text-splitters[patch]: Extend TextSplitter:keep_separator functionality (#21130)

**Description:** Added extra functionality to `CharacterTextSplitter`,
`TextSplitter` classes.
The user can select whether to append the separator to the previous
chunk with `keep_separator='end' ` or else prepend to the next chunk.
Previous functionality prepended by default to next chunk.
  
**Issue:** Fixes #20908

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>

libs/text-splitters/langchain_text_splitters/base.py

@@ -35,7 +35,7 @@ class TextSplitter(BaseDocumentTransformer, ABC):
         chunk_size: int = 4000,
         chunk_overlap: int = 200,
         length_function: Callable[[str], int] = len,
-        keep_separator: bool = False,
+        keep_separator: Union[bool, Literal["start", "end"]] = False,
         add_start_index: bool = False,
         strip_whitespace: bool = True,
     ) -> None:
@@ -45,7 +45,8 @@ class TextSplitter(BaseDocumentTransformer, ABC):
             chunk_size: Maximum size of chunks to return
             chunk_overlap: Overlap in characters between chunks
             length_function: Function that measures the length of given chunks
-            keep_separator: Whether to keep the separator in the chunks
+            keep_separator: Whether to keep the separator and where to place it
+                            in each corresponding chunk (True='start')
             add_start_index: If `True`, includes chunk's start index in metadata
             strip_whitespace: If `True`, strips whitespace from the start and end of
                               every document

libs/text-splitters/langchain_text_splitters/character.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 import re
-from typing import Any, List, Optional
+from typing import Any, List, Literal, Optional, Union
 
 from langchain_text_splitters.base import Language, TextSplitter
 
@@ -29,17 +29,25 @@ class CharacterTextSplitter(TextSplitter):
 
 
 def _split_text_with_regex(
-    text: str, separator: str, keep_separator: bool
+    text: str, separator: str, keep_separator: Union[bool, Literal["start", "end"]]
 ) -> List[str]:
     # Now that we have the separator, split 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 = [_splits[i] + _splits[i + 1] for i in range(1, len(_splits), 2)]
+            splits = (
+                ([_splits[i] + _splits[i + 1] for i in range(0, len(_splits) - 1, 2)])
+                if keep_separator == "end"
+                else ([_splits[i] + _splits[i + 1] for i in range(1, len(_splits), 2)])
+            )
             if len(_splits) % 2 == 0:
                 splits += _splits[-1:]
-            splits = [_splits[0]] + splits
+            splits = (
+                (splits + [_splits[-1]])
+                if keep_separator == "end"
+                else ([_splits[0]] + splits)
+            )
         else:
             splits = re.split(separator, text)
     else: