SuperX
/
sxc
7
0
Fork 0
Code Issues 6 Pull Requests Projects Releases Wiki Activity
Browse Source

importjob umgebaut fuer Rohdaten - etl metadata injection #53

sxc_0.3_Release
Imo John 7 months ago
parent
3cfff68e83
commit
61a9949c72
2 changed files with 697 additions and 4 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 693
      src-modules/module/sxc/etl/import_bestand/mwk_nrw_hochschulkennzahlen/feld_write.ktr
  2. 8
      src-modules/module/sxc/etl/import_bestand/mwk_nrw_hochschulkennzahlen/import_bestand_mwk_nrw_hskennz.kjb

693
src-modules/module/sxc/etl/import_bestand/mwk_nrw_hochschulkennzahlen/feld_write.ktr
Unescape View File

@ -0,0 +1,693 @@ @@ -0,0 +1,693 @@
<?xml version="1.0" encoding="UTF-8"?>
<transformation>
<info>
<name>feld_write</name>
<description/>
<extended_description/>
<trans_version/>
<trans_type>Normal</trans_type>
<trans_status>0</trans_status>
<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>2023&#x2f;03&#x2f;06 17&#x3a;37&#x3a;49.835</created_date>
<modified_user>-</modified_user>
<modified_date>2023&#x2f;03&#x2f;06 17&#x3a;37&#x3a;49.835</modified_date>
<key_for_session_key>H4sIAAAAAAAAAAMAAAAAAAAAAAA&#x3d;</key_for_session_key>
<is_key_private>N</is_key_private>
</info>
<notepads>
</notepads>
<order>
<hop>
<from>Split field to rows</from>
<to>tmp_feld</to>
<enabled>Y</enabled>
</hop>
<hop>
<from>Split field to rows</from>
<to>tmp_feld_all</to>
<enabled>Y</enabled>
</hop>
<hop>
<from>Text file input</from>
<to>Split field to rows</to>
<enabled>Y</enabled>
</hop>
</order>
<step>
<name>Split field to rows</name>
<type>SplitFieldToRows3</type>
<description/>
<distribute>N</distribute>
<custom_distribution/>
<copies>1</copies>
<partitioning>
<method>none</method>
<schema_name/>
</partitioning>
<splitfield>Field1</splitfield>
<delimiter>&#x3b;</delimiter>
<newfield>header_split</newfield>
<rownum>N</rownum>
<rownum_field/>
<resetrownumber>Y</resetrownumber>
<delimiter_is_regex>N</delimiter_is_regex>
<cluster_schema/>
<remotesteps>
<input>
</input>
<output>
</output>
</remotesteps>
<GUI>
<xloc>496</xloc>
<yloc>256</yloc>
<draw>Y</draw>
</GUI>
</step>
<step>
<name>Text file input</name>
<type>TextFileInput</type>
<description/>
<distribute>N</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>ajsiejthf</separator>
<enclosure>&#x22;</enclosure>
<enclosure_breaks>N</enclosure_breaks>
<escapechar/>
<header>N</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>ISO-8859-1</encoding>
<add_to_result_filenames>Y</add_to_result_filenames>
<file>
<name>&#x24;&#x7b;PATH_TO_UPLOADFILE&#x7d;</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>Field1</name>
<type>String</type>
<format/>
<currency/>
<decimal/>
<group/>
<nullif/>
<ifnull/>
<position>-1</position>
<length>2241</length>
<precision>-1</precision>
<trim_type>none</trim_type>
<repeat>N</repeat>
</field>
</fields>
<limit>1</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>de_DE</date_format_locale>
<shortFileFieldName>filename</shortFileFieldName>
<pathFieldName>filepath</pathFieldName>
<hiddenFieldName/>
<lastModificationTimeFieldName/>
<uriNameFieldName/>
<rootUriNameFieldName/>
<extensionFieldName/>
<sizeFieldName>size</sizeFieldName>
<cluster_schema/>
<remotesteps>
<input>
</input>
<output>
</output>
</remotesteps>
<GUI>
<xloc>320</xloc>
<yloc>176</yloc>
<draw>Y</draw>
</GUI>
</step>
<step>
<name>tmp_feld</name>
<type>TableOutput</type>
<description/>
<distribute>Y</distribute>
<custom_distribution/>
<copies>1</copies>
<partitioning>
<method>none</method>
<schema_name/>
</partitioning>
<connection>eduetl</connection>
<schema/>
<table>tmp_feld</table>
<commit>1000</commit>
<truncate>N</truncate>
<ignore_errors>N</ignore_errors>
<use_batch>Y</use_batch>
<specify_fields>Y</specify_fields>
<partitioning_enabled>N</partitioning_enabled>
<partitioning_field/>
<partitioning_daily>N</partitioning_daily>
<partitioning_monthly>Y</partitioning_monthly>
<tablename_in_field>N</tablename_in_field>
<tablename_field/>
<tablename_in_table>Y</tablename_in_table>
<return_keys>N</return_keys>
<return_field/>
<fields>
<field>
<column_name>Feld</column_name>
<stream_name>header_split</stream_name>
</field>
</fields>
<cluster_schema/>
<remotesteps>
<input>
</input>
<output>
</output>
</remotesteps>
<GUI>
<xloc>672</xloc>
<yloc>176</yloc>
<draw>Y</draw>
</GUI>
</step>
<step>
<name>tmp_feld_all</name>
<type>TableOutput</type>
<description/>
<distribute>Y</distribute>
<custom_distribution/>
<copies>1</copies>
<partitioning>
<method>none</method>
<schema_name/>
</partitioning>
<connection>eduetl</connection>
<schema/>
<table>tmp_feld_all</table>
<commit>1000</commit>
<truncate>N</truncate>
<ignore_errors>N</ignore_errors>
<use_batch>Y</use_batch>
<specify_fields>Y</specify_fields>
<partitioning_enabled>N</partitioning_enabled>
<partitioning_field/>
<partitioning_daily>N</partitioning_daily>
<partitioning_monthly>Y</partitioning_monthly>
<tablename_in_field>N</tablename_in_field>
<tablename_field/>
<tablename_in_table>Y</tablename_in_table>
<return_keys>N</return_keys>
<return_field/>
<fields>
<field>
<column_name>Feld</column_name>
<stream_name>header_split</stream_name>
</field>
</fields>
<cluster_schema/>
<remotesteps>
<input>
</input>
<output>
</output>
</remotesteps>
<GUI>
<xloc>672</xloc>
<yloc>320</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>

8
src-modules/module/sxc/etl/import_bestand/mwk_nrw_hochschulkennzahlen/import_bestand_mwk_nrw_hskennz.kjb
Unescape View File

@ -406,12 +406,12 @@ @@ -406,12 +406,12 @@
<yloc>272</yloc>
</entry>
<entry>
<name>tmp_feld_write</name>
<name>feld_write</name>
<description/>
<type>TRANS</type>
<specification_method>filename</specification_method>
<trans_object_id/>
<filename>&#x24;&#x7b;Internal.Job.Filename.Directory&#x7d;&#x2f;tmp_feld_write.ktr</filename>
<filename>&#x24;&#x7b;Internal.Job.Filename.Directory&#x7d;&#x2f;feld_write.ktr</filename>
<transname/>
<arg_from_previous>N</arg_from_previous>
<params_from_previous>N</params_from_previous>
@ -505,7 +505,7 @@ @@ -505,7 +505,7 @@
</hop>
<hop>
<from>create tmp_sxc_zahl_wert</from>
<to>tmp_feld_write</to>
<to>feld_write</to>
<from_nr>0</from_nr>
<to_nr>0</to_nr>
<enabled>Y</enabled>
@ -513,7 +513,7 @@ @@ -513,7 +513,7 @@
<unconditional>N</unconditional>
</hop>
<hop>
<from>tmp_feld_write</from>
<from>feld_write</from>
<to>delete from tmp_feld</to>
<from_nr>0</from_nr>
<to_nr>0</to_nr>

Write Preview
Loading…
Cancel
Save