From 8af70d75aa4ce502e128fa6333e3a2c99f439ffb Mon Sep 17 00:00:00 2001
From: Jonas Jenwald <jonas.jenwald@gmail.com>
Date: Sat, 23 May 2020 11:21:32 +0200
Subject: [PATCH] Allow `GlobalImageCache.clear` to, optionally, only remove
 the actual data (PR 11912 follow-up)

When "Cleanup" is triggered, you obviously need to remove all globally cached data on *both* the main- and worker-threads.
However, the current the implementation of the `GlobalImageCache.clear` method also means that we lose *all* information about which images were cached and not just their data. This thus has the somewhat unfortunate side-effect of requiring images, which were previously known to be "global", to *again* having to reach `NUM_PAGES_THRESHOLD` before being cached again.

To avoid doing unnecessary parsing after "Cleanup", we can thus let `GlobalImageCache.clear` keep track of which images were cached while still removing their actual data. This should not have any significant impact on memory usage, since the only extra thing being kept is a `RefSetCache` (essentially an Object) with a couple of `Set`s containing only integers.
---
 src/core/document.js    | 6 ++++--
 src/core/image_utils.js | 6 ++++--
 src/core/obj.js         | 4 ++--
 src/core/pdf_manager.js | 4 ++--
 src/core/worker.js      | 2 +-
 5 files changed, 13 insertions(+), 9 deletions(-)

diff --git a/src/core/document.js b/src/core/document.js
index f2d80c07b..1c7772936 100644
--- a/src/core/document.js
+++ b/src/core/document.js
@@ -844,8 +844,10 @@ class PDFDocument {
     return this.catalog.fontFallback(id, handler);
   }
 
-  async cleanup() {
-    return this.catalog ? this.catalog.cleanup() : clearPrimitiveCaches();
+  async cleanup(manuallyTriggered = false) {
+    return this.catalog
+      ? this.catalog.cleanup(manuallyTriggered)
+      : clearPrimitiveCaches();
   }
 }
 
diff --git a/src/core/image_utils.js b/src/core/image_utils.js
index 1a6a8bd87..1ae7bf6cc 100644
--- a/src/core/image_utils.js
+++ b/src/core/image_utils.js
@@ -199,8 +199,10 @@ class GlobalImageCache {
     this._imageCache.put(ref, data);
   }
 
-  clear() {
-    this._refCache.clear();
+  clear(onlyData = false) {
+    if (!onlyData) {
+      this._refCache.clear();
+    }
     this._imageCache.clear();
   }
 }
diff --git a/src/core/obj.js b/src/core/obj.js
index 939377633..fdaa1bd17 100644
--- a/src/core/obj.js
+++ b/src/core/obj.js
@@ -716,9 +716,9 @@ class Catalog {
     });
   }
 
-  cleanup() {
+  cleanup(manuallyTriggered = false) {
     clearPrimitiveCaches();
-    this.globalImageCache.clear();
+    this.globalImageCache.clear(/* onlyData = */ manuallyTriggered);
     this.pageKidsCountCache.clear();
 
     const promises = [];
diff --git a/src/core/pdf_manager.js b/src/core/pdf_manager.js
index 0ae629c63..1cdcc03fa 100644
--- a/src/core/pdf_manager.js
+++ b/src/core/pdf_manager.js
@@ -76,8 +76,8 @@ class BasePdfManager {
     return this.pdfDocument.fontFallback(id, handler);
   }
 
-  cleanup() {
-    return this.pdfDocument.cleanup();
+  cleanup(manuallyTriggered = false) {
+    return this.pdfDocument.cleanup(manuallyTriggered);
   }
 
   async ensure(obj, prop, args) {
diff --git a/src/core/worker.js b/src/core/worker.js
index 91a70db63..e03c98da2 100644
--- a/src/core/worker.js
+++ b/src/core/worker.js
@@ -625,7 +625,7 @@ var WorkerMessageHandler = {
     });
 
     handler.on("Cleanup", function wphCleanup(data) {
-      return pdfManager.cleanup();
+      return pdfManager.cleanup(/* manuallyTriggered = */ true);
     });
 
     handler.on("Terminate", function wphTerminate(data) {