From cd80a805b2afa8b68564e71ee0ff00d5dc0a7cd6 Mon Sep 17 00:00:00 2001
From: Deepak Bhagat <149673145+deepak0x@users.noreply.github.com>
Date: Tue, 28 Apr 2026 00:38:12 +0530
Subject: [PATCH] fix(text-splitters): remove invalid and duplicate separators
 in Kotlin, Rust, and Haskell (#37039)
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

## Summary

Fixes four issues in `get_separators_for_language()` in `character.py`:

- **Kotlin**: removed `"\ncase "` — `case` is not a Kotlin keyword.
Kotlin uses `when` expressions (already present in the list). This was
copied from Java/Swift.
- **Rust**: removed duplicate `"\nconst "` — appeared twice, once under
function definitions and again under control flow statements.
- **Haskell**: removed duplicate `"\n:: "` — appeared under function
definitions and again under type declarations.
- **Haskell**: removed duplicate `"\ndata "` — appeared under type
declarations and again under record field declarations.

All four are dead separators that never match or produce redundant
splits.

## Issue

Closes #37038

## Types of changes

- [x] Bug fix

## Checklist

- [x] I have read the CONTRIBUTING doc
- [x] Lint and unit tests pass locally with my changes
---
 libs/text-splitters/langchain_text_splitters/character.py | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/libs/text-splitters/langchain_text_splitters/character.py b/libs/text-splitters/langchain_text_splitters/character.py
index dd2378a787..0e2e1ab2a9 100644
--- a/libs/text-splitters/langchain_text_splitters/character.py
+++ b/libs/text-splitters/langchain_text_splitters/character.py
@@ -266,7 +266,6 @@ class RecursiveCharacterTextSplitter(TextSplitter):
                 "\nfor ",
                 "\nwhile ",
                 "\nwhen ",
-                "\ncase ",
                 "\nelse ",
                 # Split by the normal type of lines
                 "\n\n",
@@ -463,7 +462,6 @@ class RecursiveCharacterTextSplitter(TextSplitter):
                 "\nfor ",
                 "\nloop ",
                 "\nmatch ",
-                "\nconst ",
                 # Split by the normal type of lines
                 "\n\n",
                 "\n",
@@ -718,7 +716,6 @@ class RecursiveCharacterTextSplitter(TextSplitter):
                 "\ndata ",
                 "\nnewtype ",
                 "\ntype ",
-                "\n:: ",
                 # Split along module declarations
                 "\nmodule ",
                 # Split along import statements
@@ -733,7 +730,6 @@ class RecursiveCharacterTextSplitter(TextSplitter):
                 # Split along guards in function definitions
                 "\n| ",
                 # Split along record field declarations
-                "\ndata ",
                 "\n= {",
                 "\n, ",
                 # Split by the normal type of lines