From 9b2fb09c5920641a40305154b1a1acb833021107 Mon Sep 17 00:00:00 2001
From: Leon Luithlen <leon@topoteretes.com>
Date: Wed, 13 Nov 2024 15:39:17 +0100
Subject: [PATCH] Fix PdfDocument teset, give chunk_by_sentence a
 maximum_length arg

---
 cognee/tasks/chunks/chunk_by_sentence.py                      | 2 +-
 cognee/tests/unit/documents/PdfDocument_test.py               | 4 ++--
 ...unk_by_paragraph_test2.py => chunk_by_paragraph_2_test.py} | 0
 .../tests/unit/processing/chunks/chunk_by_paragraph_test.py   | 2 +-
 4 files changed, 4 insertions(+), 4 deletions(-)
 rename cognee/tests/unit/processing/chunks/{chunk_by_paragraph_test2.py => chunk_by_paragraph_2_test.py} (100%)

diff --git a/cognee/tasks/chunks/chunk_by_sentence.py b/cognee/tasks/chunks/chunk_by_sentence.py
index 7191a78c4..1ce052a6c 100644
--- a/cognee/tasks/chunks/chunk_by_sentence.py
+++ b/cognee/tasks/chunks/chunk_by_sentence.py
@@ -5,7 +5,7 @@ from uuid import uuid4
 from typing import Optional
 from .chunk_by_word import chunk_by_word
 
-def chunk_by_sentence(data: str, maximum_length: Optional[int]):
+def chunk_by_sentence(data: str, maximum_length: Optional[int] = None):
     sentence = ""
     paragraph_id = uuid4()
     chunk_index = 0
diff --git a/cognee/tests/unit/documents/PdfDocument_test.py b/cognee/tests/unit/documents/PdfDocument_test.py
index 917e9c3e0..108d61273 100644
--- a/cognee/tests/unit/documents/PdfDocument_test.py
+++ b/cognee/tests/unit/documents/PdfDocument_test.py
@@ -4,8 +4,8 @@ import uuid
 from cognee.modules.data.processing.document_types.PdfDocument import PdfDocument
 
 GROUND_TRUTH = [
-    {"word_count": 879, "len_text": 5622, "cut_type": "sentence_end"},
-    {"word_count": 951, "len_text": 6384, "cut_type": "sentence_end"},
+    {"word_count": 879, "len_text": 5607, "cut_type": "sentence_end"},
+    {"word_count": 953, "len_text": 6363, "cut_type": "sentence_end"},
 ]
 
 
diff --git a/cognee/tests/unit/processing/chunks/chunk_by_paragraph_test2.py b/cognee/tests/unit/processing/chunks/chunk_by_paragraph_2_test.py
similarity index 100%
rename from cognee/tests/unit/processing/chunks/chunk_by_paragraph_test2.py
rename to cognee/tests/unit/processing/chunks/chunk_by_paragraph_2_test.py
diff --git a/cognee/tests/unit/processing/chunks/chunk_by_paragraph_test.py b/cognee/tests/unit/processing/chunks/chunk_by_paragraph_test.py
index 28b4b37c3..f8fe00237 100644
--- a/cognee/tests/unit/processing/chunks/chunk_by_paragraph_test.py
+++ b/cognee/tests/unit/processing/chunks/chunk_by_paragraph_test.py
@@ -49,7 +49,7 @@ Third paragraph is cut and is missing the dot at the end""",
 
 def run_chunking_test(test_text, expected_chunks):
     chunks = []
-    for chunk_data in chunk_by_paragraph(test_text, 12, batch_paragraphs=False):
+    for chunk_data in chunk_by_paragraph(test_text, 12, batch_paragraphs=True):
         chunks.append(chunk_data)
 
     assert len(chunks) == 3