mirror of
https://github.com/quickwit-oss/tantivy.git
synced 2026-01-06 09:12:55 +00:00
923f0508f2
* seek_exact + cost based intersection Adds `seek_exact` and `cost` to `DocSet` for a more efficient intersection. Unlike `seek`, `seek_exact` does not require the DocSet to advance to the next hit, if the target does not exist. `cost` allows to address the different DocSet types and their cost model and is used to determine the DocSet that drives the intersection. E.g. fast field range queries may do a full scan. Phrase queries load the positions to check if a we have a hit. They both have a higher cost than their size_hint would suggest. Improves `size_hint` estimation for intersection and union, by having a estimation based on random distribution with a co-location factor. Refactor range query benchmark. Closes #2531 *Future Work* Implement `seek_exact` for BufferedUnionScorer and RangeDocSet (fast field range queries) Evaluate replacing `seek` with `seek_exact` to reduce code complexity * Apply suggestions from code review Co-authored-by: Paul Masurel <paul@quickwit.io> * add API contract verfication * impl seek_exact on union * rename seek_exact * add mixed AND OR test, fix buffered_union * Add a proptest of BooleanQuery. (#2690) * fix build * Increase the document count. * fix merge conflict * fix debug assert * Fix compilation errors after rebase - Remove duplicate proptest_boolean_query module - Remove duplicate cost() method implementations - Fix TopDocs API usage (add .order_by_score()) - Remove duplicate imports - Remove unused variable assignments --------- Co-authored-by: Paul Masurel <paul@quickwit.io> Co-authored-by: Pascal Seitz <pascal.seitz@datadoghq.com> Co-authored-by: Stu Hood <stuhood@gmail.com>
187 lines
4.9 KiB
TOML
187 lines
4.9 KiB
TOML
[package]
|
|
name = "tantivy"
|
|
version = "0.26.0"
|
|
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
|
|
license = "MIT"
|
|
categories = ["database-implementations", "data-structures"]
|
|
description = """Search engine library"""
|
|
documentation = "https://docs.rs/tantivy/"
|
|
homepage = "https://github.com/quickwit-oss/tantivy"
|
|
repository = "https://github.com/quickwit-oss/tantivy"
|
|
readme = "README.md"
|
|
keywords = ["search", "information", "retrieval"]
|
|
edition = "2021"
|
|
rust-version = "1.85"
|
|
exclude = ["benches/*.json", "benches/*.txt"]
|
|
|
|
[dependencies]
|
|
oneshot = "0.1.7"
|
|
base64 = "0.22.0"
|
|
byteorder = "1.4.3"
|
|
crc32fast = "1.3.2"
|
|
once_cell = "1.10.0"
|
|
regex = { version = "1.5.5", default-features = false, features = [
|
|
"std",
|
|
"unicode",
|
|
] }
|
|
aho-corasick = "1.0"
|
|
tantivy-fst = "0.5"
|
|
memmap2 = { version = "0.9.0", optional = true }
|
|
lz4_flex = { version = "0.11", default-features = false, optional = true }
|
|
zstd = { version = "0.13", optional = true, default-features = false }
|
|
tempfile = { version = "3.12.0", optional = true }
|
|
log = "0.4.16"
|
|
serde = { version = "1.0.219", features = ["derive"] }
|
|
serde_json = "1.0.140"
|
|
fs4 = { version = "0.13.1", optional = true }
|
|
levenshtein_automata = "0.2.1"
|
|
uuid = { version = "1.0.0", features = ["v4", "serde"] }
|
|
crossbeam-channel = "0.5.4"
|
|
rust-stemmers = "1.2.0"
|
|
downcast-rs = "2.0.1"
|
|
bitpacking = { version = "0.9.2", default-features = false, features = [
|
|
"bitpacker4x",
|
|
] }
|
|
census = "0.4.2"
|
|
rustc-hash = "2.0.0"
|
|
thiserror = "2.0.1"
|
|
htmlescape = "0.3.1"
|
|
fail = { version = "0.5.0", optional = true }
|
|
time = { version = "0.3.35", features = ["serde-well-known"] }
|
|
smallvec = "1.8.0"
|
|
rayon = "1.5.2"
|
|
lru = "0.12.0"
|
|
fastdivide = "0.4.0"
|
|
itertools = "0.14.0"
|
|
measure_time = "0.9.0"
|
|
arc-swap = "1.5.0"
|
|
bon = "3.3.1"
|
|
|
|
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 }
|
|
futures-channel = { version = "0.3.28", optional = true }
|
|
fnv = "1.0.7"
|
|
typetag = "0.2.21"
|
|
|
|
[target.'cfg(windows)'.dependencies]
|
|
winapi = "0.3.9"
|
|
|
|
[dev-dependencies]
|
|
binggan = "0.14.2"
|
|
rand = "0.8.5"
|
|
maplit = "1.0.2"
|
|
matches = "0.1.9"
|
|
pretty_assertions = "1.2.1"
|
|
proptest = "1.7.0"
|
|
test-log = "0.2.10"
|
|
futures = "0.3.21"
|
|
paste = "1.0.11"
|
|
more-asserts = "0.3.1"
|
|
rand_distr = "0.4.3"
|
|
time = { version = "0.3.10", features = ["serde-well-known", "macros"] }
|
|
postcard = { version = "1.0.4", features = [
|
|
"use-std",
|
|
], default-features = false }
|
|
|
|
[target.'cfg(not(windows))'.dev-dependencies]
|
|
criterion = { version = "0.5", default-features = false }
|
|
|
|
[dev-dependencies.fail]
|
|
version = "0.5.0"
|
|
features = ["failpoints"]
|
|
|
|
[profile.release]
|
|
opt-level = 3
|
|
debug = false
|
|
debug-assertions = false
|
|
|
|
[profile.bench]
|
|
opt-level = 3
|
|
debug = true
|
|
debug-assertions = false
|
|
|
|
[profile.test]
|
|
debug-assertions = true
|
|
overflow-checks = true
|
|
|
|
[features]
|
|
default = ["mmap", "stopwords", "lz4-compression", "columnar-zstd-compression"]
|
|
mmap = ["fs4", "tempfile", "memmap2"]
|
|
stopwords = []
|
|
|
|
lz4-compression = ["lz4_flex"]
|
|
zstd-compression = ["zstd"]
|
|
|
|
# enable zstd-compression in columnar (and sstable)
|
|
columnar-zstd-compression = ["columnar/zstd-compression"]
|
|
|
|
failpoints = ["fail", "fail/failpoints"]
|
|
unstable = [] # useful for benches.
|
|
|
|
quickwit = ["sstable", "futures-util", "futures-channel"]
|
|
|
|
# Compares only the hash of a string when indexing data.
|
|
# Increases indexing speed, but may lead to extremely rare missing terms, when there's a hash collision.
|
|
# Uses 64bit ahash.
|
|
compare_hash_only = ["stacker/compare_hash_only"]
|
|
|
|
[workspace]
|
|
members = [
|
|
"query-grammar",
|
|
"bitpacker",
|
|
"common",
|
|
"ownedbytes",
|
|
"stacker",
|
|
"sstable",
|
|
"tokenizer-api",
|
|
"columnar",
|
|
]
|
|
|
|
# Following the "fail" crate best practises, we isolate
|
|
# tests that define specific behavior in fail check points
|
|
# in a different binary.
|
|
#
|
|
# We do that because, fail rely on a global definition of
|
|
# failpoints behavior and hence, it is incompatible with
|
|
# multithreading.
|
|
[[test]]
|
|
name = "failpoints"
|
|
path = "tests/failpoints/mod.rs"
|
|
required-features = ["failpoints"]
|
|
|
|
[[bench]]
|
|
name = "analyzer"
|
|
harness = false
|
|
|
|
[[bench]]
|
|
name = "index-bench"
|
|
harness = false
|
|
|
|
[[bench]]
|
|
name = "agg_bench"
|
|
harness = false
|
|
|
|
[[bench]]
|
|
name = "exists_json"
|
|
harness = false
|
|
|
|
[[bench]]
|
|
name = "range_query"
|
|
harness = false
|
|
|
|
[[bench]]
|
|
name = "and_or_queries"
|
|
harness = false
|
|
|
|
[[bench]]
|
|
name = "range_queries"
|
|
harness = false
|