From caf1e70b6a4852605c8a5a6de211688bb9359403 Mon Sep 17 00:00:00 2001
From: Will Holley <willholley@apache.org>
Date: Thu, 2 Nov 2023 11:11:23 +0000
Subject: [PATCH] add utf8 check

---
 src/mango/src/mango_idx_view.erl |  6 +++++-
 src/mango/src/mango_selector.erl | 12 ++++++++++--
 2 files changed, 15 insertions(+), 3 deletions(-)

diff --git a/src/mango/src/mango_idx_view.erl b/src/mango/src/mango_idx_view.erl
index 29895fbf9c6..671a61fa9c2 100644
--- a/src/mango/src/mango_idx_view.erl
+++ b/src/mango/src/mango_idx_view.erl
@@ -347,7 +347,7 @@ range(Selector, Index) ->
     range(Selector, Index, '$gt', mango_json:min(), '$lt', mango_json:max()).
 
 % Adjust Low and High based on values found for the
-% givend Index in Selector.
+% given Index in Selector.
 range({[{<<"$and">>, Args}]}, Index, LCmp, Low, HCmp, High) ->
     lists:foldl(
         fun
@@ -624,6 +624,10 @@ indexable_fields_gte_test() ->
     Selector = #{<<"field">> => #{<<"$gte">> => undefined}},
     ?assertEqual([<<"field">>], indexable_fields_of(Selector)).
 
+indexable_fields_beginswith_test() ->
+    Selector = #{<<"field">> => #{<<"$beginsWith">> => undefined}},
+    ?assertEqual([<<"field">>], indexable_fields_of(Selector)).
+
 indexable_fields_gt_test() ->
     Selector = #{<<"field">> => #{<<"$gt">> => undefined}},
     ?assertEqual([<<"field">>], indexable_fields_of(Selector)).
diff --git a/src/mango/src/mango_selector.erl b/src/mango/src/mango_selector.erl
index 93d3b10ca6c..307efddc449 100644
--- a/src/mango/src/mango_selector.erl
+++ b/src/mango/src/mango_selector.erl
@@ -136,7 +136,10 @@ norm_ops({[{<<"$text">>, Arg}]}) when
 norm_ops({[{<<"$text">>, Arg}]}) ->
     ?MANGO_ERROR({bad_arg, '$text', Arg});
 norm_ops({[{<<"$beginsWith">>, Arg}]} = Cond) when is_binary(Arg) ->
-    Cond;
+    case couch_util:validate_utf8(Arg) of
+        true -> Cond;
+        false -> ?MANGO_ERROR({bad_arg, '$beginsWith', Arg})
+    end;
 % Not technically an operator but we pass it through here
 % so that this function accepts its own output. This exists
 % so that $text can have a field name value which simplifies
@@ -1070,12 +1073,17 @@ check_beginswith(Field, Prefix) ->
 match_beginswith_test() ->
     % matching
     ?assertEqual(true, check_beginswith(<<"_id">>, <<"f">>)),
-    % no match (user_id is not a binary string)
+    % no match (user_id field in the test doc contains an integer)
     ?assertEqual(false, check_beginswith(<<"user_id">>, <<"f">>)),
     % invalid (prefix is not a binary string)
     ?assertThrow(
         {mango_error, mango_selector, {invalid_operator, <<"$beginsWith">>}},
         check_beginswith(<<"user_id">>, 1)
+    ),
+    % invalid (prefix is not a utf8 string)
+    ?assertThrow(
+        {mango_error, mango_selector, {invalid_operator, <<"$beginsWith">>}},
+        check_beginswith(<<123>>, 1)
     ).
 
 -endif.