mirror of
https://github.com/quickwit-oss/tantivy.git
synced 2026-01-04 08:12:54 +00:00
Compare commits
11 Commits
tagged-use
...
release_0.
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
eb37dbee26 | ||
|
|
c6e77d27c6 | ||
|
|
db6587ed9b | ||
|
|
3fa90e70e2 | ||
|
|
6ab4102253 | ||
|
|
11c6329ca5 | ||
|
|
ab8bb93928 | ||
|
|
2b668bd2bf | ||
|
|
97a7137ef8 | ||
|
|
ffa7cdf397 | ||
|
|
caf1275e60 |
@@ -7,6 +7,8 @@ Tantivy 0.23 will be backwards compatible with indices created with v0.22 and v0
|
||||
- fix bug that causes out-of-order sstable key. [#2445](https://github.com/quickwit-oss/tantivy/pull/2445)(@fulmicoton)
|
||||
- fix ReferenceValue API flaw [#2372](https://github.com/quickwit-oss/tantivy/pull/2372)(@PSeitz)
|
||||
- fix `OwnedBytes` debug panic [#2512](https://github.com/quickwit-oss/tantivy/pull/2512)(@b41sh)
|
||||
- catch panics during merges [#2582](https://github.com/quickwit-oss/tantivy/pull/2582)(@rdettai)
|
||||
- switch from u32 to usize in bitpacker. This enables multivalued columns larger than 4GB, which crashed during merge before. [#2581](https://github.com/quickwit-oss/tantivy/pull/2581) [#2586](https://github.com/quickwit-oss/tantivy/pull/2586)(@fulmicoton-dd @PSeitz)
|
||||
|
||||
#### Breaking API Changes
|
||||
- remove index sorting [#2434](https://github.com/quickwit-oss/tantivy/pull/2434)(@PSeitz)
|
||||
@@ -24,6 +26,7 @@ Tantivy 0.23 will be backwards compatible with indices created with v0.22 and v0
|
||||
- reduce top hits memory consumption [#2426](https://github.com/quickwit-oss/tantivy/pull/2426)(@PSeitz)
|
||||
- check unsupported parameters top_hits [#2351](https://github.com/quickwit-oss/tantivy/pull/2351)(@PSeitz)
|
||||
- Change AggregationLimits to AggregationLimitsGuard [#2495](https://github.com/quickwit-oss/tantivy/pull/2495)(@PSeitz)
|
||||
- add support for counting non integer in aggregation [#2547](https://github.com/quickwit-oss/tantivy/pull/2547)(@trinity-1686a)
|
||||
- **Range Queries**
|
||||
- Support fast field range queries on json fields [#2456](https://github.com/quickwit-oss/tantivy/pull/2456)(@PSeitz)
|
||||
- Add support for str fast field range query [#2460](https://github.com/quickwit-oss/tantivy/pull/2460) [#2452](https://github.com/quickwit-oss/tantivy/pull/2452) [#2453](https://github.com/quickwit-oss/tantivy/pull/2453)(@PSeitz)
|
||||
@@ -34,7 +37,8 @@ Tantivy 0.23 will be backwards compatible with indices created with v0.22 and v0
|
||||
- add columnar format compatibility tests [#2433](https://github.com/quickwit-oss/tantivy/pull/2433)(@PSeitz)
|
||||
- Improved snippet ranges algorithm [#2474](https://github.com/quickwit-oss/tantivy/pull/2474)(@gezihuzi)
|
||||
- make find_field_with_default return json fields without path [#2476](https://github.com/quickwit-oss/tantivy/pull/2476)(@trinity-1686a)
|
||||
- feat(query): Make `BooleanQuery` support `minimum_number_should_match` [#2405](https://github.com/quickwit-oss/tantivy/pull/2405)(@LebranceBW)
|
||||
- Make `BooleanQuery` support `minimum_number_should_match` [#2405](https://github.com/quickwit-oss/tantivy/pull/2405)(@LebranceBW)
|
||||
- Make `NUM_MERGE_THREADS` configurable [#2535](https://github.com/quickwit-oss/tantivy/pull/2535)(@Barre)
|
||||
|
||||
- **RegexPhraseQuery**
|
||||
`RegexPhraseQuery` supports phrase queries with regex. E.g. query "b.* b.* wolf" matches "big bad wolf". Slop is supported as well: "b.* wolf"~2 matches "big bad wolf" [#2516](https://github.com/quickwit-oss/tantivy/pull/2516)(@PSeitz)
|
||||
@@ -60,7 +64,9 @@ This will slightly increase space and access time. [#2439](https://github.com/qu
|
||||
- fix de-escaping too much in query parser [#2427](https://github.com/quickwit-oss/tantivy/pull/2427)(@trinity-1686a)
|
||||
- improve query parser [#2416](https://github.com/quickwit-oss/tantivy/pull/2416)(@trinity-1686a)
|
||||
- Support field grouping `title:(return AND "pink panther")` [#2333](https://github.com/quickwit-oss/tantivy/pull/2333)(@trinity-1686a)
|
||||
- allow term starting with wildcard [#2568](https://github.com/quickwit-oss/tantivy/pull/2568)(@trinity-1686a)
|
||||
|
||||
- Exist queries match subpath fields [#2558](https://github.com/quickwit-oss/tantivy/pull/2558)(@rdettai)
|
||||
- add access benchmark for columnar [#2432](https://github.com/quickwit-oss/tantivy/pull/2432)(@PSeitz)
|
||||
- extend indexwriter proptests [#2342](https://github.com/quickwit-oss/tantivy/pull/2342)(@PSeitz)
|
||||
- add bench & test for columnar merging [#2428](https://github.com/quickwit-oss/tantivy/pull/2428)(@PSeitz)
|
||||
|
||||
18
Cargo.toml
18
Cargo.toml
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "tantivy"
|
||||
version = "0.23.0"
|
||||
version = "0.24.1"
|
||||
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
|
||||
license = "MIT"
|
||||
categories = ["database-implementations", "data-structures"]
|
||||
@@ -11,7 +11,7 @@ repository = "https://github.com/quickwit-oss/tantivy"
|
||||
readme = "README.md"
|
||||
keywords = ["search", "information", "retrieval"]
|
||||
edition = "2021"
|
||||
rust-version = "1.75"
|
||||
rust-version = "1.81"
|
||||
exclude = ["benches/*.json", "benches/*.txt"]
|
||||
|
||||
[dependencies]
|
||||
@@ -57,13 +57,13 @@ measure_time = "0.9.0"
|
||||
arc-swap = "1.5.0"
|
||||
bon = "3.3.1"
|
||||
|
||||
columnar = { version = "0.3", path = "./columnar", package = "tantivy-columnar" }
|
||||
sstable = { version = "0.3", path = "./sstable", package = "tantivy-sstable", optional = true }
|
||||
stacker = { version = "0.3", path = "./stacker", package = "tantivy-stacker" }
|
||||
query-grammar = { version = "0.23.0", path = "./query-grammar", package = "tantivy-query-grammar" }
|
||||
tantivy-bitpacker = { version = "0.6", path = "./bitpacker" }
|
||||
common = { version = "0.7", path = "./common/", package = "tantivy-common" }
|
||||
tokenizer-api = { version = "0.3", path = "./tokenizer-api", package = "tantivy-tokenizer-api" }
|
||||
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" }
|
||||
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 }
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "tantivy-bitpacker"
|
||||
version = "0.6.0"
|
||||
version = "0.8.0"
|
||||
edition = "2021"
|
||||
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
|
||||
license = "MIT"
|
||||
|
||||
@@ -16,14 +16,14 @@ body = """
|
||||
|
||||
{%- if version %} in {{ version }}{%- endif -%}
|
||||
{% for commit in commits %}
|
||||
{% if commit.github.pr_title -%}
|
||||
{%- set commit_message = commit.github.pr_title -%}
|
||||
{% if commit.remote.pr_title -%}
|
||||
{%- set commit_message = commit.remote.pr_title -%}
|
||||
{%- else -%}
|
||||
{%- set commit_message = commit.message -%}
|
||||
{%- endif -%}
|
||||
- {{ commit_message | split(pat="\n") | first | trim }}\
|
||||
{% if commit.github.pr_number %} \
|
||||
[#{{ commit.github.pr_number }}]({{ self::remote_url() }}/pull/{{ commit.github.pr_number }}){% if commit.github.username %}(@{{ commit.github.username }}){%- endif -%} \
|
||||
{% if commit.remote.pr_number %} \
|
||||
[#{{ commit.remote.pr_number }}]({{ self::remote_url() }}/pull/{{ commit.remote.pr_number }}){% if commit.remote.username %}(@{{ commit.remote.username }}){%- endif -%} \
|
||||
{%- endif %}
|
||||
{%- endfor -%}
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "tantivy-columnar"
|
||||
version = "0.3.0"
|
||||
version = "0.5.0"
|
||||
edition = "2021"
|
||||
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= "0.3", path = "../stacker", package="tantivy-stacker"}
|
||||
sstable = { version= "0.3", path = "../sstable", package = "tantivy-sstable" }
|
||||
common = { version= "0.7", path = "../common", package = "tantivy-common" }
|
||||
tantivy-bitpacker = { version= "0.6", path = "../bitpacker/" }
|
||||
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/" }
|
||||
serde = "1.0.152"
|
||||
downcast-rs = "2.0.1"
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "tantivy-common"
|
||||
version = "0.7.0"
|
||||
version = "0.9.0"
|
||||
authors = ["Paul Masurel <paul@quickwit.io>", "Pascal Seitz <pascal@quickwit.io>"]
|
||||
license = "MIT"
|
||||
edition = "2021"
|
||||
@@ -13,7 +13,7 @@ repository = "https://github.com/quickwit-oss/tantivy"
|
||||
|
||||
[dependencies]
|
||||
byteorder = "1.4.3"
|
||||
ownedbytes = { version= "0.7", path="../ownedbytes" }
|
||||
ownedbytes = { version= "0.9", path="../ownedbytes" }
|
||||
async-trait = "0.1"
|
||||
time = { version = "0.3.10", features = ["serde-well-known"] }
|
||||
serde = { version = "1.0.136", features = ["derive"] }
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
[package]
|
||||
authors = ["Paul Masurel <paul@quickwit.io>", "Pascal Seitz <pascal@quickwit.io>"]
|
||||
name = "ownedbytes"
|
||||
version = "0.7.0"
|
||||
version = "0.9.0"
|
||||
edition = "2021"
|
||||
description = "Expose data as static slice"
|
||||
license = "MIT"
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "tantivy-query-grammar"
|
||||
version = "0.23.0"
|
||||
version = "0.24.0"
|
||||
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
|
||||
license = "MIT"
|
||||
categories = ["database-implementations", "data-structures"]
|
||||
|
||||
@@ -39,7 +39,7 @@ mod tests {
|
||||
let json = serde_json::to_string(&ast).unwrap();
|
||||
assert_eq!(
|
||||
json,
|
||||
r#"{"clause":[["should",{"type":"literal","field_name":"title","phrase":"hello","delimiter":"none","slop":0,"prefix":false}],["should",{"type":"literal","field_name":"title","phrase":"x","delimiter":"none","slop":0,"prefix":false}]]}"#
|
||||
r#"{"type":"bool","clauses":[["should",{"type":"literal","field_name":"title","phrase":"hello","delimiter":"none","slop":0,"prefix":false}],["should",{"type":"literal","field_name":"title","phrase":"x","delimiter":"none","slop":0,"prefix":false}]]}"#
|
||||
);
|
||||
}
|
||||
|
||||
|
||||
@@ -206,8 +206,8 @@ pub enum UserInputAst {
|
||||
#[derive(Serialize)]
|
||||
#[serde(tag = "type", rename_all = "snake_case")]
|
||||
enum UserInputAstSerde {
|
||||
Clause {
|
||||
clause: Vec<(Option<Occur>, UserInputAst)>,
|
||||
Bool {
|
||||
clauses: Vec<(Option<Occur>, UserInputAst)>,
|
||||
},
|
||||
Boost {
|
||||
underlying: Box<UserInputAst>,
|
||||
@@ -220,7 +220,7 @@ enum UserInputAstSerde {
|
||||
impl From<UserInputAst> for UserInputAstSerde {
|
||||
fn from(ast: UserInputAst) -> Self {
|
||||
match ast {
|
||||
UserInputAst::Clause(clause) => UserInputAstSerde::Clause { clause },
|
||||
UserInputAst::Clause(clause) => UserInputAstSerde::Bool { clauses: clause },
|
||||
UserInputAst::Boost(underlying, boost) => {
|
||||
UserInputAstSerde::Boost { underlying, boost }
|
||||
}
|
||||
@@ -414,7 +414,7 @@ mod tests {
|
||||
let json = serde_json::to_string(&boost_ast).unwrap();
|
||||
assert_eq!(
|
||||
json,
|
||||
r#"{"type":"boost","underlying":{"type":"clause","clause":[["must",{"type":"all"}],["should",{"type":"literal","field_name":"title","phrase":"hello","delimiter":"none","slop":0,"prefix":false}]]},"boost":2.5}"#
|
||||
r#"{"type":"boost","underlying":{"type":"bool","clauses":[["must",{"type":"all"}],["should",{"type":"literal","field_name":"title","phrase":"hello","delimiter":"none","slop":0,"prefix":false}]]},"boost":2.5}"#
|
||||
);
|
||||
}
|
||||
|
||||
@@ -439,7 +439,7 @@ mod tests {
|
||||
let json = serde_json::to_string(&clause).unwrap();
|
||||
assert_eq!(
|
||||
json,
|
||||
r#"{"type":"clause","clause":[["must",{"type":"all"}],["should",{"type":"literal","field_name":"title","phrase":"hello","delimiter":"none","slop":0,"prefix":false}]]}"#
|
||||
r#"{"type":"bool","clauses":[["must",{"type":"all"}],["should",{"type":"literal","field_name":"title","phrase":"hello","delimiter":"none","slop":0,"prefix":false}]]}"#
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -41,16 +41,12 @@ impl Executor {
|
||||
///
|
||||
/// Regardless of the executor (`SingleThread` or `ThreadPool`), panics in the task
|
||||
/// will propagate to the caller.
|
||||
pub fn map<
|
||||
pub fn map<A, R, F>(&self, f: F, args: impl Iterator<Item = A>) -> crate::Result<Vec<R>>
|
||||
where
|
||||
A: Send,
|
||||
R: Send,
|
||||
AIterator: Iterator<Item = A>,
|
||||
F: Sized + Sync + Fn(A) -> crate::Result<R>,
|
||||
>(
|
||||
&self,
|
||||
f: F,
|
||||
args: AIterator,
|
||||
) -> crate::Result<Vec<R>> {
|
||||
{
|
||||
match self {
|
||||
Executor::SingleThread => args.map(f).collect::<crate::Result<_>>(),
|
||||
Executor::ThreadPool(pool) => {
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "tantivy-sstable"
|
||||
version = "0.3.0"
|
||||
version = "0.5.0"
|
||||
edition = "2021"
|
||||
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= "0.7", path="../common", package="tantivy-common"}
|
||||
common = {version= "0.9", path="../common", package="tantivy-common"}
|
||||
futures-util = "0.3.30"
|
||||
itertools = "0.14.0"
|
||||
tantivy-bitpacker = { version= "0.6", path="../bitpacker" }
|
||||
tantivy-bitpacker = { version= "0.8", path="../bitpacker" }
|
||||
tantivy-fst = "0.5"
|
||||
# experimental gives us access to Decompressor::upper_bound
|
||||
zstd = { version = "0.13", features = ["experimental"] }
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "tantivy-stacker"
|
||||
version = "0.3.0"
|
||||
version = "0.5.0"
|
||||
edition = "2021"
|
||||
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 = "0.7", path = "../common/", package = "tantivy-common" }
|
||||
common = { version = "0.9", path = "../common/", package = "tantivy-common" }
|
||||
ahash = { version = "0.8.11", default-features = false, optional = true }
|
||||
rand_distr = "0.4.3"
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "tantivy-tokenizer-api"
|
||||
version = "0.3.0"
|
||||
version = "0.5.0"
|
||||
license = "MIT"
|
||||
edition = "2021"
|
||||
description = "Tokenizer API of tantivy"
|
||||
|
||||
Reference in New Issue
Block a user