summaryrefslogtreecommitdiffstats
blob: 41b6aef1a6e42d864cb4d0b27ac0d2029b4a2217 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
#ifndef _DATE_TIME_DATE_PARSING_HPP___
#define _DATE_TIME_DATE_PARSING_HPP___

/* Copyright (c) 2002,2003,2005 CrystalClear Software, Inc.
 * Use, modification and distribution is subject to the 
 * Boost Software License, Version 1.0. (See accompanying
 * file LICENSE_1_0.txt or http://www.boost.org/LICENSE_1_0.txt)
 * Author: Jeff Garland, Bart Garst
 * $Date: 2008-11-23 06:13:35 -0500 (Sun, 23 Nov 2008) $
 */

#include <string>
#include <iterator>
#include <algorithm>
#include <boost/tokenizer.hpp>
#include <boost/lexical_cast.hpp>
#include <boost/date_time/compiler_config.hpp>
#include <boost/date_time/parse_format_base.hpp>

#if defined(BOOST_DATE_TIME_NO_LOCALE)
#include <cctype> // ::tolower(int)
#else
#include <locale> // std::tolower(char, locale)
#endif

namespace boost {
namespace date_time {

  //! A function to replace the std::transform( , , ,tolower) construct
  /*! This function simply takes a string, and changes all the characters
   * in that string to lowercase (according to the default system locale).
   * In the event that a compiler does not support locales, the old 
   * C style tolower() is used.
   */
  inline
  std::string 
  convert_to_lower(std::string inp)
  {
#if !defined(BOOST_DATE_TIME_NO_LOCALE)
    const std::locale loc(std::locale::classic());
#endif
    std::string::size_type i = 0, n = inp.length();
    for (; i < n; ++i) {
      inp[i] =
#if defined(BOOST_DATE_TIME_NO_LOCALE)
        static_cast<char>(std::tolower(inp[i]));
#else
        // tolower and others were brought in to std for borland >= v564
        // in compiler_config.hpp
        std::tolower(inp[i], loc);
#endif
    }
    return inp;
  }

    //! Helper function for parse_date.
    /* Used by-value parameter because we change the string and may
     * want to preserve the original argument */
    template<class month_type>
    inline unsigned short 
    month_str_to_ushort(std::string const& s) {
      if((s.at(0) >= '0') && (s.at(0) <= '9')) {
        return boost::lexical_cast<unsigned short>(s);
      } 
      else {
        std::string str = convert_to_lower(s);
        typename month_type::month_map_ptr_type ptr = month_type::get_month_map_ptr();
        typename month_type::month_map_type::iterator iter = ptr->find(str);
        if(iter != ptr->end()) { // required for STLport
          return iter->second;
        }
      }
      return 13; // intentionally out of range - name not found
    }
 
    //! Find index of a string in either of 2 arrays
    /*! find_match searches both arrays for a match to 's'. Both arrays
     * must contain 'size' elements. The index of the match is returned.
     * If no match is found, 'size' is returned.
     * Ex. "Jan" returns 0, "Dec" returns 11, "Tue" returns 2.
     * 'size' can be sent in with: greg_month::max() (which 12),
     * greg_weekday::max() + 1 (which is 7) or date_time::NumSpecialValues */
    template<class charT>
    short find_match(const charT* const* short_names, 
                     const charT* const* long_names, 
                     short size,
                     const std::basic_string<charT>& s) {
      for(short i = 0; i < size; ++i){
        if(short_names[i] == s || long_names[i] == s){
          return i;
        }
      }
      return size; // not-found, return a value out of range
    }
    
    //! Generic function to parse a delimited date (eg: 2002-02-10)
    /*! Accepted formats are: "2003-02-10" or " 2003-Feb-10" or
     * "2003-Feburary-10" 
     * The order in which the Month, Day, & Year appear in the argument 
     * string can be accomodated by passing in the appropriate ymd_order_spec 
     */
    template<class date_type>
    date_type
    parse_date(const std::string& s, int order_spec = ymd_order_iso) {
      std::string spec_str;
      if(order_spec == ymd_order_iso) {
        spec_str = "ymd";
      } 
      else if(order_spec == ymd_order_dmy) {
        spec_str = "dmy";
      } 
      else { // (order_spec == ymd_order_us)
        spec_str = "mdy";
      }
      
      typedef typename date_type::year_type year_type;
      typedef typename date_type::month_type month_type;
      unsigned pos = 0;
      unsigned short year(0), month(0), day(0);
      typedef typename std::basic_string<char>::traits_type traits_type;
      typedef boost::char_separator<char, traits_type> char_separator_type;
      typedef boost::tokenizer<char_separator_type,
                               std::basic_string<char>::const_iterator,
                               std::basic_string<char> > tokenizer;
      typedef boost::tokenizer<char_separator_type,
                               std::basic_string<char>::const_iterator,
                               std::basic_string<char> >::iterator tokenizer_iterator;
      // may need more delimiters, these work for the regression tests
      const char sep_char[] = {',','-','.',' ','/','\0'};
      char_separator_type sep(sep_char);
      tokenizer tok(s,sep);
      for(tokenizer_iterator beg=tok.begin(); 
          beg!=tok.end() && pos < spec_str.size(); 
          ++beg, ++pos) {
        switch(spec_str.at(pos)) {
          case 'y': 
          {
            year = boost::lexical_cast<unsigned short>(*beg);
            break;
          }
          case 'm': 
          {
            month = month_str_to_ushort<month_type>(*beg);
            break;
          }
          case 'd': 
          {
            day = boost::lexical_cast<unsigned short>(*beg);
            break;
          }
        } //switch
      }
      return date_type(year, month, day);
    }
    
    //! Generic function to parse undelimited date (eg: 20020201)
    template<class date_type>
    date_type
    parse_undelimited_date(const std::string& s) {
      int offsets[] = {4,2,2};
      int pos = 0;
      typedef typename date_type::year_type year_type;
      //typename date_type::ymd_type ymd((year_type::min)(),1,1);
      unsigned short y = 0, m = 0, d = 0;
      
      /* The two bool arguments state that parsing will not wrap 
       * (only the first 8 characters will be parsed) and partial 
       * strings will not be parsed. 
       * Ex:
       * "2005121" will parse 2005 & 12, but not the "1" */
      boost::offset_separator osf(offsets, offsets+3, false, false);
      
      typedef typename boost::tokenizer<boost::offset_separator, 
                                        std::basic_string<char>::const_iterator, 
                                        std::basic_string<char> > tokenizer_type;
      tokenizer_type tok(s, osf);
      for(typename tokenizer_type::iterator ti=tok.begin(); ti!=tok.end();++ti) {
        unsigned short i = boost::lexical_cast<unsigned short>(*ti);
        switch(pos) {
        case 0: y = i; break;
        case 1: m = i; break;
        case 2: d = i; break;
        }
        pos++;
      }
      return date_type(y,m,d);
    }
    
    //! Helper function for 'date gregorian::from_stream()'
    /*! Creates a string from the iterators that reference the
     * begining & end of a char[] or string. All elements are 
     * used in output string */
    template<class date_type, class iterator_type>
    inline 
    date_type
    from_stream_type(iterator_type& beg, 
                     iterator_type& end,
                     char) 
    {
      std::ostringstream ss;
      while(beg != end) {
        ss << *beg++;
      }
      return parse_date<date_type>(ss.str());
    }
 
    //! Helper function for 'date gregorian::from_stream()'
    /*! Returns the first string found in the stream referenced by the
     * begining & end iterators */
    template<class date_type, class iterator_type>
    inline 
    date_type
    from_stream_type(iterator_type& beg, 
                     iterator_type& /* end */,
                     std::string) 
    {
      return parse_date<date_type>(*beg);
    }

    /* I believe the wchar stuff would be best elsewhere, perhaps in
     * parse_date<>()? In the mean time this gets us started... */
    //! Helper function for 'date gregorian::from_stream()'
    /*! Creates a string from the iterators that reference the
     * begining & end of a wstring. All elements are 
     * used in output string */
    template<class date_type, class iterator_type>
    inline 
    date_type from_stream_type(iterator_type& beg, 
                               iterator_type& end,
                               wchar_t) 
    {
      std::ostringstream ss;
      while(beg != end) {
#if !defined(BOOST_DATE_TIME_NO_LOCALE)
        ss << std::use_facet<std::ctype<wchar_t> >(std::locale()).narrow(*beg++, 'X'); // 'X' will cause exception to be thrown
#else
        ss << ss.narrow(*beg++, 'X');
#endif
      }
      return parse_date<date_type>(ss.str());
    }
#ifndef BOOST_NO_STD_WSTRING
    //! Helper function for 'date gregorian::from_stream()'
    /*! Creates a string from the first wstring found in the stream
     * referenced by the begining & end iterators */
    template<class date_type, class iterator_type>
    inline 
    date_type
    from_stream_type(iterator_type& beg, 
                     iterator_type& /* end */,
                     std::wstring) {
      std::wstring ws = *beg;
      std::ostringstream ss;
      std::wstring::iterator wsb = ws.begin(), wse = ws.end();
      while(wsb != wse) {
#if !defined(BOOST_DATE_TIME_NO_LOCALE)
        ss << std::use_facet<std::ctype<wchar_t> >(std::locale()).narrow(*wsb++, 'X'); // 'X' will cause exception to be thrown
#else
        ss << ss.narrow(*wsb++, 'X'); // 'X' will cause exception to be thrown
#endif
      }
      return parse_date<date_type>(ss.str());
    }
#endif // BOOST_NO_STD_WSTRING
#if (defined(BOOST_MSVC) && (_MSC_VER < 1300))
    // This function cannot be compiled with MSVC 6.0 due to internal compiler shorcomings
#else
    //! function called by wrapper functions: date_period_from_(w)string()
    template<class date_type, class charT>
    period<date_type, typename date_type::duration_type> 
    from_simple_string_type(const std::basic_string<charT>& s){
      typedef typename std::basic_string<charT>::traits_type traits_type;
      typedef typename boost::char_separator<charT, traits_type> char_separator;
      typedef typename boost::tokenizer<char_separator, 
                                        typename std::basic_string<charT>::const_iterator, 
                                        std::basic_string<charT> > tokenizer;
      const charT sep_list[4] = {'[','/',']','\0'};
      char_separator sep(sep_list);
      tokenizer tokens(s, sep);
      typename tokenizer::iterator tok_it = tokens.begin(); 
      std::basic_string<charT> date_string = *tok_it;
      // get 2 string iterators and generate a date from them
      typename std::basic_string<charT>::iterator date_string_start = date_string.begin(), 
                                                  date_string_end = date_string.end(); 
      typedef typename std::iterator_traits<typename std::basic_string<charT>::iterator>::value_type value_type;
      date_type d1 = from_stream_type<date_type>(date_string_start, date_string_end, value_type());
      date_string = *(++tok_it); // next token
      date_string_start = date_string.begin(), date_string_end = date_string.end(); 
      date_type d2 = from_stream_type<date_type>(date_string_start, date_string_end, value_type());
      return period<date_type, typename date_type::duration_type>(d1, d2); 
    }
#endif

} } //namespace date_time




#endif