Merge pull request #66 from fonttools/unicode-17

Update to Unicode 17.0.0

Author: khaledhosny

.github/workflows/ci.yml

@@ -54,7 +54,7 @@ jobs:
     strategy:
       matrix:
         # aarch64 uses qemu so it's slow, build each py version in parallel jobs
-        python: [37, 38, 39, 310]
+        python: [38, 39, 310, 312, 313, 314]
         arch: [aarch64]
     env:
       CIBW_BUILD: cp${{ matrix.python }}-*

README.md

@@ -4,7 +4,7 @@
 unicodedata2
 ============
 
-[unicodedata] backport/updates.
+[unicodedata] backport/updates. Currently supports Unicode 17.0.0.
 
 The versions of this package match Unicode versions, so unicodedata2==13.0.0 is data from Unicode 13.0.0.
 

makeunicodedata.py

@@ -44,7 +44,7 @@
 #   * Doc/library/stdtypes.rst, and
 #   * Doc/library/unicodedata.rst
 #   * Doc/reference/lexical_analysis.rst (two occurrences)
-UNIDATA_VERSION = "16.0.0"
+UNIDATA_VERSION = "17.0.0"
 UNICODE_DATA = "UnicodeData%s.txt"
 COMPOSITION_EXCLUSIONS = "CompositionExclusions%s.txt"
 EASTASIAN_WIDTH = "EastAsianWidth%s.txt"
@@ -104,13 +104,14 @@
     ('3400', '4DBF'),    # CJK Ideograph Extension A CJK
     ('4E00', '9FFF'),    # CJK Ideograph
     ('20000', '2A6DF'),  # CJK Ideograph Extension B
-    ('2A700', '2B739'),  # CJK Ideograph Extension C
+    ('2A700', '2B73F'),  # CJK Ideograph Extension C
     ('2B740', '2B81D'),  # CJK Ideograph Extension D
-    ('2B820', '2CEA1'),  # CJK Ideograph Extension E
+    ('2B820', '2CEAD'),  # CJK Ideograph Extension E
     ('2CEB0', '2EBE0'),  # CJK Ideograph Extension F
     ('2EBF0', '2EE5D'),  # CJK Ideograph Extension I
     ('30000', '3134A'),  # CJK Ideograph Extension G
     ('31350', '323AF'),  # CJK Ideograph Extension H
+    ('323B0', '33479'),  # CJK Ideograph Extension J
 ]
 
 

setup.py

@@ -26,7 +26,7 @@
 
 setup(
     name="unicodedata2",
-    version="16.0.0",
+    version="17.0.0",
     description="Unicodedata backport updated to the latest Unicode version.",
     long_description=long_description,
     long_description_content_type="text/markdown",

tests/test_unicodedata2.py

@@ -33,7 +33,7 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
 
     # Update this if the database changes. Make sure to do a full rebuild
     # (e.g. 'make distclean && make') to get the correct checksum.
-    expectedchecksum = '23ab09ed4abdf93db23b97359108ed630dd8311d'
+    expectedchecksum = '2cf81cbeaa7cbc8f1ace57dd6c56d1f30f1a2de1'
 
     def test_function_checksum(self):
         import unicodedata2

tox.ini

@@ -1,5 +1,5 @@
 [tox]
-envlist = py{37,38,39,310,311,312}, pypy{37,38,39}
+envlist = py{38,39,310,311,312,313,314}, pypy{37,38,39}
 skip_missing_interpreters = true
 
 [testenv]