Skip to content
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

jsdomに戻し､brのみを改行とすることに変更 #149

Merged
merged 1 commit into from
Aug 3, 2024
+17 −48
Merged

jsdomに戻し､brのみを改行とすることに変更 #149

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
65 changes: 17 additions & 48 deletions web/app/feature/translate/utils/extractNumberedElements.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,57 +1,26 @@
import { Parser } from "htmlparser2";
import { JSDOM } from "jsdom";

export function extractNumberedElements(
content: string,
title: string,
): Array<{ number: number; text: string }> {
const numberedElements: Array<{ number: number; text: string }> = [
{ number: 0, text: title },
];
const doc = new JSDOM(content);
const numberedElements: Array<{ number: number; text: string }> = [];
// <br>のみを改行とする
doc.window.document.body.innerHTML = doc.window.document.body.innerHTML
.replace(/\n/g, "")
.replace(/<br\s*\/?>/gi, "\n");
Comment on lines +6 to +11
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Image description CodeRabbit

doc.window.document.body.innerHTMLの操作は、XSS攻撃に対して脆弱です。ユーザー入力を直接DOMに挿入する前に、適切なサニタイズ処理を行うべきです。

- 	doc.window.document.body.innerHTML = doc.window.document.body.innerHTML
+ 	const sanitizedContent = content.replace(/<script[^>]*>([\S\s]*?)<\/script>/gmi, '');
+ 	doc.window.document.body.innerHTML = sanitizedContent


let currentNumber: number | null = null;
let currentText: string[] = [];
let inNumberedElement = false;
const elements = doc.window.document.querySelectorAll("[data-number]");

const parser = new Parser(
{
onopentag(name: string, attributes: { [x: string]: string }) {
if (attributes["data-number"]) {
currentNumber = Number.parseInt(attributes["data-number"], 10);
inNumberedElement = true;
currentText = [];
}
},
ontext(text) {
if (inNumberedElement) {
currentText.push(text.trim());
}
},
onclosetag(name) {
if (name === "br" && inNumberedElement) {
currentText.push("::BR::");
} else if (currentNumber !== null && inNumberedElement) {
const processedText = currentText
.join("")
.replace(/\s+/g, " ")
.trim()
.replace(/::BR::/g, "\n");

if (processedText) {
numberedElements.push({
number: currentNumber,
text: processedText,
});
}
currentNumber = null;
inNumberedElement = false;
}
},
},
{ decodeEntities: true },
);

parser.write(content);
parser.end();
for (const element of elements) {
const dataNumber = element.getAttribute("data-number");
if (dataNumber !== null) {
numberedElements.push({
number: Number.parseInt(dataNumber, 10),
text: element.textContent?.trim() || "",
Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Image description CodeRabbit

Number.parseIntの使用は適切ですが、NaNチェックが不足しています。data-number属性が数値でない場合のエラーハンドリングを追加すべきです。

- 				number: Number.parseInt(dataNumber, 10),
+ 				number: Number.isNaN(Number.parseInt(dataNumber, 10)) ? 0 : Number.parseInt(dataNumber, 10),

});
}
}

return numberedElements.sort((a, b) => a.number - b.number);
}
Loading