dir, packages=OrderedDict({package_id: package_hash})
             )
 
-            (temp_package / "__init__.py").write_text("")
+            (temp_package / "__init__.py").write_text("dummy")
 
             with caplog.at_level(logging.ERROR):
                 assert pm.verify() == 1
@@ -210,7 +210,7 @@ def test_verify_method(self, caplog) -> None:
             pm.package_path_from_package_id(package_id=EXAMPLE_PACKAGE_ID)
             / INIT_FILE_NAME
         )
-        init_file.write_text("")
+        init_file.write_text("dummy")
 
         with caplog.at_level(logging.ERROR), mock.patch(
             "aea.package_manager.v0.check_fingerprint",

tests/test_package_manager/test_v1.py

@@ -352,8 +352,7 @@ def test_update_fingerprints(self, caplog) -> None:
                 dev_packages=OrderedDict({package_id: package_hash}),
             )
 
-            (temp_package / "__init__.py").write_text("")
-
+            (temp_package / "__init__.py").write_text("hello")
             with caplog.at_level(logging.ERROR):
                 assert pm.verify() == 1
                 assert (
@@ -563,7 +562,7 @@ def test_verify_method(self, caplog) -> None:
             pm.package_path_from_package_id(package_id=EXAMPLE_PACKAGE_ID)
             / INIT_FILE_NAME
         )
-        init_file.write_text("")
+        init_file.write_text("dummy")
 
         with caplog.at_level(logging.ERROR), mock.patch(
             "aea.package_manager.v1.check_fingerprint",