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
|
package shellquote
import (
"bytes"
"errors"
"strings"
"unicode/utf8"
)
var (
UnterminatedSingleQuoteError = errors.New("Unterminated single-quoted string")
UnterminatedDoubleQuoteError = errors.New("Unterminated double-quoted string")
UnterminatedEscapeError = errors.New("Unterminated backslash-escape")
)
var (
splitChars = " \n\t"
singleChar = '\''
doubleChar = '"'
escapeChar = '\\'
doubleEscapeChars = "$`\"\n\\"
)
// Split splits a string according to /bin/sh's word-splitting rules. It
// supports backslash-escapes, single-quotes, and double-quotes. Notably it does
// not support the $'' style of quoting. It also doesn't attempt to perform any
// other sort of expansion, including brace expansion, shell expansion, or
// pathname expansion.
//
// If the given input has an unterminated quoted string or ends in a
// backslash-escape, one of UnterminatedSingleQuoteError,
// UnterminatedDoubleQuoteError, or UnterminatedEscapeError is returned.
func Split(input string) (words []string, err error) {
var buf bytes.Buffer
words = make([]string, 0)
for len(input) > 0 {
// skip any splitChars at the start
c, l := utf8.DecodeRuneInString(input)
if strings.ContainsRune(splitChars, c) {
input = input[l:]
continue
} else if c == escapeChar {
// Look ahead for escaped newline so we can skip over it
next := input[l:]
if len(next) == 0 {
err = UnterminatedEscapeError
return
}
c2, l2 := utf8.DecodeRuneInString(next)
if c2 == '\n' {
input = next[l2:]
continue
}
}
var word string
word, input, err = splitWord(input, &buf)
if err != nil {
return
}
words = append(words, word)
}
return
}
func splitWord(input string, buf *bytes.Buffer) (word string, remainder string, err error) {
buf.Reset()
raw:
{
cur := input
for len(cur) > 0 {
c, l := utf8.DecodeRuneInString(cur)
cur = cur[l:]
if c == singleChar {
buf.WriteString(input[0 : len(input)-len(cur)-l])
input = cur
goto single
} else if c == doubleChar {
buf.WriteString(input[0 : len(input)-len(cur)-l])
input = cur
goto double
} else if c == escapeChar {
buf.WriteString(input[0 : len(input)-len(cur)-l])
input = cur
goto escape
} else if strings.ContainsRune(splitChars, c) {
buf.WriteString(input[0 : len(input)-len(cur)-l])
return buf.String(), cur, nil
}
}
if len(input) > 0 {
buf.WriteString(input)
input = ""
}
goto done
}
escape:
{
if len(input) == 0 {
return "", "", UnterminatedEscapeError
}
c, l := utf8.DecodeRuneInString(input)
if c == '\n' {
// a backslash-escaped newline is elided from the output entirely
} else {
buf.WriteString(input[:l])
}
input = input[l:]
}
goto raw
single:
{
i := strings.IndexRune(input, singleChar)
if i == -1 {
return "", "", UnterminatedSingleQuoteError
}
buf.WriteString(input[0:i])
input = input[i+1:]
goto raw
}
double:
{
cur := input
for len(cur) > 0 {
c, l := utf8.DecodeRuneInString(cur)
cur = cur[l:]
if c == doubleChar {
buf.WriteString(input[0 : len(input)-len(cur)-l])
input = cur
goto raw
} else if c == escapeChar {
// bash only supports certain escapes in double-quoted strings
c2, l2 := utf8.DecodeRuneInString(cur)
cur = cur[l2:]
if strings.ContainsRune(doubleEscapeChars, c2) {
buf.WriteString(input[0 : len(input)-len(cur)-l-l2])
if c2 == '\n' {
// newline is special, skip the backslash entirely
} else {
buf.WriteRune(c2)
}
input = cur
}
}
}
return "", "", UnterminatedDoubleQuoteError
}
done:
return buf.String(), input, nil
}
|
