Files
microsoft--graphrag/packages/graphrag-input/graphrag_input/csv.py
T
wehub-resource-sync 6b7e6b44f1
Python Build and Type Check / python-ci (ubuntu-latest, 3.11) (push) Has been cancelled
Python Build and Type Check / python-ci (ubuntu-latest, 3.13) (push) Has been cancelled
Python Build and Type Check / python-ci (windows-latest, 3.11) (push) Has been cancelled
Python Build and Type Check / python-ci (windows-latest, 3.13) (push) Has been cancelled
Python Integration Tests / python-ci (ubuntu-latest, 3.13) (push) Has been cancelled
Python Integration Tests / python-ci (windows-latest, 3.13) (push) Has been cancelled
Python Notebook Tests / python-ci (ubuntu-latest, 3.13) (push) Has been cancelled
Python Notebook Tests / python-ci (windows-latest, 3.13) (push) Has been cancelled
Python Smoke Tests / python-ci (ubuntu-latest, 3.13) (push) Has been cancelled
Python Smoke Tests / python-ci (windows-latest, 3.13) (push) Has been cancelled
Python Unit Tests / python-ci (ubuntu-latest, 3.13) (push) Has been cancelled
Python Unit Tests / python-ci (windows-latest, 3.13) (push) Has been cancelled
gh-pages / build (push) Has been cancelled
Python Publish (pypi) / Upload release to PyPI (push) Has been cancelled
Spellcheck / spellcheck (push) Has been cancelled
chore: import upstream snapshot with attribution
2026-07-13 12:37:31 +08:00

46 lines
1.2 KiB
Python

# Copyright (c) 2024 Microsoft Corporation.
# Licensed under the MIT License
"""A module containing 'CSVFileReader' model."""
import csv
import io
import logging
import sys
from graphrag_input.structured_file_reader import StructuredFileReader
from graphrag_input.text_document import TextDocument
logger = logging.getLogger(__name__)
try:
csv.field_size_limit(sys.maxsize)
except OverflowError:
csv.field_size_limit(100 * 1024 * 1024)
class CSVFileReader(StructuredFileReader):
"""Reader implementation for csv files."""
def __init__(self, file_pattern: str | None = None, **kwargs):
super().__init__(
file_pattern=file_pattern if file_pattern is not None else ".*\\.csv$",
**kwargs,
)
async def read_file(self, path: str) -> list[TextDocument]:
"""Read a csv file into a list of documents.
Args:
- path - The path to read the file from.
Returns
-------
- output - list with a TextDocument for each row in the file.
"""
file = await self._storage.get(path, encoding=self._encoding)
reader = csv.DictReader(io.StringIO(file))
rows = list(reader)
return await self.process_data_columns(rows, path)