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
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
|
context("Rspamd util for lua - check generic functions", function()
local util = require 'rspamd_util'
local cases = {
{
input = "test1",
result = false,
mixed_script = false,
range_start = 0x0000,
range_end = 0x017f
},
{
input = "test test xxx",
result = false,
mixed_script = false,
range_start = 0x0000,
range_end = 0x017f
},
{
input = "АбЫрвАлг",
result = true,
mixed_script = false,
range_start = 0x0000,
range_end = 0x017f
},
{
input = "АбЫрвАлг example",
result = true,
mixed_script = true,
range_start = 0x0000,
range_end = 0x017f
},
{
input = "example ąłśćżłóę",
result = false,
mixed_script = false,
range_start = 0x0000,
range_end = 0x017f
},
{
input = "ąłśćżłóę АбЫрвАлг",
result = true,
mixed_script = true,
range_start = 0x0000,
range_end = 0x017f
},
}
for i,c in ipairs(cases) do
test("is_utf_outside_range, test case #" .. i, function()
local actual = util.is_utf_outside_range(c.input, c.range_start, c.range_end)
assert_equal(c.result, actual)
end)
end
test("is_utf_outside_range, check cache", function ()
cache_size = 20
for i = 1,cache_size do
local res = util.is_utf_outside_range("a", 0x0000, 0x0000+i)
end
end)
test("is_utf_outside_range, check empty string", function ()
assert_error(util.is_utf_outside_range)
end)
test("get_string_stats, test case", function()
local res = util.get_string_stats("this is test 99")
assert_equal(res["letters"], 10)
assert_equal(res["digits"], 2)
end)
-- Tests for get_text_quality
test("get_text_quality, empty string", function()
local res = util.get_text_quality("")
assert_equal(res.total, 0)
assert_equal(res.letters, 0)
assert_equal(res.words, 0)
end)
test("get_text_quality, simple ASCII text", function()
local res = util.get_text_quality("Hello World")
assert_equal(res.total, 11)
assert_equal(res.letters, 10)
assert_equal(res.spaces, 1)
assert_equal(res.words, 2)
assert_equal(res.word_chars, 10)
assert_equal(res.uppercase, 2) -- H, W
assert_equal(res.lowercase, 8)
assert_equal(res.ascii_chars, 11)
assert_equal(res.non_ascii_chars, 0)
assert_equal(res.latin_vowels, 3) -- e, o, o
assert_equal(res.latin_consonants, 7) -- H, l, l, W, r, l, d
end)
test("get_text_quality, Russian (Cyrillic) text", function()
local res = util.get_text_quality("Привет мир")
assert_equal(res.letters, 9)
assert_equal(res.spaces, 1)
assert_equal(res.words, 2)
assert_equal(res.non_ascii_chars, 9) -- all Cyrillic letters
assert_equal(res.ascii_chars, 1) -- space
assert_equal(res.latin_vowels, 0)
assert_equal(res.latin_consonants, 0)
assert_equal(res.script_transitions, 0) -- all same script
end)
test("get_text_quality, mixed Latin and Cyrillic (script transitions)", function()
local res = util.get_text_quality("Hello Привет")
assert_equal(res.letters, 11)
assert_equal(res.words, 2)
assert_true(res.script_transitions > 0) -- at least one transition
assert_true(res.latin_vowels > 0)
assert_true(res.latin_consonants > 0)
end)
test("get_text_quality, digits only", function()
local res = util.get_text_quality("12345")
assert_equal(res.total, 5)
assert_equal(res.digits, 5)
assert_equal(res.letters, 0)
assert_equal(res.words, 0)
assert_equal(res.printable, 5)
end)
test("get_text_quality, punctuation", function()
local res = util.get_text_quality("Hello, World!")
assert_equal(res.punctuation, 2) -- comma and exclamation
assert_equal(res.words, 2)
end)
test("get_text_quality, double spaces", function()
local res = util.get_text_quality("Hello World Test")
assert_equal(res.double_spaces, 3) -- 2 in " " + 1 extra in " "
assert_equal(res.spaces, 5)
end)
test("get_text_quality, uppercase text", function()
local res = util.get_text_quality("HELLO WORLD")
assert_equal(res.uppercase, 10)
assert_equal(res.lowercase, 0)
end)
test("get_text_quality, lowercase text", function()
local res = util.get_text_quality("hello world")
assert_equal(res.uppercase, 0)
assert_equal(res.lowercase, 10)
end)
test("get_text_quality, single characters (no words)", function()
local res = util.get_text_quality("A B C D E")
assert_equal(res.letters, 5)
assert_equal(res.words, 0) -- single letters don't count as words
assert_equal(res.word_chars, 0)
end)
test("get_text_quality, vowels vs consonants", function()
local res = util.get_text_quality("aeiou")
assert_equal(res.latin_vowels, 5)
assert_equal(res.latin_consonants, 0)
res = util.get_text_quality("bcdfg")
assert_equal(res.latin_vowels, 0)
assert_equal(res.latin_consonants, 5)
end)
test("get_text_quality, emojis", function()
local res = util.get_text_quality("Hello 👋 World")
assert_equal(res.emojis, 1)
assert_equal(res.words, 2) -- Hello and World
end)
test("get_text_quality, mixed content", function()
local res = util.get_text_quality("Test123! Hello...")
assert_equal(res.letters, 9) -- Test + Hello
assert_equal(res.digits, 3)
assert_equal(res.punctuation, 4) -- ! and ...
assert_equal(res.words, 2) -- Test and Hello
end)
for i,c in ipairs(cases) do
test("is_utf_mixed_script, test case #" .. i, function()
local actual = util.is_utf_mixed_script(c.input)
assert_equal(c.mixed_script, actual)
end)
end
test("is_utf_mixed_script, invalid utf str should return errror", function()
assert_error(util.is_utf_mixed_script,'\200\213\202')
end)
test("is_utf_mixed_script, empty str should return errror", function()
assert_error(util.is_utf_mixed_script,'\200\213\202')
end)
end)
context("Rspamd string utility", function()
local ok, ffi = pcall(require, "ffi")
if not ok then
ffi = require("cffi")
end
ffi.cdef[[
char ** rspamd_string_len_split (const char *in, size_t len,
const char *spill, int max_elts, void *pool);
void g_strfreev (char **str_array);
]]
local NULL = ffi.new 'void*'
local cases = {
{'', ';,', {}},
{'', '', {}},
{'a', ';,', {'a'}},
{'a', '', {'a'}},
{'a;b', ';', {'a', 'b'}},
{'a;;b', ';', {'a', 'b'}},
{';a;;b;', ';', {'a', 'b'}},
{'ab', ';', {'ab'}},
{'a,;b', ',', {'a', ';b'}},
{'a,;b', ';,', {'a', 'b'}},
{',a,;b', ';,', {'a', 'b'}},
{',,;', ';,', {}},
{',,;a', ';,', {'a'}},
{'a,,;', ';,', {'a'}},
}
for i,case in ipairs(cases) do
test("rspamd_string_len_split: case " .. tostring(i), function()
local ret = ffi.C.rspamd_string_len_split(case[1], #case[1],
case[2], -1, NULL)
local actual = {}
while ret[#actual] ~= NULL do
actual[#actual + 1] = ffi.string(ret[#actual])
end
assert_rspamd_table_eq({
expect = case[3],
actual = actual
})
ffi.C.g_strfreev(ret)
end)
end
end)
|
