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
|
/*
Ousía
Copyright (C) 2014 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 Tokenizer.hpp
*
* Tokenizer that can be reconfigured at runtime used for parsing the plain
* text format.
*
* @author Andreas Stöckel (astoecke@techfak.uni-bielefeld.de)
*/
#ifndef _OUSIA_DYNAMIC_TOKENIZER_HPP_
#define _OUSIA_DYNAMIC_TOKENIZER_HPP_
#include <set>
#include <string>
#include <vector>
#include <core/common/Location.hpp>
#include <core/common/Whitespace.hpp>
#include "Token.hpp"
#include "TokenTrie.hpp"
namespace ousia {
// Forward declarations
class CharReader;
/**
* The Tokenizer is used to extract tokens and chunks of text from a
* CharReader. It allows to register and unregister tokens while parsing and
* to modify the handling of whitespace characters. Note that the
* Tokenizer always tries to extract the longest possible token from the
* tokenizer.
*/
class Tokenizer {
private:
/**
* Internally used token trie. This object holds all registered tokens.
*/
TokenTrie trie;
/**
* Flag defining whether whitespaces should be preserved or not.
*/
WhitespaceMode whitespaceMode;
/**
* Vector containing all registered token types.
*/
std::vector<std::string> tokens;
/**
* Next index in the tokens list where to search for a new token id.
*/
size_t nextTokenId;
/**
* Templated function used internally to read the current token. The
* function is templated in order to force code generation for all six
* combiations of whitespace modes and reading/peeking.
*
* @tparam TextHandler is the type to be used for the textHandler instance.
* @tparam read specifies whether the function should start from and advance
* the read pointer of the char reader.
* @param reader is the CharReader instance from which the data should be
* read.
* @param token is the token structure into which the token information
* should be written.
* @return false if the end of the stream has been reached, true otherwise.
*/
template <typename TextHandler, bool read>
bool next(CharReader &reader, Token &token);
public:
/**
* Constructor of the Tokenizer class.
*
* @param whitespaceMode specifies how whitespace should be handled.
*/
Tokenizer(WhitespaceMode whitespaceMode = WhitespaceMode::COLLAPSE);
/**
* Registers the given string as a token. Returns a const pointer at a
* TokenDescriptor that will be used to reference the newly created token.
*
* @param token is the token string that should be registered.
* @return a unique identifier for the registered token or EmptyToken if
* an error occured.
*/
TokenId registerToken(const std::string &token);
/**
* Unregisters the token belonging to the given TokenId.
*
* @param type is the token type that should be unregistered. The
*TokenId
* must have been returned by registerToken.
* @return true if the operation was successful, false otherwise (e.g.
* because the given TokenDescriptor was already unregistered).
*/
bool unregisterToken(TokenId type);
/**
* Returns the token that was registered under the given TokenId id or
*an
* empty string if an invalid TokenId id is given.
*
* @param type is the TokenId id for which the corresponding token
*string
* should be returned.
* @return the registered token string or an empty string if the given type
* was invalid.
*/
std::string getTokenString(TokenId type);
/**
* Sets the whitespace mode.
*
* @param whitespaceMode defines how whitespace should be treated in text
* tokens.
*/
void setWhitespaceMode(WhitespaceMode mode);
/**
* Returns the current value of the whitespace mode.
*
* @return the whitespace mode.
*/
WhitespaceMode getWhitespaceMode();
/**
* Reads a new token from the CharReader and stores it in the given
* Token instance.
*
* @param reader is the CharReader instance from which the data should be
* read.
* @param token is a reference at the token instance into which the Token
* information should be written.
* @return true if a token could be read, false if the end of the stream
* has been reached.
*/
bool read(CharReader &reader, Token &token);
/**
* The peek method does not advance the read position of the char reader,
* but reads the next token from the current char reader peek position.
*
* @param reader is the CharReader instance from which the data should be
* read.
* @param token is a reference at the token instance into which the Token
* information should be written.
* @return true if a token could be read, false if the end of the stream
* has been reached.
*/
bool peek(CharReader &reader, Token &token);
};
}
#endif /* _OUSIA_DYNAMIC_TOKENIZER_HPP_ */
|
