From fcc239ecdbd1467a4ac8b17a353e1b0ae7fd63a0 Mon Sep 17 00:00:00 2001
From: Boris Kolpackov <boris@codesynthesis.com>
Date: Tue, 6 Feb 2024 16:51:24 +0200
Subject: Map JSON null in subscript/iteration to [null] instead of empty

This in fact feels more natural in the "for consumption" model and also helps
with the nested subscript semantics.
---
 libbuild2/variable.cxx     | 47 ++++++++++++++++++++++++++++------------------
 tests/type/json/testscript | 20 ++++++++++++++------
 2 files changed, 43 insertions(+), 24 deletions(-)

diff --git a/libbuild2/variable.cxx b/libbuild2/variable.cxx
index 1785e56..1c899f9 100644
--- a/libbuild2/variable.cxx
+++ b/libbuild2/variable.cxx
@@ -1905,9 +1905,10 @@ namespace build2
     return l.as<json_value> ().compare (r.as<json_value> ());
   }
 
-  // Return null value if the index/name is out of range.
+  // Return the value as well as the indication of whether the index/name is
+  // in range.
   //
-  static value
+  static pair<value, bool>
   json_subscript_impl (const value& val, value* val_data,
                        uint64_t i, const string& n, bool index)
   {
@@ -1918,13 +1919,12 @@ namespace build2
     if (index)
     {
       if (i >= (jv.type == json_type::array  ? jv.array.size ()  :
-                jv.type == json_type::object ? jv.object.size () : 1))
-        return value ();
+                jv.type == json_type::object ? jv.object.size () :
+                jv.type == json_type::null   ? 0 : 1))
+        return make_pair (value (), false);
 
       switch (jv.type)
       {
-      case json_type::null:
-        return value (); // JSON null has no elements.
       case json_type::boolean:
       case json_type::signed_number:
       case json_type::unsigned_number:
@@ -1963,6 +1963,8 @@ namespace build2
                                : json_member (m));
           break;
         }
+      case json_type::null:
+        assert (false);
       }
     }
     else
@@ -1975,7 +1977,7 @@ namespace build2
                        }));
 
       if (i == jv.object.end ())
-        return value ();
+        return make_pair (value (), false);
 
       // Steal the member value if possible.
       //
@@ -1996,20 +1998,29 @@ namespace build2
     // @@ TODO: split this function into two (index/name) once get rid of this.
     //
 #if 1
+    value r;
     switch (jr.type)
     {
-    case json_type::null:               return value (names {});
-    case json_type::boolean:            return value (jr.boolean);
-    case json_type::signed_number:      return value (jr.signed_number);
+      // Seeing that we are reversing for consumption, it feels natural to
+      // reverse JSON null to our [null] rather than empty. This, in
+      // particular, helps nested subscript.
+      //
+#if 0
+    case json_type::null:               r = value (names {});          break;
+#else
+    case json_type::null:               r = value ();                  break;
+#endif
+    case json_type::boolean:            r = value (jr.boolean);        break;
+    case json_type::signed_number:      r = value (jr.signed_number);  break;
     case json_type::unsigned_number:
-    case json_type::hexadecimal_number: return value (jr.unsigned_number);
-    case json_type::string:             return value (move (jr.string));
+    case json_type::hexadecimal_number: r = value (jr.unsigned_number); break;
+    case json_type::string:             r = value (move (jr.string));   break;
     case json_type::array:
-    case json_type::object:             break;
+    case json_type::object:             r = value (move (jr));          break;
     }
 #endif
 
-    return value (move (jr));
+    return make_pair (move (r), true);
   }
 
   static value
@@ -2081,7 +2092,7 @@ namespace build2
     }
 
     value r (jv != nullptr
-             ? json_subscript_impl (val, val_data, i, n, index)
+             ? json_subscript_impl (val, val_data, i, n, index).first
              : value ());
 
     // Typify null values so that we get called for nested subscripts.
@@ -2100,12 +2111,12 @@ namespace build2
     //
     for (uint64_t i (0);; ++i)
     {
-      value e (json_subscript_impl (val, nullptr, i, {}, true));
+      pair<value, bool> e (json_subscript_impl (val, nullptr, i, {}, true));
 
-      if (e.null)
+      if (!e.second)
         break;
 
-      f (move (e), i == 0);
+      f (move (e.first), i == 0);
     }
   }
 
diff --git a/tests/type/json/testscript b/tests/type/json/testscript
index 2663a22..5295fbc 100644
--- a/tests/type/json/testscript
+++ b/tests/type/json/testscript
@@ -303,7 +303,7 @@
   print ($j[4])
   EOI
   2
-
+  [null]
   [null]
   EOO
 
@@ -316,7 +316,7 @@
   print ($j[five])
   EOI
   2
-
+  [null]
   [null]
   EOO
 
@@ -332,30 +332,38 @@
   : nested
   :
   $* <<EOI >>EOO
-  o = [json] one@([json] 1 2 ([json] a@3 b@4)) two@([json] x@x y@([json] 5 6))
+  o = [json] one@([json] 1 2 ([json] a@3 b@4) null) two@([json] x@x y@([json] 5 6))
   print ($o[one][1])
   print ($o[one][2][b])
   print ($o[two][y][1])
   print ($o[two][bogus][junk])
   print ($o[two][bogus][junk][garbage])
+  print ($o[one][3][junk]) # JSON null
+  print ($o[one][3][junk][garbage])
 
-  a = [json] ([json] one@1 two@([json] 2 3)) ([json] 4 5)
+  a = [json] ([json] one@1 two@([json] 2 3)) ([json] 4 5) null
   print ($a[0][one])
   print ($a[0][two][1])
   print ($a[1][1])
   print ($a[1][123][junk])
   print ($a[1][123][junk][garbage])
+  print ($a[2][junk]) # JSON null
+  print ($a[2][junk][garbage])
   EOI
   2
   4
   6
   [null]
   [null]
+  [null]
+  [null]
   1
   3
   5
   [null]
   [null]
+  [null]
+  [null]
   EOO
 
   : reverse
@@ -368,7 +376,7 @@
   print (([json] one@0xdecaf)[one])
   print (([json] one@abc)[one])
   EOI
-
+  [null]
   true
   123
   -123
@@ -435,7 +443,7 @@
   for v: ([json] null true 123 -123 0xdecaf abc)
     print $v
   EOI
-
+  [null]
   true
   123
   -123
-- 
cgit v1.1