Finalised generalisation for get_citations() method

tests/parsers/test_akomantoso.py

@@ -67,11 +67,12 @@ def test_get_citations(self):
         """Test citation extraction in the preamble section."""
         self.parser.get_preamble(preamble_xpath='.//akn:preamble', notes_xpath='.//akn:authorialNote')
         self.parser.get_citations()
+
         self.assertIsNotNone(self.parser.citations, "Citations data not found")
 
         first_citation = self.parser.citations[0]
         expected_text = "Having regard to the Treaty on the Functioning of the European Union, and in particular Article 114"
-        self.assertIn(expected_text, first_citation['citation_text'])
+        self.assertIn(expected_text, first_citation['text'])
 
     def test_get_recitals(self):
         """Test retrieval and content verification of recitals in the preamble."""

tests/parsers/test_formex.py

@@ -78,9 +78,9 @@ def test_get_citations(self):
 
 
         citations =  [
-                {'eId': 0, 'citation_text': "Having regard to the Treaty on the Functioning of the European Union,"},
-                {"eId": 1, 'citation_text':"Having regard to Council Regulation (EC) No 1234/2007 of 22 October 2007 establishing a common organisation of agricultural markets and on specific provisions for certain agricultural products (Single CMO Regulation) , and in particular Article 143 thereof,"},
-                {"eId": 2, 'citation_text':"Having regard to Council Regulation (EC) No 614/2009 of 7 July 2009 on the common system of trade for ovalbumin and lactalbumin , and in particular Article 3(4) thereof,"},
+                {'eId': 0, 'text': "Having regard to the Treaty on the Functioning of the European Union,"},
+                {"eId": 1, 'text':"Having regard to Council Regulation (EC) No 1234/2007 of 22 October 2007 establishing a common organisation of agricultural markets and on specific provisions for certain agricultural products (Single CMO Regulation) , and in particular Article 143 thereof,"},
+                {"eId": 2, 'text':"Having regard to Council Regulation (EC) No 614/2009 of 7 July 2009 on the common system of trade for ovalbumin and lactalbumin , and in particular Article 3(4) thereof,"},
             ]
 
         self.assertEqual(self.parser.citations, citations)

tulit/parsers/akomantoso.py

@@ -246,8 +246,9 @@ def get_citations(self) -> list:
         Returns
         -------
         list
-            List of dictionaries containing citation text without the associated
-            authorial notes.
+            List of dictionaries containing citation data with keys:
+            - 'eId': Citation identifier, which is retrieved from the 'eId' attribute
+            - 'citation_text': Citation text
         """
         def extract_eId(citation, index):
             return citation.get('eId')

tulit/parsers/formex.py

@@ -90,7 +90,9 @@ def get_citations(self):
         Returns
         -------
         list
-            List of dictionaries containing citation text.
+            List of dictionaries containing citation data with keys:
+            - 'eId': Citation identifier, which is the index of the citation in the preamble
+            - 'citation_text': Citation text
         """
         def extract_eId(citation, index):
             return index

tulit/parsers/parser.py

@@ -268,15 +268,15 @@ def get_citations(self, citations_xpath, citation_xpath, extract_eId=None):
 
         citations = []
         for index, citation in enumerate(citations_section.findall(citation_xpath, namespaces=self.namespaces)):
-            citation_text = "".join(citation.itertext()).strip()
-            citation_text = citation_text.replace('\n', '').replace('\t', '').replace('\r', '')  # remove newline and tab characters
-            citation_text = re.sub(' +', ' ', citation_text)  # replace multiple spaces with a single space
+            text = "".join(citation.itertext()).strip()
+            text = text.replace('\n', '').replace('\t', '').replace('\r', '')  # remove newline and tab characters
+            text = re.sub(' +', ' ', text)  # replace multiple spaces with a single space
 
             eId = extract_eId(citation, index) if extract_eId else index
             # Up until here, the code is the same as for Formex
             citations.append({
                 'eId' : eId,
-                'citation_text': citation_text,
+                'text': text,
             })
 
         self.citations = citations