From 849d8cfa2440812e8deff61a93c72727e7d9e0d5 Mon Sep 17 00:00:00 2001
From: Rob Wu <rob@robwu.nl>
Date: Sun, 18 Jun 2017 12:57:17 +0200
Subject: [PATCH 1/2] Improve memory-efficiency of DOMElement_toString in
 domstubs

Test case:
Using the PDF file from https://github.com/mozilla/pdf.js/issues/8534
node --max_old_space_size=200 examples/node/pdf2svg.js /tmp/FatalProcessOutOfMemory.pdf

Before this patch:
Node.js crashes due to OOM after processing 10 pages.

After this patch:
Node.js crashes due to OOM after processing 19 pages.
---
 examples/node/domstubs.js | 29 ++++++++++++++++-------------
 1 file changed, 16 insertions(+), 13 deletions(-)

diff --git a/examples/node/domstubs.js b/examples/node/domstubs.js
index ce4dc7890..d746b0051 100644
--- a/examples/node/domstubs.js
+++ b/examples/node/domstubs.js
@@ -91,24 +91,27 @@ DOMElement.prototype = {
   },
 
   toString: function DOMElement_toString() {
-    var attrList = [];
-    for (i in this.attributes) {
-      attrList.push(i + '="' + xmlEncode(this.attributes[i]) + '"');
+    var buf = [];
+    buf.push('<' + this.nodeName);
+    if (this.nodeName === 'svg:svg') {
+      buf.push(' xmlns:xlink="http://www.w3.org/1999/xlink"' +
+               ' xmlns:svg="http://www.w3.org/2000/svg"');
+    }
+    for (var i in this.attributes) {
+      buf.push(' ' + i + '="' + xmlEncode(this.attributes[i]) + '"');
     }
 
+    buf.push('>');
+
     if (this.nodeName === 'svg:tspan' || this.nodeName === 'svg:style') {
-      var encText = xmlEncode(this.textContent);
-      return '<' + this.nodeName + ' ' + attrList.join(' ') + '>' +
-             encText + '</' + this.nodeName + '>';
-    } else if (this.nodeName === 'svg:svg') {
-      var ns = 'xmlns:xlink="http://www.w3.org/1999/xlink" ' +
-               'xmlns:svg="http://www.w3.org/2000/svg"'
-      return '<' + this.nodeName + ' ' + ns + ' ' + attrList.join(' ') + '>' +
-             this.childNodes.join('') + '</' + this.nodeName + '>';
+      buf.push(xmlEncode(this.textContent));
     } else {
-      return '<' + this.nodeName + ' ' + attrList.join(' ') + '>' +
-             this.childNodes.join('') + '</' + this.nodeName + '>';
+      this.childNodes.forEach(function(childNode) {
+        buf.push(childNode.toString());
+      });
     }
+    buf.push('</' + this.nodeName + '>');
+    return buf.join('');
   },
 
   cloneNode: function DOMElement_cloneNode() {

From 0cc173580934c3420ab3f1bf5d2dbe67e8e4599c Mon Sep 17 00:00:00 2001
From: Rob Wu <rob@robwu.nl>
Date: Sun, 18 Jun 2017 12:58:53 +0200
Subject: [PATCH 2/2] Reduce concurrent memory footprint of pdf2svg.js

Wait for the completion of writing the generated SVG file before
processing the next page. This is to enable the garbage collector to
garbage-collect the (potentially large) SVG string before trying to
allocate memory again for the next page.

Note that since the PDF-to-SVG conversion is now sequential instead of
parallel, the time to generate all pages increases.

Test case:
node --max_old_space_size=200 examples/node/pdf2svg.js /tmp/FatalProcessOutOfMemory.pdf

Before this patch:
- Node.js crashes due to OOM after processing 20 pages.

After this patch:
- Node.js is able to convert all 203 PDFs to SVG without crashing.
---
 examples/node/pdf2svg.js | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

diff --git a/examples/node/pdf2svg.js b/examples/node/pdf2svg.js
index 7edf5df32..de2b6c56b 100644
--- a/examples/node/pdf2svg.js
+++ b/examples/node/pdf2svg.js
@@ -18,7 +18,7 @@ var pdfPath = process.argv[2] || '../../web/compressed.tracemonkey-pldi-09.pdf';
 var data = new Uint8Array(fs.readFileSync(pdfPath));
 
 // Dumps svg outputs to a folder called svgdump
-function writeToFile(svgdump, pageNum) {
+function writeToFile(svgdump, pageNum, callback) {
   var name = getFileNameFromPath(pdfPath);
   fs.mkdir('./svgdump/', function(err) {
     if (!err || err.code === 'EEXIST') {
@@ -29,7 +29,10 @@ function writeToFile(svgdump, pageNum) {
           } else {
             console.log('Page: ' + pageNum);
           }
+          callback();
         });
+    } else {
+      callback();
     }
   });
 }
@@ -67,7 +70,9 @@ pdfjsLib.getDocument({
         svgGfx.embedFonts = true;
         return svgGfx.getSVG(opList, viewport).then(function (svg) {
           var svgDump = svg.toString();
-          writeToFile(svgDump, pageNum);
+          return new Promise(function(resolve) {
+            writeToFile(svgDump, pageNum, resolve);
+          });
         });
       });
     })