1
/* -*- mode: c++; c-basic-offset: 2; indent-tabs-mode: nil; -*-
2
* vim:expandtab:shiftwidth=2:tabstop=2:smarttab:
4
* Copyright (C) 2008 Sun Microsystems
6
* This program is free software; you can redistribute it and/or modify
7
* it under the terms of the GNU General Public License as published by
8
* the Free Software Foundation; version 2 of the License.
10
* This program is distributed in the hope that it will be useful,
11
* but WITHOUT ANY WARRANTY; without even the implied warranty of
12
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
13
* GNU General Public License for more details.
15
* You should have received a copy of the GNU General Public License
16
* along with this program; if not, write to the Free Software
17
* Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
20
#ifndef DRIZZLED_LEX_INPUT_STREAM_H
21
#define DRIZZLED_LEX_INPUT_STREAM_H
24
@brief This class represents the character input stream consumed during
27
In addition to consuming the input stream, this class performs some
28
comment pre processing, by filtering out out of bound special text
29
from the query input stream.
30
Two buffers, with pointers inside each buffers, are maintained in
31
parallel. The 'raw' buffer is the original query text, which may
32
contain out-of-bound comments. The 'cpp' (for comments pre processor)
33
is the pre-processed buffer that contains only the query text that
34
should be seen once out-of-bound data is removed.
40
class Lex_input_stream
43
Lex_input_stream(Session *session, const char* buff, unsigned int length);
49
When echo is true, characters parsed from the raw input stream are
50
preserved. When false, characters parsed are silently ignored.
51
@param echo the echo mode.
53
void set_echo(bool echo)
59
Skip binary from the input stream.
60
@param n number of bytes to accept.
62
void skip_binary(int n)
66
memcpy(m_cpp_ptr, m_ptr, n);
73
Get a character, and advance in the stream.
74
@return the next character to parse.
85
Get the last character accepted.
86
@return the last character accepted.
94
Look at the next character to parse, but do not accept it.
102
Look ahead at some character to parse.
103
@param n offset of the character to look up
111
Cancel the effect of the last yyGet() or yySkip().
112
Note that the echo mode should not change between calls to yyGet / yySkip
113
and yyUnget. The caller is responsible for ensuring that.
123
Accept a character, by advancing the input stream.
128
*m_cpp_ptr++ = *m_ptr++;
134
Accept multiple characters at once.
135
@param n the number of characters to accept.
141
memcpy(m_cpp_ptr, m_ptr, n);
148
End of file indicator for the query text to parse.
149
@return true if there are no more characters to parse
153
return (m_ptr >= m_end_of_query);
157
End of file indicator for the query text to parse.
158
@param n number of characters expected
159
@return true if there are less than n characters to parse
163
return ((m_ptr + n) >= m_end_of_query);
166
/** Get the raw query buffer. */
167
const char *get_buf()
172
/** Get the pre-processed query buffer. */
173
const char *get_cpp_buf()
178
/** Get the end of the raw query buffer. */
179
const char *get_end_of_query()
181
return m_end_of_query;
184
/** Mark the stream position as the start of a new token. */
187
m_tok_start_prev= m_tok_start;
191
m_cpp_tok_start_prev= m_cpp_tok_start;
192
m_cpp_tok_start= m_cpp_ptr;
193
m_cpp_tok_end= m_cpp_ptr;
197
Adjust the starting position of the current token.
198
This is used to compensate for starting whitespace.
203
m_cpp_tok_start= m_cpp_ptr;
206
/** Get the token start position, in the raw buffer. */
207
const char *get_tok_start()
212
/** Get the token start position, in the pre-processed buffer. */
213
const char *get_cpp_tok_start()
215
return m_cpp_tok_start;
218
/** Get the token end position, in the raw buffer. */
219
const char *get_tok_end()
224
/** Get the token end position, in the pre-processed buffer. */
225
const char *get_cpp_tok_end()
227
return m_cpp_tok_end;
230
/** Get the previous token start position, in the raw buffer. */
231
const char *get_tok_start_prev()
233
return m_tok_start_prev;
236
/** Get the current stream pointer, in the raw buffer. */
237
const char *get_ptr()
242
/** Get the current stream pointer, in the pre-processed buffer. */
243
const char *get_cpp_ptr()
248
/** Get the length of the current token, in the raw buffer. */
252
The assumption is that the lexical analyser is always 1 character ahead,
253
which the -1 account for.
255
assert(m_ptr > m_tok_start);
256
return (uint32_t) ((m_ptr - m_tok_start) - 1);
259
/** Get the utf8-body string. */
260
const char *get_body_utf8_str()
265
/** Get the utf8-body length. */
266
uint32_t get_body_utf8_length()
268
return m_body_utf8_ptr - m_body_utf8;
271
void body_utf8_start(Session *session, const char *begin_ptr);
272
void body_utf8_append(const char *ptr);
273
void body_utf8_append(const char *ptr, const char *end_ptr);
274
void body_utf8_append_literal(const LEX_STRING *txt,
275
const char *end_ptr);
277
/** Current thread. */
280
/** Current line number. */
283
/** Length of the last token parsed. */
286
/** Interface with bison, value of the last token parsed. */
289
/** LALR(2) resolution, look ahead token.*/
292
/** LALR(2) resolution, value of the look ahead token.*/
293
LEX_YYSTYPE lookahead_yylval;
296
/** Pointer to the current position in the raw input stream. */
299
/** Starting position of the last token parsed, in the raw buffer. */
300
const char *m_tok_start;
302
/** Ending position of the previous token parsed, in the raw buffer. */
303
const char *m_tok_end;
305
/** End of the query text in the input stream, in the raw buffer. */
306
const char *m_end_of_query;
308
/** Starting position of the previous token parsed, in the raw buffer. */
309
const char *m_tok_start_prev;
311
/** Begining of the query text in the input stream, in the raw buffer. */
314
/** Length of the raw buffer. */
315
uint32_t m_buf_length;
317
/** Echo the parsed stream to the pre-processed buffer. */
320
/** Pre-processed buffer. */
323
/** Pointer to the current position in the pre-processed input stream. */
327
Starting position of the last token parsed,
328
in the pre-processed buffer.
330
const char *m_cpp_tok_start;
333
Starting position of the previous token parsed,
334
in the pre-procedded buffer.
336
const char *m_cpp_tok_start_prev;
339
Ending position of the previous token parsed,
340
in the pre-processed buffer.
342
const char *m_cpp_tok_end;
344
/** UTF8-body buffer created during parsing. */
347
/** Pointer to the current position in the UTF8-body buffer. */
348
char *m_body_utf8_ptr;
351
Position in the pre-processed buffer. The query from m_cpp_buf to
352
m_cpp_utf_processed_ptr is converted to UTF8-body.
354
const char *m_cpp_utf8_processed_ptr;
358
/** Current state of the lexical analyser. */
359
enum my_lex_states next_state;
361
/** Token character bitmaps, to detect 7bit strings. */
362
unsigned char tok_bitmap;
364
/** SQL_MODE = IGNORE_SPACE. */
367
/** State of the lexical analyser for comments. */
368
enum_comment_state in_comment;
371
Starting position of the TEXT_STRING or IDENT in the pre-processed
374
NOTE: this member must be used within DRIZZLElex() function only.
376
const char *m_cpp_text_start;
379
Ending position of the TEXT_STRING or IDENT in the pre-processed
382
NOTE: this member must be used within DRIZZLElex() function only.
384
const char *m_cpp_text_end;
388
} /* namespace drizzled */
390
#endif /* DRIZZLED_LEX_INPUT_STREAM_H */