Skip to content

Instantly share code, notes, and snippets.

@mattyb149
Last active August 29, 2015 14:13
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save mattyb149/e4cf796ff45983ebf87e to your computer and use it in GitHub Desktop.
Save mattyb149/e4cf796ff45983ebf87e to your computer and use it in GitHub Desktop.
Split rows based on a field value in Pentaho Data Integration
<?xml version="1.0" encoding="UTF-8"?>
<transformation>
<info>
<name>split_field_num_records</name>
<description/>
<extended_description/>
<trans_version/>
<trans_type>Normal</trans_type>
<directory>&#x2f;</directory>
<parameters>
</parameters>
<log>
<trans-log-table><connection/>
<schema/>
<table/>
<size_limit_lines/>
<interval/>
<timeout_days/>
<field><id>ID_BATCH</id><enabled>Y</enabled><name>ID_BATCH</name></field><field><id>CHANNEL_ID</id><enabled>Y</enabled><name>CHANNEL_ID</name></field><field><id>TRANSNAME</id><enabled>Y</enabled><name>TRANSNAME</name></field><field><id>STATUS</id><enabled>Y</enabled><name>STATUS</name></field><field><id>LINES_READ</id><enabled>Y</enabled><name>LINES_READ</name><subject/></field><field><id>LINES_WRITTEN</id><enabled>Y</enabled><name>LINES_WRITTEN</name><subject/></field><field><id>LINES_UPDATED</id><enabled>Y</enabled><name>LINES_UPDATED</name><subject/></field><field><id>LINES_INPUT</id><enabled>Y</enabled><name>LINES_INPUT</name><subject/></field><field><id>LINES_OUTPUT</id><enabled>Y</enabled><name>LINES_OUTPUT</name><subject/></field><field><id>LINES_REJECTED</id><enabled>Y</enabled><name>LINES_REJECTED</name><subject/></field><field><id>ERRORS</id><enabled>Y</enabled><name>ERRORS</name></field><field><id>STARTDATE</id><enabled>Y</enabled><name>STARTDATE</name></field><field><id>ENDDATE</id><enabled>Y</enabled><name>ENDDATE</name></field><field><id>LOGDATE</id><enabled>Y</enabled><name>LOGDATE</name></field><field><id>DEPDATE</id><enabled>Y</enabled><name>DEPDATE</name></field><field><id>REPLAYDATE</id><enabled>Y</enabled><name>REPLAYDATE</name></field><field><id>LOG_FIELD</id><enabled>Y</enabled><name>LOG_FIELD</name></field><field><id>EXECUTING_SERVER</id><enabled>N</enabled><name>EXECUTING_SERVER</name></field><field><id>EXECUTING_USER</id><enabled>N</enabled><name>EXECUTING_USER</name></field><field><id>CLIENT</id><enabled>N</enabled><name>CLIENT</name></field></trans-log-table>
<perf-log-table><connection/>
<schema/>
<table/>
<interval/>
<timeout_days/>
<field><id>ID_BATCH</id><enabled>Y</enabled><name>ID_BATCH</name></field><field><id>SEQ_NR</id><enabled>Y</enabled><name>SEQ_NR</name></field><field><id>LOGDATE</id><enabled>Y</enabled><name>LOGDATE</name></field><field><id>TRANSNAME</id><enabled>Y</enabled><name>TRANSNAME</name></field><field><id>STEPNAME</id><enabled>Y</enabled><name>STEPNAME</name></field><field><id>STEP_COPY</id><enabled>Y</enabled><name>STEP_COPY</name></field><field><id>LINES_READ</id><enabled>Y</enabled><name>LINES_READ</name></field><field><id>LINES_WRITTEN</id><enabled>Y</enabled><name>LINES_WRITTEN</name></field><field><id>LINES_UPDATED</id><enabled>Y</enabled><name>LINES_UPDATED</name></field><field><id>LINES_INPUT</id><enabled>Y</enabled><name>LINES_INPUT</name></field><field><id>LINES_OUTPUT</id><enabled>Y</enabled><name>LINES_OUTPUT</name></field><field><id>LINES_REJECTED</id><enabled>Y</enabled><name>LINES_REJECTED</name></field><field><id>ERRORS</id><enabled>Y</enabled><name>ERRORS</name></field><field><id>INPUT_BUFFER_ROWS</id><enabled>Y</enabled><name>INPUT_BUFFER_ROWS</name></field><field><id>OUTPUT_BUFFER_ROWS</id><enabled>Y</enabled><name>OUTPUT_BUFFER_ROWS</name></field></perf-log-table>
<channel-log-table><connection/>
<schema/>
<table/>
<timeout_days/>
<field><id>ID_BATCH</id><enabled>Y</enabled><name>ID_BATCH</name></field><field><id>CHANNEL_ID</id><enabled>Y</enabled><name>CHANNEL_ID</name></field><field><id>LOG_DATE</id><enabled>Y</enabled><name>LOG_DATE</name></field><field><id>LOGGING_OBJECT_TYPE</id><enabled>Y</enabled><name>LOGGING_OBJECT_TYPE</name></field><field><id>OBJECT_NAME</id><enabled>Y</enabled><name>OBJECT_NAME</name></field><field><id>OBJECT_COPY</id><enabled>Y</enabled><name>OBJECT_COPY</name></field><field><id>REPOSITORY_DIRECTORY</id><enabled>Y</enabled><name>REPOSITORY_DIRECTORY</name></field><field><id>FILENAME</id><enabled>Y</enabled><name>FILENAME</name></field><field><id>OBJECT_ID</id><enabled>Y</enabled><name>OBJECT_ID</name></field><field><id>OBJECT_REVISION</id><enabled>Y</enabled><name>OBJECT_REVISION</name></field><field><id>PARENT_CHANNEL_ID</id><enabled>Y</enabled><name>PARENT_CHANNEL_ID</name></field><field><id>ROOT_CHANNEL_ID</id><enabled>Y</enabled><name>ROOT_CHANNEL_ID</name></field></channel-log-table>
<step-log-table><connection/>
<schema/>
<table/>
<timeout_days/>
<field><id>ID_BATCH</id><enabled>Y</enabled><name>ID_BATCH</name></field><field><id>CHANNEL_ID</id><enabled>Y</enabled><name>CHANNEL_ID</name></field><field><id>LOG_DATE</id><enabled>Y</enabled><name>LOG_DATE</name></field><field><id>TRANSNAME</id><enabled>Y</enabled><name>TRANSNAME</name></field><field><id>STEPNAME</id><enabled>Y</enabled><name>STEPNAME</name></field><field><id>STEP_COPY</id><enabled>Y</enabled><name>STEP_COPY</name></field><field><id>LINES_READ</id><enabled>Y</enabled><name>LINES_READ</name></field><field><id>LINES_WRITTEN</id><enabled>Y</enabled><name>LINES_WRITTEN</name></field><field><id>LINES_UPDATED</id><enabled>Y</enabled><name>LINES_UPDATED</name></field><field><id>LINES_INPUT</id><enabled>Y</enabled><name>LINES_INPUT</name></field><field><id>LINES_OUTPUT</id><enabled>Y</enabled><name>LINES_OUTPUT</name></field><field><id>LINES_REJECTED</id><enabled>Y</enabled><name>LINES_REJECTED</name></field><field><id>ERRORS</id><enabled>Y</enabled><name>ERRORS</name></field><field><id>LOG_FIELD</id><enabled>N</enabled><name>LOG_FIELD</name></field></step-log-table>
<metrics-log-table><connection/>
<schema/>
<table/>
<timeout_days/>
<field><id>ID_BATCH</id><enabled>Y</enabled><name>ID_BATCH</name></field><field><id>CHANNEL_ID</id><enabled>Y</enabled><name>CHANNEL_ID</name></field><field><id>LOG_DATE</id><enabled>Y</enabled><name>LOG_DATE</name></field><field><id>METRICS_DATE</id><enabled>Y</enabled><name>METRICS_DATE</name></field><field><id>METRICS_CODE</id><enabled>Y</enabled><name>METRICS_CODE</name></field><field><id>METRICS_DESCRIPTION</id><enabled>Y</enabled><name>METRICS_DESCRIPTION</name></field><field><id>METRICS_SUBJECT</id><enabled>Y</enabled><name>METRICS_SUBJECT</name></field><field><id>METRICS_TYPE</id><enabled>Y</enabled><name>METRICS_TYPE</name></field><field><id>METRICS_VALUE</id><enabled>Y</enabled><name>METRICS_VALUE</name></field></metrics-log-table>
</log>
<maxdate>
<connection/>
<table/>
<field/>
<offset>0.0</offset>
<maxdiff>0.0</maxdiff>
</maxdate>
<size_rowset>10000</size_rowset>
<sleep_time_empty>50</sleep_time_empty>
<sleep_time_full>50</sleep_time_full>
<unique_connections>N</unique_connections>
<feedback_shown>Y</feedback_shown>
<feedback_size>50000</feedback_size>
<using_thread_priorities>Y</using_thread_priorities>
<shared_objects_file/>
<capture_step_performance>N</capture_step_performance>
<step_performance_capturing_delay>1000</step_performance_capturing_delay>
<step_performance_capturing_size_limit>100</step_performance_capturing_size_limit>
<dependencies>
</dependencies>
<partitionschemas>
</partitionschemas>
<slaveservers>
</slaveservers>
<clusterschemas>
</clusterschemas>
<created_user>-</created_user>
<created_date>2015&#x2f;01&#x2f;08 10&#x3a;05&#x3a;41.537</created_date>
<modified_user>-</modified_user>
<modified_date>2015&#x2f;01&#x2f;08 10&#x3a;05&#x3a;41.537</modified_date>
</info>
<notepads>
</notepads>
<order>
<hop> <from>Calc seat &#x23;</from><to>Select columns</to><enabled>Y</enabled> </hop>
<hop> <from>Data Grid</from><to>Clone seats</to><enabled>Y</enabled> </hop>
<hop> <from>Clone seats</from><to>Exclude original row</to><enabled>Y</enabled> </hop>
<hop> <from>Exclude original row</from><to>Calc seat &#x23;</to><enabled>Y</enabled> </hop>
</order>
<step>
<name>Data Grid</name>
<type>DataGrid</type>
<description/>
<distribute>Y</distribute>
<custom_distribution/>
<copies>1</copies>
<partitioning>
<method>none</method>
<schema_name/>
</partitioning>
<fields>
<field>
<name>event_name</name>
<type>String</type>
<format/>
<currency/>
<decimal/>
<group/>
<length>-1</length>
<precision>-1</precision>
<set_empty_string>N</set_empty_string>
</field>
<field>
<name>section_name</name>
<type>String</type>
<format/>
<currency/>
<decimal/>
<group/>
<length>-1</length>
<precision>-1</precision>
<set_empty_string>N</set_empty_string>
</field>
<field>
<name>row_name</name>
<type>String</type>
<format/>
<currency/>
<decimal/>
<group/>
<length>-1</length>
<precision>-1</precision>
<set_empty_string>N</set_empty_string>
</field>
<field>
<name>num_seats</name>
<type>Integer</type>
<format/>
<currency/>
<decimal/>
<group/>
<length>-1</length>
<precision>-1</precision>
<set_empty_string>N</set_empty_string>
</field>
<field>
<name>seat_num</name>
<type>Integer</type>
<format/>
<currency/>
<decimal/>
<group/>
<length>-1</length>
<precision>-1</precision>
<set_empty_string>N</set_empty_string>
</field>
<field>
<name>last_seat</name>
<type>Integer</type>
<format/>
<currency/>
<decimal/>
<group/>
<length>-1</length>
<precision>-1</precision>
<set_empty_string>N</set_empty_string>
</field>
<field>
<name>client_name</name>
<type>String</type>
<format/>
<currency/>
<decimal/>
<group/>
<length>-1</length>
<precision>-1</precision>
<set_empty_string>N</set_empty_string>
</field>
<field>
<name>venue_name</name>
<type>String</type>
<format/>
<currency/>
<decimal/>
<group/>
<length>-1</length>
<precision>-1</precision>
<set_empty_string>N</set_empty_string>
</field>
<field>
<name>file_prefix</name>
<type>String</type>
<format/>
<currency/>
<decimal/>
<group/>
<length>-1</length>
<precision>-1</precision>
<set_empty_string>N</set_empty_string>
</field>
</fields>
<data>
<line> <item>SJQ0802</item><item>122</item><item>28</item><item>4</item><item>6</item><item>9</item><item>49ers</item><item>Levis Stadium</item><item>sbl49ers</item> </line>
</data>
<cluster_schema/>
<remotesteps> <input> </input> <output> </output> </remotesteps> <GUI>
<xloc>34</xloc>
<yloc>32</yloc>
<draw>Y</draw>
</GUI>
</step>
<step>
<name>Calc seat &#x23;</name>
<type>Calculator</type>
<description/>
<distribute>Y</distribute>
<custom_distribution/>
<copies>1</copies>
<partitioning>
<method>none</method>
<schema_name/>
</partitioning>
<calculation><field_name>ONE</field_name>
<calc_type>CONSTANT</calc_type>
<field_a>1</field_a>
<field_b/>
<field_c/>
<value_type>Integer</value_type>
<value_length>-1</value_length>
<value_precision>-1</value_precision>
<remove>N</remove>
<conversion_mask/>
<decimal_symbol/>
<grouping_symbol/>
<currency_symbol/>
</calculation>
<calculation><field_name>temp</field_name>
<calc_type>ADD</calc_type>
<field_a>seat_num</field_a>
<field_b>seat_index_rownum</field_b>
<field_c/>
<value_type>Integer</value_type>
<value_length>-1</value_length>
<value_precision>-1</value_precision>
<remove>Y</remove>
<conversion_mask/>
<decimal_symbol/>
<grouping_symbol/>
<currency_symbol/>
</calculation>
<calculation><field_name>seatNum</field_name>
<calc_type>SUBTRACT</calc_type>
<field_a>temp</field_a>
<field_b>ONE</field_b>
<field_c/>
<value_type>Integer</value_type>
<value_length>-1</value_length>
<value_precision>-1</value_precision>
<remove>N</remove>
<conversion_mask/>
<decimal_symbol/>
<grouping_symbol/>
<currency_symbol/>
</calculation>
<cluster_schema/>
<remotesteps> <input> </input> <output> </output> </remotesteps> <GUI>
<xloc>388</xloc>
<yloc>32</yloc>
<draw>Y</draw>
</GUI>
</step>
<step>
<name>Select columns</name>
<type>SelectValues</type>
<description/>
<distribute>Y</distribute>
<custom_distribution/>
<copies>1</copies>
<partitioning>
<method>none</method>
<schema_name/>
</partitioning>
<fields> <field> <name>event_name</name>
<rename/>
<length>-2</length>
<precision>-2</precision>
</field> <field> <name>section_name</name>
<rename/>
<length>-2</length>
<precision>-2</precision>
</field> <field> <name>row_name</name>
<rename/>
<length>-2</length>
<precision>-2</precision>
</field> <field> <name>ONE</name>
<rename>num_seats</rename>
<length>-2</length>
<precision>-2</precision>
</field> <field> <name>seatNum</name>
<rename>seat_num</rename>
<length>-2</length>
<precision>-2</precision>
</field> <field> <name>seatNum</name>
<rename>last_seat</rename>
<length>-2</length>
<precision>-2</precision>
</field> <field> <name>client_name</name>
<rename/>
<length>-2</length>
<precision>-2</precision>
</field> <field> <name>venue_name</name>
<rename/>
<length>-2</length>
<precision>-2</precision>
</field> <field> <name>file_prefix</name>
<rename/>
<length>-2</length>
<precision>-2</precision>
</field> <select_unspecified>N</select_unspecified>
</fields> <cluster_schema/>
<remotesteps> <input> </input> <output> </output> </remotesteps> <GUI>
<xloc>497</xloc>
<yloc>32</yloc>
<draw>Y</draw>
</GUI>
</step>
<step>
<name>Clone seats</name>
<type>CloneRow</type>
<description/>
<distribute>Y</distribute>
<custom_distribution/>
<copies>1</copies>
<partitioning>
<method>none</method>
<schema_name/>
</partitioning>
<nrclones>0</nrclones>
<addcloneflag>Y</addcloneflag>
<cloneflagfield>clone&#x3f;</cloneflagfield>
<nrcloneinfield>Y</nrcloneinfield>
<nrclonefield>num_seats</nrclonefield>
<addclonenum>Y</addclonenum>
<clonenumfield>seat_index_rownum</clonenumfield>
<cluster_schema/>
<remotesteps> <input> </input> <output> </output> </remotesteps> <GUI>
<xloc>136</xloc>
<yloc>32</yloc>
<draw>Y</draw>
</GUI>
</step>
<step>
<name>Exclude original row</name>
<type>FilterRows</type>
<description/>
<distribute>Y</distribute>
<custom_distribution/>
<copies>1</copies>
<partitioning>
<method>none</method>
<schema_name/>
</partitioning>
<send_true_to>Calc seat &#x23;</send_true_to>
<send_false_to/>
<compare>
<condition>
<negated>N</negated>
<leftvalue>clone&#x3f;</leftvalue>
<function>&#x3d;</function>
<rightvalue/>
<value><name>constant</name><type>Boolean</type><text>Y</text><length>-1</length><precision>-1</precision><isnull>N</isnull><mask/></value> </condition>
</compare>
<cluster_schema/>
<remotesteps> <input> </input> <output> </output> </remotesteps> <GUI>
<xloc>260</xloc>
<yloc>32</yloc>
<draw>Y</draw>
</GUI>
</step>
<step_error_handling>
</step_error_handling>
<slave-step-copy-partition-distribution>
</slave-step-copy-partition-distribution>
<slave_transformation>N</slave_transformation>
</transformation>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment