1. Lib/test/test_csv.py — 上下文调整

--- 适配前
+++ 适配后
@@ -1,6 +1,6 @@
-@@ -1357,6 +1357,13 @@ def test_sniff_space_delimiter(self):
-         self.assertEqual(dialect.delimiter, ' ')
-         self.assertIs(dialect.doublequote, False)
+@@ -1314,6 +1314,13 @@ def test_doublequote(self):
+         dialect = sniffer.sniff(self.sample9)
+         self.assertTrue(dialect.doublequote)
 
     def test_sniff_quoted_single_column(self):
         # gh-98820: this sample used to take minutes.
@@ -9,6 +9,6 @@
         with self.assertRaisesRegex(csv.Error, "Could not determine delimiter"):
             sniffer.sniff(sample, delimiters=',:|\t')
 
-
 class NUL:
      def write(s, *args):
+         pass

Lib/stringprep.py

--- 原补丁/Lib/stringprep.py
+++ 适配补丁/Lib/stringprep.py
@@ -1,4 +1,4 @@
-@@ -5,12 +5,18 @@
+@@ -5,12 +5,18 @@ There are two kinds of tables: sets, for which a member test is provided,
  and mappings, for which a mapping function is provided.
  """
  
@@ -8,7 +8,7 @@
 +import unicodedata
  
 -assert unicodedata.unidata_version == '3.2.0'
-+assert unicodedata.unidata_version == '16.0.0'
++assert unicodedata.unidata_version == '13.0.0'
 +
 +from unicodedata import ucd_3_2_0 as unicodedata_320
 +
@@ -298,7 +298,7 @@
  0x1d402:'c', 0x1d403:'d', 0x1d404:'e', 0x1d405:'f',
  0x1d406:'g', 0x1d407:'h', 0x1d408:'i', 0x1d409:'j',
  0x1d40a:'k', 0x1d40b:'l', 0x1d40c:'m', 0x1d40d:'n',
-@@ -184,7 +359,16 @@ def in_table_b1(code):
+@@ -184,7 +359,16 @@ b3_exceptions = {
  0x1d79c:'\u03bd', 0x1d79d:'\u03be', 0x1d79e:'\u03bf', 0x1d79f:'\u03c0',
  0x1d7a0:'\u03c1', 0x1d7a1:'\u03b8', 0x1d7a2:'\u03c3', 0x1d7a3:'\u03c4',
  0x1d7a4:'\u03c5', 0x1d7a5:'\u03c6', 0x1d7a6:'\u03c7', 0x1d7a7:'\u03c8',

Lib/test/test_codecs.py

--- 原补丁/Lib/test/test_codecs.py
+++ 适配补丁/Lib/test/test_codecs.py
@@ -1,16 +1,17 @@
-@@ -1622,6 +1622,15 @@ def test_builtin_encode(self):
+@@ -1544,6 +1544,16 @@ class IDNACodecTest(unittest.TestCase):
          self.assertEqual("pyth\xf6n.org".encode("idna"), b"xn--pythn-mua.org")
          self.assertEqual("pyth\xf6n.org.".encode("idna"), b"xn--pythn-mua.org.")
  
-+    @support.subTests(['unicode', 'encoded'], [
-+        ('\N{CHEROKEE LETTER A}\N{CHEROKEE LETTER A}', b"xn--58da"),
-+        ('\N{GEORGIAN CAPITAL LETTER AN}.', b"xn--7md."),
-+        ('\N{CYRILLIC LETTER PALOCHKA}.example', b"xn--d5a.example"),
-+        ('\N{ROMAN NUMERAL REVERSED ONE HUNDRED}.example.', b"xn--q5g.example."),
-+    ])
-+    def test_new_unicode_case_folding(self, unicode, encoded):
-+        self.assertEqual(unicode.encode("idna"), encoded)
++    def test_new_unicode_case_folding(self):
++        for unicode, encoded in [
++            ('\N{CHEROKEE LETTER A}\N{CHEROKEE LETTER A}', b"xn--58da"),
++            ('\N{GEORGIAN CAPITAL LETTER AN}.', b"xn--7md."),
++            ('\N{CYRILLIC LETTER PALOCHKA}.example', b"xn--d5a.example"),
++            ('\N{ROMAN NUMERAL REVERSED ONE HUNDRED}.example.', b"xn--q5g.example."),
++        ]:
++            with self.subTest(unicode=unicode, encoded=encoded):
++                self.assertEqual(unicode.encode("idna"), encoded)
 +
-     def test_builtin_encode_invalid(self):
-         for case, expected in self.invalid_encode_testcases:
-             with self.subTest(case=case, expected=expected):
+     def test_builtin_decode_length_limit(self):
+         with self.assertRaisesRegex(UnicodeError, "too long"):
+             (b"xn--016c"+b"a"*1100).decode("idna")

Lib/test/test_unicodedata.py

--- 原补丁/Lib/test/test_unicodedata.py
+++ 适配补丁/Lib/test/test_unicodedata.py
@@ -1,15 +1,15 @@
-@@ -328,6 +328,15 @@ def test_bidirectional(self):
+@@ -150,6 +150,15 @@ class UnicodeFunctionsTest(UnicodeDatabaseTest):
          self.assertRaises(TypeError, self.db.bidirectional)
          self.assertRaises(TypeError, self.db.bidirectional, 'xx')
  
 +    def test_bidirectional_unassigned(self):
 +        self.assertEqual(self.db.bidirectional('\u0378'), '')
-+        self.assertEqual(self.db.bidirectional('\u077F'), '' if self.old else 'AL')
++        self.assertEqual(self.db.bidirectional('\u077F'), 'AL')
 +        self.assertEqual(self.db.bidirectional('\u20CF'), '')
 +        self.assertEqual(self.db.bidirectional('\u0590'), '')
 +        self.assertEqual(self.db.bidirectional('\uFFFF'), '')
 +        self.assertEqual(self.db.bidirectional('\U0001FFFE'), '')
-+        self.assertEqual(self.db.bidirectional('\U00010D01'), '' if self.old else 'AL')
++        self.assertEqual(self.db.bidirectional('\U00010D01'), 'AL')
 +
      def test_decomposition(self):
          self.assertEqual(self.db.decomposition('\uFFFE'),'')

Tools/unicode/makeunicodedata.py

--- 原补丁/Tools/unicode/makeunicodedata.py
+++ 适配补丁/Tools/unicode/makeunicodedata.py
@@ -6,7 +6,7 @@
  import sys
  import zipfile
  
-@@ -126,6 +127,7 @@ def maketables(trace=0):
+@@ -128,6 +129,7 @@ def maketables(trace=0):
      makeunicodename(unicode, trace)
      makeunicodedata(unicode, trace)
      makeunicodetype(unicode, trace)
@@ -14,11 +14,10 @@
  
  
  # --------------------------------------------------------------------
-@@ -711,6 +713,19 @@ def makeunicodename(unicode, trace):
-             fprint('    "%s",' % prefix)
+@@ -792,6 +794,18 @@ def makeunicodename(unicode, trace):
          fprint('};')
  
-+
+ 
 +def makestringprep():
 +    FILE = "Lib/stringprep.py"
 +

Tools/unicode/mkstringprep.py

--- 原补丁/Tools/unicode/mkstringprep.py
+++ 适配补丁/Tools/unicode/mkstringprep.py
@@ -43,7 +43,7 @@
  
  tables = []
  curname = None
-@@ -116,10 +129,18 @@ def compact_set(l):
+@@ -116,10 +129,18 @@ There are two kinds of tables: sets, for which a member test is provided,
  and mappings, for which a mapping function is provided.
  \"\"\"
  
@@ -64,7 +64,7 @@
  
  # A.1 is the table of unassigned characters
  # XXX Plane 15 PUA is listed as unassigned in Python.
-@@ -139,7 +160,7 @@ def compact_set(l):
+@@ -139,7 +160,7 @@ Cn -= set(range(0xFFFF, 0x110000, 0x10000))
  
  print("""
  def in_table_a1(code):
@@ -73,7 +73,7 @@
      c = ord(code)
      if 0xFDD0 <= c < 0xFDF0: return False
      return (c & 0xFFFF) not in (0xFFFE, 0xFFFF)
-@@ -172,21 +193,33 @@ def in_table_b1(code):
+@@ -172,21 +193,33 @@ assert name == "B.3"
  
  # B.3 is mostly Python's .lower, except for a number
  # of special cases, e.g. considering canonical forms.
@@ -122,7 +122,7 @@
      if b != c:
          return c
      else:
-@@ -226,9 +259,9 @@ def map_table_b2(a):
+@@ -226,9 +259,9 @@ assert specials == {}
  print("""
  def map_table_b2(a):
      al = map_table_b3(a)
@@ -134,7 +134,7 @@
      if b != c:
          return c
      else:
-@@ -251,16 +284,16 @@ def in_table_c11(code):
+@@ -251,16 +284,16 @@ name, table = tables[0]
  del tables[0]
  assert name == "C.1.2"
  
@@ -156,7 +156,7 @@
  """)
  
  # C.2.1 ASCII control characters
-@@ -275,7 +308,7 @@ def in_table_c11_c12(code):
+@@ -275,7 +308,7 @@ assert Cc_ascii == table_c21
  
  print("""
  def in_table_c21(code):
@@ -165,7 +165,7 @@
  """)
  
  # C.2.2 Non-ASCII control characters. It also includes
-@@ -295,11 +328,11 @@ def in_table_c21(code):
+@@ -295,11 +328,11 @@ print("""c22_specials = """ + compact_set(specials) + """
  def in_table_c22(code):
      c = ord(code)
      if c < 128: return False
@@ -179,7 +179,7 @@
             ord(code) in c22_specials
  """)
  
-@@ -313,7 +346,7 @@ def in_table_c21_c22(code):
+@@ -313,7 +346,7 @@ assert set(table.keys()) == Co
  
  print("""
  def in_table_c3(code):
@@ -188,7 +188,7 @@
  """)
  
  # C.4 Non-character code points, xFFFE, xFFFF
-@@ -346,7 +379,7 @@ def in_table_c4(code):
+@@ -346,7 +379,7 @@ assert set(table.keys()) == Cs
  
  print("""
  def in_table_c5(code):
@@ -197,7 +197,7 @@
  """)
  
  # C.6 Inappropriate for plain text
-@@ -411,7 +444,7 @@ def in_table_c9(code):
+@@ -411,7 +444,7 @@ assert set(table.keys()) == RandAL
  
  print("""
  def in_table_d1(code):
@@ -206,7 +206,7 @@
  """)
  
  # D.2 Characters with bidirectional property "L"
-@@ -424,5 +457,5 @@ def in_table_d1(code):
+@@ -424,5 +457,5 @@ assert set(table.keys()) == L
  
  print("""
  def in_table_d2(code):

Lib/csv.py

--- 原补丁/Lib/csv.py
+++ 适配补丁/Lib/csv.py
@@ -1,4 +1,4 @@
-@@ -215,12 +215,18 @@ def _guess_quote_and_delimiter(self, data, delimiters):
+@@ -213,12 +213,18 @@ class Sniffer:
          this way.
          """
  

Lib/test/test_csv.py

--- 原补丁/Lib/test/test_csv.py
+++ 适配补丁/Lib/test/test_csv.py
@@ -1,6 +1,6 @@
-@@ -1232,6 +1232,13 @@ def test_sniff_space_delimiter(self):
-         self.assertEqual(dialect.delimiter, ' ')
-         self.assertIs(dialect.doublequote, False)
+@@ -1104,6 +1104,13 @@ Stonecutters Seafood and Chop House+ Lemont+ IL+ 12/19/02+ Week Back
+         dialect = sniffer.sniff(self.sample9)
+         self.assertTrue(dialect.doublequote)
  
 +    def test_sniff_quoted_single_column(self):
 +        # gh-98820: this sample used to take minutes.
@@ -9,6 +9,6 @@
 +        with self.assertRaisesRegex(csv.Error, "Could not determine delimiter"):
 +            sniffer.sniff(sample, delimiters=',:|\t')
 +
- 
  class NUL:
      def write(s, *args):
+         pass