Skip to content

[3.14] gh-74902: Add Unicode Grapheme Cluster Break algorithm (GH-143076) #148247

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

Draft
StanFromIreland wants to merge 3 commits into
base: 3.14
Choose a base branch
from
Draft

[3.14] gh-74902: Add Unicode Grapheme Cluster Break algorithm (GH-143076) #148247

Changes from 1 commit
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
f413b87
[3.14] gh-74902: Add Unicode Grapheme Cluster Break algorithm (GH-143…
serhiy-storchaka Jan 14, 2026
a4665b5
Fix refleaks in new unicodedata classes added in gh-74902 (GH-143843)
serhiy-storchaka Jan 14, 2026
9efe825
gh-74902: Avoid hitting unicode.org for test data (GH-144195)
zware Jan 23, 2026
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
gh-74902: Avoid hitting unicode.org for test data (GH-144195) 
Use our own pythontest.net instead.
  • Loading branch information
@zware @StanFromIreland
zware authored and StanFromIreland committed Apr 8, 2026
commit 9efe82503dd46862e2d60e17a605edd960343d64
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 @@ -979,11 +999,6 @@ 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 @@ -993,17 +1008,7 @@ 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 @@ -1100,25 +1105,10 @@ 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"
testdata = download_test_data_file(TESTDATAFILE)

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