File: sql_normalizer.cpp

package info (click to toggle)
mysql-workbench 5.2.40%2Bdfsg-2
  • links: PTS, VCS
  • area: main
  • in suites: wheezy
  • size: 53,880 kB
  • sloc: cpp: 419,850; yacc: 74,784; xml: 54,510; python: 31,455; sh: 9,423; ansic: 4,736; makefile: 2,442; php: 529; java: 237
file content (114 lines) | stat: -rw-r--r-- 3,338 bytes parent folder | download
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
/* 
 * Copyright (c) 2007, 2010, Oracle and/or its affiliates. All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public License as
 * published by the Free Software Foundation; version 2 of the
 * License.
 * 
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 * GNU General Public License for more details.
 * 
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA
 * 02110-1301  USA
 */


#include "stdafx.h"

#include "sql_normalizer.h"

std::string Sql_normalizer::remove_inter_token_spaces(const std::string &text)
{
  class InterTokenSpaceFinder
  {
  public:
    InterTokenSpaceFinder(const std::string &text) : quoted(false), escaped(false), n(0), text(text) {}

    std::pair<std::string::size_type, std::string::size_type> find_next_space_free_substr()
    {
      std::pair<std::string::size_type, std::string::size_type> res= std::make_pair(n/*offset*/, 0/*count*/);
      std::pair<std::string::size_type, std::string::size_type> space_pos= find_next_intertoken_space();
      if (std::string::npos == space_pos.first)
        res.second= std::string::npos;
      else
        res.second= space_pos.first - res.first;
      return res;
    }

    std::pair<std::string::size_type, std::string::size_type> find_next_intertoken_space()
    {
      std::pair<std::string::size_type, std::string::size_type> res= std::make_pair(std::string::npos/*offset*/, 0/*count*/);
      for (std::string::size_type count= text.size(); n < count; ++n)
      {
        if (quoted)
        {
          if ('\\' == text[n])
          {
            escaped= !escaped;
            continue;
          }
          check_quote_symbol(cur_quote_sym);
        }
        else
        {
          if (std::isspace(text[n]))
          {
            res.first= n;
            for (++n; (n < count) && std::isspace(text[n]); ++n) ;
            res.second= n - res.first;
            break;
          }
          check_quote_symbol('\'') || check_quote_symbol('"') || check_quote_symbol('`');
        }
        escaped= false;
      }
      return res;
    }

  private:
    std::string::size_type n;
    char cur_quote_sym;
    bool quoted;
    bool escaped;
    const std::string &text;

    bool check_quote_symbol(char quote_sym)
    {
      if (quote_sym == text[n])
      {
        if (!escaped)
        {
          if (quoted)
          {
            if (quote_sym == cur_quote_sym)
              quoted= false;
          }
          else
          {
            cur_quote_sym= quote_sym;
            quoted= true;
          }          
        }
        return true;
      }
      return false;
    }
  };
  InterTokenSpaceFinder space_finder(text);

  std::string res;
  res.reserve(text.size());
  while (true)
  {
    std::pair<std::string::size_type, std::string::size_type> substr_pos= space_finder.find_next_space_free_substr();
    res.append(text, substr_pos.first, substr_pos.second);
    if (std::string::npos == substr_pos.second)
      break;
  }
  return res;
}