Skip to content

Instantly share code, notes, and snippets.

@mattyb149
Created February 4, 2015 22:46
Show Gist options
  • Save mattyb149/6b399c721a84a61f4d8b to your computer and use it in GitHub Desktop.
Save mattyb149/6b399c721a84a61f4d8b to your computer and use it in GitHub Desktop.
PDI transformation for use as an Apache Pig UDF
<?xml version="1.0" encoding="UTF-8"?>
<transformation>
<info>
<name>pdi-pig</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>
<slaveserver><name>di-server</name><hostname>localhost</hostname><port>9080</port><webAppName>pentaho-di</webAppName><username>admin</username><password>Encrypted 2be98afc86aa7f2e4bb18bd63c99dbdde</password><proxy_hostname/><proxy_port/><non_proxy_hosts/><master>Y</master></slaveserver>
<slaveserver><name>carte8082</name><hostname>127.0.0.1</hostname><port>8082</port><webAppName/><username>cluster</username><password>Encrypted 2be98afc86aa7f2e4cb1aa265cd86aac8</password><proxy_hostname/><proxy_port/><non_proxy_hosts/><master>N</master></slaveserver>
<slaveserver><name>carte8081</name><hostname>127.0.0.1</hostname><port>8081</port><webAppName/><username>cluster</username><password>Encrypted 2be98afc86aa7f2e4cb1aa265cd86aac8</password><proxy_hostname/><proxy_port/><non_proxy_hosts/><master>N</master></slaveserver>
<slaveserver><name>carte8083</name><hostname>127.0.0.1</hostname><port>8083</port><webAppName/><username>cluster</username><password>Encrypted 2be98afc86aa7f2e4cb1aa265cd86aac8</password><proxy_hostname/><proxy_port/><non_proxy_hosts/><master>N</master></slaveserver>
</slaveservers>
<clusterschemas>
</clusterschemas>
<created_user>-</created_user>
<created_date>2014&#x2f;12&#x2f;10 12&#x3a;52&#x3a;01.836</created_date>
<modified_user>-</modified_user>
<modified_date>2014&#x2f;12&#x2f;10 12&#x3a;52&#x3a;01.836</modified_date>
</info>
<notepads>
</notepads>
<order>
<hop> <from>INPUT</from><to>Uppercase First Name</to><enabled>Y</enabled> </hop>
<hop> <from>Uppercase First Name</from><to>First &#x2b; last &#x3d; fullname</to><enabled>Y</enabled> </hop>
<hop> <from>First &#x2b; last &#x3d; fullname</from><to>OUTPUT</to><enabled>Y</enabled> </hop>
<hop> <from>Text file input</from><to>Uppercase First Name</to><enabled>N</enabled> </hop>
</order>
<step>
<name>First &#x2b; last &#x3d; fullname</name>
<type>ConcatFields</type>
<description/>
<distribute>Y</distribute>
<custom_distribution/>
<copies>1</copies>
<partitioning>
<method>none</method>
<schema_name/>
</partitioning>
<separator> </separator>
<enclosure>&#x22;</enclosure>
<enclosure_forced>N</enclosure_forced>
<enclosure_fix_disabled>N</enclosure_fix_disabled>
<header>N</header>
<footer>N</footer>
<format>DOS</format>
<compression>None</compression>
<encoding/>
<endedLine/>
<fileNameInField>N</fileNameInField>
<fileNameField/>
<create_parent_folder>Y</create_parent_folder>
<file>
<name>file</name>
<is_command>N</is_command>
<servlet_output>N</servlet_output>
<do_not_open_new_file_init>Y</do_not_open_new_file_init>
<extention>txt</extention>
<append>N</append>
<split>N</split>
<haspartno>N</haspartno>
<add_date>N</add_date>
<add_time>N</add_time>
<SpecifyFormat>N</SpecifyFormat>
<date_time_format/>
<add_to_result_filenames>Y</add_to_result_filenames>
<pad>N</pad>
<fast_dump>N</fast_dump>
<splitevery>0</splitevery>
</file>
<fields>
<field>
<name>firstname</name>
<type>String</type>
<format/>
<currency/>
<decimal/>
<group/>
<nullif/>
<trim_type>none</trim_type>
<length>-1</length>
<precision>-1</precision>
</field>
<field>
<name>lastname</name>
<type>String</type>
<format/>
<currency/>
<decimal/>
<group/>
<nullif/>
<trim_type>none</trim_type>
<length>-1</length>
<precision>-1</precision>
</field>
</fields>
<ConcatFields>
<targetFieldName>fullname</targetFieldName>
<targetFieldLength>0</targetFieldLength>
<removeSelectedFields>Y</removeSelectedFields>
</ConcatFields>
<cluster_schema/>
<remotesteps> <input> </input> <output> </output> </remotesteps> <GUI>
<xloc>418</xloc>
<yloc>66</yloc>
<draw>Y</draw>
</GUI>
</step>
<step>
<name>INPUT</name>
<type>Injector</type>
<description/>
<distribute>Y</distribute>
<custom_distribution/>
<copies>1</copies>
<partitioning>
<method>none</method>
<schema_name/>
</partitioning>
<fields> <field> <name>lastname</name>
<type>String</type>
<length>-1</length>
<precision>-1</precision>
</field> <field> <name>firstname</name>
<type>String</type>
<length>-1</length>
<precision>-1</precision>
</field> </fields> <cluster_schema/>
<remotesteps> <input> </input> <output> </output> </remotesteps> <GUI>
<xloc>93</xloc>
<yloc>66</yloc>
<draw>Y</draw>
</GUI>
</step>
<step>
<name>OUTPUT</name>
<type>Dummy</type>
<description/>
<distribute>Y</distribute>
<custom_distribution/>
<copies>1</copies>
<partitioning>
<method>none</method>
<schema_name/>
</partitioning>
<cluster_schema/>
<remotesteps> <input> </input> <output> </output> </remotesteps> <GUI>
<xloc>555</xloc>
<yloc>66</yloc>
<draw>Y</draw>
</GUI>
</step>
<step>
<name>Text file input</name>
<type>TextFileInput</type>
<description/>
<distribute>Y</distribute>
<custom_distribution/>
<copies>1</copies>
<partitioning>
<method>none</method>
<schema_name/>
</partitioning>
<accept_filenames>N</accept_filenames>
<passing_through_fields>N</passing_through_fields>
<accept_field/>
<accept_stepname/>
<separator>&#x3b;</separator>
<enclosure>&#x22;</enclosure>
<enclosure_breaks>N</enclosure_breaks>
<escapechar/>
<header>Y</header>
<nr_headerlines>1</nr_headerlines>
<footer>N</footer>
<nr_footerlines>1</nr_footerlines>
<line_wrapped>N</line_wrapped>
<nr_wraps>1</nr_wraps>
<layout_paged>N</layout_paged>
<nr_lines_per_page>80</nr_lines_per_page>
<nr_lines_doc_header>0</nr_lines_doc_header>
<noempty>Y</noempty>
<include>N</include>
<include_field/>
<rownum>N</rownum>
<rownumByFile>N</rownumByFile>
<rownum_field/>
<format>Unix</format>
<encoding/>
<add_to_result_filenames>Y</add_to_result_filenames>
<file>
<name>&#x2f;Users&#x2f;mburgess&#x2f;customers-100.txt</name>
<filemask/>
<exclude_filemask/>
<file_required>N</file_required>
<include_subfolders>N</include_subfolders>
<type>CSV</type>
<compression>None</compression>
</file>
<filters>
</filters>
<fields>
<field>
<name>id</name>
<type>Integer</type>
<format> &#x23;</format>
<currency>&#x24;</currency>
<decimal>.</decimal>
<group>,</group>
<nullif>-</nullif>
<ifnull/>
<position>-1</position>
<length>15</length>
<precision>0</precision>
<trim_type>none</trim_type>
<repeat>N</repeat>
</field>
<field>
<name>lastname</name>
<type>String</type>
<format/>
<currency>&#x24;</currency>
<decimal>.</decimal>
<group>,</group>
<nullif>-</nullif>
<ifnull/>
<position>-1</position>
<length>10</length>
<precision>-1</precision>
<trim_type>none</trim_type>
<repeat>N</repeat>
</field>
<field>
<name>firstname</name>
<type>String</type>
<format/>
<currency>&#x24;</currency>
<decimal>.</decimal>
<group>,</group>
<nullif>-</nullif>
<ifnull/>
<position>-1</position>
<length>13</length>
<precision>-1</precision>
<trim_type>none</trim_type>
<repeat>N</repeat>
</field>
<field>
<name>zip</name>
<type>Integer</type>
<format> &#x23;</format>
<currency>&#x24;</currency>
<decimal>.</decimal>
<group>,</group>
<nullif>-</nullif>
<ifnull/>
<position>-1</position>
<length>15</length>
<precision>0</precision>
<trim_type>none</trim_type>
<repeat>N</repeat>
</field>
<field>
<name>city</name>
<type>String</type>
<format/>
<currency>&#x24;</currency>
<decimal>.</decimal>
<group>,</group>
<nullif>-</nullif>
<ifnull/>
<position>-1</position>
<length>8</length>
<precision>-1</precision>
<trim_type>none</trim_type>
<repeat>N</repeat>
</field>
<field>
<name>birthdate</name>
<type>Date</type>
<format>yyyy&#x2f;MM&#x2f;dd</format>
<currency>&#x24;</currency>
<decimal>.</decimal>
<group>,</group>
<nullif>-</nullif>
<ifnull/>
<position>-1</position>
<length>-1</length>
<precision>-1</precision>
<trim_type>none</trim_type>
<repeat>N</repeat>
</field>
<field>
<name>street</name>
<type>String</type>
<format/>
<currency>&#x24;</currency>
<decimal>.</decimal>
<group>,</group>
<nullif>-</nullif>
<ifnull/>
<position>-1</position>
<length>11</length>
<precision>-1</precision>
<trim_type>none</trim_type>
<repeat>N</repeat>
</field>
<field>
<name>housenr</name>
<type>Integer</type>
<format> &#x23;</format>
<currency>&#x24;</currency>
<decimal>.</decimal>
<group>,</group>
<nullif>-</nullif>
<ifnull/>
<position>-1</position>
<length>15</length>
<precision>0</precision>
<trim_type>none</trim_type>
<repeat>N</repeat>
</field>
<field>
<name>stateCode</name>
<type>String</type>
<format/>
<currency>&#x24;</currency>
<decimal>.</decimal>
<group>,</group>
<nullif>-</nullif>
<ifnull/>
<position>-1</position>
<length>9</length>
<precision>-1</precision>
<trim_type>none</trim_type>
<repeat>N</repeat>
</field>
<field>
<name>state</name>
<type>String</type>
<format/>
<currency>&#x24;</currency>
<decimal>.</decimal>
<group>,</group>
<nullif>-</nullif>
<ifnull/>
<position>-1</position>
<length>30</length>
<precision>-1</precision>
<trim_type>none</trim_type>
<repeat>N</repeat>
</field>
</fields>
<limit>0</limit>
<error_ignored>N</error_ignored>
<skip_bad_files>N</skip_bad_files>
<file_error_field/>
<file_error_message_field/>
<error_line_skipped>N</error_line_skipped>
<error_count_field/>
<error_fields_field/>
<error_text_field/>
<bad_line_files_destination_directory/>
<bad_line_files_extension>warning</bad_line_files_extension>
<error_line_files_destination_directory/>
<error_line_files_extension>error</error_line_files_extension>
<line_number_files_destination_directory/>
<line_number_files_extension>line</line_number_files_extension>
<date_format_lenient>Y</date_format_lenient>
<date_format_locale>en_US</date_format_locale>
<shortFileFieldName/>
<pathFieldName/>
<hiddenFieldName/>
<lastModificationTimeFieldName/>
<uriNameFieldName/>
<rootUriNameFieldName/>
<extensionFieldName/>
<sizeFieldName/>
<cluster_schema/>
<remotesteps> <input> </input> <output> </output> </remotesteps> <GUI>
<xloc>130</xloc>
<yloc>175</yloc>
<draw>Y</draw>
</GUI>
</step>
<step>
<name>Uppercase First Name</name>
<type>StringOperations</type>
<description/>
<distribute>Y</distribute>
<custom_distribution/>
<copies>1</copies>
<partitioning>
<method>none</method>
<schema_name/>
</partitioning>
<fields>
<field>
<in_stream_name>firstname</in_stream_name>
<out_stream_name/>
<trim_type>none</trim_type>
<lower_upper>upper</lower_upper>
<padding_type>none</padding_type>
<pad_char/>
<pad_len/>
<init_cap>no</init_cap>
<mask_xml>none</mask_xml>
<digits>none</digits>
<remove_special_characters>none</remove_special_characters>
</field>
<field>
<in_stream_name>lastname</in_stream_name>
<out_stream_name/>
<trim_type>none</trim_type>
<lower_upper>lower</lower_upper>
<padding_type>none</padding_type>
<pad_char/>
<pad_len/>
<init_cap>no</init_cap>
<mask_xml>none</mask_xml>
<digits>none</digits>
<remove_special_characters>none</remove_special_characters>
</field>
</fields>
<cluster_schema/>
<remotesteps> <input> </input> <output> </output> </remotesteps> <GUI>
<xloc>263</xloc>
<yloc>66</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