Created
January 31, 2015 17:22
-
-
Save rishuatgithub/96481b4ba84288703f41 to your computer and use it in GitHub Desktop.
ktr file to read zip files using Text File input step in Pentaho Kettle
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
<?xml version="1.0" encoding="UTF-8"?> | |
<transformation> | |
<info> | |
<name>T_ReadZipFile</name> | |
<description>Reading Zip File using Text File Input Step in Pentaho Kettle | Rishu Shrivastava | rishuatgithub</description> | |
<extended_description/> | |
<trans_version>1</trans_version> | |
<trans_type>Normal</trans_type> | |
<trans_status>1</trans_status> | |
<directory>/</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>2015/01/31 21:14:07.474</created_date> | |
<modified_user>-</modified_user> | |
<modified_date>2015/01/31 21:14:07.474</modified_date> | |
</info> | |
<notepads> | |
<notepad> | |
<note>-------------------------------------Reading ZIP File--------------------------------------
File Name: /testdata.zip

step configurations if you have used zipped the file in Windows.
</note> | |
<xloc>27</xloc> | |
<yloc>27</yloc> | |
<width>406</width> | |
<heigth>87</heigth> | |
<fontname>Arial</fontname> | |
<fontsize>10</fontsize> | |
<fontbold>N</fontbold> | |
<fontitalic>N</fontitalic> | |
<fontcolorred>0</fontcolorred> | |
<fontcolorgreen>0</fontcolorgreen> | |
<fontcolorblue>0</fontcolorblue> | |
<backgroundcolorred>255</backgroundcolorred> | |
<backgroundcolorgreen>205</backgroundcolorgreen> | |
<backgroundcolorblue>112</backgroundcolorblue> | |
<bordercolorred>100</bordercolorred> | |
<bordercolorgreen>100</bordercolorgreen> | |
<bordercolorblue>100</bordercolorblue> | |
<drawshadow>Y</drawshadow> | |
</notepad> | |
<notepad> | |
<note>-----------------------------------Reading GZIP file-------------------------------------
File Name: /tar.tar.gz

Step conf. if you have tarred and gz the file in UNIX.

>> Without the wildcard expression</note> | |
<xloc>545</xloc> | |
<yloc>30</yloc> | |
<width>399</width> | |
<heigth>102</heigth> | |
<fontname>Arial</fontname> | |
<fontsize>10</fontsize> | |
<fontbold>N</fontbold> | |
<fontitalic>N</fontitalic> | |
<fontcolorred>0</fontcolorred> | |
<fontcolorgreen>0</fontcolorgreen> | |
<fontcolorblue>0</fontcolorblue> | |
<backgroundcolorred>255</backgroundcolorred> | |
<backgroundcolorgreen>205</backgroundcolorgreen> | |
<backgroundcolorblue>112</backgroundcolorblue> | |
<bordercolorred>100</bordercolorred> | |
<bordercolorgreen>100</bordercolorgreen> | |
<bordercolorblue>100</bordercolorblue> | |
<drawshadow>Y</drawshadow> | |
</notepad> | |
<notepad> | |
<note>Reading GZIP Files - with wildcard entry</note> | |
<xloc>571</xloc> | |
<yloc>255</yloc> | |
<width>241</width> | |
<heigth>25</heigth> | |
<fontname>Arial</fontname> | |
<fontsize>10</fontsize> | |
<fontbold>N</fontbold> | |
<fontitalic>N</fontitalic> | |
<fontcolorred>0</fontcolorred> | |
<fontcolorgreen>0</fontcolorgreen> | |
<fontcolorblue>0</fontcolorblue> | |
<backgroundcolorred>255</backgroundcolorred> | |
<backgroundcolorgreen>205</backgroundcolorgreen> | |
<backgroundcolorblue>112</backgroundcolorblue> | |
<bordercolorred>100</bordercolorred> | |
<bordercolorgreen>100</bordercolorgreen> | |
<bordercolorblue>100</bordercolorblue> | |
<drawshadow>Y</drawshadow> | |
</notepad> | |
<notepad> | |
<note>All the input files contain a csv file with:

Two Headers : header1 and header2
values: a , b</note> | |
<xloc>76</xloc> | |
<yloc>347</yloc> | |
<width>237</width> | |
<heigth>71</heigth> | |
<fontname>Arial</fontname> | |
<fontsize>10</fontsize> | |
<fontbold>N</fontbold> | |
<fontitalic>N</fontitalic> | |
<fontcolorred>0</fontcolorred> | |
<fontcolorgreen>0</fontcolorgreen> | |
<fontcolorblue>0</fontcolorblue> | |
<backgroundcolorred>192</backgroundcolorred> | |
<backgroundcolorgreen>192</backgroundcolorgreen> | |
<backgroundcolorblue>192</backgroundcolorblue> | |
<bordercolorred>192</bordercolorred> | |
<bordercolorgreen>192</bordercolorgreen> | |
<bordercolorblue>192</bordercolorblue> | |
<drawshadow>N</drawshadow> | |
</notepad> | |
</notepads> | |
<connection> | |
<name>AgileBI</name> | |
<server>localhost</server> | |
<type>MONETDB</type> | |
<access>Native</access> | |
<database>pentaho-instaview</database> | |
<port>50006</port> | |
<username>monetdb</username> | |
<password>Encrypted 2be98afc86aa7f2e4cb14a17edb86abd8</password> | |
<servername/> | |
<data_tablespace/> | |
<index_tablespace/> | |
<read_only>true</read_only> | |
<attributes> | |
<attribute><code>EXTRA_OPTION_INFOBRIGHT.characterEncoding</code><attribute>UTF-8</attribute></attribute> | |
<attribute><code>EXTRA_OPTION_MYSQL.defaultFetchSize</code><attribute>500</attribute></attribute> | |
<attribute><code>EXTRA_OPTION_MYSQL.useCursorFetch</code><attribute>true</attribute></attribute> | |
<attribute><code>PORT_NUMBER</code><attribute>50006</attribute></attribute> | |
<attribute><code>SUPPORTS_BOOLEAN_DATA_TYPE</code><attribute>Y</attribute></attribute> | |
<attribute><code>SUPPORTS_TIMESTAMP_DATA_TYPE</code><attribute>Y</attribute></attribute> | |
</attributes> | |
</connection> | |
<connection> | |
<name>HypersonicDB</name> | |
<server>localhost</server> | |
<type>HYPERSONIC</type> | |
<access>Native</access> | |
<database>SampleData</database> | |
<port>50006</port> | |
<username/> | |
<password>Encrypted </password> | |
<servername/> | |
<data_tablespace/> | |
<index_tablespace/> | |
<attributes> | |
<attribute><code>FORCE_IDENTIFIERS_TO_LOWERCASE</code><attribute>N</attribute></attribute> | |
<attribute><code>FORCE_IDENTIFIERS_TO_UPPERCASE</code><attribute>N</attribute></attribute> | |
<attribute><code>IS_CLUSTERED</code><attribute>N</attribute></attribute> | |
<attribute><code>PORT_NUMBER</code><attribute>50006</attribute></attribute> | |
<attribute><code>PRESERVE_RESERVED_WORD_CASE</code><attribute>N</attribute></attribute> | |
<attribute><code>QUOTE_ALL_FIELDS</code><attribute>N</attribute></attribute> | |
<attribute><code>SUPPORTS_BOOLEAN_DATA_TYPE</code><attribute>N</attribute></attribute> | |
<attribute><code>SUPPORTS_TIMESTAMP_DATA_TYPE</code><attribute>N</attribute></attribute> | |
<attribute><code>USE_POOLING</code><attribute>N</attribute></attribute> | |
</attributes> | |
</connection> | |
<connection> | |
<name>PostgreSql</name> | |
<server>localhost</server> | |
<type>POSTGRESQL</type> | |
<access>Native</access> | |
<database>postgres</database> | |
<port>5433</port> | |
<username>postgres</username> | |
<password>Encrypted 2be98afc86aa7f2e4bb16bd64d980aac9</password> | |
<servername/> | |
<data_tablespace/> | |
<index_tablespace/> | |
<attributes> | |
<attribute><code>FORCE_IDENTIFIERS_TO_LOWERCASE</code><attribute>N</attribute></attribute> | |
<attribute><code>FORCE_IDENTIFIERS_TO_UPPERCASE</code><attribute>N</attribute></attribute> | |
<attribute><code>IS_CLUSTERED</code><attribute>N</attribute></attribute> | |
<attribute><code>PORT_NUMBER</code><attribute>5433</attribute></attribute> | |
<attribute><code>QUOTE_ALL_FIELDS</code><attribute>N</attribute></attribute> | |
<attribute><code>SUPPORTS_BOOLEAN_DATA_TYPE</code><attribute>N</attribute></attribute> | |
<attribute><code>USE_POOLING</code><attribute>N</attribute></attribute> | |
</attributes> | |
</connection> | |
<order> | |
</order> | |
<step> | |
<name>Read ZIP File</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>,</separator> | |
<enclosure>"</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>DOS</format> | |
<encoding>UTF-8</encoding> | |
<add_to_result_filenames>Y</add_to_result_filenames> | |
<file> | |
<name>${Internal.Transformation.Filename.Directory}/testdata.zip</name> | |
<filemask/> | |
<exclude_filemask/> | |
<file_required>N</file_required> | |
<include_subfolders>Y</include_subfolders> | |
<type>CSV</type> | |
<compression>Zip</compression> | |
</file> | |
<filters> | |
</filters> | |
<fields> | |
<field> | |
<name>header1</name> | |
<type>String</type> | |
<format/> | |
<currency>Rs.</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>header2</name> | |
<type>String</type> | |
<format/> | |
<currency>Rs.</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> | |
</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_IN</date_format_locale> | |
<shortFileFieldName/> | |
<pathFieldName/> | |
<hiddenFieldName/> | |
<lastModificationTimeFieldName/> | |
<uriNameFieldName/> | |
<rootUriNameFieldName/> | |
<extensionFieldName/> | |
<sizeFieldName/> | |
<cluster_schema/> | |
<remotesteps> <input> </input> <output> </output> </remotesteps> <GUI> | |
<xloc>208</xloc> | |
<yloc>138</yloc> | |
<draw>Y</draw> | |
</GUI> | |
</step> | |
<step> | |
<name>Read GZIP File - Without wildcard entry</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>,</separator> | |
<enclosure>"</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>mixed</format> | |
<encoding/> | |
<add_to_result_filenames>Y</add_to_result_filenames> | |
<file> | |
<name>${Internal.Transformation.Filename.Directory}/tar.tar.gz</name> | |
<filemask/> | |
<exclude_filemask/> | |
<file_required>Y</file_required> | |
<include_subfolders>Y</include_subfolders> | |
<type>CSV</type> | |
<compression>GZip</compression> | |
</file> | |
<filters> | |
</filters> | |
<fields> | |
<field> | |
<name>header1</name> | |
<type>String</type> | |
<format/> | |
<currency>Rs.</currency> | |
<decimal>.</decimal> | |
<group>,</group> | |
<nullif>-</nullif> | |
<ifnull/> | |
<position>-1</position> | |
<length>1</length> | |
<precision>-1</precision> | |
<trim_type>both</trim_type> | |
<repeat>N</repeat> | |
</field> | |
<field> | |
<name>header2</name> | |
<type>String</type> | |
<format/> | |
<currency>Rs.</currency> | |
<decimal>.</decimal> | |
<group>,</group> | |
<nullif>-</nullif> | |
<ifnull/> | |
<position>-1</position> | |
<length>1</length> | |
<precision>-1</precision> | |
<trim_type>both</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_IN</date_format_locale> | |
<shortFileFieldName/> | |
<pathFieldName/> | |
<hiddenFieldName/> | |
<lastModificationTimeFieldName/> | |
<uriNameFieldName/> | |
<rootUriNameFieldName/> | |
<extensionFieldName/> | |
<sizeFieldName/> | |
<cluster_schema/> | |
<remotesteps> <input> </input> <output> </output> </remotesteps> <GUI> | |
<xloc>686</xloc> | |
<yloc>161</yloc> | |
<draw>Y</draw> | |
</GUI> | |
</step> | |
<step> | |
<name>Read GZIP File - With wildcard entry >> Throws Error</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>,</separator> | |
<enclosure>"</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>N</noempty> | |
<include>N</include> | |
<include_field/> | |
<rownum>N</rownum> | |
<rownumByFile>N</rownumByFile> | |
<rownum_field/> | |
<format>mixed</format> | |
<encoding/> | |
<add_to_result_filenames>Y</add_to_result_filenames> | |
<file> | |
<name>${Internal.Transformation.Filename.Directory}/tar.tar.gz</name> | |
<filemask>.*\.csv</filemask> | |
<exclude_filemask/> | |
<file_required>N</file_required> | |
<include_subfolders>Y</include_subfolders> | |
<type>CSV</type> | |
<compression>GZip</compression> | |
</file> | |
<filters> | |
</filters> | |
<fields> | |
<field> | |
<name>header2</name> | |
<type>String</type> | |
<format/> | |
<currency>Rs.</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>tar/������������������������������������������������������������������������������������������������0000775�0001750�0001750�00000000000�12463175363�010726�_5����������������������������������������������������������������������������������������������������ustar__�rishu���������������������������rishu������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������tar/test.csv����������������������������������������������������������������������������������������0000664�0001750�0001750�00000000026�12463174453�012417�_0����������������������������������������������������������������������������������������������������ustar__�rishu���������������������������rishu������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������header1</name> | |
<type>String</type> | |
<format/> | |
<currency>Rs.</currency> | |
<decimal>.</decimal> | |
<group>,</group> | |
<nullif>-</nullif> | |
<ifnull/> | |
<position>-1</position> | |
<length>9194</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_IN</date_format_locale> | |
<shortFileFieldName/> | |
<pathFieldName/> | |
<hiddenFieldName/> | |
<lastModificationTimeFieldName/> | |
<uriNameFieldName/> | |
<rootUriNameFieldName/> | |
<extensionFieldName/> | |
<sizeFieldName/> | |
<cluster_schema/> | |
<remotesteps> <input> </input> <output> </output> </remotesteps> <GUI> | |
<xloc>694</xloc> | |
<yloc>316</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> | |
<attributes><group><name>DataService</name> | |
<attribute><key>name</key> | |
<value/> | |
</attribute><attribute><key>stepname</key> | |
<value/> | |
</attribute></group></attributes> | |
</transformation> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment