blob: d5deafe6edb8c7a694fbafc3070fbd23e9796b37 (
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
|
/*
Ousía
Copyright (C) 2014, 2015 Benjamin Paaßen, Andreas Stöckel
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, either version 3 of the License, or
(at your option) any later version.
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, see <http://www.gnu.org/licenses/>.
*/
/**
* @file TokenStack.hpp
*
* Contains the TokenStack class used for collecting the currently enabled user
* defined tokens on a per-field basis.
*
* @author Andreas Stöckel (astoecke@techfak.uni-bielefeld.de)
*/
#ifndef _OUSIA_PARSER_STACK_TOKEN_STACK_HPP_
#define _OUSIA_PARSER_STACK_TOKEN_STACK_HPP_
#include <memory>
#include <vector>
#include <core/common/Token.hpp>
#include <core/model/Syntax.hpp>
namespace ousia {
namespace parser_stack {
/**
* Structure describing a token once it has been found in the text. Contains
* lists pointing at the corresponding SyntaxDescriptors for the open, close and
* shortForm token types.
*/
struct TokenDescriptor {
/**
* Vector containing the SyntaxDescriptors in which the token occurs as
* "close" token. The Token is first tried to be processed as a "close"
* token.
*/
std::vector<SyntaxDescriptor> close;
/**
* Vector containing the SyntaxDescriptors in which the token occurs as
* "shortForm" token. Creating a "shortForm" of the referenced ontology
* descriptor is tried next.
*/
std::vector<SyntaxDescriptor> shortForm;
/**
* Vector containing the SyntaxDescriptors in which the token occurs as
* "open" token. The possibility of using the token in the "open" mode is
* tried in the last step.
*/
std::vector<SyntaxDescriptor> open;
};
/**
* The TokenStack class is used by the Stack class to collect all currently
* enabled user defined tokens.
*/
class TokenStack {
private:
/**
* Stack containing vectors of TokenSyntaxDescriptor instances as given by
* the user.
*/
std::vector<std::vector<SyntaxDescriptor>> stack;
public:
/**
* Pushes a list of SyntaxDescriptor instances onto the internal stack.
*
* @param tokens is a list of SyntaxDescriptor instances that should be
* stored on the stack.
* @param inherit if set to true, combines the given tokens with the tokens
* from the last stack level.
*/
void pushTokens(const std::vector<SyntaxDescriptor> &tokens, bool inherit);
/**
* Removes the previously pushed list of tokens from the stack.
*/
void popTokens();
/**
* Returns the TokenDescriptor for the given token.
*
* @param token is the token for which the different forms should be looked
* up.
*/
TokenDescriptor lookup(TokenId token) const;
/**
* Returns a set containing all currently enabled tokens. The set of enabled
* tokens are those tokens that were pushed last onto the stack. This set
* has to be passed to the TokenizedData instance in order to gather all
* tokens that are currently possible.
*
* @return a set of tokens containing all the Tokens that are currently
* possible.
*/
TokenSet tokens() const;
};
}
}
#endif /* _OUSIA_PARSER_STACK_TOKEN_STACK_HPP_ */
|
