FazBrowse GitHub Viewer | Trending |
URL:
| Home
Tools: [Download Repo ZIP]   [Original HTTPS Page]

gh-142224: `makeunicodedata.py`: parse default bidi values by StanFromIreland · Pull Request #144815 · python/cpython · GitHub

  1. python
  2. cpython

Repository navigation

gh-142224: makeunicodedata.py: parse default bidi values #144815

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
serhiy-storchaka merged 5 commits into from
Feb 18, 2026
Conversation 15 Commits 5 Checks 57 Files changed
Merged

gh-142224: makeunicodedata.py: parse default bidi values #144815

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
acb61d0
Parse bidi defaults for unassigned code points
StanFromIreland Feb 14, 2026
b665e66
Updates for Serhiy
StanFromIreland Feb 17, 2026
0262063
Merge branch 'main' into unicodetata-bidis
StanFromIreland Feb 17, 2026
a51525d
Update checksum
StanFromIreland Feb 17, 2026
6a664e5
Review
StanFromIreland Feb 18, 2026
File filter

Filter by extension

Filter by extension .h  (1) .py  (2) .rst  (1) All 3 file types selected
Viewed files
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Unified
Split
Hide whitespace
Diff view
Unified
Split
Hide whitespace
21 changes: 16 additions & 5 deletions Lib/test/test_unicodedata.py
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
Expand Up @@ -319,7 +319,7 @@ def test_category(self):
self.assertRaises(TypeError, self.db.category, 'xx')

def test_bidirectional(self):
self.assertEqual(self.db.bidirectional('\uFFFE'), '')
self.assertEqual(self.db.bidirectional('\uFFFE'), 'BN')
self.assertEqual(self.db.bidirectional(' '), 'WS')
self.assertEqual(self.db.bidirectional('A'), 'L')
self.assertEqual(self.db.bidirectional('\U00020000'), 'L')
Expand Down Expand Up @@ -347,6 +347,17 @@ def test_bidirectional(self):
self.assertRaises(TypeError, self.db.bidirectional)
self.assertRaises(TypeError, self.db.bidirectional, 'xx')

def test_bidirectional_unassigned(self):
if self.old:
return
self.assertEqual(self.db.bidirectional('\u0378'), 'L')
self.assertEqual(self.db.bidirectional('\u077F'), 'AL')
self.assertEqual(self.db.bidirectional('\u20CF'), 'ET')
self.assertEqual(self.db.bidirectional('\u0590'), 'R')
self.assertEqual(self.db.bidirectional('\uFFFF'), 'BN')
self.assertEqual(self.db.bidirectional('\U0001FFFE'), 'BN')
self.assertEqual(self.db.bidirectional('\U00010D01'), 'AL')

def test_decomposition(self):
self.assertEqual(self.db.decomposition('\uFFFE'),'')
self.assertEqual(self.db.decomposition('\u00bc'), '<fraction> 0031 2044 0034')
Expand Down Expand Up @@ -676,9 +687,9 @@ class UnicodeFunctionsTest(unittest.TestCase, BaseUnicodeFunctionsTest):

# Update this if the database changes. Make sure to do a full rebuild
# (e.g. 'make distclean && make') to get the correct checksum.
expectedchecksum = ('83cc43a2fbb779185832b4c049217d80b05bf349'
expectedchecksum = ('668dbbea1136e69d4f00677a5988b23bc78aefc6'
if quicktest else
'180bdc91143d8aa2eb9dd6726e66d37606205942')
'b869af769bd8fe352c04622ab90533dc54df5cf3')

@requires_resource('network')
def test_all_names(self):
Expand Down Expand Up @@ -966,9 +977,9 @@ def graphemes(*args):
class Unicode_3_2_0_FunctionsTest(unittest.TestCase, BaseUnicodeFunctionsTest):
db = unicodedata.ucd_3_2_0
old = True
expectedchecksum = ('4154d8d1232837e255edf3cdcbb5ab184d71f4a4'
expectedchecksum = ('2164a66700e03cba9c9f5ed9e9a8d594d2da136a'
if quicktest else
'3aabaf66823b21b3d305dad804a62f6f6387c93e')
'a8276cec9b6991779c5bdaa46c1ae7cc50bc2403')


class UnicodeMiscTest(unittest.TestCase):
Expand Down
2 changes: 2 additions & 0 deletions Misc/NEWS.d/next/Library/2026-02-13-00-00-00.gh-issue-142224.BidiMissing.rst
Show comments
View file
Open in desktop
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters. Learn more about bidirectional Unicode characters
Show hidden characters
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
:func:`unicodedata.bidirectional` now return the correct default bidi class
for unassigned code points.
Loading
Loading
Back | FazBrowse Home | New Git URL