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

Fixing piles of clippy errors.

Browse Source 
Most of these are calling clone when the struct supports Copy.

Many are using & and &mut on `self` when the function they are called
from already has an immutable or mutable borrow so this isn't needed.

I tried to stay away from actual changes or places where I'd have to
name fresh variables.
This commit is contained in:
Ewan Higgs
2022-10-13 22:02:54 +02:00
parent 95e45e1c2c
commit beb987d3d1
18 changed files with 137 additions and 157 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
milli/src/update/index_documents/extract/extract_fid_word_count_docids.rs
View File

@@ -40,7 +40,7 @@ pub fn extract_fid_word_count_docids<R: io::Read + io::Seek>(
let mut cursor = docid_word_positions.into_cursor()?;
while let Some((key, value)) = cursor.move_on_next()? {
let (document_id_bytes, _word_bytes) = try_split_array_at(key)
.ok_or_else(|| SerializationError::Decoding { db_name: Some(DOCID_WORD_POSITIONS) })?;
.ok_or(SerializationError::Decoding { db_name: Some(DOCID_WORD_POSITIONS) })?;
let document_id = u32::from_be_bytes(document_id_bytes);
let curr_document_id = *current_document_id.get_or_insert(document_id);

2
milli/src/update/index_documents/extract/extract_geo_points.rs
View File

@@ -60,5 +60,5 @@ pub fn extract_geo_points<R: io::Read + io::Seek>(
}
}
Ok(writer_into_reader(writer)?)
writer_into_reader(writer)
}

2
milli/src/update/index_documents/extract/extract_word_docids.rs
View File

@@ -51,7 +51,7 @@ pub fn extract_word_docids<R: io::Read + io::Seek>(
let mut cursor = docid_word_positions.into_cursor()?;
while let Some((key, positions)) = cursor.move_on_next()? {
let (document_id_bytes, word_bytes) = try_split_array_at(key)
.ok_or_else(|| SerializationError::Decoding { db_name: Some(DOCID_WORD_POSITIONS) })?;
.ok_or(SerializationError::Decoding { db_name: Some(DOCID_WORD_POSITIONS) })?;
let document_id = u32::from_be_bytes(document_id_bytes);
let bitmap = RoaringBitmap::from_iter(Some(document_id));

4
milli/src/update/index_documents/extract/extract_word_pair_proximity_docids.rs
View File

@@ -39,7 +39,7 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
let mut cursor = docid_word_positions.into_cursor()?;
while let Some((key, value)) = cursor.move_on_next()? {
let (document_id_bytes, word_bytes) = try_split_array_at(key)
.ok_or_else(|| SerializationError::Decoding { db_name: Some(DOCID_WORD_POSITIONS) })?;
.ok_or(SerializationError::Decoding { db_name: Some(DOCID_WORD_POSITIONS) })?;
let document_id = u32::from_be_bytes(document_id_bytes);
let word = str::from_utf8(word_bytes)?;
@@ -81,7 +81,7 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
///
/// This list is used by the engine to calculate the documents containing words that are
/// close to each other.
fn document_word_positions_into_sorter<'b>(
fn document_word_positions_into_sorter(
document_id: DocumentId,
mut word_positions_heap: BinaryHeap<PeekedWordPosition<vec::IntoIter<u32>>>,
word_pair_proximity_docids_sorter: &mut grenad::Sorter<MergeFn>,

2
milli/src/update/index_documents/extract/extract_word_position_docids.rs
View File

@@ -33,7 +33,7 @@ pub fn extract_word_position_docids<R: io::Read + io::Seek>(
let mut cursor = docid_word_positions.into_cursor()?;
while let Some((key, value)) = cursor.move_on_next()? {
let (document_id_bytes, word_bytes) = try_split_array_at(key)
.ok_or_else(|| SerializationError::Decoding { db_name: Some(DOCID_WORD_POSITIONS) })?;
.ok_or(SerializationError::Decoding { db_name: Some(DOCID_WORD_POSITIONS) })?;
let document_id = DocumentId::from_be_bytes(document_id_bytes);
for position in read_u32_ne_bytes(value) {

26
milli/src/update/index_documents/extract/mod.rs
View File

@@ -96,7 +96,7 @@ pub(crate) fn data_from_obkv_documents(
spawn_extraction_task::<_, _, Vec<grenad::Reader<File>>>(
docid_word_positions_chunks.clone(),
indexer.clone(),
indexer,
lmdb_writer_sx.clone(),
extract_word_pair_proximity_docids,
merge_cbo_roaring_bitmaps,
@@ -106,7 +106,7 @@ pub(crate) fn data_from_obkv_documents(
spawn_extraction_task::<_, _, Vec<grenad::Reader<File>>>(
docid_word_positions_chunks.clone(),
indexer.clone(),
indexer,
lmdb_writer_sx.clone(),
extract_fid_word_count_docids,
merge_cbo_roaring_bitmaps,
@@ -116,7 +116,7 @@ pub(crate) fn data_from_obkv_documents(
spawn_extraction_task::<_, _, Vec<(grenad::Reader<File>, grenad::Reader<File>)>>(
docid_word_positions_chunks.clone(),
indexer.clone(),
indexer,
lmdb_writer_sx.clone(),
move |doc_word_pos, indexer| extract_word_docids(doc_word_pos, indexer, &exact_attributes),
merge_roaring_bitmaps,
@@ -128,8 +128,8 @@ pub(crate) fn data_from_obkv_documents(
);
spawn_extraction_task::<_, _, Vec<grenad::Reader<File>>>(
docid_word_positions_chunks.clone(),
indexer.clone(),
docid_word_positions_chunks,
indexer,
lmdb_writer_sx.clone(),
extract_word_position_docids,
merge_cbo_roaring_bitmaps,
@@ -138,8 +138,8 @@ pub(crate) fn data_from_obkv_documents(
);
spawn_extraction_task::<_, _, Vec<grenad::Reader<File>>>(
docid_fid_facet_strings_chunks.clone(),
indexer.clone(),
docid_fid_facet_strings_chunks,
indexer,
lmdb_writer_sx.clone(),
extract_facet_string_docids,
keep_first_prefix_value_merge_roaring_bitmaps,
@@ -148,8 +148,8 @@ pub(crate) fn data_from_obkv_documents(
);
spawn_extraction_task::<_, _, Vec<grenad::Reader<File>>>(
docid_fid_facet_numbers_chunks.clone(),
indexer.clone(),
docid_fid_facet_numbers_chunks,
indexer,
lmdb_writer_sx.clone(),
extract_facet_number_docids,
merge_cbo_roaring_bitmaps,
@@ -183,12 +183,12 @@ fn spawn_extraction_task<FE, FS, M>(
{
rayon::spawn(move || {
let chunks: Result<M> =
chunks.into_par_iter().map(|chunk| extract_fn(chunk, indexer.clone())).collect();
chunks.into_par_iter().map(|chunk| extract_fn(chunk, indexer)).collect();
rayon::spawn(move || match chunks {
Ok(chunks) => {
debug!("merge {} database", name);
let reader = chunks.merge(merge_fn, &indexer);
let _ = lmdb_writer_sx.send(reader.map(|r| serialize_fn(r)));
let _ = lmdb_writer_sx.send(reader.map(serialize_fn));
}
Err(e) => {
let _ = lmdb_writer_sx.send(Err(e));
@@ -255,7 +255,7 @@ fn send_and_extract_flattened_documents_data(
|| {
let (documents_ids, docid_word_positions_chunk) = extract_docid_word_positions(
flattened_documents_chunk.clone(),
indexer.clone(),
indexer,
searchable_fields,
stop_words.as_ref(),
max_positions_per_attributes,
@@ -279,7 +279,7 @@ fn send_and_extract_flattened_documents_data(
fid_facet_exists_docids_chunk,
) = extract_fid_docid_facet_values(
flattened_documents_chunk.clone(),
indexer.clone(),
indexer,
faceted_fields,
)?;

11
milli/src/update/index_documents/helpers/grenad_helpers.rs
View File

@@ -61,7 +61,7 @@ pub fn sorter_into_reader(
);
sorter.write_into_stream_writer(&mut writer)?;
Ok(writer_into_reader(writer)?)
writer_into_reader(writer)
}
pub fn writer_into_reader(writer: grenad::Writer<File>) -> Result<grenad::Reader<File>> {
@@ -134,7 +134,7 @@ impl<R: io::Read + io::Seek> MergerBuilder<R> {
);
merger.write_into_stream_writer(&mut writer)?;
Ok(writer_into_reader(writer)?)
writer_into_reader(writer)
}
}
@@ -180,7 +180,6 @@ pub fn grenad_obkv_into_chunks<R: io::Read + io::Seek>(
let mut continue_reading = true;
let mut cursor = reader.into_cursor()?;
let indexer_clone = indexer.clone();
let mut transposer = move || {
if !continue_reading {
return Ok(None);
@@ -188,8 +187,8 @@ pub fn grenad_obkv_into_chunks<R: io::Read + io::Seek>(
let mut current_chunk_size = 0u64;
let mut obkv_documents = create_writer(
indexer_clone.chunk_compression_type,
indexer_clone.chunk_compression_level,
indexer.chunk_compression_type,
indexer.chunk_compression_level,
tempfile::tempfile()?,
);
@@ -224,7 +223,7 @@ pub fn write_into_lmdb_database(
match iter.next().transpose()? {
Some((key, old_val)) if key == k => {
let vals = &[Cow::Borrowed(old_val), Cow::Borrowed(v)][..];
let val = merge(k, &vals)?;
let val = merge(k, vals)?;
// safety: we don't keep references from inside the LMDB database.
unsafe { iter.put_current(k, &val)? };
}

2
milli/src/update/index_documents/helpers/merge_functions.rs
View File

@@ -88,7 +88,7 @@ pub fn keep_latest_obkv<'a>(_key: &[u8], obkvs: &[Cow<'a, [u8]>]) -> Result<Cow<
/// Merge all the obks in the order we see them.
pub fn merge_obkvs<'a>(_key: &[u8], obkvs: &[Cow<'a, [u8]>]) -> Result<Cow<'a, [u8]>> {
Ok(obkvs
.into_iter()
.iter()
.cloned()
.reduce(|acc, current| {
let first = obkv::KvReader::new(&acc);

41
milli/src/update/index_documents/mod.rs
View File

@@ -106,7 +106,7 @@ where
) -> Result<IndexDocuments<'t, 'u, 'i, 'a, F>> {
let transform = Some(Transform::new(
wtxn,
&index,
index,
indexer_config,
config.update_method,
config.autogenerate_docids,
@@ -291,18 +291,12 @@ where
// Run extraction pipeline in parallel.
pool.install(|| {
// split obkv file into several chunks
let original_chunk_iter = grenad_obkv_into_chunks(
original_documents,
pool_params.clone(),
documents_chunk_size,
);
let original_chunk_iter =
grenad_obkv_into_chunks(original_documents, pool_params, documents_chunk_size);
// split obkv file into several chunks
let flattened_chunk_iter = grenad_obkv_into_chunks(
flattened_documents,
pool_params.clone(),
documents_chunk_size,
);
let flattened_chunk_iter =
grenad_obkv_into_chunks(flattened_documents, pool_params, documents_chunk_size);
let result = original_chunk_iter.and_then(|original_chunk| {
let flattened_chunk = flattened_chunk_iter?;
@@ -341,7 +335,7 @@ where
}
let index_documents_ids = self.index.documents_ids(self.wtxn)?;
let index_is_empty = index_documents_ids.len() == 0;
let index_is_empty = index_documents_ids.is_empty();
let mut final_documents_ids = RoaringBitmap::new();
let mut word_pair_proximity_docids = None;
let mut word_position_docids = None;
@@ -378,7 +372,7 @@ where
};
let (docids, is_merged_database) =
write_typed_chunk_into_index(typed_chunk, &self.index, self.wtxn, index_is_empty)?;
write_typed_chunk_into_index(typed_chunk, self.index, self.wtxn, index_is_empty)?;
if !docids.is_empty() {
final_documents_ids |= docids;
let documents_seen_count = final_documents_ids.len();
@@ -475,7 +469,7 @@ where
);
let common_prefix_fst_words: Vec<_> = common_prefix_fst_words
.as_slice()
.linear_group_by_key(|x| x.chars().nth(0).unwrap())
.linear_group_by_key(|x| x.chars().next().unwrap())
.collect();
// We retrieve the newly added words between the previous and new prefix word fst.
@@ -498,9 +492,9 @@ where
execute_word_prefix_docids(
self.wtxn,
word_docids,
self.index.word_docids.clone(),
self.index.word_prefix_docids.clone(),
&self.indexer_config,
self.index.word_docids,
self.index.word_prefix_docids,
self.indexer_config,
&new_prefix_fst_words,
&common_prefix_fst_words,
&del_prefix_fst_words,
@@ -511,9 +505,9 @@ where
execute_word_prefix_docids(
self.wtxn,
exact_word_docids,
self.index.exact_word_docids.clone(),
self.index.exact_word_prefix_docids.clone(),
&self.indexer_config,
self.index.exact_word_docids,
self.index.exact_word_prefix_docids,
self.indexer_config,
&new_prefix_fst_words,
&common_prefix_fst_words,
&del_prefix_fst_words,
@@ -595,12 +589,7 @@ fn execute_word_prefix_docids(
builder.chunk_compression_level = indexer_config.chunk_compression_level;
builder.max_nb_chunks = indexer_config.max_nb_chunks;
builder.max_memory = indexer_config.max_memory;
builder.execute(
cursor,
&new_prefix_fst_words,
&common_prefix_fst_words,
&del_prefix_fst_words,
)?;
builder.execute(cursor, new_prefix_fst_words, common_prefix_fst_words, del_prefix_fst_words)?;
Ok(())
}

49
milli/src/update/index_documents/transform.rs
View File

@@ -72,10 +72,10 @@ fn create_fields_mapping(
// we sort by id here to ensure a deterministic mapping of the fields, that preserves
// the original ordering.
.sorted_by_key(|(&id, _)| id)
.map(|(field, name)| match index_field_map.id(&name) {
.map(|(field, name)| match index_field_map.id(name) {
Some(id) => Ok((*field, id)),
None => index_field_map
.insert(&name)
.insert(name)
.ok_or(Error::UserError(UserError::AttributeLimitReached))
.map(|id| (*field, id)),
})
@@ -192,7 +192,7 @@ impl<'a, 'i> Transform<'a, 'i> {
// Insertion in a obkv need to be done with keys ordered. For now they are ordered
// according to the document addition key order, so we sort it according to the
// fieldids map keys order.
field_buffer_cache.sort_unstable_by(|(f1, _), (f2, _)| f1.cmp(&f2));
field_buffer_cache.sort_unstable_by(|(f1, _), (f2, _)| f1.cmp(f2));
// Build the new obkv document.
let mut writer = obkv::KvWriter::new(&mut obkv_buffer);
@@ -202,24 +202,23 @@ impl<'a, 'i> Transform<'a, 'i> {
let mut original_docid = None;
let docid =
match self.new_external_documents_ids_builder.entry(external_id.clone().into()) {
Entry::Occupied(entry) => *entry.get() as u32,
Entry::Vacant(entry) => {
// If the document was already in the db we mark it as a replaced document.
// It'll be deleted later. We keep its original docid to insert it in the grenad.
if let Some(docid) = external_documents_ids.get(entry.key()) {
self.replaced_documents_ids.insert(docid);
original_docid = Some(docid);
}
let docid = self
.available_documents_ids
.next()
.ok_or(UserError::DocumentLimitReached)?;
entry.insert(docid as u64);
docid
let docid = match self.new_external_documents_ids_builder.entry((*external_id).into()) {
Entry::Occupied(entry) => *entry.get() as u32,
Entry::Vacant(entry) => {
// If the document was already in the db we mark it as a replaced document.
// It'll be deleted later. We keep its original docid to insert it in the grenad.
if let Some(docid) = external_documents_ids.get(entry.key()) {
self.replaced_documents_ids.insert(docid);
original_docid = Some(docid);
}
};
let docid = self
.available_documents_ids
.next()
.ok_or(UserError::DocumentLimitReached)?;
entry.insert(docid as u64);
docid
}
};
let mut skip_insertion = false;
if let Some(original_docid) = original_docid {
@@ -239,12 +238,12 @@ impl<'a, 'i> Transform<'a, 'i> {
// we're not replacing anything
self.replaced_documents_ids.remove(original_docid);
// and we need to put back the original id as it was before
self.new_external_documents_ids_builder.remove(&*external_id);
self.new_external_documents_ids_builder.remove(external_id);
skip_insertion = true;
} else {
// we associate the base document with the new key, everything will get merged later.
self.original_sorter.insert(&docid.to_be_bytes(), base_obkv)?;
match self.flatten_from_fields_ids_map(KvReader::new(&base_obkv))? {
match self.flatten_from_fields_ids_map(KvReader::new(base_obkv))? {
Some(buffer) => {
self.flattened_sorter.insert(docid.to_be_bytes(), &buffer)?
}
@@ -453,7 +452,7 @@ impl<'a, 'i> Transform<'a, 'i> {
{
let primary_key = self
.index
.primary_key(&wtxn)?
.primary_key(wtxn)?
.ok_or(Error::UserError(UserError::MissingPrimaryKey))?
.to_string();
@@ -520,7 +519,7 @@ impl<'a, 'i> Transform<'a, 'i> {
self.new_external_documents_ids_builder.into_iter().collect();
new_external_documents_ids_builder
.sort_unstable_by(|(left, _), (right, _)| left.cmp(&right));
.sort_unstable_by(|(left, _), (right, _)| left.cmp(right));
let mut fst_new_external_documents_ids_builder = fst::MapBuilder::memory();
new_external_documents_ids_builder.into_iter().try_for_each(|(key, value)| {
fst_new_external_documents_ids_builder.insert(key, value)
@@ -614,7 +613,7 @@ impl<'a, 'i> Transform<'a, 'i> {
let mut flattened: Vec<_> = flattened.into_iter().collect();
// we reorder the field to get all the known field first
flattened.sort_unstable_by_key(|(key, _)| {
new_fields_ids_map.id(&key).unwrap_or(FieldId::MAX)
new_fields_ids_map.id(key).unwrap_or(FieldId::MAX)
});
for (key, value) in flattened {

4
milli/src/update/index_documents/typed_chunk.rs
View File

@@ -175,7 +175,7 @@ pub(crate) fn write_typed_chunk_into_index(
let mut cursor = fid_docid_facet_number.into_cursor()?;
while let Some((key, value)) = cursor.move_on_next()? {
if valid_lmdb_key(key) {
index_fid_docid_facet_numbers.put(wtxn, key, &value)?;
index_fid_docid_facet_numbers.put(wtxn, key, value)?;
}
}
}
@@ -185,7 +185,7 @@ pub(crate) fn write_typed_chunk_into_index(
let mut cursor = fid_docid_facet_string.into_cursor()?;
while let Some((key, value)) = cursor.move_on_next()? {
if valid_lmdb_key(key) {
index_fid_docid_facet_strings.put(wtxn, key, &value)?;
index_fid_docid_facet_strings.put(wtxn, key, value)?;
}
}
}

61
milli/src/update/settings.rs
View File

@@ -15,7 +15,7 @@ use crate::update::index_documents::IndexDocumentsMethod;
use crate::update::{ClearDocuments, IndexDocuments, UpdateIndexingStep};
use crate::{FieldsIdsMap, Index, Result};
#[derive(Debug, Clone, PartialEq, Copy)]
#[derive(Debug, Clone, PartialEq, Eq, Copy)]
pub enum Setting<T> {
Set(T),
Reset,
@@ -273,24 +273,21 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
let fields_ids_map = self.index.fields_ids_map(self.wtxn)?;
// if the settings are set before any document update, we don't need to do anything, and
// will set the primary key during the first document addition.
if self.index.number_of_documents(&self.wtxn)? == 0 {
if self.index.number_of_documents(self.wtxn)? == 0 {
return Ok(());
}
let transform = Transform::new(
self.wtxn,
&self.index,
&self.indexer_config,
self.index,
self.indexer_config,
IndexDocumentsMethod::ReplaceDocuments,
false,
)?;
// We remap the documents fields based on the new `FieldsIdsMap`.
let output = transform.remap_index_documents(
self.wtxn,
old_fields_ids_map,
fields_ids_map.clone(),
)?;
let output =
transform.remap_index_documents(self.wtxn, old_fields_ids_map, fields_ids_map)?;
let new_facets = output.compute_real_facets(self.wtxn, self.index)?;
self.index.put_faceted_fields(self.wtxn, &new_facets)?;
@@ -303,7 +300,7 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
let indexing_builder = IndexDocuments::new(
self.wtxn,
self.index,
&self.indexer_config,
self.indexer_config,
IndexDocumentsConfig::default(),
&cb,
)?;
@@ -330,7 +327,7 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
fn update_distinct_field(&mut self) -> Result<bool> {
match self.distinct_field {
Setting::Set(ref attr) => {
self.index.put_distinct_field(self.wtxn, &attr)?;
self.index.put_distinct_field(self.wtxn, attr)?;
}
Setting::Reset => {
self.index.delete_distinct_field(self.wtxn)?;
@@ -356,11 +353,11 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
// Add all the searchable attributes to the field map, and then add the
// remaining fields from the old field map to the new one
for name in names.iter() {
new_fields_ids_map.insert(&name).ok_or(UserError::AttributeLimitReached)?;
new_fields_ids_map.insert(name).ok_or(UserError::AttributeLimitReached)?;
}
for (_, name) in old_fields_ids_map.iter() {
new_fields_ids_map.insert(&name).ok_or(UserError::AttributeLimitReached)?;
new_fields_ids_map.insert(name).ok_or(UserError::AttributeLimitReached)?;
}
self.index.put_all_searchable_fields_from_fields_ids_map(
@@ -462,11 +459,11 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
match self.exact_attributes {
Setting::Set(ref attrs) => {
let attrs = attrs.iter().map(String::as_str).collect::<Vec<_>>();
self.index.put_exact_attributes(&mut self.wtxn, &attrs)?;
self.index.put_exact_attributes(self.wtxn, &attrs)?;
Ok(true)
}
Setting::Reset => {
self.index.delete_exact_attributes(&mut self.wtxn)?;
self.index.delete_exact_attributes(self.wtxn)?;
Ok(true)
}
Setting::NotSet => Ok(false),
@@ -528,7 +525,7 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
fn update_primary_key(&mut self) -> Result<()> {
match self.primary_key {
Setting::Set(ref primary_key) => {
if self.index.number_of_documents(&self.wtxn)? == 0 {
if self.index.number_of_documents(self.wtxn)? == 0 {
let mut fields_ids_map = self.index.fields_ids_map(self.wtxn)?;
fields_ids_map.insert(primary_key).ok_or(UserError::AttributeLimitReached)?;
self.index.put_fields_ids_map(self.wtxn, &fields_ids_map)?;
@@ -540,7 +537,7 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
}
}
Setting::Reset => {
if self.index.number_of_documents(&self.wtxn)? == 0 {
if self.index.number_of_documents(self.wtxn)? == 0 {
self.index.delete_primary_key(self.wtxn)?;
Ok(())
} else {
@@ -574,24 +571,24 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
if one > two {
return Err(UserError::InvalidMinTypoWordLenSetting(one, two).into());
} else {
self.index.put_min_word_len_one_typo(&mut self.wtxn, one)?;
self.index.put_min_word_len_two_typos(&mut self.wtxn, two)?;
self.index.put_min_word_len_one_typo(self.wtxn, one)?;
self.index.put_min_word_len_two_typos(self.wtxn, two)?;
}
}
(Setting::Set(one), _) => {
let two = self.index.min_word_len_two_typos(&self.wtxn)?;
let two = self.index.min_word_len_two_typos(self.wtxn)?;
if one > two {
return Err(UserError::InvalidMinTypoWordLenSetting(one, two).into());
} else {
self.index.put_min_word_len_one_typo(&mut self.wtxn, one)?;
self.index.put_min_word_len_one_typo(self.wtxn, one)?;
}
}
(_, Setting::Set(two)) => {
let one = self.index.min_word_len_one_typo(&self.wtxn)?;
let one = self.index.min_word_len_one_typo(self.wtxn)?;
if one > two {
return Err(UserError::InvalidMinTypoWordLenSetting(one, two).into());
} else {
self.index.put_min_word_len_two_typos(&mut self.wtxn, two)?;
self.index.put_min_word_len_two_typos(self.wtxn, two)?;
}
}
_ => (),
@@ -621,10 +618,10 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
words.sort_unstable();
let words = fst::Set::from_iter(words.iter())?;
self.index.put_exact_words(&mut self.wtxn, &words)?;
self.index.put_exact_words(self.wtxn, &words)?;
}
Setting::Reset => {
self.index.put_exact_words(&mut self.wtxn, &fst::Set::default())?;
self.index.put_exact_words(self.wtxn, &fst::Set::default())?;
}
Setting::NotSet => (),
}
@@ -635,10 +632,10 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
fn update_max_values_per_facet(&mut self) -> Result<()> {
match self.max_values_per_facet {
Setting::Set(max) => {
self.index.put_max_values_per_facet(&mut self.wtxn, max)?;
self.index.put_max_values_per_facet(self.wtxn, max)?;
}
Setting::Reset => {
self.index.delete_max_values_per_facet(&mut self.wtxn)?;
self.index.delete_max_values_per_facet(self.wtxn)?;
}
Setting::NotSet => (),
}
@@ -649,10 +646,10 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
fn update_pagination_max_total_hits(&mut self) -> Result<()> {
match self.pagination_max_total_hits {
Setting::Set(max) => {
self.index.put_pagination_max_total_hits(&mut self.wtxn, max)?;
self.index.put_pagination_max_total_hits(self.wtxn, max)?;
}
Setting::Reset => {
self.index.delete_pagination_max_total_hits(&mut self.wtxn)?;
self.index.delete_pagination_max_total_hits(self.wtxn)?;
}
Setting::NotSet => (),
}
@@ -666,8 +663,8 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
{
self.index.set_updated_at(self.wtxn, &OffsetDateTime::now_utc())?;
let old_faceted_fields = self.index.user_defined_faceted_fields(&self.wtxn)?;
let old_fields_ids_map = self.index.fields_ids_map(&self.wtxn)?;
let old_faceted_fields = self.index.user_defined_faceted_fields(self.wtxn)?;
let old_fields_ids_map = self.index.fields_ids_map(self.wtxn)?;
self.update_displayed()?;
self.update_filterable()?;
@@ -684,7 +681,7 @@ impl<'a, 't, 'u, 'i> Settings<'a, 't, 'u, 'i> {
// If there is new faceted fields we indicate that we must reindex as we must
// index new fields as facets. It means that the distinct attribute,
// an Asc/Desc criterion or a filtered attribute as be added or removed.
let new_faceted_fields = self.index.user_defined_faceted_fields(&self.wtxn)?;
let new_faceted_fields = self.index.user_defined_faceted_fields(self.wtxn)?;
let faceted_updated = old_faceted_fields != new_faceted_fields;
let stop_words_updated = self.update_stop_words()?;

4
milli/src/update/word_prefix_docids.rs
View File

@@ -61,12 +61,12 @@ impl<'t, 'u, 'i> WordPrefixDocids<'t, 'u, 'i> {
let mut prefixes_cache = HashMap::new();
while let Some((word, data)) = new_word_docids_iter.move_on_next()? {
current_prefixes = match current_prefixes.take() {
Some(prefixes) if word.starts_with(&prefixes[0].as_bytes()) => Some(prefixes),
Some(prefixes) if word.starts_with(prefixes[0].as_bytes()) => Some(prefixes),
_otherwise => {
write_prefixes_in_sorter(&mut prefixes_cache, &mut prefix_docids_sorter)?;
common_prefix_fst_words
.iter()
.find(|prefixes| word.starts_with(&prefixes[0].as_bytes()))
.find(|prefixes| word.starts_with(prefixes[0].as_bytes()))
}
};

17
milli/src/update/word_prefix_pair_proximity_docids.rs
View File

@@ -257,7 +257,7 @@ impl<'t, 'u, 'i> WordPrefixPairProximityDocids<'t, 'u, 'i> {
#[logging_timer::time("WordPrefixPairProximityDocids::{}")]
pub fn execute<'a>(
mut self,
self,
new_word_pair_proximity_docids: grenad::Reader<CursorClonableMmap>,
new_prefix_fst_words: &'a [String],
common_prefix_fst_words: &[&'a [String]],
@@ -268,9 +268,8 @@ impl<'t, 'u, 'i> WordPrefixPairProximityDocids<'t, 'u, 'i> {
// Make a prefix trie from the common prefixes that are shorter than self.max_prefix_length
let prefixes = PrefixTrieNode::from_sorted_prefixes(
common_prefix_fst_words
.into_iter()
.map(|s| s.into_iter())
.flatten()
.iter()
.flat_map(|s| s.iter())
.map(|s| s.as_str())
.filter(|s| s.len() <= self.max_prefix_length),
);
@@ -298,7 +297,7 @@ impl<'t, 'u, 'i> WordPrefixPairProximityDocids<'t, 'u, 'i> {
// and this argument tells what to do with each new key (word1, prefix, proximity) and value (roaring bitmap)
|key, value| {
insert_into_database(
&mut self.wtxn,
self.wtxn,
*self.index.word_prefix_pair_proximity_docids.as_polymorph(),
key,
value,
@@ -311,7 +310,7 @@ impl<'t, 'u, 'i> WordPrefixPairProximityDocids<'t, 'u, 'i> {
let prefixes = PrefixTrieNode::from_sorted_prefixes(
new_prefix_fst_words
.into_iter()
.iter()
.map(|s| s.as_str())
.filter(|s| s.len() <= self.max_prefix_length),
);
@@ -445,7 +444,7 @@ fn execute_on_word_pairs_and_prefixes<I>(
let prefix_len = prefix_buffer.len();
prefix_buffer.push(0);
prefix_buffer.push(proximity);
batch.insert(&prefix_buffer, data.to_vec());
batch.insert(prefix_buffer, data.to_vec());
prefix_buffer.truncate(prefix_len);
},
);
@@ -620,7 +619,7 @@ impl PrefixTrieNode {
fn set_search_start(&self, word: &[u8], search_start: &mut PrefixTrieNodeSearchStart) -> bool {
let byte = word[0];
if self.children[search_start.0].1 == byte {
return true;
true
} else {
match self.children[search_start.0..].binary_search_by_key(&byte, |x| x.1) {
Ok(position) => {
@@ -638,7 +637,7 @@ impl PrefixTrieNode {
fn from_sorted_prefixes<'a>(prefixes: impl Iterator<Item = &'a str>) -> Self {
let mut node = PrefixTrieNode::default();
for prefix in prefixes {
node.insert_sorted_prefix(prefix.as_bytes().into_iter());
node.insert_sorted_prefix(prefix.as_bytes().iter());
}
node
}

2
milli/src/update/words_prefixes_fst.rs
View File

@@ -42,7 +42,7 @@ impl<'t, 'u, 'i> WordsPrefixesFst<'t, 'u, 'i> {
#[logging_timer::time("WordsPrefixesFst::{}")]
pub fn execute(self) -> Result<()> {
let words_fst = self.index.words_fst(&self.wtxn)?;
let words_fst = self.index.words_fst(self.wtxn)?;
let mut current_prefix = vec![SmallString32::new(); self.max_prefix_length];
let mut current_prefix_count = vec![0; self.max_prefix_length];