#include <boost/algorithm/string/find.hpp>
#include <boost/iostreams/device/mapped_file.hpp>
#include <cassert>
#include <iostream>
using namespace boost;
using namespace boost::algorithm;
using namespace boost::iostreams;
using namespace std;

int main(int argc, char **argv)
{
  if (argc != 3) {
    cerr << "Call: " << argv[0] << " PATTERN_FILE SRC_FILEn";
    return 3;
  }
  mapped_file_source pattern(argv[1]);
  mapped_file_source src(argv[2]);
  iterator_range<const char*> p_range(pattern.data(),
      pattern.data() + pattern.size());
  iterator_range<const char*> s_range(src.data(), src.data() + src.size());
  iterator_range<const char*> result = find_first(s_range, p_range);
  if (result) {
    size_t pos = result.begin()-s_range.begin();
    cout << pos << 'n';
    return 0;
  }
  return 1;
}

$ make CXXFLAGS="-Wall -g" LDLIBS="-lboost_iostreams" searchb

$ dd if=WTF_-_EPISODE_277_RACHAEL_HARRIS.mp3 of=t skip=232323 bs=1 count=4K
$ ls -l t
-rw-r--r-- 1 juser users 4096 2012-05-31 15:24 t
$ ./searchb t WTF_-_EPISODE_277_RACHAEL_HARRIS.mp3
232323

#!/usr/bin/env python
import locale
import os
import sys
import urllib2

def boyermoore_horspool(fd, needle):
    nlen = len(needle)
    nlast = nlen - 1

    skip = []
    for k in range(256):
        skip.append(nlen)
    for k in range(nlast):
        skip[ord(needle[k])] = nlast - k
    skip = tuple(skip)

    pos = 0
    consumed = 0
    haystack = bytes()
    while True:
        more = nlen - (consumed - pos)
        morebytes = fd.read(more)
        haystack = haystack[more:] + morebytes

        if len(morebytes) < more:
            return -1
        consumed = consumed + more

        i = nlast
        while i >= 0 and haystack[i] == needle[i]:
            i = i - 1
        if i == -1:
            return pos

        pos = pos + skip[ord(haystack[nlast])]

    return -1

if __name__ == "__main__":
    if len(sys.argv) < 2:
        sys.stderr.write("""Usage: horspool.py NEEDLE_FILE [URL]
Search for the contents of NEEDLE_FILE inside the content at URL.
If URL is omitted, search standard input.
If the content is found, print the offset of the first occurrence and return 0.
Otherwise, return 1.""")
        sys.exit(2)
    needle_file = open(sys.argv[1])
    needle = needle_file.read()
    needle_file.close
    fd = urllib2.urlopen(sys.argv[2]) if len(sys.argv) > 2 else sys.stdin
    offset = boyermoore_horspool(fd, needle)
    if offset >= 0: print offset
    else: sys.exit(1)
    fd.close()