traverseda
/
cpython
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

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

Also, standardize indentation of generated tables.
This commit is contained in:
Benjamin Peterson 2018-06-06 20:14:28 -07:00 committed by GitHub
parent 9f04f0df6f
commit 7c69c1c0fb
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
9 changed files with 29405 additions and 27222 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
Doc/library/unicodedata.rst
View File

@ -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

4
Doc/reference/lexical_analysis.rst
View File

@ -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

4
Lib/test/test_unicodedata.py
View File

@ -20,7 +20,7 @@ errors = 'surrogatepass'
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()

1
Misc/NEWS.d/next/Library/2018-06-05-20-22-30.bpo-33778._tSAS6.rst Normal file
View File

@ -0,0 +1 @@
Update ``unicodedata``'s database to Unicode version 11.0.0.

2
Modules/unicodedata.c
View File

@ -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 */

4815
Modules/unicodedata_db.h
View File

File diff suppressed because it is too large Load Diff

48614
Modules/unicodename_db.h
View File

File diff suppressed because it is too large Load Diff

2576
Objects/unicodetype_db.h
View File

File diff suppressed because it is too large Load Diff

35
Tools/unicode/makeunicodedata.py
View File

@ -1,9 +1,8 @@
#
# (re)generate unicode property and type databases
#
# this script converts a unicode 3.2 database file to
# Modules/unicodedata_db.h, Modules/unicodename_db.h,
# and Objects/unicodetype_db.h
# This script converts Unicode database files to Modules/unicodedata_db.h,
# Modules/unicodename_db.h, and Objects/unicodetype_db.h
#
# history:
# 2000-09-24 fl created (based on bits and pieces from unidb)
@ -34,7 +33,7 @@ import zipfile
from textwrap import dedent
SCRIPT = sys.argv[0]
VERSION = "3.2"
VERSION = "3.3"
# The Unicode Database
# --------------------
@ -42,7 +41,7 @@ VERSION = "3.2"
# * Doc/library/stdtypes.rst, and
# * Doc/library/unicodedata.rst
# * Doc/reference/lexical_analysis.rst (two occurrences)
UNIDATA_VERSION = "10.0.0"
UNIDATA_VERSION = "11.0.0"
UNICODE_DATA = "UnicodeData%s.txt"
COMPOSITION_EXCLUSIONS = "CompositionExclusions%s.txt"
EASTASIAN_WIDTH = "EastAsianWidth%s.txt"
@ -99,7 +98,7 @@ EXTENDED_CASE_MASK = 0x4000
# these ranges need to match unicodedata.c:is_unified_ideograph
cjk_ranges = [
('3400', '4DB5'),
('4E00', '9FEA'),
('4E00', '9FEF'),
('20000', '2A6D6'),
('2A700', '2B734'),
('2B740', '2B81D'),
@ -353,28 +352,28 @@ def makeunicodedata(unicode, trace):
index1, index2, shift = splitbins(index, trace)
print("static const change_record change_records_%s[] = {" % cversion, file=fp)
for record in records:
print("\t{ %s }," % ", ".join(map(str,record)), file=fp)
print(" { %s }," % ", ".join(map(str,record)), file=fp)
print("};", file=fp)
Array("changes_%s_index" % cversion, index1).dump(fp, trace)
Array("changes_%s_data" % cversion, index2).dump(fp, trace)
print("static const change_record* get_change_%s(Py_UCS4 n)" % cversion, file=fp)
print("{", file=fp)
print("\tint index;", file=fp)
print("\tif (n >= 0x110000) index = 0;", file=fp)
print("\telse {", file=fp)
print("\t\tindex = changes_%s_index[n>>%d];" % (cversion, shift), file=fp)
print("\t\tindex = changes_%s_data[(index<<%d)+(n & %d)];" % \
print(" int index;", file=fp)
print(" if (n >= 0x110000) index = 0;", file=fp)
print(" else {", file=fp)
print(" index = changes_%s_index[n>>%d];" % (cversion, shift), file=fp)
print(" index = changes_%s_data[(index<<%d)+(n & %d)];" % \
(cversion, shift, ((1<<shift)-1)), file=fp)
print("\t}", file=fp)
print("\treturn change_records_%s+index;" % cversion, file=fp)
print(" }", file=fp)
print(" return change_records_%s+index;" % cversion, file=fp)
print("}\n", file=fp)
print("static Py_UCS4 normalization_%s(Py_UCS4 n)" % cversion, file=fp)
print("{", file=fp)
print("\tswitch(n) {", file=fp)
print(" switch(n) {", file=fp)
for k, v in normalization:
print("\tcase %s: return 0x%s;" % (hex(k), v), file=fp)
print("\tdefault: return 0;", file=fp)
print("\t}\n}\n", file=fp)
print(" case %s: return 0x%s;" % (hex(k), v), file=fp)
print(" default: return 0;", file=fp)
print(" }\n}\n", file=fp)
fp.close()