Thanks to visit codestin.com
Credit goes to github.com

Skip to content

gh-80667: Fix Tangut ideographs names in unicodedata #101585

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wismill wants to merge 3 commits into from
Closed

gh-80667: Fix Tangut ideographs names in unicodedata #101585

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
0609eb2
unicodedata: Fix Tangut Ideograph names
wismill Jul 26, 2023
3821e1b
News entry
wismill Jul 26, 2023
b2c4e92
Add test
wismill Jul 26, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Add test
  • Loading branch information
@wismill
wismill committed Jul 26, 2023
commit b2c4e9276786cf9a230a605193a0fed7b3eaa9d4
45 changes: 45 additions & 0 deletions Lib/test/test_unicodedata.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -97,13 +97,58 @@ def test_function_checksum(self):
result = h.hexdigest()
self.assertEqual(result, self.expectedchecksum)

@requires_resource('network')
def test_name(self):
TESTBASEURL = "https://www.unicode.org/Public"
TESTDATAFILE = "extracted/DerivedName.txt"
TESTDATAURL = f"{TESTBASEURL}/{unicodedata.unidata_version}/ucd/{TESTDATAFILE}"

# Hit the exception early
try:
testdata = open_urlresource(TESTDATAURL, encoding="utf-8")
except PermissionError:
self.skipTest(f"Permission error when downloading {TESTDATAURL} "
f"into the test data directory")
except (OSError, HTTPException) as exc:
self.skipTest(f"Failed to download {TESTDATAURL}: {exc}")

with testdata:
self.run_name_tests(testdata)

def run_name_tests(self, testdata):
names_ref = {}

def parse_cp(s):
return int(s, 16)

# Parse data
for line in testdata:
line = line.strip()
if not line or line.startswith("#"):
continue
raw_cp, name = line.split("; ")
# Check for a range
if ".." in raw_cp:
cp1, cp2 = map(parse_cp, raw_cp.split(".."))
# remove ‘*’ at the end
name = name[:-1]
for cp in range(cp1, cp2 + 1):
names_ref[cp] = f"{name}{cp:0>4X}"
else:
cp = parse_cp(raw_cp)
names_ref[cp] = name

for cp in range(0, sys.maxunicode + 1):
self.assertEqual(self.db.name(chr(cp), None), names_ref.get(cp))

@requires_resource('cpu')
def test_name_inverse_lookup(self):
for i in range(sys.maxunicode + 1):
char = chr(i)
if looked_name := self.db.name(char, None):
self.assertEqual(self.db.lookup(looked_name), char)


def test_digit(self):
self.assertEqual(self.db.digit('A', None), None)
self.assertEqual(self.db.digit('9'), 9)
Expand Down