Skip to content

Fix KBART export to prefer electronic ISSN in journal URLs #81

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

Draft
Copilot wants to merge 3 commits into
base: master
Choose a base branch
from
Draft

Fix KBART export to prefer electronic ISSN in journal URLs #81

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
c834073
Initial plan
Copilot Feb 3, 2026
e5b3ba3
Fix KBART to prefer electronic ISSN over print ISSN in URLs
Copilot Feb 3, 2026
49a6d37
Add unit tests for KBART URL generation with electronic ISSN preference
Copilot Feb 3, 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
17 changes: 16 additions & 1 deletion export/kbart.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -118,6 +118,21 @@ def write(self, line):
else:
self.output_file.write('%s\r\n' % line)

def _generate_journal_url(self, journal, language='en'):
"""
Generate the journal URL, preferring electronic ISSN over print ISSN.
This ensures that journals that have transitioned to electronic-only
use the correct ISSN in the URL.
"""
issn = journal.any_issn(priority=u'electronic')
if journal.scielo_domain and issn:
return "http://{0}/scielo.php?script=sci_issues&pid={1}&lng={2}".format(
journal.scielo_domain,
issn,
language
)
return ''

def run(self):
for item in self.items():
self.write(item)
Expand Down Expand Up @@ -155,7 +170,7 @@ def fmt_csv(self, data):
last_document.issue.number or '' if last_document and last_document.issue else '')
else:
line += ['', '', '']
line.append(data.url().replace('sci_serial', 'sci_issues'))
line.append(self._generate_journal_url(data))
line.append('') # first_author
line.append(data.scielo_issn or '')
line.append('') # embargo_info
Expand Down
114 changes: 114 additions & 0 deletions tests/test_kbart.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,114 @@
# coding: utf-8
"""
Unit tests for KBART URL generation logic

Note: These tests verify the URL generation method in isolation using mocks.
Full integration tests require the complete SciELO infrastructure (ArticleMeta, etc.)
"""
import unittest
try:
from unittest.mock import Mock
except ImportError:
from mock import Mock


class KbartUrlGenerationTest(unittest.TestCase):
"""
Tests for the _generate_journal_url method that prefers electronic ISSN over print ISSN.
This addresses the issue where journals transition to electronic-only publication.
"""

def _create_dumper_instance(self):
"""Helper to create a Dumper instance without dependencies"""
# Import here to avoid module-level import errors
import sys
import os
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

from export.kbart import Dumper
dumper = Dumper.__new__(Dumper)
return dumper

def test_generate_journal_url_with_electronic_issn(self):
"""
Test that _generate_journal_url prefers electronic ISSN when available.
This is the fix for the Revista española de sanidad penitenciaria issue.
"""
dumper = self._create_dumper_instance()

# Create a mock journal object mimicking the problematic journal
journal = Mock()
journal.scielo_domain = 'scielo.isciii.es'
journal.electronic_issn = '2013-6463' # Current ISSN
journal.print_issn = '1575-0620' # Old ISSN (no longer used)
journal.any_issn = Mock(return_value='2013-6463') # Prefers electronic

# Test the URL generation
url = dumper._generate_journal_url(journal)

# Verify the URL uses the electronic ISSN (2013-6463), not print ISSN (1575-0620)
self.assertIn('2013-6463', url)
self.assertNotIn('1575-0620', url)
self.assertEqual(url, 'http://scielo.isciii.es/scielo.php?script=sci_issues&pid=2013-6463&lng=en')

def test_generate_journal_url_with_only_print_issn(self):
"""
Test that _generate_journal_url falls back to print ISSN when electronic is not available
"""
dumper = self._create_dumper_instance()

# Create a mock journal object
journal = Mock()
journal.scielo_domain = 'scielo.br'
journal.electronic_issn = None
journal.print_issn = '1234-5678'
journal.any_issn = Mock(return_value='1234-5678')

# Test the URL generation
url = dumper._generate_journal_url(journal)

# Verify the URL uses the print ISSN
self.assertIn('1234-5678', url)
self.assertEqual(url, 'http://scielo.br/scielo.php?script=sci_issues&pid=1234-5678&lng=en')

def test_generate_journal_url_with_no_issn(self):
"""
Test that _generate_journal_url returns empty string when no ISSN is available
"""
dumper = self._create_dumper_instance()

# Create a mock journal object
journal = Mock()
journal.scielo_domain = 'scielo.br'
journal.electronic_issn = None
journal.print_issn = None
journal.any_issn = Mock(return_value=None)

# Test the URL generation
url = dumper._generate_journal_url(journal)

# Verify the URL is empty
self.assertEqual(url, '')

def test_generate_journal_url_with_no_domain(self):
"""
Test that _generate_journal_url returns empty string when no domain is available
"""
dumper = self._create_dumper_instance()

# Create a mock journal object
journal = Mock()
journal.scielo_domain = None
journal.electronic_issn = '2013-6463'
journal.print_issn = '1575-0620'
journal.any_issn = Mock(return_value='2013-6463')

# Test the URL generation
url = dumper._generate_journal_url(journal)

# Verify the URL is empty
self.assertEqual(url, '')


if __name__ == '__main__':
unittest.main()