-
Notifications
You must be signed in to change notification settings - Fork 11
/
patternmatcher.go
474 lines (417 loc) · 12.7 KB
/
patternmatcher.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
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
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
package patternmatcher
import (
"errors"
"os"
"path/filepath"
"regexp"
"strings"
"text/scanner"
"unicode/utf8"
)
// escapeBytes is a bitmap used to check whether a character should be escaped when creating the regex.
var escapeBytes [8]byte
// shouldEscape reports whether a rune should be escaped as part of the regex.
//
// This only includes characters that require escaping in regex but are also NOT valid filepath pattern characters.
// Additionally, '\' is not excluded because there is specific logic to properly handle this, as it's a path separator
// on Windows.
//
// Adapted from regexp::QuoteMeta in go stdlib.
// See https://cs.opensource.google/go/go/+/refs/tags/go1.17.2:src/regexp/regexp.go;l=703-715;drc=refs%2Ftags%2Fgo1.17.2
func shouldEscape(b rune) bool {
return b < utf8.RuneSelf && escapeBytes[b%8]&(1<<(b/8)) != 0
}
func init() {
for _, b := range []byte(`.+()|{}$`) {
escapeBytes[b%8] |= 1 << (b / 8)
}
}
// PatternMatcher allows checking paths against a list of patterns
type PatternMatcher struct {
patterns []*Pattern
exclusions bool
}
// New creates a new matcher object for specific patterns that can
// be used later to match against patterns against paths
func New(patterns []string) (*PatternMatcher, error) {
pm := &PatternMatcher{
patterns: make([]*Pattern, 0, len(patterns)),
}
for _, p := range patterns {
// Eliminate leading and trailing whitespace.
p = strings.TrimSpace(p)
if p == "" {
continue
}
p = filepath.Clean(p)
newp := &Pattern{}
if p[0] == '!' {
if len(p) == 1 {
return nil, errors.New("illegal exclusion pattern: \"!\"")
}
newp.exclusion = true
p = p[1:]
pm.exclusions = true
}
// Do some syntax checking on the pattern.
// filepath's Match() has some really weird rules that are inconsistent
// so instead of trying to dup their logic, just call Match() for its
// error state and if there is an error in the pattern return it.
// If this becomes an issue we can remove this since its really only
// needed in the error (syntax) case - which isn't really critical.
if _, err := filepath.Match(p, "."); err != nil {
return nil, err
}
newp.cleanedPattern = p
newp.dirs = strings.Split(p, string(os.PathSeparator))
pm.patterns = append(pm.patterns, newp)
}
return pm, nil
}
// Matches returns true if "file" matches any of the patterns
// and isn't excluded by any of the subsequent patterns.
//
// The "file" argument should be a slash-delimited path.
//
// Matches is not safe to call concurrently.
//
// Deprecated: This implementation is buggy (it only checks a single parent dir
// against the pattern) and will be removed soon. Use either
// MatchesOrParentMatches or MatchesUsingParentResults instead.
func (pm *PatternMatcher) Matches(file string) (bool, error) {
matched := false
file = filepath.FromSlash(file)
parentPath := filepath.Dir(file)
parentPathDirs := strings.Split(parentPath, string(os.PathSeparator))
for _, pattern := range pm.patterns {
// Skip evaluation if this is an inclusion and the filename
// already matched the pattern, or it's an exclusion and it has
// not matched the pattern yet.
if pattern.exclusion != matched {
continue
}
match, err := pattern.match(file)
if err != nil {
return false, err
}
if !match && parentPath != "." {
// Check to see if the pattern matches one of our parent dirs.
if len(pattern.dirs) <= len(parentPathDirs) {
match, _ = pattern.match(strings.Join(parentPathDirs[:len(pattern.dirs)], string(os.PathSeparator)))
}
}
if match {
matched = !pattern.exclusion
}
}
return matched, nil
}
// MatchesOrParentMatches returns true if "file" matches any of the patterns
// and isn't excluded by any of the subsequent patterns.
//
// The "file" argument should be a slash-delimited path.
//
// Matches is not safe to call concurrently.
func (pm *PatternMatcher) MatchesOrParentMatches(file string) (bool, error) {
matched := false
file = filepath.FromSlash(file)
parentPath := filepath.Dir(file)
parentPathDirs := strings.Split(parentPath, string(os.PathSeparator))
for _, pattern := range pm.patterns {
// Skip evaluation if this is an inclusion and the filename
// already matched the pattern, or it's an exclusion and it has
// not matched the pattern yet.
if pattern.exclusion != matched {
continue
}
match, err := pattern.match(file)
if err != nil {
return false, err
}
if !match && parentPath != "." {
// Check to see if the pattern matches one of our parent dirs.
for i := range parentPathDirs {
match, _ = pattern.match(strings.Join(parentPathDirs[:i+1], string(os.PathSeparator)))
if match {
break
}
}
}
if match {
matched = !pattern.exclusion
}
}
return matched, nil
}
// MatchesUsingParentResult returns true if "file" matches any of the patterns
// and isn't excluded by any of the subsequent patterns. The functionality is
// the same as Matches, but as an optimization, the caller keeps track of
// whether the parent directory matched.
//
// The "file" argument should be a slash-delimited path.
//
// MatchesUsingParentResult is not safe to call concurrently.
//
// Deprecated: this function does behave correctly in some cases (see
// https://github.com/docker/buildx/issues/850).
//
// Use MatchesUsingParentResults instead.
func (pm *PatternMatcher) MatchesUsingParentResult(file string, parentMatched bool) (bool, error) {
matched := parentMatched
file = filepath.FromSlash(file)
for _, pattern := range pm.patterns {
// Skip evaluation if this is an inclusion and the filename
// already matched the pattern, or it's an exclusion and it has
// not matched the pattern yet.
if pattern.exclusion != matched {
continue
}
match, err := pattern.match(file)
if err != nil {
return false, err
}
if match {
matched = !pattern.exclusion
}
}
return matched, nil
}
// MatchInfo tracks information about parent dir matches while traversing a
// filesystem.
type MatchInfo struct {
parentMatched []bool
}
// MatchesUsingParentResults returns true if "file" matches any of the patterns
// and isn't excluded by any of the subsequent patterns. The functionality is
// the same as Matches, but as an optimization, the caller passes in
// intermediate results from matching the parent directory.
//
// The "file" argument should be a slash-delimited path.
//
// MatchesUsingParentResults is not safe to call concurrently.
func (pm *PatternMatcher) MatchesUsingParentResults(file string, parentMatchInfo MatchInfo) (bool, MatchInfo, error) {
parentMatched := parentMatchInfo.parentMatched
if len(parentMatched) != 0 && len(parentMatched) != len(pm.patterns) {
return false, MatchInfo{}, errors.New("wrong number of values in parentMatched")
}
file = filepath.FromSlash(file)
matched := false
matchInfo := MatchInfo{
parentMatched: make([]bool, len(pm.patterns)),
}
for i, pattern := range pm.patterns {
match := false
// If the parent matched this pattern, we don't need to recheck.
if len(parentMatched) != 0 {
match = parentMatched[i]
}
if !match {
// Skip evaluation if this is an inclusion and the filename
// already matched the pattern, or it's an exclusion and it has
// not matched the pattern yet.
if pattern.exclusion != matched {
continue
}
var err error
match, err = pattern.match(file)
if err != nil {
return false, matchInfo, err
}
// If the zero value of MatchInfo was passed in, we don't have
// any information about the parent dir's match results, and we
// apply the same logic as MatchesOrParentMatches.
if !match && len(parentMatched) == 0 {
if parentPath := filepath.Dir(file); parentPath != "." {
parentPathDirs := strings.Split(parentPath, string(os.PathSeparator))
// Check to see if the pattern matches one of our parent dirs.
for i := range parentPathDirs {
match, _ = pattern.match(strings.Join(parentPathDirs[:i+1], string(os.PathSeparator)))
if match {
break
}
}
}
}
}
matchInfo.parentMatched[i] = match
if match {
matched = !pattern.exclusion
}
}
return matched, matchInfo, nil
}
// Exclusions returns true if any of the patterns define exclusions
func (pm *PatternMatcher) Exclusions() bool {
return pm.exclusions
}
// Patterns returns array of active patterns
func (pm *PatternMatcher) Patterns() []*Pattern {
return pm.patterns
}
// Pattern defines a single regexp used to filter file paths.
type Pattern struct {
matchType matchType
cleanedPattern string
dirs []string
regexp *regexp.Regexp
exclusion bool
}
type matchType int
const (
unknownMatch matchType = iota
exactMatch
prefixMatch
suffixMatch
regexpMatch
)
func (p *Pattern) String() string {
return p.cleanedPattern
}
// Exclusion returns true if this pattern defines exclusion
func (p *Pattern) Exclusion() bool {
return p.exclusion
}
func (p *Pattern) match(path string) (bool, error) {
if p.matchType == unknownMatch {
if err := p.compile(string(os.PathSeparator)); err != nil {
return false, filepath.ErrBadPattern
}
}
switch p.matchType {
case exactMatch:
return path == p.cleanedPattern, nil
case prefixMatch:
// strip trailing **
return strings.HasPrefix(path, p.cleanedPattern[:len(p.cleanedPattern)-2]), nil
case suffixMatch:
// strip leading **
suffix := p.cleanedPattern[2:]
if strings.HasSuffix(path, suffix) {
return true, nil
}
// **/foo matches "foo"
return suffix[0] == os.PathSeparator && path == suffix[1:], nil
case regexpMatch:
return p.regexp.MatchString(path), nil
}
return false, nil
}
func (p *Pattern) compile(sl string) error {
regStr := "^"
pattern := p.cleanedPattern
// Go through the pattern and convert it to a regexp.
// We use a scanner so we can support utf-8 chars.
var scan scanner.Scanner
scan.Init(strings.NewReader(pattern))
escSL := sl
if sl == `\` {
escSL += `\`
}
p.matchType = exactMatch
for i := 0; scan.Peek() != scanner.EOF; i++ {
ch := scan.Next()
if ch == '*' {
if scan.Peek() == '*' {
// is some flavor of "**"
scan.Next()
// Treat **/ as ** so eat the "/"
if string(scan.Peek()) == sl {
scan.Next()
}
if scan.Peek() == scanner.EOF {
// is "**EOF" - to align with .gitignore just accept all
if p.matchType == exactMatch {
p.matchType = prefixMatch
} else {
regStr += ".*"
p.matchType = regexpMatch
}
} else {
// is "**"
// Note that this allows for any # of /'s (even 0) because
// the .* will eat everything, even /'s
regStr += "(.*" + escSL + ")?"
p.matchType = regexpMatch
}
if i == 0 {
p.matchType = suffixMatch
}
} else {
// is "*" so map it to anything but "/"
regStr += "[^" + escSL + "]*"
p.matchType = regexpMatch
}
} else if ch == '?' {
// "?" is any char except "/"
regStr += "[^" + escSL + "]"
p.matchType = regexpMatch
} else if shouldEscape(ch) {
// Escape some regexp special chars that have no meaning
// in golang's filepath.Match
regStr += `\` + string(ch)
} else if ch == '\\' {
// escape next char. Note that a trailing \ in the pattern
// will be left alone (but need to escape it)
if sl == `\` {
// On windows map "\" to "\\", meaning an escaped backslash,
// and then just continue because filepath.Match on
// Windows doesn't allow escaping at all
regStr += escSL
continue
}
if scan.Peek() != scanner.EOF {
regStr += `\` + string(scan.Next())
p.matchType = regexpMatch
} else {
regStr += `\`
}
} else if ch == '[' || ch == ']' {
regStr += string(ch)
p.matchType = regexpMatch
} else {
regStr += string(ch)
}
}
if p.matchType != regexpMatch {
return nil
}
regStr += "$"
re, err := regexp.Compile(regStr)
if err != nil {
return err
}
p.regexp = re
p.matchType = regexpMatch
return nil
}
// Matches returns true if file matches any of the patterns
// and isn't excluded by any of the subsequent patterns.
//
// This implementation is buggy (it only checks a single parent dir against the
// pattern) and will be removed soon. Use MatchesOrParentMatches instead.
func Matches(file string, patterns []string) (bool, error) {
pm, err := New(patterns)
if err != nil {
return false, err
}
file = filepath.Clean(file)
if file == "." {
// Don't let them exclude everything, kind of silly.
return false, nil
}
return pm.Matches(file)
}
// MatchesOrParentMatches returns true if file matches any of the patterns
// and isn't excluded by any of the subsequent patterns.
func MatchesOrParentMatches(file string, patterns []string) (bool, error) {
pm, err := New(patterns)
if err != nil {
return false, err
}
file = filepath.Clean(file)
if file == "." {
// Don't let them exclude everything, kind of silly.
return false, nil
}
return pm.MatchesOrParentMatches(file)
}