feat: filter out RSS posts that violate our Code of Conduct.

src/modules/postNews.ts

@@ -12,10 +12,26 @@ import Parser from "rss-parser";
 import { ids } from "../config/ids.js";
 import { logger } from "../utils/logger.js";
 import type { Amari } from "../interfaces/amari.js";
-import type {
-  FreeCodeCampRSS,
-  HackerNewsRSS,
-} from "../interfaces/rss.js";
+import type { FreeCodeCampRSS, HackerNewsRSS } from "../interfaces/rss.js";
+
+/**
+ * We are completely aware that the contents of this regular expression
+ * are a violation of our Code of Conduct. Unfortunately, this is necessary
+ * to allow us to filter out the RSS feeds for inappropriate content.
+ * We apologise for any distress or harm this line may cause.
+ */
+const naughtyRegex
+// eslint-disable-next-line stylistic/max-len -- Required for filtering.
+  = /\b(?:harass(?:ment|ing|ed)?|bully(?:ing)?|discriminat(?:e|ion|ory)|deadnam(?:e|ing)|misgender(?:ing|ed)?|doxx?(?:ing)?|threat(?:en(?:s|ing|ed)?)?|intimidat(?:e|ion|ing)|spam|scam|fraud|phish(?:ing)?|malware|exploit|attack(?:s|ing)?|hate\s*speech|slur|racist|sexist|homophobic|transphobic|ableist|xenophobic|bigot(?:ry|ed)?|troll(?:ing)?|abuse|derogat(?:ory|ing)|offensive|vulgar|obscene|nsfw|porn(?:o|ography)?|sexual(?:ly)?\s*(?:harass|explicit|content)|gore|violent|illegal|pirat(?:e|ed|ing)|crack(?:ed|ing)?|warez|torrent(?:s|ing)?|copyright\s*violat|stolen|leak(?:ed|ing)?\s*(?:data|info|personal)|dox|privacy\s*violat|confidential|unauthorized|solicitation|advertis(?:e|ing|ement)|promot(?:e|ion|ing)|affiliate|referral|spam(?:ming)?|sell(?:ing)?|buy(?:ing)?|commercial|marketing|drug\s*deal(?:er|ing)?|narcotics?|cocaine|heroin|meth(?:amphetamine)?|fentanyl|opiates?|opioids?|carfentanil|mdma|ecstasy|lsd|psilocybin|mushrooms?\s*trip|ketamine|pcp|ghb|rohypnol|roofies?|xanax|percocet|oxyco(?:done|ntin)|vicodin|adderall|ritalin|controlled\s*substance|illicit\s*drug|street\s*drug|drug\s*traffick(?:ing)?|prescription\s*fraud|pill\s*mill|cannabis\s*(?!legal|dispensary)|marijuana\s*(?!legal|dispensary)|weed\s*(?!control|killer)|pot\s*dealer|dope|murder(?:ing|ed)?|kill(?:ing|ed)?\s*(?:someone|person|people)|assassinat(?:e|ion)|homicide|manslaughter|assault(?:ing|ed)?|battery|kidnap(?:ping)?|abduct(?:ion|ed)?|human\s*traffick(?:ing)?|sex\s*traffick(?:ing)?|child\s*abuse|rape|sexual\s*assault|molest(?:ation|ing|ed)?|pedophil(?:e|ia)|child\s*porn|cp\s*(?=\s|$)|csam|robbery|burgl(?:ar|ary)|theft|steal(?:ing)?|shoplifting|embezzl(?:e|ement|ing)|launder(?:ing)?\s*money|extortion|blackmail|bribery|arson|terrorism|terrorist|bomb(?:ing)?|explo(?:sive|ding)|weapon\s*deal|arms\s*traffick|firearm\s*(?=illegal|unregistered)|gun\s*(?=illegal|unregistered)|counterfe(?:it|ing)|forg(?:e|ery|ing)|identity\s*theft|tax\s*evasion|insider\s*trading)\b/i;
+
+/**
+ * Used to filter out naughty words from RSS feeds.
+ * @param titleOrContent - The title or content to check.
+ * @returns True if the title or content is naughty, false if it is clean.
+ */
+const hasNaughtyWords = (titleOrContent: string): boolean => {
+  return naughtyRegex.test(titleOrContent);
+};
 
 /**
  * Fetches the RSS feed from freeCodeCamp News and posts the latest updates.
@@ -24,8 +40,9 @@ import type {
 const postFreeCodeCampNews = async(amari: Amari): Promise<void> => {
   try {
     const parser = new Parser<FreeCodeCampRSS, FreeCodeCampRSS["items"]>();
-    const { items }
-      = await parser.parseURL("https://www.freecodecamp.org/news/rss");
+    const { items } = await parser.parseURL(
+      "https://www.freecodecamp.org/news/rss",
+    );
     if (amari.lastRssItems.freeCodeCamp === null) {
       amari.lastRssItems.freeCodeCamp = items[0]?.guid ?? null;
       return;
@@ -49,12 +66,21 @@ const postFreeCodeCampNews = async(amari: Amari): Promise<void> => {
     if (amari.lastRssItems.freeCodeCamp !== items[0]?.guid) {
       amari.lastRssItems.freeCodeCamp = items[0]?.guid ?? null;
     }
-    await Promise.all(latestPosts.map(async(post) => {
-      const sent = await channel.send(post.link);
-      if (channel.type === ChannelType.GuildAnnouncement) {
-        await sent.crosspost();
-      }
-    }));
+    await Promise.all(
+      latestPosts.map(async(post) => {
+        if (
+          hasNaughtyWords(post.title)
+          || hasNaughtyWords(post.contentSnippet)
+          || hasNaughtyWords(post.content)
+        ) {
+          return;
+        }
+        const sent = await channel.send(post.link);
+        if (channel.type === ChannelType.GuildAnnouncement) {
+          await sent.crosspost();
+        }
+      }),
+    );
   } catch (error) {
     if (error instanceof Error) {
       await logger.error("post freecodecamp news module", error);
@@ -69,8 +95,9 @@ const postFreeCodeCampNews = async(amari: Amari): Promise<void> => {
 const postHackerNews = async(amari: Amari): Promise<void> => {
   try {
     const parser = new Parser<HackerNewsRSS, HackerNewsRSS["items"]>();
-    const { items }
-      = await parser.parseURL("https://hnrss.org/newest?link=comments");
+    const { items } = await parser.parseURL(
+      "https://hnrss.org/newest?link=comments",
+    );
     if (amari.lastRssItems.hackerNews === null) {
       amari.lastRssItems.hackerNews = items[0]?.guid ?? null;
       return;
@@ -94,12 +121,14 @@ const postHackerNews = async(amari: Amari): Promise<void> => {
     if (amari.lastRssItems.hackerNews !== latestPosts[0]?.guid) {
       amari.lastRssItems.hackerNews = latestPosts[0]?.guid ?? null;
     }
-    await Promise.all(latestPosts.map(async(post) => {
-      const sent = await channel.send(post.link);
-      if (channel.type === ChannelType.GuildAnnouncement) {
-        await sent.crosspost();
-      }
-    }));
+    await Promise.all(
+      latestPosts.map(async(post) => {
+        const sent = await channel.send(post.link);
+        if (channel.type === ChannelType.GuildAnnouncement) {
+          await sent.crosspost();
+        }
+      }),
+    );
   } catch (error) {
     if (error instanceof Error) {
       await logger.error("post hackernews module", error);