feat: added memoization to the regexp generation

src/core/server/services/comments/moderation/phases/wordList.ts

@@ -7,7 +7,7 @@ import {
   IntermediateModerationPhase,
   IntermediatePhaseResult,
 } from "talk-server/services/comments/moderation";
-import { containsMatchingPhrase } from "talk-server/services/comments/moderation/wordlist";
+import { containsMatchingPhraseMemoized } from "talk-server/services/comments/moderation/wordlist";
 
 // This phase checks the comment against the wordList.
 export const wordList: IntermediateModerationPhase = ({
@@ -23,7 +23,7 @@ export const wordList: IntermediateModerationPhase = ({
   // has pre-mod enabled or not. If the comment was rejected based on the
   // wordList, then reject it, otherwise if the moderation setting is
   // premod, set it to `premod`.
-  if (containsMatchingPhrase(tenant.wordList.banned, comment.body)) {
+  if (containsMatchingPhraseMemoized(tenant.wordList.banned, comment.body)) {
     // Add the flag related to Trust to the comment.
     return {
       status: GQLCOMMENT_STATUS.REJECTED,
@@ -40,9 +40,9 @@ export const wordList: IntermediateModerationPhase = ({
   // flag to it to indicate that it needs to be looked at.
   // Otherwise just return the new comment.
 
-  // If the wordlist has matched the suspect word filter and we haven't disabled
+  // If the wordList has matched the suspect word filter and we haven't disabled
   // auto-flagging suspect words, then we should flag the comment!
-  if (containsMatchingPhrase(tenant.wordList.suspect, comment.body)) {
+  if (containsMatchingPhraseMemoized(tenant.wordList.suspect, comment.body)) {
     return {
       actions: [
         {

src/core/server/services/comments/moderation/phases/wordlist.ts

@@ -1,55 +0,0 @@
-import {
-  GQLCOMMENT_FLAG_REASON,
-  GQLCOMMENT_STATUS,
-} from "talk-server/graph/tenant/schema/__generated__/types";
-import { ACTION_TYPE } from "talk-server/models/action";
-import {
-  IntermediateModerationPhase,
-  IntermediatePhaseResult,
-} from "talk-server/services/comments/moderation";
-import { containsMatchingPhrase } from "talk-server/services/comments/moderation/wordlist";
-
-// This phase checks the comment against the wordList.
-export const wordList: IntermediateModerationPhase = ({
-  tenant,
-  comment,
-}): IntermediatePhaseResult | void => {
-  // If there isn't a body, there can't be a bad word!
-  if (!comment.body) {
-    return;
-  }
-
-  // Decide the status based on whether or not the current asset/settings
-  // has pre-mod enabled or not. If the comment was rejected based on the
-  // wordList, then reject it, otherwise if the moderation setting is
-  // premod, set it to `premod`.
-  if (containsMatchingPhrase(tenant.wordList.banned, comment.body)) {
-    // Add the flag related to Trust to the comment.
-    return {
-      status: GQLCOMMENT_STATUS.REJECTED,
-      actions: [
-        {
-          action_type: ACTION_TYPE.FLAG,
-          reason: GQLCOMMENT_FLAG_REASON.COMMENT_DETECTED_BANNED_WORD,
-        },
-      ],
-    };
-  }
-
-  // If the comment has a suspect word or a link, we need to add a
-  // flag to it to indicate that it needs to be looked at.
-  // Otherwise just return the new comment.
-
-  // If the wordlist has matched the suspect word filter and we haven't disabled
-  // auto-flagging suspect words, then we should flag the comment!
-  if (containsMatchingPhrase(tenant.wordList.suspect, comment.body)) {
-    return {
-      actions: [
-        {
-          action_type: ACTION_TYPE.FLAG,
-          reason: GQLCOMMENT_FLAG_REASON.COMMENT_DETECTED_SUSPECT_WORD,
-        },
-      ],
-    };
-  }
-};

src/core/server/services/comments/moderation/wordList.ts

@@ -1,3 +1,9 @@
+import { memoize } from "lodash";
+
+// TODO: reintroduce this when we have https://github.com/DefinitelyTyped/DefinitelyTyped/pull/30035 merged
+// // Replace `memoize.Cache`.
+// memoize.Cache = WeakMap;
+
 /**
  * Escape string for special regular expression characters.
  */
@@ -21,5 +27,13 @@ export function generateRegExp(phrases: string[]) {
   return new RegExp(`(^|[^\\w])(${inner})(?=[^\\w]|$)`, "iu");
 }
 
+export const generateRegExpMemoized = memoize(generateRegExp);
+
 export const containsMatchingPhrase = (phrases: string[], testString: string) =>
   phrases.length > 0 ? generateRegExp(phrases).test(testString) : false;
+
+export const containsMatchingPhraseMemoized = (
+  phrases: string[],
+  testString: string
+) =>
+  phrases.length > 0 ? generateRegExpMemoized(phrases).test(testString) : false;

src/core/server/services/comments/moderation/wordlist.ts

@@ -1,25 +0,0 @@
-/**
- * Escape string for special regular expression characters.
- */
-export function escapeRegExp(str: string) {
-  return str.replace(/[.*+?^${}()|[\]\\]/g, "\\$&"); // $& means the whole matched string
-}
-
-/**
- * Generate a regular expression that catches the `phrases`.
- */
-export function generateRegExp(phrases: string[]) {
-  const inner = phrases
-    .map(phrase =>
-      phrase
-        .split(/\s+/)
-        .map(word => escapeRegExp(word))
-        .join('[\\s"?!.]+')
-    )
-    .join("|");
-
-  return new RegExp(`(^|[^\\w])(${inner})(?=[^\\w]|$)`, "iu");
-}
-
-export const containsMatchingPhrase = (phrases: string[], testString: string) =>
-  phrases.length > 0 ? generateRegExp(phrases).test(testString) : false;