[bugfix] Fix existing bio text showing as HTML (#531)
* fix existing bio text showing as HTML - updated replaced mentions to include instance - strips HTML from account source note in Verify handler - update text formatter to use buffers for string writes Signed-off-by: kim <grufwub@gmail.com> * go away linter Signed-off-by: kim <grufwub@gmail.com> * change buf reset location, change html mention tags Signed-off-by: kim <grufwub@gmail.com> * reduce FindLinks code complexity Signed-off-by: kim <grufwub@gmail.com> * fix HTML to text conversion Signed-off-by: kim <grufwub@gmail.com> * Update internal/regexes/regexes.go Co-authored-by: Mina Galić <mina.galic@puppet.com> * use improved html2text lib with more options Signed-off-by: kim <grufwub@gmail.com> * fix to produce actual plaintext from html Signed-off-by: kim <grufwub@gmail.com> * fix span tags instead written as space Signed-off-by: kim <grufwub@gmail.com> * performance improvements to regex replacements, fix link replace logic for un-html-ing in the future Signed-off-by: kim <grufwub@gmail.com> * fix tag/mention replacements to use input string, fix link replace to not include scheme Signed-off-by: kim <grufwub@gmail.com> * use matched input string for link replace href text Signed-off-by: kim <grufwub@gmail.com> * remove unused code (to appease linter :sobs:) Signed-off-by: kim <grufwub@gmail.com> * improve hashtagFinger regex to be more compliant Signed-off-by: kim <grufwub@gmail.com> * update breakReplacer to include both unix and windows line endings Signed-off-by: kim <grufwub@gmail.com> * add NoteRaw field to Account to store plaintext account bio, add migration for this, set for sensitive accounts Signed-off-by: kim <grufwub@gmail.com> * drop unnecessary code Signed-off-by: kim <grufwub@gmail.com> * update text package tests to fix logic changes Signed-off-by: kim <grufwub@gmail.com> * add raw note content testing to account update and account verify Signed-off-by: kim <grufwub@gmail.com> * remove unused modules Signed-off-by: kim <grufwub@gmail.com> * fix emoji regex Signed-off-by: kim <grufwub@gmail.com> * fix replacement of hashtags Signed-off-by: kim <grufwub@gmail.com> * update code comment Signed-off-by: kim <grufwub@gmail.com> Co-authored-by: Mina Galić <mina.galic@puppet.com>
This commit is contained in:
parent
08eb271a4c
commit
26b74aefaf
|
@ -75,6 +75,7 @@ func (suite *AccountUpdateTestSuite) TestAccountUpdateCredentialsPATCHHandler()
|
||||||
// check the returned api model account
|
// check the returned api model account
|
||||||
// fields should be updated
|
// fields should be updated
|
||||||
suite.Equal("<p>this is my new bio read it and weep</p>", apimodelAccount.Note)
|
suite.Equal("<p>this is my new bio read it and weep</p>", apimodelAccount.Note)
|
||||||
|
suite.Equal(newBio, apimodelAccount.Source.Note)
|
||||||
}
|
}
|
||||||
|
|
||||||
func (suite *AccountUpdateTestSuite) TestAccountUpdateCredentialsPATCHHandlerUnlockLock() {
|
func (suite *AccountUpdateTestSuite) TestAccountUpdateCredentialsPATCHHandlerUnlockLock() {
|
||||||
|
@ -194,6 +195,7 @@ func (suite *AccountUpdateTestSuite) TestAccountUpdateCredentialsPATCHHandlerGet
|
||||||
// check the returned api model account
|
// check the returned api model account
|
||||||
// fields should be updated
|
// fields should be updated
|
||||||
suite.Equal("<p>this is my new bio read it and weep</p>", apimodelAccount.Note)
|
suite.Equal("<p>this is my new bio read it and weep</p>", apimodelAccount.Note)
|
||||||
|
suite.Equal(newBio, apimodelAccount.Source.Note)
|
||||||
}
|
}
|
||||||
|
|
||||||
func (suite *AccountUpdateTestSuite) TestAccountUpdateCredentialsPATCHHandlerTwoFields() {
|
func (suite *AccountUpdateTestSuite) TestAccountUpdateCredentialsPATCHHandlerTwoFields() {
|
||||||
|
@ -235,6 +237,7 @@ func (suite *AccountUpdateTestSuite) TestAccountUpdateCredentialsPATCHHandlerTwo
|
||||||
// check the returned api model account
|
// check the returned api model account
|
||||||
// fields should be updated
|
// fields should be updated
|
||||||
suite.Equal("<p>this is my new bio read it and weep</p>", apimodelAccount.Note)
|
suite.Equal("<p>this is my new bio read it and weep</p>", apimodelAccount.Note)
|
||||||
|
suite.Equal(newBio, apimodelAccount.Source.Note)
|
||||||
suite.True(apimodelAccount.Locked)
|
suite.True(apimodelAccount.Locked)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
@ -280,6 +283,7 @@ func (suite *AccountUpdateTestSuite) TestAccountUpdateCredentialsPATCHHandlerWit
|
||||||
suite.Equal("updated zork display name!!!", apimodelAccount.DisplayName)
|
suite.Equal("updated zork display name!!!", apimodelAccount.DisplayName)
|
||||||
suite.True(apimodelAccount.Locked)
|
suite.True(apimodelAccount.Locked)
|
||||||
suite.Empty(apimodelAccount.Note)
|
suite.Empty(apimodelAccount.Note)
|
||||||
|
suite.Empty(apimodelAccount.Source.Note)
|
||||||
|
|
||||||
// header values...
|
// header values...
|
||||||
// should be set
|
// should be set
|
||||||
|
|
|
@ -86,6 +86,7 @@ func (suite *AccountVerifyTestSuite) TestAccountVerifyGet() {
|
||||||
suite.WithinDuration(time.Now(), lastStatusAt, 5*time.Minute)
|
suite.WithinDuration(time.Now(), lastStatusAt, 5*time.Minute)
|
||||||
suite.EqualValues(gtsmodel.VisibilityPublic, apimodelAccount.Source.Privacy)
|
suite.EqualValues(gtsmodel.VisibilityPublic, apimodelAccount.Source.Privacy)
|
||||||
suite.Equal(testAccount.Language, apimodelAccount.Source.Language)
|
suite.Equal(testAccount.Language, apimodelAccount.Source.Language)
|
||||||
|
suite.Equal(testAccount.NoteRaw, apimodelAccount.Source.Note)
|
||||||
}
|
}
|
||||||
|
|
||||||
func TestAccountVerifyTestSuite(t *testing.T) {
|
func TestAccountVerifyTestSuite(t *testing.T) {
|
||||||
|
|
|
@ -134,6 +134,7 @@ func copyAccount(account *gtsmodel.Account) *gtsmodel.Account {
|
||||||
DisplayName: account.DisplayName,
|
DisplayName: account.DisplayName,
|
||||||
Fields: account.Fields,
|
Fields: account.Fields,
|
||||||
Note: account.Note,
|
Note: account.Note,
|
||||||
|
NoteRaw: account.NoteRaw,
|
||||||
Memorial: account.Memorial,
|
Memorial: account.Memorial,
|
||||||
MovedToAccountID: account.MovedToAccountID,
|
MovedToAccountID: account.MovedToAccountID,
|
||||||
CreatedAt: account.CreatedAt,
|
CreatedAt: account.CreatedAt,
|
||||||
|
|
|
@ -0,0 +1,50 @@
|
||||||
|
/*
|
||||||
|
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 migrations
|
||||||
|
|
||||||
|
import (
|
||||||
|
"context"
|
||||||
|
|
||||||
|
gtsmodel "github.com/superseriousbusiness/gotosocial/internal/db/bundb/migrations/20211113114307_init"
|
||||||
|
"github.com/uptrace/bun"
|
||||||
|
)
|
||||||
|
|
||||||
|
func init() {
|
||||||
|
up := func(ctx context.Context, db *bun.DB) error {
|
||||||
|
return db.RunInTx(ctx, nil, func(ctx context.Context, tx bun.Tx) error {
|
||||||
|
// add account raw_note column
|
||||||
|
expr := tx.
|
||||||
|
NewAddColumn().
|
||||||
|
Model(>smodel.Account{}).
|
||||||
|
ColumnExpr("note_raw")
|
||||||
|
_, err := expr.Exec(ctx)
|
||||||
|
return err
|
||||||
|
})
|
||||||
|
}
|
||||||
|
|
||||||
|
down := func(ctx context.Context, db *bun.DB) error {
|
||||||
|
return db.RunInTx(ctx, nil, func(ctx context.Context, tx bun.Tx) error {
|
||||||
|
return nil
|
||||||
|
})
|
||||||
|
}
|
||||||
|
|
||||||
|
if err := Migrations.Register(up, down); err != nil {
|
||||||
|
panic(err)
|
||||||
|
}
|
||||||
|
}
|
|
@ -43,6 +43,7 @@ type Account struct {
|
||||||
DisplayName string `validate:"-" bun:""` // DisplayName for this account. Can be empty, then just the Username will be used for display purposes.
|
DisplayName string `validate:"-" bun:""` // DisplayName for this account. Can be empty, then just the Username will be used for display purposes.
|
||||||
Fields []Field `validate:"-"` // a key/value map of fields that this account has added to their profile
|
Fields []Field `validate:"-"` // a key/value map of fields that this account has added to their profile
|
||||||
Note string `validate:"-" bun:""` // A note that this account has on their profile (ie., the account's bio/description of themselves)
|
Note string `validate:"-" bun:""` // A note that this account has on their profile (ie., the account's bio/description of themselves)
|
||||||
|
NoteRaw string `validate:"-" bun:""` // The raw contents of .Note without conversion to HTML, only available when requester = target
|
||||||
Memorial bool `validate:"-" bun:",default:false"` // Is this a memorial account, ie., has the user passed away?
|
Memorial bool `validate:"-" bun:",default:false"` // Is this a memorial account, ie., has the user passed away?
|
||||||
AlsoKnownAs string `validate:"omitempty,ulid" bun:"type:CHAR(26),nullzero"` // This account is associated with x account id (TODO: migrate to be AlsoKnownAsID)
|
AlsoKnownAs string `validate:"omitempty,ulid" bun:"type:CHAR(26),nullzero"` // This account is associated with x account id (TODO: migrate to be AlsoKnownAsID)
|
||||||
MovedToAccountID string `validate:"omitempty,ulid" bun:"type:CHAR(26),nullzero"` // This account has moved this account id in the database
|
MovedToAccountID string `validate:"omitempty,ulid" bun:"type:CHAR(26),nullzero"` // This account has moved this account id in the database
|
||||||
|
|
|
@ -60,10 +60,17 @@ func (p *processor) Update(ctx context.Context, account *gtsmodel.Account, form
|
||||||
if err := validate.Note(*form.Note); err != nil {
|
if err := validate.Note(*form.Note); err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Set the raw note before processing
|
||||||
|
account.NoteRaw = *form.Note
|
||||||
|
|
||||||
|
// Process note to generate a valid HTML representation
|
||||||
note, err := p.processNote(ctx, *form.Note, account.ID)
|
note, err := p.processNote(ctx, *form.Note, account.ID)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, err
|
return nil, err
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Set updated HTML-ified note
|
||||||
account.Note = note
|
account.Note = note
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
|
@ -39,13 +39,11 @@ func (p *processor) Create(ctx context.Context, account *gtsmodel.Account, appli
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return nil, gtserror.NewErrorInternalError(err)
|
return nil, gtserror.NewErrorInternalError(err)
|
||||||
}
|
}
|
||||||
thisStatusURI := fmt.Sprintf("%s/%s", accountURIs.StatusesURI, thisStatusID)
|
|
||||||
thisStatusURL := fmt.Sprintf("%s/%s", accountURIs.StatusesURL, thisStatusID)
|
|
||||||
|
|
||||||
newStatus := >smodel.Status{
|
newStatus := >smodel.Status{
|
||||||
ID: thisStatusID,
|
ID: thisStatusID,
|
||||||
URI: thisStatusURI,
|
URI: accountURIs.StatusesURI + "/" + thisStatusID,
|
||||||
URL: thisStatusURL,
|
URL: accountURIs.StatusesURL + "/" + thisStatusID,
|
||||||
CreatedAt: time.Now(),
|
CreatedAt: time.Now(),
|
||||||
UpdatedAt: time.Now(),
|
UpdatedAt: time.Now(),
|
||||||
Local: true,
|
Local: true,
|
||||||
|
|
|
@ -242,11 +242,11 @@ func (p *processor) ProcessTags(ctx context.Context, form *apimodel.AdvancedStat
|
||||||
}
|
}
|
||||||
|
|
||||||
func (p *processor) ProcessEmojis(ctx context.Context, form *apimodel.AdvancedStatusCreateForm, accountID string, status *gtsmodel.Status) error {
|
func (p *processor) ProcessEmojis(ctx context.Context, form *apimodel.AdvancedStatusCreateForm, accountID string, status *gtsmodel.Status) error {
|
||||||
emojis := []string{}
|
|
||||||
gtsEmojis, err := p.db.EmojiStringsToEmojis(ctx, util.DeriveEmojisFromText(form.Status))
|
gtsEmojis, err := p.db.EmojiStringsToEmojis(ctx, util.DeriveEmojisFromText(form.Status))
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return fmt.Errorf("error generating emojis from status: %s", err)
|
return fmt.Errorf("error generating emojis from status: %s", err)
|
||||||
}
|
}
|
||||||
|
emojis := make([]string, 0, len(gtsEmojis))
|
||||||
for _, e := range gtsEmojis {
|
for _, e := range gtsEmojis {
|
||||||
emojis = append(emojis, e.ID)
|
emojis = append(emojis, e.ID)
|
||||||
}
|
}
|
||||||
|
|
|
@ -19,8 +19,12 @@
|
||||||
package regexes
|
package regexes
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
"bytes"
|
||||||
"fmt"
|
"fmt"
|
||||||
"regexp"
|
"regexp"
|
||||||
|
"sync"
|
||||||
|
|
||||||
|
"mvdan.cc/xurls/v2"
|
||||||
)
|
)
|
||||||
|
|
||||||
const (
|
const (
|
||||||
|
@ -47,6 +51,16 @@ const (
|
||||||
)
|
)
|
||||||
|
|
||||||
var (
|
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+)(?:@([a-zA-Z0-9_\-\.:]+))?$`
|
mentionName = `^@(\w+)(?:@([a-zA-Z0-9_\-\.:]+))?$`
|
||||||
// MentionName captures the username and domain part from a mention string
|
// 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)
|
// such as @whatever_user@example.org, returning whatever_user and example.org (without the @ symbols)
|
||||||
|
@ -58,7 +72,7 @@ var (
|
||||||
MentionFinder = regexp.MustCompile(mentionFinder)
|
MentionFinder = regexp.MustCompile(mentionFinder)
|
||||||
|
|
||||||
// hashtag regex can be played with here: https://regex101.com/r/bPxeca/1
|
// hashtag regex can be played with here: https://regex101.com/r/bPxeca/1
|
||||||
hashtagFinder = fmt.Sprintf(`(?:^|\n|\s)(#[a-zA-Z0-9]{1,%d})(?:\b)`, maximumHashtagLength)
|
hashtagFinder = fmt.Sprintf(`(?:^|\s)(?:#*)(#[a-zA-Z0-9]{1,%d})(?:#|\b)`, maximumHashtagLength)
|
||||||
// HashtagFinder finds possible hashtags in a string.
|
// HashtagFinder finds possible hashtags in a string.
|
||||||
// It returns just the string part of the hashtag, not the # symbol.
|
// It returns just the string part of the hashtag, not the # symbol.
|
||||||
HashtagFinder = regexp.MustCompile(hashtagFinder)
|
HashtagFinder = regexp.MustCompile(hashtagFinder)
|
||||||
|
@ -68,7 +82,7 @@ var (
|
||||||
EmojiShortcode = regexp.MustCompile(fmt.Sprintf("^%s$", emojiShortcode))
|
EmojiShortcode = regexp.MustCompile(fmt.Sprintf("^%s$", emojiShortcode))
|
||||||
|
|
||||||
// emoji regex can be played with here: https://regex101.com/r/478XGM/1
|
// emoji regex can be played with here: https://regex101.com/r/478XGM/1
|
||||||
emojiFinderString = fmt.Sprintf(`(?:\B)?:(%s):(?:\B)?`, emojiShortcode)
|
emojiFinderString = fmt.Sprintf(`(?:\b)?:(%s):(?:\b)?`, emojiShortcode)
|
||||||
// EmojiFinder extracts emoji strings from a piece of text.
|
// EmojiFinder extracts emoji strings from a piece of text.
|
||||||
EmojiFinder = regexp.MustCompile(emojiFinderString)
|
EmojiFinder = regexp.MustCompile(emojiFinderString)
|
||||||
|
|
||||||
|
@ -134,3 +148,21 @@ var (
|
||||||
// from eg /users/example_username/blocks/01F7XT5JZW1WMVSW1KADS8PVDH
|
// from eg /users/example_username/blocks/01F7XT5JZW1WMVSW1KADS8PVDH
|
||||||
BlockPath = regexp.MustCompile(blockPath)
|
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)
|
||||||
|
})
|
||||||
|
}
|
||||||
|
|
|
@ -19,10 +19,11 @@
|
||||||
package text
|
package text
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
"bytes"
|
||||||
"context"
|
"context"
|
||||||
"fmt"
|
|
||||||
"html"
|
"html"
|
||||||
"strings"
|
"strings"
|
||||||
|
"unicode"
|
||||||
|
|
||||||
"github.com/sirupsen/logrus"
|
"github.com/sirupsen/logrus"
|
||||||
|
|
||||||
|
@ -63,38 +64,40 @@ func postformat(in string) string {
|
||||||
}
|
}
|
||||||
|
|
||||||
func (f *formatter) ReplaceTags(ctx context.Context, in string, tags []*gtsmodel.Tag) string {
|
func (f *formatter) ReplaceTags(ctx context.Context, in string, tags []*gtsmodel.Tag) string {
|
||||||
return regexes.HashtagFinder.ReplaceAllStringFunc(in, func(match string) string {
|
return regexes.ReplaceAllStringFunc(regexes.HashtagFinder, in, func(match string, buf *bytes.Buffer) string {
|
||||||
// we have a match
|
// we have a match
|
||||||
matchTrimmed := strings.TrimSpace(match)
|
matchTrimmed := strings.TrimSpace(match)
|
||||||
tagAsEntered := strings.Split(matchTrimmed, "#")[1]
|
tagAsEntered := matchTrimmed[1:]
|
||||||
|
|
||||||
// check through the tags to find what we're matching
|
// check through the tags to find what we're matching
|
||||||
for _, tag := range tags {
|
for _, tag := range tags {
|
||||||
|
if strings.EqualFold(tagAsEntered, tag.Name) {
|
||||||
|
// Add any dropped space from match
|
||||||
|
if unicode.IsSpace(rune(match[0])) {
|
||||||
|
buf.WriteByte(match[0])
|
||||||
|
}
|
||||||
|
|
||||||
if strings.EqualFold(matchTrimmed, fmt.Sprintf("#%s", tag.Name)) {
|
|
||||||
// replace the #tag with the formatted tag content
|
// replace the #tag with the formatted tag content
|
||||||
tagContent := fmt.Sprintf(`<a href="%s" class="mention hashtag" rel="tag">#<span>%s</span></a>`, tag.URL, tagAsEntered)
|
// `<a href="tag.URL" class="mention hashtag" rel="tag">#<span>tagAsEntered</span></a>
|
||||||
|
buf.WriteString(`<a href="`)
|
||||||
// in case the match picked up any previous space or newlines (thanks to the regex), include them as well
|
buf.WriteString(tag.URL)
|
||||||
if strings.HasPrefix(match, " ") {
|
buf.WriteString(`" class="mention hashtag" rel="tag">#<span>`)
|
||||||
tagContent = " " + tagContent
|
buf.WriteString(tagAsEntered)
|
||||||
} else if strings.HasPrefix(match, "\n") {
|
buf.WriteString(`</span></a>`)
|
||||||
tagContent = "\n" + tagContent
|
return buf.String()
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// done
|
|
||||||
return tagContent
|
|
||||||
}
|
|
||||||
}
|
|
||||||
// the match wasn't in the list of tags for whatever reason, so just return the match as we found it so nothing changes
|
// the match wasn't in the list of tags for whatever reason, so just return the match as we found it so nothing changes
|
||||||
return match
|
return match
|
||||||
})
|
})
|
||||||
}
|
}
|
||||||
|
|
||||||
func (f *formatter) ReplaceMentions(ctx context.Context, in string, mentions []*gtsmodel.Mention) string {
|
func (f *formatter) ReplaceMentions(ctx context.Context, in string, mentions []*gtsmodel.Mention) string {
|
||||||
return regexes.MentionFinder.ReplaceAllStringFunc(in, func(match string) string {
|
return regexes.ReplaceAllStringFunc(regexes.MentionFinder, in, func(match string, buf *bytes.Buffer) string {
|
||||||
// we have a match
|
// we have a match, trim any spaces
|
||||||
matchTrimmed := strings.TrimSpace(match)
|
matchTrimmed := strings.TrimSpace(match)
|
||||||
|
|
||||||
// check through mentions to find what we're matching
|
// check through mentions to find what we're matching
|
||||||
for _, menchie := range mentions {
|
for _, menchie := range mentions {
|
||||||
if strings.EqualFold(matchTrimmed, menchie.NameString) {
|
if strings.EqualFold(matchTrimmed, menchie.NameString) {
|
||||||
|
@ -107,22 +110,26 @@ func (f *formatter) ReplaceMentions(ctx context.Context, in string, mentions []*
|
||||||
}
|
}
|
||||||
menchie.TargetAccount = a
|
menchie.TargetAccount = a
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// The mention's target is our target
|
||||||
targetAccount := menchie.TargetAccount
|
targetAccount := menchie.TargetAccount
|
||||||
|
|
||||||
|
// Add any dropped space from match
|
||||||
|
if unicode.IsSpace(rune(match[0])) {
|
||||||
|
buf.WriteByte(match[0])
|
||||||
|
}
|
||||||
|
|
||||||
// replace the mention with the formatted mention content
|
// replace the mention with the formatted mention content
|
||||||
mentionContent := fmt.Sprintf(`<span class="h-card"><a href="%s" class="u-url mention">@<span>%s</span></a></span>`, targetAccount.URL, targetAccount.Username)
|
// <span class="h-card"><a href="targetAccount.URL" class="u-url mention">@<span>targetAccount.Username</span></a></span>
|
||||||
|
buf.WriteString(`<span class="h-card"><a href="`)
|
||||||
// in case the match picked up any previous space or newlines (thanks to the regex), include them as well
|
buf.WriteString(targetAccount.URL)
|
||||||
if strings.HasPrefix(match, " ") {
|
buf.WriteString(`" class="u-url mention">@<span>`)
|
||||||
mentionContent = " " + mentionContent
|
buf.WriteString(targetAccount.Username)
|
||||||
} else if strings.HasPrefix(match, "\n") {
|
buf.WriteString(`</span></a></span>`)
|
||||||
mentionContent = "\n" + mentionContent
|
return buf.String()
|
||||||
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// done
|
|
||||||
return mentionContent
|
|
||||||
}
|
|
||||||
}
|
|
||||||
// the match wasn't in the list of mentions for whatever reason, so just return the match as we found it so nothing changes
|
// the match wasn't in the list of mentions for whatever reason, so just return the match as we found it so nothing changes
|
||||||
return match
|
return match
|
||||||
})
|
})
|
||||||
|
|
|
@ -19,34 +19,28 @@
|
||||||
package text
|
package text
|
||||||
|
|
||||||
import (
|
import (
|
||||||
|
"bytes"
|
||||||
"context"
|
"context"
|
||||||
"fmt"
|
|
||||||
"net/url"
|
"net/url"
|
||||||
|
"strings"
|
||||||
|
|
||||||
"mvdan.cc/xurls/v2"
|
"github.com/superseriousbusiness/gotosocial/internal/regexes"
|
||||||
)
|
)
|
||||||
|
|
||||||
// schemes is the regex for schemes we accept when looking for links.
|
|
||||||
// Basically, we accept https or http.
|
|
||||||
var schemes = `(((http|https))://)`
|
|
||||||
|
|
||||||
// FindLinks parses the given string looking for recognizable URLs (including scheme).
|
// FindLinks parses the given string looking for recognizable URLs (including scheme).
|
||||||
// It returns a list of those URLs, without changing the string, or an error if something goes wrong.
|
// It returns a list of those URLs, without changing the string, or an error if something goes wrong.
|
||||||
// If no URLs are found within the given string, an empty slice and nil will be returned.
|
// If no URLs are found within the given string, an empty slice and nil will be returned.
|
||||||
func FindLinks(in string) ([]*url.URL, error) {
|
func FindLinks(in string) []*url.URL {
|
||||||
rxStrict, err := xurls.StrictMatchingScheme(schemes)
|
var urls []*url.URL
|
||||||
if err != nil {
|
|
||||||
return nil, err
|
|
||||||
}
|
|
||||||
|
|
||||||
urls := []*url.URL{}
|
|
||||||
|
|
||||||
// bail already if we don't find anything
|
// bail already if we don't find anything
|
||||||
found := rxStrict.FindAllString(in, -1)
|
found := regexes.LinkScheme.FindAllString(in, -1)
|
||||||
if len(found) == 0 {
|
if len(found) == 0 {
|
||||||
return urls, nil
|
return nil
|
||||||
}
|
}
|
||||||
|
|
||||||
|
urlmap := map[string]struct{}{}
|
||||||
|
|
||||||
// for each string we find, we want to parse it into a URL if we can
|
// for each string we find, we want to parse it into a URL if we can
|
||||||
// if we fail to parse it, just ignore this match and continue
|
// if we fail to parse it, just ignore this match and continue
|
||||||
for _, f := range found {
|
for _, f := range found {
|
||||||
|
@ -54,29 +48,18 @@ func FindLinks(in string) ([]*url.URL, error) {
|
||||||
if err != nil {
|
if err != nil {
|
||||||
continue
|
continue
|
||||||
}
|
}
|
||||||
|
|
||||||
|
// Calculate string
|
||||||
|
ustr := u.String()
|
||||||
|
|
||||||
|
if _, ok := urlmap[ustr]; !ok {
|
||||||
|
// Has not been encountered yet
|
||||||
urls = append(urls, u)
|
urls = append(urls, u)
|
||||||
}
|
urlmap[ustr] = struct{}{}
|
||||||
|
|
||||||
// deduplicate the URLs
|
|
||||||
urlsDeduped := []*url.URL{}
|
|
||||||
|
|
||||||
for _, u := range urls {
|
|
||||||
if !contains(urlsDeduped, u) {
|
|
||||||
urlsDeduped = append(urlsDeduped, u)
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
return urlsDeduped, nil
|
return urls
|
||||||
}
|
|
||||||
|
|
||||||
// contains checks if the given url is already within a slice of URLs
|
|
||||||
func contains(urls []*url.URL, url *url.URL) bool {
|
|
||||||
for _, u := range urls {
|
|
||||||
if u.String() == url.String() {
|
|
||||||
return true
|
|
||||||
}
|
|
||||||
}
|
|
||||||
return false
|
|
||||||
}
|
}
|
||||||
|
|
||||||
// ReplaceLinks replaces all detected links in a piece of text with their HTML (href) equivalents.
|
// ReplaceLinks replaces all detected links in a piece of text with their HTML (href) equivalents.
|
||||||
|
@ -84,33 +67,20 @@ func contains(urls []*url.URL, url *url.URL) bool {
|
||||||
// href will end up double-formatted, if the text you pass here contains one or more hrefs already.
|
// href will end up double-formatted, if the text you pass here contains one or more hrefs already.
|
||||||
// To avoid this, you should sanitize any HTML out of text before you pass it into this function.
|
// To avoid this, you should sanitize any HTML out of text before you pass it into this function.
|
||||||
func (f *formatter) ReplaceLinks(ctx context.Context, in string) string {
|
func (f *formatter) ReplaceLinks(ctx context.Context, in string) string {
|
||||||
rxStrict, err := xurls.StrictMatchingScheme(schemes)
|
return regexes.ReplaceAllStringFunc(regexes.LinkScheme, in, func(urlString string, buf *bytes.Buffer) string {
|
||||||
if err != nil {
|
|
||||||
panic(err)
|
|
||||||
}
|
|
||||||
|
|
||||||
replaced := rxStrict.ReplaceAllStringFunc(in, func(urlString string) string {
|
|
||||||
thisURL, err := url.Parse(urlString)
|
thisURL, err := url.Parse(urlString)
|
||||||
if err != nil {
|
if err != nil {
|
||||||
return urlString // we can't parse it as a URL so don't replace it
|
return urlString // we can't parse it as a URL so don't replace it
|
||||||
}
|
}
|
||||||
|
// <a href="thisURL.String()" rel="noopener">urlString</a>
|
||||||
shortString := thisURL.Hostname()
|
urlString = thisURL.String()
|
||||||
|
buf.WriteString(`<a href="`)
|
||||||
if thisURL.Path != "" {
|
buf.WriteString(thisURL.String())
|
||||||
shortString += thisURL.Path
|
buf.WriteString(`" rel="noopener">`)
|
||||||
}
|
urlString = strings.TrimPrefix(urlString, thisURL.Scheme)
|
||||||
|
urlString = strings.TrimPrefix(urlString, "://")
|
||||||
if thisURL.Fragment != "" {
|
buf.WriteString(urlString)
|
||||||
shortString = shortString + "#" + thisURL.Fragment
|
buf.WriteString(`</a>`)
|
||||||
}
|
return buf.String()
|
||||||
|
|
||||||
if thisURL.RawQuery != "" {
|
|
||||||
shortString = shortString + "?" + thisURL.RawQuery
|
|
||||||
}
|
|
||||||
|
|
||||||
replacement := fmt.Sprintf(`<a href="%s" rel="noopener">%s</a>`, urlString, shortString)
|
|
||||||
return replacement
|
|
||||||
})
|
})
|
||||||
return replaced
|
|
||||||
}
|
}
|
||||||
|
|
|
@ -75,9 +75,7 @@ func (suite *LinkTestSuite) TestParseSimple() {
|
||||||
}
|
}
|
||||||
|
|
||||||
func (suite *LinkTestSuite) TestParseURLsFromText1() {
|
func (suite *LinkTestSuite) TestParseURLsFromText1() {
|
||||||
urls, err := text.FindLinks(text1)
|
urls := text.FindLinks(text1)
|
||||||
|
|
||||||
assert.NoError(suite.T(), err)
|
|
||||||
|
|
||||||
assert.Equal(suite.T(), "https://example.org/link/to/something#fragment", urls[0].String())
|
assert.Equal(suite.T(), "https://example.org/link/to/something#fragment", urls[0].String())
|
||||||
assert.Equal(suite.T(), "http://test.example.org?q=bahhhhhhhhhhhh", urls[1].String())
|
assert.Equal(suite.T(), "http://test.example.org?q=bahhhhhhhhhhhh", urls[1].String())
|
||||||
|
@ -86,16 +84,14 @@ func (suite *LinkTestSuite) TestParseURLsFromText1() {
|
||||||
}
|
}
|
||||||
|
|
||||||
func (suite *LinkTestSuite) TestParseURLsFromText2() {
|
func (suite *LinkTestSuite) TestParseURLsFromText2() {
|
||||||
urls, err := text.FindLinks(text2)
|
urls := text.FindLinks(text2)
|
||||||
assert.NoError(suite.T(), err)
|
|
||||||
|
|
||||||
// assert length 1 because the found links will be deduplicated
|
// assert length 1 because the found links will be deduplicated
|
||||||
assert.Len(suite.T(), urls, 1)
|
assert.Len(suite.T(), urls, 1)
|
||||||
}
|
}
|
||||||
|
|
||||||
func (suite *LinkTestSuite) TestParseURLsFromText3() {
|
func (suite *LinkTestSuite) TestParseURLsFromText3() {
|
||||||
urls, err := text.FindLinks(text3)
|
urls := text.FindLinks(text3)
|
||||||
assert.NoError(suite.T(), err)
|
|
||||||
|
|
||||||
// assert length 0 because `mailto:` isn't accepted
|
// assert length 0 because `mailto:` isn't accepted
|
||||||
assert.Len(suite.T(), urls, 0)
|
assert.Len(suite.T(), urls, 0)
|
||||||
|
@ -112,7 +108,7 @@ Here's link number two: <a href="http://test.example.org?q=bahhhhhhhhhhhh" rel="
|
||||||
|
|
||||||
really.cool.website <-- this one shouldn't be parsed as a link because it doesn't contain the scheme
|
really.cool.website <-- this one shouldn't be parsed as a link because it doesn't contain the scheme
|
||||||
|
|
||||||
<a href="https://example.orghttps://google.com" rel="noopener">example.orghttps//google.com</a> <-- this shouldn't work either, but it does?! OK
|
<a href="https://example.orghttps://google.com" rel="noopener">example.orghttps://google.com</a> <-- this shouldn't work either, but it does?! OK
|
||||||
`, replaced)
|
`, replaced)
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
|
@ -20,12 +20,17 @@ package text
|
||||||
|
|
||||||
import (
|
import (
|
||||||
"context"
|
"context"
|
||||||
"fmt"
|
|
||||||
"strings"
|
"strings"
|
||||||
|
|
||||||
"github.com/superseriousbusiness/gotosocial/internal/gtsmodel"
|
"github.com/superseriousbusiness/gotosocial/internal/gtsmodel"
|
||||||
)
|
)
|
||||||
|
|
||||||
|
// breakReplacer replaces new-lines with HTML breaks.
|
||||||
|
var breakReplacer = strings.NewReplacer(
|
||||||
|
"\r\n", "<br/>",
|
||||||
|
"\n", "<br/>",
|
||||||
|
)
|
||||||
|
|
||||||
func (f *formatter) FromPlain(ctx context.Context, plain string, mentions []*gtsmodel.Mention, tags []*gtsmodel.Tag) string {
|
func (f *formatter) FromPlain(ctx context.Context, plain string, mentions []*gtsmodel.Mention, tags []*gtsmodel.Tag) string {
|
||||||
content := preformat(plain)
|
content := preformat(plain)
|
||||||
|
|
||||||
|
@ -42,10 +47,10 @@ func (f *formatter) FromPlain(ctx context.Context, plain string, mentions []*gts
|
||||||
content = f.ReplaceMentions(ctx, content, mentions)
|
content = f.ReplaceMentions(ctx, content, mentions)
|
||||||
|
|
||||||
// replace newlines with breaks
|
// replace newlines with breaks
|
||||||
content = strings.ReplaceAll(content, "\n", "<br />")
|
content = breakReplacer.Replace(content)
|
||||||
|
|
||||||
// wrap the whole thing in a pee
|
// wrap the whole thing in a pee
|
||||||
content = fmt.Sprintf(`<p>%s</p>`, content)
|
content = `<p>` + content + `</p>`
|
||||||
|
|
||||||
return postformat(content)
|
return postformat(content)
|
||||||
}
|
}
|
||||||
|
|
|
@ -53,7 +53,6 @@ func (suite *PlainTestSuite) TestParseSimple() {
|
||||||
}
|
}
|
||||||
|
|
||||||
func (suite *PlainTestSuite) TestParseWithTag() {
|
func (suite *PlainTestSuite) TestParseWithTag() {
|
||||||
|
|
||||||
foundTags := []*gtsmodel.Tag{
|
foundTags := []*gtsmodel.Tag{
|
||||||
suite.testTags["welcome"],
|
suite.testTags["welcome"],
|
||||||
}
|
}
|
||||||
|
@ -63,7 +62,6 @@ func (suite *PlainTestSuite) TestParseWithTag() {
|
||||||
}
|
}
|
||||||
|
|
||||||
func (suite *PlainTestSuite) TestParseMoreComplex() {
|
func (suite *PlainTestSuite) TestParseMoreComplex() {
|
||||||
|
|
||||||
foundTags := []*gtsmodel.Tag{
|
foundTags := []*gtsmodel.Tag{
|
||||||
suite.testTags["Hashtag"],
|
suite.testTags["Hashtag"],
|
||||||
}
|
}
|
||||||
|
|
|
@ -58,7 +58,7 @@ func (c *converter) AccountToAPIAccountSensitive(ctx context.Context, a *gtsmode
|
||||||
Privacy: c.VisToAPIVis(ctx, a.Privacy),
|
Privacy: c.VisToAPIVis(ctx, a.Privacy),
|
||||||
Sensitive: a.Sensitive,
|
Sensitive: a.Sensitive,
|
||||||
Language: a.Language,
|
Language: a.Language,
|
||||||
Note: a.Note,
|
Note: a.NoteRaw,
|
||||||
Fields: apiAccount.Fields,
|
Fields: apiAccount.Fields,
|
||||||
FollowRequestsCount: frc,
|
FollowRequestsCount: frc,
|
||||||
}
|
}
|
||||||
|
@ -703,7 +703,6 @@ func (c *converter) NotificationToAPINotification(ctx context.Context, n *gtsmod
|
||||||
}
|
}
|
||||||
|
|
||||||
func (c *converter) DomainBlockToAPIDomainBlock(ctx context.Context, b *gtsmodel.DomainBlock, export bool) (*model.DomainBlock, error) {
|
func (c *converter) DomainBlockToAPIDomainBlock(ctx context.Context, b *gtsmodel.DomainBlock, export bool) (*model.DomainBlock, error) {
|
||||||
|
|
||||||
domainBlock := &model.DomainBlock{
|
domainBlock := &model.DomainBlock{
|
||||||
Domain: b.Domain,
|
Domain: b.Domain,
|
||||||
PublicComment: b.PublicComment,
|
PublicComment: b.PublicComment,
|
||||||
|
|
|
@ -319,6 +319,7 @@ func NewTestAccounts() map[string]*gtsmodel.Account {
|
||||||
DisplayName: "",
|
DisplayName: "",
|
||||||
Fields: []gtsmodel.Field{},
|
Fields: []gtsmodel.Field{},
|
||||||
Note: "",
|
Note: "",
|
||||||
|
NoteRaw: "",
|
||||||
Memorial: false,
|
Memorial: false,
|
||||||
MovedToAccountID: "",
|
MovedToAccountID: "",
|
||||||
CreatedAt: time.Now().Add(-72 * time.Hour),
|
CreatedAt: time.Now().Add(-72 * time.Hour),
|
||||||
|
@ -356,7 +357,8 @@ func NewTestAccounts() map[string]*gtsmodel.Account {
|
||||||
HeaderMediaAttachmentID: "01PFPMWK2FF0D9WMHEJHR07C3Q",
|
HeaderMediaAttachmentID: "01PFPMWK2FF0D9WMHEJHR07C3Q",
|
||||||
DisplayName: "original zork (he/they)",
|
DisplayName: "original zork (he/they)",
|
||||||
Fields: []gtsmodel.Field{},
|
Fields: []gtsmodel.Field{},
|
||||||
Note: "hey yo this is my profile!",
|
Note: "<p>hey yo this is my profile!</p>",
|
||||||
|
NoteRaw: "hey yo this is my profile!",
|
||||||
Memorial: false,
|
Memorial: false,
|
||||||
MovedToAccountID: "",
|
MovedToAccountID: "",
|
||||||
CreatedAt: time.Now().Add(-48 * time.Hour),
|
CreatedAt: time.Now().Add(-48 * time.Hour),
|
||||||
|
@ -394,7 +396,8 @@ func NewTestAccounts() map[string]*gtsmodel.Account {
|
||||||
HeaderMediaAttachmentID: "",
|
HeaderMediaAttachmentID: "",
|
||||||
DisplayName: "happy little turtle :3",
|
DisplayName: "happy little turtle :3",
|
||||||
Fields: []gtsmodel.Field{},
|
Fields: []gtsmodel.Field{},
|
||||||
Note: "i post about things that concern me",
|
Note: "<p>i post about things that concern me</p>",
|
||||||
|
NoteRaw: "i post about things that concern me",
|
||||||
Memorial: false,
|
Memorial: false,
|
||||||
MovedToAccountID: "",
|
MovedToAccountID: "",
|
||||||
CreatedAt: time.Now().Add(-190 * time.Hour),
|
CreatedAt: time.Now().Add(-190 * time.Hour),
|
||||||
|
|
Loading…
Reference in New Issue