Page Menu
Home
c4science
Search
Configure Global Search
Log In
Files
F91581735
bibclassify.in
No One
Temporary
Actions
Download File
Edit File
Delete File
View Transforms
Subscribe
Mute Notifications
Award Token
Subscribers
None
File Metadata
Details
File Info
Storage
Attached
Created
Tue, Nov 12, 10:21
Size
1 KB
Mime Type
text/x-python
Expires
Thu, Nov 14, 10:21 (1 d, 23 h)
Engine
blob
Format
Raw Data
Handle
22286638
Attached To
R3600 invenio-infoscience
bibclassify.in
View Options
#!@PYTHON@
## -*- mode: python; coding: utf-8; -*-
##
## This file is part of the CERN Document Server Software (CDSware).
## Copyright (C) 2002, 2003, 2004, 2005, 2006 CERN.
##
## The CDSware is free software; you can redistribute it and/or
## modify it under the terms of the GNU General Public License as
## published by the Free Software Foundation; either version 2 of the
## License, or (at your option) any later version.
##
## The CDSware is distributed in the hope that it will be useful, but
## WITHOUT ANY WARRANTY; without even the implied warranty of
## MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
## General Public License for more details.
##
## You should have received a copy of the GNU General Public License
## along with CDSware; if not, write to the Free Software Foundation, Inc.,
## 59 Temple Place, Suite 330, Boston, MA 02111-1307, USA.
"""CDSware BibClassify.
It extracts keywords from a pdf or text file based on a thesaurus.
Usage: bibclassify [options]
Examples:
bibclassify -f file.pdf -k thesaurus.txt -o TEXT
bibclassify -t file.txt -K ontology.rdf -m SLOW
Specific options:
-f, --pdffile=FILENAME name of the pdf file to be classified
-t, --textfile=FILENAME name of the text file to be classified
-k, --thesaurus=FILENAME name of the text thesaurus (taxonomy)
-K, --ontology=FILENAME name of the RDF or OWL ontology (experimental)
-o, --output=HTML|TEXT output list of keywords in either HTML or text
-n, --nkeywords=NUMBER max number of keywords to be found
-m, --mode=FAST|SLOW processing mode: FAST (run on abstract and selected pages), SLOW (run on whole document - more accurate)
General options:
-h, --help print this help and exit
-V, --version print version and exit
"""
try:
import sys
from cdsware.bibclassifylib import main
except ImportError, e:
print "Error: %s" % e
import sys
sys.exit(1)
main()
Event Timeline
Log In to Comment