Use a static exception map

* Make the map static, read-only and preinitialized, to avoid
  thread-safety problems.
* Invert the map, making it non-zero for exceptional characters
  (so that non-exceptional characters don't need to be mentioned)
* Tighten the set of exceptional characters, so that most of ASCII
  goes through the fast path.

This increases the speed of test_perf_* by 7.7-20.6%.

Signed-off-by: Miloslav Trmač <mitr@redhat.com>
Signed-off-by: Gergely Nagy <algernon@balabit.hu>

1 files changed, 25 insertions, 51 deletions

diff --git a/lib/buffer.c b/lib/buffer.c
index a613c98..5cb8d3f 100644
--- a/lib/buffer.c
+++ b/lib/buffer.c
@@ -30,30 +30,10 @@
 #include "config.h"
 #include "buffer.h"
 
+#include <limits.h>
 #include <stdlib.h>
 #include <string.h>
 
-static const unsigned char json_exceptions[] =
-  {
-    0x7f,  0x80,  0x81,  0x82,  0x83,  0x84,  0x85,  0x86,
-    0x87,  0x88,  0x89,  0x8a,  0x8b,  0x8c,  0x8d,  0x8e,
-    0x8f,  0x90,  0x91,  0x92,  0x93,  0x94,  0x95,  0x96,
-    0x97,  0x98,  0x99,  0x9a,  0x9b,  0x9c,  0x9d,  0x9e,
-    0x9f,  0xa0,  0xa1,  0xa2,  0xa3,  0xa4,  0xa5,  0xa6,
-    0xa7,  0xa8,  0xa9,  0xaa,  0xab,  0xac,  0xad,  0xae,
-    0xaf,  0xb0,  0xb1,  0xb2,  0xb3,  0xb4,  0xb5,  0xb6,
-    0xb7,  0xb8,  0xb9,  0xba,  0xbb,  0xbc,  0xbd,  0xbe,
-    0xbf,  0xc0,  0xc1,  0xc2,  0xc3,  0xc4,  0xc5,  0xc6,
-    0xc7,  0xc8,  0xc9,  0xca,  0xcb,  0xcc,  0xcd,  0xce,
-    0xcf,  0xd0,  0xd1,  0xd2,  0xd3,  0xd4,  0xd5,  0xd6,
-    0xd7,  0xd8,  0xd9,  0xda,  0xdb,  0xdc,  0xdd,  0xde,
-    0xdf,  0xe0,  0xe1,  0xe2,  0xe3,  0xe4,  0xe5,  0xe6,
-    0xe7,  0xe8,  0xe9,  0xea,  0xeb,  0xec,  0xed,  0xee,
-    0xef,  0xf0,  0xf1,  0xf2,  0xf3,  0xf4,  0xf5,  0xf6,
-    0xf7,  0xf8,  0xf9,  0xfa,  0xfb,  0xfc,  0xfd,  0xfe,
-    0xff,  '\0'
-  };
-
 static __thread ul_buffer_t escape_buffer;
 
 static void ul_buffer_finish (void) __attribute__((destructor));
@@ -67,10 +47,19 @@ ul_buffer_finish (void)
 static inline char *
 _ul_str_escape (const char *str, char *dest, size_t *length)
 {
+  /* Assumes ASCII!  Keep in sync with the switch! */
+  static const unsigned char json_exceptions[UCHAR_MAX + 1] =
+    {
+      [0x01] = 1, [0x02] = 1, [0x03] = 1, [0x04] = 1, [0x05] = 1, [0x06] = 1,
+      [0x07] = 1, [0x08] = 1, [0x09] = 1, [0x0a] = 1, [0x0b] = 1, [0x0c] = 1,
+      [0x0d] = 1, [0x0e] = 1, [0x0f] = 1, [0x10] = 1, [0x11] = 1, [0x12] = 1,
+      [0x13] = 1, [0x14] = 1, [0x15] = 1, [0x16] = 1, [0x17] = 1, [0x18] = 1,
+      [0x19] = 1, [0x1a] = 1, [0x1b] = 1, [0x1c] = 1, [0x1d] = 1, [0x1e] = 1,
+      [0x1f] = 1, ['\\'] = 1, ['"'] = 1
+    };
+
   const unsigned char *p;
   char *q;
-  static unsigned char exmap[256];
-  static int exmap_inited;
 
   if (!str)
     return NULL;
@@ -78,25 +67,13 @@ _ul_str_escape (const char *str, char *dest, size_t *length)
   p = (unsigned char *)str;
   q = dest;
 
-  if (!exmap_inited)
-    {
-      const unsigned char *e = json_exceptions;
-
-      memset (exmap, 0, 256);
-      while (*e)
-        {
-          exmap[*e] = 1;
-          e++;
-        }
-      exmap_inited = 1;
-    }
-
   while (*p)
     {
-      if (exmap[*p])
+      if (json_exceptions[*p] == 0)
         *q++ = *p;
       else
         {
+          /* Keep in sync with json_exceptions! */
           switch (*p)
             {
             case '\b':
@@ -124,20 +101,17 @@ _ul_str_escape (const char *str, char *dest, size_t *length)
               *q++ = '"';
               break;
             default:
-              if ((*p < ' ') || (*p >= 0177))
-                {
-                  static const char json_hex_chars[16] = "0123456789abcdef";
-
-                  *q++ = '\\';
-                  *q++ = 'u';
-                  *q++ = '0';
-                  *q++ = '0';
-                  *q++ = json_hex_chars[(*p) >> 4];
-                  *q++ = json_hex_chars[(*p) & 0xf];
-                }
-              else
-                *q++ = *p;
-              break;
+              {
+                static const char json_hex_chars[16] = "0123456789abcdef";
+
+                *q++ = '\\';
+                *q++ = 'u';
+                *q++ = '0';
+                *q++ = '0';
+                *q++ = json_hex_chars[(*p) >> 4];
+                *q++ = json_hex_chars[(*p) & 0xf];
+                break;
+              }
             }
         }
       p++;