def convert_all_to_rdf(self, start_from = 0):
conversion_log = DatabasePlainFiles(self.conversion_log_folder)
process_log = DatabasePlainFiles(self.log_folder)
process_log_filename = "rdf_conversion.log"
all_ids = self.get_files()
overall = len(all_ids)
for num, resource_id in enumerate(all_ids):
if(num < start_from):
continue
print "Converting resource to RDF " + str(num) + " out of " + str(overall)
print str(resource_id)
string = "Converting resource to RDF " + str(num) + " out of " + str(overall) + "\n"
process_log.addDbaseRaw(process_log_filename, string)
string = str(resource_id) + "\n"
process_log.addDbaseRaw(process_log_filename, string)
#Skip folders
if(resource_id == ".analyzed" or resource_id == '.all-resources' or resource_id =='.broken_retrieved'
or resource_id == "files.tar.gz"):
continue
#Init the resource
resource = ckaninterface.Resource(resource_id)
#create wiki-page for resource
string = "creating wiki page for resource" + "\n"
process_log.addDbaseRaw(process_log_filename, string)
wiki_page = resource.generate_default_wiki_page()
string = str(resource.create_wiki_page(wiki_page))
process_log.addDbaseRaw(process_log_filename, string)
#transform resource to RDF
sparqlify_message, returncode = resource.transform_to_rdf('default-tranformation-configuration')
conversion_log.addDbaseRaw(resource_id + '.log', sparqlify_message + "\n" + str(returncode))
def download_all_csv_resources(self):
""" Download csv resources
if resource unaccessible (404 or 503) - add to the list
post-processing
- check mimetype of the file
- if not csv - report
"""
db = DatabasePlainFiles(self.log_folder)
download_all_log = "download_all_log.txt"
ckan = ckaninterface.CKAN_Application()
csv_resource_list = ckan.get_csv_resource_list()
csv_resource_list_max = len(csv_resource_list) - 1
for i in range(csv_resource_list_max):
resource = ckaninterface.Resource(csv_resource_list[i])
db.addDbaseRaw(download_all_log, resource._download())
def download_n_random_csv(self, n):
db = DatabasePlainFiles(self.log_folder)
random_csv_filename = "random_csv.txt"
import random
ckan = ckaninterface.CKAN_Application()
csv_resource_list = ckan.get_csv_resource_list()
csv_resource_list_max = len(csv_resource_list) - 1
for i in range(n):
rand = random.randint(0, csv_resource_list_max)
db.addDbaseRaw(random_csv_filename, str(rand) + "\n")
resource = ckaninterface.Resource(csv_resource_list[rand])
try:
resource._download()
except:
pass
