Spaces:
Running
Running
File size: 5,611 Bytes
43d27f2 31086ae 43d27f2 31086ae 43d27f2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 |
import re
from typing import Any, List, Optional
from graphgen.bases.base_splitter import BaseSplitter
class RecursiveCharacterSplitter(BaseSplitter):
"""Splitting text by recursively look at characters.
Recursively tries to chunk by different characters to find one that works.
"""
def __init__(
self,
separators: Optional[List[str]] = None,
keep_separator: bool = True,
is_separator_regex: bool = False,
**kwargs: Any,
) -> None:
"""Create a new TextSplitter."""
super().__init__(keep_separator=keep_separator, **kwargs)
self._separators = separators or ["\n\n", "\n", " ", ""]
self._is_separator_regex = is_separator_regex
def _split_text(self, text: str, separators: List[str]) -> List[str]:
"""Split incoming text and return chunks."""
final_chunks = []
# Get appropriate separator to use
separator = separators[-1]
new_separators = []
for i, _s in enumerate(separators):
_separator = _s if self._is_separator_regex else re.escape(_s)
if _s == "":
separator = _s
break
if re.search(_separator, text):
separator = _s
new_separators = separators[i + 1 :]
break
_separator = separator if self._is_separator_regex else re.escape(separator)
splits = self._split_text_with_regex(text, _separator, self.keep_separator)
# Now go merging things, recursively splitting longer texts.
_good_splits = []
_separator = "" if self.keep_separator else separator
for s in splits:
if self.length_function(s) < self.chunk_size:
_good_splits.append(s)
else:
if _good_splits:
merged_text = self._merge_splits(_good_splits, _separator)
final_chunks.extend(merged_text)
_good_splits = []
if not new_separators:
final_chunks.append(s)
else:
other_info = self._split_text(s, new_separators)
final_chunks.extend(other_info)
if _good_splits:
merged_text = self._merge_splits(_good_splits, _separator)
final_chunks.extend(merged_text)
return final_chunks
def split_text(self, text: str) -> List[str]:
return self._split_text(text, self._separators)
class ChineseRecursiveTextSplitter(RecursiveCharacterSplitter):
def __init__(
self,
separators: Optional[List[str]] = None,
keep_separator: bool = True,
is_separator_regex: bool = True,
**kwargs: Any,
) -> None:
super().__init__(keep_separator=keep_separator, **kwargs)
self._separators = separators or [
"\n\n",
"\n",
"。|！|？",
r"\.\s|\!\s|\?\s",
r"；|;\s",
r"，|,\s",
]
self._is_separator_regex = is_separator_regex
def _split_text_with_regex_from_end(
self, text: str, separator: str, keep_separator: bool
) -> List[str]:
# Now that we have the separator, chunk the text
if separator:
if keep_separator:
# The parentheses in the pattern keep the delimiters in the result.
_splits = re.split(f"({separator})", text)
splits = ["".join(i) for i in zip(_splits[0::2], _splits[1::2])]
if len(_splits) % 2 == 1:
splits += _splits[-1:]
else:
splits = re.split(separator, text)
else:
splits = list(text)
return [s for s in splits if s != ""]
def _split_text(self, text: str, separators: List[str]) -> List[str]:
"""Split incoming text and return chunks."""
final_chunks = []
# Get appropriate separator to use
separator = separators[-1]
new_separators = []
for i, _s in enumerate(separators):
_separator = _s if self._is_separator_regex else re.escape(_s)
if _s == "":
separator = _s
break
if re.search(_separator, text):
separator = _s
new_separators = separators[i + 1 :]
break
_separator = separator if self._is_separator_regex else re.escape(separator)
splits = self._split_text_with_regex_from_end(
text, _separator, self.keep_separator
)
# Now go merging things, recursively splitting longer texts.
_good_splits = []
_separator = "" if self.keep_separator else separator
for s in splits:
if self.length_function(s) < self.chunk_size:
_good_splits.append(s)
else:
if _good_splits:
merged_text = self._merge_splits(_good_splits, _separator)
final_chunks.extend(merged_text)
_good_splits = []
if not new_separators:
final_chunks.append(s)
else:
other_info = self._split_text(s, new_separators)
final_chunks.extend(other_info)
if _good_splits:
merged_text = self._merge_splits(_good_splits, _separator)
final_chunks.extend(merged_text)
return [
re.sub(r"\n{2,}", "\n", chunk.strip())
for chunk in final_chunks
if chunk.strip() != ""
]
|