_split_text_with_regex() — langchain Function Reference
Architecture documentation for the _split_text_with_regex() function in character.py from the langchain codebase.
Entity Profile
Dependency Diagram
graph TD 4df0af83_3c38_0acb_3015_c017f66de0cc["_split_text_with_regex()"] 2928a4a1_9408_cbea_fa7c_7f66eab697a2["character.py"] 4df0af83_3c38_0acb_3015_c017f66de0cc -->|defined in| 2928a4a1_9408_cbea_fa7c_7f66eab697a2 11fcdf48_fab6_27e3_ca6c_8904e5348e23["split_text()"] 11fcdf48_fab6_27e3_ca6c_8904e5348e23 -->|calls| 4df0af83_3c38_0acb_3015_c017f66de0cc 90247d99_f9d1_5357_ea60_e7b8e740431f["_split_text()"] 90247d99_f9d1_5357_ea60_e7b8e740431f -->|calls| 4df0af83_3c38_0acb_3015_c017f66de0cc style 4df0af83_3c38_0acb_3015_c017f66de0cc fill:#6366f1,stroke:#818cf8,color:#fff
Relationship Graph
Source Code
libs/text-splitters/langchain_text_splitters/character.py lines 61–85
def _split_text_with_regex(
text: str, separator: str, *, keep_separator: 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(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, splits_[-1]])
if keep_separator == "end"
else ([splits_[0], *splits])
)
else:
splits = re.split(separator, text)
else:
splits = list(text)
return [s for s in splits if s]
Domain
Subdomains
Called By
Source
Frequently Asked Questions
What does _split_text_with_regex() do?
_split_text_with_regex() is a function in the langchain codebase, defined in libs/text-splitters/langchain_text_splitters/character.py.
Where is _split_text_with_regex() defined?
_split_text_with_regex() is defined in libs/text-splitters/langchain_text_splitters/character.py at line 61.
What calls _split_text_with_regex()?
_split_text_with_regex() is called by 2 function(s): _split_text, split_text.
Analyze Your Own Codebase
Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.
Try Supermodel Free