Merge pull request #465 from afuetterer/tests

test: restructure tests

Author: chrismattmann

tests/conftest.py

@@ -0,0 +1,9 @@
+from pathlib import Path
+
+import pytest
+
+
+@pytest.fixture
+def test_file_path():
+    return Path(__file__).parent / "files" / "rwservlet.pdf"
+

tests/test_detector.py

@@ -1,17 +1,13 @@
-from pathlib import Path
-
 from tika import detector
 
-TEST_FILE_PATH = Path(__file__).parent / "files" / "rwservlet.pdf"
-
 
-def test_local_binary():
-    with open(TEST_FILE_PATH, "rb") as file_obj:
+def test_local_binary(test_file_path):
+    with open(test_file_path, "rb") as file_obj:
         assert detector.from_file(file_obj) == "application/pdf"
 
 
-def test_local_path():
-    assert detector.from_file(str(TEST_FILE_PATH)) == "application/pdf"
+def test_local_path(test_file_path):
+    assert detector.from_file(str(test_file_path)) == "application/pdf"
 
 
 def test_local_buffer():

tests/test_from_file_service.py

@@ -14,56 +14,59 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 #
-# python -m unittest tika.tests.test_from_file_service
 
-import unittest
 from unittest import mock
 
-import tika.parser
-
-
-class CreateTest(unittest.TestCase):
-    'test different services in from_file parsing: Content, Metadata or both in recursive mode'
-
-    def test_default_service(self):
-        'parse file using default service'
-        result = tika.parser.from_file(
-            'https://boe.es/boe/dias/2019/12/02/pdfs/BOE-A-2019-17288.pdf')
-        self.assertEqual(result['metadata']['Content-Type'],'application/pdf')
-        self.assertIn('AUTORIDADES Y PERSONAL',result['content'])
-    @mock.patch('tika.parser._parse')
-    @mock.patch('tika.parser.parse1')
-    def test_remote_endpoint(self, tika_call_mock, _):
-        result = tika.parser.from_file(
-            'filename', 'http://tika:9998/tika')
-
-        tika_call_mock.assert_called_with(
-            'all', 'filename', 'http://tika:9998/tika', headers=None, config_path=None,
-            requestOptions={})
-    def test_default_service_explicit(self):
-        'parse file using default service explicitly'
-        result = tika.parser.from_file(
-            'https://boe.es/boe/dias/2019/12/02/pdfs/BOE-A-2019-17288.pdf', service='all')
-        self.assertEqual(result['metadata']['Content-Type'],'application/pdf')
-        self.assertIn('AUTORIDADES Y PERSONAL',result['content'])
-    def test_text_service(self):
-        'parse file using the content only service'
-        result = tika.parser.from_file(
-            'https://boe.es/boe/dias/2019/12/02/pdfs/BOE-A-2019-17288.pdf', service='text')
-        self.assertIsNone(result['metadata'])
-        self.assertIn('AUTORIDADES Y PERSONAL',result['content'])
-    def test_meta_service(self):
-        'parse file using the content only service'
-        result = tika.parser.from_file(
-            'https://boe.es/boe/dias/2019/12/02/pdfs/BOE-A-2019-17288.pdf', service='meta')
-        self.assertIsNone(result['content'])
-        self.assertEqual(result['metadata']['Content-Type'],'application/pdf')
-    def test_invalid_service(self):
-        'parse file using an invalid service should perform the default parsing'
-        result = tika.parser.from_file(
-            'https://boe.es/boe/dias/2019/12/02/pdfs/BOE-A-2019-17288.pdf', service='bad')
-        self.assertEqual(result['metadata']['Content-Type'],'application/pdf')
-        self.assertIn('AUTORIDADES Y PERSONAL',result['content'])
-
-if __name__ == '__main__':
-    unittest.main()
+from tika import parser
+
+TEST_PDF_URL = "https://boe.es/boe/dias/2019/12/02/pdfs/BOE-A-2019-17288.pdf"
+
+
+def test_default_service():
+    "parse file using default service"
+    result = parser.from_file(TEST_PDF_URL)
+    assert result["metadata"]["Content-Type"] == "application/pdf"
+    assert "AUTORIDADES Y PERSONAL" in result["content"]
+
+
+@mock.patch("tika.parser._parse")
+@mock.patch("tika.parser.parse1")
+def test_remote_endpoint(tika_call_mock, _):
+    result = parser.from_file("filename", "http://tika:9998/tika")
+
+    tika_call_mock.assert_called_with(
+        "all",
+        "filename",
+        "http://tika:9998/tika",
+        headers=None,
+        config_path=None,
+        requestOptions={},
+    )
+
+
+def test_default_service_explicit():
+    "parse file using default service explicitly"
+    result = parser.from_file(TEST_PDF_URL, service="all")
+    assert result["metadata"]["Content-Type"] == "application/pdf"
+    assert "AUTORIDADES Y PERSONAL" in result["content"]
+
+
+def test_text_service():
+    "parse file using the content only service"
+    result = parser.from_file(TEST_PDF_URL, service="text")
+    assert result["metadata"] is None
+    assert "AUTORIDADES Y PERSONAL" in result["content"]
+
+
+def test_meta_service():
+    "parse file using the content only service"
+    result = parser.from_file(TEST_PDF_URL, service="meta")
+    assert result["content"] is None
+    assert result["metadata"]["Content-Type"] == "application/pdf"
+
+
+def test_invalid_service():
+    "parse file using an invalid service should perform the default parsing"
+    result = parser.from_file(TEST_PDF_URL, service="bad")
+    assert result["metadata"]["Content-Type"] == "application/pdf"
+    assert "AUTORIDADES Y PERSONAL" in result["content"]

tests/test_language.py

@@ -1,17 +1,13 @@
-from pathlib import Path
-
 from tika import language
 
-TEST_FILE_PATH = Path(__file__).parent / "files" / "rwservlet.pdf"
-
 
-def test_local_binary():
-    with open(TEST_FILE_PATH, "rb") as file_obj:
+def test_local_binary(test_file_path):
+    with open(test_file_path, "rb") as file_obj:
         assert language.from_file(file_obj) == "en"
 
 
-def test_local_path():
-    assert language.from_file(str(TEST_FILE_PATH)) == "en"
+def test_local_path(test_file_path):
+    assert language.from_file(str(test_file_path)) == "en"
 
 
 def test_local_buffer():

tests/test_parser.py

@@ -0,0 +1,43 @@
+from http import HTTPStatus
+
+from tika import parser
+
+
+def test_remote_pdf():
+    """parse remote PDF"""
+    assert parser.from_file(
+        "https://upload.wikimedia.org/wikipedia/commons/4/42/Article_feedback_flow_B_-_Thank_editors.pdf")
+
+
+def test_remote_html():
+    """parse remote HTML"""
+    assert parser.from_file("http://nossl.sh")
+
+
+def test_remote_mp3():
+    """parse remote mp3"""
+    assert parser.from_file(
+        "https://archive.org/download/Ainst-Spaceshipdemo.mp3/Ainst-Spaceshipdemo.mp3")
+
+
+def test_remote_jpg():
+    """parse remote jpg"""
+    assert parser.from_file(
+        "https://upload.wikimedia.org/wikipedia/commons/b/b7/X_logo.jpg")
+
+
+def test_local_binary(test_file_path):
+    """parse file binary"""
+    with open(test_file_path, "rb") as file_obj:
+        assert parser.from_file(file_obj)
+
+
+def test_local_buffer():
+    response = parser.from_buffer("Good evening, Dave")
+    assert response["status"] == HTTPStatus.OK
+
+
+def test_local_path(test_file_path):
+    """parse file path"""
+    assert parser.from_file(str(test_file_path))
+

tests/test_pdf.py

@@ -1,10 +1,6 @@
-from pathlib import Path
-
 from tika import pdf
 
-TEST_FILE_PATH = Path(__file__).parent / "files" / "rwservlet.pdf"
-
 
-def test_local_path():
-    text_pages = pdf.text_from_pdf_pages(str(TEST_FILE_PATH))
+def test_local_path(test_file_path):
+    text_pages = pdf.text_from_pdf_pages(str(test_file_path))
     assert isinstance(text_pages, list)

tests/test_tika.py

@@ -14,56 +14,12 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-from http import HTTPStatus
-from pathlib import Path
-
-import tika.parser
 import tika.tika
-
-TEST_FILE_PATH = Path(__file__).parent / "files" / "rwservlet.pdf"
-
-
-def test_remote_pdf():
-    """parse remote PDF"""
-    assert tika.parser.from_file(
-        "https://upload.wikimedia.org/wikipedia/commons/4/42/Article_feedback_flow_B_-_Thank_editors.pdf")
-
-
-def test_remote_html():
-    """parse remote HTML"""
-    assert tika.parser.from_file("http://nossl.sh")
-
-
-def test_remote_mp3():
-    """parse remote mp3"""
-    assert tika.parser.from_file(
-        "https://archive.org/download/Ainst-Spaceshipdemo.mp3/Ainst-Spaceshipdemo.mp3")
-
-
-def test_remote_jpg():
-    """parse remote jpg"""
-    assert tika.parser.from_file(
-        "https://upload.wikimedia.org/wikipedia/commons/b/b7/X_logo.jpg")
-
-
-def test_local_binary():
-    """parse file binary"""
-    with open(TEST_FILE_PATH, "rb") as file_obj:
-        assert tika.parser.from_file(file_obj)
-
-
-def test_local_buffer():
-    response = tika.parser.from_buffer("Good evening, Dave")
-    assert response["status"] == HTTPStatus.OK
-
-
-def test_local_path():
-    """parse file path"""
-    assert tika.parser.from_file(str(TEST_FILE_PATH))
+from tika import parser
 
 
-def test_kill_server():
+def test_kill_server(test_file_path):
     """parse some file then kills server"""
-    with open(TEST_FILE_PATH, "rb") as file_obj:
+    with open(test_file_path, "rb") as file_obj:
         tika.parser.from_file(file_obj)
     assert tika.tika.killServer() is None

tests/test_unpack.py

@@ -1,30 +1,24 @@
-from tempfile import NamedTemporaryFile
-
 from tika import unpack
 
 # Test data
 TEXT_UTF8 = "Hello, world!! 😎 👽"
 TEXT_ASCII = "Hello, world!!"
 
 
-def test_utf8():
+def test_utf8(tmp_path):
     """Test UTF-8 encoding"""
-    with NamedTemporaryFile("w+b", prefix="tika-python", suffix=".txt", dir="/tmp") as f:
-        f.write(TEXT_UTF8.encode("utf8"))
-        f.flush()
-        f.seek(0)
-        parsed = unpack.from_file(f.name)
-        assert parsed["content"].strip() == TEXT_UTF8
+    test_file = tmp_path / "test_utf8.txt"
+    test_file.write_bytes(TEXT_UTF8.encode("utf8"))
+    parsed = unpack.from_file(str(test_file))
+    assert parsed["content"].strip() == TEXT_UTF8
 
 
-def test_ascii():
+def test_ascii(tmp_path):
     """Test ASCII encoding"""
-    with NamedTemporaryFile("w+t", prefix="tika-python", suffix=".txt", dir="/tmp") as f:
-        f.write(TEXT_ASCII)
-        f.flush()
-        f.seek(0)
-        parsed = unpack.from_file(f.name)
-        assert parsed["content"].strip() == TEXT_ASCII
+    test_file = tmp_path / "test_ascii.txt"
+    test_file.write_text(TEXT_ASCII)
+    parsed = unpack.from_file(str(test_file))
+    assert parsed["content"].strip() == TEXT_ASCII
 
 
 def test_from_buffer():