tulit 0.2.0__tar.gz → 0.2.2__tar.gz

{tulit-0.2.0 → tulit-0.2.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: tulit
-Version: 0.2.0
+Version: 0.2.2
 Summary: TULIT - The Universal Legal Informatics Toolkit, is set of legal informatics utilities collected in a Python package that focuses on the retrieval of legal data and metadata from official sources in the EU, and their transformation in pythonic data structures
 License: EUPL 1.2
 Author: AlessioNar
@@ -10,7 +10,6 @@ Classifier: License :: Other/Proprietary License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: beautifulsoup4 (>=4.9.3,<5.0.0)
 Requires-Dist: chardet (>=5.2.0,<6.0.0)
 Requires-Dist: coverage (>=7.6.9,<8.0.0)

{tulit-0.2.0 → tulit-0.2.2}/pyproject.toml

@@ -1,11 +1,11 @@
 [project]
 name = "tulit"
-version = "0.2.0"
+version = "0.2.2"
 description = "TULIT - The Universal Legal Informatics Toolkit, is set of legal informatics utilities collected in a Python package that focuses on the retrieval of legal data and metadata from official sources in the EU, and their transformation in pythonic data structures"
 
 [tool.poetry]
 name = "tulit"
-version = "0.2.0"
+version = "0.2.2"
 description = "TULIT - The Universal Legal Informatics Toolkit, is set of legal informatics utilities collected in a Python package that focuses on the retrieval of legal data and metadata from official sources in the EU, and their transformation in pythonic data structures"
 authors = ["AlessioNar <alessio.nardin@gmail.com>"]
 license = "EUPL 1.2"

{tulit-0.2.0 → tulit-0.2.2}/tulit/parsers/xml/formex.py

@@ -163,8 +163,8 @@ class Formex4Parser(XMLParser):
             extract_eId=extract_eId,
             get_headings=get_headings
         )
+        
             
-
     def get_articles(self):
         """
         Extracts articles from the ENACTING.TERMS section. Articles are assumed to be contained within the
@@ -182,35 +182,56 @@ class Formex4Parser(XMLParser):
 
         self.articles = []
         if self.body is not None:
-            for article in self.body.findall('.//ARTICLE'):
+            # The usage of xpath() method is to exclude nested ARTICLE elements
+            articles = self.body.xpath(".//ARTICLE[@IDENTIFIER][not(ancestor::ARTICLE)]")
+            for article in articles:
                 article_eId = article.get("IDENTIFIER")
-                article_eId = article_eId.lstrip('0')
+                article_eId = article_eId.lstrip('3')
                 article_eId = f'art_{article_eId}'
+                
                 children = []
-                amendments = []
-
-                # Check if the article contains <QUOT.S> tag
+                
+                # Check whether within the ARTICLE element there are 
+                # QUOT.S elements, that mark the presence of amendments
                 if article.findall('.//QUOT.S'):
-                    article, amendments = self._handle_amendments(article)
-                    print('Amendment article found!')
-                    print('\n')
-
-                    print('Amendments:', amendments)
-                    print('\n')
-
-                # Extract text and metadata from all relevant elements within the article
-                if article.findall('.//PARAG'):
-                    self._extract_elements(article, './/PARAG', children, amendments)
+                    for alinea in article.xpath('.//ALINEA[not(ancestor::QUOT.S)]'):
+                        children.append({
+                            "eId": 0,
+                            "text": self.clean_text(alinea),
+                            "amendment": True
+                        })
+                        
+                    #article.xpath('.//ALINEA')
+                    
+                    
+                    # Treat amendments. First extract the text contained within the
+                    # a P element that is outside of a LIST element
+                    #for p in article.xpath('.//P[not(ancestor::LIST)]'):
+                    #    self._extract_elements(p, '.', children)
+                    
+                    # Treat all the rest of the content of the ARTICLE element
+                    # as a unique child
+                    #children
+                    
+                
+                # Extract text and metadata from PARAG elements that are not descendants of QUOT.S elements (exclude amendments)
+                elif article.xpath('.//PARAG'):
+                    self._extract_elements(article, './/PARAG', children)
                 elif article.findall('.//ALINEA'):
                     # If no PARAG elements, check for ALINEA elements
-                    alineas = article.findall('.//ALINEA')
+                    alineas = article.xpath('.//ALINEA')
                     for alinea in alineas:
-                        # if there are P elements within the ALINEA, extract them first, then extract LIST//ITEM elements, if they are still absent, extract the text from the ALINEA
-                        p_elements = alinea.findall('.//P')
-                        self._extract_elements(alinea, './/P', children, amendments)
-                        self._extract_elements(alinea, './/LIST//ITEM', children, amendments, start_index=len(p_elements))
-                        if not p_elements:
-                            self._extract_elements(alinea, '.', children, amendments)                        
+                        p_elements = alinea.xpath('.//P')
+                        if p_elements:
+                            for p in p_elements:
+                                self._extract_elements(p, '.', children)
+                            for item in alinea.findall('.//LIST//ITEM'):
+                                self._extract_elements(item, '.', children)                                
+                        else:
+                            self._extract_elements(alinea, '.', children)
+                
+                                    
+                    
                 
                 self.articles.append({
                     "eId": article_eId,
@@ -223,8 +244,22 @@ class Formex4Parser(XMLParser):
         else:
             print('No enacting terms XML tag has been found')
             return []
-
-    def _extract_elements(self, parent, xpath, children, amendments, start_index=0):
+        
+    def clean_text(self, element):
+        for sub_element in element.iter():
+            if sub_element.tag == 'QUOT.START':                    
+                sub_element.text = "‘"                    
+            elif sub_element.tag == 'QUOT.END':                    
+                sub_element.text = "’"
+        text = "".join(element.itertext()).strip()
+        text = re.sub(r'^\(\d+\)', '', text).strip()
+        text = text.replace('\n', '').replace('\t', '').replace('\r', '')  # remove newline and tab characters
+        text = text.replace('\u00A0', ' ')  # replace non-breaking spaces with regular spaces
+        text = re.sub(' +', ' ', text)  # replace multiple spaces with a single space
+        text = re.sub(r'\s+([.,!?;:’])', r'\1', text)  # replace spaces before punctuation with nothing
+        return text
+    
+    def _extract_elements(self, parent, xpath, children):
         """
         Helper method to extract text and metadata from elements.
 
@@ -236,55 +271,19 @@ class Formex4Parser(XMLParser):
             The XPath expression to locate the elements.
         children : list
             The list to append the extracted elements to.
-        amendments : list
-            List of amendments extracted from the article.
-        start_index : int, optional
-            The starting index for the elements (default is 0).
         """
         elements = parent.findall(xpath)
-        amendment_index = 0
-        for index, element in enumerate(elements, start=start_index):
-            for sub_element in element.iter():
-                if sub_element.tag == 'QUOT.START':                    
-                    sub_element.text = "‘"                    
-                elif sub_element.tag == 'QUOT.END':                    
-                    sub_element.text = "’"
-    
-            text = "".join(element.itertext()).strip()
-            text = re.sub(r'^\(\d+\)', '', text).strip()
-            text = text.replace('\n', '').replace('\t', '').replace('\r', '')  # remove newline and tab characters
-            text = text.replace('\u00A0', ' ')  # replace non-breaking spaces with regular spaces
-            text = re.sub(' +', ' ', text)  # replace multiple spaces with a single space
-            text = re.sub(r'\s+([.,!?;:’])', r'\1', text)  # replace spaces before punctuation with nothing
+        for index, element in enumerate(elements):
+            
+            text = self.clean_text(element)
+            
             if text is not None and text != '' and text != ';':
                 child = {
                     "eId": element.get("IDENTIFIER") or element.get("ID") or element.get("NO.P") or index,
-                    "text": text,
-                    "contains_amendment": amendment_index < len(amendments),
-                    "amendment": amendments[amendment_index] if amendment_index < len(amendments) else None
+                    "text": text, 
+                    "amendment": False                  
                 }
-                children.append(child)
-                amendment_index += 1
-
-    def _handle_amendments(self, article):
-        """
-        Handles amendments made in the ACT using the <QUOT.S> tag.
-
-        Parameters
-        ----------
-        article : lxml.etree._Element
-            The article element to process.
-        """
-        amendments = []
-        for quot_s in article.findall('.//QUOT.S'):
-            amendment_text = " ".join(quot_s.itertext()).strip()
-            # Process the amendment text as needed
-            # For example, you could store it in a list or apply it to the article text            
-            amendments.append(amendment_text)
-        # Remove the QUOT.S tags from the article using the self.remove_node method
-        article = self.remove_node(article, './/QUOT.S')
-        return article, amendments
-        
+                children.append(child)        
     
     def get_conclusions(self):
         """