modify json

examples/confluence-reader/README.md

@@ -25,28 +25,20 @@ It follows this structured format:
         "metadata": {
             "title": "Page Title",
             "id": "Page ID",
-            "source": "Source URL"
+            "source": "Source URL",
+            "deleted": false
         },
-        "page_content": "Page Content Text",
-        "deleted": false
+        "data": "Page Content Text"
     },
     {
         "metadata": {
             "title": "Another Page Title",
             "id": "Another Page ID",
-            "source": "Another Source URL"
+            "source": "Another Source URL",
+            "deleted": true
         },
-        "page_content": "Another Page Content Text",
-        "deleted": false
-    },
-    {
-        "metadata": {
-            "title": "Yet Another Page Title",
-            "id": "Yet Another Page ID",
-            "source": "Yet Another Source URL"
-        },
-        "page_content": "Yet Another Page Content Text",
-        "deleted": false
+        "data": "Another Page Content Text"
     }
 ]
+
 ```

examples/confluence-reader/confluence_data.json

@@ -0,0 +1 @@
+[]

examples/confluence-reader/confluence_document.py

@@ -1,39 +1,36 @@
-
 class ConfluenceDocument:
-    def __init__(self, metadata, page_content, deleted=False):
+    def __init__(self, metadata, data, deleted=False):
         """
         Initializes a ConfluenceDocument instance.
 
         :param metadata: A dictionary containing metadata about the Confluence document.
                          Expected to contain 'title', 'id', and 'source'.
-        :param page_content: A string representing the content of the Confluence page.
-        :param deleted: A boolean indicating whether the document is considered deleted.
+                         'deleted' key will be added to indicate if the document is considered deleted.
+        :param data: A string representing the content of the Confluence page.
         """
         self.validate_metadata(metadata)
+        metadata['deleted'] = deleted
         self.metadata = metadata
-        self.page_content = page_content
-        self.deleted = deleted
+        self.data = data
 
     def serialize(self):
         """
         Serializes the ConfluenceDocument instance into a dictionary.
         """
         return {
             'metadata': self.metadata,
-            'page_content': self.page_content,
-            'deleted': self.deleted
+            'data': self.data
         }
 
     @staticmethod
     def validate_metadata(metadata):
         """
-        Validates the metadata dictionary to ensure it contains required keys.
+        Validates the metadata dictionary to ensure it contains required keys plus checks for 'deleted'.
 
         :param metadata: A dictionary containing metadata about the Confluence document.
-        :raises ValueError: If metadata does not contain the required keys.
+        :raises ValueError: If metadata does not contain the required keys ('title', 'id', 'source').
         """
         required_keys = {'title', 'id', 'source'}
         if not required_keys.issubset(metadata):
             missing_keys = required_keys - metadata.keys()
             raise ValueError(f"Metadata is missing required keys: {missing_keys}")
-

examples/confluence-reader/fetch_confluence_space.py

@@ -35,7 +35,7 @@ def update_saved_documents(file_path, new_docs):
     existing_docs = read_json_file(file_path) or []
 
     if isinstance(existing_docs, list) and existing_docs and isinstance(existing_docs[0], dict):
-        existing_docs = [ConfluenceDocument(doc['metadata'], doc['page_content'], doc.get('deleted', False)) for doc in existing_docs]
+        existing_docs = [ConfluenceDocument(doc['metadata'], doc['data'], doc['metadata'].get('deleted', False)) for doc in existing_docs]
 
     existing_docs_dict = {doc.metadata['id']: doc for doc in existing_docs}
 
@@ -54,13 +54,13 @@ def flag_deleted_pages(file_path, current_confluence_documents):
         log.error("Existing documents not found. Exiting.")
         return
 
-    existing_docs = [ConfluenceDocument(doc['metadata'], doc['page_content'], doc.get('deleted', False)) for doc in existing_docs]
+    existing_docs = [ConfluenceDocument(doc['metadata'], doc['data'], doc['metadata'].get('deleted', False)) for doc in existing_docs]
 
     current_page_ids = {doc.metadata['id'] for doc in current_confluence_documents}
 
     for doc in existing_docs:
         if doc.metadata['id'] not in current_page_ids:
-            doc.deleted = True
+            doc.metadata['deleted'] = True
 
     serialized_docs = [doc.serialize() for doc in existing_docs]
     write_json_file(file_path, serialized_docs)