Convert json_in and jsonb_in to report errors softly.

This requires a bit of further infrastructure-extension to allow
trapping errors reported by numeric_in and pg_unicode_to_server,
but otherwise it's pretty straightforward.

In the case of jsonb_in, we are only capturing errors reported
during the initial "parse" phase.  The value-construction phase
(JsonbValueToJsonb) can also throw errors if assorted implementation
limits are exceeded.  We should improve that, but it seems like a
separable project.

Andrew Dunstan and Tom Lane

Discussion: https://postgr.es/m/3bac9841-fe07-713d-fa42-606c225567d6@dunslane.net

1 files changed, 57 insertions, 0 deletions

diff --git a/src/backend/utils/mb/mbutils.c b/src/backend/utils/mb/mbutils.c
index 474ab476f5f..24f37e3ec98 100644
--- a/src/backend/utils/mb/mbutils.c
+++ b/src/backend/utils/mb/mbutils.c
@@ -916,6 +916,63 @@ pg_unicode_to_server(pg_wchar c, unsigned char *s)
 				  BoolGetDatum(false));
 }
 
+/*
+ * Convert a single Unicode code point into a string in the server encoding.
+ *
+ * Same as pg_unicode_to_server(), except that we don't throw errors,
+ * but simply return false on conversion failure.
+ */
+bool
+pg_unicode_to_server_noerror(pg_wchar c, unsigned char *s)
+{
+	unsigned char c_as_utf8[MAX_MULTIBYTE_CHAR_LEN + 1];
+	int			c_as_utf8_len;
+	int			converted_len;
+	int			server_encoding;
+
+	/* Fail if invalid Unicode code point */
+	if (!is_valid_unicode_codepoint(c))
+		return false;
+
+	/* Otherwise, if it's in ASCII range, conversion is trivial */
+	if (c <= 0x7F)
+	{
+		s[0] = (unsigned char) c;
+		s[1] = '\0';
+		return true;
+	}
+
+	/* If the server encoding is UTF-8, we just need to reformat the code */
+	server_encoding = GetDatabaseEncoding();
+	if (server_encoding == PG_UTF8)
+	{
+		unicode_to_utf8(c, s);
+		s[pg_utf_mblen(s)] = '\0';
+		return true;
+	}
+
+	/* For all other cases, we must have a conversion function available */
+	if (Utf8ToServerConvProc == NULL)
+		return false;
+
+	/* Construct UTF-8 source string */
+	unicode_to_utf8(c, c_as_utf8);
+	c_as_utf8_len = pg_utf_mblen(c_as_utf8);
+	c_as_utf8[c_as_utf8_len] = '\0';
+
+	/* Convert, but without throwing error if we can't */
+	converted_len = DatumGetInt32(FunctionCall6(Utf8ToServerConvProc,
+												Int32GetDatum(PG_UTF8),
+												Int32GetDatum(server_encoding),
+												CStringGetDatum((char *) c_as_utf8),
+												CStringGetDatum((char *) s),
+												Int32GetDatum(c_as_utf8_len),
+												BoolGetDatum(true)));
+
+	/* Conversion was successful iff it consumed the whole input */
+	return (converted_len == c_as_utf8_len);
+}
+
 
 /* convert a multibyte string to a wchar */
 int