1 |
|
|
/* |
2 |
|
|
* Copyright (C) 1984-2012 Mark Nudelman |
3 |
|
|
* Modified for use with illumos by Garrett D'Amore. |
4 |
|
|
* Copyright 2014 Garrett D'Amore <garrett@damore.org> |
5 |
|
|
* |
6 |
|
|
* You may distribute under the terms of either the GNU General Public |
7 |
|
|
* License or the Less License, as specified in the README file. |
8 |
|
|
* |
9 |
|
|
* For more information, see the README file. |
10 |
|
|
*/ |
11 |
|
|
|
12 |
|
|
/* |
13 |
|
|
* Routines to convert text in various ways. Used by search. |
14 |
|
|
*/ |
15 |
|
|
|
16 |
|
|
#include "charset.h" |
17 |
|
|
#include "less.h" |
18 |
|
|
|
19 |
|
|
extern int utf_mode; |
20 |
|
|
|
21 |
|
|
/* |
22 |
|
|
* Get the length of a buffer needed to convert a string. |
23 |
|
|
*/ |
24 |
|
|
int |
25 |
|
|
cvt_length(int len) |
26 |
|
|
{ |
27 |
✗✓ |
29152 |
if (utf_mode) |
28 |
|
|
/* |
29 |
|
|
* Just copying a string in UTF-8 mode can cause it to grow |
30 |
|
|
* in length. |
31 |
|
|
* Four output bytes for one input byte is the worst case. |
32 |
|
|
*/ |
33 |
|
|
len *= 4; |
34 |
|
14576 |
return (len + 1); |
35 |
|
|
} |
36 |
|
|
|
37 |
|
|
/* |
38 |
|
|
* Allocate a chpos array for use by cvt_text. |
39 |
|
|
*/ |
40 |
|
|
int * |
41 |
|
|
cvt_alloc_chpos(int len) |
42 |
|
|
{ |
43 |
|
|
int i; |
44 |
|
29152 |
int *chpos = ecalloc(sizeof (int), len); |
45 |
|
|
/* Initialize all entries to an invalid position. */ |
46 |
✓✓ |
1512084 |
for (i = 0; i < len; i++) |
47 |
|
741466 |
chpos[i] = -1; |
48 |
|
14576 |
return (chpos); |
49 |
|
|
} |
50 |
|
|
|
51 |
|
|
/* |
52 |
|
|
* Convert text. Perform the transformations specified by ops. |
53 |
|
|
* Returns converted text in odst. The original offset of each |
54 |
|
|
* odst character (when it was in osrc) is returned in the chpos array. |
55 |
|
|
*/ |
56 |
|
|
void |
57 |
|
|
cvt_text(char *odst, char *osrc, int *chpos, int *lenp, int ops) |
58 |
|
|
{ |
59 |
|
29152 |
char *dst; |
60 |
|
|
char *edst = odst; |
61 |
|
14576 |
char *src; |
62 |
|
|
char *src_end; |
63 |
|
|
LWCHAR ch; |
64 |
|
|
|
65 |
✓✗ |
14576 |
if (lenp != NULL) |
66 |
|
14576 |
src_end = osrc + *lenp; |
67 |
|
|
else |
68 |
|
|
src_end = osrc + strlen(osrc); |
69 |
|
|
|
70 |
✓✓ |
1482932 |
for (src = osrc, dst = odst; src < src_end; ) { |
71 |
|
726890 |
int src_pos = src - osrc; |
72 |
|
726890 |
int dst_pos = dst - odst; |
73 |
|
726890 |
ch = step_char(&src, +1, src_end); |
74 |
✓✓✓✗
|
726934 |
if ((ops & CVT_BS) && ch == '\b' && dst > odst) { |
75 |
|
|
/* Delete backspace and preceding char. */ |
76 |
|
|
do { |
77 |
|
44 |
dst--; |
78 |
✓✓✗✗
|
44 |
} while (dst > odst && |
79 |
✗✓✗✗
|
40 |
!IS_ASCII_OCTET(*dst) && !IS_UTF8_LEAD(*dst)); |
80 |
✗✓✗✗
|
726846 |
} else if ((ops & CVT_ANSI) && IS_CSI_START(ch)) { |
81 |
|
|
/* Skip to end of ANSI escape sequence. */ |
82 |
|
|
src++; /* skip the CSI start char */ |
83 |
|
|
while (src < src_end) |
84 |
|
|
if (!is_ansi_middle(*src++)) |
85 |
|
|
break; |
86 |
|
|
} else { |
87 |
|
|
/* Just copy the char to the destination buffer. */ |
88 |
✗✓✗✗
|
726846 |
if ((ops & CVT_TO_LC) && iswupper(ch)) |
89 |
|
|
ch = towlower(ch); |
90 |
|
726846 |
put_wchar(&dst, ch); |
91 |
|
|
/* Record the original position of the char. */ |
92 |
✓✗ |
726846 |
if (chpos != NULL) |
93 |
|
726846 |
chpos[dst_pos] = src_pos; |
94 |
|
|
} |
95 |
✓✓ |
726890 |
if (dst > edst) |
96 |
|
726802 |
edst = dst; |
97 |
|
|
} |
98 |
✓✗✓✓
✓✓ |
43011 |
if ((ops & CVT_CRLF) && edst > odst && edst[-1] == '\r') |
99 |
|
2 |
edst--; |
100 |
|
14576 |
*edst = '\0'; |
101 |
✓✗ |
14576 |
if (lenp != NULL) |
102 |
|
14576 |
*lenp = edst - odst; |
103 |
|
14576 |
} |