feat: Add UnstructuredXMLLoader for .xml files (#5955)

# Unstructured XML Loader
Adds an `UnstructuredXMLLoader` class for .xml files. Works with
unstructured>=0.6.7. A plain text representation of the text with the
XML tags will be available under the `page_content` attribute in the
doc.

### Testing
```python
from langchain.document_loaders import UnstructuredXMLLoader

loader = UnstructuredXMLLoader(
    "example_data/factbook.xml",
)
docs = loader.load()
```


## Who can review?

@hwchase17 
@eyurtsev

docs/modules/indexes/document_loaders/examples/example_data/factbook.xml

@@ -0,0 +1,27 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<factbook>
+  <country>
+    <name>United States</name>
+    <capital>Washington, DC</capital>
+    <leader>Joe Biden</leader>
+    <sport>Baseball</sport>
+  </country>
+  <country>
+    <name>Canada</name>
+    <capital>Ottawa</capital>
+    <leader>Justin Trudeau</leader>
+    <sport>Hockey</sport>
+  </country>
+  <country>
+    <name>France</name>
+    <capital>Paris</capital>
+    <leader>Emmanuel Macron</leader>
+    <sport>Soccer</sport>
+  </country>
+  <country>
+    <name>Trinidad &amp; Tobado</name>
+    <capital>Port of Spain</capital>
+    <leader>Keith Rowley</leader>
+    <sport>Track &amp; Field</sport>
+  </country>
+</factbook>

docs/modules/indexes/document_loaders/examples/xml.ipynb

@@ -0,0 +1,78 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "22a849cc",
+   "metadata": {},
+   "source": [
+    "# XML\n",
+    "\n",
+    "The `UnstructuredXMLLoader` is used to load `XML` files. The loader works with `.xml` files. The page content will be the text extracted from the XML tags."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "e6616e3a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import UnstructuredXMLLoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "a654e4d9",
+   "metadata": {},
+   "outputs": [
+    {
+      "data": {
+        "text/plain": [
+          "Document(page_content='United States\\n\\nWashington, DC\\n\\nJoe Biden\\n\\nBaseball\\n\\nCanada\\n\\nOttawa\\n\\nJustin Trudeau\\n\\nHockey\\n\\nFrance\\n\\nParis\\n\\nEmmanuel Macron\\n\\nSoccer\\n\\nTrinidad & Tobado\\n\\nPort of Spain\\n\\nKeith Rowley\\n\\nTrack & Field', metadata={'source': 'example_data/factbook.xml'})"
+        ]
+      },
+      "execution_count": 2,
+      "metadata": {},
+      "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "loader = UnstructuredXMLLoader(\n",
+    "    \"example_data/factbook.xml\",\n",
+    ")\n",
+    "docs = loader.load()\n",
+    "docs[0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a54342bb",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

langchain/document_loaders/__init__.py

@@ -121,6 +121,7 @@ from langchain.document_loaders.word_document import (
     Docx2txtLoader,
     UnstructuredWordDocumentLoader,
 )
+from langchain.document_loaders.xml import UnstructuredXMLLoader
 from langchain.document_loaders.youtube import (
     GoogleApiClient,
     GoogleApiYoutubeLoader,
@@ -242,6 +243,7 @@ __all__ = [
     "UnstructuredRTFLoader",
     "UnstructuredURLLoader",
     "UnstructuredWordDocumentLoader",
+    "UnstructuredXMLLoader",
     "WeatherDataLoader",
     "WebBaseLoader",
     "WhatsAppChatLoader",

langchain/document_loaders/xml.py

@@ -0,0 +1,22 @@
+"""Loader that loads Microsoft Excel files."""
+from typing import Any, List
+
+from langchain.document_loaders.unstructured import (
+    UnstructuredFileLoader,
+    validate_unstructured_version,
+)
+
+
+class UnstructuredXMLLoader(UnstructuredFileLoader):
+    """Loader that uses unstructured to load XML files."""
+
+    def __init__(
+        self, file_path: str, mode: str = "single", **unstructured_kwargs: Any
+    ):
+        validate_unstructured_version(min_unstructured_version="0.6.7")
+        super().__init__(file_path=file_path, mode=mode, **unstructured_kwargs)
+
+    def _get_elements(self) -> List:
+        from unstructured.partition.xml import partition_xml
+
+        return partition_xml(filename=self.file_path, **self.unstructured_kwargs)

tests/integration_tests/document_loaders/test_xml.py

@@ -0,0 +1,15 @@
+import os
+from pathlib import Path
+
+from langchain.document_loaders import UnstructuredXMLLoader
+
+EXAMPLE_DIRECTORY = file_path = Path(__file__).parent.parent / "examples"
+
+
+def test_unstructured_xml_loader() -> None:
+    """Test unstructured loader."""
+    file_path = os.path.join(EXAMPLE_DIRECTORY, "factbook.xml")
+    loader = UnstructuredXMLLoader(str(file_path))
+    docs = loader.load()
+
+    assert len(docs) == 1

tests/integration_tests/examples/factbook.xml

@@ -0,0 +1,27 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<factbook>
+  <country>
+    <name>United States</name>
+    <capital>Washington, DC</capital>
+    <leader>Joe Biden</leader>
+    <sport>Baseball</sport>
+  </country>
+  <country>
+    <name>Canada</name>
+    <capital>Ottawa</capital>
+    <leader>Justin Trudeau</leader>
+    <sport>Hockey</sport>
+  </country>
+  <country>
+    <name>France</name>
+    <capital>Paris</capital>
+    <leader>Emmanuel Macron</leader>
+    <sport>Soccer</sport>
+  </country>
+  <country>
+    <name>Trinidad &amp; Tobado</name>
+    <capital>Port of Spain</capital>
+    <leader>Keith Rowley</leader>
+    <sport>Track &amp; Field</sport>
+  </country>
+</factbook>