Skip to content
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

Add Decimal to CsvWriter and improve debug display #406

Merged
merged 3 commits into from
Jun 13, 2021
Merged

Add Decimal to CsvWriter and improve debug display #406

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e14bb59
Add Decimal to CsvWriter and improve debug display
alippai Jun 4, 2021
be1a8fd
Measure CSV writer instead of file and data creation
alippai Jun 5, 2021
83f5f6b
Re-use decimal formatting
alippai Jun 5, 2021
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
19 changes: 10 additions & 9 deletions arrow/benches/csv_writer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -28,14 +28,14 @@ use arrow::record_batch::RecordBatch;
use std::fs::File;
use std::sync::Arc;

fn record_batches_to_csv() {
fn criterion_benchmark(c: &mut Criterion) {
alippai marked this conversation as resolved.
Show resolved Hide resolved
#[cfg(feature = "csv")]
{
let schema = Schema::new(vec![
Field::new("c1", DataType::Utf8, false),
Field::new("c2", DataType::Float64, true),
Field::new("c3", DataType::UInt32, false),
Field::new("c3", DataType::Boolean, true),
Field::new("c4", DataType::Boolean, true),
]);

let c1 = StringArray::from(vec![
Expand All @@ -59,16 +59,17 @@ fn record_batches_to_csv() {
let file = File::create("target/bench_write_csv.csv").unwrap();
let mut writer = csv::Writer::new(file);
let batches = vec![&b, &b, &b, &b, &b, &b, &b, &b, &b, &b, &b];
#[allow(clippy::unit_arg)]
criterion::black_box(for batch in batches {
writer.write(batch).unwrap()

c.bench_function("record_batches_to_csv", |b| {
b.iter(|| {
#[allow(clippy::unit_arg)]
criterion::black_box(for batch in &batches {
writer.write(batch).unwrap()
});
});
});
}
}

fn criterion_benchmark(c: &mut Criterion) {
c.bench_function("record_batches_to_csv", |b| b.iter(record_batches_to_csv));
}

criterion_group!(benches, criterion_benchmark);
criterion_main!(benches);
36 changes: 24 additions & 12 deletions arrow/src/array/array_binary.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -666,6 +666,17 @@ impl DecimalArray {
self.length * i as i32
}

#[inline]
pub fn value_as_string(&self, row: usize) -> String {
let decimal_string = self.value(row).to_string();
if self.scale == 0 {
decimal_string
} else {
let splits = decimal_string.split_at(decimal_string.len() - self.scale);
format!("{}.{}", splits.0, splits.1)
}
}

pub fn from_fixed_size_list_array(
v: FixedSizeListArray,
precision: usize,
Expand Down Expand Up @@ -729,7 +740,9 @@ impl fmt::Debug for DecimalArray {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
write!(f, "DecimalArray<{}, {}>\n[\n", self.precision, self.scale)?;
print_long_array(self, f, |array, index, f| {
fmt::Debug::fmt(&array.value(index), f)
let formatted_decimal = array.value_as_string(index);

write!(f, "{}", formatted_decimal)
})?;
write!(f, "]")
}
Expand Down Expand Up @@ -758,7 +771,7 @@ impl Array for DecimalArray {
#[cfg(test)]
mod tests {
use crate::{
array::{LargeListArray, ListArray},
array::{DecimalBuilder, LargeListArray, ListArray},
datatypes::Field,
};

Expand Down Expand Up @@ -1163,17 +1176,16 @@ mod tests {

#[test]
fn test_decimal_array_fmt_debug() {
let values: [u8; 32] = [
192, 219, 180, 17, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 64, 36, 75, 238, 253,
255, 255, 255, 255, 255, 255, 255, 255, 255, 255, 255,
];
let array_data = ArrayData::builder(DataType::Decimal(23, 6))
.len(2)
.add_buffer(Buffer::from(&values[..]))
.build();
let arr = DecimalArray::from(array_data);
let values: Vec<i128> = vec![8887000000, -8887000000];
let mut decimal_builder = DecimalBuilder::new(3, 23, 6);

values.iter().for_each(|&value| {
decimal_builder.append_value(value).unwrap();
});
decimal_builder.append_null().unwrap();
let arr = decimal_builder.finish();
assert_eq!(
"DecimalArray<23, 6>\n[\n 8887000000,\n -8887000000,\n]",
"DecimalArray<23, 6>\n[\n 8887.000000,\n -8887.000000,\n null,\n]",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

this looks like a significant improvement to me 👍

format!("{:?}", arr)
);
}
Expand Down
23 changes: 16 additions & 7 deletions arrow/src/csv/writer.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,6 +70,7 @@ use std::io::Write;
use crate::datatypes::*;
use crate::error::{ArrowError, Result};
use crate::record_batch::RecordBatch;
use crate::util::display::make_string_from_decimal;
use crate::{array::*, util::serialization::lexical_to_string};
const DEFAULT_DATE_FORMAT: &str = "%F";
const DEFAULT_TIME_FORMAT: &str = "%T";
Expand Down Expand Up @@ -242,6 +243,7 @@ impl<W: Write> Writer<W> {
};
format!("{}", datetime.format(&self.timestamp_format))
}
DataType::Decimal(..) => make_string_from_decimal(col, row_index)?,
t => {
// List and Struct arrays not supported by the writer, any
// other type needs to be implemented
Expand Down Expand Up @@ -566,6 +568,7 @@ sed do eiusmod tempor,-556132.25,1,,2019-04-18T02:45:55.555000000,23:46:03,foo
Field::new("c4", DataType::Boolean, true),
Field::new("c5", DataType::Timestamp(TimeUnit::Millisecond, None), true),
Field::new("c6", DataType::Time32(TimeUnit::Second), false),
Field::new("c7", DataType::Decimal(6, 2), false),
]);

let c1 = StringArray::from(vec![
Expand All @@ -585,6 +588,11 @@ sed do eiusmod tempor,-556132.25,1,,2019-04-18T02:45:55.555000000,23:46:03,foo
None,
);
let c6 = Time32SecondArray::from(vec![1234, 24680, 85563]);
let mut c7_builder = DecimalBuilder::new(5, 6, 2);
c7_builder.append_value(12345_i128).unwrap();
c7_builder.append_value(-12345_i128).unwrap();
c7_builder.append_null().unwrap();
let c7 = c7_builder.finish();

let batch = RecordBatch::try_new(
Arc::new(schema),
Expand All @@ -595,6 +603,7 @@ sed do eiusmod tempor,-556132.25,1,,2019-04-18T02:45:55.555000000,23:46:03,foo
Arc::new(c4),
Arc::new(c5),
Arc::new(c6),
Arc::new(c7),
],
)
.unwrap();
Expand All @@ -606,13 +615,13 @@ sed do eiusmod tempor,-556132.25,1,,2019-04-18T02:45:55.555000000,23:46:03,foo
writer.write(batch).unwrap();
}

let left = "c1,c2,c3,c4,c5,c6
Lorem ipsum dolor sit amet,123.564532,3,true,,00:20:34
consectetur adipiscing elit,,2,false,2019-04-18T10:54:47.378000000,06:51:20
sed do eiusmod tempor,-556132.25,1,,2019-04-18T02:45:55.555000000,23:46:03
Lorem ipsum dolor sit amet,123.564532,3,true,,00:20:34
consectetur adipiscing elit,,2,false,2019-04-18T10:54:47.378000000,06:51:20
sed do eiusmod tempor,-556132.25,1,,2019-04-18T02:45:55.555000000,23:46:03\n";
let left = "c1,c2,c3,c4,c5,c6,c7
Lorem ipsum dolor sit amet,123.564532,3,true,,00:20:34,123.45
consectetur adipiscing elit,,2,false,2019-04-18T10:54:47.378000000,06:51:20,-123.45
sed do eiusmod tempor,-556132.25,1,,2019-04-18T02:45:55.555000000,23:46:03,
Lorem ipsum dolor sit amet,123.564532,3,true,,00:20:34,123.45
consectetur adipiscing elit,,2,false,2019-04-18T10:54:47.378000000,06:51:20,-123.45
sed do eiusmod tempor,-556132.25,1,,2019-04-18T02:45:55.555000000,23:46:03,\n";
let right = writer.writer.into_inner().map(|s| s.to_string());
assert_eq!(Some(left.to_string()), right.ok());
}
Expand Down
27 changes: 12 additions & 15 deletions arrow/src/util/display.rs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,8 @@
//! purposes. See the `pretty` crate for additional functions for
//! record batch pretty printing.

use std::sync::Arc;

use crate::array::Array;
use crate::datatypes::{
ArrowNativeType, ArrowPrimitiveType, DataType, Int16Type, Int32Type, Int64Type,
Expand Down Expand Up @@ -192,18 +194,15 @@ macro_rules! make_string_from_list {
}};
}

macro_rules! make_string_from_decimal {
($array_type: ty, $column: ident, $row: ident, $scale: ident) => {{
let array = $column.as_any().downcast_ref::<$array_type>().unwrap();
let decimal_string = array.value($row).to_string();
let formatted_decimal = if *$scale == 0 {
decimal_string
} else {
let splits = decimal_string.split_at(decimal_string.len() - *$scale);
format!("{}.{}", splits.0, splits.1)
};
Ok(formatted_decimal)
}};
#[inline(always)]
pub fn make_string_from_decimal(column: &Arc<dyn Array>, row: usize) -> Result<String> {
let array = column
.as_any()
.downcast_ref::<array::DecimalArray>()
.unwrap();

let formatted_decimal = array.value_as_string(row);
Ok(formatted_decimal)
}

/// Get the value at the given row in an array as a String.
Expand Down Expand Up @@ -231,9 +230,7 @@ pub fn array_value_to_string(column: &array::ArrayRef, row: usize) -> Result<Str
DataType::Float16 => make_string!(array::Float32Array, column, row),
DataType::Float32 => make_string!(array::Float32Array, column, row),
DataType::Float64 => make_string!(array::Float64Array, column, row),
DataType::Decimal(_, scale) => {
make_string_from_decimal!(array::DecimalArray, column, row, scale)
}
DataType::Decimal(..) => make_string_from_decimal(column, row),
DataType::Timestamp(unit, _) if *unit == TimeUnit::Second => {
make_string_datetime!(array::TimestampSecondArray, column, row)
}
Expand Down