Try to use regex heuristics instead of llm for generating one-click rules

Author: muodov

post-processing/generate-autoconsent-rules/generation.js

@@ -248,8 +248,10 @@ function generateRulesForSite(region, initialUrl, finalUrl, collectorResult, mat
     const reviewNotes = [];
     let keptCount = 0;
 
-    const llmConfirmedPopups = collectorResult.scrapedFrames.flatMap((frame) => frame.potentialPopups).filter((popup) => popup.llmMatch);
-    if (llmConfirmedPopups.length > 1 || llmConfirmedPopups[0].rejectButtons.length > 1) {
+    // const llmConfirmedPopups = collectorResult.scrapedFrames.flatMap((frame) => frame.potentialPopups).filter((popup) => popup.llmMatch);
+    const regexConfirmedPopups = collectorResult.scrapedFrames.flatMap((frame) => frame.potentialPopups).filter((popup) => popup.regexMatch);
+    // if (llmConfirmedPopups.length > 1 || llmConfirmedPopups[0].rejectButtons.length > 1) {
+    if (regexConfirmedPopups.length > 1 || regexConfirmedPopups[0].rejectButtons.length > 1) {
         console.warn('Multiple cookie popups or reject buttons found in', initialUrl);
         reviewNotes.push({
             needsReview: false, // it's not a problem by itself, unless this leads to multiple _rules_ generated, but we check that separately.
@@ -261,7 +263,8 @@ function generateRulesForSite(region, initialUrl, finalUrl, collectorResult, mat
 
     // go over all frames, all confirmed popups within them, and all reject buttons inside
     for (const frame of collectorResult.scrapedFrames) {
-        for (const popup of frame.potentialPopups.filter((p) => p.llmMatch)) {
+        // for (const popup of frame.potentialPopups.filter((p) => p.llmMatch)) {
+        for (const popup of frame.potentialPopups.filter((p) => p.regexMatch)) {
             for (const button of popup.rejectButtons) {
                 if (ruleForButtonExists(button, matchingRules, newRules, rulesToOverride)) {
                     // if there is an existing rule with the same reject button, do nothing

post-processing/generate-autoconsent-rules/main.js

@@ -148,16 +148,19 @@ async function processCookiePopupsForSite(globalParams, { finalUrl, initialUrl,
 
     const updatedExistingRules = structuredClone(existingRules);
 
-    const llmConfirmedPopups = collectorResult.scrapedFrames.flatMap((frame) => frame.potentialPopups).filter((popup) => popup.llmMatch);
+    // const llmConfirmedPopups = collectorResult.scrapedFrames.flatMap((frame) => frame.potentialPopups).filter((popup) => popup.llmMatch);
+    const regexConfirmedPopups = collectorResult.scrapedFrames.flatMap((frame) => frame.potentialPopups).filter((popup) => popup.regexMatch);
 
     // shortcut if no popups with llmMatch
-    if (llmConfirmedPopups.length === 0) {
+    // if (llmConfirmedPopups.length === 0) {
+    if (regexConfirmedPopups.length === 0) {
         return { newRuleFiles, updatedRuleFiles, keptCount: 0, reviewNotes: [], updatedExistingRules };
     }
 
     const matchingRules = findMatchingExistingRules(initialUrl, finalUrl, collectorResult, existingRules);
     console.log(
-        `Detected ${llmConfirmedPopups.length} unhandled cookie popup(s) on ${finalUrl} (matched ${matchingRules.length} existing rules)`,
+        // `Detected ${llmConfirmedPopups.length} unhandled cookie popup(s) on ${finalUrl} (matched ${matchingRules.length} existing rules)`,
+        `Detected ${regexConfirmedPopups.length} unhandled cookie popup(s) on ${finalUrl} (matched ${matchingRules.length} existing rules)`,
     );
     const { newRules, rulesToOverride, reviewNotes, keptCount } = generateRulesForSite(
         region,
@@ -309,26 +312,33 @@ async function processFiles(globalParams, existingRules) {
         totalSitesWithPopups++;
 
         const matchedRules = collectorResult.cmps.map((cmp) => cmp.name.trim()).filter((name) => name !== '');
-        const llmConfirmedPopups = collectorResult.scrapedFrames
+        // const llmConfirmedPopups = collectorResult.scrapedFrames
+        //     .flatMap((frame) => frame.potentialPopups)
+        //     .filter((popup) => popup.llmMatch);
+        const regexConfirmedPopups = collectorResult.scrapedFrames
             .flatMap((frame) => frame.potentialPopups)
-            .filter((popup) => popup.llmMatch);
+            .filter((popup) => popup.regexMatch);
         const screenshot = jsonData.data.screenshots;
 
         if (hasKnownCmp(collectorResult.cmps)) {
             totalSitesWithKnownCmps++;
             autoconsentManifest.set(fileName, {
                 siteUrl: jsonData.finalUrl,
                 matchedRules,
-                llmConfirmedPopups,
+                // llmConfirmedPopups,
+                regexConfirmedPopups,
                 screenshot,
                 newlyCreatedRules: [],
                 updatedRules: [],
                 reviewNotes: [],
             });
         } else {
-            const llmConfirmedPopups = collectorResult.scrapedFrames
+            // const llmConfirmedPopups = collectorResult.scrapedFrames
+            //     .flatMap((frame) => frame.potentialPopups)
+            //     .filter((popup) => popup.llmMatch);
+            const regexConfirmedPopups = collectorResult.scrapedFrames
                 .flatMap((frame) => frame.potentialPopups)
-                .filter((popup) => popup.llmMatch);
+                .filter((popup) => popup.regexMatch);
             /** @type {import('./types').AutoconsentManifestFileData[]} */
             let newRuleFiles = [];
             /** @type {import('./types').AutoconsentManifestFileData[]} */
@@ -337,7 +347,8 @@ async function processFiles(globalParams, existingRules) {
             /** @type {import('./types').ReviewNote[]} */
             let reviewNotes = [];
 
-            if (llmConfirmedPopups.length > 0) {
+            // if (llmConfirmedPopups.length > 0) {
+            if (regexConfirmedPopups.length > 0) {
                 totalUnhandled++;
                 const result = await processCookiePopupsForSite(globalParams, {
                     finalUrl: jsonData.finalUrl,
@@ -351,7 +362,8 @@ async function processFiles(globalParams, existingRules) {
             autoconsentManifest.set(fileName, {
                 siteUrl: jsonData.finalUrl,
                 matchedRules,
-                llmConfirmedPopups,
+                // llmConfirmedPopups,
+                regexConfirmedPopups,
                 screenshot,
                 newlyCreatedRules: newRuleFiles,
                 updatedRules: updatedRuleFiles,

post-processing/generate-autoconsent-rules/types.js

@@ -42,7 +42,8 @@
  * @typedef {{
  *  siteUrl: string;
  *  matchedRules: string[];
- *  llmConfirmedPopups: PopupData[];
+ *  _llmConfirmedPopups?: PopupData[];
+ *  regexConfirmedPopups: PopupData[];
  *  screenshot: string;
  *  newlyCreatedRules: AutoconsentManifestFileData[];
  *  updatedRules: AutoconsentManifestFileData[];