mirror of
https://github.com/IfcOpenShell/IfcOpenShell.git
synced 2026-08-10 17:58:20 +00:00
Revert "Squashed commit of the following:"
This reverts commit f07cf1d1ef.
This commit is contained in:
Gorgious
@@ -18,9 +18,6 @@
|
||||
|
||||
import json
|
||||
from pathlib import Path
|
||||
from pprint import pprint
|
||||
import copy
|
||||
import ifcopenshell
|
||||
|
||||
try:
|
||||
import glob
|
||||
@@ -42,17 +39,15 @@ SCHEMA_FILES = {
|
||||
"IFC2X3": {
|
||||
"entities": BASE_MODULE_PATH / "schema/ifc2x3_entities.json",
|
||||
"properties": BASE_MODULE_PATH / "schema/ifc2x3_properties.json",
|
||||
"types": BASE_MODULE_PATH / "schema/ifc2x3_types.json",
|
||||
},
|
||||
"IFC4": {
|
||||
"entities": BASE_MODULE_PATH / "schema/ifc4_entities.json",
|
||||
"properties": BASE_MODULE_PATH / "schema/ifc4_properties.json",
|
||||
"types": BASE_MODULE_PATH / "schema/ifc4_types.json",
|
||||
},
|
||||
}
|
||||
|
||||
db = None
|
||||
schema_by_name = {"IFC2X3": None, "IFC4": None}
|
||||
|
||||
|
||||
def get_db(version):
|
||||
global db
|
||||
@@ -70,35 +65,17 @@ def get_db(version):
|
||||
db[ifc_version][data_type] = json.load(fi)
|
||||
return db.get(version)
|
||||
|
||||
def get_schema_by_name(version):
|
||||
global schema_by_name
|
||||
if not schema_by_name[version]:
|
||||
schema_by_name[version] = ifcopenshell.ifcopenshell_wrapper.schema_by_name(version)
|
||||
return schema_by_name[version]
|
||||
|
||||
def get_entity_doc(version, entity_name, recursive=True):
|
||||
def get_entity_doc(version, entity):
|
||||
db = get_db(version)
|
||||
if db:
|
||||
entity = copy.deepcopy(db["entities"].get(entity_name))
|
||||
if not recursive:
|
||||
return entity
|
||||
|
||||
ifc_schema = get_schema_by_name(version)
|
||||
ifc_entity = ifc_schema.declaration_by_name(entity_name)
|
||||
ifc_supertype = ifc_entity.supertype()
|
||||
if ifc_entity.supertype():
|
||||
parent_entity = get_entity_doc(version, ifc_supertype.name(), recursive=True)
|
||||
if 'attributes' not in entity:
|
||||
entity['attributes'] = dict()
|
||||
for parent_attr in parent_entity["attributes"]:
|
||||
entity['attributes'][parent_attr] = parent_entity["attributes"][parent_attr]
|
||||
return entity
|
||||
return db["entities"].get(entity)
|
||||
|
||||
|
||||
def get_attribute_doc(version, entity, attribute, recursive=True):
|
||||
def get_attribute_doc(version, entity, attribute):
|
||||
db = get_db(version)
|
||||
if db:
|
||||
entity = get_entity_doc(version, entity, recursive)
|
||||
entity = db["entities"].get(entity)
|
||||
if entity:
|
||||
return entity["attributes"].get(attribute)
|
||||
|
||||
@@ -114,6 +91,7 @@ def get_property_set_doc(version, pset):
|
||||
if db:
|
||||
return db["properties"].get(pset)
|
||||
|
||||
|
||||
def get_property_doc(version, pset, prop):
|
||||
db = get_db(version)
|
||||
if db:
|
||||
@@ -121,10 +99,6 @@ def get_property_doc(version, pset, prop):
|
||||
if pset:
|
||||
return pset["properties"].get(prop)
|
||||
|
||||
def get_type_doc(version, ifc_type):
|
||||
db = get_db(version)
|
||||
if db:
|
||||
return db["types"].get(ifc_type)
|
||||
|
||||
class DocExtractor:
|
||||
def extract_ifc2x3(self):
|
||||
@@ -143,10 +117,10 @@ class DocExtractor:
|
||||
# probably due domains on the website being from 4_0
|
||||
# example (property set / github domain / website domain):
|
||||
# Pset_AirTerminalBoxPHistory IfcControlExtension IfcHvacDomain
|
||||
|
||||
self.extract_ifc2x3_property_sets_site_domains()
|
||||
self.extract_ifc2x3_entities()
|
||||
self.extract_ifc2x3_property_sets()
|
||||
self.extract_ifc2x3_types()
|
||||
|
||||
def extract_ifc2x3_property_sets_site_domains(self):
|
||||
property_sets_domains = dict()
|
||||
@@ -212,14 +186,14 @@ class DocExtractor:
|
||||
# because BeautifulSoup wrongly assume we confused
|
||||
# html code for filepath and gives warnings
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter("ignore", category=MarkupResemblesLocatorWarning)
|
||||
warnings.simplefilter("ignore", category=MarkupResemblesLocatorWarning)
|
||||
|
||||
for html_attr in bs_tree.find_all("docattribute"):
|
||||
attr_name = html_attr["name"]
|
||||
if attr_name == "PredefinedType":
|
||||
# get references to all predefined types
|
||||
defined_type = html_attr["definedtype"]
|
||||
enum_path = xml_path.parents[2] / "Types" / defined_type / "DocEnumeration.xml"
|
||||
enum_path = xml_path.parents[2] / "Types" / defined_type / 'DocEnumeration.xml'
|
||||
with open(enum_path, "r", encoding="utf-8") as fi:
|
||||
enum_bs_tree = BeautifulSoup(fi.read(), features="lxml")
|
||||
hrefs = [i["href"] for i in enum_bs_tree.find_all("docconstant")]
|
||||
@@ -257,6 +231,7 @@ class DocExtractor:
|
||||
attr_description = attr_description.strip().rstrip(">").strip()
|
||||
entity_attrs[attr_name] = attr_description
|
||||
|
||||
|
||||
if entity_attrs:
|
||||
entities_dict[entity_name]["attributes"] = entity_attrs
|
||||
|
||||
@@ -278,6 +253,7 @@ class DocExtractor:
|
||||
def extract_ifc2x3_property_sets(self):
|
||||
property_sets_dict = dict()
|
||||
property_sets_references = dict()
|
||||
property_sets_spec_urls = dict()
|
||||
|
||||
# extract lists of properties and theirs references for each property set
|
||||
parsed_paths = [
|
||||
@@ -292,27 +268,9 @@ class DocExtractor:
|
||||
for property_set_path in glob.iglob(f"{parse_folder_path}/**/"):
|
||||
property_set_path = Path(property_set_path)
|
||||
property_set_name = property_set_path.stem
|
||||
property_set_dict = dict()
|
||||
|
||||
property_references = list()
|
||||
xml_path = property_set_path / "DocPropertySet.xml"
|
||||
md_path = property_set_path / "Documentation.md"
|
||||
|
||||
if md_path.is_file():
|
||||
with open(md_path, "r", encoding="utf-8-sig") as fi:
|
||||
# convert markdown to html for easier parsing
|
||||
html = markdown(fi.read())
|
||||
property_set_description = BeautifulSoup(html, features="lxml").find("p").text
|
||||
property_set_description = property_set_description.replace("\n", " ")
|
||||
property_set_description = property_set_description.split("HISTORY:", 1)[0]
|
||||
property_set_description = property_set_description.strip()
|
||||
property_set_dict["description"] = property_set_description
|
||||
else:
|
||||
print(
|
||||
f"WARNING. Property set {property_set_name} has no Documentation.md, "
|
||||
f"property set will be left without description."
|
||||
)
|
||||
|
||||
with open(xml_path, "r", encoding="utf-8") as fi:
|
||||
bs_tree = BeautifulSoup(fi.read(), features="lxml")
|
||||
for html_attr in bs_tree.find_all("docproperty"):
|
||||
@@ -324,8 +282,7 @@ class DocExtractor:
|
||||
"https://standards.buildingsmart.org/IFC/RELEASE/IFC2x3/TC1/HTML"
|
||||
f"/psd/{property_set_domain}/{property_set_name}.xml"
|
||||
)
|
||||
property_set_dict["spec_url"] = spec_url
|
||||
property_sets_dict[property_set_name] = property_set_dict
|
||||
property_sets_spec_urls[property_set_name] = spec_url
|
||||
|
||||
# setup references look up tables to convert property hrefs to actual data paths
|
||||
references_paths_lookup = self.setup_ifc2x3_reference_lookup()
|
||||
@@ -388,54 +345,16 @@ class DocExtractor:
|
||||
for property_reference in property_sets_references[property_set_name]:
|
||||
property_name, property_dict = get_property_info_by_href(property_reference)
|
||||
properties_dict[property_name] = property_dict
|
||||
property_sets_dict[property_set_name]["properties"] = properties_dict
|
||||
property_sets_dict[property_set_name] = {
|
||||
"properties": properties_dict,
|
||||
"spec_url": property_sets_spec_urls[property_set_name],
|
||||
}
|
||||
|
||||
# export property sets data
|
||||
with open(BASE_MODULE_PATH / "schema/ifc2x3_properties.json", "w", encoding="utf-8") as fo:
|
||||
print(f"{len(property_sets_dict)} property sets parsed")
|
||||
json.dump(property_sets_dict, fo, sort_keys=True, indent=4)
|
||||
|
||||
def extract_ifc2x3_types(self):
|
||||
types_dict = dict()
|
||||
# search
|
||||
types_paths = [
|
||||
filepath for filepath in glob.iglob(f"{IFC2x3_DOCS_LOCATION}/Sections/**/Types", recursive=True)
|
||||
]
|
||||
for parse_folder_path in types_paths:
|
||||
for type_path in glob.iglob(f"{parse_folder_path}/**/"):
|
||||
type_path = Path(type_path)
|
||||
type_name = type_path.stem
|
||||
types_dict[type_name] = dict()
|
||||
md_path = type_path / "Documentation.md"
|
||||
|
||||
# utf-8-sig because of \ufeff occcurs - meaning it's utf bom encoded
|
||||
with open(md_path, "r", encoding="utf-8-sig") as fi:
|
||||
# convert markdown to html for easier parsing
|
||||
html = markdown(fi.read())
|
||||
type_description = BeautifulSoup(html, features="lxml").find("p").text
|
||||
type_description = type_description.replace("\n", " ")
|
||||
type_description = type_description.replace("\u00a0", " ")
|
||||
type_description = type_description.replace("Definition from ISO/CD 10303-46:1992: ", "")
|
||||
type_description = type_description.replace("Definition from ISO/CD 10303-42:1992 ", "")
|
||||
type_description = type_description.replace("Definition from ISO/CD 10303-42:1992: ", "")
|
||||
type_description = type_description.replace("Definition from ISO/CD 10303-41:1992: ", "")
|
||||
|
||||
type_description = type_description.strip()
|
||||
|
||||
if type_description:
|
||||
types_dict[type_name]['description'] = type_description
|
||||
|
||||
spec_url = (
|
||||
"https://standards.buildingsmart.org/IFC/RELEASE/IFC2x3/TC1/HTML/"
|
||||
f"{md_path.parents[2].name.lower()}/lexical/{type_name.lower()}.htm"
|
||||
)
|
||||
types_dict[type_name]['spec_url'] = spec_url
|
||||
|
||||
# export entities data
|
||||
with open(BASE_MODULE_PATH / "schema/ifc2x3_types.json", "w", encoding="utf-8") as fo:
|
||||
print(f"{len(types_dict)} ifc types parsed")
|
||||
json.dump(types_dict, fo, sort_keys=True, indent=4)
|
||||
|
||||
def extract_ifc4(self):
|
||||
print("Parsing data for Ifc4.0.2.1")
|
||||
if not IFC4_DOCS_LOCATION.is_dir():
|
||||
@@ -455,7 +374,6 @@ class DocExtractor:
|
||||
self.extract_ifc4_property_sets_site_domains()
|
||||
self.extract_ifc4_entities()
|
||||
self.extract_ifc4_property_sets()
|
||||
self.extract_ifc4_types()
|
||||
|
||||
def extract_ifc4_property_sets_site_domains(self):
|
||||
property_sets_domains = dict()
|
||||
@@ -516,12 +434,12 @@ class DocExtractor:
|
||||
entity_name = entity_path.stem
|
||||
entities_dict[entity_name] = dict()
|
||||
|
||||
# utf-8-sig because of \ufeff occcurs - meaning it's utf bom encoded
|
||||
md_path = entity_path / "Documentation.md"
|
||||
xml_path = entity_path / "DocEntity.xml"
|
||||
md_url_part = urllib.parse.quote(str(md_path.relative_to(Path(__file__).parent).as_posix()))
|
||||
github_md_url = f"https://github.com/buildingSMART/IFC/blob/{md_url_part}"
|
||||
|
||||
# utf-8-sig because of \ufeff occcurs - meaning it's utf bom encoded
|
||||
with open(md_path, "r", encoding="utf-8-sig") as fi:
|
||||
# convert markdown to html for easier parsing
|
||||
html = markdown(fi.read())
|
||||
@@ -541,13 +459,12 @@ class DocExtractor:
|
||||
# html code for filepath and gives warnings
|
||||
with warnings.catch_warnings():
|
||||
warnings.simplefilter("ignore", category=MarkupResemblesLocatorWarning)
|
||||
|
||||
for html_attr in bs_tree.find_all("docattribute"):
|
||||
attr_name = html_attr["name"]
|
||||
if attr_name == "PredefinedType":
|
||||
# get references to all predefined types
|
||||
defined_type = html_attr["definedtype"]
|
||||
enum_path = xml_path.parents[2] / "Types" / defined_type / "DocEnumeration.xml"
|
||||
enum_path = xml_path.parents[2] / "Types" / defined_type / 'DocEnumeration.xml'
|
||||
with open(enum_path, "r", encoding="utf-8") as fi:
|
||||
enum_bs_tree = BeautifulSoup(fi.read(), features="lxml")
|
||||
hrefs = [i["href"] for i in enum_bs_tree.find_all("docconstant")]
|
||||
@@ -603,6 +520,7 @@ class DocExtractor:
|
||||
# function parses both property and quantity sets
|
||||
property_sets_dict = dict()
|
||||
property_sets_references = dict()
|
||||
property_sets_spec_urls = dict()
|
||||
|
||||
# extract lists of properties and theirs references for each property set
|
||||
parsed_paths = [
|
||||
@@ -621,27 +539,10 @@ class DocExtractor:
|
||||
for property_set_path in glob.iglob(f"{parse_folder_path}/**/"):
|
||||
property_set_path = Path(property_set_path)
|
||||
property_set_name = property_set_path.stem
|
||||
property_set_dict = dict()
|
||||
|
||||
property_references = list()
|
||||
property_quantity = property_set_path.parents[0].name == "QuantitySets"
|
||||
xml_path = property_set_path / ("DocQuantitySet.xml" if property_quantity else "DocPropertySet.xml")
|
||||
md_path = property_set_path / "Documentation.md"
|
||||
|
||||
if md_path.is_file():
|
||||
with open(md_path, "r", encoding="utf-8-sig") as fi:
|
||||
# convert markdown to html for easier parsing
|
||||
html = markdown(fi.read())
|
||||
property_set_description = BeautifulSoup(html, features="lxml").find("p").text
|
||||
property_set_description = property_set_description.replace("\n", " ")
|
||||
property_set_description = property_set_description.split("HISTORY:", 1)[0]
|
||||
property_set_description = property_set_description.strip()
|
||||
property_set_dict["description"] = property_set_description
|
||||
else:
|
||||
print(
|
||||
f"WARNING. Property set {property_set_name} has no Documentation.md, "
|
||||
f"property set will be left without description."
|
||||
)
|
||||
|
||||
with open(xml_path, "r", encoding="utf-8") as fi:
|
||||
bs_tree = BeautifulSoup(fi.read(), features="lxml")
|
||||
@@ -660,11 +561,10 @@ class DocExtractor:
|
||||
spec_url = (
|
||||
"https://standards.buildingsmart.org/IFC/RELEASE/IFC4/ADD2_TC1/HTML"
|
||||
f"/schema/{property_set_domain}"
|
||||
f"/{'qset' if property_quantity else 'pset'}"
|
||||
f'/{"qset" if property_quantity else "pset"}'
|
||||
f"/{property_set_name.lower()}.htm"
|
||||
)
|
||||
property_set_dict["spec_url"] = spec_url
|
||||
property_sets_dict[property_set_name] = property_set_dict
|
||||
property_sets_spec_urls[property_set_name] = spec_url
|
||||
|
||||
# setup references look up tables to convert property hrefs to actual data paths
|
||||
references_paths_lookup = self.setup_ifc4_reference_lookup()
|
||||
@@ -729,61 +629,25 @@ class DocExtractor:
|
||||
for property_reference in property_sets_references[property_set_name]:
|
||||
property_name, property_dict = get_property_info_by_href(property_reference)
|
||||
properties_dict[property_name] = property_dict
|
||||
property_sets_dict[property_set_name]["properties"] = properties_dict
|
||||
property_sets_dict[property_set_name] = {"properties": properties_dict}
|
||||
if property_set_name in property_sets_spec_urls:
|
||||
spec_url = property_sets_spec_urls[property_set_name]
|
||||
property_sets_dict[property_set_name]["spec_url"] = spec_url
|
||||
|
||||
# export property sets data
|
||||
with open(BASE_MODULE_PATH / "schema/ifc4_properties.json", "w", encoding="utf-8") as fo:
|
||||
print(f"{len(property_sets_dict)} property sets parsed")
|
||||
json.dump(property_sets_dict, fo, sort_keys=True, indent=4)
|
||||
|
||||
def extract_ifc4_types(self):
|
||||
types_dict = dict()
|
||||
# search
|
||||
types_paths = [
|
||||
filepath for filepath in glob.iglob(f"{IFC4_DOCS_LOCATION}/Sections/**/Types", recursive=True)
|
||||
]
|
||||
for parse_folder_path in types_paths:
|
||||
for type_path in glob.iglob(f"{parse_folder_path}/**/"):
|
||||
type_path = Path(type_path)
|
||||
type_name = type_path.stem
|
||||
types_dict[type_name] = dict()
|
||||
md_path = type_path / "Documentation.md"
|
||||
|
||||
# utf-8-sig because of \ufeff occcurs - meaning it's utf bom encoded
|
||||
with open(md_path, "r", encoding="utf-8-sig") as fi:
|
||||
# convert markdown to html for easier parsing
|
||||
html = markdown(fi.read().replace("{ .extDef}", ""))
|
||||
type_description = BeautifulSoup(html, features="lxml").find("p").text
|
||||
type_description = type_description.replace("\n", " ")
|
||||
type_description = type_description.replace("\u00a0", " ")
|
||||
type_description = type_description.replace("{ .extDef}", "")
|
||||
type_description = type_description.replace("NOTE Definition according to ISO/CD 10303-41:1992 ", "")
|
||||
type_description = type_description.replace("Definition from ISO/CD 10303-41:1992: ", "")
|
||||
|
||||
type_description = type_description.strip()
|
||||
|
||||
if type_description:
|
||||
types_dict[type_name]['description'] = type_description
|
||||
|
||||
spec_url = (
|
||||
"https://standards.buildingsmart.org/IFC/RELEASE/IFC4/ADD2_TC1/HTML/schema/"
|
||||
f"{md_path.parents[2].name.lower()}/lexical/{type_name.lower()}.htm"
|
||||
)
|
||||
types_dict[type_name]['spec_url'] = spec_url
|
||||
|
||||
# export entities data
|
||||
with open(BASE_MODULE_PATH / "schema/ifc4_types.json", "w", encoding="utf-8") as fo:
|
||||
print(f"{len(types_dict)} ifc types parsed")
|
||||
json.dump(types_dict, fo, sort_keys=True, indent=4)
|
||||
|
||||
def run_doc_api_examples():
|
||||
print("Entities (with parent entities attributes included):")
|
||||
print(get_entity_doc("IFC2X3", "IfcWindow"))
|
||||
print(get_entity_doc("IFC4", "IfcWindow"))
|
||||
print("Entities:")
|
||||
print(get_entity_doc("IFC2X3", "IfcActionRequest"))
|
||||
print(get_entity_doc("IFC4", "IfcActionRequest"))
|
||||
|
||||
print("Entity attributes (with parent entities attributes included):")
|
||||
print(get_attribute_doc("IFC2X3", "IfcWindow", "OwnerHistory"))
|
||||
print(get_attribute_doc("IFC4", "IfcWindow", "OwnerHistory"))
|
||||
print("Entity attributes:")
|
||||
print(get_attribute_doc("IFC2X3", "IfcActionRequest", "RequestID"))
|
||||
print(get_attribute_doc("IFC4", "IfcActionRequest", "LongDescription"))
|
||||
|
||||
print("Entity predefined types:")
|
||||
print(get_predefined_type_doc("IFC2X3", "IfcControllerType", "FLOATING"))
|
||||
@@ -797,10 +661,6 @@ def run_doc_api_examples():
|
||||
print(get_property_doc("IFC2X3", "Pset_ZoneCommon", "Category"))
|
||||
print(get_property_doc("IFC4", "Pset_ZoneCommon", "NetPlannedArea"))
|
||||
|
||||
print("Types:")
|
||||
print(get_type_doc("IFC2X3", "IfcIsothermalMoistureCapacityMeasure"))
|
||||
print(get_type_doc("IFC4", "IfcDuration"))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
extractor = DocExtractor()
|
||||
|
||||
Reference in New Issue
Block a user