Skip to content

gh-101372: Fix unicodedata.is_normalized to properly handle the UCD 3… #101388

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
corona10 merged 5 commits into from
Feb 6, 2023
Merged

gh-101372: Fix unicodedata.is_normalized to properly handle the UCD 3… #101388

Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
3cc6f06
gh-101372: Fix unicodedata.is_normalized to properly handle the UCD 3…
corona10 Jan 28, 2023
9e663af
Rename the test
corona10 Jan 28, 2023
d8edb54
Sampling test sets
corona10 Jan 28, 2023
080b6cc
Add multi multicharacter case
corona10 Jan 28, 2023
c197665
Address code review
corona10 Feb 6, 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
Address code review
  • Loading branch information
@corona10
corona10 committed Feb 6, 2023
commit c1976653b1fa15a08f4ff0008d001e1bbec0b602
16 changes: 0 additions & 16 deletions Lib/test/test_unicodedata.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,6 @@

import hashlib
from http.client import HTTPException
import random
import sys
import unicodedata
import unittest
Expand Down Expand Up @@ -217,21 +216,6 @@ def test_issue29456(self):
self.assertEqual(self.db.normalize('NFC', u11a7_str_a), u11a7_str_b)
self.assertEqual(self.db.normalize('NFC', u11c3_str_a), u11c3_str_b)

def test_is_normalized_unicode_3_2_0(self):
sample_chrs = random.sample(range(0x110000), 100)
for form in ('NFC', 'NFD', 'NFKC', 'NFKD'):
with self.subTest(form=form):
for x in sample_chrs:
norm = self.db.ucd_3_2_0.normalize(form, chr(x))
self.assertTrue(self.db.ucd_3_2_0.is_normalized(form, norm))

def test_is_normalized_unicode_3_2_0_multicharacter(self):
sample_chrs = random.sample(range(0x110000), 100)
for form in ('NFC', 'NFD', 'NFKC', 'NFKD'):
s = ''.join(map(chr, sample_chrs))
norm = self.db.ucd_3_2_0.normalize(form, s)
self.assertTrue(self.db.ucd_3_2_0.is_normalized(form, norm))

def test_east_asian_width(self):
eaw = self.db.east_asian_width
self.assertRaises(TypeError, eaw, b'a')
Expand Down