Skip to content

Remove camelot #2624

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

Open
symroe wants to merge 5 commits into
base: master
Choose a base branch
from
Open

Remove camelot #2624

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
169a5b1
Remove SOPN tooling
symroe Nov 15, 2025
59fcfcf
Remove a load of Camelot code
symroe Nov 15, 2025
089ef66
fixup! Remove a load of Camelot code
symroe Jan 30, 2026
a5b245d
Remove Camelot from the requirements
symroe Jan 30, 2026
8aafe62
Don't skip tests
symroe Feb 2, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 0 additions & 2 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,8 +24,6 @@ test-results
node_modules/
.vscode/
/test-env
/ynr/apps/sopn_parsing/tests/data/sopn_baseline.json
/ynr/apps/sopn_parsing/tests/data/sopn_baseline_copy.json
# PyCharm
.idea/

Expand Down
45 changes: 0 additions & 45 deletions Makefile
View file
Open in desktop

This file was deleted.

5 changes: 1 addition & 4 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -41,12 +41,10 @@ dependencies = [
"markdown-it-py==4.0.0",
"nameparser==1.1.2",
"ndg-httpsclient==0.5.1",

"openai==1.30.3",
# for compatibility with openai==1.30.3
# TODO: review/remove when we upgrade openai package
"httpx==0.27.0",

"Pillow==10.3.0",
"psycopg==3.1.12",
"python-dateutil==2.8.2",
Expand All @@ -58,14 +56,13 @@ dependencies = [
"whitenoise==6.5.0",
"sorl-thumbnail-serializer-field",
"slacker2",

# SOPN parsing
"pdfminer.six==20201018",
"camelot-py[cv]==0.8.2",
"pypandoc_binary==1.14",
"PyPDF2==2.12.1",
"amazon-textract-response-parser==1.0.3",
"amazon-textract-helper==0.0.35",
"pandas>=3.0.0",
]

[dependency-groups]
Expand Down
131 changes: 30 additions & 101 deletions uv.lock
View file
Open in desktop

Large diffs are not rendered by default.

76 changes: 0 additions & 76 deletions ynr/apps/bulk_adding/tests/test_bulk_add.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -752,79 +752,3 @@ def test_bulk_add_person_removes_spaces_from_name(self):
self.assertContains(resp, "Review candidates")
resp = form.submit()
self.assertContains(resp, "Bart Simpson")

def test_fall_back_to_camelot_if_no_textract(self):
data = {"name": "Bart", "party_id": "PP52"}

raw_people = RawPeople.objects.create(
ballot=self.dulwich_post_ballot,
data=[data],
source_type=RawPeople.SOURCE_PARSED_PDF,
)

self.assertEqual(
raw_people.as_form_kwargs(),
{
"initial": [
{
"name": "Bart",
"party": ["PP52", "PP52"],
"previous_party_affiliations": [],
"source": "",
}
]
},
)
raw_people.delete()

textract_data = {"name": "Lisa", "party_id": "PP53"}
raw_people = RawPeople.objects.create(
ballot=self.dulwich_post_ballot,
data=[data],
textract_data=[textract_data],
source_type=RawPeople.SOURCE_PARSED_PDF,
)

self.assertEqual(
raw_people.as_form_kwargs(),
{
"initial": [
{
"name": "Lisa",
"party": ["PP53", "PP53"],
"previous_party_affiliations": [],
"source": "",
}
]
},
)

def test_can_change_parser_in_frontend(self):
"""
Check that a query param can change the parser we use
"""
BallotSOPN.objects.create(
source_url="http://example.com",
ballot=self.dulwich_post_ballot,
uploaded_file="sopn.pdf",
)
RawPeople.objects.create(
ballot=self.dulwich_post_ballot,
data=[{"name": "Bart", "party_id": "PP52"}],
textract_data=[{"name": "Lisa", "party_id": "PP53"}],
source_type=RawPeople.SOURCE_PARSED_PDF,
)
response = self.app.get(
"/bulk_adding/sopn/parl.65808.2015-05-07/", user=self.user
)
form = response.forms["bulk_add_form"]
# This should be the Textract data
self.assertEqual(form.fields["form-0-name"][0].value, "Lisa")

response = self.app.get(
"/bulk_adding/sopn/parl.65808.2015-05-07/?v1_parser=1",
user=self.user,
)
form = response.forms["bulk_add_form"]
# This should be the Textract data
self.assertEqual(form.fields["form-0-name"][0].value, "Bart")
4 changes: 0 additions & 4 deletions ynr/apps/bulk_adding/views/sopns.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -123,12 +123,8 @@ def get(self, request, *args, **kwargs):
return super().get(request, *args, **kwargs)

def get_active_parser(self) -> Optional[SOPNParsingBackends]:
if self.request.GET.get("v1_parser"):
return SOPNParsingBackends.CAMELOT
if self.ballot.rawpeople.textract_data:
return SOPNParsingBackends.TEXTRACT
if self.ballot.rawpeople.data:
return SOPNParsingBackends.CAMELOT
return None

def get_context_data(self, **kwargs):
Expand Down
16 changes: 0 additions & 16 deletions ynr/apps/elections/templates/elections/includes/_sopn_debug.html
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,28 +7,12 @@ <h3>Parsing Status</h3>
<ul>
<li>Pages matched: {% if object.sopn.get_pages %}Yes (matched pages: {{ object.sopn.get_pages|join:", " }}
){% else %}No{% endif %}</li>
<li>Camelot tables extracted: {% if object.sopn.camelotparsedsopn %}Yes{% else %}No{% endif %}</li>
<li>Raw Person Data: {% if object.rawpeople %}Yes{% else %}No{% endif %}</li>
<li>AWS Textract Data: {% if textract_parsed.raw_data %}Yes{% else %}No{% endif %}</li>
<li>AWS Textract Parsed? {% if textract_parsed.parsed_data %}Yes{% else %}
No{% endif %}</li>
</ul>

<h3>Camelot raw Data</h3>
{% if object.sopn.camelotparsedsopn.raw_data %}
<pre>{{ object.sopn.camelotparsedsopn.as_pandas.to_dict|pprint }}</pre>
{% else %}
N/A
{% endif %}

<h3>Camelot table Data</h3>
{% if object.sopn.camelotparsedsopn.data_as_html %}
{{ object.sopn.camelotparsedsopn.data_as_html|safe }}
{% else %}
N/A
{% endif %}
<br/>


{% if textract_parsed and textract_parsed.as_textractor_document %}
<h3>AWS extracted table{{ textract_parsed.as_textractor_document.tables|pluralize }}</h3>
Expand Down
8 changes: 0 additions & 8 deletions ynr/apps/official_documents/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,6 @@
from typing import List

from candidates.models import Ballot
from django.conf import settings
from django.core.files.base import ContentFile
from django.core.validators import FileExtensionValidator
from django.db import models
Expand Down Expand Up @@ -258,7 +257,6 @@ def parse(self):

"""

from sopn_parsing.helpers.extract_tables import extract_ballot_table
from sopn_parsing.helpers.textract_helpers import (
NotUsingAWSException,
TextractSOPNHelper,
Expand All @@ -274,12 +272,6 @@ def parse(self):
# There's a cron job that should pick up the result and carry on parsing later.
textract_helper.start_detection()

if getattr(
settings, "CAMELOT_ENABLED", False
) and self.uploaded_file.name.endswith(".pdf"):
# Camelot
extract_ballot_table(self.ballot)


class BallotSOPNHistory(BaseBallotSOPN):
ballot = models.ForeignKey(
Expand Down
38 changes: 0 additions & 38 deletions ynr/apps/official_documents/tests/test_upload.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,6 @@
import textwrap
from os.path import dirname, join, realpath
from pathlib import Path
from unittest import skipIf

from candidates.models import LoggedAction
from candidates.tests.auth import TestUserMixin
Expand All @@ -27,7 +26,6 @@
EXAMPLE_DOCX_FILENAME,
EXAMPLE_HTML_FILENAME,
)
from sopn_parsing.tests import should_skip_conversion_tests
from webtest import Upload

TEST_MEDIA_ROOT = realpath(
Expand Down Expand Up @@ -114,20 +112,8 @@ def test_upload_authorized(self):
with open(self.example_image_filename, "rb") as f:
form["uploaded_file"] = Upload("pilot.jpg", f.read())

# TODO: Add back in
# with patch(
# "official_documents.views.extract_pages_for_ballot"
# ) as extract_pages, patch(
# "official_documents.views.extract_ballot_table"
# ) as extract_tables, patch(
# "official_documents.views.parse_raw_data_for_ballot"
# ) as parse_tables:
response = form.submit()
self.assertEqual(response.status_code, 302)
# TODO: Add back in
# extract_pages.assert_called_once()
# extract_tables.assert_called_once()
# parse_tables.assert_called_once()

ballot_sopns = BallotSOPN.objects.all()
self.assertEqual(ballot_sopns.count(), 1)
Expand Down Expand Up @@ -155,9 +141,6 @@ def test_upload_authorized(self):
)
self.assertInHTML("Update SOPN", response.text)

@skipIf(
should_skip_conversion_tests(), "Required conversion libs not installed"
)
def test_docx_upload_form_validation(self):
self.assertFalse(LoggedAction.objects.exists())
response = self.app.get(
Expand All @@ -181,26 +164,11 @@ def test_docx_upload_form_validation(self):
with open(self.example_docx_filename, "rb") as f:
form["uploaded_file"] = Upload("pilot.docx", f.read())

# TODO: add back in
# with patch(
# "official_documents.views.extract_pages_for_ballot"
# ) as extract_pages, patch(
# "official_documents.views.extract_ballot_table"
# ) as extract_tables, patch(
# "official_documents.views.parse_raw_data_for_ballot"
# ) as parse_tables:
response = form.submit()
self.assertEqual(response.status_code, 302)
# TODO Add back in
# extract_pages.assert_called_once()
# extract_tables.assert_called_once()
# parse_tables.assert_called_once()
self.assertEqual(BallotSOPN.objects.count(), 1)
self.assertEqual(response.location, self.ballot.get_sopn_url())

@skipIf(
should_skip_conversion_tests(), "Required conversion libs not installed"
)
def test_html_upload_form_validation(self):
self.assertFalse(LoggedAction.objects.exists())
response = self.app.get(
Expand Down Expand Up @@ -229,9 +197,6 @@ def test_html_upload_form_validation(self):
response.text,
)

@skipIf(
should_skip_conversion_tests(), "Required conversion libs not installed"
)
def test_jpg_form_validation(self):
self.assertFalse(LoggedAction.objects.exists())
response = self.app.get(
Expand All @@ -256,9 +221,6 @@ def test_jpg_form_validation(self):
self.assertEqual(response.status_code, 302)
self.assertEqual(BallotSOPN.objects.count(), 1)

@skipIf(
should_skip_conversion_tests(), "Required conversion libs not installed"
)
def test_update_existing_sopn(self):
self.assertFalse(LoggedAction.objects.exists())
response = self.app.get(
Expand Down
63 changes: 0 additions & 63 deletions ynr/apps/sopn_parsing/helpers/extract_tables.py
View file
Open in desktop

This file was deleted.

Loading