Combine aggregate columns per function instead of summing every one

sumRows folded every numeric column by addition, which is only correct
for count and sum, so min/max returned a sum, avg an average of
averages, and a to_string extract collapsed into one empty-key row.

- Combine count and sum by adding, min and max by the extreme, on text
  columns as well as numeric ones
- Rewrite an avg extract into an upstream sum and count and divide the
  totals, answering under the avg key the client asked for
- Refuse an aggregate pdbmux cannot merge with 400 naming the clash
- Treat to_string and jsonb_typeof as row functions that group rather
  than fold, and key groups on every non-aggregate projected column
- Give the e2e fixture per-node resource line numbers and titles whose
  extremes differ per backend
This commit is contained in:
2026-09-06 23:17:10 +10:00
parent e889cf8f7f
commit 66ed7b615c
8 changed files with 1214 additions and 193 deletions
+208
View File
@@ -6,10 +6,12 @@ import (
"context"
"encoding/json"
"fmt"
"math"
"net/http"
"net/url"
"reflect"
"sort"
"strings"
"testing"
)
@@ -361,6 +363,212 @@ func TestResourcesAggregatesAreSummed(t *testing.T) {
}
}
// oneAggregateRow reads the single row a whole-estate aggregate returns.
func oneAggregateRow(t *testing.T, rows []map[string]any) map[string]any {
t.Helper()
if len(rows) != 1 {
t.Fatalf("want exactly one aggregate row, got %d: %v", len(rows), rows)
}
return rows[0]
}
// aggregateNumber reads one numeric aggregate column, which openvoxdb nulls when
// the backend matched nothing.
func aggregateNumber(t *testing.T, row map[string]any, column string) float64 {
t.Helper()
n, ok := row[column].(float64)
if !ok {
t.Fatalf("aggregate row has no numeric %s: %v", column, row)
}
return n
}
// backendAggregate runs a whole-estate aggregate against one backend directly.
func backendAggregate(ctx context.Context, t *testing.T, b *backend, path, q string) map[string]any {
t.Helper()
return oneAggregateRow(t, b.query(ctx, t, path, query(q)))
}
// min and max are extremes, not sums: the merged answer has to be the smallest
// and largest the backends reported, both of which the fixture makes distinct.
func TestResourcesMinMaxAreExtremes(t *testing.T) {
ctx := context.Background()
const q = `["extract",[["function","min","line"],["function","max","line"]]]`
a := backendAggregate(ctx, t, h.a, resourcesPath, q)
b := backendAggregate(ctx, t, h.b, resourcesPath, q)
minA, maxA := aggregateNumber(t, a, "min"), aggregateNumber(t, a, "max")
minB, maxB := aggregateNumber(t, b, "min"), aggregateNumber(t, b, "max")
if minA == minB || maxA == maxB {
t.Fatalf("the fixture gives both backends the same extremes (min %v/%v, max %v/%v)", minA, minB, maxA, maxB)
}
got := oneAggregateRow(t, get(t, resourcesPath, query(q)).rows(t))
if wantMin := math.Min(minA, minB); aggregateNumber(t, got, "min") != wantMin {
t.Errorf("/resources min = %v, want %v (%s=%v, %s=%v)", got["min"], wantMin, h.a.name, minA, h.b.name, minB)
}
wantMax := math.Max(maxA, maxB)
if gotMax := aggregateNumber(t, got, "max"); gotMax != wantMax {
t.Errorf("/resources max = %v, want %v (%s=%v, %s=%v)", gotMax, wantMax, h.a.name, maxA, h.b.name, maxB)
} else if gotMax == maxA+maxB {
t.Errorf("/resources max = %v, which is the sum of the backends' maxima", gotMax)
}
}
// openvoxdb allows min/max on text columns, where the merged answer used to be
// whichever backend happened to answer first. The fixture puts the estate's
// smallest resource title in one backend and its largest in the other, so a
// first-wins merge gets one of the two wrong whichever way round it reads them.
func TestResourcesMinMaxOnATextColumn(t *testing.T) {
ctx := context.Background()
const q = `["extract",[["function","min","title"],["function","max","title"]],["=","type","File"]]`
a := backendAggregate(ctx, t, h.a, resourcesPath, q)
b := backendAggregate(ctx, t, h.b, resourcesPath, q)
minA, minB := aggregateString(t, a, "min"), aggregateString(t, b, "min")
maxA, maxB := aggregateString(t, a, "max"), aggregateString(t, b, "max")
if minA == minB || maxA == maxB {
t.Fatalf("the fixture gives both backends the same extremes (min %q/%q, max %q/%q)", minA, minB, maxA, maxB)
}
got := oneAggregateRow(t, get(t, resourcesPath, query(q)).rows(t))
if want := min(minA, minB); got["min"] != want {
t.Errorf("/resources min(title) = %v, want %q (%s=%q, %s=%q)", got["min"], want, h.a.name, minA, h.b.name, minB)
}
if want := max(maxA, maxB); got["max"] != want {
t.Errorf("/resources max(title) = %v, want %q (%s=%q, %s=%q)", got["max"], want, h.a.name, maxA, h.b.name, maxB)
}
}
func aggregateString(t *testing.T, row map[string]any, column string) string {
t.Helper()
s, ok := row[column].(string)
if !ok {
t.Fatalf("aggregate row has no string %s: %v", column, row)
}
return s
}
// avg is decomposed into an upstream sum and count, so the merged answer is the
// true weighted average of the estate rather than an average of averages.
func TestResourcesAvgIsWeighted(t *testing.T) {
ctx := context.Background()
const parts = `["extract",[["function","sum","line"],["function","count","line"]]]`
a := backendAggregate(ctx, t, h.a, resourcesPath, parts)
b := backendAggregate(ctx, t, h.b, resourcesPath, parts)
sumA, countA := aggregateNumber(t, a, "sum"), aggregateNumber(t, a, "count")
sumB, countB := aggregateNumber(t, b, "sum"), aggregateNumber(t, b, "count")
if countA == countB {
t.Fatalf("the fixture gives both backends %v rows, so a weighted average is indistinguishable from a plain one", countA)
}
want := (sumA + sumB) / (countA + countB)
const q = `["extract",[["function","avg","line"]]]`
got := aggregateNumber(t, oneAggregateRow(t, get(t, resourcesPath, query(q)).rows(t)), "avg")
if math.Abs(got-want) > 1e-9 {
t.Fatalf("/resources avg(line) = %v, want %v ((%v+%v)/(%v+%v))", got, want, sumA, sumB, countA, countB)
}
avgA := aggregateNumber(t, backendAggregate(ctx, t, h.a, resourcesPath, q), "avg")
avgB := aggregateNumber(t, backendAggregate(ctx, t, h.b, resourcesPath, q), "avg")
if math.Abs(got-(avgA+avgB)) < 1e-9 {
t.Errorf("/resources avg(line) = %v, which is the sum of the backends' averages", got)
}
if math.Abs(got-(avgA+avgB)/2) < 1e-9 {
t.Errorf("/resources avg(line) = %v, which is an unweighted average of averages", got)
}
}
func TestResourcesAvgWithGroupBy(t *testing.T) {
ctx := context.Background()
const parts = `["extract",[["function","sum","line"],["function","count","line"],"type"],["group_by","type"]]`
const q = `["extract",[["function","avg","line"],"type"],["group_by","type"]]`
sums, counts := map[string]float64{}, map[string]float64{}
for _, b := range []*backend{h.a, h.b} {
for _, row := range b.query(ctx, t, resourcesPath, query(parts)) {
typ, ok := row["type"].(string)
if !ok {
t.Fatalf("grouped row has no type: %v", row)
}
if n, ok := row["sum"].(float64); ok {
sums[typ] += n
counts[typ] += aggregateNumber(t, row, "count")
}
}
}
if len(sums) == 0 {
t.Fatal("no grouped rows carried a sum, so the weighted average is untested")
}
for _, row := range get(t, resourcesPath, query(q)).rows(t) {
typ, ok := row["type"].(string)
if !ok {
t.Fatalf("grouped row has no type: %v", row)
}
if counts[typ] == 0 {
if row["avg"] != nil {
t.Errorf("avg(line) for %s = %v, want null over no rows", typ, row["avg"])
}
continue
}
want := sums[typ] / counts[typ]
if got := aggregateNumber(t, row, "avg"); math.Abs(got-want) > 1e-9 {
t.Errorf("avg(line) for %s = %v, want %v", typ, got, want)
}
}
}
// A query pdbmux cannot merge is refused outright rather than answered with a
// plausible wrong number.
func TestUnmergeableAggregateIsRefused(t *testing.T) {
resp := rawGet(t, resourcesPath, query(`["extract",[["function","avg","line"],["function","count"]]]`))
if resp.status != http.StatusBadRequest {
t.Fatalf("status %d, want 400: %s", resp.status, resp.body)
}
if !strings.Contains(string(resp.body), "avg") {
t.Errorf("refusal %q does not name the limitation", resp.body)
}
}
// to_string is a scalar expression, so it yields one row per record: alone it
// must not collapse the estate into a single row, and with a companion count it
// groups.
func TestReportsToString(t *testing.T) {
ctx := context.Background()
const bare = `["extract",[["function","to_string","producer_timestamp","FMDAY"]]]`
wantRows := len(h.a.query(ctx, t, reportsPath, query(bare))) + len(h.b.query(ctx, t, reportsPath, query(bare)))
if wantRows < 2 {
t.Fatalf("the fixture yields %d to_string rows, so a collapse would be invisible", wantRows)
}
rows := get(t, reportsPath, query(bare)).rows(t)
if len(rows) != wantRows {
t.Errorf("/reports to_string returned %d rows, want %d (every backend's rows)", len(rows), wantRows)
}
for _, row := range rows {
if _, ok := row["to_string"].(string); !ok {
t.Fatalf("to_string row has no string column: %v", row)
}
}
const grouped = `["extract",[["function","to_string","producer_timestamp","FMDAY"],["function","count"]],["group_by",["function","to_string","producer_timestamp","FMDAY"]]]`
want := map[string]float64{}
for _, b := range []*backend{h.a, h.b} {
for _, row := range b.query(ctx, t, reportsPath, query(grouped)) {
want[row["to_string"].(string)] += aggregateNumber(t, row, "count")
}
}
got := map[string]float64{}
for _, row := range get(t, reportsPath, query(grouped)).rows(t) {
got[row["to_string"].(string)] += aggregateNumber(t, row, "count")
}
if !reflect.DeepEqual(got, want) {
t.Errorf("grouped /reports to_string counts = %v, want %v", got, want)
}
}
// A fact count row carries no certname, so the per-certname fact merge would
// keep one backend's rows and drop the other's; only adding the numbers is right.
func TestFactsAggregatesAreSummed(t *testing.T) {