gonvert/gonvert.go at master · timakin/gonvert · GitHub

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
package gonvert

import (
	"github.com/k0kubun/pp"
	"github.com/saintfish/chardet"
	c "github.com/timakin/gonvert/converter"
)

type CharCode int

const (
	UTF8 CharCode = iota
	SJIS
	EUCJP
	GBK
	UTF16BE
	UTF16LE
)

var charcodes = map[string]CharCode{
	"UTF-8":     UTF8,
	"Shift_JIS": SJIS,
	"EUC-JP":    EUCJP,
	"GBK":       GBK,
	"UTF-16BE":  UTF16BE,
	"UTF-16LE":  UTF16LE,
}

type CodePair struct {
	From, To CharCode
}

func New(text string, codes ...CharCode) c.Converter {
	converter := createConverter(text, codes)

	return converter
}

func createConverter(text string, codes []CharCode) c.Converter {
	textByte := []byte(text)
	var fromCode, toCode CharCode

	if len(codes) == 1 {
		charDetector := chardet.NewTextDetector()
		detectResult, err := charDetector.DetectBest(textByte)
		if err != nil {
			pp.Fatal(err)
		}
		fromCode = charcodes[detectResult.Charset]
		toCode = codes[0]
	} else if len(codes) >= 2 {
		toCode = codes[0]
		fromCode = codes[1]
	} else {
		panic("Please specify 1 or 2 character-code arguements.")
	}

	var converter c.Converter
	codepair := CodePair{fromCode, toCode}

	switch codepair {
	case (CodePair{UTF8, SJIS}):
		{
			converter = &c.UTF8ToSJISConverter{TextByte: textByte}
		}
	case (CodePair{SJIS, UTF8}):
		{
			converter = &c.SJISToUTF8Converter{TextByte: textByte}
		}
	case (CodePair{UTF8, EUCJP}):
		{
			converter = &c.UTF8ToEUCJPConverter{TextByte: textByte}
		}
	case (CodePair{EUCJP, UTF8}):
		{
			converter = &c.EUCJPToUTF8Converter{TextByte: textByte}
		}
	case (CodePair{SJIS, EUCJP}):
		{
			converter = &c.SJISToEUCJPConverter{TextByte: textByte}
		}
	case (CodePair{EUCJP, SJIS}):
		{
			converter = &c.EUCJPToSJISConverter{TextByte: textByte}
		}
	case (CodePair{UTF8, GBK}):
		{
			converter = &c.UTF8ToGBKConverter{TextByte: textByte}
		}
	case (CodePair{GBK, UTF8}):
		{
			converter = &c.GBKToUTF8Converter{TextByte: textByte}
		}
	case (CodePair{GBK, SJIS}):
		{
			converter = &c.GBKToSJISConverter{TextByte: textByte}
		}
	case (CodePair{SJIS, GBK}):
		{
			converter = &c.SJISToGBKConverter{TextByte: textByte}
		}
	case (CodePair{GBK, EUCJP}):
		{
			converter = &c.GBKToEUCJPConverter{TextByte: textByte}
		}
	case (CodePair{EUCJP, GBK}):
		{
			converter = &c.EUCJPToGBKConverter{TextByte: textByte}
		}
	case (CodePair{UTF8, UTF16BE}):
		{
			converter = &c.UTF8ToUTF16BEConverter{TextByte: textByte}
		}
	case (CodePair{UTF16BE, UTF8}):
		{
			converter = &c.UTF16BEToUTF8Converter{TextByte: textByte}
		}
	case (CodePair{UTF8, UTF16LE}):
		{
			converter = &c.UTF8ToUTF16LEConverter{TextByte: textByte}
		}
	case (CodePair{UTF16LE, UTF8}):
		{
			converter = &c.UTF16LEToUTF8Converter{TextByte: textByte}
		}
	default:
		{
			converter = &c.DefaultConverter{TextByte: textByte}
		}
	}
	return converter
}