Compare commits

...

3 Commits

Author SHA1 Message Date
Paul Masurel
1b38a9ba62 Added unit test for aggregation 2025-08-28 12:19:22 +02:00
PSeitz-dd
c37af9c1ff update release instructions (#2687) 2025-08-22 07:57:48 +08:00
PSeitz
33794a114c chore: Release (#2686)
Co-authored-by: Pascal Seitz <pascal.seitz@datadoghq.com>
2025-08-20 18:29:37 +08:00
10 changed files with 74 additions and 35 deletions

View File

@@ -1,6 +1,6 @@
[package]
name = "tantivy"
version = "0.24.0"
version = "0.25.0"
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
license = "MIT"
categories = ["database-implementations", "data-structures"]
@@ -57,13 +57,13 @@ measure_time = "0.9.0"
arc-swap = "1.5.0"
bon = "3.3.1"
columnar = { version = "0.5", path = "./columnar", package = "tantivy-columnar" }
sstable = { version = "0.5", path = "./sstable", package = "tantivy-sstable", optional = true }
stacker = { version = "0.5", path = "./stacker", package = "tantivy-stacker" }
query-grammar = { version = "0.24.0", path = "./query-grammar", package = "tantivy-query-grammar" }
tantivy-bitpacker = { version = "0.8", path = "./bitpacker" }
common = { version = "0.9", path = "./common/", package = "tantivy-common" }
tokenizer-api = { version = "0.5", path = "./tokenizer-api", package = "tantivy-tokenizer-api" }
columnar = { version = "0.6", path = "./columnar", package = "tantivy-columnar" }
sstable = { version = "0.6", path = "./sstable", package = "tantivy-sstable", optional = true }
stacker = { version = "0.6", path = "./stacker", package = "tantivy-stacker" }
query-grammar = { version = "0.25.0", path = "./query-grammar", package = "tantivy-query-grammar" }
tantivy-bitpacker = { version = "0.9", path = "./bitpacker" }
common = { version = "0.10", path = "./common/", package = "tantivy-common" }
tokenizer-api = { version = "0.6", path = "./tokenizer-api", package = "tantivy-tokenizer-api" }
sketches-ddsketch = { version = "0.3.0", features = ["use_serde"] }
hyperloglogplus = { version = "0.4.1", features = ["const-loop"] }
futures-util = { version = "0.3.28", optional = true }

View File

@@ -1,4 +1,4 @@
# Release a new Tantivy Version
# Releasing a new Tantivy Version
## Steps
@@ -10,12 +10,29 @@
6. Set git tag with new version
In conjucation with `cargo-release` Steps 1-4 (I'm not sure if the change detection works):
Set new packages to version 0.0.0
[`cargo-release`](https://github.com/crate-ci/cargo-release) will help us with steps 1-5:
Replace prev-tag-name
```bash
cargo release --workspace --no-publish -v --prev-tag-name 0.19 --push-remote origin minor --no-tag --execute
cargo release --workspace --no-publish -v --prev-tag-name 0.24 --push-remote origin minor --no-tag
```
no-tag or it will create tags for all the subpackages
`no-tag` or it will create tags for all the subpackages
cargo release will _not_ ignore unchanged packages, but it will print warnings for them.
e.g. "warning: updating ownedbytes to 0.10.0 despite no changes made since tag 0.24"
We need to manually ignore these unchanged packages
```bash
cargo release --workspace --no-publish -v --prev-tag-name 0.24 --push-remote origin minor --no-tag --exclude tokenizer-api
```
Add `--execute` to actually publish the packages, otherwise it will only print the commands that would be run.
### Tag Version
```bash
git tag 0.25.0
git push upstream tag 0.25.0
```

View File

@@ -1,6 +1,6 @@
[package]
name = "tantivy-bitpacker"
version = "0.8.0"
version = "0.9.0"
edition = "2024"
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
license = "MIT"

View File

@@ -1,6 +1,6 @@
[package]
name = "tantivy-columnar"
version = "0.5.0"
version = "0.6.0"
edition = "2024"
license = "MIT"
homepage = "https://github.com/quickwit-oss/tantivy"
@@ -12,10 +12,10 @@ categories = ["database-implementations", "data-structures", "compression"]
itertools = "0.14.0"
fastdivide = "0.4.0"
stacker = { version= "0.5", path = "../stacker", package="tantivy-stacker"}
sstable = { version= "0.5", path = "../sstable", package = "tantivy-sstable" }
common = { version= "0.9", path = "../common", package = "tantivy-common" }
tantivy-bitpacker = { version= "0.8", path = "../bitpacker/" }
stacker = { version= "0.6", path = "../stacker", package="tantivy-stacker"}
sstable = { version= "0.6", path = "../sstable", package = "tantivy-sstable" }
common = { version= "0.10", path = "../common", package = "tantivy-common" }
tantivy-bitpacker = { version= "0.9", path = "../bitpacker/" }
serde = "1.0.152"
downcast-rs = "2.0.1"

View File

@@ -1,6 +1,6 @@
[package]
name = "tantivy-common"
version = "0.9.0"
version = "0.10.0"
authors = ["Paul Masurel <paul@quickwit.io>", "Pascal Seitz <pascal@quickwit.io>"]
license = "MIT"
edition = "2024"

View File

@@ -1,6 +1,6 @@
[package]
name = "tantivy-query-grammar"
version = "0.24.0"
version = "0.25.0"
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
license = "MIT"
categories = ["database-implementations", "data-structures"]

View File

@@ -155,7 +155,7 @@ fn test_aggregation_flushing(
searcher.search(&AllQuery, &collector).unwrap()
};
let res: Value = serde_json::from_str(&serde_json::to_string(&agg_res)?)?;
let res: Value = serde_json::to_value(&agg_res)?;
assert_eq!(res["bucketsL1"]["buckets"][0]["doc_count"], 3);
assert_eq!(
@@ -270,7 +270,7 @@ fn test_aggregation_level1_simple() -> crate::Result<()> {
let searcher = reader.searcher();
let agg_res: AggregationResults = searcher.search(&term_query, &collector).unwrap();
let res: Value = serde_json::from_str(&serde_json::to_string(&agg_res)?)?;
let res: Value = serde_json::to_value(&agg_res)?;
assert_eq!(res["average"]["value"], 12.142857142857142);
assert_eq!(
res["range"]["buckets"],
@@ -304,6 +304,29 @@ fn test_aggregation_level1_simple() -> crate::Result<()> {
Ok(())
}
#[test]
fn test_aggregation_term_truncate_sum_other_doc_count() {
let index = get_test_index_2_segments(true).unwrap();
let reader = index.reader().unwrap();
let count_per_text: Aggregation = serde_json::from_value(json!({ "terms": { "field": "text", "size": 1 } })).unwrap();
let aggs: Aggregations = vec![("group_by_term_truncate".to_string(), count_per_text)]
.into_iter()
.collect();
let collector = get_collector(aggs);
let searcher = reader.searcher();
let agg_res: AggregationResults = searcher.search(&AllQuery, &collector).unwrap();
let res: Value = serde_json::to_value(&agg_res).unwrap();
assert_eq!(res, serde_json::json!({
"group_by_term_truncate": {
"buckets": [{ "doc_count": 7, "key": "cool" }],
"doc_count_error_upper_bound": 0,
"sum_other_doc_count": 2,
},
}));
}
#[test]
fn test_aggregation_level1() -> crate::Result<()> {
let index = get_test_index_2_segments(true)?;
@@ -342,7 +365,7 @@ fn test_aggregation_level1() -> crate::Result<()> {
let searcher = reader.searcher();
let agg_res: AggregationResults = searcher.search(&term_query, &collector).unwrap();
let res: Value = serde_json::from_str(&serde_json::to_string(&agg_res)?)?;
let res: Value = serde_json::to_value(&agg_res)?;
assert_eq!(res["average"]["value"], 12.142857142857142);
assert_eq!(res["average_f64"]["value"], 12.214285714285714);
assert_eq!(res["average_i64"]["value"], 12.142857142857142);
@@ -397,7 +420,7 @@ fn test_aggregation_level2(
IndexRecordOption::Basic,
);
let elasticsearch_compatible_json_req = r#"
let elasticsearch_compatible_json_req = serde_json::json!(
{
"rangef64": {
"range": {
@@ -450,9 +473,8 @@ fn test_aggregation_level2(
"term_agg": { "terms": { "field": "text" } }
}
}
}
"#;
let agg_req: Aggregations = serde_json::from_str(elasticsearch_compatible_json_req).unwrap();
});
let agg_req: Aggregations = serde_json::from_value(elasticsearch_compatible_json_req).unwrap();
let agg_res: AggregationResults = if use_distributed_collector {
let collector =
@@ -469,7 +491,7 @@ fn test_aggregation_level2(
searcher.search(&term_query, &collector).unwrap()
};
let res: Value = serde_json::from_str(&serde_json::to_string(&agg_res)?)?;
let res: Value = serde_json::to_value(agg_res)?;
assert_eq!(res["range"]["buckets"][1]["key"], "3-7");
assert_eq!(res["range"]["buckets"][1]["doc_count"], 2u64);

View File

@@ -1,6 +1,6 @@
[package]
name = "tantivy-sstable"
version = "0.5.0"
version = "0.6.0"
edition = "2024"
license = "MIT"
homepage = "https://github.com/quickwit-oss/tantivy"
@@ -10,10 +10,10 @@ categories = ["database-implementations", "data-structures", "compression"]
description = "sstables for tantivy"
[dependencies]
common = {version= "0.9", path="../common", package="tantivy-common"}
common = {version= "0.10", path="../common", package="tantivy-common"}
futures-util = "0.3.30"
itertools = "0.14.0"
tantivy-bitpacker = { version= "0.8", path="../bitpacker" }
tantivy-bitpacker = { version= "0.9", path="../bitpacker" }
tantivy-fst = "0.5"
# experimental gives us access to Decompressor::upper_bound
zstd = { version = "0.13", optional = true, features = ["experimental"] }

View File

@@ -1,6 +1,6 @@
[package]
name = "tantivy-stacker"
version = "0.5.0"
version = "0.6.0"
edition = "2024"
license = "MIT"
homepage = "https://github.com/quickwit-oss/tantivy"
@@ -9,7 +9,7 @@ description = "term hashmap used for indexing"
[dependencies]
murmurhash32 = "0.3"
common = { version = "0.9", path = "../common/", package = "tantivy-common" }
common = { version = "0.10", path = "../common/", package = "tantivy-common" }
ahash = { version = "0.8.11", default-features = false, optional = true }
rand_distr = "0.4.3"

View File

@@ -1,6 +1,6 @@
[package]
name = "tantivy-tokenizer-api"
version = "0.5.0"
version = "0.6.0"
license = "MIT"
edition = "2021"
description = "Tokenizer API of tantivy"