This file is indexed.

/usr/share/doc/swig2.0-doc/Devel/scanner.html is in swig2.0-doc 2.0.12-1ubuntu4.

This file is owned by root:root, with mode 0o644.

The actual contents of the file can be viewed below.

  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
<html>
<head>
<title>SWIG C Scanner</title>
</head>

<body>
<center>
<h1>SWIG C/C++ Scanning</h1>

<p>
David M. Beazley <br>
dave-swig@dabeaz.com<br>
January 11, 2007<br>

</b>
</center>

<h2>Introduction</h2>

This document describes functions that can be used to tokenize C/C++
input text.  These functions are relatively low-level and are meant to
be used in the implementation of scanners that can be plugged into yacc or used for
other purposes.  For instance, the preprocessor uses these functions to evaluate and test 
constant expressions.  

<p>
All of these functions are declared in <tt>Source/Swig/swigscan.h</tt>.   This API is considered to be stable.

<h2>Creation and Deletion of Scanners</h2>

The following functions are used to create and destroy a scanner object.  More than one scanner object can be created and used
as necessary.

<p>
<b><tt>Scanner *NewScanner()</tt></b>

<blockquote>
Creates a new scanner object.  The scanner contains initially contains no text.  To feed text to the scanner use <tt>Scanner_push()</tt>.
</blockquote>

<p>
<b><tt>Scanner *DelScanner()</tt></b>

<blockquote>
Deletes a scanner object. 
</blockquote>

<h2>Scanner Functions</h2>

<p>
<b><tt>void Scanner_clear(Scanner *s)</tt></b>
<blockquote>
Clears all text from the scanner.  This can be used to reset a scanner to its initial state, ready to receive new input text.
</blockquote>

<p>
<b><tt>void Scanner_push(Scanner *s, String *text)</tt></b>
<blockquote>
Pushes an input string into the scanner. Subsequent tokens will be
returned from the new string.  If the scanner is already processing a
string, the pushed string takes precedence--in effect, interrupting
the scanning of the previous string.  This behavior is used to
implement certain SWIG features such as the <tt>%inline</tt>
directive. Once the pushed string has been completely scanned, the
scanner will return to scanning the previous string (if any).  The
scanning of text relies upon the DOH file interface to strings
(<tt>Getc()</tt>, <tt>Ungetc()</tt>, etc.).  Prior to calling this
function, the input string should be set so that its file pointer is
in the location where you want scanning to begin. You may have to
use <tt>Seek()</tt> to set the file pointer back to the beginning of a
string prior to using this function.
</blockquote>

<p>
<b><tt>void Scanner_pushtoken(Scanner *s, int tokvalue, String_or_char *val)</tt></b>
<blockquote>
Pushes a token into the scanner.  This exact token will be returned by the next call to <tt>Scanner_token()</tt>.  
<tt>tokvalue</tt> is the integer token value to return and <tt>val</tt> is the token text to return.   This
function is only used to handle very special parsing cases. For instance, if you need the scanner to
return a fictitious token into order to enter a special parsing case.
</blockquote>

<p>
<b><tt>int Scanner_token(Scanner *s)</tt></b>

<blockquote>
Returns the next token.  An integer token code is returned (see table below) on success.  If no more input text is
available 0 is returned.  If a scanning error occurred, -1 is returned.  In this case, error information can be
obtained using <tt>Scanner_errinfo()</tt>.
</blockquote>

<p>
<b><tt>String *Scanner_text(Scanner *s)</tt></b>
<blockquote>
Returns the scanned text corresponding to the last token returned by <tt>Scanner_token()</tt>.   The returned string
is only valid until the next call to <tt>Scanner_token()</tt>. If you need to save it, make a copy.
</blockquote>

<p>
<b><tt>void Scanner_skip_line(Scanner *s)</tt></b>
<blockquote>
Skips to the end of the current line.   The text skipped can be obtained using <tt>Scanner_text()</tt> afterwards.
</blockquote>

<p>
<b><tt>void Scanner_skip_balanced(Scanner *s, int startchar, int endchar)</tt></b>
<blockquote>
Skips to the end of a block of text denoted by starting and ending characters.  For example, <tt>{</tt> and <tt>}</tt>.  The
function is smart about how it skips text.  String literals and comments are ignored.   The function also is aware of nesting.  The
skipped text can be obtained using <tt>Scanner_text()</tt> afterwards. Returns 0 on success, -1 if no matching <tt>endchar</tt> could be found.
</blockquote>


<p>
<b><tt>void Scanner_set_location(Scanner *s, int startchar, int endchar)</tt></b>
<blockquote>
Changes the current filename and line number of the scanner.
</blockquote>

<p>
<b><tt>String *Scanner_file(Scanner *s)</tt></b>
<blockquote>
Gets the current filename associated with text in the scanner.
</blockquote>

<p>
<b><tt>int Scanner_line(Scanner *s)</tt></b>
<blockquote>
Gets the current line number associated with text in the scanner.
</blockquote>

<p>
<b><tt>int Scanner_start_line(Scanner *s)</tt></b>
<blockquote>
Gets the starting line number of the last token returned by the scanner.
</blockquote>

<p>
<b><tt>void Scanner_idstart(Scanner *s, char *idchar)</tt></b>
<blockquote>
Sets additional characters (other than the C default) that may be used to start C identifiers.  <tt>idchar</tt> is a string
containing the characters (e.g., "%@").  The purpose of this function is to up special keywords such as "%module" or "@directive" as
simple identifiers.
</blockquote>

<p>
<b><tt>String *Scanner_errmsg(Scanner *s)</tt></b>
<blockquote>
Returns the error message associated with the last scanner error (if any).   This will only return a meaningful result
if <tt>Scanner_token()</tt> returned -1.
</blockquote>

<p>
<b><tt>int Scanner_errline(Scanner *s)</tt></b>
<blockquote>
Returns the line number associated with the last scanner error (if any).   This will only return a meaningful result
if <tt>Scanner_token()</tt> returned -1.  The line number usually corresponds to the starting line number of a particular
token (e.g., for unterminated strings, comments, etc.).
</blockquote>

<p>
<b><tt>int Scanner_isoperator(int tokval)</tt></b>
<blockquote>
A convenience function that returns 0 or 1 depending on whether <tt>tokval</tt> is a valid C/C++ operator (i.e., a candidate for
operator overloading).  
</blockquote>

<p>
<b><tt>void Scanner_freeze_line(int val)</tt></b>
<blockquote>
Freezes the current line number depending upon whether or not <tt>val</tt> is 1 or 0.  When the line number is frozen, newline characters will not result in 
updates to the line number.  This is sometimes useful in tracking line numbers through complicated macro expansions.
</blockquote>


<h2>Token Codes</h2>

The following table shows token codes returned by the scanner.  These are integer codes returned by
the <tt>Scanner_token()</tt> function.

<blockquote>
<pre>
Token code                   C Token
-------------------------    -------------
SWIG_TOKEN_LPAREN            (
SWIG_TOKEN_RPAREN            )
SWIG_TOKEN_SEMI              ; 
SWIG_TOKEN_COMMA             , 
SWIG_TOKEN_STAR              * 
SWIG_TOKEN_TIMES             *
SWIG_TOKEN_LBRACE            { 
SWIG_TOKEN_RBRACE            } 
SWIG_TOKEN_EQUAL             = 
SWIG_TOKEN_EQUALTO           == 
SWIG_TOKEN_NOTEQUAL          != 
SWIG_TOKEN_PLUS              + 
SWIG_TOKEN_MINUS             - 
SWIG_TOKEN_AND               &amp; 
SWIG_TOKEN_LAND              &amp;&amp; 
SWIG_TOKEN_OR                | 
SWIG_TOKEN_LOR               || 
SWIG_TOKEN_XOR               ^ 
SWIG_TOKEN_LESSTHAN          &lt; 
SWIG_TOKEN_GREATERTHAN       &gt; 
SWIG_TOKEN_LTEQUAL           &lt;= 
SWIG_TOKEN_GTEQUAL           &gt;= 
SWIG_TOKEN_NOT               ~ 
SWIG_TOKEN_LNOT              ! 
SWIG_TOKEN_LBRACKET          [ 
SWIG_TOKEN_RBRACKET          ] 
SWIG_TOKEN_SLASH             / 
SWIG_TOKEN_DIVIDE            /
SWIG_TOKEN_BACKSLASH         \ 
SWIG_TOKEN_POUND             # 
SWIG_TOKEN_PERCENT           % 
SWIG_TOKEN_MODULO            %
SWIG_TOKEN_COLON             : 
SWIG_TOKEN_DCOLON            :: 
SWIG_TOKEN_DCOLONSTAR        ::*
SWIG_TOKEN_LSHIFT            &lt;&lt; 
SWIG_TOKEN_RSHIFT            &gt;&gt; 
SWIG_TOKEN_QUESTION          ? 
SWIG_TOKEN_PLUSPLUS          ++ 
SWIG_TOKEN_MINUSMINUS        -- 
SWIG_TOKEN_PLUSEQUAL         += 
SWIG_TOKEN_MINUSEQUAL        -= 
SWIG_TOKEN_TIMESEQUAL        *= 
SWIG_TOKEN_DIVEQUAL          /= 
SWIG_TOKEN_ANDEQUAL          &amp;= 
SWIG_TOKEN_OREQUAL           |= 
SWIG_TOKEN_XOREQUAL          ^= 
SWIG_TOKEN_LSEQUAL           &lt;&lt;= 
SWIG_TOKEN_RSEQUAL           &gt;&gt;= 
SWIG_TOKEN_MODEQUAL          %= 
SWIG_TOKEN_ARROW             -&gt; 
SWIG_TOKEN_ARROWSTAR         -&gt;* 
SWIG_TOKEN_PERIOD            . 
SWIG_TOKEN_AT                @ 
SWIG_TOKEN_DOLLAR            $ 
SWIG_TOKEN_ENDLINE           Literal newline
SWIG_TOKEN_ID                identifier 
SWIG_TOKEN_FLOAT             Floating point with F suffix (e.g., 3.1415F)
SWIG_TOKEN_DOUBLE            Floating point (e.g., 3.1415 )
SWIG_TOKEN_INT               Integer (e.g., 314)
SWIG_TOKEN_UINT              Unsigned integer (e.g., 314U)
SWIG_TOKEN_LONG              Long integer (e.g., 314L) 
SWIG_TOKEN_ULONG             Unsigned long integer (e.g., 314UL)
SWIG_TOKEN_LONGLONG          Long long integer (e.g., 314LL )
SWIG_TOKEN_ULONGLONG         Unsigned long long integer (e.g., 314ULL) 
SWIG_TOKEN_CHAR              Character literal in single quotes ('c')
SWIG_TOKEN_STRING            String literal in double quotes ("str")
SWIG_TOKEN_RSTRING           Reverse quote string (`str`)
SWIG_TOKEN_CODEBLOCK         SWIG code literal block %{ ... %}
SWIG_TOKEN_COMMENT           C or C++ comment  (// or /* ... */)
SWIG_TOKEN_ILLEGAL           Illegal character
</pre>
</blockquote>

<b>Notes</b>

<ul>
<li>When more than one token code exist for the same token text, those codes are identical (e.g., <tt>SWIG_TOKEN_STAR</tt> and <tt>SWIG_TOKEN_TIMES</tt>).

<p>
<li>
String literals are returned in their exact representation in which escape codes (if any) have been interpreted.

<p>
<li>
All C identifiers and keywords are simply returned as <tt>SWIG_TOKEN_ID</tt>.  To check for specific keywords, you will need to
add extra checking on the returned text.

<p>
<li>C and C++ comments include the comment starting and ending text (e.g., "//", "/*").

<p>
<li>The maximum token integer value is found in the constant <tt>SWIG_MAXTOKENS</tt>.   This can be used if you wanted to create 
an array or table for the purposes of remapping tokens to a different set of codes. For instance, if you are
using these functions to write a yacc-compatible lexer.
</ul>

</body>
</html>