tantivy/src/aggregation/metric/max.rs

use std::fmt::Debug;

use serde::{Deserialize, Serialize};

use super::*;
use crate::aggregation::*;

/// A single-value metric aggregation that computes the maximum of numeric values that are
/// extracted from the aggregated documents.
/// See [super::SingleMetricResult] for return value.
///
/// # JSON Format
/// ```json
/// {
///     "max": {
///         "field": "score"
///     }
/// }
/// ```
#[derive(Clone, Debug, PartialEq, Serialize, Deserialize)]
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(default, deserialize_with = "deserialize_option_f64")]
    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,
            missing: None,
        }
    }
    /// Returns the field name the aggregation is computed on.
    pub fn field_name(&self) -> &str {
        &self.field
    }
}

/// Intermediate result of the maximum aggregation that can be combined with other intermediate
/// results.
#[derive(Default, Clone, Debug, PartialEq, Serialize, Deserialize)]
pub struct IntermediateMax {
    stats: IntermediateStats,
}

impl IntermediateMax {
    /// Creates a new [`IntermediateMax`] instance from a [`SegmentStatsCollector`].
    pub(crate) fn from_collector(collector: SegmentStatsCollector) -> Self {
        Self {
            stats: collector.stats,
        }
    }
    /// Merges the other intermediate result into self.
    pub fn merge_fruits(&mut self, other: IntermediateMax) {
        self.stats.merge_fruits(other.stats);
    }
    /// Computes the final maximum value.
    pub fn finalize(&self) -> Option<f64> {
        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, IndexWriter};

    #[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: IndexWriter = 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(())
    }
}