add CoNLL-U document loader (#1297)

I've added a simple
[CoNLL-U](https://universaldependencies.org/format.html) document
loader. CoNLL-U is a common format for NLP tasks and is used, for
example, in the Universal Dependencies treebank corpora. The loader
reads a single file in standard CoNLL-U format and returns a document.

docs/modules/document_loaders/examples/CoNLL-U.ipynb

@@ -0,0 +1,116 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "9f98a15e",
+   "metadata": {},
+   "source": [
+    "# CoNLL-U\n",
+    "This is an example of how to load a file in [CoNLL-U](https://universaldependencies.org/format.html) format. The whole file is treated as one document. The example data (`conllu.conllu`) is based on one of the standard UD/CoNLL-U examples."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d9b2e33e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from langchain.document_loaders import CoNLLULoader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5b5eec48",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "loader = CoNLLULoader(\"example_data/conllu.conllu\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "10f3f725",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "document = loader.load()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "acbb3579",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "document"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.8.8"
+  },
+  "toc": {
+   "base_numbering": 1,
+   "nav_menu": {},
+   "number_sections": true,
+   "sideBar": true,
+   "skip_h1_title": false,
+   "title_cell": "Table of Contents",
+   "title_sidebar": "Contents",
+   "toc_cell": false,
+   "toc_position": {},
+   "toc_section_display": true,
+   "toc_window_display": false
+  },
+  "varInspector": {
+   "cols": {
+    "lenName": 16,
+    "lenType": 16,
+    "lenVar": 40
+   },
+   "kernels_config": {
+    "python": {
+     "delete_cmd_postfix": "",
+     "delete_cmd_prefix": "del ",
+     "library": "var_list.py",
+     "varRefreshCmd": "print(var_dic_list())"
+    },
+    "r": {
+     "delete_cmd_postfix": ") ",
+     "delete_cmd_prefix": "rm(",
+     "library": "var_list.r",
+     "varRefreshCmd": "cat(var_dic_list()) "
+    }
+   },
+   "types_to_exclude": [
+    "module",
+    "function",
+    "builtin_function_or_method",
+    "instance",
+    "_Feature"
+   ],
+   "window_display": false
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

docs/modules/document_loaders/examples/example_data/conllu.conllu

@@ -0,0 +1,8 @@
+# sent_id = 1
+# text = They buy and sell books.
+1	They	they	PRON	PRP	Case=Nom|Number=Plur	2	nsubj	2:nsubj|4:nsubj	_
+2	buy	buy	VERB	VBP	Number=Plur|Person=3|Tense=Pres	0	root	0:root	_
+3	and	and	CONJ	CC 	_	4	cc	4:cc	_
+4	sell	sell	VERB	VBP	Number=Plur|Person=3|Tense=Pres	2	conj	0:root|2:conj	_
+5	books	book	NOUN	NNS	Number=Plur	2	obj	2:obj|4:obj	SpaceAfter=No
+6	.	.	PUNCT	.	_	2	punct	2:punct	_

docs/modules/document_loaders/how_to_guides.rst

@@ -57,6 +57,8 @@ There are a lot of different document loaders that LangChain supports. Below are
 
 `Online PDF <./examples/online_pdf.html>`_: A walkthrough of how to load data from an online PDF.
 
+`CoNLL-U <./examples/CoNLL-U.html>`_: A walkthrough of how to load data from a ConLL-U file.
+
 .. toctree::
    :maxdepth: 1
    :glob:

langchain/document_loaders/__init__.py

@@ -3,6 +3,7 @@
 from langchain.document_loaders.airbyte_json import AirbyteJSONLoader
 from langchain.document_loaders.azlyrics import AZLyricsLoader
 from langchain.document_loaders.college_confidential import CollegeConfidentialLoader
+from langchain.document_loaders.conllu import CoNLLULoader
 from langchain.document_loaders.directory import DirectoryLoader
 from langchain.document_loaders.docx import UnstructuredDocxLoader
 from langchain.document_loaders.email import UnstructuredEmailLoader
@@ -77,4 +78,5 @@ __all__ = [
     "SRTLoader",
     "FacebookChatLoader",
     "NotebookLoader",
+    "CoNLLULoader",
 ]

langchain/document_loaders/conllu.py

@@ -0,0 +1,33 @@
+"""Load CoNLL-U files."""
+import csv
+from typing import List
+
+from langchain.docstore.document import Document
+from langchain.document_loaders.base import BaseLoader
+
+
+class CoNLLULoader(BaseLoader):
+    """Load CoNLL-U files."""
+
+    def __init__(self, file_path: str):
+        """Initialize with file path."""
+        self.file_path = file_path
+
+    def load(self) -> List[Document]:
+        """Load from file path."""
+        with open(self.file_path, encoding="utf8") as f:
+            tsv = list(csv.reader(f, delimiter="\t"))
+
+            # If len(line) > 1, the line is not a comment
+            lines = [line for line in tsv if len(line) > 1]
+
+        text = ""
+        for i, line in enumerate(lines):
+            # Do not add a space after a punctuation mark or at the end of the sentence
+            if line[9] == "SpaceAfter=No" or i == len(lines) - 1:
+                text += line[1]
+            else:
+                text += line[1] + " "
+
+        metadata = {"source": self.file_path}
+        return [Document(page_content=text, metadata=metadata)]