TST: Set up reusable pytest fixtures

tests/bench.py

@@ -19,7 +19,6 @@
 TESTS_ROOT = Path(__file__).parent.resolve()
 PROJECT_ROOT = TESTS_ROOT.parent
 RESOURCE_ROOT = PROJECT_ROOT / "resources"
-SAMPLE_ROOT = PROJECT_ROOT / "sample-files"
 
 
 def page_ops(pdf_path, password):
@@ -140,8 +139,8 @@ def text_extraction(pdf_path):
     return text
 
 
-def test_text_extraction(benchmark):
-    file_path = SAMPLE_ROOT / "009-pdflatex-geotopo/GeoTopo.pdf"
+def test_text_extraction(benchmark, sample_files_dir):
+    file_path = sample_files_dir / "009-pdflatex-geotopo/GeoTopo.pdf"
     benchmark(text_extraction, file_path)
 
 

tests/conftest.py

@@ -5,9 +5,11 @@
 
 import pytest
 
+from pypdf import PdfReader, PdfWriter
+from pypdf._page import PageObject
+
 TESTS_ROOT = Path(__file__).parent.resolve()
 PROJECT_ROOT = TESTS_ROOT.parent
-RESOURCE_ROOT = PROJECT_ROOT / "resources"
 
 
 @pytest.fixture(scope="session")
@@ -18,3 +20,39 @@ def pdf_file_path(tmp_path_factory):
 @pytest.fixture(scope="session")
 def txt_file_path(tmp_path_factory):
     return tmp_path_factory.mktemp("pypdf-data") / f"{uuid.uuid4()}.txt"
+
+
+# Reusable PDF fixtures
+@pytest.fixture
+def crazyones_pdf_page_one(crazyones_pdf_reader) -> PageObject:
+    return crazyones_pdf_reader.pages[0]
+
+
+@pytest.fixture
+def crazyones_pdf_path(resources_dir) -> Path:
+    return resources_dir / "crazyones.pdf"
+
+
+@pytest.fixture
+def crazyones_pdf_reader(crazyones_pdf_path) -> PdfReader:
+    return PdfReader(crazyones_pdf_path)
+
+
+@pytest.fixture
+def crazyones_pdf_writer(crazyones_pdf_path) -> PdfWriter:
+    return PdfWriter(crazyones_pdf_path)
+
+
+@pytest.fixture
+def project_dir() -> Path:
+    return PROJECT_ROOT
+
+
+@pytest.fixture
+def resources_dir(project_dir) -> Path:
+    return project_dir / "resources"
+
+
+@pytest.fixture
+def sample_files_dir(project_dir) -> Path:
+    return project_dir / "sample-files"

tests/generic/test_files.py

@@ -3,7 +3,6 @@
 import shutil
 import subprocess
 from io import BytesIO
-from pathlib import Path
 
 import pytest
 
@@ -24,16 +23,13 @@
 )
 from tests import get_data_from_url
 
-TESTS_ROOT = Path(__file__).parent.parent.resolve()
-PROJECT_ROOT = TESTS_ROOT.parent
-SAMPLE_ROOT = PROJECT_ROOT / "sample-files"
-
 PDFATTACH_BINARY = shutil.which("pdfattach")
 
 
+@pytest.mark.samples
 @pytest.mark.skipif(PDFATTACH_BINARY is None, reason="Requires poppler-utils")
-def test_embedded_file__basic(tmpdir):
-    clean_path = SAMPLE_ROOT / "002-trivial-libre-office-writer" / "002-trivial-libre-office-writer.pdf"
+def test_embedded_file__basic(tmpdir, sample_files_dir):
+    clean_path = sample_files_dir / "002-trivial-libre-office-writer" / "002-trivial-libre-office-writer.pdf"
     attached_path = tmpdir / "attached.pdf"
     file_path = tmpdir / "test.txt"
     file_path.write_binary(b"Hello World\n")

tests/test_annotations.py

@@ -24,15 +24,10 @@
 
 from . import get_data_from_url
 
-TESTS_ROOT = Path(__file__).parent.resolve()
-PROJECT_ROOT = TESTS_ROOT.parent
-RESOURCE_ROOT = PROJECT_ROOT / "resources"
 
-
-def test_ellipse(pdf_file_path):
+def test_ellipse(pdf_file_path, crazyones_pdf_reader):
     # Arrange
-    pdf_path = RESOURCE_ROOT / "crazyones.pdf"
-    reader = PdfReader(pdf_path)
+    reader = crazyones_pdf_reader
     page = reader.pages[0]
     writer = PdfWriter()
     writer.add_page(page)
@@ -49,9 +44,9 @@ def test_ellipse(pdf_file_path):
         writer.write(fp)
 
 
-def test_text(pdf_file_path):
+def test_text(pdf_file_path, resources_dir):
     # Arrange
-    pdf_path = RESOURCE_ROOT / "outline-without-title.pdf"
+    pdf_path = resources_dir / "outline-without-title.pdf"
     reader = PdfReader(pdf_path)
     page = reader.pages[0]
     writer = PdfWriter()
@@ -70,10 +65,9 @@ def test_text(pdf_file_path):
         writer.write(fp)
 
 
-def test_free_text(pdf_file_path):
+def test_free_text(pdf_file_path, crazyones_pdf_reader):
     # Arrange
-    pdf_path = RESOURCE_ROOT / "crazyones.pdf"
-    reader = PdfReader(pdf_path)
+    reader = crazyones_pdf_reader
     page = reader.pages[0]
     writer = PdfWriter()
     writer.add_page(page)
@@ -136,13 +130,10 @@ def test_annotation_dictionary():
     assert a.flags == 123
 
 
-def test_polygon(pdf_file_path):
+def test_polygon(pdf_file_path, crazyones_pdf_page_one):
     # Arrange
-    pdf_path = RESOURCE_ROOT / "crazyones.pdf"
-    reader = PdfReader(pdf_path)
-    page = reader.pages[0]
     writer = PdfWriter()
-    writer.add_page(page)
+    writer.add_page(crazyones_pdf_page_one)
 
     with pytest.raises(ValueError):
         Polygon(
@@ -159,13 +150,10 @@ def test_polygon(pdf_file_path):
         writer.write(fp)
 
 
-def test_polyline(pdf_file_path):
+def test_polyline(pdf_file_path, crazyones_pdf_page_one):
     # Arrange
-    pdf_path = RESOURCE_ROOT / "crazyones.pdf"
-    reader = PdfReader(pdf_path)
-    page = reader.pages[0]
     writer = PdfWriter()
-    writer.add_page(page)
+    writer.add_page(crazyones_pdf_page_one)
 
     with pytest.raises(
             ValueError,
@@ -185,13 +173,10 @@ def test_polyline(pdf_file_path):
         writer.write(fp)
 
 
-def test_line(pdf_file_path):
+def test_line(pdf_file_path, crazyones_pdf_page_one):
     # Arrange
-    pdf_path = RESOURCE_ROOT / "crazyones.pdf"
-    reader = PdfReader(pdf_path)
-    page = reader.pages[0]
     writer = PdfWriter()
-    writer.add_page(page)
+    writer.add_page(crazyones_pdf_page_one)
 
     # Act
     line_annotation = Line(
@@ -207,13 +192,10 @@ def test_line(pdf_file_path):
         writer.write(fp)
 
 
-def test_rectangle(pdf_file_path):
+def test_rectangle(pdf_file_path, crazyones_pdf_page_one):
     # Arrange
-    pdf_path = RESOURCE_ROOT / "crazyones.pdf"
-    reader = PdfReader(pdf_path)
-    page = reader.pages[0]
     writer = PdfWriter()
-    writer.add_page(page)
+    writer.add_page(crazyones_pdf_page_one)
 
     # Act
     square_annotation = Rectangle(
@@ -229,11 +211,9 @@ def test_rectangle(pdf_file_path):
         writer.write(fp)
 
 
-def test_highlight(pdf_file_path):
+def test_highlight(pdf_file_path, crazyones_pdf_page_one):
     # Arrange
-    pdf_path = RESOURCE_ROOT / "crazyones.pdf"
-    reader = PdfReader(pdf_path)
-    page = reader.pages[0]
+    page = crazyones_pdf_page_one
     writer = PdfWriter()
     writer.add_page(page)
 
@@ -293,9 +273,9 @@ def test_highlight(pdf_file_path):
         writer.write(fp)
 
 
-def test_link(pdf_file_path):
+def test_link(pdf_file_path, resources_dir):
     # Arrange
-    pdf_path = RESOURCE_ROOT / "outline-without-title.pdf"
+    pdf_path = resources_dir / "outline-without-title.pdf"
     reader = PdfReader(pdf_path)
     page = reader.pages[0]
     writer = PdfWriter()
@@ -340,9 +320,9 @@ def test_link(pdf_file_path):
         writer.write(fp)
 
 
-def test_popup(caplog):
+def test_popup(caplog, resources_dir):
     # Arrange
-    pdf_path = RESOURCE_ROOT / "outline-without-title.pdf"
+    pdf_path = resources_dir / "outline-without-title.pdf"
     reader = PdfReader(pdf_path)
     page = reader.pages[0]
     writer = PdfWriter()

tests/test_cmap.py

@@ -1,21 +1,16 @@
 """Test the pypdf_cmap module."""
 from io import BytesIO
-from pathlib import Path
 
 import pytest
 
-from pypdf import PdfReader, PdfWriter
+from pypdf import PdfReader
 from pypdf._cmap import get_encoding, parse_bfchar
 from pypdf._codecs import charset_encoding
 from pypdf._font import Font
 from pypdf.generic import ArrayObject, DictionaryObject, IndirectObject, NameObject, NullObject
 
 from . import get_data_from_url
 
-TESTS_ROOT = Path(__file__).parent.resolve()
-PROJECT_ROOT = TESTS_ROOT.parent
-RESOURCE_ROOT = PROJECT_ROOT / "resources"
-
 
 @pytest.mark.enable_socket
 @pytest.mark.slow
@@ -218,25 +213,22 @@ def test_eten_b5():
     reader.pages[0].extract_text().startswith("1/7 \n富邦新終身壽險")
 
 
-def test_missing_entries_in_cmap():
+def test_missing_entries_in_cmap(crazyones_pdf_reader):
     """
     Issue #2702: this issue is observed on damaged pdfs
     use of this file in test has been discarded as too slow/long
     we will create the same error from crazyones
     """
-    pdf_path = RESOURCE_ROOT / "crazyones.pdf"
-    reader = PdfReader(pdf_path)
-    p = reader.pages[0]
+    p = crazyones_pdf_reader.pages[0]
     p["/Resources"]["/Font"]["/F1"][NameObject("/ToUnicode")] = IndirectObject(
-        99999999, 0, reader
+        99999999, 0, crazyones_pdf_reader
     )
     p.extract_text()
 
 
-def test_null_missing_width():
+def test_null_missing_width(crazyones_pdf_writer):
     """For coverage of #2792"""
-    writer = PdfWriter(RESOURCE_ROOT / "crazyones.pdf")
-    page = writer.pages[0]
+    page = crazyones_pdf_writer.pages[0]
     ft = page["/Resources"]["/Font"]["/F1"]
     ft[NameObject("/Widths")] = ArrayObject()
     ft["/FontDescriptor"][NameObject("/MissingWidth")] = NullObject()

tests/test_codecs.py

@@ -1,6 +1,5 @@
 """Test LZW-related code."""
 from io import BytesIO
-from pathlib import Path
 
 import pytest
 
@@ -10,10 +9,6 @@
 
 from . import get_data_from_url
 
-TESTS_ROOT = Path(__file__).parent.resolve()
-PROJECT_ROOT = TESTS_ROOT.parent
-RESOURCE_ROOT = PROJECT_ROOT / "resources"
-
 test_cases = [
     pytest.param(b"", id="Empty input"),
     pytest.param(b"A", id="Single character"),
@@ -68,8 +63,8 @@ def test_decode_lzw(encoded, expected_decoded):
     assert actual_decoded == expected_decoded
 
 
-def test_lzw_decoder_table_overflow(caplog):
-    path = RESOURCE_ROOT / "lzw_decoder_table_overflow.bin"
+def test_lzw_decoder_table_overflow(caplog, resources_dir):
+    path = resources_dir / "lzw_decoder_table_overflow.bin"
     codec = LzwCodec()
     assert codec.decode(path.read_bytes()).startswith(
         b'0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ!"#$%&\'()*+,-./:;<=>?@'

tests/test_doc_common.py

@@ -5,7 +5,6 @@
 import subprocess
 from io import BytesIO
 from operator import itemgetter
-from pathlib import Path
 from unittest import mock
 
 import pytest
@@ -15,18 +14,14 @@
 from pypdf.generic import EmbeddedFile, NameObject, NullObject, TextStringObject, ViewerPreferences
 from tests import get_data_from_url
 
-TESTS_ROOT = Path(__file__).parent.resolve()
-PROJECT_ROOT = TESTS_ROOT.parent
-SAMPLE_ROOT = PROJECT_ROOT / "sample-files"
-RESOURCES_ROOT = PROJECT_ROOT / "resources"
-
 PDFATTACH_BINARY = shutil.which("pdfattach")
 
 
+@pytest.mark.samples
 @pytest.mark.skipif(PDFATTACH_BINARY is None, reason="Requires poppler-utils")
-def test_attachments(tmpdir):
+def test_attachments(tmpdir, sample_files_dir):
     # No attachments.
-    clean_path = SAMPLE_ROOT / "002-trivial-libre-office-writer" / "002-trivial-libre-office-writer.pdf"
+    clean_path = sample_files_dir / "002-trivial-libre-office-writer" / "002-trivial-libre-office-writer.pdf"
     with PdfReader(clean_path) as pdf:
         assert pdf._list_attachments() == []
         assert list(pdf.attachment_list) == []
@@ -171,8 +166,8 @@ def test_byte_encoded_named_destinations():
     }
 
 
-def test_viewer_preferences__indirect_reference():
-    input_path = RESOURCES_ROOT / "git.pdf"
+def test_viewer_preferences__indirect_reference(resources_dir):
+    input_path = resources_dir / "git.pdf"
     reader = PdfReader(input_path)
     assert (0, 24) not in reader.resolved_objects
     viewer_preferences = reader.viewer_preferences
@@ -452,10 +447,8 @@ def test_outline__issue3462():
     ]
 
 
-def test_flatten__cyclic_references():
-    path = RESOURCES_ROOT / "crazyones.pdf"
-
-    reader = PdfReader(path)
+def test_flatten__cyclic_references(crazyones_pdf_reader):
+    reader = crazyones_pdf_reader
     assert len(reader.pages) == 1
     reader._flatten()