Skip to content

gh-74902: Avoid hitting unicode.org for test data #144195

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

Merged
zware merged 1 commit into from
Jan 23, 2026
+23 −33
Merged

gh-74902: Avoid hitting unicode.org for test data #144195

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
56 changes: 23 additions & 33 deletions Lib/test/test_unicodedata.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,26 @@ def iterallchars():
maxunicode = 0xffff if quicktest else sys.maxunicode
return map(chr, range(maxunicode + 1))


def check_version(testfile):
hdr = testfile.readline()
return unicodedata.unidata_version in hdr


def download_test_data_file(filename):
TESTDATAURL = f"http://www.pythontest.net/unicode/{unicodedata.unidata_version}/{filename}"

try:
return open_urlresource(TESTDATAURL, encoding="utf-8", check=check_version)
except PermissionError:
raise unittest.SkipTest(
f"Permission error when downloading {TESTDATAURL} "
f"into the test data directory"
)
except (OSError, HTTPException) as exc:
raise unittest.SkipTest(f"Failed to download {TESTDATAURL}: {exc}")


class UnicodeMethodsTest(unittest.TestCase):

# update this, if the database changes
Expand Down Expand Up @@ -956,11 +976,6 @@ def test_segment_object(self):


class NormalizationTest(unittest.TestCase):
@staticmethod
def check_version(testfile):
hdr = testfile.readline()
return unicodedata.unidata_version in hdr

@staticmethod
def unistr(data):
data = [int(x, 16) for x in data.split(" ")]
Expand All @@ -970,17 +985,7 @@ def unistr(data):
@requires_resource('cpu')
def test_normalization(self):
TESTDATAFILE = "NormalizationTest.txt"
TESTDATAURL = f"http://www.pythontest.net/unicode/{unicodedata.unidata_version}/{TESTDATAFILE}"

# Hit the exception early
try:
testdata = open_urlresource(TESTDATAURL, encoding="utf-8",
check=self.check_version)
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}")
testdata = download_test_data_file(TESTDATAFILE)

with testdata:
self.run_normalization_tests(testdata, unicodedata)
Expand Down Expand Up @@ -1077,25 +1082,10 @@ class MyStr(str):


class GraphemeBreakTest(unittest.TestCase):
@staticmethod
def check_version(testfile):
hdr = testfile.readline()
return unicodedata.unidata_version in hdr

@requires_resource('network')
def test_grapheme_break(self):
TESTDATAFILE = "auxiliary/GraphemeBreakTest.txt"
TESTDATAURL = f"https://www.unicode.org/Public/{unicodedata.unidata_version}/ucd/{TESTDATAFILE}"

# Hit the exception early
try:
testdata = open_urlresource(TESTDATAURL, encoding="utf-8",
check=self.check_version)
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}")
TESTDATAFILE = "GraphemeBreakTest.txt"
Copy link
Member

@serhiy-storchaka serhiy-storchaka Jan 23, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

So, it is not in auxiliary?

Copy link
Member Author

@zware zware Jan 23, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It is not; since we only have three files in there (up from two before adding this one), the extra directory seemed unnecessary. Easy enough to add back if you want it, though.

testdata = download_test_data_file(TESTDATAFILE)

with testdata:
self.run_grapheme_break_tests(testdata)
Expand Down
Loading