Skip to content

chore: separate column predicates from partition filters #149

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Dec 23, 2024
Merged

chore: separate column predicates from partition filters #149

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
c3d3546
feat: separate column predicates from partition filters
tchow-zlai Dec 20, 2024
ca9bb4c
fill out all params
tchow-zlai Dec 20, 2024
2659da6
pr feedback
tchow-zlai Dec 23, 2024
0903016
Merge branch 'main' into tchow/bq-support-5
tchow-zlai Dec 23, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion spark/src/main/scala/ai/chronon/spark/GroupBy.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -677,7 +677,8 @@ object GroupBy {
tableUtils.scanDfBase(
selects,
if (mutations) source.getEntities.mutationTable.cleanSpec else source.table,
Option(source.query.wheres).map(_.toScala).getOrElse(Seq.empty[String]) ++ partitionConditions,
Option(source.query.wheres).map(_.toScala).getOrElse(Seq.empty[String]),
partitionConditions,
Some(metaColumns ++ keys.map(_ -> null))
)
}
Expand Down
4 changes: 2 additions & 2 deletions spark/src/main/scala/ai/chronon/spark/Join.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -213,10 +213,10 @@ class Join(joinConf: api.Join,
} else {
leftRange
}
val wheres = Seq(s"ds >= '${effectiveRange.start}'", s"ds <= '${effectiveRange.end}'")
val wheres = effectiveRange.whereClauses("ds")
val sql = QueryUtils.build(null, partTable, wheres)
logger.info(s"Pulling data from joinPart table with: $sql")
(joinPart, tableUtils.scanDfBase(null, partTable, wheres))
(joinPart, tableUtils.scanDfBase(null, partTable, List.empty, wheres, None))
}
}

Expand Down
8 changes: 6 additions & 2 deletions spark/src/main/scala/ai/chronon/spark/TableUtils.scala
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -785,7 +785,8 @@ case class TableUtils(sparkSession: SparkSession) {

def scanDfBase(selectMap: Map[String, String],
table: String,
wheres: scala.collection.Seq[String],
wheres: Seq[String],
rangeWheres: Seq[String],
fallbackSelects: Option[Map[String, String]] = None): DataFrame = {
val dp = DataPointer(table)
var df = dp.toDf(sparkSession)
Expand All @@ -798,9 +799,12 @@ case class TableUtils(sparkSession: SparkSession) {
| ${selects.mkString("\n ").green}
| wheres:
| ${wheres.mkString(",\n ").green}
| partition filters:
| ${rangeWheres.mkString(",\n ").green}
|""".stripMargin.yellow)
if (selects.nonEmpty) df = df.selectExpr(selects: _*)
if (wheres.nonEmpty) df = df.where(wheres.map(w => s"($w)").mkString(" AND "))
if (rangeWheres.nonEmpty) df = df.where(rangeWheres.map(w => s"($w)").mkString(" AND "))
df
}

Expand All @@ -822,7 +826,7 @@ case class TableUtils(sparkSession: SparkSession) {

val selects = Option(query).flatMap(q => Option(q.selects)).map(_.toScala).getOrElse(Map.empty)

scanDfBase(selects, table, wheres, fallbackSelects)
scanDfBase(selects, table, wheres, rangeWheres, fallbackSelects)
}

def partitionRange(table: String): PartitionRange = {
Expand Down
Loading