dev/MultiforaDB
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

tests/spec: an aggregation corpus, recorded from mongod

Browse Source 
M2.5's gate, built before the milestone it gates -- the same order that put
`expectEvents` before the free list in M1 and Tier 0 before everything in M2.

`mongodb/specifications` has no aggregation suite, which is amendment A6's
central finding, so this milestone has to bring its own. The hazard in a corpus
we author is obvious and fatal: it can encode our own bugs as expectations and
then agree with us forever. So the split is enforced by the tooling.
`sources/*.json` holds documents and pipelines and nothing else; `record.js`
asks a real mongod 8.3.7 what each pipeline answers and writes the unified-
format file from the reply. Inputs authored, expectations measured -- the
discipline that corrected three assumptions in M1's session work and every
error code in M2, where the alternative would have shipped both times.

No second runner. `run.js --suite-dir` points the existing one somewhere else,
so the entity model, the matchers, the skip accounting and `expectEvents` come
for free; a second runner would drift from the first exactly where it mattered.
`--scorecard` is refused with `--suite-dir`, because `scorecard.txt` is the crud
corpus's record and the milestones are compared against it -- writing it from an
unrelated run would replace that record silently.

Errors record the code and not the message: message text is mongod's to change
between releases. Group pipelines end in a `$sort`, because group output order
is unspecified and a case depending on it would fail for the wrong reason on
either server.

The first source covers `$group`: nine accumulators including the edge cases
that decide an implementation -- `$avg` over a group whose values are not
numbers, `$min` of a field no document has, `$push` skipping a missing field,
`$first`/`$last` against input order, grouping on an array, a compound `_id`.

Where it starts, run against the M2 tip:

    group-accumulators.json    9 pass   10 fail   0 skip

The nine include the four refusals M2 added, which answer with mongod's own
codes -- so the corpus already confirms that half. The ten are the milestone.
The crud corpus is unchanged at 201/90/196.
This commit is contained in:
A.Shakhmatov
2026-08-09 21:59:59 +03:00
parent 8ebeb9d4ec
commit 3044a38d1c
5 changed files with 1117 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

807
tests/spec/aggregate/group-accumulators.json Normal file
View File

@@ -0,0 +1,807 @@
{
"description": "group-accumulators",
"schemaVersion": "1.4",
"createEntities": [
{
"client": {
"id": "client0"
}
},
{
"database": {
"id": "database0",
"client": "client0",
"databaseName": "aggregate-corpus"
}
},
{
"collection": {
"id": "collection0",
"database": "database0",
"collectionName": "coll"
}
}
],
"initialData": [
{
"collectionName": "coll",
"databaseName": "aggregate-corpus",
"documents": [
{
"_id": 1,
"g": "a",
"x": 10,
"s": "p",
"t": [
1,
2
]
},
{
"_id": 2,
"g": "a",
"x": 20,
"s": "q",
"t": [
2,
3
]
},
{
"_id": 3,
"g": "b",
"x": 30,
"s": "p",
"t": []
},
{
"_id": 4,
"g": "b",
"x": 7,
"s": "r"
},
{
"_id": 5,
"g": "b",
"x": "not a number",
"s": "p",
"t": [
4
]
}
]
}
],
"tests": [
{
"description": "$sum over a field path",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$group": {
"_id": "$g",
"v": {
"$sum": "$x"
}
}
},
{
"$sort": {
"_id": 1
}
}
]
},
"expectResult": [
{
"_id": "a",
"v": 30
},
{
"_id": "b",
"v": 37
}
]
}
]
},
{
"description": "$sum counts with a constant",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$group": {
"_id": "$g",
"v": {
"$sum": 1
}
}
},
{
"$sort": {
"_id": 1
}
}
]
},
"expectResult": [
{
"_id": "a",
"v": 2
},
{
"_id": "b",
"v": 3
}
]
}
]
},
{
"description": "$avg ignores non-numeric values",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$group": {
"_id": "$g",
"v": {
"$avg": "$x"
}
}
},
{
"$sort": {
"_id": 1
}
}
]
},
"expectResult": [
{
"_id": "a",
"v": 15
},
{
"_id": "b",
"v": 18.5
}
]
}
]
},
{
"description": "$avg of a group with no numeric value at all",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$group": {
"_id": "$s",
"v": {
"$avg": "$missing"
}
}
},
{
"$sort": {
"_id": 1
}
}
]
},
"expectResult": [
{
"_id": "p",
"v": null
},
{
"_id": "q",
"v": null
},
{
"_id": "r",
"v": null
}
]
}
]
},
{
"description": "$min and $max compare across types",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$group": {
"_id": "$g",
"lo": {
"$min": "$x"
},
"hi": {
"$max": "$x"
}
}
},
{
"$sort": {
"_id": 1
}
}
]
},
"expectResult": [
{
"_id": "a",
"lo": 10,
"hi": 20
},
{
"_id": "b",
"lo": 7,
"hi": "not a number"
}
]
}
]
},
{
"description": "$min of a field no document has",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$group": {
"_id": "$g",
"v": {
"$min": "$missing"
}
}
},
{
"$sort": {
"_id": 1
}
}
]
},
"expectResult": [
{
"_id": "a",
"v": null
},
{
"_id": "b",
"v": null
}
]
}
]
},
{
"description": "$first and $last follow the input order",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$sort": {
"_id": 1
}
},
{
"$group": {
"_id": "$g",
"f": {
"$first": "$x"
},
"l": {
"$last": "$x"
}
}
},
{
"$sort": {
"_id": 1
}
}
]
},
"expectResult": [
{
"_id": "a",
"f": 10,
"l": 20
},
{
"_id": "b",
"f": 30,
"l": "not a number"
}
]
}
]
},
{
"description": "$push keeps duplicates and order",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$sort": {
"_id": 1
}
},
{
"$group": {
"_id": "$s",
"v": {
"$push": "$g"
}
}
},
{
"$sort": {
"_id": 1
}
}
]
},
"expectResult": [
{
"_id": "p",
"v": [
"a",
"b",
"b"
]
},
{
"_id": "q",
"v": [
"a"
]
},
{
"_id": "r",
"v": [
"b"
]
}
]
}
]
},
{
"description": "$push of a missing field skips it",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$sort": {
"_id": 1
}
},
{
"$group": {
"_id": "$g",
"v": {
"$push": "$t"
}
}
},
{
"$sort": {
"_id": 1
}
}
]
},
"expectResult": [
{
"_id": "a",
"v": [
[
1,
2
],
[
2,
3
]
]
},
{
"_id": "b",
"v": [
[],
[
4
]
]
}
]
}
]
},
{
"description": "$addToSet drops duplicates",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$group": {
"_id": "$s",
"v": {
"$addToSet": "$g"
}
}
},
{
"$sort": {
"_id": 1
}
}
]
},
"expectResult": [
{
"_id": "p",
"v": [
"a",
"b"
]
},
{
"_id": "q",
"v": [
"a"
]
},
{
"_id": "r",
"v": [
"b"
]
}
]
}
]
},
{
"description": "$count is the number of documents in the group",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$group": {
"_id": "$g",
"v": {
"$count": {}
}
}
},
{
"$sort": {
"_id": 1
}
}
]
},
"expectResult": [
{
"_id": "a",
"v": 2
},
{
"_id": "b",
"v": 3
}
]
}
]
},
{
"description": "a compound _id groups on every field",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$group": {
"_id": {
"g": "$g",
"s": "$s"
},
"n": {
"$sum": 1
}
}
},
{
"$sort": {
"_id.g": 1,
"_id.s": 1
}
}
]
},
"expectResult": [
{
"_id": {
"g": "a",
"s": "p"
},
"n": 1
},
{
"_id": {
"g": "a",
"s": "q"
},
"n": 1
},
{
"_id": {
"g": "b",
"s": "p"
},
"n": 2
},
{
"_id": {
"g": "b",
"s": "r"
},
"n": 1
}
]
}
]
},
{
"description": "a constant _id puts everything in one group",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$group": {
"_id": null,
"n": {
"$sum": 1
}
}
}
]
},
"expectResult": [
{
"_id": null,
"n": 5
}
]
}
]
},
{
"description": "an _id path that no document has",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$group": {
"_id": "$missing",
"n": {
"$sum": 1
}
}
}
]
},
"expectResult": [
{
"_id": null,
"n": 5
}
]
}
]
},
{
"description": "grouping on an array field",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$group": {
"_id": "$t",
"n": {
"$sum": 1
}
}
},
{
"$sort": {
"_id": 1
}
}
]
},
"expectResult": [
{
"_id": null,
"n": 1
},
{
"_id": [],
"n": 1
},
{
"_id": [
1,
2
],
"n": 1
},
{
"_id": [
2,
3
],
"n": 1
},
{
"_id": [
4
],
"n": 1
}
]
}
]
},
{
"description": "an unknown accumulator is refused",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$group": {
"_id": "$g",
"v": {
"$bogusAcc": "$x"
}
}
}
]
},
"expectError": {
"isError": true,
"errorCode": 15952
}
}
]
},
{
"description": "an accumulator that is not a document is refused",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$group": {
"_id": "$g",
"v": "$x"
}
}
]
},
"expectError": {
"isError": true,
"errorCode": 40234
}
}
]
},
{
"description": "two accumulators in one field are refused",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$group": {
"_id": "$g",
"v": {
"$sum": "$x",
"$max": "$x"
}
}
}
]
},
"expectError": {
"isError": true,
"errorCode": 40238
}
}
]
},
{
"description": "a $group without _id is refused",
"operations": [
{
"object": "collection0",
"name": "aggregate",
"arguments": {
"pipeline": [
{
"$group": {
"n": {
"$sum": 1
}
}
}
]
},
"expectError": {
"isError": true,
"errorCode": 15955
}
}
]
}
]
}