From efad8d63bcd9aa77269eb3dd92c6cab769b107db Mon Sep 17 00:00:00 2001 From: zclllyybb Date: Wed, 13 May 2026 10:07:20 +0800 Subject: [PATCH] [fix](script) Replace clickbench new data link (#63187) because the old one is broken. --- tools/clickbench-tools/load-clickbench-data.sh | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/tools/clickbench-tools/load-clickbench-data.sh b/tools/clickbench-tools/load-clickbench-data.sh index 4f08671a812..87522dff0f3 100755 --- a/tools/clickbench-tools/load-clickbench-data.sh +++ b/tools/clickbench-tools/load-clickbench-data.sh @@ -126,9 +126,9 @@ function load() { need_download=false cd $DATA_DIR for i in $(seq 0 9); do - if [ ! -f "$DATA_DIR/hits_split${i}" ]; then - echo "will download hits_split${i} to $DATA_DIR" - wget --continue "https://doris-test-data.oss-cn-hongkong.aliyuncs.com/ClickBench/hits_split${i}" & + if [ ! -f "$DATA_DIR/hits_split${i}.tsv" ]; then + echo "will download hits_split${i}.tsv to $DATA_DIR" + wget --continue "https://bench-dataset.oss-cn-beijing.aliyuncs.com/clickhouse/hits_compatible/hits_split${i}.tsv" & PID=$! wget_pids[${#wget_pids[@]}]=$PID fi @@ -145,14 +145,14 @@ function load() { if [[ -z ${TXN_ID} ]]; then curl --location-trusted \ -u $USER:$PASSWORD \ - -T "$DATA_DIR/hits_split${i}" \ + -T "$DATA_DIR/hits_split${i}.tsv" \ -H "Expect: 100-continue" \ -H "columns: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,CLID" \ http://$FE_HOST:$FE_HTTP_PORT/api/$DB/hits/_stream_load else curl --location-trusted \ -u $USER:$PASSWORD \ - -T "$DATA_DIR/hits_split${i}" \ + -T "$DATA_DIR/hits_split${i}.tsv" \ -H "Expect: 100-continue" \ -H "label:${TXN_ID}_${i}" \ -H "columns: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,CLID" \