From 799630daba40fe434406bd59083e8fe736178d1e Mon Sep 17 00:00:00 2001
From: pubpub-zz <4083478+pubpub-zz@users.noreply.github.com>
Date: Thu, 15 Aug 2024 14:28:51 +0200
Subject: [PATCH] BUG: Fix sheared image (#2801)

Closes #2411.
---
 pypdf/_xobj_image_helpers.py |  2 +-
 tests/test_images.py         | 11 +++++++++++
 tests/test_workflows.py      |  2 +-
 3 files changed, 13 insertions(+), 2 deletions(-)

diff --git a/pypdf/_xobj_image_helpers.py b/pypdf/_xobj_image_helpers.py
index 7a3f40d95..d870b1589 100644
--- a/pypdf/_xobj_image_helpers.py
+++ b/pypdf/_xobj_image_helpers.py
@@ -122,7 +122,7 @@ def bits2byte(data: bytes, size: Tuple[int, int], bits: int) -> bytes:
     by = 0
     bit = 8 - bits
     for y in range(size[1]):
-        if (bit != 0) and (bit != 8 - bits):
+        if bit != 8 - bits:
             by += 1
             bit = 8 - bits
         for x in range(size[0]):
diff --git a/tests/test_images.py b/tests/test_images.py
index 5955bf47c..5fd7d0968 100644
--- a/tests/test_images.py
+++ b/tests/test_images.py
@@ -462,3 +462,14 @@ def test_extract_image_from_object(caplog):
         co = reader.pages[0].get_contents()
         co.decode_as_image()
     assert "does not seem to be an Image" in caplog.text
+
+
+@pytest.mark.enable_socket()
+def test_4bits_images(caplog):
+    url = "https://github.com/user-attachments/files/16624406/tt.pdf"
+    name = "iss2411.pdf"
+    reader = PdfReader(BytesIO(get_data_from_url(url, name=name)))
+    url = "https://github.com/user-attachments/assets/53058564-9a28-4e4a-818f-a6528013d7dc"
+    name = "iss2411.png"
+    img = Image.open(BytesIO(get_data_from_url(url, name=name)))
+    assert image_similarity(reader.pages[0].images[1].image, img) == 1.0
diff --git a/tests/test_workflows.py b/tests/test_workflows.py
index 4407b8fd5..1125222fc 100644
--- a/tests/test_workflows.py
+++ b/tests/test_workflows.py
@@ -412,7 +412,7 @@ def test_get_metadata(url, name, expected_metadata):
     ("url", "name", "strict", "exception"),
     [
         (
-            "https://corpora.tika.apache.org/base/docs/govdocs1/938/938702.pdf",
+            "https://github.com/user-attachments/files/16624503/tika-938702.pdf",
             "tika-938702.pdf",
             False,
             None,  # iss #1090 is now fixed