paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-02 13:45:10 -05:00
Code Issues Packages Projects Releases Wiki Activity

add conditions to unittests

Browse Source
This commit is contained in:
phail 2022-11-12 15:48:30 +01:00
parent acd3832417
commit b01cbc9aa0
3 changed files with 123 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

BIN
src/paperless_mail/tests/samples/sample.html.pdf.webp Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 2.8 KiB

88
src/paperless_mail/tests/test_parsers.py
View File

@ -268,7 +268,7 @@ class TestParser(TestCase):
@mock.patch("documents.loggers.LoggingMixin.log") # Disable log output
def test_tika_parse(self, m):
html = '<html><head><meta http-equiv="content-type" content="text/html; charset=UTF-8"></head><body><p>Some Text</p></body></html>'
expected_text = "\n\n\n\n\n\n\n\n\nSome Text\n"
expected_text = "Some Text"
tika_server_original = self.parser.tika_server
@ -285,7 +285,7 @@ class TestParser(TestCase):
# Check successful parsing
parsed = self.parser.tika_parse(html)
self.assertEqual(expected_text, parsed)
self.assertEqual(expected_text, parsed.strip())
@mock.patch("paperless_mail.parsers.MailDocumentParser.generate_pdf_from_mail")
@mock.patch("paperless_mail.parsers.MailDocumentParser.generate_pdf_from_html")
@ -355,19 +355,46 @@ class TestParser(TestCase):
) as html_expected_handle:
self.assertHTMLEqual(html_expected_handle.read(), html_handle.read())
@mock.patch("documents.loggers.LoggingMixin.log") # Disable log output
def test_generate_pdf_from_mail(self, m):
@mock.patch("paperless_mail.parsers.requests.post")
@mock.patch("paperless_mail.parsers.MailDocumentParser.mail_to_html")
def test_generate_pdf_from_mail(
self,
mock_mail_to_html: mock.MagicMock,
mock_post: mock.MagicMock,
):
mock_response = mock.MagicMock()
mock_response.content = b"Content"
mock_post.return_value = mock_response
mock_mail_to_html.return_value = "Testresponse"
mail = self.parser.get_parsed(os.path.join(self.SAMPLE_FILES, "html.eml"))
pdf_path = os.path.join(self.parser.tempdir, "test_generate_pdf_from_mail.pdf")
retval = self.parser.generate_pdf_from_mail(mail)
self.assertEqual(b"Content", retval)
with open(pdf_path, "wb") as file:
file.write(self.parser.generate_pdf_from_mail(mail))
file.close()
mock_generate_pdf_from_mail.assert_called_once_with(
self.parser.get_parsed(None),
)
mock_generate_pdf_from_html.assert_called_once_with(
self.parser.get_parsed(None).html,
self.parser.get_parsed(None).attachments,
)
self.assertEqual(
self.parser.gotenberg_server + "/forms/pdfengines/merge",
mock_post.call_args.args[0],
)
self.assertEqual({}, mock_post.call_args.kwargs["headers"])
self.assertEqual(
b"Mail Return",
mock_post.call_args.kwargs["files"]["1_mail.pdf"][1].read(),
)
self.assertEqual(
b"HTML Return",
mock_post.call_args.kwargs["files"]["2_html.pdf"][1].read(),
)
extracted = extract_text(pdf_path)
expected = "From Name <someone@example.de>\n\n2022-10-15 09:23\n\nSubject HTML Message\n\nTo someone@example.de\n\nAttachments IntM6gnXFm00FEV5.png (6.89 KiB), 600+kbfile.txt (0.59 MiB)\n\nSome Text \n\nand an embedded image.\n\n\x0c"
self.assertEqual(expected, extracted)
mock_response.raise_for_status.assert_called_once()
def test_transform_inline_html(self):
class MailAttachmentMock:
@ -391,13 +418,18 @@ class TestParser(TestCase):
self.assertTrue(result[0][0] in resulting_html)
self.assertFalse("<script" in resulting_html.lower())
@mock.patch("paperless_mail.parsers.requests.post")
@mock.patch("documents.loggers.LoggingMixin.log") # Disable log output
def test_generate_pdf_from_html(self, m):
def test_generate_pdf_from_html(self, m, mock_post: mock.MagicMock):
class MailAttachmentMock:
def __init__(self, payload, content_id):
self.payload = payload
self.content_id = content_id
mock_response = mock.MagicMock()
mock_response.content = b"Content"
mock_post.return_value = mock_response
result = None
with open(os.path.join(self.SAMPLE_FILES, "sample.html")) as html_file:
@ -409,12 +441,30 @@ class TestParser(TestCase):
]
result = self.parser.generate_pdf_from_html(html, attachments)
pdf_path = os.path.join(self.parser.tempdir, "test_generate_pdf_from_html.pdf")
self.assertEqual(
self.parser.gotenberg_server + "/forms/chromium/convert/html",
mock_post.call_args.args[0],
)
self.assertEqual({}, mock_post.call_args.kwargs["headers"])
self.assertEqual(
{
"marginTop": "0.1",
"marginBottom": "0.1",
"marginLeft": "0.1",
"marginRight": "0.1",
"paperWidth": "8.27",
"paperHeight": "11.7",
"scale": "1.0",
},
mock_post.call_args.kwargs["data"],
)
with open(pdf_path, "wb") as file:
file.write(result)
file.close()
# read to assert it is a file like object.
mock_post.call_args.kwargs["files"]["cidpart1pNdUSz0sD3NqVtPgexamplede"][
1
].read()
mock_post.call_args.kwargs["files"]["index.html"][1].read()
extracted = extract_text(pdf_path)
expected = "Some Text\n\n This image should not be shown.\n\nand an embedded image.\n\nParagraph unchanged.\n\n\x0c"
self.assertEqual(expected, extracted)
mock_response.raise_for_status.assert_called_once()
self.assertEqual(b"Content", result)

65
src/paperless_mail/tests/test_parsers_live.py
View File

@ -62,7 +62,7 @@ class TestParserLive(TestCase):
@mock.patch("documents.loggers.LoggingMixin.log") # Disable log output
def test_tika_parse(self, m):
html = '<html><head><meta http-equiv="content-type" content="text/html; charset=UTF-8"></head><body><p>Some Text</p></body></html>'
expected_text = "\n\n\n\n\n\n\n\n\nSome Text\n"
expected_text = "Some Text"
tika_server_original = self.parser.tika_server
@ -79,7 +79,7 @@ class TestParserLive(TestCase):
# Check successful parsing
parsed = self.parser.tika_parse(html)
self.assertEqual(expected_text, parsed)
self.assertEqual(expected_text, parsed.strip())
@pytest.mark.skipif(
"GOTENBERG_LIVE" not in os.environ,
@ -124,7 +124,10 @@ class TestParserLive(TestCase):
file.write(self.parser.generate_pdf_from_mail(mail))
file.close()
converted = os.path.join(parser.tempdir, "test_generate_pdf_from_mail.webp")
converted = os.path.join(
self.parser.tempdir,
"test_generate_pdf_from_mail.webp",
)
run_convert(
density=300,
scale="500x5000>",
@ -149,14 +152,12 @@ class TestParserLive(TestCase):
f"PDF looks different. Check if {converted} looks weird.",
)
# Only run if convert is available
@pytest.mark.skipif(
"PAPERLESS_TEST_SKIP_CONVERT" in os.environ,
reason="PAPERLESS_TEST_SKIP_CONVERT set, skipping Test",
"GOTENBERG_LIVE" not in os.environ,
reason="No gotenberg server",
)
@mock.patch("documents.loggers.LoggingMixin.log") # Disable log output
def test_generate_pdf_from_html(self, m):
# TODO
def test_generate_pdf_from_html_no_convert(self, m):
class MailAttachmentMock:
def __init__(self, payload, content_id):
self.payload = payload
@ -179,7 +180,44 @@ class TestParserLive(TestCase):
file.write(result)
file.close()
converted = os.path.join(parser.tempdir, "test_generate_pdf_from_html.webp")
extracted = extract_text(pdf_path)
expected = "Some Text\n\n This image should not be shown.\n\nand an embedded image.\n\nParagraph unchanged.\n\n\x0c"
self.assertEqual(expected, extracted)
@pytest.mark.skipif(
"GOTENBERG_LIVE" not in os.environ,
reason="No gotenberg server",
)
# Only run if convert is available
@pytest.mark.skipif(
"PAPERLESS_TEST_SKIP_CONVERT" in os.environ,
reason="PAPERLESS_TEST_SKIP_CONVERT set, skipping Test",
)
@mock.patch("documents.loggers.LoggingMixin.log") # Disable log output
def test_generate_pdf_from_html(self, m):
class MailAttachmentMock:
def __init__(self, payload, content_id):
self.payload = payload
self.content_id = content_id
result = None
with open(os.path.join(self.SAMPLE_FILES, "sample.html")) as html_file:
with open(os.path.join(self.SAMPLE_FILES, "sample.png"), "rb") as png_file:
html = html_file.read()
png = png_file.read()
attachments = [
MailAttachmentMock(png, "part1.pNdUSz0s.D3NqVtPg@example.de"),
]
result = self.parser.generate_pdf_from_html(html, attachments)
pdf_path = os.path.join(self.parser.tempdir, "sample.html.pdf")
with open(pdf_path, "wb") as file:
file.write(result)
file.close()
converted = os.path.join(self.parser.tempdir, "sample.html.pdf.webp")
run_convert(
density=300,
scale="500x5000>",
@ -195,9 +233,10 @@ class TestParserLive(TestCase):
thumb_hash = self.hashfile(converted)
# The created pdf is not reproducible. But the converted image should always look the same.
expected_hash = (
"267d61f0ab8f128a037002a424b2cb4bfe18a81e17f0b70f15d241688ed47d1a"
expected_hash = self.hashfile(
os.path.join(self.SAMPLE_FILES, "sample.html.pdf.webp"),
)
self.assertEqual(
thumb_hash,
expected_hash,
@ -206,6 +245,10 @@ class TestParserLive(TestCase):
)
@staticmethod
@pytest.mark.skipif(
"GOTENBERG_LIVE" not in os.environ,
reason="No gotenberg server",
)
def test_is_online_image_still_available():
"""
A public image is used in the html sample file. We have no control