Merge pull request #51 from sciknoworg/dev

cosmetic fix and encoders refactoring

Author: HamedBabaei

docs/source/conf.py

@@ -70,10 +70,7 @@
     "external_links": [
           ("Github", "https://github.com/sciknoworg/OntoAligner"),
           ("Pypi", "https://pypi.org/project/OntoAligner/")
-    ],
-    "navigation_depth": 4,
-    "collapse_navigation": True,
-    "logo_only": True,
+    ]
 }
 
 html_static_path = ["_static"]

ontoaligner/base/dataset.py

@@ -1,4 +1,4 @@
-# Copyright 2025 Scientific Knowledge Organization (SciKnowOrg) Research Group. 
+# Copyright 2025 Scientific Knowledge Organization (SciKnowOrg) Research Group.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -19,7 +19,6 @@
     - OMDataset: A base class for handling ontology matching datasets, including parsing ontologies and alignments
                 and collecting dataset-related information.
 """
-import os
 import json
 from abc import ABC
 from typing import Any, Dict
@@ -95,17 +94,6 @@ def load_from_json(self, json_file_path: str) -> Dict:
             json_data = json.load(f)
         return json_data
 
-    def __dir__(self):
-        """
-        Returns the directory structure for the dataset.
-
-        This method constructs the directory path based on the track and ontology name.
-
-        Returns:
-            str: The constructed directory path for the dataset.
-        """
-        return os.path.join(self.track, self.ontology_name)
-
     def __str__(self):
         """
         Returns a string representation of the dataset's ontology name.
@@ -115,4 +103,4 @@ def __str__(self):
         Returns:
             str: The ontology name as a string.
         """
-        return f"{self.ontology_name}"
+        return f"Track: {self.track}, Source-Target sets: {self.ontology_name}"

ontoaligner/base/ontology.py

@@ -1,4 +1,4 @@
-# Copyright 2025 Scientific Knowledge Organization (SciKnowOrg) Research Group. 
+# Copyright 2025 Scientific Knowledge Organization (SciKnowOrg) Research Group.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -22,7 +22,7 @@
     - BaseAlignmentsParser: A base class for parsing alignment data, extracting relationships between
                             entities and their corresponding RDF data.
 """
-from abc import ABC, abstractmethod
+from abc import ABC
 from typing import Any, Dict, List
 
 
@@ -126,7 +126,6 @@ def get_synonyms(self, owl_class: Any) -> List:
         """
         return self.get_owl_items(owl_class.hasRelatedSynonym)
 
-    @abstractmethod
     def get_comments(self, owl_class: Any) -> List:
         """
         Abstract method to retrieve comments for the given ontology class.

ontoaligner/encoder/encoders.py

@@ -1,4 +1,4 @@
-# Copyright 2025 Scientific Knowledge Organization (SciKnowOrg) Research Group. 
+# Copyright 2025 Scientific Knowledge Organization (SciKnowOrg) Research Group.
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
 # you may not use this file except in compliance with the License.
@@ -23,7 +23,74 @@
 """
 from typing import Any, Dict
 
-from .encoders import LightweightEncoder
+from ..base import BaseEncoder
+
+class LightweightEncoder(BaseEncoder):
+    """
+    A lightweight encoder for parsing ontology data and preprocessing it.
+
+    This class provides methods for parsing ontological data, applying text preprocessing,
+    and formatting the data into a structure suitable for further processing.
+    """
+    def parse(self, **kwargs) -> Any:
+        """
+        Parses the source and target ontologies, applying preprocessing.
+
+        This method extracts ontology items (IRI and label) from the source and target ontologies,
+        applies text preprocessing to the labels, and returns the encoded data.
+
+        Parameters:
+            **kwargs: Contains the source and target ontologies as keyword arguments.
+
+        Returns:
+            list: A list containing two elements, the processed source and target ontologies.
+        """
+        source_onto, target_onto = kwargs["source"], kwargs["target"]
+        source_ontos = []
+        for source in source_onto:
+            encoded_source = self.get_owl_items(owl=source)
+            encoded_source["text"] = self.preprocess(encoded_source["text"])
+            source_ontos.append(encoded_source)
+        target_ontos = []
+        for target in target_onto:
+            encoded_target = self.get_owl_items(owl=target)
+            encoded_target["text"] = self.preprocess(encoded_target["text"])
+            target_ontos.append(encoded_target)
+        return [source_ontos, target_ontos]
+
+    def __str__(self):
+        """
+        Returns a string representation of the encoder.
+
+        Returns:
+            dict: A dictionary with the class name as key and items_in_owl as value.
+        """
+        return {"LightweightEncoder": self.items_in_owl}
+
+    def get_owl_items(self, owl: Dict) -> Any:
+        """
+        Abstract method for extracting ontology data.
+
+        This method should be implemented by subclasses to extract specific ontology data
+        (e.g., IRI and label) from the provided ontology item.
+
+        Parameters:
+            owl (Dict): A dictionary representing an ontology item.
+
+        Returns:
+            Any: The extracted ontology data.
+        """
+        pass
+
+    def get_encoder_info(self):
+        """
+        Provides information about the encoder.
+
+        Returns:
+            str: A description of the encoder's function in the overall pipeline.
+        """
+        return "INPUT CONSIST OF COMBINED INFORMATION TO FUZZY STRING MATCHING"
+
 
 class ConceptLightweightEncoder(LightweightEncoder):
     """