From a3d196fe396bb04d363f0c27bcd2523ef1e85ba7 Mon Sep 17 00:00:00 2001 From: yarikoptic Date: Thu, 7 May 2020 21:07:28 +0000 Subject: [PATCH] original complaint about filenames obfuscated by addurl --- ...d_be_taken_as_is_without_obfuscation_.mdwn | 47 +++++++++++++++++++ 1 file changed, 47 insertions(+) create mode 100644 doc/bugs/addurl__58___content-disposition_field_should_be_taken_as_is_without_obfuscation_.mdwn diff --git a/doc/bugs/addurl__58___content-disposition_field_should_be_taken_as_is_without_obfuscation_.mdwn b/doc/bugs/addurl__58___content-disposition_field_should_be_taken_as_is_without_obfuscation_.mdwn new file mode 100644 index 0000000000..390160b92d --- /dev/null +++ b/doc/bugs/addurl__58___content-disposition_field_should_be_taken_as_is_without_obfuscation_.mdwn @@ -0,0 +1,47 @@ +### Please describe the problem. + +Original complaints could be found mentioned in the comments of the [importfeed page](https://git-annex.branchable.com/git-annex-importfeed/): when using `addurl`, and even when the server provides Content-Disposition field with the filename, git-annex seems (BTW -- no Content-Disposition was mentioned in the --debug output) to take that filename value and obfuscates it (replaces '-' with '_' etc) to what supposed to be the original filename. + + +[[!format sh """ +$> mkdir /tmp/testrepo; cd /tmp/testrepo; git init; git annex init; +mkdir: cannot create directory ‘/tmp/testrepo’: File exists +E: could not determine git repository root +Initialized empty Git repository in /tmp/testrepo/.git/ +init ok +(recording state in git...) + +$> git annex addurl --fast https://girder.dandiarchive.org/api/v1/item/5e9f9588b5c9745bad9f58ff/download +addurl https://girder.dandiarchive.org/api/v1/item/5e9f9588b5c9745bad9f58ff/download (to sub_mouse_AAYYT_ses_20180420_sample_2_slice_20180420_slice_2_cell_20180420_sample_2.nwb) ok +(recording state in git...) + +$> ls -l +total 4 +lrwxrwxrwx 1 yoh yoh 184 May 7 17:02 sub_mouse_AAYYT_ses_20180420_sample_2_slice_20180420_slice_2_cell_20180420_sample_2.nwb -> .git/annex/objects/Gj/9z/URL-s9335000--https&c%%girder.dandiarchive.org-48163bc503cb7181516be86ef215f923/URL-s9335000--https&c%%girder.dandiarchive.org-48163bc503cb7181516be86ef215f923 +"""]]] + +whenever original content-disposition was having "-" in the filename, which are perfectly safe the filename AFAIK: + +[[!format sh """ +$> wget -S https://girder.dandiarchive.org/api/v1/item/5e9f9588b5c9745bad9f58ff/download +... bunch of forwards to the final one with the content disposition field +Resolving dandiarchive.s3.amazonaws.com (dandiarchive.s3.amazonaws.com)... 52.219.101.51 +Connecting to dandiarchive.s3.amazonaws.com (dandiarchive.s3.amazonaws.com)|52.219.101.51|:443... connected. +HTTP request sent, awaiting response... + HTTP/1.1 200 OK + x-amz-id-2: VgJE1jV5XUkBQXZDWgR5WEDfmHJp4Fj6fGo6z2tYkLfyTsxDWC+m92B2qOSVppCuiRFu2QpNV5M= + x-amz-request-id: 1221CAC30E3931CF + Date: Thu, 07 May 2020 21:02:52 GMT + Last-Modified: Wed, 22 Apr 2020 00:54:32 GMT + ETag: "acf3b4f5951435245a0efcd4a518e77d" + Content-Disposition: attachment; filename="sub-mouse-AAYYT_ses-20180420-sample-2_slice-20180420-slice-2_cell-20180420-sample-2.nwb" +... + +$> git annex version +git-annex version: 7.20190708+git9-gfa3524b95-1~ndall+1 + +"""]] + + +[[!meta author=yoh]] +[[!tag projects/dandi]]