searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2025-07-04 20:37:15 +02:00
Code Issues Releases Wiki Activity

Refactor word prefix pair proximity indexation

Browse source
This commit is contained in:
Loïc Lecrenier 2022-07-06 18:20:15 +02:00
parent f55034ed54
commit 306593144d
7 changed files with 649 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

1
milli/src/heed_codec/mod.rs
View file

@ -16,3 +16,4 @@ pub use self::roaring_bitmap_length::{
};
pub use self::str_beu32_codec::StrBEU32Codec;
pub use self::str_str_u8_codec::StrStrU8Codec;
pub use self::str_str_u8_codec::UncheckedStrStrU8Codec;

35
milli/src/heed_codec/str_str_u8_codec.rs
View file

@ -9,9 +9,11 @@ impl<'a> heed::BytesDecode<'a> for StrStrU8Codec {
fn bytes_decode(bytes: &'a [u8]) -> Option<Self::DItem> {
let (n, bytes) = bytes.split_last()?;
let s1_end = bytes.iter().position(|b| *b == 0)?;
let (s1_bytes, s2_bytes) = bytes.split_at(s1_end);
let (s1_bytes, rest) = bytes.split_at(s1_end);
let rest = &rest[1..];
let s1 = str::from_utf8(s1_bytes).ok()?;
let s2 = str::from_utf8(&s2_bytes[1..]).ok()?;
let (_, s2_bytes) = rest.split_last()?;
let s2 = str::from_utf8(s2_bytes).ok()?;
Some((s1, s2, *n))
}
}
@ -24,6 +26,35 @@ impl<'a> heed::BytesEncode<'a> for StrStrU8Codec {
bytes.extend_from_slice(s1.as_bytes());
bytes.push(0);
bytes.extend_from_slice(s2.as_bytes());
bytes.push(0);
bytes.push(*n);
Some(Cow::Owned(bytes))
}
}
pub struct UncheckedStrStrU8Codec;
impl<'a> heed::BytesDecode<'a> for UncheckedStrStrU8Codec {
type DItem = (&'a [u8], &'a [u8], u8);
fn bytes_decode(bytes: &'a [u8]) -> Option<Self::DItem> {
let (n, bytes) = bytes.split_last()?;
let s1_end = bytes.iter().position(|b| *b == 0)?;
let (s1_bytes, rest) = bytes.split_at(s1_end);
let rest = &rest[1..];
let (_, s2_bytes) = rest.split_last()?;
Some((s1_bytes, s2_bytes, *n))
}
}
impl<'a> heed::BytesEncode<'a> for UncheckedStrStrU8Codec {
type EItem = (&'a [u8], &'a [u8], u8);
fn bytes_encode((s1, s2, n): &Self::EItem) -> Option<Cow<[u8]>> {
let mut bytes = Vec::with_capacity(s1.len() + s2.len() + 1 + 1);
bytes.extend_from_slice(s1);
bytes.push(0);
bytes.extend_from_slice(s2);
bytes.push(0);
bytes.push(*n);
Some(Cow::Owned(bytes))
}