search 25 000 words within a text

Question

I need to find occurrences of ~ 25 000 words within a text. What is the most suitable algorithm/library for this purpose?

target language is C++

Answer 1

I once used the Boyer-Moore algorithm and it was quite fast.

Boyer-Moore isn't apt for efficiently searching many words. There is actually a very efficient algorithm for doing just that, called the Wu-Manber algorithm. I'll post a reference implementation. Notice, however, that I did this some time ago for educational purpose only. Hence, the implementation isn't really apt for direct usage and can also be made more efficient.

It also uses the stdext::hash_map from the Dinkumware STL. Subsitute with std::tr1::unordered_map or an appropriate implementation.

There's an explanation of the algorithm in a lecture script from a lecture at the Freie Universität Berlin, held by Knut Reinert.

The original paper is also online (just found it again) but I don't particularly like the pseudocode presented there.

#ifndef FINDER_HPP
#define FINDER_HPP

#include <string>

namespace thru { namespace matching {

class Finder {
public:
    virtual bool find() = 0;

    virtual std::size_t position() const = 0;

    virtual ~Finder() = 0;

protected:
    static size_t code_from_chr(char c) {
        return static_cast<size_t>(static_cast<unsigned char>(c));
    }
};

inline Finder::~Finder() { }

} } // namespace thru::matching

#endif // !defined(FINDER_HPP)

---

#include <vector>
#include <hash_map>

#include "finder.hpp"

#ifndef WUMANBER_HPP
#define WUMANBER_HPP

namespace thru { namespace matching {

class WuManberFinder : public Finder {
public:

    WuManberFinder(std::string const& text, std::vector<std::string> const& patterns);

    bool find();

    std::size_t position() const;

    std::size_t pattern_index() const;

private:

    template <typename K, typename V>
    struct HashMap {
        typedef stdext::hash_map<K, V> Type;
    };

    typedef HashMap<std::string, std::size_t>::Type shift_type;
    typedef HashMap<std::string, std::vector<std::size_t> >::Type hash_type;

    std::string const& m_text;
    std::vector<std::string> const& m_patterns;
    shift_type m_shift;
    hash_type m_hash;
    std::size_t m_pos;
    std::size_t m_find_pos;
    std::size_t m_find_pattern_index;
    std::size_t m_lmin;
    std::size_t m_lmax;
    std::size_t m_B;
};

} } // namespace thru::matching

#endif // !defined(WUMANBER_HPP)

---

#include <cmath>
#include <iostream>

#include "wumanber.hpp"

using namespace std;

namespace thru { namespace matching {

WuManberFinder::WuManberFinder(string const& text, vector<string> const& patterns)
    : m_text(text)
    , m_patterns(patterns)
    , m_shift()
    , m_hash()
    , m_pos()
    , m_find_pos(0)
    , m_find_pattern_index(0)
    , m_lmin(m_patterns[0].size())
    , m_lmax(m_patterns[0].size())
    , m_B()
{
    for (size_t i = 0; i < m_patterns.size(); ++i) {
        if (m_patterns[i].size() < m_lmin)
            m_lmin = m_patterns[i].size();
        else if (m_patterns[i].size() > m_lmax)
            m_lmax = m_patterns[i].size();
    }

    m_pos = m_lmin;
    m_B = static_cast<size_t>(ceil(log(2.0 * m_lmin * m_patterns.size()) / log(256.0)));

    for (size_t i = 0; i < m_patterns.size(); ++i)
        m_hash[m_patterns[i].substr(m_patterns[i].size() - m_B)].push_back(i);

    for (size_t i = 0; i < m_patterns.size(); ++i) {
        for (size_t j = 0; j < m_patterns[i].size() - m_B + 1; ++j) {
            string bgram = m_patterns[i].substr(j, m_B);
            size_t pos = m_patterns[i].size() - j - m_B;

            shift_type::iterator old = m_shift.find(bgram);
            if (old == m_shift.end())
                m_shift[bgram] = pos;
            else
                old->second = min(old->second, pos);
        }
    }
}

bool WuManberFinder::find() {
    while (m_pos <= m_text.size()) {
        string bgram = m_text.substr(m_pos - m_B, m_B);
        shift_type::iterator i = m_shift.find(bgram);
        if (i == m_shift.end())
            m_pos += m_lmin - m_B + 1;
        else {
            if (i->second == 0) {
                vector<size_t>& list = m_hash[bgram];
                // Verify all patterns in list against the text.
                ++m_pos;
                for (size_t j = 0; j < list.size(); ++j) {
                    string const& str = m_patterns[list[j]];
                    m_find_pos = m_pos - str.size() - 1;
                    size_t k = 0;

                    for (; k < str.size(); ++k)
                        if (str[k] != m_text[m_find_pos + k])
                            break;

                    if (k == str.size()) {
                        m_find_pattern_index = list[j];
                        return true;
                    }
                }
            }
            else
                m_pos += i->second;
        }
    }

    return false;
}

size_t WuManberFinder::position() const {
    return m_find_pos;
}

size_t WuManberFinder::pattern_index() const {
    return m_find_pattern_index;
}

} } // namespace thru::matching

Example of usage:

vector<string> patterns;
patterns.push_back("announce");
patterns.push_back("annual");
patterns.push_back("annually");

WuManberFinder wmf("CPM_annual_conference_announce", patterns);

while (wmf.find())
    cout << "Pattern \"" << patterns[wmf.pattern_index()] <<
        "\" found at position " << wmf.position() << endl;