line_reader.c revision 349524 
1/*-
2 * Copyright (c) 2008 Tim Kientzle
3 * Copyright (c) 2010 Joerg Sonnenberger
4 * All rights reserved.
5 *
6 * Redistribution and use in source and binary forms, with or without
7 * modification, are permitted provided that the following conditions
8 * are met:
9 * 1. Redistributions of source code must retain the above copyright
10 *    notice, this list of conditions and the following disclaimer
11 *    in this position and unchanged.
12 * 2. Redistributions in binary form must reproduce the above copyright
13 *    notice, this list of conditions and the following disclaimer in the
14 *    documentation and/or other materials provided with the distribution.
15 *
16 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR(S) ``AS IS'' AND ANY EXPRESS OR
17 * IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
18 * OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
19 * IN NO EVENT SHALL THE AUTHOR(S) BE LIABLE FOR ANY DIRECT, INDIRECT,
20 * INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
21 * NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
22 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
23 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
25 * THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26 */
27
28#include "lafe_platform.h"
29__FBSDID("$FreeBSD: stable/11/contrib/libarchive/libarchive_fe/line_reader.c 349524 2019-06-28 22:33:44Z mm $");
30
31#include <errno.h>
32#include <stdio.h>
33#include <stdlib.h>
34#include <string.h>
35
36#include "err.h"
37#include "line_reader.h"
38
39#if defined(_WIN32) && !defined(__CYGWIN__) && !defined(__BORLANDC__)
40#define strdup _strdup
41#endif
42
43/*
44 * Read lines from file and do something with each one.  If option_null
45 * is set, lines are terminated with zero bytes; otherwise, they're
46 * terminated with newlines.
47 *
48 * This uses a self-sizing buffer to handle arbitrarily-long lines.
49 */
50struct lafe_line_reader {
51	FILE *f;
52	char *buff, *buff_end, *line_start, *line_end;
53	char *pathname;
54	size_t buff_length;
55	int nullSeparator; /* Lines separated by null, not CR/CRLF/etc. */
56};
57
58struct lafe_line_reader *
59lafe_line_reader(const char *pathname, int nullSeparator)
60{
61	struct lafe_line_reader *lr;
62
63	lr = calloc(1, sizeof(*lr));
64	if (lr == NULL)
65		lafe_errc(1, ENOMEM, "Can't open %s", pathname);
66
67	lr->nullSeparator = nullSeparator;
68	lr->pathname = strdup(pathname);
69
70	if (strcmp(pathname, "-") == 0)
71		lr->f = stdin;
72	else
73		lr->f = fopen(pathname, "r");
74	if (lr->f == NULL)
75		lafe_errc(1, errno, "Couldn't open %s", pathname);
76	lr->buff_length = 8192;
77	lr->line_start = lr->line_end = lr->buff_end = lr->buff = NULL;
78
79	return (lr);
80}
81
82static void
83lafe_line_reader_find_eol(struct lafe_line_reader *lr)
84{
85
86	lr->line_end += strcspn(lr->line_end,
87	    lr->nullSeparator ? "" : "\x0d\x0a");
88	*lr->line_end = '\0'; /* Noop if line_end == buff_end */
89}
90
91const char *
92lafe_line_reader_next(struct lafe_line_reader *lr)
93{
94	size_t bytes_wanted, bytes_read, new_buff_size;
95	char *line_start, *p;
96
97	for (;;) {
98		/* If there's a line in the buffer, return it immediately. */
99		while (lr->line_end < lr->buff_end) {
100			line_start = lr->line_start;
101			lr->line_start = ++lr->line_end;
102			lafe_line_reader_find_eol(lr);
103
104			if (lr->nullSeparator || line_start[0] != '\0')
105				return (line_start);
106		}
107
108		/* If we're at end-of-file, process the final data. */
109		if (lr->f == NULL) {
110			if (lr->line_start == lr->buff_end)
111				return (NULL); /* No more text */
112			line_start = lr->line_start;
113			lr->line_start = lr->buff_end;
114			return (line_start);
115		}
116
117		/* Buffer only has part of a line. */
118		if (lr->line_start > lr->buff) {
119			/* Move a leftover fractional line to the beginning. */
120			memmove(lr->buff, lr->line_start,
121			    lr->buff_end - lr->line_start);
122			lr->buff_end -= lr->line_start - lr->buff;
123			lr->line_end -= lr->line_start - lr->buff;
124			lr->line_start = lr->buff;
125		} else {
126			/* Line is too big; enlarge the buffer. */
127			new_buff_size = lr->buff_length * 2;
128			if (new_buff_size <= lr->buff_length)
129				lafe_errc(1, ENOMEM,
130				    "Line too long in %s", lr->pathname);
131			lr->buff_length = new_buff_size;
132			/*
133			 * Allocate one extra byte to allow terminating
134			 * the buffer.
135			 */
136			p = realloc(lr->buff, new_buff_size + 1);
137			if (p == NULL)
138				lafe_errc(1, ENOMEM,
139				    "Line too long in %s", lr->pathname);
140			lr->buff_end = p + (lr->buff_end - lr->buff);
141			lr->line_end = p + (lr->line_end - lr->buff);
142			lr->line_start = lr->buff = p;
143		}
144
145		/* Get some more data into the buffer. */
146		bytes_wanted = lr->buff + lr->buff_length - lr->buff_end;
147		bytes_read = fread(lr->buff_end, 1, bytes_wanted, lr->f);
148		lr->buff_end += bytes_read;
149		*lr->buff_end = '\0'; /* Always terminate buffer */
150		lafe_line_reader_find_eol(lr);
151
152		if (ferror(lr->f))
153			lafe_errc(1, errno, "Can't read %s", lr->pathname);
154		if (feof(lr->f)) {
155			if (lr->f != stdin)
156				fclose(lr->f);
157			lr->f = NULL;
158		}
159	}
160}
161
162void
163lafe_line_reader_free(struct lafe_line_reader *lr)
164{
165	free(lr->buff);
166	free(lr->pathname);
167	free(lr);
168}
169