[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>

3 files changed, 10 insertions, 5 deletions

diff --git a/internal/processing/account/update.go b/internal/processing/account/update.go
index 738aa8c88..3d6bbae2a 100644
--- a/internal/processing/account/update.go
+++ b/internal/processing/account/update.go
@@ -60,10 +60,17 @@ func (p *processor) Update(ctx context.Context, account *gtsmodel.Account, form
 		if err := validate.Note(*form.Note); err != nil {
 			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)
 		if err != nil {
 			return nil, err
 		}
+
+		// Set updated HTML-ified note
 		account.Note = note
 	}
 
diff --git a/internal/processing/status/create.go b/internal/processing/status/create.go
index 1e93af162..add8a5bc6 100644
--- a/internal/processing/status/create.go
+++ b/internal/processing/status/create.go
@@ -39,13 +39,11 @@ func (p *processor) Create(ctx context.Context, account *gtsmodel.Account, appli
 	if err != nil {
 		return nil, gtserror.NewErrorInternalError(err)
 	}
-	thisStatusURI := fmt.Sprintf("%s/%s", accountURIs.StatusesURI, thisStatusID)
-	thisStatusURL := fmt.Sprintf("%s/%s", accountURIs.StatusesURL, thisStatusID)
 
 	newStatus := &gtsmodel.Status{
 		ID:                       thisStatusID,
-		URI:                      thisStatusURI,
-		URL:                      thisStatusURL,
+		URI:                      accountURIs.StatusesURI + "/" + thisStatusID,
+		URL:                      accountURIs.StatusesURL + "/" + thisStatusID,
 		CreatedAt:                time.Now(),
 		UpdatedAt:                time.Now(),
 		Local:                    true,
diff --git a/internal/processing/status/util.go b/internal/processing/status/util.go
index 5de66af8a..190d88f1b 100644
--- a/internal/processing/status/util.go
+++ b/internal/processing/status/util.go
@@ -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 {
-	emojis := []string{}
 	gtsEmojis, err := p.db.EmojiStringsToEmojis(ctx, util.DeriveEmojisFromText(form.Status))
 	if err != nil {
 		return fmt.Errorf("error generating emojis from status: %s", err)
 	}
+	emojis := make([]string, 0, len(gtsEmojis))
 	for _, e := range gtsEmojis {
 		emojis = append(emojis, e.ID)
 	}