DataCleaner
DataCleaner copied to clipboard
NPE: write HDFS file
Step to reproduce:
- Open the sample job below
- Open "Create CSV" component
- Go to the path of the file ("hdfs:///datacleaner/results/test/DKCustomers.csv")
- Remove the 3 slashes from the path.
Result:
Expected result: No NPE.
Job:
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<job xmlns="http://eobjects.org/analyzerbeans/job/1.0">
<job-metadata>
<job-description>Created with DataCleaner Enterprise edition 5.0</job-description>
<author>claudiap</author>
<updated-date>2016-04-12+02:00</updated-date>
<metadata-properties>
<property name="CoordinatesX.datastores.customers.csv">40</property>
<property name="CoordinatesY.datastores.customers.csv">40</property>
</metadata-properties>
</job-metadata>
<source>
<data-context ref="Customers"/>
<columns>
<column id="col_id" path="id" type="STRING"/>
<column id="col_given_name" path="given_name" type="STRING"/>
<column id="col_family_name" path="family_name" type="STRING"/>
<column id="col_company" path="company" type="STRING"/>
<column id="col_address_line" path="address_line" type="STRING"/>
<column id="col_post_code" path="post_code" type="STRING"/>
<column id="col_city" path="city" type="STRING"/>
<column id="col_country" path="country" type="STRING"/>
<column id="col_email" path="email" type="STRING"/>
<column id="col_birthdate" path="birthdate" type="STRING"/>
<column id="col_gender" path="gender" type="STRING"/>
<column id="col_job_title" path="job_title" type="STRING"/>
<column id="col_income_amount" path="income_amount" type="STRING"/>
<column id="col_income_currency" path="income_currency" type="STRING"/>
</columns>
</source>
<transformation>
<filter>
<descriptor ref="Equals"/>
<metadata-properties>
<property name="CoordinatesY">300</property>
<property name="CoordinatesX">121</property>
</metadata-properties>
<properties>
<property name="Compare values" value="[DK]"/>
</properties>
<input ref="col_country" name="Input column"/>
<outcome id="outcome_0" category="EQUALS"/>
</filter>
</transformation>
<analysis>
<analyzer requires="outcome_0">
<descriptor ref="Create CSV file"/>
<metadata-properties>
<property name="CoordinatesX">419</property>
<property name="CoordinatesY">249</property>
</metadata-properties>
<properties>
<property name="File" value="s3://hdfs:///datacleaner/results/test/DKCustomers.csv"/>
<property name="Separator char" value="&#44;"/>
<property name="Quote char" value="&quot;"/>
<property name="Escape char" value="\"/>
<property name="Include header" value="true"/>
<property name="Encoding" value="UTF-8"/>
<property name="Fields" value="[id,given_name,family_name,company,address_line,post_code,city,country,email,birthdate,gender,job_title,income_amount,income_currency]"/>
<property name="Overwrite file if exists" value="true"/>
</properties>
<input ref="col_id" name="Columns"/>
<input ref="col_given_name" name="Columns"/>
<input ref="col_family_name" name="Columns"/>
<input ref="col_company" name="Columns"/>
<input ref="col_address_line" name="Columns"/>
<input ref="col_post_code" name="Columns"/>
<input ref="col_city" name="Columns"/>
<input ref="col_country" name="Columns"/>
<input ref="col_email" name="Columns"/>
<input ref="col_birthdate" name="Columns"/>
<input ref="col_gender" name="Columns"/>
<input ref="col_job_title" name="Columns"/>
<input ref="col_income_amount" name="Columns"/>
<input ref="col_income_currency" name="Columns"/>
</analyzer>
</analysis>
</job>