llua_confluence_accesslog_star-dist Normal 0 / ID_BATCH Y ID_BATCH CHANNEL_ID Y CHANNEL_ID TRANSNAME Y TRANSNAME STATUS Y STATUS LINES_READ Y LINES_READ LINES_WRITTEN Y LINES_WRITTEN LINES_UPDATED Y LINES_UPDATED LINES_INPUT Y LINES_INPUT LINES_OUTPUT Y LINES_OUTPUT LINES_REJECTED Y LINES_REJECTED ERRORS Y ERRORS STARTDATE Y STARTDATE ENDDATE Y ENDDATE LOGDATE Y LOGDATE DEPDATE Y DEPDATE REPLAYDATE Y REPLAYDATE LOG_FIELD Y LOG_FIELD EXECUTING_SERVER N EXECUTING_SERVER EXECUTING_USER N EXECUTING_USER CLIENT N CLIENT
ID_BATCH Y ID_BATCH SEQ_NR Y SEQ_NR LOGDATE Y LOGDATE TRANSNAME Y TRANSNAME STEPNAME Y STEPNAME STEP_COPY Y STEP_COPY LINES_READ Y LINES_READ LINES_WRITTEN Y LINES_WRITTEN LINES_UPDATED Y LINES_UPDATED LINES_INPUT Y LINES_INPUT LINES_OUTPUT Y LINES_OUTPUT LINES_REJECTED Y LINES_REJECTED ERRORS Y ERRORS INPUT_BUFFER_ROWS Y INPUT_BUFFER_ROWS OUTPUT_BUFFER_ROWS Y OUTPUT_BUFFER_ROWS
ID_BATCH Y ID_BATCH CHANNEL_ID Y CHANNEL_ID LOG_DATE Y LOG_DATE LOGGING_OBJECT_TYPE Y LOGGING_OBJECT_TYPE OBJECT_NAME Y OBJECT_NAME OBJECT_COPY Y OBJECT_COPY REPOSITORY_DIRECTORY Y REPOSITORY_DIRECTORY FILENAME Y FILENAME OBJECT_ID Y OBJECT_ID OBJECT_REVISION Y OBJECT_REVISION PARENT_CHANNEL_ID Y PARENT_CHANNEL_ID ROOT_CHANNEL_ID Y ROOT_CHANNEL_ID
ID_BATCH Y ID_BATCH CHANNEL_ID Y CHANNEL_ID LOG_DATE Y LOG_DATE TRANSNAME Y TRANSNAME STEPNAME Y STEPNAME STEP_COPY Y STEP_COPY LINES_READ Y LINES_READ LINES_WRITTEN Y LINES_WRITTEN LINES_UPDATED Y LINES_UPDATED LINES_INPUT Y LINES_INPUT LINES_OUTPUT Y LINES_OUTPUT LINES_REJECTED Y LINES_REJECTED ERRORS Y ERRORS LOG_FIELD N LOG_FIELD
ID_BATCH Y ID_BATCH CHANNEL_ID Y CHANNEL_ID LOG_DATE Y LOG_DATE METRICS_DATE Y METRICS_DATE METRICS_CODE Y METRICS_CODE METRICS_DESCRIPTION Y METRICS_DESCRIPTION METRICS_SUBJECT Y METRICS_SUBJECT METRICS_TYPE Y METRICS_TYPE METRICS_VALUE Y METRICS_VALUE
0.0 0.0 500000 50 50 N Y 50000 Y N 1000 100 cluster N dynamic Y 1 ati-dev-ana01 ati-dev-ana01 9081 pentaho-di njain Encrypted 2be98afc86aa7f2e4bb18bd63c99dbdde Y N ATI-PRD-ANA03 ATI-PRD-ANA03 9080 pentaho-di admin Encrypted 2be98afc86aa7f2e4bb18bd63c99dbdde N N ATI-STG-ANA03 ATI-STG-ANA03 9080 pentaho-di pentaho Encrypted 2be98afc86aa7f2b4ae17ba71d69dff8b N N DI Server localhost 9080 pentaho-di joe Encrypted 2be98afc86aa7f2e4bb18bd63c99dbdde Y N DI Server 5.0 localhost 9080 pentaho-di admin Encrypted 2be98afc86aa7f2e4bb18bd63c99dbdde Y N local 127.0.0.1 9080 cluster Encrypted 2be98afc86aa7f2e4cb1aa265cd86aac8 Y N Master localhost 8081 cluster Encrypted 2be98afc86aa7f2e4cb1aa265cd86aac8 Y N remote 192.168.1.16 9080 pentaho-di/kettle admin Encrypted 2be98afc86aa7f2e4bb18bd63c99dbdde Y N Slave1 localhost 8082 cluster Encrypted 2be98afc86aa7f2e4cb1aa265cd86aac8 N N Slave2 localhost 8083 cluster Encrypted 2be98afc86aa7f2e4cb1aa265cd86aac8 N N Slave3 localhost 8084 cluster Encrypted 2be98afc86aa7f2e4cb1aa265cd86aac8 N N Slave4 localhost 8085 cluster Encrypted 2be98afc86aa7f2e4cb1aa265cd86aac8 N N Slave5 localhost 8086 cluster Encrypted 2be98afc86aa7f2e4cb1aa265cd86aac8 N N ClusterSchema 40000 2000 5000 Y N Slave3 Slave2 Slave1 Master ClusterSchema_dynamic 40000 2000 5000 Y Y Master - 2022/03/16 11:54:13.714 schmitz 2023/03/29 12:47:25.388 H4sIAAAAAAAAAAMAAAAAAAAAAAA= N Extract & Transform 16 16 131 26 .AppleSystemUIFont 13 N N 0 0 0 255 205 112 100 100 100 Y Load 112 1328 40 26 .AppleSystemUIFont 13 N N 0 0 0 255 205 112 100 100 100 Y Data Warehouse [ihre_domain/container_name] POSTGRESQL Native datawarehouse [host/container_port] datawarehouse Encrypted 64617461776170dbf0c0bd19c29686bb18bd63c99dbdde FORCE_IDENTIFIERS_TO_LOWERCASE N FORCE_IDENTIFIERS_TO_UPPERCASE N IS_CLUSTERED N PORT_NUMBER [host/container_port] PRESERVE_RESERVED_WORD_CASE Y QUOTE_ALL_FIELDS N SUPPORTS_BOOLEAN_DATA_TYPE N SUPPORTS_TIMESTAMP_DATA_TYPE N USE_POOLING N Confluence DB [ihre_domain/container_name] POSTGRESQL Native confluence [host/container_port] confluence Encrypted 636f6e64d2edcaa609c29686bb18bd63c99dbdde FORCE_IDENTIFIERS_TO_LOWERCASE N FORCE_IDENTIFIERS_TO_UPPERCASE N IS_CLUSTERED N PORT_NUMBER [host/container_port] PRESERVE_RESERVED_WORD_CASE Y QUOTE_ALL_FIELDS N SUPPORTS_BOOLEAN_DATA_TYPE Y SUPPORTS_TIMESTAMP_DATA_TYPE Y USE_POOLING N Table input - content Sort rows - contentid Y Sort rows - contentid Merge join CONTENT_ID - contentid Y Sort rows - CONTENT_ID Merge join CONTENT_ID - contentid Y Table input - usercontent_relation Sort rows - targetcontentid Y Sort rows - targetcontentid Merge join CONTENT_ID - targetcontentid Y Sort rows - CONTENT_ID 2 Merge join CONTENT_ID - targetcontentid Y Table input - user_mapping Stream lookup - USER Y Merge join CONTENT_ID - targetcontentid Stream lookup - USER Y Stream lookup - USER Stream lookup - creator Y Table input - user_mapping Stream lookup - creator Y Table input - user_mapping Stream lookup - lastmodifier Y Stream lookup - creator Stream lookup - lastmodifier Y Table input - user_mapping Stream lookup - username Y Stream lookup - lastmodifier Stream lookup - username Y Stream lookup - username Select values - only mandatory fields Y Select values - only mandatory fields Select values - meta data TIME to Date Y Select values - meta data TIME to Date Calculator - split date & time fields Y Calculator - split date & time fields Select values - remove TIME Y Select values - remove TIME Dummy - Maintable Y Dummy - Maintable Combination lookup/update - dim_user Y Combination lookup/update - dim_user Select values - rename id to user_id Y Combination lookup/update 2 - dim_date Select values 2 - rename id to date_id Y Select values - rename id to user_id Combination lookup/update 2 - dim_date Y Combination lookup/update - dim_time Select values - rename id to time_id Y Select values 2 - rename id to date_id Combination lookup/update - dim_time Y Combination lookup/update - dim_user_content_relation Select values - rename id to user_content_relation_id Y Select values - rename id to time_id Combination lookup/update - dim_user_content_relation Y Select values - rename id to user_content_relation_id Dimension lookup/update - dim_content Y Dimension lookup/update - dim_content Select values - remove and rename lookup fields Y Select values - remove and rename lookup fields Blocking step Y Blocking step Insert / update Y Dummy - Maintable Concat fields - date & time Y Concat fields - date & time Text file output - CSV for PM Y Merge join CONTENT_ID - contentid Sort rows - CONTENT_ID 2 Y Table input - acccesslog Filter rows - CONTENT_TYPE == ATTACHMENT Y Filter rows - CONTENT_TYPE == ATTACHMENT Regex evaluation - extract the CONTENT_ID (<pageid>|<contentid>|<action>) Y Regex evaluation - extract the CONTENT_ID (<pageid>|<contentid>|<action>) Select values: remove CONTENT_ID and result Y Select values: remove CONTENT_ID and result Select values: rename CONTENT_ID_EXTRACTED to CONTENT_ID; sort fields Y Filter rows - CONTENT_TYPE == ATTACHMENT Dummy (with correct CONTENT_ID) Y Dummy (with correct CONTENT_ID) Append streams Y Select values: rename CONTENT_ID_EXTRACTED to CONTENT_ID; sort fields Append streams Y Append streams Select values: cast CONTENT_ID from String to Integer(15) Y Select values: cast CONTENT_ID from String to Integer(15) Sort rows - CONTENT_ID Y Blocking step BlockingStep Y 1 none Y %%java.io.tmpdir%% block 5000 Y 688 2272 Y Calculator - split date & time fields Calculator Y 1 none Y year YEAR_OF_DATE TIME None -1 -1 N month MONTH_OF_DATE TIME None -1 -1 N day DAY_OF_MONTH TIME None -1 -1 N hour HOUR_OF_DAY TIME None -1 -1 N minute MINUTE_OF_HOUR TIME None -1 -1 N second SECOND_OF_MINUTE TIME None -1 -1 N 688 1408 Y Combination lookup/update - dim_time CombinationLookup Y 1 none llua_confluence_accesslog
dim_time
Data Warehouse 100 9999 Y N N hashcode hour hour minute minute second second id tablemax N 688 1984 Y Combination lookup/update - dim_user CombinationLookup Y 1 none llua_confluence_accesslog dim_user
Data Warehouse 100 9999 Y N N hashcode action_user_name username id tablemax N 688 1808 Y Combination lookup/update - dim_user_content_relation CombinationLookup Y 1 none llua_confluence_accesslog dim_user_content_relation
Data Warehouse 100 9999 Y N N hashcode relationname relation_name id tablemax N 688 2080 Y Combination lookup/update 2 - dim_date CombinationLookup Y 1 none llua_confluence_accesslog dim_date
Data Warehouse 100 9999 Y N N hashcode year year month month day day id tablemax N 688 1888 Y Concat fields - date & time ConcatFields Y 1 none - " N N
N
N
DOS None N Y N Y txt N N N N N N Y N N 0 year None none -1 -1 month None none -1 -1 day None none -1 -1 hour None none -1 -1 minute None none -1 -1 second None none -1 -1 action_date_time 255 N 528 1712 Y Dimension lookup/update - dim_content DimensionLookup Y 1 none llua_confluence_accesslog dim_content
Data Warehouse 100 Y CONTENT_ID content_id date_from date_to CONTENT_TYPE CONTENT_TYPE Update content_status content_status Update creationdate creationdate Update creator_name creator_name Update last_modifier_name last_modifier_name Insert lastmoddate lastmoddate Insert pageid pageid Insert prevver prevver Insert spaceid spaceid Insert userinfo_user_name userinfo_user_name Update title title Punch through id tablemax N version 1900 2199 5000 N N none N 688 2176 Y Dummy - Maintable Dummy N 1 none 688 1712 Y Insert / update InsertUpdate Y 1 none Data Warehouse 100 N llua_confluence_accesslog fact_action
accesslog_id id = user_content_relation_id user_content_relation_id Y action action Y date_id date_id Y time_id time_id Y user_id user_id Y content_id content_id Y id accesslog_id N 688 2368 Y Merge join CONTENT_ID - contentid MergeJoin Y 1 none LEFT OUTER Sort rows - CONTENT_ID Sort rows - contentid CONTENT_ID contentid 688 592 Y Merge join CONTENT_ID - targetcontentid MergeJoin Y 1 none LEFT OUTER Sort rows - CONTENT_ID 2 Sort rows - targetcontentid CONTENT_ID targetcontentid 688 784 Y Select values - meta data TIME to Date SelectValues N 1 none N TIME TIME Date -2 -2 false false 688 1312 Y Select values - only mandatory fields SelectValues Y 1 none ACTION CONTENT_ID CONTENT_TYPE TIME version creationdate lastmoddate prevver content_status pageid spaceid relationname action_user_name creator_name last_modifier_name userinfo_user_name ID accesslog_id title N 688 1232 Y Select values - remove TIME SelectValues Y 1 none N TIME 688 1488 Y Select values - remove and rename lookup fields SelectValues Y 1 none user_content_relation_id ACTION action date_id time_id user_id userinfo_user_name id content_id Y 1040 2176 Y Select values - rename id to time_id SelectValues Y 1 none id time_id Y 1040 1984 Y Select values - rename id to user_content_relation_id SelectValues Y 1 none id user_content_relation_id Y 1040 2080 Y Select values - rename id to user_id SelectValues Y 1 none id user_id Y 1040 1808 Y Select values 2 - rename id to date_id SelectValues Y 1 none id date_id Y 1040 1888 Y Sort rows - CONTENT_ID SortRows N 1 none %%java.io.tmpdir%% out 1000000 N N CONTENT_ID Y N N 0 N 688 496 Y Sort rows - CONTENT_ID 2 SortRows Y 1 none %%java.io.tmpdir%% out 1000000 N N CONTENT_ID Y N N 0 N 688 688 Y Sort rows - contentid SortRows N 1 none %%java.io.tmpdir%% out 1000000 N N contentid Y N N 0 N 368 592 Y Sort rows - targetcontentid SortRows Y 1 none %%java.io.tmpdir%% out 1000000 N N targetcontentid Y N N 0 N 368 784 Y Stream lookup - USER StreamLookup Y 1 none Table input - user_mapping N Y N N USER user_key username action_user_name None 688 896 Y Stream lookup - creator StreamLookup Y 1 none Table input - user_mapping N Y N N creator user_key username creator_name None 688 976 Y Stream lookup - lastmodifier StreamLookup Y 1 none Table input - user_mapping N Y N N lastmodifier user_key username last_modifier_name None 688 1056 Y Stream lookup - username StreamLookup Y 1 none Table input - user_mapping N Y N N username user_key username userinfo_user_name None 688 1136 Y Table input - acccesslog TableInput Y 1 none Confluence DB SELECT "ACTION" , "CONTENT_ID" , "CONTENT_TYPE" , "ID" , cast("TIME" as bigint) , "USER" FROM public.AO_CE3AF1_ACCESS_RECORD_ENTITY 0 N N N N String normal ACTION 255 -1 Table input - acccesslog ACTION . , none N Y 0 N N N en_US Europe/Berlin N String normal CONTENT_ID 32 -1 Table input - acccesslog CONTENT_ID . , none N Y 0 N N N en_US Europe/Berlin N String normal CONTENT_TYPE 255 -1 Table input - acccesslog CONTENT_TYPE . , none N Y 0 N N N en_US Europe/Berlin N Integer normal ID 9 0 Table input - acccesslog ID ####0;-####0 . , none N Y 0 N N N en_US Europe/Berlin N Integer normal TIME 15 0 Table input - acccesslog TIME ####0;-####0 . , none N Y 0 N N N en_US Europe/Berlin N String normal USER 32 -1 Table input - acccesslog USER . , none N Y 0 N N N en_US Europe/Berlin N 128 80 Y Table input - content TableInput Y 1 none Confluence DB SELECT contentid , hibernateversion , contenttype , title , version , creator , creationdate , lastmodifier , lastmoddate , prevver , content_status , pageid , spaceid , username FROM public.content 0 N N N N Integer normal contentid 15 0 Table input - content contentid ####0;-####0 . , none N Y 0 N N N en_US Europe/Berlin N Integer normal hibernateversion 9 0 Table input - content hibernateversion ####0;-####0 . , none N Y 0 N N N en_US Europe/Berlin N String normal contenttype 255 -1 Table input - content contenttype . , none N Y 0 N N N en_US Europe/Berlin N String normal title 255 -1 Table input - content title . , none N Y 0 N N N en_US Europe/Berlin N Integer normal version 9 0 Table input - content version ####0;-####0 . , none N Y 0 N N N en_US Europe/Berlin N String normal creator 255 -1 Table input - content creator . , none N Y 0 N N N en_US Europe/Berlin N Timestamp normal creationdate 6 -1 Table input - content creationdate . , none N Y 0 N N N en_US Europe/Berlin N String normal lastmodifier 255 -1 Table input - content lastmodifier . , none N Y 0 N N N en_US Europe/Berlin N Timestamp normal lastmoddate 6 -1 Table input - content lastmoddate . , none N Y 0 N N N en_US Europe/Berlin N Integer normal prevver 15 0 Table input - content prevver ####0;-####0 . , none N Y 0 N N N en_US Europe/Berlin N String normal content_status 255 -1 Table input - content content_status . , none N Y 0 N N N en_US Europe/Berlin N Integer normal pageid 15 0 Table input - content pageid ####0;-####0 . , none N Y 0 N N N en_US Europe/Berlin N Integer normal spaceid 15 0 Table input - content spaceid ####0;-####0 . , none N Y 0 N N N en_US Europe/Berlin N String normal username 255 -1 Table input - content username . , none N Y 0 N N N en_US Europe/Berlin N 144 592 Y Table input - usercontent_relation TableInput Y 1 none Confluence DB SELECT targetcontentid , relationname FROM public.usercontent_relation 0 N N N N Integer normal targetcontentid 15 0 Table input - usercontent_relation targetcontentid ####0;-####0 . , none N Y 0 N N N en_US Europe/Berlin N String normal relationname 255 -1 Table input - usercontent_relation relationname . , none N Y 0 N N N en_US Europe/Berlin N 144 784 Y Table input - user_mapping TableInput N 1 none Confluence DB SELECT user_key , username FROM public.user_mapping 0 N N N N String normal user_key 255 -1 Table input - user_mapping user_key . , none N Y 0 N N N en_US Europe/Berlin N String normal username 255 -1 Table input - user_mapping username . , none N Y 0 N N N en_US Europe/Berlin N 144 896 Y Text file output - CSV for PM TextFileOutput Y 1 none ; " N N
Y
N
UNIX None UTF-8 N Y ${DI_HOME}/csv/confluence_accesslog N Y csv N N N N N Y -yyyy-MM-dd-HH-mm-ss Y N N 336 1712 Y Filter rows - CONTENT_TYPE == ATTACHMENT FilterRows Y 1 none Regex evaluation - extract the CONTENT_ID (<pageid>|<contentid>|<action>) Dummy (with correct CONTENT_ID) N CONTENT_TYPE = constant String ATTACHMENT -1 -1 N 368 80 Y Regex evaluation - extract the CONTENT_ID (<pageid>|<contentid>|<action>) RegexEval N 1 none CONTENT_ID result N Y Y N N N N N N N CONTENT_ID_EXTRACTED String -1 -1 none 368 176 Y Select values: remove CONTENT_ID and result SelectValues Y 1 none N CONTENT_ID result 368 256 Y Select values: rename CONTENT_ID_EXTRACTED to CONTENT_ID; sort fields SelectValues Y 1 none ACTION CONTENT_ID_EXTRACTED CONTENT_ID CONTENT_TYPE ID TIME USER N 368 336 Y Dummy (with correct CONTENT_ID) Dummy N 1 none 688 80 Y Append streams Append Y 1 none Dummy (with correct CONTENT_ID) Select values: rename CONTENT_ID_EXTRACTED to CONTENT_ID; sort fields 688 336 Y Select values: cast CONTENT_ID from String to Integer(15) SelectValues Y 1 none N CONTENT_ID CONTENT_ID Integer 15 -2 false false 688 416 Y N