Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Derive "safeHtml" from all "bodyHtml" values #3168

Merged
merged 2 commits into from
Jul 13, 2023
Merged

Derive "safeHtml" from all "bodyHtml" values #3168

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b837fea
Derive "safeHtml" from all "bodyHtml" values
tillprochaska Jul 9, 2023
694f4de
Bump followthemoney to 3.4.4
tillprochaska Jul 12, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
41 changes: 41 additions & 0 deletions aleph/tests/test_entities_api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -125,6 +125,47 @@ def test_view_bookmarked(self):
res = self.client.get(url, headers=headers)
assert res.json["bookmarked"], res.json

def test_view_sanitize_html(self):
data = {
"schema": "HyperText",
"properties": {
"bodyHtml": "<style>body { color: red; }</style><p>Hello World!</p><script>alert('Ooops')</script>",
},
}

entity = self.create_entity(data, self.col)
index_entity(entity)

_, headers = self.login(is_admin=True)
url = f"/api/2/entities/{entity.id}"
res = self.client.get(url, headers=headers)

actual = res.json["safeHtml"]
expected = ["<html><body><div><p>Hello World!</p></div></body></html>"]
assert actual == expected, actual

def test_view_sanitize_html_multi_value(self):
data = {
"schema": "Email",
"properties": {
"bodyHtml": ["This is part 1.", "This is part 2."],
},
}

entity = self.create_entity(data, self.col)
index_entity(entity)

_, headers = self.login(is_admin=True)
url = f"/api/2/entities/{entity.id}"
res = self.client.get(url, headers=headers)

actual = res.json["safeHtml"]
expected = [
"<html><body><p>This is part 1.</p></body></html>",
"<html><body><p>This is part 2.</p></body></html>",
]
assert actual == expected, actual

def test_update(self):
_, headers = self.login(is_admin=True)
url = "/api/2/entities/%s" % self.id
Expand Down
6 changes: 4 additions & 2 deletions aleph/views/entities_api.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -305,10 +305,12 @@ def view(entity_id):
entity = get_index_entity(entity_id, request.authz.READ, excludes=excludes)
tag_request(collection_id=entity.get("collection_id"))
proxy = model.get_proxy(entity)
html = proxy.first("bodyHtml", quiet=True)
html = proxy.get("bodyHtml", quiet=True)
source_url = proxy.first("sourceUrl", quiet=True)
encoding = proxy.first("encoding", quiet=True)
entity["safeHtml"] = sanitize_html(html, source_url, encoding=encoding)
entity["safeHtml"] = [
sanitize_html(value, source_url, encoding=encoding) for value in html
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is a utility function that we wrote, or a third party created?

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is a utility we wrote wrapping the Cleaner class from lxml:

]
entity["shallow"] = False

if request.authz.logged_in:
Expand Down
2 changes: 1 addition & 1 deletion requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# Dependencies maintained by OCCRP
banal==1.0.6
followthemoney==3.4.3
followthemoney==3.4.4
followthemoney-store[postgresql]==3.0.5
followthemoney-compare==0.4.4
fingerprints==1.0.3
Expand Down
8 changes: 7 additions & 1 deletion ui/src/viewers/EmailViewer.jsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -73,16 +73,22 @@ class EmailViewer extends PureComponent {

renderBody() {
const { document } = this.props;

if (document.isPending) {
return <Skeleton.Text type="span" length={1000} />;
}

if (document.safeHtml && document.safeHtml.length) {
return <span dangerouslySetInnerHTML={{ __html: document.safeHtml }} />;
return document.safeHtml.map((value, index) => (
<div key={index} dangerouslySetInnerHTML={{ __html: value }} />
));
}

const bodyText = document.getFirst('bodyText');
if (bodyText && bodyText.length > 0) {
return <Pre>{bodyText}</Pre>;
}

return (
<p className={Classes.TEXT_MUTED}>
<FormattedMessage
Expand Down
4 changes: 3 additions & 1 deletion ui/src/viewers/HtmlViewer.jsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,9 @@ class HtmlViewer extends Component {
const body = document.isPending ? (
<Skeleton.Text type="p" length={4000} />
) : (
<span dangerouslySetInnerHTML={{ __html: document.safeHtml }} />
document.safeHtml.map((value, index) => (
<div key={index} dangerouslySetInnerHTML={{ __html: value }} />
))
);
return (
<div className="outer">
Expand Down