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
|
# Copyright © 2022, 飞麦 <fitmap@qq.com>, All rights reserved.
# frozen_string_literal: true
#
# 将字符串中的繁体字转换为对应的简体字
#
module Chinese
# 对字符串中的有序字符进行二分查找
#
# * +ele+ - 待查找的字符
#
def self.binary_search(ele)
low = 0
# 升序繁体字符串
@traditional ||= File.read('/N/chn/traditional.txt')
high = @traditional.length - 1
while low <= high
mid = (low + high) / 2
case @traditional[mid] <=> ele
when -1 then low = mid + 1
when +1 then high = mid - 1
else return mid
end
end
-1
end
# 将繁体字符串转变为简体字符串, 非繁体字符原样输出
# 特别注意: 由于存在一些多个繁体字对应单个简体字的情况, 反向的单字转换不准确
# 另外也存在少量多个简体字对应单个繁体字的情况, 正向的单字转换也不一定非常准确
#
# * +str_traditional+ - 繁体字符串(可含有简体字符)
# * return 简体字符串
#
def self.simplify(str_traditional)
buf_a = []
# 对应简体字符串
@simplified ||= File.read('/N/chn/simplified.txt')
str_traditional.each_char do |ch|
index = binary_search(ch)
buf_a << (index.negative? ? ch : @simplified[index])
end
buf_a.join
end
# 将繁体字符串转变为简体字符串, 非繁体字符原样输出
# 特别注意: 由于存在一些多个繁体字对应单个简体字的情况, 反向的单字转换不准确
# 另外也存在少量多个简体字对应单个繁体字的情况, 正向的单字转换也不一定非常准确
#
# * +str_traditional+ - 繁体字符串(可含有简体字符)
# * return 简体字符串
#
def self.simplify2(str_traditional)
buf = ''
# 对应简体字符串
@simplified ||= File.read('/N/chn/simplified.txt')
str_traditional.each_char do |ch|
index = binary_search(ch)
buf += (index.negative? ? ch : @simplified[index])
end
buf
end
# 检查繁体字是否按升序排列
def self.check
last = ''
okay = true
@traditional ||= File.read('/N/chn/traditional.txt')
@traditional.each_char do |ch|
if ch <= last
puts "Bad sequence on #{last} ~ #{ch}"
okay = false
end
last = ch
end
okay
end
end
if $PROGRAM_NAME == __FILE__
input_name = ARGV[0]
output_name = ARGV[1]
File.open(input_name, 'r') do |file_input|
File.open(output_name, 'wb') do |file_output|
file_input.each_line do |line|
file_output.print Chinese.simplify(line)
end
end
end
end
|
