def task_cns_template(args=None):
mapping = {
"version": [u"版本"],
"domain": [u"直属分类"],
"name": [u"规范属性名"],
"nameZh": [u"cnschema属性名"],
"alternateName": [u"中文属性名"],
"nameSchemaorg": [u"schema.org属性名"],
"nameWikidata": [u"wikidata属性名"],
"descriptionWikipedia": [u"wikipedia定义"],
"range": [u"预期的属性类型"],
"value": [u"example value"],
"jsonld": [u"example json-ld"],
}
filename = "../local/201707/cns-t-organization.xls"
filename = file2abspath(filename, __file__)
excel_data = excel2json(filename)
bindings = collections.defaultdict(dict)
for sheet_data in excel_data["data"].values():
if len(sheet_data) == 0:
continue
logging.info(len(sheet_data))
for row in sheet_data:
logging.info(json.dumps(row, ensure_ascii=False))
domain = row["domain"] #row[u"直属分类"]
propName = row[u"name"]
rangeList = row[u"range"]
bindings[domain][propName] = row
break
logging.info(bindings)
def read_cns_core(version):
name = "cns-core"
filename = "../local/releases/{}/{}.xls".format(version, name)
filename = file2abspath(filename, __file__)
temp = excel2json(filename)
keys = temp["fields"].values()[0]
items = temp["data"].values()[0]
logging.info(len(items))
#cleanup
itemsNew = []
for item in items:
itemNew = {}
for p in item.keys():
#skip commented fields
if p.startswith("#"):
continue
itemNew[p] = item.get(p, "")
if p == "description":
itemNew[p] = clean_schemaorg_description(itemNew[p])
#if p == "@id":
# itemNew["schemaorgUrl"] = itemNew[p]
# itemNew[p] = re.sub("http://schema.org", "http://cnschema.org", itemNew[p])
itemsNew.append(itemNew)
items = itemsNew
#keys = [x for x in keys if x in items[0].keys()]
return items
def read_cns_core_excel(version, path="local"):
name = "cns-core"
filename = "../{}/releases/{}/{}.xls".format(path, version, name)
filename = file2abspath(filename, __file__)
temp = excel2json(filename)
keys = temp["fields"].values()[0]
items = temp["data"].values()[0]
logging.info(len(items))
return items
def read_cns_core_excel(version, path="data"):
if version == "3.2":
return read_cns_core_excel_v1(version, path)
name = "schemaorg_translate"
filename = "../{}/releases/{}/{}.xlsx".format(path, version, name)
filename = file2abspath(filename, __file__)
temp = excel2json(filename)
keys = temp["fields"][version]
items = temp["data"][version]
# enhance with @id
for item in items:
item["@id"] = "http://cnschema.org/{}".format(item["name"])
logging.info(len(items))
return items
def read_cns_core_excel(version, path="data"):
if version == "3.2":
return read_cns_core_excel_v1(version, path)
# https://docs.google.com/spreadsheets/d/1mpiBxI5rK_qs86IpbXgN1xbhrxS_VYF0XjI_fcRpl00/edit#gid=364353024
name = "schemaorg_translate"
filename = "../{}/releases/{}/{}.xlsx".format(path, version, name)
filename = file2abspath(filename, __file__)
temp = excel2json(filename)
keys = temp["fields"][version]
items = temp["data"][version]
# enhance with @id
for item in items:
item["@id"] = "http://cnschema.org/{}".format(item["name"])
logging.info(len(items))
return items
