Attempt to also cache images at the "page"-level (issue 16263)

Currently we have two separate image-caches on the worker-thread:
 - A local one, which is unique to each `PartialEvaluator.getOperatorList` invocation. This one caches both names *and* references, since image-resources may be accessed in either way.
 - A global one, which applies to the entire PDF documents and all its pages. This one only caches references, since nothing else would work.

This patch introduces a third image-cache, which essentially sits "between" the two existing ones. The new `RegionalImageCache`[1] will be usable throughout a `PartialEvaluator` instance, and consequently it *only* caches references, which thus allows us to keep track of repeated image-resources found in e.g. different /Form and /SMask objects.

---
[1] For lack of a better word, since naming things is hard...

src/core/evaluator.js

@@ -59,6 +59,7 @@ import {
   LocalGStateCache,
   LocalImageCache,
   LocalTilingPatternCache,
+  RegionalImageCache,
 } from "./image_utils.js";
 import { NullStream, Stream } from "./stream.js";
 import { BaseStream } from "./base_stream.js";
@@ -229,6 +230,7 @@ class PartialEvaluator {
     this.options = options || DefaultPartialEvaluatorOptions;
     this.parsingType3Font = false;
 
+    this._regionalImageCache = new RegionalImageCache();
     this._fetchBuiltInCMapBound = this.fetchBuiltInCMap.bind(this);
     ImageResizer.setMaxArea(this.options.canvasMaxAreaInBytes);
   }
@@ -635,11 +637,20 @@ class PartialEvaluator {
         );
 
         if (cacheKey) {
-          localImageCache.set(cacheKey, imageRef, {
+          const cacheData = {
             fn: OPS.paintImageMaskXObject,
             args,
             optionalContent,
-          });
+          };
+          localImageCache.set(cacheKey, imageRef, cacheData);
+
+          if (imageRef) {
+            this._regionalImageCache.set(
+              /* name = */ null,
+              imageRef,
+              cacheData
+            );
+          }
         }
         return;
       }
@@ -664,11 +675,20 @@ class PartialEvaluator {
         );
 
         if (cacheKey) {
-          localImageCache.set(cacheKey, imageRef, {
+          const cacheData = {
             fn: OPS.paintSolidColorImageMask,
             args: [],
             optionalContent,
-          });
+          };
+          localImageCache.set(cacheKey, imageRef, cacheData);
+
+          if (imageRef) {
+            this._regionalImageCache.set(
+              /* name = */ null,
+              imageRef,
+              cacheData
+            );
+          }
         }
         return;
       }
@@ -693,11 +713,16 @@ class PartialEvaluator {
       );
 
       if (cacheKey) {
-        localImageCache.set(cacheKey, imageRef, {
+        const cacheData = {
           fn: OPS.paintImageMaskXObject,
           args,
           optionalContent,
-        });
+        };
+        localImageCache.set(cacheKey, imageRef, cacheData);
+
+        if (imageRef) {
+          this._regionalImageCache.set(/* name = */ null, imageRef, cacheData);
+        }
       }
       return;
     }
@@ -790,13 +815,16 @@ class PartialEvaluator {
     operatorList.addImageOps(OPS.paintImageXObject, args, optionalContent);
 
     if (cacheKey) {
-      localImageCache.set(cacheKey, imageRef, {
+      const cacheData = {
         fn: OPS.paintImageXObject,
         args,
         optionalContent,
-      });
+      };
+      localImageCache.set(cacheKey, imageRef, cacheData);
 
       if (imageRef) {
+        this._regionalImageCache.set(/* name = */ null, imageRef, cacheData);
+
         assert(!isInline, "Cannot cache an inline image globally.");
         this.globalImageCache.addPageIndex(imageRef, this.pageIndex);
 
@@ -1723,7 +1751,9 @@ class PartialEvaluator {
 
                 let xobj = xobjs.getRaw(name);
                 if (xobj instanceof Ref) {
-                  const localImage = localImageCache.getByRef(xobj);
+                  const localImage =
+                    localImageCache.getByRef(xobj) ||
+                    self._regionalImageCache.getByRef(xobj);
                   if (localImage) {
                     operatorList.addImageOps(
                       localImage.fn,

src/core/image_utils.js

@@ -156,6 +156,22 @@ class LocalTilingPatternCache extends BaseLocalCache {
   }
 }
 
+class RegionalImageCache extends BaseLocalCache {
+  constructor(options) {
+    super({ onlyRefs: true });
+  }
+
+  set(name = null, ref, data) {
+    if (!ref) {
+      throw new Error('RegionalImageCache.set - expected "ref" argument.');
+    }
+    if (this._imageCache.has(ref)) {
+      return;
+    }
+    this._imageCache.put(ref, data);
+  }
+}
+
 class GlobalImageCache {
   static get NUM_PAGES_THRESHOLD() {
     return shadow(this, "NUM_PAGES_THRESHOLD", 2);
@@ -288,4 +304,5 @@ export {
   LocalGStateCache,
   LocalImageCache,
   LocalTilingPatternCache,
+  RegionalImageCache,
 };

test/pdfs/.gitignore

@@ -225,6 +225,7 @@
 !issue840.pdf
 !160F-2019.pdf
 !issue4402_reduced.pdf
+!issue16263.pdf
 !issue845r.pdf
 !issue3405r.pdf
 !issue14130.pdf

test/test_manifest.json

@@ -4721,6 +4721,12 @@
        "link": false,
        "type": "eq"
     },
+    {  "id": "issue16263",
+       "file": "pdfs/issue16263.pdf",
+       "md5": "93c3e7884f1f2d072442898127e0a6fd",
+       "rounds": 1,
+       "type": "eq"
+    },
     {  "id": "issue2006",
       "file": "pdfs/issue2006.pdf",
       "md5": "71ec73831ece9b508ad20efa6ff28642",