Feature/adding csharp support to textsplitter (#10350)

**Description:** Adding C# language support for
`RecursiveCharacterTextSplitter`
**Issue:**   N/A
**Dependencies:** N/A

---------

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

libs/langchain/langchain/text_splitter.py

@@ -627,6 +627,7 @@ class Language(str, Enum):
     LATEX = "latex"
     HTML = "html"
     SOL = "sol"
+    CSHARP = "csharp"
 
 
 class RecursiveCharacterTextSplitter(TextSplitter):
@@ -1002,6 +1003,43 @@ class RecursiveCharacterTextSplitter(TextSplitter):
                 "<title",
                 "",
             ]
+        elif language == Language.CSHARP:
+            return [
+                "\ninterface ",
+                "\nenum ",
+                "\nimplements ",
+                "\ndelegate ",
+                "\nevent ",
+                # Split along class definitions
+                "\nclass ",
+                "\nabstract ",
+                # Split along method definitions
+                "\npublic ",
+                "\nprotected ",
+                "\nprivate ",
+                "\nstatic ",
+                "\nreturn ",
+                # Split along control flow statements
+                "\nif ",
+                "\ncontinue ",
+                "\nfor ",
+                "\nforeach ",
+                "\nwhile ",
+                "\nswitch ",
+                "\nbreak ",
+                "\ncase ",
+                "\nelse ",
+                # Split by exceptions
+                "\ntry ",
+                "\nthrow ",
+                "\nfinally ",
+                "\ncatch ",
+                # Split by the normal type of lines
+                "\n\n",
+                "\n",
+                " ",
+                "",
+            ]
         elif language == Language.SOL:
             return [
                 # Split along compiler information definitions
@@ -1032,6 +1070,7 @@ class RecursiveCharacterTextSplitter(TextSplitter):
                 " ",
                 "",
             ]
+
         else:
             raise ValueError(
                 f"Language {language} is not supported! "

libs/langchain/tests/unit_tests/test_text_splitter.py

@@ -498,6 +498,73 @@ public class HelloWorld {
     ]
 
 
+def test_csharp_code_splitter() -> None:
+    splitter = RecursiveCharacterTextSplitter.from_language(
+        Language.CSHARP, chunk_size=CHUNK_SIZE, chunk_overlap=0
+    )
+    code = """
+using System;
+class Program
+{
+    static void Main()
+    {
+        int age = 30; // Change the age value as needed
+
+        // Categorize the age without any console output
+        if (age < 18)
+        {
+            // Age is under 18
+        }
+        else if (age >= 18 && age < 65)
+        {
+            // Age is an adult
+        }
+        else
+        {
+            // Age is a senior citizen
+        }
+    }
+}
+    """
+
+    chunks = splitter.split_text(code)
+    assert chunks == [
+        "using System;",
+        "class Program\n{",
+        "static void",
+        "Main()",
+        "{",
+        "int age",
+        "= 30; // Change",
+        "the age value",
+        "as needed",
+        "//",
+        "Categorize the",
+        "age without any",
+        "console output",
+        "if (age",
+        "< 18)",
+        "{",
+        "//",
+        "Age is under 18",
+        "}",
+        "else if",
+        "(age >= 18 &&",
+        "age < 65)",
+        "{",
+        "//",
+        "Age is an adult",
+        "}",
+        "else",
+        "{",
+        "//",
+        "Age is a senior",
+        "citizen",
+        "}\n    }",
+        "}",
+    ]
+
+
 def test_cpp_code_splitter() -> None:
     splitter = RecursiveCharacterTextSplitter.from_language(
         Language.CPP, chunk_size=CHUNK_SIZE, chunk_overlap=0