Test search uses ancestor headings as context for improved results

- Update test data to add deeper outline hierarchy for testing
  hierarchy as context
- Update collateral tests that need count of entries updated, deleted
  asserts to be updated

tests/conftest.py

@@ -386,6 +386,44 @@ def sample_org_data():
 def get_sample_data(type):
     sample_data = {
         "org": {
+            "elisp.org": """
+* Emacs Khoj
+  /An Emacs interface for [[https://github.com/khoj-ai/khoj][khoj]]/
+
+** Requirements
+   - Install and Run [[https://github.com/khoj-ai/khoj][khoj]]
+
+** Installation
+*** Direct
+     - Put ~khoj.el~ in your Emacs load path. For e.g ~/.emacs.d/lisp
+     - Load via ~use-package~ in your ~/.emacs.d/init.el or .emacs file by adding below snippet
+       #+begin_src elisp
+         ;; Khoj Package
+         (use-package khoj
+           :load-path "~/.emacs.d/lisp/khoj.el"
+           :bind ("C-c s" . 'khoj))
+       #+end_src
+
+*** Using [[https://github.com/quelpa/quelpa#installation][Quelpa]]
+     - Ensure [[https://github.com/quelpa/quelpa#installation][Quelpa]], [[https://github.com/quelpa/quelpa-use-package#installation][quelpa-use-package]] are installed
+     - Add below snippet to your ~/.emacs.d/init.el or .emacs config file and execute it.
+       #+begin_src elisp
+         ;; Khoj Package
+         (use-package khoj
+           :quelpa (khoj :fetcher url :url "https://raw.githubusercontent.com/khoj-ai/khoj/master/interface/emacs/khoj.el")
+           :bind ("C-c s" . 'khoj))
+       #+end_src
+
+** Usage
+   1. Call ~khoj~ using keybinding ~C-c s~ or ~M-x khoj~
+   2. Enter Query in Natural Language
+      e.g "What is the meaning of life?" "What are my life goals?"
+   3. Wait for results
+      *Note: It takes about 15s on a Mac M1 and a ~100K lines corpus of org-mode files*
+   4. (Optional) Narrow down results further
+      Include/Exclude specific words from results by adding to query
+
+""",
             "readme.org": """
 * Khoj
   /Allow natural language search on user content like notes, images using transformer based models/
@@ -401,7 +439,7 @@ def get_sample_data(type):
    git clone https://github.com/khoj-ai/khoj && cd khoj
    conda env create -f environment.yml
    conda activate khoj
-   #+end_src"""
+   #+end_src""",
         },
         "markdown": {
             "readme.markdown": """

tests/data/org/interface_emacs_readme.org

@@ -5,7 +5,7 @@
    - Install and Run [[https://github.com/khoj-ai/khoj][khoj]]
 
 ** Installation
-   - Direct Install
+*** Direct
      - Put ~khoj.el~ in your Emacs load path. For e.g ~/.emacs.d/lisp
 
      - Load via ~use-package~ in your ~/.emacs.d/init.el or .emacs file by adding below snippet
@@ -16,7 +16,7 @@
            :bind ("C-c s" . 'khoj))
        #+end_src
 
-   - Use [[https://github.com/quelpa/quelpa#installation][Quelpa]]
+*** Using [[https://github.com/quelpa/quelpa#installation][Quelpa]]
      - Ensure [[https://github.com/quelpa/quelpa#installation][Quelpa]], [[https://github.com/quelpa/quelpa-use-package#installation][quelpa-use-package]] are installed
      - Add below snippet to your ~/.emacs.d/init.el or .emacs config file and execute it.
        #+begin_src elisp

tests/data/org/main_readme.org

@@ -22,16 +22,16 @@
    #+end_src
 
 ** Use
-   - *Khoj via Emacs*
+*** *Khoj via Emacs*
      - [[https://github.com/khoj-ai/khoj/tree/master/interface/emacs#installation][Install]] [[./interface/emacs/khoj.el][khoj.el]]
      - Run ~M-x khoj <user-query>~ or Call ~C-c C-s~
 
-   - *Khoj via API*
+*** *Khoj via API*
      - Query: ~GET~ [[http://localhost:42110/api/search?q=%22what%20is%20the%20meaning%20of%20life%22][http://localhost:42110/api/search?q="What is the meaning of life"]]
      - Update Index: ~GET~ [[http://localhost:42110/api/update][http://localhost:42110/api/update]]
      - [[http://localhost:42110/docs][Khoj API Docs]]
 
-   - *Call Khoj via Python Script Directly*
+*** *Call Khoj via Python Script Directly*
      #+begin_src shell
      python3 search_types/asymmetric.py \
      --compressed-jsonl .notes.jsonl.gz \

tests/test_client.py

@@ -321,7 +321,7 @@ def test_notes_search_with_include_filter(client, sample_org_data, default_user:
     assert response.status_code == 200
     # assert actual_data contains word "Emacs"
     search_result = response.json()[0]["entry"]
-    assert "Emacs" in search_result
+    assert "emacs" in search_result
 
 
 # ----------------------------------------------------------------------------------------------------
@@ -347,6 +347,27 @@ def test_notes_search_with_exclude_filter(client, sample_org_data, default_user:
     assert "clone" not in search_result
 
 
+# ----------------------------------------------------------------------------------------------------
+@pytest.mark.django_db(transaction=True)
+def test_notes_search_requires_parent_context(
+    client, search_config: SearchConfig, sample_org_data, default_user: KhojUser
+):
+    # Arrange
+    headers = {"Authorization": "Bearer kk-secret"}
+    text_search.setup(OrgToEntries, sample_org_data, regenerate=False, user=default_user)
+    user_query = quote("Install Khoj on Emacs")
+
+    # Act
+    response = client.get(f"/api/search?q={user_query}&n=1&t=org&r=true&max_distance=0.18", headers=headers)
+
+    # Assert
+    assert response.status_code == 200
+
+    assert len(response.json()) == 1, "Expected only 1 result"
+    search_result = response.json()[0]["entry"]
+    assert "Emacs load path" in search_result, "Expected 'Emacs load path' in search result"
+
+
 # ----------------------------------------------------------------------------------------------------
 @pytest.mark.django_db(transaction=True)
 def test_different_user_data_not_accessed(client, sample_org_data, default_user: KhojUser):

tests/test_multiple_users.py

@@ -69,7 +69,7 @@ def test_index_update_with_user2_inaccessible_user1(client, api_user2: KhojApiUs
 
     # Assert
     assert update_response.status_code == 200
-    assert len(results) == 4
+    assert len(results) == 5
     for result in results:
         assert result["additional"]["file"] not in source_file_symbol
 

tests/test_text_search.py

@@ -70,7 +70,7 @@ def test_text_search_setup_with_empty_file_creates_no_entries(
         text_search.setup(OrgToEntries, data, regenerate=True, user=default_user)
 
     # Assert
-    assert "Deleted 3 entries. Created 0 new entries for user " in caplog.records[-1].message
+    assert "Deleted 8 entries. Created 0 new entries for user " in caplog.records[-1].message
     verify_embeddings(0, default_user)
 
 
@@ -90,7 +90,7 @@ def test_text_indexer_deletes_embedding_before_regenerate(
 
     # Assert
     assert "Deleting all entries for file type org" in caplog.text
-    assert "Deleted 3 entries. Created 10 new entries for user " in caplog.records[-1].message
+    assert "Deleted 8 entries. Created 13 new entries for user " in caplog.records[-1].message
 
 
 # ----------------------------------------------------------------------------------------------------
@@ -106,7 +106,7 @@ def test_text_search_setup_batch_processes(content_config: ContentConfig, defaul
         text_search.setup(OrgToEntries, data, regenerate=True, user=default_user)
 
     # Assert
-    assert "Deleted 3 entries. Created 10 new entries for user " in caplog.records[-1].message
+    assert "Deleted 8 entries. Created 13 new entries for user " in caplog.records[-1].message
 
 
 # ----------------------------------------------------------------------------------------------------
@@ -284,9 +284,9 @@ def test_regenerate_index_with_new_entry(
     final_logs = caplog.text
 
     # Assert
-    assert "Deleted 3 entries. Created 10 new entries for user " in initial_logs
+    assert "Deleted 8 entries. Created 13 new entries for user " in initial_logs
-    assert "Deleted 10 entries. Created 11 new entries for user " in final_logs
+    assert "Deleted 13 entries. Created 14 new entries for user " in final_logs
-    verify_embeddings(11, default_user)
+    verify_embeddings(14, default_user)
 
 
 # ----------------------------------------------------------------------------------------------------
@@ -320,7 +320,7 @@ def test_update_index_with_duplicate_entries_in_stable_order(
 
     # Assert
     # verify only 1 entry added even if there are multiple duplicate entries
-    assert "Deleted 3 entries. Created 1 new entries for user " in initial_logs
+    assert "Deleted 8 entries. Created 1 new entries for user " in initial_logs
     assert "Deleted 0 entries. Created 0 new entries for user " in final_logs
 
     verify_embeddings(1, default_user)
@@ -357,7 +357,7 @@ def test_update_index_with_deleted_entry(org_config_with_only_new_file: LocalOrg
 
     # Assert
     # verify only 1 entry added even if there are multiple duplicate entries
-    assert "Deleted 3 entries. Created 2 new entries for user " in initial_logs
+    assert "Deleted 8 entries. Created 2 new entries for user " in initial_logs
     assert "Deleted 1 entries. Created 0 new entries for user " in final_logs
 
     verify_embeddings(1, default_user)
@@ -388,9 +388,9 @@ def test_update_index_with_new_entry(content_config: ContentConfig, new_org_file
     final_logs = caplog.text
 
     # Assert
-    assert "Deleted 3 entries. Created 10 new entries for user " in initial_logs
+    assert "Deleted 8 entries. Created 13 new entries for user " in initial_logs
     assert "Deleted 0 entries. Created 1 new entries for user " in final_logs
-    verify_embeddings(11, default_user)
+    verify_embeddings(14, default_user)
 
 
 # ----------------------------------------------------------------------------------------------------