Nebula 版本号是2.5.0 Exchange 的版本号也是 2.5.0
创建过 schema
在使用nebula-exchange导数据时,一直报错
Exception in thread “main” com.vesoft.nebula.client.meta.exception.ExecuteFailedException: Execute failed: Get Space execute failed, errorCode: E_SPACE_NOT_FOUND
配置文件如下:
{
# Spark relation config
spark: {
app: {
name: Nebula Exchange 2.5.0
}
master:local
driver: {
cores: 1
maxResultSize: 1G
}
executor: {
memory:1G
}
cores:{
max: 16
}
}
nebula: {
address:{
graph:["192.168.220.xx:9669"]
meta:["192.169.220.xx:9559"]
}
user: root
pswd: root
space:basketballplayer
# nebula client connection parameters
connection {
# socket connect & execute timeout, unit: millisecond
timeout: 300000
}
error: {
# max number of failures, if the number of failures is bigger than max, then exit the application.
max: 32
# failed import job will be recorded in output path
output: /nebula-exchange/errors
}
# use google's RateLimiter to limit the requests send to NebulaGraph
rate: {
# the stable throughput of RateLimiter
limit: 1024
# Acquires a permit from RateLimiter, unit: MILLISECONDS
# if it can't be obtained within the specified timeout, then give up the request.
timeout: 1000
}
}
# Processing tags
# There are tag config examples for different dataSources.
tags: [
{
name: player
type: {
source: csv
sink: client
}
path: "file:/dataset/vertex_player.csv"
# if your csv file has no header, then use _c0,_c1,_c2,.. to indicate fields
fields: [_c1, _c2]
nebula.fields: [age, name]
vertex: {
field:_c0
}
separator: ","
header: false
batch: 256
partition: 32
}
{
name: team
type: {
source: csv
sink: client
}
path: "/dataset/vertex_team.csv"
fields: [_c1]
nebula.fields: [name]
vertex: {
field: _c0
#policy: hash
}
separator: ","
header: false
batch: 256
partition: 32
}
]
edges: [
{
name: follow
type: {
source: csv
sink: client
}
path: "/dataset/edge_follow.csv"
fields: [_c2]
nebula.fields: [degree]
source: {
field:_c0
#policy:hash
}
target: {
field:_c1
#policy:hash
}
separator: ","
header: false
batch: 256
partition: 32
}
{
name: server
type: {
source: csv
sink: client
}
path: "/dataset/edge_serve.csv"
fields: [_c2, _c3]
nebula.fields: [start_year, end_year]
source: {
field: _c0
#policy: hash
}
target: {
field: _c1
}
# 指定一个列作为rank的源(可选)
# ranking: csv-field-2
separator: ","
header: false
batch: 256
partition: 32
}
]
}