summaryrefslogtreecommitdiff
path: root/pkg/storage/image_regexp.go
blob: 96de64884e3d4ee0236783bdc4a32c12bdce2f92 (plain)
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
package storage

// This is a fork of docker/distribution code to be used when manipulating image
// references.
// DO NOT EDIT THIS FILE.

import "regexp"

var (
	// alphaNumericRegexp defines the alpha numeric atom, typically a
	// component of names. This only allows lower case characters and digits.
	alphaNumericRegexp = match(`[a-z0-9]+`)

	// separatorRegexp defines the separators allowed to be embedded in name
	// components. This allow one period, one or two underscore and multiple
	// dashes.
	separatorRegexp = match(`(?:[._]|__|[-]*)`)

	// nameComponentRegexp restricts registry path component names to start
	// with at least one letter or number, with following parts able to be
	// separated by one period, one or two underscore and multiple dashes.
	nameComponentRegexp = expression(
		alphaNumericRegexp,
		optional(repeated(separatorRegexp, alphaNumericRegexp)))

	// domainComponentRegexp restricts the registry domain component of a
	// repository name to start with a component as defined by domainRegexp
	// and followed by an optional port.
	domainComponentRegexp = match(`(?:[a-zA-Z0-9]|[a-zA-Z0-9][a-zA-Z0-9-]*[a-zA-Z0-9])`)

	// domainRegexp defines the structure of potential domain components
	// that may be part of image names. This is purposely a subset of what is
	// allowed by DNS to ensure backwards compatibility with Docker image
	// names.
	domainRegexp = expression(
		domainComponentRegexp,
		optional(repeated(literal(`.`), domainComponentRegexp)),
		optional(literal(`:`), match(`[0-9]+`)))

	// NameRegexp is the format for the name component of references. The
	// regexp has capturing groups for the domain and name part omitting
	// the separating forward slash from either.
	NameRegexp = expression(
		optional(domainRegexp, literal(`/`)),
		nameComponentRegexp,
		optional(repeated(literal(`/`), nameComponentRegexp)))

	// anchoredNameRegexp is used to parse a name value, capturing the
	// domain and trailing components.
	anchoredNameRegexp = anchored(
		optional(capture(domainRegexp), literal(`/`)),
		capture(nameComponentRegexp,
			optional(repeated(literal(`/`), nameComponentRegexp))))

	// IdentifierRegexp is the format for string identifier used as a
	// content addressable identifier using sha256. These identifiers
	// are like digests without the algorithm, since sha256 is used.
	IdentifierRegexp = match(`([a-f0-9]{64})`)

	// ShortIdentifierRegexp is the format used to represent a prefix
	// of an identifier. A prefix may be used to match a sha256 identifier
	// within a list of trusted identifiers.
	ShortIdentifierRegexp = match(`([a-f0-9]{6,64})`)
)

// match compiles the string to a regular expression.
var match = regexp.MustCompile

// literal compiles s into a literal regular expression, escaping any regexp
// reserved characters.
func literal(s string) *regexp.Regexp {
	re := match(regexp.QuoteMeta(s))

	if _, complete := re.LiteralPrefix(); !complete {
		panic("must be a literal")
	}

	return re
}

func splitDomain(name string) (string, string) {
	match := anchoredNameRegexp.FindStringSubmatch(name)
	if len(match) != 3 {
		return "", name
	}
	return match[1], match[2]
}

// expression defines a full expression, where each regular expression must
// follow the previous.
func expression(res ...*regexp.Regexp) *regexp.Regexp {
	var s string
	for _, re := range res {
		s += re.String()
	}

	return match(s)
}

// optional wraps the expression in a non-capturing group and makes the
// production optional.
func optional(res ...*regexp.Regexp) *regexp.Regexp {
	return match(group(expression(res...)).String() + `?`)
}

// repeated wraps the regexp in a non-capturing group to get one or more
// matches.
func repeated(res ...*regexp.Regexp) *regexp.Regexp {
	return match(group(expression(res...)).String() + `+`)
}

// group wraps the regexp in a non-capturing group.
func group(res ...*regexp.Regexp) *regexp.Regexp {
	return match(`(?:` + expression(res...).String() + `)`)
}

// capture wraps the expression in a capturing group.
func capture(res ...*regexp.Regexp) *regexp.Regexp {
	return match(`(` + expression(res...).String() + `)`)
}

// anchored anchors the regular expression by adding start and end delimiters.
func anchored(res ...*regexp.Regexp) *regexp.Regexp {
	return match(`^` + expression(res...).String() + `$`)
}