From 1491459deaa145ea875be6bdc9480921403de1c4 Mon Sep 17 00:00:00 2001
From: Jonas Jenwald <jonas.jenwald@gmail.com>
Date: Wed, 29 Dec 2021 15:57:34 +0100
Subject: [PATCH] Improve caching for the `Catalog.getPageIndex` method (PR
 13319 follow-up)

This method is now being used a lot more, compared to when it's added, since it's now used together with scripting as part of the `PDFDocument.fieldObjects` parsing (called during viewer initialization).
For /Page Dictionaries that we've already parsed, the `pageIndex` corresponding to a particular Reference is already known and we're thus able to skip *all* parsing in the `Catalog.getPageIndex` method for those cases.
---
 src/core/catalog.js  | 17 ++++++++++++++---
 src/core/document.js |  7 ++++++-
 2 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/src/core/catalog.js b/src/core/catalog.js
index 54c6849ef..30ccddf16 100644
--- a/src/core/catalog.js
+++ b/src/core/catalog.js
@@ -1099,7 +1099,8 @@ class Catalog {
       visitedNodes.put(pagesRef);
     }
     const xref = this.xref,
-      pageKidsCountCache = this.pageKidsCountCache;
+      pageKidsCountCache = this.pageKidsCountCache,
+      pageIndexCache = this.pageIndexCache;
     let currentPageIndex = 0;
 
     while (nodesToVisit.length) {
@@ -1128,9 +1129,13 @@ class Catalog {
             // Cache the Page reference, since it can *greatly* improve
             // performance by reducing redundant lookups in long documents
             // where all nodes are found at *one* level of the tree.
-            if (currentNode && !pageKidsCountCache.has(currentNode)) {
+            if (!pageKidsCountCache.has(currentNode)) {
               pageKidsCountCache.put(currentNode, 1);
             }
+            // Help improve performance of the `getPageIndex` method.
+            if (!pageIndexCache.has(currentNode)) {
+              pageIndexCache.put(currentNode, currentPageIndex);
+            }
 
             if (currentPageIndex === pageIndex) {
               return [obj, currentNode];
@@ -1215,10 +1220,16 @@ class Catalog {
     if (pagesRef instanceof Ref) {
       visitedNodes.put(pagesRef);
     }
-    const map = new Map();
+    const map = new Map(),
+      pageIndexCache = this.pageIndexCache;
     let pageIndex = 0;
 
     function addPageDict(pageDict, pageRef) {
+      // Help improve performance of the `getPageIndex` method.
+      if (pageRef && !pageIndexCache.has(pageRef)) {
+        pageIndexCache.put(pageRef, pageIndex);
+      }
+
       map.set(pageIndex++, [pageDict, pageRef]);
     }
     function addPageError(error) {
diff --git a/src/core/document.js b/src/core/document.js
index 5daeeb186..06b3f3895 100644
--- a/src/core/document.js
+++ b/src/core/document.js
@@ -1285,9 +1285,14 @@ class PDFDocument {
           type = await xref.fetchAsync(type);
         }
         if (isName(type, "Page") || (!obj.has("Type") && !obj.has("Kids"))) {
-          if (ref && !catalog.pageKidsCountCache.has(ref)) {
+          if (!catalog.pageKidsCountCache.has(ref)) {
             catalog.pageKidsCountCache.put(ref, 1); // Cache the Page reference.
           }
+          // Help improve performance of the `Catalog.getPageIndex` method.
+          if (!catalog.pageIndexCache.has(ref)) {
+            catalog.pageIndexCache.put(ref, 0);
+          }
+
           return [obj, ref];
         }
       }