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
|
-- URL parser tests
context("URL check functions", function()
local mpool = require("rspamd_mempool")
local url = require("rspamd_url")
local logger = require("rspamd_logger")
local ffi = require("ffi")
ffi.cdef[[
void rspamd_url_init (const char *tld_file);
unsigned ottery_rand_range(unsigned top);
void rspamd_http_normalize_path_inplace(char *path, size_t len, size_t *nlen);
]]
local test_dir = string.gsub(debug.getinfo(1).source, "^@(.+/)[^/]+$", "%1")
ffi.C.rspamd_url_init(string.format('%s/%s', test_dir, "test_tld.dat"))
test("Extract urls from text", function()
local pool = mpool.create()
local cases = {
{"test.com", {"test.com", nil}},
{" test.com", {"test.com", nil}},
{"<test.com> text", {"test.com", nil}},
{"test.com. text", {"test.com", nil}},
{"mailto:A.User@example.com text", {"example.com", "A.User"}},
{"http://Тест.Рф:18 text", {"тест.рф", nil}},
{"http://user:password@тест2.РФ:18 text", {"тест2.рф", "user"}},
{"somebody@example.com", {"example.com", "somebody"}},
{"https://127.0.0.1/abc text", {"127.0.0.1", nil}},
{"https://127.0.0.1 text", {"127.0.0.1", nil}},
{"https://[::1]:1", {"::1", nil}},
{"https://user:password@[::1]:1", {"::1", nil}},
{"https://user:password@[::1]", {"::1", nil}},
{"https://user:password@[::1]/1", {"::1", nil}},
}
for _,c in ipairs(cases) do
local res = url.create(pool, c[1])
assert_not_nil(res, "cannot parse " .. c[1])
local t = res:to_table()
--local s = logger.slog("%1 -> %2", c[1], t)
--print(s)
assert_not_nil(t, "cannot convert to table " .. c[1])
assert_equal(c[2][1], t['host'])
if c[2][2] then
assert_equal(c[2][2], t['user'])
end
end
pool:destroy()
end)
-- Some cases from https://code.google.com/p/google-url/source/browse/trunk/src/url_canon_unittest.cc
test("Parse urls", function()
local pool = mpool.create()
-- input, parseable, {host, port, user, password, path, query, part}
local cases = {
{"http://%30%78%63%30%2e%30%32%35%30.01", true, { --0xc0.0250.01
host = '192.168.0.1',
}},
{"http://www.google.com/foo?bar=baz#", true, {
host = 'www.google.com', path = 'foo', query = 'bar=baz', tld = 'google.com'
}},
{"http://[www.google.com]/", false},
{"<test.com", true, {
host = 'test.com', tld = 'test.com',
}},
{"test.com>", false},
{",test.com text", false},
{"ht\ttp:@www.google.com:80/;p?#", false},
{"http://user:pass@/", false},
{"http://foo:-80/", false},
{"http:////////user:@google.com:99?foo", true, {
host = 'google.com', user = 'user', port = 99, query = 'foo'
}},
{"http://%25DOMAIN:foobar@foodomain.com/", true, {
host = 'foodomain.com', user = '%25DOMAIN'
}},
{"http://0.0xFFFFFF", true, {
host = '0.255.255.255'
}},
{"http://030052000001", true, {
host = '192.168.0.1'
}},
{"http://0xc0.052000001", true, {
host = '192.168.0.1'
}},
{"http://192.168.0.1.", true, {
host = '192.168.0.1'
}},
{"http://[::eeee:192.168.0.1]", true, {
host = '::eeee:c0a8:1'
}},
{"http://twitter.com#test", true, {
host = 'twitter.com', fragment = 'test'
}},
}
for _,c in ipairs(cases) do
local res = url.create(pool, c[1])
if c[2] then
assert_not_nil(res, "cannot parse " .. c[1])
local uf = res:to_table()
for k,v in pairs(c[3]) do
assert_not_nil(uf[k], k .. ' is missing in url, must be ' .. v)
assert_equal(uf[k], v, 'expected ' .. v .. ' for ' .. k .. ' but got ' .. uf[k] .. ' in url ' .. c[1])
end
for k,v in pairs(uf) do
if k ~= 'url' and k ~= 'protocol' and k ~= 'tld' then
assert_not_nil(c[3][k], k .. ' should be absent but it is ' .. v .. ' in: ' .. c[1])
end
end
else
assert_nil(res, "should not parse " .. c[1] .. ' parsed to: ' .. tostring(res))
end
end
end
)
test("Normalize paths", function()
local cases = {
{"/././foo", "/foo"},
{"/a/b/c/./../../g", "/a/g"},
{"/./.foo", "/.foo"},
{"/foo/.", "/foo"},
{"/foo/./", "/foo"},
{"/foo/bar/..", "/foo"},
{"/foo/bar/../", "/foo/"},
{"/foo/..bar", "/foo/..bar"},
{"/foo/bar/../ton", "/foo/ton"},
{"/foo/bar/../ton/../../a", "/a"},
{"/foo/../../..", "/"},
{"/foo/../../../ton", "/ton"},
{"////../..", "/"},
}
for _,v in ipairs(cases) do
print(v[1])
local buf = ffi.new("uint8_t[?]", #v[1])
local sizbuf = ffi.new("size_t[1]")
ffi.copy(buf, v[1], #v[1])
ffi.C.rspamd_http_normalize_path_inplace(buf, #v[1], sizbuf)
local res = ffi.string(buf, tonumber(sizbuf[0]))
assert_equal(v[2], res, 'expected ' .. v[2] .. ' but got ' .. res .. ' in path ' .. v[1])
end
end)
end)
|
