implode: Better invalid input validation and handling

src/builtin.c

@@ -1201,7 +1201,28 @@ static jv f_string_implode(jq_state *jq, jv a) {
   if (jv_get_kind(a) != JV_KIND_ARRAY) {
     return ret_error(a, jv_string("implode input must be an array"));
   }
-  return jv_string_implode(a);
+
+  int len = jv_array_length(jv_copy(a));
+  jv s = jv_string_empty(len);
+
+  for (int i = 0; i < len; i++) {
+    jv n = jv_array_get(jv_copy(a), i);
+    if (jv_get_kind(n) != JV_KIND_NUMBER || jvp_number_is_nan(n)) {
+      jv_free(a);
+      jv_free(s);
+      return type_error(n, "can't be imploded, unicode codepoint needs to be numeric");
+    }
+
+    int nv = jv_number_value(n);
+    jv_free(n);
+    // outside codepoint range or in utf16 surrogate pair range
+    if (nv < 0 || nv > 0x10FFFF || (nv >= 0xD800 && nv <= 0xDFFF))
+      nv = 0xFFFD; // U+FFFD REPLACEMENT CHARACTER
+    s = jv_string_append_codepoint(s, nv);
+  }
+
+  jv_free(a);
+  return s;
 }
 
 static jv f_setpath(jq_state *jq, jv a, jv b, jv c) { return jv_setpath(a, b, c); }

src/jv.c

@@ -1368,7 +1368,8 @@ jv jv_string_implode(jv j) {
     assert(JVP_HAS_KIND(n, JV_KIND_NUMBER));
     int nv = jv_number_value(n);
     jv_free(n);
-    if (nv > 0x10FFFF)
+    // outside codepoint range or in utf16 surrogate pair range
+    if (nv < 0 || nv > 0x10FFFF || (nv >= 0xD800 && nv <= 0xDFFF))
       nv = 0xFFFD; // U+FFFD REPLACEMENT CHARACTER
     s = jv_string_append_codepoint(s, nv);
   }

src/jv.h

@@ -63,6 +63,7 @@ jv jv_number(double);
 jv jv_number_with_literal(const char*);
 double jv_number_value(jv);
 int jv_is_integer(jv);
+int jvp_number_is_nan(jv);
 
 int jv_number_has_literal(jv n);
 const char* jv_number_get_literal(jv);

src/jv_type_private.h

@@ -2,6 +2,5 @@
 #define JV_TYPE_PRIVATE
 
 int jvp_number_cmp(jv, jv);
-int jvp_number_is_nan(jv);
 
 #endif //JV_TYPE_PRIVATE

tests/jq.test

@@ -1914,3 +1914,14 @@ any(keys[]|tostring?;true)
 {"a":"1","b":"2","c":"3"}
 true
 
+
+# explode/implode
+# test replacement character (65533) for outside codepoint range and 0xd800 (55296) - 0xdfff (57343) utf16 surrogate pair range
+# 1.1 and 1.9 to test round down of non-ints
+implode|explode
+[-1,0,1,2,3,1114111,1114112,55295,55296,57343,57344,1.1,1.9]
+[65533,0,1,2,3,1114111,65533,55295,65533,65533,57344,1,1]
+
+map(try implode catch .)
+[123,["a"],[nan]]
+["implode input must be an array","string (\"a\") can't be imploded, unicode codepoint needs to be numeric","number (null) can't be imploded, unicode codepoint needs to be numeric"]