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
33 lines
1.1 KiB
Python
33 lines
1.1 KiB
Python
# Copyright (c) 2024 Microsoft Corporation.
|
|
# Licensed under the MIT License
|
|
|
|
"""A module containing 'create_chunk_results' function."""
|
|
|
|
from collections.abc import Callable
|
|
|
|
from graphrag_chunking.text_chunk import TextChunk
|
|
|
|
|
|
def create_chunk_results(
|
|
chunks: list[str],
|
|
transform: Callable[[str], str] | None = None,
|
|
encode: Callable[[str], list[int]] | None = None,
|
|
) -> list[TextChunk]:
|
|
"""Create chunk results from a list of text chunks. The index assignments are 0-based and assume chunks were not stripped relative to the source text."""
|
|
results = []
|
|
start_char = 0
|
|
for index, chunk in enumerate(chunks):
|
|
end_char = start_char + len(chunk) - 1 # 0-based indices
|
|
result = TextChunk(
|
|
original=chunk,
|
|
text=transform(chunk) if transform else chunk,
|
|
index=index,
|
|
start_char=start_char,
|
|
end_char=end_char,
|
|
)
|
|
if encode:
|
|
result.token_count = len(encode(result.text))
|
|
results.append(result)
|
|
start_char = end_char + 1
|
|
return results
|