Merge pull request #2547 from quickwit-oss/trinity/count-str

add support for counting non integer in aggregation

Author: trinity-1686a

src/aggregation/agg_req_with_accessor.rs

@@ -271,10 +271,6 @@ impl AggregationWithAccessor {
                 field: ref field_name,
                 ..
             })
-            | Count(CountAggregation {
-                field: ref field_name,
-                ..
-            })
             | Max(MaxAggregation {
                 field: ref field_name,
                 ..
@@ -299,6 +295,24 @@ impl AggregationWithAccessor {
                     get_ff_reader(reader, field_name, Some(get_numeric_or_date_column_types()))?;
                 add_agg_with_accessor(&agg, accessor, column_type, &mut res)?;
             }
+            Count(CountAggregation {
+                field: ref field_name,
+                ..
+            }) => {
+                let allowed_column_types = [
+                    ColumnType::I64,
+                    ColumnType::U64,
+                    ColumnType::F64,
+                    ColumnType::Str,
+                    ColumnType::DateTime,
+                    ColumnType::Bool,
+                    ColumnType::IpAddr,
+                    // ColumnType::Bytes Unsupported
+                ];
+                let (accessor, column_type) =
+                    get_ff_reader(reader, field_name, Some(&allowed_column_types))?;
+                add_agg_with_accessor(&agg, accessor, column_type, &mut res)?;
+            }
             Percentiles(ref percentiles) => {
                 let (accessor, column_type) = get_ff_reader(
                     reader,

src/aggregation/metric/stats.rs

@@ -220,9 +220,23 @@ impl SegmentStatsCollector {
                 .column_block_accessor
                 .fetch_block(docs, &agg_accessor.accessor);
         }
-        for val in agg_accessor.column_block_accessor.iter_vals() {
-            let val1 = f64_from_fastfield_u64(val, &self.field_type);
-            self.stats.collect(val1);
+        if [
+            ColumnType::I64,
+            ColumnType::U64,
+            ColumnType::F64,
+            ColumnType::DateTime,
+        ]
+        .contains(&self.field_type)
+        {
+            for val in agg_accessor.column_block_accessor.iter_vals() {
+                let val1 = f64_from_fastfield_u64(val, &self.field_type);
+                self.stats.collect(val1);
+            }
+        } else {
+            for _val in agg_accessor.column_block_accessor.iter_vals() {
+                // we ignore the value and simply record that we got something
+                self.stats.collect(0.0);
+            }
         }
     }
 }
@@ -435,6 +449,11 @@ mod tests {
                     "field": "score",
                 },
             },
+            "count_str": {
+                "value_count": {
+                    "field": "text",
+                },
+            },
             "range": range_agg
         }))
         .unwrap();
@@ -500,6 +519,13 @@ mod tests {
             })
         );
 
+        assert_eq!(
+            res["count_str"],
+            json!({
+                "value": 7.0,
+            })
+        );
+
         Ok(())
     }
 

src/aggregation/mod.rs

@@ -578,7 +578,7 @@ mod tests {
             .set_indexing_options(
                 TextFieldIndexing::default().set_index_option(IndexRecordOption::WithFreqs),
             )
-            .set_fast(None)
+            .set_fast(Some("raw"))
             .set_stored();
         let text_field = schema_builder.add_text_field("text", text_fieldtype);
         let date_field = schema_builder.add_date_field("date", FAST);