fix: Ensure consistent data storage by explicitly using \n for newlines when storing files (#1601)

<!-- .github/pull_request_template.md -->

## Description
<!--
Please provide a clear, human-generated description of the changes in
this PR.
DO NOT use AI-generated descriptions. We want to understand your thought
process and reasoning.
-->

`LocalFileStorage.store(...)` when storing strings, uses system defaults
for newlines.

It is universally `\n` in Unix and MacOS, but for Windows by default its
`\r\n` (ancient Windows standard)

This results in hash mismatch, although content is identical.

Windows can work with `\n`, so this PR explicitly uses `\n` for newline
encoding

## Type of Change
<!-- Please check the relevant option -->
- [ ] Bug fix (non-breaking change that fixes an issue)
- [ ] New feature (non-breaking change that adds functionality)
- [ ] Breaking change (fix or feature that would cause existing
functionality to change)
- [ ] Documentation update
- [ ] Code refactoring
- [ ] Performance improvement
- [ ] Other (please specify):

## Screenshots/Videos (if applicable)
<!-- Add screenshots or videos to help explain your changes -->

## Pre-submission Checklist
<!-- Please check all boxes that apply before submitting your PR -->
- [ ] **I have tested my changes thoroughly before submitting this PR**
- [ ] **This PR contains minimal changes necessary to address the
issue/feature**
- [ ] My code follows the project's coding standards and style
guidelines
- [ ] I have added tests that prove my fix is effective or that my
feature works
- [ ] I have added necessary documentation (if applicable)
- [ ] All new and existing tests pass
- [ ] I have searched existing PRs to ensure this change hasn't been
submitted already
- [ ] I have linked any relevant issues in the description
- [ ] My commits have clear and descriptive messages

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.

cognee/infrastructure/files/storage/LocalFileStorage.py

@@ -82,16 +82,16 @@ class LocalFileStorage(Storage):
         self.ensure_directory_exists(file_dir_path)
 
         if overwrite or not os.path.exists(full_file_path):
-            with open(
+            if isinstance(data, str):
-                full_file_path,
+                with open(full_file_path, mode="w", encoding="utf-8", newline="\n") as file:
-                mode="w" if isinstance(data, str) else "wb",
-                encoding="utf-8" if isinstance(data, str) else None,
-            ) as file:
-                if hasattr(data, "read"):
-                    data.seek(0)
-                    file.write(data.read())
-                else:
                     file.write(data)
+            else:
+                with open(full_file_path, mode="wb") as file:
+                    if hasattr(data, "read"):
+                        data.seek(0)
+                        file.write(data.read())
+                    else:
+                        file.write(data)
 
                 file.close()
 

cognee/infrastructure/files/storage/S3FileStorage.py

@@ -70,18 +70,18 @@ class S3FileStorage(Storage):
         if overwrite or not await self.file_exists(file_path):
 
             def save_data_to_file():
-                with self.s3.open(
+                if isinstance(data, str):
-                    full_file_path,
+                    with self.s3.open(
-                    mode="w" if isinstance(data, str) else "wb",
+                        full_file_path, mode="w", encoding="utf-8", newline="\n"
-                    encoding="utf-8" if isinstance(data, str) else None,
+                    ) as file:
-                ) as file:
-                    if hasattr(data, "read"):
-                        data.seek(0)
-                        file.write(data.read())
-                    else:
                         file.write(data)
-
+                else:
-                    file.close()
+                    with self.s3.open(full_file_path, mode="wb") as file:
+                        if hasattr(data, "read"):
+                            data.seek(0)
+                            file.write(data.read())
+                        else:
+                            file.write(data)
 
             await run_async(save_data_to_file)