snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2025-10-30 23:46:28 +00:00
Code Issues Packages Projects Releases Wiki Activity

Prepare refactor of facets database

Browse Source 
Prepare refactor of facets database
This commit is contained in:
Loïc Lecrenier
2022-08-29 16:01:54 +02:00
committed by Loïc Lecrenier
parent 004c09a8e2
commit c3f49f766d
27 changed files with 1662 additions and 1624 deletions
Download Patch File Download Diff File Expand all files Collapse all files

108
milli/src/update/delete_documents.rs
View File

@@ -10,9 +10,7 @@ use time::OffsetDateTime;
use super::ClearDocuments;
use crate::error::{InternalError, SerializationError, UserError};
use crate::heed_codec::facet::{
FacetLevelValueU32Codec, FacetStringLevelZeroValueCodec, FacetStringZeroBoundsValueCodec,
};
use crate::heed_codec::facet::FacetStringZeroBoundsValueCodec;
use crate::heed_codec::CboRoaringBitmapCodec;
use crate::index::{db_name, main_key};
use crate::{
@@ -442,11 +440,11 @@ impl<'t, 'u, 'i> DeleteDocuments<'t, 'u, 'i> {
}
// We delete the documents ids that are under the facet field id values.
remove_docids_from_facet_field_id_docids(
self.wtxn,
facet_id_f64_docids,
&self.to_delete_docids,
)?;
// TODO: remove_docids_from_facet_field_id_docids(
// self.wtxn,
// facet_id_f64_docids,
// &self.to_delete_docids,
// )?;
// We delete the documents ids that are under the facet field id values.
remove_docids_from_facet_field_id_docids(
self.wtxn,
@@ -587,57 +585,57 @@ fn remove_docids_from_facet_field_id_string_docids<'a, C, D>(
db: &heed::Database<C, D>,
to_remove: &RoaringBitmap,
) -> crate::Result<()> {
let db_name = Some(crate::index::db_name::FACET_ID_STRING_DOCIDS);
let mut iter = db.remap_types::<ByteSlice, ByteSlice>().iter_mut(wtxn)?;
while let Some(result) = iter.next() {
let (key, val) = result?;
match FacetLevelValueU32Codec::bytes_decode(key) {
Some(_) => {
// If we are able to parse this key it means it is a facet string group
// level key. We must then parse the value using the appropriate codec.
let (group, mut docids) =
FacetStringZeroBoundsValueCodec::<CboRoaringBitmapCodec>::bytes_decode(val)
.ok_or_else(|| SerializationError::Decoding { db_name })?;
// let db_name = Some(crate::index::db_name::FACET_ID_STRING_DOCIDS);
// let mut iter = db.remap_types::<ByteSlice, ByteSlice>().iter_mut(wtxn)?;
// while let Some(result) = iter.next() {
// let (key, val) = result?;
// match FacetLevelValueU32Codec::bytes_decode(key) {
// Some(_) => {
// // If we are able to parse this key it means it is a facet string group
// // level key. We must then parse the value using the appropriate codec.
// let (group, mut docids) =
// FacetStringZeroBoundsValueCodec::<CboRoaringBitmapCodec>::bytes_decode(val)
// .ok_or_else(|| SerializationError::Decoding { db_name })?;
let previous_len = docids.len();
docids -= to_remove;
if docids.is_empty() {
// safety: we don't keep references from inside the LMDB database.
unsafe { iter.del_current()? };
} else if docids.len() != previous_len {
let key = key.to_owned();
let val = &(group, docids);
let value_bytes =
FacetStringZeroBoundsValueCodec::<CboRoaringBitmapCodec>::bytes_encode(val)
.ok_or_else(|| SerializationError::Encoding { db_name })?;
// let previous_len = docids.len();
// docids -= to_remove;
// if docids.is_empty() {
// // safety: we don't keep references from inside the LMDB database.
// unsafe { iter.del_current()? };
// } else if docids.len() != previous_len {
// let key = key.to_owned();
// let val = &(group, docids);
// let value_bytes =
// FacetStringZeroBoundsValueCodec::<CboRoaringBitmapCodec>::bytes_encode(val)
// .ok_or_else(|| SerializationError::Encoding { db_name })?;
// safety: we don't keep references from inside the LMDB database.
unsafe { iter.put_current(&key, &value_bytes)? };
}
}
None => {
// The key corresponds to a level zero facet string.
let (original_value, mut docids) =
FacetStringLevelZeroValueCodec::bytes_decode(val)
.ok_or_else(|| SerializationError::Decoding { db_name })?;
// // safety: we don't keep references from inside the LMDB database.
// unsafe { iter.put_current(&key, &value_bytes)? };
// }
// }
// None => {
// // The key corresponds to a level zero facet string.
// let (original_value, mut docids) =
// FacetStringLevelZeroValueCodec::bytes_decode(val)
// .ok_or_else(|| SerializationError::Decoding { db_name })?;
let previous_len = docids.len();
docids -= to_remove;
if docids.is_empty() {
// safety: we don't keep references from inside the LMDB database.
unsafe { iter.del_current()? };
} else if docids.len() != previous_len {
let key = key.to_owned();
let val = &(original_value, docids);
let value_bytes = FacetStringLevelZeroValueCodec::bytes_encode(val)
.ok_or_else(|| SerializationError::Encoding { db_name })?;
// let previous_len = docids.len();
// docids -= to_remove;
// if docids.is_empty() {
// // safety: we don't keep references from inside the LMDB database.
// unsafe { iter.del_current()? };
// } else if docids.len() != previous_len {
// let key = key.to_owned();
// let val = &(original_value, docids);
// let value_bytes = FacetStringLevelZeroValueCodec::bytes_encode(val)
// .ok_or_else(|| SerializationError::Encoding { db_name })?;
// safety: we don't keep references from inside the LMDB database.
unsafe { iter.put_current(&key, &value_bytes)? };
}
}
}
}
// // safety: we don't keep references from inside the LMDB database.
// unsafe { iter.put_current(&key, &value_bytes)? };
// }
// }
// }
// }
Ok(())
}

261
milli/src/update/facets.rs
View File

@@ -136,11 +136,12 @@ use roaring::RoaringBitmap;
use time::OffsetDateTime;
use crate::error::InternalError;
use crate::heed_codec::facet::{
FacetLevelValueF64Codec, FacetLevelValueU32Codec, FacetStringLevelZeroCodec,
FacetStringLevelZeroValueCodec, FacetStringZeroBoundsValueCodec,
use crate::heed_codec::facet::new::ordered_f64_codec::OrderedF64Codec;
use crate::heed_codec::facet::new::str_ref::StrRefCodec;
use crate::heed_codec::facet::new::{
FacetGroupValue, FacetGroupValueCodec, FacetKey, FacetKeyCodec,
};
use crate::heed_codec::CboRoaringBitmapCodec;
// use crate::heed_codec::CboRoaringBitmapCodec;
use crate::update::index_documents::{create_writer, write_into_lmdb_database, writer_into_reader};
use crate::{FieldId, Index, Result};
@@ -187,16 +188,18 @@ impl<'t, 'u, 'i> Facets<'t, 'u, 'i> {
debug!("Computing and writing the facet values levels docids into LMDB on disk...");
let mut nested_wtxn = self.index.env.nested_write_txn(self.wtxn).unwrap();
for field_id in faceted_fields {
// Clear the facet string levels.
clear_field_string_levels(
self.wtxn,
self.index.facet_id_string_docids.remap_types::<ByteSlice, DecodeIgnore>(),
field_id,
)?;
// clear_field_string_levels(
// &mut nested_wtxn,
// self.index.facet_id_string_docids.remap_types::<ByteSlice, DecodeIgnore>(),
// field_id,
// )?;
let (facet_string_levels, string_documents_ids) = compute_facet_strings_levels(
self.wtxn,
&mut nested_wtxn,
self.index.facet_id_string_docids,
self.chunk_compression_type,
self.chunk_compression_level,
@@ -206,13 +209,13 @@ impl<'t, 'u, 'i> Facets<'t, 'u, 'i> {
)?;
self.index.put_string_faceted_documents_ids(
self.wtxn,
&mut nested_wtxn,
field_id,
&string_documents_ids,
)?;
for facet_strings_level in facet_string_levels {
write_into_lmdb_database(
self.wtxn,
&mut nested_wtxn,
*self.index.facet_id_string_docids.as_polymorph(),
facet_strings_level,
|_, _| {
@@ -221,11 +224,11 @@ impl<'t, 'u, 'i> Facets<'t, 'u, 'i> {
)?;
}
// Clear the facet number levels.
clear_field_number_levels(self.wtxn, self.index.facet_id_f64_docids, field_id)?;
// // Clear the facet number levels.
// clear_field_number_levels(&mut nested_wtxn, self.index.facet_id_f64_docids, field_id)?;
let (facet_number_levels, number_documents_ids) = compute_facet_number_levels(
self.wtxn,
&mut nested_wtxn,
self.index.facet_id_f64_docids,
self.chunk_compression_type,
self.chunk_compression_level,
@@ -235,14 +238,14 @@ impl<'t, 'u, 'i> Facets<'t, 'u, 'i> {
)?;
self.index.put_number_faceted_documents_ids(
self.wtxn,
&mut nested_wtxn,
field_id,
&number_documents_ids,
)?;
for facet_number_level in facet_number_levels {
write_into_lmdb_database(
self.wtxn,
&mut nested_wtxn,
*self.index.facet_id_f64_docids.as_polymorph(),
facet_number_level,
|_, _| {
@@ -263,8 +266,8 @@ impl<'t, 'u, 'i> Facets<'t, 'u, 'i> {
/// that must be inserted into the database.
/// 2. a roaring bitmap of all the document ids present in the database
fn compute_facet_number_levels<'t>(
rtxn: &'t heed::RoTxn,
db: heed::Database<FacetLevelValueF64Codec, CboRoaringBitmapCodec>,
rtxn: &'t mut heed::RwTxn,
db: heed::Database<FacetKeyCodec<OrderedF64Codec>, FacetGroupValueCodec>,
compression_type: CompressionType,
compression_level: Option<u32>,
level_group_size: NonZeroUsize,
@@ -277,7 +280,7 @@ fn compute_facet_number_levels<'t>(
.remap_types::<DecodeIgnore, DecodeIgnore>()
.fold(Ok(0usize), |count, result| result.and(count).map(|c| c + 1))?;
let level_0_start = (field_id, 0, f64::MIN, f64::MIN);
let level_0_start = FacetKey { field_id, level: 0, left_bound: f64::MIN };
// Groups sizes are always a power of the original level_group_size and therefore a group
// always maps groups of the previous level and never splits previous levels groups in half.
@@ -289,37 +292,31 @@ fn compute_facet_number_levels<'t>(
let mut number_document_ids = RoaringBitmap::new();
if let Some((top_level, _)) = group_size_iter.last() {
let subwriters =
recursive_compute_levels::<FacetLevelValueF64Codec, CboRoaringBitmapCodec, f64>(
rtxn,
db,
compression_type,
compression_level,
*top_level,
level_0_start,
&(level_0_start..),
first_level_size,
level_group_size,
&mut |bitmaps, _, _| {
for bitmap in bitmaps {
number_document_ids |= bitmap;
}
Ok(())
},
&|_i, (_field_id, _level, left, _right)| *left,
&|bitmap| bitmap,
&|writer, level, left, right, docids| {
write_number_entry(writer, field_id, level.get(), left, right, &docids)?;
Ok(())
},
)?;
let subwriters = recursive_compute_levels::<OrderedF64Codec>(
rtxn,
db,
compression_type,
compression_level,
field_id,
*top_level,
level_0_start,
&(level_0_start..),
first_level_size,
level_group_size,
&mut |bitmaps, _| {
for bitmap in bitmaps {
number_document_ids |= bitmap;
}
Ok(())
},
)?;
Ok((subwriters, number_document_ids))
} else {
let mut documents_ids = RoaringBitmap::new();
for result in db.range(rtxn, &(level_0_start..))?.take(first_level_size) {
let (_key, docids) = result?;
documents_ids |= docids;
let (_key, group_value) = result?;
documents_ids |= group_value.bitmap;
}
Ok((vec![], documents_ids))
@@ -333,8 +330,8 @@ fn compute_facet_number_levels<'t>(
/// that must be inserted into the database.
/// 2. a roaring bitmap of all the document ids present in the database
fn compute_facet_strings_levels<'t>(
rtxn: &'t heed::RoTxn,
db: heed::Database<FacetStringLevelZeroCodec, FacetStringLevelZeroValueCodec>,
rtxn: &'t mut heed::RwTxn,
db: heed::Database<FacetKeyCodec<StrRefCodec>, FacetGroupValueCodec>,
compression_type: CompressionType,
compression_level: Option<u32>,
level_group_size: NonZeroUsize,
@@ -347,7 +344,7 @@ fn compute_facet_strings_levels<'t>(
.remap_types::<DecodeIgnore, DecodeIgnore>()
.fold(Ok(0usize), |count, result| result.and(count).map(|c| c + 1))?;
let level_0_start = (field_id, "");
let level_0_start = FacetKey { field_id, level: 0, left_bound: "" };
// Groups sizes are always a power of the original level_group_size and therefore a group
// always maps groups of the previous level and never splits previous levels groups in half.
@@ -359,40 +356,31 @@ fn compute_facet_strings_levels<'t>(
let mut strings_document_ids = RoaringBitmap::new();
if let Some((top_level, _)) = group_size_iter.last() {
let subwriters = recursive_compute_levels::<
FacetStringLevelZeroCodec,
FacetStringLevelZeroValueCodec,
(u32, &str),
>(
let subwriters = recursive_compute_levels::<StrRefCodec>(
rtxn,
db,
compression_type,
compression_level,
field_id,
*top_level,
level_0_start,
&(level_0_start..),
first_level_size,
level_group_size,
&mut |bitmaps, _, _| {
&mut |bitmaps, _| {
for bitmap in bitmaps {
strings_document_ids |= bitmap;
}
Ok(())
},
&|i, (_field_id, value)| (i as u32, *value),
&|value| value.1,
&|writer, level, start_bound, end_bound, docids| {
write_string_entry(writer, field_id, level, start_bound, end_bound, docids)?;
Ok(())
},
)?;
Ok((subwriters, strings_document_ids))
} else {
let mut documents_ids = RoaringBitmap::new();
for result in db.range(rtxn, &(level_0_start..))?.take(first_level_size) {
let (_key, (_original_value, docids)) = result?;
documents_ids |= docids;
let (_key, group_value) = result?;
documents_ids |= group_value.bitmap;
}
Ok((vec![], documents_ids))
@@ -436,29 +424,26 @@ from the level below were read/created. Its arguments are:
A vector of grenad::Reader. The reader at index `i` corresponds to the elements of level `i + 1`
that must be inserted into the database.
*/
fn recursive_compute_levels<'t, KeyCodec, ValueCodec, Bound>(
rtxn: &'t heed::RoTxn,
db: heed::Database<KeyCodec, ValueCodec>,
fn recursive_compute_levels<'t, BoundCodec>(
rtxn: &'t mut heed::RwTxn,
db: heed::Database<FacetKeyCodec<BoundCodec>, FacetGroupValueCodec>,
compression_type: CompressionType,
compression_level: Option<u32>,
field_id: FieldId,
level: u8,
level_0_start: <KeyCodec as BytesDecode<'t>>::DItem,
level_0_range: &'t RangeFrom<<KeyCodec as BytesDecode<'t>>::DItem>,
level_0_start: FacetKey<<BoundCodec as BytesEncode<'t>>::EItem>,
level_0_range: &'t RangeFrom<FacetKey<<BoundCodec as BytesEncode<'t>>::EItem>>,
level_0_size: usize,
level_group_size: NonZeroUsize,
computed_group_bitmap: &mut dyn FnMut(&[RoaringBitmap], Bound, Bound) -> Result<()>,
bound_from_db_key: &dyn for<'a> Fn(usize, &'a <KeyCodec as BytesDecode<'t>>::DItem) -> Bound,
bitmap_from_db_value: &dyn Fn(<ValueCodec as BytesDecode<'t>>::DItem) -> RoaringBitmap,
write_entry: &dyn Fn(&mut Writer<File>, NonZeroU8, Bound, Bound, RoaringBitmap) -> Result<()>,
computed_group_bitmap: &mut dyn FnMut(
&[RoaringBitmap],
<BoundCodec as BytesEncode<'t>>::EItem,
) -> Result<()>,
) -> Result<Vec<Reader<File>>>
where
KeyCodec: for<'a> BytesEncode<'a>
+ for<'a> BytesDecode<'a, DItem = <KeyCodec as BytesEncode<'a>>::EItem>,
for<'a> <KeyCodec as BytesEncode<'a>>::EItem: Sized,
ValueCodec: for<'a> BytesEncode<'a>
+ for<'a> BytesDecode<'a, DItem = <ValueCodec as BytesEncode<'a>>::EItem>,
for<'a> <ValueCodec as BytesEncode<'a>>::EItem: Sized,
Bound: Copy,
for<'a> BoundCodec:
BytesEncode<'a> + BytesDecode<'a, DItem = <BoundCodec as BytesEncode<'a>>::EItem>,
for<'a> <BoundCodec as BytesEncode<'a>>::EItem: Copy + Sized,
{
if level == 0 {
// base case for the recursion
@@ -468,31 +453,32 @@ where
// 2. fill the `bitmaps` vector to give it to level 1 once `level_group_size` elements were read
let mut bitmaps = vec![];
let mut start_bound = bound_from_db_key(0, &level_0_start);
let mut end_bound = bound_from_db_key(0, &level_0_start);
let mut start_bound = level_0_start.left_bound;
// let mut end_bound = level_0_start.bound;
let mut first_iteration_for_new_group = true;
for (i, db_result_item) in db.range(rtxn, level_0_range)?.take(level_0_size).enumerate() {
let (key, value) = db_result_item?;
let bound = bound_from_db_key(i, &key);
let docids = bitmap_from_db_value(value);
let bound = key.left_bound;
let docids = value.bitmap;
if first_iteration_for_new_group {
start_bound = bound;
first_iteration_for_new_group = false;
}
end_bound = bound;
// end_bound = bound;
bitmaps.push(docids);
if bitmaps.len() == level_group_size.get() {
computed_group_bitmap(&bitmaps, start_bound, end_bound)?;
computed_group_bitmap(&bitmaps, start_bound)?;
first_iteration_for_new_group = true;
bitmaps.clear();
}
}
// don't forget to give the leftover bitmaps as well
if !bitmaps.is_empty() {
computed_group_bitmap(&bitmaps, start_bound, end_bound)?;
computed_group_bitmap(&bitmaps, start_bound)?;
bitmaps.clear();
}
// level 0 is already stored in the DB
@@ -516,48 +502,52 @@ where
db,
compression_type,
compression_level,
field_id,
level - 1,
level_0_start,
level_0_range,
level_0_size,
level_group_size,
&mut |sub_bitmaps: &[RoaringBitmap], start_range, end_range| {
&mut |sub_bitmaps: &[RoaringBitmap],
start_range: <BoundCodec as BytesEncode<'t>>::EItem| {
let mut combined_bitmap = RoaringBitmap::default();
for bitmap in sub_bitmaps {
combined_bitmap |= bitmap;
}
range_for_bitmaps.push((start_range, end_range));
range_for_bitmaps.push(start_range);
bitmaps.push(combined_bitmap);
if bitmaps.len() == level_group_size.get() {
let start_bound = range_for_bitmaps.first().unwrap().0;
let end_bound = range_for_bitmaps.last().unwrap().1;
computed_group_bitmap(&bitmaps, start_bound, end_bound)?;
for (bitmap, (start_bound, end_bound)) in
bitmaps.drain(..).zip(range_for_bitmaps.drain(..))
let start_bound = range_for_bitmaps.first().unwrap();
computed_group_bitmap(&bitmaps, *start_bound)?;
for (bitmap, start_bound) in bitmaps.drain(..).zip(range_for_bitmaps.drain(..))
{
write_entry(
write_entry::<BoundCodec>(
&mut cur_writer,
field_id,
NonZeroU8::new(level).unwrap(),
start_bound,
end_bound,
bitmap,
)?;
}
}
Ok(())
},
bound_from_db_key,
bitmap_from_db_value,
write_entry,
)?;
// don't forget to insert the leftover elements into the writer as well
if !bitmaps.is_empty() {
let start_range = range_for_bitmaps.first().unwrap().0;
let end_range = range_for_bitmaps.last().unwrap().1;
computed_group_bitmap(&bitmaps, start_range, end_range)?;
for (bitmap, (left, right)) in bitmaps.drain(..).zip(range_for_bitmaps.drain(..)) {
write_entry(&mut cur_writer, NonZeroU8::new(level).unwrap(), left, right, bitmap)?;
let start_range = range_for_bitmaps.first().unwrap();
let end_range = range_for_bitmaps.last().unwrap();
computed_group_bitmap(&bitmaps, *start_range)?;
for (bitmap, bound) in bitmaps.drain(..).zip(range_for_bitmaps.drain(..)) {
write_entry(
&mut cur_writer,
field_id,
NonZeroU8::new(level).unwrap(),
bound,
bitmap,
)?;
}
}
@@ -566,60 +556,25 @@ where
}
}
fn clear_field_number_levels<'t>(
wtxn: &'t mut heed::RwTxn,
db: heed::Database<FacetLevelValueF64Codec, CboRoaringBitmapCodec>,
field_id: FieldId,
) -> heed::Result<()> {
let left = (field_id, 1, f64::MIN, f64::MIN);
let right = (field_id, u8::MAX, f64::MAX, f64::MAX);
let range = left..=right;
db.delete_range(wtxn, &range).map(drop)
}
fn clear_field_string_levels<'t>(
wtxn: &'t mut heed::RwTxn,
db: heed::Database<ByteSlice, DecodeIgnore>,
field_id: FieldId,
) -> heed::Result<()> {
let left = (field_id, NonZeroU8::new(1).unwrap(), u32::MIN, u32::MIN);
let right = (field_id, NonZeroU8::new(u8::MAX).unwrap(), u32::MAX, u32::MAX);
let range = left..=right;
db.remap_key_type::<FacetLevelValueU32Codec>().delete_range(wtxn, &range).map(drop)
}
fn write_number_entry(
writer: &mut Writer<File>,
field_id: FieldId,
level: u8,
left: f64,
right: f64,
ids: &RoaringBitmap,
) -> Result<()> {
let key = (field_id, level, left, right);
let key = FacetLevelValueF64Codec::bytes_encode(&key).ok_or(Error::Encoding)?;
let data = CboRoaringBitmapCodec::bytes_encode(&ids).ok_or(Error::Encoding)?;
writer.insert(&key, &data)?;
Ok(())
}
fn write_string_entry(
fn write_entry<BoundCodec>(
writer: &mut Writer<File>,
field_id: FieldId,
level: NonZeroU8,
(left_id, left_value): (u32, &str),
(right_id, right_value): (u32, &str),
bound: <BoundCodec as BytesEncode<'_>>::EItem,
docids: RoaringBitmap,
) -> Result<()> {
let key = (field_id, level, left_id, right_id);
let key = FacetLevelValueU32Codec::bytes_encode(&key).ok_or(Error::Encoding)?;
let data = match level.get() {
1 => (Some((left_value, right_value)), docids),
_ => (None, docids),
};
let data = FacetStringZeroBoundsValueCodec::<CboRoaringBitmapCodec>::bytes_encode(&data)
.ok_or(Error::Encoding)?;
writer.insert(&key, &data)?;
Ok(())
) -> Result<()>
where
for<'a> BoundCodec: BytesEncode<'a>,
for<'a> <BoundCodec as BytesEncode<'a>>::EItem: Copy + Sized,
{
todo!()
// let key = FacetKey { field_id, level: level.get(), left_bound: bound };
// let key_bytes = FacetKeyCodec::<BoundCodec>::bytes_encode(&key).ok_or(Error::Encoding)?;
// let value_bytes =
// FacetGroupValueCodec::bytes_encode(&FacetGroupValue { size: 4, bitmap: docids })
// .ok_or(Error::Encoding)?;
// writer.insert(&key_bytes, &value_bytes)?;
// Ok(())
}
#[cfg(test)]

13
milli/src/update/index_documents/extract/extract_facet_number_docids.rs
View File

@@ -6,7 +6,7 @@ use heed::{BytesDecode, BytesEncode};
use super::helpers::{
create_sorter, merge_cbo_roaring_bitmaps, sorter_into_reader, GrenadParameters,
};
use crate::heed_codec::facet::{FacetLevelValueF64Codec, FieldDocIdFacetF64Codec};
use crate::heed_codec::facet::FieldDocIdFacetF64Codec;
use crate::Result;
/// Extracts the facet number and the documents ids where this facet number appear.
@@ -31,13 +31,14 @@ pub fn extract_facet_number_docids<R: io::Read + io::Seek>(
let mut cursor = docid_fid_facet_number.into_cursor()?;
while let Some((key_bytes, _)) = cursor.move_on_next()? {
let (field_id, document_id, number) =
FieldDocIdFacetF64Codec::bytes_decode(key_bytes).unwrap();
todo!()
// let (field_id, document_id, number) =
// FieldDocIdFacetF64Codec::bytes_decode(key_bytes).unwrap();
let key = (field_id, 0, number, number);
let key_bytes = FacetLevelValueF64Codec::bytes_encode(&key).unwrap();
// let key = (field_id, 0, number, number);
// // let key_bytes = FacetLevelValueF64Codec::bytes_encode(&key).unwrap();
facet_number_docids_sorter.insert(key_bytes, document_id.to_ne_bytes())?;
// facet_number_docids_sorter.insert(key_bytes, document_id.to_ne_bytes())?;
}
sorter_into_reader(facet_number_docids_sorter, indexer)

24
milli/src/update/index_documents/extract/extract_facet_string_docids.rs
View File

@@ -4,11 +4,9 @@ use std::{io, str};
use roaring::RoaringBitmap;
use super::helpers::{
create_sorter, keep_first_prefix_value_merge_roaring_bitmaps, sorter_into_reader,
try_split_array_at, GrenadParameters,
};
use crate::heed_codec::facet::{encode_prefix_string, FacetStringLevelZeroCodec};
use super::helpers::{create_sorter, sorter_into_reader, try_split_array_at, GrenadParameters};
use crate::update::index_documents::merge_cbo_roaring_bitmaps;
// use crate::heed_codec::facet::{encode_prefix_string, FacetStringLevelZeroCodec};
use crate::{FieldId, Result};
/// Extracts the facet string and the documents ids where this facet string appear.
@@ -24,7 +22,7 @@ pub fn extract_facet_string_docids<R: io::Read + io::Seek>(
let mut facet_string_docids_sorter = create_sorter(
grenad::SortAlgorithm::Stable,
keep_first_prefix_value_merge_roaring_bitmaps,
merge_cbo_roaring_bitmaps, // TODO: check
indexer.chunk_compression_type,
indexer.chunk_compression_level,
indexer.max_nb_chunks,
@@ -42,14 +40,16 @@ pub fn extract_facet_string_docids<R: io::Read + io::Seek>(
let original_value = str::from_utf8(original_value_bytes)?;
key_buffer.clear();
FacetStringLevelZeroCodec::serialize_into(
field_id,
str::from_utf8(normalized_value_bytes)?,
&mut key_buffer,
);
// TODO
// FacetStringLevelZeroCodec::serialize_into(
// field_id,
// str::from_utf8(normalized_value_bytes)?,
// &mut key_buffer,
// );
value_buffer.clear();
encode_prefix_string(original_value, &mut value_buffer)?;
// TODO
// encode_prefix_string(original_value, &mut value_buffer)?;
let bitmap = RoaringBitmap::from_iter(Some(document_id));
bitmap.serialize_into(&mut value_buffer)?;

6
milli/src/update/index_documents/extract/mod.rs
View File

@@ -25,8 +25,8 @@ use self::extract_word_docids::extract_word_docids;
use self::extract_word_pair_proximity_docids::extract_word_pair_proximity_docids;
use self::extract_word_position_docids::extract_word_position_docids;
use super::helpers::{
as_cloneable_grenad, keep_first_prefix_value_merge_roaring_bitmaps, merge_cbo_roaring_bitmaps,
merge_roaring_bitmaps, CursorClonableMmap, GrenadParameters, MergeFn, MergeableReader,
as_cloneable_grenad, merge_cbo_roaring_bitmaps, merge_roaring_bitmaps, CursorClonableMmap,
GrenadParameters, MergeFn, MergeableReader,
};
use super::{helpers, TypedChunk};
use crate::{FieldId, Result};
@@ -142,7 +142,7 @@ pub(crate) fn data_from_obkv_documents(
indexer,
lmdb_writer_sx.clone(),
extract_facet_string_docids,
keep_first_prefix_value_merge_roaring_bitmaps,
merge_roaring_bitmaps, // TODO: check (cbo?)
TypedChunk::FieldIdFacetStringDocids,
"field-id-facet-string-docids",
);

52
milli/src/update/index_documents/helpers/merge_functions.rs
View File

@@ -5,7 +5,7 @@ use std::result::Result as StdResult;
use roaring::RoaringBitmap;
use super::read_u32_ne_bytes;
use crate::heed_codec::facet::{decode_prefix_string, encode_prefix_string};
// use crate::heed_codec::facet::{decode_prefix_string, encode_prefix_string};
use crate::heed_codec::CboRoaringBitmapCodec;
use crate::Result;
@@ -49,32 +49,32 @@ pub fn merge_roaring_bitmaps<'a>(_key: &[u8], values: &[Cow<'a, [u8]>]) -> Resul
}
}
pub fn keep_first_prefix_value_merge_roaring_bitmaps<'a>(
_key: &[u8],
values: &[Cow<'a, [u8]>],
) -> Result<Cow<'a, [u8]>> {
if values.len() == 1 {
Ok(values[0].clone())
} else {
let original = decode_prefix_string(&values[0]).unwrap().0;
let merged_bitmaps = values
.iter()
.map(AsRef::as_ref)
.map(decode_prefix_string)
.map(Option::unwrap)
.map(|(_, bitmap_bytes)| bitmap_bytes)
.map(RoaringBitmap::deserialize_from)
.map(StdResult::unwrap)
.reduce(|a, b| a | b)
.unwrap();
// pub fn keep_first_prefix_value_merge_roaring_bitmaps<'a>(
// _key: &[u8],
// values: &[Cow<'a, [u8]>],
// ) -> Result<Cow<'a, [u8]>> {
// if values.len() == 1 {
// Ok(values[0].clone())
// } else {
// let original = decode_prefix_string(&values[0]).unwrap().0;
// let merged_bitmaps = values
// .iter()
// .map(AsRef::as_ref)
// .map(decode_prefix_string)
// .map(Option::unwrap)
// .map(|(_, bitmap_bytes)| bitmap_bytes)
// .map(RoaringBitmap::deserialize_from)
// .map(StdResult::unwrap)
// .reduce(|a, b| a | b)
// .unwrap();
let cap = std::mem::size_of::<u16>() + original.len() + merged_bitmaps.serialized_size();
let mut buffer = Vec::with_capacity(cap);
encode_prefix_string(original, &mut buffer)?;
merged_bitmaps.serialize_into(&mut buffer)?;
Ok(Cow::Owned(buffer))
}
}
// let cap = std::mem::size_of::<u16>() + original.len() + merged_bitmaps.serialized_size();
// let mut buffer = Vec::with_capacity(cap);
// encode_prefix_string(original, &mut buffer)?;
// merged_bitmaps.serialize_into(&mut buffer)?;
// Ok(Cow::Owned(buffer))
// }
// }
pub fn keep_first<'a>(_key: &[u8], values: &[Cow<'a, [u8]>]) -> Result<Cow<'a, [u8]>> {
Ok(values[0].clone())

6
milli/src/update/index_documents/helpers/mod.rs
View File

@@ -13,9 +13,9 @@ pub use grenad_helpers::{
writer_into_reader, GrenadParameters, MergeableReader,
};
pub use merge_functions::{
concat_u32s_array, keep_first, keep_first_prefix_value_merge_roaring_bitmaps, keep_latest_obkv,
merge_cbo_roaring_bitmaps, merge_obkvs, merge_roaring_bitmaps, merge_two_obkvs,
roaring_bitmap_from_u32s_array, serialize_roaring_bitmap, MergeFn,
concat_u32s_array, keep_first, keep_latest_obkv, merge_cbo_roaring_bitmaps, merge_obkvs,
merge_roaring_bitmaps, merge_two_obkvs, roaring_bitmap_from_u32s_array,
serialize_roaring_bitmap, MergeFn,
};
/// The maximum length a word can be

16
milli/src/update/index_documents/typed_chunk.rs
View File

@@ -13,7 +13,6 @@ use super::helpers::{
valid_lmdb_key, CursorClonableMmap,
};
use super::{ClonableMmap, MergeFn};
use crate::heed_codec::facet::{decode_prefix_string, encode_prefix_string};
use crate::update::index_documents::helpers::as_cloneable_grenad;
use crate::{
lat_lng_to_xyz, BoRoaringBitmapCodec, CboRoaringBitmapCodec, DocumentId, GeoPoint, Index,
@@ -197,13 +196,14 @@ pub(crate) fn write_typed_chunk_into_index(
index_is_empty,
|value, _buffer| Ok(value),
|new_values, db_values, buffer| {
let (_, new_values) = decode_prefix_string(new_values).unwrap();
let new_values = RoaringBitmap::deserialize_from(new_values)?;
let (db_original, db_values) = decode_prefix_string(db_values).unwrap();
let db_values = RoaringBitmap::deserialize_from(db_values)?;
let values = new_values | db_values;
encode_prefix_string(db_original, buffer)?;
Ok(values.serialize_into(buffer)?)
todo!()
// let (_, new_values) = decode_prefix_string(new_values).unwrap();
// let new_values = RoaringBitmap::deserialize_from(new_values)?;
// let (db_original, db_values) = decode_prefix_string(db_values).unwrap();
// let db_values = RoaringBitmap::deserialize_from(db_values)?;
// let values = new_values | db_values;
// encode_prefix_string(db_original, buffer)?;
// Ok(values.serialize_into(buffer)?)
},
)?;
is_merged_database = true;