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
|
// GoToSocial
// Copyright (C) GoToSocial Authors admin@gotosocial.org
// SPDX-License-Identifier: AGPL-3.0-or-later
//
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU Affero General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU Affero General Public License for more details.
//
// You should have received a copy of the GNU Affero General Public License
// along with this program. If not, see <http://www.gnu.org/licenses/>.
package regexes
import (
"bytes"
"regexp"
"sync"
"mvdan.cc/xurls/v2"
)
const (
users = "users"
actors = "actors"
statuses = "statuses"
inbox = "inbox"
outbox = "outbox"
followers = "followers"
following = "following"
liked = "liked"
publicKey = "main-key"
follow = "follow"
blocks = "blocks"
reports = "reports"
schemes = `(http|https)://` // Allowed URI protocols for parsing links in text.
alphaNumeric = `\p{L}\p{M}*|\p{N}` // A single number or script character in any language, including chars with accents.
usernameGrp = `(?:` + alphaNumeric + `|\.|\-|\_)` // Non-capturing group that matches against a single valid username character.
domainGrp = `(?:` + alphaNumeric + `|\.|\-|\:)` // Non-capturing group that matches against a single valid domain character.
mentionName = `^@(` + usernameGrp + `+)(?:@(` + domainGrp + `+))?$` // Extract parts of one mention, maybe including domain.
mentionFinder = `(?:^|\s)(@` + usernameGrp + `+(?:@` + domainGrp + `+)?)` // Extract all mentions from a text, each mention may include domain.
emojiShortcode = `\w{2,30}` // Pattern for emoji shortcodes. maximumEmojiShortcodeLength = 30
emojiFinder = `(?:\b)?:(` + emojiShortcode + `):(?:\b)?` // Extract all emoji shortcodes from a text.
usernameStrict = `^[a-z0-9_]{2,64}$` // Pattern for usernames on THIS instance. maximumUsernameLength = 64
usernameRelaxed = `[a-z0-9_\.]{2,}` // Relaxed version of username that can match instance accounts too.
misskeyReportNotesFinder = `(?m)(?:^Note: ((?:http|https):\/\/.*)$)` // Extract reported Note URIs from the text of a Misskey report/flag.
ulid = `[0123456789ABCDEFGHJKMNPQRSTVWXYZ]{26}` // Pattern for ULID.
ulidValidate = `^` + ulid + `$` // Validate one ULID.
/*
Path parts / capture.
*/
userPathPrefix = `^/?` + users + `/(` + usernameRelaxed + `)`
userPath = userPathPrefix + `$`
publicKeyPath = userPathPrefix + `/` + publicKey + `$`
inboxPath = userPathPrefix + `/` + inbox + `$`
outboxPath = userPathPrefix + `/` + outbox + `$`
followersPath = userPathPrefix + `/` + followers + `$`
followingPath = userPathPrefix + `/` + following + `$`
likedPath = userPathPrefix + `/` + liked + `$`
followPath = userPathPrefix + `/` + follow + `/(` + ulid + `)$`
likePath = userPathPrefix + `/` + liked + `/(` + ulid + `)$`
statusesPath = userPathPrefix + `/` + statuses + `/(` + ulid + `)$`
blockPath = userPathPrefix + `/` + blocks + `/(` + ulid + `)$`
reportPath = `^/?` + reports + `/(` + ulid + `)$`
filePath = `^/?(` + ulid + `)/([a-z]+)/([a-z]+)/(` + ulid + `)\.([a-z]+)$`
)
var (
// LinkScheme captures http/https schemes in URLs.
LinkScheme = func() *regexp.Regexp {
rgx, err := xurls.StrictMatchingScheme(schemes)
if err != nil {
panic(err)
}
return rgx
}()
// MentionName captures the username and domain part from
// a mention string such as @whatever_user@example.org,
// returning whatever_user and example.org (without the @ symbols).
// Will also work for characters with umlauts and other accents.
// See: https://regex101.com/r/9tjNUy/1 for explanation and examples.
MentionName = regexp.MustCompile(mentionName)
// MentionFinder extracts whole mentions from a piece of text.
MentionFinder = regexp.MustCompile(mentionFinder)
// EmojiShortcode validates an emoji name.
EmojiShortcode = regexp.MustCompile(emojiShortcode)
// EmojiFinder extracts emoji strings from a piece of text.
// See: https://regex101.com/r/478XGM/1
EmojiFinder = regexp.MustCompile(emojiFinder)
// Username can be used to validate usernames of new signups on this instance.
Username = regexp.MustCompile(usernameStrict)
// MisskeyReportNotes captures a list of Note URIs from report content created by Misskey.
// See: https://regex101.com/r/EnTOBV/1
MisskeyReportNotes = regexp.MustCompile(misskeyReportNotesFinder)
// UserPath validates and captures the username part from eg /users/example_username.
UserPath = regexp.MustCompile(userPath)
// PublicKeyPath parses a path that validates and captures the username part from eg /users/example_username/main-key
PublicKeyPath = regexp.MustCompile(publicKeyPath)
// InboxPath parses a path that validates and captures the username part from eg /users/example_username/inbox
InboxPath = regexp.MustCompile(inboxPath)
// OutboxPath parses a path that validates and captures the username part from eg /users/example_username/outbox
OutboxPath = regexp.MustCompile(outboxPath)
// FollowersPath parses a path that validates and captures the username part from eg /users/example_username/followers
FollowersPath = regexp.MustCompile(followersPath)
// FollowingPath parses a path that validates and captures the username part from eg /users/example_username/following
FollowingPath = regexp.MustCompile(followingPath)
// LikedPath parses a path that validates and captures the username part from eg /users/example_username/liked
LikedPath = regexp.MustCompile(likedPath)
// ULID parses and validate a ULID.
ULID = regexp.MustCompile(ulidValidate)
// FollowPath parses a path that validates and captures the username part and the ulid part
// from eg /users/example_username/follow/01F7XT5JZW1WMVSW1KADS8PVDH
FollowPath = regexp.MustCompile(followPath)
// LikePath parses a path that validates and captures the username part and the ulid part
// from eg /users/example_username/liked/01F7XT5JZW1WMVSW1KADS8PVDH
LikePath = regexp.MustCompile(likePath)
// StatusesPath parses a path that validates and captures the username part and the ulid part
// from eg /users/example_username/statuses/01F7XT5JZW1WMVSW1KADS8PVDH
// The regex can be played with here: https://regex101.com/r/G9zuxQ/1
StatusesPath = regexp.MustCompile(statusesPath)
// BlockPath parses a path that validates and captures the username part and the ulid part
// from eg /users/example_username/blocks/01F7XT5JZW1WMVSW1KADS8PVDH
BlockPath = regexp.MustCompile(blockPath)
// ReportPath parses a path that validates and captures the ulid part
// from eg /reports/01GP3AWY4CRDVRNZKW0TEAMB5R
ReportPath = regexp.MustCompile(reportPath)
// FilePath parses a file storage path of the form [ACCOUNT_ID]/[MEDIA_TYPE]/[MEDIA_SIZE]/[FILE_NAME]
// eg 01F8MH1H7YV1Z7D2C8K2730QBF/attachment/small/01F8MH8RMYQ6MSNY3JM2XT1CQ5.jpeg
// It captures the account id, media type, media size, file name, and file extension, eg
// `01F8MH1H7YV1Z7D2C8K2730QBF`, `attachment`, `small`, `01F8MH8RMYQ6MSNY3JM2XT1CQ5`, `jpeg`.
FilePath = regexp.MustCompile(filePath)
)
// bufpool is a memory pool of byte buffers for use in our regex utility functions.
var bufpool = sync.Pool{
New: func() any {
buf := bytes.NewBuffer(make([]byte, 0, 512))
return buf
},
}
// ReplaceAllStringFunc will call through to .ReplaceAllStringFunc in the provided regex, but provide you a clean byte buffer for optimized string writes.
func ReplaceAllStringFunc(rgx *regexp.Regexp, src string, repl func(match string, buf *bytes.Buffer) string) string {
buf := bufpool.Get().(*bytes.Buffer) //nolint
defer bufpool.Put(buf)
return rgx.ReplaceAllStringFunc(src, func(match string) string {
buf.Reset() // reset use
return repl(match, buf)
})
}
|
