Dmitry Dolgov wrote:
On 6 April 2018 at 16:25, Teodor Sigaev <teo...@sigaev.ru> wrote:
1) I don't like jsonb_all_to_tsvector too.. What if we will accept new
variant to index? Let me suggest:
tsvector jsonb_to_tsvector([regclass,] jsonb, text[])
where text[] arg is actually a flags, array contains any combination of
literals 'numeric', 'string', 'boolean' (and even 'key' to index keys_ to
point which types should be indexed. More than it, may be, it should a jsonb
type for possible improvements in future. For now, it shouldbe a jsonb array
type with string elements described above, example:
select jsonb_to_tsvector('{"a": "aaa in bbb ddd ccc", "b":123}',
'["numeric", "boolean"]');
Form jsonb_to_tsvector('...', '["string"]) is effectively the same as
current to_tsvector(jsonb)
Thank you for the suggestion, this sounds appealing. But I have two questions:
* why it should be a jsonb array, not a regular array?
To simplify extension of this array in future, for example to add limitation of
recursion level in converted jsonb, etc.
* it would introduce the idea of jsonb element type expressed in text format,
so "string", "numeric", "boolean" etc - are there any consequences of that?
As far as I understand so far there was only jsonb_typeof.
Good catch, jsonb_typeof strings are okay: "string", "number", "boolean"
also "all", "key", "value"
See workable sketch for parsing jsonb flags and new worker variant.
2) Now it fails, and I see something strange in resuling tsvector
Oh, sorry, stupid copy-paste mistake in the condition. Just for the records,
I've attached fixed version of the previous patch (without any changes about an
array instead of a boolean flag).
by the way:
Datum
jsonb_to_tsvector(PG_FUNCTION_ARGS)
{
Jsonb *jb = PG_GETARG_JSONB_P(0);
...
PG_FREE_IF_COPY(jb, 1); //wrong arg number
}
jsonb_all_to_tsvector and json variants too
--
Teodor Sigaev E-mail: teo...@sigaev.ru
WWW: http://www.sigaev.ru/
typedef enum JsonToIndex {
jtiKey = 0x01,
jtiString = 0x02,
jtiNumeric = 0x04,
jtiBool = 0x08,
jtiAll = jtiKey | jtiString | jtiNumeric | jtiBool
} JsonToIndex;
static uint32
parse_jsonb_index_flags(Jsonb *jb)
{
JsonbIterator *it;
JsonbValue v;
JsonbIteratorToken type;
uint32 flags = 0;
it = JsonbIteratorInit(&jb->root);
type = JsonbIteratorNext(&it, &v, false);
if (type != WJB_BEGIN_ARRAY)
elog(ERROR, "wrong flag type");
while ((type = JsonbIteratorNext(&it, &v, false)) == WJB_ELEM)
{
if (v.type != jbvString)
elog(ERROR, "text is only accepted");
if (v.val.string.len == 3 &&
pg_strncasecmp(v.val.string.val, "all", 3) == 0)
flags |= jtiAll;
else if (v.val.string.len == 3 &&
pg_strncasecmp(v.val.string.val, "key", 3) == 0)
flags |= jtiKey;
else if (v.val.string.len == 6 &&
pg_strncasecmp(v.val.string.val, "string", 5) == 0)
flags |= jtiString;
else if (v.val.string.len == 7 &&
pg_strncasecmp(v.val.string.val, "numeric", 7) == 0)
flags |= jtiNumeric;
else if (v.val.string.len == 7 &&
pg_strncasecmp(v.val.string.val, "boolean", 7) == 0)
flags |= jtiBool;
else
elog(ERROR, "string, numeric, boolean, key and all are only accepted");
}
if (type != WJB_END_ARRAY)
elog(ERROR, "wrong flag type");
JsonbIteratorNext(&it, &v, false);
return flags;
}
/*
* Worker function for jsonb(_all)_to_tsvector(_byid)
*/
static TSVector
jsonb_to_tsvector_worker(Oid cfgId, Jsonb *jb, uint32 flags)
{
TSVectorBuildState state;
ParsedText prs;
JsonbIterator *it;
JsonbValue v;
JsonbIteratorToken type;
prs.words = NULL;
prs.curwords = 0;
state.prs = &prs;
state.cfgId = cfgId;
it = JsonbIteratorInit(&jb->root);
type = JsonbIteratorNext(&it, &v, false);
while ((type = JsonbIteratorNext(&it, &v, false)) != WJB_DONE)
{
if (type == WJB_KEY && (flags & jtiKey))
add_to_tsvector(&state, v.val.string.val, v.val.string.len);
else if (type == WJB_VALUE || type == WJB_ELEM)
{
switch(v.type)
{
case jbvString:
if (flags & jtiString)
add_to_tsvector(&state, v.val.string.val,
v.val.string.len);
break;
case jbvNumeric:
if (flags & jtiNumeric)
{
char *val;
val = DatumGetCString(DirectFunctionCall1(numeric_out,
NumericGetDatum(v.val.numeric)));
add_to_tsvector(&state, val, strlen(val));
}
break;
case jbvBool:
if (flags & jtiBool)
{
if (v.val.boolean)
add_to_tsvector(&state, pstrdup("true"), 4);
else
add_to_tsvector(&state, pstrdup("false"), 5);
}
break;
default:
break;
}
}
}
return make_tsvector(&prs);
}
