From c5c2849f0ba78496acf07d8f4fc012505001bfd7 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=BB=84=E6=9C=9D=E6=99=96?= <huangzhwork@gmail.com>
Date: Wed, 24 Jul 2024 19:26:41 +0800
Subject: [PATCH] Remove useless MarkdownSplitter

---
 src/Document/MarkdownDocument.php     |  4 +--
 src/TextSplitter/MarkdownSplitter.php | 49 ---------------------------
 2 files changed, 2 insertions(+), 51 deletions(-)
 delete mode 100644 src/TextSplitter/MarkdownSplitter.php

diff --git a/src/Document/MarkdownDocument.php b/src/Document/MarkdownDocument.php
index 7e74e3a..067239b 100644
--- a/src/Document/MarkdownDocument.php
+++ b/src/Document/MarkdownDocument.php
@@ -12,13 +12,13 @@
 
 namespace Hyperf\Odin\Document;
 
-use Hyperf\Odin\TextSplitter\MarkdownSplitter;
+use Hyperf\Odin\TextSplitter\RecursiveCharacterTextSplitter;
 
 class MarkdownDocument extends Document
 {
     public function split(): array
     {
-        $recursiveCharacterTextSplitter = new MarkdownSplitter();
+        $recursiveCharacterTextSplitter = new RecursiveCharacterTextSplitter('markdown');
         return $recursiveCharacterTextSplitter->splitText($this->getContent());
     }
 
diff --git a/src/TextSplitter/MarkdownSplitter.php b/src/TextSplitter/MarkdownSplitter.php
deleted file mode 100644
index 6ea6010..0000000
--- a/src/TextSplitter/MarkdownSplitter.php
+++ /dev/null
@@ -1,49 +0,0 @@
-<?php
-
-declare(strict_types=1);
-/**
- * This file is part of Hyperf.
- *
- * @link     https://www.hyperf.io
- * @document https://hyperf.wiki
- * @contact  group@hyperf.io
- * @license  https://github.com/hyperf/hyperf/blob/master/LICENSE
- */
-
-namespace Hyperf\Odin\TextSplitter;
-
-class MarkdownSplitter extends RecursiveCharacterTextSplitter
-{
-    public function __construct(
-        $separators = null,
-        $isSeparatorRegex = false,
-        $chunkSize = 4000,
-        $chunkOverlap = 200,
-        $keepSeparator = false,
-        $addStartIndex = false,
-        $stripWhitespace = true
-    ) {
-        if (! $separators) {
-            $separators = [
-                # First, try to split along Markdown headings (starting with level 2)
-                "\n#{1,6} ",
-                # Note the alternative syntax for headings (below) is not handled here
-                # Heading level 2
-                # ---------------
-                # End of code block
-                "```\n",
-                # Horizontal lines
-                "\n\\*\\*\\*+\n",
-                "\n---+\n",
-                "\n___+\n",
-                # Note that this splitter doesn't handle horizontal lines defined
-                # by *three or more* of ***, ---, or ___, but this is not handled
-                "\n\n",
-                "\n",
-                ' ',
-                '',
-            ];
-        }
-        parent::__construct($separators, $isSeparatorRegex, $chunkSize, $chunkOverlap, $keepSeparator, $addStartIndex, $stripWhitespace);
-    }
-}