0

我是 OrientDB 的新手,在将 .csv (MovieLens) 数据集导入 OrientDB 时遇到问题。
这是 .csv 文件的格式

movieId , title                             , genres
   1    , Toy Story (1995)                  , Adventure|Animation|Children|Comedy|Fantasy
   2    , Jumanji (1995)                    , Adventure|Children|Fantasy
   3    , Grumpier Old Men (1995)           , Comedy|Romance
   4    , Waiting to Exhale (1995)          , Comedy|Drama|Romance
   5    , Father of the Bride Part II (1995), Comedy
   6    , Heat (1995)                       , Action|Crime|Thriller

我在用“|”分割“流派”字段时遇到问题。我在 orientdb studio 中创建了 split 函数并在 JSON ETL 配置脚本中调用它,它仍然无法识别它并抛出异常。

OrientDB Studio 中的拆分函数

异常 JSON 脚本:

{
"config": {
"log": "info",
parallel: false
},
"source": { "file": { "path": "E:\Orient DB\OrientDB Project\Project DataSet MovieLens\ml-latest\movies.csv"} },
"extractor": { "row": {} },
"transformers": [
{ "csv": {"separator": ",",
"columnsOnFirstLine":true,
"columns":["id","title:string","genres"]}},
{ "field": { "fieldName": "genresArray", "expression": " split(genres,'|') "} },
{ "field": { "fieldName": "genresArray_0", "expression": "genresArray[0]"} },
{ "field": { "fieldName": "genresArray_1", "expression": "genresArray[1]"} },
{ "field": { "fieldName": "genresArray_2", "expression": "genresArray[2]"} },
{ "field": { "fieldName": "genresArray_3", "expression": "genresArray[3]"} },
{ "field": { "fieldName": "genresArray_4", "expression": "genresArray[4]"} },
{ "field": { "fieldName": "genresArray_5", "expression": "genresArray[5]"} },
{ "vertex": { "class": "Movies" } },
{ "edge": {
"class": "HasGenera",
"joinFieldName": "genresArray_0",
"lookup": "Genres.description",
"unresolvedLinkAction": "CREATE"
} },
{ "edge": {
"class": "HasGenera",
"joinFieldName": "genresArray_1",
"lookup": "Genres.description",
"unresolvedLinkAction": "CREATE"
} },
{ "edge": {
"class": "HasGenera",
"joinFieldName": "genresArray_2",
"lookup": "Genres.description",
"unresolvedLinkAction": "CREATE"
} },
{ "edge": {
"class": "HasGenera",
"joinFieldName": "genresArray_3",
"lookup": "Genres.description",
"unresolvedLinkAction": "CREATE"
} },
{ "edge": {
"class": "HasGenera",
"joinFieldName": "genresArray_4",
"lookup": "Genres.description",
"unresolvedLinkAction": "CREATE"
} },
{ "edge": {
"class": "HasGenera",
"joinFieldName": "genresArray_5",
"lookup": "Genres.description",
"unresolvedLinkAction": "CREATE"
} }
],
"loader": {
"orientdb": {
"dbURL": "remote:localhost/MovieRating",
"dbType": "graph",
"standardElementConstraints": false,
"classes": [
{"name": "Movies", "extends": "V"},
{"name": "Genres", "extends": "V"},
{"name": "HasGenera", "extends": "E"}
], "indexes": [
{"class":"Movies", "fields":["id:integer"], "type":"UNIQUE" },
{"class":"Genres", "fields":["description:string"], "type":"UNIQUE_HASH_INDEX" }
]
}
}
}
4

0 回答 0