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
|
#include <ctype.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/types.h>
#include <time.h>
#include <wchar.h>
#include "util.h"
/* print link; if link is relative use baseurl to make it absolute */
void
printlink(const char *link, const char *baseurl, FILE *fp)
{
const char *ebaseproto, *ebasedomain, *p;
int isrelative;
/* protocol part */
for(p = link; *p && (isalpha((int)*p) || isdigit((int)*p) ||
*p == '+' || *p == '-' || *p == '.'); p++);
/* relative link (baseurl is used). */
isrelative = strncmp(p, "://", strlen("://"));
if(isrelative) {
if((ebaseproto = strstr(baseurl, "://"))) {
ebaseproto += strlen("://");
fwrite(baseurl, 1, ebaseproto - baseurl, fp);
} else {
ebaseproto = baseurl;
if(*baseurl || (link[0] == '/' && link[1] == '/'))
fputs("http://", fp);
}
if(link[0] == '/') { /* relative to baseurl domain (not path). */
if(link[1] == '/') /* absolute url but with protocol from baseurl. */
link += 2;
else if((ebasedomain = strchr(ebaseproto, '/')))
/* relative to baseurl and baseurl path. */
fwrite(ebaseproto, 1, ebasedomain - ebaseproto, fp);
else
fputs(ebaseproto, stdout);
} else if((ebasedomain = strrchr(ebaseproto, '/'))) {
/* relative to baseurl and baseurl path. */
fwrite(ebaseproto, 1, ebasedomain - ebaseproto + 1, fp);
} else {
fputs(ebaseproto, fp);
if(*baseurl && *link)
fputc('/', fp);
}
}
fputs(link, fp);
}
/* read a field-separated line from 'fp',
* separated by a character 'separator',
* 'fields' is a list of pointer with a maximum size of 'maxfields'.
* 'line' buffer is allocated using malloc, 'size' will contain the
* allocated buffer size.
* returns: amount of fields read. */
unsigned int
parseline(char **line, size_t *size, char **fields,
unsigned int maxfields, int separator, FILE *fp)
{
unsigned int i = 0;
char *prev, *s;
if(getline(line, size, fp) > 0) {
for(prev = *line; (s = strchr(prev, separator)) && i <= maxfields; i++) {
*s = '\0';
fields[i] = prev;
prev = s + 1;
}
fields[i] = prev;
/* make non-parsed fields empty. */
for(i++; i < maxfields; i++)
fields[i] = "";
}
return i;
}
const char *
trimend(const char *s)
{
size_t len = strlen(s);
for(; len > 0 && isspace((int)s[len - 1]); len--)
;
return &s[len];
}
const char *
trimstart(const char *s)
{
for(; *s && isspace((int)*s); s++)
;
return s;
}
/* print feed name for id; spaces and tabs in string as "-"
* (spaces in anchors are not valid). */
void
printfeednameid(const char *s, FILE *fp)
{
const char *e;
s = trimstart(s);
e = trimend(s);
for(; *s && s != e; s++)
fputc(isspace((int)*s) ? '-' : tolower((int)*s), fp);
}
void
printhtmlencoded(const char *s, FILE *fp) {
for(; *s; s++) {
switch(*s) {
case '<': fputs("<", fp); break;
case '>': fputs(">", fp); break;
/* case '&': fputs("&", fp); break;*/
default:
fputc(*s, fp);
}
}
}
void
printutf8pad(FILE *fp, const char *s, size_t len, int pad)
{
wchar_t w;
size_t n = 0, i;
int r;
for(i = 0; *s && n < len; i++, s++) {
if(ISUTF8(*s)) {
if((r = mbtowc(&w, s, 4)) == -1)
break;
if((r = wcwidth(w)) == -1)
r = 1;
n += (size_t)r;
}
putc(*s, fp);
}
for(; n < len; n++)
putc(pad, fp);
}
|
