Skip to content

Commit

Permalink
feat: add functions for splitting strings (#346)
Browse files Browse the repository at this point in the history
  • Loading branch information
@richtia
richtia authored Nov 1, 2022
1 parent f3f6bdc commit 20a2f14
Showing 1 changed file with 97 additions and 27 deletions.
124 changes: 97 additions & 27 deletions extensions/functions_string.yaml
View file
Original file line number Diff line number Diff line change
Expand Up @@ -101,13 +101,13 @@ scalar_functions:
impls:
- args:
- name: case_sensitivity
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII]
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII ]
required: false
- name: multiline
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED]
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED ]
required: false
- name: dotall
options: [ DOTALL_DISABLED, DOTALL_ENABLED]
options: [ DOTALL_DISABLED, DOTALL_ENABLED ]
required: false
- value: "varchar<L1>"
name: "input"
Expand All @@ -120,13 +120,13 @@ scalar_functions:
return: "varchar<L1>"
- args:
- name: case_sensitivity
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII]
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII ]
required: false
- name: multiline
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED]
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED ]
required: false
- name: dotall
options: [ DOTALL_DISABLED, DOTALL_ENABLED]
options: [ DOTALL_DISABLED, DOTALL_ENABLED ]
required: false
- value: "string"
name: "input"
Expand Down Expand Up @@ -523,13 +523,13 @@ scalar_functions:
impls:
- args:
- name: case_sensitivity
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII]
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII ]
required: false
- name: multiline
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED]
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED ]
required: false
- name: dotall
options: [ DOTALL_DISABLED, DOTALL_ENABLED]
options: [ DOTALL_DISABLED, DOTALL_ENABLED ]
required: false
- value: "varchar<L1>"
name: "input"
Expand All @@ -542,13 +542,13 @@ scalar_functions:
return: i64
- args:
- name: case_sensitivity
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII]
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII ]
required: false
- name: multiline
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED]
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED ]
required: false
- name: dotall
options: [ DOTALL_DISABLED, DOTALL_ENABLED]
options: [ DOTALL_DISABLED, DOTALL_ENABLED ]
required: false
- value: "string"
name: "input"
Expand Down Expand Up @@ -620,13 +620,13 @@ scalar_functions:
impls:
- args:
- name: case_sensitivity
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII]
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII ]
required: false
- name: multiline
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED]
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED ]
required: false
- name: dotall
options: [ DOTALL_DISABLED, DOTALL_ENABLED]
options: [ DOTALL_DISABLED, DOTALL_ENABLED ]
required: false
- value: "string"
name: "input"
Expand All @@ -637,13 +637,13 @@ scalar_functions:
return: i64
- args:
- name: case_sensitivity
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII]
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII ]
required: false
- name: multiline
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED]
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED ]
required: false
- name: dotall
options: [ DOTALL_DISABLED, DOTALL_ENABLED]
options: [ DOTALL_DISABLED, DOTALL_ENABLED ]
required: false
- value: "varchar<L1>"
name: "input"
Expand All @@ -654,13 +654,13 @@ scalar_functions:
return: i64
- args:
- name: case_sensitivity
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII]
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII ]
required: false
- name: multiline
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED]
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED ]
required: false
- name: dotall
options: [ DOTALL_DISABLED, DOTALL_ENABLED]
options: [ DOTALL_DISABLED, DOTALL_ENABLED ]
required: false
- value: "fixedchar<L1>"
name: "input"
Expand Down Expand Up @@ -1015,13 +1015,13 @@ scalar_functions:
impls:
- args:
- name: case_sensitivity
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII]
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII ]
required: false
- name: multiline
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED]
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED ]
required: false
- name: dotall
options: [ DOTALL_DISABLED, DOTALL_ENABLED]
options: [ DOTALL_DISABLED, DOTALL_ENABLED ]
required: false
- value: "string"
name: "input"
Expand All @@ -1041,13 +1041,13 @@ scalar_functions:
return: "string"
- args:
- name: case_sensitivity
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII]
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII ]
required: false
- name: multiline
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED]
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED ]
required: false
- name: dotall
options: [ DOTALL_DISABLED, DOTALL_ENABLED]
options: [ DOTALL_DISABLED, DOTALL_ENABLED ]
required: false
- value: "varchar<L1>"
name: "input"
Expand Down Expand Up @@ -1263,6 +1263,76 @@ scalar_functions:
- value: i32
name: "count"
return: "string"
-
name: string_split
description: >-
Split a string into a list of strings, based on a specified `separator` character.
impls:
- args:
- value: "varchar<L1>"
name: "input"
description: The input string.
- value: "varchar<L2>"
name: "separator"
description: A character used for splitting the string.
return: "List<varchar<L1>>"
- args:
- value: "string"
name: "input"
description: The input string.
- value: "string"
name: "separator"
description: A character used for splitting the string.
return: "List<string>"
-
name: regex_string_split
description: >-
Split a string into a list of strings, based on a regular expression pattern. The
substrings matched by the pattern will be used as the separators to split the input
string and will not be included in the resulting list. The regular expression
pattern should follow the International Components for Unicode implementation
(https://unicode-org.github.io/icu/userguide/strings/regexp.html).
The `case_sensitivity` option specifies case-sensitive or case-insensitive matching.
Enabling the `multiline` option will treat the input string as multiple lines. This makes
the `^` and `$` characters match at the beginning and end of any line, instead of just the
beginning and end of the input string. Enabling the `dotall` option makes the `.` character
match line terminator characters in a string.
impls:
- args:
- name: case_sensitivity
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII ]
required: false
- name: multiline
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED ]
required: false
- name: dotall
options: [ DOTALL_DISABLED, DOTALL_ENABLED ]
required: false
- value: "varchar<L1>"
name: "input"
description: The input string.
- value: "varchar<L2>"
name: "pattern"
description: The regular expression to search for within the input string.
return: "List<varchar<L1>>"
- args:
- name: case_sensitivity
options: [ CASE_SENSITIVE, CASE_INSENSITIVE, CASE_INSENSITIVE_ASCII ]
required: false
- name: multiline
options: [ MULTILINE_DISABLED, MULTILINE_ENABLED ]
required: false
- name: dotall
options: [ DOTALL_DISABLED, DOTALL_ENABLED ]
required: false
- value: "string"
name: "input"
description: The input string.
- value: "string"
name: "pattern"
description: The regular expression to search for within the input string.
return: "List<string>"

aggregate_functions:

Expand Down

0 comments on commit 20a2f14

Please sign in to comment.