]>
git.cameronkatri.com Git - mandoc.git/blob - preconv.c
1 /* $Id: preconv.c,v 1.12 2014/11/14 04:24:04 schwarze Exp $ */
3 * Copyright (c) 2011 Kristaps Dzonsons <kristaps@bsd.lv>
4 * Copyright (c) 2014 Ingo Schwarze <schwarze@openbsd.org>
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.
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.
20 #include <sys/types.h>
25 #include "libmandoc.h"
28 preconv_encode(struct buf
*ib
, size_t *ii
, struct buf
*ob
, size_t *oi
,
36 if ( ! (*filenc
& MPARSE_UTF8
))
42 for (i
= *ii
; i
< ib
->sz
; i
++) {
45 if ( ! (cu
& 128) || (cu
& 64)) {
46 /* Bad sequence header. */
50 /* Accept only legitimate bit patterns. */
52 if (cu
> 191 || cu
< 128) {
53 /* Bad in-sequence bits. */
57 accum
|= (cu
& 63) << --state
* 6;
63 ob
->buf
[(*oi
)++] = accum
;
65 *oi
+= snprintf(ob
->buf
+ *oi
,
66 11, "\\[u%.4X]", accum
);
68 *filenc
&= ~MPARSE_LATIN1
;
72 * Entering a UTF-8 state: if we encounter a
73 * UTF-8 bitmask, calculate the expected UTF-8
76 for (state
= 0; state
< 7; state
++)
77 if ( ! (cu
& (1 << (7 - state
))))
80 /* Accept only legitimate bit patterns. */
84 if (cu
<= 244 && cu
>= 240) {
85 accum
= (cu
& 7) << 18;
88 /* Bad 4-sequence start bits. */
91 if (cu
<= 239 && cu
>= 224) {
92 accum
= (cu
& 15) << 12;
95 /* Bad 3-sequence start bits. */
98 if (cu
<= 223 && cu
>= 194) {
99 accum
= (cu
& 31) << 6;
102 /* Bad 2-sequence start bits. */
105 /* Bad sequence bit mask. */
112 /* FALLTHROUGH: Invalid or incomplete UTF-8 sequence. */
115 if ( ! (*filenc
& MPARSE_LATIN1
))
118 *oi
+= snprintf(ob
->buf
+ *oi
, 11,
119 "\\[u%.4X]", (unsigned char)ib
->buf
[(*ii
)++]);
121 *filenc
&= ~MPARSE_UTF8
;
126 preconv_cue(const struct buf
*b
, size_t offset
)
128 const char *ln
, *eoln
, *eoph
;
131 ln
= b
->buf
+ offset
;
134 /* Look for the end-of-line. */
136 if (NULL
== (eoln
= memchr(ln
, '\n', sz
)))
139 /* Check if we have the correct header/trailer. */
141 if ((sz
= (size_t)(eoln
- ln
)) < 10 ||
142 memcmp(ln
, ".\\\" -*-", 7) || memcmp(eoln
- 3, "-*-", 3))
143 return(MPARSE_UTF8
| MPARSE_LATIN1
);
145 /* Move after the header and adjust for the trailer. */
151 while (sz
> 0 && ' ' == *ln
) {
158 /* Find the end-of-phrase marker (or eoln). */
160 if (NULL
== (eoph
= memchr(ln
, ';', sz
)))
165 /* Only account for the "coding" phrase. */
167 if ((phsz
= eoph
- ln
) < 7 ||
168 strncasecmp(ln
, "coding:", 7)) {
177 while (sz
> 0 && ' ' == *ln
) {
184 /* Check us against known encodings. */
186 if (phsz
> 4 && !strncasecmp(ln
, "utf-8", 5))
188 if (phsz
> 10 && !strncasecmp(ln
, "iso-latin-1", 11))
189 return(MPARSE_LATIN1
);
192 return(MPARSE_UTF8
| MPARSE_LATIN1
);