Created
October 24, 2012 11:36
-
-
Save bloomonkey/3945599 to your computer and use it in GitHub Desktop.
Revisions
-
bloomonkey revised this gist
Oct 24, 2012 . 1 changed file with 3 additions and 0 deletions.There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode charactersOriginal file line number Diff line number Diff line change @@ -67,15 +67,18 @@ def get_outputStream(options): def printSubjectURIs(options, args): # Put the subject into a query string if options.components: qString = 'dc.subject exact "{0}"'.format(' '.join(args[1:])) else: qString = 'dc.subject exact "{0}" and ead.istoplevel=1'.format(' '.join(args[1:])) # Parse the query CQL into a Query object try: q = qf.get_query(session, qString) except: session.logger.log_error(session, "Invalid CQL: {0}".format(qString)) return 1 # Search the database with the Query resultSet = db.search(session, q) unitidWf = db.get_object(session, 'unitidIdentifierWorkflow') # Get the output stream (usually file or stdout) -
bloomonkey revised this gist
Oct 24, 2012 . 1 changed file with 9 additions and 3 deletions.There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode charactersOriginal file line number Diff line number Diff line change @@ -76,13 +76,19 @@ def printSubjectURIs(options, args): except: session.logger.log_error(session, "Invalid CQL: {0}".format(qString)) return 1 resultSet = db.search(session, q) unitidWf = db.get_object(session, 'unitidIdentifierWorkflow') # Get the output stream (usually file or stdout) with get_outputStream(options) as outStream: # Iterate through all results in resultSet for result in resultSet: # Fetch the Record in EAD schema rec = result.fetch_record(session, schema='ead') # Use a Workflow to return the <unitid> based identifier new_id = unitidWf.process(session, rec) # Assemble the URI uri = "{0}/{1}".format(baseDataUri, new_id) # Write the URI to the output stream outStream.write(uri + '\n') return 0 -
bloomonkey revised this gist
Oct 24, 2012 . 1 changed file with 1 addition and 1 deletion.There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode charactersOriginal file line number Diff line number Diff line change @@ -83,7 +83,7 @@ def printSubjectURIs(options, args): rec = rsi.fetch_record(session, schema='ead') new_id = unitidWf.process(session, rec) uri = "{0}/{1}".format(baseDataUri, new_id) outStream.write(uri + '\n') return 0 -
bloomonkey revised this gist
Oct 24, 2012 . 1 changed file with 2 additions and 2 deletions.There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode charactersOriginal file line number Diff line number Diff line change @@ -68,9 +68,9 @@ def get_outputStream(options): def printSubjectURIs(options, args): if options.components: qString = 'dc.subject exact "{0}"'.format(' '.join(args[1:])) else: qString = 'dc.subject exact "{0}" and ead.istoplevel=1'.format(' '.join(args[1:])) try: q = qf.get_query(session, qString) except: -
bloomonkey revised this gist
Oct 24, 2012 . 1 changed file with 1 addition and 1 deletion.There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode charactersOriginal file line number Diff line number Diff line change @@ -46,7 +46,7 @@ def __init__(self, **kwargs): self.add_option( "-c", "--components", dest="components", action="store_true", default=False, help="Include component URIs" -
bloomonkey revised this gist
Oct 24, 2012 . 1 changed file with 2 additions and 1 deletion.There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode charactersOriginal file line number Diff line number Diff line change @@ -7,6 +7,7 @@ import sys import os from contextlib import contextmanager from optparse import OptionParser cheshirePath = os.environ.get('C3HOME', os.path.expanduser('~/cheshire3')) @@ -99,4 +100,4 @@ def printSubjectURIs(options, args): if __name__ == '__main__': (options, args) = option_parser.parse_args(sys.argv) sys.exit(printSubjectURIs(options, args)) -
bloomonkey created this gist
Oct 24, 2012 .There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode charactersOriginal file line number Diff line number Diff line change @@ -0,0 +1,102 @@ """Generate Archives Hub URIs for records matching a given subject. Usage: %prog [options] subject """ import sys import os from optparse import OptionParser cheshirePath = os.environ.get('C3HOME', os.path.expanduser('~/cheshire3')) # Hack sys.path to look for over-ridden cheshire3 modules sys.path.insert(1, os.path.join(cheshirePath, 'cheshire3', 'code')) # Cheshire3 imports from cheshire3.baseObjects import Session from cheshire3.server import SimpleServer # Build environment... session = Session() serv = SimpleServer(session, os.path.join(cheshirePath, 'cheshire3', 'configs', 'serverConfig.xml') ) class MyOptionParser(OptionParser): """Custom option parser for outputting list of record URIs.""" def __init__(self, **kwargs): OptionParser.__init__(self, **kwargs) # Options self.add_option( "-o", "--output", dest="outfile", default=None, help=" ".join(["Write output to OUTFILE.", "If omitted output will be printed to STDOUT."]), metavar="OUTFILE" ) self.add_option( "-c", "--components", dest="component", action="store_true", default=False, help="Include component URIs" ) @contextmanager def get_outputStream(options): """Context manager for appropriate output stream based on given options.""" if options.outfile is not None: f = open(os.path.abspath(options.outfile), 'w') try: yield f finally: f.close() else: yield sys.stdout def printSubjectURIs(options, args): if options.components: qString = "dc.subject exact {0}".format(' '.join(args[1:])) else: qString = "dc.subject exact {0} and ead.istoplevel=1".format(' '.join(args[1:])) try: q = qf.get_query(session, qString) except: session.logger.log_error(session, "Invalid CQL: {0}".format(qString)) return 1 rs = db.search(session, q) unitidWf = db.get_object(session, 'unitidIdentifierWorkflow') with get_outputStream(options) as outStream: for rsi in rs: rec = rsi.fetch_record(session, schema='ead') new_id = unitidWf.process(session, rec) uri = "{0}/{1}".format(baseDataUri, new_id) outStream.write(uri) return 0 db = serv.get_object(session, 'db_hub') session.database = db.id session.logger = db.get_path(session, 'defaultLogger') qf = db.get_object(session, 'defaultQueryFactory') hubBaseUrl = 'http://archiveshub.ac.uk' apacheDataUrl = '/data' baseDataUri = '{0}{1}'.format(hubBaseUrl, apacheDataUrl) option_parser = MyOptionParser() if __name__ == '__main__': (options, args) = option_parser.parse_args(sys.argv) sys.exit(printSubjectURIs(options, args))