Add enhanced text sanitization

This commit is contained in:
Lina Tawfik
2025-05-28 17:29:09 -07:00
parent 176dbc369d
commit 61cd297c18
8 changed files with 541 additions and 175 deletions

View File

@@ -0,0 +1,64 @@
export function stripInvisibleCharacters(content: string): string {
content = content.replace(/[\u200B\u200C\u200D\uFEFF]/g, "");
content = content.replace(
/[\u0000-\u0008\u000B\u000C\u000E-\u001F\u007F-\u009F]/g,
"",
);
content = content.replace(/\u00AD/g, "");
content = content.replace(/[\u202A-\u202E\u2066-\u2069]/g, "");
return content;
}
export function stripMarkdownImageAltText(content: string): string {
return content.replace(/!\[[^\]]*\]\(/g, "![](");
}
export function stripMarkdownLinkTitles(content: string): string {
content = content.replace(/(\[[^\]]*\]\([^)]+)\s+"[^"]*"/g, "$1");
content = content.replace(/(\[[^\]]*\]\([^)]+)\s+'[^']*'/g, "$1");
return content;
}
export function stripHiddenAttributes(content: string): string {
content = content.replace(/\salt\s*=\s*["'][^"']*["']/gi, "");
content = content.replace(/\salt\s*=\s*[^\s>]+/gi, "");
content = content.replace(/\stitle\s*=\s*["'][^"']*["']/gi, "");
content = content.replace(/\stitle\s*=\s*[^\s>]+/gi, "");
content = content.replace(/\saria-label\s*=\s*["'][^"']*["']/gi, "");
content = content.replace(/\saria-label\s*=\s*[^\s>]+/gi, "");
content = content.replace(/\sdata-[a-zA-Z0-9-]+\s*=\s*["'][^"']*["']/gi, "");
content = content.replace(/\sdata-[a-zA-Z0-9-]+\s*=\s*[^\s>]+/gi, "");
content = content.replace(/\splaceholder\s*=\s*["'][^"']*["']/gi, "");
content = content.replace(/\splaceholder\s*=\s*[^\s>]+/gi, "");
return content;
}
export function normalizeHtmlEntities(content: string): string {
content = content.replace(/&#(\d+);/g, (_, dec) => {
const num = parseInt(dec, 10);
if (num >= 32 && num <= 126) {
return String.fromCharCode(num);
}
return "";
});
content = content.replace(/&#x([0-9a-fA-F]+);/g, (_, hex) => {
const num = parseInt(hex, 16);
if (num >= 32 && num <= 126) {
return String.fromCharCode(num);
}
return "";
});
return content;
}
export function sanitizeContent(content: string): string {
content = stripInvisibleCharacters(content);
content = stripMarkdownImageAltText(content);
content = stripMarkdownLinkTitles(content);
content = stripHiddenAttributes(content);
content = normalizeHtmlEntities(content);
return content;
}
export const stripHtmlComments = (content: string) =>
content.replace(/<!--[\s\S]*?-->/g, "");