hudi spparksql 注意点

spark sql 加载hudi文件是 注意  加 /*

spark.read.laod(path:String) 不要用 spark.read.laod(path:_*)

sparksql源码

/**
 * Loads input in as a `DataFrame`, for data sources that require a path (e.g. data backed by
 * a local or distributed file system).
 *
 * @since 1.4.0
 */
def load(path: String): DataFrame = {
  option("path", path).load(Seq.empty: _*) // force invocation of `load(...varargs...)`
}

/**
 * Loads input in as a `DataFrame`, for data sources that support multiple paths.
 * Only works if the source is a HadoopFsRelationProvider.
 *
 * @since 1.6.0
 */
@scala.annotation.varargs
def load(paths: String*): DataFrame = {
  if (source.toLowerCase(Locale.ROOT) == DDLUtils.HIVE_PROVIDER) {
    throw new AnalysisException("Hive data source can only be used with tables, you can not " +
      "read files of Hive data source directly.")
  }
...........
}

hudi_spark_bundle datasource源码

override def createRelation(sqlContext: SQLContext,
                            optParams: Map[String, String],
                            schema: StructType): BaseRelation = {
  // Add default options for unspecified read options keys.
  val parameters = translateViewTypesToQueryTypes(optParams)

  val path = parameters.get("path")
  val readPathsStr = parameters.get(DataSourceReadOptions.READ_PATHS_OPT_KEY)
  if (path.isEmpty && readPathsStr.isEmpty) {
    throw new HoodieException(s"'path' or '$READ_PATHS_OPT_KEY' or both must be specified.")
  }

  val readPaths = readPathsStr.map(p => p.split(",").toSeq).getOrElse(Seq())
  ....
}