X-Git-Url: http://erislabs.net/gitweb/?a=blobdiff_plain;f=lib%2Fc-strcasestr.c;h=9e0cd387f2ee86475d5565c8b35bbd05ca8797e0;hb=44d6eead9ba864662836a9f9d95913b4e0cb2a3b;hp=12e2e9d96978b49bc79db73ef720cc411615790c;hpb=99099106c3c1cb16ed1e91be970332fe225e278b;p=gnulib.git

diff --git a/lib/c-strcasestr.c b/lib/c-strcasestr.c
index 12e2e9d96..9e0cd387f 100644
--- a/lib/c-strcasestr.c
+++ b/lib/c-strcasestr.c
@@ -21,10 +21,102 @@
 /* Specification.  */
 #include "c-strcasestr.h"
 
+#include <stdbool.h>
 #include <stddef.h>
+#include <string.h>
 
+#include "allocsa.h"
 #include "c-ctype.h"
 
+/* Knuth-Morris-Pratt algorithm.
+   See http://en.wikipedia.org/wiki/Knuth-Morris-Pratt_algorithm
+   Return a boolean indicating success.  */
+static bool
+knuth_morris_pratt (const char *haystack, const char *needle,
+		    const char **resultp)
+{
+  size_t m = strlen (needle);
+
+  /* Allocate the table.  */
+  size_t *table = (size_t *) allocsa (m * sizeof (size_t));
+  if (table == NULL)
+    return false;
+  /* Fill the table.
+     For 0 < i < m:
+       0 < table[i] <= i is defined such that
+       rhaystack[0..i-1] == needle[0..i-1] and rhaystack[i] != needle[i]
+       implies
+       forall 0 <= x < table[i]: rhaystack[x..x+m-1] != needle[0..m-1],
+       and table[i] is as large as possible with this property.
+     table[0] remains uninitialized.  */
+  {
+    size_t i, j;
+
+    table[1] = 1;
+    j = 0;
+    for (i = 2; i < m; i++)
+      {
+	unsigned char b = c_tolower ((unsigned char) needle[i - 1]);
+
+	for (;;)
+	  {
+	    if (b == c_tolower ((unsigned char) needle[j]))
+	      {
+		table[i] = i - ++j;
+		break;
+	      }
+	    if (j == 0)
+	      {
+		table[i] = i;
+		break;
+	      }
+	    j = j - table[j];
+	  }
+      }
+  }
+
+  /* Search, using the table to accelerate the processing.  */
+  {
+    size_t j;
+    const char *rhaystack;
+    const char *phaystack;
+
+    *resultp = NULL;
+    j = 0;
+    rhaystack = haystack;
+    phaystack = haystack;
+    /* Invariant: phaystack = rhaystack + j.  */
+    while (*phaystack != '\0')
+      if (c_tolower ((unsigned char) needle[j])
+	  == c_tolower ((unsigned char) *phaystack))
+	{
+	  j++;
+	  phaystack++;
+	  if (j == m)
+	    {
+	      /* The entire needle has been found.  */
+	      *resultp = rhaystack;
+	      break;
+	    }
+	}
+      else if (j > 0)
+	{
+	  /* Found a match of needle[0..j-1], mismatch at needle[j].  */
+	  rhaystack += table[j];
+	  j -= table[j];
+	}
+      else
+	{
+	  /* Found a mismatch at needle[0] already.  */
+	  rhaystack++;
+	  phaystack++;
+	}
+  }
+
+  freesa (table);
+  return true;
+}
+
 /* Find the first occurrence of NEEDLE in HAYSTACK, using case-insensitive
    comparison.
    Note: This function may, in multibyte locales, return success even if
@@ -39,6 +131,26 @@ c_strcasestr (const char *haystack, const char *needle)
          needle may be found in haystack.  */
   if (*needle != '\0')
     {
+      /* Minimizing the worst-case complexity:
+	 Let n = strlen(haystack), m = strlen(needle).
+	 The naïve algorithm is O(n*m) worst-case.
+	 The Knuth-Morris-Pratt algorithm is O(n) worst-case but it needs a
+	 memory allocation.
+	 To achieve linear complexity and yet amortize the cost of the memory
+	 allocation, we activate the Knuth-Morris-Pratt algorithm only once
+	 the naïve algorithm has already run for some time; more precisely,
+	 when
+	   - the outer loop count is >= 10,
+	   - the average number of comparisons per outer loop is >= 5,
+	   - the total number of comparisons is >= m.
+	 But we try it only once.  If the memory allocation attempt failed,
+	 we don't retry it.  */
+      bool try_kmp = true;
+      size_t outer_loop_count = 0;
+      size_t comparison_count = 0;
+      size_t last_ccount = 0;			/* last comparison count */
+      const char *needle_last_ccount = needle;	/* = needle + last_ccount */
+
       /* Speed up the following searches of needle by caching its first
 	 character.  */
       unsigned char b = c_tolower ((unsigned char) *needle);
@@ -49,6 +161,37 @@ c_strcasestr (const char *haystack, const char *needle)
 	  if (*haystack == '\0')
 	    /* No match.  */
 	    return NULL;
+
+	  /* See whether it's advisable to use an asymptotically faster
+	     algorithm.  */
+	  if (try_kmp
+	      && outer_loop_count >= 10
+	      && comparison_count >= 5 * outer_loop_count)
+	    {
+	      /* See if needle + comparison_count now reaches the end of
+		 needle.  */
+	      if (needle_last_ccount != NULL)
+		{
+		  needle_last_ccount +=
+		    strnlen (needle_last_ccount, comparison_count - last_ccount);
+		  if (*needle_last_ccount == '\0')
+		    needle_last_ccount = NULL;
+		  last_ccount = comparison_count;
+		}
+	      if (needle_last_ccount == NULL)
+		{
+		  /* Try the Knuth-Morris-Pratt algorithm.  */
+		  const char *result;
+		  bool success =
+		    knuth_morris_pratt (haystack, needle - 1, &result);
+		  if (success)
+		    return (char *) result;
+		  try_kmp = false;
+		}
+	    }
+
+	  outer_loop_count++;
+	  comparison_count++;
 	  if (c_tolower ((unsigned char) *haystack) == b)
 	    /* The first character matches.  */
 	    {
@@ -63,6 +206,7 @@ c_strcasestr (const char *haystack, const char *needle)
 		  if (*rhaystack == '\0')
 		    /* No match.  */
 		    return NULL;
+		  comparison_count++;
 		  if (c_tolower ((unsigned char) *rhaystack)
 		      != c_tolower ((unsigned char) *rneedle))
 		    /* Nothing in this round.  */