Add file of each entry to entry dict in org_to_jsonl converter

- This will help filter query to org content type using file filter
- Do not explicitly specify items being extracted from json of each
  entry in text_search as all text search content types do not have
  file being set in jsonl converters

src/processor/org_mode/org_to_jsonl.py

@@ -28,10 +28,10 @@ def org_to_jsonl(org_files, org_file_filter, output_file):
     org_files = get_org_files(org_files, org_file_filter)
 
     # Extract Entries from specified Org files
-    entries = extract_org_entries(org_files)
+    entries, file_to_entries = extract_org_entries(org_files)
 
     # Process Each Entry from All Notes Files
-    jsonl_data = convert_org_entries_to_jsonl(entries)
+    jsonl_data = convert_org_entries_to_jsonl(entries, file_to_entries)
 
     # Compress JSONL formatted Data
     if output_file.suffix == ".gz":
@@ -66,18 +66,19 @@ def get_org_files(org_files=None, org_file_filter=None):
 def extract_org_entries(org_files):
     "Extract entries from specified Org files"
     entries = []
+    entry_to_file_map = []
     for org_file in org_files:
-        entries.extend(
-            orgnode.makelist(
-                str(org_file)))
+        org_file_entries = orgnode.makelist(str(org_file))
+        entry_to_file_map += [org_file]*len(org_file_entries)
+        entries.extend(org_file_entries)
 
-    return entries
+    return entries, entry_to_file_map
 
 
-def convert_org_entries_to_jsonl(entries) -> str:
+def convert_org_entries_to_jsonl(entries, entry_to_file_map) -> str:
     "Convert each Org-Mode entries to JSON and collate as JSONL"
     jsonl = ''
-    for entry in entries:
+    for entry_id, entry in enumerate(entries):
         entry_dict = dict()
 
         # Ignore title notes i.e notes with just headings and empty body
@@ -106,6 +107,7 @@ def convert_org_entries_to_jsonl(entries) -> str:
 
         if entry_dict:
             entry_dict["raw"] = f'{entry}'
+            entry_dict["file"] = f'{entry_to_file_map[entry_id]}'
 
             # Convert Dictionary to JSON and Append to JSONL string
             jsonl += f'{json.dumps(entry_dict, ensure_ascii=False)}\n'

src/search_type/text_search.py

@@ -52,9 +52,7 @@ def initialize_model(search_config: TextSearchConfig):
 
 def extract_entries(jsonl_file):
     "Load entries from compressed jsonl"
-    return [{'compiled': f'{entry["compiled"]}', 'raw': f'{entry["raw"]}'}
-            for entry
-            in load_jsonl(jsonl_file)]
+    return load_jsonl(jsonl_file)
 
 
 def compute_embeddings(entries, bi_encoder, embeddings_file, regenerate=False):
@@ -83,7 +81,7 @@ def query(raw_query: str, model: TextSearchModel, rank_results=False):
     for filter in filters_in_query:
         query, entries, corpus_embeddings = filter.apply(query, entries, corpus_embeddings)
     end = time.time()
-    logger.debug(f"Filter Time: {end - start:.3f} seconds")
+    logger.debug(f"Total Filter Time: {end - start:.3f} seconds")
 
     if entries is None or len(entries) == 0:
         return [], []

tests/test_org_to_jsonl.py

@@ -21,10 +21,10 @@ def test_entry_with_empty_body_line_to_jsonl(tmp_path):
 
     # Act
     # Extract Entries from specified Org files
-    entries = extract_org_entries(org_files=[orgfile])
+    entries, entry_to_file_map = extract_org_entries(org_files=[orgfile])
 
     # Process Each Entry from All Notes Files
-    jsonl_data = convert_org_entries_to_jsonl(entries)
+    jsonl_data = convert_org_entries_to_jsonl(entries, entry_to_file_map)
 
     # Assert
     assert is_none_or_empty(jsonl_data)
@@ -43,10 +43,10 @@ def test_entry_with_body_to_jsonl(tmp_path):
 
     # Act
     # Extract Entries from specified Org files
-    entries = extract_org_entries(org_files=[orgfile])
+    entries, entry_to_file_map = extract_org_entries(org_files=[orgfile])
 
     # Process Each Entry from All Notes Files
-    jsonl_string = convert_org_entries_to_jsonl(entries)
+    jsonl_string = convert_org_entries_to_jsonl(entries, entry_to_file_map)
     jsonl_data = [json.loads(json_string) for json_string in jsonl_string.splitlines()] 
 
     # Assert