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
|
#! /usr/bin/env ruby
$LOAD_PATH.unshift("..")
require 'test/unit'
require 'gonzui'
require 'test-util'
include Gonzui
class TextTokenizerTest < Test::Unit::TestCase
include TestUtil
def _test_collect(text)
list = []
TextTokenizer.each_word(text) {|word, pos|
assert(word.is_a?(String))
assert(pos.is_a?(Integer))
list.push([word, pos])
}
return list
end
def _test_with_words(words, delim)
text = words.join(delim)
list = _test_collect(text)
pos = 0
words.each_with_index {|word, i|
assert_equal(word, list[i][0])
assert_equal(pos, list[i][1])
pos += word.length + delim.length
}
end
def _test_text(text, n)
list = _test_collect(text)
assert_equal(n, list.length)
end
def test_each
words = ["foo", "bar", "baz"]
_test_with_words(words, " ")
_test_with_words(words, "\n")
_test_with_words(words, ", ")
_test_with_words(words, ",\n")
_test_with_words(words, "!#%&\n\n\n@@")
_test_text("foo_bar", 1)
_test_text("あ", 1) # single multi-byte character
_test_text("あい", 2) # two multi-byte characters
end
end
|
