snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2025-09-14 00:36:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

Fix clippy issues

Browse Source
This commit is contained in:
Louis Dureuil
2023-11-06 11:19:31 +01:00
parent 1bccf2079e
commit cbaa54cafd
11 changed files with 25 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
milli/src/update/index_documents/extract/extract_docid_word_positions.rs
View File

@ -198,7 +198,7 @@ fn tokenizer_builder<'a>(
}
if let Some(script_language) = script_language {
tokenizer_builder.allow_list(&script_language);
tokenizer_builder.allow_list(script_language);
}
tokenizer_builder
@ -206,6 +206,7 @@ fn tokenizer_builder<'a>(
/// Extract words maped with their positions of a document,
/// ensuring no Language detection mistakes was made.
#[allow(clippy::too_many_arguments)] // FIXME: consider grouping arguments in a struct
fn lang_safe_tokens_from_document<'a>(
obkv: &KvReader<FieldId>,
searchable_fields: &Option<HashSet<FieldId>>,
@ -220,9 +221,9 @@ fn lang_safe_tokens_from_document<'a>(
let mut script_language_word_count = HashMap::new();
tokens_from_document(
&obkv,
obkv,
searchable_fields,
&tokenizer,
tokenizer,
max_positions_per_attributes,
del_add,
buffers,
@ -257,7 +258,7 @@ fn lang_safe_tokens_from_document<'a>(
// rerun the extraction.
tokens_from_document(
&obkv,
obkv,
searchable_fields,
&tokenizer,
max_positions_per_attributes,

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

@ -45,7 +45,7 @@ pub fn extract_fid_word_count_docids<R: io::Read + io::Seek>(
.ok_or(SerializationError::Decoding { db_name: Some(DOCID_WORD_POSITIONS) })?;
let document_id = u32::from_be_bytes(document_id_bytes);
let del_add_reader = KvReaderDelAdd::new(&value);
let del_add_reader = KvReaderDelAdd::new(value);
let deletion = del_add_reader
// get deleted words
.get(DelAdd::Deletion)

12
milli/src/update/index_documents/extract/extract_word_docids.rs
View File

@ -57,17 +57,17 @@ pub fn extract_word_docids<R: io::Read + io::Seek>(
let document_id = u32::from_be_bytes(document_id_bytes);
let fid = u16::from_be_bytes(fid_bytes);
let del_add_reader = KvReaderDelAdd::new(&value);
let del_add_reader = KvReaderDelAdd::new(value);
// extract all unique words to remove.
if let Some(deletion) = del_add_reader.get(DelAdd::Deletion) {
for (_pos, word) in KvReaderU16::new(&deletion).iter() {
for (_pos, word) in KvReaderU16::new(deletion).iter() {
del_words.insert(word.to_vec());
}
}
// extract all unique additional words.
if let Some(addition) = del_add_reader.get(DelAdd::Addition) {
for (_pos, word) in KvReaderU16::new(&addition).iter() {
for (_pos, word) in KvReaderU16::new(addition).iter() {
add_words.insert(word.to_vec());
}
}
@ -122,9 +122,9 @@ pub fn extract_word_docids<R: io::Read + io::Seek>(
// every words contained in an attribute set to exact must be pushed in the exact_words list.
if exact_attributes.contains(&fid) {
exact_word_docids_sorter.insert(word.as_bytes(), &value)?;
exact_word_docids_sorter.insert(word.as_bytes(), value)?;
} else {
word_docids_sorter.insert(word.as_bytes(), &value)?;
word_docids_sorter.insert(word.as_bytes(), value)?;
}
}
@ -169,7 +169,7 @@ fn words_into_sorter(
};
key_buffer.clear();
key_buffer.extend_from_slice(&word_bytes);
key_buffer.extend_from_slice(word_bytes);
key_buffer.push(0);
key_buffer.extend_from_slice(&fid.to_be_bytes());
word_fid_docids_sorter.insert(&key_buffer, value_writer.into_inner().unwrap())?;

9
milli/src/update/index_documents/extract/extract_word_pair_proximity_docids.rs
View File

@ -29,7 +29,6 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
let max_memory = indexer.max_memory_by_thread();
let mut word_pair_proximity_docids_sorters: Vec<_> = (1..MAX_DISTANCE)
.into_iter()
.map(|_| {
create_sorter(
grenad::SortAlgorithm::Unstable,
@ -75,7 +74,7 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
let (del, add): (Result<_>, Result<_>) = rayon::join(
|| {
// deletions
if let Some(deletion) = KvReaderDelAdd::new(&value).get(DelAdd::Deletion) {
if let Some(deletion) = KvReaderDelAdd::new(value).get(DelAdd::Deletion) {
for (position, word) in KvReaderU16::new(deletion).iter() {
// drain the proximity window until the head word is considered close to the word we are inserting.
while del_word_positions.get(0).map_or(false, |(_w, p)| {
@ -104,7 +103,7 @@ pub fn extract_word_pair_proximity_docids<R: io::Read + io::Seek>(
},
|| {
// additions
if let Some(addition) = KvReaderDelAdd::new(&value).get(DelAdd::Addition) {
if let Some(addition) = KvReaderDelAdd::new(value).get(DelAdd::Addition) {
for (position, word) in KvReaderU16::new(addition).iter() {
// drain the proximity window until the head word is considered close to the word we are inserting.
while add_word_positions.get(0).map_or(false, |(_w, p)| {
@ -170,7 +169,7 @@ fn document_word_positions_into_sorter(
document_id: DocumentId,
del_word_pair_proximity: &BTreeMap<(String, String), u8>,
add_word_pair_proximity: &BTreeMap<(String, String), u8>,
word_pair_proximity_docids_sorters: &mut Vec<grenad::Sorter<MergeFn>>,
word_pair_proximity_docids_sorters: &mut [grenad::Sorter<MergeFn>],
) -> Result<()> {
use itertools::merge_join_by;
use itertools::EitherOrBoth::{Both, Left, Right};
@ -201,7 +200,7 @@ fn document_word_positions_into_sorter(
};
key_buffer.clear();
key_buffer.push(*prox as u8);
key_buffer.push(*prox);
key_buffer.extend_from_slice(w1.as_bytes());
key_buffer.push(0);
key_buffer.extend_from_slice(w2.as_bytes());

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

@ -60,7 +60,7 @@ pub fn extract_word_position_docids<R: io::Read + io::Seek>(
current_document_id = Some(document_id);
let del_add_reader = KvReaderDelAdd::new(&value);
let del_add_reader = KvReaderDelAdd::new(value);
// extract all unique words to remove.
if let Some(deletion) = del_add_reader.get(DelAdd::Deletion) {
for (position, word_bytes) in KvReaderU16::new(deletion).iter() {