-
Notifications
You must be signed in to change notification settings - Fork 56
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
7 changed files
with
197 additions
and
435 deletions.
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
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
4 changes: 2 additions & 2 deletions
4
wrangler-transform/src/e2e-test/resources/BQValidationExpectedFiles/Directive_parse_excel
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 |
|---|---|---|
| @@ -1,2 +1,2 @@ | ||
| {"copiedname":"very","id":0,"name":"very","phone":"8838.0","uniquenum":"very,0"} | ||
| {"copiedname":"hello","id":2,"name":"hell","phone":"12345.0","uniquenum":"hello,2"} | ||
| {"copiedname":"very","id":0,"name":"very","phone":"8838.0","rollno":"3.0","uniquenum":"very,0"} | ||
| {"copiedname":"hello","id":2,"name":"hell","phone":"12345.0","rollno":"1.0","uniquenum":"hello,2"} |
2 changes: 1 addition & 1 deletion
2
wrangler-transform/src/e2e-test/resources/pluginParameters.properties
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
425 changes: 0 additions & 425 deletions
425
.../src/e2e-test/resources/testData/Wrangler/parse_excel_Wrangle-cdap-data-pipeline (1).json
This file was deleted.
Oops, something went wrong.
186 changes: 186 additions & 0 deletions
186
...rc/e2e-test/resources/testData/Wrangler/parse_excel_wrangler_copy-cdap-data-pipeline.json
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 +1,186 @@ | ||
| { | ||
| "name": "parse_excel_wrangler_copy", | ||
| "description": "Data Pipeline Application", | ||
| "artifact": { | ||
| "name": "cdap-data-pipeline", | ||
| "version": "6.10.0-SNAPSHOT", | ||
| "scope": "SYSTEM" | ||
| }, | ||
| "config": { | ||
| "resources": { | ||
| "memoryMB": 2048, | ||
| "virtualCores": 1 | ||
| }, | ||
| "driverResources": { | ||
| "memoryMB": 2048, | ||
| "virtualCores": 1 | ||
| }, | ||
| "connections": [ | ||
| { | ||
| "from": "GCSFile", | ||
| "to": "Wrangler" | ||
| }, | ||
| { | ||
| "from": "Wrangler", | ||
| "to": "BigQuery" | ||
| } | ||
| ], | ||
| "postActions": [], | ||
| "properties": {}, | ||
| "processTimingEnabled": true, | ||
| "stageLoggingEnabled": true, | ||
| "stages": [ | ||
| { | ||
| "name": "GCSFile", | ||
| "plugin": { | ||
| "name": "GCSFile", | ||
| "type": "batchsource", | ||
| "label": "GCSFile", | ||
| "artifact": { | ||
| "name": "google-cloud", | ||
| "version": "0.23.0-SNAPSHOT", | ||
| "scope": "SYSTEM" | ||
| }, | ||
| "properties": { | ||
| "format": "blob", | ||
| "path": "gs://00000000-e2e-0014a44f-81be-4501-8360-0ddca1c39789/test1.xlsx", | ||
| "fileEncoding": "UTF-8", | ||
| "useConnection": "false", | ||
| "referenceName": "test", | ||
| "schema": "{\"type\":\"record\",\"name\":\"blob\",\"fields\":[{\"name\":\"body\",\"type\":\"bytes\"}]}", | ||
| "project": "auto-detect", | ||
| "serviceAccountType": "filePath", | ||
| "serviceFilePath": "auto-detect", | ||
| "sampleSize": "1000", | ||
| "filenameOnly": "false", | ||
| "recursive": "false", | ||
| "ignoreNonExistingFolders": "false", | ||
| "encrypted": "false" | ||
| } | ||
| }, | ||
| "outputSchema": [ | ||
| { | ||
| "name": "etlSchemaBody", | ||
| "schema": "{\"type\":\"record\",\"name\":\"blob\",\"fields\":[{\"name\":\"body\",\"type\":\"bytes\"}]}" | ||
| } | ||
| ], | ||
| "id": "GCSFile", | ||
| "type": "batchsource", | ||
| "label": "GCSFile", | ||
| "icon": "fa-plug", | ||
| "$$hashKey": "object:475", | ||
| "isPluginAvailable": true, | ||
| "_uiPosition": { | ||
| "left": "496px", | ||
| "top": "343px" | ||
| } | ||
| }, | ||
| { | ||
| "name": "Wrangler", | ||
| "plugin": { | ||
| "name": "Wrangler", | ||
| "type": "transform", | ||
| "label": "Wrangler", | ||
| "artifact": { | ||
| "name": "wrangler-transform", | ||
| "version": "4.10.0-SNAPSHOT", | ||
| "scope": "SYSTEM" | ||
| }, | ||
| "properties": { | ||
| "directives": "parse-as-excel :body '0' true\ncopy name copiedname\nmerge name bkd uniquenum ','\nrename bkd rollno\ndrop fwd\nswap id rollno\nsplit-to-rows :name 'o'\nfilter-rows-on condition-false rollno !~ '2.0'", | ||
| "field": "*", | ||
| "precondition": "false", | ||
| "workspaceId": "667f9e85-6c36-4d38-ad48-ef85db7a04a2", | ||
| "schema": "{\"type\":\"record\",\"name\":\"output\",\"fields\":[{\"name\":\"id\",\"type\":[\"int\",\"null\"]},{\"name\":\"rollno\",\"type\":[\"string\",\"null\"]},{\"name\":\"name\",\"type\":[\"string\",\"null\"]},{\"name\":\"phone\",\"type\":[\"string\",\"null\"]},{\"name\":\"copiedname\",\"type\":[\"string\",\"null\"]},{\"name\":\"uniquenum\",\"type\":[\"string\",\"null\"]}]}", | ||
| "on-error": "fail-pipeline" | ||
| } | ||
| }, | ||
| "outputSchema": [ | ||
| { | ||
| "name": "etlSchemaBody", | ||
| "schema": "{\"type\":\"record\",\"name\":\"output\",\"fields\":[{\"name\":\"id\",\"type\":[\"int\",\"null\"]},{\"name\":\"rollno\",\"type\":[\"string\",\"null\"]},{\"name\":\"name\",\"type\":[\"string\",\"null\"]},{\"name\":\"phone\",\"type\":[\"string\",\"null\"]},{\"name\":\"copiedname\",\"type\":[\"string\",\"null\"]},{\"name\":\"uniquenum\",\"type\":[\"string\",\"null\"]}]}" | ||
| } | ||
| ], | ||
| "inputSchema": [ | ||
| { | ||
| "name": "GCSFile", | ||
| "schema": "{\"type\":\"record\",\"name\":\"blob\",\"fields\":[{\"name\":\"body\",\"type\":\"bytes\"}]}" | ||
| } | ||
| ], | ||
| "id": "Wrangler", | ||
| "type": "transform", | ||
| "label": "Wrangler", | ||
| "icon": "icon-DataPreparation", | ||
| "$$hashKey": "object:476", | ||
| "isPluginAvailable": true, | ||
| "_uiPosition": { | ||
| "left": "796px", | ||
| "top": "343px" | ||
| } | ||
| }, | ||
| { | ||
| "name": "BigQuery", | ||
| "plugin": { | ||
| "name": "BigQueryTable", | ||
| "type": "batchsink", | ||
| "label": "BigQuery", | ||
| "artifact": { | ||
| "name": "google-cloud", | ||
| "version": "0.23.0-SNAPSHOT", | ||
| "scope": "SYSTEM" | ||
| }, | ||
| "properties": { | ||
| "useConnection": "false", | ||
| "project": "auto-detect", | ||
| "serviceAccountType": "filePath", | ||
| "serviceFilePath": "auto-detect", | ||
| "dataset": "Wrangler", | ||
| "table": "extab34", | ||
| "operation": "insert", | ||
| "truncateTable": "false", | ||
| "allowSchemaRelaxation": "false", | ||
| "location": "US", | ||
| "createPartitionedTable": "false", | ||
| "partitioningType": "TIME", | ||
| "partitionFilterRequired": "false", | ||
| "schema": "{\"type\":\"record\",\"name\":\"output\",\"fields\":[{\"name\":\"id\",\"type\":[\"int\",\"null\"]},{\"name\":\"rollno\",\"type\":[\"string\",\"null\"]},{\"name\":\"name\",\"type\":[\"string\",\"null\"]},{\"name\":\"phone\",\"type\":[\"string\",\"null\"]},{\"name\":\"copiedname\",\"type\":[\"string\",\"null\"]},{\"name\":\"uniquenum\",\"type\":[\"string\",\"null\"]}]}" | ||
| } | ||
| }, | ||
| "outputSchema": [ | ||
| { | ||
| "name": "etlSchemaBody", | ||
| "schema": "{\"type\":\"record\",\"name\":\"output\",\"fields\":[{\"name\":\"id\",\"type\":[\"int\",\"null\"]},{\"name\":\"rollno\",\"type\":[\"string\",\"null\"]},{\"name\":\"name\",\"type\":[\"string\",\"null\"]},{\"name\":\"phone\",\"type\":[\"string\",\"null\"]},{\"name\":\"copiedname\",\"type\":[\"string\",\"null\"]},{\"name\":\"uniquenum\",\"type\":[\"string\",\"null\"]}]}" | ||
| } | ||
| ], | ||
| "inputSchema": [ | ||
| { | ||
| "name": "Wrangler", | ||
| "schema": "{\"type\":\"record\",\"name\":\"output\",\"fields\":[{\"name\":\"id\",\"type\":[\"int\",\"null\"]},{\"name\":\"rollno\",\"type\":[\"string\",\"null\"]},{\"name\":\"name\",\"type\":[\"string\",\"null\"]},{\"name\":\"phone\",\"type\":[\"string\",\"null\"]},{\"name\":\"copiedname\",\"type\":[\"string\",\"null\"]},{\"name\":\"uniquenum\",\"type\":[\"string\",\"null\"]}]}" | ||
| } | ||
| ], | ||
| "id": "BigQuery", | ||
| "type": "batchsink", | ||
| "label": "BigQuery", | ||
| "icon": "fa-plug", | ||
| "$$hashKey": "object:477", | ||
| "isPluginAvailable": true, | ||
| "_uiPosition": { | ||
| "left": "1096px", | ||
| "top": "343px" | ||
| } | ||
| } | ||
| ], | ||
| "schedule": "0 1 */1 * *", | ||
| "engine": "spark", | ||
| "numOfRecordsPreview": 100, | ||
| "rangeRecordsPreview": { | ||
| "min": 1, | ||
| "max": "5000" | ||
| }, | ||
| "description": "Data Pipeline Application", | ||
| "maxConcurrentRuns": 1, | ||
| "pushdownEnabled": false, | ||
| "transformationPushdown": {} | ||
| }, | ||
| "version": "2dd12daa-5395-11ee-9dac-000000d0cf32" | ||
| } |