nsivabalan commented on a change in pull request #2651:
URL: https://github.com/apache/hudi/pull/2651#discussion_r590522313
##########
File path:
hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/hudi/DefaultSource.scala
##########
@@ -66,10 +69,15 @@ class DefaultSource extends RelationProvider
override def createRelation(sqlContext: SQLContext,
optParams: Map[String, String],
schema: StructType): BaseRelation = {
+ val path = removeStar(optParams.get("path"))
Review comment:
minor. can we add a comment here as to what this does. something like
```Translates path from "/basepath/*/*/*/*" or "/basepath/*/*" to
"/basepath/" if applicable```
##########
File path:
hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/hudi/DefaultSource.scala
##########
@@ -79,40 +87,64 @@ class DefaultSource extends RelationProvider
val allPaths = path.map(p => Seq(p)).getOrElse(Seq()) ++ readPaths
val fs = FSUtils.getFs(allPaths.head,
sqlContext.sparkContext.hadoopConfiguration)
- val globPaths = HoodieSparkUtils.checkAndGlobPathIfNecessary(allPaths, fs)
-
- val tablePath = DataSourceUtils.getTablePath(fs, globPaths.toArray)
+ // Get the table base path
+ val tablePathOpt = TablePathUtils.getTablePath(fs, new Path(allPaths.head))
+ val tablePath = if (tablePathOpt.isPresent) {
+ tablePathOpt.get().toString
+ } else {
+ throw new HoodieException(s"Failed to get the table path, " +
+ s"Maybe ${allPaths.head} is not a hoodie table path")
+ }
log.info("Obtained hudi table path: " + tablePath)
val metaClient =
HoodieTableMetaClient.builder().setConf(fs.getConf).setBasePath(tablePath).build()
val isBootstrappedTable =
metaClient.getTableConfig.getBootstrapBasePath.isPresent
- log.info("Is bootstrapped table => " + isBootstrappedTable)
-
- if (parameters(QUERY_TYPE_OPT_KEY).equals(QUERY_TYPE_SNAPSHOT_OPT_VAL)) {
- if (metaClient.getTableType.equals(HoodieTableType.MERGE_ON_READ)) {
- if (isBootstrappedTable) {
- // Snapshot query is not supported for Bootstrapped MOR tables
- log.warn("Snapshot query is not supported for Bootstrapped
Merge-on-Read tables." +
- " Falling back to Read Optimized query.")
- new HoodieBootstrapRelation(sqlContext, schema, globPaths,
metaClient, optParams)
- } else {
- new MergeOnReadSnapshotRelation(sqlContext, optParams, schema,
globPaths, metaClient)
- }
- } else {
- getBaseFileOnlyView(sqlContext, parameters, schema, readPaths,
isBootstrappedTable, globPaths, metaClient)
- }
- } else
if(parameters(QUERY_TYPE_OPT_KEY).equals(QUERY_TYPE_READ_OPTIMIZED_OPT_VAL)) {
- getBaseFileOnlyView(sqlContext, parameters, schema, readPaths,
isBootstrappedTable, globPaths, metaClient)
- } else if
(parameters(QUERY_TYPE_OPT_KEY).equals(QUERY_TYPE_INCREMENTAL_OPT_VAL)) {
- val metaClient =
HoodieTableMetaClient.builder().setConf(fs.getConf).setBasePath(tablePath).build()
- if (metaClient.getTableType.equals(HoodieTableType.MERGE_ON_READ)) {
- new MergeOnReadIncrementalRelation(sqlContext, optParams, schema,
metaClient)
+ val tableType = metaClient.getTableType
+ val queryType = parameters(QUERY_TYPE_OPT_KEY)
+ log.info(s"Is bootstrapped table => $isBootstrappedTable, tableType is:
$tableType")
+
+ (tableType, queryType, isBootstrappedTable) match {
+
+ case (COPY_ON_WRITE, QUERY_TYPE_SNAPSHOT_OPT_VAL, false) |
+ (COPY_ON_WRITE, QUERY_TYPE_READ_OPTIMIZED_OPT_VAL, false) |
+ (MERGE_ON_READ, QUERY_TYPE_READ_OPTIMIZED_OPT_VAL, false) =>
+ getBaseFileOnlyView(sqlContext, parameters, schema, tablePath,
metaClient)
+
+ case (COPY_ON_WRITE, QUERY_TYPE_INCREMENTAL_OPT_VAL, _) =>
Review comment:
can we move this to line 118. would be nice to have all incremental next
to each other.
##########
File path:
hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/hudi/DefaultSource.scala
##########
@@ -66,10 +69,15 @@ class DefaultSource extends RelationProvider
override def createRelation(sqlContext: SQLContext,
optParams: Map[String, String],
schema: StructType): BaseRelation = {
+ val path = removeStar(optParams.get("path"))
// Add default options for unspecified read options keys.
- val parameters = translateViewTypesToQueryTypes(optParams)
+ val parameters = if (path.isDefined) {
+ translateViewTypesToQueryTypes(optParams) + ("path" -> path.get)
+ } else {
+ translateViewTypesToQueryTypes(optParams)
+ }
+ // Remove the "*" from the path in order to be compatible with the
previous query path with "*"
Review comment:
shouldn't this comment go to line 72?
##########
File path:
hudi-spark-datasource/hudi-spark/src/main/scala/org/apache/hudi/DefaultSource.scala
##########
@@ -79,40 +87,64 @@ class DefaultSource extends RelationProvider
val allPaths = path.map(p => Seq(p)).getOrElse(Seq()) ++ readPaths
val fs = FSUtils.getFs(allPaths.head,
sqlContext.sparkContext.hadoopConfiguration)
- val globPaths = HoodieSparkUtils.checkAndGlobPathIfNecessary(allPaths, fs)
-
- val tablePath = DataSourceUtils.getTablePath(fs, globPaths.toArray)
+ // Get the table base path
+ val tablePathOpt = TablePathUtils.getTablePath(fs, new Path(allPaths.head))
+ val tablePath = if (tablePathOpt.isPresent) {
+ tablePathOpt.get().toString
+ } else {
+ throw new HoodieException(s"Failed to get the table path, " +
+ s"Maybe ${allPaths.head} is not a hoodie table path")
+ }
log.info("Obtained hudi table path: " + tablePath)
val metaClient =
HoodieTableMetaClient.builder().setConf(fs.getConf).setBasePath(tablePath).build()
val isBootstrappedTable =
metaClient.getTableConfig.getBootstrapBasePath.isPresent
- log.info("Is bootstrapped table => " + isBootstrappedTable)
-
- if (parameters(QUERY_TYPE_OPT_KEY).equals(QUERY_TYPE_SNAPSHOT_OPT_VAL)) {
- if (metaClient.getTableType.equals(HoodieTableType.MERGE_ON_READ)) {
- if (isBootstrappedTable) {
- // Snapshot query is not supported for Bootstrapped MOR tables
- log.warn("Snapshot query is not supported for Bootstrapped
Merge-on-Read tables." +
- " Falling back to Read Optimized query.")
- new HoodieBootstrapRelation(sqlContext, schema, globPaths,
metaClient, optParams)
- } else {
- new MergeOnReadSnapshotRelation(sqlContext, optParams, schema,
globPaths, metaClient)
- }
- } else {
- getBaseFileOnlyView(sqlContext, parameters, schema, readPaths,
isBootstrappedTable, globPaths, metaClient)
- }
- } else
if(parameters(QUERY_TYPE_OPT_KEY).equals(QUERY_TYPE_READ_OPTIMIZED_OPT_VAL)) {
- getBaseFileOnlyView(sqlContext, parameters, schema, readPaths,
isBootstrappedTable, globPaths, metaClient)
- } else if
(parameters(QUERY_TYPE_OPT_KEY).equals(QUERY_TYPE_INCREMENTAL_OPT_VAL)) {
- val metaClient =
HoodieTableMetaClient.builder().setConf(fs.getConf).setBasePath(tablePath).build()
- if (metaClient.getTableType.equals(HoodieTableType.MERGE_ON_READ)) {
- new MergeOnReadIncrementalRelation(sqlContext, optParams, schema,
metaClient)
+ val tableType = metaClient.getTableType
+ val queryType = parameters(QUERY_TYPE_OPT_KEY)
+ log.info(s"Is bootstrapped table => $isBootstrappedTable, tableType is:
$tableType")
+
+ (tableType, queryType, isBootstrappedTable) match {
+
+ case (COPY_ON_WRITE, QUERY_TYPE_SNAPSHOT_OPT_VAL, false) |
+ (COPY_ON_WRITE, QUERY_TYPE_READ_OPTIMIZED_OPT_VAL, false) |
Review comment:
can we do (_, QUERY_TYPE_READ_OPTIMIZED_OPT_VAL, false) here?
##########
File path:
hudi-common/src/main/java/org/apache/hudi/common/table/HoodieTableConfig.java
##########
@@ -258,4 +268,5 @@ public String getArchivelogFolder() {
public Properties getProperties() {
return props;
}
+
Review comment:
why extra line ?
--
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:
[email protected]
