Merge pull request #33861 from RogerYK/fix-substring-negative-offset-length

Fix substring negative offset length

docs/en/sql-reference/functions/array-functions.md

@@ -620,9 +620,9 @@ arraySlice(array, offset[, length])
 
 **Arguments**
 
--   `array` – Array of data.
--   `offset` – Indent from the edge of the array. A positive value indicates an offset on the left, and a negative value is an indent on the right. Numbering of the array items begins with 1.
--   `length` – The length of the required slice. If you specify a negative value, the function returns an open slice `[offset, array_length - length)`. If you omit the value, the function returns the slice `[offset, the_end_of_array]`.
+- `array` – Array of data.
+- `offset` – Indent from the edge of the array. A positive value indicates an offset on the left, and a negative value is an indent on the right. Numbering of the array items begins with 1.
+- `length` – The length of the required slice. If you specify a negative value, the function returns an open slice `[offset, array_length - length]`. If you omit the value, the function returns the slice `[offset, the_end_of_array]`.
 
 **Example**
 

docs/en/sql-reference/functions/bit-functions.md

@@ -130,13 +130,9 @@ bitSlice(s, offset[, length])
 
 **Arguments**
 
-- `s` — s is [String](../../sql-reference/data-types/string.md)
-  or [FixedString](../../sql-reference/data-types/fixedstring.md).
-- `offset` — The start index with bit, A positive value indicates an offset on the left, and a negative value is an
-  indent on the right. Numbering of the bits begins with 1.
-- `length` — The length of substring with bit. If you specify a negative value, the function returns an open substring [
-  offset, array_length - length). If you omit the value, the function returns the substring [offset, the_end_string]. 
-  If length exceeds s, it will be truncate.If length isn't multiple of 8, will fill 0 on the right.
+- `s` — s is [String](../../sql-reference/data-types/string.md) or [FixedString](../../sql-reference/data-types/fixedstring.md).
+- `offset` — The start index with bit, A positive value indicates an offset on the left, and a negative value is an indent on the right. Numbering of the bits begins with 1.
+- `length` — The length of substring with bit. If you specify a negative value, the function returns an open substring \[offset, array_length - length\]. If you omit the value, the function returns the substring \[offset, the_end_string\]. If length exceeds s, it will be truncate.If length isn't multiple of 8, will fill 0 on the right.
 
 **Returned value**
 

docs/en/sql-reference/functions/string-functions.md

@@ -480,7 +480,7 @@ Result:
 
 ## substring(s, offset, length), mid(s, offset, length), substr(s, offset, length) {#substring}
 
-Returns a substring starting with the byte from the ‘offset’ index that is ‘length’ bytes long. Character indexing starts from one (as in standard SQL). The ‘offset’ and ‘length’ arguments must be constants.
+Returns a substring starting with the byte from the ‘offset’ index that is ‘length’ bytes long. Character indexing starts from one (as in standard SQL).
 
 ## substringUTF8(s, offset, length) {#substringutf8}
 

docs/ru/sql-reference/functions/array-functions.md

@@ -574,9 +574,9 @@ arraySlice(array, offset[, length])
 
 **Аргументы**
 
--   `array` – массив данных.
--   `offset` – отступ от края массива. Положительное значение - отступ слева, отрицательное значение - отступ справа. Отсчет элементов массива начинается с 1.
--   `length` – длина необходимого среза. Если указать отрицательное значение, то функция вернёт открытый срез `[offset, array_length - length)`. Если не указать значение, то функция вернёт срез `[offset, the_end_of_array]`.
+- `array` – массив данных.
+- `offset` – отступ от края массива. Положительное значение - отступ слева, отрицательное значение - отступ справа. Отсчёт элементов массива начинается с 1.
+- `length` – длина необходимого среза. Если указать отрицательное значение, то функция вернёт открытый срез `[offset, array_length - length]`. Если не указать значение, то функция вернёт срез `[offset, the_end_of_array]`.
 
 **Пример**
 

docs/zh/sql-reference/functions/array-functions.md

@@ -397,9 +397,9 @@ SELECT arrayPushFront(['b'], 'a') AS res
 
 **参数**
 
--   `array` – 数组。
--   `offset` – 数组的偏移。正值表示左侧的偏移量，负值表示右侧的缩进值。数组下标从1开始。
--   `length` - 子数组的长度。如果指定负值，则该函数返回`[offset，array_length  -  length`。如果省略该值，则该函数返回`[offset，the_end_of_array]`。
+- `array` – 数组。
+- `offset` – 数组的偏移。正值表示左侧的偏移量，负值表示右侧的缩进值。数组下标从1开始。
+- `length` - 子数组的长度。如果指定负值，则该函数返回`[offset，array_length - length]`。如果省略该值，则该函数返回`[offset，the_end_of_array]`。
 
 **示例**
 

src/Functions/GatherUtils/Algorithms.h

@@ -308,7 +308,7 @@ void NO_INLINE sliceFromRightConstantOffsetBounded(Source && src, Sink && sink,
     {
         ssize_t size = length;
         if (size < 0)
-            size += static_cast<ssize_t>(src.getElementSize()) - offset;
+            size += offset;
 
         if (size > 0)
             writeSlice(src.getSliceFromRight(offset, size), sink);

tests/queries/0_stateless/00498_array_functions_concat_slice_push_pop.reference

@@ -217,12 +217,12 @@ arraySlice(arr1, -4, 2)
 arraySlice(arr1, -4, -1)
 []	2	4	[]
 []	2	4	[]
-[1,2,3,4,5]	2	4	[]
-[1,2,3,4,5,6,7]	2	4	[4,5]
-[1,2,3,4,5,6,7]	2	4	[4,5]
-[1,2,3,4,5,6,7]	2	4	[4,5]
-[1,2,3,4,5,6,7]	2	4	[4,5]
-[1,2,3,4,5,6,7]	2	4	[4,5]
+[1,2,3,4,5]	2	4	[2,3,4]
+[1,2,3,4,5,6,7]	2	4	[4,5,6]
+[1,2,3,4,5,6,7]	2	4	[4,5,6]
+[1,2,3,4,5,6,7]	2	4	[4,5,6]
+[1,2,3,4,5,6,7]	2	4	[4,5,6]
+[1,2,3,4,5,6,7]	2	4	[4,5,6]
 arrayPushFront(arr1, 1)
 []	[1]
 []	[1]
@@ -504,12 +504,12 @@ arraySlice(arr1, -4, 2)
 arraySlice(arr1, -4, -1)
 []	2	4	[]
 []	2	4	[]
-[1,2,3,4,5]	2	4	[]
-[1,NULL,3,4,NULL,6,7]	2	4	[4,NULL]
-[1,2,3,NULL,5,6,7]	2	4	[NULL,5]
-[1,2,3,4,5,NULL,7]	2	4	[4,5]
-[1,2,3,4,5,6,7]	2	4	[4,5]
-[1,NULL,3,NULL,5,6,7]	2	4	[NULL,5]
+[1,2,3,4,5]	2	4	[2,3,4]
+[1,NULL,3,4,NULL,6,7]	2	4	[4,NULL,6]
+[1,2,3,NULL,5,6,7]	2	4	[NULL,5,6]
+[1,2,3,4,5,NULL,7]	2	4	[4,5,NULL]
+[1,2,3,4,5,6,7]	2	4	[4,5,6]
+[1,NULL,3,NULL,5,6,7]	2	4	[NULL,5,6]
 arrayPushFront(arr1, 1)
 []	[1]
 []	[1]
@@ -817,12 +817,12 @@ arraySlice(arr1, -4, 2)
 arraySlice(arr1, -4, -1)
 []	2	4	[]
 []	2	4	[]
-[1,2,3,4,5]	2	4	[]
-[1,NULL,3,4,NULL,6,7]	2	4	[4,NULL]
-[1,2,3,NULL,5,6,7]	2	4	[NULL,5]
-[1,2,3,4,5,NULL,7]	2	4	[4,5]
-[1,2,3,4,5,6,7]	2	4	[4,5]
-[1,NULL,3,NULL,5,6,7]	2	4	[NULL,5]
+[1,2,3,4,5]	2	4	[2,3,4]
+[1,NULL,3,4,NULL,6,7]	2	4	[4,NULL,6]
+[1,2,3,NULL,5,6,7]	2	4	[NULL,5,6]
+[1,2,3,4,5,NULL,7]	2	4	[4,5,NULL]
+[1,2,3,4,5,6,7]	2	4	[4,5,6]
+[1,NULL,3,NULL,5,6,7]	2	4	[NULL,5,6]
 arrayPushFront(arr1, 1)
 []	[1]
 []	[1]
@@ -1104,12 +1104,12 @@ arraySlice(arr1, -4, 2)
 arraySlice(arr1, -4, -1)
 []	2	4	[]
 []	2	4	[]
-['1','2','3','4','5']	2	4	[]
-['1',NULL,'3','4',NULL,'6','7']	2	4	['4',NULL]
-['1','2','3',NULL,'5','6','7']	2	4	[NULL,'5']
-['1','2','3','4','5',NULL,'7']	2	4	['4','5']
-['1','2','3','4','5','6','7']	2	4	['4','5']
-['1',NULL,'3',NULL,'5','6','7']	2	4	[NULL,'5']
+['1','2','3','4','5']	2	4	['2','3','4']
+['1',NULL,'3','4',NULL,'6','7']	2	4	['4',NULL,'6']
+['1','2','3',NULL,'5','6','7']	2	4	[NULL,'5','6']
+['1','2','3','4','5',NULL,'7']	2	4	['4','5',NULL]
+['1','2','3','4','5','6','7']	2	4	['4','5','6']
+['1',NULL,'3',NULL,'5','6','7']	2	4	[NULL,'5','6']
 arrayPushFront(arr1, 1)
 []	['1']
 []	['1']

tests/queries/0_stateless/00970_substring_arg_validation.reference

@@ -1 +1 @@
-o
+

tests/queries/0_stateless/02185_arraySlice_negative_offset_size.reference

@@ -0,0 +1,15 @@
+[]
+[]
+[]
+[7]
+[7]
+[7]
+-
+[]
+[]
+[]
+[6]
+[]
+[]
+[]
+[]

tests/queries/0_stateless/02185_arraySlice_negative_offset_size.sql

@@ -0,0 +1,25 @@
+select arraySlice([1, 2, 3, 4, 5, 6, 7, 8], -2, -2);
+select arraySlice(materialize([1, 2, 3, 4, 5, 6, 7, 8]), -2, -2);
+select arraySlice(materialize([1, 2, 3, 4, 5, 6, 7, 8]), materialize(-2), materialize(-2));
+
+select arraySlice([1, 2, 3, 4, 5, 6, 7, 8], -2, -1);
+select arraySlice(materialize([1, 2, 3, 4, 5, 6, 7, 8]), -2, -1);
+select arraySlice(materialize([1, 2, 3, 4, 5, 6, 7, 8]), materialize(-2), materialize(-1));
+
+select '-';
+drop table if exists t;
+create table t
+(
+    s Array(Int),
+    l Int8,
+    r Int8
+) engine = Memory;
+
+insert into t values ([1, 2, 3, 4, 5, 6, 7, 8], -2, -2), ([1, 2, 3, 4, 5, 6, 7, 8], -3, -3);
+
+select arraySlice(s, -2, -2) from t;
+select arraySlice(s, l, -2) from t;
+select arraySlice(s, -2, r) from t;
+select arraySlice(s, l, r) from t;
+
+drop table t;

tests/queries/0_stateless/02185_substring_negative_offset_size.reference

@@ -0,0 +1,31 @@
+
+
+
+g
+g
+g
+-
+
+
+
+g
+g
+g
+-
+
+
+
+6
+
+
+
+
+-
+
+
+
+6
+
+
+
+

tests/queries/0_stateless/02185_substring_negative_offset_size.sql

@@ -0,0 +1,48 @@
+select substring('abcdefgh', -2, -2);
+select substring(materialize('abcdefgh'), -2, -2);
+select substring(materialize('abcdefgh'), materialize(-2), materialize(-2));
+
+select substring('abcdefgh', -2, -1);
+select substring(materialize('abcdefgh'), -2, -1);
+select substring(materialize('abcdefgh'), materialize(-2), materialize(-1));
+
+select '-';
+select substring(cast('abcdefgh' as FixedString(8)), -2, -2);
+select substring(materialize(cast('abcdefgh' as FixedString(8))), -2, -2);
+select substring(materialize(cast('abcdefgh' as FixedString(8))), materialize(-2), materialize(-2));
+
+select substring(cast('abcdefgh' as FixedString(8)), -2, -1);
+select substring(materialize(cast('abcdefgh' as FixedString(8))), -2, -1);
+select substring(materialize(cast('abcdefgh' as FixedString(8))), materialize(-2), materialize(-1));
+
+select '-';
+drop table if exists t;
+create table t
+(
+    s String,
+    l Int8,
+    r Int8
+) engine = Memory;
+
+insert into t values ('abcdefgh', -2, -2),('12345678', -3, -3);
+
+select substring(s, -2, -2) from t;
+select substring(s, l, -2) from t;
+select substring(s, -2, r) from t;
+select substring(s, l, r) from t;
+
+select '-';
+drop table if exists t;
+create table t(
+                  s FixedString(8),
+                  l Int8,
+                  r Int8
+) engine = Memory;
+insert into t values ('abcdefgh', -2, -2),('12345678', -3, -3);
+
+select substring(s, -2, -2) from t;
+select substring(s, l, -2) from t;
+select substring(s, -2, r) from t;
+select substring(s, l, r) from t;
+
+drop table if exists t;