view release on metacpan or  search on metacpan

common.h  view on Meta::CPAN

//
//  CRF++ -- Yet Another CRF toolkit
//
//  $Id: common.h 1588 2007-02-12 09:03:39Z taku $;
//
//  Copyright(C) 2005-2007 Taku Kudo <taku@chasen.org>
//
#ifndef _CRFPP_COMMON_H
#define _CRFPP_COMMON_H

#include <setjmp.h>
#include <cstdlib>
#include <cstdio>
#include <cstring>
#include <string>
#include <strstream>
#include <iostream>
#include <algorithm>
#include <cmath>

#ifdef HAVE_CONFIG_H
#include "config.h"
#endif

#define COPYRIGHT  "CRF++: Yet Another CRF Tool Kit\nCopyright(C)" \
"2005-2007 Taku Kudo, All rights reserved.\n"
#define MODEL_VERSION 100

#if defined(_WIN32) && !defined(__CYGWIN__)
# define OUTPUT_MODE std::ios::binary|std::ios::out
#else
# define OUTPUT_MODE std::ios::out
#endif

#define BUF_SIZE 8192

namespace CRFPP {
  template <class T> inline T _min(T x, T y) { return(x < y) ? x : y; }
  template <class T> inline T _max(T x, T y) { return(x > y) ? x : y; }

  template <class Iterator>
  inline size_t tokenizeCSV(char *str,
                            Iterator out, size_t max) {
    char *eos = str + std::strlen(str);
    char *start = 0;
    char *end = 0;
    size_t n = 0;

    for (; str < eos; ++str) {
      while (*str == ' ' || *str == '\t') ++str;  // skip white spaces
      bool inquote = false;
      if (*str == '"') {
        start = ++str;
        end = start;
        for (; str < eos; ++str) {
          if (*str == '"') {
            str++;
            if (*str != '"')
              break;
          }
          *end++ = *str;
        }
        inquote = true;
        str = std::find(str, eos, ',');
      } else {
        start = str;
        str = std::find(str, eos, ',');
        end = str;
      }
      if (max-- > 1) *end = '\0';
      *out++ = start;
      ++n;
      if (max == 0) break;
    }

    return n;
  }

  template <class Iterator>
  inline size_t tokenize(char *str, const char *del,
                         Iterator out, size_t max) {
    char *stre = str + std::strlen(str);
    const char *dele = del + std::strlen(del);
    size_t size = 0;

    while (size < max) {
      char *n = std::find_first_of(str, stre, del, dele);
      *n = '\0';
      *out++ = str;
      ++size;
      if (n == stre) break;
      str = n + 1;
    }

    return size;
  }

  // continus run of space is regarded as one space
  template <class Iterator>
  inline size_t tokenize2(char *str, const char *del,
                          Iterator out, size_t max) {
    char *stre = str + std::strlen(str);
    const char *dele = del + std::strlen(del);
    size_t size = 0;

    while (size < max) {
      char *n = std::find_first_of(str, stre, del, dele);
      *n = '\0';
      if (*str != '\0') {
        *out++ = str;
        ++size;
      }
      if (n == stre) break;
      str = n + 1;
    }

    return size;
  }

  void inline dtoa(double val, char *s) {
    std::sprintf(s, "%-16f", val);
    char *p = s;
    for (; *p != ' '; ++p) {}
    *p = '\0';
    return;
  }

  template <class T> inline void itoa(T val, char *s) {
    char *t;
    T mod;