Fixed formula and preamble final

tests/parsers/test_akomantoso.py

@@ -36,15 +36,14 @@ def test_get_preamble(self):
         """Test retrieval of preamble data from the XML file."""
         self.parser.get_preamble()
         self.assertIsNotNone(self.parser.preamble, "Preamble element not found")
-        self.assertIsNotNone(self.parser.formula, "Formula not found")
 
 
     def test_get_formula(self):
         """Test extraction of formula text within the preamble."""
         self.parser.get_preamble()
 
-        formula_data = self.parser.get_formula()
-        self.assertIn("THE EUROPEAN PARLIAMENT AND THE COUNCIL OF THE EUROPEAN UNION", formula_data)
+        self.parser.get_formula()
+        self.assertEqual(self.parser.formula, "THE EUROPEAN PARLIAMENT AND THE COUNCIL OF THE EUROPEAN UNION,")
 
     def test_get_citations(self):
         """Test citation extraction in the preamble section."""
@@ -77,11 +76,14 @@ def test_get_recitals(self):
                 self.assertIn(expected_values['text'], self.parser.recitals[index]['text'], 
                               f"Recital {index} text does not match expected content")
 
-    def test_get_act(self):
-        """Test retrieval of the act element."""
-        self.parser.get_act()
-        self.assertIsInstance(self.parser.act, etree._Element, "Act element should be an lxml.etree._Element")
-
+    def test_get_preamble_final(self):
+        """Test extraction of the final preamble text."""
+        self.parser.get_preamble()
+        self.parser.get_preamble_final()
+        preamble_final = "HAVE ADOPTED THIS DIRECTIVE:"
+        self.assertEqual(self.parser.preamble_final, preamble_final, "Final preamble text does not match expected content")
+
+
     def test_get_body(self):
         """Test retrieval of the body element."""
         self.parser.get_body()

tests/parsers/test_formex.py

@@ -23,24 +23,22 @@ def test_get_root(self):
     def test_get_preface(self):
 
         self.parser.get_preface()
-        expected = (
-            "Commission Implementing Regulation (EU) No 1319/2011 of 15 December 2011 "
-            "fixing representative prices in the poultrymeat and egg sectors and for egg "
-            "albumin, and amending Regulation (EC) No 1484/95"
-        )
-        self.assertEqual(self.parser.preface, expected)
+        preface = "Commission Implementing Regulation (EU) No 1319/2011 of 15 December 2011 fixing representative prices in the poultrymeat and egg sectors and for egg albumin, and amending Regulation (EC) No 1484/95"        
+        self.assertEqual(self.parser.preface, preface)
 
-    def test_get_preamble(self):
-        """Test parsing the preamble section with quotations and numbered considerations in Formex4Parser."""
-
+    def test_get_preamble(self):        
         self.parser.get_preamble()
         self.assertIsNotNone(self.parser.preamble)
 
     def test_get_formula(self):
-        initial_statement = {
-            "initial_statement": "THE EUROPEAN COMMISSION,",
-        }
-        pass
+
+        self.parser.get_preamble()
+        self.parser.get_formula()
+
+        formula = "THE EUROPEAN COMMISSION,"
+
+        self.assertEqual(self.parser.formula, formula)
+
 
     def test_get_citations(self):
 
@@ -57,7 +55,6 @@ def test_get_citations(self):
 
 
     def test_get_recitals(self):
-        """Test parsing the preamble section with quotations and numbered considerations in Formex4Parser."""
 
         self.parser.get_preamble()
         self.parser.get_recitals()
@@ -70,18 +67,21 @@ def test_get_recitals(self):
                 {"eId": "(4)", "text": "The measures provided for in this Regulation are in accordance with the opinion of the Management Committee for the Common Organisation of Agricultural Markets,"},
         ]
 
-        preamble_final = {
-            "preamble_final": "HAS ADOPTED THIS REGULATION:"
-        }
-
         self.assertEqual(self.parser.recitals, recitals)      
 
+    def test_get_preamble_final(self):
+        self.parser.get_preamble()
+
+        self.parser.get_preamble_final()
+        preamble_final = "HAS ADOPTED THIS REGULATION:"
+
+        self.assertEqual(self.parser.preamble_final, preamble_final)
+
     def test_get_body(self):
         self.parser.get_body()
         self.assertIsNotNone(self.parser.body, "Body element should not be None")    
 
     def test_get_chapters(self):
-        """Test retrieval and content of chapter headings."""
         self.parser = Formex4Parser()
         self.parser.get_root(iopa)
         self.parser.get_body()

tulit/parsers/akomantoso.py

@@ -47,15 +47,7 @@ def get_formula(self):
             Concatenated text from all paragraphs within the formula element.
             Returns None if no formula is found.
         """
-        formula = self.preamble.find('.//akn:formula', namespaces=self.namespaces)
-        # Extract text from <p> within <formula>
-        formula_text = ' '.join(p.text.strip() for p in formula.findall('akn:p', namespaces=self.namespaces) if p.text)
-        if formula is None:
-            return None
-
-        self.formula = formula_text
-        return self.formula
-
+        return super().get_formula(formula_xpath='.//akn:formula', paragraph_xpath='akn:p')
 
     def get_citations(self) -> list:
         """
@@ -107,8 +99,20 @@ def extract_eId(recital):
         )
 
     def get_preamble_final(self):
-        return super().get_preamble_final()
-
+        """
+        Extracts the final preamble text from the document.
+
+        Returns
+        -------
+        str or None
+            Concatenated text from the final preamble element.
+            Returns None if no final preamble is found.
+        """
+        preamble_final = self.preamble.find(".//akn:block", namespaces=self.namespaces).text
+        self.preamble_final = preamble_final
+        return self.preamble_final
+
+        #return super().get_preamble_final(preamble_final_xpath='.//block[@name="preamble.final"]')    
 
     def get_body(self):
         return super().get_body('.//akn:body')

tulit/parsers/formex.py

@@ -47,14 +47,9 @@ def get_formula(self):
         str
             Formula text from the preamble.
         """
-        formula = self.preamble.findtext('PREAMBLE.INIT')
-
-        if formula is None:
-            return None
-
-        self.formula = formula
-
+        self.formula = self.preamble.findtext('PREAMBLE.INIT')
         return self.formula
+
 
     def get_citations(self):
         """
@@ -105,7 +100,18 @@ def extract_eId(recital):
         )
 
     def get_preamble_final(self):
-        return super().get_preamble_final()
+        """
+        Extracts the final preamble text from the document.
+
+        Returns
+        -------
+        str or None
+            Concatenated text from the final preamble element.
+            Returns None if no final preamble is found.
+        """
+        self.preamble_final = self.preamble.findtext('PREAMBLE.FINAL')
+
+        return self.preamble_final
 
     def get_body(self):
         return super().get_body('.//ENACTING.TERMS')

tulit/parsers/parser.py

@@ -49,6 +49,7 @@ def __init__(self):
         self.formula = None    
         self.citations = None
         self.recitals = None
+        self.preamble_final = None
 
         self.body = None
         self.chapters = []
@@ -256,10 +257,32 @@ def get_preamble(self, preamble_xpath, notes_xpath) -> None:
 
         if self.preamble is not None:            
             self.preamble = self.remove_node(self.preamble, notes_xpath)
-            #preamble_data["preamble_final"] = self.preamble.findtext('PREAMBLE.FINAL')
 
-    def get_formula(self):
-        pass
+    def get_formula(self, formula_xpath: str, paragraph_xpath: str) -> str:
+        """
+        Extracts formula text from the preamble.
+
+        Parameters
+        ----------
+        formula_xpath : str
+            XPath expression to locate the formula element.
+        paragraph_xpath : str
+            XPath expression to locate the paragraphs within the formula.
+
+        Returns
+        -------
+        str or None
+            Concatenated text from all paragraphs within the formula element.
+            Returns None if no formula is found.
+        """
+        formula = self.preamble.find(formula_xpath, namespaces=self.namespaces)
+        if formula is None:
+            return None
+
+        # Extract text from <p> within <formula>
+        formula_text = ' '.join(p.text.strip() for p in formula.findall(paragraph_xpath, namespaces=self.namespaces) if p.text)
+        self.formula = formula_text
+        return self.formula
 
     def get_citations(self, citations_xpath, citation_xpath, extract_eId=None):
         """
@@ -333,8 +356,27 @@ def get_recitals(self, recitals_xpath, recital_xpath, text_xpath, extract_intro=
 
         self.recitals = recitals
 
-    def get_preamble_final(self):
-        pass
+    def get_preamble_final(self) -> str:
+        """
+        Extracts the final preamble text from the document.
+
+        Parameters
+        ----------
+        preamble_final_xpath : str
+            XPath expression to locate the final preamble element.
+
+        Returns
+        -------
+        str or None
+            Concatenated text from the final preamble element.
+            Returns None if no final preamble is found.
+        """
+        preamble_final = self.preamble.findtext('.//block', namespaces=self.namespaces)
+        if preamble_final is None:
+            return None
+
+        self.preamble_final = preamble_final
+        return self.preamble_final
 
     def get_body(self, body_xpath) -> None:
         """
@@ -486,6 +528,12 @@ def parse(self, file: str, schema, format) -> None:
                 except Exception as e:
                     print(f"Error in get_recitals: {e}")
 
+                try:
+                    self.get_preamble_final()
+                    print(f"Preamble final parsed successfully.")
+                except Exception as e:
+                    print(f"Error in get_preamble_final: {e}")
+
                 try:
                     self.get_body()
                     print("Body element found.")