Stop being lazy

Author: StanFromIreland

Doc/library/unicodedata.rst

@@ -133,7 +133,7 @@ following functions:
 .. function:: block(chr, /)
 
    Returns the `block
-   <https://www.unicode.org/versions/17.0.0/core-spec/chapter-3/#G64189>`_
+   <https://www.unicode.org/versions/Unicode17.0.0/core-spec/chapter-3/#G64189>`_
    assigned to the character *chr*. For example::
 
       >>> unicodedata.block('S')

Doc/whatsnew/3.15.rst

@@ -1135,7 +1135,7 @@ unicodedata
   (Contributed by Serhiy Storchaka and Guillaume Sanchez in :gh:`74902`.)
 
 * Add :func:`~unicodedata.block` function to return the `Unicode block
-  <https://www.unicode.org/versions/17.0.0/core-spec/chapter-3/#G64189>`_
+  <https://www.unicode.org/versions/Unicode17.0.0/core-spec/chapter-3/#G64189>`_
   assigned to a character.
   (Contributed by Stan Ulbrych in :gh:`66802`.)
 

Lib/test/test_unicodedata.py

@@ -1057,6 +1057,7 @@ def test_block(self):
         self.assertEqual(self.db.block('\U00100000'), 'Supplementary Private Use Area-B')
         self.assertEqual(self.db.block('\U0010FFFF'), 'Supplementary Private Use Area-B')
 
+    def test_block_invalid_input(self):
         self.assertRaises(TypeError, self.db.block)
         self.assertRaises(TypeError, self.db.block, b'x')
         self.assertRaises(TypeError, self.db.block, 120)

Misc/NEWS.d/next/Library/2026-02-20-13-03-10.gh-issue-66802.OYcAi_.rst

@@ -1,3 +1,3 @@
 Add :func:`unicodedata.block` function to return the `Unicode block
-<https://www.unicode.org/versions/17.0.0/core-spec/chapter-3/#G64189>`_ of a
+<https://www.unicode.org/versions/Unicode17.0.0/core-spec/chapter-3/#G64189>`_ of a
 character.

Modules/unicodedata.c

@@ -2080,17 +2080,18 @@ unicodedata_block_impl(PyObject *module, int chr)
 /*[clinic end generated code: output=5f8b40c49eaec75a input=0834cf2642d6eaae]*/
 {
     Py_UCS4 c = (Py_UCS4)chr;
-    int l = 0, h = BLOCK_COUNT - 1;
-    while (l <= h) {
-        int m = (l + h) / 2;
-        if (c < _PyUnicode_Blocks[m].s) {
-            h = m - 1;
+    int lo = 0, hi = BLOCK_COUNT - 1;
+    while (lo <= hi) {
+        int mid = (lo + hi) / 2;
+        if (c < _PyUnicode_Blocks[mid].start) {
+            hi = mid - 1;
         }
-        else if (c > _PyUnicode_Blocks[m].e) {
-            l = m + 1;
+        else if (c > _PyUnicode_Blocks[mid].end) {
+            lo = mid + 1;
         }
         else {
-            return PyUnicode_FromString(_PyUnicode_BlockNames[_PyUnicode_Blocks[m].name]);
+            size_t name = _PyUnicode_Blocks[mid].name;
+            return PyUnicode_FromString(_PyUnicode_BlockNames[name]);
         }
     }
     // Otherwise, return the default value per

Modules/unicodedata_db.h

@@ -397,26 +397,26 @@ def makeunicodedata(unicode, trace):
         names = []
         name_to_index = {}
         blocks = []
-        for s, e, name in unicode.blocks:
+        for start, end, name in unicode.blocks:
             if name not in name_to_index:
                 name_to_index[name] = len(names)
                 names.append(name)
-            blocks.append((s, e, name_to_index[name]))
+            blocks.append((start, end, name_to_index[name]))
 
         fprint("static const char * const _PyUnicode_BlockNames[] = {")
         for name in names:
             fprint('    "%s",' % name)
         fprint("};")
 
         fprint("typedef struct {")
-        fprint("    Py_UCS4 s;")
-        fprint("    Py_UCS4 e;")
+        fprint("    Py_UCS4 start;")
+        fprint("    Py_UCS4 end;")
         fprint("    unsigned short name;")
         fprint("} _PyUnicode_Block;")
 
         fprint("static const _PyUnicode_Block _PyUnicode_Blocks[] = {")
-        for s, e, name in blocks:
-            fprint("    {0x%04X, 0x%04X, %d}," % (s, e, name))
+        for start, end, name in blocks:
+            fprint("    {0x%04X, 0x%04X, %d}," % (start, end, name))
         fprint("};")
         fprint(f"#define BLOCK_COUNT {len(blocks)}")
         fprint()
@@ -1238,8 +1238,8 @@ def __init__(self, version, ideograph_check=True):
             self.blocks = []
             for record in UcdFile(BLOCKS, version).records():
                 start_end, name = record
-                s, e = [int(c, 16) for c in start_end.split('..')]
-                self.blocks.append((s, e, name))
+                start, end = [int(c, 16) for c in start_end.split('..')]
+                self.blocks.append((start, end, name))
             self.blocks.sort()
 
     def uselatin1(self):