[Tarantool-patches] [PATCH v1 1/1] sql: modify signature of TRIM()
imeevma at tarantool.org
imeevma at tarantool.org
Tue Aug 17 15:50:11 MSK 2021
This patch changes the signature of SQL built-in function TRIM(). This
gives us an easier way to check the types of the arguments to this
function. Additionally, these changes fix a bug where using TRIM with
the BOTH, LEADING, or TRAILING keywords would result in a loss of a
collation.
Needed for #6105
Closes #6299
---
https://github.com/tarantool/tarantool/issues/6299
https://github.com/tarantool/tarantool/tree/imeevma/gh-6299-fix-trim-signature
src/box/sql/func.c | 80 ++++++-------------
src/box/sql/parse.y | 36 +++++----
.../gh-6299-lost-collation-on-trim.test.lua | 47 +++++++++++
3 files changed, 90 insertions(+), 73 deletions(-)
create mode 100755 test/sql-tap/gh-6299-lost-collation-on-trim.test.lua
diff --git a/src/box/sql/func.c b/src/box/sql/func.c
index 1622104d3..c73061e33 100644
--- a/src/box/sql/func.c
+++ b/src/box/sql/func.c
@@ -1481,37 +1481,11 @@ trim_prepare_char_len(struct sql_context *context,
}
/**
- * Normalize args from @a argv input array when it has one arg
- * only.
+ * Normalize args from @a argv input array when it has two args.
*
* Case: TRIM(<str>)
* Call trimming procedure with TRIM_BOTH as the flags and " " as
* the trimming set.
- */
-static void
-trim_func_one_arg(struct sql_context *context, sql_value *arg)
-{
- /* In case of VARBINARY type default trim octet is X'00'. */
- const unsigned char *default_trim;
- if (mem_is_null(arg))
- return;
- if (mem_is_bin(arg))
- default_trim = (const unsigned char *) "\0";
- else
- default_trim = (const unsigned char *) " ";
- const unsigned char *input_str = mem_as_ustr(arg);
- int input_str_sz = mem_len_unsafe(arg);
- uint8_t trim_char_len[1] = { 1 };
- trim_procedure(context, TRIM_BOTH, default_trim, trim_char_len, 1,
- input_str, input_str_sz);
-}
-
-/**
- * Normalize args from @a argv input array when it has two args.
- *
- * Case: TRIM(<character_set> FROM <str>)
- * If user has specified <character_set> only, call trimming
- * procedure with TRIM_BOTH as the flags and that trimming set.
*
* Case: TRIM(LEADING/TRAILING/BOTH FROM <str>)
* If user has specified side keyword only, then call trimming
@@ -1521,32 +1495,29 @@ static void
trim_func_two_args(struct sql_context *context, sql_value *arg1,
sql_value *arg2)
{
- const unsigned char *input_str, *trim_set;
- if ((input_str = mem_as_ustr(arg2)) == NULL)
+ const unsigned char *trim_set;
+ if (mem_is_bin(arg1))
+ trim_set = (const unsigned char *)"\0";
+ else
+ trim_set = (const unsigned char *)" ";
+ const unsigned char *input_str;
+ if ((input_str = mem_as_ustr(arg1)) == NULL)
return;
- int input_str_sz = mem_len_unsafe(arg2);
- if (sql_value_type(arg1) == MP_INT || sql_value_type(arg1) == MP_UINT) {
- uint8_t len_one = 1;
- trim_procedure(context, mem_get_int_unsafe(arg1),
- (const unsigned char *) " ", &len_one, 1,
- input_str, input_str_sz);
- } else if ((trim_set = mem_as_ustr(arg1)) != NULL) {
- int trim_set_sz = mem_len_unsafe(arg1);
- uint8_t *char_len;
- int char_cnt = trim_prepare_char_len(context, trim_set,
- trim_set_sz, &char_len);
- if (char_cnt == -1)
- return;
- trim_procedure(context, TRIM_BOTH, trim_set, char_len, char_cnt,
- input_str, input_str_sz);
- sql_free(char_len);
- }
+ int input_str_sz = mem_len_unsafe(arg1);
+ assert(arg2->type == MEM_TYPE_UINT);
+ uint8_t len_one = 1;
+ trim_procedure(context, arg2->u.u, trim_set,
+ &len_one, 1, input_str, input_str_sz);
}
/**
* Normalize args from @a argv input array when it has three args.
*
+ * Case: TRIM(<character_set> FROM <str>)
+ * If user has specified <character_set> only, call trimming procedure with
+ * TRIM_BOTH as the flags and that trimming set.
+ *
* Case: TRIM(LEADING/TRAILING/BOTH <character_set> FROM <str>)
* If user has specified side keyword and <character_set>, then
* call trimming procedure with that args.
@@ -1555,20 +1526,20 @@ static void
trim_func_three_args(struct sql_context *context, sql_value *arg1,
sql_value *arg2, sql_value *arg3)
{
- assert(sql_value_type(arg1) == MP_INT || sql_value_type(arg1) == MP_UINT);
+ assert(arg2->type == MEM_TYPE_UINT);
const unsigned char *input_str, *trim_set;
- if ((input_str = mem_as_ustr(arg3)) == NULL ||
- (trim_set = mem_as_ustr(arg2)) == NULL)
+ if ((input_str = mem_as_ustr(arg1)) == NULL ||
+ (trim_set = mem_as_ustr(arg3)) == NULL)
return;
- int trim_set_sz = mem_len_unsafe(arg2);
- int input_str_sz = mem_len_unsafe(arg3);
+ int trim_set_sz = mem_len_unsafe(arg3);
+ int input_str_sz = mem_len_unsafe(arg1);
uint8_t *char_len;
int char_cnt = trim_prepare_char_len(context, trim_set, trim_set_sz,
&char_len);
if (char_cnt == -1)
return;
- trim_procedure(context, mem_get_int_unsafe(arg1), trim_set, char_len,
+ trim_procedure(context, arg2->u.u, trim_set, char_len,
char_cnt, input_str, input_str_sz);
sql_free(char_len);
}
@@ -1584,9 +1555,6 @@ static void
trim_func(struct sql_context *context, int argc, sql_value **argv)
{
switch (argc) {
- case 1:
- trim_func_one_arg(context, argv[0]);
- break;
case 2:
trim_func_two_args(context, argv[0], argv[1]);
break;
@@ -1595,7 +1563,7 @@ trim_func(struct sql_context *context, int argc, sql_value **argv)
break;
default:
diag_set(ClientError, ER_FUNC_WRONG_ARG_COUNT, "TRIM",
- "1 or 2 or 3", argc);
+ "2 or 3", argc);
context->is_aborted = true;
}
}
diff --git a/src/box/sql/parse.y b/src/box/sql/parse.y
index bd041e862..d06f45fd9 100644
--- a/src/box/sql/parse.y
+++ b/src/box/sql/parse.y
@@ -1132,32 +1132,34 @@ expr(A) ::= TRIM(X) LP trim_operands(Y) RP(E). {
%type trim_operands {struct ExprList *}
%destructor trim_operands {sql_expr_list_delete(pParse->db, $$);}
-trim_operands(A) ::= trim_from_clause(F) expr(Y). {
- A = sql_expr_list_append(pParse->db, F, Y.pExpr);
+trim_operands(A) ::= trim_specification(N) expr(Z) FROM expr(Y). {
+ A = sql_expr_list_append(pParse->db, NULL, Y.pExpr);
+ struct Expr *p = sql_expr_new_dequoted(pParse->db, TK_INTEGER,
+ &sqlIntTokens[N]);
+ A = sql_expr_list_append(pParse->db, A, p);
+ A = sql_expr_list_append(pParse->db, A, Z.pExpr);
}
-trim_operands(A) ::= expr(Y). {
+trim_operands(A) ::= trim_specification(N) FROM expr(Y). {
A = sql_expr_list_append(pParse->db, NULL, Y.pExpr);
+ struct Expr *p = sql_expr_new_dequoted(pParse->db, TK_INTEGER,
+ &sqlIntTokens[N]);
+ A = sql_expr_list_append(pParse->db, A, p);
}
-%type trim_from_clause {struct ExprList *}
-%destructor trim_from_clause {sql_expr_list_delete(pParse->db, $$);}
-
-/*
- * The following two rules cover three cases of keyword
- * (LEADING/TRAILING/BOTH) and <trim_character_set> combination.
- * The case when both of them are absent is disallowed.
- */
-trim_from_clause(A) ::= expr(Y) FROM. {
+trim_operands(A) ::= expr(Z) FROM expr(Y). {
A = sql_expr_list_append(pParse->db, NULL, Y.pExpr);
+ struct Expr *p = sql_expr_new_dequoted(pParse->db, TK_INTEGER,
+ &sqlIntTokens[TRIM_BOTH]);
+ A = sql_expr_list_append(pParse->db, A, p);
+ A = sql_expr_list_append(pParse->db, A, Z.pExpr);
}
-trim_from_clause(A) ::= trim_specification(N) expr_optional(Y) FROM. {
+trim_operands(A) ::= expr(Y). {
+ A = sql_expr_list_append(pParse->db, NULL, Y.pExpr);
struct Expr *p = sql_expr_new_dequoted(pParse->db, TK_INTEGER,
- &sqlIntTokens[N]);
- A = sql_expr_list_append(pParse->db, NULL, p);
- if (Y != NULL)
- A = sql_expr_list_append(pParse->db, A, Y);
+ &sqlIntTokens[TRIM_BOTH]);
+ A = sql_expr_list_append(pParse->db, A, p);
}
%type expr_optional {struct Expr *}
diff --git a/test/sql-tap/gh-6299-lost-collation-on-trim.test.lua b/test/sql-tap/gh-6299-lost-collation-on-trim.test.lua
new file mode 100755
index 000000000..1799da839
--- /dev/null
+++ b/test/sql-tap/gh-6299-lost-collation-on-trim.test.lua
@@ -0,0 +1,47 @@
+#!/usr/bin/env tarantool
+local test = require("sqltester")
+test:plan(4)
+
+--
+-- Make sure that collation is not lost when TRIM called with BOTH, LEADING, or
+-- TRAILING keywords specified.
+--
+
+test:execsql[[
+ CREATE TABLE t (i INT PRIMARY KEY, s STRING COLLATE "unicode_ci");
+ INSERT INTO t VALUES (1,'A'), (2,'a');
+]]
+
+test:do_execsql_test(
+ "gh-6299-2",
+ [[
+ SELECT DISTINCT trim(LEADING FROM s) FROM t;
+ ]], {
+ 'A'
+ })
+
+test:do_execsql_test(
+ "gh-6299-3",
+ [[
+ SELECT DISTINCT trim(TRAILING FROM s) FROM t;
+ ]], {
+ 'A'
+ })
+
+test:do_execsql_test(
+ "gh-6299-4",
+ [[
+ SELECT DISTINCT trim(BOTH FROM s) FROM t;
+ ]], {
+ 'A'
+ })
+
+test:do_execsql_test(
+ "gh-6299-1",
+ [[
+ SELECT DISTINCT trim(s) FROM t;
+ ]], {
+ 'A'
+ })
+
+test:finish_test()
--
2.25.1
More information about the Tarantool-patches
mailing list