File: scan.c

package info (click to toggle)
ftjam 2.5.2-1.1
  • links: PTS
  • area: main
  • in suites: bullseye, buster, jessie, jessie-kfreebsd, lenny, sid, squeeze, stretch, wheezy
  • size: 1,216 kB
  • ctags: 1,237
  • sloc: ansic: 7,226; sh: 2,751; yacc: 443; makefile: 121
file content (395 lines) | stat: -rwxr-xr-x 8,090 bytes parent folder | download | duplicates (2)
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
/*
 * Copyright 1993-2002 Christopher Seiwald and Perforce Software, Inc.
 *
 * This file is part of Jam - see jam.c for Copyright information.
 */

/*
 * scan.c - the jam yacc scanner
 *
 * 12/26/93 (seiwald) - bump buf in yylex to 10240 - yuk.
 * 09/16/94 (seiwald) - check for overflows, unmatched {}'s, etc.
 *			Also handle tokens abutting EOF by remembering
 *			to return EOF now matter how many times yylex()
 *			reinvokes yyline().
 * 02/11/95 (seiwald) - honor only punctuation keywords if SCAN_PUNCT.
 * 07/27/95 (seiwald) - Include jamgram.h after scan.h, so that YYSTYPE is
 *			defined before Linux's yacc tries to redefine it.
 * 01/10/01 (seiwald) - \ can now escape any whitespace char
 * 11/04/02 (seiwald) - const-ing for string literals
 */

# include "jam.h"
# include "lists.h"
# include "parse.h"
# include "scan.h"
# include "jamgram.h"
# include "jambase.h"
# include "newstr.h"

struct keyword {
	const char *word;
	int type;
} keywords[] = {
# include "jamgramtab.h"
	{ 0, 0 }
} ;

struct include {
	struct include *next;	/* next serial include file */
	const char 	*string;	/* pointer into current line */
	char	**strings;	/* for yyfparse() -- text to parse */
	FILE 	*file;		/* for yyfparse() -- file being read */
	const char 	*fname;		/* for yyfparse() -- file name */
	int 	line;		/* line counter for error messages */
	char 	buf[ 512 ];	/* for yyfparse() -- line buffer */
} ;

static struct include *incp = 0; /* current file; head of chain */

static int scanmode = SCAN_NORMAL;
static int anyerrors = 0;
static char *symdump( YYSTYPE *s );

# define BIGGEST_TOKEN 10240	/* no single token can be larger */

/* 
 * Set parser mode: normal, string, or keyword
 */

void
yymode( int n )
{
	scanmode = n;
}

void
yyerror( const char *s )
{
	if( incp )
	    printf( "%s: line %d: ", incp->fname, incp->line );

	printf( "%s at %s\n", s, symdump( &yylval ) );

	++anyerrors;
}

int
yyanyerrors()
{
	return anyerrors != 0;
}

void
yyfparse( const char *s )
{
	struct include *i = (struct include *)malloc( sizeof( *i ) );

	/* Push this onto the incp chain. */

	i->string = "";
	i->strings = 0;
	i->file = 0;
	i->fname = copystr( s );
	i->line = 0;
	i->next = incp;
	incp = i;

	/* If the filename is "+", it means use the internal jambase. */

	if( !strcmp( s, "+" ) )
	    i->strings = jambase;
}

/*
 * yyline() - read new line and return first character
 *
 * Fabricates a continuous stream of characters across include files,
 * returning EOF at the bitter end.
 */

int
yyline()
{
	struct include *i = incp;

	if( !incp )
	    return EOF;

	/* Once we start reading from the input stream, we reset the */
	/* include insertion point so that the next include file becomes */
	/* the head of the list. */

	/* If there is more data in this line, return it. */

	if( *i->string )
	    return *i->string++;

	/* If we're reading from an internal string list, go to the */
	/* next string. */

	if( i->strings )
	{
	    if( !*i->strings )
		goto next;

	    i->line++;
	    i->string = *(i->strings++);
	    return *i->string++;
	}

	/* If necessary, open the file */

	if( !i->file )
	{
	    FILE *f = stdin;

	    if( strcmp( i->fname, "-" ) && !( f = fopen( i->fname, "r" ) ) )
		perror( i->fname );

	    i->file = f;
	}

	/* If there's another line in this file, start it. */

	if( i->file && fgets( i->buf, sizeof( i->buf ), i->file ) )
	{
	    i->line++;
	    i->string = i->buf;
	    return *i->string++;
	}

    next:
	/* This include is done.  */
	/* Free it up and return EOF so yyparse() returns to parse_file(). */

	incp = i->next;

	/* Close file, free name */

	if( i->file && i->file != stdin )
	    fclose( i->file );
	freestr( i->fname );
	free( (char *)i );

	return EOF;
}

/*
 * yylex() - set yylval to current token; return its type
 *
 * Macros to move things along:
 *
 *	yychar() - return and advance character; invalid after EOF
 *	yyprev() - back up one character; invalid before yychar()
 *
 * yychar() returns a continuous stream of characters, until it hits
 * the EOF of the current include file.
 */

# define yychar() ( *incp->string ? *incp->string++ : yyline() )
# define yyprev() ( incp->string-- )

int
yylex()
{
	int c;
	char buf[BIGGEST_TOKEN];
	char *b = buf;

	if( !incp )
	    goto eof;

	/* Get first character (whitespace or of token) */

	c = yychar();

	if( scanmode == SCAN_STRING )
	{
	    /* If scanning for a string (action's {}'s), look for the */
	    /* closing brace.  We handle matching braces, if they match! */

	    int nest = 1;

	    while( c != EOF && b < buf + sizeof( buf ) )
	    {
		    if( c == '{' )
			nest++;

		    if( c == '}' && !--nest )
			break;

		    *b++ = c;

		    c = yychar();
	    }

	    /* We ate the ending brace -- regurgitate it. */

	    if( c != EOF )
		yyprev();

	    /* Check obvious errors. */

	    if( b == buf + sizeof( buf ) )
	    {
		yyerror( "action block too big" );
		goto eof;
	    }

	    if( nest )
	    {
		yyerror( "unmatched {} in action block" );
		goto eof;
	    }

	    *b = 0;
	    yylval.type = STRING;
	    yylval.string = newstr( buf );

	}
	else
	{
	    char *b = buf;
	    struct keyword *k;
	    int inquote = 0;
	    int notkeyword;
		
	    /* Eat white space */

	    for( ;; )
	    {
		/* Skip past white space */

		while( c != EOF && isspace( c ) )
			c = yychar();

		/* Not a comment?  Swallow up comment line. */

		if( c != '#' )
			break;
		while( ( c = yychar() ) != EOF && c != '\n' )
			;
	    }

	    /* c now points to the first character of a token. */

	    if( c == EOF )
		goto eof;

	    /* While scanning the word, disqualify it for (expensive) */
	    /* keyword lookup when we can: $anything, "anything", \anything */

	    notkeyword = c == '$';

	    /* look for white space to delimit word */
	    /* "'s get stripped but preserve white space */
	    /* \ protects next character */

	    while( 
		c != EOF &&
		b < buf + sizeof( buf ) &&
		( inquote || !isspace( c ) ) )
	    {
		if( c == '"' )
		{
		    /* begin or end " */
		    inquote = !inquote;
		    notkeyword = 1;
		}
		else if( c != '\\' )
		{
		    /* normal char */
		    *b++ = c;
		}
		else if( ( c = yychar()) != EOF )
		{
		    /* \c */
		    *b++ = c;
		    notkeyword = 1;
		}
		else
		{
		    /* \EOF */
		    break;
		}

		c = yychar();
	    }

	    /* Check obvious errors. */

	    if( b == buf + sizeof( buf ) )
	    {
		yyerror( "string too big" );
		goto eof;
	    }

	    if( inquote )
	    {
		yyerror( "unmatched \" in string" );
		goto eof;
	    }

	    /* We looked ahead a character - back up. */

	    if( c != EOF )
		yyprev();

	    /* scan token table */
	    /* don't scan if it's obviously not a keyword or if its */
	    /* an alphabetic when were looking for punctuation */

	    *b = 0;
	    yylval.type = ARG;

	    if( !notkeyword && !( isalpha( *buf ) && scanmode == SCAN_PUNCT ) )
	    {
		for( k = keywords; k->word; k++ )
		    if( *buf == *k->word && !strcmp( k->word, buf ) )
		{
		    yylval.type = k->type;
		    yylval.string = k->word;	/* used by symdump */
		    break;
		}
	    }

	    if( yylval.type == ARG )
		yylval.string = newstr( buf );
	}

	if( DEBUG_SCAN )
		printf( "scan %s\n", symdump( &yylval ) );

	return yylval.type;

eof:
	yylval.type = EOF;
	return yylval.type;
}

static char *
symdump( YYSTYPE *s )
{
	static char buf[ BIGGEST_TOKEN + 20 ];

	switch( s->type )
	{
	case EOF:
		sprintf( buf, "EOF" );
		break;
	case 0:
		sprintf( buf, "unknown symbol %s", s->string );
		break;
	case ARG:
		sprintf( buf, "argument %s", s->string );
		break;
	case STRING:
		sprintf( buf, "string \"%s\"", s->string );
		break;
	default:
		sprintf( buf, "keyword %s", s->string );
		break;
	}
	return buf;
}