Unify 5 copies of the KMP code.

[gnulib.git] / lib / c-strcasestr.c

diff --git a/lib/c-strcasestr.c b/lib/c-strcasestr.c
index 36b2a9f..428be70 100644 (file)
--- a/lib/c-strcasestr.c
+++ b/lib/c-strcasestr.c
@@ -27,127 +27,9 @@
 #include "malloca.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 *) nmalloca (m, sizeof (size_t));
-  if (table == NULL)
-    return false;
-  /* Fill the table.
-     For 0 < i < m:
-       0 < table[i] <= i is defined such that
-       forall 0 < x < table[i]: needle[x..i-1] != needle[0..i-1-x],
-       and table[i] is as large as possible with this property.
-     This implies:
-     1) For 0 < i < m:
-          If table[i] < i,
-          needle[table[i]..i-1] = needle[0..i-1-table[i]].
-     2) For 0 < i < m:
-          rhaystack[0..i-1] == needle[0..i-1]
-          and exists h, i <= h < m: rhaystack[h] != needle[h]
-          implies
-          forall 0 <= x < table[i]: rhaystack[x..x+m-1] != needle[0..m-1].
-     table[0] remains uninitialized.  */
-  {
-    size_t i, j;
-
-    /* i = 1: Nothing to verify for x = 0.  */
-    table[1] = 1;
-    j = 0;
-
-    for (i = 2; i < m; i++)
-      {
-       /* Here: j = i-1 - table[i-1].
-          The inequality needle[x..i-1] != needle[0..i-1-x] is known to hold
-          for x < table[i-1], by induction.
-          Furthermore, if j>0: needle[i-1-j..i-2] = needle[0..j-1].  */
-       unsigned char b = c_tolower ((unsigned char) needle[i - 1]);
-
-       for (;;)
-         {
-           /* Invariants: The inequality needle[x..i-1] != needle[0..i-1-x]
-              is known to hold for x < i-1-j.
-              Furthermore, if j>0: needle[i-1-j..i-2] = needle[0..j-1].  */
-           if (b == c_tolower ((unsigned char) needle[j]))
-             {
-               /* Set table[i] := i-1-j.  */
-               table[i] = i - ++j;
-               break;
-             }
-           /* The inequality needle[x..i-1] != needle[0..i-1-x] also holds
-              for x = i-1-j, because
-                needle[i-1] != needle[j] = needle[i-1-x].  */
-           if (j == 0)
-             {
-               /* The inequality holds for all possible x.  */
-               table[i] = i;
-               break;
-             }
-           /* The inequality needle[x..i-1] != needle[0..i-1-x] also holds
-              for i-1-j < x < i-1-j+table[j], because for these x:
-                needle[x..i-2]
-                = needle[x-(i-1-j)..j-1]
-                != needle[0..j-1-(x-(i-1-j))]  (by definition of table[j])
-                   = needle[0..i-2-x],
-              hence needle[x..i-1] != needle[0..i-1-x].
-              Furthermore
-                needle[i-1-j+table[j]..i-2]
-                = needle[table[j]..j-1]
-                = needle[0..j-1-table[j]]  (by definition of table[j]).  */
-           j = j - table[j];
-         }
-       /* Here: j = i - table[i].  */
-      }
-  }
-
-  /* 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++;
-       }
-  }
-
-  freea (table);
-  return true;
-}
+/* Knuth-Morris-Pratt algorithm.  */
+#define CANON_ELEMENT(c) c_tolower (c)
+#include "str-kmp.h"
 
 /* Find the first occurrence of NEEDLE in HAYSTACK, using case-insensitive
    comparison.
@@ -215,7 +97,7 @@ c_strcasestr (const char *haystack, const char *needle)
                  /* Try the Knuth-Morris-Pratt algorithm.  */
                  const char *result;
                  bool success =
-                   knuth_morris_pratt (haystack, needle - 1, &result);
+                   knuth_morris_pratt_unibyte (haystack, needle - 1, &result);
                  if (success)
                    return (char *) result;
                  try_kmp = false;