Normalize for the search the facets values

This commit is contained in:
Clément Renault
2023-07-20 17:57:07 +02:00
parent 3070a20580
commit df528b41d8
12 changed files with 178 additions and 46 deletions

View File

@ -1,4 +1,5 @@
use std::borrow::Cow;
use std::collections::BTreeSet;
use std::io;
use std::result::Result as StdResult;
@ -44,6 +45,27 @@ pub fn merge_roaring_bitmaps<'a>(_key: &[u8], values: &[Cow<'a, [u8]>]) -> Resul
}
}
pub fn merge_btreeset_string<'a>(_key: &[u8], values: &[Cow<'a, [u8]>]) -> Result<Cow<'a, [u8]>> {
if values.len() == 1 {
Ok(values[0].clone())
} else {
// TODO improve the perf by using a `#[borrow] Cow<str>`.
let strings: BTreeSet<String> = values
.iter()
.map(AsRef::as_ref)
.map(serde_json::from_slice::<BTreeSet<String>>)
.map(StdResult::unwrap)
.reduce(|mut current, new| {
for x in new {
current.insert(x);
}
current
})
.unwrap();
Ok(Cow::Owned(serde_json::to_vec(&strings).unwrap()))
}
}
pub fn keep_first<'a>(_key: &[u8], values: &[Cow<'a, [u8]>]) -> Result<Cow<'a, [u8]>> {
Ok(values[0].clone())
}

View File

@ -13,9 +13,9 @@ pub use grenad_helpers::{
GrenadParameters, MergeableReader,
};
pub use merge_functions::{
concat_u32s_array, keep_first, keep_latest_obkv, merge_cbo_roaring_bitmaps,
merge_obkvs_and_operations, merge_roaring_bitmaps, merge_two_obkvs, serialize_roaring_bitmap,
MergeFn,
concat_u32s_array, keep_first, keep_latest_obkv, merge_btreeset_string,
merge_cbo_roaring_bitmaps, merge_obkvs_and_operations, merge_roaring_bitmaps, merge_two_obkvs,
serialize_roaring_bitmap, MergeFn,
};
use crate::MAX_WORD_LENGTH;

View File

@ -26,7 +26,7 @@ pub use self::enrich::{
};
pub use self::helpers::{
as_cloneable_grenad, create_sorter, create_writer, fst_stream_into_hashset,
fst_stream_into_vec, merge_cbo_roaring_bitmaps, merge_roaring_bitmaps,
fst_stream_into_vec, merge_btreeset_string, merge_cbo_roaring_bitmaps, merge_roaring_bitmaps,
sorter_into_lmdb_database, valid_lmdb_key, writer_into_reader, ClonableMmap, MergeFn,
};
use self::helpers::{grenad_obkv_into_chunks, GrenadParameters};