Skip to content

Commit

Permalink
feat: add string transform functions (#267)
Browse files Browse the repository at this point in the history 
 - add concat_ws, repeat, reverse, replace_slice, lower, upper, swapcase,
   capitalize, title, char_length and octet_length to functions_string.yaml
 - modify concat to be variadic

BREAKING CHANGE: compound name for concat has changed to concat:str and
concat:vchar (one argument) to make it 1+ variadic
  • Loading branch information
@richtia
richtia committed Sep 2, 2022
1 parent 3baea53 commit ff2f7f1
Showing 1 changed file with 313 additions and 8 deletions.
321 changes: 313 additions & 8 deletions extensions/functions_string.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -3,15 +3,19 @@
scalar_functions:
-
name: concat
description: Concatenate two strings
description: Concatenate strings.
impls:
- args:
- value: "varchar<L1>"
- value: "varchar<L2>"
return: "varchar<L1 + L2>"
name: "input"
variadic:
min: 1
return: "varchar<L1>"
- args:
- value: "string"
- value: "string"
name: "input"
variadic:
min: 1
return: "string"
-
name: like
Expand Down Expand Up @@ -45,23 +49,32 @@ scalar_functions:
-
name: substring
description: >-
Extract a substring of a specified length starting from position start.
A start value of 1 refers to the first characters of the string.
Extract a substring of a specified `length` starting from position `start`.
A `start` value of 1 refers to the first characters of the string.
impls:
- args:
- value: "varchar<L1>"
name: "input"
- value: i32
name: "start"
- value: i32
name: "length"
return: "varchar<L1>"
- args:
- value: "string"
name: "input"
- value: i32
name: "start"
- value: i32
name: "length"
return: "string"
- args:
- value: "fixedchar<l1>"
name: "input"
- value: i32
name: "start"
- value: i32
name: "length"
return: "string"
-
name: starts_with
Expand Down Expand Up @@ -497,6 +510,290 @@ scalar_functions:
name: "replacement"
description: The replacement string.
return: "varchar<L1>"
-
name: concat_ws
description: Concatenate strings together separated by a separator.
impls:
- args:
- value: "string"
name: "separator"
description: Character to separate strings by.
- value: "string"
name: "string_arguments"
description: Strings to be concatenated.
variadic:
min: 1
return: "string"
- args:
- value: "varchar<L2>"
name: "separator"
description: Character to separate strings by.
- value: "varchar<L1>"
name: "string_arguments"
description: Strings to be concatenated.
variadic:
min: 1
return: "varchar<L1>"
-
name: repeat
description: Repeat a string `count` number of times.
impls:
- args:
- value: "string"
name: "input"
- value: i64
name: "count"
return: "string"
- args:
- value: "varchar<L1>"
- value: i64
name: "input"
- value: i64
name: "count"
return: "varchar<L1>"
-
name: reverse
description: Returns the string in reverse order.
impls:
- args:
- value: "string"
name: "input"
return: "string"
- args:
- value: "varchar<L1>"
name: "input"
return: "varchar<L1>"
- args:
- value: "fixedchar<L1>"
name: "input"
return: "fixedchar<L1>"
-
name: replace_slice
description: >-
Replace a slice of the input string. A specified 'length' of characters will be deleted from
the input string beginning at the 'start' position and will be replaced by a new string. A
start value of 1 indicates the first character of the input string. If start is negative
or zero, or greater than the length of the input string, a null string is returned. If 'length'
is negative, a null string is returned. If 'length' is zero, inserting of the new string
occurs at the specified 'start' position and no characters are deleted. If 'length' is
greater than the input string, deletion will occur up to the last character of the input string.
impls:
- args:
- value: "string"
name: "input"
description: Input string.
- value: i64
name: "start"
description: The position in the string to start deleting/inserting characters.
- value: i64
name: "length"
description: The number of characters to delete from the input string.
- value: "string"
name: "replacement"
description: The new string to insert at the start position.
return: "string"
- args:
- value: "varchar<L1>"
name: "input"
description: Input string.
- value: i64
name: "start"
description: The position in the string to start deleting/inserting characters.
- value: i64
name: "length"
description: The number of characters to delete from the input string.
- value: "varchar<L2>"
name: "replacement"
description: The new string to insert at the start position.
return: "varchar<L1>"
-
name: lower
description: >-
Transform the string to lower case characters. Implementation should follow the utf8_unicode_ci
collations according to the Unicode Collation Algorithm described at http://www.unicode.org/reports/tr10/.
impls:
- args:
- name: char_set
options: [ UTF8, ASCII_ONLY ]
required: false
- value: "string"
name: "input"
return: "string"
- args:
- name: char_set
options: [ UTF8, ASCII_ONLY ]
required: false
- value: "varchar<L1>"
name: "input"
return: "varchar<L1>"
- args:
- name: char_set
options: [ UTF8, ASCII_ONLY ]
required: false
- value: "fixedchar<L1>"
name: "input"
return: "fixedchar<L1>"
-
name: upper
description: >-
Transform the string to upper case characters. Implementation should follow the utf8_unicode_ci
collations according to the Unicode Collation Algorithm described at http://www.unicode.org/reports/tr10/.
impls:
- args:
- name: char_set
options: [ UTF8, ASCII_ONLY ]
required: false
- value: "string"
name: "input"
return: "string"
- args:
- name: char_set
options: [ UTF8, ASCII_ONLY ]
required: false
- value: "varchar<L1>"
name: "input"
return: "varchar<L1>"
- args:
- name: char_set
options: [ UTF8, ASCII_ONLY ]
required: false
- value: "fixedchar<L1>"
name: "input"
return: "fixedchar<L1>"
-
name: swapcase
description: >-
Transform the string's lowercase characters to uppercase and uppercase characters to
lowercase. Implementation should follow the utf8_unicode_ci collations according to the
Unicode Collation Algorithm described at http://www.unicode.org/reports/tr10/.
impls:
- args:
- name: char_set
options: [ UTF8, ASCII_ONLY ]
required: false
- value: "string"
name: "input"
return: "string"
- args:
- name: char_set
options: [ UTF8, ASCII_ONLY ]
required: false
- value: "varchar<L1>"
name: "input"
return: "varchar<L1>"
- args:
- name: char_set
options: [ UTF8, ASCII_ONLY ]
required: false
- value: "fixedchar<L1>"
name: "input"
return: "fixedchar<L1>"
-
name: capitalize
description: >-
Capitalize the first character of the input string. Implementation should follow the
utf8_unicode_ci collations according to the Unicode Collation Algorithm described at
http://www.unicode.org/reports/tr10/.
impls:
- args:
- name: char_set
options: [ UTF8, ASCII_ONLY ]
required: false
- value: "string"
name: "input"
return: "string"
- args:
- name: char_set
options: [ UTF8, ASCII_ONLY ]
required: false
- value: "varchar<L1>"
name: "input"
return: "varchar<L1>"
- args:
- name: char_set
options: [ UTF8, ASCII_ONLY ]
required: false
- value: "fixedchar<L1>"
name: "input"
return: "fixedchar<L1>"
-
name: title
description: >-
Converts the input string into titlecase. Capitalize the first character of each word in the
input string except for articles (a, an, the). Implementation should follow the
utf8_unicode_ci collations according to the Unicode Collation Algorithm described at
http://www.unicode.org/reports/tr10/.
impls:
- args:
- name: char_set
options: [ UTF8, ASCII_ONLY ]
required: false
- value: "string"
name: "input"
return: "string"
- args:
- name: char_set
options: [ UTF8, ASCII_ONLY ]
required: false
- value: "varchar<L1>"
name: "input"
return: "varchar<L1>"
- args:
- name: char_set
options: [ UTF8, ASCII_ONLY ]
required: false
- value: "fixedchar<L1>"
name: "input"
return: "fixedchar<L1>"
-
name: char_length
description: >-
Return the number of characters in the input string. The length includes trailing spaces.
impls:
- args:
- value: "string"
name: "input"
return: i64
- args:
- value: "varchar<L1>"
name: "input"
return: i64
- args:
- value: "fixedchar<L1>"
name: "input"
return: i64
-
name: bit_length
description: Return the number of bits in the input string.
impls:
- args:
- value: "string"
name: "input"
return: i64
- args:
- value: "varchar<L1>"
name: "input"
return: i64
- args:
- value: "fixedchar<L1>"
name: "input"
return: i64
-
name: octet_length
description: Return the number of bytes in the input string.
impls:
- args:
- value: "string"
name: "input"
return: i64
- args:
- value: "varchar<L1>"
name: "input"
return: i64
- args:
- value: "fixedchar<L1>"
name: "input"
return: i64
-
name: ltrim
description: >-
Expand Down Expand Up @@ -627,25 +924,33 @@ scalar_functions:
return: "string"
-
name: left
description: Extract count characters starting from the left of the string.
description: Extract `count` characters starting from the left of the string.
impls:
- args:
- value: "varchar<L1>"
name: "input"
- value: i32
name: "count"
return: "varchar<L1>"
- args:
- value: "string"
name: "input"
- value: i32
name: "count"
return: "string"
-
name: right
description: Extract count characters starting from the right of the string.
description: Extract `count` characters starting from the right of the string.
impls:
- args:
- value: "varchar<L1>"
name: "input"
- value: i32
name: "count"
return: "varchar<L1>"
- args:
- value: "string"
name: "input"
- value: i32
name: "count"
return: "string"

0 comments on commit ff2f7f1

Please sign in to comment.