feat: Add support for the Solidity language (#6054)

<!--
Thank you for contributing to LangChain! Your PR will appear in our
release under the title you set. Please make sure it highlights your
valuable contribution.

Replace this with a description of the change, the issue it fixes (if
applicable), and relevant context. List any dependencies required for
this change.

After you're done, someone will review your PR. They may suggest
improvements. If no one reviews your PR within a few days, feel free to
@-mention the same people again, as notifications can get lost.

Finally, we'd love to show appreciation for your contribution - if you'd
like us to shout you out on Twitter, please also include your handle!
-->

## Add Solidity programming language support for code splitter.

Twitter: @0xjord4n_

<!-- If you're adding a new integration, please include:

1. a test for the integration - favor unit tests that does not rely on
network access.
2. an example notebook showing its use


See contribution guidelines for more information on how to write tests,
lint
etc:


https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
#### Who can review?

Tag maintainers/contributors who might be interested:
@hwchase17

<!-- For a quicker response, figure out the right person to tag with @

  @hwchase17 - project lead

  Tracing / Callbacks
  - @agola11

  Async
  - @agola11

  DataLoaders
  - @eyurtsev

  Models
  - @hwchase17
  - @agola11

  Agents / Tools / Toolkits
  - @hwchase17

  VectorStores / Retrievers / Memory
  - @dev2049

 -->

docs/modules/indexes/text_splitters/examples/code_splitter.ipynb

@@ -43,7 +43,8 @@
           " 'swift',\n",
           " 'markdown',\n",
           " 'latex',\n",
-       " 'html']"
+          " 'html',\n",
+          " 'sol']"
          ]
         },
         "execution_count": 2,
@@ -160,6 +161,49 @@
        "js_docs"
       ]
      },
+     {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+       "## Solidity\n",
+       "Here's an example using the Solidity text splitter"
+      ]
+     },
+     {
+      "cell_type": "code",
+      "execution_count": 5,
+      "metadata": {},
+      "outputs": [
+        {
+         "data": {
+          "text/plain": [
+            "[Document(page_content='pragma solidity ^0.8.20;', metadata={}),\n",
+            " Document(page_content='contract HelloWorld {\\n   function add(uint a, uint b) pure public returns(uint) {\\n       return a + b;\\n   }\\n}', metadata={})]"
+          ]
+         },
+         "execution_count": 5,
+         "metadata": {},
+         "output_type": "execute_result"
+        }
+       ],
+      "source": [
+       "SOL_CODE = \"\"\"\n",
+       "pragma solidity ^0.8.20;",
+       "\n",
+       "contract HelloWorld {\n",
+       "   function add(uint a, uint b) pure public returns(uint) {\n",
+       "       return a + b;\n",
+       "   }\n",
+       "}\n",
+       "\"\"\"\n",
+       "\n",
+       "sol_splitter = RecursiveCharacterTextSplitter.from_language(\n",
+       "    language=Language.SOL, chunk_size=128, chunk_overlap=0\n",
+       ")\n",
+       "sol_docs = sol_splitter.create_documents([SOL_CODE])\n",
+       "sol_docs"
+      ]
+     },
      {
       "cell_type": "markdown",
       "metadata": {},
@@ -188,7 +232,7 @@
        "```\n",
        "\n",
        "As an open source project in a rapidly developing field, we are extremely open to contributions.\n",
-    "\"\"\"\n"
+       "\"\"\""
       ]
      },
      {
@@ -410,4 +454,4 @@
     },
     "nbformat": 4,
     "nbformat_minor": 2
-}
+   }   

langchain/text_splitter.py

@@ -565,6 +565,7 @@ class Language(str, Enum):
     MARKDOWN = "markdown"
     LATEX = "latex"
     HTML = "html"
+    SOL = "sol"
 
 
 class RecursiveCharacterTextSplitter(TextSplitter):
@@ -895,7 +896,7 @@ class RecursiveCharacterTextSplitter(TextSplitter):
                 "\n\\\begin{quotation}",
                 "\n\\\begin{verse}",
                 "\n\\\begin{verbatim}",
-                ## Now split by math environments
+                # Now split by math environments
                 "\n\\\begin{align}",
                 "$$",
                 "$",
@@ -935,6 +936,36 @@ class RecursiveCharacterTextSplitter(TextSplitter):
                 "<title",
                 "",
             ]
+        elif language == Language.SOL:
+            return [
+                # Split along compiler informations definitions
+                "\npragma ",
+                "\nusing ",
+                # Split along contract definitions
+                "\ncontract ",
+                "\ninterface ",
+                "\nlibrary ",
+                # Split along method definitions
+                "\nconstructor ",
+                "\ntype ",
+                "\nfunction ",
+                "\nevent ",
+                "\nmodifier ",
+                "\nerror ",
+                "\nstruct ",
+                "\nenum ",
+                # Split along control flow statements
+                "\nif ",
+                "\nfor ",
+                "\nwhile ",
+                "\ndo while ",
+                "\nassembly ",
+                # Split by the normal type of lines
+                "\n\n",
+                "\n",
+                " ",
+                "",
+            ]
         else:
             raise ValueError(
                 f"Language {language} is not supported! "

tests/unit_tests/test_text_splitter.py

@@ -798,3 +798,31 @@ def test_md_header_text_splitter_3() -> None:
     ]
 
     assert output == expected_output
+
+
+def test_solidity_code_splitter() -> None:
+    splitter = RecursiveCharacterTextSplitter.from_language(
+        Language.SOL, chunk_size=CHUNK_SIZE, chunk_overlap=0
+    )
+    code = """pragma solidity ^0.8.20;
+  contract HelloWorld {
+    function add(uint a, uint b) pure public returns(uint) {
+      return  a + b;
+    }
+  }
+  """
+    chunks = splitter.split_text(code)
+    assert chunks == [
+        "pragma solidity",
+        "^0.8.20;",
+        "contract",
+        "HelloWorld {",
+        "function",
+        "add(uint a,",
+        "uint b) pure",
+        "public",
+        "returns(uint) {",
+        "return  a",
+        "+ b;",
+        "}\n  }",
+    ]