filipriec/komp_ac
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

rust fmt and server clippy changes

Browse Source
This commit is contained in:
Priec
2025-12-21 00:15:26 +01:00
parent a506cd8f08
commit e5ce96e210
5 changed files with 60 additions and 84 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
common/src/lib.rs
View File

@@ -37,7 +37,6 @@ pub mod proto {
pub mod table_validation {
include!("proto/komp_ac.table_validation.rs");
}
pub const FILE_DESCRIPTOR_SET: &[u8] =
include_bytes!("proto/descriptor.bin");
pub const FILE_DESCRIPTOR_SET: &[u8] = include_bytes!("proto/descriptor.bin");
}
}

33
common/src/search.rs
View File

@@ -48,30 +48,27 @@ pub fn register_slovak_tokenizers(index: &Index) -> tantivy::Result<()> {
let tokenizer_manager = index.tokenizers();
// TOKENIZER for `prefix_edge`: Edge N-gram (1-4 chars)
let edge_tokenizer =
TextAnalyzer::builder(NgramTokenizer::new(1, 4, true)?)
.filter(RemoveLongFilter::limit(40))
.filter(LowerCaser)
.filter(AsciiFoldingFilter)
.build();
let edge_tokenizer = TextAnalyzer::builder(NgramTokenizer::new(1, 4, true)?)
.filter(RemoveLongFilter::limit(40))
.filter(LowerCaser)
.filter(AsciiFoldingFilter)
.build();
tokenizer_manager.register("slovak_prefix_edge", edge_tokenizer);
// TOKENIZER for `prefix_full`: Simple word tokenizer
let full_tokenizer =
TextAnalyzer::builder(SimpleTokenizer::default())
.filter(RemoveLongFilter::limit(40))
.filter(LowerCaser)
.filter(AsciiFoldingFilter)
.build();
let full_tokenizer = TextAnalyzer::builder(SimpleTokenizer::default())
.filter(RemoveLongFilter::limit(40))
.filter(LowerCaser)
.filter(AsciiFoldingFilter)
.build();
tokenizer_manager.register("slovak_prefix_full", full_tokenizer);
// NGRAM TOKENIZER: For substring matching.
let ngram_tokenizer =
TextAnalyzer::builder(NgramTokenizer::new(3, 3, false)?)
.filter(RemoveLongFilter::limit(40))
.filter(LowerCaser)
.filter(AsciiFoldingFilter)
.build();
let ngram_tokenizer = TextAnalyzer::builder(NgramTokenizer::new(3, 3, false)?)
.filter(RemoveLongFilter::limit(40))
.filter(LowerCaser)
.filter(AsciiFoldingFilter)
.build();
tokenizer_manager.register("slovak_ngram", ngram_tokenizer);
Ok(())