[GitHub] [hudi] pengzhiwei2018 commented on a change in pull request #2283: [HUDI-1415] Read Hoodie Table As Spark DataSource Table

[GitBox <gi...@apache.org>]

pengzhiwei2018 commented on a change in pull request #2283:
URL: https://github.com/apache/hudi/pull/2283#discussion_r580215958



##########
File path: hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/hudi/HoodieSparkSqlWriter.scala
##########
@@ -377,11 +388,71 @@ private[hudi] object HoodieSparkSqlWriter {
     hiveSyncConfig.supportTimestamp = parameters.get(HIVE_SUPPORT_TIMESTAMP).exists(r => r.toBoolean)
     hiveSyncConfig.decodePartition = parameters.getOrElse(URL_ENCODE_PARTITIONING_OPT_KEY,
       DEFAULT_URL_ENCODE_PARTITIONING_OPT_VAL).toBoolean
+    hiveSyncConfig.tableProperties = parameters.getOrElse(HIVE_TABLE_PROPERTIES, null)
+    hiveSyncConfig.serdeProperties = createSqlTableSerdeProperties(parameters, basePath.toString,
+      hiveSyncConfig.partitionFields.size())
     hiveSyncConfig
   }
 
-  private def metaSync(parameters: Map[String, String],
-                       basePath: Path,
+  /**
+    * Add Spark Sql related table properties to the HIVE_TABLE_PROPERTIES.
+    * @param sqlConf
+    * @param schema
+    * @param parameters
+    * @return A new parameters added the HIVE_TABLE_PROPERTIES property.
+    */
+  private def addSqlTableProperties(sqlConf: SQLConf, schema: StructType,
+                                    parameters: Map[String, String]): Map[String, String] = {
+    val partitionSet = parameters(HIVE_PARTITION_FIELDS_OPT_KEY)
+      .split(",").map(_.trim).filter(!_.isEmpty).toSet
+    val threshold = sqlConf.getConf(SCHEMA_STRING_LENGTH_THRESHOLD)
+
+    val (partCols, dataCols) = schema.partition(c => partitionSet.contains(c.name))
+    val reOrdered = StructType(dataCols ++ partCols)
+    val parts = reOrdered.json.grouped(threshold).toSeq
+
+    var properties = Map(
+      "spark.sql.sources.provider" -> "hudi",
+      "spark.sql.sources.schema.numParts" -> parts.size.toString
+    )
+    parts.zipWithIndex.foreach { case (part, index) =>
+      properties += s"spark.sql.sources.schema.part.$index" -> part
+    }
+    // add partition columns
+    if (partitionSet.nonEmpty) {
+      properties += "spark.sql.sources.schema.numPartCols" -> partitionSet.size.toString
+      partitionSet.zipWithIndex.foreach { case (partCol, index) =>
+        properties += s"spark.sql.sources.schema.partCol.$index" -> partCol
+      }
+    }
+    var sqlPropertyText = ConfigUtils.configToString(properties)
+    sqlPropertyText = if (parameters.containsKey(HIVE_TABLE_PROPERTIES)) {
+      sqlPropertyText + "\n" + parameters(HIVE_TABLE_PROPERTIES)
+    } else {
+      sqlPropertyText
+    }
+    parameters + (HIVE_TABLE_PROPERTIES -> sqlPropertyText)
+  }
+
+  private def createSqlTableSerdeProperties(parameters: Map[String, String],
+                                            basePath: String, pathDepth: Int): String = {
+    assert(pathDepth >= 0, "Path Depth must great or equal to 0")
+    var pathProp = s"path=$basePath"
+    if (pathProp.endsWith("/")) {
+      pathProp = pathProp.substring(0, pathProp.length - 1)
+    }
+    for (_ <- 0 until pathDepth + 1) {
+      pathProp = s"$pathProp/*"

Review comment:
       Yes, we append the "star" to  the `pathProp` and generate the final pathProp value.




----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org