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
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
|
/* $OpenPackages$ */
/* $OpenBSD: lowparse.c,v 1.10 2001/05/29 12:17:05 espie Exp $ */
/* low-level parsing functions. */
/*
* Copyright (c) 1999,2000 Marc Espie.
*
* Extensive code changes for the OpenBSD project.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
*
* THIS SOFTWARE IS PROVIDED BY THE OPENBSD PROJECT AND CONTRIBUTORS
* ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE OPENBSD
* PROJECT OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
#include <assert.h>
#include <stddef.h>
#include <stdio.h>
#include <string.h>
#include <unistd.h>
#include "config.h"
#include "defines.h"
#include "buf.h"
#include "lowparse.h"
#include "error.h"
#include "lst.h"
#include "memory.h"
/* XXX check whether we can free filenames at the end, for a proper
* definition of `end'. */
#if 0
static LIST fileNames; /* file names to free at end */
#endif
/* Input stream structure, file or string. */
typedef struct {
const char *fname; /* Name of file */
unsigned long lineno; /* Line number */
FILE *F; /* Open stream, or NULL if pure string. */
char *str; /* Input string, if F == NULL. */
/* Line buffer. */
char *ptr; /* Where we are. */
char *end; /* Don't overdo it. */
} IFile;
static IFile *current; /* IFile being parsed. */
static LIST input_stack; /* Stack of IFiles waiting to be parsed
* (includes and loop reparses) */
/* IFile ctors.
*
* obj = new_ifile(filename, filehandle);
* Create input object from filename, filehandle. */
static IFile *new_ifile(const char *, FILE *);
/* obj = new_istring(str, filename, lineno);
* Create input object from str, filename, lineno. */
static IFile *new_istring(char *, const char *, unsigned long);
/* free_ifile(obj);
* Discard consumed input object, closing streams, freeing memory. */
static void free_ifile(IFile *);
/* Handling basic character reading.
* c = ParseReadc();
* New character c from current input stream, or EOF at end of stream. */
#define ParseReadc() current->ptr < current->end ? *current->ptr++ : newline()
/* len = newline();
* Guts for ParseReadc. Grabs a new line off fgetln when we have
* consumed the current line and returns its length. Or EOF at end of
* stream. */
static int newline(void);
/* c = skiptoendofline();
* Skips to the end of the current line, returns either '\n' or EOF. */
static int skiptoendofline(void);
/* Helper functions to handle basic parsing. */
/* ParseFoldLF(buffer, firstchar);
* Grabs logical line into buffer, the first character has already been
* read into firstchar. */
static void ParseFoldLF(Buffer, int);
/* firstchar = ParseSkipEmptyLines(buffer);
* Scans lines, skipping empty lines. May put some characters into
* buffer, returns the first character useful to continue parsing
* (e.g., not a backslash or a space. */
static int ParseSkipEmptyLines(Buffer);
static IFile *
new_ifile(name, stream)
const char *name;
FILE *stream;
{
IFile *ifile;
#if 0
Lst_AtEnd(&fileNames, name);
#endif
ifile = emalloc(sizeof(*ifile));
ifile->fname = name;
ifile->str = NULL;
/* Naturally enough, we start reading at line 0. */
ifile->lineno = 0;
ifile->F = stream;
ifile->ptr = ifile->end = NULL;
return ifile;
}
static void
free_ifile(ifile)
IFile *ifile;
{
if (ifile->F && fileno(ifile->F) != STDIN_FILENO)
(void)fclose(ifile->F);
free(ifile->str);
/* Note we can't free the file names yet, as they are embedded in GN for
* error reports. */
free(ifile);
}
static IFile *
new_istring(str, name, lineno)
char *str;
const char *name;
unsigned long lineno;
{
IFile *ifile;
ifile = emalloc(sizeof(*ifile));
/* No malloc, name is always taken from an already existing ifile */
ifile->fname = name;
ifile->F = NULL;
/* Strings are used in for loops, so we need to reset the line counter
* to an appropriate value. */
ifile->lineno = lineno;
ifile->ptr = ifile->str = str;
ifile->end = str + strlen(str);
return ifile;
}
void
Parse_FromString(str, lineno)
char *str;
unsigned long lineno;
{
if (DEBUG(FOR))
(void)fprintf(stderr, "%s\n----\n", str);
if (current != NULL)
Lst_Push(&input_stack, current);
current = new_istring(str, current->fname, lineno);
}
void
Parse_FromFile(name, stream)
const char *name;
FILE *stream;
{
if (current != NULL)
Lst_Push(&input_stack, current);
current = new_ifile(name, stream);
}
bool
Parse_NextFile()
{
if (current != NULL)
free_ifile(current);
current = (IFile *)Lst_Pop(&input_stack);
return current != NULL;
}
static int
newline()
{
size_t len;
if (current->F) {
current->ptr = fgetln(current->F, &len);
if (current->ptr) {
current->end = current->ptr + len;
return *current->ptr++;
} else {
current->end = NULL;
}
}
return EOF;
}
static int
skiptoendofline()
{
if (current->F) {
if (current->end - current->ptr > 1)
current->ptr = current->end - 1;
if (*current->ptr == '\n')
return *current->ptr++;
return EOF;
} else {
int c;
do {
c = ParseReadc();
} while (c != '\n' && c != EOF);
return c;
}
}
char *
Parse_ReadNextConditionalLine(linebuf)
Buffer linebuf;
{
int c;
/* If first char isn't dot, skip to end of line, handling \ */
while ((c = ParseReadc()) != '.') {
for (;c != '\n'; c = ParseReadc()) {
if (c == '\\') {
c = ParseReadc();
if (c == '\n')
current->lineno++;
}
if (c == EOF) {
Parse_Error(PARSE_FATAL, "Unclosed conditional");
return NULL;
}
}
current->lineno++;
}
/* This is the line we need to copy */
return Parse_ReadUnparsedLine(linebuf, "conditional");
}
static void
ParseFoldLF(linebuf, c)
Buffer linebuf;
int c;
{
for (;;) {
if (c == '\n') {
current->lineno++;
break;
}
if (c == EOF)
break;
Buf_AddChar(linebuf, c);
c = ParseReadc();
while (c == '\\') {
c = ParseReadc();
if (c == '\n') {
Buf_AddSpace(linebuf);
current->lineno++;
do {
c = ParseReadc();
} while (c == ' ' || c == '\t');
} else {
Buf_AddChar(linebuf, '\\');
if (c == '\\') {
Buf_AddChar(linebuf, '\\');
c = ParseReadc();
}
break;
}
}
}
}
char *
Parse_ReadUnparsedLine(linebuf, type)
Buffer linebuf;
const char *type;
{
int c;
Buf_Reset(linebuf);
c = ParseReadc();
if (c == EOF) {
Parse_Error(PARSE_FATAL, "Unclosed %s", type);
return NULL;
}
/* Handle '\' at beginning of line, since \\n needs special treatment */
while (c == '\\') {
c = ParseReadc();
if (c == '\n') {
current->lineno++;
do {
c = ParseReadc();
} while (c == ' ' || c == '\t');
} else {
Buf_AddChar(linebuf, '\\');
if (c == '\\') {
Buf_AddChar(linebuf, '\\');
c = ParseReadc();
}
break;
}
}
ParseFoldLF(linebuf, c);
return Buf_Retrieve(linebuf);
}
/* This is a fairly complex function, but without it, we could not skip
* blocks of comments without reading them. */
static int
ParseSkipEmptyLines(linebuf)
Buffer linebuf;
{
int c; /* the current character */
for (;;) {
Buf_Reset(linebuf);
c = ParseReadc();
/* Strip leading spaces, fold on '\n' */
if (c == ' ') {
do {
c = ParseReadc();
} while (c == ' ' || c == '\t');
while (c == '\\') {
c = ParseReadc();
if (c == '\n') {
current->lineno++;
do {
c = ParseReadc();
} while (c == ' ' || c == '\t');
} else {
Buf_AddChar(linebuf, '\\');
if (c == '\\') {
Buf_AddChar(linebuf, '\\');
c = ParseReadc();
}
if (c == EOF)
return '\n';
else
return c;
}
}
assert(c != '\t');
}
if (c == '#')
c = skiptoendofline();
/* Almost identical to spaces, except this occurs after comments
* have been taken care of, and we keep the tab itself. */
if (c == '\t') {
Buf_AddChar(linebuf, '\t');
do {
c = ParseReadc();
} while (c == ' ' || c == '\t');
while (c == '\\') {
c = ParseReadc();
if (c == '\n') {
current->lineno++;
do {
c = ParseReadc();
} while (c == ' ' || c == '\t');
} else {
Buf_AddChar(linebuf, '\\');
if (c == '\\') {
Buf_AddChar(linebuf, '\\');
c = ParseReadc();
}
if (c == EOF)
return '\n';
else
return c;
return c;
}
}
}
if (c == '\n')
current->lineno++;
else
return c;
}
}
/* Parse_ReadNormalLine removes beginning and trailing blanks (but keeps
* the first tab), handles escaped newlinews, and skip over uninteresting
* lines.
*
* The line number is advanced, which implies that continuation
* lines are numbered with the last line no (we could do better, at a
* price).
*
* Trivial comments are also removed, but we can't do more, as
* we don't know which lines are shell commands or not. */
char *
Parse_ReadNormalLine(linebuf)
Buffer linebuf;
{
int c; /* the current character */
c = ParseSkipEmptyLines(linebuf);
if (c == EOF)
return NULL;
else {
ParseFoldLF(linebuf, c);
Buf_KillTrailingSpaces(linebuf);
return Buf_Retrieve(linebuf);
}
}
unsigned long
Parse_Getlineno()
{
return current->lineno;
}
const char *
Parse_Getfilename()
{
return current->fname;
}
#ifdef CLEANUP
void
LowParse_Init()
{
Lst_Init(&input_stack);
current = NULL;
}
void
LowParse_End()
{
Lst_Destroy(&input_stack, NOFREE); /* Should be empty now */
#ifdef 0
Lst_Destroy(&fileNames, (SimpleProc)free);
#endif
}
#endif
void
Parse_ReportErrors()
{
if (fatal_errors) {
#ifdef CLEANUP
while (Parse_NextFile())
;
#endif
fprintf(stderr, "Fatal errors encountered -- cannot continue\n");
exit(1);
} else
assert(current == NULL);
}
|