File: Tokeniser.h

package info (click to toggle)
darkradiant 3.9.0-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid, trixie
  • size: 41,080 kB
  • sloc: cpp: 264,743; ansic: 10,659; python: 1,852; xml: 1,650; sh: 92; makefile: 21
file content (276 lines) | stat: -rw-r--r-- 7,483 bytes parent folder | download | duplicates (3)
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
#pragma once

#include <string>
#include <iterator>
#include "string/tokeniser.h"
#include "ParseException.h"

namespace parser 
{

/**
 * greebo: Abstract type of a StringTokeniser, which splits a given
 * input string into pieces. It must provide a basic set of methods
 * to retrieve the tokens one by one.
 */
class StringTokeniser
{
public:
    /**
	 * Destructor
	 */
	virtual ~StringTokeniser() {}

	/** Test if this StringTokeniser has more tokens to return.
     *
     * @returns
     * true if there are further tokens, false otherwise
     */
    virtual bool hasMoreTokens() = 0;

    /** Return the next token in the sequence. This function consumes
     * the returned token and advances the internal state to the following
     * token.
     *
     * @returns
     * std::string containing the next token in the sequence.
     *
     * @pre
     * hasMoreTokens() must be true, otherwise an exception will be thrown.
     */
    virtual std::string nextToken() = 0;

    /** Assert that the next token in the sequence must be equal to the provided
     * value. A ParseException is thrown if the assert fails.
     *
     * @param val
     * The expected value of the token.
     */
	virtual void assertNextToken(const std::string& val) = 0;

    /** Skip the next n tokens. This method provides a convenient way to dispose
     * of a number of tokens without returning them.
     *
     * @param n
     * The number of tokens to consume.
     */
    virtual void skipTokens(unsigned int n) = 0;
};

/** Base class of a tokeniser wrapping around a string::tokeniser
 *
 *  Standard delimiters are initialised to whitespace: " \t\n\v\r"
 */
template<typename ContainerT>
class BasicStringTokeniser :
	public StringTokeniser
{
private:
    // Internal tokenizer helper
    typedef string::CharTokeniserFunc CharSeparator;
    typedef string::Tokeniser<CharSeparator> CharTokeniser;

	CharSeparator _separator;
    CharTokeniser _tok;
    CharTokeniser::Iterator _tokIter;

public:
    /** Construct a Tokeniser with the given input string, and optionally
     * a list of separators.
     *
     * @param str
     * The string to tokenise.
     *
     * @param delims
     * The list of characters to use as delimiters.
     *
     * @param keptDelims
     * The list of delimiters to keep
     */
    BasicStringTokeniser(const ContainerT& str,
						 const char* delimiters = " \t\n\v\r") :
    	_separator(delimiters),
		_tok(str, _separator),
		_tokIter(_tok.getIterator())
    {}

    /** Test if this StringTokeniser has more tokens to return.
     *
     * @returns
     * true if there are further tokens, false otherwise
     */
    bool hasMoreTokens() override
	{
		return !_tokIter.isExhausted();
    }

    /** Return the next token in the sequence. This function consumes
     * the returned token and advances the internal state to the following
     * token.
     *
     * @returns
     * std::string containing the next token in the sequence.
     *
     * @pre
     * hasMoreTokens() must be true, otherwise an exception will be thrown.
     */
    std::string nextToken() override
	{
		if (hasMoreTokens())
		{
			return *(_tokIter++);
		}

        throw ParseException("Tokeniser: no more tokens");
    }

    /** Assert that the next token in the sequence must be equal to the provided
     * value. A ParseException is thrown if the assert fails.
     *
     * @param val
     * The expected value of the token.
     */
	void assertNextToken(const std::string& val) override
	{
        const std::string tok = nextToken();

        if (tok != val) throw ParseException("Tokeniser: Assertion failed: Required \"" + 
			val + "\", found \"" + tok + "\"");
    }

    /** Skip the next n tokens. This method provides a convenient way to dispose
     * of a number of tokens without returning them.
     *
     * @param n
     * The number of tokens to consume.
     */
    void skipTokens(unsigned int n) override
	{
        for (unsigned int i = 0; i < n; i++)
		{
            if (hasMoreTokens())
			{
                _tokIter++;
				continue;
            }
            
			throw ParseException("Tokeniser: no more tokens");
        }
    }
}; // class BasicStringTokeniser

/**
 * Specialisation of BasicStringTokeniser to work with std::istream objects. This is
 * needed because an std::istream does not provide begin() and end() methods
 * to get an iterator, but needs a separate istream_iterator<> to be constructed
 * for it.
 */
template<>
class BasicStringTokeniser<std::istream> :
    public StringTokeniser
{
private:
    // Istream iterator type
    typedef std::istream_iterator<char> CharStreamIterator;

    // Internal tokenizer helper
    typedef string::CharTokeniserFunc CharSeparator;
    typedef string::Tokeniser<CharSeparator, CharStreamIterator> CharTokeniser;

    CharSeparator _separator;
    CharTokeniser _tok;
    CharTokeniser::Iterator _tokIter;

    // Helper function to set noskipws on the input stream.
    static std::istream& setNoskipws(std::istream& is)
    {
        is >> std::noskipws;
        return is;
    }

public:
    /** Construct a Tokeniser with the given input string, and optionally
     * a list of separators.
     *
     * @param str
     * The string to tokenise.
     *
     * @param delims
     * The list of characters to use as delimiters.
     *
     * @param keptDelims
     * The list of delimiters to keep
     */
    BasicStringTokeniser(std::istream& str,
        const char* delimiters = " \t\n\v\r") :
        _separator(delimiters),
        _tok(CharStreamIterator(setNoskipws(str)), CharStreamIterator(), _separator),
        _tokIter(_tok.getIterator())
    {}

    /** Test if this StringTokeniser has more tokens to return.
     *
     * @returns
     * true if there are further tokens, false otherwise
     */
    bool hasMoreTokens() override
    {
        return !_tokIter.isExhausted();
    }

    /** Return the next token in the sequence. This function consumes
     * the returned token and advances the internal state to the following
     * token.
     *
     * @returns
     * std::string containing the next token in the sequence.
     *
     * @pre
     * hasMoreTokens() must be true, otherwise an exception will be thrown.
     */
    std::string nextToken() override
    {
        if (hasMoreTokens())
        {
            return *(_tokIter++);
        }

        throw ParseException("Tokeniser: no more tokens");
    }

    /** Assert that the next token in the sequence must be equal to the provided
     * value. A ParseException is thrown if the assert fails.
     *
     * @param val
     * The expected value of the token.
     */
    void assertNextToken(const std::string& val) override
    {
        const std::string tok = nextToken();

        if (tok != val) throw ParseException("Tokeniser: Assertion failed: Required \"" +
            val + "\", found \"" + tok + "\"");
    }

    /** Skip the next n tokens. This method provides a convenient way to dispose
     * of a number of tokens without returning them.
     *
     * @param n
     * The number of tokens to consume.
     */
    void skipTokens(unsigned int n) override
    {
        for (unsigned int i = 0; i < n; i++)
        {
            if (hasMoreTokens())
            {
                _tokIter++;
                continue;
            }

            throw ParseException("Tokeniser: no more tokens");
        }
    }
}; // class BasicStringTokeniser

} // namespace parser