DB-GPT/dbgpt/util/splitter_utils.py
2024-01-10 10:39:04 +08:00

81 lines
2.5 KiB
Python

from typing import Callable, List
def split_text_keep_separator(text: str, separator: str) -> List[str]:
"""Split text with separator and keep the separator at the end of each split."""
parts = text.split(separator)
result = [separator + s if i > 0 else s for i, s in enumerate(parts)]
return [s for s in result if s]
def split_by_sep(sep: str, keep_sep: bool = True) -> Callable[[str], List[str]]:
"""Split text by separator."""
if keep_sep:
return lambda text: split_text_keep_separator(text, sep)
else:
return lambda text: text.split(sep)
def split_by_char() -> Callable[[str], List[str]]:
"""Split text by character."""
return lambda text: list(text)
def split_by_sentence_tokenizer() -> Callable[[str], List[str]]:
import os
import nltk
from llama_index.utils import get_cache_dir
cache_dir = get_cache_dir()
nltk_data_dir = os.environ.get("NLTK_DATA", cache_dir)
# update nltk path for nltk so that it finds the data
if nltk_data_dir not in nltk.data.path:
nltk.data.path.append(nltk_data_dir)
try:
nltk.data.find("tokenizers/punkt")
except LookupError:
nltk.download("punkt", download_dir=nltk_data_dir)
tokenizer = nltk.tokenize.PunktSentenceTokenizer()
# get the spans and then return the sentences
# using the start index of each span
# instead of using end, use the start of the next span if available
def split(text: str) -> List[str]:
spans = list(tokenizer.span_tokenize(text))
sentences = []
for i, span in enumerate(spans):
start = span[0]
if i < len(spans) - 1:
end = spans[i + 1][0]
else:
end = len(text)
sentences.append(text[start:end])
return sentences
return split
def split_by_regex(regex: str) -> Callable[[str], List[str]]:
"""Split text by regex."""
import re
return lambda text: re.findall(regex, text)
def split_by_phrase_regex() -> Callable[[str], List[str]]:
"""Split text by phrase regex.
This regular expression will split the sentences into phrases,
where each phrase is a sequence of one or more non-comma,
non-period, and non-semicolon characters, followed by an optional comma,
period, or semicolon. The regular expression will also capture the
delimiters themselves as separate items in the list of phrases.
"""
regex = "[^,.;。]+[,.;。]?"
return split_by_regex(regex)