def command(cls, config_ini, cache_dir, delete_files):
common.load_config(config_ini)
common.register_translator()
#rev = model.repo.new_revision()
#rev.author = 'fix_secondary_theme.py'
files_to_delete = []
count = 0
for f in glob.iglob(os.path.join(cache_dir, '*/*/*')):
a = model.Session.query(Archival).filter(
Archival.cache_filepath == f).first()
size = os.path.getsize(f)
if a == None:
print stats.add('Not in archival table', f.decode('utf8'),
size)
files_to_delete.append(f)
else:
res = model.Resource.get(a.resource_id)
if not res:
print stats.add('No matching resouce', f.decode('utf8'),
size)
files_to_delete.append(f)
elif res.state == 'deleted':
print stats.add('Resource is deleted', f.decode('utf8'),
size)
files_to_delete.append(f)
else:
pkg = res.resource_group.package
if pkg.state == 'deleted':
print stats.add('Package is deleted', f.decode('utf8'),
size)
files_to_delete.append(f)
else:
stats.add('OK', f.decode('utf8'), size)
count += 1
if count % 250 == 0:
print '\n\nProgress after %s:' % count
print stats.report()
print stats.report()
if delete_files:
print 'Deleting %s files' % len(files_to_delete)
for f in files_to_delete:
try:
os.unlink(f)
except OSError:
print stats.add('ERROR Deleting', f.decode('utf8'), 0)
print 'Done'
def command(cls, config_ini, cache_dir, delete_files):
common.load_config(config_ini)
common.register_translator()
#rev = model.repo.new_revision()
#rev.author = 'fix_secondary_theme.py'
files_to_delete = []
count = 0
for f in glob.iglob(os.path.join(cache_dir, '*/*/*')):
a = model.Session.query(Archival).filter(Archival.cache_filepath==f).first()
size = os.path.getsize(f)
if a == None:
print stats.add('Not in archival table', f.decode('utf8'), size)
files_to_delete.append(f)
else:
res = model.Resource.get(a.resource_id)
if not res:
print stats.add('No matching resouce', f.decode('utf8'), size)
files_to_delete.append(f)
elif res.state == 'deleted':
print stats.add('Resource is deleted', f.decode('utf8'), size)
files_to_delete.append(f)
else:
pkg = res.resource_group.package
if pkg.state == 'deleted':
print stats.add('Package is deleted', f.decode('utf8'), size)
files_to_delete.append(f)
else:
stats.add('OK', f.decode('utf8'), size)
count += 1
if count % 250 == 0:
print '\n\nProgress after %s:' % count
print stats.report()
print stats.report()
if delete_files:
print 'Deleting %s files' % len(files_to_delete)
for f in files_to_delete:
try:
os.unlink(f)
except OSError:
print stats.add('ERROR Deleting', f.decode('utf8'), 0)
print 'Done'
def fix(config_ini, write):
common.load_config(config_ini)
common.register_translator()
if write:
rev = model.repo.new_revision()
rev.author = 'script-' + __file__
# rev.author "script-" prefix stops the changes appearing in the
# publisher_activity report
packages = model.Session.query(model.Package) \
.filter_by(state='active') \
.join(model.PackageExtra) \
.filter_by(state='active') \
.filter(or_(model.PackageExtra.key == 'theme-secondary',
model.PackageExtra.key == 'themes-secondary'))\
.all()
for pkg in packages:
withs = pkg.extras.get('themes-secondary')
withouts = pkg.extras.get('theme-secondary')
if withs and not withouts:
print stats.add('Dropped the s', pkg.name)
if write:
pkg.extras['theme-secondary'] = withs
del pkg.extras['themes-secondary']
elif withouts and not withs:
print stats.add('Already without an s', pkg.name)
elif withouts and withs:
print stats.add('Merged the two', pkg.name)
withouts = json.loads(withouts)
if isinstance(withouts, basestring):
withouts = [withouts]
withs = set(json.loads(withs))
mix = json.dumps(withouts + list((withs - set(withouts))))
if write:
pkg.extras['theme-secondary'] = mix
del pkg.extras['themes-secondary']
if write:
model.Session.commit()
print stats.report()
def fix(config_ini, write):
common.load_config(config_ini)
common.register_translator()
if write:
rev = model.repo.new_revision()
rev.author = 'script-' + __file__
# rev.author "script-" prefix stops the changes appearing in the
# publisher_activity report
packages = model.Session.query(model.Package) \
.filter_by(state='active') \
.join(model.PackageExtra) \
.filter_by(state='active') \
.filter(or_(model.PackageExtra.key == 'theme-secondary',
model.PackageExtra.key == 'themes-secondary'))\
.all()
for pkg in packages:
withs = pkg.extras.get('themes-secondary')
withouts = pkg.extras.get('theme-secondary')
if withs and not withouts:
print stats.add('Dropped the s', pkg.name)
if write:
pkg.extras['theme-secondary'] = withs
del pkg.extras['themes-secondary']
elif withouts and not withs:
print stats.add('Already without an s', pkg.name)
elif withouts and withs:
print stats.add('Merged the two', pkg.name)
withouts = json.loads(withouts)
if isinstance(withouts, basestring):
withouts = [withouts]
withs = set(json.loads(withs))
mix = json.dumps(withouts + list((withs - set(withouts))))
if write:
pkg.extras['theme-secondary'] = mix
del pkg.extras['themes-secondary']
if write:
model.Session.commit()
print stats.report()
def command(cls, config_ini, cache_dir, delete):
common.load_config(config_ini)
common.register_translator()
#rev = model.repo.new_revision()
#rev.author = 'fix_secondary_theme.py'
no_archival = []
deleted_res = []
for f in glob.glob(os.path.join(cache_dir, '*/*/*')):
a = model.Session.query(Archival).filter(
Archival.cache_filepath == f).first()
if a == None:
stats.add('No archival', f.decode('utf8'))
no_archival.append(f)
else:
res = model.Resource.get(a.resource_id)
if res.state == 'deleted':
stats.add('Deleted Resouce', f.decode('utf8'))
deleted_res.append(f)
else:
stats.add('OK', f.decode('utf8'))
if delete:
for f in chain(deleted_res, no_archival):
try:
os.unlink(f)
except OSError:
stats.add('Error Deleting', f.decode('utf8'))
#with open('no-archival.txt', 'w') as outfile:
# for f in no_archival:
# outfile.write("%s\n" % f)
#with open('deleted-res.txt', 'w') as outfile:
# for f in deleted_res:
# outfile.write("%s\n" % f)
print stats.report()
def command(cls, config_ini, package_zip_dir, delete_files):
common.load_config(config_ini)
common.register_translator()
files_to_delete = []
count = 0
for f in glob.iglob(os.path.join(package_zip_dir, '*')):
a = model.Session.query(PackageZip) \
.filter(PackageZip.filepath==f) \
.first()
size = os.path.getsize(f)
if a == None:
print stats.add('Not in packagezip table', f.decode('utf8'),
size)
files_to_delete.append(f)
else:
pkg = model.Package.get(a.package_id)
if pkg.state == 'deleted':
print stats.add('Package is deleted', f.decode('utf8'),
size)
files_to_delete.append(f)
else:
stats.add('OK', f.decode('utf8'), size)
count += 1
if count % 250 == 0:
print '\n\nProgress after %s:' % count
print stats.report()
print stats.report()
if delete_files:
print 'Deleting %s files' % len(files_to_delete)
for f in files_to_delete:
try:
os.unlink(f)
except OSError:
print stats.add('ERROR Deleting', f.decode('utf8'), 0)
print 'Done'
def command(cls, config_ini, cache_dir, delete):
common.load_config(config_ini)
common.register_translator()
#rev = model.repo.new_revision()
#rev.author = 'fix_secondary_theme.py'
no_archival = []
deleted_res = []
for f in glob.glob(os.path.join(cache_dir, '*/*/*')):
a = model.Session.query(Archival).filter(Archival.cache_filepath==f).first()
if a == None:
stats.add('No archival', f.decode('utf8'))
no_archival.append(f)
else:
res = model.Resource.get(a.resource_id)
if res.state == 'deleted':
stats.add('Deleted Resouce', f.decode('utf8'))
deleted_res.append(f)
else:
stats.add('OK', f.decode('utf8'))
if delete:
for f in chain(deleted_res, no_archival):
try:
os.unlink(f)
except OSError:
stats.add('Error Deleting', f.decode('utf8'))
#with open('no-archival.txt', 'w') as outfile:
# for f in no_archival:
# outfile.write("%s\n" % f)
#with open('deleted-res.txt', 'w') as outfile:
# for f in deleted_res:
# outfile.write("%s\n" % f)
print stats.report()
def command(cls, config_ini, package_zip_dir, delete_files):
common.load_config(config_ini)
common.register_translator()
files_to_delete = []
count = 0
for f in glob.iglob(os.path.join(package_zip_dir, '*')):
a = model.Session.query(PackageZip) \
.filter(PackageZip.filepath==f) \
.first()
size = os.path.getsize(f)
if a == None:
print stats.add('Not in packagezip table', f.decode('utf8'), size)
files_to_delete.append(f)
else:
pkg = model.Package.get(a.package_id)
if pkg.state == 'deleted':
print stats.add('Package is deleted', f.decode('utf8'), size)
files_to_delete.append(f)
else:
stats.add('OK', f.decode('utf8'), size)
count += 1
if count % 250 == 0:
print '\n\nProgress after %s:' % count
print stats.report()
print stats.report()
if delete_files:
print 'Deleting %s files' % len(files_to_delete)
for f in files_to_delete:
try:
os.unlink(f)
except OSError:
print stats.add('ERROR Deleting', f.decode('utf8'), 0)
print 'Done'
warnings = []
log = None
def warn(msg, *params):
global warnings
warnings.append(msg % params)
global_log.warn(msg, *params)
def usage():
print """
Coupled Resources tool
Usage:
python coupled_resources.py <CKAN config ini filepath> detect
- finds datasets that are coupled and adds their harvest_source_reference
"""
if __name__ == '__main__':
if len(sys.argv) != 3:
print 'Wrong number of arguments %i' % len(sys.argv)
usage()
sys.exit(0)
cmd, config_ini, action = sys.argv
common.load_config(config_ini)
CoupledResources.setup_logging(config_ini)
common.register_translator()
if action == 'detect':
CoupledResources.detect()
else:
raise NotImplementedError
admin_ids = [i[0] for i in model.Session.query(model.User.id).filter_by(sysadmin=True).all()]
members = model.Session.query(model.Member)\
.filter_by(table_name='user', capacity='admin', state='active')\
.filter(model.Member.table_id.in_(admin_ids))
print "There are %s memberships to be deleted" % members.count()
members.update({'state': 'deleted'}, synchronize_session='fetch')
model.Session.commit()
if __name__ == '__main__':
usage = __doc__ + """
usage:
%prog <ckan.ini>
"""
if len(sys.argv) < 2:
print usage
sys.exit("Wrong number of args")
config_filepath = sys.argv[1]
print 'Loading CKAN config...'
common.load_config(config_filepath)
common.register_translator()
print 'Done'
remove_admins()
warnings = []
log = None
def warn(msg, *params):
global warnings
warnings.append(msg % params)
global_log.warn(msg, *params)
def usage():
print """
Coupled Resources tool
Usage:
python coupled_resources.py <CKAN config ini filepath> detect
- finds datasets that are coupled and adds their harvest_source_reference
"""
if __name__ == '__main__':
if len(sys.argv) != 3:
print 'Wrong number of arguments %i' % len(sys.argv)
usage()
sys.exit(0)
cmd, config_ini, action = sys.argv
common.load_config(config_ini)
CoupledResources.setup_logging(config_ini)
common.register_translator()
if action == 'detect':
CoupledResources.detect()
else:
raise NotImplementedError
usage = __doc__ + """
usage:
%prog [-w] [YY-MM-DD|all] <ckan.ini>
"""
parser = OptionParser(usage=usage)
#parser.add_option("-w", "--write",
# action="store_true", dest="write",
# help="write the theme to the datasets")
parser.add_option('-f', '--filename', dest='filename')
parser.add_option('-o', '--organization', dest='organization')
(options, args) = parser.parse_args()
if len(args) != 2:
parser.error('Wrong number of arguments (%i)' % len(args))
date_str, config_filepath = args
print 'Loading CKAN config...'
common.load_config(config_filepath)
common.register_translator()
print 'Done'
if date_str == 'all':
now = datetime.date.today()
date = datetime.date(2012, 6, 1)
while date <= now:
dump_groups(date, options)
date += datetime.timedelta(days=31)
while date.day != 1:
date -= datetime.timedelta(days=1)
else:
date = datetime.date(*[int(chunk) for chunk in date_str.split('-')])
dump_groups(date, options)