feat: Visualize complex Hive column types #1072
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,79 @@ | ||
| import { parseType } from 'lib/utils/complex-types'; | ||
|
|
||
| test('parseType', () => { | ||
| expect( | ||
| parseType( | ||
| 'struct<date:struct<year:int,month:int,day:int>,hour:int,minute:int,second:int,timeZoneId:string>' | ||
| ) | ||
| ).toEqual({ | ||
| date: { | ||
| year: 'int', | ||
| month: 'int', | ||
| day: 'int', | ||
| }, | ||
| hour: 'int', | ||
| minute: 'int', | ||
| second: 'int', | ||
| timeZoneId: 'string', | ||
| }); | ||
|
|
||
| expect( | ||
| parseType( | ||
| 'array<struct<size:struct<width:int,height:int,isAspectRatio:boolean>>>' | ||
| ) | ||
| ).toEqual([ | ||
| { | ||
| size: { | ||
| width: 'int', | ||
| height: 'int', | ||
| isAspectRatio: 'boolean', | ||
| }, | ||
| }, | ||
| ]); | ||
|
|
||
| expect( | ||
| parseType( | ||
| 'struct<purchasePath:string,resultToken:string,sessionId:string,site:struct<eapid:bigint,tpid:bigint>,tests:array<struct<bucketValue:string,experimentId:string,instanceId:string>>,user:struct<guid:string,tuid:string>>' | ||
| ) | ||
| ).toEqual({ | ||
| purchasePath: 'string', | ||
| resultToken: 'string', | ||
| sessionId: 'string', | ||
| site: { | ||
| eapid: 'bigint', | ||
| tpid: 'bigint', | ||
| }, | ||
| tests: [ | ||
| { | ||
| bucketValue: 'string', | ||
| experimentId: 'string', | ||
| instanceId: 'string', | ||
| }, | ||
| ], | ||
| user: { | ||
| guid: 'string', | ||
| tuid: 'string', | ||
| }, | ||
| }); | ||
|
|
||
| expect(parseType('map<string,string>')).toEqual({ | ||
| key: 'string', | ||
| value: 'string', | ||
| }); | ||
|
|
||
| expect( | ||
| parseType( | ||
| 'map<string,uniontype<string,int,bigint,float,double,struct<year:int,month:int,day:int>>>' | ||
| ) | ||
| ).toEqual({ | ||
| key: 'string', | ||
| value: [ | ||
| 'string', | ||
| 'int', | ||
| 'bigint', | ||
| 'float', | ||
| 'double', | ||
| { year: 'int', month: 'int', day: 'int' }, | ||
| ], | ||
| }); | ||
| }); |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,153 @@ | ||
| /** | ||
| * Convert a complex Hive type string to a nested JSON object | ||
| * | ||
| * Example: 'struct<date:struct<year:int,month:int,day:int>,hour:int,minute:int,second:int,timeZoneId:string>' | ||
| * Output: { | ||
| date: { | ||
| year: 'int', | ||
| month: 'int', | ||
| day: 'int', | ||
| }, | ||
| hour: 'int', | ||
| minute: 'int', | ||
| second: 'int', | ||
| timeZoneId: 'string', | ||
| } | ||
| */ | ||
| export function parseType(type: string): any | string { | ||
|
There was a problem hiding this comment. will there be cases of
and what happens if the parsing fails? |
||
| if (type.startsWith('struct<')) { | ||
| return parseStructType(type); | ||
| } else if (type.startsWith('array<')) { | ||
| return parseArrayType(type); | ||
| } else if (type.startsWith('map<')) { | ||
| return parseMapType(type); | ||
| } else if (type.startsWith('uniontype<')) { | ||
| return parseUnionType(type); | ||
| } else { | ||
| return type; | ||
| } | ||
| } | ||
|
|
||
| export function parseStructType(type: string): Record<string, any> | string { | ||
| const structRegex = /struct<(.*)>/; | ||
| const structMatch = type.match(structRegex); | ||
| if (!structMatch) { | ||
| return type; | ||
| } | ||
|
|
||
| const structStr = structMatch[1]; | ||
| const structObj: Record<string, any> = {}; | ||
| let currentKey = ''; | ||
| let currentVal = ''; | ||
| let depth = 0; | ||
|
|
||
| for (const char of structStr) { | ||
| if (char === ':') { | ||
| if (depth > 0) { | ||
| currentVal += char; | ||
| } else { | ||
| currentKey = currentVal; | ||
| currentVal = ''; | ||
| } | ||
| } else if (char === ',') { | ||
| if (depth === 0) { | ||
| structObj[currentKey] = parseType(currentVal); | ||
| currentKey = ''; | ||
| currentVal = ''; | ||
| } else { | ||
| currentVal += char; | ||
| } | ||
| } else if (char === '<') { | ||
| depth += 1; | ||
| currentVal += char; | ||
| } else if (char === '>') { | ||
| depth -= 1; | ||
| currentVal += char; | ||
| } else { | ||
| currentVal += char; | ||
| } | ||
| } | ||
|
|
||
| structObj[currentKey] = parseType(currentVal); | ||
| return structObj; | ||
| } | ||
|
|
||
| export function parseMapType(type: string): Record<string, any> | string { | ||
| const mapRegex = /map<(.*)>/; | ||
| const mapMatch = type.match(mapRegex); | ||
| if (!mapMatch) { | ||
| return type; | ||
| } | ||
|
|
||
| const mapStr = mapMatch[1]; | ||
| const mapObj: Record<string, any> = {}; | ||
| let currentKey = ''; | ||
| let currentVal = ''; | ||
| let depth = 0; | ||
|
|
||
| for (const char of mapStr) { | ||
| if (char === ',') { | ||
| if (depth > 0) { | ||
| currentVal += char; | ||
| } else { | ||
| currentKey = currentVal; | ||
| currentVal = ''; | ||
| } | ||
| } else if (char === '<') { | ||
| depth += 1; | ||
| currentVal += char; | ||
| } else if (char === '>') { | ||
| depth -= 1; | ||
| currentVal += char; | ||
| } else { | ||
| currentVal += char; | ||
| } | ||
| } | ||
|
|
||
| mapObj.key = parseType(currentKey); | ||
| mapObj.value = parseType(currentVal); | ||
| return mapObj; | ||
| } | ||
|
|
||
| export function parseUnionType(type: string): Record<string, any> | string { | ||
| const unionRegex = /uniontype<(.*)>/; | ||
| const unionMatch = type.match(unionRegex); | ||
| if (!unionMatch) { | ||
| return type; | ||
| } | ||
|
|
||
| const unionStr = unionMatch[1]; | ||
| const unionList: string[] = []; | ||
| let currentVal = ''; | ||
| let depth = 0; | ||
|
|
||
| for (const char of unionStr) { | ||
| if (char === ',') { | ||
| if (depth > 0) { | ||
| currentVal += char; | ||
| } else { | ||
| unionList.push(currentVal); | ||
| currentVal = ''; | ||
| } | ||
| } else if (char === '<') { | ||
| depth += 1; | ||
| currentVal += char; | ||
| } else if (char === '>') { | ||
| depth -= 1; | ||
| currentVal += char; | ||
| } else { | ||
| currentVal += char; | ||
| } | ||
| } | ||
| unionList.push(currentVal); | ||
|
|
||
| return unionList.map((t) => parseType(t)); | ||
| } | ||
|
|
||
| export function parseArrayType(type: string): Record<string, any> | string { | ||
| if (type.startsWith('array<')) { | ||
| const array = type.substring('array<'.length, type.length - 1); | ||
| return [parseType(array)]; | ||
| } | ||
| return type; | ||
| } | ||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
why need the
<> </>? it only has a single child