snowykami/meilisearch
1
0
Fork 0
mirror of https://github.com/meilisearch/meilisearch.git synced 2024-11-26 12:05:05 +08:00
Code Issues Actions 5 Packages Projects Releases Wiki Activity

Merge pull request #199 from meilisearch/fix-soft-hard-separator

Browse Source 
Do not consider underscores and middle dash hard separators
This commit is contained in:
Clément Renault 2019-09-24 23:09:38 +02:00 committed by GitHub
commit 57dd679026
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 8 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
meilidb-tokenizer/src/lib.rs
View File

@ -39,8 +39,8 @@ fn is_separator(c: char) -> bool {
fn classify_separator(c: char) -> Option<SeparatorCategory> {
match c {
' ' | '\'' | ':' | '"' => Some(Soft),
'.' | ';' | ',' | '!' | '?' | '-' | '_' | '(' | ')' => Some(Hard),
' ' | '-' | '_' | '\'' | ':' | '"' => Some(Soft),
'.' | ';' | ',' | '!' | '?' | '(' | ')' => Some(Hard),
_ => None,
}
}
@ -249,8 +249,8 @@ mod tests {
assert_eq!(tokenizer.next(), Some(Token { word: "yo", word_index: 0, char_index: 0 }));
assert_eq!(tokenizer.next(), Some(Token { word: "lolo", word_index: 8, char_index: 5 }));
assert_eq!(tokenizer.next(), Some(Token { word: "wtf", word_index: 16, char_index: 12 }));
assert_eq!(tokenizer.next(), Some(Token { word: "lol", word_index: 24, char_index: 18 }));
assert_eq!(tokenizer.next(), Some(Token { word: "aïe", word_index: 32, char_index: 24 }));
assert_eq!(tokenizer.next(), Some(Token { word: "lol", word_index: 17, char_index: 18 }));
assert_eq!(tokenizer.next(), Some(Token { word: "aïe", word_index: 25, char_index: 24 }));
assert_eq!(tokenizer.next(), None);
}
@ -268,8 +268,8 @@ mod tests {
assert_eq!(tokenizer.next(), Some(Token { word: "yo", word_index: 0, char_index: 0 }));
assert_eq!(tokenizer.next(), Some(Token { word: "lolo", word_index: 8, char_index: 5 }));
assert_eq!(tokenizer.next(), Some(Token { word: "😱", word_index: 16, char_index: 12 }));
assert_eq!(tokenizer.next(), Some(Token { word: "lol", word_index: 24, char_index: 16 }));
assert_eq!(tokenizer.next(), Some(Token { word: "😣", word_index: 32, char_index: 22 }));
assert_eq!(tokenizer.next(), Some(Token { word: "lol", word_index: 17, char_index: 16 }));
assert_eq!(tokenizer.next(), Some(Token { word: "😣", word_index: 25, char_index: 22 }));
assert_eq!(tokenizer.next(), None);
}
@ -288,8 +288,8 @@ mod tests {
assert_eq!(tokenizer.next(), Some(Token { word: "\u{2ed3}", word_index: 1, char_index: 1 }));
assert_eq!(tokenizer.next(), Some(Token { word: "\u{2ef2}", word_index: 2, char_index: 2 }));
assert_eq!(tokenizer.next(), Some(Token { word: "lolilol", word_index: 3, char_index: 4 }));
assert_eq!(tokenizer.next(), Some(Token { word: "hello", word_index: 11, char_index: 14 }));
assert_eq!(tokenizer.next(), Some(Token { word: "\u{2ec7}", word_index: 12, char_index: 23 }));
assert_eq!(tokenizer.next(), Some(Token { word: "hello", word_index: 4, char_index: 14 }));
assert_eq!(tokenizer.next(), Some(Token { word: "\u{2ec7}", word_index: 5, char_index: 23 }));
assert_eq!(tokenizer.next(), None);
}
}