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
|
// Boost tokenizer examples -------------------------------------------------//
// Copyright John R. Bandela 2001.
// Distributed under the Boost Software License, Version 1.0. (See
// accompanying file LICENSE_1_0.txt or copy at
// http://www.boost.org/LICENSE_1_0.txt)
// See http://www.boost.org for updates, documentation, and revision history.
#include <iostream>
#include <iterator>
#include <string>
#include <boost/tokenizer.hpp>
#include <boost/array.hpp>
#include <boost/test/minimal.hpp>
int test_main( int /*argc*/, char* /*argv*/[] )
{
using namespace std;
using namespace boost;
// Use tokenizer
{
const string test_string = ";;Hello|world||-foo--bar;yow;baz|";
string answer[] = { "Hello", "world", "foo", "bar", "yow", "baz" };
typedef tokenizer<char_separator<char> > Tok;
char_separator<char> sep("-;|");
Tok t(test_string, sep);
BOOST_REQUIRE(equal(t.begin(),t.end(),answer));
}
{
const string test_string = ";;Hello|world||-foo--bar;yow;baz|";
string answer[] = { "", "", "Hello", "|", "world", "|", "", "|", "",
"foo", "", "bar", "yow", "baz", "|", "" };
typedef tokenizer<char_separator<char> > Tok;
char_separator<char> sep("-;", "|", boost::keep_empty_tokens);
Tok t(test_string, sep);
BOOST_REQUIRE(equal(t.begin(), t.end(), answer));
}
{
const string test_string = "This,,is, a.test..";
string answer[] = {"This","is","a","test"};
typedef tokenizer<> Tok;
Tok t(test_string);
BOOST_REQUIRE(equal(t.begin(),t.end(),answer));
}
{
const string test_string = "Field 1,\"embedded,comma\",quote \\\", escape \\\\";
string answer[] = {"Field 1","embedded,comma","quote \""," escape \\"};
typedef tokenizer<escaped_list_separator<char> > Tok;
Tok t(test_string);
BOOST_REQUIRE(equal(t.begin(),t.end(),answer));
}
{
const string test_string = ",1,;2\\\";3\\;,4,5^\\,\'6,7\';";
string answer[] = {"","1","","2\"","3;","4","5\\","6,7",""};
typedef tokenizer<escaped_list_separator<char> > Tok;
escaped_list_separator<char> sep("\\^",",;","\"\'");
Tok t(test_string,sep);
BOOST_REQUIRE(equal(t.begin(),t.end(),answer));
}
{
const string test_string = "12252001";
string answer[] = {"12","25","2001"};
typedef tokenizer<offset_separator > Tok;
boost::array<int,3> offsets = {{2,2,4}};
offset_separator func(offsets.begin(),offsets.end());
Tok t(test_string,func);
BOOST_REQUIRE(equal(t.begin(),t.end(),answer));
}
// Use token_iterator_generator
{
const string test_string = "This,,is, a.test..";
string answer[] = {"This","is","a","test"};
typedef token_iterator_generator<char_delimiters_separator<char> >::type Iter;
Iter begin = make_token_iterator<string>(test_string.begin(),
test_string.end(),char_delimiters_separator<char>());
Iter end;
BOOST_REQUIRE(equal(begin,end,answer));
}
{
const string test_string = "Field 1,\"embedded,comma\",quote \\\", escape \\\\";
string answer[] = {"Field 1","embedded,comma","quote \""," escape \\"};
typedef token_iterator_generator<escaped_list_separator<char> >::type Iter;
Iter begin = make_token_iterator<string>(test_string.begin(),
test_string.end(),escaped_list_separator<char>());
Iter begin_c(begin);
Iter end;
BOOST_REQUIRE(equal(begin,end,answer));
while(begin_c != end)
{
BOOST_REQUIRE(begin_c.at_end() == 0);
++begin_c;
}
BOOST_REQUIRE(begin_c.at_end());
}
{
const string test_string = "12252001";
string answer[] = {"12","25","2001"};
typedef token_iterator_generator<offset_separator>::type Iter;
boost::array<int,3> offsets = {{2,2,4}};
offset_separator func(offsets.begin(),offsets.end());
Iter begin = make_token_iterator<string>(test_string.begin(),
test_string.end(),func);
Iter end= make_token_iterator<string>(test_string.end(),
test_string.end(),func);
BOOST_REQUIRE(equal(begin,end,answer));
}
// Test copying
{
const string test_string = "abcdef";
token_iterator_generator<offset_separator>::type beg, end, other;
boost::array<int,3> ar = {{1,2,3}};
offset_separator f(ar.begin(),ar.end());
beg = make_token_iterator<string>(test_string.begin(),test_string.end(),f);
++beg;
other = beg;
++other;
BOOST_REQUIRE(*beg=="bc");
BOOST_REQUIRE(*other=="def");
other = make_token_iterator<string>(test_string.begin(),
test_string.end(),f);
BOOST_REQUIRE(*other=="a");
}
// Test non-default constructed char_delimiters_separator
{
const string test_string = "how,are you, doing";
string answer[] = {"how",",","are you",","," doing"};
tokenizer<> t(test_string,char_delimiters_separator<char>(true,",",""));
BOOST_REQUIRE(equal(t.begin(),t.end(),answer));
}
return 0;
}
|
