From 2182369a4def2c98d92f76567cbc3868d32c5b4a Mon Sep 17 00:00:00 2001 From: Martin Thoma Date: Tue, 28 Jun 2022 21:20:27 +0200 Subject: [PATCH] Mention strict=True --- benchmark.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/benchmark.py b/benchmark.py index 54bf63a..0990b10 100644 --- a/benchmark.py +++ b/benchmark.py @@ -128,7 +128,7 @@ def pymupdf_get_text(data: bytes) -> str: with PyMuPDF.open(stream=data, filetype="pdf") as doc: text = "" for page in doc: - text += page.get_text() + text += page.get_text() + "\n" return text @@ -136,7 +136,7 @@ def pypdf2_get_text(data: bytes) -> str: text = "" reader = PyPDF2.PdfFileReader(BytesIO(data)) for page in reader.pages: - text += page.extract_text() + text += page.extract_text() + "\n" return text