- Metadata file
not recommended for production use as lead to small file problems
update provided through metadata files are queued before merged
- Metadata API
use either metadata file or API, not both
API overwrites metadata, and take effects immediately
[donghua@cdh-vm data]$ hdfs dfs -ls /data/donghua/*drink*
-rw-r--r-- 1 donghua hive 145 2018-06-03 11:27 /data/donghua/.drinks.csv.navigator
-rw-r--r-- 1 donghua hive 5918 2018-06-03 00:07 /data/donghua/drinks.csv
[donghua@cdh-vm data]$ hdfs dfs -cat /data/donghua/.drinks.csv.navigator
{
"name":"drinks dataset"
"description": "metadata example using .drinks.csv.navigator"
"properties":{
"Dept":"myDept"
},
"tags":["external"]
}
curl -u admin:admin -X GET 'http://cdh01:7187/api/v13/entities/?query=originalName:imdb_1000.csv&limit=100&offset=0'
[donghua@cdh-vm data]$ curl -u admin:admin -X GET 'http://cdh-vm:7187/api/v13/entities/?query=originalName%3D%22imdb_1000.csv%22&limit=100&offset=0'
[ {
"originalName" : "imdb_1000.csv",
"originalDescription" : null,
"sourceId" : "5",
"firstClassParentId" : null,
"parentPath" : "/data/donghua",
"deleteTime" : 0,
"extractorRunId" : "5##20",
"customProperties" : null,
"name" : null,
"description" : null,
"tags" : null,
"properties" : {
"__cloudera_internal__hueLink" : "http://cdh-vm:8889/filebrowser/#/data/donghua/imdb_1000.csv"
},
"technicalProperties" : null,
"fileSystemPath" : "/data/donghua/imdb_1000.csv",
"type" : "FILE",
"size" : 91499,
"created" : "2018-06-03T00:07:55.434Z",
"lastModified" : "2018-06-03T00:07:55.434Z",
"lastAccessed" : "2018-06-03T00:07:54.880Z",
"permissions" : "rw-r--r--",
"owner" : "donghua",
"group" : "hive",
"blockSize" : 134217728,
"mimeType" : "application/octet-stream",
"ezkeyName" : null,
"replication" : 1,
"metaClassName" : "fselement",
"deleted" : false,
"packageName" : "nav",
"userEntity" : false,
"sourceType" : "HDFS",
"identity" : "20388",
"internalType" : "fselement"
}, {
"originalName" : "imdb_1000.csv",
"originalDescription" : null,
"sourceId" : "5",
"firstClassParentId" : null,
"parentPath" : "/user/hive/warehouse/testdb.db/imdb_1000",
"deleteTime" : 0,
"extractorRunId" : "5##22",
"customProperties" : null,
"name" : null,
"description" : null,
"tags" : null,
"properties" : {
"__cloudera_internal__hueLink" : "http://cdh-vm:8889/filebrowser/#/user/hive/warehouse/testdb.db/imdb_1000/imdb_1000.csv"
},
"technicalProperties" : null,
"fileSystemPath" : "/user/hive/warehouse/testdb.db/imdb_1000/imdb_1000.csv",
"type" : "FILE",
"size" : 91499,
"created" : "2018-06-03T01:06:12.920Z",
"lastModified" : "2018-06-03T01:06:12.920Z",
"lastAccessed" : "2018-06-03T01:06:12.920Z",
"permissions" : "rw-r--r--",
"owner" : "hive",
"group" : "hive",
"blockSize" : 134217728,
"mimeType" : "application/octet-stream",
"ezkeyName" : null,
"replication" : 1,
"metaClassName" : "fselement",
"deleted" : false,
"packageName" : "nav",
"userEntity" : false,
"sourceType" : "HDFS",
"identity" : "22303",
"internalType" : "fselement"
}, {
"originalName" : "imdb_1000.csv._COPYING_",
"originalDescription" : null,
"sourceId" : "5",
"firstClassParentId" : null,
"parentPath" : "/data/donghua",
"deleteTime" : 1527984475434,
"extractorRunId" : "5##20",
"customProperties" : null,
"name" : null,
"description" : null,
"tags" : null,
"properties" : null,
"technicalProperties" : null,
"fileSystemPath" : "/data/donghua/imdb_1000.csv._COPYING_",
"type" : "FILE",
"size" : 91499,
"created" : "2018-06-03T00:07:54.880Z",
"lastModified" : "2018-06-03T00:07:54.880Z",
"lastAccessed" : "2018-06-03T00:07:54.880Z",
"permissions" : "rw-r--r--",
"owner" : "donghua",
"group" : "hive",
"blockSize" : 134217728,
"mimeType" : "application/octet-stream",
"ezkeyName" : null,
"replication" : 1,
"metaClassName" : "fselement",
"deleted" : true,
"packageName" : "nav",
"userEntity" : false,
"sourceType" : "HDFS",
"identity" : "20386",
"internalType" : "fselement"
} ]
curl -u admin:admin -X POST 'http://cdh-vm:7187/api/v13/entities/?query=originalName%3D%22imdb_1000.csv%22&limit=100&offset=0' \
-H "Content-Type:application/json" -d \
'{
"sourceId":"5",
"originalName" : "imdb_1000.csv",
"parentPath" : "/data/donghua",
"name":"imdb dataset",
"description": "metadata example using API",
"properties":{
"Dept":"myDept"
},
"tags":["external"]
}'
[donghua@cdh-vm data]$ curl -u admin:admin -X POST 'http://cdh-vm:7187/api/v13/entities/?query=originalName%3D%22imdb_1000.csv%22&limit=100&offset=0' \
> -H "Content-Type:application/json" -d \
> '{
> "sourceId":"5",
> "originalName" : "imdb_1000.csv",
> "parentPath" : "/data/donghua",
> "name":"imdb dataset",
> "description": "metadata example using API",
> "properties":{
> "Dept":"myDept"
> },
> "tags":["external"]
> }'
{
"originalName" : "imdb_1000.csv",
"originalDescription" : null,
"sourceId" : "5",
"firstClassParentId" : null,
"parentPath" : "/data/donghua",
"deleteTime" : 0,
"extractorRunId" : "5##20",
"customProperties" : null,
"name" : "imdb dataset",
"description" : "metadata example using API",
"tags" : [ "external" ],
"properties" : {
"Dept" : "myDept",
"__cloudera_internal__hueLink" : "http://cdh-vm:8889/filebrowser/#/data/donghua/imdb_1000.csv"
},
"technicalProperties" : null,
"fileSystemPath" : "/data/donghua/imdb_1000.csv",
"type" : "FILE",
"size" : 91499,
"created" : "2018-06-03T00:07:55.434Z",
"lastModified" : "2018-06-03T00:07:55.434Z",
"lastAccessed" : "2018-06-03T00:07:54.880Z",
"permissions" : "rw-r--r--",
"owner" : "donghua",
"group" : "hive",
"blockSize" : 134217728,
"mimeType" : "application/octet-stream",
"ezkeyName" : null,
"replication" : 1,
"metaClassName" : "fselement",
"deleted" : false,
"packageName" : "nav",
"userEntity" : false,
"sourceType" : "HDFS",
"identity" : "20388",
"internalType" : "fselement"
}
No comments:
Post a Comment