Skip to content

Commit 968b4a8

Browse files
fix(tokenizers): use mandarin instead of japanese in tokenizer language (#904)
1 parent 7278dcd commit 968b4a8

File tree

2 files changed

+6
-4
lines changed

2 files changed

+6
-4
lines changed

packages/tokenizers/src/index.ts

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,7 @@
11
import { createTokenizer as createJapaneseTokenizer } from "./japanese.js";
2+
import { createTokenizer as createMandarinTokenizer } from "./mandarin.js";
23

34
export default {
45
japanese: createJapaneseTokenizer,
6+
mandarin: createMandarinTokenizer,
57
}

packages/tokenizers/src/mandarin.ts

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,15 +1,15 @@
11
import type { DefaultTokenizer, DefaultTokenizerConfig } from "@orama/orama";
22
import { normalizeToken } from "@orama/orama/internals";
33

4-
const tokenizerLanguage = "japanese";
4+
const tokenizerLanguage = "mandarin";
55

66
type TLanguage = typeof tokenizerLanguage;
77

8-
type JapaneseTokenizerConfig = DefaultTokenizerConfig & {
8+
type MandarinTokenizerConfig = DefaultTokenizerConfig & {
99
language: TLanguage;
1010
};
1111

12-
const defaultConfig: JapaneseTokenizerConfig = {
12+
const defaultConfig: MandarinTokenizerConfig = {
1313
language: tokenizerLanguage,
1414
};
1515

@@ -68,7 +68,7 @@ function tokenizeInternal(
6868
}
6969

7070
export function createTokenizer(
71-
config: JapaneseTokenizerConfig = defaultConfig,
71+
config: MandarinTokenizerConfig = defaultConfig,
7272
): DefaultTokenizer {
7373
const tokenizerConfig = {
7474
tokenize: tokenizeInternal,

0 commit comments

Comments
 (0)
pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy