Add lookup tests and fix case-insensitivity for Tangut ideographs.

Author: serhiy-storchaka

Lib/test/test_ucn.py

@@ -111,6 +111,30 @@ def test_cjk_unified_ideographs(self):
         self.checkletter("cjK UniFIeD idEogRAph-2aBcD", "\U0002abcd")
         self.checkletter("CJk uNIfiEd IDeOGraPH-2AbCd", "\U0002abcd")
 
+    def test_tangut_ideographs(self):
+        self.checkletter("TANGUT IDEOGRAPH-17000", "\U00017000")
+        self.checkletter("TANGUT IDEOGRAPH-187FF", "\U000187ff")
+        self.checkletter("TANGUT IDEOGRAPH-18D00", "\U00018D00")
+        self.checkletter("TANGUT IDEOGRAPH-18D1E", "\U00018d1e")
+        self.checkletter("tangut ideograph-18d1e", "\U00018d1e")
+
+    def test_egyptian_hieroglyphs(self):
+        self.checkletter("EGYPTIAN HIEROGLYPH-13460", "\U00013460")
+        self.checkletter("EGYPTIAN HIEROGLYPH-143FA", "\U000143fa")
+        self.checkletter("egyptian hieroglyph-143fa", "\U000143fa")
+
+    def test_khitan_small_script_characters(self):
+        self.checkletter("KHITAN SMALL SCRIPT CHARACTER-18B00", "\U00018b00")
+        self.checkletter("KHITAN SMALL SCRIPT CHARACTER-18CD5", "\U00018cd5")
+        self.checkletter("KHITAN SMALL SCRIPT CHARACTER-18CFF", "\U00018cff")
+        self.checkletter("KHITAN SMALL SCRIPT CHARACTER-18CFF", "\U00018cff")
+        self.checkletter("khitan small script character-18cff", "\U00018cff")
+
+    def test_nushu_characters(self):
+        self.checkletter("NUSHU CHARACTER-1B170", "\U0001b170")
+        self.checkletter("NUSHU CHARACTER-1B2FB", "\U0001b2fb")
+        self.checkletter("nushu character-1b2fb", "\U0001b2fb")
+
     def test_bmp_characters(self):
         for code in range(0x10000):
             char = chr(code)

Modules/unicodedata.c

@@ -1498,7 +1498,7 @@ _getcode(const char* name, int namelen, Py_UCS4* code)
     }
 
     /* Check for Tangut ideographs. */
-    if (strncmp(name, "TANGUT IDEOGRAPH-", 17) == 0) {
+    if (PyOS_strnicmp(name, "TANGUT IDEOGRAPH-", 17) == 0) {
         /* Five hexdigits must follow. */
         unsigned int v = 0;
         name += 17;
@@ -1507,10 +1507,11 @@ _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++;