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
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
|
// SPDX-License-Identifier: GPL-3.0-or-later
package matcher
import (
"errors"
"path/filepath"
"regexp"
"unicode/utf8"
)
// globMatcher implements Matcher, it uses filepath.MatchString to match.
type globMatcher string
var (
errBadGlobPattern = errors.New("bad glob pattern")
erGlobPattern = regexp.MustCompile(`(?s)^(?:[*?]|\[\^?([^\\-\]]|\\.|.-.)+\]|\\.|[^\*\?\\\[])*$`)
)
// NewGlobMatcher create a new matcher with glob format
func NewGlobMatcher(expr string) (Matcher, error) {
switch expr {
case "":
return stringFullMatcher(""), nil
case "*":
return TRUE(), nil
}
// any strings pass this regexp check are valid pattern
if !erGlobPattern.MatchString(expr) {
return nil, errBadGlobPattern
}
size := len(expr)
chars := []rune(expr)
startWith := true
endWith := true
startIdx := 0
endIdx := size - 1
if chars[startIdx] == '*' {
startWith = false
startIdx = 1
}
if chars[endIdx] == '*' {
endWith = false
endIdx--
}
unescapedExpr := make([]rune, 0, endIdx-startIdx+1)
for i := startIdx; i <= endIdx; i++ {
ch := chars[i]
if ch == '\\' {
nextCh := chars[i+1]
unescapedExpr = append(unescapedExpr, nextCh)
i++
} else if isGlobMeta(ch) {
return globMatcher(expr), nil
} else {
unescapedExpr = append(unescapedExpr, ch)
}
}
return NewStringMatcher(string(unescapedExpr), startWith, endWith)
}
func isGlobMeta(ch rune) bool {
switch ch {
case '*', '?', '[':
return true
default:
return false
}
}
// Match matches.
func (m globMatcher) Match(b []byte) bool {
return m.MatchString(string(b))
}
// MatchString matches.
func (m globMatcher) MatchString(line string) bool {
rs, _ := m.globMatch(line)
return rs
}
func (m globMatcher) globMatch(name string) (matched bool, err error) {
pattern := string(m)
Pattern:
for len(pattern) > 0 {
var star bool
var chunk string
star, chunk, pattern = scanChunk(pattern)
if star && chunk == "" {
// Trailing * matches rest of string unless it has a /.
// return !strings.Contains(name, string(Separator)), nil
return true, nil
}
// Look for match at current position.
t, ok, err := matchChunk(chunk, name)
// if we're the last chunk, make sure we've exhausted the name
// otherwise we'll give a false result even if we could still match
// using the star
if ok && (len(t) == 0 || len(pattern) > 0) {
name = t
continue
}
if err != nil {
return false, err
}
if star {
// Look for match skipping i+1 bytes.
// Cannot skip /.
for i := 0; i < len(name); i++ {
//for i := 0; i < len(name) && name[i] != Separator; i++ {
t, ok, err := matchChunk(chunk, name[i+1:])
if ok {
// if we're the last chunk, make sure we exhausted the name
if len(pattern) == 0 && len(t) > 0 {
continue
}
name = t
continue Pattern
}
if err != nil {
return false, err
}
}
}
return false, nil
}
return len(name) == 0, nil
}
// scanChunk gets the next segment of pattern, which is a non-star string
// possibly preceded by a star.
func scanChunk(pattern string) (star bool, chunk, rest string) {
for len(pattern) > 0 && pattern[0] == '*' {
pattern = pattern[1:]
star = true
}
inrange := false
var i int
Scan:
for i = 0; i < len(pattern); i++ {
switch pattern[i] {
case '\\':
if i+1 < len(pattern) {
i++
}
case '[':
inrange = true
case ']':
inrange = false
case '*':
if !inrange {
break Scan
}
}
}
return star, pattern[0:i], pattern[i:]
}
// matchChunk checks whether chunk matches the beginning of s.
// If so, it returns the remainder of s (after the match).
// Chunk is all single-character operators: literals, char classes, and ?.
func matchChunk(chunk, s string) (rest string, ok bool, err error) {
for len(chunk) > 0 {
if len(s) == 0 {
return
}
switch chunk[0] {
case '[':
// character class
r, n := utf8.DecodeRuneInString(s)
s = s[n:]
chunk = chunk[1:]
// We can't end right after '[', we're expecting at least
// a closing bracket and possibly a caret.
if len(chunk) == 0 {
err = filepath.ErrBadPattern
return
}
// possibly negated
negated := chunk[0] == '^'
if negated {
chunk = chunk[1:]
}
// parse all ranges
match := false
nrange := 0
for {
if len(chunk) > 0 && chunk[0] == ']' && nrange > 0 {
chunk = chunk[1:]
break
}
var lo, hi rune
if lo, chunk, err = getEsc(chunk); err != nil {
return
}
hi = lo
if chunk[0] == '-' {
if hi, chunk, err = getEsc(chunk[1:]); err != nil {
return
}
}
if lo <= r && r <= hi {
match = true
}
nrange++
}
if match == negated {
return
}
case '?':
//if s[0] == Separator {
// return
//}
_, n := utf8.DecodeRuneInString(s)
s = s[n:]
chunk = chunk[1:]
case '\\':
chunk = chunk[1:]
if len(chunk) == 0 {
err = filepath.ErrBadPattern
return
}
fallthrough
default:
if chunk[0] != s[0] {
return
}
s = s[1:]
chunk = chunk[1:]
}
}
return s, true, nil
}
// getEsc gets a possibly-escaped character from chunk, for a character class.
func getEsc(chunk string) (r rune, nchunk string, err error) {
if len(chunk) == 0 || chunk[0] == '-' || chunk[0] == ']' {
err = filepath.ErrBadPattern
return
}
if chunk[0] == '\\' {
chunk = chunk[1:]
if len(chunk) == 0 {
err = filepath.ErrBadPattern
return
}
}
r, n := utf8.DecodeRuneInString(chunk)
if r == utf8.RuneError && n == 1 {
err = filepath.ErrBadPattern
}
nchunk = chunk[n:]
if len(nchunk) == 0 {
err = filepath.ErrBadPattern
}
return
}
|
