[qa] Add tests covering acquisition of USPTO PDF documents and drawings

CHANGES.rst

@@ -20,6 +20,7 @@ Development
 - [qa] Improve Python test harness
 - [mw] Fix getting PDF documents and drawings from USPTO. Thanks, @aghster!
 - [qa] Add software test infrastructure for data acquisition subsystems
+- [qa] Add tests covering the acquisition of USPTO PDF documents and drawings
 
 
 2019-11-01 0.169.3

tests/access/test_uspto.py

@@ -0,0 +1,113 @@
+# -*- coding: utf-8 -*-
+# (c) 2022 Andreas Motl <andreas.motl@ip-tools.org>
+"""
+Validate PDF document acquisition from USPTO servers.
+"""
+import pytest
+from pyramid.httpexceptions import HTTPNotFound
+
+from patzilla.access.uspto.image import fetch_first_drawing
+from patzilla.access.uspto.pdf import fetch_pdf, document_viewer_url, pdf_index, pdf_url, fetch_url
+from patzilla.util.numbers.common import split_patent_number
+
+
+class TestFetchResourceValid:
+
+    @pytest.mark.slow
+    def test_full_pdf_application(self):
+        # TODO: Find a smaller application document.
+        pdf = fetch_pdf("US2022110447A1")
+        assert pdf.startswith("%PDF")
+
+    @pytest.mark.slow
+    def test_full_pdf_publication(self):
+        # US2548918 has only 240k, which is great for testing.
+        pdf = fetch_pdf("US2548918")
+        assert pdf.startswith("%PDF")
+
+    @pytest.mark.slow
+    def test_first_drawing_application(self):
+        # TODO: Find a smaller application document.
+        drawing = fetch_first_drawing("US2022110447A1")
+        assert drawing.startswith(b"\x49\x49\x2a\x00")
+
+    @pytest.mark.slow
+    def test_first_drawing_publication(self):
+        # US2548918 has only 240k, which is great for testing.
+        drawing = fetch_first_drawing(split_patent_number("US2548918"))
+        assert drawing.startswith(b"\x49\x49\x2a\x00")
+
+
+class TestFetchResourceInvalid:
+
+    @pytest.mark.slow
+    def test_full_pdf_application_notfound(self):
+        with pytest.raises(HTTPNotFound) as ex:
+            fetch_pdf("US0000000000")
+        assert ex.match("Resource at .+ not found")
+
+    @pytest.mark.slow
+    def test_full_pdf_publication_notfound(self):
+        with pytest.raises(HTTPNotFound) as ex:
+            fetch_pdf("US0000000")
+        assert ex.match("Resource at .+ not found")
+
+
+class TestDocumentViewerUrlValid:
+
+    @pytest.mark.slow
+    def test_application_validated(self):
+        assert document_viewer_url("US2022110447A1") == {'origin': 'USPTO', 'location': 'https://pdfaiw.uspto.gov/.aiw?docid=20220110447'}
+
+    @pytest.mark.slow
+    def test_publication_validated(self):
+        assert document_viewer_url("US2548918") == {'origin': 'USPTO', 'location': 'https://pdfpiw.uspto.gov/.piw?docid=02548918'}
+
+    def test_application_unvalidated(self):
+        assert document_viewer_url("US2022110447A1", validate=False) == {'origin': 'USPTO', 'location': 'https://pdfaiw.uspto.gov/.aiw?docid=20220110447'}
+
+    def test_publication_unvalidated(self):
+        assert document_viewer_url("US2548918", validate=False) == {'origin': 'USPTO', 'location': 'https://pdfpiw.uspto.gov/.piw?docid=02548918'}
+
+
+class TestDocumentViewerUrlInvalid:
+
+    @pytest.mark.slow
+    def test_application_validated(self):
+        with pytest.raises(HTTPNotFound) as ex:
+            document_viewer_url("US0000000000")
+        ex.match("Resource at .+ not found")
+
+    @pytest.mark.slow
+    def test_publication_validated(self):
+        with pytest.raises(HTTPNotFound) as ex:
+            document_viewer_url("US0000000")
+        ex.match("Resource at .+ not found")
+
+    def test_application_unvalidated(self):
+        assert document_viewer_url("US0000000000", validate=False) == {'origin': 'USPTO', 'location': 'https://pdfaiw.uspto.gov/.aiw?docid=00000000000'}
+
+    def test_publication_unvalidated(self):
+        assert document_viewer_url("US0000000", validate=False) == {'origin': 'USPTO', 'location': 'https://pdfpiw.uspto.gov/.piw?docid=00000000'}
+
+
+def test_pdf_index_unknown_application(caplog):
+    section_url_map = pdf_index("US2022110447A1", include=-99)
+    assert not section_url_map
+    assert "Unable to compute PDF section map for document US2022110447A1" in caplog.messages
+
+
+def test_pdf_index_unknown_publication(caplog):
+    section_url_map = pdf_index("US2548918", include=-99)
+    assert not section_url_map
+    assert "Unable to compute PDF section map for document US2548918" in caplog.messages
+
+
+def test_pdf_url_invalid():
+    assert pdf_url(None) is None
+
+
+def test_fetch_url_failure():
+    with pytest.raises(HTTPNotFound) as ex:
+        assert fetch_url("https://httpbin.org/status/500") is None
+    ex.match("Accessing resource at .+ failed. status=500, response=")