Head

GCC Code Coverage Report

Directory:	./		Exec	Total	Coverage
File:	usr.bin/mandoc/preconv.c	Lines:	40	72	55.6 %
Date:	2017-11-07	Branches:	45	83	54.2 %


/*	$OpenBSD: preconv.c,v 1.8 2017/02/18 13:43:34 schwarze Exp $ */
/*
 * Copyright (c) 2011 Kristaps Dzonsons <kristaps@bsd.lv>
 * Copyright (c) 2014 Ingo Schwarze <schwarze@openbsd.org>
 *
 * Permission to use, copy, modify, and distribute this software for any
 * purpose with or without fee is hereby granted, provided that the above
 * copyright notice and this permission notice appear in all copies.
 *
 * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
 * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
 * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
 * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
 * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
 * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
 * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
 */
#include <sys/types.h>

#include <assert.h>
#include <stdio.h>
#include <string.h>
#include "mandoc.h"
#include "libmandoc.h"

int
preconv_encode(const struct buf *ib, size_t *ii, struct buf *ob, size_t *oi,
    int *filenc)
{
	const unsigned char	*cu;
	int			 nby;
	unsigned int		 accum;

	cu = (const unsigned char *)ib->buf + *ii;
	assert(*cu & 0x80);

	if ( ! (*filenc & MPARSE_UTF8))
		goto latin;

	nby = 1;
	while (nby < 5 && *cu & (1 << (7 - nby)))
		nby++;

	switch (nby) {
	case 2:
		accum = *cu & 0x1f;
		if (accum < 0x02)  /* Obfuscated ASCII. */
			goto latin;
		break;
	case 3:
		accum = *cu & 0x0f;
		break;
	case 4:
		accum = *cu & 0x07;
		if (accum > 0x04) /* Beyond Unicode. */
			goto latin;
		break;
	default:  /* Bad sequence header. */
		goto latin;
	}

	cu++;
	switch (nby) {
	case 3:
		if ((accum == 0x00 && ! (*cu & 0x20)) ||  /* Use 2-byte. */
		    (accum == 0x0d && *cu & 0x20))  /* Surrogates. */
			goto latin;
		break;
	case 4:
		if ((accum == 0x00 && ! (*cu & 0x30)) ||  /* Use 3-byte. */
		    (accum == 0x04 && *cu & 0x30))  /* Beyond Unicode. */
			goto latin;
		break;
	default:
		break;
	}

	while (--nby) {
		if ((*cu & 0xc0) != 0x80)  /* Invalid continuation. */
			goto latin;
		accum <<= 6;
		accum += *cu & 0x3f;
		cu++;
	}

	assert(accum > 0x7f);
	assert(accum < 0x110000);
	assert(accum < 0xd800 || accum > 0xdfff);

	*oi += snprintf(ob->buf + *oi, 11, "\\[u%.4X]", accum);
	*ii = (const char *)cu - ib->buf;
	*filenc &= ~MPARSE_LATIN1;
	return 1;

latin:
	if ( ! (*filenc & MPARSE_LATIN1))
		return 0;

	*oi += snprintf(ob->buf + *oi, 11,
	    "\\[u%.4X]", (unsigned char)ib->buf[(*ii)++]);

	*filenc &= ~MPARSE_UTF8;
	return 1;
}

int
preconv_cue(const struct buf *b, size_t offset)
{
	const char	*ln, *eoln, *eoph;
	size_t		 sz, phsz;

	ln = b->buf + offset;
	sz = b->sz - offset;

	/* Look for the end-of-line. */

	if (NULL == (eoln = memchr(ln, '\n', sz)))
		eoln = ln + sz;

	/* Check if we have the correct header/trailer. */

	if ((sz = (size_t)(eoln - ln)) < 10 ||
	    memcmp(ln, ".\\\" -*-", 7) || memcmp(eoln - 3, "-*-", 3))
		return MPARSE_UTF8 | MPARSE_LATIN1;

	/* Move after the header and adjust for the trailer. */

	ln += 7;
	sz -= 10;

	while (sz > 0) {
		while (sz > 0 && ' ' == *ln) {
			ln++;
			sz--;
		}
		if (0 == sz)
			break;

		/* Find the end-of-phrase marker (or eoln). */

		if (NULL == (eoph = memchr(ln, ';', sz)))
			eoph = eoln - 3;
		else
			eoph++;

		/* Only account for the "coding" phrase. */

		if ((phsz = eoph - ln) < 7 ||
		    strncasecmp(ln, "coding:", 7)) {
			sz -= phsz;
			ln += phsz;
			continue;
		}

		sz -= 7;
		ln += 7;

		while (sz > 0 && ' ' == *ln) {
			ln++;
			sz--;
		}
		if (0 == sz)
			return 0;

		/* Check us against known encodings. */

		if (phsz > 4 && !strncasecmp(ln, "utf-8", 5))
			return MPARSE_UTF8;
		if (phsz > 10 && !strncasecmp(ln, "iso-latin-1", 11))
			return MPARSE_LATIN1;
		return 0;
	}
	return MPARSE_UTF8 | MPARSE_LATIN1;
}


Generated by: GCOVR (Version 3.3)

Line	Branch	Exec	Source
1			/* $OpenBSD: preconv.c,v 1.8 2017/02/18 13:43:34 schwarze Exp $ */
2			/*
3			* Copyright (c) 2011 Kristaps Dzonsons <kristaps@bsd.lv>
4			* Copyright (c) 2014 Ingo Schwarze <schwarze@openbsd.org>
5			*
6			* Permission to use, copy, modify, and distribute this software for any
7			* purpose with or without fee is hereby granted, provided that the above
8			* copyright notice and this permission notice appear in all copies.
9			*
10			* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
11			* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
12			* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
13			* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
14			* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
15			* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
16			* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
17			*/
18			#include <sys/types.h>
19
20			#include <assert.h>
21			#include <stdio.h>
22			#include <string.h>
23			#include "mandoc.h"
24			#include "libmandoc.h"
25
26			int
27			preconv_encode(const struct buf ib, size_t ii, struct buf ob, size_t oi,
28			int *filenc)
29			{
30			const unsigned char *cu;
31			int nby;
32			unsigned int accum;
33
34		4806	cu = (const unsigned char )ib->buf + ii;
35	✗✓	2403	assert(*cu & 0x80);
36
37	✓✗	2403	if ( ! (*filenc & MPARSE_UTF8))
38			goto latin;
39
40			nby = 1;
41	✓✓✓✓	18981	while (nby < 5 && *cu & (1 << (7 - nby)))
42		2349	nby++;
43
44	✓✓✓✓	2538	switch (nby) {
45			case 2:
46		243	accum = *cu & 0x1f;
47	✓✓	243	if (accum < 0x02) /* Obfuscated ASCII. */
48			goto latin;
49			break;
50			case 3:
51		351	accum = *cu & 0x0f;
52		351	break;
53			case 4:
54		432	accum = *cu & 0x07;
55	✓✓	432	if (accum > 0x04) /* Beyond Unicode. */
56			goto latin;
57			break;
58			default: /* Bad sequence header. */
59			goto latin;
60			}
61
62		2295	cu++;
63	✓✓✓	2295	switch (nby) {
64			case 3:
65	✓✓✓✓ ✓✓	594	if ((accum == 0x00 && ! (cu & 0x20)) \|\| / Use 2-byte. */
66	✓✓	378	(accum == 0x0d && cu & 0x20)) / Surrogates. */
67			goto latin;
68			break;
69			case 4:
70	✓✓✓✓ ✓✓	702	if ((accum == 0x00 && ! (cu & 0x30)) \|\| / Use 3-byte. */
71	✓✓	324	(accum == 0x04 && cu & 0x30)) / Beyond Unicode. */
72			goto latin;
73			break;
74			default:
75			break;
76			}
77
78	✓✓	2592	while (--nby) {
79	✓✓	1080	if ((cu & 0xc0) != 0x80) / Invalid continuation. */
80			goto latin;
81		1026	accum <<= 6;
82		1026	accum += *cu & 0x3f;
83		1026	cu++;
84			}
85
86	✗✓	486	assert(accum > 0x7f);
87	✗✓	486	assert(accum < 0x110000);
88	✗✓	486	assert(accum < 0xd800 \|\| accum > 0xdfff);
89
90		486	oi += snprintf(ob->buf + oi, 11, "\\[u%.4X]", accum);
91		486	ii = (const char )cu - ib->buf;
92		486	*filenc &= ~MPARSE_LATIN1;
93		486	return 1;
94
95			latin:
96	✓✗	1917	if ( ! (*filenc & MPARSE_LATIN1))
97		1917	return 0;
98
99			oi += snprintf(ob->buf + oi, 11,
100			"\\[u%.4X]", (unsigned char)ib->buf[(*ii)++]);
101
102			*filenc &= ~MPARSE_UTF8;
103			return 1;
104		2403	}
105
106			int
107			preconv_cue(const struct buf *b, size_t offset)
108			{
109			const char ln, eoln, *eoph;
110			size_t sz, phsz;
111
112		50204	ln = b->buf + offset;
113		25102	sz = b->sz - offset;
114
115			/* Look for the end-of-line. */
116
117	✗✓	25102	if (NULL == (eoln = memchr(ln, '\n', sz)))
118			eoln = ln + sz;
119
120			/* Check if we have the correct header/trailer. */
121
122	✓✓✗✗	25102	if ((sz = (size_t)(eoln - ln)) < 10 \|\|
123	✗✓	23131	memcmp(ln, ".\\\" --", 7) \|\| memcmp(eoln - 3, "--", 3))
124		25102	return MPARSE_UTF8 \| MPARSE_LATIN1;
125
126			/* Move after the header and adjust for the trailer. */
127
128			ln += 7;
129			sz -= 10;
130
131			while (sz > 0) {
132			while (sz > 0 && ' ' == *ln) {
133			ln++;
134			sz--;
135			}
136			if (0 == sz)
137			break;
138
139			/* Find the end-of-phrase marker (or eoln). */
140
141			if (NULL == (eoph = memchr(ln, ';', sz)))
142			eoph = eoln - 3;
143			else
144			eoph++;
145
146			/* Only account for the "coding" phrase. */
147
148			if ((phsz = eoph - ln) < 7 \|\|
149			strncasecmp(ln, "coding:", 7)) {
150			sz -= phsz;
151			ln += phsz;
152			continue;
153			}
154
155			sz -= 7;
156			ln += 7;
157
158			while (sz > 0 && ' ' == *ln) {
159			ln++;
160			sz--;
161			}
162			if (0 == sz)
163			return 0;
164
165			/* Check us against known encodings. */
166
167			if (phsz > 4 && !strncasecmp(ln, "utf-8", 5))
168			return MPARSE_UTF8;
169			if (phsz > 10 && !strncasecmp(ln, "iso-latin-1", 11))
170			return MPARSE_LATIN1;
171			return 0;
172			}
173			return MPARSE_UTF8 \| MPARSE_LATIN1;
174		25102	}