def test_save_soup(self):
soup = create_soup(self.source_filename)
save_soup(soup, self.xml_filename)
soup = create_soup(self.xml_filename)
self.assertEqual(soup.book.attrs["heading"], "X")
with self.assertRaises(OSError):
save_soup(soup, 100)
def find_references(decision):
try:
logs = []
areas_exists = os.path.exists(f"{DE_DECISIONS_REFERENCE_AREAS}/{decision}")
parsed_exists = os.path.exists(
f"{DE_DECISIONS_REFERENCE_PARSED_XML}/{decision}"
)
if not (areas_exists and parsed_exists): # General preparation
with open(f"{DE_DECISIONS_HIERARCHY}/{decision}", encoding="utf8") as f:
file_content = f.read()
file_content = file_content.replace(
"<!DOCTYPE dokument SYSTEM "
'"http://www.rechtsprechung-im-internet.de/dtd/v1/rii-dok.dtd">',
"",
)
soup = BeautifulSoup(file_content, "lxml-xml")
# Get Entscheidungsdatum
date = get_lawnames_date(soup.document.attrs["datum"])
# Get laws in effect at time of decision
laws_lookup = get_stemmed_law_names(date, law_names)
parser = StatutesParser(laws_lookup)
extractor = StatutesExtractor(laws_lookup)
if not areas_exists:
logs.append(
find_references_in_soup(
soup,
extractor,
para=0,
art=0,
text_tag_name=["text", "norm"],
)
# set para and atr to 0 that refernece with naming a law are ignored.
)
save_soup(soup, f"{DE_DECISIONS_REFERENCE_AREAS}/{decision}")
if not parsed_exists:
with open(
f"{DE_DECISIONS_REFERENCE_AREAS}/{decision}", encoding="utf8"
) as f:
soup = BeautifulSoup(f.read(), "lxml-xml")
parse_reference_content_in_soup(soup, parser, decision)
identify_reference_law_name_in_soup(
soup, parser, current_lawid=None, skip_errors=True
)
identify_lawreference_law_name_in_soup(soup, laws_lookup)
save_soup(soup, f"{DE_DECISIONS_REFERENCE_PARSED_XML}/{decision}")
except Exception:
print("-----", decision, "-----")
the_type, the_value, the_traceback = sys.exc_info()
traceback.print_exception(the_type, the_value, the_traceback)
raise
def test_save_soup_failed(self):
class TestException(Exception):
pass
class FailingTestObj:
def __str__(self):
raise TestException()
with self.assertRaises(TestException):
save_soup(FailingTestObj(), "temp2.xml")
self.assertFalse(os.path.exists("temp2.xml"))
def execute_item(self, item):
src = US_REG_XML_PATH if self.regulations else US_XML_PATH
dest = (US_REG_REFERENCE_AREAS_PATH
if self.regulations else US_REFERENCE_AREAS_PATH)
soup = create_soup(f"{src}/{item}")
logs = find_references(soup, usc_pattern, {"pattern": "block"})
logs += find_references(soup, inline_pattern, {"pattern": "inline"})
if self.regulations:
logs += find_authority_references(soup, usc_pattern)
save_soup(soup, f"{dest}/{item}")
return logs
def clean_decision(decision):
if not os.path.exists(f"{DE_DECISIONS_XML}/{decision}"):
with open(f"{DE_DECISIONS_DOWNLOAD_XML}/{decision}",
encoding="utf8") as f:
content = f.read()
content = content.replace("\xa0", " ")
soup = BeautifulSoup(content, "lxml-xml")
for doc_parts in get_docparts_with_p(soup):
contents = clean_abs(doc_parts)
replace_tag_with_content(doc_parts, contents, soup)
soup_str = fix_data(decision, str(soup))
save_soup(soup_str, f"{DE_DECISIONS_XML}/{decision}")
def execute_item(self, item):
from statutes_pipeline_steps.us_reference_reg import parse_authority_references
src = (
US_REG_REFERENCE_AREAS_PATH if self.regulations else US_REFERENCE_AREAS_PATH
)
dest = (
US_REG_REFERENCE_PARSED_PATH
if self.regulations
else US_REFERENCE_PARSED_PATH
)
soup = create_soup(f"{src}/{item}")
this_title = self.get_title_from_filename(item)
try:
logs = parse_references(soup, this_title, this_usc=not self.regulations)
logs += parse_authority_references(soup)
except Exception:
print(item)
raise
save_soup(soup, f"{dest}/{item}")
return logs
def execute_item(self, item):
src = (DE_REG_REFERENCE_AREAS_PATH
if self.regulations else DE_REFERENCE_AREAS_PATH)
dest = (DE_REG_REFERENCE_PARSED_PATH
if self.regulations else DE_REFERENCE_PARSED_PATH)
laws_lookup = get_stemmed_law_names_for_filename(item, self.law_names)
parser = StatutesParser(laws_lookup)
logs = list()
# for debug
logs.append(f"Start file - {item}")
soup = create_soup(f"{src}/{item}")
parse_reference_content_in_soup(soup, parser, debug_context=item)
current_lawid = soup.document.attrs["key"].split("_")[1]
identify_reference_law_name_in_soup(soup, parser, current_lawid)
identify_lawreference_law_name_in_soup(soup, laws_lookup)
identify_reference_in_juris_vso_list(soup, parser)
save_soup(soup, f"{dest}/{item}")
return logs
def simplify_gii_xml(source, destination):
soup = create_soup(source)
simplify(soup)
save_soup(soup, destination)
