fix: resolve issue with txt file type handling (#1697)

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

## Description
Remove custom text file resolution, it sometimes wrongly marks other
file types as txt

## 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
- [x] 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.
This commit is contained in:
Vasilije 2025-10-29 20:33:56 +01:00 committed by GitHub
commit 6b2666352a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 2 additions and 37 deletions

View file

@ -22,42 +22,6 @@ class FileTypeException(Exception):
self.message = message
class TxtFileType(filetype.Type):
"""
Represents a text file type with specific MIME and extension properties.
Public methods:
- match: Determines whether a given buffer matches the text file type.
"""
MIME = "text/plain"
EXTENSION = "txt"
def __init__(self):
super(TxtFileType, self).__init__(mime=TxtFileType.MIME, extension=TxtFileType.EXTENSION)
def match(self, buf):
"""
Determine if the given buffer contains text content.
Parameters:
-----------
- buf: The buffer to check for text content.
Returns:
--------
Returns True if the buffer is identified as text content, otherwise False.
"""
return is_text_content(buf)
txt_file_type = TxtFileType()
filetype.add_type(txt_file_type)
def guess_file_type(file: BinaryIO) -> filetype.Type:
"""
Guess the file type from the given binary file stream.

View file

@ -1,6 +1,7 @@
import filetype
from typing import Dict, List, Optional, Any
from .LoaderInterface import LoaderInterface
from cognee.infrastructure.files.utils.guess_file_type import guess_file_type
from cognee.shared.logging_utils import get_logger
logger = get_logger(__name__)
@ -80,7 +81,7 @@ class LoaderEngine:
"""
from pathlib import Path
file_info = filetype.guess(file_path)
file_info = guess_file_type(file_path)
path_extension = Path(file_path).suffix.lstrip(".")