text-splitters[minor]: Added Haskell support in langchain.text_splitter module (#16191)

- **Description:** Haskell language support added in text_splitter
module
  - **Dependencies:** No
  - **Twitter handle:** @nisargtr

If no one reviews your PR within a few days, please @-mention one of
@baskaryan, @eyurtsev, @hwchase17.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>

libs/text-splitters/langchain_text_splitters/base.py

@@ -291,6 +291,7 @@ class Language(str, Enum):
     C = "c"
     LUA = "lua"
     PERL = "perl"
+    HASKELL = "haskell"
 
 
 @dataclass(frozen=True)

libs/text-splitters/langchain_text_splitters/character.py

@@ -571,7 +571,45 @@ class RecursiveCharacterTextSplitter(TextSplitter):
                 " ",
                 "",
             ]
-
+        elif language == Language.HASKELL:
+            return [
+                # Split along function definitions
+                "\nmain :: ",
+                "\nmain = ",
+                "\nlet ",
+                "\nin ",
+                "\ndo ",
+                "\nwhere ",
+                "\n:: ",
+                "\n= ",
+                # Split along type declarations
+                "\ndata ",
+                "\nnewtype ",
+                "\ntype ",
+                "\n:: ",
+                # Split along module declarations
+                "\nmodule ",
+                # Split along import statements
+                "\nimport ",
+                "\nqualified ",
+                "\nimport qualified ",
+                # Split along typeclass declarations
+                "\nclass ",
+                "\ninstance ",
+                # Split along case expressions
+                "\ncase ",
+                # Split along guards in function definitions
+                "\n| ",
+                # Split along record field declarations
+                "\ndata ",
+                "\n= {",
+                "\n, ",
+                # Split by the normal type of lines
+                "\n\n",
+                "\n",
+                " ",
+                "",
+            ]
         else:
             raise ValueError(
                 f"Language {language} is not supported! "

libs/text-splitters/tests/unit_tests/test_text_splitters.py

@@ -1248,6 +1248,38 @@ def test_solidity_code_splitter() -> None:
     ]
 
 
+def test_haskell_code_splitter() -> None:
+    splitter = RecursiveCharacterTextSplitter.from_language(
+        Language.HASKELL, chunk_size=CHUNK_SIZE, chunk_overlap=0
+    )
+    code = """
+        main :: IO ()
+        main = do
+          putStrLn "Hello, World!"
+
+        -- Some sample functions
+        add :: Int -> Int -> Int
+        add x y = x + y
+    """
+    # Adjusted expected chunks to account for indentation and newlines
+    expected_chunks = [
+        "main ::",
+        "IO ()",
+        "main = do",
+        "putStrLn",
+        '"Hello, World!"',
+        "--",
+        "Some sample",
+        "functions",
+        "add :: Int ->",
+        "Int -> Int",
+        "add x y = x",
+        "+ y",
+    ]
+    chunks = splitter.split_text(code)
+    assert chunks == expected_chunks
+
+
 @pytest.mark.requires("lxml")
 def test_html_header_text_splitter(tmp_path: Path) -> None:
     splitter = HTMLHeaderTextSplitter(