Improved docstrings for Formex4Parser

AlessioNar · Dec 23, 2024 · e44247f · e44247f
1 parent b7e7db5
commit e44247f
Show file tree

Hide file tree

Showing 4 changed files with 57 additions and 27 deletions.
diff --git a/docs/source/index.rst b/docs/source/index.rst
@@ -14,17 +14,17 @@ Contents
 --------
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 3
 
    getting_started
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 3
 
    download
 
 .. toctree::
-   :maxdepth: 2
+   :maxdepth: 3
 
    parsers
 
diff --git a/docs/source/parsers.rst b/docs/source/parsers.rst
@@ -3,22 +3,22 @@ Parsers
 
 This package contains modules for parsing various types of legal documents. Below are the details for each module.
 
-.. automodule:: parsers.parser
+.. automodule:: tulit.parsers.parser
     :members:
     :undoc-members:
     :show-inheritance:
 
-.. automodule:: parsers.formex
+.. automodule:: tulit.parsers.formex
     :members:
     :undoc-members:
     :show-inheritance:
 
-.. automodule:: parsers.akomantoso
+.. automodule:: tulit.parsers.akomantoso
     :members:
     :undoc-members:
     :show-inheritance:
 
-.. automodule:: parsers.html
+.. automodule:: tulit.parsers.html
     :members:
     :undoc-members:
     :show-inheritance:
diff --git a/tulit/parsers/formex.py b/tulit/parsers/formex.py
@@ -4,10 +4,6 @@
 from lxml import etree
 from .parser import Parser
 
-FMX_NAMESPACES = {
-    'fmx': 'http://formex.publications.europa.eu/schema/formex-05.56-20160701.xd'
-}
-
 class Formex4Parser(Parser):
     """
     A parser for processing and extracting content from Formex XML files.
@@ -20,15 +16,46 @@ class Formex4Parser(Parser):
     ----------
     namespaces : dict
         Dictionary mapping namespace prefixes to their URIs.
+    schema : lxml.etree.XMLSchema or None
+        The XML schema used for validation.
+    valid : bool or None
+        Indicates whether the XML file is valid against the schema.
+    root : lxml.etree.Element or None
+        The root element of the parsed XML document.
+    metadata : dict
+        Extracted metadata from the XML document.
+    preface : str or None
+        Extracted preface text from the XML document.
+    preamble : lxml.etree.Element or None
+        The preamble section of the XML document.
+    formula : None
+        Placeholder for future use.
+    citations : list or None
+        List of extracted citations from the preamble.
+    recitals : list or None
+        List of extracted recitals from the preamble.
+    body : lxml.etree.Element or None
+        The body section of the XML document.
+    chapters : list
+        List of extracted chapters from the body.
+    articles : list
+        List of extracted articles from the body.
+    articles_text : list
+        List of extracted article texts.
+    conclusions : None
+        Placeholder for future use.
     """
 
     def __init__(self):
         """
         Initializes the parser.
         """
         # Define the namespace mapping
-        self.namespaces = {}
-        self.namespaces = FMX_NAMESPACES
+
+        self.namespaces = {
+            'fmx': 'http://formex.publications.europa.eu/schema/formex-05.56-20160701.xd'
+        }
+
         self.schema = None
         self.valid = None
 

diff --git a/tulit/parsers/parser.py b/tulit/parsers/parser.py
@@ -7,7 +7,10 @@
 
 class Parser(ABC):
     @abstractmethod
-    def parse(self, data):
+    def parse(self):
+        """
+        Abstract method to parse the data. This method must be implemented by the subclass.
+        """
         pass
 
     def get_root(self, file: str):
@@ -31,19 +34,19 @@ def get_root(self, file: str):
 
     def remove_node(self, tree, node):
         """
-            Removes specified nodes from the XML tree while preserving their tail text.
-
-            Parameters
-            ----------
-            tree : lxml.etree._Element
-                The XML tree or subtree to process.
-            node : str
-                XPath expression identifying the nodes to remove.
-
-            Returns
-            -------
-            lxml.etree._Element
-                The modified XML tree with specified nodes removed.
+        Removes specified nodes from the XML tree while preserving their tail text.
+        
+        Parameters
+        ----------
+        tree : lxml.etree._Element
+            The XML tree or subtree to process.
+        node : str
+            XPath expression identifying the nodes to remove.
+        
+        Returns
+        -------
+        lxml.etree._Element
+            The modified XML tree with specified nodes removed.
         """
         if tree.findall(node, namespaces=self.namespaces) is not None:
             for item in tree.findall(node, namespaces=self.namespaces):