From f62a8888f50d4ac135c177ae07a78560fea79f34 Mon Sep 17 00:00:00 2001
From: Luke Mewburn <Luke@Mewburn.net>
Date: Fri, 29 Dec 2023 23:34:25 +1100
Subject: [PATCH] reimplement find_bm() using std::search

Use std::search() to implement find_bm() instead of using a
local implementation of Boyer-Moore.

Avoids integer overflow reported in issue #31 and PR #31.
Should fix build problem in issue #7.

std::search is also faster for the test program in issue #31
on a system with an Intel Xeon E-2224 CPU:
- gcc 8.5, find_bm(): 3.16s
- g++ 8.5, std::search: 2.40s
- g++ 13, std::search: 2.16s

Experiments using the C++17 std::boyer_moore_searcher or
std::boyer_moore_horspool_searcher were also slower than
std::search in this experiment.
---
 mimetic/utils.h | 37 ++-----------------------------------
 1 file changed, 2 insertions(+), 35 deletions(-)

diff --git a/mimetic/utils.h b/mimetic/utils.h
index 2c2497c..5290b56 100644
--- a/mimetic/utils.h
+++ b/mimetic/utils.h
@@ -6,6 +6,7 @@
  ***************************************************************************/
 #ifndef _MIMETIC_UTILS_H_
 #define _MIMETIC_UTILS_H_
+#include <algorithm>
 #include <iostream>
 #include <string>
 #include <ctype.h>
@@ -43,37 +44,6 @@ int str2int(const std::string& s);
 /// returns a string hexadecimal representation of \p n
 std::string int2hex(unsigned int n);
 
-// find_bm specialization for random access iterators
-template<typename Iterator>
-Iterator find_bm(Iterator bit, Iterator eit, const std::string& word, const std::random_access_iterator_tag&)
-{
-    int bLen = word.length();
-    const char* pWord = word.c_str();
-    int i, t, shift[256];
-    unsigned char c;
-
-    for(i = 0; i < 256; ++i)  
-        shift[i] = bLen;
-
-    for(i = 0; i < bLen; ++i)
-        shift[ (unsigned char) pWord[i] ] = bLen -i - 1;
-
-    for(i = t = bLen-1; t >= 0; --i, --t)
-    {
-        if((bit + i) >= eit)
-            return eit; 
-
-        while((c = *(bit + i)) != pWord[t]) 
-        {
-            i += std::max(bLen-t, shift[c]);
-            if((bit + i) >= eit) return eit; 
-            t = bLen-1;
-        }
-    }
-
-    return bit + i + 1;
-}
-
 // boyer-moore find 
 /**
  * find the first occurrence of \p word in (\p bit, \p eit]
@@ -84,12 +54,9 @@ Iterator find_bm(Iterator bit, Iterator eit, const std::string& word, const std:
 template<typename Iterator>
 Iterator find_bm(Iterator bit, Iterator eit, const std::string& word)
 {
-    return find_bm(bit, eit, word, 
-        typename std::iterator_traits<Iterator>::iterator_category());
+    return std::search(bit, eit, word.begin(), word.end());
 }
 
-
-
 } // ns utils
 
 }