strcase: some optimisations

Lookup tables for toupper() and tolower() make Curl_strcasecompare()
about 1.5 times faster. Reorganising Curl_strcasecompare() to fully exit
early then also allows simplifying the check at the end, for another
15%. In total, the changes make Curl_strcasecompare() around 1.6 to 1.7
times faster.

Note that these optimisation assume ASCII. The original
Curl_raw_toupper() and raw_tolower() look like they already made that
assumption.

Closes #8875

diff --git a/lib/strcase.c b/lib/strcase.c
index 692a3f14aee735a0aef725e3e16cb1103af2ed29..f377c461dfa5c62d88bbdcda1a111b4a4b1ce867 100644 (file)
--- a/lib/strcase.c
+++ b/lib/strcase.c
@@ -28,13 +28,50 @@
 
 static char raw_tolower(char in);
 
+/* Mapping table to go from lowercase to uppercase for plain ASCII.*/
+static const unsigned char touppermap[256] = {
+0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21,
+22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40,
+41, 42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59,
+60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78,
+79, 80, 81, 82, 83, 84, 85, 86, 87, 88, 89, 90, 91, 92, 93, 94, 95, 96, 65,
+66, 67, 68, 69, 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 83, 84,
+85, 86, 87, 88, 89, 90, 123, 124, 125, 126, 127, 128, 129, 130, 131, 132, 133,
+134, 135, 136, 137, 138, 139, 140, 141, 142, 143, 144, 145, 146, 147, 148, 149,
+150, 151, 152, 153, 154, 155, 156, 157, 158, 159, 160, 161, 162, 163, 164, 165,
+166, 167, 168, 169, 170, 171, 172, 173, 174, 175, 176, 177, 178, 179, 180, 181,
+182, 183, 184, 185, 186, 187, 188, 189, 190, 191, 192, 193, 194, 195, 196, 197,
+198, 199, 200, 201, 202, 203, 204, 205, 206, 207, 208, 209, 210, 211, 212, 213,
+214, 215, 216, 217, 218, 219, 220, 221, 222, 223, 224, 225, 226, 227, 228, 229,
+230, 231, 232, 233, 234, 235, 236, 237, 238, 239, 240, 241, 242, 243, 244, 245,
+246, 247, 248, 249, 250, 251, 252, 253, 254, 255
+};
+
+/* Mapping table to go from uppercase to lowercase for plain ASCII.*/
+static const unsigned char tolowermap[256] = {
+0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21,
+22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40, 41,
+42, 43, 44, 45, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61,
+62, 63, 64, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110,
+111, 112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 91, 92, 93, 94, 95,
+96, 97, 98, 99, 100, 101, 102, 103, 104, 105, 106, 107, 108, 109, 110, 111,
+112, 113, 114, 115, 116, 117, 118, 119, 120, 121, 122, 123, 124, 125, 126, 127,
+128, 129, 130, 131, 132, 133, 134, 135, 136, 137, 138, 139, 140, 141, 142, 143,
+144, 145, 146, 147, 148, 149, 150, 151, 152, 153, 154, 155, 156, 157, 158, 159,
+160, 161, 162, 163, 164, 165, 166, 167, 168, 169, 170, 171, 172, 173, 174, 175,
+176, 177, 178, 179, 180, 181, 182, 183, 184, 185, 186, 187, 188, 189, 190, 191,
+192, 193, 194, 195, 196, 197, 198, 199, 200, 201, 202, 203, 204, 205, 206, 207,
+208, 209, 210, 211, 212, 213, 214, 215, 216, 217, 218, 219, 220, 221, 222, 223,
+224, 225, 226, 227, 228, 229, 230, 231, 232, 233, 234, 235, 236, 237, 238, 239,
+240, 241, 242, 243, 244, 245, 246, 247, 248, 249, 250, 251, 252, 253, 254, 255
+};
+
+
 /* Portable, consistent toupper. Do not use toupper() because its behavior is
    altered by the current locale. */
 char Curl_raw_toupper(char in)
 {
-  if(in >= 'a' && in <= 'z')
-    return (char)('A' + in - 'a');
-  return in;
+  return touppermap[(unsigned char) in];
 }
 
 
@@ -42,9 +79,7 @@ char Curl_raw_toupper(char in)
    altered by the current locale. */
 static char raw_tolower(char in)
 {
-  if(in >= 'A' && in <= 'Z')
-    return (char)('a' + in - 'A');
-  return in;
+  return tolowermap[(unsigned char) in];
 }
 
 /*
@@ -62,14 +97,15 @@ int Curl_strcasecompare(const char *first, const char *second)
   while(*first && *second) {
     if(Curl_raw_toupper(*first) != Curl_raw_toupper(*second))
       /* get out of the loop as soon as they don't match */
-      break;
+      return 0;
     first++;
     second++;
   }
-  /* we do the comparison here (possibly again), just to make sure that if the
-     loop above is skipped because one of the strings reached zero, we must not
-     return this as a successful match */
-  return (Curl_raw_toupper(*first) == Curl_raw_toupper(*second));
+  /* If we're here either the strings are the same or the length is different.
+     We can just test if the "current" character is non-zero for one and zero
+     for the other. Note that the characters may not be exactly the same even
+     if they match, we only want to compare zero-ness. */
+  return !*first == !*second;
 }
 
 int Curl_safe_strcasecompare(const char *first, const char *second)