gotosocial/internal/regexes/regexes.go
tobi dfdc473cef
[chore] Webfinger rework (#627)
* move finger to dereferencer

* totally break GetRemoteAccount

* start reworking finger func a bit

* start reworking getRemoteAccount a bit

* move mention parts to namestring

* rework webfingerget

* use util function to extract webfinger parts

* use accountDomain

* rework finger again, final form

* just a real nasty commit, the worst

* remove refresh from account

* use new ASRepToAccount signature

* fix incorrect debug call

* fix for new getRemoteAccount

* rework GetRemoteAccount

* start updating tests to remove repetition

* break a lot of tests
Move shared test logic into the testrig,
rather than having it scattered all over
the place. This allows us to just mock
the transport controller once, and have
all tests use it (unless they need not to
for some other reason).

* fix up tests to use main mock httpclient

* webfinger only if necessary

* cheeky linting with the lads

* update mentionName regex
recognize instance accounts

* don't finger instance accounts

* test webfinger part extraction

* increase default worker count to 4 per cpu

* don't repeat regex parsing

* final search for discovered accountDomain

* be more permissive in namestring lookup

* add more extraction tests

* simplify GetParseMentionFunc

* skip long search if local account

* fix broken test
2022-06-11 11:01:34 +02:00

168 lines
6.9 KiB
Go

/*
GoToSocial
Copyright (C) 2021-2022 GoToSocial Authors admin@gotosocial.org
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"
"fmt"
"regexp"
"sync"
"mvdan.cc/xurls/v2"
)
const (
users = "users"
actors = "actors"
statuses = "statuses"
inbox = "inbox"
outbox = "outbox"
followers = "followers"
following = "following"
liked = "liked"
// collections = "collections"
// featured = "featured"
publicKey = "main-key"
follow = "follow"
// update = "updates"
blocks = "blocks"
)
const (
maximumUsernameLength = 64
maximumEmojiShortcodeLength = 30
maximumHashtagLength = 30
)
var (
schemes = `(http|https)://`
// LinkScheme captures http/https schemes in URLs.
LinkScheme = func() *regexp.Regexp {
rgx, err := xurls.StrictMatchingScheme(schemes)
if err != nil {
panic(err)
}
return rgx
}()
mentionName = `^@([\w\-\.]+)(?:@([\w\-\.:]+))?$`
// MentionName captures the username and domain part from a mention string
// such as @whatever_user@example.org, returning whatever_user and example.org (without the @ symbols)
MentionName = regexp.MustCompile(mentionName)
// mention regex can be played around with here: https://regex101.com/r/G1oGR0/1
mentionFinder = `(?:^|\s)(@\w+(?:@[a-zA-Z0-9_\-\.]+)?)`
// MentionFinder extracts mentions from a piece of text.
MentionFinder = regexp.MustCompile(mentionFinder)
// hashtag regex can be played with here: https://regex101.com/r/bPxeca/1
hashtagFinder = fmt.Sprintf(`(?:^|\s)(?:#*)(#[a-zA-Z0-9]{1,%d})(?:#|\b)`, maximumHashtagLength)
// HashtagFinder finds possible hashtags in a string.
// It returns just the string part of the hashtag, not the # symbol.
HashtagFinder = regexp.MustCompile(hashtagFinder)
emojiShortcode = fmt.Sprintf(`\w{2,%d}`, maximumEmojiShortcodeLength)
// EmojiShortcode validates an emoji name.
EmojiShortcode = regexp.MustCompile(fmt.Sprintf("^%s$", emojiShortcode))
// emoji regex can be played with here: https://regex101.com/r/478XGM/1
emojiFinderString = fmt.Sprintf(`(?:\b)?:(%s):(?:\b)?`, emojiShortcode)
// EmojiFinder extracts emoji strings from a piece of text.
EmojiFinder = regexp.MustCompile(emojiFinderString)
// usernameString defines an acceptable username on this instance
usernameString = fmt.Sprintf(`[a-z0-9_]{2,%d}`, maximumUsernameLength)
// Username can be used to validate usernames of new signups
Username = regexp.MustCompile(fmt.Sprintf(`^%s$`, usernameString))
userPathString = fmt.Sprintf(`^?/%s/(%s)$`, users, usernameString)
// UserPath parses a path that validates and captures the username part from eg /users/example_username
UserPath = regexp.MustCompile(userPathString)
publicKeyPath = fmt.Sprintf(`^?/%s/(%s)/%s`, users, usernameString, publicKey)
// PublicKeyPath parses a path that validates and captures the username part from eg /users/example_username/main-key
PublicKeyPath = regexp.MustCompile(publicKeyPath)
inboxPath = fmt.Sprintf(`^/?%s/(%s)/%s$`, users, usernameString, inbox)
// InboxPath parses a path that validates and captures the username part from eg /users/example_username/inbox
InboxPath = regexp.MustCompile(inboxPath)
outboxPath = fmt.Sprintf(`^/?%s/(%s)/%s$`, users, usernameString, outbox)
// OutboxPath parses a path that validates and captures the username part from eg /users/example_username/outbox
OutboxPath = regexp.MustCompile(outboxPath)
actorPath = fmt.Sprintf(`^?/%s/(%s)$`, actors, usernameString)
// ActorPath parses a path that validates and captures the username part from eg /actors/example_username
ActorPath = regexp.MustCompile(actorPath)
followersPath = fmt.Sprintf(`^/?%s/(%s)/%s$`, users, usernameString, followers)
// FollowersPath parses a path that validates and captures the username part from eg /users/example_username/followers
FollowersPath = regexp.MustCompile(followersPath)
followingPath = fmt.Sprintf(`^/?%s/(%s)/%s$`, users, usernameString, following)
// FollowingPath parses a path that validates and captures the username part from eg /users/example_username/following
FollowingPath = regexp.MustCompile(followingPath)
followPath = fmt.Sprintf(`^/?%s/(%s)/%s/(%s)$`, users, usernameString, follow, ulid)
// 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)
ulid = `[0123456789ABCDEFGHJKMNPQRSTVWXYZ]{26}`
// ULID parses and validate a ULID.
ULID = regexp.MustCompile(fmt.Sprintf(`^%s$`, ulid))
likedPath = fmt.Sprintf(`^/?%s/(%s)/%s$`, users, usernameString, liked)
// LikedPath parses a path that validates and captures the username part from eg /users/example_username/liked
LikedPath = regexp.MustCompile(likedPath)
likePath = fmt.Sprintf(`^/?%s/(%s)/%s/(%s)$`, users, usernameString, liked, ulid)
// LikePath parses a path that validates and captures the username part and the ulid part
// from eg /users/example_username/like/01F7XT5JZW1WMVSW1KADS8PVDH
LikePath = regexp.MustCompile(likePath)
statusesPath = fmt.Sprintf(`^/?%s/(%s)/%s/(%s)$`, users, usernameString, statuses, ulid)
// 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 = fmt.Sprintf(`^/?%s/(%s)/%s/(%s)$`, users, usernameString, blocks, ulid)
// 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)
)
// 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)
})
}