mirror of
https://github.com/quickwit-oss/tantivy.git
synced 2026-01-01 23:12:54 +00:00
Compare commits
1 Commits
trinity/yo
...
bugfix-pos
| Author | SHA1 | Date | |
|---|---|---|---|
|
727d024a23 |
@@ -1,7 +1,6 @@
|
||||
Tantivy 0.19
|
||||
================================
|
||||
|
||||
- Limit fast fields to u32 (`get_val(u32)`) [#1644](https://github.com/quickwit-oss/tantivy/pull/1644) (@PSeitz)
|
||||
- Major bugfix: Fix missing fieldnorms for u64, i64, f64, bool, bytes and date [#1620](https://github.com/quickwit-oss/tantivy/pull/1620) (@PSeitz)
|
||||
- Updated [Date Field Type](https://github.com/quickwit-oss/tantivy/pull/1396)
|
||||
The `DateTime` type has been updated to hold timestamps with microseconds precision.
|
||||
@@ -28,6 +27,7 @@ Tantivy 0.19
|
||||
- [#1582](https://github.com/quickwit-oss/tantivy/pull/1582 (@PSeitz)
|
||||
- [#1611](https://github.com/quickwit-oss/tantivy/pull/1611 (@PSeitz)
|
||||
|
||||
|
||||
Tantivy 0.18
|
||||
================================
|
||||
|
||||
@@ -44,10 +44,6 @@ Tantivy 0.18
|
||||
- Add terms aggregation (@PSeitz)
|
||||
- Add support for zstd compression (@kryesh)
|
||||
|
||||
Tantivy 0.18.1
|
||||
================================
|
||||
- Hotfix: positions computation. #1629 (@fmassot, @fulmicoton, @PSeitz)
|
||||
|
||||
Tantivy 0.17
|
||||
================================
|
||||
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[package]
|
||||
name = "tantivy"
|
||||
version = "0.19.0-dev"
|
||||
version = "0.18.0"
|
||||
authors = ["Paul Masurel <paul.masurel@gmail.com>"]
|
||||
license = "MIT"
|
||||
categories = ["database-implementations", "data-structures"]
|
||||
@@ -14,13 +14,12 @@ edition = "2021"
|
||||
rust-version = "1.62"
|
||||
|
||||
[dependencies]
|
||||
oneshot = "0.1.5"
|
||||
oneshot = "0.1.3"
|
||||
base64 = "0.13.0"
|
||||
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 = "0.7"
|
||||
tantivy-fst = "0.4.0"
|
||||
memmap2 = { version = "0.5.3", optional = true }
|
||||
lz4_flex = { version = "0.9.2", default-features = false, features = ["checked-decode"], optional = true }
|
||||
@@ -46,7 +45,7 @@ rust-stemmers = "1.2.0"
|
||||
downcast-rs = "1.2.0"
|
||||
bitpacking = { version = "0.8.4", default-features = false, features = ["bitpacker4x"] }
|
||||
census = "0.4.0"
|
||||
rustc-hash = "1.1.0"
|
||||
fnv = "1.0.7"
|
||||
thiserror = "1.0.30"
|
||||
htmlescape = "0.3.1"
|
||||
fail = "0.5.0"
|
||||
@@ -61,7 +60,6 @@ measure_time = "0.8.2"
|
||||
ciborium = { version = "0.2", optional = true}
|
||||
async-trait = "0.1.53"
|
||||
arc-swap = "1.5.0"
|
||||
yoke = { version = "0.6.2", features = ["derive"] }
|
||||
|
||||
[target.'cfg(windows)'.dependencies]
|
||||
winapi = "0.3.9"
|
||||
|
||||
100000
benches/hdfs_with_array.json
100000
benches/hdfs_with_array.json
File diff suppressed because it is too large
Load Diff
@@ -1,159 +1,116 @@
|
||||
use criterion::{criterion_group, criterion_main, Criterion};
|
||||
use itertools::Itertools;
|
||||
use pprof::criterion::{Output, PProfProfiler};
|
||||
use serde_json::{self, Value as JsonValue};
|
||||
use tantivy::directory::RamDirectory;
|
||||
use tantivy::schema::{
|
||||
FieldValue, TextFieldIndexing, TextOptions, Value, INDEXED, STORED, STRING, TEXT,
|
||||
};
|
||||
use tantivy::{Document, Index, IndexBuilder};
|
||||
use tantivy::schema::{INDEXED, STORED, STRING, TEXT};
|
||||
use tantivy::Index;
|
||||
|
||||
const HDFS_LOGS: &str = include_str!("hdfs.json");
|
||||
const NUM_REPEATS: usize = 20;
|
||||
const NUM_REPEATS: usize = 2;
|
||||
|
||||
pub fn hdfs_index_benchmark(c: &mut Criterion) {
|
||||
let mut schema_builder = tantivy::schema::SchemaBuilder::new();
|
||||
let text_indexing_options = TextFieldIndexing::default()
|
||||
.set_tokenizer("default")
|
||||
.set_fieldnorms(false)
|
||||
.set_index_option(tantivy::schema::IndexRecordOption::WithFreqsAndPositions);
|
||||
let mut text_options = TextOptions::default().set_indexing_options(text_indexing_options);
|
||||
let text_field = schema_builder.add_text_field("body", text_options);
|
||||
let schema = schema_builder.build();
|
||||
|
||||
// prepare doc
|
||||
let mut documents_no_array = Vec::new();
|
||||
let mut documents_with_array = Vec::new();
|
||||
for doc_json in HDFS_LOGS.trim().split("\n") {
|
||||
let json_obj: serde_json::Map<String, JsonValue> = serde_json::from_str(doc_json).unwrap();
|
||||
let text = json_obj.get("body").unwrap().as_str().unwrap();
|
||||
let mut doc_no_array = Document::new();
|
||||
doc_no_array.add_text(text_field, text);
|
||||
documents_no_array.push(doc_no_array);
|
||||
let mut doc_with_array = Document::new();
|
||||
doc_with_array.add_borrowed_values(text.to_owned(), |text| {
|
||||
text.split(' ')
|
||||
.map(|text| FieldValue::new(text_field, text.into()))
|
||||
.collect()
|
||||
});
|
||||
documents_with_array.push(doc_with_array);
|
||||
}
|
||||
let schema = {
|
||||
let mut schema_builder = tantivy::schema::SchemaBuilder::new();
|
||||
schema_builder.add_u64_field("timestamp", INDEXED);
|
||||
schema_builder.add_text_field("body", TEXT);
|
||||
schema_builder.add_text_field("severity", STRING);
|
||||
schema_builder.build()
|
||||
};
|
||||
let schema_with_store = {
|
||||
let mut schema_builder = tantivy::schema::SchemaBuilder::new();
|
||||
schema_builder.add_u64_field("timestamp", INDEXED | STORED);
|
||||
schema_builder.add_text_field("body", TEXT | STORED);
|
||||
schema_builder.add_text_field("severity", STRING | STORED);
|
||||
schema_builder.build()
|
||||
};
|
||||
let dynamic_schema = {
|
||||
let mut schema_builder = tantivy::schema::SchemaBuilder::new();
|
||||
schema_builder.add_json_field("json", TEXT);
|
||||
schema_builder.build()
|
||||
};
|
||||
|
||||
let mut group = c.benchmark_group("index-hdfs");
|
||||
group.sample_size(20);
|
||||
group.bench_function("index-hdfs-no-commit", |b| {
|
||||
b.iter(|| {
|
||||
let ram_directory = RamDirectory::create();
|
||||
let mut index_writer = IndexBuilder::new()
|
||||
.schema(schema.clone())
|
||||
.single_segment_index_writer(ram_directory, 100_000_000)
|
||||
.unwrap();
|
||||
let index = Index::create_in_ram(schema.clone());
|
||||
let index_writer = index.writer_with_num_threads(1, 100_000_000).unwrap();
|
||||
for _ in 0..NUM_REPEATS {
|
||||
let documents_cloned = documents_no_array.clone();
|
||||
for doc in documents_cloned {
|
||||
for doc_json in HDFS_LOGS.trim().split("\n") {
|
||||
let doc = schema.parse_document(doc_json).unwrap();
|
||||
index_writer.add_document(doc).unwrap();
|
||||
}
|
||||
}
|
||||
})
|
||||
});
|
||||
group.bench_function("index-hdfs-with-array-no-commit", |b| {
|
||||
group.bench_function("index-hdfs-with-commit", |b| {
|
||||
b.iter(|| {
|
||||
let ram_directory = RamDirectory::create();
|
||||
let mut index_writer = IndexBuilder::new()
|
||||
.schema(schema.clone())
|
||||
.single_segment_index_writer(ram_directory, 100_000_000)
|
||||
.unwrap();
|
||||
let index = Index::create_in_ram(schema.clone());
|
||||
let mut index_writer = index.writer_with_num_threads(1, 100_000_000).unwrap();
|
||||
for _ in 0..NUM_REPEATS {
|
||||
let documents_with_array_cloned = documents_with_array.clone();
|
||||
for doc in documents_with_array_cloned {
|
||||
for doc_json in HDFS_LOGS.trim().split("\n") {
|
||||
let doc = schema.parse_document(doc_json).unwrap();
|
||||
index_writer.add_document(doc).unwrap();
|
||||
}
|
||||
}
|
||||
index_writer.commit().unwrap();
|
||||
})
|
||||
});
|
||||
group.bench_function("index-hdfs-no-commit-with-docstore", |b| {
|
||||
b.iter(|| {
|
||||
let index = Index::create_in_ram(schema_with_store.clone());
|
||||
let index_writer = index.writer_with_num_threads(1, 100_000_000).unwrap();
|
||||
for _ in 0..NUM_REPEATS {
|
||||
for doc_json in HDFS_LOGS.trim().split("\n") {
|
||||
let doc = schema.parse_document(doc_json).unwrap();
|
||||
index_writer.add_document(doc).unwrap();
|
||||
}
|
||||
}
|
||||
})
|
||||
});
|
||||
// group.bench_function("index-hdfs-with-commit", |b| {
|
||||
// b.iter(|| {
|
||||
// let ram_directory = RamDirectory::create();
|
||||
// let mut index_writer = IndexBuilder::new()
|
||||
// .schema(schema.clone())
|
||||
// .single_segment_index_writer(ram_directory, 100_000_000)
|
||||
// .unwrap();
|
||||
// for _ in 0..NUM_REPEATS {
|
||||
// for doc_json in HDFS_LOGS.trim().split("\n") {
|
||||
// let doc = schema.parse_document(doc_json).unwrap();
|
||||
// index_writer.add_document(doc).unwrap();
|
||||
// }
|
||||
// }
|
||||
// index_writer.commit().unwrap();
|
||||
// })
|
||||
// });
|
||||
// group.bench_function("index-hdfs-no-commit-with-docstore", |b| {
|
||||
// b.iter(|| {
|
||||
// let ram_directory = RamDirectory::create();
|
||||
// let mut index_writer = IndexBuilder::new()
|
||||
// .schema(schema.clone())
|
||||
// .single_segment_index_writer(ram_directory, 100_000_000)
|
||||
// .unwrap();
|
||||
// for _ in 0..NUM_REPEATS {
|
||||
// for doc_json in HDFS_LOGS.trim().split("\n") {
|
||||
// let doc = schema.parse_document(doc_json).unwrap();
|
||||
// index_writer.add_document(doc).unwrap();
|
||||
// }
|
||||
// }
|
||||
// })
|
||||
// });
|
||||
// group.bench_function("index-hdfs-with-commit-with-docstore", |b| {
|
||||
// b.iter(|| {
|
||||
// let ram_directory = RamDirectory::create();
|
||||
// let mut index_writer = IndexBuilder::new()
|
||||
// .schema(schema.clone())
|
||||
// .single_segment_index_writer(ram_directory, 100_000_000)
|
||||
// .unwrap();
|
||||
// for _ in 0..NUM_REPEATS {
|
||||
// for doc_json in HDFS_LOGS.trim().split("\n") {
|
||||
// let doc = schema.parse_document(doc_json).unwrap();
|
||||
// index_writer.add_document(doc).unwrap();
|
||||
// }
|
||||
// }
|
||||
// index_writer.commit().unwrap();
|
||||
// })
|
||||
// });
|
||||
// group.bench_function("index-hdfs-no-commit-json-without-docstore", |b| {
|
||||
// b.iter(|| {
|
||||
// let ram_directory = RamDirectory::create();
|
||||
// let mut index_writer = IndexBuilder::new()
|
||||
// .schema(schema.clone())
|
||||
// .single_segment_index_writer(ram_directory, 100_000_000)
|
||||
// .unwrap();
|
||||
// for _ in 0..NUM_REPEATS {
|
||||
// for doc_json in HDFS_LOGS.trim().split("\n") {
|
||||
// let json_val: serde_json::Map<String, serde_json::Value> =
|
||||
// serde_json::from_str(doc_json).unwrap();
|
||||
// let doc = tantivy::doc!(json_field=>json_val);
|
||||
// index_writer.add_document(doc).unwrap();
|
||||
// }
|
||||
// }
|
||||
// index_writer.commit().unwrap();
|
||||
// })
|
||||
// });
|
||||
// group.bench_function("index-hdfs-with-commit-json-without-docstore", |b| {
|
||||
// b.iter(|| {
|
||||
// let ram_directory = RamDirectory::create();
|
||||
// let mut index_writer = IndexBuilder::new()
|
||||
// .schema(schema.clone())
|
||||
// .single_segment_index_writer(ram_directory, 100_000_000)
|
||||
// .unwrap();
|
||||
// for _ in 0..NUM_REPEATS {
|
||||
// for doc_json in HDFS_LOGS.trim().split("\n") {
|
||||
// let json_val: serde_json::Map<String, serde_json::Value> =
|
||||
// serde_json::from_str(doc_json).unwrap();
|
||||
// let doc = tantivy::doc!(json_field=>json_val);
|
||||
// index_writer.add_document(doc).unwrap();
|
||||
// }
|
||||
// }
|
||||
// index_writer.commit().unwrap();
|
||||
// })
|
||||
//});
|
||||
group.bench_function("index-hdfs-with-commit-with-docstore", |b| {
|
||||
b.iter(|| {
|
||||
let index = Index::create_in_ram(schema_with_store.clone());
|
||||
let mut index_writer = index.writer_with_num_threads(1, 100_000_000).unwrap();
|
||||
for _ in 0..NUM_REPEATS {
|
||||
for doc_json in HDFS_LOGS.trim().split("\n") {
|
||||
let doc = schema.parse_document(doc_json).unwrap();
|
||||
index_writer.add_document(doc).unwrap();
|
||||
}
|
||||
}
|
||||
index_writer.commit().unwrap();
|
||||
})
|
||||
});
|
||||
group.bench_function("index-hdfs-no-commit-json-without-docstore", |b| {
|
||||
b.iter(|| {
|
||||
let index = Index::create_in_ram(dynamic_schema.clone());
|
||||
let json_field = dynamic_schema.get_field("json").unwrap();
|
||||
let mut index_writer = index.writer_with_num_threads(1, 100_000_000).unwrap();
|
||||
for _ in 0..NUM_REPEATS {
|
||||
for doc_json in HDFS_LOGS.trim().split("\n") {
|
||||
let json_val: serde_json::Map<String, serde_json::Value> =
|
||||
serde_json::from_str(doc_json).unwrap();
|
||||
let doc = tantivy::doc!(json_field=>json_val);
|
||||
index_writer.add_document(doc).unwrap();
|
||||
}
|
||||
}
|
||||
index_writer.commit().unwrap();
|
||||
})
|
||||
});
|
||||
group.bench_function("index-hdfs-with-commit-json-without-docstore", |b| {
|
||||
b.iter(|| {
|
||||
let index = Index::create_in_ram(dynamic_schema.clone());
|
||||
let json_field = dynamic_schema.get_field("json").unwrap();
|
||||
let mut index_writer = index.writer_with_num_threads(1, 100_000_000).unwrap();
|
||||
for _ in 0..NUM_REPEATS {
|
||||
for doc_json in HDFS_LOGS.trim().split("\n") {
|
||||
let json_val: serde_json::Map<String, serde_json::Value> =
|
||||
serde_json::from_str(doc_json).unwrap();
|
||||
let doc = tantivy::doc!(json_field=>json_val);
|
||||
index_writer.add_document(doc).unwrap();
|
||||
}
|
||||
}
|
||||
index_writer.commit().unwrap();
|
||||
})
|
||||
});
|
||||
}
|
||||
|
||||
criterion_group! {
|
||||
|
||||
@@ -87,15 +87,15 @@ impl BitUnpacker {
|
||||
}
|
||||
|
||||
#[inline]
|
||||
pub fn get(&self, idx: u32, data: &[u8]) -> u64 {
|
||||
pub fn get(&self, idx: u64, data: &[u8]) -> u64 {
|
||||
if self.num_bits == 0 {
|
||||
return 0u64;
|
||||
}
|
||||
let addr_in_bits = idx * self.num_bits as u32;
|
||||
let addr_in_bits = idx * self.num_bits;
|
||||
let addr = addr_in_bits >> 3;
|
||||
let bit_shift = addr_in_bits & 7;
|
||||
debug_assert!(
|
||||
addr + 8 <= data.len() as u32,
|
||||
addr + 8 <= data.len() as u64,
|
||||
"The fast field field should have been padded with 7 bytes."
|
||||
);
|
||||
let bytes: [u8; 8] = (&data[(addr as usize)..(addr as usize) + 8])
|
||||
@@ -130,7 +130,7 @@ mod test {
|
||||
fn test_bitpacker_util(len: usize, num_bits: u8) {
|
||||
let (bitunpacker, vals, data) = create_fastfield_bitpacker(len, num_bits);
|
||||
for (i, val) in vals.iter().enumerate() {
|
||||
assert_eq!(bitunpacker.get(i as u32, &data), *val);
|
||||
assert_eq!(bitunpacker.get(i as u64, &data), *val);
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -130,7 +130,7 @@ impl BlockedBitpacker {
|
||||
let pos_in_block = idx % BLOCK_SIZE as usize;
|
||||
if let Some(metadata) = self.offset_and_bits.get(metadata_pos) {
|
||||
let unpacked = BitUnpacker::new(metadata.num_bits()).get(
|
||||
pos_in_block as u32,
|
||||
pos_in_block as u64,
|
||||
&self.compressed_blocks[metadata.offset() as usize..],
|
||||
);
|
||||
unpacked + metadata.base_value()
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
use std::borrow::Cow;
|
||||
use std::io::{Read, Write};
|
||||
use std::{fmt, io};
|
||||
|
||||
@@ -211,23 +210,6 @@ impl BinarySerializable for String {
|
||||
}
|
||||
}
|
||||
|
||||
impl<'a> BinarySerializable for Cow<'a, str> {
|
||||
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
|
||||
let data: &[u8] = self.as_bytes();
|
||||
VInt(data.len() as u64).serialize(writer)?;
|
||||
writer.write_all(data)
|
||||
}
|
||||
|
||||
fn deserialize<R: Read>(reader: &mut R) -> io::Result<Self> {
|
||||
let string_length = VInt::deserialize(reader)?.val() as usize;
|
||||
let mut result = String::with_capacity(string_length);
|
||||
reader
|
||||
.take(string_length as u64)
|
||||
.read_to_string(&mut result)?;
|
||||
Ok(Cow::Owned(result))
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
pub mod test {
|
||||
|
||||
|
||||
@@ -105,7 +105,7 @@ impl SegmentCollector for StatsSegmentCollector {
|
||||
type Fruit = Option<Stats>;
|
||||
|
||||
fn collect(&mut self, doc: u32, _score: Score) {
|
||||
let value = self.fast_field_reader.get_val(doc) as f64;
|
||||
let value = self.fast_field_reader.get_val(doc as u64) as f64;
|
||||
self.stats.count += 1;
|
||||
self.stats.sum += value;
|
||||
self.stats.squared_sum += value * value;
|
||||
|
||||
@@ -51,7 +51,7 @@ impl Warmer for DynamicPriceColumn {
|
||||
let product_id_reader = segment.fast_fields().u64(self.field)?;
|
||||
let product_ids: Vec<ProductId> = segment
|
||||
.doc_ids_alive()
|
||||
.map(|doc| product_id_reader.get_val(doc))
|
||||
.map(|doc| product_id_reader.get_val(doc as u64))
|
||||
.collect();
|
||||
let mut prices_it = self.price_fetcher.fetch_prices(&product_ids).into_iter();
|
||||
let mut price_vals: Vec<Price> = Vec::new();
|
||||
|
||||
@@ -65,7 +65,7 @@ mod tests {
|
||||
b.iter(|| {
|
||||
let mut a = 0u64;
|
||||
for _ in 0..n {
|
||||
a = column.get_val(a as u32);
|
||||
a = column.get_val(a as u64);
|
||||
}
|
||||
a
|
||||
});
|
||||
@@ -101,7 +101,7 @@ mod tests {
|
||||
fn get_u128_column_from_data(data: &[u128]) -> Arc<dyn Column<u128>> {
|
||||
let mut out = vec![];
|
||||
let iter_gen = || data.iter().cloned();
|
||||
serialize_u128(iter_gen, data.len() as u32, &mut out).unwrap();
|
||||
serialize_u128(iter_gen, data.len() as u64, &mut out).unwrap();
|
||||
let out = OwnedBytes::new(out);
|
||||
open_u128::<u128>(out).unwrap()
|
||||
}
|
||||
@@ -111,15 +111,7 @@ mod tests {
|
||||
let (major_item, _minor_item, data) = get_data_50percent_item();
|
||||
let column = get_u128_column_from_data(&data);
|
||||
|
||||
b.iter(|| {
|
||||
let mut positions = Vec::new();
|
||||
column.get_positions_for_value_range(
|
||||
major_item..=major_item,
|
||||
0..data.len() as u32,
|
||||
&mut positions,
|
||||
);
|
||||
positions
|
||||
});
|
||||
b.iter(|| column.get_between_vals(major_item..=major_item));
|
||||
}
|
||||
|
||||
#[bench]
|
||||
@@ -127,15 +119,7 @@ mod tests {
|
||||
let (_major_item, minor_item, data) = get_data_50percent_item();
|
||||
let column = get_u128_column_from_data(&data);
|
||||
|
||||
b.iter(|| {
|
||||
let mut positions = Vec::new();
|
||||
column.get_positions_for_value_range(
|
||||
minor_item..=minor_item,
|
||||
0..data.len() as u32,
|
||||
&mut positions,
|
||||
);
|
||||
positions
|
||||
});
|
||||
b.iter(|| column.get_between_vals(minor_item..=minor_item));
|
||||
}
|
||||
|
||||
#[bench]
|
||||
@@ -143,15 +127,7 @@ mod tests {
|
||||
let (_major_item, _minor_item, data) = get_data_50percent_item();
|
||||
let column = get_u128_column_from_data(&data);
|
||||
|
||||
b.iter(|| {
|
||||
let mut positions = Vec::new();
|
||||
column.get_positions_for_value_range(
|
||||
0..=u128::MAX,
|
||||
0..data.len() as u32,
|
||||
&mut positions,
|
||||
);
|
||||
positions
|
||||
});
|
||||
b.iter(|| column.get_between_vals(0..=u128::MAX));
|
||||
}
|
||||
|
||||
#[bench]
|
||||
@@ -161,7 +137,7 @@ mod tests {
|
||||
b.iter(|| {
|
||||
let mut a = 0u128;
|
||||
for i in 0u64..column.num_vals() as u64 {
|
||||
a += column.get_val(i as u32);
|
||||
a += column.get_val(i);
|
||||
}
|
||||
a
|
||||
});
|
||||
@@ -175,7 +151,7 @@ mod tests {
|
||||
let n = column.num_vals();
|
||||
let mut a = 0u128;
|
||||
for i in (0..n / 5).map(|val| val * 5) {
|
||||
a += column.get_val(i);
|
||||
a += column.get_val(i as u64);
|
||||
}
|
||||
a
|
||||
});
|
||||
@@ -200,9 +176,9 @@ mod tests {
|
||||
let n = permutation.len();
|
||||
let column: Arc<dyn Column<u64>> = serialize_and_load(&permutation);
|
||||
b.iter(|| {
|
||||
let mut a = 0;
|
||||
let mut a = 0u64;
|
||||
for i in (0..n / 7).map(|val| val * 7) {
|
||||
a += column.get_val(i as u32);
|
||||
a += column.get_val(i as u64);
|
||||
}
|
||||
a
|
||||
});
|
||||
@@ -215,7 +191,7 @@ mod tests {
|
||||
let column: Arc<dyn Column<u64>> = serialize_and_load(&permutation);
|
||||
b.iter(|| {
|
||||
let mut a = 0u64;
|
||||
for i in 0u32..n as u32 {
|
||||
for i in 0u64..n as u64 {
|
||||
a += column.get_val(i);
|
||||
}
|
||||
a
|
||||
@@ -229,8 +205,8 @@ mod tests {
|
||||
let column: Arc<dyn Column<u64>> = serialize_and_load(&permutation);
|
||||
b.iter(|| {
|
||||
let mut a = 0u64;
|
||||
for i in 0..n {
|
||||
a += column.get_val(i as u32);
|
||||
for i in 0..n as u64 {
|
||||
a += column.get_val(i);
|
||||
}
|
||||
a
|
||||
});
|
||||
|
||||
@@ -17,7 +17,7 @@ pub struct BitpackedReader {
|
||||
|
||||
impl Column for BitpackedReader {
|
||||
#[inline]
|
||||
fn get_val(&self, doc: u32) -> u64 {
|
||||
fn get_val(&self, doc: u64) -> u64 {
|
||||
self.bit_unpacker.get(doc, &self.data)
|
||||
}
|
||||
#[inline]
|
||||
@@ -30,7 +30,7 @@ impl Column for BitpackedReader {
|
||||
self.normalized_header.max_value
|
||||
}
|
||||
#[inline]
|
||||
fn num_vals(&self) -> u32 {
|
||||
fn num_vals(&self) -> u64 {
|
||||
self.normalized_header.num_vals
|
||||
}
|
||||
}
|
||||
|
||||
@@ -36,7 +36,7 @@ impl BinarySerializable for Block {
|
||||
}
|
||||
}
|
||||
|
||||
fn compute_num_blocks(num_vals: u32) -> usize {
|
||||
fn compute_num_blocks(num_vals: u64) -> usize {
|
||||
(num_vals as usize + CHUNK_SIZE - 1) / CHUNK_SIZE
|
||||
}
|
||||
|
||||
@@ -72,13 +72,13 @@ impl FastFieldCodec for BlockwiseLinearCodec {
|
||||
|
||||
// Estimate first_chunk and extrapolate
|
||||
fn estimate(column: &dyn crate::Column) -> Option<f32> {
|
||||
if column.num_vals() < 10 * CHUNK_SIZE as u32 {
|
||||
if column.num_vals() < 10 * CHUNK_SIZE as u64 {
|
||||
return None;
|
||||
}
|
||||
let mut first_chunk: Vec<u64> = column.iter().take(CHUNK_SIZE as usize).collect();
|
||||
let line = Line::train(&VecColumn::from(&first_chunk));
|
||||
for (i, buffer_val) in first_chunk.iter_mut().enumerate() {
|
||||
let interpolated_val = line.eval(i as u32);
|
||||
let interpolated_val = line.eval(i as u64);
|
||||
*buffer_val = buffer_val.wrapping_sub(interpolated_val);
|
||||
}
|
||||
let estimated_bit_width = first_chunk
|
||||
@@ -95,7 +95,7 @@ impl FastFieldCodec for BlockwiseLinearCodec {
|
||||
};
|
||||
let num_bits = estimated_bit_width as u64 * column.num_vals() as u64
|
||||
// function metadata per block
|
||||
+ metadata_per_block as u64 * (column.num_vals() as u64 / CHUNK_SIZE as u64);
|
||||
+ metadata_per_block as u64 * (column.num_vals() / CHUNK_SIZE as u64);
|
||||
let num_bits_uncompressed = 64 * column.num_vals();
|
||||
Some(num_bits as f32 / num_bits_uncompressed as f32)
|
||||
}
|
||||
@@ -121,7 +121,7 @@ impl FastFieldCodec for BlockwiseLinearCodec {
|
||||
assert!(!buffer.is_empty());
|
||||
|
||||
for (i, buffer_val) in buffer.iter_mut().enumerate() {
|
||||
let interpolated_val = line.eval(i as u32);
|
||||
let interpolated_val = line.eval(i as u64);
|
||||
*buffer_val = buffer_val.wrapping_sub(interpolated_val);
|
||||
}
|
||||
let bit_width = buffer.iter().copied().map(compute_num_bits).max().unwrap();
|
||||
@@ -161,9 +161,9 @@ pub struct BlockwiseLinearReader {
|
||||
|
||||
impl Column for BlockwiseLinearReader {
|
||||
#[inline(always)]
|
||||
fn get_val(&self, idx: u32) -> u64 {
|
||||
let block_id = (idx / CHUNK_SIZE as u32) as usize;
|
||||
let idx_within_block = idx % (CHUNK_SIZE as u32);
|
||||
fn get_val(&self, idx: u64) -> u64 {
|
||||
let block_id = (idx / CHUNK_SIZE as u64) as usize;
|
||||
let idx_within_block = idx % (CHUNK_SIZE as u64);
|
||||
let block = &self.blocks[block_id];
|
||||
let interpoled_val: u64 = block.line.eval(idx_within_block);
|
||||
let block_bytes = &self.data[block.data_start_offset..];
|
||||
@@ -180,7 +180,7 @@ impl Column for BlockwiseLinearReader {
|
||||
self.normalized_header.max_value
|
||||
}
|
||||
|
||||
fn num_vals(&self) -> u32 {
|
||||
fn num_vals(&self) -> u64 {
|
||||
self.normalized_header.num_vals
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
use std::marker::PhantomData;
|
||||
use std::ops::{Range, RangeInclusive};
|
||||
use std::ops::RangeInclusive;
|
||||
|
||||
use tantivy_bitpacker::minmax;
|
||||
|
||||
@@ -14,7 +14,7 @@ pub trait Column<T: PartialOrd = u64>: Send + Sync {
|
||||
/// # Panics
|
||||
///
|
||||
/// May panic if `idx` is greater than the column length.
|
||||
fn get_val(&self, idx: u32) -> T;
|
||||
fn get_val(&self, idx: u64) -> T;
|
||||
|
||||
/// Fills an output buffer with the fast field values
|
||||
/// associated with the `DocId` going from
|
||||
@@ -27,28 +27,21 @@ pub trait Column<T: PartialOrd = u64>: Send + Sync {
|
||||
#[inline]
|
||||
fn get_range(&self, start: u64, output: &mut [T]) {
|
||||
for (out, idx) in output.iter_mut().zip(start..) {
|
||||
*out = self.get_val(idx as u32);
|
||||
*out = self.get_val(idx);
|
||||
}
|
||||
}
|
||||
|
||||
/// Get the positions of values which are in the provided value range.
|
||||
///
|
||||
/// Note that position == docid for single value fast fields
|
||||
/// Return the positions of values which are in the provided range.
|
||||
#[inline]
|
||||
fn get_positions_for_value_range(
|
||||
&self,
|
||||
value_range: RangeInclusive<T>,
|
||||
doc_id_range: Range<u32>,
|
||||
positions: &mut Vec<u32>,
|
||||
) {
|
||||
let doc_id_range = doc_id_range.start..doc_id_range.end.min(self.num_vals());
|
||||
|
||||
for idx in doc_id_range.start..doc_id_range.end {
|
||||
fn get_between_vals(&self, range: RangeInclusive<T>) -> Vec<u64> {
|
||||
let mut vals = Vec::new();
|
||||
for idx in 0..self.num_vals() {
|
||||
let val = self.get_val(idx);
|
||||
if value_range.contains(&val) {
|
||||
positions.push(idx);
|
||||
if range.contains(&val) {
|
||||
vals.push(idx);
|
||||
}
|
||||
}
|
||||
vals
|
||||
}
|
||||
|
||||
/// Returns the minimum value for this fast field.
|
||||
@@ -68,7 +61,7 @@ pub trait Column<T: PartialOrd = u64>: Send + Sync {
|
||||
fn max_value(&self) -> T;
|
||||
|
||||
/// The number of values in the column.
|
||||
fn num_vals(&self) -> u32;
|
||||
fn num_vals(&self) -> u64;
|
||||
|
||||
/// Returns a iterator over the data
|
||||
fn iter<'a>(&'a self) -> Box<dyn Iterator<Item = T> + 'a> {
|
||||
@@ -84,7 +77,7 @@ pub struct VecColumn<'a, T = u64> {
|
||||
}
|
||||
|
||||
impl<'a, C: Column<T>, T: Copy + PartialOrd> Column<T> for &'a C {
|
||||
fn get_val(&self, idx: u32) -> T {
|
||||
fn get_val(&self, idx: u64) -> T {
|
||||
(*self).get_val(idx)
|
||||
}
|
||||
|
||||
@@ -96,7 +89,7 @@ impl<'a, C: Column<T>, T: Copy + PartialOrd> Column<T> for &'a C {
|
||||
(*self).max_value()
|
||||
}
|
||||
|
||||
fn num_vals(&self) -> u32 {
|
||||
fn num_vals(&self) -> u64 {
|
||||
(*self).num_vals()
|
||||
}
|
||||
|
||||
@@ -110,7 +103,7 @@ impl<'a, C: Column<T>, T: Copy + PartialOrd> Column<T> for &'a C {
|
||||
}
|
||||
|
||||
impl<'a, T: Copy + PartialOrd + Send + Sync> Column<T> for VecColumn<'a, T> {
|
||||
fn get_val(&self, position: u32) -> T {
|
||||
fn get_val(&self, position: u64) -> T {
|
||||
self.values[position as usize]
|
||||
}
|
||||
|
||||
@@ -126,8 +119,8 @@ impl<'a, T: Copy + PartialOrd + Send + Sync> Column<T> for VecColumn<'a, T> {
|
||||
self.max_value
|
||||
}
|
||||
|
||||
fn num_vals(&self) -> u32 {
|
||||
self.values.len() as u32
|
||||
fn num_vals(&self) -> u64 {
|
||||
self.values.len() as u64
|
||||
}
|
||||
|
||||
fn get_range(&self, start: u64, output: &mut [T]) {
|
||||
@@ -163,7 +156,7 @@ struct MonotonicMappingColumn<C, T, Input> {
|
||||
/// monotonic_mapping.inverse(monotonic_mapping.mapping(el)) == el
|
||||
///
|
||||
/// The inverse of the mapping is required for:
|
||||
/// `fn get_positions_for_value_range(&self, range: RangeInclusive<T>) -> Vec<u64> `
|
||||
/// `fn get_between_vals(&self, range: RangeInclusive<T>) -> Vec<u64> `
|
||||
/// The user provides the original value range and we need to monotonic map them in the same way the
|
||||
/// serialization does before calling the underlying column.
|
||||
///
|
||||
@@ -195,7 +188,7 @@ where
|
||||
Output: PartialOrd + Send + Sync + Clone,
|
||||
{
|
||||
#[inline]
|
||||
fn get_val(&self, idx: u32) -> Output {
|
||||
fn get_val(&self, idx: u64) -> Output {
|
||||
let from_val = self.from_column.get_val(idx);
|
||||
self.monotonic_mapping.mapping(from_val)
|
||||
}
|
||||
@@ -210,7 +203,7 @@ where
|
||||
self.monotonic_mapping.mapping(from_max_value)
|
||||
}
|
||||
|
||||
fn num_vals(&self) -> u32 {
|
||||
fn num_vals(&self) -> u64 {
|
||||
self.from_column.num_vals()
|
||||
}
|
||||
|
||||
@@ -222,17 +215,10 @@ where
|
||||
)
|
||||
}
|
||||
|
||||
fn get_positions_for_value_range(
|
||||
&self,
|
||||
range: RangeInclusive<Output>,
|
||||
doc_id_range: Range<u32>,
|
||||
positions: &mut Vec<u32>,
|
||||
) {
|
||||
self.from_column.get_positions_for_value_range(
|
||||
fn get_between_vals(&self, range: RangeInclusive<Output>) -> Vec<u64> {
|
||||
self.from_column.get_between_vals(
|
||||
self.monotonic_mapping.inverse(range.start().clone())
|
||||
..=self.monotonic_mapping.inverse(range.end().clone()),
|
||||
doc_id_range,
|
||||
positions,
|
||||
)
|
||||
}
|
||||
|
||||
@@ -255,7 +241,7 @@ where
|
||||
T: Iterator + Clone + ExactSizeIterator + Send + Sync,
|
||||
T::Item: PartialOrd,
|
||||
{
|
||||
fn get_val(&self, idx: u32) -> T::Item {
|
||||
fn get_val(&self, idx: u64) -> T::Item {
|
||||
self.0.clone().nth(idx as usize).unwrap()
|
||||
}
|
||||
|
||||
@@ -267,8 +253,8 @@ where
|
||||
self.0.clone().last().unwrap()
|
||||
}
|
||||
|
||||
fn num_vals(&self) -> u32 {
|
||||
self.0.len() as u32
|
||||
fn num_vals(&self) -> u64 {
|
||||
self.0.len() as u64
|
||||
}
|
||||
|
||||
fn iter(&self) -> Box<dyn Iterator<Item = T::Item> + '_> {
|
||||
|
||||
@@ -57,7 +57,7 @@ fn num_bits(val: u128) -> u8 {
|
||||
/// metadata.
|
||||
pub fn get_compact_space(
|
||||
values_deduped_sorted: &BTreeSet<u128>,
|
||||
total_num_values: u32,
|
||||
total_num_values: u64,
|
||||
cost_per_blank: usize,
|
||||
) -> CompactSpace {
|
||||
let mut compact_space_builder = CompactSpaceBuilder::new();
|
||||
|
||||
@@ -14,7 +14,7 @@ use std::{
|
||||
cmp::Ordering,
|
||||
collections::BTreeSet,
|
||||
io::{self, Write},
|
||||
ops::{Range, RangeInclusive},
|
||||
ops::RangeInclusive,
|
||||
};
|
||||
|
||||
use common::{BinarySerializable, CountingWriter, VInt, VIntU128};
|
||||
@@ -165,13 +165,13 @@ pub struct IPCodecParams {
|
||||
bit_unpacker: BitUnpacker,
|
||||
min_value: u128,
|
||||
max_value: u128,
|
||||
num_vals: u32,
|
||||
num_vals: u64,
|
||||
num_bits: u8,
|
||||
}
|
||||
|
||||
impl CompactSpaceCompressor {
|
||||
/// Taking the vals as Vec may cost a lot of memory. It is used to sort the vals.
|
||||
pub fn train_from(iter: impl Iterator<Item = u128>, num_vals: u32) -> Self {
|
||||
pub fn train_from(iter: impl Iterator<Item = u128>, num_vals: u64) -> Self {
|
||||
let mut values_sorted = BTreeSet::new();
|
||||
values_sorted.extend(iter);
|
||||
let total_num_values = num_vals;
|
||||
@@ -200,7 +200,7 @@ impl CompactSpaceCompressor {
|
||||
bit_unpacker: BitUnpacker::new(num_bits),
|
||||
min_value,
|
||||
max_value,
|
||||
num_vals: total_num_values,
|
||||
num_vals: total_num_values as u64,
|
||||
num_bits,
|
||||
},
|
||||
}
|
||||
@@ -267,7 +267,7 @@ impl BinarySerializable for IPCodecParams {
|
||||
let _header_flags = u64::deserialize(reader)?;
|
||||
let min_value = VIntU128::deserialize(reader)?.0;
|
||||
let max_value = VIntU128::deserialize(reader)?.0;
|
||||
let num_vals = VIntU128::deserialize(reader)?.0 as u32;
|
||||
let num_vals = VIntU128::deserialize(reader)?.0 as u64;
|
||||
let num_bits = u8::deserialize(reader)?;
|
||||
let compact_space = CompactSpace::deserialize(reader)?;
|
||||
|
||||
@@ -284,7 +284,7 @@ impl BinarySerializable for IPCodecParams {
|
||||
|
||||
impl Column<u128> for CompactSpaceDecompressor {
|
||||
#[inline]
|
||||
fn get_val(&self, doc: u32) -> u128 {
|
||||
fn get_val(&self, doc: u64) -> u128 {
|
||||
self.get(doc)
|
||||
}
|
||||
|
||||
@@ -296,7 +296,7 @@ impl Column<u128> for CompactSpaceDecompressor {
|
||||
self.max_value()
|
||||
}
|
||||
|
||||
fn num_vals(&self) -> u32 {
|
||||
fn num_vals(&self) -> u64 {
|
||||
self.params.num_vals
|
||||
}
|
||||
|
||||
@@ -304,15 +304,8 @@ impl Column<u128> for CompactSpaceDecompressor {
|
||||
fn iter(&self) -> Box<dyn Iterator<Item = u128> + '_> {
|
||||
Box::new(self.iter())
|
||||
}
|
||||
|
||||
#[inline]
|
||||
fn get_positions_for_value_range(
|
||||
&self,
|
||||
value_range: RangeInclusive<u128>,
|
||||
doc_id_range: Range<u32>,
|
||||
positions: &mut Vec<u32>,
|
||||
) {
|
||||
self.get_positions_for_value_range(value_range, doc_id_range, positions)
|
||||
fn get_between_vals(&self, range: RangeInclusive<u128>) -> Vec<u64> {
|
||||
self.get_between_vals(range)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -347,19 +340,12 @@ impl CompactSpaceDecompressor {
|
||||
/// Comparing on compact space: Real dataset 1.08 GElements/s
|
||||
///
|
||||
/// Comparing on original space: Real dataset .06 GElements/s (not completely optimized)
|
||||
#[inline]
|
||||
pub fn get_positions_for_value_range(
|
||||
&self,
|
||||
value_range: RangeInclusive<u128>,
|
||||
doc_id_range: Range<u32>,
|
||||
positions: &mut Vec<u32>,
|
||||
) {
|
||||
if value_range.start() > value_range.end() {
|
||||
return;
|
||||
pub fn get_between_vals(&self, range: RangeInclusive<u128>) -> Vec<u64> {
|
||||
if range.start() > range.end() {
|
||||
return Vec::new();
|
||||
}
|
||||
let doc_id_range = doc_id_range.start..doc_id_range.end.min(self.num_vals());
|
||||
let from_value = *value_range.start();
|
||||
let to_value = *value_range.end();
|
||||
let from_value = *range.start();
|
||||
let to_value = *range.end();
|
||||
assert!(to_value >= from_value);
|
||||
let compact_from = self.u128_to_compact(from_value);
|
||||
let compact_to = self.u128_to_compact(to_value);
|
||||
@@ -367,7 +353,7 @@ impl CompactSpaceDecompressor {
|
||||
// Quick return, if both ranges fall into the same non-mapped space, the range can't cover
|
||||
// any values, so we can early exit
|
||||
match (compact_to, compact_from) {
|
||||
(Err(pos1), Err(pos2)) if pos1 == pos2 => return,
|
||||
(Err(pos1), Err(pos2)) if pos1 == pos2 => return Vec::new(),
|
||||
_ => {}
|
||||
}
|
||||
|
||||
@@ -389,28 +375,27 @@ impl CompactSpaceDecompressor {
|
||||
});
|
||||
|
||||
let range = compact_from..=compact_to;
|
||||
|
||||
let scan_num_docs = doc_id_range.end - doc_id_range.start;
|
||||
let mut positions = Vec::new();
|
||||
|
||||
let step_size = 4;
|
||||
let cutoff = doc_id_range.start + scan_num_docs - scan_num_docs % step_size;
|
||||
let cutoff = self.params.num_vals - self.params.num_vals % step_size;
|
||||
|
||||
let mut push_if_in_range = |idx, val| {
|
||||
if range.contains(&val) {
|
||||
positions.push(idx);
|
||||
}
|
||||
};
|
||||
let get_val = |idx| self.params.bit_unpacker.get(idx, &self.data);
|
||||
let get_val = |idx| self.params.bit_unpacker.get(idx as u64, &self.data);
|
||||
// unrolled loop
|
||||
for idx in (doc_id_range.start..cutoff).step_by(step_size as usize) {
|
||||
for idx in (0..cutoff).step_by(step_size as usize) {
|
||||
let idx1 = idx;
|
||||
let idx2 = idx + 1;
|
||||
let idx3 = idx + 2;
|
||||
let idx4 = idx + 3;
|
||||
let val1 = get_val(idx1 as u32);
|
||||
let val2 = get_val(idx2 as u32);
|
||||
let val3 = get_val(idx3 as u32);
|
||||
let val4 = get_val(idx4 as u32);
|
||||
let val1 = get_val(idx1);
|
||||
let val2 = get_val(idx2);
|
||||
let val3 = get_val(idx3);
|
||||
let val4 = get_val(idx4);
|
||||
push_if_in_range(idx1, val1);
|
||||
push_if_in_range(idx2, val2);
|
||||
push_if_in_range(idx3, val3);
|
||||
@@ -418,15 +403,17 @@ impl CompactSpaceDecompressor {
|
||||
}
|
||||
|
||||
// handle rest
|
||||
for idx in cutoff..doc_id_range.end {
|
||||
push_if_in_range(idx, get_val(idx as u32));
|
||||
for idx in cutoff..self.params.num_vals {
|
||||
push_if_in_range(idx, get_val(idx));
|
||||
}
|
||||
|
||||
positions
|
||||
}
|
||||
|
||||
#[inline]
|
||||
fn iter_compact(&self) -> impl Iterator<Item = u64> + '_ {
|
||||
(0..self.params.num_vals)
|
||||
.map(move |idx| self.params.bit_unpacker.get(idx, &self.data) as u64)
|
||||
.map(move |idx| self.params.bit_unpacker.get(idx as u64, &self.data) as u64)
|
||||
}
|
||||
|
||||
#[inline]
|
||||
@@ -438,7 +425,7 @@ impl CompactSpaceDecompressor {
|
||||
}
|
||||
|
||||
#[inline]
|
||||
pub fn get(&self, idx: u32) -> u128 {
|
||||
pub fn get(&self, idx: u64) -> u128 {
|
||||
let compact = self.params.bit_unpacker.get(idx, &self.data);
|
||||
self.compact_to_u128(compact)
|
||||
}
|
||||
@@ -465,7 +452,7 @@ mod tests {
|
||||
]
|
||||
.into_iter()
|
||||
.collect();
|
||||
let compact_space = get_compact_space(ips, ips.len() as u32, 11);
|
||||
let compact_space = get_compact_space(ips, ips.len() as u64, 11);
|
||||
let amplitude = compact_space.amplitude_compact_space();
|
||||
assert_eq!(amplitude, 17);
|
||||
assert_eq!(1, compact_space.u128_to_compact(2).unwrap());
|
||||
@@ -496,7 +483,7 @@ mod tests {
|
||||
#[test]
|
||||
fn compact_space_amplitude_test() {
|
||||
let ips = &[100000u128, 1000000].into_iter().collect();
|
||||
let compact_space = get_compact_space(ips, ips.len() as u32, 1);
|
||||
let compact_space = get_compact_space(ips, ips.len() as u64, 1);
|
||||
let amplitude = compact_space.amplitude_compact_space();
|
||||
assert_eq!(amplitude, 2);
|
||||
}
|
||||
@@ -504,21 +491,16 @@ mod tests {
|
||||
fn test_all(data: OwnedBytes, expected: &[u128]) {
|
||||
let decompressor = CompactSpaceDecompressor::open(data).unwrap();
|
||||
for (idx, expected_val) in expected.iter().cloned().enumerate() {
|
||||
let val = decompressor.get(idx as u32);
|
||||
let val = decompressor.get(idx as u64);
|
||||
assert_eq!(val, expected_val);
|
||||
|
||||
let test_range = |range: RangeInclusive<u128>| {
|
||||
let expected_positions = expected
|
||||
.iter()
|
||||
.positions(|val| range.contains(val))
|
||||
.map(|pos| pos as u32)
|
||||
.map(|pos| pos as u64)
|
||||
.collect::<Vec<_>>();
|
||||
let mut positions = Vec::new();
|
||||
decompressor.get_positions_for_value_range(
|
||||
range,
|
||||
0..decompressor.num_vals(),
|
||||
&mut positions,
|
||||
);
|
||||
let positions = decompressor.get_between_vals(range);
|
||||
assert_eq!(positions, expected_positions);
|
||||
};
|
||||
|
||||
@@ -533,7 +515,7 @@ mod tests {
|
||||
let mut out = Vec::new();
|
||||
serialize_u128(
|
||||
|| u128_vals.iter().cloned(),
|
||||
u128_vals.len() as u32,
|
||||
u128_vals.len() as u64,
|
||||
&mut out,
|
||||
)
|
||||
.unwrap();
|
||||
@@ -558,107 +540,24 @@ mod tests {
|
||||
];
|
||||
let data = test_aux_vals(vals);
|
||||
let decomp = CompactSpaceDecompressor::open(data).unwrap();
|
||||
let complete_range = 0..vals.len() as u32;
|
||||
for (pos, val) in vals.iter().enumerate() {
|
||||
let val = *val as u128;
|
||||
let pos = pos as u32;
|
||||
let mut positions = Vec::new();
|
||||
decomp.get_positions_for_value_range(val..=val, pos..pos + 1, &mut positions);
|
||||
assert_eq!(positions, vec![pos]);
|
||||
}
|
||||
|
||||
// handle docid range out of bounds
|
||||
let positions = get_positions_for_value_range_helper(&decomp, 0..=1, 1..u32::MAX);
|
||||
assert_eq!(positions, vec![]);
|
||||
|
||||
let positions =
|
||||
get_positions_for_value_range_helper(&decomp, 0..=1, complete_range.clone());
|
||||
let positions = decomp.get_between_vals(0..=1);
|
||||
assert_eq!(positions, vec![0]);
|
||||
let positions =
|
||||
get_positions_for_value_range_helper(&decomp, 0..=2, complete_range.clone());
|
||||
let positions = decomp.get_between_vals(0..=2);
|
||||
assert_eq!(positions, vec![0]);
|
||||
let positions =
|
||||
get_positions_for_value_range_helper(&decomp, 0..=3, complete_range.clone());
|
||||
let positions = decomp.get_between_vals(0..=3);
|
||||
assert_eq!(positions, vec![0, 2]);
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(
|
||||
&decomp,
|
||||
99999u128..=99999u128,
|
||||
complete_range.clone()
|
||||
),
|
||||
vec![3]
|
||||
);
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(
|
||||
&decomp,
|
||||
99999u128..=100000u128,
|
||||
complete_range.clone()
|
||||
),
|
||||
vec![3, 4]
|
||||
);
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(
|
||||
&decomp,
|
||||
99998u128..=100000u128,
|
||||
complete_range.clone()
|
||||
),
|
||||
vec![3, 4]
|
||||
);
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(
|
||||
&decomp,
|
||||
99998u128..=99999u128,
|
||||
complete_range.clone()
|
||||
),
|
||||
vec![3]
|
||||
);
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(
|
||||
&decomp,
|
||||
99998u128..=99998u128,
|
||||
complete_range.clone()
|
||||
),
|
||||
vec![]
|
||||
);
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(
|
||||
&decomp,
|
||||
333u128..=333u128,
|
||||
complete_range.clone()
|
||||
),
|
||||
vec![8]
|
||||
);
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(
|
||||
&decomp,
|
||||
332u128..=333u128,
|
||||
complete_range.clone()
|
||||
),
|
||||
vec![8]
|
||||
);
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(
|
||||
&decomp,
|
||||
332u128..=334u128,
|
||||
complete_range.clone()
|
||||
),
|
||||
vec![8]
|
||||
);
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(
|
||||
&decomp,
|
||||
333u128..=334u128,
|
||||
complete_range.clone()
|
||||
),
|
||||
vec![8]
|
||||
);
|
||||
assert_eq!(decomp.get_between_vals(99999u128..=99999u128), vec![3]);
|
||||
assert_eq!(decomp.get_between_vals(99999u128..=100000u128), vec![3, 4]);
|
||||
assert_eq!(decomp.get_between_vals(99998u128..=100000u128), vec![3, 4]);
|
||||
assert_eq!(decomp.get_between_vals(99998u128..=99999u128), vec![3]);
|
||||
assert_eq!(decomp.get_between_vals(99998u128..=99998u128), vec![]);
|
||||
assert_eq!(decomp.get_between_vals(333u128..=333u128), vec![8]);
|
||||
assert_eq!(decomp.get_between_vals(332u128..=333u128), vec![8]);
|
||||
assert_eq!(decomp.get_between_vals(332u128..=334u128), vec![8]);
|
||||
assert_eq!(decomp.get_between_vals(333u128..=334u128), vec![8]);
|
||||
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(
|
||||
&decomp,
|
||||
4_000_211_221u128..=5_000_000_000u128,
|
||||
complete_range.clone()
|
||||
),
|
||||
decomp.get_between_vals(4_000_211_221u128..=5_000_000_000u128),
|
||||
vec![6, 7]
|
||||
);
|
||||
}
|
||||
@@ -683,29 +582,12 @@ mod tests {
|
||||
];
|
||||
let data = test_aux_vals(vals);
|
||||
let decomp = CompactSpaceDecompressor::open(data).unwrap();
|
||||
let complete_range = 0..vals.len() as u32;
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(&decomp, 0..=5, complete_range.clone()),
|
||||
vec![]
|
||||
);
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(&decomp, 0..=100, complete_range.clone()),
|
||||
vec![0]
|
||||
);
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(&decomp, 0..=105, complete_range.clone()),
|
||||
vec![0]
|
||||
);
|
||||
}
|
||||
|
||||
fn get_positions_for_value_range_helper<C: Column<T> + ?Sized, T: PartialOrd>(
|
||||
column: &C,
|
||||
value_range: RangeInclusive<T>,
|
||||
doc_id_range: Range<u32>,
|
||||
) -> Vec<u32> {
|
||||
let mut positions = Vec::new();
|
||||
column.get_positions_for_value_range(value_range, doc_id_range, &mut positions);
|
||||
positions
|
||||
let positions = decomp.get_between_vals(0..=5);
|
||||
assert_eq!(positions, vec![]);
|
||||
let positions = decomp.get_between_vals(0..=100);
|
||||
assert_eq!(positions, vec![0]);
|
||||
let positions = decomp.get_between_vals(0..=105);
|
||||
assert_eq!(positions, vec![0]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -726,33 +608,13 @@ mod tests {
|
||||
5_000_000_000,
|
||||
];
|
||||
let mut out = Vec::new();
|
||||
serialize_u128(|| vals.iter().cloned(), vals.len() as u32, &mut out).unwrap();
|
||||
serialize_u128(|| vals.iter().cloned(), vals.len() as u64, &mut out).unwrap();
|
||||
let decomp = open_u128::<u128>(OwnedBytes::new(out)).unwrap();
|
||||
let complete_range = 0..vals.len() as u32;
|
||||
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(&*decomp, 199..=200, complete_range.clone()),
|
||||
vec![0]
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(&*decomp, 199..=201, complete_range.clone()),
|
||||
vec![0, 1]
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(&*decomp, 200..=200, complete_range.clone()),
|
||||
vec![0]
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
get_positions_for_value_range_helper(
|
||||
&*decomp,
|
||||
1_000_000..=1_000_000,
|
||||
complete_range.clone()
|
||||
),
|
||||
vec![11]
|
||||
);
|
||||
assert_eq!(decomp.get_between_vals(199..=200), vec![0]);
|
||||
assert_eq!(decomp.get_between_vals(199..=201), vec![0, 1]);
|
||||
assert_eq!(decomp.get_between_vals(200..=200), vec![0]);
|
||||
assert_eq!(decomp.get_between_vals(1_000_000..=1_000_000), vec![11]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
|
||||
@@ -199,9 +199,9 @@ mod tests {
|
||||
let actual_compression = out.len() as f32 / (data.len() as f32 * 8.0);
|
||||
|
||||
let reader = crate::open::<u64>(OwnedBytes::new(out)).unwrap();
|
||||
assert_eq!(reader.num_vals(), data.len() as u32);
|
||||
assert_eq!(reader.num_vals(), data.len() as u64);
|
||||
for (doc, orig_val) in data.iter().copied().enumerate() {
|
||||
let val = reader.get_val(doc as u32);
|
||||
let val = reader.get_val(doc as u64);
|
||||
assert_eq!(
|
||||
val, orig_val,
|
||||
"val `{val}` does not match orig_val {orig_val:?}, in data set {name}, data \
|
||||
@@ -211,18 +211,13 @@ mod tests {
|
||||
|
||||
if !data.is_empty() {
|
||||
let test_rand_idx = rand::thread_rng().gen_range(0..=data.len() - 1);
|
||||
let expected_positions: Vec<u32> = data
|
||||
let expected_positions: Vec<u64> = data
|
||||
.iter()
|
||||
.enumerate()
|
||||
.filter(|(_, el)| **el == data[test_rand_idx])
|
||||
.map(|(pos, _)| pos as u32)
|
||||
.map(|(pos, _)| pos as u64)
|
||||
.collect();
|
||||
let mut positions = Vec::new();
|
||||
reader.get_positions_for_value_range(
|
||||
data[test_rand_idx]..=data[test_rand_idx],
|
||||
0..data.len() as u32,
|
||||
&mut positions,
|
||||
);
|
||||
let positions = reader.get_between_vals(data[test_rand_idx]..=data[test_rand_idx]);
|
||||
assert_eq!(expected_positions, positions);
|
||||
}
|
||||
Some((estimation, actual_compression))
|
||||
@@ -434,7 +429,7 @@ mod bench {
|
||||
b.iter(|| {
|
||||
let mut sum = 0u64;
|
||||
for pos in value_iter() {
|
||||
let val = col.get_val(pos as u32);
|
||||
let val = col.get_val(pos as u64);
|
||||
sum = sum.wrapping_add(val);
|
||||
}
|
||||
sum
|
||||
@@ -446,7 +441,7 @@ mod bench {
|
||||
b.iter(|| {
|
||||
let mut sum = 0u64;
|
||||
for pos in value_iter() {
|
||||
let val = col.get_val(pos as u32);
|
||||
let val = col.get_val(pos as u64);
|
||||
sum = sum.wrapping_add(val);
|
||||
}
|
||||
sum
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
use std::io;
|
||||
use std::num::NonZeroU32;
|
||||
use std::num::NonZeroU64;
|
||||
|
||||
use common::{BinarySerializable, VInt};
|
||||
|
||||
@@ -29,7 +29,7 @@ pub struct Line {
|
||||
/// compute_slope(y0, y1)
|
||||
/// = compute_slope(y0 + X % 2^64, y1 + X % 2^64)
|
||||
/// `
|
||||
fn compute_slope(y0: u64, y1: u64, num_vals: NonZeroU32) -> u64 {
|
||||
fn compute_slope(y0: u64, y1: u64, num_vals: NonZeroU64) -> u64 {
|
||||
let dy = y1.wrapping_sub(y0);
|
||||
let sign = dy <= (1 << 63);
|
||||
let abs_dy = if sign {
|
||||
@@ -43,7 +43,7 @@ fn compute_slope(y0: u64, y1: u64, num_vals: NonZeroU32) -> u64 {
|
||||
return 0u64;
|
||||
}
|
||||
|
||||
let abs_slope = (abs_dy << 32) / num_vals.get() as u64;
|
||||
let abs_slope = (abs_dy << 32) / num_vals.get();
|
||||
if sign {
|
||||
abs_slope
|
||||
} else {
|
||||
@@ -62,8 +62,8 @@ fn compute_slope(y0: u64, y1: u64, num_vals: NonZeroU32) -> u64 {
|
||||
|
||||
impl Line {
|
||||
#[inline(always)]
|
||||
pub fn eval(&self, x: u32) -> u64 {
|
||||
let linear_part = ((x as u64).wrapping_mul(self.slope) >> 32) as i32 as u64;
|
||||
pub fn eval(&self, x: u64) -> u64 {
|
||||
let linear_part = (x.wrapping_mul(self.slope) >> 32) as i32 as u64;
|
||||
self.intercept.wrapping_add(linear_part)
|
||||
}
|
||||
|
||||
@@ -75,7 +75,7 @@ impl Line {
|
||||
Self::train_from(
|
||||
first_val,
|
||||
last_val,
|
||||
num_vals as u32,
|
||||
num_vals,
|
||||
sample_positions_and_values.iter().cloned(),
|
||||
)
|
||||
}
|
||||
@@ -84,11 +84,11 @@ impl Line {
|
||||
fn train_from(
|
||||
first_val: u64,
|
||||
last_val: u64,
|
||||
num_vals: u32,
|
||||
num_vals: u64,
|
||||
positions_and_values: impl Iterator<Item = (u64, u64)>,
|
||||
) -> Self {
|
||||
// TODO replace with let else
|
||||
let idx_last_val = if let Some(idx_last_val) = NonZeroU32::new(num_vals - 1) {
|
||||
let idx_last_val = if let Some(idx_last_val) = NonZeroU64::new(num_vals - 1) {
|
||||
idx_last_val
|
||||
} else {
|
||||
return Line::default();
|
||||
@@ -129,7 +129,7 @@ impl Line {
|
||||
};
|
||||
let heuristic_shift = y0.wrapping_sub(MID_POINT);
|
||||
line.intercept = positions_and_values
|
||||
.map(|(pos, y)| y.wrapping_sub(line.eval(pos as u32)))
|
||||
.map(|(pos, y)| y.wrapping_sub(line.eval(pos)))
|
||||
.min_by_key(|&val| val.wrapping_sub(heuristic_shift))
|
||||
.unwrap_or(0u64); //< Never happens.
|
||||
line
|
||||
@@ -199,7 +199,7 @@ mod tests {
|
||||
let line = Line::train(&VecColumn::from(&ys));
|
||||
ys.iter()
|
||||
.enumerate()
|
||||
.map(|(x, y)| y.wrapping_sub(line.eval(x as u32)))
|
||||
.map(|(x, y)| y.wrapping_sub(line.eval(x as u64)))
|
||||
.max()
|
||||
}
|
||||
|
||||
|
||||
@@ -19,7 +19,7 @@ pub struct LinearReader {
|
||||
|
||||
impl Column for LinearReader {
|
||||
#[inline]
|
||||
fn get_val(&self, doc: u32) -> u64 {
|
||||
fn get_val(&self, doc: u64) -> u64 {
|
||||
let interpoled_val: u64 = self.linear_params.line.eval(doc);
|
||||
let bitpacked_diff = self.linear_params.bit_unpacker.get(doc, &self.data);
|
||||
interpoled_val.wrapping_add(bitpacked_diff)
|
||||
@@ -37,7 +37,7 @@ impl Column for LinearReader {
|
||||
}
|
||||
|
||||
#[inline]
|
||||
fn num_vals(&self) -> u32 {
|
||||
fn num_vals(&self) -> u64 {
|
||||
self.header.num_vals
|
||||
}
|
||||
}
|
||||
@@ -93,7 +93,7 @@ impl FastFieldCodec for LinearCodec {
|
||||
.iter()
|
||||
.enumerate()
|
||||
.map(|(pos, actual_value)| {
|
||||
let calculated_value = line.eval(pos as u32);
|
||||
let calculated_value = line.eval(pos as u64);
|
||||
actual_value.wrapping_sub(calculated_value)
|
||||
})
|
||||
.max()
|
||||
@@ -108,7 +108,7 @@ impl FastFieldCodec for LinearCodec {
|
||||
|
||||
let mut bit_packer = BitPacker::new();
|
||||
for (pos, actual_value) in column.iter().enumerate() {
|
||||
let calculated_value = line.eval(pos as u32);
|
||||
let calculated_value = line.eval(pos as u64);
|
||||
let offset = actual_value.wrapping_sub(calculated_value);
|
||||
bit_packer.write(offset, num_bits, write)?;
|
||||
}
|
||||
@@ -140,7 +140,7 @@ impl FastFieldCodec for LinearCodec {
|
||||
let estimated_bit_width = sample_positions_and_values
|
||||
.into_iter()
|
||||
.map(|(pos, actual_value)| {
|
||||
let interpolated_val = line.eval(pos as u32);
|
||||
let interpolated_val = line.eval(pos as u64);
|
||||
actual_value.wrapping_sub(interpolated_val)
|
||||
})
|
||||
.map(|diff| ((diff as f32 * 1.5) * 2.0) as u64)
|
||||
|
||||
@@ -90,7 +90,7 @@ fn bench_ip() {
|
||||
{
|
||||
let mut data = vec![];
|
||||
for dataset in dataset.chunks(500_000) {
|
||||
serialize_u128(|| dataset.iter().cloned(), dataset.len() as u32, &mut data).unwrap();
|
||||
serialize_u128(|| dataset.iter().cloned(), dataset.len() as u64, &mut data).unwrap();
|
||||
}
|
||||
let compression = data.len() as f64 / (dataset.len() * 16) as f64;
|
||||
println!("Compression 50_000 chunks {:.4}", compression);
|
||||
@@ -103,7 +103,7 @@ fn bench_ip() {
|
||||
let mut data = vec![];
|
||||
{
|
||||
print_time!("creation");
|
||||
serialize_u128(|| dataset.iter().cloned(), dataset.len() as u32, &mut data).unwrap();
|
||||
serialize_u128(|| dataset.iter().cloned(), dataset.len() as u64, &mut data).unwrap();
|
||||
}
|
||||
|
||||
let compression = data.len() as f64 / (dataset.len() * 16) as f64;
|
||||
@@ -115,15 +115,9 @@ fn bench_ip() {
|
||||
|
||||
let decompressor = open_u128::<u128>(OwnedBytes::new(data)).unwrap();
|
||||
// Sample some ranges
|
||||
let mut doc_values = Vec::new();
|
||||
for value in dataset.iter().take(1110).skip(1100).cloned() {
|
||||
doc_values.clear();
|
||||
print_time!("get range");
|
||||
decompressor.get_positions_for_value_range(
|
||||
value..=value,
|
||||
0..decompressor.num_vals(),
|
||||
&mut doc_values,
|
||||
);
|
||||
let doc_values = decompressor.get_between_vals(value..=value);
|
||||
println!("{:?}", doc_values.len());
|
||||
}
|
||||
}
|
||||
|
||||
@@ -46,14 +46,14 @@ use crate::{
|
||||
#[derive(Debug, Copy, Clone)]
|
||||
pub struct NormalizedHeader {
|
||||
/// The number of values in the underlying column.
|
||||
pub num_vals: u32,
|
||||
pub num_vals: u64,
|
||||
/// The max value of the underlying column.
|
||||
pub max_value: u64,
|
||||
}
|
||||
|
||||
#[derive(Debug, Copy, Clone)]
|
||||
pub(crate) struct Header {
|
||||
pub num_vals: u32,
|
||||
pub num_vals: u64,
|
||||
pub min_value: u64,
|
||||
pub max_value: u64,
|
||||
pub gcd: Option<NonZeroU64>,
|
||||
@@ -110,7 +110,7 @@ pub fn normalize_column<C: Column>(
|
||||
|
||||
impl BinarySerializable for Header {
|
||||
fn serialize<W: io::Write>(&self, writer: &mut W) -> io::Result<()> {
|
||||
VInt(self.num_vals as u64).serialize(writer)?;
|
||||
VInt(self.num_vals).serialize(writer)?;
|
||||
VInt(self.min_value).serialize(writer)?;
|
||||
VInt(self.max_value - self.min_value).serialize(writer)?;
|
||||
if let Some(gcd) = self.gcd {
|
||||
@@ -123,7 +123,7 @@ impl BinarySerializable for Header {
|
||||
}
|
||||
|
||||
fn deserialize<R: io::Read>(reader: &mut R) -> io::Result<Self> {
|
||||
let num_vals = VInt::deserialize(reader)?.0 as u32;
|
||||
let num_vals = VInt::deserialize(reader)?.0;
|
||||
let min_value = VInt::deserialize(reader)?.0;
|
||||
let amplitude = VInt::deserialize(reader)?.0;
|
||||
let max_value = min_value + amplitude;
|
||||
@@ -164,7 +164,7 @@ pub fn estimate<T: MonotonicallyMappableToU64>(
|
||||
/// Serializes u128 values with the compact space codec.
|
||||
pub fn serialize_u128<F: Fn() -> I, I: Iterator<Item = u128>>(
|
||||
iter_gen: F,
|
||||
num_vals: u32,
|
||||
num_vals: u64,
|
||||
output: &mut impl io::Write,
|
||||
) -> io::Result<()> {
|
||||
// TODO write header, to later support more codecs
|
||||
|
||||
@@ -62,20 +62,6 @@ fn word<'a>() -> impl Parser<&'a str, Output = String> {
|
||||
})
|
||||
}
|
||||
|
||||
// word variant that allows more characters, e.g. for range queries that don't allow field
|
||||
// specifier
|
||||
fn relaxed_word<'a>() -> impl Parser<&'a str, Output = String> {
|
||||
(
|
||||
satisfy(|c: char| {
|
||||
!c.is_whitespace() && !['`', '{', '}', '"', '[', ']', '(', ')'].contains(&c)
|
||||
}),
|
||||
many(satisfy(|c: char| {
|
||||
!c.is_whitespace() && !['{', '}', '"', '[', ']', '(', ')'].contains(&c)
|
||||
})),
|
||||
)
|
||||
.map(|(s1, s2): (char, String)| format!("{}{}", s1, s2))
|
||||
}
|
||||
|
||||
/// Parses a date time according to rfc3339
|
||||
/// 2015-08-02T18:54:42+02
|
||||
/// 2021-04-13T19:46:26.266051969+00:00
|
||||
@@ -195,8 +181,8 @@ fn spaces1<'a>() -> impl Parser<&'a str, Output = ()> {
|
||||
fn range<'a>() -> impl Parser<&'a str, Output = UserInputLeaf> {
|
||||
let range_term_val = || {
|
||||
attempt(date_time())
|
||||
.or(word())
|
||||
.or(negative_number())
|
||||
.or(relaxed_word())
|
||||
.or(char('*').with(value("*".to_string())))
|
||||
};
|
||||
|
||||
@@ -663,34 +649,6 @@ mod test {
|
||||
.expect("Cannot parse date range")
|
||||
.0;
|
||||
assert_eq!(res6, expected_flexible_dates);
|
||||
// IP Range Unbounded
|
||||
let expected_weight = UserInputLeaf::Range {
|
||||
field: Some("ip".to_string()),
|
||||
lower: UserInputBound::Inclusive("::1".to_string()),
|
||||
upper: UserInputBound::Unbounded,
|
||||
};
|
||||
let res1 = range()
|
||||
.parse("ip: >=::1")
|
||||
.expect("Cannot parse ip v6 format")
|
||||
.0;
|
||||
let res2 = range()
|
||||
.parse("ip:[::1 TO *}")
|
||||
.expect("Cannot parse ip v6 format")
|
||||
.0;
|
||||
assert_eq!(res1, expected_weight);
|
||||
assert_eq!(res2, expected_weight);
|
||||
|
||||
// IP Range Bounded
|
||||
let expected_weight = UserInputLeaf::Range {
|
||||
field: Some("ip".to_string()),
|
||||
lower: UserInputBound::Inclusive("::0.0.0.50".to_string()),
|
||||
upper: UserInputBound::Exclusive("::0.0.0.52".to_string()),
|
||||
};
|
||||
let res1 = range()
|
||||
.parse("ip:[::0.0.0.50 TO ::0.0.0.52}")
|
||||
.expect("Cannot parse ip v6 format")
|
||||
.0;
|
||||
assert_eq!(res1, expected_weight);
|
||||
}
|
||||
|
||||
#[test]
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
|
||||
use std::collections::HashMap;
|
||||
|
||||
use rustc_hash::FxHashMap;
|
||||
use fnv::FnvHashMap;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use super::agg_req::BucketAggregationInternal;
|
||||
@@ -145,7 +145,7 @@ pub enum BucketEntries<T> {
|
||||
/// Vector format bucket entries
|
||||
Vec(Vec<T>),
|
||||
/// HashMap format bucket entries
|
||||
HashMap(FxHashMap<String, T>),
|
||||
HashMap(FnvHashMap<String, T>),
|
||||
}
|
||||
|
||||
/// This is the default entry for a bucket, which contains a key, count, and optionally
|
||||
|
||||
@@ -331,10 +331,10 @@ impl SegmentHistogramCollector {
|
||||
.expect("unexpected fast field cardinatility");
|
||||
let mut iter = doc.chunks_exact(4);
|
||||
for docs in iter.by_ref() {
|
||||
let val0 = self.f64_from_fastfield_u64(accessor.get_val(docs[0]));
|
||||
let val1 = self.f64_from_fastfield_u64(accessor.get_val(docs[1]));
|
||||
let val2 = self.f64_from_fastfield_u64(accessor.get_val(docs[2]));
|
||||
let val3 = self.f64_from_fastfield_u64(accessor.get_val(docs[3]));
|
||||
let val0 = self.f64_from_fastfield_u64(accessor.get_val(docs[0] as u64));
|
||||
let val1 = self.f64_from_fastfield_u64(accessor.get_val(docs[1] as u64));
|
||||
let val2 = self.f64_from_fastfield_u64(accessor.get_val(docs[2] as u64));
|
||||
let val3 = self.f64_from_fastfield_u64(accessor.get_val(docs[3] as u64));
|
||||
|
||||
let bucket_pos0 = get_bucket_num(val0);
|
||||
let bucket_pos1 = get_bucket_num(val1);
|
||||
@@ -371,7 +371,7 @@ impl SegmentHistogramCollector {
|
||||
)?;
|
||||
}
|
||||
for &doc in iter.remainder() {
|
||||
let val = f64_from_fastfield_u64(accessor.get_val(doc), &self.field_type);
|
||||
let val = f64_from_fastfield_u64(accessor.get_val(doc as u64), &self.field_type);
|
||||
if !bounds.contains(val) {
|
||||
continue;
|
||||
}
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
use std::fmt::Debug;
|
||||
use std::ops::Range;
|
||||
|
||||
use rustc_hash::FxHashMap;
|
||||
use fnv::FnvHashMap;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use crate::aggregation::agg_req_with_accessor::{
|
||||
@@ -176,7 +176,7 @@ impl SegmentRangeCollector {
|
||||
) -> crate::Result<IntermediateBucketResult> {
|
||||
let field_type = self.field_type;
|
||||
|
||||
let buckets: FxHashMap<SerializedKey, IntermediateRangeBucketEntry> = self
|
||||
let buckets: FnvHashMap<SerializedKey, IntermediateRangeBucketEntry> = self
|
||||
.buckets
|
||||
.into_iter()
|
||||
.map(move |range_bucket| {
|
||||
@@ -263,10 +263,10 @@ impl SegmentRangeCollector {
|
||||
.as_single()
|
||||
.expect("unexpected fast field cardinality");
|
||||
for docs in iter.by_ref() {
|
||||
let val1 = accessor.get_val(docs[0]);
|
||||
let val2 = accessor.get_val(docs[1]);
|
||||
let val3 = accessor.get_val(docs[2]);
|
||||
let val4 = accessor.get_val(docs[3]);
|
||||
let val1 = accessor.get_val(docs[0] as u64);
|
||||
let val2 = accessor.get_val(docs[1] as u64);
|
||||
let val3 = accessor.get_val(docs[2] as u64);
|
||||
let val4 = accessor.get_val(docs[3] as u64);
|
||||
let bucket_pos1 = self.get_bucket_pos(val1);
|
||||
let bucket_pos2 = self.get_bucket_pos(val2);
|
||||
let bucket_pos3 = self.get_bucket_pos(val3);
|
||||
@@ -278,7 +278,7 @@ impl SegmentRangeCollector {
|
||||
self.increment_bucket(bucket_pos4, docs[3], &bucket_with_accessor.sub_aggregation)?;
|
||||
}
|
||||
for &doc in iter.remainder() {
|
||||
let val = accessor.get_val(doc);
|
||||
let val = accessor.get_val(doc as u64);
|
||||
let bucket_pos = self.get_bucket_pos(val);
|
||||
self.increment_bucket(bucket_pos, doc, &bucket_with_accessor.sub_aggregation)?;
|
||||
}
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
use std::fmt::Debug;
|
||||
|
||||
use fnv::FnvHashMap;
|
||||
use itertools::Itertools;
|
||||
use rustc_hash::FxHashMap;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use super::{CustomOrder, Order, OrderTarget};
|
||||
@@ -199,7 +199,7 @@ impl TermsAggregationInternal {
|
||||
#[derive(Clone, Debug, PartialEq)]
|
||||
/// Container to store term_ids and their buckets.
|
||||
struct TermBuckets {
|
||||
pub(crate) entries: FxHashMap<u32, TermBucketEntry>,
|
||||
pub(crate) entries: FnvHashMap<u32, TermBucketEntry>,
|
||||
blueprint: Option<SegmentAggregationResultsCollector>,
|
||||
}
|
||||
|
||||
@@ -397,7 +397,7 @@ impl SegmentTermCollector {
|
||||
.expect("internal error: inverted index not loaded for term aggregation");
|
||||
let term_dict = inverted_index.terms();
|
||||
|
||||
let mut dict: FxHashMap<String, IntermediateTermBucketEntry> = Default::default();
|
||||
let mut dict: FnvHashMap<String, IntermediateTermBucketEntry> = Default::default();
|
||||
let mut buffer = vec![];
|
||||
for (term_id, entry) in entries {
|
||||
term_dict
|
||||
@@ -1129,9 +1129,9 @@ mod tests {
|
||||
|
||||
assert_eq!(res["my_texts"]["buckets"][0]["key"], "terma");
|
||||
assert_eq!(res["my_texts"]["buckets"][0]["doc_count"], 4);
|
||||
assert_eq!(res["my_texts"]["buckets"][1]["key"], "termc");
|
||||
assert_eq!(res["my_texts"]["buckets"][1]["key"], "termb");
|
||||
assert_eq!(res["my_texts"]["buckets"][1]["doc_count"], 0);
|
||||
assert_eq!(res["my_texts"]["buckets"][2]["key"], "termb");
|
||||
assert_eq!(res["my_texts"]["buckets"][2]["key"], "termc");
|
||||
assert_eq!(res["my_texts"]["buckets"][2]["doc_count"], 0);
|
||||
assert_eq!(res["my_texts"]["sum_other_doc_count"], 0);
|
||||
assert_eq!(res["my_texts"]["doc_count_error_upper_bound"], 0);
|
||||
|
||||
@@ -5,8 +5,8 @@
|
||||
use std::cmp::Ordering;
|
||||
use std::collections::HashMap;
|
||||
|
||||
use fnv::FnvHashMap;
|
||||
use itertools::Itertools;
|
||||
use rustc_hash::FxHashMap;
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
use super::agg_req::{
|
||||
@@ -288,7 +288,7 @@ impl IntermediateBucketResult {
|
||||
.keyed;
|
||||
let buckets = if is_keyed {
|
||||
let mut bucket_map =
|
||||
FxHashMap::with_capacity_and_hasher(buckets.len(), Default::default());
|
||||
FnvHashMap::with_capacity_and_hasher(buckets.len(), Default::default());
|
||||
for bucket in buckets {
|
||||
bucket_map.insert(bucket.key.to_string(), bucket);
|
||||
}
|
||||
@@ -308,7 +308,7 @@ impl IntermediateBucketResult {
|
||||
|
||||
let buckets = if req.as_histogram().unwrap().keyed {
|
||||
let mut bucket_map =
|
||||
FxHashMap::with_capacity_and_hasher(buckets.len(), Default::default());
|
||||
FnvHashMap::with_capacity_and_hasher(buckets.len(), Default::default());
|
||||
for bucket in buckets {
|
||||
bucket_map.insert(bucket.key.to_string(), bucket);
|
||||
}
|
||||
@@ -396,13 +396,13 @@ impl IntermediateBucketResult {
|
||||
#[derive(Default, Clone, Debug, PartialEq, Serialize, Deserialize)]
|
||||
/// Range aggregation including error counts
|
||||
pub struct IntermediateRangeBucketResult {
|
||||
pub(crate) buckets: FxHashMap<SerializedKey, IntermediateRangeBucketEntry>,
|
||||
pub(crate) buckets: FnvHashMap<SerializedKey, IntermediateRangeBucketEntry>,
|
||||
}
|
||||
|
||||
#[derive(Default, Clone, Debug, PartialEq, Serialize, Deserialize)]
|
||||
/// Term aggregation including error counts
|
||||
pub struct IntermediateTermBucketResult {
|
||||
pub(crate) entries: FxHashMap<String, IntermediateTermBucketEntry>,
|
||||
pub(crate) entries: FnvHashMap<String, IntermediateTermBucketEntry>,
|
||||
pub(crate) sum_other_doc_count: u64,
|
||||
pub(crate) doc_count_error_upper_bound: u64,
|
||||
}
|
||||
@@ -499,8 +499,8 @@ trait MergeFruits {
|
||||
}
|
||||
|
||||
fn merge_maps<V: MergeFruits + Clone>(
|
||||
entries_left: &mut FxHashMap<SerializedKey, V>,
|
||||
mut entries_right: FxHashMap<SerializedKey, V>,
|
||||
entries_left: &mut FnvHashMap<SerializedKey, V>,
|
||||
mut entries_right: FnvHashMap<SerializedKey, V>,
|
||||
) {
|
||||
for (name, entry_left) in entries_left.iter_mut() {
|
||||
if let Some(entry_right) = entries_right.remove(name) {
|
||||
@@ -626,7 +626,7 @@ mod tests {
|
||||
|
||||
fn get_sub_test_tree(data: &[(String, u64)]) -> IntermediateAggregationResults {
|
||||
let mut map = HashMap::new();
|
||||
let mut buckets = FxHashMap::default();
|
||||
let mut buckets = FnvHashMap::default();
|
||||
for (key, doc_count) in data {
|
||||
buckets.insert(
|
||||
key.to_string(),
|
||||
@@ -653,7 +653,7 @@ mod tests {
|
||||
data: &[(String, u64, String, u64)],
|
||||
) -> IntermediateAggregationResults {
|
||||
let mut map = HashMap::new();
|
||||
let mut buckets: FxHashMap<_, _> = Default::default();
|
||||
let mut buckets: FnvHashMap<_, _> = Default::default();
|
||||
for (key, doc_count, sub_aggregation_key, sub_aggregation_count) in data {
|
||||
buckets.insert(
|
||||
key.to_string(),
|
||||
|
||||
@@ -60,10 +60,10 @@ impl SegmentAverageCollector {
|
||||
pub(crate) fn collect_block(&mut self, doc: &[DocId], field: &dyn Column<u64>) {
|
||||
let mut iter = doc.chunks_exact(4);
|
||||
for docs in iter.by_ref() {
|
||||
let val1 = field.get_val(docs[0]);
|
||||
let val2 = field.get_val(docs[1]);
|
||||
let val3 = field.get_val(docs[2]);
|
||||
let val4 = field.get_val(docs[3]);
|
||||
let val1 = field.get_val(docs[0] as u64);
|
||||
let val2 = field.get_val(docs[1] as u64);
|
||||
let val3 = field.get_val(docs[2] as u64);
|
||||
let val4 = field.get_val(docs[3] as u64);
|
||||
let val1 = f64_from_fastfield_u64(val1, &self.field_type);
|
||||
let val2 = f64_from_fastfield_u64(val2, &self.field_type);
|
||||
let val3 = f64_from_fastfield_u64(val3, &self.field_type);
|
||||
@@ -74,7 +74,7 @@ impl SegmentAverageCollector {
|
||||
self.data.collect(val4);
|
||||
}
|
||||
for &doc in iter.remainder() {
|
||||
let val = field.get_val(doc);
|
||||
let val = field.get_val(doc as u64);
|
||||
let val = f64_from_fastfield_u64(val, &self.field_type);
|
||||
self.data.collect(val);
|
||||
}
|
||||
|
||||
@@ -166,10 +166,10 @@ impl SegmentStatsCollector {
|
||||
pub(crate) fn collect_block(&mut self, doc: &[DocId], field: &dyn Column<u64>) {
|
||||
let mut iter = doc.chunks_exact(4);
|
||||
for docs in iter.by_ref() {
|
||||
let val1 = field.get_val(docs[0]);
|
||||
let val2 = field.get_val(docs[1]);
|
||||
let val3 = field.get_val(docs[2]);
|
||||
let val4 = field.get_val(docs[3]);
|
||||
let val1 = field.get_val(docs[0] as u64);
|
||||
let val2 = field.get_val(docs[1] as u64);
|
||||
let val3 = field.get_val(docs[2] as u64);
|
||||
let val4 = field.get_val(docs[3] as u64);
|
||||
let val1 = f64_from_fastfield_u64(val1, &self.field_type);
|
||||
let val2 = f64_from_fastfield_u64(val2, &self.field_type);
|
||||
let val3 = f64_from_fastfield_u64(val3, &self.field_type);
|
||||
@@ -180,7 +180,7 @@ impl SegmentStatsCollector {
|
||||
self.stats.collect(val4);
|
||||
}
|
||||
for &doc in iter.remainder() {
|
||||
let val = field.get_val(doc);
|
||||
let val = field.get_val(doc as u64);
|
||||
let val = f64_from_fastfield_u64(val, &self.field_type);
|
||||
self.stats.collect(val);
|
||||
}
|
||||
|
||||
@@ -177,7 +177,7 @@ where
|
||||
type Fruit = TSegmentCollector::Fruit;
|
||||
|
||||
fn collect(&mut self, doc: u32, score: Score) {
|
||||
let value = self.fast_field_reader.get_val(doc);
|
||||
let value = self.fast_field_reader.get_val(doc as u64);
|
||||
if (self.predicate)(value) {
|
||||
self.segment_collector.collect(doc, score)
|
||||
}
|
||||
|
||||
@@ -94,7 +94,7 @@ impl SegmentCollector for SegmentHistogramCollector {
|
||||
type Fruit = Vec<u64>;
|
||||
|
||||
fn collect(&mut self, doc: DocId, _score: Score) {
|
||||
let value = self.ff_reader.get_val(doc);
|
||||
let value = self.ff_reader.get_val(doc as u64);
|
||||
self.histogram_computer.add_value(value);
|
||||
}
|
||||
|
||||
|
||||
@@ -201,7 +201,7 @@ impl SegmentCollector for FastFieldSegmentCollector {
|
||||
type Fruit = Vec<u64>;
|
||||
|
||||
fn collect(&mut self, doc: DocId, _score: Score) {
|
||||
let val = self.reader.get_val(doc);
|
||||
let val = self.reader.get_val(doc as u64);
|
||||
self.vals.push(val);
|
||||
}
|
||||
|
||||
|
||||
@@ -137,7 +137,7 @@ struct ScorerByFastFieldReader {
|
||||
|
||||
impl CustomSegmentScorer<u64> for ScorerByFastFieldReader {
|
||||
fn score(&mut self, doc: DocId) -> u64 {
|
||||
self.ff_reader.get_val(doc)
|
||||
self.ff_reader.get_val(doc as u64)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -458,7 +458,7 @@ impl TopDocs {
|
||||
///
|
||||
/// // We can now define our actual scoring function
|
||||
/// move |doc: DocId, original_score: Score| {
|
||||
/// let popularity: u64 = popularity_reader.get_val(doc);
|
||||
/// let popularity: u64 = popularity_reader.get_val(doc as u64);
|
||||
/// // Well.. For the sake of the example we use a simple logarithm
|
||||
/// // function.
|
||||
/// let popularity_boost_score = ((2u64 + popularity) as Score).log2();
|
||||
@@ -567,8 +567,8 @@ impl TopDocs {
|
||||
///
|
||||
/// // We can now define our actual scoring function
|
||||
/// move |doc: DocId| {
|
||||
/// let popularity: u64 = popularity_reader.get_val(doc);
|
||||
/// let boosted: u64 = boosted_reader.get_val(doc);
|
||||
/// let popularity: u64 = popularity_reader.get_val(doc as u64);
|
||||
/// let boosted: u64 = boosted_reader.get_val(doc as u64);
|
||||
/// // Score do not have to be `f64` in tantivy.
|
||||
/// // Here we return a couple to get lexicographical order
|
||||
/// // for free.
|
||||
|
||||
@@ -32,9 +32,10 @@ impl BytesFastFieldReader {
|
||||
Ok(BytesFastFieldReader { idx_reader, values })
|
||||
}
|
||||
|
||||
fn range(&self, doc: DocId) -> Range<u32> {
|
||||
let start = self.idx_reader.get_val(doc) as u32;
|
||||
let end = self.idx_reader.get_val(doc + 1) as u32;
|
||||
fn range(&self, doc: DocId) -> Range<u64> {
|
||||
let idx = doc as u64;
|
||||
let start = self.idx_reader.get_val(idx);
|
||||
let end = self.idx_reader.get_val(idx + 1);
|
||||
start..end
|
||||
}
|
||||
|
||||
@@ -47,7 +48,7 @@ impl BytesFastFieldReader {
|
||||
/// Returns the length of the bytes associated with the given `doc`
|
||||
pub fn num_bytes(&self, doc: DocId) -> u64 {
|
||||
let range = self.range(doc);
|
||||
(range.end - range.start) as u64
|
||||
range.end - range.start
|
||||
}
|
||||
|
||||
/// Returns the overall number of bytes in this bytes fast field.
|
||||
@@ -57,7 +58,7 @@ impl BytesFastFieldReader {
|
||||
}
|
||||
|
||||
impl MultiValueLength for BytesFastFieldReader {
|
||||
fn get_range(&self, doc_id: DocId) -> std::ops::Range<u32> {
|
||||
fn get_range(&self, doc_id: DocId) -> std::ops::Range<u64> {
|
||||
self.range(doc_id)
|
||||
}
|
||||
fn get_len(&self, doc_id: DocId) -> u64 {
|
||||
|
||||
@@ -51,7 +51,7 @@ mod writer;
|
||||
/// for a doc_id
|
||||
pub trait MultiValueLength {
|
||||
/// returns the positions for a docid
|
||||
fn get_range(&self, doc_id: DocId) -> std::ops::Range<u32>;
|
||||
fn get_range(&self, doc_id: DocId) -> std::ops::Range<u64>;
|
||||
/// returns the num of values associated with a doc_id
|
||||
fn get_len(&self, doc_id: DocId) -> u64;
|
||||
/// returns the sum of num values for all doc_ids
|
||||
@@ -184,9 +184,9 @@ mod tests {
|
||||
#[test]
|
||||
pub fn test_fastfield() {
|
||||
let test_fastfield = fastfield_codecs::serialize_and_load(&[100u64, 200u64, 300u64][..]);
|
||||
assert_eq!(test_fastfield.get_val(0), 100);
|
||||
assert_eq!(test_fastfield.get_val(1), 200);
|
||||
assert_eq!(test_fastfield.get_val(2), 300);
|
||||
assert_eq!(test_fastfield.get_val(0u64), 100);
|
||||
assert_eq!(test_fastfield.get_val(1u64), 200);
|
||||
assert_eq!(test_fastfield.get_val(2u64), 300);
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -402,7 +402,7 @@ mod tests {
|
||||
assert_eq!(fast_field_reader.min_value(), -100i64);
|
||||
assert_eq!(fast_field_reader.max_value(), 9_999i64);
|
||||
for (doc, i) in (-100i64..10_000i64).enumerate() {
|
||||
assert_eq!(fast_field_reader.get_val(doc as u32), i);
|
||||
assert_eq!(fast_field_reader.get_val(doc as u64), i);
|
||||
}
|
||||
let mut buffer = vec![0i64; 100];
|
||||
fast_field_reader.get_range(53, &mut buffer[..]);
|
||||
@@ -484,7 +484,7 @@ mod tests {
|
||||
let fast_field_reader = open::<u64>(data)?;
|
||||
|
||||
for a in 0..n {
|
||||
assert_eq!(fast_field_reader.get_val(a as u32), permutation[a as usize]);
|
||||
assert_eq!(fast_field_reader.get_val(a as u64), permutation[a as usize]);
|
||||
}
|
||||
}
|
||||
Ok(())
|
||||
@@ -976,7 +976,7 @@ mod tests {
|
||||
let test_fastfield = open::<DateTime>(file.read_bytes()?)?;
|
||||
|
||||
for (i, time) in times.iter().enumerate() {
|
||||
assert_eq!(test_fastfield.get_val(i as u32), time.truncate(precision));
|
||||
assert_eq!(test_fastfield.get_val(i as u64), time.truncate(precision));
|
||||
}
|
||||
Ok(len)
|
||||
}
|
||||
|
||||
@@ -515,7 +515,7 @@ mod bench {
|
||||
for val in block {
|
||||
doc.add_u64(field, *val);
|
||||
}
|
||||
fast_field_writers.add_document(&doc).unwrap();
|
||||
fast_field_writers.add_document(&doc);
|
||||
}
|
||||
fast_field_writers
|
||||
.serialize(&mut serializer, &HashMap::new(), None)
|
||||
@@ -573,7 +573,7 @@ mod bench {
|
||||
for val in block {
|
||||
doc.add_u64(field, *val);
|
||||
}
|
||||
fast_field_writers.add_document(&doc).unwrap();
|
||||
fast_field_writers.add_document(&doc);
|
||||
}
|
||||
fast_field_writers
|
||||
.serialize(&mut serializer, &HashMap::new(), None)
|
||||
@@ -606,7 +606,7 @@ mod bench {
|
||||
for val in block {
|
||||
doc.add_u64(field, *val);
|
||||
}
|
||||
fast_field_writers.add_document(&doc).unwrap();
|
||||
fast_field_writers.add_document(&doc);
|
||||
}
|
||||
fast_field_writers
|
||||
.serialize(&mut serializer, &HashMap::new(), Some(&doc_id_mapping))
|
||||
|
||||
@@ -33,19 +33,19 @@ impl<Item: FastValue> MultiValuedFastFieldReader<Item> {
|
||||
/// Returns `[start, end)`, such that the values associated with
|
||||
/// the given document are `start..end`.
|
||||
#[inline]
|
||||
fn range(&self, doc: DocId) -> Range<u32> {
|
||||
let start = self.idx_reader.get_val(doc) as u32;
|
||||
let end = self.idx_reader.get_val(doc + 1) as u32;
|
||||
fn range(&self, doc: DocId) -> Range<u64> {
|
||||
let idx = doc as u64;
|
||||
let start = self.idx_reader.get_val(idx);
|
||||
let end = self.idx_reader.get_val(idx + 1);
|
||||
start..end
|
||||
}
|
||||
|
||||
/// Returns the array of values associated with the given `doc`.
|
||||
#[inline]
|
||||
fn get_vals_for_range(&self, range: Range<u32>, vals: &mut Vec<Item>) {
|
||||
fn get_vals_for_range(&self, range: Range<u64>, vals: &mut Vec<Item>) {
|
||||
let len = (range.end - range.start) as usize;
|
||||
vals.resize(len, Item::make_zero());
|
||||
self.vals_reader
|
||||
.get_range(range.start as u64, &mut vals[..]);
|
||||
self.vals_reader.get_range(range.start, &mut vals[..]);
|
||||
}
|
||||
|
||||
/// Returns the array of values associated with the given `doc`.
|
||||
@@ -88,7 +88,7 @@ impl<Item: FastValue> MultiValuedFastFieldReader<Item> {
|
||||
}
|
||||
|
||||
impl<Item: FastValue> MultiValueLength for MultiValuedFastFieldReader<Item> {
|
||||
fn get_range(&self, doc_id: DocId) -> Range<u32> {
|
||||
fn get_range(&self, doc_id: DocId) -> Range<u64> {
|
||||
self.range(doc_id)
|
||||
}
|
||||
fn get_len(&self, doc_id: DocId) -> u64 {
|
||||
@@ -127,9 +127,9 @@ impl<T: MonotonicallyMappableToU128> MultiValuedU128FastFieldReader<T> {
|
||||
/// Returns `[start, end)`, such that the values associated
|
||||
/// to the given document are `start..end`.
|
||||
#[inline]
|
||||
fn range(&self, doc: DocId) -> Range<u32> {
|
||||
let start = self.idx_reader.get_val(doc) as u32;
|
||||
let end = self.idx_reader.get_val(doc + 1) as u32;
|
||||
fn range(&self, doc: DocId) -> Range<u64> {
|
||||
let start = self.idx_reader.get_val(doc as u64);
|
||||
let end = self.idx_reader.get_val(doc as u64 + 1);
|
||||
start..end
|
||||
}
|
||||
|
||||
@@ -145,11 +145,10 @@ impl<T: MonotonicallyMappableToU128> MultiValuedU128FastFieldReader<T> {
|
||||
|
||||
/// Returns the array of values associated to the given `doc`.
|
||||
#[inline]
|
||||
fn get_vals_for_range(&self, range: Range<u32>, vals: &mut Vec<T>) {
|
||||
fn get_vals_for_range(&self, range: Range<u64>, vals: &mut Vec<T>) {
|
||||
let len = (range.end - range.start) as usize;
|
||||
vals.resize(len, T::from_u128(0));
|
||||
self.vals_reader
|
||||
.get_range(range.start as u64, &mut vals[..]);
|
||||
self.vals_reader.get_range(range.start, &mut vals[..]);
|
||||
}
|
||||
|
||||
/// Returns the array of values associated to the given `doc`.
|
||||
@@ -160,14 +159,8 @@ impl<T: MonotonicallyMappableToU128> MultiValuedU128FastFieldReader<T> {
|
||||
}
|
||||
|
||||
/// Returns all docids which are in the provided value range
|
||||
pub fn get_positions_for_value_range(
|
||||
&self,
|
||||
value_range: RangeInclusive<T>,
|
||||
doc_id_range: Range<u32>,
|
||||
) -> Vec<DocId> {
|
||||
let mut positions = Vec::new(); // TODO replace
|
||||
self.vals_reader
|
||||
.get_positions_for_value_range(value_range, doc_id_range, &mut positions);
|
||||
pub fn get_between_vals(&self, range: RangeInclusive<T>) -> Vec<DocId> {
|
||||
let positions = self.vals_reader.get_between_vals(range);
|
||||
|
||||
positions_to_docids(&positions, self.idx_reader.as_ref())
|
||||
}
|
||||
@@ -210,7 +203,7 @@ impl<T: MonotonicallyMappableToU128> MultiValuedU128FastFieldReader<T> {
|
||||
}
|
||||
|
||||
impl<T: MonotonicallyMappableToU128> MultiValueLength for MultiValuedU128FastFieldReader<T> {
|
||||
fn get_range(&self, doc_id: DocId) -> std::ops::Range<u32> {
|
||||
fn get_range(&self, doc_id: DocId) -> std::ops::Range<u64> {
|
||||
self.range(doc_id)
|
||||
}
|
||||
fn get_len(&self, doc_id: DocId) -> u64 {
|
||||
@@ -230,14 +223,14 @@ impl<T: MonotonicallyMappableToU128> MultiValueLength for MultiValuedU128FastFie
|
||||
///
|
||||
/// TODO: Instead of a linear scan we can employ a expotential search into binary search to match a
|
||||
/// docid to its value position.
|
||||
fn positions_to_docids<C: Column + ?Sized>(positions: &[u32], idx_reader: &C) -> Vec<DocId> {
|
||||
fn positions_to_docids<C: Column + ?Sized>(positions: &[u64], idx_reader: &C) -> Vec<DocId> {
|
||||
let mut docs = vec![];
|
||||
let mut cur_doc = 0u32;
|
||||
let mut last_doc = None;
|
||||
|
||||
for pos in positions {
|
||||
loop {
|
||||
let end = idx_reader.get_val(cur_doc + 1) as u32;
|
||||
let end = idx_reader.get_val(cur_doc as u64 + 1);
|
||||
if end > *pos {
|
||||
// avoid duplicates
|
||||
if Some(cur_doc) == last_doc {
|
||||
@@ -265,7 +258,7 @@ mod tests {
|
||||
|
||||
#[test]
|
||||
fn test_positions_to_docid() {
|
||||
let positions = vec![10u32, 11, 15, 20, 21, 22];
|
||||
let positions = vec![10u64, 11, 15, 20, 21, 22];
|
||||
|
||||
let offsets = vec![0, 10, 12, 15, 22, 23];
|
||||
{
|
||||
|
||||
@@ -3,7 +3,7 @@ use std::io;
|
||||
use fastfield_codecs::{
|
||||
Column, MonotonicallyMappableToU128, MonotonicallyMappableToU64, VecColumn,
|
||||
};
|
||||
use rustc_hash::FxHashMap;
|
||||
use fnv::FnvHashMap;
|
||||
|
||||
use super::get_fastfield_codecs_for_multivalue;
|
||||
use crate::fastfield::writer::unexpected_value;
|
||||
@@ -144,7 +144,7 @@ impl MultiValuedFastFieldWriter {
|
||||
pub fn serialize(
|
||||
mut self,
|
||||
serializer: &mut CompositeFastFieldSerializer,
|
||||
term_mapping_opt: Option<&FxHashMap<UnorderedTermId, TermOrdinal>>,
|
||||
term_mapping_opt: Option<&FnvHashMap<UnorderedTermId, TermOrdinal>>,
|
||||
doc_id_map: Option<&DocIdMapping>,
|
||||
) -> io::Result<()> {
|
||||
{
|
||||
@@ -219,7 +219,7 @@ pub(crate) struct MultivalueStartIndex<'a, C: Column> {
|
||||
|
||||
impl<'a, C: Column> MultivalueStartIndex<'a, C> {
|
||||
pub fn new(column: &'a C, doc_id_map: &'a DocIdMapping) -> Self {
|
||||
assert_eq!(column.num_vals(), doc_id_map.num_old_doc_ids() as u32 + 1);
|
||||
assert_eq!(column.num_vals(), doc_id_map.num_old_doc_ids() as u64 + 1);
|
||||
let (min, max) =
|
||||
tantivy_bitpacker::minmax(iter_remapped_multivalue_index(doc_id_map, column))
|
||||
.unwrap_or((0u64, 0u64));
|
||||
@@ -232,7 +232,7 @@ impl<'a, C: Column> MultivalueStartIndex<'a, C> {
|
||||
}
|
||||
}
|
||||
impl<'a, C: Column> Column for MultivalueStartIndex<'a, C> {
|
||||
fn get_val(&self, _idx: u32) -> u64 {
|
||||
fn get_val(&self, _idx: u64) -> u64 {
|
||||
unimplemented!()
|
||||
}
|
||||
|
||||
@@ -244,8 +244,8 @@ impl<'a, C: Column> Column for MultivalueStartIndex<'a, C> {
|
||||
self.max
|
||||
}
|
||||
|
||||
fn num_vals(&self) -> u32 {
|
||||
(self.doc_id_map.num_new_doc_ids() + 1) as u32
|
||||
fn num_vals(&self) -> u64 {
|
||||
(self.doc_id_map.num_new_doc_ids() + 1) as u64
|
||||
}
|
||||
|
||||
fn iter(&self) -> Box<dyn Iterator<Item = u64> + '_> {
|
||||
@@ -262,7 +262,7 @@ fn iter_remapped_multivalue_index<'a, C: Column>(
|
||||
) -> impl Iterator<Item = u64> + 'a {
|
||||
let mut offset = 0;
|
||||
std::iter::once(0).chain(doc_id_map.iter_old_doc_ids().map(move |old_doc| {
|
||||
let num_vals_for_doc = column.get_val(old_doc + 1) - column.get_val(old_doc);
|
||||
let num_vals_for_doc = column.get_val(old_doc as u64 + 1) - column.get_val(old_doc as u64);
|
||||
offset += num_vals_for_doc;
|
||||
offset as u64
|
||||
}))
|
||||
@@ -369,7 +369,7 @@ impl MultiValueU128FastFieldWriter {
|
||||
serializer.create_u128_fast_field_with_idx(
|
||||
self.field,
|
||||
iter_gen,
|
||||
self.vals.len() as u32,
|
||||
self.vals.len() as u64,
|
||||
1,
|
||||
)?;
|
||||
}
|
||||
|
||||
@@ -90,7 +90,7 @@ impl CompositeFastFieldSerializer {
|
||||
&mut self,
|
||||
field: Field,
|
||||
iter_gen: F,
|
||||
num_vals: u32,
|
||||
num_vals: u64,
|
||||
idx: usize,
|
||||
) -> io::Result<()> {
|
||||
let field_write = self.composite_write.for_field_with_idx(field, idx);
|
||||
|
||||
@@ -3,7 +3,7 @@ use std::io;
|
||||
|
||||
use common;
|
||||
use fastfield_codecs::{Column, MonotonicallyMappableToU128, MonotonicallyMappableToU64};
|
||||
use rustc_hash::FxHashMap;
|
||||
use fnv::FnvHashMap;
|
||||
use tantivy_bitpacker::BlockedBitpacker;
|
||||
|
||||
use super::multivalued::{MultiValueU128FastFieldWriter, MultiValuedFastFieldWriter};
|
||||
@@ -256,7 +256,7 @@ impl FastFieldsWriter {
|
||||
pub fn serialize(
|
||||
self,
|
||||
serializer: &mut CompositeFastFieldSerializer,
|
||||
mapping: &HashMap<Field, FxHashMap<UnorderedTermId, TermOrdinal>>,
|
||||
mapping: &HashMap<Field, FnvHashMap<UnorderedTermId, TermOrdinal>>,
|
||||
doc_id_map: Option<&DocIdMapping>,
|
||||
) -> io::Result<()> {
|
||||
for field_writer in self.term_id_writers {
|
||||
@@ -363,7 +363,7 @@ impl U128FastFieldWriter {
|
||||
serializer.create_u128_fast_field_with_idx(
|
||||
self.field,
|
||||
iter_gen,
|
||||
self.val_count as u32,
|
||||
self.val_count as u64,
|
||||
0,
|
||||
)?;
|
||||
} else {
|
||||
@@ -371,7 +371,7 @@ impl U128FastFieldWriter {
|
||||
serializer.create_u128_fast_field_with_idx(
|
||||
self.field,
|
||||
iter_gen,
|
||||
self.val_count as u32,
|
||||
self.val_count as u64,
|
||||
0,
|
||||
)?;
|
||||
}
|
||||
@@ -511,7 +511,7 @@ impl IntFastFieldWriter {
|
||||
vals: &self.vals,
|
||||
min_value: min,
|
||||
max_value: max,
|
||||
num_vals: self.val_count as u32,
|
||||
num_vals: self.val_count as u64,
|
||||
};
|
||||
|
||||
serializer.create_auto_detect_u64_fast_field(self.field, fastfield_accessor)?;
|
||||
@@ -526,7 +526,7 @@ struct WriterFastFieldAccessProvider<'map, 'bitp> {
|
||||
vals: &'bitp BlockedBitpacker,
|
||||
min_value: u64,
|
||||
max_value: u64,
|
||||
num_vals: u32,
|
||||
num_vals: u64,
|
||||
}
|
||||
|
||||
impl<'map, 'bitp> Column for WriterFastFieldAccessProvider<'map, 'bitp> {
|
||||
@@ -538,7 +538,7 @@ impl<'map, 'bitp> Column for WriterFastFieldAccessProvider<'map, 'bitp> {
|
||||
/// # Panics
|
||||
///
|
||||
/// May panic if `doc` is greater than the index.
|
||||
fn get_val(&self, _doc: u32) -> u64 {
|
||||
fn get_val(&self, _doc: u64) -> u64 {
|
||||
unimplemented!()
|
||||
}
|
||||
|
||||
@@ -562,7 +562,7 @@ impl<'map, 'bitp> Column for WriterFastFieldAccessProvider<'map, 'bitp> {
|
||||
self.max_value
|
||||
}
|
||||
|
||||
fn num_vals(&self) -> u32 {
|
||||
fn num_vals(&self) -> u64 {
|
||||
self.num_vals
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1472,7 +1472,7 @@ mod tests {
|
||||
let fast_field_reader = segment_reader.fast_fields().u64(id_field)?;
|
||||
let in_order_alive_ids: Vec<u64> = segment_reader
|
||||
.doc_ids_alive()
|
||||
.map(|doc| fast_field_reader.get_val(doc))
|
||||
.map(|doc| fast_field_reader.get_val(doc as u64))
|
||||
.collect();
|
||||
assert_eq!(&in_order_alive_ids[..], &[9, 8, 7, 6, 5, 4, 1, 0]);
|
||||
Ok(())
|
||||
@@ -1533,7 +1533,7 @@ mod tests {
|
||||
let fast_field_reader = segment_reader.fast_fields().u64(id_field)?;
|
||||
let in_order_alive_ids: Vec<u64> = segment_reader
|
||||
.doc_ids_alive()
|
||||
.map(|doc| fast_field_reader.get_val(doc))
|
||||
.map(|doc| fast_field_reader.get_val(doc as u64))
|
||||
.collect();
|
||||
assert_eq!(&in_order_alive_ids[..], &[9, 8, 7, 6, 5, 4, 2, 0]);
|
||||
Ok(())
|
||||
@@ -1619,7 +1619,6 @@ mod tests {
|
||||
);
|
||||
|
||||
let large_text_field = schema_builder.add_text_field("large_text_field", TEXT | STORED);
|
||||
let multi_text_fields = schema_builder.add_text_field("multi_text_fields", TEXT | STORED);
|
||||
|
||||
let multi_numbers = schema_builder.add_u64_field(
|
||||
"multi_numbers",
|
||||
@@ -1659,12 +1658,6 @@ mod tests {
|
||||
|
||||
let ip_exists = |id| id % 3 != 0; // 0 does not exist
|
||||
|
||||
let multi_text_field_text1 = "test1 test2 test3 test1 test2 test3";
|
||||
// rotate left
|
||||
let multi_text_field_text2 = "test2 test3 test1 test2 test3 test1";
|
||||
// rotate right
|
||||
let multi_text_field_text3 = "test3 test1 test2 test3 test1 test2";
|
||||
|
||||
for &op in ops {
|
||||
match op {
|
||||
IndexingOp::AddDoc { id } => {
|
||||
@@ -1685,10 +1678,7 @@ mod tests {
|
||||
multi_bools => (id % 2u64) == 0,
|
||||
text_field => id.to_string(),
|
||||
facet_field => facet,
|
||||
large_text_field => LOREM,
|
||||
multi_text_fields => multi_text_field_text1,
|
||||
multi_text_fields => multi_text_field_text2,
|
||||
multi_text_fields => multi_text_field_text3,
|
||||
large_text_field=> LOREM
|
||||
))?;
|
||||
} else {
|
||||
index_writer.add_document(doc!(id_field=>id,
|
||||
@@ -1706,10 +1696,7 @@ mod tests {
|
||||
multi_bools => (id % 2u64) == 0,
|
||||
text_field => id.to_string(),
|
||||
facet_field => facet,
|
||||
large_text_field => LOREM,
|
||||
multi_text_fields => multi_text_field_text1,
|
||||
multi_text_fields => multi_text_field_text2,
|
||||
multi_text_fields => multi_text_field_text3,
|
||||
large_text_field=> LOREM
|
||||
))?;
|
||||
}
|
||||
}
|
||||
@@ -1760,7 +1747,7 @@ mod tests {
|
||||
let ff_reader = segment_reader.fast_fields().u64(id_field).unwrap();
|
||||
segment_reader
|
||||
.doc_ids_alive()
|
||||
.map(move |doc| ff_reader.get_val(doc))
|
||||
.map(move |doc| ff_reader.get_val(doc as u64))
|
||||
})
|
||||
.collect();
|
||||
|
||||
@@ -1771,7 +1758,7 @@ mod tests {
|
||||
let ff_reader = segment_reader.fast_fields().u64(id_field).unwrap();
|
||||
segment_reader
|
||||
.doc_ids_alive()
|
||||
.map(move |doc| ff_reader.get_val(doc))
|
||||
.map(move |doc| ff_reader.get_val(doc as u64))
|
||||
})
|
||||
.collect();
|
||||
|
||||
@@ -1804,7 +1791,7 @@ mod tests {
|
||||
.flat_map(|segment_reader| {
|
||||
let ff_reader = segment_reader.fast_fields().ip_addr(ip_field).unwrap();
|
||||
segment_reader.doc_ids_alive().flat_map(move |doc| {
|
||||
let val = ff_reader.get_val(doc);
|
||||
let val = ff_reader.get_val(doc as u64);
|
||||
if val == Ipv6Addr::from_u128(0) {
|
||||
// TODO Fix null handling
|
||||
None
|
||||
@@ -1861,7 +1848,7 @@ mod tests {
|
||||
ff_reader.get_vals(doc, &mut vals);
|
||||
assert_eq!(vals.len(), 2);
|
||||
assert_eq!(vals[0], vals[1]);
|
||||
assert_eq!(id_reader.get_val(doc), vals[0]);
|
||||
assert_eq!(id_reader.get_val(doc as u64), vals[0]);
|
||||
|
||||
let mut bool_vals = vec![];
|
||||
bool_ff_reader.get_vals(doc, &mut bool_vals);
|
||||
@@ -1935,21 +1922,11 @@ mod tests {
|
||||
|
||||
for (existing_id, count) in &expected_ids_and_num_occurrences {
|
||||
let (existing_id, count) = (*existing_id, *count);
|
||||
let get_num_hits = |field| do_search(&existing_id.to_string(), field).len() as u64;
|
||||
assert_eq!(get_num_hits(text_field), count);
|
||||
assert_eq!(get_num_hits(i64_field), count);
|
||||
assert_eq!(get_num_hits(f64_field), count);
|
||||
assert_eq!(get_num_hits(id_field), count);
|
||||
|
||||
// Test multi text
|
||||
assert_eq!(
|
||||
do_search("\"test1 test2\"", multi_text_fields).len(),
|
||||
num_docs_expected
|
||||
);
|
||||
assert_eq!(
|
||||
do_search("\"test2 test3\"", multi_text_fields).len(),
|
||||
num_docs_expected
|
||||
);
|
||||
let assert_field = |field| do_search(&existing_id.to_string(), field).len() as u64;
|
||||
assert_eq!(assert_field(text_field), count);
|
||||
assert_eq!(assert_field(i64_field), count);
|
||||
assert_eq!(assert_field(f64_field), count);
|
||||
assert_eq!(assert_field(id_field), count);
|
||||
|
||||
// Test bytes
|
||||
let term = Term::from_field_bytes(bytes_field, existing_id.to_le_bytes().as_slice());
|
||||
@@ -2012,7 +1989,7 @@ mod tests {
|
||||
facet_reader
|
||||
.facet_from_ord(facet_ords[0], &mut facet)
|
||||
.unwrap();
|
||||
let id = ff_reader.get_val(doc_id);
|
||||
let id = ff_reader.get_val(doc_id as u64);
|
||||
let facet_expected = Facet::from(&("/cola/".to_string() + &id.to_string()));
|
||||
|
||||
assert_eq!(facet, facet_expected);
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
use fastfield_codecs::MonotonicallyMappableToU64;
|
||||
use fnv::FnvHashMap;
|
||||
use murmurhash32::murmurhash2;
|
||||
use rustc_hash::FxHashMap;
|
||||
|
||||
use crate::fastfield::FastValue;
|
||||
use crate::postings::{IndexingContext, IndexingPosition, PostingsWriter};
|
||||
@@ -52,7 +52,7 @@ use crate::{DatePrecision, DateTime, DocId, Term};
|
||||
/// path map to the same index position as long as the probability is relatively low.
|
||||
#[derive(Default)]
|
||||
struct IndexingPositionsPerPath {
|
||||
positions_per_path: FxHashMap<u32, IndexingPosition>,
|
||||
positions_per_path: FnvHashMap<u32, IndexingPosition>,
|
||||
}
|
||||
|
||||
impl IndexingPositionsPerPath {
|
||||
|
||||
@@ -368,7 +368,7 @@ impl IndexMerger {
|
||||
fast_field_serializer.create_u128_fast_field_with_idx(
|
||||
field,
|
||||
iter_gen,
|
||||
doc_id_mapping.len() as u32,
|
||||
doc_id_mapping.len() as u64,
|
||||
1,
|
||||
)?;
|
||||
|
||||
@@ -397,13 +397,13 @@ impl IndexMerger {
|
||||
let iter_gen = || {
|
||||
doc_id_mapping.iter_old_doc_addrs().map(|doc_addr| {
|
||||
let fast_field_reader = &fast_field_readers[doc_addr.segment_ord as usize];
|
||||
fast_field_reader.get_val(doc_addr.doc_id)
|
||||
fast_field_reader.get_val(doc_addr.doc_id as u64)
|
||||
})
|
||||
};
|
||||
fast_field_serializer.create_u128_fast_field_with_idx(
|
||||
field,
|
||||
iter_gen,
|
||||
doc_id_mapping.len() as u32,
|
||||
doc_id_mapping.len() as u64,
|
||||
0,
|
||||
)?;
|
||||
Ok(())
|
||||
@@ -510,8 +510,8 @@ impl IndexMerger {
|
||||
doc_id_reader_pair
|
||||
.into_iter()
|
||||
.kmerge_by(|a, b| {
|
||||
let val1 = a.2.get_val(a.0);
|
||||
let val2 = b.2.get_val(b.0);
|
||||
let val1 = a.2.get_val(a.0 as u64);
|
||||
let val2 = b.2.get_val(b.0 as u64);
|
||||
if sort_by_field.order == Order::Asc {
|
||||
val1 < val2
|
||||
} else {
|
||||
|
||||
@@ -190,13 +190,13 @@ mod tests {
|
||||
assert_eq!(fast_field.get_val(4), 2u64);
|
||||
assert_eq!(fast_field.get_val(3), 3u64);
|
||||
if force_disjunct_segment_sort_values {
|
||||
assert_eq!(fast_field.get_val(2), 20u64);
|
||||
assert_eq!(fast_field.get_val(1), 100u64);
|
||||
assert_eq!(fast_field.get_val(2u64), 20u64);
|
||||
assert_eq!(fast_field.get_val(1u64), 100u64);
|
||||
} else {
|
||||
assert_eq!(fast_field.get_val(2), 10u64);
|
||||
assert_eq!(fast_field.get_val(1), 20u64);
|
||||
assert_eq!(fast_field.get_val(2u64), 10u64);
|
||||
assert_eq!(fast_field.get_val(1u64), 20u64);
|
||||
}
|
||||
assert_eq!(fast_field.get_val(0), 1_000u64);
|
||||
assert_eq!(fast_field.get_val(0u64), 1_000u64);
|
||||
|
||||
// test new field norm mapping
|
||||
{
|
||||
@@ -545,7 +545,7 @@ mod bench_sorted_index_merge {
|
||||
// add values in order of the new doc_ids
|
||||
let mut val = 0;
|
||||
for (doc_id, _reader, field_reader) in sorted_doc_ids {
|
||||
val = field_reader.get_val(doc_id);
|
||||
val = field_reader.get_val(doc_id as u64);
|
||||
}
|
||||
|
||||
val
|
||||
|
||||
@@ -158,6 +158,7 @@ impl SegmentWriter {
|
||||
let doc_id = self.max_doc;
|
||||
let vals_grouped_by_field = doc
|
||||
.field_values()
|
||||
.iter()
|
||||
.sorted_by_key(|el| el.field())
|
||||
.group_by(|el| el.field());
|
||||
for (field, field_values) in &vals_grouped_by_field {
|
||||
@@ -501,17 +502,9 @@ mod tests {
|
||||
let reader = StoreReader::open(directory.open_read(path).unwrap(), 0).unwrap();
|
||||
let doc = reader.get(0).unwrap();
|
||||
|
||||
assert_eq!(doc.value_count(), 2);
|
||||
let mut field_value_iter = doc.field_values();
|
||||
assert_eq!(
|
||||
field_value_iter.next().unwrap().value().as_text(),
|
||||
Some("A")
|
||||
);
|
||||
assert_eq!(
|
||||
field_value_iter.next().unwrap().value().as_text(),
|
||||
Some("title")
|
||||
);
|
||||
assert!(field_value_iter.next().is_none());
|
||||
assert_eq!(doc.field_values().len(), 2);
|
||||
assert_eq!(doc.field_values()[0].value().as_text(), Some("A"));
|
||||
assert_eq!(doc.field_values()[1].value().as_text(), Some("title"));
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -792,90 +785,4 @@ mod tests {
|
||||
// On release this was [2, 1]. (< note the decreasing values)
|
||||
assert_eq!(positions, &[2, 5]);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_multiple_field_value_and_long_tokens() {
|
||||
let mut schema_builder = Schema::builder();
|
||||
let text = schema_builder.add_text_field("text", TEXT);
|
||||
let schema = schema_builder.build();
|
||||
let mut doc = Document::default();
|
||||
// This is a bit of a contrived example.
|
||||
let tokens = PreTokenizedString {
|
||||
text: "roller-coaster".to_string(),
|
||||
tokens: vec![Token {
|
||||
offset_from: 0,
|
||||
offset_to: 14,
|
||||
position: 0,
|
||||
text: "rollercoaster".to_string(),
|
||||
position_length: 2,
|
||||
}],
|
||||
};
|
||||
doc.add_pre_tokenized_text(text, tokens.clone());
|
||||
doc.add_pre_tokenized_text(text, tokens);
|
||||
let index = Index::create_in_ram(schema);
|
||||
let mut index_writer = index.writer_for_tests().unwrap();
|
||||
index_writer.add_document(doc).unwrap();
|
||||
index_writer.commit().unwrap();
|
||||
let reader = index.reader().unwrap();
|
||||
let searcher = reader.searcher();
|
||||
let seg_reader = searcher.segment_reader(0);
|
||||
let inv_index = seg_reader.inverted_index(text).unwrap();
|
||||
let term = Term::from_field_text(text, "rollercoaster");
|
||||
let mut postings = inv_index
|
||||
.read_postings(&term, IndexRecordOption::WithFreqsAndPositions)
|
||||
.unwrap()
|
||||
.unwrap();
|
||||
assert_eq!(postings.doc(), 0u32);
|
||||
let mut positions = Vec::new();
|
||||
postings.positions(&mut positions);
|
||||
assert_eq!(positions, &[0, 3]); //< as opposed to 0, 2 if we had a position length of 1.
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn test_last_token_not_ending_last() {
|
||||
let mut schema_builder = Schema::builder();
|
||||
let text = schema_builder.add_text_field("text", TEXT);
|
||||
let schema = schema_builder.build();
|
||||
let mut doc = Document::default();
|
||||
// This is a bit of a contrived example.
|
||||
let tokens = PreTokenizedString {
|
||||
text: "contrived-example".to_string(), //< I can't think of a use case where this corner case happens in real life.
|
||||
tokens: vec![
|
||||
Token {
|
||||
// Not the last token, yet ends after the last token.
|
||||
offset_from: 0,
|
||||
offset_to: 14,
|
||||
position: 0,
|
||||
text: "long_token".to_string(),
|
||||
position_length: 3,
|
||||
},
|
||||
Token {
|
||||
offset_from: 0,
|
||||
offset_to: 14,
|
||||
position: 1,
|
||||
text: "short".to_string(),
|
||||
position_length: 1,
|
||||
},
|
||||
],
|
||||
};
|
||||
doc.add_pre_tokenized_text(text, tokens);
|
||||
doc.add_text(text, "hello");
|
||||
let index = Index::create_in_ram(schema);
|
||||
let mut index_writer = index.writer_for_tests().unwrap();
|
||||
index_writer.add_document(doc).unwrap();
|
||||
index_writer.commit().unwrap();
|
||||
let reader = index.reader().unwrap();
|
||||
let searcher = reader.searcher();
|
||||
let seg_reader = searcher.segment_reader(0);
|
||||
let inv_index = seg_reader.inverted_index(text).unwrap();
|
||||
let term = Term::from_field_text(text, "hello");
|
||||
let mut postings = inv_index
|
||||
.read_postings(&term, IndexRecordOption::WithFreqsAndPositions)
|
||||
.unwrap()
|
||||
.unwrap();
|
||||
assert_eq!(postings.doc(), 0u32);
|
||||
let mut positions = Vec::new();
|
||||
postings.positions(&mut positions);
|
||||
assert_eq!(positions, &[4]); //< as opposed to 3 if we had a position length of 1.
|
||||
}
|
||||
}
|
||||
|
||||
@@ -12,7 +12,7 @@ pub(crate) struct RemappedDocIdColumn<'a> {
|
||||
fast_field_readers: Vec<Arc<dyn Column<u64>>>,
|
||||
min_value: u64,
|
||||
max_value: u64,
|
||||
num_vals: u32,
|
||||
num_vals: u64,
|
||||
}
|
||||
|
||||
fn compute_min_max_val(
|
||||
@@ -32,7 +32,7 @@ fn compute_min_max_val(
|
||||
// we need to recompute the max / min
|
||||
segment_reader
|
||||
.doc_ids_alive()
|
||||
.map(|doc_id| u64_reader.get_val(doc_id))
|
||||
.map(|doc_id| u64_reader.get_val(doc_id as u64))
|
||||
.minmax()
|
||||
.into_option()
|
||||
}
|
||||
@@ -73,13 +73,13 @@ impl<'a> RemappedDocIdColumn<'a> {
|
||||
fast_field_readers,
|
||||
min_value,
|
||||
max_value,
|
||||
num_vals: doc_id_mapping.len() as u32,
|
||||
num_vals: doc_id_mapping.len() as u64,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl<'a> Column for RemappedDocIdColumn<'a> {
|
||||
fn get_val(&self, _doc: u32) -> u64 {
|
||||
fn get_val(&self, _doc: u64) -> u64 {
|
||||
unimplemented!()
|
||||
}
|
||||
|
||||
@@ -90,7 +90,7 @@ impl<'a> Column for RemappedDocIdColumn<'a> {
|
||||
.map(|old_doc_addr| {
|
||||
let fast_field_reader =
|
||||
&self.fast_field_readers[old_doc_addr.segment_ord as usize];
|
||||
fast_field_reader.get_val(old_doc_addr.doc_id)
|
||||
fast_field_reader.get_val(old_doc_addr.doc_id as u64)
|
||||
}),
|
||||
)
|
||||
}
|
||||
@@ -102,7 +102,7 @@ impl<'a> Column for RemappedDocIdColumn<'a> {
|
||||
self.max_value
|
||||
}
|
||||
|
||||
fn num_vals(&self) -> u32 {
|
||||
fn num_vals(&self) -> u64 {
|
||||
self.num_vals
|
||||
}
|
||||
}
|
||||
|
||||
@@ -13,7 +13,7 @@ pub(crate) struct RemappedDocIdMultiValueColumn<'a> {
|
||||
fast_field_readers: Vec<MultiValuedFastFieldReader<u64>>,
|
||||
min_value: u64,
|
||||
max_value: u64,
|
||||
num_vals: u32,
|
||||
num_vals: u64,
|
||||
}
|
||||
|
||||
impl<'a> RemappedDocIdMultiValueColumn<'a> {
|
||||
@@ -61,13 +61,13 @@ impl<'a> RemappedDocIdMultiValueColumn<'a> {
|
||||
fast_field_readers,
|
||||
min_value,
|
||||
max_value,
|
||||
num_vals: num_vals as u32,
|
||||
num_vals: num_vals as u64,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl<'a> Column for RemappedDocIdMultiValueColumn<'a> {
|
||||
fn get_val(&self, _pos: u32) -> u64 {
|
||||
fn get_val(&self, _pos: u64) -> u64 {
|
||||
unimplemented!()
|
||||
}
|
||||
|
||||
@@ -89,7 +89,7 @@ impl<'a> Column for RemappedDocIdMultiValueColumn<'a> {
|
||||
self.max_value
|
||||
}
|
||||
|
||||
fn num_vals(&self) -> u32 {
|
||||
fn num_vals(&self) -> u64 {
|
||||
self.num_vals
|
||||
}
|
||||
}
|
||||
@@ -99,7 +99,7 @@ pub(crate) struct RemappedDocIdMultiValueIndexColumn<'a, T: MultiValueLength> {
|
||||
multi_value_length_readers: Vec<&'a T>,
|
||||
min_value: u64,
|
||||
max_value: u64,
|
||||
num_vals: u32,
|
||||
num_vals: u64,
|
||||
}
|
||||
|
||||
impl<'a, T: MultiValueLength> RemappedDocIdMultiValueIndexColumn<'a, T> {
|
||||
@@ -123,7 +123,7 @@ impl<'a, T: MultiValueLength> RemappedDocIdMultiValueIndexColumn<'a, T> {
|
||||
max_value += multi_value_length_reader.get_len(doc);
|
||||
}
|
||||
}
|
||||
num_vals += segment_reader.num_docs();
|
||||
num_vals += segment_reader.num_docs() as u64;
|
||||
multi_value_length_readers.push(multi_value_length_reader);
|
||||
}
|
||||
Self {
|
||||
@@ -137,7 +137,7 @@ impl<'a, T: MultiValueLength> RemappedDocIdMultiValueIndexColumn<'a, T> {
|
||||
}
|
||||
|
||||
impl<'a, T: MultiValueLength + Send + Sync> Column for RemappedDocIdMultiValueIndexColumn<'a, T> {
|
||||
fn get_val(&self, _pos: u32) -> u64 {
|
||||
fn get_val(&self, _pos: u64) -> u64 {
|
||||
unimplemented!()
|
||||
}
|
||||
|
||||
@@ -162,7 +162,7 @@ impl<'a, T: MultiValueLength + Send + Sync> Column for RemappedDocIdMultiValueIn
|
||||
self.max_value
|
||||
}
|
||||
|
||||
fn num_vals(&self) -> u32 {
|
||||
fn num_vals(&self) -> u64 {
|
||||
self.num_vals
|
||||
}
|
||||
}
|
||||
|
||||
@@ -311,7 +311,7 @@ pub use crate::postings::Postings;
|
||||
pub use crate::schema::{DateOptions, DatePrecision, Document, Term};
|
||||
|
||||
/// Index format version.
|
||||
const INDEX_FORMAT_VERSION: u32 = 5;
|
||||
const INDEX_FORMAT_VERSION: u32 = 4;
|
||||
|
||||
/// Structure version for the index.
|
||||
#[derive(Clone, PartialEq, Eq, Serialize, Deserialize)]
|
||||
@@ -819,7 +819,7 @@ pub mod tests {
|
||||
fn test_indexedfield_not_in_documents() -> crate::Result<()> {
|
||||
let mut schema_builder = Schema::builder();
|
||||
let text_field = schema_builder.add_text_field("text", TEXT);
|
||||
let absent_field = schema_builder.add_text_field("absent_text", TEXT);
|
||||
let absent_field = schema_builder.add_text_field("text", TEXT);
|
||||
let schema = schema_builder.build();
|
||||
let index = Index::create_in_ram(schema);
|
||||
let mut index_writer = index.writer_for_tests()?;
|
||||
@@ -1001,7 +1001,7 @@ pub mod tests {
|
||||
let fast_field_signed = schema_builder.add_i64_field("signed", FAST);
|
||||
let fast_field_float = schema_builder.add_f64_field("float", FAST);
|
||||
let text_field = schema_builder.add_text_field("text", TEXT);
|
||||
let stored_int_field = schema_builder.add_u64_field("stored_int", STORED);
|
||||
let stored_int_field = schema_builder.add_u64_field("text", STORED);
|
||||
let schema = schema_builder.build();
|
||||
|
||||
let index = Index::create_in_ram(schema);
|
||||
|
||||
@@ -3,7 +3,7 @@ use std::io;
|
||||
use std::marker::PhantomData;
|
||||
use std::ops::Range;
|
||||
|
||||
use rustc_hash::FxHashMap;
|
||||
use fnv::FnvHashMap;
|
||||
|
||||
use super::stacker::Addr;
|
||||
use crate::fastfield::MultiValuedFastFieldWriter;
|
||||
@@ -56,12 +56,12 @@ pub(crate) fn serialize_postings(
|
||||
doc_id_map: Option<&DocIdMapping>,
|
||||
schema: &Schema,
|
||||
serializer: &mut InvertedIndexSerializer,
|
||||
) -> crate::Result<HashMap<Field, FxHashMap<UnorderedTermId, TermOrdinal>>> {
|
||||
) -> crate::Result<HashMap<Field, FnvHashMap<UnorderedTermId, TermOrdinal>>> {
|
||||
let mut term_offsets: Vec<(Term<&[u8]>, Addr, UnorderedTermId)> =
|
||||
Vec::with_capacity(ctx.term_index.len());
|
||||
term_offsets.extend(ctx.term_index.iter());
|
||||
term_offsets.sort_unstable_by_key(|(k, _, _)| k.clone());
|
||||
let mut unordered_term_mappings: HashMap<Field, FxHashMap<UnorderedTermId, TermOrdinal>> =
|
||||
let mut unordered_term_mappings: HashMap<Field, FnvHashMap<UnorderedTermId, TermOrdinal>> =
|
||||
HashMap::new();
|
||||
|
||||
let field_offsets = make_field_partition(&term_offsets);
|
||||
@@ -74,7 +74,7 @@ pub(crate) fn serialize_postings(
|
||||
let unordered_term_ids = term_offsets[byte_offsets.clone()]
|
||||
.iter()
|
||||
.map(|&(_, _, bucket)| bucket);
|
||||
let mapping: FxHashMap<UnorderedTermId, TermOrdinal> = unordered_term_ids
|
||||
let mapping: FnvHashMap<UnorderedTermId, TermOrdinal> = unordered_term_ids
|
||||
.enumerate()
|
||||
.map(|(term_ord, unord_term_id)| {
|
||||
(unord_term_id as UnorderedTermId, term_ord as TermOrdinal)
|
||||
@@ -170,7 +170,7 @@ pub(crate) trait PostingsWriter: Send + Sync {
|
||||
term_buffer.truncate_value_bytes(end_of_path_idx);
|
||||
term_buffer.append_bytes(token.text.as_bytes());
|
||||
let start_position = indexing_position.end_position + token.position as u32;
|
||||
end_position = end_position.max(start_position + token.position_length as u32);
|
||||
end_position = start_position + token.position_length as u32;
|
||||
let unordered_term_id = self.subscribe(doc_id, start_position, term_buffer, ctx);
|
||||
if let Some(term_id_fast_field_writer) = term_id_fast_field_writer_opt.as_mut() {
|
||||
term_id_fast_field_writer.add_val(unordered_term_id);
|
||||
|
||||
@@ -86,7 +86,10 @@ impl DocSet for BitSetDocSet {
|
||||
self.doc
|
||||
}
|
||||
|
||||
/// Returns the number of values set in the underlying bitset.
|
||||
/// Returns half of the `max_doc`
|
||||
/// This is quite a terrible heuristic,
|
||||
/// but we don't have access to any better
|
||||
/// value.
|
||||
fn size_hint(&self) -> u32 {
|
||||
self.docs.len() as u32
|
||||
}
|
||||
|
||||
@@ -18,7 +18,6 @@ mod phrase_query;
|
||||
mod query;
|
||||
mod query_parser;
|
||||
mod range_query;
|
||||
mod range_query_ip_fastfield;
|
||||
mod regex_query;
|
||||
mod reqopt_scorer;
|
||||
mod scorer;
|
||||
|
||||
@@ -31,7 +31,7 @@ pub struct MoreLikeThisQuery {
|
||||
#[derive(Debug, PartialEq, Clone)]
|
||||
enum TargetDocument {
|
||||
DocumentAdress(DocAddress),
|
||||
DocumentFields(Vec<(Field, Vec<Value<'static>>)>),
|
||||
DocumentFields(Vec<(Field, Vec<Value>)>),
|
||||
}
|
||||
|
||||
impl MoreLikeThisQuery {
|
||||
@@ -160,10 +160,7 @@ impl MoreLikeThisQueryBuilder {
|
||||
/// that will be used to compose the resulting query.
|
||||
/// This interface is meant to be used when you want to provide your own set of fields
|
||||
/// not necessarily from a specific document.
|
||||
pub fn with_document_fields(
|
||||
self,
|
||||
doc_fields: Vec<(Field, Vec<Value<'static>>)>,
|
||||
) -> MoreLikeThisQuery {
|
||||
pub fn with_document_fields(self, doc_fields: Vec<(Field, Vec<Value>)>) -> MoreLikeThisQuery {
|
||||
MoreLikeThisQuery {
|
||||
mlt: self.mlt,
|
||||
target: TargetDocument::DocumentFields(doc_fields),
|
||||
|
||||
@@ -6,13 +6,12 @@ use common::BitSet;
|
||||
use crate::core::{Searcher, SegmentReader};
|
||||
use crate::error::TantivyError;
|
||||
use crate::query::explanation::does_not_match;
|
||||
use crate::query::range_query_ip_fastfield::IPFastFieldRangeWeight;
|
||||
use crate::query::{BitSetDocSet, ConstScorer, Explanation, Query, Scorer, Weight};
|
||||
use crate::schema::{Field, IndexRecordOption, Term, Type};
|
||||
use crate::termdict::{TermDictionary, TermStreamer};
|
||||
use crate::{DocId, Score};
|
||||
|
||||
pub(crate) fn map_bound<TFrom, TTo, Transform: Fn(&TFrom) -> TTo>(
|
||||
fn map_bound<TFrom, TTo, Transform: Fn(&TFrom) -> TTo>(
|
||||
bound: &Bound<TFrom>,
|
||||
transform: &Transform,
|
||||
) -> Bound<TTo> {
|
||||
@@ -30,17 +29,8 @@ pub(crate) fn map_bound<TFrom, TTo, Transform: Fn(&TFrom) -> TTo>(
|
||||
///
|
||||
/// # Implementation
|
||||
///
|
||||
/// ## Default
|
||||
/// The default implementation collects all documents _upfront_ into a `BitSet`.
|
||||
/// This is done by iterating over the terms within the range and loading all docs for each
|
||||
/// `TermInfo` from the inverted index (posting list) and put them into a `BitSet`.
|
||||
/// Depending on the number of terms matched, this is a potentially expensive operation.
|
||||
///
|
||||
/// ## IP fast field
|
||||
/// For IP fast fields a custom variant is used, by scanning the fast field. Unlike the default
|
||||
/// variant we can walk in a lazy fashion over it, since the fastfield is implicit orderered by
|
||||
/// DocId.
|
||||
///
|
||||
/// The current implement will iterate over the terms within the range
|
||||
/// and append all of the document cross into a `BitSet`.
|
||||
///
|
||||
/// # Example
|
||||
///
|
||||
@@ -259,8 +249,7 @@ impl Query for RangeQuery {
|
||||
_scoring_enabled: bool,
|
||||
) -> crate::Result<Box<dyn Weight>> {
|
||||
let schema = searcher.schema();
|
||||
let field_type = schema.get_field_entry(self.field).field_type();
|
||||
let value_type = field_type.value_type();
|
||||
let value_type = schema.get_field_entry(self.field).field_type().value_type();
|
||||
if value_type != self.value_type {
|
||||
let err_msg = format!(
|
||||
"Create a range query of the type {:?}, when the field given was of type {:?}",
|
||||
@@ -268,20 +257,11 @@ impl Query for RangeQuery {
|
||||
);
|
||||
return Err(TantivyError::SchemaError(err_msg));
|
||||
}
|
||||
|
||||
if field_type.is_ip_addr() && field_type.is_fast() {
|
||||
Ok(Box::new(IPFastFieldRangeWeight::new(
|
||||
self.field,
|
||||
&self.left_bound,
|
||||
&self.right_bound,
|
||||
)))
|
||||
} else {
|
||||
Ok(Box::new(RangeWeight {
|
||||
field: self.field,
|
||||
left_bound: self.left_bound.clone(),
|
||||
right_bound: self.right_bound.clone(),
|
||||
}))
|
||||
}
|
||||
Ok(Box::new(RangeWeight {
|
||||
field: self.field,
|
||||
left_bound: self.left_bound.clone(),
|
||||
right_bound: self.right_bound.clone(),
|
||||
}))
|
||||
}
|
||||
}
|
||||
|
||||
@@ -355,7 +335,7 @@ mod tests {
|
||||
use super::RangeQuery;
|
||||
use crate::collector::{Count, TopDocs};
|
||||
use crate::query::QueryParser;
|
||||
use crate::schema::{Document, Field, IntoIpv6Addr, Schema, FAST, INDEXED, STORED, TEXT};
|
||||
use crate::schema::{Document, Field, IntoIpv6Addr, Schema, INDEXED, STORED, TEXT};
|
||||
use crate::{doc, Index};
|
||||
|
||||
#[test]
|
||||
@@ -529,24 +509,10 @@ mod tests {
|
||||
Ok(())
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn search_ip_range_test_posting_list() {
|
||||
search_ip_range_test_opt(false);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn search_ip_range_test() {
|
||||
search_ip_range_test_opt(true);
|
||||
}
|
||||
|
||||
fn search_ip_range_test_opt(with_fast_field: bool) {
|
||||
let mut schema_builder = Schema::builder();
|
||||
let ip_field = if with_fast_field {
|
||||
schema_builder.add_ip_addr_field("ip", INDEXED | STORED | FAST)
|
||||
} else {
|
||||
schema_builder.add_ip_addr_field("ip", INDEXED | STORED)
|
||||
};
|
||||
let text_field = schema_builder.add_text_field("text", TEXT | STORED);
|
||||
let ip_field = schema_builder.add_ip_addr_field("ip", INDEXED | STORED);
|
||||
let schema = schema_builder.build();
|
||||
let index = Index::create_in_ram(schema);
|
||||
let ip_addr_1 = IpAddr::from_str("127.0.0.10").unwrap().into_ipv6_addr();
|
||||
@@ -554,22 +520,16 @@ mod tests {
|
||||
|
||||
{
|
||||
let mut index_writer = index.writer(3_000_000).unwrap();
|
||||
for _ in 0..1_000 {
|
||||
index_writer
|
||||
.add_document(doc!(
|
||||
ip_field => ip_addr_1,
|
||||
text_field => "BLUBBER"
|
||||
))
|
||||
.unwrap();
|
||||
}
|
||||
for _ in 0..1_000 {
|
||||
index_writer
|
||||
.add_document(doc!(
|
||||
ip_field => ip_addr_2,
|
||||
text_field => "BLOBBER"
|
||||
))
|
||||
.unwrap();
|
||||
}
|
||||
index_writer
|
||||
.add_document(doc!(
|
||||
ip_field => ip_addr_1
|
||||
))
|
||||
.unwrap();
|
||||
index_writer
|
||||
.add_document(doc!(
|
||||
ip_field => ip_addr_2
|
||||
))
|
||||
.unwrap();
|
||||
|
||||
index_writer.commit().unwrap();
|
||||
}
|
||||
@@ -583,25 +543,24 @@ mod tests {
|
||||
count
|
||||
};
|
||||
let query_from_text = |text: &str| {
|
||||
QueryParser::for_index(&index, vec![])
|
||||
QueryParser::for_index(&index, vec![ip_field])
|
||||
.parse_query(text)
|
||||
.unwrap()
|
||||
};
|
||||
|
||||
// Inclusive range
|
||||
assert_eq!(
|
||||
get_num_hits(query_from_text("ip:[127.0.0.1 TO 127.0.0.20]")),
|
||||
2000
|
||||
2
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
get_num_hits(query_from_text("ip:[127.0.0.10 TO 127.0.0.20]")),
|
||||
2000
|
||||
2
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
get_num_hits(query_from_text("ip:[127.0.0.11 TO 127.0.0.20]")),
|
||||
1000
|
||||
1
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
@@ -609,84 +568,9 @@ mod tests {
|
||||
0
|
||||
);
|
||||
|
||||
assert_eq!(get_num_hits(query_from_text("ip:[127.0.0.11 TO *]")), 1000);
|
||||
assert_eq!(get_num_hits(query_from_text("ip:[127.0.0.11 TO *]")), 1);
|
||||
assert_eq!(get_num_hits(query_from_text("ip:[127.0.0.21 TO *]")), 0);
|
||||
assert_eq!(get_num_hits(query_from_text("ip:[* TO 127.0.0.9]")), 0);
|
||||
assert_eq!(get_num_hits(query_from_text("ip:[* TO 127.0.0.10]")), 1000);
|
||||
|
||||
// Exclusive range
|
||||
assert_eq!(
|
||||
get_num_hits(query_from_text("ip:{127.0.0.1 TO 127.0.0.20}")),
|
||||
1000
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
get_num_hits(query_from_text("ip:{127.0.0.1 TO 127.0.0.21}")),
|
||||
2000
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
get_num_hits(query_from_text("ip:{127.0.0.10 TO 127.0.0.20}")),
|
||||
0
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
get_num_hits(query_from_text("ip:{127.0.0.11 TO 127.0.0.20}")),
|
||||
0
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
get_num_hits(query_from_text("ip:{127.0.0.11 TO 127.0.0.19}")),
|
||||
0
|
||||
);
|
||||
|
||||
assert_eq!(get_num_hits(query_from_text("ip:{127.0.0.11 TO *}")), 1000);
|
||||
assert_eq!(get_num_hits(query_from_text("ip:{127.0.0.10 TO *}")), 1000);
|
||||
assert_eq!(get_num_hits(query_from_text("ip:{127.0.0.21 TO *}")), 0);
|
||||
assert_eq!(get_num_hits(query_from_text("ip:{127.0.0.20 TO *}")), 0);
|
||||
assert_eq!(get_num_hits(query_from_text("ip:{127.0.0.19 TO *}")), 1000);
|
||||
assert_eq!(get_num_hits(query_from_text("ip:{* TO 127.0.0.9}")), 0);
|
||||
assert_eq!(get_num_hits(query_from_text("ip:{* TO 127.0.0.10}")), 0);
|
||||
assert_eq!(get_num_hits(query_from_text("ip:{* TO 127.0.0.11}")), 1000);
|
||||
|
||||
// Inclusive/Exclusive range
|
||||
assert_eq!(
|
||||
get_num_hits(query_from_text("ip:[127.0.0.1 TO 127.0.0.20}")),
|
||||
1000
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
get_num_hits(query_from_text("ip:{127.0.0.1 TO 127.0.0.20]")),
|
||||
2000
|
||||
);
|
||||
|
||||
// Intersection
|
||||
assert_eq!(
|
||||
get_num_hits(query_from_text(
|
||||
"text:BLUBBER AND ip:[127.0.0.10 TO 127.0.0.10]"
|
||||
)),
|
||||
1000
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
get_num_hits(query_from_text(
|
||||
"text:BLOBBER AND ip:[127.0.0.10 TO 127.0.0.10]"
|
||||
)),
|
||||
0
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
get_num_hits(query_from_text(
|
||||
"text:BLOBBER AND ip:[127.0.0.20 TO 127.0.0.20]"
|
||||
)),
|
||||
1000
|
||||
);
|
||||
|
||||
assert_eq!(
|
||||
get_num_hits(query_from_text(
|
||||
"text:BLUBBER AND ip:[127.0.0.20 TO 127.0.0.20]"
|
||||
)),
|
||||
0
|
||||
);
|
||||
assert_eq!(get_num_hits(query_from_text("ip:[* TO 127.0.0.10]")), 1);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1,595 +0,0 @@
|
||||
//! IP Fastfields support efficient scanning for range queries.
|
||||
//! We use this variant only if the fastfield exists, otherwise the default in `range_query` is
|
||||
//! used, which uses the term dictionary + postings.
|
||||
|
||||
use std::net::Ipv6Addr;
|
||||
use std::ops::{Bound, RangeInclusive};
|
||||
use std::sync::Arc;
|
||||
|
||||
use common::BinarySerializable;
|
||||
use fastfield_codecs::{Column, MonotonicallyMappableToU128};
|
||||
|
||||
use super::range_query::map_bound;
|
||||
use super::{ConstScorer, Explanation, Scorer, Weight};
|
||||
use crate::schema::{Cardinality, Field};
|
||||
use crate::{DocId, DocSet, Score, SegmentReader, TantivyError, TERMINATED};
|
||||
|
||||
/// `IPFastFieldRangeWeight` uses the ip address fast field to execute range queries.
|
||||
pub struct IPFastFieldRangeWeight {
|
||||
field: Field,
|
||||
left_bound: Bound<Ipv6Addr>,
|
||||
right_bound: Bound<Ipv6Addr>,
|
||||
}
|
||||
|
||||
impl IPFastFieldRangeWeight {
|
||||
pub fn new(field: Field, left_bound: &Bound<Vec<u8>>, right_bound: &Bound<Vec<u8>>) -> Self {
|
||||
let ip_from_bound_raw_data = |data: &Vec<u8>| {
|
||||
let left_ip_u128: u128 =
|
||||
u128::from_be(BinarySerializable::deserialize(&mut &data[..]).unwrap());
|
||||
Ipv6Addr::from_u128(left_ip_u128)
|
||||
};
|
||||
let left_bound = map_bound(left_bound, &ip_from_bound_raw_data);
|
||||
let right_bound = map_bound(right_bound, &ip_from_bound_raw_data);
|
||||
Self {
|
||||
field,
|
||||
left_bound,
|
||||
right_bound,
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl Weight for IPFastFieldRangeWeight {
|
||||
fn scorer(&self, reader: &SegmentReader, boost: Score) -> crate::Result<Box<dyn Scorer>> {
|
||||
let field_type = reader.schema().get_field_entry(self.field).field_type();
|
||||
match field_type.fastfield_cardinality().unwrap() {
|
||||
Cardinality::SingleValue => {
|
||||
let ip_addr_fast_field = reader.fast_fields().ip_addr(self.field)?;
|
||||
let value_range = bound_to_value_range(
|
||||
&self.left_bound,
|
||||
&self.right_bound,
|
||||
ip_addr_fast_field.as_ref(),
|
||||
);
|
||||
let docset = IpRangeDocSet::new(value_range, ip_addr_fast_field);
|
||||
Ok(Box::new(ConstScorer::new(docset, boost)))
|
||||
}
|
||||
Cardinality::MultiValues => unimplemented!(),
|
||||
}
|
||||
}
|
||||
|
||||
fn explain(&self, reader: &SegmentReader, doc: DocId) -> crate::Result<Explanation> {
|
||||
let mut scorer = self.scorer(reader, 1.0)?;
|
||||
if scorer.seek(doc) != doc {
|
||||
return Err(TantivyError::InvalidArgument(format!(
|
||||
"Document #({}) does not match",
|
||||
doc
|
||||
)));
|
||||
}
|
||||
let explanation = Explanation::new("Const", scorer.score());
|
||||
|
||||
Ok(explanation)
|
||||
}
|
||||
}
|
||||
|
||||
fn bound_to_value_range(
|
||||
left_bound: &Bound<Ipv6Addr>,
|
||||
right_bound: &Bound<Ipv6Addr>,
|
||||
column: &dyn Column<Ipv6Addr>,
|
||||
) -> RangeInclusive<Ipv6Addr> {
|
||||
let start_value = match left_bound {
|
||||
Bound::Included(ip_addr) => *ip_addr,
|
||||
Bound::Excluded(ip_addr) => Ipv6Addr::from(ip_addr.to_u128() + 1),
|
||||
Bound::Unbounded => column.min_value(),
|
||||
};
|
||||
|
||||
let end_value = match right_bound {
|
||||
Bound::Included(ip_addr) => *ip_addr,
|
||||
Bound::Excluded(ip_addr) => Ipv6Addr::from(ip_addr.to_u128() - 1),
|
||||
Bound::Unbounded => column.max_value(),
|
||||
};
|
||||
start_value..=end_value
|
||||
}
|
||||
|
||||
/// Helper to have a cursor over a vec of docids
|
||||
struct VecCursor {
|
||||
docs: Vec<u32>,
|
||||
current_pos: usize,
|
||||
}
|
||||
impl VecCursor {
|
||||
fn new() -> Self {
|
||||
Self {
|
||||
docs: Vec::with_capacity(32),
|
||||
current_pos: 0,
|
||||
}
|
||||
}
|
||||
fn next(&mut self) -> Option<u32> {
|
||||
self.current_pos += 1;
|
||||
self.current()
|
||||
}
|
||||
#[inline]
|
||||
fn current(&self) -> Option<u32> {
|
||||
self.docs.get(self.current_pos).map(|el| *el as u32)
|
||||
}
|
||||
|
||||
fn get_cleared_data(&mut self) -> &mut Vec<u32> {
|
||||
self.docs.clear();
|
||||
self.current_pos = 0;
|
||||
&mut self.docs
|
||||
}
|
||||
|
||||
fn is_empty(&self) -> bool {
|
||||
self.current_pos >= self.docs.len()
|
||||
}
|
||||
}
|
||||
|
||||
struct IpRangeDocSet {
|
||||
/// The range filter on the values.
|
||||
value_range: RangeInclusive<Ipv6Addr>,
|
||||
ip_addr_fast_field: Arc<dyn Column<Ipv6Addr>>,
|
||||
/// The next docid start range to fetch (inclusive).
|
||||
next_fetch_start: u32,
|
||||
/// Number of docs range checked in a batch.
|
||||
///
|
||||
/// There are two patterns.
|
||||
/// - We do a full scan. => We can load large chunks. We don't know in advance if seek call
|
||||
/// will come, so we start with small chunks
|
||||
/// - We load docs, interspersed with seek calls. When there are big jumps in the seek, we
|
||||
/// should load small chunks. When the seeks are small, we can employ the same strategy as on a
|
||||
/// full scan.
|
||||
fetch_horizon: u32,
|
||||
/// Current batch of loaded docs.
|
||||
loaded_docs: VecCursor,
|
||||
last_seek_pos_opt: Option<u32>,
|
||||
}
|
||||
|
||||
const DEFALT_FETCH_HORIZON: u32 = 128;
|
||||
impl IpRangeDocSet {
|
||||
fn new(
|
||||
value_range: RangeInclusive<Ipv6Addr>,
|
||||
ip_addr_fast_field: Arc<dyn Column<Ipv6Addr>>,
|
||||
) -> Self {
|
||||
let mut ip_range_docset = Self {
|
||||
value_range,
|
||||
ip_addr_fast_field,
|
||||
loaded_docs: VecCursor::new(),
|
||||
next_fetch_start: 0,
|
||||
fetch_horizon: DEFALT_FETCH_HORIZON,
|
||||
last_seek_pos_opt: None,
|
||||
};
|
||||
ip_range_docset.reset_fetch_range();
|
||||
ip_range_docset.fetch_block();
|
||||
ip_range_docset
|
||||
}
|
||||
|
||||
fn reset_fetch_range(&mut self) {
|
||||
self.fetch_horizon = DEFALT_FETCH_HORIZON;
|
||||
}
|
||||
|
||||
/// Returns true if more data could be fetched
|
||||
fn fetch_block(&mut self) {
|
||||
const MAX_HORIZON: u32 = 100_000;
|
||||
while self.loaded_docs.is_empty() {
|
||||
let finished_to_end = self.fetch_horizon(self.fetch_horizon);
|
||||
if finished_to_end {
|
||||
break;
|
||||
}
|
||||
// Fetch more data, increase horizon. Horizon only gets reset when doing a seek.
|
||||
self.fetch_horizon = (self.fetch_horizon * 2).min(MAX_HORIZON);
|
||||
}
|
||||
}
|
||||
|
||||
/// check if the distance between the seek calls is large
|
||||
fn is_last_seek_distance_large(&self, new_seek: DocId) -> bool {
|
||||
if let Some(last_seek_pos) = self.last_seek_pos_opt {
|
||||
(new_seek - last_seek_pos) >= 128
|
||||
} else {
|
||||
true
|
||||
}
|
||||
}
|
||||
|
||||
/// Fetches a block for docid range [next_fetch_start .. next_fetch_start + HORIZON]
|
||||
fn fetch_horizon(&mut self, horizon: u32) -> bool {
|
||||
let mut finished_to_end = false;
|
||||
|
||||
let limit = self.ip_addr_fast_field.num_vals();
|
||||
let mut end = self.next_fetch_start + horizon;
|
||||
if end >= limit {
|
||||
end = limit;
|
||||
finished_to_end = true;
|
||||
}
|
||||
|
||||
let data = self.loaded_docs.get_cleared_data();
|
||||
self.ip_addr_fast_field.get_positions_for_value_range(
|
||||
self.value_range.clone(),
|
||||
self.next_fetch_start..end,
|
||||
data,
|
||||
);
|
||||
self.next_fetch_start = end;
|
||||
finished_to_end
|
||||
}
|
||||
}
|
||||
|
||||
impl DocSet for IpRangeDocSet {
|
||||
#[inline]
|
||||
fn advance(&mut self) -> DocId {
|
||||
if let Some(docid) = self.loaded_docs.next() {
|
||||
docid as u32
|
||||
} else {
|
||||
if self.next_fetch_start >= self.ip_addr_fast_field.num_vals() as u32 {
|
||||
return TERMINATED;
|
||||
}
|
||||
self.fetch_block();
|
||||
self.loaded_docs.current().unwrap_or(TERMINATED)
|
||||
}
|
||||
}
|
||||
|
||||
#[inline]
|
||||
fn doc(&self) -> DocId {
|
||||
self.loaded_docs
|
||||
.current()
|
||||
.map(|el| el as u32)
|
||||
.unwrap_or(TERMINATED)
|
||||
}
|
||||
|
||||
/// Advances the `DocSet` forward until reaching the target, or going to the
|
||||
/// lowest [`DocId`] greater than the target.
|
||||
///
|
||||
/// If the end of the `DocSet` is reached, [`TERMINATED`] is returned.
|
||||
///
|
||||
/// Calling `.seek(target)` on a terminated `DocSet` is legal. Implementation
|
||||
/// of `DocSet` should support it.
|
||||
///
|
||||
/// Calling `seek(TERMINATED)` is also legal and is the normal way to consume a `DocSet`.
|
||||
fn seek(&mut self, target: DocId) -> DocId {
|
||||
if self.is_last_seek_distance_large(target) {
|
||||
self.reset_fetch_range();
|
||||
}
|
||||
if target > self.next_fetch_start {
|
||||
self.next_fetch_start = target;
|
||||
}
|
||||
let mut doc = self.doc();
|
||||
debug_assert!(doc <= target);
|
||||
while doc < target {
|
||||
doc = self.advance();
|
||||
}
|
||||
self.last_seek_pos_opt = Some(target);
|
||||
doc
|
||||
}
|
||||
|
||||
fn size_hint(&self) -> u32 {
|
||||
0 // heuristic possible by checking number of hits when fetching a block
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use proptest::prelude::ProptestConfig;
|
||||
use proptest::strategy::Strategy;
|
||||
use proptest::{prop_oneof, proptest};
|
||||
|
||||
use super::*;
|
||||
use crate::collector::Count;
|
||||
use crate::query::QueryParser;
|
||||
use crate::schema::{Schema, FAST, INDEXED, STORED, STRING};
|
||||
use crate::Index;
|
||||
|
||||
#[derive(Clone, Debug)]
|
||||
pub struct Doc {
|
||||
pub id: String,
|
||||
pub ip: Ipv6Addr,
|
||||
}
|
||||
|
||||
fn operation_strategy() -> impl Strategy<Value = Doc> {
|
||||
prop_oneof![
|
||||
(0u64..100u64).prop_map(doc_from_id_1),
|
||||
(1u64..100u64).prop_map(doc_from_id_2),
|
||||
]
|
||||
}
|
||||
|
||||
pub fn doc_from_id_1(id: u64) -> Doc {
|
||||
Doc {
|
||||
// ip != id
|
||||
id: id.to_string(),
|
||||
ip: Ipv6Addr::from_u128(id as u128),
|
||||
}
|
||||
}
|
||||
fn doc_from_id_2(id: u64) -> Doc {
|
||||
Doc {
|
||||
// ip != id
|
||||
id: (id - 1).to_string(),
|
||||
ip: Ipv6Addr::from_u128(id as u128),
|
||||
}
|
||||
}
|
||||
|
||||
proptest! {
|
||||
#![proptest_config(ProptestConfig::with_cases(10))]
|
||||
#[test]
|
||||
fn test_ip_range_for_docs_prop(ops in proptest::collection::vec(operation_strategy(), 1..1000)) {
|
||||
assert!(test_ip_range_for_docs(ops).is_ok());
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn ip_range_regression1_test() {
|
||||
let ops = vec![
|
||||
doc_from_id_1(52),
|
||||
doc_from_id_1(63),
|
||||
doc_from_id_1(12),
|
||||
doc_from_id_2(91),
|
||||
doc_from_id_2(33),
|
||||
];
|
||||
assert!(test_ip_range_for_docs(ops).is_ok());
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn ip_range_regression2_test() {
|
||||
let ops = vec![doc_from_id_1(0)];
|
||||
assert!(test_ip_range_for_docs(ops).is_ok());
|
||||
}
|
||||
|
||||
pub fn create_index_from_docs(docs: &[Doc]) -> Index {
|
||||
let mut schema_builder = Schema::builder();
|
||||
let ip_field = schema_builder.add_ip_addr_field("ip", INDEXED | STORED | FAST);
|
||||
let text_field = schema_builder.add_text_field("id", STRING | STORED);
|
||||
let schema = schema_builder.build();
|
||||
let index = Index::create_in_ram(schema);
|
||||
|
||||
{
|
||||
let mut index_writer = index.writer(3_000_000).unwrap();
|
||||
for doc in docs.iter() {
|
||||
index_writer
|
||||
.add_document(doc!(
|
||||
ip_field => doc.ip,
|
||||
text_field => doc.id.to_string(),
|
||||
))
|
||||
.unwrap();
|
||||
}
|
||||
|
||||
index_writer.commit().unwrap();
|
||||
}
|
||||
index
|
||||
}
|
||||
|
||||
fn test_ip_range_for_docs(docs: Vec<Doc>) -> crate::Result<()> {
|
||||
let index = create_index_from_docs(&docs);
|
||||
let reader = index.reader().unwrap();
|
||||
let searcher = reader.searcher();
|
||||
|
||||
let get_num_hits = |query| searcher.search(&query, &(Count)).unwrap();
|
||||
let query_from_text = |text: &str| {
|
||||
QueryParser::for_index(&index, vec![])
|
||||
.parse_query(text)
|
||||
.unwrap()
|
||||
};
|
||||
|
||||
let gen_query_inclusive = |from: Ipv6Addr, to: Ipv6Addr| {
|
||||
format!("ip:[{} TO {}]", &from.to_string(), &to.to_string())
|
||||
};
|
||||
|
||||
let test_sample = |sample_docs: Vec<Doc>| {
|
||||
let mut ips: Vec<Ipv6Addr> = sample_docs.iter().map(|doc| doc.ip).collect();
|
||||
ips.sort();
|
||||
let expected_num_hits = docs
|
||||
.iter()
|
||||
.filter(|doc| (ips[0]..=ips[1]).contains(&doc.ip))
|
||||
.count();
|
||||
|
||||
let query = gen_query_inclusive(ips[0], ips[1]);
|
||||
assert_eq!(get_num_hits(query_from_text(&query)), expected_num_hits);
|
||||
|
||||
// Intersection search
|
||||
let id_filter = sample_docs[0].id.to_string();
|
||||
let expected_num_hits = docs
|
||||
.iter()
|
||||
.filter(|doc| (ips[0]..=ips[1]).contains(&doc.ip) && doc.id == id_filter)
|
||||
.count();
|
||||
let query = format!("{} AND id:{}", query, &id_filter);
|
||||
assert_eq!(get_num_hits(query_from_text(&query)), expected_num_hits);
|
||||
};
|
||||
|
||||
test_sample(vec![docs[0].clone(), docs[0].clone()]);
|
||||
if docs.len() > 1 {
|
||||
test_sample(vec![docs[0].clone(), docs[1].clone()]);
|
||||
test_sample(vec![docs[1].clone(), docs[1].clone()]);
|
||||
}
|
||||
if docs.len() > 2 {
|
||||
test_sample(vec![docs[1].clone(), docs[2].clone()]);
|
||||
}
|
||||
|
||||
Ok(())
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(all(test, feature = "unstable"))]
|
||||
mod bench {
|
||||
|
||||
use rand::{thread_rng, Rng};
|
||||
use test::Bencher;
|
||||
|
||||
use super::tests::*;
|
||||
use super::*;
|
||||
use crate::collector::Count;
|
||||
use crate::query::QueryParser;
|
||||
use crate::Index;
|
||||
|
||||
fn get_index_0_to_100() -> Index {
|
||||
let mut rng = thread_rng();
|
||||
let num_vals = 100_000;
|
||||
let docs: Vec<_> = (0..num_vals)
|
||||
.map(|_i| {
|
||||
let id = if rng.gen_bool(0.01) {
|
||||
"veryfew".to_string() // 1%
|
||||
} else if rng.gen_bool(0.1) {
|
||||
"few".to_string() // 9%
|
||||
} else {
|
||||
"many".to_string() // 90%
|
||||
};
|
||||
Doc {
|
||||
id: id,
|
||||
// Multiply by 1000, so that we create many buckets in the compact space
|
||||
ip: Ipv6Addr::from_u128(rng.gen_range(0..100) * 1000),
|
||||
}
|
||||
})
|
||||
.collect();
|
||||
|
||||
let index = create_index_from_docs(&docs);
|
||||
index
|
||||
}
|
||||
fn excute_query(
|
||||
start_inclusive: Ipv6Addr,
|
||||
end_inclusive: Ipv6Addr,
|
||||
suffix: &str,
|
||||
index: &Index,
|
||||
) -> usize {
|
||||
let gen_query_inclusive = |from: Ipv6Addr, to: Ipv6Addr| {
|
||||
format!(
|
||||
"ip:[{} TO {}] {}",
|
||||
&from.to_string(),
|
||||
&to.to_string(),
|
||||
suffix
|
||||
)
|
||||
};
|
||||
|
||||
let query = gen_query_inclusive(start_inclusive, end_inclusive);
|
||||
let query_from_text = |text: &str| {
|
||||
QueryParser::for_index(&index, vec![])
|
||||
.parse_query(text)
|
||||
.unwrap()
|
||||
};
|
||||
let query = query_from_text(&query);
|
||||
let reader = index.reader().unwrap();
|
||||
let searcher = reader.searcher();
|
||||
searcher.search(&query, &(Count)).unwrap()
|
||||
}
|
||||
|
||||
#[bench]
|
||||
fn bench_ip_range_hit_90_percent(bench: &mut Bencher) {
|
||||
let index = get_index_0_to_100();
|
||||
|
||||
bench.iter(|| {
|
||||
let start = Ipv6Addr::from_u128(0);
|
||||
let end = Ipv6Addr::from_u128(90 * 1000);
|
||||
|
||||
excute_query(start, end, "", &index)
|
||||
});
|
||||
}
|
||||
|
||||
#[bench]
|
||||
fn bench_ip_range_hit_10_percent(bench: &mut Bencher) {
|
||||
let index = get_index_0_to_100();
|
||||
|
||||
bench.iter(|| {
|
||||
let start = Ipv6Addr::from_u128(0);
|
||||
let end = Ipv6Addr::from_u128(10 * 1000);
|
||||
|
||||
excute_query(start, end, "", &index)
|
||||
});
|
||||
}
|
||||
|
||||
#[bench]
|
||||
fn bench_ip_range_hit_1_percent(bench: &mut Bencher) {
|
||||
let index = get_index_0_to_100();
|
||||
|
||||
bench.iter(|| {
|
||||
let start = Ipv6Addr::from_u128(10 * 1000);
|
||||
let end = Ipv6Addr::from_u128(10 * 1000);
|
||||
|
||||
excute_query(start, end, "", &index)
|
||||
});
|
||||
}
|
||||
|
||||
#[bench]
|
||||
fn bench_ip_range_hit_10_percent_intersect_with_10_percent(bench: &mut Bencher) {
|
||||
let index = get_index_0_to_100();
|
||||
|
||||
bench.iter(|| {
|
||||
let start = Ipv6Addr::from_u128(0);
|
||||
let end = Ipv6Addr::from_u128(10 * 1000);
|
||||
|
||||
excute_query(start, end, "AND id:few", &index)
|
||||
});
|
||||
}
|
||||
|
||||
#[bench]
|
||||
fn bench_ip_range_hit_1_percent_intersect_with_10_percent(bench: &mut Bencher) {
|
||||
let index = get_index_0_to_100();
|
||||
|
||||
bench.iter(|| {
|
||||
let start = Ipv6Addr::from_u128(10 * 1000);
|
||||
let end = Ipv6Addr::from_u128(10 * 1000);
|
||||
|
||||
excute_query(start, end, "AND id:few", &index)
|
||||
});
|
||||
}
|
||||
|
||||
#[bench]
|
||||
fn bench_ip_range_hit_1_percent_intersect_with_90_percent(bench: &mut Bencher) {
|
||||
let index = get_index_0_to_100();
|
||||
|
||||
bench.iter(|| {
|
||||
let start = Ipv6Addr::from_u128(10 * 1000);
|
||||
let end = Ipv6Addr::from_u128(10 * 1000);
|
||||
|
||||
excute_query(start, end, "AND id:many", &index)
|
||||
});
|
||||
}
|
||||
|
||||
#[bench]
|
||||
fn bench_ip_range_hit_1_percent_intersect_with_1_percent(bench: &mut Bencher) {
|
||||
let index = get_index_0_to_100();
|
||||
|
||||
bench.iter(|| {
|
||||
let start = Ipv6Addr::from_u128(10 * 1000);
|
||||
let end = Ipv6Addr::from_u128(10 * 1000);
|
||||
|
||||
excute_query(start, end, "AND id:veryfew", &index)
|
||||
});
|
||||
}
|
||||
|
||||
#[bench]
|
||||
fn bench_ip_range_hit_10_percent_intersect_with_90_percent(bench: &mut Bencher) {
|
||||
let index = get_index_0_to_100();
|
||||
|
||||
bench.iter(|| {
|
||||
let start = Ipv6Addr::from_u128(0);
|
||||
let end = Ipv6Addr::from_u128(10 * 1000);
|
||||
|
||||
excute_query(start, end, "AND id:many", &index)
|
||||
});
|
||||
}
|
||||
|
||||
#[bench]
|
||||
fn bench_ip_range_hit_90_percent_intersect_with_90_percent(bench: &mut Bencher) {
|
||||
let index = get_index_0_to_100();
|
||||
|
||||
bench.iter(|| {
|
||||
let start = Ipv6Addr::from_u128(0);
|
||||
let end = Ipv6Addr::from_u128(90 * 1000);
|
||||
|
||||
excute_query(start, end, "AND id:many", &index)
|
||||
});
|
||||
}
|
||||
|
||||
#[bench]
|
||||
fn bench_ip_range_hit_90_percent_intersect_with_10_percent(bench: &mut Bencher) {
|
||||
let index = get_index_0_to_100();
|
||||
|
||||
bench.iter(|| {
|
||||
let start = Ipv6Addr::from_u128(0);
|
||||
let end = Ipv6Addr::from_u128(90 * 1000);
|
||||
|
||||
excute_query(start, end, "AND id:few", &index)
|
||||
});
|
||||
}
|
||||
|
||||
#[bench]
|
||||
fn bench_ip_range_hit_90_percent_intersect_with_1_percent(bench: &mut Bencher) {
|
||||
let index = get_index_0_to_100();
|
||||
|
||||
bench.iter(|| {
|
||||
let start = Ipv6Addr::from_u128(0);
|
||||
let end = Ipv6Addr::from_u128(90 * 1000);
|
||||
|
||||
excute_query(start, end, "AND id:veryfew", &index)
|
||||
});
|
||||
}
|
||||
}
|
||||
@@ -115,7 +115,7 @@ mod tests {
|
||||
pub fn test_term_set_query() -> crate::Result<()> {
|
||||
let mut schema_builder = Schema::builder();
|
||||
let field1 = schema_builder.add_text_field("field1", TEXT);
|
||||
let field2 = schema_builder.add_text_field("field2", TEXT);
|
||||
let field2 = schema_builder.add_text_field("field1", TEXT);
|
||||
let schema = schema_builder.build();
|
||||
let index = Index::create_in_ram(schema);
|
||||
{
|
||||
|
||||
@@ -1,105 +1,35 @@
|
||||
use std::collections::{HashMap, HashSet};
|
||||
use std::io::{self, Read, Write};
|
||||
use std::mem;
|
||||
use std::net::Ipv6Addr;
|
||||
use std::sync::Arc;
|
||||
use std::{fmt, mem};
|
||||
|
||||
use common::{BinarySerializable, VInt};
|
||||
use itertools::Either;
|
||||
use yoke::erased::ErasedArcCart;
|
||||
use yoke::Yoke;
|
||||
|
||||
use super::*;
|
||||
use crate::schema::value::MaybeOwnedString;
|
||||
use crate::tokenizer::PreTokenizedString;
|
||||
use crate::DateTime;
|
||||
|
||||
/// A group of FieldValue sharing an underlying storage
|
||||
///
|
||||
/// Or a single owned FieldValue.
|
||||
#[derive(Clone)]
|
||||
enum FieldValueGroup {
|
||||
Single(FieldValue<'static>),
|
||||
Group(Yoke<VecFieldValue<'static>, ErasedArcCart>),
|
||||
}
|
||||
|
||||
// this NewType is required to make it possible to yoke a vec with non 'static inner values.
|
||||
#[derive(yoke::Yokeable, Clone)]
|
||||
struct VecFieldValue<'a>(Vec<FieldValue<'a>>);
|
||||
|
||||
impl<'a> std::ops::Deref for VecFieldValue<'a> {
|
||||
type Target = Vec<FieldValue<'a>>;
|
||||
|
||||
fn deref(&self) -> &Self::Target {
|
||||
&self.0
|
||||
}
|
||||
}
|
||||
|
||||
impl<'a> From<Vec<FieldValue<'a>>> for VecFieldValue<'a> {
|
||||
fn from(field_values: Vec<FieldValue>) -> VecFieldValue {
|
||||
VecFieldValue(field_values)
|
||||
}
|
||||
}
|
||||
|
||||
impl FieldValueGroup {
|
||||
fn iter(&self) -> impl Iterator<Item = &FieldValue> {
|
||||
match self {
|
||||
FieldValueGroup::Single(field_value) => Either::Left(std::iter::once(field_value)),
|
||||
FieldValueGroup::Group(field_values) => Either::Right(field_values.get().iter()),
|
||||
}
|
||||
}
|
||||
|
||||
fn count(&self) -> usize {
|
||||
match self {
|
||||
FieldValueGroup::Single(_) => 1,
|
||||
FieldValueGroup::Group(field_values) => field_values.get().len(),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl From<Vec<FieldValue<'static>>> for FieldValueGroup {
|
||||
fn from(field_values: Vec<FieldValue<'static>>) -> FieldValueGroup {
|
||||
FieldValueGroup::Group(
|
||||
Yoke::new_always_owned(field_values.into())
|
||||
.wrap_cart_in_arc()
|
||||
.erase_arc_cart(),
|
||||
)
|
||||
}
|
||||
}
|
||||
|
||||
/// Tantivy's Document is the object that can
|
||||
/// be indexed and then searched for.
|
||||
///
|
||||
/// Documents are fundamentally a collection of unordered couples `(field, value)`.
|
||||
/// In this list, one field may appear more than once.
|
||||
#[derive(Clone, Default)]
|
||||
// TODO bring back Ser/De and Debug
|
||||
//#[derive(Clone, Debug, serde::Serialize, serde::Deserialize, Default)]
|
||||
//#[serde(bound(deserialize = "'static: 'de, 'de: 'static"))]
|
||||
#[derive(Clone, Debug, serde::Serialize, serde::Deserialize, Default)]
|
||||
pub struct Document {
|
||||
field_values: Vec<FieldValueGroup>,
|
||||
field_values: Vec<FieldValue>,
|
||||
}
|
||||
|
||||
impl fmt::Debug for Document {
|
||||
fn fmt(&self, _: &mut fmt::Formatter<'_>) -> fmt::Result {
|
||||
todo!()
|
||||
}
|
||||
}
|
||||
|
||||
impl From<Vec<FieldValue<'static>>> for Document {
|
||||
fn from(field_values: Vec<FieldValue<'static>>) -> Self {
|
||||
let field_values = vec![field_values.into()];
|
||||
impl From<Vec<FieldValue>> for Document {
|
||||
fn from(field_values: Vec<FieldValue>) -> Self {
|
||||
Document { field_values }
|
||||
}
|
||||
}
|
||||
impl PartialEq for Document {
|
||||
fn eq(&self, other: &Document) -> bool {
|
||||
// super slow, but only here for tests
|
||||
let convert_to_comparable_map = |field_values| {
|
||||
let convert_to_comparable_map = |field_values: &[FieldValue]| {
|
||||
let mut field_value_set: HashMap<Field, HashSet<String>> = Default::default();
|
||||
for field_value in field_values {
|
||||
// for some reason rustc fails to guess the type
|
||||
let field_value: &FieldValue = field_value;
|
||||
for field_value in field_values.iter() {
|
||||
let json_val = serde_json::to_string(field_value.value()).unwrap();
|
||||
field_value_set
|
||||
.entry(field_value.field())
|
||||
@@ -109,9 +39,9 @@ impl PartialEq for Document {
|
||||
field_value_set
|
||||
};
|
||||
let self_field_values: HashMap<Field, HashSet<String>> =
|
||||
convert_to_comparable_map(self.field_values());
|
||||
convert_to_comparable_map(&self.field_values);
|
||||
let other_field_values: HashMap<Field, HashSet<String>> =
|
||||
convert_to_comparable_map(other.field_values());
|
||||
convert_to_comparable_map(&other.field_values);
|
||||
self_field_values.eq(&other_field_values)
|
||||
}
|
||||
}
|
||||
@@ -119,13 +49,12 @@ impl PartialEq for Document {
|
||||
impl Eq for Document {}
|
||||
|
||||
impl IntoIterator for Document {
|
||||
type Item = FieldValue<'static>;
|
||||
type Item = FieldValue;
|
||||
|
||||
type IntoIter = std::vec::IntoIter<FieldValue<'static>>;
|
||||
type IntoIter = std::vec::IntoIter<FieldValue>;
|
||||
|
||||
fn into_iter(self) -> Self::IntoIter {
|
||||
todo!()
|
||||
// self.field_values.into_iter()
|
||||
self.field_values.into_iter()
|
||||
}
|
||||
}
|
||||
|
||||
@@ -155,7 +84,7 @@ impl Document {
|
||||
|
||||
/// Add a text field.
|
||||
pub fn add_text<S: ToString>(&mut self, field: Field, text: S) {
|
||||
let value = Value::Str(MaybeOwnedString::from_string(text.to_string()));
|
||||
let value = Value::Str(text.to_string());
|
||||
self.add_field_value(field, value);
|
||||
}
|
||||
|
||||
@@ -209,35 +138,15 @@ impl Document {
|
||||
}
|
||||
|
||||
/// Add a (field, value) to the document.
|
||||
pub fn add_field_value<T: Into<Value<'static>>>(&mut self, field: Field, typed_val: T) {
|
||||
pub fn add_field_value<T: Into<Value>>(&mut self, field: Field, typed_val: T) {
|
||||
let value = typed_val.into();
|
||||
let field_value = FieldValue { field, value };
|
||||
self.field_values.push(FieldValueGroup::Single(field_value));
|
||||
}
|
||||
|
||||
/// Add multiple borrowed values, also taking the container they're borrowing from
|
||||
// TODO add a try_ variant?
|
||||
pub fn add_borrowed_values<T, F>(&mut self, storage: T, f: F)
|
||||
where
|
||||
T: Send + Sync + 'static,
|
||||
F: FnOnce(&T) -> Vec<FieldValue>,
|
||||
{
|
||||
let yoke =
|
||||
Yoke::attach_to_cart(Arc::new(storage), |storage| f(storage).into()).erase_arc_cart();
|
||||
|
||||
self.field_values.push(FieldValueGroup::Group(yoke));
|
||||
self.field_values.push(field_value);
|
||||
}
|
||||
|
||||
/// field_values accessor
|
||||
pub fn field_values(&self) -> impl Iterator<Item = &FieldValue> {
|
||||
self.field_values.iter().flat_map(|group| group.iter())
|
||||
}
|
||||
|
||||
/// Return the total number of values
|
||||
///
|
||||
/// More efficient than calling `self.field_values().count()`
|
||||
pub fn value_count(&self) -> usize {
|
||||
self.field_values.iter().map(|group| group.count()).sum()
|
||||
pub fn field_values(&self) -> &[FieldValue] {
|
||||
&self.field_values
|
||||
}
|
||||
|
||||
/// Sort and groups the field_values by field.
|
||||
@@ -245,7 +154,7 @@ impl Document {
|
||||
/// The result of this method is not cached and is
|
||||
/// computed on the fly when this method is called.
|
||||
pub fn get_sorted_field_values(&self) -> Vec<(Field, Vec<&Value>)> {
|
||||
let mut field_values: Vec<&FieldValue> = self.field_values().collect();
|
||||
let mut field_values: Vec<&FieldValue> = self.field_values().iter().collect();
|
||||
field_values.sort_by_key(|field_value| field_value.field());
|
||||
|
||||
let mut field_values_it = field_values.into_iter();
|
||||
@@ -280,7 +189,6 @@ impl Document {
|
||||
pub fn get_all(&self, field: Field) -> impl Iterator<Item = &Value> {
|
||||
self.field_values
|
||||
.iter()
|
||||
.flat_map(|group| group.iter())
|
||||
.filter(move |field_value| field_value.field() == field)
|
||||
.map(FieldValue::value)
|
||||
}
|
||||
@@ -294,6 +202,7 @@ impl Document {
|
||||
pub fn serialize_stored<W: Write>(&self, schema: &Schema, writer: &mut W) -> io::Result<()> {
|
||||
let stored_field_values = || {
|
||||
self.field_values()
|
||||
.iter()
|
||||
.filter(|field_value| schema.get_field_entry(field_value.field()).is_stored())
|
||||
};
|
||||
let num_field_values = stored_field_values().count();
|
||||
@@ -307,9 +216,7 @@ impl Document {
|
||||
} => {
|
||||
let field_value = FieldValue {
|
||||
field: *field,
|
||||
value: Value::Str(MaybeOwnedString::from_string(
|
||||
pre_tokenized_text.text.to_string(),
|
||||
)),
|
||||
value: Value::Str(pre_tokenized_text.text.to_string()),
|
||||
};
|
||||
field_value.serialize(writer)?;
|
||||
}
|
||||
@@ -323,7 +230,7 @@ impl Document {
|
||||
impl BinarySerializable for Document {
|
||||
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
|
||||
let field_values = self.field_values();
|
||||
VInt(self.value_count() as u64).serialize(writer)?;
|
||||
VInt(field_values.len() as u64).serialize(writer)?;
|
||||
for field_value in field_values {
|
||||
field_value.serialize(writer)?;
|
||||
}
|
||||
@@ -352,7 +259,7 @@ mod tests {
|
||||
let text_field = schema_builder.add_text_field("title", TEXT);
|
||||
let mut doc = Document::default();
|
||||
doc.add_text(text_field, "My title");
|
||||
assert_eq!(doc.value_count(), 1);
|
||||
assert_eq!(doc.field_values().len(), 1);
|
||||
}
|
||||
|
||||
#[test]
|
||||
@@ -366,7 +273,7 @@ mod tests {
|
||||
.clone(),
|
||||
);
|
||||
doc.add_text(Field::from_field_id(1), "hello");
|
||||
assert_eq!(doc.value_count(), 2);
|
||||
assert_eq!(doc.field_values().len(), 2);
|
||||
let mut payload: Vec<u8> = Vec::new();
|
||||
doc.serialize(&mut payload).unwrap();
|
||||
assert_eq!(payload.len(), 26);
|
||||
|
||||
@@ -9,7 +9,6 @@ use super::ip_options::IpAddrOptions;
|
||||
use super::{Cardinality, IntoIpv6Addr};
|
||||
use crate::schema::bytes_options::BytesOptions;
|
||||
use crate::schema::facet_options::FacetOptions;
|
||||
use crate::schema::value::MaybeOwnedString;
|
||||
use crate::schema::{
|
||||
DateOptions, Facet, IndexRecordOption, JsonObjectOptions, NumericOptions, TextFieldIndexing,
|
||||
TextOptions, Value,
|
||||
@@ -177,11 +176,6 @@ impl FieldType {
|
||||
}
|
||||
}
|
||||
|
||||
/// returns true if this is an ip address field
|
||||
pub fn is_ip_addr(&self) -> bool {
|
||||
matches!(self, FieldType::IpAddr(_))
|
||||
}
|
||||
|
||||
/// returns true if the field is indexed.
|
||||
pub fn is_indexed(&self) -> bool {
|
||||
match *self {
|
||||
@@ -238,11 +232,11 @@ impl FieldType {
|
||||
/// returns true if the field is fast.
|
||||
pub fn fastfield_cardinality(&self) -> Option<Cardinality> {
|
||||
match *self {
|
||||
FieldType::Bytes(ref bytes_options) => {
|
||||
bytes_options.is_fast().then_some(Cardinality::SingleValue)
|
||||
FieldType::Bytes(ref bytes_options) if bytes_options.is_fast() => {
|
||||
Some(Cardinality::SingleValue)
|
||||
}
|
||||
FieldType::Str(ref text_options) => {
|
||||
text_options.is_fast().then_some(Cardinality::MultiValues)
|
||||
FieldType::Str(ref text_options) if text_options.is_fast() => {
|
||||
Some(Cardinality::MultiValues)
|
||||
}
|
||||
FieldType::U64(ref int_options)
|
||||
| FieldType::I64(ref int_options)
|
||||
@@ -251,7 +245,7 @@ impl FieldType {
|
||||
FieldType::Date(ref date_options) => date_options.get_fastfield_cardinality(),
|
||||
FieldType::Facet(_) => Some(Cardinality::MultiValues),
|
||||
FieldType::JsonObject(_) => None,
|
||||
FieldType::IpAddr(ref ip_addr_options) => ip_addr_options.get_fastfield_cardinality(),
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -330,7 +324,7 @@ impl FieldType {
|
||||
/// Tantivy will not try to cast values.
|
||||
/// For instance, If the json value is the integer `3` and the
|
||||
/// target field is a `Str`, this method will return an Error.
|
||||
pub fn value_from_json(&self, json: JsonValue) -> Result<Value<'static>, ValueParsingError> {
|
||||
pub fn value_from_json(&self, json: JsonValue) -> Result<Value, ValueParsingError> {
|
||||
match json {
|
||||
JsonValue::String(field_text) => {
|
||||
match self {
|
||||
@@ -342,7 +336,7 @@ impl FieldType {
|
||||
})?;
|
||||
Ok(DateTime::from_utc(dt_with_fixed_tz).into())
|
||||
}
|
||||
FieldType::Str(_) => Ok(Value::Str(MaybeOwnedString::from_string(field_text))),
|
||||
FieldType::Str(_) => Ok(Value::Str(field_text)),
|
||||
FieldType::U64(_) | FieldType::I64(_) | FieldType::F64(_) => {
|
||||
Err(ValueParsingError::TypeError {
|
||||
expected: "an integer",
|
||||
|
||||
@@ -7,13 +7,12 @@ use crate::schema::{Field, Value};
|
||||
/// `FieldValue` holds together a `Field` and its `Value`.
|
||||
#[allow(missing_docs)]
|
||||
#[derive(Debug, Clone, PartialEq, Eq, serde::Serialize, serde::Deserialize)]
|
||||
#[serde(bound(deserialize = "'a: 'de, 'de: 'a"))]
|
||||
pub struct FieldValue<'a> {
|
||||
pub struct FieldValue {
|
||||
pub field: Field,
|
||||
pub value: Value<'a>,
|
||||
pub value: Value,
|
||||
}
|
||||
|
||||
impl<'a> FieldValue<'a> {
|
||||
impl FieldValue {
|
||||
/// Constructor
|
||||
pub fn new(field: Field, value: Value) -> FieldValue {
|
||||
FieldValue { field, value }
|
||||
@@ -30,13 +29,13 @@ impl<'a> FieldValue<'a> {
|
||||
}
|
||||
}
|
||||
|
||||
impl<'a> From<FieldValue<'a>> for Value<'a> {
|
||||
fn from(field_value: FieldValue<'a>) -> Self {
|
||||
impl From<FieldValue> for Value {
|
||||
fn from(field_value: FieldValue) -> Self {
|
||||
field_value.value
|
||||
}
|
||||
}
|
||||
|
||||
impl<'a> BinarySerializable for FieldValue<'a> {
|
||||
impl BinarySerializable for FieldValue {
|
||||
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
|
||||
self.field.serialize(writer)?;
|
||||
self.value.serialize(writer)
|
||||
|
||||
@@ -10,5 +10,4 @@ use crate::schema::Value;
|
||||
/// A `NamedFieldDocument` is a simple representation of a document
|
||||
/// as a `BTreeMap<String, Vec<Value>>`.
|
||||
#[derive(Debug, Deserialize, Serialize)]
|
||||
#[serde(bound(deserialize = "'static: 'de, 'de: 'static"))]
|
||||
pub struct NamedFieldDocument(pub BTreeMap<String, Vec<Value<'static>>>);
|
||||
pub struct NamedFieldDocument(pub BTreeMap<String, Vec<Value>>);
|
||||
|
||||
@@ -46,9 +46,13 @@ impl SchemaBuilder {
|
||||
/// Adds a new u64 field.
|
||||
/// Returns the associated field handle
|
||||
///
|
||||
/// # Panics
|
||||
/// # Caution
|
||||
///
|
||||
/// Panics when field already exists.
|
||||
/// Appending two fields with the same name
|
||||
/// will result in the shadowing of the first
|
||||
/// by the second one.
|
||||
/// The first field will get a field id
|
||||
/// but only the second one will be indexed
|
||||
pub fn add_u64_field<T: Into<NumericOptions>>(
|
||||
&mut self,
|
||||
field_name_str: &str,
|
||||
@@ -62,9 +66,13 @@ impl SchemaBuilder {
|
||||
/// Adds a new i64 field.
|
||||
/// Returns the associated field handle
|
||||
///
|
||||
/// # Panics
|
||||
/// # Caution
|
||||
///
|
||||
/// Panics when field already exists.
|
||||
/// Appending two fields with the same name
|
||||
/// will result in the shadowing of the first
|
||||
/// by the second one.
|
||||
/// The first field will get a field id
|
||||
/// but only the second one will be indexed
|
||||
pub fn add_i64_field<T: Into<NumericOptions>>(
|
||||
&mut self,
|
||||
field_name_str: &str,
|
||||
@@ -78,9 +86,13 @@ impl SchemaBuilder {
|
||||
/// Adds a new f64 field.
|
||||
/// Returns the associated field handle
|
||||
///
|
||||
/// # Panics
|
||||
/// # Caution
|
||||
///
|
||||
/// Panics when field already exists.
|
||||
/// Appending two fields with the same name
|
||||
/// will result in the shadowing of the first
|
||||
/// by the second one.
|
||||
/// The first field will get a field id
|
||||
/// but only the second one will be indexed
|
||||
pub fn add_f64_field<T: Into<NumericOptions>>(
|
||||
&mut self,
|
||||
field_name_str: &str,
|
||||
@@ -94,9 +106,13 @@ impl SchemaBuilder {
|
||||
/// Adds a new bool field.
|
||||
/// Returns the associated field handle
|
||||
///
|
||||
/// # Panics
|
||||
/// # Caution
|
||||
///
|
||||
/// Panics when field already exists.
|
||||
/// Appending two fields with the same name
|
||||
/// will result in the shadowing of the first
|
||||
/// by the second one.
|
||||
/// The first field will get a field id
|
||||
/// but only the second one will be indexed
|
||||
pub fn add_bool_field<T: Into<NumericOptions>>(
|
||||
&mut self,
|
||||
field_name_str: &str,
|
||||
@@ -112,9 +128,13 @@ impl SchemaBuilder {
|
||||
/// Internally, Tantivy simply stores dates as i64 UTC timestamps,
|
||||
/// while the user supplies DateTime values for convenience.
|
||||
///
|
||||
/// # Panics
|
||||
/// # Caution
|
||||
///
|
||||
/// Panics when field already exists.
|
||||
/// Appending two fields with the same name
|
||||
/// will result in the shadowing of the first
|
||||
/// by the second one.
|
||||
/// The first field will get a field id
|
||||
/// but only the second one will be indexed
|
||||
pub fn add_date_field<T: Into<DateOptions>>(
|
||||
&mut self,
|
||||
field_name_str: &str,
|
||||
@@ -128,9 +148,13 @@ impl SchemaBuilder {
|
||||
/// Adds a ip field.
|
||||
/// Returns the associated field handle.
|
||||
///
|
||||
/// # Panics
|
||||
/// # Caution
|
||||
///
|
||||
/// Panics when field already exists.
|
||||
/// Appending two fields with the same name
|
||||
/// will result in the shadowing of the first
|
||||
/// by the second one.
|
||||
/// The first field will get a field id
|
||||
/// but only the second one will be indexed
|
||||
pub fn add_ip_addr_field<T: Into<IpAddrOptions>>(
|
||||
&mut self,
|
||||
field_name_str: &str,
|
||||
@@ -144,9 +168,13 @@ impl SchemaBuilder {
|
||||
/// Adds a new text field.
|
||||
/// Returns the associated field handle
|
||||
///
|
||||
/// # Panics
|
||||
/// # Caution
|
||||
///
|
||||
/// Panics when field already exists.
|
||||
/// Appending two fields with the same name
|
||||
/// will result in the shadowing of the first
|
||||
/// by the second one.
|
||||
/// The first field will get a field id
|
||||
/// but only the second one will be indexed
|
||||
pub fn add_text_field<T: Into<TextOptions>>(
|
||||
&mut self,
|
||||
field_name_str: &str,
|
||||
@@ -200,10 +228,8 @@ impl SchemaBuilder {
|
||||
pub fn add_field(&mut self, field_entry: FieldEntry) -> Field {
|
||||
let field = Field::from_field_id(self.fields.len() as u32);
|
||||
let field_name = field_entry.name().to_string();
|
||||
if let Some(_previous_value) = self.fields_map.insert(field_name, field) {
|
||||
panic!("Field already exists in schema {}", field_entry.name());
|
||||
};
|
||||
self.fields.push(field_entry);
|
||||
self.fields_map.insert(field_name, field);
|
||||
field
|
||||
}
|
||||
|
||||
@@ -308,11 +334,7 @@ impl Schema {
|
||||
let mut field_map = BTreeMap::new();
|
||||
for (field, field_values) in doc.get_sorted_field_values() {
|
||||
let field_name = self.get_field_name(field);
|
||||
let values: Vec<Value> = field_values
|
||||
.into_iter()
|
||||
.cloned()
|
||||
.map(Value::into_owned)
|
||||
.collect();
|
||||
let values: Vec<Value> = field_values.into_iter().cloned().collect();
|
||||
field_map.insert(field_name.to_string(), values);
|
||||
}
|
||||
NamedFieldDocument(field_map)
|
||||
@@ -342,21 +364,20 @@ impl Schema {
|
||||
if let Some(field) = self.get_field(&field_name) {
|
||||
let field_entry = self.get_field_entry(field);
|
||||
let field_type = field_entry.field_type();
|
||||
// TODO rewrite this with shared allocation?
|
||||
match json_value {
|
||||
JsonValue::Array(json_items) => {
|
||||
for json_item in json_items {
|
||||
let value = field_type
|
||||
.value_from_json(json_item)
|
||||
.map_err(|e| DocParsingError::ValueError(field_name.clone(), e))?;
|
||||
doc.add_field_value(field, value.into_owned());
|
||||
doc.add_field_value(field, value);
|
||||
}
|
||||
}
|
||||
_ => {
|
||||
let value = field_type
|
||||
.value_from_json(json_value)
|
||||
.map_err(|e| DocParsingError::ValueError(field_name.clone(), e))?;
|
||||
doc.add_field_value(field, value.into_owned());
|
||||
doc.add_field_value(field, value);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -711,7 +732,7 @@ mod tests {
|
||||
let schema = schema_builder.build();
|
||||
{
|
||||
let doc = schema.parse_document("{}").unwrap();
|
||||
assert_eq!(doc.value_count(), 0);
|
||||
assert!(doc.field_values().is_empty());
|
||||
}
|
||||
{
|
||||
let doc = schema
|
||||
|
||||
@@ -1,7 +1,6 @@
|
||||
use std::fmt;
|
||||
use std::net::Ipv6Addr;
|
||||
|
||||
pub use not_safe::MaybeOwnedString;
|
||||
use serde::de::Visitor;
|
||||
use serde::{Deserialize, Deserializer, Serialize, Serializer};
|
||||
use serde_json::Map;
|
||||
@@ -13,9 +12,9 @@ use crate::DateTime;
|
||||
/// Value represents the value of a any field.
|
||||
/// It is an enum over all over all of the possible field type.
|
||||
#[derive(Debug, Clone, PartialEq)]
|
||||
pub enum Value<'a> {
|
||||
pub enum Value {
|
||||
/// The str type is used for any text information.
|
||||
Str(MaybeOwnedString<'a>),
|
||||
Str(String),
|
||||
/// Pre-tokenized str type,
|
||||
PreTokStr(PreTokenizedString),
|
||||
/// Unsigned 64-bits Integer `u64`
|
||||
@@ -31,38 +30,16 @@ pub enum Value<'a> {
|
||||
/// Facet
|
||||
Facet(Facet),
|
||||
/// Arbitrarily sized byte array
|
||||
// TODO allow Cow<'a, [u8]>
|
||||
Bytes(Vec<u8>),
|
||||
/// Json object value.
|
||||
// TODO allow Cow keys and borrowed values
|
||||
JsonObject(serde_json::Map<String, serde_json::Value>),
|
||||
/// IpV6 Address. Internally there is no IpV4, it needs to be converted to `Ipv6Addr`.
|
||||
IpAddr(Ipv6Addr),
|
||||
}
|
||||
|
||||
impl<'a> Value<'a> {
|
||||
/// Convert a borrowing [`Value`] to an owning one.
|
||||
pub fn into_owned(self) -> Value<'static> {
|
||||
use Value::*;
|
||||
match self {
|
||||
Str(val) => Str(MaybeOwnedString::from_string(val.into_string())),
|
||||
PreTokStr(val) => PreTokStr(val),
|
||||
U64(val) => U64(val),
|
||||
I64(val) => I64(val),
|
||||
F64(val) => F64(val),
|
||||
Bool(val) => Bool(val),
|
||||
Date(val) => Date(val),
|
||||
Facet(val) => Facet(val),
|
||||
Bytes(val) => Bytes(val),
|
||||
JsonObject(val) => JsonObject(val),
|
||||
IpAddr(val) => IpAddr(val),
|
||||
}
|
||||
}
|
||||
}
|
||||
impl Eq for Value {}
|
||||
|
||||
impl<'a> Eq for Value<'a> {}
|
||||
|
||||
impl<'a> Serialize for Value<'a> {
|
||||
impl Serialize for Value {
|
||||
fn serialize<S>(&self, serializer: S) -> Result<S::Ok, S::Error>
|
||||
where S: Serializer {
|
||||
match *self {
|
||||
@@ -88,13 +65,13 @@ impl<'a> Serialize for Value<'a> {
|
||||
}
|
||||
}
|
||||
|
||||
impl<'de> Deserialize<'de> for Value<'de> {
|
||||
impl<'de> Deserialize<'de> for Value {
|
||||
fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
|
||||
where D: Deserializer<'de> {
|
||||
struct ValueVisitor;
|
||||
|
||||
impl<'de> Visitor<'de> for ValueVisitor {
|
||||
type Value = Value<'de>;
|
||||
type Value = Value;
|
||||
|
||||
fn expecting(&self, formatter: &mut fmt::Formatter<'_>) -> fmt::Result {
|
||||
formatter.write_str("a string or u32")
|
||||
@@ -116,13 +93,12 @@ impl<'de> Deserialize<'de> for Value<'de> {
|
||||
Ok(Value::Bool(v))
|
||||
}
|
||||
|
||||
// TODO add visit_borrowed_str
|
||||
fn visit_str<E>(self, v: &str) -> Result<Self::Value, E> {
|
||||
Ok(Value::Str(MaybeOwnedString::from_string(v.to_owned())))
|
||||
Ok(Value::Str(v.to_owned()))
|
||||
}
|
||||
|
||||
fn visit_string<E>(self, v: String) -> Result<Self::Value, E> {
|
||||
Ok(Value::Str(MaybeOwnedString::from_string(v)))
|
||||
Ok(Value::Str(v))
|
||||
}
|
||||
}
|
||||
|
||||
@@ -130,7 +106,7 @@ impl<'de> Deserialize<'de> for Value<'de> {
|
||||
}
|
||||
}
|
||||
|
||||
impl<'a> Value<'a> {
|
||||
impl Value {
|
||||
/// Returns the text value, provided the value is of the `Str` type.
|
||||
/// (Returns `None` if the value is not of the `Str` type).
|
||||
pub fn as_text(&self) -> Option<&str> {
|
||||
@@ -248,87 +224,86 @@ impl<'a> Value<'a> {
|
||||
}
|
||||
}
|
||||
|
||||
impl From<String> for Value<'static> {
|
||||
fn from(s: String) -> Value<'static> {
|
||||
Value::Str(MaybeOwnedString::from_string(s))
|
||||
impl From<String> for Value {
|
||||
fn from(s: String) -> Value {
|
||||
Value::Str(s)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<Ipv6Addr> for Value<'static> {
|
||||
fn from(v: Ipv6Addr) -> Value<'static> {
|
||||
impl From<Ipv6Addr> for Value {
|
||||
fn from(v: Ipv6Addr) -> Value {
|
||||
Value::IpAddr(v)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<u64> for Value<'static> {
|
||||
fn from(v: u64) -> Value<'static> {
|
||||
impl From<u64> for Value {
|
||||
fn from(v: u64) -> Value {
|
||||
Value::U64(v)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<i64> for Value<'static> {
|
||||
fn from(v: i64) -> Value<'static> {
|
||||
impl From<i64> for Value {
|
||||
fn from(v: i64) -> Value {
|
||||
Value::I64(v)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<f64> for Value<'static> {
|
||||
fn from(v: f64) -> Value<'static> {
|
||||
impl From<f64> for Value {
|
||||
fn from(v: f64) -> Value {
|
||||
Value::F64(v)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<bool> for Value<'static> {
|
||||
impl From<bool> for Value {
|
||||
fn from(b: bool) -> Self {
|
||||
Value::Bool(b)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<DateTime> for Value<'static> {
|
||||
fn from(dt: DateTime) -> Value<'static> {
|
||||
impl From<DateTime> for Value {
|
||||
fn from(dt: DateTime) -> Value {
|
||||
Value::Date(dt)
|
||||
}
|
||||
}
|
||||
|
||||
impl<'a> From<&'a str> for Value<'a> {
|
||||
fn from(s: &'a str) -> Value<'a> {
|
||||
Value::Str(MaybeOwnedString::from_str(s))
|
||||
impl<'a> From<&'a str> for Value {
|
||||
fn from(s: &'a str) -> Value {
|
||||
Value::Str(s.to_string())
|
||||
}
|
||||
}
|
||||
|
||||
// TODO change lifetime to 'a
|
||||
impl<'a> From<&'a [u8]> for Value<'static> {
|
||||
fn from(bytes: &'a [u8]) -> Value<'static> {
|
||||
impl<'a> From<&'a [u8]> for Value {
|
||||
fn from(bytes: &'a [u8]) -> Value {
|
||||
Value::Bytes(bytes.to_vec())
|
||||
}
|
||||
}
|
||||
|
||||
impl From<Facet> for Value<'static> {
|
||||
fn from(facet: Facet) -> Value<'static> {
|
||||
impl From<Facet> for Value {
|
||||
fn from(facet: Facet) -> Value {
|
||||
Value::Facet(facet)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<Vec<u8>> for Value<'static> {
|
||||
fn from(bytes: Vec<u8>) -> Value<'static> {
|
||||
impl From<Vec<u8>> for Value {
|
||||
fn from(bytes: Vec<u8>) -> Value {
|
||||
Value::Bytes(bytes)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<PreTokenizedString> for Value<'static> {
|
||||
fn from(pretokenized_string: PreTokenizedString) -> Value<'static> {
|
||||
impl From<PreTokenizedString> for Value {
|
||||
fn from(pretokenized_string: PreTokenizedString) -> Value {
|
||||
Value::PreTokStr(pretokenized_string)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<serde_json::Map<String, serde_json::Value>> for Value<'static> {
|
||||
fn from(json_object: serde_json::Map<String, serde_json::Value>) -> Value<'static> {
|
||||
impl From<serde_json::Map<String, serde_json::Value>> for Value {
|
||||
fn from(json_object: serde_json::Map<String, serde_json::Value>) -> Value {
|
||||
Value::JsonObject(json_object)
|
||||
}
|
||||
}
|
||||
|
||||
impl From<serde_json::Value> for Value<'static> {
|
||||
fn from(json_value: serde_json::Value) -> Value<'static> {
|
||||
impl From<serde_json::Value> for Value {
|
||||
fn from(json_value: serde_json::Value) -> Value {
|
||||
match json_value {
|
||||
serde_json::Value::Object(json_object) => Value::JsonObject(json_object),
|
||||
_ => {
|
||||
@@ -345,7 +320,7 @@ mod binary_serialize {
|
||||
use common::{f64_to_u64, u64_to_f64, BinarySerializable};
|
||||
use fastfield_codecs::MonotonicallyMappableToU128;
|
||||
|
||||
use super::{MaybeOwnedString, Value};
|
||||
use super::Value;
|
||||
use crate::schema::Facet;
|
||||
use crate::tokenizer::PreTokenizedString;
|
||||
use crate::DateTime;
|
||||
@@ -366,13 +341,12 @@ mod binary_serialize {
|
||||
|
||||
const TOK_STR_CODE: u8 = 0;
|
||||
|
||||
impl<'a> BinarySerializable for Value<'a> {
|
||||
impl BinarySerializable for Value {
|
||||
fn serialize<W: Write>(&self, writer: &mut W) -> io::Result<()> {
|
||||
match *self {
|
||||
Value::Str(ref text) => {
|
||||
TEXT_CODE.serialize(writer)?;
|
||||
// TODO impl trait for MaybeOwnedString
|
||||
text.as_str().to_owned().serialize(writer)
|
||||
text.serialize(writer)
|
||||
}
|
||||
Value::PreTokStr(ref tok_str) => {
|
||||
EXT_CODE.serialize(writer)?;
|
||||
@@ -434,7 +408,7 @@ mod binary_serialize {
|
||||
match type_code {
|
||||
TEXT_CODE => {
|
||||
let text = String::deserialize(reader)?;
|
||||
Ok(Value::Str(MaybeOwnedString::from_string(text)))
|
||||
Ok(Value::Str(text))
|
||||
}
|
||||
U64_CODE => {
|
||||
let value = u64::deserialize(reader)?;
|
||||
@@ -576,104 +550,3 @@ mod tests {
|
||||
assert_eq!(serialized_value_json, r#""1996-12-20T01:39:57Z""#);
|
||||
}
|
||||
}
|
||||
|
||||
mod not_safe {
|
||||
use std::ops::Deref;
|
||||
|
||||
union Ref<'a, T: ?Sized> {
|
||||
shared: &'a T,
|
||||
uniq: &'a mut T,
|
||||
}
|
||||
|
||||
pub struct MaybeOwnedString<'a> {
|
||||
string: Ref<'a, str>,
|
||||
capacity: usize,
|
||||
}
|
||||
|
||||
impl<'a> MaybeOwnedString<'a> {
|
||||
pub fn from_str(string: &'a str) -> MaybeOwnedString<'a> {
|
||||
MaybeOwnedString {
|
||||
string: Ref { shared: string },
|
||||
capacity: 0,
|
||||
}
|
||||
}
|
||||
|
||||
pub fn from_string(mut string: String) -> MaybeOwnedString<'static> {
|
||||
string.shrink_to_fit(); // <= actually important for safety, todo use the Vec .as_ptr instead
|
||||
|
||||
let mut s = std::mem::ManuallyDrop::new(string);
|
||||
let ptr = s.as_mut_ptr();
|
||||
let len = s.len();
|
||||
let capacity = s.capacity();
|
||||
|
||||
let string = unsafe {
|
||||
std::str::from_utf8_unchecked_mut(std::slice::from_raw_parts_mut(ptr, len))
|
||||
};
|
||||
MaybeOwnedString {
|
||||
string: Ref { uniq: string },
|
||||
capacity,
|
||||
}
|
||||
}
|
||||
|
||||
pub fn into_string(mut self) -> String {
|
||||
if self.capacity != 0 {
|
||||
let string = unsafe { &mut self.string.uniq };
|
||||
unsafe {
|
||||
return String::from_raw_parts(string.as_mut_ptr(), self.len(), self.capacity);
|
||||
};
|
||||
}
|
||||
self.deref().to_owned()
|
||||
}
|
||||
|
||||
pub fn as_str(&self) -> &str {
|
||||
self.deref()
|
||||
}
|
||||
}
|
||||
|
||||
impl<'a> Deref for MaybeOwnedString<'a> {
|
||||
type Target = str;
|
||||
|
||||
#[inline]
|
||||
fn deref(&self) -> &str {
|
||||
unsafe { self.string.shared }
|
||||
}
|
||||
}
|
||||
|
||||
impl<'a> Drop for MaybeOwnedString<'a> {
|
||||
fn drop(&mut self) {
|
||||
// if capacity is 0, either it's an empty String so there is no dealloc to do, or it's
|
||||
// borrowed
|
||||
if self.capacity != 0 {
|
||||
let string = unsafe { &mut self.string.uniq };
|
||||
unsafe { String::from_raw_parts(string.as_mut_ptr(), self.len(), self.capacity) };
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl<'a> Clone for MaybeOwnedString<'a> {
|
||||
fn clone(&self) -> Self {
|
||||
if self.capacity == 0 {
|
||||
MaybeOwnedString {
|
||||
string: Ref {
|
||||
shared: unsafe { self.string.shared },
|
||||
},
|
||||
capacity: 0,
|
||||
}
|
||||
} else {
|
||||
MaybeOwnedString::from_string(self.deref().to_owned())
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl<'a> std::fmt::Debug for MaybeOwnedString<'a> {
|
||||
fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
|
||||
f.write_str(self.deref())
|
||||
}
|
||||
}
|
||||
|
||||
impl<'a> PartialEq for MaybeOwnedString<'a> {
|
||||
fn eq(&self, other: &Self) -> bool {
|
||||
self.deref() == other.deref()
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
@@ -126,7 +126,6 @@ mod ngram_tokenizer;
|
||||
mod raw_tokenizer;
|
||||
mod remove_long;
|
||||
mod simple_tokenizer;
|
||||
mod split_compound_words;
|
||||
mod stemmer;
|
||||
mod stop_word_filter;
|
||||
mod tokenized_string;
|
||||
@@ -142,7 +141,6 @@ pub use self::ngram_tokenizer::NgramTokenizer;
|
||||
pub use self::raw_tokenizer::RawTokenizer;
|
||||
pub use self::remove_long::RemoveLongFilter;
|
||||
pub use self::simple_tokenizer::SimpleTokenizer;
|
||||
pub use self::split_compound_words::SplitCompoundWords;
|
||||
pub use self::stemmer::{Language, Stemmer};
|
||||
pub use self::stop_word_filter::StopWordFilter;
|
||||
pub use self::tokenized_string::{PreTokenizedStream, PreTokenizedString};
|
||||
|
||||
@@ -1,252 +0,0 @@
|
||||
use std::sync::Arc;
|
||||
|
||||
use aho_corasick::{AhoCorasick, AhoCorasickBuilder, MatchKind, StateID};
|
||||
|
||||
use super::{BoxTokenStream, Token, TokenFilter, TokenStream};
|
||||
|
||||
/// A [`TokenFilter`] which splits compound words into their parts
|
||||
/// based on a given dictionary.
|
||||
///
|
||||
/// Words only will be split if they can be fully decomposed into
|
||||
/// consecutive matches into the given dictionary.
|
||||
///
|
||||
/// This is mostly useful to split [compound nouns][compound] common to many
|
||||
/// Germanic languages into their constituents.
|
||||
///
|
||||
/// # Example
|
||||
///
|
||||
/// The quality of the dictionary determines the quality of the splits,
|
||||
/// e.g. the missing stem "back" of "backen" implies that "brotbackautomat"
|
||||
/// is not split in the following example.
|
||||
///
|
||||
/// ```rust
|
||||
/// use tantivy::tokenizer::{SimpleTokenizer, SplitCompoundWords, TextAnalyzer};
|
||||
///
|
||||
/// let tokenizer =
|
||||
/// TextAnalyzer::from(SimpleTokenizer).filter(SplitCompoundWords::from_dictionary([
|
||||
/// "dampf", "schiff", "fahrt", "brot", "backen", "automat",
|
||||
/// ]));
|
||||
///
|
||||
/// let mut stream = tokenizer.token_stream("dampfschifffahrt");
|
||||
/// assert_eq!(stream.next().unwrap().text, "dampf");
|
||||
/// assert_eq!(stream.next().unwrap().text, "schiff");
|
||||
/// assert_eq!(stream.next().unwrap().text, "fahrt");
|
||||
/// assert_eq!(stream.next(), None);
|
||||
///
|
||||
/// let mut stream = tokenizer.token_stream("brotbackautomat");
|
||||
/// assert_eq!(stream.next().unwrap().text, "brotbackautomat");
|
||||
/// assert_eq!(stream.next(), None);
|
||||
/// ```
|
||||
///
|
||||
/// [compound]: https://en.wikipedia.org/wiki/Compound_(linguistics)
|
||||
#[derive(Clone)]
|
||||
pub struct SplitCompoundWords<S: StateID> {
|
||||
dict: Arc<AhoCorasick<S>>,
|
||||
}
|
||||
|
||||
impl SplitCompoundWords<usize> {
|
||||
/// Create a filter from a given dictionary.
|
||||
///
|
||||
/// The dictionary will be used to construct an [`AhoCorasick`] automaton
|
||||
/// with reasonable defaults. See [`from_automaton`][Self::from_automaton] if
|
||||
/// more control over its construction is required.
|
||||
pub fn from_dictionary<I, P>(dict: I) -> Self
|
||||
where
|
||||
I: IntoIterator<Item = P>,
|
||||
P: AsRef<[u8]>,
|
||||
{
|
||||
let dict = AhoCorasickBuilder::new()
|
||||
.match_kind(MatchKind::LeftmostLongest)
|
||||
.build(dict);
|
||||
|
||||
Self::from_automaton(dict)
|
||||
}
|
||||
}
|
||||
|
||||
impl<S: StateID> SplitCompoundWords<S> {
|
||||
/// Create a filter from a given automaton.
|
||||
///
|
||||
/// The automaton should use one of the leftmost-first match kinds
|
||||
/// and it should not be anchored.
|
||||
pub fn from_automaton(dict: AhoCorasick<S>) -> Self {
|
||||
Self {
|
||||
dict: Arc::new(dict),
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl<S: StateID + Send + Sync + 'static> TokenFilter for SplitCompoundWords<S> {
|
||||
fn transform<'a>(&self, stream: BoxTokenStream<'a>) -> BoxTokenStream<'a> {
|
||||
BoxTokenStream::from(SplitCompoundWordsTokenStream {
|
||||
dict: self.dict.clone(),
|
||||
tail: stream,
|
||||
cuts: Vec::new(),
|
||||
parts: Vec::new(),
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
struct SplitCompoundWordsTokenStream<'a, S: StateID> {
|
||||
dict: Arc<AhoCorasick<S>>,
|
||||
tail: BoxTokenStream<'a>,
|
||||
cuts: Vec<usize>,
|
||||
parts: Vec<Token>,
|
||||
}
|
||||
|
||||
impl<'a, S: StateID> SplitCompoundWordsTokenStream<'a, S> {
|
||||
// Will use `self.cuts` to fill `self.parts` if `self.tail.token()`
|
||||
// can fully be split into consecutive matches against `self.dict`.
|
||||
fn split(&mut self) {
|
||||
let token = self.tail.token();
|
||||
let mut text = token.text.as_str();
|
||||
|
||||
self.cuts.clear();
|
||||
let mut pos = 0;
|
||||
|
||||
for match_ in self.dict.find_iter(text) {
|
||||
if pos != match_.start() {
|
||||
break;
|
||||
}
|
||||
|
||||
self.cuts.push(pos);
|
||||
pos = match_.end();
|
||||
}
|
||||
|
||||
if pos == token.text.len() {
|
||||
// Fill `self.parts` in reverse order,
|
||||
// so that `self.parts.pop()` yields
|
||||
// the tokens in their original order.
|
||||
for pos in self.cuts.iter().rev() {
|
||||
let (head, tail) = text.split_at(*pos);
|
||||
|
||||
text = head;
|
||||
self.parts.push(Token {
|
||||
text: tail.to_owned(),
|
||||
..*token
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
impl<'a, S: StateID> TokenStream for SplitCompoundWordsTokenStream<'a, S> {
|
||||
fn advance(&mut self) -> bool {
|
||||
self.parts.pop();
|
||||
|
||||
if !self.parts.is_empty() {
|
||||
return true;
|
||||
}
|
||||
|
||||
if !self.tail.advance() {
|
||||
return false;
|
||||
}
|
||||
|
||||
// Will yield either `self.parts.last()` or
|
||||
// `self.tail.token()` if it could not be split.
|
||||
self.split();
|
||||
true
|
||||
}
|
||||
|
||||
fn token(&self) -> &Token {
|
||||
self.parts.last().unwrap_or_else(|| self.tail.token())
|
||||
}
|
||||
|
||||
fn token_mut(&mut self) -> &mut Token {
|
||||
self.parts
|
||||
.last_mut()
|
||||
.unwrap_or_else(|| self.tail.token_mut())
|
||||
}
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use crate::tokenizer::{SimpleTokenizer, TextAnalyzer};
|
||||
|
||||
#[test]
|
||||
fn splitting_compound_words_works() {
|
||||
let tokenizer = TextAnalyzer::from(SimpleTokenizer)
|
||||
.filter(SplitCompoundWords::from_dictionary(["foo", "bar"]));
|
||||
|
||||
{
|
||||
let mut stream = tokenizer.token_stream("");
|
||||
assert_eq!(stream.next(), None);
|
||||
}
|
||||
|
||||
{
|
||||
let mut stream = tokenizer.token_stream("foo bar");
|
||||
assert_eq!(stream.next().unwrap().text, "foo");
|
||||
assert_eq!(stream.next().unwrap().text, "bar");
|
||||
assert_eq!(stream.next(), None);
|
||||
}
|
||||
|
||||
{
|
||||
let mut stream = tokenizer.token_stream("foobar");
|
||||
assert_eq!(stream.next().unwrap().text, "foo");
|
||||
assert_eq!(stream.next().unwrap().text, "bar");
|
||||
assert_eq!(stream.next(), None);
|
||||
}
|
||||
|
||||
{
|
||||
let mut stream = tokenizer.token_stream("foobarbaz");
|
||||
assert_eq!(stream.next().unwrap().text, "foobarbaz");
|
||||
assert_eq!(stream.next(), None);
|
||||
}
|
||||
|
||||
{
|
||||
let mut stream = tokenizer.token_stream("baz foobar qux");
|
||||
assert_eq!(stream.next().unwrap().text, "baz");
|
||||
assert_eq!(stream.next().unwrap().text, "foo");
|
||||
assert_eq!(stream.next().unwrap().text, "bar");
|
||||
assert_eq!(stream.next().unwrap().text, "qux");
|
||||
assert_eq!(stream.next(), None);
|
||||
}
|
||||
|
||||
{
|
||||
let mut stream = tokenizer.token_stream("foobar foobar");
|
||||
assert_eq!(stream.next().unwrap().text, "foo");
|
||||
assert_eq!(stream.next().unwrap().text, "bar");
|
||||
assert_eq!(stream.next().unwrap().text, "foo");
|
||||
assert_eq!(stream.next().unwrap().text, "bar");
|
||||
assert_eq!(stream.next(), None);
|
||||
}
|
||||
|
||||
{
|
||||
let mut stream = tokenizer.token_stream("foobar foo bar foobar");
|
||||
assert_eq!(stream.next().unwrap().text, "foo");
|
||||
assert_eq!(stream.next().unwrap().text, "bar");
|
||||
assert_eq!(stream.next().unwrap().text, "foo");
|
||||
assert_eq!(stream.next().unwrap().text, "bar");
|
||||
assert_eq!(stream.next().unwrap().text, "foo");
|
||||
assert_eq!(stream.next().unwrap().text, "bar");
|
||||
assert_eq!(stream.next(), None);
|
||||
}
|
||||
|
||||
{
|
||||
let mut stream = tokenizer.token_stream("foobazbar foo bar foobar");
|
||||
assert_eq!(stream.next().unwrap().text, "foobazbar");
|
||||
assert_eq!(stream.next().unwrap().text, "foo");
|
||||
assert_eq!(stream.next().unwrap().text, "bar");
|
||||
assert_eq!(stream.next().unwrap().text, "foo");
|
||||
assert_eq!(stream.next().unwrap().text, "bar");
|
||||
assert_eq!(stream.next(), None);
|
||||
}
|
||||
|
||||
{
|
||||
let mut stream = tokenizer.token_stream("foobar qux foobar");
|
||||
assert_eq!(stream.next().unwrap().text, "foo");
|
||||
assert_eq!(stream.next().unwrap().text, "bar");
|
||||
assert_eq!(stream.next().unwrap().text, "qux");
|
||||
assert_eq!(stream.next().unwrap().text, "foo");
|
||||
assert_eq!(stream.next().unwrap().text, "bar");
|
||||
assert_eq!(stream.next(), None);
|
||||
}
|
||||
|
||||
{
|
||||
let mut stream = tokenizer.token_stream("barfoo");
|
||||
assert_eq!(stream.next().unwrap().text, "bar");
|
||||
assert_eq!(stream.next().unwrap().text, "foo");
|
||||
assert_eq!(stream.next(), None);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,6 +1,3 @@
|
||||
use std::borrow::Cow;
|
||||
use std::mem;
|
||||
|
||||
use rust_stemmers::{self, Algorithm};
|
||||
use serde::{Deserialize, Serialize};
|
||||
|
||||
@@ -87,7 +84,6 @@ impl TokenFilter for Stemmer {
|
||||
BoxTokenStream::from(StemmerTokenStream {
|
||||
tail: token_stream,
|
||||
stemmer: inner_stemmer,
|
||||
buffer: String::new(),
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -95,7 +91,6 @@ impl TokenFilter for Stemmer {
|
||||
pub struct StemmerTokenStream<'a> {
|
||||
tail: BoxTokenStream<'a>,
|
||||
stemmer: rust_stemmers::Stemmer,
|
||||
buffer: String,
|
||||
}
|
||||
|
||||
impl<'a> TokenStream for StemmerTokenStream<'a> {
|
||||
@@ -103,16 +98,10 @@ impl<'a> TokenStream for StemmerTokenStream<'a> {
|
||||
if !self.tail.advance() {
|
||||
return false;
|
||||
}
|
||||
let token = self.tail.token_mut();
|
||||
let stemmed_str = self.stemmer.stem(&token.text);
|
||||
match stemmed_str {
|
||||
Cow::Owned(stemmed_str) => token.text = stemmed_str,
|
||||
Cow::Borrowed(stemmed_str) => {
|
||||
self.buffer.clear();
|
||||
self.buffer.push_str(stemmed_str);
|
||||
mem::swap(&mut token.text, &mut self.buffer);
|
||||
}
|
||||
}
|
||||
// TODO remove allocation
|
||||
let stemmed_str: String = self.stemmer.stem(&self.token().text).into_owned();
|
||||
self.token_mut().text.clear();
|
||||
self.token_mut().text.push_str(&stemmed_str);
|
||||
true
|
||||
}
|
||||
|
||||
|
||||
@@ -10,21 +10,28 @@
|
||||
//! assert_eq!(stream.next().unwrap().text, "crafty");
|
||||
//! assert!(stream.next().is_none());
|
||||
//! ```
|
||||
use rustc_hash::FxHashSet;
|
||||
use std::collections::HashSet;
|
||||
use std::hash::BuildHasherDefault;
|
||||
|
||||
use fnv::FnvHasher;
|
||||
|
||||
use super::{Token, TokenFilter, TokenStream};
|
||||
use crate::tokenizer::BoxTokenStream;
|
||||
|
||||
// configure our hashers for SPEED
|
||||
type StopWordHasher = BuildHasherDefault<FnvHasher>;
|
||||
type StopWordHashSet = HashSet<String, StopWordHasher>;
|
||||
|
||||
/// `TokenFilter` that removes stop words from a token stream
|
||||
#[derive(Clone)]
|
||||
pub struct StopWordFilter {
|
||||
words: FxHashSet<String>,
|
||||
words: StopWordHashSet,
|
||||
}
|
||||
|
||||
impl StopWordFilter {
|
||||
/// Creates a `StopWordFilter` given a list of words to remove
|
||||
pub fn remove(words: Vec<String>) -> StopWordFilter {
|
||||
let mut set = FxHashSet::default();
|
||||
let mut set = StopWordHashSet::default();
|
||||
|
||||
for word in words {
|
||||
set.insert(word);
|
||||
@@ -45,7 +52,7 @@ impl StopWordFilter {
|
||||
}
|
||||
|
||||
pub struct StopWordFilterStream<'a> {
|
||||
words: FxHashSet<String>,
|
||||
words: StopWordHashSet,
|
||||
tail: BoxTokenStream<'a>,
|
||||
}
|
||||
|
||||
|
||||
Reference in New Issue
Block a user