mirror of
https://github.com/ClickHouse/ClickHouse.git
synced 2024-12-01 03:52:15 +00:00
39 lines
2.6 KiB
YAML
39 lines
2.6 KiB
YAML
|
executionFrameworkSpec:
|
||
|
|
name: 'standalone'
|
||
|
|
segmentGenerationJobRunnerClassName: 'org.apache.pinot.plugin.ingestion.batch.standalone.SegmentGenerationJobRunner'
|
||
|
|
segmentTarPushJobRunnerClassName: 'org.apache.pinot.plugin.ingestion.batch.standalone.SegmentTarPushJobRunner'
|
||
|
|
segmentUriPushJobRunnerClassName: 'org.apache.pinot.plugin.ingestion.batch.standalone.SegmentUriPushJobRunner'
|
||
|
|
segmentMetadataPushJobRunnerClassName: 'org.apache.pinot.plugin.ingestion.batch.standalone.SegmentMetadataPushJobRunner'
|
||
|
|
jobType: SegmentCreationAndTarPush
|
||
|
|
inputDirURI: 'PWD_DIR_PLACEHOLDER'
|
||
|
|
includeFileNamePattern: 'glob:PWD_DIR_PLACEHOLDER/hits.tsv'
|
||
|
|
outputDirURI: 'batch/hits/segments'
|
||
|
|
overwriteOutput: true
|
||
|
|
segmentCreationJobParallelism: 10
|
||
|
|
pinotFSSpecs:
|
||
|
|
- scheme: file
|
||
|
|
className: org.apache.pinot.spi.filesystem.LocalPinotFS
|
||
|
|
recordReaderSpec:
|
||
|
|
dataFormat: 'csv'
|
||
|
|
className: 'org.apache.pinot.plugin.inputformat.csv.CSVRecordReader'
|
||
|
|
configClassName: 'org.apache.pinot.plugin.inputformat.csv.CSVRecordReaderConfig'
|
||
|
|
configs:
|
||
|
|
fileFormat: 'default'
|
||
|
|
delimiter: ' '
|
||
|
|
multiValueDelimiter: ''
|
||
|
|
header: 'WatchID JavaEnable Title GoodEvent EventTime EventDate CounterID ClientIP RegionID UserID CounterClass OS UserAgent URL Referer IsRefresh RefererCategoryID RefererRegionID URLCategoryID URLRegionID ResolutionWidth ResolutionHeight ResolutionDepth FlashMajor FlashMinor FlashMinor2 NetMajor NetMinor UserAgentMajor UserAgentMinor CookieEnable JavascriptEnable IsMobile MobilePhone MobilePhoneModel Params IPNetworkID TraficSourceID SearchEngineID SearchPhrase AdvEngineID IsArtifical WindowClientWidth WindowClientHeight ClientTimeZone ClientEventTime SilverlightVersion1 SilverlightVersion2 SilverlightVersion3 SilverlightVersion4 PageCharset CodeVersion IsLink IsDownload IsNotBounce FUniqID OriginalURL HID IsOldCounter IsEvent IsParameter DontCountHits WithHash HitColor LocalEventTime Age Sex Income Interests Robotness RemoteIP WindowName OpenerName HistoryLength BrowserLanguage BrowserCountry SocialNetwork SocialAction HTTPError SendTiming DNSTiming ConnectTiming ResponseStartTiming ResponseEndTiming FetchTiming SocialSourceNetworkID SocialSourcePage ParamPrice ParamOrderID ParamCurrency ParamCurrencyID OpenstatServiceName OpenstatCampaignID OpenstatAdID OpenstatSourceID UTMSource UTMMedium UTMCampaign UTMContent UTMTerm FromTag HasGCLID RefererHash URLHash'
|
||
|
|
|
||
|
|
|
||
|
|
tableSpec:
|
||
|
|
tableName: 'hits'
|
||
|
|
schemaURI: 'http://localhost:9000/tables/hits/schema'
|
||
|
|
tableConfigURI: 'http://localhost:9000/tables/hits'
|
||
|
|
|
||
|
|
pinotClusterSpecs:
|
||
|
|
- controllerURI: 'http://localhost:9000'
|
||
|
|
|
||
|
|
pushJobSpec:
|
||
|
|
pushAttempts: 10
|
||
|
|
pushRetryIntervalMillis: 1000
|
||
|
|
segmentUriPrefix: 'file://'
|