Support exclusion file filters (#826)

### Overview
Support exclude file filter in user search queries

### Details
- All of the exclude file filter terms need to be satisfied
- Any one of the include file filter terms should be satisfied

### Example
- **Search Query**: *what happened yesterday? -file:"tasks.org" -file:"work.md" file:"diary.org" file:"journal.org*
- **Behavior**: Query will try find relevant notes in any of `journal.org` or `diary.org` and not in `tasks.org` and not in `work.md`

### Details
* Add support for exclusion file filters
* Translate file filter to valid Django DB entry filter regex
* Exclude all files when multiple exclude file filter in query

Previously we were applying an "Or" filter, which would exclude any
file mentioned in a query with multiple exclude file filter.

This is not what we naturally mean when we ask excluding a file in a query

* Rename, rearrange, deduplicate and add file filter tests

Closes #728
---------

Co-authored-by: Debanjum Singh Solanky <debanjum@gmail.com>

src/khoj/database/adapters/__init__.py

@@ -1048,7 +1048,7 @@ class FileObjectAdapters:
 
 
 class EntryAdapters:
-    word_filer = WordFilter()
+    word_filter = WordFilter()
     file_filter = FileFilter()
     date_filter = DateFilter()
 
@@ -1150,14 +1150,14 @@ class EntryAdapters:
     def apply_filters(user: KhojUser, query: str, file_type_filter: str = None):
         q_filter_terms = Q()
 
-        explicit_word_terms = EntryAdapters.word_filer.get_filter_terms(query)
+        word_filters = EntryAdapters.word_filter.get_filter_terms(query)
         file_filters = EntryAdapters.file_filter.get_filter_terms(query)
         date_filters = EntryAdapters.date_filter.get_query_date_range(query)
 
-        if len(explicit_word_terms) == 0 and len(file_filters) == 0 and len(date_filters) == 0:
+        if len(word_filters) == 0 and len(file_filters) == 0 and len(date_filters) == 0:
             return Entry.objects.filter(user=user)
 
-        for term in explicit_word_terms:
+        for term in word_filters:
             if term.startswith("+"):
                 q_filter_terms &= Q(raw__icontains=term[1:])
             elif term.startswith("-"):
@@ -1167,7 +1167,16 @@ class EntryAdapters:
 
         if len(file_filters) > 0:
             for term in file_filters:
-                q_file_filter_terms |= Q(file_path__regex=term)
+                if term.startswith("-"):
+                    # Convert the glob term to a regex pattern
+                    regex_term = re.escape(term[1:]).replace(r"\*", ".*").replace(r"\?", ".")
+                    # Exclude all files that match the regex term
+                    q_file_filter_terms &= ~Q(file_path__regex=regex_term)
+                else:
+                    # Convert the glob term to a regex pattern
+                    regex_term = re.escape(term).replace(r"\*", ".*").replace(r"\?", ".")
+                    # Include any files that match the regex term
+                    q_file_filter_terms |= Q(file_path__regex=regex_term)
 
             q_filter_terms &= q_file_filter_terms
 
@@ -1182,9 +1191,7 @@ class EntryAdapters:
                 formatted_max_date = date.fromtimestamp(max_date).strftime("%Y-%m-%d")
                 q_filter_terms &= Q(embeddings_dates__date__lte=formatted_max_date)
 
-        relevant_entries = Entry.objects.filter(user=user).filter(
-            q_filter_terms,
-        )
+        relevant_entries = Entry.objects.filter(user=user).filter(q_filter_terms)
         if file_type_filter:
             relevant_entries = relevant_entries.filter(file_type=file_type_filter)
         return relevant_entries

src/khoj/search_filter/file_filter.py

@@ -11,7 +11,8 @@ logger = logging.getLogger(__name__)
 
 
 class FileFilter(BaseFilter):
-    file_filter_regex = r'file:"(.+?)" ?'
+    file_filter_regex = r'(?<!-)file:"(.+?)" ?'
+    excluded_file_filter_regex = r'-file:"(.+?)" ?'
 
     def __init__(self, entry_key="file"):
         self.entry_key = entry_key
@@ -20,7 +21,9 @@ class FileFilter(BaseFilter):
 
     def get_filter_terms(self, query: str) -> List[str]:
         "Get all filter terms in query"
-        return [f"{self.convert_to_regex(term)}" for term in re.findall(self.file_filter_regex, query)]
+        required_files = [f"{required_file}" for required_file in re.findall(self.file_filter_regex, query)]
+        excluded_files = [f"-{excluded_file}" for excluded_file in re.findall(self.excluded_file_filter_regex, query)]
+        return required_files + excluded_files
 
     def convert_to_regex(self, file_filter: str) -> str:
         "Convert file filter to regex"

tests/test_file_filter.py

@@ -3,7 +3,7 @@ from khoj.search_filter.file_filter import FileFilter
 from khoj.utils.rawconfig import Entry
 
 
-def test_no_file_filter():
+def test_can_filter_no_file_filter():
     # Arrange
     file_filter = FileFilter()
     q_with_no_filter = "head tail"
@@ -15,76 +15,114 @@ def test_no_file_filter():
     assert can_filter == False
 
 
-def test_file_filter_with_non_existent_file():
+def test_can_filter_non_existent_file():
     # Arrange
     file_filter = FileFilter()
-    q_with_no_filter = 'head file:"nonexistent.org" tail'
+    q_with_filter = 'head file:"nonexistent.org" tail'
 
     # Act
-    can_filter = file_filter.can_filter(q_with_no_filter)
+    can_filter = file_filter.can_filter(q_with_filter)
 
     # Assert
     assert can_filter == True
 
 
-def test_single_file_filter():
+def test_can_filter_single_file_include():
     # Arrange
     file_filter = FileFilter()
-    q_with_no_filter = 'head file:"file 1.org" tail'
+    q_with_filter = 'head file:"file 1.org" tail'
 
     # Act
-    can_filter = file_filter.can_filter(q_with_no_filter)
+    can_filter = file_filter.can_filter(q_with_filter)
 
     # Assert
     assert can_filter == True
 
 
-def test_file_filter_with_partial_match():
+def test_can_filter_single_file_exclude():
     # Arrange
     file_filter = FileFilter()
-    q_with_no_filter = 'head file:"1.org" tail'
+    q_with_filter = 'head -file:"1.org" tail'
 
     # Act
-    can_filter = file_filter.can_filter(q_with_no_filter)
+    can_filter = file_filter.can_filter(q_with_filter)
 
     # Assert
     assert can_filter == True
 
 
-def test_file_filter_with_regex_match():
+def test_can_filter_file_with_regex_match():
     # Arrange
     file_filter = FileFilter()
-    q_with_no_filter = 'head file:"*.org" tail'
+    q_with_filter = 'head file:"*.org" tail'
 
     # Act
-    can_filter = file_filter.can_filter(q_with_no_filter)
+    can_filter = file_filter.can_filter(q_with_filter)
 
     # Assert
     assert can_filter == True
 
 
-def test_multiple_file_filter():
+def test_can_filter_multiple_file_includes():
     # Arrange
     file_filter = FileFilter()
-    q_with_no_filter = 'head tail file:"file 1.org" file:"file2.org"'
+    q_with_filter = 'head tail file:"file 1.org" file:"file2.org"'
 
     # Act
-    can_filter = file_filter.can_filter(q_with_no_filter)
+    can_filter = file_filter.can_filter(q_with_filter)
 
     # Assert
     assert can_filter == True
 
 
-def test_get_file_filter_terms():
+def test_get_single_include_file_filter_terms():
     # Arrange
     file_filter = FileFilter()
-    q_with_filter_terms = 'head tail file:"file 1.org" file:"/path/to/dir/*.org"'
+    q_with_filter_terms = 'head tail file:"/path/to/dir/*.org"'
 
     # Act
     filter_terms = file_filter.get_filter_terms(q_with_filter_terms)
 
     # Assert
-    assert filter_terms == ["file 1\\.org", "/path/to/dir/.*\\.org"]
+    assert filter_terms == ["/path/to/dir/*.org"]
+
+
+def test_get_single_exclude_file_filter_terms():
+    # Arrange
+    file_filter = FileFilter()
+    q_with_filter_terms = 'head tail -file:"file 1.org"'
+
+    # Act
+    filter_terms = file_filter.get_filter_terms(q_with_filter_terms)
+
+    # Assert
+    assert filter_terms == ["-file 1.org"]
+
+
+def test_get_single_include_exclude_file_filter_terms():
+    # Arrange
+    file_filter = FileFilter()
+    q_with_filter_terms = 'head tail -file:"file 1.org" file:"/path/to/dir/*.org"'
+
+    # Act
+    filter_terms = file_filter.get_filter_terms(q_with_filter_terms)
+
+    # Assert
+    assert filter_terms == ["/path/to/dir/*.org", "-file 1.org"]
+
+
+def test_get_multiple_include_exclude_file_filter_terms():
+    # Arrange
+    file_filter = FileFilter()
+    q_with_filter_terms = (
+        'head -file:"file 1.org" file:"file 1.org" file:"/path/to/dir/.*.org" -file:"/path/to/dir/*.org" tail'
+    )
+
+    # Act
+    filter_terms = file_filter.get_filter_terms(q_with_filter_terms)
+
+    # Assert
+    assert filter_terms == ["file 1.org", "/path/to/dir/.*.org", "-file 1.org", "-/path/to/dir/*.org"]
 
 
 def arrange_content():