Skip to content

Use tokenize instead of getTokenizer #16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Dec 12, 2021
Merged

Use tokenize instead of getTokenizer #16

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
7ddafe2
Use tokenize instead of getTokenizer
k-tahiro Dec 10, 2021
9974bd2
Bug fix
k-tahiro Dec 10, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
103 changes: 51 additions & 52 deletions src/max-ten.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
// LICENSE : MIT
"use strict";
import { RuleHelper } from "textlint-rule-helper";
import { getTokenizer } from "kuromojin";
import { tokenize } from "kuromojin";
import { splitAST, Syntax as SentenceSyntax } from "sentence-splitter";
import { StringSource } from "textlint-util-to-string";

Expand Down Expand Up @@ -103,59 +103,58 @@ module.exports = function (context, options = {}) {
2. sentence to tokens
3. check tokens
*/
return getTokenizer().then((tokenizer) => {
sentences.forEach((sentence) => {
const source = new StringSource(sentence);
const text = source.toString();
const tokens = tokenizer.tokenizeForSentence(text);
let currentTenCount = 0;
let lastToken = null;
tokens.forEach((token, index) => {
const surface = token.surface_form;
if (surface === touten) {
// 名詞に囲まわれている場合は例外とする
const isSandwiched = isSandwichedMeishi({
before: findSiblingMeaningToken({
tokens,
currentIndex: index,
direction: "prev"
}),
token: token,
after: findSiblingMeaningToken({
tokens,
currentIndex: index,
direction: "next"
})
});
// strictなら例外を例外としない
if (!isStrict && isSandwiched) {
return;
}
currentTenCount++;
lastToken = token;
}
if (surface === kuten) {
// reset
currentTenCount = 0;
}
// report
if (currentTenCount > maxLen) {
const positionInSentence = source.originalIndexFromIndex(lastToken.word_position - 1);
// relative index from Paragraph Node
// Sentence start(relative) + word position(relative)
const index = sentence.range[0] - node.range[0] + positionInSentence;
const ruleError = new context.RuleError(
`一つの文で"${touten}"を${maxLen + 1}つ以上使用しています`,
{
index
}
);
report(node, ruleError);
currentTenCount = 0;
const checkSentence = async (sentence) => {
const source = new StringSource(sentence);
const text = source.toString();
const tokens = await tokenize(text);
let currentTenCount = 0;
let lastToken = null;
tokens.forEach((token, index) => {
const surface = token.surface_form;
if (surface === touten) {
// 名詞に囲まわれている場合は例外とする
const isSandwiched = isSandwichedMeishi({
before: findSiblingMeaningToken({
tokens,
currentIndex: index,
direction: "prev"
}),
token: token,
after: findSiblingMeaningToken({
tokens,
currentIndex: index,
direction: "next"
})
});
// strictなら例外を例外としない
if (!isStrict && isSandwiched) {
return;
}
});
currentTenCount++;
lastToken = token;
}
if (surface === kuten) {
// reset
currentTenCount = 0;
}
// report
if (currentTenCount > maxLen) {
const positionInSentence = source.originalIndexFromIndex(lastToken.word_position - 1);
// relative index from Paragraph Node
// Sentence start(relative) + word position(relative)
const index = sentence.range[0] - node.range[0] + positionInSentence;
const ruleError = new context.RuleError(
`一つの文で"${touten}"を${maxLen + 1}つ以上使用しています`,
{
index
}
);
report(node, ruleError);
currentTenCount = 0;
}
});
});
};
return Promise.all(sentences.map(checkSentence));
}
};
};