/
readutf16.go
211 lines (188 loc) · 4.92 KB
/
readutf16.go
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
package wp_spotlight
import (
"bufio"
"bytes"
"encoding/binary"
"os"
"runtime"
"unicode/utf16"
"unicode/utf8"
)
// ReadUTF16 required to correctly read the metadata JSON files
// via https://stackoverflow.com/questions/15783830/how-to-read-utf16-text-file-to-string-in-golang/15794113
func ReadUTF16(fileName string) ([]byte, error) {
file, err := os.Open(fileName)
if err != nil {
return nil, err
}
defer file.Close()
reader := bufio.NewReader(file)
scanner := bufio.NewScanner(reader)
//adjust the capacity to accommodate largest likely file
const maxCapacity = 256 * 1024
buf := make([]byte, maxCapacity)
scanner.Buffer(buf, maxCapacity)
var bo binary.ByteOrder // probably binary.LittleEndian but specifying value causes issues!
splitFunc, orderFunc := ScanUTF16LinesFunc(bo)
scanner.Split(splitFunc)
var rv []byte
for scanner.Scan() {
b := scanner.Bytes()
s := UTF16BytesToString(b, orderFunc())
rv = []byte(s)
}
err = scanner.Err()
return rv, err
}
// ScanUTF16LinesFunc returns two functions dependent upon byteOrder:
// SplitFunc is a split function for a Scanner that returns each line of
// text, stripped of any trailing end-of-line marker. The returned line may
// be empty. The end-of-line marker is one optional carriage return followed
// by one mandatory newline. In regular expression notation, it is `\r?\n`.
// The last non-empty line of input will be returned even if it has no
// newline.
// OrderFunc returns byte order
func ScanUTF16LinesFunc(byteOrder binary.ByteOrder) (bufio.SplitFunc, func() binary.ByteOrder) {
// Function closure variables
var endian = unknownEndian
switch byteOrder {
case binary.BigEndian:
endian = bigEndian
case binary.LittleEndian:
endian = littleEndian
}
const bom = 0xFEFF
var checkBOM bool = endian == unknownEndian
// Scanner split function
splitFunc := func(data []byte, atEOF bool) (advance int, token []byte, err error) {
if atEOF && len(data) == 0 {
return 0, nil, nil
}
if checkBOM {
checkBOM = false
if len(data) > 1 {
switch uint16(bom) {
case uint16(data[0])<<8 | uint16(data[1]):
endian = bigEndian
return 2, nil, nil
case uint16(data[1])<<8 | uint16(data[0]):
endian = littleEndian
return 2, nil, nil
}
}
}
// Scan for newline-terminated lines.
i := 0
for {
j := bytes.IndexByte(data[i:], '\n')
if j < 0 {
break
}
i += j
switch e := i % 2; e {
case 1: // UTF-16BE
if endian != littleEndian {
if i > 1 {
if data[i-1] == '\x00' {
endian = bigEndian
// We have a full newline-terminated line.
return i + 1, dropCRBE(data[0 : i-1]), nil
}
}
}
case 0: // UTF-16LE
if endian != bigEndian {
if i+1 < len(data) {
i++
if data[i] == '\x00' {
endian = littleEndian
// We have a full newline-terminated line.
return i + 1, dropCRLE(data[0 : i-1]), nil
}
}
}
}
i++
}
// If we're at EOF, we have a final, non-terminated line. Return it.
if atEOF {
// drop CR.
advance = len(data)
switch endian {
case bigEndian:
data = dropCRBE(data)
case littleEndian:
data = dropCRLE(data)
default:
data, endian = dropCR(data)
}
if endian == unknownEndian {
if runtime.GOOS == "windows" {
endian = littleEndian
} else {
endian = bigEndian
}
}
return advance, data, nil
}
// Request more data.
return 0, nil, nil
}
// Endian byte order function
orderFunc := func() (byteOrder binary.ByteOrder) {
switch endian {
case bigEndian:
byteOrder = binary.BigEndian
case littleEndian:
byteOrder = binary.LittleEndian
}
return byteOrder
}
return splitFunc, orderFunc
}
// UTF16BytesToString converts UTF-16 encoded bytes, in big or little endian byte order,
// to a UTF-8 encoded string.
func UTF16BytesToString(b []byte, o binary.ByteOrder) string {
utf := make([]uint16, (len(b)+(2-1))/2)
for i := 0; i+(2-1) < len(b); i += 2 {
utf[i/2] = o.Uint16(b[i:])
}
if len(b)/2 < len(utf) {
utf[len(utf)-1] = utf8.RuneError
}
return string(utf16.Decode(utf))
}
// UTF-16 endian byte order
const (
unknownEndian = iota
bigEndian
littleEndian
)
// dropCREndian drops a terminal \r from the endian data.
func dropCREndian(data []byte, t1, t2 byte) []byte {
if len(data) > 1 {
if data[len(data)-2] == t1 && data[len(data)-1] == t2 {
return data[0 : len(data)-2]
}
}
return data
}
// dropCRBE drops a terminal \r from the big endian data.
func dropCRBE(data []byte) []byte {
return dropCREndian(data, '\x00', '\r')
}
// dropCRLE drops a terminal \r from the little endian data.
func dropCRLE(data []byte) []byte {
return dropCREndian(data, '\r', '\x00')
}
// dropCR drops a terminal \r from the data.
func dropCR(data []byte) ([]byte, int) {
var endian = unknownEndian
switch ld := len(data); {
case ld != len(dropCRLE(data)):
endian = littleEndian
case ld != len(dropCRBE(data)):
endian = bigEndian
}
return data, endian
}