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.

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 missing parameter for stats,min,max,count,sum,avg #2151

Merged
merged 2 commits into from
Aug 28, 2023
Merged
Show file tree
Hide file tree
Changes from 1 commit
Commits
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
24 changes: 18 additions & 6 deletions src/aggregation/agg_req_with_accessor.rs
Original file line number Diff line number Diff line change
Expand Up @@ -112,12 +112,24 @@ impl AggregationWithAccessor {
fallback_type,
)?
}
Average(AverageAggregation { field: field_name })
| Count(CountAggregation { field: field_name })
| Max(MaxAggregation { field: field_name })
| Min(MinAggregation { field: field_name })
| Stats(StatsAggregation { field: field_name })
| Sum(SumAggregation { field: field_name }) => {
Average(AverageAggregation {
field: field_name, ..
})
| Count(CountAggregation {
field: field_name, ..
})
| Max(MaxAggregation {
field: field_name, ..
})
| Min(MinAggregation {
field: field_name, ..
})
| Stats(StatsAggregation {
field: field_name, ..
})
| Sum(SumAggregation {
field: field_name, ..
}) => {
let (accessor, field_type) =
get_ff_reader(reader, field_name, Some(get_numeric_or_date_column_types()))?;

Expand Down
42 changes: 42 additions & 0 deletions src/aggregation/bucket/term_agg.rs
Original file line number Diff line number Diff line change
Expand Up @@ -1455,6 +1455,47 @@ mod tests {

Ok(())
}
#[test]
fn terms_empty_json() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let json = schema_builder.add_json_field("json", FAST);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests().unwrap();
// => Segment with empty json
index_writer.add_document(doc!()).unwrap();
index_writer.commit().unwrap();
// => Segment with json, but no field partially_empty
index_writer
.add_document(doc!(json => json!({"different_field": "blue"})))
.unwrap();
index_writer.commit().unwrap();
//// => Segment with field partially_empty
index_writer
.add_document(doc!(json => json!({"partially_empty": "blue"})))
.unwrap();
index_writer.add_document(doc!())?;
index_writer.commit().unwrap();

let agg_req: Aggregations = serde_json::from_value(json!({
"my_texts": {
"terms": {
"field": "json.partially_empty"
},
}
}))
.unwrap();

let res = exec_request_with_query(agg_req, &index, None)?;

assert_eq!(res["my_texts"]["buckets"][0]["key"], "blue");
assert_eq!(res["my_texts"]["buckets"][0]["doc_count"], 1);
assert_eq!(res["my_texts"]["buckets"][1], serde_json::Value::Null);
assert_eq!(res["my_texts"]["sum_other_doc_count"], 0);
assert_eq!(res["my_texts"]["doc_count_error_upper_bound"], 0);

Ok(())
}

#[test]
fn terms_aggregation_bytes() -> crate::Result<()> {
Expand Down Expand Up @@ -1492,6 +1533,7 @@ mod tests {

Ok(())
}

#[test]
fn terms_aggregation_missing_multi_value() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
Expand Down
11 changes: 10 additions & 1 deletion src/aggregation/metric/average.rs
Original file line number Diff line number Diff line change
Expand Up @@ -20,12 +20,21 @@ use super::{IntermediateStats, SegmentStatsCollector};
pub struct AverageAggregation {
/// The field name to compute the average on.
pub field: String,
/// The missing parameter defines how documents that are missing a value should be treated.
/// By default they will be ignored but it is also possible to treat them as if they had a
/// value. Examples in JSON format:
/// { "field": "my_numbers", "missing": "10.0" }
#[serde(skip_serializing_if = "Option::is_none", default)]
PSeitz marked this conversation as resolved.
Show resolved Hide resolved
pub missing: Option<f64>,
}

impl AverageAggregation {
/// Creates a new [`AverageAggregation`] instance from a field name.
pub fn from_field_name(field_name: String) -> Self {
Self { field: field_name }
Self {
field: field_name,
missing: None,
}
}
/// Returns the field name the aggregation is computed on.
pub fn field_name(&self) -> &str {
Expand Down
11 changes: 10 additions & 1 deletion src/aggregation/metric/count.rs
Original file line number Diff line number Diff line change
Expand Up @@ -20,12 +20,21 @@ use super::{IntermediateStats, SegmentStatsCollector};
pub struct CountAggregation {
/// The field name to compute the count on.
pub field: String,
/// The missing parameter defines how documents that are missing a value should be treated.
/// By default they will be ignored but it is also possible to treat them as if they had a
/// value. Examples in JSON format:
/// { "field": "my_numbers", "missing": "10.0" }
#[serde(skip_serializing_if = "Option::is_none", default)]
PSeitz marked this conversation as resolved.
Show resolved Hide resolved
pub missing: Option<f64>,
}

impl CountAggregation {
/// Creates a new [`CountAggregation`] instance from a field name.
pub fn from_field_name(field_name: String) -> Self {
Self { field: field_name }
Self {
field: field_name,
missing: None,
}
}
/// Returns the field name the aggregation is computed on.
pub fn field_name(&self) -> &str {
Expand Down
63 changes: 62 additions & 1 deletion src/aggregation/metric/max.rs
Original file line number Diff line number Diff line change
Expand Up @@ -20,12 +20,21 @@ use super::{IntermediateStats, SegmentStatsCollector};
pub struct MaxAggregation {
/// The field name to compute the maximum on.
pub field: String,
/// The missing parameter defines how documents that are missing a value should be treated.
/// By default they will be ignored but it is also possible to treat them as if they had a
/// value. Examples in JSON format:
/// { "field": "my_numbers", "missing": "10.0" }
#[serde(skip_serializing_if = "Option::is_none", default)]
PSeitz marked this conversation as resolved.
Show resolved Hide resolved
pub missing: Option<f64>,
}

impl MaxAggregation {
/// Creates a new [`MaxAggregation`] instance from a field name.
pub fn from_field_name(field_name: String) -> Self {
Self { field: field_name }
Self {
field: field_name,
missing: None,
}
}
/// Returns the field name the aggregation is computed on.
pub fn field_name(&self) -> &str {
Expand Down Expand Up @@ -56,3 +65,55 @@ impl IntermediateMax {
self.stats.finalize().max
}
}

#[cfg(test)]
mod tests {
use crate::aggregation::agg_req::Aggregations;
use crate::aggregation::tests::exec_request_with_query;
use crate::schema::{Schema, FAST};
use crate::Index;

#[test]
fn test_max_agg_with_missing() -> crate::Result<()> {
let mut schema_builder = Schema::builder();
let json = schema_builder.add_json_field("json", FAST);
let schema = schema_builder.build();
let index = Index::create_in_ram(schema);
let mut index_writer = index.writer_for_tests().unwrap();
// => Segment with empty json
index_writer.add_document(doc!()).unwrap();
index_writer.commit().unwrap();
// => Segment with json, but no field partially_empty
index_writer
.add_document(doc!(json => json!({"different_field": "blue"})))
.unwrap();
index_writer.commit().unwrap();
//// => Segment with field partially_empty
index_writer
.add_document(doc!(json => json!({"partially_empty": 10.0})))
.unwrap();
index_writer.add_document(doc!())?;
index_writer.commit().unwrap();

let agg_req: Aggregations = serde_json::from_value(json!({
"my_stats": {
"max": {
"field": "json.partially_empty",
"missing": 100.0,
}
}
}))
.unwrap();

let res = exec_request_with_query(agg_req, &index, None)?;

assert_eq!(
res["my_stats"],
json!({
"value": 100.0,
})
);

Ok(())
}
}
11 changes: 10 additions & 1 deletion src/aggregation/metric/min.rs
Original file line number Diff line number Diff line change
Expand Up @@ -20,12 +20,21 @@ use super::{IntermediateStats, SegmentStatsCollector};
pub struct MinAggregation {
/// The field name to compute the minimum on.
pub field: String,
/// The missing parameter defines how documents that are missing a value should be treated.
/// By default they will be ignored but it is also possible to treat them as if they had a
/// value. Examples in JSON format:
/// { "field": "my_numbers", "missing": "10.0" }
#[serde(skip_serializing_if = "Option::is_none", default)]
PSeitz marked this conversation as resolved.
Show resolved Hide resolved
pub missing: Option<f64>,
}

impl MinAggregation {
/// Creates a new [`MinAggregation`] instance from a field name.
pub fn from_field_name(field_name: String) -> Self {
Self { field: field_name }
Self {
field: field_name,
missing: None,
}
}
/// Returns the field name the aggregation is computed on.
pub fn field_name(&self) -> &str {
Expand Down
7 changes: 7 additions & 0 deletions src/aggregation/metric/percentiles.rs
Original file line number Diff line number Diff line change
Expand Up @@ -80,6 +80,12 @@
/// Whether to return the percentiles as a hash map
#[serde(default = "default_as_true")]
pub keyed: bool,
/// The missing parameter defines how documents that are missing a value should be treated.
/// By default they will be ignored but it is also possible to treat them as if they had a
/// value. Examples in JSON format:
/// { "field": "my_numbers", "missing": "10.0" }
#[serde(skip_serializing_if = "Option::is_none", default)]
pub missing: Option<f64>,
}
fn default_percentiles() -> &'static [f64] {
&[1.0, 5.0, 25.0, 50.0, 75.0, 95.0, 99.0]
Expand All @@ -95,6 +101,7 @@
field: field_name,
percents: None,
keyed: default_as_true(),
missing: None,
}
}
/// Returns the field name the aggregation is computed on.
Expand Down Expand Up @@ -463,7 +470,7 @@

fn test_aggregation_percentiles(merge_segments: bool) -> crate::Result<()> {
use rand_distr::Distribution;
let num_values_in_segment = vec![100, 30_000, 8000];

Check warning on line 473 in src/aggregation/metric/percentiles.rs

View workflow job for this annotation

GitHub Actions / clippy

useless use of `vec!`

warning: useless use of `vec!` --> src/aggregation/metric/percentiles.rs:473:37 | 473 | let num_values_in_segment = vec![100, 30_000, 8000]; | ^^^^^^^^^^^^^^^^^^^^^^^ help: you can use an array directly: `[100, 30_000, 8000]` | = help: for further information visit https://rust-lang.github.io/rust-clippy/master/index.html#useless_vec = note: `#[warn(clippy::useless_vec)]` on by default
let lg_norm = rand_distr::LogNormal::new(2.996f64, 0.979f64).unwrap();
let mut rng = StdRng::from_seed([1u8; 32]);

Expand Down
Loading
Loading