searchengines-web/MeiliSearch
searchengines-web/MeiliSearch
1
0
Fork 0
mirror of https://github.com/meilisearch/MeiliSearch synced 2024-12-26 22:50:07 +01:00
Code Issues Releases Wiki Activity

Fix typos

Browse Source
This commit is contained in:
ManyTheFish 2023-03-09 10:56:17 +01:00
parent 7e2fd82e41
commit b4b859ec8c
3 changed files with 10 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
meilisearch/src/search.rs
View File

@ -375,15 +375,15 @@ pub fn perform_search(
&displayed_ids,
);
let mut tokenizer_buidler = TokenizerBuilder::default();
tokenizer_buidler.create_char_map(true);
let mut tokenizer_builder = TokenizerBuilder::default();
tokenizer_builder.create_char_map(true);
let script_lang_map = index.script_language(&rtxn)?;
if !script_lang_map.is_empty() {
tokenizer_buidler.allow_list(&script_lang_map);
tokenizer_builder.allow_list(&script_lang_map);
}
let mut formatter_builder = MatcherBuilder::new(matching_words, tokenizer_buidler.build());
let mut formatter_builder = MatcherBuilder::new(matching_words, tokenizer_builder.build());
formatter_builder.crop_marker(query.crop_marker);
formatter_builder.highlight_prefix(query.highlight_pre_tag);
formatter_builder.highlight_suffix(query.highlight_post_tag);

2
milli/src/index.rs
View File

@ -1224,7 +1224,7 @@ impl Index {
}
}
let threshold = total / 20; // 5% (arbitrar)
let threshold = total / 20; // 5% (arbitrary)
for (script, language, count) in script_language_doc_count {
if count > threshold {
if let Some(languages) = script_language.get_mut(&script) {

10
milli/src/update/index_documents/extract/extract_docid_word_positions.rs
View File

@ -89,7 +89,7 @@ pub fn extract_docid_word_positions<R: io::Read + io::Seek>(
// if the allow list is empty, meaning that no Language is considered frequent,
// then we don't rerun the extraction.
if !script_language.is_empty() {
// build a new temporar tokenizer including the allow list.
// build a new temporary tokenizer including the allow list.
let mut tokenizer_builder = TokenizerBuilder::new();
if let Some(stop_words) = stop_words {
tokenizer_builder.stop_words(stop_words);
@ -260,7 +260,7 @@ fn process_tokens<'a>(
fn potential_language_detection_error(languages_frequency: &Vec<(Language, usize)>) -> bool {
if languages_frequency.len() > 1 {
let threshold = compute_laguage_frequency_threshold(languages_frequency);
let threshold = compute_language_frequency_threshold(languages_frequency);
languages_frequency.iter().any(|(_, c)| *c <= threshold)
} else {
false
@ -271,7 +271,7 @@ fn most_frequent_languages(
(script, languages_frequency): (&Script, &Vec<(Language, usize)>),
) -> Option<(Script, Vec<Language>)> {
if languages_frequency.len() > 1 {
let threshold = compute_laguage_frequency_threshold(languages_frequency);
let threshold = compute_language_frequency_threshold(languages_frequency);
let languages: Vec<_> =
languages_frequency.iter().filter(|(_, c)| *c > threshold).map(|(l, _)| *l).collect();
@ -286,7 +286,7 @@ fn most_frequent_languages(
}
}
fn compute_laguage_frequency_threshold(languages_frequency: &[(Language, usize)]) -> usize {
fn compute_language_frequency_threshold(languages_frequency: &[(Language, usize)]) -> usize {
let total: usize = languages_frequency.iter().map(|(_, c)| c).sum();
total / 10 // 10% is a completely arbitrar value.
total / 10 // 10% is a completely arbitrary value.
}