Fix malformed journal links with double http:// prefix

core/home/tests.py

@@ -0,0 +1,64 @@
+from unittest.mock import patch
+
+from django.test import TestCase
+
+from collection.models import Collection
+from core.users.models import User
+from journal.models import Journal, SciELOJournal
+
+from core.home.views import _get_scielo_journals_data
+
+
+class TestGetScieloJournalsData(TestCase):
+    def setUp(self):
+        self.user = User.objects.create(username="testuser", password="testpass")
+        self.collection = Collection.objects.create(
+            creator=self.user,
+            acron3="per",
+            domain="http://www.scielo.org.pe",
+        )
+        self.journal = Journal.objects.create(
+            creator=self.user,
+            title="Test Journal Peru",
+        )
+        self.scielo_journal = SciELOJournal.objects.create(
+            issn_scielo="2709-3689",
+            collection=self.collection,
+            journal=self.journal,
+            journal_acron="tjperu",
+        )
+
+    def test_scielo_url_does_not_have_double_http_prefix(self):
+        """URL must not contain 'http://http://' when domain already has http://"""
+        data = _get_scielo_journals_data()
+        self.assertTrue(len(data) > 0)
+        for item in data:
+            self.assertNotIn("http://http://", item["scielo_url"])
+            self.assertNotIn("http://https://", item["scielo_url"])
+
+    def test_scielo_url_is_well_formed(self):
+        """URL must be a valid scielo.php URL with the correct domain"""
+        data = _get_scielo_journals_data()
+        self.assertEqual(len(data), 1)
+        expected_url = (
+            "http://www.scielo.org.pe/scielo.php?script=sci_serial"
+            "&pid=2709-3689&lng=en"
+        )
+        self.assertEqual(data[0]["scielo_url"], expected_url)
+
+    def test_scielo_url_strips_trailing_slash_from_domain(self):
+        """Trailing slash in domain must not produce double slash in URL"""
+        self.collection.domain = "http://www.scielo.org.pe/"
+        self.collection.save()
+        data = _get_scielo_journals_data()
+        self.assertEqual(len(data), 1)
+        self.assertNotIn("//scielo.php", data[0]["scielo_url"])
+
+    def test_scielo_url_with_https_domain(self):
+        """URL must be correct when domain uses https://"""
+        self.collection.domain = "https://www.scielo.br"
+        self.collection.save()
+        data = _get_scielo_journals_data()
+        self.assertEqual(len(data), 1)
+        self.assertTrue(data[0]["scielo_url"].startswith("https://www.scielo.br/"))
+        self.assertNotIn("https://https://", data[0]["scielo_url"])

core/home/views.py

@@ -75,7 +75,7 @@ def _get_scielo_journals_data():
                 "",
             )
             scielo_url = (
-                f"http://{domain}/scielo.php?script=sci_serial&pid={issn_scielo}&lng=en"
+                f"{domain.rstrip('/')}/scielo.php?script=sci_serial&pid={issn_scielo}&lng=en"
             )
             formatted_data.append(
                 {

core/templates/home/include/list_journal_page/journals_table.html

@@ -26,7 +26,7 @@
                                 {% elif journal.status in "DS" %} 
                                     <span class="material-icons align-middle fs-5" style="color: #c63800;">fiber_manual_record</span> 
                                 {% endif %}
-                                <a target="_blank" href="http://{{ journal.collection__domain }}/scielo.php?script=sci_serial&pid={{journal.issn_scielo}}&lng=en">{{ journal.journal__title }}</a><span style="color: #888; font-size: 0.9em; opacity: 0.7; padding: 4px 8px;">{{journal.collection__main_name}}</span>
+                                <a target="_blank" href="{{ journal.collection__domain }}/scielo.php?script=sci_serial&pid={{journal.issn_scielo}}&lng=en">{{ journal.journal__title }}</a><span style="color: #888; font-size: 0.9em; opacity: 0.7; padding: 4px 8px;">{{journal.collection__main_name}}</span>
                             </th>
                         </tr>
                         {% endfor %}

core/templates/home/include/list_journal_page/journals_table_by_publisher.html

@@ -25,7 +25,7 @@
                                         {% elif scielojournal.status in "DS" %}
                                             <span class="material-icons align-middle fs-5" style="color: #c63800;">fiber_manual_record</span>
                                         {% endif %}
-                                        <a target="_blank" href="http://{{ scielojournal.collection.domain }}/scielo.php?script=sci_serial&pid={{ scielojournal.issn_scielo }}&lng=en">{{ scielojournal.journal.title }}</a><span style="color: #888; font-size: 0.9em; opacity: 0.7; padding: 4px 8px;">{{ scielojournal.collection.main_name }}</span> 
+                                        <a target="_blank" href="{{ scielojournal.collection.domain }}/scielo.php?script=sci_serial&pid={{ scielojournal.issn_scielo }}&lng=en">{{ scielojournal.journal.title }}</a><span style="color: #888; font-size: 0.9em; opacity: 0.7; padding: 4px 8px;">{{ scielojournal.collection.main_name }}</span> 
                                     {% endfor %}
                                 </ul>
                             </td>

journal/sources/classic_website.py

@@ -19,7 +19,7 @@
 def get_issn(collection):
     try:
         collections = requests.get(
-            f"http://{collection}/scielo.php?script=sci_alphabetic&lng=es&nrm=iso&debug=xml",
+            f"{collection.rstrip('/')}/scielo.php?script=sci_alphabetic&lng=es&nrm=iso&debug=xml",
             timeout=10,
         )
         data = xmltodict.parse(collections.text)
@@ -52,7 +52,7 @@ def get_issn(collection):
 def get_journal_xml(collection, issn):
     try:
         official_journal = requests.get(
-            f"http://{collection}/scielo.php?script=sci_serial&pid={issn}&lng=es&nrm=iso&debug=xml",
+            f"{collection.rstrip('/')}/scielo.php?script=sci_serial&pid={issn}&lng=es&nrm=iso&debug=xml",
             timeout=10,
         )
         return xmltodict.parse(official_journal.text)

journal/tests.py

@@ -1,5 +1,5 @@
 import json
-from unittest.mock import MagicMock, patch
+from unittest.mock import MagicMock, Mock, patch
 
 from django.test import TestCase
 from django_test_migrations.migrator import Migrator
@@ -387,3 +387,101 @@ def test_backward_compatibility_without_raw_fields(self):
         self.assertIsNone(publisher_history.raw_country_name)
 
 
+from journal.sources.classic_website import get_issn, get_journal_xml
+
+
+class TestClassicWebsiteGetIssn(TestCase):
+    @patch("journal.sources.classic_website.requests.get")
+    @patch("journal.sources.classic_website.xmltodict.parse")
+    def test_get_issn_url_does_not_have_double_http_prefix(self, mock_parse, mock_get):
+        """get_issn must not prepend http:// when domain already contains it"""
+        mock_response = Mock()
+        mock_response.text = ""
+        mock_get.return_value = mock_response
+        mock_parse.return_value = {"SERIALLIST": {"LIST": {"SERIAL": []}}}
+
+        list(get_issn("http://www.scielo.org.pe"))
+
+        called_url = mock_get.call_args[0][0]
+        self.assertNotIn("http://http://", called_url)
+        self.assertTrue(called_url.startswith("http://www.scielo.org.pe/"))
+
+    @patch("journal.sources.classic_website.requests.get")
+    @patch("journal.sources.classic_website.xmltodict.parse")
+    def test_get_issn_url_strips_trailing_slash(self, mock_parse, mock_get):
+        """get_issn must not produce double slash when domain has trailing slash"""
+        mock_response = Mock()
+        mock_response.text = ""
+        mock_get.return_value = mock_response
+        mock_parse.return_value = {"SERIALLIST": {"LIST": {"SERIAL": []}}}
+
+        list(get_issn("http://www.scielo.org.pe/"))
+
+        called_url = mock_get.call_args[0][0]
+        self.assertNotIn("//scielo.php", called_url)
+
+    @patch("journal.sources.classic_website.requests.get")
+    @patch("journal.sources.classic_website.xmltodict.parse")
+    def test_get_issn_url_with_https_domain(self, mock_parse, mock_get):
+        """get_issn must not produce double https:// when domain uses https://"""
+        mock_response = Mock()
+        mock_response.text = ""
+        mock_get.return_value = mock_response
+        mock_parse.return_value = {"SERIALLIST": {"LIST": {"SERIAL": []}}}
+
+        list(get_issn("https://www.scielo.br"))
+
+        called_url = mock_get.call_args[0][0]
+        self.assertNotIn("http://https://", called_url)
+        self.assertTrue(called_url.startswith("https://www.scielo.br/"))
+
+
+class TestClassicWebsiteGetJournalXml(TestCase):
+    @patch("journal.sources.classic_website.requests.get")
+    @patch("journal.sources.classic_website.xmltodict.parse")
+    def test_get_journal_xml_url_does_not_have_double_http_prefix(
+        self, mock_parse, mock_get
+    ):
+        """get_journal_xml must not prepend http:// when domain already contains it"""
+        mock_response = Mock()
+        mock_response.text = ""
+        mock_get.return_value = mock_response
+        mock_parse.return_value = {}
+
+        get_journal_xml("http://www.scielo.org.pe", "2709-3689")
+
+        called_url = mock_get.call_args[0][0]
+        self.assertNotIn("http://http://", called_url)
+        self.assertTrue(called_url.startswith("http://www.scielo.org.pe/"))
+
+    @patch("journal.sources.classic_website.requests.get")
+    @patch("journal.sources.classic_website.xmltodict.parse")
+    def test_get_journal_xml_url_strips_trailing_slash(self, mock_parse, mock_get):
+        """get_journal_xml must not produce double slash when domain has trailing slash"""
+        mock_response = Mock()
+        mock_response.text = ""
+        mock_get.return_value = mock_response
+        mock_parse.return_value = {}
+
+        get_journal_xml("http://www.scielo.org.pe/", "2709-3689")
+
+        called_url = mock_get.call_args[0][0]
+        self.assertNotIn("//scielo.php", called_url)
+
+    @patch("journal.sources.classic_website.requests.get")
+    @patch("journal.sources.classic_website.xmltodict.parse")
+    def test_get_journal_xml_url_with_https_domain(self, mock_parse, mock_get):
+        """get_journal_xml must not produce double https:// when domain uses https://"""
+        mock_response = Mock()
+        mock_response.text = ""
+        mock_get.return_value = mock_response
+        mock_parse.return_value = {}
+
+        get_journal_xml("https://www.scielo.br", "0034-8910")
+
+        called_url = mock_get.call_args[0][0]
+        self.assertNotIn("http://https://", called_url)
+        self.assertTrue(called_url.startswith("https://www.scielo.br/"))
+
+
+