def generate_page_entity_detail(self):
# write html using template file
#load template page
filename = os.path.join(os.path.dirname(__file__),
"../templates/page.mustache")
with codecs.open(filename, encoding="utf-8") as f:
templatePage = f.read()
for xid in sorted(self.map_id_schemaorg):
#if not "Music" in xid:
# continue
item = self.map_id_schemaorg.get(xid)
if "#" in xid:
logging.warn("skip {}".format(xid))
continue
entry = self.convert_extend2mustach(item)
html = pystache.render(templatePage, entry)
filename = os.path.join(self.dir_output,
"{}.html".format(entry["rdfs:label"]))
create_dir_if_not_exist(filename)
with codecs.open(filename, "w", encoding="utf-8") as f:
f.write(html)
filename = os.path.join(self.dir_output,
"data/{}.json".format(entry["rdfs:label"]))
create_dir_if_not_exist(filename)
json2file(entry, filename)
def task_cns_make_html(args=None):
name = "cns-core"
version = "3.2"
site = "cnschema.org"
items = read_cns_core_jsonld(version, path="data")
map_id_cnschema = {}
for item in items:
schemaorg_id = item["schemaorgUrl"]
map_id_cnschema[schemaorg_id] = item
# update map_id_schemaorg with cnschem properties
so = Schemaorg(version)
map_id_schemaorg = so.load_data()
for entry in map_id_schemaorg.values():
entry.update(
json_dict_copy(map_id_cnschema.get(entry["@id"], {}),
MAP_CNSCHEMA))
for p in ["isDomainOf", "isRangeOf"]:
target_list = entry.get(p, [])
for target in target_list:
target.update(
json_dict_copy(map_id_cnschema.get(target["@id"], {}),
MAP_CNSCHEMA))
#rewrite map_id_schemaorg schema.org => cnschema.org items_new = schemaorg2cnschema(items_new)
map_id_schemaorg = schemaorg2cnschema(map_id_schemaorg)
filename = '../local/releases/3.2/cns-core.extend.json'
filename = file2abspath(filename, __file__)
json2file(map_id_schemaorg, filename)
website = WebsiteV1(version, site, map_id_schemaorg)
website.run()
def write_cns_core(items, version, formats=["excel", "jsonld"]):
name = "cns-core"
# write excel
keys = [
"category", "@id", "name", "description", "supersededBy", "nameZh",
"descriptionZh", "alternateName", "wikidataName", "wikidataUrl",
"wikipediaUrl", "schemaorgUrl"
]
# validation
for key in keys:
assert key in items[0].keys()
# write excel
if "excel" in formats:
filename = "../data/releases/{}/{}.xls".format(version, name)
filename = file2abspath(filename, __file__)
json2excel(items, keys, filename)
# write json-ld
if "jsonld" in formats:
for item in items:
p = "alternateName"
item[p] = split_string_by_comma(item.get(p, ""))
filename = "../data/releases/{}/{}.jsonld".format(version, name)
filename = file2abspath(filename, __file__)
output = {
"@context": {
"@vocab": "http://cnschema.org/"
},
"@graph": items
}
json2file(filename, output)
def generate_page_vocab(self):
data_json = {}
data_json["classes"] = self._recusive_tree2json(
["http://cnschema.org/Thing"])
data_json["types"] = self._recusive_tree2json(
["http://cnschema.org/DataType"])
data_json["properties"] = []
data_fields = [
"rdfs:label", "rdfs:comment", "nameZh", "descriptionZh",
"_supersede"
]
for xid in sorted(self.map_id_schemaorg):
item = self.map_id_schemaorg[xid]
if item["_group"] != "property":
continue
item_simple = {}
for p in data_fields:
if p in item:
item_simple[p] = item[p]
data_json["properties"].append(item_simple)
filename = os.path.join(self.dir_output, "data2/classes.json")
create_dir_if_not_exist(filename)
json2file(data_json["classes"][0], filename)
filename = os.path.join(self.dir_output, "data2/properties.json")
json2file(data_json["properties"], filename)
def load_data(self):
filename_cache = os.path.join(self.dir_output, "schemaorg.json")
if os.path.exists(filename_cache):
return file2json(filename_cache)
#examples
self._init_examples()
# the word count stats 2015
self._init_stat2015()
# init the schema, with information from examples and stats
self._init_schema()
json2file(self.map_id_node, filename_cache)
return self.map_id_node
def generate_page_vocab(self):
# classes, types, properties
data_json = {}
content_json = {}
lines = []
self._recusive_tree2li(["http://cnschema.org/Thing"], lines)
content_json["classes"] = u"\n".join(lines)
data_json["classes"] = self._recusive_tree2json(
["http://cnschema.org/Thing"])
lines = []
self._recusive_tree2li(["http://cnschema.org/DataType"], lines)
content_json["types"] = u"\n".join(lines)
data_json["types"] = self._recusive_tree2json(
["http://cnschema.org/DataType"])
content_json["properties"] = []
data_json["properties"] = []
data_fields = [
"rdfs:label", "rdfs:comment", "nameZh", "descriptionZh",
"_supersede"
]
for xid in sorted(self.map_id_schemaorg):
item = self.map_id_schemaorg[xid]
if item["_group"] != "property":
continue
#print xid
content_json["properties"].append(item)
item_simple = {}
for p in data_fields:
if p in item:
item_simple[p] = item[p]
data_json["properties"].append(item_simple)
#load template page
filename = os.path.join(os.path.dirname(__file__),
"../templates/vocab.mustache")
with codecs.open(filename, encoding="utf-8") as f:
templatePage = f.read()
# apply template
html = pystache.render(templatePage, content_json)
filename = os.path.join(self.dir_output, "docs/vocab.htm")
create_dir_if_not_exist(filename)
with codecs.open(filename, "w", encoding="utf-8") as f:
f.write(html)
filename = os.path.join(self.dir_output, "docs/vocab.json")
create_dir_if_not_exist(filename)
json2file(data_json, filename)
filename = os.path.join(self.dir_output, "docs/classes.json")
json2file(data_json["classes"][0], filename)
filename = os.path.join(self.dir_output, "docs/properties.json")
json2file(data_json["properties"], filename)
def task_superclasses(args):
filename = "../local/releases/3.2/schema_taxonomy.json"
filename = file2abspath(filename, __file__)
data = file2json(filename)
pairs = []
loadmapping(data, [], pairs)
logging.info(json.dumps(pairs, indent=4, ensure_ascii=False))
mapping = collections.defaultdict(list)
for pair in pairs:
key = pair["to"]
mapping[key].append(pair["to"])
for pair in pairs:
key = pair["to"]
for parent in pair["path"]:
if parent not in mapping[key]:
mapping[key].append(parent)
logging.info(json.dumps(mapping, indent=4, ensure_ascii=False))
filename = "../data/releases/3.2/schema.superclass.json"
filename = file2abspath(filename, __file__)
json2file(mapping, filename)
