gh-80667: Fix case-sensitivity of some Unicode literal escapes (GH-107281)

Lookup for CJK ideograms and Hangul syllables is now case-insensitive,
as is the case for other character names.

diff --git a/Lib/test/test_ucn.py b/Lib/test/test_ucn.py
index 0e2c25aaff2fe9dadb3439b302da25c54ee76fab..0c641a455c0747cb81e027c49c5f9eee452dd0f8 100644 (file)
--- a/Lib/test/test_ucn.py
+++ b/Lib/test/test_ucn.py
@@ -88,6 +88,9 @@ class UnicodeNamesTest(unittest.TestCase):
         self.checkletter("HANGUL SYLLABLE HWEOK", "\ud6f8")
         self.checkletter("HANGUL SYLLABLE HIH", "\ud7a3")
 
+        self.checkletter("haNGul SYllABle WAe", '\uc65c')
+        self.checkletter("HAngUL syLLabLE waE", '\uc65c')
+
         self.assertRaises(ValueError, unicodedata.name, "\ud7a4")
 
     def test_cjk_unified_ideographs(self):
@@ -103,6 +106,11 @@ class UnicodeNamesTest(unittest.TestCase):
         self.checkletter("CJK UNIFIED IDEOGRAPH-2B81D", "\U0002B81D")
         self.checkletter("CJK UNIFIED IDEOGRAPH-3134A", "\U0003134A")
 
+        self.checkletter("cjK UniFIeD idEogRAph-3aBc", "\u3abc")
+        self.checkletter("CJk uNIfiEd IDeOGraPH-3AbC", "\u3abc")
+        self.checkletter("cjK UniFIeD idEogRAph-2aBcD", "\U0002abcd")
+        self.checkletter("CJk uNIfiEd IDeOGraPH-2AbCd", "\U0002abcd")
+
     def test_bmp_characters(self):
         for code in range(0x10000):
             char = chr(code)

diff --git a/Misc/NEWS.d/next/Core_and_Builtins/2023-07-26-00-03-00.gh-issue-80667.N7Dh8B.rst b/Misc/NEWS.d/next/Core_and_Builtins/2023-07-26-00-03-00.gh-issue-80667.N7Dh8B.rst
new file mode 100644 (file)
index 0000000..db87a5e
--- /dev/null
+++ b/Misc/NEWS.d/next/Core_and_Builtins/2023-07-26-00-03-00.gh-issue-80667.N7Dh8B.rst
@@ -0,0 +1,2 @@
+Literals using the ``\N{name}`` escape syntax can now construct CJK
+ideographs and Hangul syllables using case-insensitive names.

diff --git a/Modules/unicodedata.c b/Modules/unicodedata.c
index 091e6bcb9f3f49b423b93196f95d583fdf64895b..44ffedec3840fea52eea8470476c96d2328a27e3 100644 (file)
--- a/Modules/unicodedata.c
+++ b/Modules/unicodedata.c
@@ -1405,7 +1405,7 @@ find_syllable(const char *str, int *len, int *pos, int count, int column)
         len1 = Py_SAFE_DOWNCAST(strlen(s), size_t, int);
         if (len1 <= *len)
             continue;
-        if (strncmp(str, s, len1) == 0) {
+        if (PyOS_strnicmp(str, s, len1) == 0) {
             *len = len1;
             *pos = i;
         }
@@ -1437,7 +1437,7 @@ _getcode(const char* name, int namelen, Py_UCS4* code)
      * PUA */
 
     /* Check for hangul syllables. */
-    if (strncmp(name, "HANGUL SYLLABLE ", 16) == 0) {
+    if (PyOS_strnicmp(name, "HANGUL SYLLABLE ", 16) == 0) {
         int len, L = -1, V = -1, T = -1;
         const char *pos = name + 16;
         find_syllable(pos, &len, &L, LCount, 0);
@@ -1455,7 +1455,7 @@ _getcode(const char* name, int namelen, Py_UCS4* code)
     }
 
     /* Check for unified ideographs. */
-    if (strncmp(name, "CJK UNIFIED IDEOGRAPH-", 22) == 0) {
+    if (PyOS_strnicmp(name, "CJK UNIFIED IDEOGRAPH-", 22) == 0) {
         /* Four or five hexdigits must follow. */
         unsigned int v;
         v = 0;
@@ -1465,10 +1465,11 @@ _getcode(const char* name, int namelen, Py_UCS4* code)
             return 0;
         while (namelen--) {
             v *= 16;
-            if (*name >= '0' && *name <= '9')
-                v += *name - '0';
-            else if (*name >= 'A' && *name <= 'F')
-                v += *name - 'A' + 10;
+            Py_UCS1 c = Py_TOUPPER(*name);
+            if (c >= '0' && c <= '9')
+                v += c - '0';
+            else if (c >= 'A' && c <= 'F')
+                v += c - 'A' + 10;
             else
                 return 0;
             name++;