-
Notifications
You must be signed in to change notification settings - Fork 750
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.
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
Fix reading nested lists from parquet files #1517
Changes from all commits
File filter
Filter by extension
Conversations
Jump to
Diff view
Diff view
There are no files selected for viewing
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -1330,10 +1330,12 @@ mod tests { | |
use rand::distributions::uniform::SampleUniform; | ||
use rand::{thread_rng, Rng}; | ||
|
||
use crate::arrow::{parquet_to_arrow_schema, ArrowWriter}; | ||
use arrow::array::{ | ||
Array, ArrayRef, LargeListArray, ListArray, PrimitiveArray, StringArray, | ||
StructArray, | ||
}; | ||
use arrow::datatypes::DataType::Struct; | ||
use arrow::datatypes::{ | ||
ArrowPrimitiveType, DataType as ArrowType, Date32Type as ArrowDate32, Field, | ||
Int32Type as ArrowInt32, Int64Type as ArrowInt64, | ||
|
@@ -1348,6 +1350,8 @@ mod tests { | |
use crate::column::page::{Page, PageReader}; | ||
use crate::data_type::{ByteArray, ByteArrayType, DataType, Int32Type, Int64Type}; | ||
use crate::errors::Result; | ||
use crate::file::properties::WriterProperties; | ||
use crate::file::serialized_reader::SerializedFileReader; | ||
use crate::schema::parser::parse_message_type; | ||
use crate::schema::types::{ColumnDescPtr, SchemaDescriptor}; | ||
use crate::util::test_common::make_pages; | ||
|
@@ -2268,4 +2272,67 @@ mod tests { | |
&PrimitiveArray::<ArrowInt32>::from(vec![Some(3), Some(4)]) | ||
); | ||
} | ||
|
||
#[test] | ||
fn test_nested_lists() { | ||
// Construct column schema | ||
let message_type = " | ||
message table { | ||
REPEATED group table_info { | ||
REQUIRED BYTE_ARRAY name; | ||
REPEATED group cols { | ||
REQUIRED BYTE_ARRAY name; | ||
REQUIRED INT32 type; | ||
OPTIONAL INT32 length; | ||
} | ||
REPEATED group tags { | ||
REQUIRED BYTE_ARRAY name; | ||
REQUIRED INT32 type; | ||
OPTIONAL INT32 length; | ||
} | ||
} | ||
} | ||
"; | ||
Comment on lines
+2280
to
+2295
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. This message type is copied from the issue. |
||
|
||
let schema = parse_message_type(message_type) | ||
.map(|t| Arc::new(SchemaDescriptor::new(Arc::new(t)))) | ||
.unwrap(); | ||
|
||
let arrow_schema = parquet_to_arrow_schema(schema.as_ref(), &None).unwrap(); | ||
|
||
let file = tempfile::tempfile().unwrap(); | ||
let props = WriterProperties::builder() | ||
.set_max_row_group_size(200) | ||
.build(); | ||
|
||
let mut writer = ArrowWriter::try_new( | ||
file.try_clone().unwrap(), | ||
Arc::new(arrow_schema), | ||
Some(props), | ||
) | ||
.unwrap(); | ||
writer.close().unwrap(); | ||
|
||
let file_reader: Arc<dyn FileReader> = | ||
Arc::new(SerializedFileReader::new(file).unwrap()); | ||
|
||
let file_metadata = file_reader.metadata().file_metadata(); | ||
let arrow_schema = parquet_to_arrow_schema( | ||
file_metadata.schema_descr(), | ||
file_metadata.key_value_metadata(), | ||
) | ||
.unwrap(); | ||
|
||
let mut array_reader = build_array_reader( | ||
file_reader.metadata().file_metadata().schema_descr_ptr(), | ||
Arc::new(arrow_schema.clone()), | ||
vec![0usize].into_iter(), | ||
Box::new(file_reader), | ||
) | ||
.unwrap(); | ||
|
||
let batch = array_reader.next_batch(100).unwrap(); | ||
assert_eq!(batch.data_type(), &Struct(arrow_schema.fields().clone())); | ||
assert_eq!(batch.len(), 0); | ||
} | ||
} |
Original file line number | Diff line number | Diff line change |
---|---|---|
|
@@ -152,9 +152,10 @@ impl<'a> TypeVisitor<Option<Box<dyn ArrayReader>>, &'a ArrayReaderBuilderContext | |
)?; | ||
|
||
if cur_type.get_basic_info().repetition() == Repetition::REPEATED { | ||
Err(ArrowError( | ||
"Reading repeated field is not supported yet!".to_string(), | ||
)) | ||
Err(ArrowError(format!( | ||
"Reading repeated field ({:?}) is not supported yet!", | ||
cur_type.name() | ||
))) | ||
} else { | ||
Ok(Some(reader)) | ||
} | ||
|
@@ -189,9 +190,10 @@ impl<'a> TypeVisitor<Option<Box<dyn ArrayReader>>, &'a ArrayReaderBuilderContext | |
if cur_type.get_basic_info().has_repetition() | ||
&& cur_type.get_basic_info().repetition() == Repetition::REPEATED | ||
{ | ||
Err(ArrowError( | ||
"Reading repeated field is not supported yet!".to_string(), | ||
)) | ||
Err(ArrowError(format!( | ||
"Reading repeated field ({:?}) is not supported yet!", | ||
cur_type.name(), | ||
))) | ||
} else { | ||
Ok(Some(reader)) | ||
} | ||
|
@@ -321,11 +323,8 @@ impl<'a> TypeVisitor<Option<Box<dyn ArrayReader>>, &'a ArrayReaderBuilderContext | |
_ => (), | ||
} | ||
|
||
let item_reader = self | ||
.dispatch(item_type.clone(), &new_context) | ||
.unwrap() | ||
.unwrap(); | ||
Comment on lines
-324
to
-327
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. When a column is not included, There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. 👍 I found using a whitespace blind diff made the changes easier to understand: https://github.com/apache/arrow-rs/pull/1517/files?w=1 |
||
|
||
let reader = self.dispatch(item_type.clone(), &new_context); | ||
if let Ok(Some(item_reader)) = reader { | ||
let item_reader_type = item_reader.get_data_type().clone(); | ||
|
||
match item_reader_type { | ||
|
@@ -339,7 +338,8 @@ impl<'a> TypeVisitor<Option<Box<dyn ArrayReader>>, &'a ArrayReaderBuilderContext | |
// a list is a group type with a single child. The list child's | ||
// name comes from the child's field name. | ||
// if the child's name is "list" and it has a child, then use this child | ||
if list_child.name() == "list" && !list_child.get_fields().is_empty() { | ||
if list_child.name() == "list" && !list_child.get_fields().is_empty() | ||
{ | ||
list_child = list_child.get_fields().first().unwrap(); | ||
} | ||
let arrow_type = self | ||
|
@@ -386,6 +386,9 @@ impl<'a> TypeVisitor<Option<Box<dyn ArrayReader>>, &'a ArrayReaderBuilderContext | |
Ok(Some(list_array_reader)) | ||
} | ||
} | ||
} else { | ||
reader | ||
} | ||
} | ||
} | ||
|
||
|
@@ -698,7 +701,12 @@ impl<'a> ArrayReaderBuilder { | |
ArrowType::Struct(fields) => { | ||
field = fields.iter().find(|f| f.name() == part) | ||
} | ||
ArrowType::List(list_field) => field = Some(list_field.as_ref()), | ||
ArrowType::List(list_field) => match list_field.data_type() { | ||
ArrowType::Struct(fields) => { | ||
field = fields.iter().find(|f| f.name() == part) | ||
} | ||
_ => field = Some(list_field.as_ref()), | ||
}, | ||
Comment on lines
+704
to
+709
There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. This was tested by using the example in #1515. Not sure if it is easy to add a unit test. There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Shall we put the example parquet file into There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. I think ideally we would construct a parquet file with this pattern programmatically (aka write it out in a test and then read it back in). if that is not possible / feasible, adding an example in parquet-testing would be second best There was a problem hiding this comment. Choose a reason for hiding this commentThe reason will be displayed to describe this comment to others. Learn more. Sounds good. Let me try to make one. Thanks. |
||
_ => field = None, | ||
} | ||
} else { | ||
|
@@ -710,14 +718,13 @@ impl<'a> ArrayReaderBuilder { | |
} | ||
} | ||
|
||
|
||
#[cfg(test)] | ||
mod tests { | ||
use std::sync::Arc; | ||
use super::*; | ||
use crate::arrow::parquet_to_arrow_schema; | ||
use crate::file::reader::{FileReader, SerializedFileReader}; | ||
use crate::util::test_common::get_test_file; | ||
use super::*; | ||
use std::sync::Arc; | ||
|
||
#[test] | ||
fn test_create_array_reader() { | ||
|
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I tested running this test without the rest of the code change in this PR and I got: