Skip to content

gh-130273: Add pure Python implementation of unicodedata.iter_graphemes() #148218

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

Open
ambv wants to merge 6 commits into
base: main
Choose a base branch
from
+858 −24
Open

gh-130273: Add pure Python implementation of unicodedata.iter_graphemes() #148218

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
df60e53
Add pure Python implementation of unicodedata.iter_graphemes()
ambv Apr 7, 2026
6262980
Add _py_grapheme to stdlib_module_names.h
ambv Apr 7, 2026
38db422
Make the first argument positional-only
ambv Apr 7, 2026
70bdb56
Make _py_grapheme standalone by generating property tables
ambv Apr 7, 2026
5701c0b
Fix newlines to make linter happy
ambv Apr 7, 2026
e073e06
Achieve 100% statement and branch test coverage
ambv Apr 7, 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
Achieve 100% statement and branch test coverage
  • Loading branch information
@ambv
ambv committed Apr 7, 2026
commit e073e06a18ed1f3409a77da8232bc931815f2b13
6 changes: 2 additions & 4 deletions Lib/_py_grapheme.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,10 +67,8 @@ def __repr__(self):
def _get_gcb(cp):
"""Return the Grapheme_Cluster_Break value for a codepoint."""
idx = bisect_right(_GCB_STARTS, cp) - 1
if idx >= 0:
entry = GCB_RANGES[idx]
if cp <= entry[1]:
return entry[2]
if idx >= 0 and cp <= GCB_RANGES[idx][1]:
return GCB_RANGES[idx][2]
# Hangul syllables: LV if (cp - S_BASE) % T_COUNT == 0, else LVT
if _HANGUL_S_BASE <= cp < _HANGUL_S_BASE + _HANGUL_S_COUNT:
if (cp - _HANGUL_S_BASE) % _HANGUL_T_COUNT == 0:
Expand Down
23 changes: 12 additions & 11 deletions Lib/test/test_unicodedata.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1182,17 +1182,6 @@ def test_linebreak_7643(self):
self.assertEqual(len(lines), 1,
r"%a should not be a linebreak" % c)

def test_segment_object(self):
segments = list(unicodedata.iter_graphemes('spa\u0300m'))
self.assertEqual(len(segments), 4, segments)
segment = segments[2]
self.assertEqual(segment.start, 2)
self.assertEqual(segment.end, 4)
self.assertEqual(str(segment), 'a\u0300')
self.assertEqual(repr(segment), '<Segment 2:4>')
self.assertRaises(TypeError, iter, segment)
self.assertRaises(TypeError, len, segment)


class NormalizationTest(unittest.TestCase):
@staticmethod
Expand Down Expand Up @@ -1384,6 +1373,18 @@ def test_segment_object(self):
self.assertEqual(segment.start, 2)
self.assertEqual(segment.end, 4)
self.assertEqual(str(segment), 'a\u0300')
Comment thread
ambv marked this conversation as resolved.
self.assertEqual(repr(segment), '<Segment 2:4>')
self.assertRaises(TypeError, iter, segment)
self.assertRaises(TypeError, len, segment)

def test_grapheme_break_fsm_edges(self):
graphemes = self._graphemes
# ExtPict followed by non-Extend/non-ZWJ resets the EP FSM
self.assertEqual(graphemes('\u2764b'), ['\u2764', 'b'])
# Consonant followed by InCB Extend (not Linker) stays in Started
self.assertEqual(graphemes('\u0915\u0951'), ['\u0915\u0951'])
# Consonant followed by InCB None resets InCB FSM
self.assertEqual(graphemes('\u0915b'), ['\u0915', 'b'])

def _graphemes(self, *args):
return list(map(str, self.iter_graphemes(*args)))
Expand Down
Loading