Merge pull request #4293 from overleaf/jpa-pdf-js-error-handling

[frontend] fix broken PDF preview caused by missing error handling

GitOrigin-RevId: a7bba8d1b351a53fb20eb670d2ae4c6d215d0d85

services/web/frontend/js/ide/pdfng/directives/pdfJsLoader.js

@@ -18,8 +18,8 @@
  * to customise the loader's options. However the rest of the file is identical
  * to the one provided by PDF.js.
  */
-var pdfjs = require('pdfjs-dist/build/pdf.js')
-var PdfjsWorker = require('pdfjs-dist/build/pdf.worker.js')
+var pdfjs = require('libs/pdfjs-dist/build/pdf.js')
+var PdfjsWorker = require('libs/pdfjs-dist/build/pdf.worker.js')
 
 if (typeof window !== 'undefined' && 'Worker' in window) {
   pdfjs.GlobalWorkerOptions.workerPort = new PdfjsWorker()

services/web/frontend/js/ide/pdfng/directives/pdfRenderer.js

@@ -71,22 +71,23 @@ export default App.factory(
             disableAutoFetch: !!this.options.disableAutoFetch,
             disableStream: !!this.options.disableAutoFetch,
           })
+          this.errorCallback = this.options.errorCallback
+          this.pageSizeChangeCallback = this.options.pageSizeChangeCallback
           this.pdfjs.onProgress = this.options.progressCallback
           this.document = this.pdfjs
           this.navigateFn = this.options.navigateFn
           this.spinner = new pdfSpinner()
           this.resetState()
-          this.document.promise.then(pdfDocument => {
-            return pdfDocument.getDownloadInfo().then(() => {
-              return this.options.loadedCallback()
+          this.document.promise
+            .then(pdfDocument => {
+              return pdfDocument.getDownloadInfo().then(() => {
+                return this.options.loadedCallback()
+              })
+            })
+            .catch(exception => {
+              // error getting document
+              return this.errorCallback(exception)
             })
-          })
-          this.errorCallback = this.options.errorCallback
-          this.pageSizeChangeCallback = this.options.pageSizeChangeCallback
-          this.pdfjs.promise.catch(exception => {
-            // error getting document
-            return this.errorCallback(exception)
-          })
         }
 
         resetState() {
@@ -525,10 +526,12 @@ export default App.factory(
         destroy() {
           this.shuttingDown = true
           this.resetState()
-          return this.pdfjs.promise.then(function (document) {
-            document.cleanup()
-            return document.destroy()
-          })
+          return this.pdfjs.promise
+            .then(function (document) {
+              document.cleanup()
+              return document.destroy()
+            })
+            .catch(() => {})
         }
       }
       PDFRenderer.initClass()

services/web/frontend/js/vendor/libs/pdfjs-dist/CHANGELOG.md

@@ -0,0 +1,52 @@
+# 2021-07-05
+
+For https://github.com/overleaf/issues/issues/4503#issuecomment-873961735
+
+#### Fork base
+
+Based on v2.2.228 (d7afb74a6e1980da5041f376e7a7c7caef5f42ea)
+
+#### Changes:
+
+- fix handling of fetch errors (9826c6eb1ecd501ac3eb1e9d9a98a3e6edde3fd0)
+- do not bundle NodeJS stream backend (6d118ec35e6e6f954938a485178748f1bb8bdd8a)
+
+#### Reproducing of artifacts
+
+- NodeJS v10.23.3 in docker
+- npm v6.14.11 in docker
+- `pdf.js$ npm ci`
+- `pdf.js$ npx gulp generic`
+- `pdf.js$ cp build/generic/build/pdf.* build/generic/LICENSE HERE/build`
+
+#### Testing
+
+PDF.JS does not properly handle network errors for range requests. Any of the initial probe request or following chunk requests can get the editor stuck.
+
+Once any of the requests has failed, the current pdf.js document is stuck and it's (loading) promise never resolves/rejects. This is in turn breaking the frontend cleanup ahead of switching the pdf. New successful compiles will get queued on top of the stuck promise.
+
+https://github.com/overleaf/web-internal/blob/9ed96cd93d3c4d3b23ff223c658ce80bc895484a/frontend/js/ide/pdfng/directives/pdfRenderer.js#L549-L552
+
+https://github.com/overleaf/web-internal/blob/9ed96cd93d3c4d3b23ff223c658ce80bc895484a/frontend/js/ide/pdfng/directives/pdfViewer.js#L46-L47
+
+Steps to reproduce:
+
+### old (and new) logs ui
+
+- set network speed to something very slow (the chrome dev-tools allow custom profiles, set 1kb/s up/down and 1s latency)
+- wait for the compile response to arrive (see new pending requests for log/pdf)
+- trigger a clear cache in another browser tab
+- resume fast network speed
+
+### new logs ui
+
+- open dropdown of (re-)compile button
+- set network speed to something very slow
+- wait for the compile response to arrive (see new pending requests for log/pdf)
+- click re-compile from scratch (which shifts over the stop compile open of the dropdown)
+- resume fast network speed
+
+Alternative reproduction steps involving hacking the ssl-proxy:
+
+- https://digital-science.slack.com/archives/C0216GDEG9L/p1625240302143900
+- https://digital-science.slack.com/archives/C0216GDEG9L/p1625238107141300

services/web/frontend/js/vendor/libs/pdfjs-dist/build/LICENSE

@@ -0,0 +1,177 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS

services/web/frontend/js/vendor/libs/pdfjs-dist/patches/0001-misc-fix-handling-of-fetch-errors-backport.patch

@@ -0,0 +1,67 @@
+From 9826c6eb1ecd501ac3eb1e9d9a98a3e6edde3fd0 Mon Sep 17 00:00:00 2001
+From: Jakob Ackermann <jakob.ackermann@overleaf.com>
+Date: Mon, 5 Jul 2021 16:23:18 +0100
+Subject: [PATCH] [misc] fix handling of fetch errors (backport)
+
+Testing:
+- delete the pdf file while the initial request is inflight
+- delete the pdf file after the initial request has finished
+---
+ src/core/chunked_stream.js  | 8 +++-----
+ src/display/fetch_stream.js | 2 +-
+ 2 files changed, 4 insertions(+), 6 deletions(-)
+
+diff --git a/src/core/chunked_stream.js b/src/core/chunked_stream.js
+index 26a93f673..ab39037c1 100644
+--- a/src/core/chunked_stream.js
++++ b/src/core/chunked_stream.js
+@@ -307,7 +307,7 @@ class ChunkedStreamManager {
+     }
+ 
+     let chunks = [], loaded = 0;
+-    const promise = new Promise((resolve, reject) => {
++    return new Promise((resolve, reject) => {
+       const readChunk = (chunk) => {
+         try {
+           if (!chunk.done) {
+@@ -328,14 +328,12 @@ class ChunkedStreamManager {
+         }
+       };
+       rangeReader.read().then(readChunk, reject);
+-    });
+-    promise.then((data) => {
++    }).then((data) => {
+       if (this.aborted) {
+         return; // Ignoring any data after abort.
+       }
+       this.onReceiveData({ chunk: data, begin, });
+     });
+-    // TODO check errors
+   }
+ 
+   /**
+@@ -384,7 +382,7 @@ class ChunkedStreamManager {
+     for (const groupedChunk of groupedChunksToRequest) {
+       const begin = groupedChunk.beginChunk * this.chunkSize;
+       const end = Math.min(groupedChunk.endChunk * this.chunkSize, this.length);
+-      this.sendRequest(begin, end);
++      this.sendRequest(begin, end).catch(capability.reject);
+     }
+ 
+     return capability.promise;
+diff --git a/src/display/fetch_stream.js b/src/display/fetch_stream.js
+index f70ed1d54..e736c9494 100644
+--- a/src/display/fetch_stream.js
++++ b/src/display/fetch_stream.js
+@@ -222,7 +222,7 @@ class PDFFetchStreamRangeReader {
+       }
+       this._readCapability.resolve();
+       this._reader = response.body.getReader();
+-    });
++    }).catch(this._readCapability.reject);
+ 
+     this.onProgress = null;
+   }
+-- 
+2.17.1
+

services/web/frontend/js/vendor/libs/pdfjs-dist/patches/0002-misc-do-not-bundle-NodeJS-stream-backend.patch

@@ -0,0 +1,30 @@
+From 6d118ec35e6e6f954938a485178748f1bb8bdd8a Mon Sep 17 00:00:00 2001
+From: Jakob Ackermann <jakob.ackermann@overleaf.com>
+Date: Mon, 5 Jul 2021 17:28:00 +0100
+Subject: [PATCH 2/2] [misc] do not bundle NodeJS stream backend
+
+---
+ src/pdf.js | 7 +------
+ 1 file changed, 1 insertion(+), 6 deletions(-)
+
+diff --git a/src/pdf.js b/src/pdf.js
+index 4ccf2c1a7..7058c7a46 100644
+--- a/src/pdf.js
++++ b/src/pdf.js
+@@ -32,12 +32,7 @@ let pdfjsDisplayAPICompatibility = require('./display/api_compatibility.js');
+ 
+ if (typeof PDFJSDev === 'undefined' || PDFJSDev.test('GENERIC')) {
+   const isNodeJS = require('./shared/is_node.js');
+-  if (isNodeJS()) {
+-    let PDFNodeStream = require('./display/node_stream.js').PDFNodeStream;
+-    pdfjsDisplayAPI.setPDFNetworkStreamFactory((params) => {
+-      return new PDFNodeStream(params);
+-    });
+-  } else {
++  if (!isNodeJS()) {
+     let PDFNetworkStream = require('./display/network.js').PDFNetworkStream;
+     let PDFFetchStream;
+     if (pdfjsDisplayDisplayUtils.isFetchSupported()) {
+-- 
+2.17.1
+