mirror of
https://github.com/superseriousbusiness/gotosocial.git
synced 2024-11-27 02:33:47 +01:00
26b74aefaf
* 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>
137 lines
4.6 KiB
Go
137 lines
4.6 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 text
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"html"
|
|
"strings"
|
|
"unicode"
|
|
|
|
"github.com/sirupsen/logrus"
|
|
|
|
"github.com/superseriousbusiness/gotosocial/internal/gtsmodel"
|
|
"github.com/superseriousbusiness/gotosocial/internal/regexes"
|
|
)
|
|
|
|
// preformat contains some common logic for making a string ready for formatting, which should be used for all user-input text.
|
|
func preformat(in string) string {
|
|
// do some preformatting of the text
|
|
|
|
// 1. unescape everything that might be html escaped
|
|
s := html.UnescapeString(in)
|
|
|
|
// 2. trim leading or trailing whitespace
|
|
s = strings.TrimSpace(s)
|
|
return s
|
|
}
|
|
|
|
// postformat contains some common logic for html sanitization of text, wrapping elements, and trimming newlines and whitespace
|
|
func postformat(in string) string {
|
|
// do some postformatting of the text
|
|
|
|
// 1. sanitize html to remove potentially dangerous elements
|
|
s := SanitizeHTML(in)
|
|
|
|
// 2. the sanitize step tends to escape characters inside codeblocks, which is behavior we don't want, so unescape everything again
|
|
s = html.UnescapeString(s)
|
|
|
|
// 3. minify html to remove any trailing newlines, spaces, unnecessary elements, etc etc
|
|
mini, err := MinifyHTML(s)
|
|
if err != nil {
|
|
// if the minify failed, just return what we have
|
|
return s
|
|
}
|
|
// return minified version of the html
|
|
return mini
|
|
}
|
|
|
|
func (f *formatter) ReplaceTags(ctx context.Context, in string, tags []*gtsmodel.Tag) string {
|
|
return regexes.ReplaceAllStringFunc(regexes.HashtagFinder, in, func(match string, buf *bytes.Buffer) string {
|
|
// we have a match
|
|
matchTrimmed := strings.TrimSpace(match)
|
|
tagAsEntered := matchTrimmed[1:]
|
|
|
|
// check through the tags to find what we're matching
|
|
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])
|
|
}
|
|
|
|
// replace the #tag with the formatted tag content
|
|
// `<a href="tag.URL" class="mention hashtag" rel="tag">#<span>tagAsEntered</span></a>
|
|
buf.WriteString(`<a href="`)
|
|
buf.WriteString(tag.URL)
|
|
buf.WriteString(`" class="mention hashtag" rel="tag">#<span>`)
|
|
buf.WriteString(tagAsEntered)
|
|
buf.WriteString(`</span></a>`)
|
|
return buf.String()
|
|
}
|
|
}
|
|
|
|
// 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
|
|
})
|
|
}
|
|
|
|
func (f *formatter) ReplaceMentions(ctx context.Context, in string, mentions []*gtsmodel.Mention) string {
|
|
return regexes.ReplaceAllStringFunc(regexes.MentionFinder, in, func(match string, buf *bytes.Buffer) string {
|
|
// we have a match, trim any spaces
|
|
matchTrimmed := strings.TrimSpace(match)
|
|
|
|
// check through mentions to find what we're matching
|
|
for _, menchie := range mentions {
|
|
if strings.EqualFold(matchTrimmed, menchie.NameString) {
|
|
// make sure we have an account attached to this mention
|
|
if menchie.TargetAccount == nil {
|
|
a, err := f.db.GetAccountByID(ctx, menchie.TargetAccountID)
|
|
if err != nil {
|
|
logrus.Errorf("error getting account with id %s from the db: %s", menchie.TargetAccountID, err)
|
|
return match
|
|
}
|
|
menchie.TargetAccount = a
|
|
}
|
|
|
|
// The mention's target is our target
|
|
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
|
|
// <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="`)
|
|
buf.WriteString(targetAccount.URL)
|
|
buf.WriteString(`" class="u-url mention">@<span>`)
|
|
buf.WriteString(targetAccount.Username)
|
|
buf.WriteString(`</span></a></span>`)
|
|
return buf.String()
|
|
}
|
|
}
|
|
|
|
// 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
|
|
})
|
|
}
|