From 963b25159a69eb3264cb7179082fe6ffce16126b Mon Sep 17 00:00:00 2001
From: Martin Thoma <info@martin-thoma.de>
Date: Tue, 26 Apr 2022 17:02:57 +0200
Subject: [PATCH] TST: Use external repository for larger/more PDFs for testing
 (#820)

* Use submodule so that the connection is clear. Ensure that Flake8 issues of the submodule don't show up here
* As a first step, just try to get the number of pages from the non-encrypted PDFs
* Create an "external" pytest marker which allows people to deactivate tests that need the submodule
---
 .github/workflows/github-ci.yaml |  4 +++-
 .gitmodules                      |  3 +++
 Tests/test_page.py               | 25 +++++++++++++++++++++++++
 docs/dev/intro.md                | 17 +++++++++++++++++
 pytest.ini                       |  3 ++-
 sample-files                     |  1 +
 6 files changed, 51 insertions(+), 2 deletions(-)
 create mode 100644 .gitmodules
 create mode 160000 sample-files

diff --git a/.github/workflows/github-ci.yaml b/.github/workflows/github-ci.yaml
index 6ed659f4d..7c7260c39 100644
--- a/.github/workflows/github-ci.yaml
+++ b/.github/workflows/github-ci.yaml
@@ -26,6 +26,8 @@ jobs:
     steps:
     - name: Checkout Code
       uses: actions/checkout@v3
+      with:
+        submodules: 'recursive'
     - name: Setup Python
       uses: actions/setup-python@v3
       with:
@@ -46,7 +48,7 @@ jobs:
         pip install .
     - name: Test with flake8
       run: |
-        flake8 . --ignore=E203,W503,W504,E,F403,F405 --exclude build
+        flake8 . --ignore=E203,W503,W504,E,F403,F405 --exclude build,sample-files
       if: matrix.python-version != '2.7'
     - name: Test with pytest
       run: |
diff --git a/.gitmodules b/.gitmodules
new file mode 100644
index 000000000..10cd5293e
--- /dev/null
+++ b/.gitmodules
@@ -0,0 +1,3 @@
+[submodule "sample-files"]
+	path = sample-files
+	url = https://github.com/py-pdf/sample-files
diff --git a/Tests/test_page.py b/Tests/test_page.py
index c5ea98662..69efea831 100644
--- a/Tests/test_page.py
+++ b/Tests/test_page.py
@@ -1,4 +1,5 @@
 import os
+import json
 
 import pytest
 
@@ -7,6 +8,30 @@
 TESTS_ROOT = os.path.abspath(os.path.dirname(__file__))
 PROJECT_ROOT = os.path.dirname(TESTS_ROOT)
 RESOURCE_ROOT = os.path.join(PROJECT_ROOT, "Resources")
+EXTERNAL_ROOT = os.path.join(PROJECT_ROOT, "sample-files")
+
+
+def get_all_sample_files():
+    with open(os.path.join(EXTERNAL_ROOT, "files.json")) as fp:
+        data = fp.read()
+    meta = json.loads(data)
+    return meta
+
+
+all_files_meta = get_all_sample_files()
+
+
+@pytest.mark.external
+@pytest.mark.parametrize(
+    "meta",
+    [m for m in all_files_meta["data"] if not m["encrypted"]],
+    ids=[m["path"] for m in all_files_meta["data"] if not m["encrypted"]],
+)
+def test_read(meta):
+    pdf_path = os.path.join(EXTERNAL_ROOT, meta["path"])
+    reader = PdfFileReader(pdf_path)
+    reader.pages[0]
+    assert len(reader.pages) == meta["pages"]
 
 
 @pytest.mark.parametrize(
diff --git a/docs/dev/intro.md b/docs/dev/intro.md
index 627b0a57c..c19a06067 100644
--- a/docs/dev/intro.md
+++ b/docs/dev/intro.md
@@ -15,6 +15,23 @@ pip install -r requirements/dev.txt
 pytest .
 ```
 
+We have the following pytest markers defined:
+
+* `no_py27`: Flag for tests that fail under Python 2.7 only
+* `external`: Tests which use files from [the `sample-files` git submodule](https://github.com/py-pdf/sample-files)
+
+You can locally choose not to run those via `pytest -m "not external"`.
+
+## The sample-files git submodule
+The reason for having the submodule `sample-files` is that we want to keep
+the size of the PyPDF2 repository small while we also want to have an extensive
+test suite. Those two goals contradict each other.
+
+The `Resources` folder should contain a select set of core examples that cover
+most cases we typically want to test for. The `sample-files` might cover a lot
+more edge cases, the behavior we get when file sizes get bigger, different
+PDF producers.
+
 ## Tools: git and pre-commit
 
 Git is a command line application for version control. If you don't know it,
diff --git a/pytest.ini b/pytest.ini
index c7afa9968..2b994a831 100644
--- a/pytest.ini
+++ b/pytest.ini
@@ -1,3 +1,4 @@
 [pytest]
 markers =
-    no_py27: Flag for tests that fail under Python 2.7 only
\ No newline at end of file
+    no_py27: Flag for tests that fail under Python 2.7 only
+    external: Tests which use files from https://github.com/py-pdf/sample-files
diff --git a/sample-files b/sample-files
new file mode 160000
index 000000000..6e3a1bb2c
--- /dev/null
+++ b/sample-files
@@ -0,0 +1 @@
+Subproject commit 6e3a1bb2c72eaa3406f5e596479953950f91152c