style(search): remove em dashes from PR2 comments/docstrings

src/documents/search/_backend.py

@@ -539,7 +539,7 @@ class TantivyBackend:
         if note_texts:
             doc.add_text("notes_text", " ".join(note_texts))
 
-        # Custom fields — JSON for structured queries (custom_fields.name:x,
+        # Custom fields: JSON for structured queries (custom_fields.name:x,
         # custom_fields.value:y). There is no companion text field here, unlike
         # notes: custom field values are reachable only through the JSON field.
         for cfi in document.custom_fields.all():

src/documents/search/_query.py

@@ -440,7 +440,7 @@ def parse_user_query(
        (notes.note:/custom_fields.value:) directly in the registry, via
        each JSON field's SubpathSpec(default=True).
     2. Any diagnostics (bad dates/numbers) map to SearchQueryError subclasses
-       and raise — the view returns HTTP 400 with every offending field
+       and raise, the view returns HTTP 400 with every offending field
        listed, not just the first.
     3. emit() turns the AST into a tantivy.Query directly (no string
        round-trip). A QueryError is routed by its Diagnostic's Cause
@@ -450,7 +450,7 @@ def parse_user_query(
     4. Optional fuzzy blend (ADVANCED_FUZZY_SEARCH_THRESHOLD) builds a
        plain word string from the parsed AST's free-text tokens
        (whoosh_compat.free_text_tokens) and feeds THAT to
-       index.parse_query — never raw_query, whose whoosh grammar (date
+       index.parse_query, never raw_query, whose whoosh grammar (date
        keywords, bracket-class wildcards, etc.) tantivy's parser rejects,
        which used to silently knock the fuzzy clause out of any mixed
        query (see _try_parse_fuzzy_query).

src/documents/tests/search/test_acceptance.py

@@ -1,6 +1,6 @@
 """Result-level acceptance corpus: real documents indexed via build_schema(),
 real queries run through parse_user_query(), matched-document-ID sets
-asserted — not intermediate ASTs or query strings. This is paperless-ngx's
+asserted, not intermediate ASTs or query strings. This is paperless-ngx's
 analogue of whoosh-compat's own tests/emitter/test_acceptance_e2e.py.
 
 Supersedes test_query.py's TestParseUserQuery result-level cases.
@@ -268,7 +268,7 @@ class TestFuzzyBlendSurvivesWhooshGrammar:
 
 class TestUnquotedDateKeywordPhrases:
     """The unquoted spelling (added:previous month) is honored natively by
-    whoosh-compat's own grammar for this closed phrase vocabulary — no
+    whoosh-compat's own grammar for this closed phrase vocabulary, no
     app-level rewrite is involved. Pins that the historically supported
     spelling keeps working now that paperless no longer pre-quotes it."""
 

src/documents/tests/search/test_date_keyword_phrase_removal.py

@@ -3,7 +3,7 @@ _quote_date_keyword_phrases rewrite.
 
 That rewrite matched date-keyword phrases (e.g. "previous month" after a
 date field) anywhere in the raw query string, including inside an
-unrelated quoted string, and inserted quotes mid-phrase there too — its
+unrelated quoted string, and inserted quotes mid-phrase there too. Its
 own docstring gave ``title:"see added:previous month notes"`` as the
 example of what it corrupted. whoosh-compat's grammar accepts the same
 phrase vocabulary unquoted natively (see TestUnquotedDateKeywordPhrases

src/documents/tests/search/test_query.py

@@ -119,7 +119,7 @@ class TestParseUserQuery:
         query_index: tantivy.Index,
     ) -> None:
         # parse_user_query never falls back to the raw query string on a parse
-        # error — a bad date diagnostic from whoosh-compat always maps to an
+        # error: a bad date diagnostic from whoosh-compat always maps to an
         # InvalidDateQuery and must propagate, so the view can return a 400
         # instead of silently parsing the raw (invalid) date.
         with pytest.raises(InvalidDateQuery) as exc_info:
@@ -154,7 +154,7 @@ class TestParseUserQuery:
         self,
         query_index: tantivy.Index,
     ) -> None:
-        # tag_id is intentionally excluded from the FieldRegistry — whoosh-compat
+        # tag_id is intentionally excluded from the FieldRegistry: whoosh-compat
         # parity leniency folds it into literal text, not a diagnostic/400.
         # A result-level assertion that this fold actually matches nothing
         # against real documents lives in