Veeupup commented on code in PR #8413:
URL: https://github.com/apache/arrow-datafusion/pull/8413#discussion_r1417291602
##########
datafusion-cli/src/functions.rs:
##########
@@ -196,3 +209,110 @@ pub fn display_all_functions() -> Result<()> {
println!("{}", pretty_format_batches(&[batch]).unwrap());
Ok(())
}
+
+/// PARQUET_META table function
+struct ParquetMetadataTable {
+ schema: SchemaRef,
+ batch: RecordBatch,
+}
+
+#[async_trait]
+impl TableProvider for ParquetMetadataTable {
+ fn as_any(&self) -> &dyn std::any::Any {
+ self
+ }
+
+ fn schema(&self) -> arrow::datatypes::SchemaRef {
+ self.schema.clone()
+ }
+
+ fn table_type(&self) -> datafusion::logical_expr::TableType {
+ datafusion::logical_expr::TableType::Base
+ }
+
+ async fn scan(
+ &self,
+ _state: &SessionState,
+ projection: Option<&Vec<usize>>,
+ _filters: &[Expr],
+ _limit: Option<usize>,
+ ) -> Result<Arc<dyn ExecutionPlan>> {
+ Ok(Arc::new(MemoryExec::try_new(
+ &[vec![self.batch.clone()]],
+ TableProvider::schema(self),
+ projection.cloned(),
+ )?))
+ }
+}
+
+pub struct ParquetMetadataFunc {}
+
+impl TableFunctionImpl for ParquetMetadataFunc {
+ fn call(&self, exprs: &[Expr]) -> Result<Arc<dyn TableProvider>> {
+ let Some(Expr::Column(Column { name, .. })) = exprs.get(0) else {
+ return plan_err!("read_csv requires at least one string argument");
+ };
+
+ let file = File::open(name)?;
+ let reader = SerializedFileReader::new(file)?;
+ let metadata = reader.metadata();
+
+ let schema = Arc::new(Schema::new(vec![
+ Field::new("version", DataType::Int32, false),
+ Field::new("num_rows", DataType::Int64, false),
+ Field::new("created_by", DataType::Utf8, false),
+ Field::new("columns_order", DataType::Utf8, false),
+ Field::new("num_row_groups", DataType::Int64, false),
+ Field::new("row_groups", DataType::Utf8, false),
+ ]));
+
+ // construct recordbatch from metadata
+ let num_groups = metadata.num_row_groups();
+ let row_groups = metadata
+ .row_groups()
+ .iter()
+ .map(|rg| {
+ format!(
+ "num_columns: {}, num_rows: {}, total_byte_size: {},
sorting_columns: {:?}",
Review Comment:
it seems that each column in each row_group will be one row in duckdb, so
there will be `Num(cols) * Num(row_group)` rows
I'll just mock the duckdb display format then ~
--
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.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
