[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Page MenuHomePhabricator

Error creating PDF on Commons: "convert: no decode delegate for this image format" (fixed in GS 9.07)
Closed, ResolvedPublic

Description

David Cuenca reports on mediawiki-l that a PDF from Google docs does not render on Commons. See http://thread.gmane.org/gmane.org.wikimedia.mediawiki/41507 for his message.

The PDF's URL is: https://commons.wikimedia.org/wiki/File:Interproject_links_tabbed_interface_proposal_presentation.pdf

Visiting a thumbnail's URL (https://upload.wikimedia.org/wikipedia/commons/thumb/3/3b/Interproject_links_tabbed_interface_proposal_presentation.pdf/page1-800px-Interproject_links_tabbed_interface_proposal_presentation.pdf.jpg) reveals the following error message:

Error generating thumbnail

Error creating thumbnail: convert: no decode delegate for this image format `/tmp/magick-STzEaZl6' @ error/constitute.c/ReadImage/532.
convert: missing an image filename `/tmp/transform_d32a7a881ee9-1.jpg' @ error/convert.c/ConvertImageCommand/3011.


Version: unspecified
Severity: normal

Event Timeline

bzimport raised the priority of this task from to Low.Nov 22 2014, 1:32 AM
bzimport set Reference to bz48007.
bzimport added a subscriber: Unknown Object (MLST).

Same error for https://commons.wikimedia.org/wiki/File:Cox_and_box.pdf

Error creating thumbnail: convert: no decode delegate for this image format `/tmp/magick-09CMSXr6' @ error/constitute.c/ReadImage/532.
convert: missing an image filename `/tmp/transform_85fdac282e66-1.jpg' @ error/convert.c/ConvertImageCommand/3011.

Split from list in bug 41665 comment 2

Ghostscript not liking the file.

bawolff@Bawolff-L:~$ gs Interproject_links_tabbed_interface_proposal_presentation.pdf
GPL Ghostscript 8.71 (2010-02-10)
Copyright (C) 2010 Artifex Software, Inc. All rights reserved.
This software comes with NO WARRANTY: see the file PUBLIC for details.
Processing pages 1 through 14.
Page 1
Error: /rangecheck in --run--
Operand stack:

--dict:8/17(L)--

Execution stack:

%interp_exit   .runexec2   --nostringval--   --nostringval--   --nostringval--   2   %stopped_push   --nostringval--   --nostringval--   --nostringval--   false   1   %stopped_push   1878   1   3   %oparray_pop   1877   1   3   %oparray_pop   1861   1   3   %oparray_pop   --nostringval--   --nostringval--   2   1   14   --nostringval--   %for_pos_int_continue   --nostringval--   --nostringval--   false   1   %stopped_push   --nostringval--   --nostringval--

Dictionary stack:

--dict:1153/1684(ro)(G)--   --dict:1/20(G)--   --dict:75/200(L)--   --dict:75/200(L)--   --dict:108/127(ro)(G)--   --dict:290/300(ro)(G)--   --dict:22/25(L)--   --dict:6/8(L)--   --dict:21/40(L)--   --dict:1/1(ro)(G)--   --dict:1/1(ro)(G)--   --dict:1/1(ro)(G)--   --dict:5/5(L)--

Current allocation mode is local
Last OS error: 11
GPL Ghostscript 8.71: Unrecoverable error, exit code 1

otoh, ImageMagick seemed to be ok locally when I tried convert.

bawolff@Bawolff-L:~$ convert --version
Version: ImageMagick 6.6.0-4 2010-11-16 Q16 http://www.imagemagick.org
Copyright: Copyright (C) 1999-2010 ImageMagick Studio LLC
Features: OpenMP


So possibly something that could be fixed on update.

Upstream ticket closed as INVALID: "Please try the current version of Ghostscript and, if the problem persists, reopen the bug report."

Cannot reproduce the problem with 9.07 on Fedora 19:

$:andre\> gs ~/Desktop/Interproject_links_tabbed_interface_proposal_presentation.pdf
GPL Ghostscript 9.07 (2013-02-14)
Copyright (C) 2012 Artifex Software, Inc. All rights reserved.
This software comes with NO WARRANTY: see the file PUBLIC for details.
Processing pages 1 through 14.
Page 1

showpage, press <return> to continue<<

[...]
Page 14

showpage, press <return> to continue<<

GS>quit
$:andre\>

I apologize, I should have mentioned my version of ghostscript is insanely old. I imagine the version on production is fairly old to.

I guess this puts this ticket in ops territory - upgrade ghostscript and/or image magick

(In reply to comment #8)

Could you please fix this bug? Thanks, Yann

See comment 6 and comment 7. Fixing the PDF file instead should be easier.

https://commons.wikimedia.org/wiki/File:Jaur%C3%A8s_-_De_la_realite_du_monde_sensible.pdf

There is no problem displaying this file locally (AReader XI), so I don't understand your answer. Regards, Yann

Well, corrupt JPX streams might still be parseable by Adobe's decoder...

$:andre\> gs Jaurès_-_De_la_realite_du_monde_sensible.pdf
GPL Ghostscript 9.10 (2013-08-30)
Copyright (C) 2013 Artifex Software, Inc. All rights reserved.
This software comes with NO WARRANTY: see the file PUBLIC for details.
Processing pages 1 through 450.
Page 1

  • ERROR: Unable to process JPXDecode data. Page will be missing data.
  • ERROR: Unable to process JPXDecode data. Page will be missing data.

https://upload.wikimedia.org/wikipedia/commons/thumb/0/08/FastCCI_-_Taming_the_Commons_Category_Tree.pdf/page1-200px-FastCCI_-_Taming_the_Commons_Category_Tree.pdf.jpg?blah

Error generating thumbnail

Error creating thumbnail: **** Error reading a content stream. The page may be incomplete.
convert: no decode delegate for this image format `/tmp/magick-2P3awEZB' @ error/constitute.c/ReadImage/532.
convert: missing an image filename `/tmp/transform_bec33f9bb3e6-1.jpg' @ error/convert.c/ConvertImageCommand/3011.

daniel wrote:

The file in the comment above was created by printing to PDF from Google chrome on Mac. It does not strike me as a fringe issue.

All of the linked files except for the last one thumbnail correctly for me. We're running Ghostscript 9.10 in production these days.

https://upload.wikimedia.org/wikipedia/commons/thumb/0/08/FastCCI_-_Taming_the_Commons_Category_Tree.pdf/page1-200px-FastCCI_-_Taming_the_Commons_Category_Tree.pdf.jpg?blah

Error generating thumbnail

Error creating thumbnail: **** Error reading a content stream. The page may be incomplete.
convert: no decode delegate for this image format `/tmp/magick-2P3awEZB' @ error/constitute.c/ReadImage/532.
convert: missing an image filename `/tmp/transform_bec33f9bb3e6-1.jpg' @ error/convert.c/ConvertImageCommand/3011.

This looks like a different error message, and funnily only appears for the first page on the PDF. Filed as T110852.

matmarex set Security to None.

Is this another bug?

Yes - see the error messages you get for those thumbnails.

FYI I have this error message on some PDF scans (on a private wiki). The issue is with Ghostscript 9.26, who writes the following error message at the beginning of the file (before the JPEG real content):

**** Error: stream operator isn't terminated by valid EOL.
            Output may be incorrect.

The user-displayed error is ImageMagick who does not understand the JPEG image (which is normal). Hence it is not a MediaWiki or an ImageMagick issue, but a Ghostscript’s one. If I find something useful to solve it, I will report it here if anyone else has this issue in the recent days.

ubtuntu 16.04
imagemagick: Version: ImageMagick 6.8.9-9 Q16 x86_64 2018-09-28
ghostscript: 9.26

i have the same issue. on a private wiki a client uploaded a pdf scanned with an HP laserjet. the error message i get is

no decode delegate for this image format `' @ error/constitute.c/ReadImage/501. convert: no images defined `/tmp/transform_82d28da241a8.jpg' @ error/convert.c/ConvertImageCommand/3210.

gs also outputs the same error as mentioned above by @Seb35; imagemagick does too during conversion.

i ran

convert pdffile.pdf test.jpg && identify test-0.jpg | grep "corrupt"

with no console output which shows that the image generated is valid jpg, right?

NB: locally i tested with gs 9.26 and ImageMagick 6.9.9-38 Q16 x86_64 and no error was printed; i did not test this setting on the wiki server

i ran

convert pdffile.pdf test.jpg && identify test-0.jpg | grep "corrupt"

with no console output which shows that the image generated is valid jpg, right?

Did you attempt to view the file?

yes i did. i didn't recognize anything wrong with the image file. i used gnome's image viewer.

so here's a reproducable case.

  • os: alpine 3.8
  • mediawiki 1.32.1
  • php 7.2.18 (fpm-fcgi)
  • extension: pdf handler (img preview works with other files, e.g. the cox and box.pdf linked above)
  • $wgMaxShellMemory = 0;
  • $wgMaxShellTime = 0;
  • gs 9.26
  • imagemagick 7.0.8-38 Q16 x86_64 2019-04-15

after running (see SO)

pdftocairo -pdf corrupt.pdf repaired.pdf

gs parsed the pdf correctly and the pdf preview worked;

I reopen this task with a better proposed resolution, and possibly also solving T110852 if still opened (according to the quick description in T50007#1588117).

These errors comes from /usr/share/ghostscript/*/Resource/Init/pdf_base.ps and possibly other files (search your error message in this directory). I opened an upstream bug with your file @Schtom , but it was closed WONTFIX with the advice not using a pipe and I found in the meantime the following detail in the documentation.

Ghostscript documentation says:

To redirect stdout to stderr use -sstdout=%stderr

I propose to add this parameter in PdfHandler.php. The upstream team advices to put this parameter *after* -sStdoutFile=- (see the upstream bug).

Change 545296 had a related patch set uploaded (by Seb35; owner: Seb35):
[mediawiki/extensions/PdfHandler@master] Send ghostscript errors to stderr instead of stdout

https://gerrit.wikimedia.org/r/545296

We are also having this issue on a private wiki.

Hi @PhotographerTom. The task summary says "(fixed in GS 9.07)". Which version of GhostScript are you using on your private wiki?
Did you apply the patch by Seb35 linked above?

Change 545296 merged by jenkins-bot:
[mediawiki/extensions/PdfHandler@master] Send ghostscript errors to stderr instead of stdout

https://gerrit.wikimedia.org/r/545296

This has been fixed either via the patch in this task and/or via the patch in T236240.