Skip to content

Commit

Permalink
wrangler ui features
Browse files Browse the repository at this point in the history
  • Loading branch information
AnkitCLI committed Nov 7, 2024
1 parent 637cf06 commit 5182f79
Show file tree
Hide file tree
Showing 16 changed files with 806 additions and 1 deletion.
Original file line number Diff line number Diff line change
@@ -0,0 +1,121 @@
# Copyright © 2024 Cask Data, Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License"); you may not
# use this file except in compliance with the License. You may obtain a copy of
# the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
# WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
# License for the specific language governing permissions and limitations under
# the License.

@Wrangler
Feature: datatype parsers

@BQ_SOURCE_TS_TEST @BQ_SOURCE_TEST @BQ_SINK_TEST
Scenario: To verify User is able to run a pipeline using parse timestamp directive
Given Open Wrangler connections page
Then Click plugin property: "addConnection" button
Then Click plugin property: "bqConnectionRow"
Then Enter input plugin property: "name" with value: "bqConnectionName"
Then Replace input plugin property: "projectId" with value: "projectId"
Then Enter input plugin property: "datasetProjectId" with value: "projectId"
Then Override Service account details in Wrangler connection page if set in environment variables
Then Click plugin property: "testConnection" button
Then Verify the test connection is successful
Then Click plugin property: "connectionCreate" button
Then Verify the connection with name: "bqConnectionName" is created successfully
Then Select connection data row with name: "dataset"
Then Select connection data row with name: "bqSourceTable"
Then Verify connection datatable is displayed for the data: "bqSourceTable"
Then Expand dropdown column: "update_date" and apply directive: "Parse" as "SIMPLEDATE" with: "yyyy-MM-dd" option
Then Expand dropdown column: "create_date" and apply directive: "Parse" as "SIMPLEDATE" with: "yyyy-MM-dd" option
Then Enter directive from CLI "parse-timestamp :time"
Then Enter directive from CLI "parse-as-currency :price :newprice"
Then Enter directive from CLI "format-as-currency :newprice :format_price"
Then Enter directive from CLI "diff-date :create_date :update_date :diff_date"
Then Enter directive from CLI "timestamp-to-datetime :update_date"
Then Enter directive from CLI "rename :newprice :id"
Then Click Create Pipeline button and choose the type of pipeline as: "Batch pipeline"
Then Verify plugin: "BigQueryTable" node is displayed on the canvas with a timeout of 120 seconds
Then Expand Plugin group in the LHS plugins list: "Sink"
Then Select plugin: "BigQuery" from the plugins list as: "Sink"
Then Navigate to the properties page of plugin: "BigQuery2"
Then Click plugin property: "useConnection"
Then Click on the Browse Connections button
Then Select connection: "bqConnectionName"
Then Enter input plugin property: "referenceName" with value: "BQSinkReferenceName"
Then Enter input plugin property: "dataset" with value: "dataset"
Then Enter input plugin property: "table" with value: "bqTargetTable"
Then Validate "BigQuery" plugin properties
Then Close the Plugin Properties page
Then Connect plugins: "Wrangler" and "BigQuery2" to establish connection
Then Save the pipeline
Then Deploy the pipeline
Then Run the Pipeline in Runtime
Then Wait till pipeline is in running state
Then Open and capture logs
Then Verify the pipeline status is "Succeeded"
Then Close the pipeline logs
Then Validate The Data From BQ To BQ With Actual And Expected File for: "ExpectedDirective_parse_Timestamp"
Given Open Wrangler connections page
Then Expand connections of type: "BigQuery"
Then Open action menu for connection: "bqConnectionName" of type: "BigQuery"
Then Select action: "Delete" for connection: "bqConnectionName" of type: "BigQuery"
Then Click plugin property: "Delete" button
Then Verify connection: "bqConnectionName" of type: "BigQuery" is deleted successfully


@BQ_SOURCE_DATETIME_TEST @BQ_SOURCE_TEST @BQ_SINK_TEST
Scenario: To verify User is able to run a pipeline using parse datetime directive
Given Open Wrangler connections page
Then Click plugin property: "addConnection" button
Then Click plugin property: "bqConnectionRow"
Then Enter input plugin property: "name" with value: "bqConnectionName"
Then Replace input plugin property: "projectId" with value: "projectId"
Then Enter input plugin property: "datasetProjectId" with value: "projectId"
Then Override Service account details in Wrangler connection page if set in environment variables
Then Click plugin property: "testConnection" button
Then Verify the test connection is successful
Then Click plugin property: "connectionCreate" button
Then Verify the connection with name: "bqConnectionName" is created successfully
Then Select connection data row with name: "dataset"
Then Select connection data row with name: "bqSourceTable"
Then Verify connection datatable is displayed for the data: "bqSourceTable"
Then Expand dropdown column: "timestamp" and apply directive: "Parse" with directive type: "DATETIME" and select: "Custom_Format" and enter: "yyyy-MM-dd'T'HH:mm:ssX'['z']'"
Then Enter directive from CLI "current-datetime :create_date"
Then Enter directive from CLI "datetime-to-timestamp :timestamp"
Then Enter directive from CLI "format-datetime :create_date 'y'"
Then Enter directive from CLI "format-date :timestamp yyyy-mm-dd"
Then Enter directive from CLI "rename timestamp timecolumn"
Then Click Create Pipeline button and choose the type of pipeline as: "Batch pipeline"
Then Verify plugin: "BigQueryTable" node is displayed on the canvas with a timeout of 120 seconds
Then Expand Plugin group in the LHS plugins list: "Sink"
Then Select plugin: "BigQuery" from the plugins list as: "Sink"
Then Navigate to the properties page of plugin: "BigQuery2"
Then Click plugin property: "useConnection"
Then Click on the Browse Connections button
Then Select connection: "bqConnectionName"
Then Enter input plugin property: "referenceName" with value: "BQSinkReferenceName"
Then Enter input plugin property: "dataset" with value: "dataset"
Then Enter input plugin property: "table" with value: "bqTargetTable"
Then Validate "BigQuery" plugin properties
Then Close the Plugin Properties page
Then Connect plugins: "Wrangler" and "BigQuery2" to establish connection
Then Save the pipeline
Then Deploy the pipeline
Then Run the Pipeline in Runtime
Then Wait till pipeline is in running state
Then Open and capture logs
Then Verify the pipeline status is "Succeeded"
Then Close the pipeline logs
Then Validate The Data From BQ To BQ With Actual And Expected File for: "ExpectedDirective_parse_DatetimeNew"
Given Open Wrangler connections page
Then Expand connections of type: "BigQuery"
Then Open action menu for connection: "bqConnectionName" of type: "BigQuery"
Then Select action: "Delete" for connection: "bqConnectionName" of type: "BigQuery"
Then Click plugin property: "Delete" button
Then Verify connection: "bqConnectionName" of type: "BigQuery" is deleted successfully
Original file line number Diff line number Diff line change
@@ -0,0 +1,65 @@
# Copyright © 2024 Cask Data, Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License"); you may not
# use this file except in compliance with the License. You may obtain a copy of
# the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
# WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
# License for the specific language governing permissions and limitations under
# the License.

@Wrangler
Feature: Wrangler - Run time scenarios for Parse Avro

@BQ_SOURCE_AVRO_TEST @BQ_SOURCE_TEST @BQ_SINK_TEST
Scenario: To verify User is able to run a pipeline using parse avro directive
Given Open Wrangler connections page
Then Click plugin property: "addConnection" button
Then Click plugin property: "bqConnectionRow"
Then Enter input plugin property: "name" with value: "bqConnectionName"
Then Replace input plugin property: "projectId" with value: "projectId"
Then Enter input plugin property: "datasetProjectId" with value: "projectId"
Then Override Service account details in Wrangler connection page if set in environment variables
Then Click plugin property: "testConnection" button
Then Verify the test connection is successful
Then Click plugin property: "connectionCreate" button
Then Verify the connection with name: "bqConnectionName" is created successfully
Then Select connection data row with name: "dataset"
Then Select connection data row with name: "bqSourceTable"
Then Verify connection datatable is displayed for the data: "bqSourceTable"
Then Expand dropdown column: "body" and apply directive: "Parse" as "Avro"
Then Enter directive from CLI "filter-rows-on condition-true name == null || name =~ '^\W*$'"
Then Enter directive from CLI "cut-character name nameNew 2-3"
Then Enter directive from CLI "set-type :value integer"
Then Click Create Pipeline button and choose the type of pipeline as: "Batch pipeline"
Then Verify plugin: "BigQueryTable" node is displayed on the canvas with a timeout of 120 seconds
Then Expand Plugin group in the LHS plugins list: "Sink"
Then Select plugin: "BigQuery" from the plugins list as: "Sink"
Then Navigate to the properties page of plugin: "BigQuery2"
Then Click plugin property: "useConnection"
Then Click on the Browse Connections button
Then Select connection: "bqConnectionName"
Then Enter input plugin property: "referenceName" with value: "BQSinkReferenceName"
Then Enter input plugin property: "dataset" with value: "dataset"
Then Enter input plugin property: "table" with value: "bqTargetTable"
Then Validate "BigQuery" plugin properties
Then Close the Plugin Properties page
Then Connect plugins: "Wrangler" and "BigQuery2" to establish connection
Then Save the pipeline
Then Deploy the pipeline
Then Run the Pipeline in Runtime
Then Wait till pipeline is in running state
Then Open and capture logs
Then Verify the pipeline status is "Succeeded"
Then Close the pipeline logs
Then Validate The Data From BQ To BQ With Actual And Expected File for: "ExpectedDirective_parse_avro"
Given Open Wrangler connections page
Then Expand connections of type: "BigQuery"
Then Open action menu for connection: "bqConnectionName" of type: "BigQuery"
Then Select action: "Delete" for connection: "bqConnectionName" of type: "BigQuery"
Then Click plugin property: "Delete" button
Then Verify connection: "bqConnectionName" of type: "BigQuery" is deleted successfully
Original file line number Diff line number Diff line change
@@ -0,0 +1,71 @@
# Copyright © 2024 Cask Data, Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License"); you may not
# use this file except in compliance with the License. You may obtain a copy of
# the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
# WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
# License for the specific language governing permissions and limitations under
# the License.

@Wrangler
Feature: Wrangler - Run time scenarios for parse csv using UI

@BQ_SOURCE_CSV_TEST @BQ_SOURCE_TEST @BQ_SINK_TEST
Scenario: To verify User is able to run a pipeline using parse csv directive
Given Open Wrangler connections page
Then Click plugin property: "addConnection" button
Then Click plugin property: "bqConnectionRow"
Then Enter input plugin property: "name" with value: "bqConnectionName"
Then Replace input plugin property: "projectId" with value: "projectId"
Then Enter input plugin property: "datasetProjectId" with value: "projectId"
Then Override Service account details in Wrangler connection page if set in environment variables
Then Click plugin property: "testConnection" button
Then Verify the test connection is successful
Then Click plugin property: "connectionCreate" button
Then Verify the connection with name: "bqConnectionName" is created successfully
Then Select connection data row with name: "dataset"
Then Select connection data row with name: "bqSourceTable"
Then Verify connection datatable is displayed for the data: "bqSourceTable"
Then Expand dropdown column: "body" and apply directive: "Parse" as "CSV" with: "Comma" option
Then Expand dropdown column: "body_3" and apply directive: "FillNullOrEmptyCells" as "shubh"
Then Enter directive from CLI "rename body_1 new_id"
Then Enter directive from CLI "quantize body_4 body_q 1:2=20,3:4=40"
Then Expand dropdown column: "body_4" and apply directive: "ChangeDataType" as "Integer"
Then Enter directive from CLI "columns-replace s/^new_//g"
Then Enter directive from CLI "set-headers :abc"
Then Enter directive from CLI "change-column-case uppercase"
Then Enter directive from CLI "cleanse-column-names "
Then Enter directive from CLI "split-to-rows :id '#'"
Then Click Create Pipeline button and choose the type of pipeline as: "Batch pipeline"
Then Verify plugin: "BigQueryTable" node is displayed on the canvas with a timeout of 120 seconds
Then Expand Plugin group in the LHS plugins list: "Sink"
Then Select plugin: "BigQuery" from the plugins list as: "Sink"
Then Navigate to the properties page of plugin: "BigQuery2"
Then Click plugin property: "useConnection"
Then Click on the Browse Connections button
Then Select connection: "bqConnectionName"
Then Enter input plugin property: "referenceName" with value: "BQSinkReferenceName"
Then Enter input plugin property: "dataset" with value: "dataset"
Then Enter input plugin property: "table" with value: "bqTargetTable"
Then Validate "BigQuery" plugin properties
Then Close the Plugin Properties page
Then Connect plugins: "Wrangler" and "BigQuery2" to establish connection
Then Save the pipeline
Then Deploy the pipeline
Then Run the Pipeline in Runtime
Then Wait till pipeline is in running state
Then Open and capture logs
Then Verify the pipeline status is "Succeeded"
Then Close the pipeline logs
Then Validate The Data From BQ To BQ With Actual And Expected File for: "ExpectedDirective_parse_csv"
Given Open Wrangler connections page
Then Expand connections of type: "BigQuery"
Then Open action menu for connection: "bqConnectionName" of type: "BigQuery"
Then Select action: "Delete" for connection: "bqConnectionName" of type: "BigQuery"
Then Click plugin property: "Delete" button
Then Verify connection: "bqConnectionName" of type: "BigQuery" is deleted successfully
Original file line number Diff line number Diff line change
@@ -0,0 +1,70 @@
# Copyright © 2024 Cask Data, Inc.
#
# Licensed under the Apache License, Version 2.0 (the "License"); you may not
# use this file except in compliance with the License. You may obtain a copy of
# the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS, WITHOUT
# WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the
# License for the specific language governing permissions and limitations under
# the License.

@Wrangler
Feature: Parse as excel

@BQ_SINK_TEST
Scenario: To verify User is able to run a pipeline using parse Excel directive
Given Open Wrangler connections page
Then Click plugin property: "addConnection" button
Then Click plugin property: "bqConnectionRow"
Then Enter input plugin property: "name" with value: "bqConnectionName"
Then Replace input plugin property: "projectId" with value: "projectId"
Then Enter input plugin property: "datasetProjectId" with value: "projectId"
Then Override Service account details in Wrangler connection page if set in environment variables
Then Click plugin property: "testConnection" button
Then Verify the test connection is successful
Then Click plugin property: "connectionCreate" button
Then Verify the connection with name: "bqConnectionName" is created successfully
Then Select connection data row with name: "dataset"
Then Select connection data row with name: "bqSourceTableExcel"
Then Verify connection datatable is displayed for the data: "bqSourceTableExcel"
Then Enter directive from CLI "parse-as-excel :body '0' true"
Then Expand dropdown column: "name" and apply directive: "CopyColumn" as "copiedname"
Then Enter directive from CLI "merge name bkd uniquenum ','"
Then Enter directive from CLI "rename bkd rollno"
Then Expand dropdown column: "fwd" and apply directive: "DeleteColumn"
Then Select checkbox on two columns: "id" and "rollno"
Then Expand dropdown column: "id" and apply directive: "SwapTwoColumnNames"
Then Enter directive from CLI "split-to-rows :name 'o'"
Then Enter directive from CLI "filter-rows-on condition-false rollno !~ '2.0'"
Then Click Create Pipeline button and choose the type of pipeline as: "Batch pipeline"
Then Verify plugin: "BigQueryTable" node is displayed on the canvas with a timeout of 120 seconds
Then Expand Plugin group in the LHS plugins list: "Sink"
Then Select plugin: "BigQuery" from the plugins list as: "Sink"
Then Navigate to the properties page of plugin: "BigQuery2"
Then Click plugin property: "useConnection"
Then Click on the Browse Connections button
Then Select connection: "bqConnectionName"
Then Enter input plugin property: "referenceName" with value: "BQSinkReferenceName"
Then Enter input plugin property: "dataset" with value: "dataset"
Then Enter input plugin property: "table" with value: "bqTargetTable"
Then Validate "BigQuery" plugin properties
Then Close the Plugin Properties page
Then Connect plugins: "Wrangler" and "BigQuery2" to establish connection
Then Save the pipeline
Then Deploy the pipeline
Then Run the Pipeline in Runtime
Then Wait till pipeline is in running state
Then Open and capture logs
Then Verify the pipeline status is "Succeeded"
Then Close the pipeline logs
Then Validate The Data From BQ To BQ With Actual And Expected File for: "ExpectedDirective_parse_excel"
Given Open Wrangler connections page
Then Expand connections of type: "BigQuery"
Then Open action menu for connection: "bqConnectionName" of type: "BigQuery"
Then Select action: "Delete" for connection: "bqConnectionName" of type: "BigQuery"
Then Click plugin property: "Delete" button
Then Verify connection: "bqConnectionName" of type: "BigQuery" is deleted successfully
Loading

0 comments on commit 5182f79

Please sign in to comment.