Mercurial > hg > sworduploader

changeset 15:e24aea2d14a4

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
- v0.6: use server.cfg, maintain dir structure with dir upload
author Marco Fabiani <marco.fabiani@eecs.qmul.ac.uk>
date Tue, 29 May 2012 11:55:26 +0100
parents 273fc80d9623
children 8b69bba225c9
files README server.cfg sworduploader.py
diffstat 3 files changed, 29 insertions(+), 12 deletions(-) [+]
line wrap: on
line diff
--- a/README	Fri May 25 13:14:05 2012 +0100
+++ b/README	Tue May 29 11:55:26 2012 +0100
@@ -20,6 +20,7 @@
 Installation:
 
 - no installation required, simply copy the script sworduploader.py to a suitable location. The first time you run the script, it will create the sword2_logging.conf file.
+- a server.cfg file is also available. If the --servicedoc option is not used, sworduploader will read the first line of server.cfg and use it as the server's URL. If the server.cfg is missing, it will default to C4DM's server.
 
 -----------------------------------------------
 Usage:
@@ -40,17 +41,17 @@
 optional arguments:
   -h, --help            show this help message and exit
   --username USER_NAME  DSpace username.
-  --zip                 If "data" is a directory, compress it and post it as a
-                        single file. The zip file will be saved along with the
-                        individual files.
   --title TITLE         Title (ignored for METS packages).
   --author AUTHOR [AUTHOR ...]
                         Author(s) (ignored for METS packages). Accepts
                         multiple entries in the format "Surname, Name"
   --date DATE           Date of creation (string) (ignored for METS packages).
-  --servicedoc DSPACEURL
-                        Url of the SWORDv2 service document (default:
-                        http://c4dm.eecs.qmul.ac.uk/rdr/swordv2/servicedocument
+  --zip                 If "data" is a directory, compress it and post it as a
+                        single file. The zip file will be saved along with the
+                        individual files.
+  --servicedoc SD  		Url of the SWORDv2 service document (default: use
+                        server.cfg if available, otherwise http://c4dm.eecs.qm
+                        ul.ac.uk/rdr/swordv2/servicedocument
 
 If the submission is created successfully, it will remain open to be completed
 with the necessary metadata and licenses, using the DSpace web interface. The
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/server.cfg	Tue May 29 11:55:26 2012 +0100
@@ -0,0 +1,1 @@
+http://c4dm.eecs.qmul.ac.uk/rdr/swordv2/servicedocument
\ No newline at end of file
--- a/sworduploader.py	Fri May 25 13:14:05 2012 +0100
+++ b/sworduploader.py	Tue May 29 11:55:26 2012 +0100
@@ -2,10 +2,10 @@
 
 """
 
-SWORD2 DSpace bulk uploader - v0.5
+SWORD2 DSpace bulk uploader - v0.6
 
 A python script to submit large numbers of files to a SWORD2-compatible repository, specifically DSpace 1.8x.
-Built on the SWORD2 python client library: https://bitbucket.org/beno/python-sword2/overview with modifications.
+Built on the SWORD2 python client library: https://github.com/swordapp/python-client-sword2.
 
 Dependencies:
 
@@ -14,6 +14,13 @@
 - sword2 library: https://github.com/swordapp/python-client-sword2 
 
 -----------------------------------
+Updates log:
+
+v0.6: 	- now uploading a directory will also maintain the path structure
+		- introduced a file where to specify the server (server.cfg)
+v0.5: changed the default server to C4DM live server
+
+-----------------------------------
   Centre for Digital Music, Queen Mary, University of London
   Copyright (c) 2012 Marco Fabiani
 
@@ -53,7 +60,7 @@
 parser.add_argument("--author", dest="author", type=str,nargs="+", help="Author(s) (ignored for METS packages). Accepts multiple entries in the format \"Surname, Name\"")
 parser.add_argument("--date", dest="date", type=str,nargs=1, help="Date of creation (string) (ignored for METS packages).")
 parser.add_argument("--zip", action="store_true",dest="zip",default=False, help="If \"data\" is a directory, compress it and post it as a single file. The zip file will be saved along with the individual files.")
-parser.add_argument("--servicedoc", dest="sd", type=str,nargs=1, help="Url of the SWORDv2 service document (default: http://c4dm.eecs.qmul.ac.uk/smdmrd-test/swordv2/servicedocument")
+parser.add_argument("--servicedoc", dest="sd", type=str,nargs=1, help="Url of the SWORDv2 service document (default: use server.cfg if available, otherwise http://c4dm.eecs.qmul.ac.uk/rdr/swordv2/servicedocument")
 
 args = parser.parse_args()
 data = args.data[0]
@@ -63,7 +70,12 @@
 	storezip = False
 
 if args.sd == None:
-	sd = "http://c4dm.eecs.qmul.ac.uk/rdr/swordv2/servicedocument"
+	try:
+		f = open("server.cfg", "r")
+		sd = f.readline()
+		print "server.cfg: ", sd
+	except:
+		sd = "http://c4dm.eecs.qmul.ac.uk/rdr/swordv2/servicedocument"
 else:
 	sd = args.sd[0]
 
@@ -192,12 +204,15 @@
 				creation_receipt = c.create(col_iri = collection.href, metadata_entry = entry, in_progress=True)
 				
 				# Add the files
+				# Get the longest common path in order to send the correct filename to keep the structure
+				common = os.path.commonprefix(fileslist)
 				for f in fileslist:
-					print "Uploading file ",os.path.basename(f)
+					filename = os.path.relpath(f,common)
+					print "Uploading file ", filename
 					payload = open(f,"rb")
 					deposit_receipt = c.add_file_to_resource(edit_media_iri = creation_receipt.edit_media,
 						payload = payload,
-						filename = os.path.basename(f),
+						filename = filename,
 						mimetype = 'application/zip',
 						packaging = 'http://purl.org/net/sword/package/Binary')
 					payload.close()