Thanks to visit codestin.com
Credit goes to github.com

Skip to content

Commit 94d08d9

Browse files
benjaminpbenjaminp
committed
upgrade unicode db to 6.3.0 (closes #19221)
1 parent 78d692f commit 94d08d9

8 files changed

Lines changed: 17195 additions & 17153 deletions

File tree

‎Doc/library/unicodedata.rst‎

Lines changed: 4 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -15,8 +15,8 @@
1515

1616
This module provides access to the Unicode Character Database (UCD) which
1717
defines character properties for all Unicode characters. The data contained in
18-
this database is compiled from the `UCD version 6.2.0
19-
<http://www.unicode.org/Public/6.2.0/ucd>`_.
18+
this database is compiled from the `UCD version 6.3.0
19+
<http://www.unicode.org/Public/6.3.0/ucd>`_.
2020

2121
The module uses the same names and symbols as defined by Unicode
2222
Standard Annex #44, `"Unicode Character Database"
@@ -166,6 +166,6 @@ Examples:
166166

167167
.. rubric:: Footnotes
168168

169-
.. [#] http://www.unicode.org/Public/6.2.0/ucd/NameAliases.txt
169+
.. [#] http://www.unicode.org/Public/6.3.0/ucd/NameAliases.txt
170170
171-
.. [#] http://www.unicode.org/Public/6.2.0/ucd/NamedSequences.txt
171+
.. [#] http://www.unicode.org/Public/6.3.0/ucd/NamedSequences.txt

‎Lib/test/test_unicodedata.py‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -21,7 +21,7 @@
2121
class UnicodeMethodsTest(unittest.TestCase):
2222

2323
# update this, if the database changes
24-
expectedchecksum = 'bf7a78f1a532421b5033600102e23a92044dbba9'
24+
expectedchecksum = 'e74e878de71b6e780ffac271785c3cb58f6251f3'
2525

2626
def test_method_checksum(self):
2727
h = hashlib.sha1()

‎Misc/NEWS‎

Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -10,6 +10,8 @@ Projected release date: 2013-10-20
1010
Core and Builtins
1111
-----------------
1212

13+
- Issue #19221: Upgrade Unicode database to version 6.3.0.
14+
1315
- Issue #16742: The result of the C callback PyOS_ReadlineFunctionPointer must
1416
now be a string allocated by PyMem_RawMalloc() or PyMem_RawRealloc() (or NULL
1517
if an error occurred), instead of a string allocated by PyMem_Malloc() or

‎Modules/unicodedata.c‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1322,10 +1322,10 @@ PyDoc_STRVAR(unicodedata_docstring,
13221322
"This module provides access to the Unicode Character Database which\n\
13231323
defines character properties for all Unicode characters. The data in\n\
13241324
this database is based on the UnicodeData.txt file version\n\
1325-
6.0.0 which is publically available from ftp://ftp.unicode.org/.\n\
1325+
6.3.0 which is publically available from ftp://ftp.unicode.org/.\n\
13261326
\n\
13271327
The module uses the same names and symbols as defined by the\n\
1328-
UnicodeData File Format 6.0.0 (see\n\
1328+
UnicodeData File Format 6.3.0 (see\n\
13291329
http://www.unicode.org/reports/tr44/tr44-6.html).");
13301330

13311331

‎Modules/unicodedata_db.h‎

Lines changed: 792 additions & 784 deletions
Large diffs are not rendered by default.

‎Modules/unicodename_db.h‎

Lines changed: 16386 additions & 16352 deletions
Large diffs are not rendered by default.

‎Objects/unicodetype_db.h‎

Lines changed: 6 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -1589,7 +1589,7 @@ static unsigned short index2[] = {
15891589
55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 0, 0,
15901590
0, 0, 0, 55, 55, 55, 5, 6, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 21, 21, 21,
15911591
21, 21, 0, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 25, 25, 25, 25, 25, 25, 25, 25,
1592-
25, 25, 25, 5, 0, 0, 5, 5, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,
1592+
25, 25, 25, 5, 21, 0, 5, 5, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,
15931593
55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,
15941594
55, 55, 55, 96, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 25, 25, 25, 25,
15951595
25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 25, 7, 8,
@@ -1801,7 +1801,7 @@ static unsigned short index2[] = {
18011801
25, 25, 25, 25, 25, 25, 25, 25, 5, 5, 5, 96, 5, 5, 5, 5, 55, 25, 0, 0, 7,
18021802
8, 9, 10, 11, 12, 13, 14, 15, 16, 0, 0, 0, 0, 0, 0, 27, 27, 27, 27, 27,
18031803
27, 27, 27, 27, 27, 0, 0, 0, 0, 0, 0, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
1804-
25, 25, 25, 2, 0, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 0, 0, 0, 0, 0, 0,
1804+
25, 25, 25, 21, 0, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 0, 0, 0, 0, 0, 0,
18051805
55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,
18061806
55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 96,
18071807
55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,
@@ -1828,7 +1828,7 @@ static unsigned short index2[] = {
18281828
7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 132, 0, 0, 0, 5, 5, 5, 5, 5, 5, 5,
18291829
5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
18301830
5, 5, 5, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,
1831-
55, 55, 55, 55, 55, 55, 55, 25, 25, 18, 18, 18, 0, 0, 5, 5, 55, 55, 55,
1831+
55, 55, 55, 55, 55, 55, 55, 25, 25, 18, 18, 25, 0, 0, 5, 5, 55, 55, 55,
18321832
55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,
18331833
55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,
18341834
55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 18, 25, 18, 25,
@@ -1915,7 +1915,7 @@ static unsigned short index2[] = {
19151915
5, 5, 5, 5, 5, 5, 5, 5, 5, 6, 5, 5, 6, 3, 3, 21, 21, 21, 21, 21, 2, 5, 5,
19161916
5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 18, 18, 5, 5, 5, 5, 5, 5, 5, 5, 5,
19171917
5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 18, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 2, 21,
1918-
21, 21, 21, 21, 0, 0, 0, 0, 0, 21, 21, 21, 21, 21, 21, 245, 95, 0, 0,
1918+
21, 21, 21, 21, 0, 21, 21, 21, 21, 21, 21, 21, 21, 21, 21, 245, 95, 0, 0,
19191919
246, 247, 248, 249, 250, 251, 5, 5, 5, 5, 5, 95, 245, 26, 22, 23, 246,
19201920
247, 248, 249, 250, 251, 5, 5, 5, 5, 5, 0, 95, 95, 95, 95, 95, 95, 95,
19211921
95, 95, 95, 95, 95, 95, 0, 0, 0, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5,
@@ -2925,9 +2925,6 @@ static unsigned short index2[] = {
29252925
double _PyUnicode_ToNumeric(Py_UCS4 ch)
29262926
{
29272927
switch (ch) {
2928-
case 0x12456:
2929-
case 0x12457:
2930-
return (double) -1.0;
29312928
case 0x0F33:
29322929
return (double) -1.0/2.0;
29332930
case 0x0030:
@@ -3383,6 +3380,7 @@ double _PyUnicode_ToNumeric(Py_UCS4 ch)
33833380
case 0x12435:
33843381
case 0x1244A:
33853382
case 0x12450:
3383+
case 0x12456:
33863384
case 0x12459:
33873385
case 0x1D361:
33883386
case 0x1D7D0:
@@ -3539,6 +3537,7 @@ double _PyUnicode_ToNumeric(Py_UCS4 ch)
35393537
case 0x1243B:
35403538
case 0x1244B:
35413539
case 0x12451:
3540+
case 0x12457:
35423541
case 0x1D362:
35433542
case 0x1D7D1:
35443543
case 0x1D7DB:
@@ -4294,7 +4293,6 @@ int _PyUnicode_IsWhitespace(const Py_UCS4 ch)
42944293
case 0x0085:
42954294
case 0x00A0:
42964295
case 0x1680:
4297-
case 0x180E:
42984296
case 0x2000:
42994297
case 0x2001:
43004298
case 0x2002:

‎Tools/unicode/makeunicodedata.py‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -37,7 +37,7 @@
3737
VERSION = "3.2"
3838

3939
# The Unicode Database
40-
UNIDATA_VERSION = "6.2.0"
40+
UNIDATA_VERSION = "6.3.0"
4141
UNICODE_DATA = "UnicodeData%s.txt"
4242
COMPOSITION_EXCLUSIONS = "CompositionExclusions%s.txt"
4343
EASTASIAN_WIDTH = "EastAsianWidth%s.txt"
@@ -68,7 +68,7 @@
6868

6969
BIDIRECTIONAL_NAMES = [ "", "L", "LRE", "LRO", "R", "AL", "RLE", "RLO",
7070
"PDF", "EN", "ES", "ET", "AN", "CS", "NSM", "BN", "B", "S", "WS",
71-
"ON" ]
71+
"ON", "LRI", "RLI", "FSI", "PDI" ]
7272

7373
EASTASIANWIDTH_NAMES = [ "F", "H", "W", "Na", "A", "N" ]
7474

0 commit comments

Comments
 (0)