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

Also, standardize indentation of generated tables.
(cherry picked from commit 7c69c1c0)
Co-authored-by: Benjamin Peterson <benjamin@python.org>

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

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

Lib/test/test_unicodedata.py

@@ -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()

Misc/NEWS.d/next/Library/2018-06-05-20-22-30.bpo-33778._tSAS6.rst

+Update ``unicodedata``'s database to Unicode version 11.0.0.

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 */

Tools/unicode/makeunicodedata.py

 #
 # (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'),
@@ -276,8 +275,8 @@ def makeunicodedata(unicode, trace):
     print("struct reindex{int start;short count,index;};", file=fp)
     print("static struct reindex nfc_first[] = {", file=fp)
     for start,end in comp_first_ranges:
-        print("  { %d, %d, %d}," % (start,end-start,comp_first[start]), file=fp)
-    print("  {0,0,0}", file=fp)
+        print("    { %d, %d, %d}," % (start,end-start,comp_first[start]), file=fp)
+    print("    {0,0,0}", file=fp)
     print("};\n", file=fp)
     print("static struct reindex nfc_last[] = {", file=fp)
     for start,end in comp_last_ranges:
@@ -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()