update to Unicode 11.0.0 (closes bpo-33778) (GH-7439) (GH-7470)

Also, standardize indentation of generated tables. (cherry picked from commit 7c69c1c) Co-authored-by: Benjamin Peterson <benjamin@python.org>
python · Jun 7, 2018 · 4705ea3 · 4705ea3
1 parent d2a2af0
commit 4705ea3
Show file tree

Hide file tree

Showing 9 changed files with 28,286 additions and 26,103 deletions.
diff --git a/Doc/library/unicodedata.rst b/Doc/library/unicodedata.rst
@@ -17,8 +17,8 @@
 
 This module provides access to the Unicode Character Database (UCD) which
 defines character properties for all Unicode characters. The data contained in
-this database is compiled from the `UCD version 10.0.0
-<http://www.unicode.org/Public/10.0.0/ucd>`_.
+this database is compiled from the `UCD version 11.0.0
+<http://www.unicode.org/Public/11.0.0/ucd>`_.
 
 The module uses the same names and symbols as defined by Unicode
 Standard Annex #44, `"Unicode Character Database"
@@ -168,6 +168,6 @@ Examples:
 
 .. rubric:: Footnotes
 
-.. [#] http://www.unicode.org/Public/10.0.0/ucd/NameAliases.txt
+.. [#] http://www.unicode.org/Public/11.0.0/ucd/NameAliases.txt
 
-.. [#] http://www.unicode.org/Public/10.0.0/ucd/NamedSequences.txt
+.. [#] http://www.unicode.org/Public/11.0.0/ucd/NamedSequences.txt
diff --git a/Doc/reference/lexical_analysis.rst b/Doc/reference/lexical_analysis.rst
@@ -313,7 +313,7 @@ The Unicode category codes mentioned above stand for:
 * *Nd* - decimal numbers
 * *Pc* - connector punctuations
 * *Other_ID_Start* - explicit list of characters in `PropList.txt
-  <http://www.unicode.org/Public/10.0.0/ucd/PropList.txt>`_ to support backwards
+  <http://www.unicode.org/Public/11.0.0/ucd/PropList.txt>`_ to support backwards
   compatibility
 * *Other_ID_Continue* - likewise
 
@@ -876,4 +876,4 @@ occurrence outside string literals and comments is an unconditional error:
 
 .. rubric:: Footnotes
 
-.. [#] http://www.unicode.org/Public/10.0.0/ucd/NameAliases.txt
+.. [#] http://www.unicode.org/Public/11.0.0/ucd/NameAliases.txt
diff --git a/Lib/test/test_unicodedata.py b/Lib/test/test_unicodedata.py
@@ -20,7 +20,7 @@
 class UnicodeMethodsTest(unittest.TestCase):
 
     # update this, if the database changes
-    expectedchecksum = '727091e0fd5807eb41c72912ae95cdd74c795e27'
+    expectedchecksum = '97a41f208c53d5e08c77c1175187e95386b82b6f'
 
     def test_method_checksum(self):
         h = hashlib.sha1()
@@ -80,7 +80,7 @@ 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 = 'db6f92bb5010f8e85000634b08e77233355ab37a'
+    expectedchecksum = '4f73278b19c2ec3099724c132f0b90a1d25c19e4'
     def test_function_checksum(self):
         data = []
         h = hashlib.sha1()

diff --git a/Misc/NEWS.d/next/Library/2018-06-05-20-22-30.bpo-33778._tSAS6.rst b/Misc/NEWS.d/next/Library/2018-06-05-20-22-30.bpo-33778._tSAS6.rst
@@ -0,0 +1 @@
+Update ``unicodedata``'s database to Unicode version 11.0.0.
diff --git a/Modules/unicodedata.c b/Modules/unicodedata.c
@@ -921,7 +921,7 @@ is_unified_ideograph(Py_UCS4 code)
 {
     return
         (0x3400 <= code && code <= 0x4DB5)   || /* CJK Ideograph Extension A */
-        (0x4E00 <= code && code <= 0x9FEA)   || /* CJK Ideograph */
+        (0x4E00 <= code && code <= 0x9FEF)   || /* CJK Ideograph */
         (0x20000 <= code && code <= 0x2A6D6) || /* CJK Ideograph Extension B */
         (0x2A700 <= code && code <= 0x2B734) || /* CJK Ideograph Extension C */
         (0x2B740 <= code && code <= 0x2B81D) || /* CJK Ideograph Extension D */
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1 @@
		Update ``unicodedata``'s database to Unicode version 11.0.0.