Markdown Statuses (#116)

* parse markdown statuses if desired

* add some preliminary docs for writing posts

5 files changed, 253 insertions, 0 deletions

diff --git a/internal/text/common.go b/internal/text/common.go
new file mode 100644
index 000000000..0165af630
--- /dev/null
+++ b/internal/text/common.go
@@ -0,0 +1,46 @@
+/*
+   GoToSocial
+   Copyright (C) 2021 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 (
+	"fmt"
+	"strings"
+)
+
+// 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. Trim all the whitespace
+	s := strings.TrimSpace(in)
+	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 any dodgy scripts or other disallowed elements
+	s := SanitizeHTML(in)
+	// 2. wrap the whole thing in a paragraph
+	s = fmt.Sprintf(`<p>%s</p>`, s)
+	// 3. remove any cheeky newlines
+	s = strings.ReplaceAll(s, "\n", "")
+	// 4. remove any whitespace added as a result of the formatting
+	s = strings.TrimSpace(s)
+	return s
+}
diff --git a/internal/text/formatter.go b/internal/text/formatter.go
new file mode 100644
index 000000000..f8cca6675
--- /dev/null
+++ b/internal/text/formatter.go
@@ -0,0 +1,49 @@
+/*
+   GoToSocial
+   Copyright (C) 2021 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 (
+	"github.com/sirupsen/logrus"
+	"github.com/superseriousbusiness/gotosocial/internal/config"
+	"github.com/superseriousbusiness/gotosocial/internal/db"
+	"github.com/superseriousbusiness/gotosocial/internal/gtsmodel"
+)
+
+// Formatter wraps some logic and functions for parsing statuses and other text input into nice html.
+type Formatter interface {
+	// FromMarkdown parses an HTML text from a markdown-formatted text.
+	FromMarkdown(md string, mentions []*gtsmodel.Mention, tags []*gtsmodel.Tag) string
+	// FromPlain parses an HTML text from a plaintext.
+	FromPlain(plain string, mentions []*gtsmodel.Mention, tags []*gtsmodel.Tag) string
+}
+
+type formatter struct {
+	cfg *config.Config
+	db  db.DB
+	log *logrus.Logger
+}
+
+// NewFormatter returns a new Formatter interface for parsing statuses and other text input into nice html.
+func NewFormatter(cfg *config.Config, db db.DB, log *logrus.Logger) Formatter {
+	return &formatter{
+		cfg: cfg,
+		db:  db,
+		log: log,
+	}
+}
diff --git a/internal/text/markdown.go b/internal/text/markdown.go
new file mode 100644
index 000000000..d1309f389
--- /dev/null
+++ b/internal/text/markdown.go
@@ -0,0 +1,58 @@
+/*
+   GoToSocial
+   Copyright (C) 2021 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 (
+	"fmt"
+	"strings"
+
+	"github.com/russross/blackfriday/v2"
+	"github.com/superseriousbusiness/gotosocial/internal/gtsmodel"
+)
+
+var bfExtensions = blackfriday.NoIntraEmphasis |
+	blackfriday.FencedCode |
+	blackfriday.Autolink |
+	blackfriday.Strikethrough |
+	blackfriday.SpaceHeadings |
+	blackfriday.BackslashLineBreak
+
+func (f *formatter) FromMarkdown(md string, mentions []*gtsmodel.Mention, tags []*gtsmodel.Tag) string {
+	content := preformat(md)
+
+	// do the markdown parsing *first*
+	content = string(blackfriday.Run([]byte(content), blackfriday.WithExtensions(bfExtensions)))
+
+	// format mentions nicely
+	for _, menchie := range mentions {
+		targetAccount := &gtsmodel.Account{}
+		if err := f.db.GetByID(menchie.TargetAccountID, targetAccount); err == nil {
+			mentionContent := fmt.Sprintf(`<span class="h-card"><a href="%s" class="u-url mention">@<span>%s</span></a></span>`, targetAccount.URL, targetAccount.Username)
+			content = strings.ReplaceAll(content, menchie.NameString, mentionContent)
+		}
+	}
+
+	// format tags nicely
+	for _, tag := range tags {
+		tagContent := fmt.Sprintf(`<a href="%s" class="mention hashtag" rel="tag">#<span>%s</span></a>`, tag.URL, tag.Name)
+		content = strings.ReplaceAll(content, fmt.Sprintf("#%s", tag.Name), tagContent)
+	}
+
+	return postformat(content)
+}
diff --git a/internal/text/plain.go b/internal/text/plain.go
new file mode 100644
index 000000000..24ef16f8e
--- /dev/null
+++ b/internal/text/plain.go
@@ -0,0 +1,50 @@
+/*
+   GoToSocial
+   Copyright (C) 2021 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 (
+	"fmt"
+	"strings"
+
+	"github.com/superseriousbusiness/gotosocial/internal/gtsmodel"
+)
+
+func (f *formatter) FromPlain(plain string, mentions []*gtsmodel.Mention, tags []*gtsmodel.Tag) string {
+	content := preformat(plain)
+
+	// format mentions nicely
+	for _, menchie := range mentions {
+		targetAccount := &gtsmodel.Account{}
+		if err := f.db.GetByID(menchie.TargetAccountID, targetAccount); err == nil {
+			mentionContent := fmt.Sprintf(`<span class="h-card"><a href="%s" class="u-url mention">@<span>%s</span></a></span>`, targetAccount.URL, targetAccount.Username)
+			content = strings.ReplaceAll(content, menchie.NameString, mentionContent)
+		}
+	}
+
+	// format tags nicely
+	for _, tag := range tags {
+		tagContent := fmt.Sprintf(`<a href="%s" class="mention hashtag" rel="tag">#<span>%s</span></a>`, tag.URL, tag.Name)
+		content = strings.ReplaceAll(content, fmt.Sprintf("#%s", tag.Name), tagContent)
+	}
+
+	// replace newlines with breaks
+	content = strings.ReplaceAll(content, "\n", "<br />")
+
+	return postformat(content)
+}
diff --git a/internal/text/sanitize.go b/internal/text/sanitize.go
new file mode 100644
index 000000000..aac9d8aab
--- /dev/null
+++ b/internal/text/sanitize.go
@@ -0,0 +1,50 @@
+/*
+   GoToSocial
+   Copyright (C) 2021 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 (
+	"github.com/microcosm-cc/bluemonday"
+)
+
+// '[A]llows a broad selection of HTML elements and attributes that are safe for user generated content.
+// Note that this policy does not allow iframes, object, embed, styles, script, etc.
+// An example usage scenario would be blog post bodies where a variety of formatting is expected along with the potential for TABLEs and IMGs.'
+//
+// Source: https://github.com/microcosm-cc/bluemonday#usage
+var regular *bluemonday.Policy = bluemonday.UGCPolicy().
+	RequireNoReferrerOnLinks(true).
+	RequireNoFollowOnLinks(true).
+	RequireCrossOriginAnonymous(true)
+
+// '[C]an be thought of as equivalent to stripping all HTML elements and their attributes as it has nothing on its allowlist.
+// An example usage scenario would be blog post titles where HTML tags are not expected at all
+// and if they are then the elements and the content of the elements should be stripped. This is a very strict policy.'
+//
+// Source: https://github.com/microcosm-cc/bluemonday#usage
+var strict *bluemonday.Policy = bluemonday.StrictPolicy()
+
+// SanitizeHTML cleans up HTML in the given string, allowing through only safe HTML elements.
+func SanitizeHTML(in string) string {
+	return regular.Sanitize(in)
+}
+
+// RemoveHTML removes all HTML from the given string.
+func RemoveHTML(in string) string {
+	return strict.Sanitize(in)
+}