gh-121562: optimized hex_from_char (#121563)

Performance improvement to `float.fromhex`: use a lookup table
for computing the hexadecimal value of a character, in place of the
previous switch-case construct. Patch by Bruno Lima.

diff --git a/Misc/NEWS.d/next/Core and Builtins/2024-07-10-02-02-32.gh-issue-121562.8beIMi.rst b/Misc/NEWS.d/next/Core and Builtins/2024-07-10-02-02-32.gh-issue-121562.8beIMi.rst
new file mode 100644 (file)
index 0000000..9403809
--- /dev/null
+++ b/Misc/NEWS.d/next/Core and Builtins/2024-07-10-02-02-32.gh-issue-121562.8beIMi.rst
@@ -0,0 +1,2 @@
+Optimized performance of hex_from_char by replacing switch-case with a
+lookup table

diff --git a/Objects/floatobject.c b/Objects/floatobject.c
index 2627ba80eed8ca1b93c4f6ec62dd51cf9f80fdb0..31f4145c123334944c67af2318bbe96728c2a9ec 100644 (file)
--- a/Objects/floatobject.c
+++ b/Objects/floatobject.c
@@ -1142,69 +1142,39 @@ char_from_hex(int x)
     return Py_hexdigits[x];
 }
 
+/* This table maps characters to their hexadecimal values, only
+ * works with encodings whose lower half is ASCII (like UTF-8).
+ * '0' maps to 0, ..., '9' maps to 9.
+ * 'a' and 'A' map to 10, ..., 'f' and 'F' map to 15.
+ * All other indices map to -1.
+ */
+static const int
+_CHAR_TO_HEX[256] = {
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    0,  1,  2,  3,  4,  5,  6,  7,  8,  9,  -1, -1, -1, -1, -1, -1,
+    -1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, 10, 11, 12, 13, 14, 15, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+    -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
+};
+
+/* Convert a character to its hexadecimal value, or -1 if it's not a
+ * valid hexadecimal character, only works with encodings whose lower
+ * half is ASCII (like UTF-8).
+ */
 static int
-hex_from_char(char c) {
-    int x;
-    switch(c) {
-    case '0':
-        x = 0;
-        break;
-    case '1':
-        x = 1;
-        break;
-    case '2':
-        x = 2;
-        break;
-    case '3':
-        x = 3;
-        break;
-    case '4':
-        x = 4;
-        break;
-    case '5':
-        x = 5;
-        break;
-    case '6':
-        x = 6;
-        break;
-    case '7':
-        x = 7;
-        break;
-    case '8':
-        x = 8;
-        break;
-    case '9':
-        x = 9;
-        break;
-    case 'a':
-    case 'A':
-        x = 10;
-        break;
-    case 'b':
-    case 'B':
-        x = 11;
-        break;
-    case 'c':
-    case 'C':
-        x = 12;
-        break;
-    case 'd':
-    case 'D':
-        x = 13;
-        break;
-    case 'e':
-    case 'E':
-        x = 14;
-        break;
-    case 'f':
-    case 'F':
-        x = 15;
-        break;
-    default:
-        x = -1;
-        break;
-    }
-    return x;
+hex_from_char(unsigned char c) {
+    return _CHAR_TO_HEX[c];
 }
 
 /* convert a float to a hexadecimal string */