summaryrefslogtreecommitdiffstats
path: root/source3/utils/debugparse.c
blob: 5835de1b8d7cd87421f48e444e9a286315b1f114 (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
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
/* ========================================================================== **
 *                                debugparse.c
 *
 * Copyright (C) 1998 by Christopher R. Hertel
 *
 * Email: crh@ubiqx.mn.org
 *
 * -------------------------------------------------------------------------- **
 * This module is a very simple parser for Samba debug log files.
 * -------------------------------------------------------------------------- **
 *
 *  This library is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU Lesser General Public
 *  License as published by the Free Software Foundation; either
 *  version 3 of the License, or (at your option) any later version.
 *
 *  This library 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
 *  Library General Public License for more details.
 *
 *  You should have received a copy of the GNU Lesser General Public
 *  License along with this library; if not, see <http://www.gnu.org/licenses/>.
 *
 * -------------------------------------------------------------------------- **
 * The important function in this module is dbg_char2token().  The rest is
 * basically fluff.  (Potentially useful fluff, but still fluff.)
 * ========================================================================== **
 */

#include "debugparse.h"

/* -------------------------------------------------------------------------- **
 * Constants...
 *
 *  DBG_BSIZE - This internal constant is used only by dbg_test().  It is the
 *          size of the read buffer.  I've tested the function using a
 *          DBG_BSIZE value of 2.
 */

#define DBG_BSIZE 128

/* -------------------------------------------------------------------------- **
 * Functions...
 */

const char *dbg_token2string( dbg_Token tok )
  /* ------------------------------------------------------------------------ **
   * Given a token, return a string describing the token.
   *
   *  Input:  tok - One of the set of dbg_Tokens defined in debugparse.h.
   *
   *  Output: A string identifying the token.  This is useful for debugging,
   *          etc.
   *
   *  Note:   If the token is not known, this function will return the
   *          string "<unknown>".
   *
   * ------------------------------------------------------------------------ **
   */
  {
  switch( tok )
    {
    case dbg_null:
      return( "null" );
    case dbg_ignore:
      return( "ignore" );
    case dbg_header:
      return( "header" );
    case dbg_timestamp:
      return( "time stamp" );
    case dbg_level:
      return( "level" );
    case dbg_sourcefile:
      return( "source file" );
    case dbg_function:
      return( "function" );
    case dbg_lineno:
      return( "line number" );
    case dbg_message:
      return( "message" );
    case dbg_eof:
      return( "[EOF]" );
    }
  return( "<unknown>" );
  } /* dbg_token2string */

dbg_Token dbg_char2token( dbg_Token *state, int c )
  /* ------------------------------------------------------------------------ **
   * Parse input one character at a time.
   *
   *  Input:  state - A pointer to a token variable.  This is used to
   *                  maintain the parser state between calls.  For
   *                  each input stream, you should set up a separate
   *                  state variable and initialize it to dbg_null.
   *                  Pass a pointer to it into this function with each
   *                  character in the input stream.  See dbg_test()
   *                  for an example.
   *          c     - The "current" character in the input stream.
   *
   *  Output: A token.
   *          The token value will change when delimiters are found,
   *          which indicate a transition between syntactical objects.
   *          Possible return values are:
   *
   *          dbg_null        - The input character was an end-of-line.
   *                            This resets the parser to its initial state
   *                            in preparation for parsing the next line.
   *          dbg_eof         - Same as dbg_null, except that the character
   *                            was an end-of-file.
   *          dbg_ignore      - Returned for whitespace and delimiters.
   *                            These lexical tokens are only of interest
   *                            to the parser.
   *          dbg_header      - Indicates the start of a header line.  The
   *                            input character was '[' and was the first on
   *                            the line.
   *          dbg_timestamp   - Indicates that the input character was part
   *                            of a header timestamp.
   *          dbg_level       - Indicates that the input character was part
   *                            of the debug-level value in the header.
   *          dbg_sourcefile  - Indicates that the input character was part
   *                            of the sourcefile name in the header.
   *          dbg_function    - Indicates that the input character was part
   *                            of the function name in the header.
   *          dbg_lineno      - Indicates that the input character was part
   *                            of the DEBUG call line number in the header.
   *          dbg_message     - Indicates that the input character was part
   *                            of the DEBUG message text.
   *
   * ------------------------------------------------------------------------ **
   */
  {
  /* The terminating characters that we see will greatly depend upon
   * how they are read.  For example, if gets() is used instead of
   * fgets(), then we will not see newline characters.  A lot also
   * depends on the calling function, which may handle terminators
   * itself.
   *
   * '\n', '\0', and EOF are all considered line terminators.  The
   * dbg_eof token is sent back if an EOF is encountered.
   *
   * Warning:  only allow the '\0' character to be sent if you are
   *           using gets() to read whole lines (thus replacing '\n'
   *           with '\0').  Sending '\0' at the wrong time will mess
   *           up the parsing.
   */
  switch( c )
    {
    case EOF:
      *state = dbg_null;   /* Set state to null (initial state) so */
      return( dbg_eof );   /* that we can restart with new input.  */
    case '\n':
    case '\0':
      *state = dbg_null;   /* A newline or eoln resets to the null state. */
      return( dbg_null );
    }

  /* When within the body of the message, only a line terminator
   * can cause a change of state.  We've already checked for line
   * terminators, so if the current state is dbg_msgtxt, simply
   * return that as our current token.
   */
  if( dbg_message == *state )
    return( dbg_message );

  /* If we are at the start of a new line, and the input character 
   * is an opening bracket, then the line is a header line, otherwise
   * it's a message body line.
   */
  if( dbg_null == *state )
    {
    if( '[' == c )
      {
      *state = dbg_timestamp;
      return( dbg_header );
      }
    *state = dbg_message;
    return( dbg_message );
    }

  /* We've taken care of terminators, text blocks and new lines.
   * The remaining possibilities are all within the header line
   * itself.
   */

  /* Within the header line, whitespace can be ignored *except*
   * within the timestamp.
   */
  if( isspace( c ) )
    {
    /* Fudge.  The timestamp may contain space characters. */
    if( (' ' == c) && (dbg_timestamp == *state) )
      return( dbg_timestamp );
    /* Otherwise, ignore whitespace. */
    return( dbg_ignore );
    }

  /* Okay, at this point we know we're somewhere in the header.
   * Valid header *states* are: dbg_timestamp, dbg_level,
   * dbg_sourcefile, dbg_function, and dbg_lineno.
   */
  switch( c )
    {
    case ',':
      if( dbg_timestamp == *state )
        {
        *state = dbg_level;
        return( dbg_ignore );
        }
      break;
    case ']':
      if( dbg_level == *state )
        {
        *state = dbg_sourcefile;
        return( dbg_ignore );
        }
      break;
    case ':':
      if( dbg_sourcefile == *state )
        {
        *state = dbg_function;
        return( dbg_ignore );
        }
      break;
    case '(':
      if( dbg_function == *state )
        {
        *state = dbg_lineno;
        return( dbg_ignore );
        }
      break;
    case ')':
      if( dbg_lineno == *state )
        {
        *state = dbg_null;
        return( dbg_ignore );
        }
      break;
    }

  /* If the previous block did not result in a state change, then
   * return the current state as the current token.
   */
  return( *state );
  } /* dbg_char2token */

void dbg_test( void );
void dbg_test( void )
  /* ------------------------------------------------------------------------ **
   * Simple test function.
   *
   *  Input:  none.
   *  Output: none.
   *  Notes:  This function was used to test dbg_char2token().  It reads a
   *          Samba log file from stdin and prints parsing info to stdout.
   *          It also serves as a simple example.
   *
   * ------------------------------------------------------------------------ **
   */
  {
  char bufr[DBG_BSIZE];
  int  i;
  int  linecount  = 1;
  dbg_Token old   = dbg_null,
            newtok= dbg_null,
            state = dbg_null;

  while( fgets( bufr, DBG_BSIZE, stdin ) )
    {
    for( i = 0; bufr[i]; i++ )
      {
      old = newtok;
      newtok = dbg_char2token( &state, bufr[i] );
      switch( newtok )
        {
        case dbg_header:
          if( linecount > 1 )
            (void)putchar( '\n' );
          break;
        case dbg_null:
          linecount++;
          break;
        case dbg_ignore:
          break;
        default:
          if( old != newtok )
            (void)printf( "\n[%05d]%12s: ", linecount, dbg_token2string(newtok) );
          (void)putchar( bufr[i] );
        }
      }
    }
  (void)putchar( '\n' );
  } /* dbg_test */


/* -------------------------------------------------------------------------- **
 * This simple main line can be uncommented and used to test the parser.
 */

/*
 * int main( void )
 *  {
 *  dbg_test();
 *  return( 0 );
 *  }
 */

/* ========================================================================== */