added test case and the suggested changes

haystack/components/preprocessors/document_splitter.py

@@ -21,7 +21,7 @@ def __init__(
  ):
  """
  :param split_by: The unit by which the document should be split. Choose from "word" for splitting by " ",
- "sentence" for splitting by ".", "page" for splittling by "\f" or "passage" for splitting by "\\n\\n".
+ "sentence" for splitting by ".", "page" for splitting by "\f" or "passage" for splitting by "\\n\\n".
  :param split_length: The maximum number of units in each split.
  :param split_overlap: The number of units that each split should overlap.
  """
@@ -74,7 +74,7 @@ def _split_into_units(self, text: str, split_by: Literal["word", "sentence", "pa
  split_at = " "
  else:
  raise NotImplementedError(
- "DocumentSplitter only supports 'page', 'passage', 'sentence' or 'word' split_by options."
+ "DocumentSplitter only supports 'word', 'sentence', 'passage' or 'page' split_by options."
  )
  units = text.split(split_at)
  # Add the delimiter back to all units except the last one

test/components/preprocessors/test_document_splitter.py

@@ -94,6 +94,20 @@ def test_split_by_passage(self):
  assert result["documents"][1].content == "And there is a third sentence.\n\n"
  assert result["documents"][2].content == " And another passage."
 
+ def test_split_by_page(self):
+ splitter = DocumentSplitter(split_by="page", split_length=1)
+ result = splitter.run(
+ documents=[
+ Document(
+ content="This is a text with some words. There is a second sentence.\f And there is a third sentence.\f And another passage."
+ )
+ ]
+ )
+ assert len(result["documents"]) == 3
+ assert result["documents"][0].content == "This is a text with some words. There is a second sentence.\x0c"
+ assert result["documents"][1].content == " And there is a third sentence.\x0c"
+ assert result["documents"][2].content == " And another passage."
+
  def test_split_by_word_with_overlap(self):
  splitter = DocumentSplitter(split_by="word", split_length=10, split_overlap=2)
  result = splitter.run(