summaryrefslogtreecommitdiff
path: root/source/xps/xps-util.c
blob: 5d708eaaf7c9611c3b39ca51de83e157b37c2fe0 (plain)
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
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
#include "mupdf/xps.h"

static inline int xps_tolower(int c)
{
	if (c >= 'A' && c <= 'Z')
		return c + 32;
	return c;
}

int
xps_strcasecmp(char *a, char *b)
{
	while (xps_tolower(*a) == xps_tolower(*b))
	{
		if (*a++ == 0)
			return 0;
		b++;
	}
	return xps_tolower(*a) - xps_tolower(*b);
}

/* A URL is defined as consisting of a:
 * SCHEME (e.g. http:)
 * AUTHORITY (username, password, hostname, port, eg //test:passwd@mupdf.com:999)
 * PATH (e.g. /download)
 * QUERY (e.g. ?view=page)
 * FRAGMENT (e.g. #fred) (not strictly part of the URL)
 */
static char *
skip_scheme(char *path)
{
	char *p = path;

	/* Skip over: alpha *(alpha | digit | "+" | "-" | ".") looking for : */
	if (*p >= 'a' && *p <= 'z')
	{}
	else if (*p >= 'A' && *p <= 'Z')
	{}
	else
		return path;

	while (*++p)
	{
		if (*p >= 'a' && *p <= 'z')
		{}
		else if (*p >= 'A' && *p <= 'Z')
		{}
		else if (*p >= '0' && *p <= '9')
		{}
		else if (*p == '+')
		{}
		else if (*p == '-')
		{}
		else if (*p == '.')
		{}
		else if (*p == ':')
			return p+1;
		else
			break;
	}
	return path;
}

static char *
skip_authority(char *path)
{
	char *p = path;

	/* Authority section must start with '//' */
	if (p[0] != '/' || p[1] != '/')
		return path;
	p += 2;

	/* Authority is terminated by end of URL, '/' or '?' */
	while (*p && *p != '/' && *p != '?')
		p++;

	return p;
}

#define SEP(x) ((x)=='/' || (x) == 0)

static char *
clean_path(char *name)
{
	char *p, *q, *dotdot, *start;
	int rooted;

	start = skip_scheme(name);
	start = skip_authority(start);
	rooted = start[0] == '/';

	/*
	 * invariants:
	 *		p points at beginning of path element we're considering.
	 *		q points just past the last path element we wrote (no slash).
	 *		dotdot points just past the point where .. cannot backtrack
	 *				any further (no slash).
	 */
	p = q = dotdot = start + rooted;
	while (*p)
	{
		if(p[0] == '/') /* null element */
			p++;
		else if (p[0] == '.' && SEP(p[1]))
			p += 1; /* don't count the separator in case it is nul */
		else if (p[0] == '.' && p[1] == '.' && SEP(p[2]))
		{
			p += 2;
			if (q > dotdot) /* can backtrack */
			{
				while(--q > dotdot && *q != '/')
					;
			}
			else if (!rooted) /* /.. is / but ./../ is .. */
			{
				if (q != start)
					*q++ = '/';
				*q++ = '.';
				*q++ = '.';
				dotdot = q;
			}
		}
		else /* real path element */
		{
			if (q != start+rooted)
				*q++ = '/';
			while ((*q = *p) != '/' && *q != 0)
				p++, q++;
		}
	}

	if (q == start) /* empty string is really "." */
		*q++ = '.';
	*q = '\0';

	return name;
}

void
xps_resolve_url(fz_context *ctx, xps_document *doc, char *output, char *base_uri, char *path, int output_size)
{
	char *p = skip_authority(skip_scheme(path));

	if (p != path || path[0] == '/')
	{
		fz_strlcpy(output, path, output_size);
	}
	else
	{
		int len = fz_strlcpy(output, base_uri, output_size);
		if (len == 0 || output[len-1] != '/')
			fz_strlcat(output, "/", output_size);
		fz_strlcat(output, path, output_size);
	}
	clean_path(output);
}

int
xps_url_is_remote(fz_context *ctx, xps_document *doc, char *path)
{
	return path != skip_authority(skip_scheme(path));
}