paradizelost/paperless-ngx
1
0
Fork 0
mirror of https://github.com/paperless-ngx/paperless-ngx.git synced 2025-04-25 10:49:30 -05:00
Code Issues Packages Projects Releases Wiki Activity

add unittest for transform_inline_html

Browse Source
This commit is contained in:
phail 2022-10-18 23:48:07 +02:00
parent fda844f64c
commit e384bd78c5
4 changed files with 49 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
src/paperless_mail/parsers.py
View File

@ -296,22 +296,26 @@ class MailDocumentParser(DocumentParser):
return response.content
def transform_inline_html(self, orig_html, attachments):
@staticmethod
def transform_inline_html(html, attachments):
def clean_html_script(text: str):
text = text.replace("<script", "<div hidden ")
text = text.replace("</script", "</div")
compiled_open = re.compile(re.escape("<script"), re.IGNORECASE)
text = compiled_open.sub("<div hidden ", text)
compiled_close = re.compile(re.escape("</script"), re.IGNORECASE)
text = compiled_close.sub("</div", text)
return text
orig_html = clean_html_script(orig_html)
html_clean = clean_html_script(html)
files = []
for a in attachments:
name_cid = "cid:" + a.content_id
name_clean = "".join(e for e in name_cid if e.isalnum())
files.append((name_clean, BytesIO(a.payload)))
orig_html = orig_html.replace(name_cid, name_clean)
html_clean = html_clean.replace(name_cid, name_clean)
files.append(("index.html", StringIO(orig_html)))
files.append(("index.html", StringIO(html_clean)))
return files

15
src/paperless_mail/tests/samples/sample.html Normal file
View File

@ -0,0 +1,15 @@
<html>
<head>
<meta http-equiv="content-type" content="text/html; charset=UTF-8">
</head>
<body>
<p>Some Text</p>
<p><img src="cid:part1.pNdUSz0s.D3NqVtPg@example.de" alt=""></p>
<p>and an embedded image.<br>
</p>
<p id="changeme">Paragraph unchanged.</p>
<scRipt>
document.getElementById("changeme").innerHTML = "Paragraph changed via Java Script.";
</script>
</body>
</html>

BIN
src/paperless_mail/tests/samples/sample.png Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 6.9 KiB

24
src/paperless_mail/tests/test_eml.py
View File

@ -282,3 +282,27 @@ class TestParser(TestCase):
# Check successful parsing
parsed = parser.tika_parse(html)
self.assertEqual(expected_text, parsed)
def test_transform_inline_html(self):
class MailAttachmentMock:
def __init__(self, payload, content_id):
self.payload = payload
self.content_id = content_id
parser = MailDocumentParser(None)
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 = parser.transform_inline_html(html, attachments)
resulting_html = result[-1][1].read()
self.assertTrue(result[-1][0] == "index.html")
self.assertTrue(result[0][0] in resulting_html)
self.assertFalse("<script" in resulting_html.lower())