Decouple results shown to user and text the model is trained on

- Previously:
  The text the model was trained on was being used to
  re-create a semblance of the original org-mode entry.

- Now:
  - Store raw entry as another key:value in each entry json too
    Only return actual raw org entries in results
    But create embeddings like before
  - Also add link to entry in file:<filename>::<line_number> form
    in property drawer of returned results
    This can be used to jump to actual entry in it's original file

src/processor/org_mode/org_to_jsonl.py

@@ -120,15 +120,9 @@ def convert_org_entries_to_jsonl(entries, verbose=0):
             if verbose > 2:
                 print(f"Body: {entry.Body()}")
 
-        for property_key in ('ID', 'QUERY', 'TYPE', 'CATEGORY'):
-            if entry.Property(property_key):
-                if 'Property' not in entry_dict:
-                    entry_dict['Property'] = dict()
-                entry_dict['Property'][property_key] = entry.Property(property_key)
-                if verbose > 2:
-                    print(f'Property: {entry_dict["PROPERTY"][property_key]}')
-
         if entry_dict:
+            entry_dict["Raw"] = f'{entry}'
+
             # Convert Dictionary to JSON and Append to JSONL string
             jsonl += f'{json.dumps(entry_dict, ensure_ascii=False)}\n'
 

src/processor/org_mode/orgnode.py

@@ -77,7 +77,7 @@ def makelist(filename):
                 deadline_date = ''
              thisNode.setProperties(propdict)
              nodelist.append( thisNode )
-             propdict = dict()
+             propdict = {'SOURCE': f'file:{filename}::{ctr}'}
           level = hdng.group(1)
           heading =  hdng.group(2)
           bodytext = ""
@@ -325,8 +325,14 @@ class Orgnode(object):
            n = n + ':' + t
            closecolon = ':'
         n = n + closecolon
-# Need to output Scheduled Date, Deadline Date, property tags The
-# following will output the text used to construct the object
-        n = n + "\n" + self.body
+        # Need to output Scheduled Date, Deadline Date, property tags The
+        # following will output the text used to construct the object
+        n = n + "\n"
+        n = n + ":PROPERTIES:\n"
+        for key, value in self.properties.items():
+           n = n + f":{key}: {value}\n"
+        n = n + ":END:\n"
+
+        n = n + self.body
 
         return n