postgres.git / summary / log / commit / refs
commit dde5b01c33f9a8c41f5598dd5d4db718df171eed
Author: Michael Paquier <michael@paquier.xyz>
Date: Wed Jan 31 04:16:47 2024 +0000
Fix various issues with ALTER TEXT SEARCH CONFIGURATION
This commit addresses a set of issues when changing token type mappings
in a text search configuration when using duplicated token names:
- ADD MAPPING would fail on insertion because of a constraint failure
after inserting the same mapping.
- ALTER MAPPING with an "overridden" configuration failed with "tuple
already updated by self" when the token mappings are removed.
- DROP MAPPING failed with "tuple already updated by self", like
previously, but in a different code path.
The code is refactored so the token names (with their numbers) are
handled as a List with unique members rather than an array with numbers,
ensuring that no duplicates mess up with the catalog inserts, updates
and deletes. The list is generated by getTokenTypes(), with the same
error handling as previously while duplicated tokens are discarded from
the list used to work on the catalogs.
Regression tests are expanded to cover much more ground for the cases
fixed by this commit, as there was no coverage for the code touched in
this commit. A bit more is done regarding the fact that a token name
not supported by a configuration's parser should result in an error even
if IF EXISTS is used in a DROP MAPPING clause. This is implied in the
code but there was no coverage for that, and it was very easy to miss.
These issues exist since at least their introduction in core with
140d4ebcb46e, so backpatch all the way down.
Reported-by: Alexander Lakhin
Author: Tender Wang, Michael Paquier
Discussion: https://postgr.es/m/18310-1eb233c5908189c8@postgresql.org
Backpatch-through: 12
src/backend/commands/tsearchcmds.c | 95 ++++++++++++++++++++++++-----------
src/test/regress/expected/tsdicts.out | 34 +++++++++++++
src/test/regress/sql/tsdicts.sql | 30 +++++++++++
src/tools/pgindent/typedefs.list | 1 +
4 files changed, 130 insertions(+), 30 deletions(-)
diff --git a/src/backend/commands/tsearchcmds.c b/src/backend/commands/tsearchcmds.c
index e06fb32b3d1..d3ce548ea11 100644
--- a/src/backend/commands/tsearchcmds.c
+++ b/src/backend/commands/tsearchcmds.c
@@ -48,6 +48,12 @@
#include "utils/rel.h"
#include "utils/syscache.h"
+/* Single entry of List returned by getTokenTypes() */
+typedef struct
+{
+ int num; /* token type number */
+ char *name; /* token type name */
+} TSTokenTypeItem;
static void MakeConfigurationMapping(AlterTSConfigurationStmt *stmt,
HeapTuple tup, Relation relMap);
@@ -1151,22 +1157,45 @@ AlterTSConfiguration(AlterTSConfigurationStmt *stmt)
}
/*
- * Translate a list of token type names to an array of token type numbers
+ * Check whether a token type name is a member of a TSTokenTypeItem list.
*/
-static int *
+static bool
+tstoken_list_member(char *token_name, List *tokens)
+{
+ ListCell *c;
+ bool found = false;
+
+ foreach(c, tokens)
+ {
+ TSTokenTypeItem *ts = (TSTokenTypeItem *) lfirst(c);
+
+ if (strcmp(token_name, ts->name) == 0)
+ {
+ found = true;
+ break;
+ }
+ }
+
+ return found;
+}
+
+/*
+ * Translate a list of token type names to a list of unique TSTokenTypeItem.
+ *
+ * Duplicated entries list are removed from tokennames.
+ */
+static List *
getTokenTypes(Oid prsId, List *tokennames)
{
TSParserCacheEntry *prs = lookup_ts_parser_cache(prsId);
LexDescr *list;
- int *res,
- i,
- ntoken;
+ List *result = NIL;
+ int ntoken;
ListCell *tn;
ntoken = list_length(tokennames);
if (ntoken == 0)
- return NULL;
- res = (int *) palloc(sizeof(int) * ntoken);
+ return NIL;
if (!OidIsValid(prs->lextypeOid))
elog(ERROR, "method lextype isn't defined for text search parser %u",
@@ -1176,19 +1205,26 @@ getTokenTypes(Oid prsId, List *tokennames)
list = (LexDescr *) DatumGetPointer(OidFunctionCall1(prs->lextypeOid,
(Datum) 0));
- i = 0;
foreach(tn, tokennames)
{
Value *val = (Value *) lfirst(tn);
bool found = false;
int j;
+ /* Skip if this token is already in the result */
+ if (tstoken_list_member(strVal(val), result))
+ continue;
+
j = 0;
while (list && list[j].lexid)
{
if (strcmp(strVal(val), list[j].alias) == 0)
{
- res[i] = list[j].lexid;
+ TSTokenTypeItem *ts = (TSTokenTypeItem *) palloc0(sizeof(TSTokenTypeItem));
+
+ ts->num = list[j].lexid;
+ ts->name = pstrdup(strVal(val));
+ result = lappend(result, ts);
found = true;
break;
}
@@ -1199,10 +1235,9 @@ getTokenTypes(Oid prsId, List *tokennames)
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("token type \"%s\" does not exist",
strVal(val))));
- i++;
}
- return res;
+ return result;
}
/*
@@ -1220,8 +1255,7 @@ MakeConfigurationMapping(AlterTSConfigurationStmt *stmt,
int i;
int j;
Oid prsId;
- int *tokens,
- ntoken;
+ List *tokens = NIL;
Oid *dictIds;
int ndict;
ListCell *c;
@@ -1231,15 +1265,16 @@ MakeConfigurationMapping(AlterTSConfigurationStmt *stmt,
prsId = tsform->cfgparser;
tokens = getTokenTypes(prsId, stmt->tokentype);
- ntoken = list_length(stmt->tokentype);
if (stmt->override)
{
/*
* delete maps for tokens if they exist and command was ALTER
*/
- for (i = 0; i < ntoken; i++)
+ foreach(c, tokens)
{
+ TSTokenTypeItem *ts = (TSTokenTypeItem *) lfirst(c);
+
ScanKeyInit(&skey[0],
Anum_pg_ts_config_map_mapcfg,
BTEqualStrategyNumber, F_OIDEQ,
@@ -1247,7 +1282,7 @@ MakeConfigurationMapping(AlterTSConfigurationStmt *stmt,
ScanKeyInit(&skey[1],
Anum_pg_ts_config_map_maptokentype,
BTEqualStrategyNumber, F_INT4EQ,
- Int32GetDatum(tokens[i]));
+ Int32GetDatum(ts->num));
scan = systable_beginscan(relMap, TSConfigMapIndexId, true,
NULL, 2, skey);
@@ -1302,9 +1337,11 @@ MakeConfigurationMapping(AlterTSConfigurationStmt *stmt,
{
bool tokmatch = false;
- for (j = 0; j < ntoken; j++)
+ foreach(c, tokens)
{
- if (cfgmap->maptokentype == tokens[j])
+ TSTokenTypeItem *ts = (TSTokenTypeItem *) lfirst(c);
+
+ if (cfgmap->maptokentype == ts->num)
{
tokmatch = true;
break;
@@ -1345,8 +1382,10 @@ MakeConfigurationMapping(AlterTSConfigurationStmt *stmt,
/*
* Insertion of new entries
*/
- for (i = 0; i < ntoken; i++)
+ foreach(c, tokens)
{
+ TSTokenTypeItem *ts = (TSTokenTypeItem *) lfirst(c);
+
for (j = 0; j < ndict; j++)
{
Datum values[Natts_pg_ts_config_map];
@@ -1354,7 +1393,7 @@ MakeConfigurationMapping(AlterTSConfigurationStmt *stmt,
memset(nulls, false, sizeof(nulls));
values[Anum_pg_ts_config_map_mapcfg - 1] = ObjectIdGetDatum(cfgId);
- values[Anum_pg_ts_config_map_maptokentype - 1] = Int32GetDatum(tokens[i]);
+ values[Anum_pg_ts_config_map_maptokentype - 1] = Int32GetDatum(ts->num);
values[Anum_pg_ts_config_map_mapseqno - 1] = Int32GetDatum(j + 1);
values[Anum_pg_ts_config_map_mapdict - 1] = ObjectIdGetDatum(dictIds[j]);
@@ -1381,9 +1420,8 @@ DropConfigurationMapping(AlterTSConfigurationStmt *stmt,
ScanKeyData skey[2];
SysScanDesc scan;
HeapTuple maptup;
- int i;
Oid prsId;
- int *tokens;
+ List *tokens = NIL;
ListCell *c;
tsform = (Form_pg_ts_config) GETSTRUCT(tup);
@@ -1392,10 +1430,9 @@ DropConfigurationMapping(AlterTSConfigurationStmt *stmt,
tokens = getTokenTypes(prsId, stmt->tokentype);
- i = 0;
- foreach(c, stmt->tokentype)
+ foreach(c, tokens)
{
- Value *val = (Value *) lfirst(c);
+ TSTokenTypeItem *ts = (TSTokenTypeItem *) lfirst(c);
bool found = false;
ScanKeyInit(&skey[0],
@@ -1405,7 +1442,7 @@ DropConfigurationMapping(AlterTSConfigurationStmt *stmt,
ScanKeyInit(&skey[1],
Anum_pg_ts_config_map_maptokentype,
BTEqualStrategyNumber, F_INT4EQ,
- Int32GetDatum(tokens[i]));
+ Int32GetDatum(ts->num));
scan = systable_beginscan(relMap, TSConfigMapIndexId, true,
NULL, 2, skey);
@@ -1425,17 +1462,15 @@ DropConfigurationMapping(AlterTSConfigurationStmt *stmt,
ereport(ERROR,
(errcode(ERRCODE_UNDEFINED_OBJECT),
errmsg("mapping for token type \"%s\" does not exist",
- strVal(val))));
+ ts->name)));
}
else
{
ereport(NOTICE,
(errmsg("mapping for token type \"%s\" does not exist, skipping",
- strVal(val))));
+ ts->name)));
}
}
-
- i++;
}
EventTriggerCollectAlterTSConfig(stmt, cfgId, NULL, 0);
diff --git a/src/test/regress/expected/tsdicts.out b/src/test/regress/expected/tsdicts.out
index c8042931429..4eff85da793 100644
--- a/src/test/regress/expected/tsdicts.out
+++ b/src/test/regress/expected/tsdicts.out
@@ -687,3 +687,37 @@ CREATE TEXT SEARCH DICTIONARY tsdict_case
"AffFile" = ispell_sample
);
ERROR: unrecognized Ispell parameter: "DictFile"
+-- Test grammar for configurations
+CREATE TEXT SEARCH CONFIGURATION dummy_tst (COPY=english);
+-- Overriden mapping change with duplicated tokens.
+ALTER TEXT SEARCH CONFIGURATION dummy_tst
+ ALTER MAPPING FOR word, word WITH ispell;
+-- Not a token supported by the configuration's parser, fails.
+ALTER TEXT SEARCH CONFIGURATION dummy_tst
+ DROP MAPPING FOR not_a_token, not_a_token;
+ERROR: token type "not_a_token" does not exist
+-- Not a token supported by the configuration's parser, fails even
+-- with IF EXISTS.
+ALTER TEXT SEARCH CONFIGURATION dummy_tst
+ DROP MAPPING IF EXISTS FOR not_a_token, not_a_token;
+ERROR: token type "not_a_token" does not exist
+-- Token supported by the configuration's parser, succeeds.
+ALTER TEXT SEARCH CONFIGURATION dummy_tst
+ DROP MAPPING FOR word, word;
+-- No mapping for token supported by the configuration's parser, fails.
+ALTER TEXT SEARCH CONFIGURATION dummy_tst
+ DROP MAPPING FOR word;
+ERROR: mapping for token type "word" does not exist
+-- Token supported by the configuration's parser, cannot be found,
+-- succeeds with IF EXISTS.
+ALTER TEXT SEARCH CONFIGURATION dummy_tst
+ DROP MAPPING IF EXISTS FOR word, word;
+NOTICE: mapping for token type "word" does not exist, skipping
+-- Re-add mapping, with duplicated tokens supported by the parser.
+ALTER TEXT SEARCH CONFIGURATION dummy_tst
+ ADD MAPPING FOR word, word WITH ispell;
+-- Not a token supported by the configuration's parser, fails.
+ALTER TEXT SEARCH CONFIGURATION dummy_tst
+ ADD MAPPING FOR not_a_token WITH ispell;
+ERROR: token type "not_a_token" does not exist
+DROP TEXT SEARCH CONFIGURATION dummy_tst;
diff --git a/src/test/regress/sql/tsdicts.sql b/src/test/regress/sql/tsdicts.sql
index ddc6c7f4453..6a2b00369ce 100644
--- a/src/test/regress/sql/tsdicts.sql
+++ b/src/test/regress/sql/tsdicts.sql
@@ -251,3 +251,33 @@ CREATE TEXT SEARCH DICTIONARY tsdict_case
"DictFile" = ispell_sample,
"AffFile" = ispell_sample
);
+
+-- Test grammar for configurations
+CREATE TEXT SEARCH CONFIGURATION dummy_tst (COPY=english);
+-- Overriden mapping change with duplicated tokens.
+ALTER TEXT SEARCH CONFIGURATION dummy_tst
+ ALTER MAPPING FOR word, word WITH ispell;
+-- Not a token supported by the configuration's parser, fails.
+ALTER TEXT SEARCH CONFIGURATION dummy_tst
+ DROP MAPPING FOR not_a_token, not_a_token;
+-- Not a token supported by the configuration's parser, fails even
+-- with IF EXISTS.
+ALTER TEXT SEARCH CONFIGURATION dummy_tst
+ DROP MAPPING IF EXISTS FOR not_a_token, not_a_token;
+-- Token supported by the configuration's parser, succeeds.
+ALTER TEXT SEARCH CONFIGURATION dummy_tst
+ DROP MAPPING FOR word, word;
+-- No mapping for token supported by the configuration's parser, fails.
+ALTER TEXT SEARCH CONFIGURATION dummy_tst
+ DROP MAPPING FOR word;
+-- Token supported by the configuration's parser, cannot be found,
+-- succeeds with IF EXISTS.
+ALTER TEXT SEARCH CONFIGURATION dummy_tst
+ DROP MAPPING IF EXISTS FOR word, word;
+-- Re-add mapping, with duplicated tokens supported by the parser.
+ALTER TEXT SEARCH CONFIGURATION dummy_tst
+ ADD MAPPING FOR word, word WITH ispell;
+-- Not a token supported by the configuration's parser, fails.
+ALTER TEXT SEARCH CONFIGURATION dummy_tst
+ ADD MAPPING FOR not_a_token WITH ispell;
+DROP TEXT SEARCH CONFIGURATION dummy_tst;
diff --git a/src/tools/pgindent/typedefs.list b/src/tools/pgindent/typedefs.list
index 2ba43907bcc..fb59bd3be73 100644
--- a/src/tools/pgindent/typedefs.list
+++ b/src/tools/pgindent/typedefs.list
@@ -2594,6 +2594,7 @@ TSQuerySign
TSReadPointer
TSTemplateInfo
TSTernaryValue
+TSTokenTypeItem
TSTokenTypeStorage
TSVector
TSVectorBuildState
[parent: 2acba01ddc2a]