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
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
|
<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=US-ASCII">
<title>Quickstart 1 - A word counter using Spirit.Lex</title>
<link rel="stylesheet" href="../../../../../../../doc/src/boostbook.css" type="text/css">
<meta name="generator" content="DocBook XSL Stylesheets V1.76.1">
<link rel="home" href="../../../index.html" title="Spirit 2.5.2">
<link rel="up" href="../tutorials.html" title="Spirit.Lex Tutorials">
<link rel="prev" href="lexer_tutorials.html" title="Spirit.Lex Tutorials Overview">
<link rel="next" href="lexer_quickstart2.html" title="Quickstart 2 - A better word counter using Spirit.Lex">
</head>
<body bgcolor="white" text="black" link="#0000FF" vlink="#840084" alink="#0000FF">
<table cellpadding="2" width="100%"><tr>
<td valign="top"><img alt="Boost C++ Libraries" width="277" height="86" src="../../../../../../../boost.png"></td>
<td align="center"><a href="../../../../../../../index.html">Home</a></td>
<td align="center"><a href="../../../../../../../libs/libraries.htm">Libraries</a></td>
<td align="center"><a href="http://www.boost.org/users/people.html">People</a></td>
<td align="center"><a href="http://www.boost.org/users/faq.html">FAQ</a></td>
<td align="center"><a href="../../../../../../../more/index.htm">More</a></td>
</tr></table>
<hr>
<div class="spirit-nav">
<a accesskey="p" href="lexer_tutorials.html"><img src="../../../../../../../doc/src/images/prev.png" alt="Prev"></a><a accesskey="u" href="../tutorials.html"><img src="../../../../../../../doc/src/images/up.png" alt="Up"></a><a accesskey="h" href="../../../index.html"><img src="../../../../../../../doc/src/images/home.png" alt="Home"></a><a accesskey="n" href="lexer_quickstart2.html"><img src="../../../../../../../doc/src/images/next.png" alt="Next"></a>
</div>
<div class="section">
<div class="titlepage"><div><div><h4 class="title">
<a name="spirit.lex.tutorials.lexer_quickstart1"></a><a class="link" href="lexer_quickstart1.html" title="Quickstart 1 - A word counter using Spirit.Lex">Quickstart
1 - A word counter using <span class="emphasis"><em>Spirit.Lex</em></span></a>
</h4></div></div></div>
<p>
<span class="emphasis"><em>Spirit.Lex</em></span> is very modular, which follows the general
building principle of the <a href="http://boost-spirit.com" target="_top">Spirit</a>
libraries. You never pay for features you don't use. It is nicely integrated
with the other parts of <a href="http://boost-spirit.com" target="_top">Spirit</a>
but nevertheless can be used separately to build stand alone lexical analyzers.
The first quick start example describes a stand alone application: counting
characters, words, and lines in a file, very similar to what the well known
Unix command <code class="computeroutput"><span class="identifier">wc</span></code> is doing
(for the full example code see here: <a href="../../../../../example/lex/word_count_functor.cpp" target="_top">word_count_functor.cpp</a>).
</p>
<h6>
<a name="spirit.lex.tutorials.lexer_quickstart1.h0"></a>
<span><a name="spirit.lex.tutorials.lexer_quickstart1.prerequisites"></a></span><a class="link" href="lexer_quickstart1.html#spirit.lex.tutorials.lexer_quickstart1.prerequisites">Prerequisites</a>
</h6>
<p>
The only required <code class="computeroutput"><span class="preprocessor">#include</span></code>
specific to <span class="emphasis"><em>Spirit.Lex</em></span> follows. It is a wrapper for
all necessary definitions to use <span class="emphasis"><em>Spirit.Lex</em></span> in a stand
alone fashion, and on top of the <a href="http://www.benhanson.net/lexertl.html" target="_top">Lexertl</a>
library. Additionally we <code class="computeroutput"><span class="preprocessor">#include</span></code>
two of the Boost headers to define <code class="computeroutput"><span class="identifier">boost</span><span class="special">::</span><span class="identifier">bind</span><span class="special">()</span></code> and <code class="computeroutput"><span class="identifier">boost</span><span class="special">::</span><span class="identifier">ref</span><span class="special">()</span></code>.
</p>
<p>
</p>
<pre class="programlisting"><span class="preprocessor">#include</span> <span class="special"><</span><span class="identifier">boost</span><span class="special">/</span><span class="identifier">spirit</span><span class="special">/</span><span class="identifier">include</span><span class="special">/</span><span class="identifier">lex_lexertl</span><span class="special">.</span><span class="identifier">hpp</span><span class="special">></span>
<span class="preprocessor">#include</span> <span class="special"><</span><span class="identifier">boost</span><span class="special">/</span><span class="identifier">bind</span><span class="special">.</span><span class="identifier">hpp</span><span class="special">></span>
<span class="preprocessor">#include</span> <span class="special"><</span><span class="identifier">boost</span><span class="special">/</span><span class="identifier">ref</span><span class="special">.</span><span class="identifier">hpp</span><span class="special">></span>
</pre>
<p>
</p>
<p>
To make all the code below more readable we introduce the following namespaces.
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">namespace</span> <span class="identifier">lex</span> <span class="special">=</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">spirit</span><span class="special">::</span><span class="identifier">lex</span><span class="special">;</span>
</pre>
<p>
</p>
<h6>
<a name="spirit.lex.tutorials.lexer_quickstart1.h1"></a>
<span><a name="spirit.lex.tutorials.lexer_quickstart1.defining_tokens"></a></span><a class="link" href="lexer_quickstart1.html#spirit.lex.tutorials.lexer_quickstart1.defining_tokens">Defining
Tokens</a>
</h6>
<p>
The most important step while creating a lexer using <span class="emphasis"><em>Spirit.Lex</em></span>
is to define the tokens to be recognized in the input sequence. This is
normally done by defining the regular expressions describing the matching
character sequences, and optionally their corresponding token ids. Additionally
the defined tokens need to be associated with an instance of a lexer object
as provided by the library. The following code snippet shows how this can
be done using <span class="emphasis"><em>Spirit.Lex</em></span>.
</p>
<p>
The template <code class="computeroutput"><span class="identifier">word_count_tokens</span></code>
defines three different tokens: <code class="computeroutput"><span class="identifier">ID_WORD</span></code>,
<code class="computeroutput"><span class="identifier">ID_EOL</span></code>, and <code class="computeroutput"><span class="identifier">ID_CHAR</span></code>, representing a word (anything
except a whitespace or a newline), a newline character, and any other character
(<code class="computeroutput"><span class="identifier">ID_WORD</span></code>, <code class="computeroutput"><span class="identifier">ID_EOL</span></code>, and <code class="computeroutput"><span class="identifier">ID_CHAR</span></code>
are enum values representing the token ids, but could be anything else
convertible to an integer as well). The direct base class of any token
definition class needs to be the template <code class="computeroutput"><span class="identifier">lex</span><span class="special">::</span><span class="identifier">lexer</span><span class="special"><></span></code>, where the corresponding template
parameter (here: <code class="computeroutput"><span class="identifier">lex</span><span class="special">::</span><span class="identifier">lexertl</span><span class="special">::</span><span class="identifier">lexer</span><span class="special"><</span><span class="identifier">BaseIterator</span><span class="special">></span></code>)
defines which underlying lexer engine has to be used to provide the required
state machine functionality. In this example we use the Lexertl based lexer
engine as the underlying lexer type.
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">template</span> <span class="special"><</span><span class="keyword">typename</span> <span class="identifier">Lexer</span><span class="special">></span>
<span class="keyword">struct</span> <span class="identifier">word_count_tokens</span> <span class="special">:</span> <span class="identifier">lex</span><span class="special">::</span><span class="identifier">lexer</span><span class="special"><</span><span class="identifier">Lexer</span><span class="special">></span>
<span class="special">{</span>
<span class="identifier">word_count_tokens</span><span class="special">()</span>
<span class="special">{</span>
<span class="comment">// define tokens (the regular expression to match and the corresponding</span>
<span class="comment">// token id) and add them to the lexer </span>
<span class="keyword">this</span><span class="special">-></span><span class="identifier">self</span><span class="special">.</span><span class="identifier">add</span>
<span class="special">(</span><span class="string">"[^ \t\n]+"</span><span class="special">,</span> <span class="identifier">ID_WORD</span><span class="special">)</span> <span class="comment">// words (anything except ' ', '\t' or '\n')</span>
<span class="special">(</span><span class="string">"\n"</span><span class="special">,</span> <span class="identifier">ID_EOL</span><span class="special">)</span> <span class="comment">// newline characters</span>
<span class="special">(</span><span class="string">"."</span><span class="special">,</span> <span class="identifier">ID_CHAR</span><span class="special">)</span> <span class="comment">// anything else is a plain character</span>
<span class="special">;</span>
<span class="special">}</span>
<span class="special">};</span>
</pre>
<p>
</p>
<h6>
<a name="spirit.lex.tutorials.lexer_quickstart1.h2"></a>
<span><a name="spirit.lex.tutorials.lexer_quickstart1.doing_the_useful_work"></a></span><a class="link" href="lexer_quickstart1.html#spirit.lex.tutorials.lexer_quickstart1.doing_the_useful_work">Doing
the Useful Work</a>
</h6>
<p>
We will use a setup, where we want the <span class="emphasis"><em>Spirit.Lex</em></span>
library to invoke a given function after any of of the generated tokens
is recognized. For this reason we need to implement a functor taking at
least the generated token as an argument and returning a boolean value
allowing to stop the tokenization process. The default token type used
in this example carries a token value of the type <a href="../../../../../../../libs/range/doc/html/range/reference/utilities/iterator_range.html" target="_top"><code class="computeroutput"><span class="identifier">boost</span><span class="special">::</span><span class="identifier">iterator_range</span></code></a><code class="computeroutput"><span class="special"><</span><span class="identifier">BaseIterator</span><span class="special">></span></code>
pointing to the matched range in the underlying input sequence.
</p>
<p>
In this example the struct 'counter' is used as a functor counting the
characters, words and lines in the analyzed input sequence by identifying
the matched tokens as passed from the <span class="emphasis"><em>Spirit.Lex</em></span> library.
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">struct</span> <span class="identifier">counter</span>
<span class="special">{</span>
<span class="comment">// the function operator gets called for each of the matched tokens</span>
<span class="comment">// c, l, w are references to the counters used to keep track of the numbers</span>
<span class="keyword">template</span> <span class="special"><</span><span class="keyword">typename</span> <span class="identifier">Token</span><span class="special">></span>
<span class="keyword">bool</span> <span class="keyword">operator</span><span class="special">()(</span><span class="identifier">Token</span> <span class="keyword">const</span><span class="special">&</span> <span class="identifier">t</span><span class="special">,</span> <span class="identifier">std</span><span class="special">::</span><span class="identifier">size_t</span><span class="special">&</span> <span class="identifier">c</span><span class="special">,</span> <span class="identifier">std</span><span class="special">::</span><span class="identifier">size_t</span><span class="special">&</span> <span class="identifier">w</span><span class="special">,</span> <span class="identifier">std</span><span class="special">::</span><span class="identifier">size_t</span><span class="special">&</span> <span class="identifier">l</span><span class="special">)</span> <span class="keyword">const</span>
<span class="special">{</span>
<span class="keyword">switch</span> <span class="special">(</span><span class="identifier">t</span><span class="special">.</span><span class="identifier">id</span><span class="special">())</span> <span class="special">{</span>
<span class="keyword">case</span> <span class="identifier">ID_WORD</span><span class="special">:</span> <span class="comment">// matched a word</span>
<span class="comment">// since we're using a default token type in this example, every </span>
<span class="comment">// token instance contains a `iterator_range<BaseIterator>` as its token</span>
<span class="comment">// attribute pointing to the matched character sequence in the input </span>
<span class="special">++</span><span class="identifier">w</span><span class="special">;</span> <span class="identifier">c</span> <span class="special">+=</span> <span class="identifier">t</span><span class="special">.</span><span class="identifier">value</span><span class="special">().</span><span class="identifier">size</span><span class="special">();</span>
<span class="keyword">break</span><span class="special">;</span>
<span class="keyword">case</span> <span class="identifier">ID_EOL</span><span class="special">:</span> <span class="comment">// matched a newline character</span>
<span class="special">++</span><span class="identifier">l</span><span class="special">;</span> <span class="special">++</span><span class="identifier">c</span><span class="special">;</span>
<span class="keyword">break</span><span class="special">;</span>
<span class="keyword">case</span> <span class="identifier">ID_CHAR</span><span class="special">:</span> <span class="comment">// matched something else</span>
<span class="special">++</span><span class="identifier">c</span><span class="special">;</span>
<span class="keyword">break</span><span class="special">;</span>
<span class="special">}</span>
<span class="keyword">return</span> <span class="keyword">true</span><span class="special">;</span> <span class="comment">// always continue to tokenize</span>
<span class="special">}</span>
<span class="special">};</span>
</pre>
<p>
</p>
<p>
All what is left is to write some boilerplate code helping to tie together
the pieces described so far. To simplify this example we call the <code class="computeroutput"><span class="identifier">lex</span><span class="special">::</span><span class="identifier">tokenize</span><span class="special">()</span></code>
function implemented in <span class="emphasis"><em>Spirit.Lex</em></span> (for a more detailed
description of this function see here: <span class="bold"><strong>FIXME</strong></span>),
even if we could have written a loop to iterate over the lexer iterators
[<code class="computeroutput"><span class="identifier">first</span></code>, <code class="computeroutput"><span class="identifier">last</span></code>)
as well.
</p>
<h6>
<a name="spirit.lex.tutorials.lexer_quickstart1.h3"></a>
<span><a name="spirit.lex.tutorials.lexer_quickstart1.pulling_everything_together"></a></span><a class="link" href="lexer_quickstart1.html#spirit.lex.tutorials.lexer_quickstart1.pulling_everything_together">Pulling
Everything Together</a>
</h6>
<p>
The main function simply loads the given file into memory (as a <code class="computeroutput"><span class="identifier">std</span><span class="special">::</span><span class="identifier">string</span></code>), instantiates an instance of
the token definition template using the correct iterator type (<code class="computeroutput"><span class="identifier">word_count_tokens</span><span class="special"><</span><span class="keyword">char</span> <span class="keyword">const</span><span class="special">*></span></code>), and finally calls <code class="computeroutput"><span class="identifier">lex</span><span class="special">::</span><span class="identifier">tokenize</span></code>, passing an instance of the
counter function object. The return value of <code class="computeroutput"><span class="identifier">lex</span><span class="special">::</span><span class="identifier">tokenize</span><span class="special">()</span></code> will be <code class="computeroutput"><span class="keyword">true</span></code>
if the whole input sequence has been successfully tokenized, and <code class="computeroutput"><span class="keyword">false</span></code> otherwise.
</p>
<p>
</p>
<pre class="programlisting"><span class="keyword">int</span> <span class="identifier">main</span><span class="special">(</span><span class="keyword">int</span> <span class="identifier">argc</span><span class="special">,</span> <span class="keyword">char</span><span class="special">*</span> <span class="identifier">argv</span><span class="special">[])</span>
<span class="special">{</span>
<span class="comment">// these variables are used to count characters, words and lines</span>
<span class="identifier">std</span><span class="special">::</span><span class="identifier">size_t</span> <span class="identifier">c</span> <span class="special">=</span> <span class="number">0</span><span class="special">,</span> <span class="identifier">w</span> <span class="special">=</span> <span class="number">0</span><span class="special">,</span> <span class="identifier">l</span> <span class="special">=</span> <span class="number">0</span><span class="special">;</span>
<span class="comment">// read input from the given file</span>
<span class="identifier">std</span><span class="special">::</span><span class="identifier">string</span> <span class="identifier">str</span> <span class="special">(</span><span class="identifier">read_from_file</span><span class="special">(</span><span class="number">1</span> <span class="special">==</span> <span class="identifier">argc</span> <span class="special">?</span> <span class="string">"word_count.input"</span> <span class="special">:</span> <span class="identifier">argv</span><span class="special">[</span><span class="number">1</span><span class="special">]));</span>
<span class="comment">// create the token definition instance needed to invoke the lexical analyzer</span>
<span class="identifier">word_count_tokens</span><span class="special"><</span><span class="identifier">lex</span><span class="special">::</span><span class="identifier">lexertl</span><span class="special">::</span><span class="identifier">lexer</span><span class="special"><></span> <span class="special">></span> <span class="identifier">word_count_functor</span><span class="special">;</span>
<span class="comment">// tokenize the given string, the bound functor gets invoked for each of </span>
<span class="comment">// the matched tokens</span>
<span class="keyword">char</span> <span class="keyword">const</span><span class="special">*</span> <span class="identifier">first</span> <span class="special">=</span> <span class="identifier">str</span><span class="special">.</span><span class="identifier">c_str</span><span class="special">();</span>
<span class="keyword">char</span> <span class="keyword">const</span><span class="special">*</span> <span class="identifier">last</span> <span class="special">=</span> <span class="special">&</span><span class="identifier">first</span><span class="special">[</span><span class="identifier">str</span><span class="special">.</span><span class="identifier">size</span><span class="special">()];</span>
<span class="keyword">bool</span> <span class="identifier">r</span> <span class="special">=</span> <span class="identifier">lex</span><span class="special">::</span><span class="identifier">tokenize</span><span class="special">(</span><span class="identifier">first</span><span class="special">,</span> <span class="identifier">last</span><span class="special">,</span> <span class="identifier">word_count_functor</span><span class="special">,</span>
<span class="identifier">boost</span><span class="special">::</span><span class="identifier">bind</span><span class="special">(</span><span class="identifier">counter</span><span class="special">(),</span> <span class="identifier">_1</span><span class="special">,</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">ref</span><span class="special">(</span><span class="identifier">c</span><span class="special">),</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">ref</span><span class="special">(</span><span class="identifier">w</span><span class="special">),</span> <span class="identifier">boost</span><span class="special">::</span><span class="identifier">ref</span><span class="special">(</span><span class="identifier">l</span><span class="special">)));</span>
<span class="comment">// print results</span>
<span class="keyword">if</span> <span class="special">(</span><span class="identifier">r</span><span class="special">)</span> <span class="special">{</span>
<span class="identifier">std</span><span class="special">::</span><span class="identifier">cout</span> <span class="special"><<</span> <span class="string">"lines: "</span> <span class="special"><<</span> <span class="identifier">l</span> <span class="special"><<</span> <span class="string">", words: "</span> <span class="special"><<</span> <span class="identifier">w</span>
<span class="special"><<</span> <span class="string">", characters: "</span> <span class="special"><<</span> <span class="identifier">c</span> <span class="special"><<</span> <span class="string">"\n"</span><span class="special">;</span>
<span class="special">}</span>
<span class="keyword">else</span> <span class="special">{</span>
<span class="identifier">std</span><span class="special">::</span><span class="identifier">string</span> <span class="identifier">rest</span><span class="special">(</span><span class="identifier">first</span><span class="special">,</span> <span class="identifier">last</span><span class="special">);</span>
<span class="identifier">std</span><span class="special">::</span><span class="identifier">cout</span> <span class="special"><<</span> <span class="string">"Lexical analysis failed\n"</span> <span class="special"><<</span> <span class="string">"stopped at: \""</span>
<span class="special"><<</span> <span class="identifier">rest</span> <span class="special"><<</span> <span class="string">"\"\n"</span><span class="special">;</span>
<span class="special">}</span>
<span class="keyword">return</span> <span class="number">0</span><span class="special">;</span>
<span class="special">}</span>
</pre>
<p>
</p>
<h6>
<a name="spirit.lex.tutorials.lexer_quickstart1.h4"></a>
<span><a name="spirit.lex.tutorials.lexer_quickstart1.comparing__emphasis_spirit_lex__emphasis__with__ulink_url__http___flex_sourceforge_net___flex__ulink_"></a></span><a class="link" href="lexer_quickstart1.html#spirit.lex.tutorials.lexer_quickstart1.comparing__emphasis_spirit_lex__emphasis__with__ulink_url__http___flex_sourceforge_net___flex__ulink_">Comparing
<span class="emphasis"><em>Spirit.Lex</em></span> with <a href="http://flex.sourceforge.net/" target="_top">Flex</a></a>
</h6>
<p>
This example was deliberately chosen to be as much as possible similar
to the equivalent <a href="http://flex.sourceforge.net/" target="_top">Flex</a>
program (see below), which isn't too different from what has to be written
when using <span class="emphasis"><em>Spirit.Lex</em></span>.
</p>
<div class="note"><table border="0" summary="Note">
<tr>
<td rowspan="2" align="center" valign="top" width="25"><img alt="[Note]" src="../../../images/note.png"></td>
<th align="left">Note</th>
</tr>
<tr><td align="left" valign="top"><p>
Interestingly enough, performance comparisons of lexical analyzers written
using <span class="emphasis"><em>Spirit.Lex</em></span> with equivalent programs generated
by <a href="http://flex.sourceforge.net/" target="_top">Flex</a> show that both
have comparable execution speeds! Generally, thanks to the highly optimized
<a href="http://www.benhanson.net/lexertl.html" target="_top">Lexertl</a> library
and due its carefully designed integration with <a href="http://boost-spirit.com" target="_top">Spirit</a>
the abstraction penalty to be paid for using <span class="emphasis"><em>Spirit.Lex</em></span>
is negligible.
</p></td></tr>
</table></div>
<p>
The remaining examples in this tutorial will use more sophisticated features
of <span class="emphasis"><em>Spirit.Lex</em></span>, mainly to allow further simplification
of the code to be written, while maintaining the similarity with corresponding
features of <a href="http://flex.sourceforge.net/" target="_top">Flex</a>. <span class="emphasis"><em>Spirit.Lex</em></span>
has been designed to be as similar to <a href="http://flex.sourceforge.net/" target="_top">Flex</a>
as possible. That is why this documentation will provide the corresponding
<a href="http://flex.sourceforge.net/" target="_top">Flex</a> code for the shown
<span class="emphasis"><em>Spirit.Lex</em></span> examples almost everywhere. So consequently,
here is the <a href="http://flex.sourceforge.net/" target="_top">Flex</a> code
corresponding to the example as shown above.
</p>
<p>
</p>
<pre class="programlisting"><span class="special">%{</span>
<span class="preprocessor">#define</span> <span class="identifier">ID_WORD</span> <span class="number">1000</span>
<span class="preprocessor">#define</span> <span class="identifier">ID_EOL</span> <span class="number">1001</span>
<span class="preprocessor">#define</span> <span class="identifier">ID_CHAR</span> <span class="number">1002</span>
<span class="keyword">int</span> <span class="identifier">c</span> <span class="special">=</span> <span class="number">0</span><span class="special">,</span> <span class="identifier">w</span> <span class="special">=</span> <span class="number">0</span><span class="special">,</span> <span class="identifier">l</span> <span class="special">=</span> <span class="number">0</span><span class="special">;</span>
<span class="special">%}</span>
<span class="special">%%</span>
<span class="special">[^</span> <span class="special">\</span><span class="identifier">t</span><span class="special">\</span><span class="identifier">n</span><span class="special">]+</span> <span class="special">{</span> <span class="keyword">return</span> <span class="identifier">ID_WORD</span><span class="special">;</span> <span class="special">}</span>
<span class="special">\</span><span class="identifier">n</span> <span class="special">{</span> <span class="keyword">return</span> <span class="identifier">ID_EOL</span><span class="special">;</span> <span class="special">}</span>
<span class="special">.</span> <span class="special">{</span> <span class="keyword">return</span> <span class="identifier">ID_CHAR</span><span class="special">;</span> <span class="special">}</span>
<span class="special">%%</span>
<span class="keyword">bool</span> <span class="identifier">count</span><span class="special">(</span><span class="keyword">int</span> <span class="identifier">tok</span><span class="special">)</span>
<span class="special">{</span>
<span class="keyword">switch</span> <span class="special">(</span><span class="identifier">tok</span><span class="special">)</span> <span class="special">{</span>
<span class="keyword">case</span> <span class="identifier">ID_WORD</span><span class="special">:</span> <span class="special">++</span><span class="identifier">w</span><span class="special">;</span> <span class="identifier">c</span> <span class="special">+=</span> <span class="identifier">yyleng</span><span class="special">;</span> <span class="keyword">break</span><span class="special">;</span>
<span class="keyword">case</span> <span class="identifier">ID_EOL</span><span class="special">:</span> <span class="special">++</span><span class="identifier">l</span><span class="special">;</span> <span class="special">++</span><span class="identifier">c</span><span class="special">;</span> <span class="keyword">break</span><span class="special">;</span>
<span class="keyword">case</span> <span class="identifier">ID_CHAR</span><span class="special">:</span> <span class="special">++</span><span class="identifier">c</span><span class="special">;</span> <span class="keyword">break</span><span class="special">;</span>
<span class="keyword">default</span><span class="special">:</span>
<span class="keyword">return</span> <span class="keyword">false</span><span class="special">;</span>
<span class="special">}</span>
<span class="keyword">return</span> <span class="keyword">true</span><span class="special">;</span>
<span class="special">}</span>
<span class="keyword">void</span> <span class="identifier">main</span><span class="special">()</span>
<span class="special">{</span>
<span class="keyword">int</span> <span class="identifier">tok</span> <span class="special">=</span> <span class="identifier">EOF</span><span class="special">;</span>
<span class="keyword">do</span> <span class="special">{</span>
<span class="identifier">tok</span> <span class="special">=</span> <span class="identifier">yylex</span><span class="special">();</span>
<span class="keyword">if</span> <span class="special">(!</span><span class="identifier">count</span><span class="special">(</span><span class="identifier">tok</span><span class="special">))</span>
<span class="keyword">break</span><span class="special">;</span>
<span class="special">}</span> <span class="keyword">while</span> <span class="special">(</span><span class="identifier">EOF</span> <span class="special">!=</span> <span class="identifier">tok</span><span class="special">);</span>
<span class="identifier">printf</span><span class="special">(</span><span class="string">"%d %d %d\n"</span><span class="special">,</span> <span class="identifier">l</span><span class="special">,</span> <span class="identifier">w</span><span class="special">,</span> <span class="identifier">c</span><span class="special">);</span>
<span class="special">}</span>
</pre>
<p>
</p>
</div>
<table xmlns:rev="http://www.cs.rpi.edu/~gregod/boost/tools/doc/revision" width="100%"><tr>
<td align="left"></td>
<td align="right"><div class="copyright-footer">Copyright © 2001-2011 Joel de Guzman, Hartmut Kaiser<p>
Distributed under the Boost Software License, Version 1.0. (See accompanying
file LICENSE_1_0.txt or copy at <a href="http://www.boost.org/LICENSE_1_0.txt" target="_top">http://www.boost.org/LICENSE_1_0.txt</a>)
</p>
</div></td>
</tr></table>
<hr>
<div class="spirit-nav">
<a accesskey="p" href="lexer_tutorials.html"><img src="../../../../../../../doc/src/images/prev.png" alt="Prev"></a><a accesskey="u" href="../tutorials.html"><img src="../../../../../../../doc/src/images/up.png" alt="Up"></a><a accesskey="h" href="../../../index.html"><img src="../../../../../../../doc/src/images/home.png" alt="Home"></a><a accesskey="n" href="lexer_quickstart2.html"><img src="../../../../../../../doc/src/images/next.png" alt="Next"></a>
</div>
</body>
</html>
|
