PDF文件,目前只支持半结构化数据之间的同步,其他的是不支持的,下面是oss同步到oss的例子:
注意:
1.将fileFormat参数配置成binary类型;
2.在Reader端配置"path": [ "" ]这个参数;
{
"type": "job",
"steps": [
{
"stepType": "oss",
"parameter": {
"fieldDelimiterOrigin": ",",
"nullFormat": "",
"compress": "",
"datasource": "lzz_oss",
"column": [
{
"name": 0,
"type": "string",
"index": 0
}
],
"skipHeader": "false",
"encoding": "UTF-8",
"fieldDelimiter": ",",
"fileFormat": "binary",
"object": [
"lzz05.pdf"
],
"path": [
"lzz05.pdf"
]
},
"name": "Reader",
"category": "reader"
},
{
"stepType": "oss",
"parameter": {
"fieldDelimiterOrigin": ",",
"nullFormat": "null",
"dateFormat": "yyyy-MM-dd HH:mm:ss",
"datasource": "lzz_oss",
"column": [
"0"
],
"writeMode": "truncate",
"encoding": "UTF-8",
"fieldDelimiter": ",",
"fileFormat": "binary",
"object": "lzz.docx"
},
"name": "Writer",
"category": "writer"
}
],
"version": "2.0",
"order": {
"hops": [
{
"from": "Reader",
"to": "Writer"
}
]
},
"setting": {
"errorLimit": {
"record": ""
},
"speed": {
"concurrent": 2,
"throttle": false,
"dmu": 1
}
}
}