Skip to content

[function](cast)Make string casting to integers more like MySQL's behavior #38847

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
zhangstar333 merged 3 commits into from
Aug 22, 2024
Merged

[function](cast)Make string casting to integers more like MySQL's behavior #38847

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
17478ba
upd
Mryange Aug 5, 2024
7b40d55
case
Mryange Aug 7, 2024
800af2b
add order by
Mryange Aug 8, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 18 additions & 2 deletions be/src/util/string_parser.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -243,6 +243,20 @@ class StringParser {
return true;
}

// For strings like "3.0", "3.123", and "3.", can parse them as 3.
static inline bool is_float_suffix(const char* __restrict s, int len) {
return (s[0] == '.' && is_all_digit(s + 1, len - 1));
}

static inline bool is_all_digit(const char* __restrict s, int len) {
for (int i = 0; i < len; ++i) {
if (!LIKELY(s[i] >= '0' && s[i] <= '9')) {
Copy link
Contributor

@github-actions github-actions bot Aug 5, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

warning: boolean expression can be simplified by DeMorgan's theorem [readability-simplify-boolean-expr]

            if (!LIKELY(s[i] >= '0' && s[i] <= '9')) {
                 ^
Additional context

be/src/common/compiler_util.h:34: expanded from macro 'LIKELY'

#define LIKELY(expr) __builtin_expect(!!(expr), 1)
                                       ^

return false;
}
}
return true;
}

// Returns the position of the first non-whitespace character in s.
static inline int skip_leading_whitespace(const char* __restrict s, int len) {
int i = 0;
Expand Down Expand Up @@ -306,7 +320,8 @@ T StringParser::string_to_int_internal(const char* __restrict s, int len, ParseR
}
val = val * 10 + digit;
} else {
if ((UNLIKELY(i == first || !is_all_whitespace(s + i, len - i)))) {
if ((UNLIKELY(i == first || (!is_all_whitespace(s + i, len - i) &&
Copy link
Contributor

@github-actions github-actions bot Aug 5, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

warning: boolean expression can be simplified by DeMorgan's theorem [readability-simplify-boolean-expr]

            if ((UNLIKELY(i == first || (!is_all_whitespace(s + i, len - i) &&
                 ^
Additional context

be/src/common/compiler_util.h:35: expanded from macro 'UNLIKELY'

#define UNLIKELY(expr) __builtin_expect(!!(expr), 0)
                                         ^

!is_float_suffix(s + i, len - i))))) {
// Reject the string because either the first char was not a digit,
// or the remaining chars are not all whitespace
*result = PARSE_FAILURE;
Expand Down Expand Up @@ -448,7 +463,8 @@ T StringParser::string_to_int_no_overflow(const char* __restrict s, int len, Par
T digit = s[i] - '0';
val = val * 10 + digit;
} else {
if ((UNLIKELY(!is_all_whitespace(s + i, len - i)))) {
if ((UNLIKELY(!is_all_whitespace(s + i, len - i) &&
Copy link
Contributor

@github-actions github-actions bot Aug 5, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

warning: boolean expression can be simplified by DeMorgan's theorem [readability-simplify-boolean-expr]

            if ((UNLIKELY(!is_all_whitespace(s + i, len - i) &&
                 ^
Additional context

be/src/common/compiler_util.h:35: expanded from macro 'UNLIKELY'

#define UNLIKELY(expr) __builtin_expect(!!(expr), 0)
                                         ^

!is_float_suffix(s + i, len - i)))) {
*result = PARSE_FAILURE;
return 0;
}
Expand Down
6 changes: 6 additions & 0 deletions regression-test/data/datatype_p0/string/test_string_basic.out
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,3 +98,9 @@
-- !test --
a

-- !cast_string_to_int --
3 3 0 0 3 \N 3

-- !cast_string_to_int --
3 3 0 0 3 \N 3

9 changes: 6 additions & 3 deletions regression-test/data/load_p0/stream_load/test_stream_load_cast.out
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,18 +1,21 @@
-- This file is automatically generated. You should know what you did if you want to edit this
-- !sql1 --
\N \N \N \N \N \N \N \N \N \N \N \N
3 3 3 3 3 \N \N \N \N \N \N \N

-- !sql2 --
\N \N \N \N \N \N \N \N \N \N \N \N
3 3 3 3 3 \N \N \N \N \N \N \N
3 3 3 3 3 \N \N \N \N \N \N \N

-- !sql3 --
\N \N \N \N \N \N \N \N \N \N \N \N
3 3 3 3 3 \N \N \N \N \N \N \N

-- !sql4 --
\N \N \N \N \N 3.12 3.12 3.1 2024-04-02 2024-04-02 2024-04-02T17:00 2024-04-02T17:00
3 3 3 3 3 3.12 3.12 3.1 2024-04-02 2024-04-02 2024-04-02T17:00 2024-04-02T17:00

-- !sql5 --
\N \N \N \N \N \N \N 99999999.9 \N \N \N \N
3 3 3 3 3 3.12 3.12 3.1 2024-04-02 2024-04-02 2024-04-02T17:00 2024-04-02T17:00

-- !sql6 --
\N \N \N \N \N \N \N 99999999.9 \N \N \N \N
Expand Down
6 changes: 3 additions & 3 deletions regression-test/data/nereids_p0/sql_functions/cast_function/test_cast_function.out
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,11 +30,11 @@ true
\N

-- !sql_to_small --
\N
1212

-- !sql_to_int --
\N
1212

-- !sql_to_big --
\N
1212

16 changes: 8 additions & 8 deletions regression-test/data/variant_p0/compaction/test_compaction.out
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,8 +58,8 @@
14 [null]
17 [1]
17 [1]
18 [1, 2, null]
18 [1, 2, null]
18 [1, 2, 1]
18 [1, 2, 1]

-- !sql_3 --
19 1 {"c":1}
Expand Down Expand Up @@ -146,8 +146,8 @@
14 [null]
17 [1]
17 [1]
18 [1, 2, null]
18 [1, 2, null]
18 [1, 2, 1]
18 [1, 2, 1]

-- !sql_33 --
19 1 {"c":1}
Expand Down Expand Up @@ -206,7 +206,7 @@
-- !sql_2 --
14 [null]
17 [1]
18 [1, 2, null]
18 [1, 2, 1]

-- !sql_3 --
19 1 {"c":1}
Expand Down Expand Up @@ -259,7 +259,7 @@
-- !sql_22 --
14 [null]
17 [1]
18 [1, 2, null]
18 [1, 2, 1]

-- !sql_33 --
19 1 {"c":1}
Expand Down Expand Up @@ -310,7 +310,7 @@
-- !sql_2 --
14 [null]
17 [1]
18 [1, 2, null]
18 [1, 2, 1]

-- !sql_3 --
19 1 {"c":1}
Expand Down Expand Up @@ -363,7 +363,7 @@
-- !sql_22 --
14 [null]
17 [1]
18 [1, 2, null]
18 [1, 2, 1]

-- !sql_33 --
19 1 {"c":1}
Expand Down
2 changes: 1 addition & 1 deletion regression-test/data/variant_p0/load.out
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
-- This file is automatically generated. You should know what you did if you want to edit this
-- !sql1 --
1 [1, 2, null]
1 [1, 2, 1]
1 [1]
1 [1]
1 [null]
Expand Down
8 changes: 7 additions & 1 deletion regression-test/suites/datatype_p0/string/test_string_basic.groovy
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -376,5 +376,11 @@ suite("test_string_basic") {
}
assertEquals(table_too_long, "fail")
sql "drop table if exists varchar_table_too_long;"
}

// calculations on the BE.
sql """ set debug_skip_fold_constant = true;"""
qt_cast_string_to_int""" select cast('3.123' as int),cast('3.000' as int) , cast('0000.0000' as int) , cast('0000' as int), cast('3.123' as int), cast('3.000 ' as int), cast('3.' as int)"""
// calculations on the FE.
sql """ set debug_skip_fold_constant = false;"""
qt_cast_string_to_int""" select cast('3.123' as int),cast('3.000' as int) , cast('0000.0000' as int) , cast('0000' as int), cast('3.123' as int), cast('3.000 ' as int), cast('3.' as int)"""
}
24 changes: 12 additions & 12 deletions regression-test/suites/load_p0/stream_load/test_stream_load_cast.groovy
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,7 +62,7 @@ suite("test_stream_load_cast", "p0") {
}
}
sql "sync"
qt_sql1 "select * from ${tableName}"
qt_sql1 "select * from ${tableName} order by k0"
sql "sync"
sql "truncate table ${tableName}"
sql "sync"
Expand All @@ -83,9 +83,9 @@ suite("test_stream_load_cast", "p0") {
}
log.info("Stream load result: ${result}".toString())
def json = parseJson(result)
assertEquals("fail", json.Status.toLowerCase())
assertEquals("success", json.Status.toLowerCase())
assertEquals(1, json.NumberTotalRows)
assertEquals(1, json.NumberFilteredRows)
assertEquals(0, json.NumberFilteredRows)
}
}

Expand All @@ -112,7 +112,7 @@ suite("test_stream_load_cast", "p0") {
}
}
sql "sync"
qt_sql2 "select * from ${tableName}"
qt_sql2 "select * from ${tableName} order by k0"
sql "sync"
sql "truncate table ${tableName}"
sql "sync"
Expand All @@ -134,9 +134,9 @@ suite("test_stream_load_cast", "p0") {
}
log.info("Stream load result: ${result}".toString())
def json = parseJson(result)
assertEquals("fail", json.Status.toLowerCase())
assertEquals("success", json.Status.toLowerCase())
assertEquals(1, json.NumberTotalRows)
assertEquals(1, json.NumberFilteredRows)
assertEquals(0, json.NumberFilteredRows)
}
}

Expand All @@ -162,7 +162,7 @@ suite("test_stream_load_cast", "p0") {
}
}
sql "sync"
qt_sql3 "select * from ${tableName}"
qt_sql3 "select * from ${tableName} order by k0"
sql "sync"
sql "truncate table ${tableName}"
sql "sync"
Expand Down Expand Up @@ -210,7 +210,7 @@ suite("test_stream_load_cast", "p0") {
}
}
sql "sync"
qt_sql4 "select * from ${tableName}"
qt_sql4 "select * from ${tableName} order by k0"
sql "sync"
sql "truncate table ${tableName}"
sql "sync"
Expand All @@ -231,9 +231,9 @@ suite("test_stream_load_cast", "p0") {
}
log.info("Stream load result: ${result}".toString())
def json = parseJson(result)
assertEquals("fail", json.Status.toLowerCase())
assertEquals("success", json.Status.toLowerCase())
assertEquals(1, json.NumberTotalRows)
assertEquals(1, json.NumberFilteredRows)
assertEquals(0, json.NumberFilteredRows)
}
}

Expand All @@ -259,7 +259,7 @@ suite("test_stream_load_cast", "p0") {
}
}
sql "sync"
qt_sql5 "select * from ${tableName}"
qt_sql5 "select * from ${tableName} order by k0"
sql "sync"
sql "truncate table ${tableName}"
sql "sync"
Expand Down Expand Up @@ -311,7 +311,7 @@ suite("test_stream_load_cast", "p0") {
}
}
sql "sync"
qt_sql6 "select * from ${tableName}"
qt_sql6 "select * from ${tableName} order by k0"
sql "sync"
sql "truncate table ${tableName}"
sql "sync"
Expand Down