mirror of
https://github.com/hwchase17/langchain.git
synced 2025-09-06 13:33:37 +00:00
community: Add PHP language parser to document_loaders (#19850)
**Description:** Added a PHP language parser to document_loaders **Issue:** N/A **Dependencies:** N/A **Twitter handle:** N/A --------- Co-authored-by: Chester Curme <chester.curme@gmail.com>
This commit is contained in:
@@ -612,6 +612,63 @@
|
||||
"haskell_docs = haskell_splitter.create_documents([HASKELL_CODE])\n",
|
||||
"haskell_docs"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4a11f7cd-cd85-430c-b307-5b5b5f07f8db",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## PHP\n",
|
||||
"Here's an example using the PHP text splitter:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "90c66e7e-87a5-4a81-bece-7949aabf2369",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='<?php\\nnamespace foo;'),\n",
|
||||
" Document(page_content='class Hello {'),\n",
|
||||
" Document(page_content='public function __construct() { }\\n}'),\n",
|
||||
" Document(page_content='function hello() {\\n echo \"Hello World!\";\\n}'),\n",
|
||||
" Document(page_content='interface Human {\\n public function breath();\\n}'),\n",
|
||||
" Document(page_content='trait Foo { }\\nenum Color\\n{\\n case Red;'),\n",
|
||||
" Document(page_content='case Blue;\\n}')]"
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"PHP_CODE = \"\"\"<?php\n",
|
||||
"namespace foo;\n",
|
||||
"class Hello {\n",
|
||||
" public function __construct() { }\n",
|
||||
"}\n",
|
||||
"function hello() {\n",
|
||||
" echo \"Hello World!\";\n",
|
||||
"}\n",
|
||||
"interface Human {\n",
|
||||
" public function breath();\n",
|
||||
"}\n",
|
||||
"trait Foo { }\n",
|
||||
"enum Color\n",
|
||||
"{\n",
|
||||
" case Red;\n",
|
||||
" case Blue;\n",
|
||||
"}\"\"\"\n",
|
||||
"php_splitter = RecursiveCharacterTextSplitter.from_language(\n",
|
||||
" language=Language.PHP, chunk_size=50, chunk_overlap=0\n",
|
||||
")\n",
|
||||
"haskell_docs = php_splitter.create_documents([PHP_CODE])\n",
|
||||
"haskell_docs"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
@@ -630,7 +687,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
"version": "3.10.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
Reference in New Issue
Block a user