Cache the "raw" standard font data in the worker-thread (PR 12726 follow-up)

*This implementation is basically a copy of the pre-existing `builtInCMapCache` implementation.*

For some, badly generated, PDF documents it's possible that we'll end up having to fetch the *same* standard font data over and over (which is obviously inefficient).
While not common, it's certainly possible that a PDF document uses *custom* font names where the actual font then references one of the standard fonts; see e.g. issue 11399 for one such example.

Note that I did suggest adding worker-thread caching of standard font data in PR 12726, however it wasn't deemed necessary at the time. Now that we have a real-world example that benefit from caching, I think that we should simply implement this now.

src/core/catalog.js

@@ -71,6 +71,7 @@ class Catalog {
 
     this.fontCache = new RefSetCache();
     this.builtInCMapCache = new Map();
+    this.standardFontDataCache = new Map();
     this.globalImageCache = new GlobalImageCache();
     this.pageKidsCountCache = new RefSetCache();
     this.pageIndexCache = new RefSetCache();
@@ -1020,6 +1021,7 @@ class Catalog {
       }
       this.fontCache.clear();
       this.builtInCMapCache.clear();
+      this.standardFontDataCache.clear();
     });
   }
 

src/core/document.js

@@ -79,6 +79,7 @@ class Page {
     globalIdFactory,
     fontCache,
     builtInCMapCache,
+    standardFontDataCache,
     globalImageCache,
     nonBlendModesSet,
     xfaFactory,
@@ -90,6 +91,7 @@ class Page {
     this.ref = ref;
     this.fontCache = fontCache;
     this.builtInCMapCache = builtInCMapCache;
+    this.standardFontDataCache = standardFontDataCache;
     this.globalImageCache = globalImageCache;
     this.nonBlendModesSet = nonBlendModesSet;
     this.evaluatorOptions = pdfManager.evaluatorOptions;
@@ -255,6 +257,7 @@ class Page {
       idFactory: this._localIdFactory,
       fontCache: this.fontCache,
       builtInCMapCache: this.builtInCMapCache,
+      standardFontDataCache: this.standardFontDataCache,
       globalImageCache: this.globalImageCache,
       options: this.evaluatorOptions,
     });
@@ -321,6 +324,7 @@ class Page {
       idFactory: this._localIdFactory,
       fontCache: this.fontCache,
       builtInCMapCache: this.builtInCMapCache,
+      standardFontDataCache: this.standardFontDataCache,
       globalImageCache: this.globalImageCache,
       options: this.evaluatorOptions,
     });
@@ -425,6 +429,7 @@ class Page {
         idFactory: this._localIdFactory,
         fontCache: this.fontCache,
         builtInCMapCache: this.builtInCMapCache,
+        standardFontDataCache: this.standardFontDataCache,
         globalImageCache: this.globalImageCache,
         options: this.evaluatorOptions,
       });
@@ -889,6 +894,7 @@ class PDFDocument {
       idFactory: this._globalIdFactory,
       fontCache: this.catalog.fontCache,
       builtInCMapCache: this.catalog.builtInCMapCache,
+      standardFontDataCache: this.catalog.standardFontDataCache,
       options,
     });
     const operatorList = new OperatorList();
@@ -1148,6 +1154,7 @@ class PDFDocument {
           globalIdFactory: this._globalIdFactory,
           fontCache: catalog.fontCache,
           builtInCMapCache: catalog.builtInCMapCache,
+          standardFontDataCache: catalog.standardFontDataCache,
           globalImageCache: catalog.globalImageCache,
           nonBlendModesSet: catalog.nonBlendModesSet,
           xfaFactory: this.xfaFactory,
@@ -1170,6 +1177,7 @@ class PDFDocument {
         globalIdFactory: this._globalIdFactory,
         fontCache: catalog.fontCache,
         builtInCMapCache: catalog.builtInCMapCache,
+        standardFontDataCache: catalog.standardFontDataCache,
         globalImageCache: catalog.globalImageCache,
         nonBlendModesSet: catalog.nonBlendModesSet,
         xfaFactory: null,

src/core/evaluator.js

@@ -207,6 +207,7 @@ class PartialEvaluator {
     idFactory,
     fontCache,
     builtInCMapCache,
+    standardFontDataCache,
     globalImageCache,
     options = null,
   }) {
@@ -216,6 +217,7 @@ class PartialEvaluator {
     this.idFactory = idFactory;
     this.fontCache = fontCache;
     this.builtInCMapCache = builtInCMapCache;
+    this.standardFontDataCache = standardFontDataCache;
     this.globalImageCache = globalImageCache;
     this.options = options || DefaultPartialEvaluatorOptions;
     this.parsingType3Font = false;
@@ -390,8 +392,13 @@ class PartialEvaluator {
   }
 
   async fetchStandardFontData(name) {
+    const cachedData = this.standardFontDataCache.get(name);
+    if (cachedData) {
+      return new Stream(cachedData);
+    }
+
     // The symbol fonts are not consistent across platforms, always load the
-    // font data for them.
+    // standard font data for them.
     if (
       this.options.useSystemFonts &&
       name !== "Symbol" &&
@@ -399,31 +406,42 @@ class PartialEvaluator {
     ) {
       return null;
     }
-    const standardFontNameToFileName = getFontNameToFileMap();
-    const filename = standardFontNameToFileName[name];
+
+    const standardFontNameToFileName = getFontNameToFileMap(),
+      filename = standardFontNameToFileName[name];
+    let data;
+
     if (this.options.standardFontDataUrl !== null) {
       const url = `${this.options.standardFontDataUrl}${filename}`;
       const response = await fetch(url);
       if (!response.ok) {
         warn(
-          `fetchStandardFontData failed to fetch file "${url}" with "${response.statusText}".`
+          `fetchStandardFontData: failed to fetch file "${url}" with "${response.statusText}".`
+        );
+      } else {
+        data = await response.arrayBuffer();
+      }
+    } else {
+      // Get the data on the main-thread instead.
+      try {
+        data = await this.handler.sendWithPromise("FetchStandardFontData", {
+          filename,
+        });
+      } catch (e) {
+        warn(
+          `fetchStandardFontData: failed to fetch file "${filename}" with "${e}".`
         );
-        return null;
       }
-      return new Stream(await response.arrayBuffer());
     }
-    // Get the data on the main thread instead.
-    try {
-      const data = await this.handler.sendWithPromise("FetchStandardFontData", {
-        filename,
-      });
-      return new Stream(data);
-    } catch (e) {
-      warn(
-        `fetchStandardFontData failed to fetch file "${filename}" with "${e}".`
-      );
+
+    if (!data) {
+      return null;
     }
-    return null;
+    // Cache the "raw" standard font data, to avoid fetching it repeateadly
+    // (see e.g. issue 11399).
+    this.standardFontDataCache.set(name, data);
+
+    return new Stream(data);
   }
 
   async buildFormXObject(

test/unit/annotation_spec.js

@@ -125,6 +125,7 @@ describe("annotation", function () {
       idFactory: createIdFactory(/* pageIndex = */ 0),
       fontCache: new RefSetCache(),
       builtInCMapCache,
+      standardFontDataCache: new Map(),
     });
   });